X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/0e019ad6e74196f697d451c846c4af8778bd2a51..b5679dc0b0f66c67e5dfb402dadb01eedc5529ae:/regcomp.sym diff --git a/regcomp.sym b/regcomp.sym index 3c9f97c..3b4db9c 100644 --- a/regcomp.sym +++ b/regcomp.sym @@ -9,10 +9,12 @@ # Note that the order in this file is important. # # Format for first section: -# NAME \s+ TYPE, arg-description [flags] [num-args] [longjump-len] ; DESCRIPTION +# NAME \s+ TYPE, arg-description [num-args] [flags] [longjump-len] ; DESCRIPTION +# flag means is REGNODE_SIMPLE; flag means is REGNODE_VARIES # # # run perl regen.pl after editing this file +# Also update perlredebguts.pod @@ -30,10 +32,21 @@ 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 +# The regops that have varieties that vary depending on the character set regex +# modifiers have to ordered thusly: /d, /l, /u, /a, /aa. This is because code +# in regcomp.c uses the enum value of the modifier as an offset from the /d +# version. The complements must come after the non-complements. +# BOUND, ALNUM, SPACE, DIGIT, and their complements are affected, as well as +# EXACTF. +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 code in 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: @@ -42,19 +55,46 @@ 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, 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 + +# Order (within each group) of the below is important. See ordering comment +# above. The PLACEHOLDERn ones are wasting a value. Right now, we have plenty +# to spare, but these would be obvious candidates if ever we ran out of node +# types in a U8. +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 +PLACEHOLDER1 NOTHING, no ; placeholder for missing DIGITU +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 +PLACEHOLDER2 NOTHING, no ; placeholder for missing NDIGITU +NDIGITA NDIGIT, no 0 S ; Match [^0-9] + +POSIXD POSIXD, none 0 S ; currently unused except as a placeholder +POSIXL POSIXD, none 0 S ; currently unused except as a placeholder +POSIXU POSIXD, none 0 S ; currently unused except as a placeholder +POSIXA POSIXD, none 0 S ; Some [[:class:]] under /a; the FLAGS field gives which one +NPOSIXD POSIXD, none 0 S ; currently unused except as a placeholder +NPOSIXL POSIXD, none 0 S ; currently unused except as a placeholder +NPOSIXU POSIXD, none 0 S ; currently unused except as a placeholder +NPOSIXA POSIXD, none 0 S ; complement of POSIXA, [[:^class:]] +# End of order is important (within groups) + CLUMP CLUMP, no 0 V ; Match any extended grapheme cluster sequence #* Alternation @@ -76,12 +116,15 @@ 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 @@ -116,16 +159,18 @@ 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. @@ -156,7 +201,7 @@ 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. @@ -191,14 +236,14 @@ KEEPS KEEPS, no ; $& begins here. #*New charclass like patterns LNBREAK LNBREAK, none ; generic newline pattern + +# regcomp.c expects the node number of the complement to be one greater than +# the non-complement VERTWS VERTWS, none 0 S ; vertical whitespace (Perl 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 ################################################################################