X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/24b23f37fefbcc71a881f6805d87449a234dc645..97c226b87fecccdf4a4af5defd1836198a9666e5:/regnodes.h diff --git a/regnodes.h b/regnodes.h index 010b943..09c1184 100644 --- a/regnodes.h +++ b/regnodes.h @@ -1,13 +1,13 @@ /* -*- 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 111 +#define REGMATCH_STATE_MAX 151 #define END 0 /* 0000 End of program. */ #define SUCCEED 1 /* 0x01 Return from a subroutine, basically. */ @@ -18,76 +18,109 @@ #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 BOUND 9 /* 0x09 Match "" at any word boundary using native charset semantics for non-utf8 */ +#define BOUNDL 10 /* 0x0a Match "" at any locale word boundary */ +#define BOUNDU 11 /* 0x0b Match "" at any word boundary using Unicode semantics */ +#define BOUNDA 12 /* 0x0c Match "" at any word boundary using ASCII semantics */ +#define NBOUND 13 /* 0x0d Match "" at any word non-boundary using native charset semantics for non-utf8 */ +#define NBOUNDL 14 /* 0x0e Match "" at any locale word non-boundary */ +#define NBOUNDU 15 /* 0x0f Match "" at any word non-boundary using Unicode semantics */ +#define NBOUNDA 16 /* 0x10 Match "" at any word non-boundary using ASCII semantics */ +#define GPOS 17 /* 0x11 Matches where last m//g left off. */ +#define REG_ANY 18 /* 0x12 Match any one character (except newline). */ +#define SANY 19 /* 0x13 Match any one character. */ +#define CANY 20 /* 0x14 Match any one byte. */ +#define ANYOF 21 /* 0x15 Match character in (or not in) this class, single char match only */ +#define ANYOFV 22 /* 0x16 Match character in (or not in) this class, can match-multiple chars */ +#define ALNUM 23 /* 0x17 Match any alphanumeric character using native charset semantics for non-utf8 */ +#define ALNUML 24 /* 0x18 Match any alphanumeric char in locale */ +#define ALNUMU 25 /* 0x19 Match any alphanumeric char using Unicode semantics */ +#define ALNUMA 26 /* 0x1a Match [A-Za-z_0-9] */ +#define NALNUM 27 /* 0x1b Match any non-alphanumeric character using native charset semantics for non-utf8 */ +#define NALNUML 28 /* 0x1c Match any non-alphanumeric char in locale */ +#define NALNUMU 29 /* 0x1d Match any non-alphanumeric char using Unicode semantics */ +#define NALNUMA 30 /* 0x1e Match [^A-Za-z_0-9] */ +#define SPACE 31 /* 0x1f Match any whitespace character using native charset semantics for non-utf8 */ +#define SPACEL 32 /* 0x20 Match any whitespace char in locale */ +#define SPACEU 33 /* 0x21 Match any whitespace char using Unicode semantics */ +#define SPACEA 34 /* 0x22 Match [ \t\n\f\r] */ +#define NSPACE 35 /* 0x23 Match any non-whitespace character using native charset semantics for non-utf8 */ +#define NSPACEL 36 /* 0x24 Match any non-whitespace char in locale */ +#define NSPACEU 37 /* 0x25 Match any non-whitespace char using Unicode semantics */ +#define NSPACEA 38 /* 0x26 Match [^ \t\n\f\r] */ +#define DIGIT 39 /* 0x27 Match any numeric character using native charset semantics for non-utf8 */ +#define DIGITL 40 /* 0x28 Match any numeric character in locale */ +#define DIGITA 41 /* 0x29 Match [0-9] */ +#define NDIGIT 42 /* 0x2a Match any non-numeric character using native charset semantics for non-utf8 */ +#define NDIGITL 43 /* 0x2b Match any non-numeric character in locale */ +#define NDIGITA 44 /* 0x2c Match [^0-9] */ +#define CLUMP 45 /* 0x2d Match any extended grapheme cluster sequence */ +#define BRANCH 46 /* 0x2e Match this alternative, or the next... */ +#define BACK 47 /* 0x2f Match "", "next" ptr points backward. */ +#define EXACT 48 /* 0x30 Match this string (preceded by length). */ +#define EXACTF 49 /* 0x31 Match this (folded if in UTF-8) string, folded, native charset semantics for non-utf8 (prec. by length). */ +#define EXACTFL 50 /* 0x32 Match this (not guaranteed to be folded) string, folded in locale (w/len). */ +#define EXACTFU 51 /* 0x33 Match this (folded if in UTF-8) string, folded, Unicode semantics for non-utf8 (prec. by length). */ +#define EXACTFA 52 /* 0x34 Match this (not guaranteed to be folded) string, folded, Unicode semantics for non-utf8, but no ASCII-range character matches outside ASCII (prec. by length),. */ +#define NOTHING 53 /* 0x35 Match empty string. */ +#define TAIL 54 /* 0x36 Match empty string. Can jump here from outside. */ +#define STAR 55 /* 0x37 Match this (simple) thing 0 or more times. */ +#define PLUS 56 /* 0x38 Match this (simple) thing 1 or more times. */ +#define CURLY 57 /* 0x39 Match this simple thing {n,m} times. */ +#define CURLYN 58 /* 0x3a Capture next-after-this simple thing */ +#define CURLYM 59 /* 0x3b Capture this medium-complex thing {n,m} times. */ +#define CURLYX 60 /* 0x3c Match this complex thing {n,m} times. */ +#define WHILEM 61 /* 0x3d Do curly processing and see if rest matches. */ +#define OPEN 62 /* 0x3e Mark this point in input as start of */ +#define CLOSE 63 /* 0x3f Analogous to OPEN. */ +#define REF 64 /* 0x40 Match some already matched string */ +#define REFF 65 /* 0x41 Match already matched string, folded using native charset semantics for non-utf8 */ +#define REFFL 66 /* 0x42 Match already matched string, folded in loc. */ +#define REFFU 67 /* 0x43 Match already matched string, folded using unicode semantics for non-utf8 */ +#define REFFA 68 /* 0x44 Match already matched string, folded using unicode semantics for non-utf8, no mixing ASCII, non-ASCII */ +#define NREF 69 /* 0x45 Match some already matched string */ +#define NREFF 70 /* 0x46 Match already matched string, folded using native charset semantics for non-utf8 */ +#define NREFFL 71 /* 0x47 Match already matched string, folded in loc. */ +#define NREFFU 72 /* 0x48 Match already matched string, folded using unicode semantics for non-utf8 */ +#define NREFFA 73 /* 0x49 Match already matched string, folded using unicode semantics for non-utf8, no mixing ASCII, non-ASCII */ +#define IFMATCH 74 /* 0x4a Succeeds if the following matches. */ +#define UNLESSM 75 /* 0x4b Fails if the following matches. */ +#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 LONGJMP 79 /* 0x4f Jump far away. */ +#define BRANCHJ 80 /* 0x50 BRANCH with long offset. */ +#define EVAL 81 /* 0x51 Execute some Perl code. */ +#define MINMOD 82 /* 0x52 Next operator is not greedy. */ +#define LOGICAL 83 /* 0x53 Next opcode should set the flag only. */ +#define RENUM 84 /* 0x54 Group with independently numbered parens. */ +#define TRIE 85 /* 0x55 Match many EXACT(F[ALU]?)? at once. flags==type */ +#define TRIEC 86 /* 0x56 Same as TRIE, but with embedded charclass data */ +#define AHOCORASICK 87 /* 0x57 Aho Corasick stclass. flags==type */ +#define AHOCORASICKC 88 /* 0x58 Same as AHOCORASICK, but with embedded charclass data */ +#define GOSUB 89 /* 0x59 recurse to paren arg1 at (signed) ofs arg2 */ +#define GOSTART 90 /* 0x5a recurse to start of pattern */ +#define NGROUPP 91 /* 0x5b Whether the group matched. */ +#define INSUBP 92 /* 0x5c Whether we are in a specific recurse. */ +#define DEFINEP 93 /* 0x5d Never execute directly. */ +#define ENDLIKE 94 /* 0x5e Used only for the type field of verbs */ +#define OPFAIL 95 /* 0x5f Same as (?!) */ +#define ACCEPT 96 /* 0x60 Accepts the current matched string. */ +#define VERB 97 /* 0x61 Used only for the type field of verbs */ +#define PRUNE 98 /* 0x62 Pattern fails at this startpoint if no-backtracking through this */ +#define MARKPOINT 99 /* 0x63 Push the current location for rollback by cut. */ +#define SKIP 100 /* 0x64 On failure skip forward (to the mark) before retrying */ +#define COMMIT 101 /* 0x65 Pattern fails outright if backtracking through this */ +#define CUTGROUP 102 /* 0x66 On failure go to the next alternation in the group */ +#define KEEPS 103 /* 0x67 $& begins here. */ +#define LNBREAK 104 /* 0x68 generic newline pattern */ +#define VERTWS 105 /* 0x69 vertical whitespace (Perl 6) */ +#define NVERTWS 106 /* 0x6a not vertical whitespace (Perl 6) */ +#define HORIZWS 107 /* 0x6b horizontal whitespace (Perl 6) */ +#define NHORIZWS 108 /* 0x6c not horizontal whitespace (Perl 6) */ +#define FOLDCHAR 109 /* 0x6d codepoint with tricky case folding properties. */ +#define OPTIMIZED 110 /* 0x6e Placeholder for dump. */ +#define PSEUDO 111 /* 0x6f 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 +154,14 @@ #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 +169,159 @@ 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, /* BOL */ + BOL, /* MBOL */ + BOL, /* SBOL */ + EOL, /* EOS */ + EOL, /* EOL */ + EOL, /* MEOL */ + EOL, /* SEOL */ + BOUND, /* BOUND */ + BOUND, /* BOUNDL */ + BOUND, /* BOUNDU */ + BOUND, /* BOUNDA */ + NBOUND, /* NBOUND */ + NBOUND, /* NBOUNDL */ + NBOUND, /* NBOUNDU */ + NBOUND, /* NBOUNDA */ + GPOS, /* GPOS */ + REG_ANY, /* REG_ANY */ + REG_ANY, /* SANY */ + REG_ANY, /* CANY */ + ANYOF, /* ANYOF */ + ANYOF, /* ANYOFV */ + ALNUM, /* ALNUM */ + ALNUM, /* ALNUML */ + ALNUM, /* ALNUMU */ + ALNUM, /* ALNUMA */ + NALNUM, /* NALNUM */ + NALNUM, /* NALNUML */ + NALNUM, /* NALNUMU */ + NALNUM, /* NALNUMA */ + SPACE, /* SPACE */ + SPACE, /* SPACEL */ + SPACE, /* SPACEU */ + SPACE, /* SPACEA */ + NSPACE, /* NSPACE */ + NSPACE, /* NSPACEL */ + NSPACE, /* NSPACEU */ + NSPACE, /* NSPACEA */ + DIGIT, /* DIGIT */ + DIGIT, /* DIGITL */ + DIGIT, /* DIGITA */ + NDIGIT, /* NDIGIT */ + NDIGIT, /* NDIGITL */ + NDIGIT, /* NDIGITA */ + CLUMP, /* CLUMP */ + BRANCH, /* BRANCH */ + BACK, /* BACK */ + EXACT, /* EXACT */ + EXACT, /* EXACTF */ + EXACT, /* EXACTFL */ + EXACT, /* EXACTFU */ + EXACT, /* EXACTFA */ + 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 */ + 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 */ + 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 */ + 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 */ - 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 @@ -258,31 +340,48 @@ static const U8 regarglen[] = { 0, /* SEOL */ 0, /* BOUND */ 0, /* BOUNDL */ + 0, /* BOUNDU */ + 0, /* BOUNDA */ 0, /* NBOUND */ 0, /* NBOUNDL */ + 0, /* NBOUNDU */ + 0, /* NBOUNDA */ 0, /* GPOS */ 0, /* REG_ANY */ 0, /* SANY */ 0, /* CANY */ 0, /* ANYOF */ + 0, /* ANYOFV */ 0, /* ALNUM */ 0, /* ALNUML */ + 0, /* ALNUMU */ + 0, /* ALNUMA */ 0, /* NALNUM */ 0, /* NALNUML */ + 0, /* NALNUMU */ + 0, /* NALNUMA */ 0, /* SPACE */ 0, /* SPACEL */ + 0, /* SPACEU */ + 0, /* SPACEA */ 0, /* NSPACE */ 0, /* NSPACEL */ + 0, /* NSPACEU */ + 0, /* NSPACEA */ 0, /* DIGIT */ 0, /* DIGITL */ + 0, /* DIGITA */ 0, /* NDIGIT */ 0, /* NDIGITL */ + 0, /* NDIGITA */ 0, /* CLUMP */ 0, /* BRANCH */ 0, /* BACK */ 0, /* EXACT */ 0, /* EXACTF */ 0, /* EXACTFL */ + 0, /* EXACTFU */ + 0, /* EXACTFA */ 0, /* NOTHING */ 0, /* TAIL */ 0, /* STAR */ @@ -297,6 +396,13 @@ 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), /* IFMATCH */ EXTRA_SIZE(struct regnode_1), /* UNLESSM */ EXTRA_SIZE(struct regnode_1), /* SUSPEND */ @@ -314,16 +420,25 @@ 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, /* VERTWS */ + 0, /* NVERTWS */ + 0, /* HORIZWS */ + 0, /* NHORIZWS */ + EXTRA_SIZE(struct regnode_1), /* FOLDCHAR */ 0, /* OPTIMIZED */ 0, /* PSEUDO */ }; @@ -342,31 +457,48 @@ static const char reg_off_by_arg[] = { 0, /* SEOL */ 0, /* BOUND */ 0, /* BOUNDL */ + 0, /* BOUNDU */ + 0, /* BOUNDA */ 0, /* NBOUND */ 0, /* NBOUNDL */ + 0, /* NBOUNDU */ + 0, /* NBOUNDA */ 0, /* GPOS */ 0, /* REG_ANY */ 0, /* SANY */ 0, /* CANY */ 0, /* ANYOF */ + 0, /* ANYOFV */ 0, /* ALNUM */ 0, /* ALNUML */ + 0, /* ALNUMU */ + 0, /* ALNUMA */ 0, /* NALNUM */ 0, /* NALNUML */ + 0, /* NALNUMU */ + 0, /* NALNUMA */ 0, /* SPACE */ 0, /* SPACEL */ + 0, /* SPACEU */ + 0, /* SPACEA */ 0, /* NSPACE */ 0, /* NSPACEL */ + 0, /* NSPACEU */ + 0, /* NSPACEA */ 0, /* DIGIT */ 0, /* DIGITL */ + 0, /* DIGITA */ 0, /* NDIGIT */ 0, /* NDIGITL */ + 0, /* NDIGITA */ 0, /* CLUMP */ 0, /* BRANCH */ 0, /* BACK */ 0, /* EXACT */ 0, /* EXACTF */ 0, /* EXACTFL */ + 0, /* EXACTFU */ + 0, /* EXACTFA */ 0, /* NOTHING */ 0, /* TAIL */ 0, /* STAR */ @@ -381,6 +513,13 @@ 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 */ 2, /* IFMATCH */ 2, /* UNLESSM */ 1, /* SUSPEND */ @@ -398,24 +537,37 @@ 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, /* 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 */ -#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 */ @@ -427,74 +579,107 @@ const char * reg_name[] = { "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 */ + "BOUNDU", /* 0x0b */ + "BOUNDA", /* 0x0c */ + "NBOUND", /* 0x0d */ + "NBOUNDL", /* 0x0e */ + "NBOUNDU", /* 0x0f */ + "NBOUNDA", /* 0x10 */ + "GPOS", /* 0x11 */ + "REG_ANY", /* 0x12 */ + "SANY", /* 0x13 */ + "CANY", /* 0x14 */ + "ANYOF", /* 0x15 */ + "ANYOFV", /* 0x16 */ + "ALNUM", /* 0x17 */ + "ALNUML", /* 0x18 */ + "ALNUMU", /* 0x19 */ + "ALNUMA", /* 0x1a */ + "NALNUM", /* 0x1b */ + "NALNUML", /* 0x1c */ + "NALNUMU", /* 0x1d */ + "NALNUMA", /* 0x1e */ + "SPACE", /* 0x1f */ + "SPACEL", /* 0x20 */ + "SPACEU", /* 0x21 */ + "SPACEA", /* 0x22 */ + "NSPACE", /* 0x23 */ + "NSPACEL", /* 0x24 */ + "NSPACEU", /* 0x25 */ + "NSPACEA", /* 0x26 */ + "DIGIT", /* 0x27 */ + "DIGITL", /* 0x28 */ + "DIGITA", /* 0x29 */ + "NDIGIT", /* 0x2a */ + "NDIGITL", /* 0x2b */ + "NDIGITA", /* 0x2c */ + "CLUMP", /* 0x2d */ + "BRANCH", /* 0x2e */ + "BACK", /* 0x2f */ + "EXACT", /* 0x30 */ + "EXACTF", /* 0x31 */ + "EXACTFL", /* 0x32 */ + "EXACTFU", /* 0x33 */ + "EXACTFA", /* 0x34 */ + "NOTHING", /* 0x35 */ + "TAIL", /* 0x36 */ + "STAR", /* 0x37 */ + "PLUS", /* 0x38 */ + "CURLY", /* 0x39 */ + "CURLYN", /* 0x3a */ + "CURLYM", /* 0x3b */ + "CURLYX", /* 0x3c */ + "WHILEM", /* 0x3d */ + "OPEN", /* 0x3e */ + "CLOSE", /* 0x3f */ + "REF", /* 0x40 */ + "REFF", /* 0x41 */ + "REFFL", /* 0x42 */ + "REFFU", /* 0x43 */ + "REFFA", /* 0x44 */ + "NREF", /* 0x45 */ + "NREFF", /* 0x46 */ + "NREFFL", /* 0x47 */ + "NREFFU", /* 0x48 */ + "NREFFA", /* 0x49 */ + "IFMATCH", /* 0x4a */ + "UNLESSM", /* 0x4b */ + "SUSPEND", /* 0x4c */ + "IFTHEN", /* 0x4d */ + "GROUPP", /* 0x4e */ + "LONGJMP", /* 0x4f */ + "BRANCHJ", /* 0x50 */ + "EVAL", /* 0x51 */ + "MINMOD", /* 0x52 */ + "LOGICAL", /* 0x53 */ + "RENUM", /* 0x54 */ + "TRIE", /* 0x55 */ + "TRIEC", /* 0x56 */ + "AHOCORASICK", /* 0x57 */ + "AHOCORASICKC", /* 0x58 */ + "GOSUB", /* 0x59 */ + "GOSTART", /* 0x5a */ + "NGROUPP", /* 0x5b */ + "INSUBP", /* 0x5c */ + "DEFINEP", /* 0x5d */ + "ENDLIKE", /* 0x5e */ + "OPFAIL", /* 0x5f */ + "ACCEPT", /* 0x60 */ + "VERB", /* 0x61 */ + "PRUNE", /* 0x62 */ + "MARKPOINT", /* 0x63 */ + "SKIP", /* 0x64 */ + "COMMIT", /* 0x65 */ + "CUTGROUP", /* 0x66 */ + "KEEPS", /* 0x67 */ + "LNBREAK", /* 0x68 */ + "VERTWS", /* 0x69 */ + "NVERTWS", /* 0x6a */ + "HORIZWS", /* 0x6b */ + "NHORIZWS", /* 0x6c */ + "FOLDCHAR", /* 0x6d */ + "OPTIMIZED", /* 0x6e */ + "PSEUDO", /* 0x6f */ /* ------------ States ------------- */ "TRIE_next", /* REGNODE_MAX +0x01 */ "TRIE_next_fail", /* REGNODE_MAX +0x02 */ @@ -528,12 +713,103 @@ 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 /* DEBUGGING */ +#endif /* DOINIT */ + +/* PL_reg_extflags_name[] - Opcode/state names in string form, for debugging */ + +#ifndef DOINIT +EXTCONST char * PL_reg_extflags_name[]; #else -#ifdef DEBUGGING -extern const char * reg_name[]; -#endif -#endif /* REG_COMP_C */ +EXTCONST char * const PL_reg_extflags_name[] = { + /* Bits in extflags defined: 11111111111111111111111011111111 */ + "MULTILINE", /* 0x00000001 */ + "SINGLELINE", /* 0x00000002 */ + "FOLD", /* 0x00000004 */ + "EXTENDED", /* 0x00000008 */ + "KEEPCOPY", /* 0x00000010 */ + "CHARSET", /* 0x000000e0 */ + "CHARSET", /* 0x000000e0 */ + "CHARSET", /* 0x000000e0 */ + "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 */ + "CHECK_ALL", /* 0x00080000 */ + "MATCH_UTF8", /* 0x00100000 */ + "USE_INTUIT_NOML", /* 0x00200000 */ + "USE_INTUIT_ML", /* 0x00400000 */ + "INTUIT_TAIL", /* 0x00800000 */ + "SPLIT", /* 0x01000000 */ + "COPY_DONE", /* 0x02000000 */ + "TAINTED_SEEN", /* 0x04000000 */ + "TAINTED", /* 0x08000000 */ + "START_ONLY", /* 0x10000000 */ + "SKIPWHITE", /* 0x20000000 */ + "WHITE", /* 0x40000000 */ + "NULL", /* 0x80000000 */ +}; +#endif /* DOINIT */ + +/* 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__ = { + ANYOFV, CLUMP, BRANCH, BACK, STAR, PLUS, CURLY, CURLYN, CURLYM, CURLYX, + WHILEM, REF, REFF, REFFL, REFFU, REFFA, NREF, NREFF, NREFFL, NREFFU, + NREFFA, SUSPEND, IFTHEN, BRANCHJ, + 0 +}; +#endif /* DOINIT */ + +#ifndef DOINIT +EXTCONST U8 PL_varies_bitmask[]; +#else +EXTCONST U8 PL_varies_bitmask[] = { + 0x00, 0x00, 0x40, 0x00, 0x00, 0xE0, 0x80, 0x3F, 0xFF, 0x33, 0x01, 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, ALNUM, ALNUML, ALNUMU, ALNUMA, NALNUM, + NALNUML, NALNUMU, NALNUMA, SPACE, SPACEL, SPACEU, SPACEA, NSPACE, + NSPACEL, NSPACEU, NSPACEA, DIGIT, DIGITL, DIGITA, NDIGIT, NDIGITL, + NDIGITA, VERTWS, NVERTWS, HORIZWS, NHORIZWS, + 0 +}; +#endif /* DOINIT */ + +#ifndef DOINIT +EXTCONST U8 PL_simple_bitmask[]; +#else +EXTCONST U8 PL_simple_bitmask[] = { + 0x00, 0x00, 0xBC, 0xFF, 0xFF, 0x1F, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x1E +}; +#endif /* DOINIT */ /* ex: set ro: */