X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/9aa1e39f96ac28f6ce5d814d9a1eccf1464aba4a..1d9630e7857d6fbae6fddd261fbb80c9c9a8cfd6:/regcomp.sym diff --git a/regcomp.sym b/regcomp.sym index 4de5d79..b702c43 100644 --- a/regcomp.sym +++ b/regcomp.sym @@ -11,8 +11,10 @@ # Note that the order in this file is important. # # Format for first section: -# NAME \s+ TYPE, arg-description [num-args] [flags] [longjump-len] ; DESCRIPTION -# flag means is REGNODE_SIMPLE; flag means is REGNODE_VARIES +# NAME \s+ TYPE, arg-description [num-args] [flags] [longjump] ; DESCRIPTION +# flag means is REGNODE_SIMPLE; flag means is REGNODE_VARIES; <.> is +# a placeholder +# longjump is 1 if the (first) argument holds the next offset. # # # run perl regen.pl after editing this file @@ -24,40 +26,48 @@ 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. +#* 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 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 +BOUND BOUND, no ; Like BOUNDA for non-utf8, otherwise match "" between any Unicode \w\W or \W\w +BOUNDL BOUND, no ; Like BOUND/BOUNDU, but \w and \W are defined by current locale +BOUNDU BOUND, no ; Match "" at any boundary of a given type using /u rules. +BOUNDA BOUND, no ; Match "" at any boundary between \w\W or \W\w, where \w is [_a-zA-Z0-9] # 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. +NBOUND NBOUND, no ; Like NBOUNDA for non-utf8, otherwise match "" between any Unicode \w\w or \W\W +NBOUNDL NBOUND, no ; Like NBOUND/NBOUNDU, but \w and \W are defined by current locale +NBOUNDU NBOUND, no ; Match "" at any non-boundary of a given type using using /u rules. +NBOUNDA NBOUND, no ; Match "" betweeen any \w\w or \W\W, where \w is [_a-zA-Z0-9] #* [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 -ANYOF_WARN_SUPER ANYOF, sv 0 S ; Match character in (or not in) this class, warn (if enabled) upon matching a char above Unicode max; -ANYOF_SYNTHETIC ANYOF, sv 0 S ; Synthetic start class - +ANYOF ANYOF, sv charclass S ; Match character in (or not in) this class, single char match only +ANYOFD ANYOF, sv charclass S ; Like ANYOF, but /d is in effect +ANYOFL ANYOF, sv charclass S ; Like ANYOF, but /l is in effect +ANYOFPOSIXL ANYOF, sv charclass_posixl S ; Like ANYOFL, but matches [[:posix:]] classes +ANYOFH ANYOF, sv 1 S ; Like ANYOF, but only has "High" matches, none in the bitmap; +ANYOFHb ANYOF, sv 1 S ; Like ANYOFH, but all matches share the same first byte, the repurposed flags field contains it +ANYOFM ANYOFM byte 1 S ; Like ANYOF, but matches an invariant byte as determined by the mask and arg +NANYOFM ANYOFM byte 1 S ; complement of ANYOFM + +#* 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 @@ -84,23 +94,35 @@ CLUMP CLUMP, no 0 V ; Match any extended grapheme cluster sequence #* 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 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 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 +EXACTL EXACT, str ; Like EXACT, but /l is in effect (used so locale-related warnings can be checked for). +EXACTF EXACT, str ; Match this string using /id rules (w/len); (string not UTF-8, not guaranteed to be folded). +EXACTFL EXACT, str ; Match this string using /il rules (w/len); (string not guaranteed to be folded). +EXACTFU EXACT, str ; Match this string using /iu rules (w/len); (string folded iff in UTF-8; non-UTF8 folded length <= unfolded). +EXACTFAA EXACT, str ; Match this string using /iaa rules (w/len) (string folded iff in UTF-8; non-UTF8 folded length <= unfolded). + +# End of important relative ordering. + +EXACTFUP EXACT, str ; Match this string using /iu rules (w/len); (string not UTF-8, not guaranteed to be folded; and its Problematic). +# In order for a non-UTF-8 EXACTFAA to think the pattern is pre-folded when +# matching a UTF-8 target string, there would have to be something like an +# EXACTFAA_MICRO which would not be considered pre-folded for UTF-8 targets, +# since the fold of the MICRO SIGN would not be done, and would be +# representable in the UTF-8 target string. + +EXACTFLU8 EXACT, str ; Like EXACTFU, but use /il, UTF-8, folded, and everything in it is above 255. +EXACTFAA_NO_TRIE EXACT, str ; Match this string using /iaa rules (w/len) (string not UTF-8, not guaranteed to be folded, not currently trie-able). + + +EXACT_ONLY8 EXACT, str ; Like EXACT, but only UTF-8 encoded targets can match +EXACTFU_ONLY8 EXACT, str ; Like EXACTFU, but only UTF-8 encoded targets can match +# One could add EXACTFAA8 and something that has the same effect for /l, +# but these would be extremely uncommon + +EXACTFU_S_EDGE EXACT, str ; /di rules, but nothing in it precludes /ui, except begins and/or ends with [Ss]; (string not UTF-8; compile-time only). #*Do nothing types @@ -111,7 +133,7 @@ TAIL NOTHING, no ; Match empty string. Can jump here from outsi #*Loops #* STAR,PLUS '?', and complex '*' and '+', are implemented as -#* circular BRANCH structures using BACK. Simple cases +#* circular BRANCH structures. Simple cases #* (one character per match) are implemented with STAR #* and PLUS for speed and to minimize recursive plunges. #* @@ -130,39 +152,42 @@ WHILEM WHILEM, no 0 V ; Do curly processing and see if rest matches. #*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. +CLOSE CLOSE, num 1 ; Close corresponding OPEN of #n. +SROPEN SROPEN, none ; Same as OPEN, but for script run +SRCLOSE SRCLOSE, none ; Close preceding SROPEN 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. +REFF REF, num 1 V ; Match already matched string, using /di rules. +REFFL REF, num 1 V ; Match already matched string, using /li rules. # 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 +REFFU REF, num 1 V ; Match already matched string, usng /ui. +REFFA REF, num 1 V ; Match already matched string, using /aai rules. #*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. -SUSPEND BRANCHJ, off 1 V 1 ; "Independent" sub-RE. -IFTHEN BRANCHJ, off 1 V 1 ; Switch, should be preceded by switcher. -GROUPP GROUPP, num 1 ; Whether the group matched. +REFN REF, no-sv 1 V ; Match some already matched string +REFFN REF, no-sv 1 V ; Match already matched string, using /di rules. +REFFLN REF, no-sv 1 V ; Match already matched string, using /li rules. +REFFUN REF, num 1 V ; Match already matched string, using /ui rules. +REFFAN REF, num 1 V ; Match already matched string, using /aai rules. #*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 . 1 ; Succeeds if the following matches; non-zero flags "f", next_off "o" means lookbehind assertion starting "f..(f-o)" characters before current +UNLESSM BRANCHJ, off 1 . 1 ; Fails if the following matches; non-zero flags "f", next_off "o" means lookbehind assertion starting "f..(f-o)" characters before current +SUSPEND BRANCHJ, off 1 V 1 ; "Independent" sub-RE. +IFTHEN BRANCHJ, off 1 V 1 ; Switch, should be preceded by switcher. +GROUPP GROUPP, num 1 ; Whether the group matched. + + #*The heavy worker -EVAL EVAL, evl 1 ; Execute some Perl code. +EVAL EVAL, evl/flags 2L ; Execute some Perl code. #*Modifiers @@ -188,18 +213,16 @@ AHOCORASICKC TRIE,trie charclass ; Same as AHOCORASICK, but with embedded c #*Regex Subroutines GOSUB GOSUB, num/ofs 2L ; recurse to paren arg1 at (signed) ofs arg2 -GOSTART GOSTART, no ; recurse to start of pattern #*Special conditionals -NGROUPP NGROUPP, no-sv 1 ; Whether the group matched. +GROUPPN GROUPPN, no-sv 1 ; Whether the group matched. INSUBP INSUBP, num 1 ; Whether we are in a specific recurse. DEFINEP DEFINEP, none 1 ; Never execute directly. #*Backtracking Verbs ENDLIKE ENDLIKE, none ; Used only for the type field of verbs -OPFAIL ENDLIKE, none ; Same as (?!) -ACCEPT ENDLIKE, parno 1 ; Accepts the current matched string. - +OPFAIL ENDLIKE, no-sv 1 ; Same as (?!), but with verb arg +ACCEPT ENDLIKE, no-sv/num 2L ; Accepts the current matched string, with verbar #*Verbs With Arguments VERB VERB, no-sv 1 ; Used only for the type field of verbs @@ -243,13 +266,13 @@ PSEUDO PSEUDO, off ; Pseudo opcode for internal use. # # TRIE next:FAIL -EVAL AB:FAIL +EVAL B,postponed_AB:FAIL CURLYX end:FAIL WHILEM A_pre,A_min,A_max,B_min,B_max:FAIL BRANCH next:FAIL CURLYM A,B:FAIL IFMATCH A:FAIL -CURLY B_min_known,B_min,B_max:FAIL +CURLY B_min,B_max:FAIL COMMIT next:FAIL MARKPOINT next:FAIL SKIP next:FAIL