X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/1e355c70208127b17a934c726d2dd38bbd1b662f..b4941db24e5b5bf41a100f8944f5845de2bdf8ab:/regcomp.sym diff --git a/regcomp.sym b/regcomp.sym index 634e32d..6908712 100644 --- a/regcomp.sym +++ b/regcomp.sym @@ -2,14 +2,17 @@ # # File has two sections, divided by a line of dashes '-'. # -# Empty rows after #-comment are removed from input are ignored +# Lines beginning with # are ignored, except for those that start with #* +# which are included in pod/perldebguts.pod. # within a line may be part +# of a description. # # First section is for regops, second section is for regmatch-states # # 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 @@ -21,89 +24,99 @@ END END, no ; End of program. SUCCEED END, no ; Return from a subroutine, basically. -#* Anchors: +#* Line Start Anchors: +#Note flags field for SBOL indicates if it is a /^/ or a /\A/ +SBOL BOL, no ; Match "" at beginning of line: /^/, /\A/ +MBOL BOL, no ; Same, assuming multiline: /^/m -BOL BOL, no ; Match "" at beginning of line. -MBOL BOL, no ; Same, assuming multiline. -SBOL BOL, no ; Same, assuming singleline. -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 using native charset semantics for non-utf8 +#* Line End Anchors: +SEOL EOL, no ; Match "" at end of line: /$/ +MEOL EOL, no ; Same, assuming multiline: /$/m +EOS EOL, no ; Match "" at end of string: /\z/ + +#* Match Start Anchors: +GPOS GPOS, no ; Matches where last m//g left off. + +#* Word Boundary Opcodes: +# 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, POSIX and their complements are affected, as well as EXACTF. +BOUND BOUND, no ; Match "" at any word boundary using native charset rules for non-utf8 BOUNDL BOUND, no ; Match "" at any locale word boundary -BOUNDU BOUND, no ; Match "" at any word boundary using Unicode semantics -NBOUND NBOUND, no ; Match "" at any word non-boundary using native charset semantics for non-utf8 +BOUNDU BOUND, no ; Match "" at any word boundary using Unicode rules +BOUNDA BOUND, no ; Match "" at any word boundary using ASCII rules +# 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 rules 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 -GPOS GPOS, no ; Matches where last m//g left off. +NBOUNDU NBOUND, no ; Match "" at any word non-boundary using Unicode rules +NBOUNDA NBOUND, no ; Match "" at any word non-boundary using ASCII rules #* [Special] alternatives: - 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 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 -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 -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 -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 -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 -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 + +#* POSIX Character Classes: +# Order of the below is important. See ordering comment above. +POSIXD POSIXD, none 0 S ; Some [[:class:]] under /d; the FLAGS field gives which one +POSIXL POSIXD, none 0 S ; Some [[:class:]] under /l; the FLAGS field gives which one +POSIXU POSIXD, none 0 S ; Some [[:class:]] under /u; the FLAGS field gives which one +POSIXA POSIXD, none 0 S ; Some [[:class:]] under /a; the FLAGS field gives which one +NPOSIXD NPOSIXD, none 0 S ; complement of POSIXD, [[:^class:]] +NPOSIXL NPOSIXD, none 0 S ; complement of POSIXL, [[:^class:]] +NPOSIXU NPOSIXD, none 0 S ; complement of POSIXU, [[:^class:]] +NPOSIXA NPOSIXD, none 0 S ; complement of POSIXA, [[:^class:]] +# End of order is important + CLUMP CLUMP, no 0 V ; Match any extended grapheme cluster sequence #* Alternation -# BRANCH The set of branches constituting a single choice are hooked -# together with their "next" pointers, since precedence prevents -# anything being concatenated to any individual branch. The -# "next" pointer of the last BRANCH in a choice points to the -# thing following the whole choice. This is also where the -# final "next" pointer of each individual branch points; each -# branch starts with the operand node of a BRANCH node. -# +#* BRANCH The set of branches constituting a single choice are +#* hooked together with their "next" pointers, since +#* precedence prevents anything being concatenated to +#* any individual branch. The "next" pointer of the last +#* BRANCH in a choice points to the thing following the +#* whole choice. This is also where the final "next" +#* pointer of each individual branch points; each branch +#* starts with the operand node of a BRANCH node. +#* BRANCH BRANCH, node 0 V ; Match this alternative, or the next... #*Back pointer -# BACK Normal "next" pointers all implicitly point forward; BACK -# exists to make loop structures possible. -# not used +#* BACK Normal "next" pointers all implicitly point forward; +#* BACK exists to make loop structures possible. +#* not used BACK BACK, no 0 V ; Match "", "next" ptr points backward. #*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). +EXACTFA_NO_TRIE EXACT, str ; Match this string (which is not trie-able; not guaranteed to be folded) using /iaa rules (w/len). #*Do nothing types NOTHING NOTHING, no ; Match empty string. -# A variant of above which delimits a group, thus stops optimizations +#*A variant of above which delimits a group, thus stops optimizations TAIL NOTHING, no ; Match empty string. Can jump here from outside. #*Loops -# STAR,PLUS '?', and complex '*' and '+', are implemented as circular -# BRANCH structures using BACK. Simple cases (one character -# per match) are implemented with STAR and PLUS for speed -# and to minimize recursive plunges. -# +#* STAR,PLUS '?', and complex '*' and '+', are implemented as +#* circular BRANCH structures using BACK. Simple cases +#* (one character per match) are implemented with STAR +#* and PLUS for speed and to minimize recursive plunges. +#* STAR STAR, node 0 V ; Match this (simple) thing 0 or more times. PLUS PLUS, node 0 V ; Match this (simple) thing 1 or more times. @@ -112,39 +125,43 @@ CURLYN CURLY, no 2 V ; Capture next-after-this simple thing CURLYM CURLY, no 2 V ; Capture this medium-complex thing {n,m} times. CURLYX CURLY, sv 2 V ; Match this complex thing {n,m} times. -# This terminator creates a loop structure for CURLYX +#*This terminator creates a loop structure for CURLYX WHILEM WHILEM, no 0 V ; Do curly processing and see if rest matches. #*Buffer related -# OPEN,CLOSE,GROUPP ...are numbered at compile time. +#*OPEN,CLOSE,GROUPP ...are numbered at compile time. OPEN OPEN, num 1 ; Mark this point in input as start of #n. 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 +REFF REF, num 1 V ; Match already matched string, folded using native charset rules 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 +REFFU REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8 +REFFA REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8, no mixing ASCII, non-ASCII -#*Named references. Code in regcomp.c assumes that these all are after the numbered references +#*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 +NREFF REF, no-sv 1 V ; Match already matched string, folded using native charset rules 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 +NREFFU REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8 +NREFFA REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8, no mixing ASCII, non-ASCII +#*Support for long RE +LONGJMP LONGJMP, off 1 . 1 ; Jump far away. +BRANCHJ BRANCHJ, off 1 V 1 ; BRANCH with long offset. + +#*Special Case Regops IFMATCH BRANCHJ, off 1 . 2 ; Succeeds if the following matches. UNLESSM BRANCHJ, off 1 . 2 ; Fails if the following matches. SUSPEND BRANCHJ, off 1 V 1 ; "Independent" sub-RE. -IFTHEN BRANCHJ, off 1 V 1 ; Switch, should be preceded by switcher . +IFTHEN BRANCHJ, off 1 V 1 ; Switch, should be preceded by switcher. GROUPP GROUPP, num 1 ; Whether the group matched. -#*Support for long RE - -LONGJMP LONGJMP, off 1 . 1 ; Jump far away. -BRANCHJ BRANCHJ, off 1 V 1 ; BRANCH with long offset. #*The heavy worker @@ -155,16 +172,17 @@ EVAL EVAL, evl 1 ; Execute some Perl code. MINMOD MINMOD, no ; Next operator is not greedy. LOGICAL LOGICAL, no ; Next opcode should set the flag only. -# This is not used yet +#*This is not used yet RENUM BRANCHJ, off 1 . 1 ; Group with independently numbered parens. #*Trie Related -# Behave the same as A|LIST|OF|WORDS would. The '..C' variants have -# inline charclass data (ascii only), the 'C' store it in the structure. +#* Behave the same as A|LIST|OF|WORDS would. The '..C' variants +#* have 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. @@ -199,13 +217,6 @@ KEEPS KEEPS, no ; $& begins here. #*New charclass like patterns LNBREAK LNBREAK, none ; generic newline pattern -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 @@ -213,20 +224,20 @@ FOLDCHAR FOLDCHAR, codepoint 1 ; codepoint with tricky case folding propert #*SPECIAL REGOPS -# This is not really a node, but an optimized away piece of a "long" node. -# To simplify debugging output, we mark it as if it were a node +#* This is not really a node, but an optimized away piece of a "long" +#* node. To simplify debugging output, we mark it as if it were a node OPTIMIZED NOTHING, off ; Placeholder for dump. -# Special opcode with the property that no opcode in a compiled program -# will ever be of this type. Thus it can be used as a flag value that -# no other opcode has been seen. END is used similarly, in that an END -# node cant be optimized. So END implies "unoptimizable" and PSEUDO mean -# "not seen anything to optimize yet". +#* Special opcode with the property that no opcode in a compiled program +#* will ever be of this type. Thus it can be used as a flag value that +#* no other opcode has been seen. END is used similarly, in that an END +#* node cant be optimized. So END implies "unoptimizable" and PSEUDO +#* mean "not seen anything to optimize yet". PSEUDO PSEUDO, off ; Pseudo opcode for internal use. ------------------------------------------------------------------------------- # Format for second section: -# REGOP \t typelist [ \t typelist] [# Comment] +# REGOP \t typelist [ \t typelist] # typelist= namelist # = namelist:FAIL # = name:count