X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/fa01018c102d8360898153b9f4b062716ad06702..08b2a930f16c631ad58d4ec6d184e81c0a4ec7b6:/regcomp.sym?ds=sidebyside diff --git a/regcomp.sym b/regcomp.sym index f0ee701..e8400b9 100644 --- a/regcomp.sym +++ b/regcomp.sym @@ -9,7 +9,8 @@ # 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 @@ -31,11 +32,17 @@ 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. +# 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 a line regexec.c to be greater than all BOUND ones +# 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 @@ -49,6 +56,11 @@ 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 + +# 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 ALNUMU ALNUM, no 0 S ; Match any alphanumeric char using Unicode semantics @@ -67,10 +79,23 @@ NSPACEU NSPACE, no 0 S ; Match any non-whitespace char using Unicode 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 +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 @@ -92,15 +117,15 @@ 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 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). -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_NO_TRIE EXACT, str ; Match this folded UTF-8 string using /iu rules, but don't generate a trie for it 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 @@ -212,12 +237,14 @@ 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) - # NEW STUFF SOMEWHERE ABOVE THIS LINE ################################################################################