X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/24b23f37fefbcc71a881f6805d87449a234dc645..62e6ef3356e0e6acf57ba63e809b4ccbd3a17981:/regnodes.h diff --git a/regnodes.h b/regnodes.h index 010b943..937dd57 100644 --- a/regnodes.h +++ b/regnodes.h @@ -1,93 +1,107 @@ /* -*- buffer-read-only: t -*- !!!!!!! DO NOT EDIT THIS FILE !!!!!!! - This file is built by regcomp.pl from regcomp.sym. + 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 78 -#define REGMATCH_STATE_MAX 110 +#define REGNODE_MAX 90 +#define REGMATCH_STATE_MAX 130 #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. */ -#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 combining character 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 (prec. by length). */ -#define EXACTFL 35 /* 0x23 Match this string, folded in locale (w/len). */ -#define NOTHING 36 /* 0x24 Match empty string. */ -#define TAIL 37 /* 0x25 Match empty string. Can jump here from outside. */ -#define STAR 38 /* 0x26 Match this (simple) thing 0 or more times. */ -#define PLUS 39 /* 0x27 Match this (simple) thing 1 or more times. */ -#define CURLY 40 /* 0x28 Match this simple thing {n,m} times. */ -#define CURLYN 41 /* 0x29 Capture next-after-this simple thing */ -#define CURLYM 42 /* 0x2a Capture this medium-complex thing {n,m} times. */ -#define CURLYX 43 /* 0x2b Match this complex thing {n,m} times. */ -#define WHILEM 44 /* 0x2c Do curly processing and see if rest matches. */ -#define OPEN 45 /* 0x2d Mark this point in input as start of */ -#define CLOSE 46 /* 0x2e Analogous to OPEN. */ -#define REF 47 /* 0x2f Match some already matched string */ -#define REFF 48 /* 0x30 Match already matched string, folded */ -#define REFFL 49 /* 0x31 Match already matched string, folded in loc. */ -#define IFMATCH 50 /* 0x32 Succeeds if the following matches. */ -#define UNLESSM 51 /* 0x33 Fails if the following matches. */ -#define SUSPEND 52 /* 0x34 "Independent" sub-RE. */ -#define IFTHEN 53 /* 0x35 Switch, should be preceeded by switcher . */ -#define GROUPP 54 /* 0x36 Whether the group matched. */ -#define LONGJMP 55 /* 0x37 Jump far away. */ -#define BRANCHJ 56 /* 0x38 BRANCH with long offset. */ -#define EVAL 57 /* 0x39 Execute some Perl code. */ -#define MINMOD 58 /* 0x3a Next operator is not greedy. */ -#define LOGICAL 59 /* 0x3b Next opcode should set the flag only. */ -#define RENUM 60 /* 0x3c Group with independently numbered parens. */ -#define TRIE 61 /* 0x3d Match many EXACT(FL?)? at once. flags==type */ -#define TRIEC 62 /* 0x3e Same as TRIE, but with embedded charclass data */ -#define AHOCORASICK 63 /* 0x3f Aho Corasick stclass. flags==type */ -#define AHOCORASICKC 64 /* 0x40 Same as AHOCORASICK, but with embedded charclass data */ -#define GOSUB 65 /* 0x41 recurse to paren arg1 at (signed) ofs arg2 */ -#define GOSTART 66 /* 0x42 recurse to start of pattern */ -#define NREF 67 /* 0x43 Match some already matched string */ -#define NREFF 68 /* 0x44 Match already matched string, folded */ -#define NREFFL 69 /* 0x45 Match already matched string, folded in loc. */ -#define NGROUPP 70 /* 0x46 Whether the group matched. */ -#define INSUBP 71 /* 0x47 Whether we are in a specific recurse. */ -#define DEFINEP 72 /* 0x48 Never execute directly. */ -#define OPFAIL 73 /* 0x49 Same as (?!) */ -#define COMMIT 74 /* 0x4a Pattern fails if backtracking through this */ -#define CUT 75 /* 0x4b ... and restarts at the cursor point */ -#define OPERROR 76 /* 0x4c Pattern fails outright if backtracking through this */ -#define OPTIMIZED 77 /* 0x4d Placeholder for dump. */ -#define PSEUDO 78 /* 0x4e 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 Match "" at any word boundary using native charset rules for non-utf8 */ +#define BOUNDL 9 /* 0x09 Match "" at any locale word boundary */ +#define BOUNDU 10 /* 0x0a Match "" at any word boundary using Unicode rules */ +#define BOUNDA 11 /* 0x0b Match "" at any word boundary using ASCII rules */ +#define NBOUND 12 /* 0x0c Match "" at any word non-boundary using native charset rules for non-utf8 */ +#define NBOUNDL 13 /* 0x0d Match "" at any locale word non-boundary */ +#define NBOUNDU 14 /* 0x0e Match "" at any word non-boundary using Unicode rules */ +#define NBOUNDA 15 /* 0x0f Match "" at any word non-boundary using ASCII rules */ +#define REG_ANY 16 /* 0x10 Match any one character (except newline). */ +#define SANY 17 /* 0x11 Match any one character. */ +#define CANY 18 /* 0x12 Match any one byte. */ +#define ANYOF 19 /* 0x13 Match character in (or not in) this class, single char match only */ +#define POSIXD 20 /* 0x14 Some [[:class:]] under /d; the FLAGS field gives which one */ +#define POSIXL 21 /* 0x15 Some [[:class:]] under /l; the FLAGS field gives which one */ +#define POSIXU 22 /* 0x16 Some [[:class:]] under /u; the FLAGS field gives which one */ +#define POSIXA 23 /* 0x17 Some [[:class:]] under /a; the FLAGS field gives which one */ +#define NPOSIXD 24 /* 0x18 complement of POSIXD, [[:^class:]] */ +#define NPOSIXL 25 /* 0x19 complement of POSIXL, [[:^class:]] */ +#define NPOSIXU 26 /* 0x1a complement of POSIXU, [[:^class:]] */ +#define NPOSIXA 27 /* 0x1b complement of POSIXA, [[:^class:]] */ +#define CLUMP 28 /* 0x1c Match any extended grapheme cluster sequence */ +#define BRANCH 29 /* 0x1d Match this alternative, or the next... */ +#define EXACT 30 /* 0x1e Match this string (preceded by length). */ +#define EXACTF 31 /* 0x1f Match this non-UTF-8 string (not guaranteed to be folded) using /id rules (w/len). */ +#define EXACTFL 32 /* 0x20 Match this string (not guaranteed to be folded) using /il rules (w/len). */ +#define EXACTFU 33 /* 0x21 Match this string (folded iff in UTF-8, length in folding doesn't change if not in UTF-8) using /iu rules (w/len). */ +#define EXACTFA 34 /* 0x22 Match this string (not guaranteed to be folded) using /iaa rules (w/len). */ +#define EXACTFU_SS 35 /* 0x23 Match this string (folded iff in UTF-8, length in folding may change even if not in UTF-8) using /iu rules (w/len). */ +#define EXACTFA_NO_TRIE 36 /* 0x24 Match this string (which is not trie-able; not guaranteed to be folded) using /iaa rules (w/len). */ +#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 #n. */ +#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 rules 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 rules for non-utf8 */ +#define REFFA 52 /* 0x34 Match already matched string, folded using unicode rules for non-utf8, no mixing ASCII, non-ASCII */ +#define NREF 53 /* 0x35 Match some already matched string */ +#define NREFF 54 /* 0x36 Match already matched string, folded using native charset rules for non-utf8 */ +#define NREFFL 55 /* 0x37 Match already matched string, folded in loc. */ +#define NREFFU 56 /* 0x38 Match already matched string, folded using unicode rules for non-utf8 */ +#define NREFFA 57 /* 0x39 Match already matched string, folded using unicode rules for non-utf8, no mixing ASCII, non-ASCII */ +#define LONGJMP 58 /* 0x3a Jump far away. */ +#define BRANCHJ 59 /* 0x3b BRANCH with long offset. */ +#define IFMATCH 60 /* 0x3c Succeeds if the following matches. */ +#define UNLESSM 61 /* 0x3d Fails if the following matches. */ +#define SUSPEND 62 /* 0x3e "Independent" sub-RE. */ +#define IFTHEN 63 /* 0x3f Switch, should be preceded by switcher. */ +#define GROUPP 64 /* 0x40 Whether the group matched. */ +#define EVAL 65 /* 0x41 Execute some Perl code. */ +#define MINMOD 66 /* 0x42 Next operator is not greedy. */ +#define LOGICAL 67 /* 0x43 Next opcode should set the flag only. */ +#define RENUM 68 /* 0x44 Group with independently numbered parens. */ +#define TRIE 69 /* 0x45 Match many EXACT(F[ALU]?)? at once. flags==type */ +#define TRIEC 70 /* 0x46 Same as TRIE, but with embedded charclass data */ +#define AHOCORASICK 71 /* 0x47 Aho Corasick stclass. flags==type */ +#define AHOCORASICKC 72 /* 0x48 Same as AHOCORASICK, but with embedded charclass data */ +#define GOSUB 73 /* 0x49 recurse to paren arg1 at (signed) ofs arg2 */ +#define GOSTART 74 /* 0x4a recurse to start of pattern */ +#define NGROUPP 75 /* 0x4b Whether the group matched. */ +#define INSUBP 76 /* 0x4c Whether we are in a specific recurse. */ +#define DEFINEP 77 /* 0x4d Never execute directly. */ +#define ENDLIKE 78 /* 0x4e Used only for the type field of verbs */ +#define OPFAIL 79 /* 0x4f Same as (?!) */ +#define ACCEPT 80 /* 0x50 Accepts the current matched string. */ +#define VERB 81 /* 0x51 Used only for the type field of verbs */ +#define PRUNE 82 /* 0x52 Pattern fails at this startpoint if no-backtracking through this */ +#define MARKPOINT 83 /* 0x53 Push the current location for rollback by cut. */ +#define SKIP 84 /* 0x54 On failure skip forward (to the mark) before retrying */ +#define COMMIT 85 /* 0x55 Pattern fails outright if backtracking through this */ +#define CUTGROUP 86 /* 0x56 On failure go to the next alternation in the group */ +#define KEEPS 87 /* 0x57 $& begins here. */ +#define LNBREAK 88 /* 0x58 generic newline pattern */ +#define OPTIMIZED 89 /* 0x59 Placeholder for dump. */ +#define PSEUDO 90 /* 0x5a 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 */ @@ -121,6 +135,14 @@ #define CURLY_B_max_fail (REGNODE_MAX + 30) /* state for CURLY */ #define COMMIT_next (REGNODE_MAX + 31) /* state for COMMIT */ #define COMMIT_next_fail (REGNODE_MAX + 32) /* state for COMMIT */ +#define MARKPOINT_next (REGNODE_MAX + 33) /* state for MARKPOINT */ +#define MARKPOINT_next_fail (REGNODE_MAX + 34) /* state for MARKPOINT */ +#define SKIP_next (REGNODE_MAX + 35) /* state for SKIP */ +#define SKIP_next_fail (REGNODE_MAX + 36) /* state for SKIP */ +#define CUTGROUP_next (REGNODE_MAX + 37) /* state for CUTGROUP */ +#define CUTGROUP_next_fail (REGNODE_MAX + 38) /* state for CUTGROUP */ +#define KEEPS_next (REGNODE_MAX + 39) /* state for KEEPS */ +#define KEEPS_next_fail (REGNODE_MAX + 40) /* state for KEEPS */ /* PL_regkind[] What type of regop or state is this. */ @@ -128,118 +150,138 @@ EXTCONST U8 PL_regkind[]; #else EXTCONST U8 PL_regkind[] = { - END, /* END */ - END, /* SUCCEED */ - BOL, /* BOL */ - BOL, /* MBOL */ - BOL, /* SBOL */ - EOL, /* EOS */ - EOL, /* EOL */ - EOL, /* MEOL */ - EOL, /* SEOL */ - BOUND, /* BOUND */ - BOUND, /* BOUNDL */ - NBOUND, /* NBOUND */ - NBOUND, /* NBOUNDL */ - GPOS, /* GPOS */ - 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 */ - CLUMP, /* CLUMP */ - BRANCH, /* BRANCH */ - BACK, /* BACK */ - EXACT, /* EXACT */ - EXACT, /* EXACTF */ - EXACT, /* EXACTFL */ - NOTHING, /* NOTHING */ - NOTHING, /* TAIL */ - STAR, /* STAR */ - PLUS, /* PLUS */ - CURLY, /* CURLY */ - CURLY, /* CURLYN */ - CURLY, /* CURLYM */ - CURLY, /* CURLYX */ - WHILEM, /* WHILEM */ - OPEN, /* OPEN */ - CLOSE, /* CLOSE */ - REF, /* REF */ - REF, /* REFF */ - REF, /* REFFL */ - BRANCHJ, /* IFMATCH */ - BRANCHJ, /* UNLESSM */ - BRANCHJ, /* SUSPEND */ - BRANCHJ, /* IFTHEN */ - GROUPP, /* GROUPP */ - LONGJMP, /* LONGJMP */ - BRANCHJ, /* BRANCHJ */ - EVAL, /* EVAL */ - MINMOD, /* MINMOD */ - LOGICAL, /* LOGICAL */ - BRANCHJ, /* RENUM */ - TRIE, /* TRIE */ - TRIE, /* TRIEC */ - TRIE, /* AHOCORASICK */ - TRIE, /* AHOCORASICKC */ - GOSUB, /* GOSUB */ - GOSTART, /* GOSTART */ - NREF, /* NREF */ - NREF, /* NREFF */ - NREF, /* NREFFL */ - NGROUPP, /* NGROUPP */ - INSUBP, /* INSUBP */ - DEFINEP, /* DEFINEP */ - OPFAIL, /* OPFAIL */ - COMMIT, /* COMMIT */ - COMMIT, /* CUT */ - OPERROR, /* OPERROR */ - NOTHING, /* OPTIMIZED */ - PSEUDO, /* PSEUDO */ + END, /* END */ + END, /* SUCCEED */ + BOL, /* SBOL */ + BOL, /* MBOL */ + EOL, /* SEOL */ + EOL, /* MEOL */ + EOL, /* EOS */ + GPOS, /* GPOS */ + BOUND, /* BOUND */ + BOUND, /* BOUNDL */ + BOUND, /* BOUNDU */ + BOUND, /* BOUNDA */ + NBOUND, /* NBOUND */ + NBOUND, /* NBOUNDL */ + NBOUND, /* NBOUNDU */ + NBOUND, /* NBOUNDA */ + REG_ANY, /* REG_ANY */ + REG_ANY, /* SANY */ + REG_ANY, /* CANY */ + ANYOF, /* ANYOF */ + POSIXD, /* POSIXD */ + POSIXD, /* POSIXL */ + POSIXD, /* POSIXU */ + POSIXD, /* POSIXA */ + NPOSIXD, /* NPOSIXD */ + NPOSIXD, /* NPOSIXL */ + NPOSIXD, /* NPOSIXU */ + NPOSIXD, /* NPOSIXA */ + CLUMP, /* CLUMP */ + BRANCH, /* BRANCH */ + EXACT, /* EXACT */ + EXACT, /* EXACTF */ + EXACT, /* EXACTFL */ + EXACT, /* EXACTFU */ + EXACT, /* EXACTFA */ + EXACT, /* EXACTFU_SS */ + EXACT, /* EXACTFA_NO_TRIE */ + NOTHING, /* NOTHING */ + NOTHING, /* TAIL */ + STAR, /* STAR */ + PLUS, /* PLUS */ + CURLY, /* CURLY */ + CURLY, /* CURLYN */ + CURLY, /* CURLYM */ + CURLY, /* CURLYX */ + WHILEM, /* WHILEM */ + OPEN, /* OPEN */ + CLOSE, /* CLOSE */ + REF, /* REF */ + REF, /* REFF */ + REF, /* REFFL */ + REF, /* REFFU */ + REF, /* REFFA */ + REF, /* NREF */ + REF, /* NREFF */ + REF, /* NREFFL */ + REF, /* NREFFU */ + REF, /* NREFFA */ + LONGJMP, /* LONGJMP */ + BRANCHJ, /* BRANCHJ */ + BRANCHJ, /* IFMATCH */ + BRANCHJ, /* UNLESSM */ + BRANCHJ, /* SUSPEND */ + BRANCHJ, /* IFTHEN */ + GROUPP, /* GROUPP */ + EVAL, /* EVAL */ + MINMOD, /* MINMOD */ + LOGICAL, /* LOGICAL */ + BRANCHJ, /* RENUM */ + TRIE, /* TRIE */ + TRIE, /* TRIEC */ + TRIE, /* AHOCORASICK */ + TRIE, /* AHOCORASICKC */ + GOSUB, /* GOSUB */ + GOSTART, /* GOSTART */ + NGROUPP, /* NGROUPP */ + INSUBP, /* INSUBP */ + DEFINEP, /* DEFINEP */ + ENDLIKE, /* ENDLIKE */ + ENDLIKE, /* OPFAIL */ + ENDLIKE, /* ACCEPT */ + VERB, /* VERB */ + VERB, /* PRUNE */ + VERB, /* MARKPOINT */ + VERB, /* SKIP */ + VERB, /* COMMIT */ + VERB, /* CUTGROUP */ + KEEPS, /* KEEPS */ + LNBREAK, /* LNBREAK */ + NOTHING, /* OPTIMIZED */ + PSEUDO, /* PSEUDO */ /* ------------ States ------------- */ - TRIE, /* TRIE_next */ - TRIE, /* TRIE_next_fail */ - EVAL, /* EVAL_AB */ - EVAL, /* EVAL_AB_fail */ - CURLYX, /* CURLYX_end */ - CURLYX, /* CURLYX_end_fail */ - WHILEM, /* WHILEM_A_pre */ - WHILEM, /* WHILEM_A_pre_fail */ - WHILEM, /* WHILEM_A_min */ - WHILEM, /* WHILEM_A_min_fail */ - WHILEM, /* WHILEM_A_max */ - WHILEM, /* WHILEM_A_max_fail */ - WHILEM, /* WHILEM_B_min */ - WHILEM, /* WHILEM_B_min_fail */ - WHILEM, /* WHILEM_B_max */ - WHILEM, /* WHILEM_B_max_fail */ - BRANCH, /* BRANCH_next */ - BRANCH, /* BRANCH_next_fail */ - CURLYM, /* CURLYM_A */ - CURLYM, /* CURLYM_A_fail */ - CURLYM, /* CURLYM_B */ - 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 */ - CURLY, /* CURLY_B_max_fail */ - COMMIT, /* COMMIT_next */ - COMMIT, /* COMMIT_next_fail */ + TRIE, /* TRIE_next */ + TRIE, /* TRIE_next_fail */ + EVAL, /* EVAL_AB */ + EVAL, /* EVAL_AB_fail */ + CURLYX, /* CURLYX_end */ + CURLYX, /* CURLYX_end_fail */ + WHILEM, /* WHILEM_A_pre */ + WHILEM, /* WHILEM_A_pre_fail */ + WHILEM, /* WHILEM_A_min */ + WHILEM, /* WHILEM_A_min_fail */ + WHILEM, /* WHILEM_A_max */ + WHILEM, /* WHILEM_A_max_fail */ + WHILEM, /* WHILEM_B_min */ + WHILEM, /* WHILEM_B_min_fail */ + WHILEM, /* WHILEM_B_max */ + WHILEM, /* WHILEM_B_max_fail */ + BRANCH, /* BRANCH_next */ + BRANCH, /* BRANCH_next_fail */ + CURLYM, /* CURLYM_A */ + CURLYM, /* CURLYM_A_fail */ + CURLYM, /* CURLYM_B */ + 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 */ + CURLY, /* CURLY_B_max_fail */ + COMMIT, /* COMMIT_next */ + COMMIT, /* COMMIT_next_fail */ + MARKPOINT, /* MARKPOINT_next */ + MARKPOINT, /* MARKPOINT_next_fail */ + SKIP, /* SKIP_next */ + SKIP, /* SKIP_next_fail */ + CUTGROUP, /* CUTGROUP_next */ + CUTGROUP, /* CUTGROUP_next_fail */ + KEEPS, /* KEEPS_next */ + KEEPS, /* KEEPS_next_fail */ }; #endif @@ -249,40 +291,41 @@ EXTCONST U8 PL_regkind[] = { 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_1), /* ANYOF */ + 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, /* EXACTF */ 0, /* EXACTFL */ + 0, /* EXACTFU */ + 0, /* EXACTFA */ + 0, /* EXACTFU_SS */ + 0, /* EXACTFA_NO_TRIE */ 0, /* NOTHING */ 0, /* TAIL */ 0, /* STAR */ @@ -297,14 +340,21 @@ static const U8 regarglen[] = { 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), /* REFFA */ + 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), /* NREFFA */ + 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 */ @@ -314,16 +364,20 @@ static const U8 regarglen[] = { EXTRA_SIZE(struct regnode_charclass), /* AHOCORASICKC */ EXTRA_SIZE(struct regnode_2L), /* GOSUB */ 0, /* GOSTART */ - EXTRA_SIZE(struct regnode_1), /* NREF */ - EXTRA_SIZE(struct regnode_1), /* NREFF */ - EXTRA_SIZE(struct regnode_1), /* NREFFL */ EXTRA_SIZE(struct regnode_1), /* NGROUPP */ EXTRA_SIZE(struct regnode_1), /* INSUBP */ EXTRA_SIZE(struct regnode_1), /* DEFINEP */ + 0, /* ENDLIKE */ 0, /* OPFAIL */ - 0, /* COMMIT */ - 0, /* CUT */ - 0, /* OPERROR */ + EXTRA_SIZE(struct regnode_1), /* ACCEPT */ + EXTRA_SIZE(struct regnode_1), /* VERB */ + EXTRA_SIZE(struct regnode_1), /* PRUNE */ + EXTRA_SIZE(struct regnode_1), /* MARKPOINT */ + EXTRA_SIZE(struct regnode_1), /* SKIP */ + EXTRA_SIZE(struct regnode_1), /* COMMIT */ + EXTRA_SIZE(struct regnode_1), /* CUTGROUP */ + 0, /* KEEPS */ + 0, /* LNBREAK */ 0, /* OPTIMIZED */ 0, /* PSEUDO */ }; @@ -333,40 +387,41 @@ 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, /* POSIXD */ + 0, /* POSIXL */ + 0, /* POSIXU */ + 0, /* POSIXA */ + 0, /* NPOSIXD */ + 0, /* NPOSIXL */ + 0, /* NPOSIXU */ + 0, /* NPOSIXA */ 0, /* CLUMP */ 0, /* BRANCH */ - 0, /* BACK */ 0, /* EXACT */ 0, /* EXACTF */ 0, /* EXACTFL */ + 0, /* EXACTFU */ + 0, /* EXACTFA */ + 0, /* EXACTFU_SS */ + 0, /* EXACTFA_NO_TRIE */ 0, /* NOTHING */ 0, /* TAIL */ 0, /* STAR */ @@ -381,13 +436,20 @@ static const char reg_off_by_arg[] = { 0, /* REF */ 0, /* REFF */ 0, /* REFFL */ + 0, /* REFFU */ + 0, /* REFFA */ + 0, /* NREF */ + 0, /* NREFF */ + 0, /* NREFFL */ + 0, /* NREFFU */ + 0, /* NREFFA */ + 1, /* LONGJMP */ + 1, /* BRANCHJ */ 2, /* IFMATCH */ 2, /* UNLESSM */ 1, /* SUSPEND */ 1, /* IFTHEN */ 0, /* GROUPP */ - 1, /* LONGJMP */ - 1, /* BRANCHJ */ 0, /* EVAL */ 0, /* MINMOD */ 0, /* LOGICAL */ @@ -398,103 +460,123 @@ static const char reg_off_by_arg[] = { 0, /* AHOCORASICKC */ 0, /* GOSUB */ 0, /* GOSTART */ - 0, /* NREF */ - 0, /* NREFF */ - 0, /* NREFFL */ 0, /* NGROUPP */ 0, /* INSUBP */ 0, /* DEFINEP */ + 0, /* ENDLIKE */ 0, /* OPFAIL */ + 0, /* ACCEPT */ + 0, /* VERB */ + 0, /* PRUNE */ + 0, /* MARKPOINT */ + 0, /* SKIP */ 0, /* COMMIT */ - 0, /* CUT */ - 0, /* OPERROR */ + 0, /* CUTGROUP */ + 0, /* KEEPS */ + 0, /* LNBREAK */ 0, /* OPTIMIZED */ 0, /* PSEUDO */ }; +#endif /* REG_COMP_C */ + /* reg_name[] - Opcode/state names in string form, for debugging */ -#ifdef DEBUGGING -const char * reg_name[] = { +#ifndef DOINIT +EXTCONST char * PL_reg_name[]; +#else +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 */ - "NOTHING", /* 0x24 */ - "TAIL", /* 0x25 */ - "STAR", /* 0x26 */ - "PLUS", /* 0x27 */ - "CURLY", /* 0x28 */ - "CURLYN", /* 0x29 */ - "CURLYM", /* 0x2a */ - "CURLYX", /* 0x2b */ - "WHILEM", /* 0x2c */ - "OPEN", /* 0x2d */ - "CLOSE", /* 0x2e */ - "REF", /* 0x2f */ - "REFF", /* 0x30 */ - "REFFL", /* 0x31 */ - "IFMATCH", /* 0x32 */ - "UNLESSM", /* 0x33 */ - "SUSPEND", /* 0x34 */ - "IFTHEN", /* 0x35 */ - "GROUPP", /* 0x36 */ - "LONGJMP", /* 0x37 */ - "BRANCHJ", /* 0x38 */ - "EVAL", /* 0x39 */ - "MINMOD", /* 0x3a */ - "LOGICAL", /* 0x3b */ - "RENUM", /* 0x3c */ - "TRIE", /* 0x3d */ - "TRIEC", /* 0x3e */ - "AHOCORASICK", /* 0x3f */ - "AHOCORASICKC", /* 0x40 */ - "GOSUB", /* 0x41 */ - "GOSTART", /* 0x42 */ - "NREF", /* 0x43 */ - "NREFF", /* 0x44 */ - "NREFFL", /* 0x45 */ - "NGROUPP", /* 0x46 */ - "INSUBP", /* 0x47 */ - "DEFINEP", /* 0x48 */ - "OPFAIL", /* 0x49 */ - "COMMIT", /* 0x4a */ - "CUT", /* 0x4b */ - "OPERROR", /* 0x4c */ - "OPTIMIZED", /* 0x4d */ - "PSEUDO", /* 0x4e */ + "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 */ + "CANY", /* 0x12 */ + "ANYOF", /* 0x13 */ + "POSIXD", /* 0x14 */ + "POSIXL", /* 0x15 */ + "POSIXU", /* 0x16 */ + "POSIXA", /* 0x17 */ + "NPOSIXD", /* 0x18 */ + "NPOSIXL", /* 0x19 */ + "NPOSIXU", /* 0x1a */ + "NPOSIXA", /* 0x1b */ + "CLUMP", /* 0x1c */ + "BRANCH", /* 0x1d */ + "EXACT", /* 0x1e */ + "EXACTF", /* 0x1f */ + "EXACTFL", /* 0x20 */ + "EXACTFU", /* 0x21 */ + "EXACTFA", /* 0x22 */ + "EXACTFU_SS", /* 0x23 */ + "EXACTFA_NO_TRIE", /* 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 */ + "REFFA", /* 0x34 */ + "NREF", /* 0x35 */ + "NREFF", /* 0x36 */ + "NREFFL", /* 0x37 */ + "NREFFU", /* 0x38 */ + "NREFFA", /* 0x39 */ + "LONGJMP", /* 0x3a */ + "BRANCHJ", /* 0x3b */ + "IFMATCH", /* 0x3c */ + "UNLESSM", /* 0x3d */ + "SUSPEND", /* 0x3e */ + "IFTHEN", /* 0x3f */ + "GROUPP", /* 0x40 */ + "EVAL", /* 0x41 */ + "MINMOD", /* 0x42 */ + "LOGICAL", /* 0x43 */ + "RENUM", /* 0x44 */ + "TRIE", /* 0x45 */ + "TRIEC", /* 0x46 */ + "AHOCORASICK", /* 0x47 */ + "AHOCORASICKC", /* 0x48 */ + "GOSUB", /* 0x49 */ + "GOSTART", /* 0x4a */ + "NGROUPP", /* 0x4b */ + "INSUBP", /* 0x4c */ + "DEFINEP", /* 0x4d */ + "ENDLIKE", /* 0x4e */ + "OPFAIL", /* 0x4f */ + "ACCEPT", /* 0x50 */ + "VERB", /* 0x51 */ + "PRUNE", /* 0x52 */ + "MARKPOINT", /* 0x53 */ + "SKIP", /* 0x54 */ + "COMMIT", /* 0x55 */ + "CUTGROUP", /* 0x56 */ + "KEEPS", /* 0x57 */ + "LNBREAK", /* 0x58 */ + "OPTIMIZED", /* 0x59 */ + "PSEUDO", /* 0x5a */ /* ------------ States ------------- */ "TRIE_next", /* REGNODE_MAX +0x01 */ "TRIE_next_fail", /* REGNODE_MAX +0x02 */ @@ -528,12 +610,131 @@ const char * reg_name[] = { "CURLY_B_max_fail", /* REGNODE_MAX +0x1e */ "COMMIT_next", /* REGNODE_MAX +0x1f */ "COMMIT_next_fail", /* REGNODE_MAX +0x20 */ + "MARKPOINT_next", /* REGNODE_MAX +0x21 */ + "MARKPOINT_next_fail", /* REGNODE_MAX +0x22 */ + "SKIP_next", /* REGNODE_MAX +0x23 */ + "SKIP_next_fail", /* REGNODE_MAX +0x24 */ + "CUTGROUP_next", /* REGNODE_MAX +0x25 */ + "CUTGROUP_next_fail", /* REGNODE_MAX +0x26 */ + "KEEPS_next", /* REGNODE_MAX +0x27 */ + "KEEPS_next_fail", /* REGNODE_MAX +0x28 */ +}; +#endif /* DOINIT */ + +/* PL_reg_extflags_name[] - Opcode/state names in string form, for debugging */ + +#ifndef DOINIT +EXTCONST char * PL_reg_extflags_name[]; +#else +EXTCONST char * const PL_reg_extflags_name[] = { + /* Bits in extflags defined: 11111111111111110000001111111111 */ + "MULTILINE", /* 0x00000001 */ + "SINGLELINE", /* 0x00000002 */ + "FOLD", /* 0x00000004 */ + "EXTENDED", /* 0x00000008 */ + "EXTENDED_MORE", /* 0x00000010 */ + "KEEPCOPY", /* 0x00000020 */ + "CHARSET0", /* 0x00000040 : "CHARSET" - 0x000001c0 */ + "CHARSET1", /* 0x00000080 : "CHARSET" - 0x000001c0 */ + "CHARSET2", /* 0x00000100 : "CHARSET" - 0x000001c0 */ + "SPLIT", /* 0x00000200 */ + "UNUSED_BIT_10", /* 0x00000400 */ + "UNUSED_BIT_11", /* 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 */ + "IS_ANCHORED", /* 0x01000000 */ + "COPY_DONE", /* 0x02000000 */ + "TAINTED_SEEN", /* 0x04000000 */ + "TAINTED", /* 0x08000000 */ + "START_ONLY", /* 0x10000000 */ + "SKIPWHITE", /* 0x20000000 */ + "WHITE", /* 0x40000000 */ + "NULL", /* 0x80000000 */ }; -#endif /* DEBUGGING */ +#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 */ + "CANY_SEEN", /* 0x00000080 - PREGf_CANY_SEEN */ + "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 */ +}; +#endif /* DOINIT */ + #ifdef DEBUGGING -extern const char * reg_name[]; +# define REG_INTFLAGS_NAME_SIZE 13 #endif -#endif /* REG_COMP_C */ + +/* 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))) + +#ifndef DOINIT +EXTCONST U8 PL_varies[] __attribute__deprecated__; +#else +EXTCONST U8 PL_varies[] __attribute__deprecated__ = { + CLUMP, BRANCH, STAR, PLUS, CURLY, CURLYN, CURLYM, CURLYX, WHILEM, REF, + REFF, REFFL, REFFU, REFFA, NREF, NREFF, NREFFL, NREFFU, NREFFA, + BRANCHJ, SUSPEND, IFTHEN, + 0 +}; +#endif /* DOINIT */ + +#ifndef DOINIT +EXTCONST U8 PL_varies_bitmask[]; +#else +EXTCONST U8 PL_varies_bitmask[] = { + 0x00, 0x00, 0x00, 0x30, 0x80, 0x3F, 0xFF, 0xCB, 0x00, 0x00, 0x00, 0x00 +}; +#endif /* DOINIT */ + +/* The following always have a length of 1. U8 we can do strchr() on it. */ +/* (Note that length 1 means "one character" under UTF8, not "one octet".) */ +#define REGNODE_SIMPLE(node) (PL_simple_bitmask[(node) >> 3] & (1 << ((node) & 7))) + +#ifndef DOINIT +EXTCONST U8 PL_simple[] __attribute__deprecated__; +#else +EXTCONST U8 PL_simple[] __attribute__deprecated__ = { + REG_ANY, SANY, CANY, ANYOF, POSIXD, POSIXL, POSIXU, POSIXA, NPOSIXD, + NPOSIXL, NPOSIXU, NPOSIXA, + 0 +}; +#endif /* DOINIT */ + +#ifndef DOINIT +EXTCONST U8 PL_simple_bitmask[]; +#else +EXTCONST U8 PL_simple_bitmask[] = { + 0x00, 0x00, 0xFF, 0x0F, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 +}; +#endif /* DOINIT */ /* ex: set ro: */