X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/28b5d7bf98b62fd30fb98fcdb5c701b1b2acdd8f..bb3eff5d3d7e45d422801f5cc0f329daf0c4766d:/regnodes.h diff --git a/regnodes.h b/regnodes.h index 35a4cc1..211980d 100644 --- a/regnodes.h +++ b/regnodes.h @@ -2,134 +2,146 @@ !!!!!!! DO NOT EDIT THIS FILE !!!!!!! This file is built by regen/regcomp.pl from regcomp.sym. Any changes made here will be lost! -*/ + */ /* Regops and State definitions */ -#define REGNODE_MAX 93 -#define REGMATCH_STATE_MAX 133 +#define REGNODE_MAX 103 +#define REGMATCH_STATE_MAX 143 #define END 0 /* 0000 End of program. */ #define SUCCEED 1 /* 0x01 Return from a subroutine, basically. */ -#define BOL 2 /* 0x02 Match "" at beginning of line. */ -#define MBOL 3 /* 0x03 Same, assuming multiline. */ -#define SBOL 4 /* 0x04 Same, assuming singleline. */ -#define EOS 5 /* 0x05 Match "" at end of string. */ -#define EOL 6 /* 0x06 Match "" at end of line. */ -#define MEOL 7 /* 0x07 Same, assuming multiline. */ -#define SEOL 8 /* 0x08 Same, assuming singleline. */ -#define BOUND 9 /* 0x09 Match "" at any word boundary */ -#define BOUNDL 10 /* 0x0a Match "" at any word boundary */ -#define NBOUND 11 /* 0x0b Match "" at any word non-boundary */ -#define NBOUNDL 12 /* 0x0c Match "" at any word non-boundary */ -#define GPOS 13 /* 0x0d Matches where last m//g left off. */ -#define REG_ANY 14 /* 0x0e Match any one character (except newline). */ -#define SANY 15 /* 0x0f Match any one character. */ -#define CANY 16 /* 0x10 Match any one byte. */ -#define ANYOF 17 /* 0x11 Match character in (or not in) this class, folding is native charset for non-utf8. */ -#define ALNUM 18 /* 0x12 Match any alphanumeric character */ -#define ALNUML 19 /* 0x13 Match any alphanumeric char in locale */ -#define NALNUM 20 /* 0x14 Match any non-alphanumeric character */ -#define NALNUML 21 /* 0x15 Match any non-alphanumeric char in locale */ -#define SPACE 22 /* 0x16 Match any whitespace character */ -#define SPACEL 23 /* 0x17 Match any whitespace char in locale */ -#define NSPACE 24 /* 0x18 Match any non-whitespace character */ -#define NSPACEL 25 /* 0x19 Match any non-whitespace char in locale */ -#define DIGIT 26 /* 0x1a Match any numeric character */ -#define DIGITL 27 /* 0x1b Match any numeric character in locale */ -#define NDIGIT 28 /* 0x1c Match any non-numeric character */ -#define NDIGITL 29 /* 0x1d Match any non-numeric character in locale */ -#define CLUMP 30 /* 0x1e Match any extended grapheme cluster sequence */ -#define BRANCH 31 /* 0x1f Match this alternative, or the next... */ -#define BACK 32 /* 0x20 Match "", "next" ptr points backward. */ -#define EXACT 33 /* 0x21 Match this string (preceded by length). */ -#define EXACTF 34 /* 0x22 Match this string, folded, native charset semantics for non-utf8 (prec. by length). */ -#define EXACTFL 35 /* 0x23 Match this string, folded in locale (w/len). */ -#define EXACTFU 36 /* 0x24 Match this string, folded, Unicode semantics for non-utf8 (prec. by length). */ -#define NOTHING 37 /* 0x25 Match empty string. */ -#define TAIL 38 /* 0x26 Match empty string. Can jump here from outside. */ -#define STAR 39 /* 0x27 Match this (simple) thing 0 or more times. */ -#define PLUS 40 /* 0x28 Match this (simple) thing 1 or more times. */ -#define CURLY 41 /* 0x29 Match this simple thing {n,m} times. */ -#define CURLYN 42 /* 0x2a Capture next-after-this simple thing */ -#define CURLYM 43 /* 0x2b Capture this medium-complex thing {n,m} times. */ -#define CURLYX 44 /* 0x2c Match this complex thing {n,m} times. */ -#define WHILEM 45 /* 0x2d Do curly processing and see if rest matches. */ -#define OPEN 46 /* 0x2e Mark this point in input as start of */ -#define CLOSE 47 /* 0x2f Analogous to OPEN. */ -#define REF 48 /* 0x30 Match some already matched string */ -#define REFF 49 /* 0x31 Match already matched string, folded using native charset semantics for non-utf8 */ -#define REFFL 50 /* 0x32 Match already matched string, folded in loc. */ -#define REFFU 51 /* 0x33 Match already matched string, folded using unicode semantics for non-utf8 */ -#define NREF 52 /* 0x34 Match some already matched string */ -#define NREFF 53 /* 0x35 Match already matched string, folded using native charset semantics for non-utf8 */ -#define NREFFL 54 /* 0x36 Match already matched string, folded in loc. */ -#define NREFFU 55 /* 0x37 Match already matched string, folded using unicode semantics for non-utf8 */ -#define IFMATCH 56 /* 0x38 Succeeds if the following matches. */ -#define UNLESSM 57 /* 0x39 Fails if the following matches. */ -#define SUSPEND 58 /* 0x3a "Independent" sub-RE. */ -#define IFTHEN 59 /* 0x3b Switch, should be preceeded by switcher . */ -#define GROUPP 60 /* 0x3c Whether the group matched. */ -#define LONGJMP 61 /* 0x3d Jump far away. */ -#define BRANCHJ 62 /* 0x3e BRANCH with long offset. */ -#define EVAL 63 /* 0x3f Execute some Perl code. */ -#define MINMOD 64 /* 0x40 Next operator is not greedy. */ -#define LOGICAL 65 /* 0x41 Next opcode should set the flag only. */ -#define RENUM 66 /* 0x42 Group with independently numbered parens. */ -#define TRIE 67 /* 0x43 Match many EXACT(F[LU]?)? at once. flags==type */ -#define TRIEC 68 /* 0x44 Same as TRIE, but with embedded charclass data */ -#define AHOCORASICK 69 /* 0x45 Aho Corasick stclass. flags==type */ -#define AHOCORASICKC 70 /* 0x46 Same as AHOCORASICK, but with embedded charclass data */ -#define GOSUB 71 /* 0x47 recurse to paren arg1 at (signed) ofs arg2 */ -#define GOSTART 72 /* 0x48 recurse to start of pattern */ -#define NGROUPP 73 /* 0x49 Whether the group matched. */ -#define INSUBP 74 /* 0x4a Whether we are in a specific recurse. */ -#define DEFINEP 75 /* 0x4b Never execute directly. */ -#define ENDLIKE 76 /* 0x4c Used only for the type field of verbs */ -#define OPFAIL 77 /* 0x4d Same as (?!) */ -#define ACCEPT 78 /* 0x4e Accepts the current matched string. */ -#define VERB 79 /* 0x4f Used only for the type field of verbs */ -#define PRUNE 80 /* 0x50 Pattern fails at this startpoint if no-backtracking through this */ -#define MARKPOINT 81 /* 0x51 Push the current location for rollback by cut. */ -#define SKIP 82 /* 0x52 On failure skip forward (to the mark) before retrying */ -#define COMMIT 83 /* 0x53 Pattern fails outright if backtracking through this */ -#define CUTGROUP 84 /* 0x54 On failure go to the next alternation in the group */ -#define KEEPS 85 /* 0x55 $& begins here. */ -#define LNBREAK 86 /* 0x56 generic newline pattern */ -#define VERTWS 87 /* 0x57 vertical whitespace (Perl 6) */ -#define NVERTWS 88 /* 0x58 not vertical whitespace (Perl 6) */ -#define HORIZWS 89 /* 0x59 horizontal whitespace (Perl 6) */ -#define NHORIZWS 90 /* 0x5a not horizontal whitespace (Perl 6) */ -#define FOLDCHAR 91 /* 0x5b codepoint with tricky case folding properties. */ -#define OPTIMIZED 92 /* 0x5c Placeholder for dump. */ -#define PSEUDO 93 /* 0x5d Pseudo opcode for internal use. */ +#define SBOL 2 /* 0x02 Match "" at beginning of line: /^/, /\A/ */ +#define BOL 2 /* 0x02 type alias */ +#define MBOL 3 /* 0x03 Same, assuming multiline: /^/m */ +#define SEOL 4 /* 0x04 Match "" at end of line: /$/ */ +#define EOL 4 /* 0x04 type alias */ +#define MEOL 5 /* 0x05 Same, assuming multiline: /$/m */ +#define EOS 6 /* 0x06 Match "" at end of string: /\z/ */ +#define GPOS 7 /* 0x07 Matches where last m//g left off. */ +#define BOUND 8 /* 0x08 Like BOUNDA for non-utf8, otherwise match "" between any Unicode \w\W or \W\w */ +#define BOUNDL 9 /* 0x09 Like BOUND/BOUNDU, but \w and \W are defined by current locale */ +#define BOUNDU 10 /* 0x0a Match "" at any boundary of a given type using /u rules. */ +#define BOUNDA 11 /* 0x0b Match "" at any boundary between \w\W or \W\w, where \w is [_a-zA-Z0-9] */ +#define NBOUND 12 /* 0x0c Like NBOUNDA for non-utf8, otherwise match "" between any Unicode \w\w or \W\W */ +#define NBOUNDL 13 /* 0x0d Like NBOUND/NBOUNDU, but \w and \W are defined by current locale */ +#define NBOUNDU 14 /* 0x0e Match "" at any non-boundary of a given type using using /u rules. */ +#define NBOUNDA 15 /* 0x0f Match "" betweeen any \w\w or \W\W, where \w is [_a-zA-Z0-9] */ +#define REG_ANY 16 /* 0x10 Match any one character (except newline). */ +#define SANY 17 /* 0x11 Match any one character. */ +#define ANYOF 18 /* 0x12 Match character in (or not in) this class, single char match only */ +#define ANYOFD 19 /* 0x13 Like ANYOF, but /d is in effect */ +#define ANYOFL 20 /* 0x14 Like ANYOF, but /l is in effect */ +#define ANYOFPOSIXL 21 /* 0x15 Like ANYOFL, but matches [[:posix:]] classes */ +#define ANYOFH 22 /* 0x16 Like ANYOF, but only has "High" matches, none in the bitmap; the flags field contains the lowest matchable UTF-8 start byte */ +#define ANYOFHb 23 /* 0x17 Like ANYOFH, but all matches share the same UTF-8 start byte, given in the flags field */ +#define ANYOFHr 24 /* 0x18 Like ANYOFH, but the flags field contains packed bounds for all matchable UTF-8 start bytes. */ +#define ANYOFM 25 /* 0x19 Like ANYOF, but matches an invariant byte as determined by the mask and arg */ +#define NANYOFM 26 /* 0x1a complement of ANYOFM */ +#define POSIXD 27 /* 0x1b Some [[:class:]] under /d; the FLAGS field gives which one */ +#define POSIXL 28 /* 0x1c Some [[:class:]] under /l; the FLAGS field gives which one */ +#define POSIXU 29 /* 0x1d Some [[:class:]] under /u; the FLAGS field gives which one */ +#define POSIXA 30 /* 0x1e Some [[:class:]] under /a; the FLAGS field gives which one */ +#define NPOSIXD 31 /* 0x1f complement of POSIXD, [[:^class:]] */ +#define NPOSIXL 32 /* 0x20 complement of POSIXL, [[:^class:]] */ +#define NPOSIXU 33 /* 0x21 complement of POSIXU, [[:^class:]] */ +#define NPOSIXA 34 /* 0x22 complement of POSIXA, [[:^class:]] */ +#define CLUMP 35 /* 0x23 Match any extended grapheme cluster sequence */ +#define BRANCH 36 /* 0x24 Match this alternative, or the next... */ +#define EXACT 37 /* 0x25 Match this string (preceded by length). */ +#define EXACTL 38 /* 0x26 Like EXACT, but /l is in effect (used so locale-related warnings can be checked for). */ +#define EXACTF 39 /* 0x27 Match this string using /id rules (w/len); (string not UTF-8, not guaranteed to be folded). */ +#define EXACTFL 40 /* 0x28 Match this string using /il rules (w/len); (string not guaranteed to be folded). */ +#define EXACTFU 41 /* 0x29 Match this string using /iu rules (w/len); (string folded iff in UTF-8; non-UTF8 folded length <= unfolded). */ +#define EXACTFAA 42 /* 0x2a Match this string using /iaa rules (w/len) (string folded iff in UTF-8; non-UTF8 folded length <= unfolded). */ +#define EXACTFUP 43 /* 0x2b Match this string using /iu rules (w/len); (string not UTF-8, not guaranteed to be folded; and its Problematic). */ +#define EXACTFLU8 44 /* 0x2c Like EXACTFU, but use /il, UTF-8, folded, and everything in it is above 255. */ +#define EXACTFAA_NO_TRIE 45 /* 0x2d Match this string using /iaa rules (w/len) (string not UTF-8, not guaranteed to be folded, not currently trie-able). */ +#define EXACT_ONLY8 46 /* 0x2e Like EXACT, but only UTF-8 encoded targets can match */ +#define EXACTFU_ONLY8 47 /* 0x2f Like EXACTFU, but only UTF-8 encoded targets can match */ +#define EXACTFU_S_EDGE 48 /* 0x30 /di rules, but nothing in it precludes /ui, except begins and/or ends with [Ss]; (string not UTF-8; compile-time only). */ +#define NOTHING 49 /* 0x31 Match empty string. */ +#define TAIL 50 /* 0x32 Match empty string. Can jump here from outside. */ +#define STAR 51 /* 0x33 Match this (simple) thing 0 or more times. */ +#define PLUS 52 /* 0x34 Match this (simple) thing 1 or more times. */ +#define CURLY 53 /* 0x35 Match this simple thing {n,m} times. */ +#define CURLYN 54 /* 0x36 Capture next-after-this simple thing */ +#define CURLYM 55 /* 0x37 Capture this medium-complex thing {n,m} times. */ +#define CURLYX 56 /* 0x38 Match this complex thing {n,m} times. */ +#define WHILEM 57 /* 0x39 Do curly processing and see if rest matches. */ +#define OPEN 58 /* 0x3a Mark this point in input as start of #n. */ +#define CLOSE 59 /* 0x3b Close corresponding OPEN of #n. */ +#define SROPEN 60 /* 0x3c Same as OPEN, but for script run */ +#define SRCLOSE 61 /* 0x3d Close preceding SROPEN */ +#define REF 62 /* 0x3e Match some already matched string */ +#define REFF 63 /* 0x3f Match already matched string, using /di rules. */ +#define REFFL 64 /* 0x40 Match already matched string, using /li rules. */ +#define REFFU 65 /* 0x41 Match already matched string, usng /ui. */ +#define REFFA 66 /* 0x42 Match already matched string, using /aai rules. */ +#define REFN 67 /* 0x43 Match some already matched string */ +#define REFFN 68 /* 0x44 Match already matched string, using /di rules. */ +#define REFFLN 69 /* 0x45 Match already matched string, using /li rules. */ +#define REFFUN 70 /* 0x46 Match already matched string, using /ui rules. */ +#define REFFAN 71 /* 0x47 Match already matched string, using /aai rules. */ +#define LONGJMP 72 /* 0x48 Jump far away. */ +#define BRANCHJ 73 /* 0x49 BRANCH with long offset. */ +#define IFMATCH 74 /* 0x4a Succeeds if the following matches; non-zero flags "f", next_off "o" means lookbehind assertion starting "f..(f-o)" characters before current */ +#define UNLESSM 75 /* 0x4b Fails if the following matches; non-zero flags "f", next_off "o" means lookbehind assertion starting "f..(f-o)" characters before current */ +#define SUSPEND 76 /* 0x4c "Independent" sub-RE. */ +#define IFTHEN 77 /* 0x4d Switch, should be preceded by switcher. */ +#define GROUPP 78 /* 0x4e Whether the group matched. */ +#define EVAL 79 /* 0x4f Execute some Perl code. */ +#define MINMOD 80 /* 0x50 Next operator is not greedy. */ +#define LOGICAL 81 /* 0x51 Next opcode should set the flag only. */ +#define RENUM 82 /* 0x52 Group with independently numbered parens. */ +#define TRIE 83 /* 0x53 Match many EXACT(F[ALU]?)? at once. flags==type */ +#define TRIEC 84 /* 0x54 Same as TRIE, but with embedded charclass data */ +#define AHOCORASICK 85 /* 0x55 Aho Corasick stclass. flags==type */ +#define AHOCORASICKC 86 /* 0x56 Same as AHOCORASICK, but with embedded charclass data */ +#define GOSUB 87 /* 0x57 recurse to paren arg1 at (signed) ofs arg2 */ +#define GROUPPN 88 /* 0x58 Whether the group matched. */ +#define INSUBP 89 /* 0x59 Whether we are in a specific recurse. */ +#define DEFINEP 90 /* 0x5a Never execute directly. */ +#define ENDLIKE 91 /* 0x5b Used only for the type field of verbs */ +#define OPFAIL 92 /* 0x5c Same as (?!), but with verb arg */ +#define ACCEPT 93 /* 0x5d Accepts the current matched string, with verbar */ +#define VERB 94 /* 0x5e Used only for the type field of verbs */ +#define PRUNE 95 /* 0x5f Pattern fails at this startpoint if no-backtracking through this */ +#define MARKPOINT 96 /* 0x60 Push the current location for rollback by cut. */ +#define SKIP 97 /* 0x61 On failure skip forward (to the mark) before retrying */ +#define COMMIT 98 /* 0x62 Pattern fails outright if backtracking through this */ +#define CUTGROUP 99 /* 0x63 On failure go to the next alternation in the group */ +#define KEEPS 100 /* 0x64 $& begins here. */ +#define LNBREAK 101 /* 0x65 generic newline pattern */ +#define OPTIMIZED 102 /* 0x66 Placeholder for dump. */ +#define PSEUDO 103 /* 0x67 Pseudo opcode for internal use. */ /* ------------ States ------------- */ #define TRIE_next (REGNODE_MAX + 1) /* state for TRIE */ #define TRIE_next_fail (REGNODE_MAX + 2) /* state for TRIE */ -#define EVAL_AB (REGNODE_MAX + 3) /* state for EVAL */ -#define EVAL_AB_fail (REGNODE_MAX + 4) /* state for EVAL */ -#define CURLYX_end (REGNODE_MAX + 5) /* state for CURLYX */ -#define CURLYX_end_fail (REGNODE_MAX + 6) /* state for CURLYX */ -#define WHILEM_A_pre (REGNODE_MAX + 7) /* state for WHILEM */ -#define WHILEM_A_pre_fail (REGNODE_MAX + 8) /* state for WHILEM */ -#define WHILEM_A_min (REGNODE_MAX + 9) /* state for WHILEM */ -#define WHILEM_A_min_fail (REGNODE_MAX + 10) /* state for WHILEM */ -#define WHILEM_A_max (REGNODE_MAX + 11) /* state for WHILEM */ -#define WHILEM_A_max_fail (REGNODE_MAX + 12) /* state for WHILEM */ -#define WHILEM_B_min (REGNODE_MAX + 13) /* state for WHILEM */ -#define WHILEM_B_min_fail (REGNODE_MAX + 14) /* state for WHILEM */ -#define WHILEM_B_max (REGNODE_MAX + 15) /* state for WHILEM */ -#define WHILEM_B_max_fail (REGNODE_MAX + 16) /* state for WHILEM */ -#define BRANCH_next (REGNODE_MAX + 17) /* state for BRANCH */ -#define BRANCH_next_fail (REGNODE_MAX + 18) /* state for BRANCH */ -#define CURLYM_A (REGNODE_MAX + 19) /* state for CURLYM */ -#define CURLYM_A_fail (REGNODE_MAX + 20) /* state for CURLYM */ -#define CURLYM_B (REGNODE_MAX + 21) /* state for CURLYM */ -#define CURLYM_B_fail (REGNODE_MAX + 22) /* state for CURLYM */ -#define IFMATCH_A (REGNODE_MAX + 23) /* state for IFMATCH */ -#define IFMATCH_A_fail (REGNODE_MAX + 24) /* state for IFMATCH */ -#define CURLY_B_min_known (REGNODE_MAX + 25) /* state for CURLY */ -#define CURLY_B_min_known_fail (REGNODE_MAX + 26) /* state for CURLY */ +#define EVAL_B (REGNODE_MAX + 3) /* state for EVAL */ +#define EVAL_B_fail (REGNODE_MAX + 4) /* state for EVAL */ +#define EVAL_postponed_AB (REGNODE_MAX + 5) /* state for EVAL */ +#define EVAL_postponed_AB_fail (REGNODE_MAX + 6) /* state for EVAL */ +#define CURLYX_end (REGNODE_MAX + 7) /* state for CURLYX */ +#define CURLYX_end_fail (REGNODE_MAX + 8) /* state for CURLYX */ +#define WHILEM_A_pre (REGNODE_MAX + 9) /* state for WHILEM */ +#define WHILEM_A_pre_fail (REGNODE_MAX + 10) /* state for WHILEM */ +#define WHILEM_A_min (REGNODE_MAX + 11) /* state for WHILEM */ +#define WHILEM_A_min_fail (REGNODE_MAX + 12) /* state for WHILEM */ +#define WHILEM_A_max (REGNODE_MAX + 13) /* state for WHILEM */ +#define WHILEM_A_max_fail (REGNODE_MAX + 14) /* state for WHILEM */ +#define WHILEM_B_min (REGNODE_MAX + 15) /* state for WHILEM */ +#define WHILEM_B_min_fail (REGNODE_MAX + 16) /* state for WHILEM */ +#define WHILEM_B_max (REGNODE_MAX + 17) /* state for WHILEM */ +#define WHILEM_B_max_fail (REGNODE_MAX + 18) /* state for WHILEM */ +#define BRANCH_next (REGNODE_MAX + 19) /* state for BRANCH */ +#define BRANCH_next_fail (REGNODE_MAX + 20) /* state for BRANCH */ +#define CURLYM_A (REGNODE_MAX + 21) /* state for CURLYM */ +#define CURLYM_A_fail (REGNODE_MAX + 22) /* state for CURLYM */ +#define CURLYM_B (REGNODE_MAX + 23) /* state for CURLYM */ +#define CURLYM_B_fail (REGNODE_MAX + 24) /* state for CURLYM */ +#define IFMATCH_A (REGNODE_MAX + 25) /* state for IFMATCH */ +#define IFMATCH_A_fail (REGNODE_MAX + 26) /* state for IFMATCH */ #define CURLY_B_min (REGNODE_MAX + 27) /* state for CURLY */ #define CURLY_B_min_fail (REGNODE_MAX + 28) /* state for CURLY */ #define CURLY_B_max (REGNODE_MAX + 29) /* state for CURLY */ @@ -153,41 +165,53 @@ EXTCONST U8 PL_regkind[]; EXTCONST U8 PL_regkind[] = { END, /* END */ END, /* SUCCEED */ - BOL, /* BOL */ - BOL, /* MBOL */ BOL, /* SBOL */ - EOL, /* EOS */ - EOL, /* EOL */ - EOL, /* MEOL */ + BOL, /* MBOL */ EOL, /* SEOL */ + EOL, /* MEOL */ + EOL, /* EOS */ + GPOS, /* GPOS */ BOUND, /* BOUND */ BOUND, /* BOUNDL */ + BOUND, /* BOUNDU */ + BOUND, /* BOUNDA */ NBOUND, /* NBOUND */ NBOUND, /* NBOUNDL */ - GPOS, /* GPOS */ + NBOUND, /* NBOUNDU */ + NBOUND, /* NBOUNDA */ REG_ANY, /* REG_ANY */ REG_ANY, /* SANY */ - REG_ANY, /* CANY */ ANYOF, /* ANYOF */ - ALNUM, /* ALNUM */ - ALNUM, /* ALNUML */ - NALNUM, /* NALNUM */ - NALNUM, /* NALNUML */ - SPACE, /* SPACE */ - SPACE, /* SPACEL */ - NSPACE, /* NSPACE */ - NSPACE, /* NSPACEL */ - DIGIT, /* DIGIT */ - DIGIT, /* DIGITL */ - NDIGIT, /* NDIGIT */ - NDIGIT, /* NDIGITL */ + ANYOF, /* ANYOFD */ + ANYOF, /* ANYOFL */ + ANYOF, /* ANYOFPOSIXL */ + ANYOF, /* ANYOFH */ + ANYOF, /* ANYOFHb */ + ANYOF, /* ANYOFHr */ + ANYOFM, /* ANYOFM */ + ANYOFM, /* NANYOFM */ + POSIXD, /* POSIXD */ + POSIXD, /* POSIXL */ + POSIXD, /* POSIXU */ + POSIXD, /* POSIXA */ + NPOSIXD, /* NPOSIXD */ + NPOSIXD, /* NPOSIXL */ + NPOSIXD, /* NPOSIXU */ + NPOSIXD, /* NPOSIXA */ CLUMP, /* CLUMP */ BRANCH, /* BRANCH */ - BACK, /* BACK */ EXACT, /* EXACT */ + EXACT, /* EXACTL */ EXACT, /* EXACTF */ EXACT, /* EXACTFL */ EXACT, /* EXACTFU */ + EXACT, /* EXACTFAA */ + EXACT, /* EXACTFUP */ + EXACT, /* EXACTFLU8 */ + EXACT, /* EXACTFAA_NO_TRIE */ + EXACT, /* EXACT_ONLY8 */ + EXACT, /* EXACTFU_ONLY8 */ + EXACT, /* EXACTFU_S_EDGE */ NOTHING, /* NOTHING */ NOTHING, /* TAIL */ STAR, /* STAR */ @@ -199,21 +223,25 @@ EXTCONST U8 PL_regkind[] = { WHILEM, /* WHILEM */ OPEN, /* OPEN */ CLOSE, /* CLOSE */ + SROPEN, /* SROPEN */ + SRCLOSE, /* SRCLOSE */ REF, /* REF */ REF, /* REFF */ REF, /* REFFL */ REF, /* REFFU */ - REF, /* NREF */ - REF, /* NREFF */ - REF, /* NREFFL */ - REF, /* NREFFU */ + REF, /* REFFA */ + REF, /* REFN */ + REF, /* REFFN */ + REF, /* REFFLN */ + REF, /* REFFUN */ + REF, /* REFFAN */ + LONGJMP, /* LONGJMP */ + BRANCHJ, /* BRANCHJ */ BRANCHJ, /* IFMATCH */ BRANCHJ, /* UNLESSM */ BRANCHJ, /* SUSPEND */ BRANCHJ, /* IFTHEN */ GROUPP, /* GROUPP */ - LONGJMP, /* LONGJMP */ - BRANCHJ, /* BRANCHJ */ EVAL, /* EVAL */ MINMOD, /* MINMOD */ LOGICAL, /* LOGICAL */ @@ -223,8 +251,7 @@ EXTCONST U8 PL_regkind[] = { TRIE, /* AHOCORASICK */ TRIE, /* AHOCORASICKC */ GOSUB, /* GOSUB */ - GOSTART, /* GOSTART */ - NGROUPP, /* NGROUPP */ + GROUPPN, /* GROUPPN */ INSUBP, /* INSUBP */ DEFINEP, /* DEFINEP */ ENDLIKE, /* ENDLIKE */ @@ -238,18 +265,15 @@ EXTCONST U8 PL_regkind[] = { VERB, /* CUTGROUP */ KEEPS, /* KEEPS */ LNBREAK, /* LNBREAK */ - VERTWS, /* VERTWS */ - NVERTWS, /* NVERTWS */ - HORIZWS, /* HORIZWS */ - NHORIZWS, /* NHORIZWS */ - FOLDCHAR, /* FOLDCHAR */ NOTHING, /* OPTIMIZED */ PSEUDO, /* PSEUDO */ /* ------------ States ------------- */ TRIE, /* TRIE_next */ TRIE, /* TRIE_next_fail */ - EVAL, /* EVAL_AB */ - EVAL, /* EVAL_AB_fail */ + EVAL, /* EVAL_B */ + EVAL, /* EVAL_B_fail */ + EVAL, /* EVAL_postponed_AB */ + EVAL, /* EVAL_postponed_AB_fail */ CURLYX, /* CURLYX_end */ CURLYX, /* CURLYX_end_fail */ WHILEM, /* WHILEM_A_pre */ @@ -270,8 +294,6 @@ EXTCONST U8 PL_regkind[] = { CURLYM, /* CURLYM_B_fail */ IFMATCH, /* IFMATCH_A */ IFMATCH, /* IFMATCH_A_fail */ - CURLY, /* CURLY_B_min_known */ - CURLY, /* CURLY_B_min_known_fail */ CURLY, /* CURLY_B_min */ CURLY, /* CURLY_B_min_fail */ CURLY, /* CURLY_B_max */ @@ -289,47 +311,60 @@ EXTCONST U8 PL_regkind[] = { }; #endif +#ifdef REG_COMP_C + /* regarglen[] - How large is the argument part of the node (in regnodes) */ -#ifdef REG_COMP_C static const U8 regarglen[] = { 0, /* END */ 0, /* SUCCEED */ - 0, /* BOL */ - 0, /* MBOL */ 0, /* SBOL */ - 0, /* EOS */ - 0, /* EOL */ - 0, /* MEOL */ + 0, /* MBOL */ 0, /* SEOL */ + 0, /* MEOL */ + 0, /* EOS */ + 0, /* GPOS */ 0, /* BOUND */ 0, /* BOUNDL */ + 0, /* BOUNDU */ + 0, /* BOUNDA */ 0, /* NBOUND */ 0, /* NBOUNDL */ - 0, /* GPOS */ + 0, /* NBOUNDU */ + 0, /* NBOUNDA */ 0, /* REG_ANY */ 0, /* SANY */ - 0, /* CANY */ - 0, /* ANYOF */ - 0, /* ALNUM */ - 0, /* ALNUML */ - 0, /* NALNUM */ - 0, /* NALNUML */ - 0, /* SPACE */ - 0, /* SPACEL */ - 0, /* NSPACE */ - 0, /* NSPACEL */ - 0, /* DIGIT */ - 0, /* DIGITL */ - 0, /* NDIGIT */ - 0, /* NDIGITL */ + EXTRA_SIZE(struct regnode_charclass), /* ANYOF */ + EXTRA_SIZE(struct regnode_charclass), /* ANYOFD */ + EXTRA_SIZE(struct regnode_charclass), /* ANYOFL */ + EXTRA_SIZE(struct regnode_charclass_posixl), /* ANYOFPOSIXL */ + EXTRA_SIZE(struct regnode_1), /* ANYOFH */ + EXTRA_SIZE(struct regnode_1), /* ANYOFHb */ + EXTRA_SIZE(struct regnode_1), /* ANYOFHr */ + EXTRA_SIZE(struct regnode_1), /* ANYOFM */ + EXTRA_SIZE(struct regnode_1), /* NANYOFM */ + 0, /* POSIXD */ + 0, /* POSIXL */ + 0, /* POSIXU */ + 0, /* POSIXA */ + 0, /* NPOSIXD */ + 0, /* NPOSIXL */ + 0, /* NPOSIXU */ + 0, /* NPOSIXA */ 0, /* CLUMP */ 0, /* BRANCH */ - 0, /* BACK */ 0, /* EXACT */ + 0, /* EXACTL */ 0, /* EXACTF */ 0, /* EXACTFL */ 0, /* EXACTFU */ + 0, /* EXACTFAA */ + 0, /* EXACTFUP */ + 0, /* EXACTFLU8 */ + 0, /* EXACTFAA_NO_TRIE */ + 0, /* EXACT_ONLY8 */ + 0, /* EXACTFU_ONLY8 */ + 0, /* EXACTFU_S_EDGE */ 0, /* NOTHING */ 0, /* TAIL */ 0, /* STAR */ @@ -341,22 +376,26 @@ static const U8 regarglen[] = { 0, /* WHILEM */ EXTRA_SIZE(struct regnode_1), /* OPEN */ EXTRA_SIZE(struct regnode_1), /* CLOSE */ + 0, /* SROPEN */ + 0, /* SRCLOSE */ EXTRA_SIZE(struct regnode_1), /* REF */ EXTRA_SIZE(struct regnode_1), /* REFF */ EXTRA_SIZE(struct regnode_1), /* REFFL */ EXTRA_SIZE(struct regnode_1), /* REFFU */ - EXTRA_SIZE(struct regnode_1), /* NREF */ - EXTRA_SIZE(struct regnode_1), /* NREFF */ - EXTRA_SIZE(struct regnode_1), /* NREFFL */ - EXTRA_SIZE(struct regnode_1), /* NREFFU */ + EXTRA_SIZE(struct regnode_1), /* REFFA */ + EXTRA_SIZE(struct regnode_1), /* REFN */ + EXTRA_SIZE(struct regnode_1), /* REFFN */ + EXTRA_SIZE(struct regnode_1), /* REFFLN */ + EXTRA_SIZE(struct regnode_1), /* REFFUN */ + EXTRA_SIZE(struct regnode_1), /* REFFAN */ + EXTRA_SIZE(struct regnode_1), /* LONGJMP */ + EXTRA_SIZE(struct regnode_1), /* BRANCHJ */ EXTRA_SIZE(struct regnode_1), /* IFMATCH */ EXTRA_SIZE(struct regnode_1), /* UNLESSM */ EXTRA_SIZE(struct regnode_1), /* SUSPEND */ EXTRA_SIZE(struct regnode_1), /* IFTHEN */ EXTRA_SIZE(struct regnode_1), /* GROUPP */ - EXTRA_SIZE(struct regnode_1), /* LONGJMP */ - EXTRA_SIZE(struct regnode_1), /* BRANCHJ */ - EXTRA_SIZE(struct regnode_1), /* EVAL */ + EXTRA_SIZE(struct regnode_2L), /* EVAL */ 0, /* MINMOD */ 0, /* LOGICAL */ EXTRA_SIZE(struct regnode_1), /* RENUM */ @@ -365,13 +404,12 @@ static const U8 regarglen[] = { EXTRA_SIZE(struct regnode_1), /* AHOCORASICK */ EXTRA_SIZE(struct regnode_charclass), /* AHOCORASICKC */ EXTRA_SIZE(struct regnode_2L), /* GOSUB */ - 0, /* GOSTART */ - EXTRA_SIZE(struct regnode_1), /* NGROUPP */ + EXTRA_SIZE(struct regnode_1), /* GROUPPN */ EXTRA_SIZE(struct regnode_1), /* INSUBP */ EXTRA_SIZE(struct regnode_1), /* DEFINEP */ 0, /* ENDLIKE */ - 0, /* OPFAIL */ - EXTRA_SIZE(struct regnode_1), /* ACCEPT */ + EXTRA_SIZE(struct regnode_1), /* OPFAIL */ + EXTRA_SIZE(struct regnode_2L), /* ACCEPT */ EXTRA_SIZE(struct regnode_1), /* VERB */ EXTRA_SIZE(struct regnode_1), /* PRUNE */ EXTRA_SIZE(struct regnode_1), /* MARKPOINT */ @@ -380,11 +418,6 @@ static const U8 regarglen[] = { EXTRA_SIZE(struct regnode_1), /* CUTGROUP */ 0, /* KEEPS */ 0, /* LNBREAK */ - 0, /* VERTWS */ - 0, /* NVERTWS */ - 0, /* HORIZWS */ - 0, /* NHORIZWS */ - EXTRA_SIZE(struct regnode_1), /* FOLDCHAR */ 0, /* OPTIMIZED */ 0, /* PSEUDO */ }; @@ -394,41 +427,53 @@ static const U8 regarglen[] = { static const char reg_off_by_arg[] = { 0, /* END */ 0, /* SUCCEED */ - 0, /* BOL */ - 0, /* MBOL */ 0, /* SBOL */ - 0, /* EOS */ - 0, /* EOL */ - 0, /* MEOL */ + 0, /* MBOL */ 0, /* SEOL */ + 0, /* MEOL */ + 0, /* EOS */ + 0, /* GPOS */ 0, /* BOUND */ 0, /* BOUNDL */ + 0, /* BOUNDU */ + 0, /* BOUNDA */ 0, /* NBOUND */ 0, /* NBOUNDL */ - 0, /* GPOS */ + 0, /* NBOUNDU */ + 0, /* NBOUNDA */ 0, /* REG_ANY */ 0, /* SANY */ - 0, /* CANY */ 0, /* ANYOF */ - 0, /* ALNUM */ - 0, /* ALNUML */ - 0, /* NALNUM */ - 0, /* NALNUML */ - 0, /* SPACE */ - 0, /* SPACEL */ - 0, /* NSPACE */ - 0, /* NSPACEL */ - 0, /* DIGIT */ - 0, /* DIGITL */ - 0, /* NDIGIT */ - 0, /* NDIGITL */ + 0, /* ANYOFD */ + 0, /* ANYOFL */ + 0, /* ANYOFPOSIXL */ + 0, /* ANYOFH */ + 0, /* ANYOFHb */ + 0, /* ANYOFHr */ + 0, /* ANYOFM */ + 0, /* NANYOFM */ + 0, /* POSIXD */ + 0, /* POSIXL */ + 0, /* POSIXU */ + 0, /* POSIXA */ + 0, /* NPOSIXD */ + 0, /* NPOSIXL */ + 0, /* NPOSIXU */ + 0, /* NPOSIXA */ 0, /* CLUMP */ 0, /* BRANCH */ - 0, /* BACK */ 0, /* EXACT */ + 0, /* EXACTL */ 0, /* EXACTF */ 0, /* EXACTFL */ 0, /* EXACTFU */ + 0, /* EXACTFAA */ + 0, /* EXACTFUP */ + 0, /* EXACTFLU8 */ + 0, /* EXACTFAA_NO_TRIE */ + 0, /* EXACT_ONLY8 */ + 0, /* EXACTFU_ONLY8 */ + 0, /* EXACTFU_S_EDGE */ 0, /* NOTHING */ 0, /* TAIL */ 0, /* STAR */ @@ -440,21 +485,25 @@ static const char reg_off_by_arg[] = { 0, /* WHILEM */ 0, /* OPEN */ 0, /* CLOSE */ + 0, /* SROPEN */ + 0, /* SRCLOSE */ 0, /* REF */ 0, /* REFF */ 0, /* REFFL */ 0, /* REFFU */ - 0, /* NREF */ - 0, /* NREFF */ - 0, /* NREFFL */ - 0, /* NREFFU */ - 2, /* IFMATCH */ - 2, /* UNLESSM */ + 0, /* REFFA */ + 0, /* REFN */ + 0, /* REFFN */ + 0, /* REFFLN */ + 0, /* REFFUN */ + 0, /* REFFAN */ + 1, /* LONGJMP */ + 1, /* BRANCHJ */ + 1, /* IFMATCH */ + 1, /* UNLESSM */ 1, /* SUSPEND */ 1, /* IFTHEN */ 0, /* GROUPP */ - 1, /* LONGJMP */ - 1, /* BRANCHJ */ 0, /* EVAL */ 0, /* MINMOD */ 0, /* LOGICAL */ @@ -464,8 +513,7 @@ static const char reg_off_by_arg[] = { 0, /* AHOCORASICK */ 0, /* AHOCORASICKC */ 0, /* GOSUB */ - 0, /* GOSTART */ - 0, /* NGROUPP */ + 0, /* GROUPPN */ 0, /* INSUBP */ 0, /* DEFINEP */ 0, /* ENDLIKE */ @@ -479,17 +527,13 @@ static const char reg_off_by_arg[] = { 0, /* CUTGROUP */ 0, /* KEEPS */ 0, /* LNBREAK */ - 0, /* VERTWS */ - 0, /* NVERTWS */ - 0, /* HORIZWS */ - 0, /* NHORIZWS */ - 0, /* FOLDCHAR */ 0, /* OPTIMIZED */ 0, /* PSEUDO */ }; #endif /* REG_COMP_C */ + /* reg_name[] - Opcode/state names in string form, for debugging */ #ifndef DOINIT @@ -498,125 +542,135 @@ EXTCONST char * PL_reg_name[]; EXTCONST char * const PL_reg_name[] = { "END", /* 0000 */ "SUCCEED", /* 0x01 */ - "BOL", /* 0x02 */ + "SBOL", /* 0x02 */ "MBOL", /* 0x03 */ - "SBOL", /* 0x04 */ - "EOS", /* 0x05 */ - "EOL", /* 0x06 */ - "MEOL", /* 0x07 */ - "SEOL", /* 0x08 */ - "BOUND", /* 0x09 */ - "BOUNDL", /* 0x0a */ - "NBOUND", /* 0x0b */ - "NBOUNDL", /* 0x0c */ - "GPOS", /* 0x0d */ - "REG_ANY", /* 0x0e */ - "SANY", /* 0x0f */ - "CANY", /* 0x10 */ - "ANYOF", /* 0x11 */ - "ALNUM", /* 0x12 */ - "ALNUML", /* 0x13 */ - "NALNUM", /* 0x14 */ - "NALNUML", /* 0x15 */ - "SPACE", /* 0x16 */ - "SPACEL", /* 0x17 */ - "NSPACE", /* 0x18 */ - "NSPACEL", /* 0x19 */ - "DIGIT", /* 0x1a */ - "DIGITL", /* 0x1b */ - "NDIGIT", /* 0x1c */ - "NDIGITL", /* 0x1d */ - "CLUMP", /* 0x1e */ - "BRANCH", /* 0x1f */ - "BACK", /* 0x20 */ - "EXACT", /* 0x21 */ - "EXACTF", /* 0x22 */ - "EXACTFL", /* 0x23 */ - "EXACTFU", /* 0x24 */ - "NOTHING", /* 0x25 */ - "TAIL", /* 0x26 */ - "STAR", /* 0x27 */ - "PLUS", /* 0x28 */ - "CURLY", /* 0x29 */ - "CURLYN", /* 0x2a */ - "CURLYM", /* 0x2b */ - "CURLYX", /* 0x2c */ - "WHILEM", /* 0x2d */ - "OPEN", /* 0x2e */ - "CLOSE", /* 0x2f */ - "REF", /* 0x30 */ - "REFF", /* 0x31 */ - "REFFL", /* 0x32 */ - "REFFU", /* 0x33 */ - "NREF", /* 0x34 */ - "NREFF", /* 0x35 */ - "NREFFL", /* 0x36 */ - "NREFFU", /* 0x37 */ - "IFMATCH", /* 0x38 */ - "UNLESSM", /* 0x39 */ - "SUSPEND", /* 0x3a */ - "IFTHEN", /* 0x3b */ - "GROUPP", /* 0x3c */ - "LONGJMP", /* 0x3d */ - "BRANCHJ", /* 0x3e */ - "EVAL", /* 0x3f */ - "MINMOD", /* 0x40 */ - "LOGICAL", /* 0x41 */ - "RENUM", /* 0x42 */ - "TRIE", /* 0x43 */ - "TRIEC", /* 0x44 */ - "AHOCORASICK", /* 0x45 */ - "AHOCORASICKC", /* 0x46 */ - "GOSUB", /* 0x47 */ - "GOSTART", /* 0x48 */ - "NGROUPP", /* 0x49 */ - "INSUBP", /* 0x4a */ - "DEFINEP", /* 0x4b */ - "ENDLIKE", /* 0x4c */ - "OPFAIL", /* 0x4d */ - "ACCEPT", /* 0x4e */ - "VERB", /* 0x4f */ - "PRUNE", /* 0x50 */ - "MARKPOINT", /* 0x51 */ - "SKIP", /* 0x52 */ - "COMMIT", /* 0x53 */ - "CUTGROUP", /* 0x54 */ - "KEEPS", /* 0x55 */ - "LNBREAK", /* 0x56 */ - "VERTWS", /* 0x57 */ - "NVERTWS", /* 0x58 */ - "HORIZWS", /* 0x59 */ - "NHORIZWS", /* 0x5a */ - "FOLDCHAR", /* 0x5b */ - "OPTIMIZED", /* 0x5c */ - "PSEUDO", /* 0x5d */ + "SEOL", /* 0x04 */ + "MEOL", /* 0x05 */ + "EOS", /* 0x06 */ + "GPOS", /* 0x07 */ + "BOUND", /* 0x08 */ + "BOUNDL", /* 0x09 */ + "BOUNDU", /* 0x0a */ + "BOUNDA", /* 0x0b */ + "NBOUND", /* 0x0c */ + "NBOUNDL", /* 0x0d */ + "NBOUNDU", /* 0x0e */ + "NBOUNDA", /* 0x0f */ + "REG_ANY", /* 0x10 */ + "SANY", /* 0x11 */ + "ANYOF", /* 0x12 */ + "ANYOFD", /* 0x13 */ + "ANYOFL", /* 0x14 */ + "ANYOFPOSIXL", /* 0x15 */ + "ANYOFH", /* 0x16 */ + "ANYOFHb", /* 0x17 */ + "ANYOFHr", /* 0x18 */ + "ANYOFM", /* 0x19 */ + "NANYOFM", /* 0x1a */ + "POSIXD", /* 0x1b */ + "POSIXL", /* 0x1c */ + "POSIXU", /* 0x1d */ + "POSIXA", /* 0x1e */ + "NPOSIXD", /* 0x1f */ + "NPOSIXL", /* 0x20 */ + "NPOSIXU", /* 0x21 */ + "NPOSIXA", /* 0x22 */ + "CLUMP", /* 0x23 */ + "BRANCH", /* 0x24 */ + "EXACT", /* 0x25 */ + "EXACTL", /* 0x26 */ + "EXACTF", /* 0x27 */ + "EXACTFL", /* 0x28 */ + "EXACTFU", /* 0x29 */ + "EXACTFAA", /* 0x2a */ + "EXACTFUP", /* 0x2b */ + "EXACTFLU8", /* 0x2c */ + "EXACTFAA_NO_TRIE", /* 0x2d */ + "EXACT_ONLY8", /* 0x2e */ + "EXACTFU_ONLY8", /* 0x2f */ + "EXACTFU_S_EDGE", /* 0x30 */ + "NOTHING", /* 0x31 */ + "TAIL", /* 0x32 */ + "STAR", /* 0x33 */ + "PLUS", /* 0x34 */ + "CURLY", /* 0x35 */ + "CURLYN", /* 0x36 */ + "CURLYM", /* 0x37 */ + "CURLYX", /* 0x38 */ + "WHILEM", /* 0x39 */ + "OPEN", /* 0x3a */ + "CLOSE", /* 0x3b */ + "SROPEN", /* 0x3c */ + "SRCLOSE", /* 0x3d */ + "REF", /* 0x3e */ + "REFF", /* 0x3f */ + "REFFL", /* 0x40 */ + "REFFU", /* 0x41 */ + "REFFA", /* 0x42 */ + "REFN", /* 0x43 */ + "REFFN", /* 0x44 */ + "REFFLN", /* 0x45 */ + "REFFUN", /* 0x46 */ + "REFFAN", /* 0x47 */ + "LONGJMP", /* 0x48 */ + "BRANCHJ", /* 0x49 */ + "IFMATCH", /* 0x4a */ + "UNLESSM", /* 0x4b */ + "SUSPEND", /* 0x4c */ + "IFTHEN", /* 0x4d */ + "GROUPP", /* 0x4e */ + "EVAL", /* 0x4f */ + "MINMOD", /* 0x50 */ + "LOGICAL", /* 0x51 */ + "RENUM", /* 0x52 */ + "TRIE", /* 0x53 */ + "TRIEC", /* 0x54 */ + "AHOCORASICK", /* 0x55 */ + "AHOCORASICKC", /* 0x56 */ + "GOSUB", /* 0x57 */ + "GROUPPN", /* 0x58 */ + "INSUBP", /* 0x59 */ + "DEFINEP", /* 0x5a */ + "ENDLIKE", /* 0x5b */ + "OPFAIL", /* 0x5c */ + "ACCEPT", /* 0x5d */ + "VERB", /* 0x5e */ + "PRUNE", /* 0x5f */ + "MARKPOINT", /* 0x60 */ + "SKIP", /* 0x61 */ + "COMMIT", /* 0x62 */ + "CUTGROUP", /* 0x63 */ + "KEEPS", /* 0x64 */ + "LNBREAK", /* 0x65 */ + "OPTIMIZED", /* 0x66 */ + "PSEUDO", /* 0x67 */ /* ------------ States ------------- */ "TRIE_next", /* REGNODE_MAX +0x01 */ "TRIE_next_fail", /* REGNODE_MAX +0x02 */ - "EVAL_AB", /* REGNODE_MAX +0x03 */ - "EVAL_AB_fail", /* REGNODE_MAX +0x04 */ - "CURLYX_end", /* REGNODE_MAX +0x05 */ - "CURLYX_end_fail", /* REGNODE_MAX +0x06 */ - "WHILEM_A_pre", /* REGNODE_MAX +0x07 */ - "WHILEM_A_pre_fail", /* REGNODE_MAX +0x08 */ - "WHILEM_A_min", /* REGNODE_MAX +0x09 */ - "WHILEM_A_min_fail", /* REGNODE_MAX +0x0a */ - "WHILEM_A_max", /* REGNODE_MAX +0x0b */ - "WHILEM_A_max_fail", /* REGNODE_MAX +0x0c */ - "WHILEM_B_min", /* REGNODE_MAX +0x0d */ - "WHILEM_B_min_fail", /* REGNODE_MAX +0x0e */ - "WHILEM_B_max", /* REGNODE_MAX +0x0f */ - "WHILEM_B_max_fail", /* REGNODE_MAX +0x10 */ - "BRANCH_next", /* REGNODE_MAX +0x11 */ - "BRANCH_next_fail", /* REGNODE_MAX +0x12 */ - "CURLYM_A", /* REGNODE_MAX +0x13 */ - "CURLYM_A_fail", /* REGNODE_MAX +0x14 */ - "CURLYM_B", /* REGNODE_MAX +0x15 */ - "CURLYM_B_fail", /* REGNODE_MAX +0x16 */ - "IFMATCH_A", /* REGNODE_MAX +0x17 */ - "IFMATCH_A_fail", /* REGNODE_MAX +0x18 */ - "CURLY_B_min_known", /* REGNODE_MAX +0x19 */ - "CURLY_B_min_known_fail", /* REGNODE_MAX +0x1a */ + "EVAL_B", /* REGNODE_MAX +0x03 */ + "EVAL_B_fail", /* REGNODE_MAX +0x04 */ + "EVAL_postponed_AB", /* REGNODE_MAX +0x05 */ + "EVAL_postponed_AB_fail", /* REGNODE_MAX +0x06 */ + "CURLYX_end", /* REGNODE_MAX +0x07 */ + "CURLYX_end_fail", /* REGNODE_MAX +0x08 */ + "WHILEM_A_pre", /* REGNODE_MAX +0x09 */ + "WHILEM_A_pre_fail", /* REGNODE_MAX +0x0a */ + "WHILEM_A_min", /* REGNODE_MAX +0x0b */ + "WHILEM_A_min_fail", /* REGNODE_MAX +0x0c */ + "WHILEM_A_max", /* REGNODE_MAX +0x0d */ + "WHILEM_A_max_fail", /* REGNODE_MAX +0x0e */ + "WHILEM_B_min", /* REGNODE_MAX +0x0f */ + "WHILEM_B_min_fail", /* REGNODE_MAX +0x10 */ + "WHILEM_B_max", /* REGNODE_MAX +0x11 */ + "WHILEM_B_max_fail", /* REGNODE_MAX +0x12 */ + "BRANCH_next", /* REGNODE_MAX +0x13 */ + "BRANCH_next_fail", /* REGNODE_MAX +0x14 */ + "CURLYM_A", /* REGNODE_MAX +0x15 */ + "CURLYM_A_fail", /* REGNODE_MAX +0x16 */ + "CURLYM_B", /* REGNODE_MAX +0x17 */ + "CURLYM_B_fail", /* REGNODE_MAX +0x18 */ + "IFMATCH_A", /* REGNODE_MAX +0x19 */ + "IFMATCH_A_fail", /* REGNODE_MAX +0x1a */ "CURLY_B_min", /* REGNODE_MAX +0x1b */ "CURLY_B_min_fail", /* REGNODE_MAX +0x1c */ "CURLY_B_max", /* REGNODE_MAX +0x1d */ @@ -640,32 +694,32 @@ EXTCONST char * const PL_reg_name[] = { EXTCONST char * PL_reg_extflags_name[]; #else EXTCONST char * const PL_reg_extflags_name[] = { - /* Bits in extflags defined: 11111111111111111111111001111111 */ + /* Bits in extflags defined: 11111111111111110000111111111111 */ "MULTILINE", /* 0x00000001 */ "SINGLELINE", /* 0x00000002 */ "FOLD", /* 0x00000004 */ "EXTENDED", /* 0x00000008 */ - "KEEPCOPY", /* 0x00000010 */ - "LOCALE", /* 0x00000020 */ - "UNICODE", /* 0x00000040 */ - "UNUSED_BIT_7", /* 0x00000080 */ - "UNUSED_BIT_8", /* 0x00000100 */ - "ANCH_BOL", /* 0x00000200 */ - "ANCH_MBOL", /* 0x00000400 */ - "ANCH_SBOL", /* 0x00000800 */ - "ANCH_GPOS", /* 0x00001000 */ - "GPOS_SEEN", /* 0x00002000 */ - "GPOS_FLOAT", /* 0x00004000 */ - "LOOKBEHIND_SEEN", /* 0x00008000 */ - "EVAL_SEEN", /* 0x00010000 */ - "CANY_SEEN", /* 0x00020000 */ - "NOSCAN", /* 0x00040000 */ + "EXTENDED_MORE", /* 0x00000010 */ + "NOCAPTURE", /* 0x00000020 */ + "KEEPCOPY", /* 0x00000040 */ + "CHARSET0", /* 0x00000080 : "CHARSET" - 0x00000380 */ + "CHARSET1", /* 0x00000100 : "CHARSET" - 0x00000380 */ + "CHARSET2", /* 0x00000200 : "CHARSET" - 0x00000380 */ + "STRICT", /* 0x00000400 */ + "SPLIT", /* 0x00000800 */ + "UNUSED_BIT_12", /* 0x00001000 */ + "UNUSED_BIT_13", /* 0x00002000 */ + "UNUSED_BIT_14", /* 0x00004000 */ + "UNUSED_BIT_15", /* 0x00008000 */ + "NO_INPLACE_SUBST", /* 0x00010000 */ + "EVAL_SEEN", /* 0x00020000 */ + "UNBOUNDED_QUANTIFIER_SEEN",/* 0x00040000 */ "CHECK_ALL", /* 0x00080000 */ "MATCH_UTF8", /* 0x00100000 */ "USE_INTUIT_NOML", /* 0x00200000 */ "USE_INTUIT_ML", /* 0x00400000 */ "INTUIT_TAIL", /* 0x00800000 */ - "SPLIT", /* 0x01000000 */ + "IS_ANCHORED", /* 0x01000000 */ "COPY_DONE", /* 0x02000000 */ "TAINTED_SEEN", /* 0x04000000 */ "TAINTED", /* 0x08000000 */ @@ -676,6 +730,36 @@ EXTCONST char * const PL_reg_extflags_name[] = { }; #endif /* DOINIT */ +#ifdef DEBUGGING +# define REG_EXTFLAGS_NAME_SIZE 32 +#endif + +/* PL_reg_intflags_name[] - Opcode/state names in string form, for debugging */ + +#ifndef DOINIT +EXTCONST char * PL_reg_intflags_name[]; +#else +EXTCONST char * const PL_reg_intflags_name[] = { + "SKIP", /* 0x00000001 - PREGf_SKIP */ + "IMPLICIT", /* 0x00000002 - PREGf_IMPLICIT - Converted .* to ^.* */ + "NAUGHTY", /* 0x00000004 - PREGf_NAUGHTY - how exponential is this pattern? */ + "VERBARG_SEEN", /* 0x00000008 - PREGf_VERBARG_SEEN */ + "CUTGROUP_SEEN", /* 0x00000010 - PREGf_CUTGROUP_SEEN */ + "USE_RE_EVAL", /* 0x00000020 - PREGf_USE_RE_EVAL - compiled with "use re 'eval'" */ + "NOSCAN", /* 0x00000040 - PREGf_NOSCAN */ + "GPOS_SEEN", /* 0x00000100 - PREGf_GPOS_SEEN */ + "GPOS_FLOAT", /* 0x00000200 - PREGf_GPOS_FLOAT */ + "ANCH_MBOL", /* 0x00000400 - PREGf_ANCH_MBOL */ + "ANCH_SBOL", /* 0x00000800 - PREGf_ANCH_SBOL */ + "ANCH_GPOS", /* 0x00001000 - PREGf_ANCH_GPOS */ + "RECURSE_SEEN", /* 0x00002000 - PREGf_RECURSE_SEEN */ +}; +#endif /* DOINIT */ + +#ifdef DEBUGGING +# define REG_INTFLAGS_NAME_SIZE 13 +#endif + /* The following have no fixed length. U8 so we can do strchr() on it. */ #define REGNODE_VARIES(node) (PL_varies_bitmask[(node) >> 3] & (1 << ((node) & 7))) @@ -683,9 +767,9 @@ EXTCONST char * const PL_reg_extflags_name[] = { EXTCONST U8 PL_varies[] __attribute__deprecated__; #else EXTCONST U8 PL_varies[] __attribute__deprecated__ = { - CLUMP, BRANCH, BACK, STAR, PLUS, CURLY, CURLYN, CURLYM, CURLYX, WHILEM, - REF, REFF, REFFL, REFFU, NREF, NREFF, NREFFL, NREFFU, SUSPEND, IFTHEN, - BRANCHJ, + CLUMP, BRANCH, STAR, PLUS, CURLY, CURLYN, CURLYM, CURLYX, WHILEM, REF, + REFF, REFFL, REFFU, REFFA, REFN, REFFN, REFFLN, REFFUN, REFFAN, + BRANCHJ, SUSPEND, IFTHEN, 0 }; #endif /* DOINIT */ @@ -694,7 +778,7 @@ EXTCONST U8 PL_varies[] __attribute__deprecated__ = { EXTCONST U8 PL_varies_bitmask[]; #else EXTCONST U8 PL_varies_bitmask[] = { - 0x00, 0x00, 0x00, 0xC0, 0x81, 0x3F, 0xFF, 0x4C, 0x00, 0x00, 0x00, 0x00 + 0x00, 0x00, 0x00, 0x00, 0x18, 0x00, 0xF8, 0xC3, 0xFF, 0x32, 0x00, 0x00, 0x00 }; #endif /* DOINIT */ @@ -706,9 +790,9 @@ EXTCONST U8 PL_varies_bitmask[] = { EXTCONST U8 PL_simple[] __attribute__deprecated__; #else EXTCONST U8 PL_simple[] __attribute__deprecated__ = { - REG_ANY, SANY, CANY, ANYOF, ALNUM, ALNUML, NALNUM, NALNUML, SPACE, - SPACEL, NSPACE, NSPACEL, DIGIT, DIGITL, NDIGIT, NDIGITL, VERTWS, - NVERTWS, HORIZWS, NHORIZWS, + REG_ANY, SANY, ANYOF, ANYOFD, ANYOFL, ANYOFPOSIXL, ANYOFH, ANYOFHb, + ANYOFHr, ANYOFM, NANYOFM, POSIXD, POSIXL, POSIXU, POSIXA, NPOSIXD, + NPOSIXL, NPOSIXU, NPOSIXA, 0 }; #endif /* DOINIT */ @@ -717,7 +801,7 @@ EXTCONST U8 PL_simple[] __attribute__deprecated__ = { EXTCONST U8 PL_simple_bitmask[]; #else EXTCONST U8 PL_simple_bitmask[] = { - 0x00, 0xC0, 0xFF, 0x3F, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80, 0x07 + 0x00, 0x00, 0xFF, 0xFF, 0x07, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }; #endif /* DOINIT */