X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/fee505829585692618c3f9bb28a8f0464553ec94..04863ba129586c36255f07ee939d537fc1d6508b:/regnodes.h diff --git a/regnodes.h b/regnodes.h index c05003d..cab219b 100644 --- a/regnodes.h +++ b/regnodes.h @@ -6,8 +6,8 @@ /* Regops and State definitions */ -#define REGNODE_MAX 93 -#define REGMATCH_STATE_MAX 133 +#define REGNODE_MAX 105 +#define REGMATCH_STATE_MAX 145 #define END 0 /* 0000 End of program. */ #define SUCCEED 1 /* 0x01 Return from a subroutine, basically. */ @@ -21,117 +21,129 @@ #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 Unicode rules */ +#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 Unicode rules */ +#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 POSIXD 21 /* 0x15 Some [[:class:]] under /d; the FLAGS field gives which one */ -#define POSIXL 22 /* 0x16 Some [[:class:]] under /l; the FLAGS field gives which one */ -#define POSIXU 23 /* 0x17 Some [[:class:]] under /u; the FLAGS field gives which one */ -#define POSIXA 24 /* 0x18 Some [[:class:]] under /a; the FLAGS field gives which one */ -#define NPOSIXD 25 /* 0x19 complement of POSIXD, [[:^class:]] */ -#define NPOSIXL 26 /* 0x1a complement of POSIXL, [[:^class:]] */ -#define NPOSIXU 27 /* 0x1b complement of POSIXU, [[:^class:]] */ -#define NPOSIXA 28 /* 0x1c complement of POSIXA, [[:^class:]] */ -#define CLUMP 29 /* 0x1d Match any extended grapheme cluster sequence */ -#define BRANCH 30 /* 0x1e Match this alternative, or the next... */ -#define EXACT 31 /* 0x1f Match this string (preceded by length). */ -#define EXACTL 32 /* 0x20 Like EXACT, but /l is in effect (used so locale-related warnings can be checked for). */ -#define EXACTF 33 /* 0x21 Match this non-UTF-8 string (not guaranteed to be folded) using /id rules (w/len). */ -#define EXACTFL 34 /* 0x22 Match this string (not guaranteed to be folded) using /il rules (w/len). */ -#define EXACTFU 35 /* 0x23 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 36 /* 0x24 Match this string (not guaranteed to be folded) using /iaa rules (w/len). */ -#define EXACTFU_SS 37 /* 0x25 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 EXACTFLU8 38 /* 0x26 Rare cirucmstances: like EXACTFU, but is under /l, UTF-8, folded, and everything in it is above 255. */ -#define EXACTFA_NO_TRIE 39 /* 0x27 Match this string (which is not trie-able; not guaranteed to be folded) using /iaa rules (w/len). */ -#define NOTHING 40 /* 0x28 Match empty string. */ -#define TAIL 41 /* 0x29 Match empty string. Can jump here from outside. */ -#define STAR 42 /* 0x2a Match this (simple) thing 0 or more times. */ -#define PLUS 43 /* 0x2b Match this (simple) thing 1 or more times. */ -#define CURLY 44 /* 0x2c Match this simple thing {n,m} times. */ -#define CURLYN 45 /* 0x2d Capture next-after-this simple thing */ -#define CURLYM 46 /* 0x2e Capture this medium-complex thing {n,m} times. */ -#define CURLYX 47 /* 0x2f Match this complex thing {n,m} times. */ -#define WHILEM 48 /* 0x30 Do curly processing and see if rest matches. */ -#define OPEN 49 /* 0x31 Mark this point in input as start of #n. */ -#define CLOSE 50 /* 0x32 Analogous to OPEN. */ -#define REF 51 /* 0x33 Match some already matched string */ -#define REFF 52 /* 0x34 Match already matched string, folded using native charset rules for non-utf8 */ -#define REFFL 53 /* 0x35 Match already matched string, folded in loc. */ -#define REFFU 54 /* 0x36 Match already matched string, folded using unicode rules for non-utf8 */ -#define REFFA 55 /* 0x37 Match already matched string, folded using unicode rules for non-utf8, no mixing ASCII, non-ASCII */ -#define NREF 56 /* 0x38 Match some already matched string */ -#define NREFF 57 /* 0x39 Match already matched string, folded using native charset rules for non-utf8 */ -#define NREFFL 58 /* 0x3a Match already matched string, folded in loc. */ -#define NREFFU 59 /* 0x3b Match already matched string, folded using unicode rules for non-utf8 */ -#define NREFFA 60 /* 0x3c Match already matched string, folded using unicode rules for non-utf8, no mixing ASCII, non-ASCII */ -#define LONGJMP 61 /* 0x3d Jump far away. */ -#define BRANCHJ 62 /* 0x3e BRANCH with long offset. */ -#define IFMATCH 63 /* 0x3f Succeeds if the following matches. */ -#define UNLESSM 64 /* 0x40 Fails if the following matches. */ -#define SUSPEND 65 /* 0x41 "Independent" sub-RE. */ -#define IFTHEN 66 /* 0x42 Switch, should be preceded by switcher. */ -#define GROUPP 67 /* 0x43 Whether the group matched. */ -#define EVAL 68 /* 0x44 Execute some Perl code. */ -#define MINMOD 69 /* 0x45 Next operator is not greedy. */ -#define LOGICAL 70 /* 0x46 Next opcode should set the flag only. */ -#define RENUM 71 /* 0x47 Group with independently numbered parens. */ -#define TRIE 72 /* 0x48 Match many EXACT(F[ALU]?)? at once. flags==type */ -#define TRIEC 73 /* 0x49 Same as TRIE, but with embedded charclass data */ -#define AHOCORASICK 74 /* 0x4a Aho Corasick stclass. flags==type */ -#define AHOCORASICKC 75 /* 0x4b Same as AHOCORASICK, but with embedded charclass data */ -#define GOSUB 76 /* 0x4c recurse to paren arg1 at (signed) ofs arg2 */ -#define GOSTART 77 /* 0x4d recurse to start of pattern */ -#define NGROUPP 78 /* 0x4e Whether the group matched. */ -#define INSUBP 79 /* 0x4f Whether we are in a specific recurse. */ -#define DEFINEP 80 /* 0x50 Never execute directly. */ -#define ENDLIKE 81 /* 0x51 Used only for the type field of verbs */ -#define OPFAIL 82 /* 0x52 Same as (?!), but with verb arg */ -#define ACCEPT 83 /* 0x53 Accepts the current matched string, with verbar */ -#define VERB 84 /* 0x54 Used only for the type field of verbs */ -#define PRUNE 85 /* 0x55 Pattern fails at this startpoint if no-backtracking through this */ -#define MARKPOINT 86 /* 0x56 Push the current location for rollback by cut. */ -#define SKIP 87 /* 0x57 On failure skip forward (to the mark) before retrying */ -#define COMMIT 88 /* 0x58 Pattern fails outright if backtracking through this */ -#define CUTGROUP 89 /* 0x59 On failure go to the next alternation in the group */ -#define KEEPS 90 /* 0x5a $& begins here. */ -#define LNBREAK 91 /* 0x5b generic newline pattern */ -#define OPTIMIZED 92 /* 0x5c Placeholder for dump. */ -#define PSEUDO 93 /* 0x5d Pseudo opcode for internal use. */ +#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 (flags field is the length). */ +#define LEXACT 38 /* 0x26 Match this long string (preceded by length; flags unused). */ +#define EXACTL 39 /* 0x27 Like EXACT, but /l is in effect (used so locale-related warnings can be checked for). */ +#define EXACTF 40 /* 0x28 Like EXACT, but match using /id rules; (string not UTF-8, not guaranteed to be folded). */ +#define EXACTFL 41 /* 0x29 Like EXACT, but match using /il rules; (string not likely to be folded). */ +#define EXACTFU 42 /* 0x2a Like EXACT, but match using /iu rules; (string folded). */ +#define EXACTFAA 43 /* 0x2b Like EXACT, but match using /iaa rules; (string folded iff pattern is UTF8; folded length <= unfolded). */ +#define EXACTFUP 44 /* 0x2c Like EXACT, but match using /iu rules; (string not UTF-8, not guaranteed to be folded; and it is Problematic). */ +#define EXACTFLU8 45 /* 0x2d Like EXACTFU, but use /il, UTF-8, (string is folded, and everything in it is above 255. */ +#define EXACTFAA_NO_TRIE 46 /* 0x2e Like EXACT, but match using /iaa rules (string not UTF-8, not guaranteed to be folded, not currently trie-able). */ +#define EXACT_REQ8 47 /* 0x2f Like EXACT, but only UTF-8 encoded targets can match */ +#define LEXACT_REQ8 48 /* 0x30 Like LEXACT, but only UTF-8 encoded targets can match */ +#define EXACTFU_REQ8 49 /* 0x31 Like EXACTFU, but only UTF-8 encoded targets can match */ +#define EXACTFU_S_EDGE 50 /* 0x32 /di rules, but nothing in it precludes /ui, except begins and/or ends with [Ss]; (string not UTF-8; compile-time only). */ +#define NOTHING 51 /* 0x33 Match empty string. */ +#define TAIL 52 /* 0x34 Match empty string. Can jump here from outside. */ +#define STAR 53 /* 0x35 Match this (simple) thing 0 or more times. */ +#define PLUS 54 /* 0x36 Match this (simple) thing 1 or more times. */ +#define CURLY 55 /* 0x37 Match this simple thing {n,m} times. */ +#define CURLYN 56 /* 0x38 Capture next-after-this simple thing */ +#define CURLYM 57 /* 0x39 Capture this medium-complex thing {n,m} times. */ +#define CURLYX 58 /* 0x3a Match this complex thing {n,m} times. */ +#define WHILEM 59 /* 0x3b Do curly processing and see if rest matches. */ +#define OPEN 60 /* 0x3c Mark this point in input as start of #n. */ +#define CLOSE 61 /* 0x3d Close corresponding OPEN of #n. */ +#define SROPEN 62 /* 0x3e Same as OPEN, but for script run */ +#define SRCLOSE 63 /* 0x3f Close preceding SROPEN */ +#define REF 64 /* 0x40 Match some already matched string */ +#define REFF 65 /* 0x41 Match already matched string, using /di rules. */ +#define REFFL 66 /* 0x42 Match already matched string, using /li rules. */ +#define REFFU 67 /* 0x43 Match already matched string, usng /ui. */ +#define REFFA 68 /* 0x44 Match already matched string, using /aai rules. */ +#define REFN 69 /* 0x45 Match some already matched string */ +#define REFFN 70 /* 0x46 Match already matched string, using /di rules. */ +#define REFFLN 71 /* 0x47 Match already matched string, using /li rules. */ +#define REFFUN 72 /* 0x48 Match already matched string, using /ui rules. */ +#define REFFAN 73 /* 0x49 Match already matched string, using /aai rules. */ +#define LONGJMP 74 /* 0x4a Jump far away. */ +#define BRANCHJ 75 /* 0x4b BRANCH with long offset. */ +#define IFMATCH 76 /* 0x4c Succeeds if the following matches; non-zero flags "f", next_off "o" means lookbehind assertion starting "f..(f-o)" characters before current */ +#define UNLESSM 77 /* 0x4d Fails if the following matches; non-zero flags "f", next_off "o" means lookbehind assertion starting "f..(f-o)" characters before current */ +#define SUSPEND 78 /* 0x4e "Independent" sub-RE. */ +#define IFTHEN 79 /* 0x4f Switch, should be preceded by switcher. */ +#define GROUPP 80 /* 0x50 Whether the group matched. */ +#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 GROUPPN 90 /* 0x5a Whether the group matched. */ +#define INSUBP 91 /* 0x5b Whether we are in a specific recurse. */ +#define DEFINEP 92 /* 0x5c Never execute directly. */ +#define ENDLIKE 93 /* 0x5d Used only for the type field of verbs */ +#define OPFAIL 94 /* 0x5e Same as (?!), but with verb arg */ +#define ACCEPT 95 /* 0x5f Accepts the current matched string, with verbar */ +#define VERB 96 /* 0x60 Used only for the type field of verbs */ +#define PRUNE 97 /* 0x61 Pattern fails at this startpoint if no-backtracking through this */ +#define MARKPOINT 98 /* 0x62 Push the current location for rollback by cut. */ +#define SKIP 99 /* 0x63 On failure skip forward (to the mark) before retrying */ +#define COMMIT 100 /* 0x64 Pattern fails outright if backtracking through this */ +#define CUTGROUP 101 /* 0x65 On failure go to the next alternation in the group */ +#define KEEPS 102 /* 0x66 $& begins here. */ +#define LNBREAK 103 /* 0x67 generic newline pattern */ +#define OPTIMIZED 104 /* 0x68 Placeholder for dump. */ +#define PSEUDO 105 /* 0x69 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 */ @@ -174,6 +186,12 @@ EXTCONST U8 PL_regkind[] = { ANYOF, /* ANYOF */ ANYOF, /* ANYOFD */ ANYOF, /* ANYOFL */ + ANYOF, /* ANYOFPOSIXL */ + ANYOF, /* ANYOFH */ + ANYOF, /* ANYOFHb */ + ANYOF, /* ANYOFHr */ + ANYOFM, /* ANYOFM */ + ANYOFM, /* NANYOFM */ POSIXD, /* POSIXD */ POSIXD, /* POSIXL */ POSIXD, /* POSIXU */ @@ -185,14 +203,19 @@ EXTCONST U8 PL_regkind[] = { CLUMP, /* CLUMP */ BRANCH, /* BRANCH */ EXACT, /* EXACT */ + EXACT, /* LEXACT */ EXACT, /* EXACTL */ EXACT, /* EXACTF */ EXACT, /* EXACTFL */ EXACT, /* EXACTFU */ - EXACT, /* EXACTFA */ - EXACT, /* EXACTFU_SS */ + EXACT, /* EXACTFAA */ + EXACT, /* EXACTFUP */ EXACT, /* EXACTFLU8 */ - EXACT, /* EXACTFA_NO_TRIE */ + EXACT, /* EXACTFAA_NO_TRIE */ + EXACT, /* EXACT_REQ8 */ + EXACT, /* LEXACT_REQ8 */ + EXACT, /* EXACTFU_REQ8 */ + EXACT, /* EXACTFU_S_EDGE */ NOTHING, /* NOTHING */ NOTHING, /* TAIL */ STAR, /* STAR */ @@ -204,16 +227,18 @@ EXTCONST U8 PL_regkind[] = { WHILEM, /* WHILEM */ OPEN, /* OPEN */ CLOSE, /* CLOSE */ + SROPEN, /* SROPEN */ + SRCLOSE, /* SRCLOSE */ REF, /* REF */ REF, /* REFF */ REF, /* REFFL */ REF, /* REFFU */ REF, /* REFFA */ - REF, /* NREF */ - REF, /* NREFF */ - REF, /* NREFFL */ - REF, /* NREFFU */ - REF, /* NREFFA */ + REF, /* REFN */ + REF, /* REFFN */ + REF, /* REFFLN */ + REF, /* REFFUN */ + REF, /* REFFAN */ LONGJMP, /* LONGJMP */ BRANCHJ, /* BRANCHJ */ BRANCHJ, /* IFMATCH */ @@ -230,8 +255,7 @@ EXTCONST U8 PL_regkind[] = { TRIE, /* AHOCORASICK */ TRIE, /* AHOCORASICKC */ GOSUB, /* GOSUB */ - GOSTART, /* GOSTART */ - NGROUPP, /* NGROUPP */ + GROUPPN, /* GROUPPN */ INSUBP, /* INSUBP */ DEFINEP, /* DEFINEP */ ENDLIKE, /* ENDLIKE */ @@ -250,8 +274,10 @@ EXTCONST U8 PL_regkind[] = { /* ------------ 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 */ @@ -272,8 +298,6 @@ 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 */ @@ -291,9 +315,10 @@ 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 */ @@ -313,9 +338,15 @@ static const U8 regarglen[] = { 0, /* NBOUNDA */ 0, /* REG_ANY */ 0, /* SANY */ - EXTRA_SIZE(struct regnode_1), /* ANYOF */ - EXTRA_SIZE(struct regnode_1), /* ANYOFD */ - EXTRA_SIZE(struct regnode_1), /* ANYOFL */ + 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 */ @@ -327,14 +358,19 @@ static const U8 regarglen[] = { 0, /* CLUMP */ 0, /* BRANCH */ 0, /* EXACT */ + EXTRA_SIZE(struct regnode_1), /* LEXACT */ 0, /* EXACTL */ 0, /* EXACTF */ 0, /* EXACTFL */ 0, /* EXACTFU */ - 0, /* EXACTFA */ - 0, /* EXACTFU_SS */ + 0, /* EXACTFAA */ + 0, /* EXACTFUP */ 0, /* EXACTFLU8 */ - 0, /* EXACTFA_NO_TRIE */ + 0, /* EXACTFAA_NO_TRIE */ + 0, /* EXACT_REQ8 */ + EXTRA_SIZE(struct regnode_1), /* LEXACT_REQ8 */ + 0, /* EXACTFU_REQ8 */ + 0, /* EXACTFU_S_EDGE */ 0, /* NOTHING */ 0, /* TAIL */ 0, /* STAR */ @@ -346,16 +382,18 @@ 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), /* 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), /* 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 */ @@ -372,8 +410,7 @@ 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 */ @@ -415,6 +452,12 @@ static const char reg_off_by_arg[] = { 0, /* ANYOF */ 0, /* ANYOFD */ 0, /* ANYOFL */ + 0, /* ANYOFPOSIXL */ + 0, /* ANYOFH */ + 0, /* ANYOFHb */ + 0, /* ANYOFHr */ + 0, /* ANYOFM */ + 0, /* NANYOFM */ 0, /* POSIXD */ 0, /* POSIXL */ 0, /* POSIXU */ @@ -426,14 +469,19 @@ static const char reg_off_by_arg[] = { 0, /* CLUMP */ 0, /* BRANCH */ 0, /* EXACT */ + 0, /* LEXACT */ 0, /* EXACTL */ 0, /* EXACTF */ 0, /* EXACTFL */ 0, /* EXACTFU */ - 0, /* EXACTFA */ - 0, /* EXACTFU_SS */ + 0, /* EXACTFAA */ + 0, /* EXACTFUP */ 0, /* EXACTFLU8 */ - 0, /* EXACTFA_NO_TRIE */ + 0, /* EXACTFAA_NO_TRIE */ + 0, /* EXACT_REQ8 */ + 0, /* LEXACT_REQ8 */ + 0, /* EXACTFU_REQ8 */ + 0, /* EXACTFU_S_EDGE */ 0, /* NOTHING */ 0, /* TAIL */ 0, /* STAR */ @@ -445,20 +493,22 @@ 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, /* REFFA */ - 0, /* NREF */ - 0, /* NREFF */ - 0, /* NREFFL */ - 0, /* NREFFU */ - 0, /* NREFFA */ + 0, /* REFN */ + 0, /* REFFN */ + 0, /* REFFLN */ + 0, /* REFFUN */ + 0, /* REFFAN */ 1, /* LONGJMP */ 1, /* BRANCHJ */ - 2, /* IFMATCH */ - 2, /* UNLESSM */ + 1, /* IFMATCH */ + 1, /* UNLESSM */ 1, /* SUSPEND */ 1, /* IFTHEN */ 0, /* GROUPP */ @@ -471,8 +521,7 @@ 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 */ @@ -492,6 +541,7 @@ static const char reg_off_by_arg[] = { #endif /* REG_COMP_C */ + /* reg_name[] - Opcode/state names in string form, for debugging */ #ifndef DOINIT @@ -519,106 +569,118 @@ EXTCONST char * const PL_reg_name[] = { "ANYOF", /* 0x12 */ "ANYOFD", /* 0x13 */ "ANYOFL", /* 0x14 */ - "POSIXD", /* 0x15 */ - "POSIXL", /* 0x16 */ - "POSIXU", /* 0x17 */ - "POSIXA", /* 0x18 */ - "NPOSIXD", /* 0x19 */ - "NPOSIXL", /* 0x1a */ - "NPOSIXU", /* 0x1b */ - "NPOSIXA", /* 0x1c */ - "CLUMP", /* 0x1d */ - "BRANCH", /* 0x1e */ - "EXACT", /* 0x1f */ - "EXACTL", /* 0x20 */ - "EXACTF", /* 0x21 */ - "EXACTFL", /* 0x22 */ - "EXACTFU", /* 0x23 */ - "EXACTFA", /* 0x24 */ - "EXACTFU_SS", /* 0x25 */ - "EXACTFLU8", /* 0x26 */ - "EXACTFA_NO_TRIE", /* 0x27 */ - "NOTHING", /* 0x28 */ - "TAIL", /* 0x29 */ - "STAR", /* 0x2a */ - "PLUS", /* 0x2b */ - "CURLY", /* 0x2c */ - "CURLYN", /* 0x2d */ - "CURLYM", /* 0x2e */ - "CURLYX", /* 0x2f */ - "WHILEM", /* 0x30 */ - "OPEN", /* 0x31 */ - "CLOSE", /* 0x32 */ - "REF", /* 0x33 */ - "REFF", /* 0x34 */ - "REFFL", /* 0x35 */ - "REFFU", /* 0x36 */ - "REFFA", /* 0x37 */ - "NREF", /* 0x38 */ - "NREFF", /* 0x39 */ - "NREFFL", /* 0x3a */ - "NREFFU", /* 0x3b */ - "NREFFA", /* 0x3c */ - "LONGJMP", /* 0x3d */ - "BRANCHJ", /* 0x3e */ - "IFMATCH", /* 0x3f */ - "UNLESSM", /* 0x40 */ - "SUSPEND", /* 0x41 */ - "IFTHEN", /* 0x42 */ - "GROUPP", /* 0x43 */ - "EVAL", /* 0x44 */ - "MINMOD", /* 0x45 */ - "LOGICAL", /* 0x46 */ - "RENUM", /* 0x47 */ - "TRIE", /* 0x48 */ - "TRIEC", /* 0x49 */ - "AHOCORASICK", /* 0x4a */ - "AHOCORASICKC", /* 0x4b */ - "GOSUB", /* 0x4c */ - "GOSTART", /* 0x4d */ - "NGROUPP", /* 0x4e */ - "INSUBP", /* 0x4f */ - "DEFINEP", /* 0x50 */ - "ENDLIKE", /* 0x51 */ - "OPFAIL", /* 0x52 */ - "ACCEPT", /* 0x53 */ - "VERB", /* 0x54 */ - "PRUNE", /* 0x55 */ - "MARKPOINT", /* 0x56 */ - "SKIP", /* 0x57 */ - "COMMIT", /* 0x58 */ - "CUTGROUP", /* 0x59 */ - "KEEPS", /* 0x5a */ - "LNBREAK", /* 0x5b */ - "OPTIMIZED", /* 0x5c */ - "PSEUDO", /* 0x5d */ + "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 */ + "LEXACT", /* 0x26 */ + "EXACTL", /* 0x27 */ + "EXACTF", /* 0x28 */ + "EXACTFL", /* 0x29 */ + "EXACTFU", /* 0x2a */ + "EXACTFAA", /* 0x2b */ + "EXACTFUP", /* 0x2c */ + "EXACTFLU8", /* 0x2d */ + "EXACTFAA_NO_TRIE", /* 0x2e */ + "EXACT_REQ8", /* 0x2f */ + "LEXACT_REQ8", /* 0x30 */ + "EXACTFU_REQ8", /* 0x31 */ + "EXACTFU_S_EDGE", /* 0x32 */ + "NOTHING", /* 0x33 */ + "TAIL", /* 0x34 */ + "STAR", /* 0x35 */ + "PLUS", /* 0x36 */ + "CURLY", /* 0x37 */ + "CURLYN", /* 0x38 */ + "CURLYM", /* 0x39 */ + "CURLYX", /* 0x3a */ + "WHILEM", /* 0x3b */ + "OPEN", /* 0x3c */ + "CLOSE", /* 0x3d */ + "SROPEN", /* 0x3e */ + "SRCLOSE", /* 0x3f */ + "REF", /* 0x40 */ + "REFF", /* 0x41 */ + "REFFL", /* 0x42 */ + "REFFU", /* 0x43 */ + "REFFA", /* 0x44 */ + "REFN", /* 0x45 */ + "REFFN", /* 0x46 */ + "REFFLN", /* 0x47 */ + "REFFUN", /* 0x48 */ + "REFFAN", /* 0x49 */ + "LONGJMP", /* 0x4a */ + "BRANCHJ", /* 0x4b */ + "IFMATCH", /* 0x4c */ + "UNLESSM", /* 0x4d */ + "SUSPEND", /* 0x4e */ + "IFTHEN", /* 0x4f */ + "GROUPP", /* 0x50 */ + "EVAL", /* 0x51 */ + "MINMOD", /* 0x52 */ + "LOGICAL", /* 0x53 */ + "RENUM", /* 0x54 */ + "TRIE", /* 0x55 */ + "TRIEC", /* 0x56 */ + "AHOCORASICK", /* 0x57 */ + "AHOCORASICKC", /* 0x58 */ + "GOSUB", /* 0x59 */ + "GROUPPN", /* 0x5a */ + "INSUBP", /* 0x5b */ + "DEFINEP", /* 0x5c */ + "ENDLIKE", /* 0x5d */ + "OPFAIL", /* 0x5e */ + "ACCEPT", /* 0x5f */ + "VERB", /* 0x60 */ + "PRUNE", /* 0x61 */ + "MARKPOINT", /* 0x62 */ + "SKIP", /* 0x63 */ + "COMMIT", /* 0x64 */ + "CUTGROUP", /* 0x65 */ + "KEEPS", /* 0x66 */ + "LNBREAK", /* 0x67 */ + "OPTIMIZED", /* 0x68 */ + "PSEUDO", /* 0x69 */ /* ------------ 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 */ @@ -700,11 +762,12 @@ EXTCONST char * const PL_reg_intflags_name[] = { "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 12 +# define REG_INTFLAGS_NAME_SIZE 13 #endif /* The following have no fixed length. U8 so we can do strchr() on it. */ @@ -715,7 +778,7 @@ 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, + REFF, REFFL, REFFU, REFFA, REFN, REFFN, REFFLN, REFFUN, REFFAN, BRANCHJ, SUSPEND, IFTHEN, 0 }; @@ -725,7 +788,7 @@ EXTCONST U8 PL_varies[] __attribute__deprecated__ = { EXTCONST U8 PL_varies_bitmask[]; #else EXTCONST U8 PL_varies_bitmask[] = { - 0x00, 0x00, 0x00, 0x60, 0x00, 0xFC, 0xF9, 0x5F, 0x06, 0x00, 0x00, 0x00 + 0x00, 0x00, 0x00, 0x00, 0x18, 0x00, 0xE0, 0x0F, 0xFF, 0xCB, 0x00, 0x00, 0x00, 0x00 }; #endif /* DOINIT */ @@ -737,8 +800,9 @@ EXTCONST U8 PL_varies_bitmask[] = { EXTCONST U8 PL_simple[] __attribute__deprecated__; #else EXTCONST U8 PL_simple[] __attribute__deprecated__ = { - REG_ANY, SANY, ANYOF, ANYOFD, ANYOFL, POSIXD, POSIXL, POSIXU, POSIXA, - NPOSIXD, NPOSIXL, NPOSIXU, NPOSIXA, + REG_ANY, SANY, ANYOF, ANYOFD, ANYOFL, ANYOFPOSIXL, ANYOFH, ANYOFHb, + ANYOFHr, ANYOFM, NANYOFM, POSIXD, POSIXL, POSIXU, POSIXA, NPOSIXD, + NPOSIXL, NPOSIXU, NPOSIXA, 0 }; #endif /* DOINIT */ @@ -747,7 +811,7 @@ EXTCONST U8 PL_simple[] __attribute__deprecated__ = { EXTCONST U8 PL_simple_bitmask[]; #else EXTCONST U8 PL_simple_bitmask[] = { - 0x00, 0x00, 0xFF, 0x1F, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 + 0x00, 0x00, 0xFF, 0xFF, 0x07, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }; #endif /* DOINIT */