X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/63ac0dadb1aafcf0c171d3c1422c1923b611b2fc..8c1182fda8158a86281b1ea6464176d1c68f2f18:/regcomp.sym diff --git a/regcomp.sym b/regcomp.sym index 2fb1785..13d3787 100644 --- a/regcomp.sym +++ b/regcomp.sym @@ -13,6 +13,7 @@ # # # run perl regen.pl after editing this file +# Also update perlredebguts.pod @@ -33,10 +34,12 @@ SEOL EOL, no ; Same, assuming singleline. 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: @@ -49,19 +52,25 @@ ANYOFV ANYOF, sv 0 V ; Match character in (or not in) this class, c 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 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 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 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 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 +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 @@ -83,12 +92,15 @@ BRANCH BRANCH, node 0 V ; Match this alternative, or the next... # not used BACK BACK, no 0 V ; Match "", "next" ptr points backward. -#*Literals +#*Literals - NOTE the relative ordering of these types is important do not change it EXACT EXACT, str ; Match this string (preceded by length). -EXACTF EXACT, str ; Match this string, folded, native charset semantics for non-utf8 (prec. by length). -EXACTFL EXACT, str ; Match this string, folded in locale (w/len). -EXACTFU EXACT, str ; Match this string, folded, Unicode semantics for non-utf8 (prec. by length). +EXACTF EXACT, str ; Match this non-UTF-8 string (not guaranteed to be folded) using /id rules (w/len). +EXACTFL EXACT, str ; Match this string (not guaranteed to be folded) using /il rules (w/len). +EXACTFU EXACT, str ; Match this string (folded iff in UTF-8, length in folding doesn't change if not in UTF-8) using /iu rules (w/len). +EXACTFA EXACT, str ; Match this string (not guaranteed to be folded) using /iaa rules (w/len). +EXACTFU_SS EXACT, str ; Match this string (folded iff in UTF-8, length in folding may change even if not in UTF-8) using /iu rules (w/len). +EXACTFU_TRICKYFOLD EXACT, str ; Match this folded UTF-8 string using /iu rules #*Do nothing types @@ -123,16 +135,18 @@ CLOSE CLOSE, num 1 ; Analogous to OPEN. REF REF, num 1 V ; Match some already matched string REFF REF, num 1 V ; Match already matched string, folded using native charset semantics for non-utf8 REFFL REF, num 1 V ; Match already matched string, folded in loc. -# REFFU and NREFFU could have been implemented using the FLAGS field of the +# N?REFF[AU] could have been implemented using the FLAGS field of the # regnode, but by having a separate node type, we can use the existing switch # statement to avoid some tests REFFU REF, num 1 V ; Match already matched string, folded using unicode semantics for non-utf8 +REFFA REF, num 1 V ; Match already matched string, folded using unicode semantics for non-utf8, no mixing ASCII, non-ASCII #*Named references. Code in regcomp.c assumes that these all are after the numbered references NREF REF, no-sv 1 V ; Match some already matched string NREFF REF, no-sv 1 V ; Match already matched string, folded using native charset semantics for non-utf8 NREFFL REF, no-sv 1 V ; Match already matched string, folded in loc. NREFFU REF, num 1 V ; Match already matched string, folded using unicode semantics for non-utf8 +NREFFA REF, num 1 V ; Match already matched string, folded using unicode semantics for non-utf8, no mixing ASCII, non-ASCII IFMATCH BRANCHJ, off 1 . 2 ; Succeeds if the following matches. UNLESSM BRANCHJ, off 1 . 2 ; Fails if the following matches. @@ -163,7 +177,7 @@ RENUM BRANCHJ, off 1 . 1 ; Group with independently numbered parens. # inline charclass data (ascii only), the 'C' store it in the structure. # NOTE: the relative order of the TRIE-like regops is significant -TRIE TRIE, trie 1 ; Match many EXACT(F[LU]?)? at once. flags==type +TRIE TRIE, trie 1 ; Match many EXACT(F[ALU]?)? at once. flags==type TRIEC TRIE,trie charclass ; Same as TRIE, but with embedded charclass data # For start classes, contains an added fail table. @@ -203,8 +217,6 @@ NVERTWS NVERTWS, none 0 S ; not vertical whitespace (Perl 6) HORIZWS HORIZWS, none 0 S ; horizontal whitespace (Perl 6) NHORIZWS NHORIZWS, none 0 S ; not horizontal whitespace (Perl 6) -FOLDCHAR FOLDCHAR, codepoint 1 ; codepoint with tricky case folding properties. - # NEW STUFF SOMEWHERE ABOVE THIS LINE