diff options
-rw-r--r-- | pod/perldebguts.pod | 2 | ||||
-rw-r--r-- | regcomp.c | 39 | ||||
-rw-r--r-- | regcomp.sym | 4 | ||||
-rw-r--r-- | regexec.c | 68 | ||||
-rw-r--r-- | regnodes.h | 341 | ||||
-rw-r--r-- | t/re/anyof.t | 70 |
6 files changed, 309 insertions, 215 deletions
diff --git a/pod/perldebguts.pod b/pod/perldebguts.pod index b7b3e54013..2a077e036d 100644 --- a/pod/perldebguts.pod +++ b/pod/perldebguts.pod @@ -626,6 +626,8 @@ will be lost. delta from the base lower 20; the flags field contains the lowest matchable UTF-8 start byte + ANYOFRb packed 1 Like ANYOFR, but all matches share the same + UTF-8 start byte, given in the flags field ANYOFM byte 1 Like ANYOF, but matches an invariant byte as determined by the mask and arg @@ -1588,7 +1588,7 @@ S_get_ANYOF_cp_list_for_ssc(pTHX_ const RExC_state_t *pRExC_state, unsigned int i; const U32 n = ARG(node); bool new_node_has_latin1 = FALSE; - const U8 flags = (inRANGE(OP(node), ANYOFH, ANYOFHr)) + const U8 flags = (inRANGE(OP(node), ANYOFH, ANYOFRb)) ? 0 : ANYOF_FLAGS(node); @@ -1643,7 +1643,7 @@ S_get_ANYOF_cp_list_for_ssc(pTHX_ const RExC_state_t *pRExC_state, } /* Add in the points from the bit map */ - if (! inRANGE(OP(node), ANYOFH, ANYOFHr)) { + if (! inRANGE(OP(node), ANYOFH, ANYOFRb)) { for (i = 0; i < NUM_ANYOF_CODE_POINTS; i++) { if (ANYOF_BITMAP_TEST(node, i)) { unsigned int start = i++; @@ -1730,7 +1730,7 @@ S_ssc_and(pTHX_ const RExC_state_t *pRExC_state, regnode_ssc *ssc, * another SSC or a regular ANYOF class. Can create false positives. */ SV* anded_cp_list; - U8 and_with_flags = inRANGE(OP(and_with), ANYOFH, ANYOFHr) + U8 and_with_flags = inRANGE(OP(and_with), ANYOFH, ANYOFRb) ? 0 : ANYOF_FLAGS(and_with); U8 anded_flags; @@ -1916,7 +1916,7 @@ S_ssc_or(pTHX_ const RExC_state_t *pRExC_state, regnode_ssc *ssc, SV* ored_cp_list; U8 ored_flags; - U8 or_with_flags = inRANGE(OP(or_with), ANYOFH, ANYOFHr) + U8 or_with_flags = inRANGE(OP(or_with), ANYOFH, ANYOFRb) ? 0 : ANYOF_FLAGS(or_with); @@ -5890,6 +5890,7 @@ Perl_re_printf( aTHX_ "LHS=%" UVuf " RHS=%" UVuf "\n", } case ANYOFR: + case ANYOFRb: { SV* cp_list = NULL; @@ -14980,7 +14981,7 @@ S_populate_ANYOF_from_invlist(pTHX_ regnode *node, SV** invlist_ptr) assert(PL_regkind[OP(node)] == ANYOF); /* There is no bitmap for this node type */ - if (inRANGE(OP(node), ANYOFH, ANYOFHr)) { + if (inRANGE(OP(node), ANYOFH, ANYOFRb)) { return; } @@ -19253,6 +19254,7 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state, I32 *flagp, U32 depth, { U8 low_utf8[UTF8_MAXBYTES+1]; + U8 high_utf8[UTF8_MAXBYTES+1]; ret = reganode(pRExC_state, ANYOFR, (start[0] | (end[0] - start[0]) << ANYOFR_BASE_BITS)); @@ -19261,7 +19263,22 @@ S_regclass(pTHX_ RExC_state_t *pRExC_state, I32 *flagp, U32 depth, * allow efficient ruling out at run time of many possible inputs. * */ (void) uvchr_to_utf8(low_utf8, start[0]); - ANYOF_FLAGS(REGNODE_p(ret)) = NATIVE_UTF8_TO_I8(low_utf8[0]); + (void) uvchr_to_utf8(high_utf8, end[0]); + + /* If all code points share the same first byte, this can be an + * ANYOFRb. Otherwise store the lowest UTF-8 start byte which can + * quickly rule out many inputs at run-time without having to + * compute the code point from UTF-8. For EBCDIC, we use I8, as + * not doing that transformation would not rule out nearly so many + * things */ + if (low_utf8[0] == high_utf8[0]) { + OP(REGNODE_p(ret)) = ANYOFRb; + ANYOF_FLAGS(REGNODE_p(ret)) = low_utf8[0]; + } + else { + ANYOF_FLAGS(REGNODE_p(ret)) + = NATIVE_UTF8_TO_I8(low_utf8[0]); + } goto not_anyof; } @@ -20670,7 +20687,7 @@ Perl_regprop(pTHX_ const regexp *prog, SV *sv, const regnode *o, const regmatch_ bool inverted; - if (inRANGE(OP(o), ANYOFH, ANYOFR)) { + if (inRANGE(OP(o), ANYOFH, ANYOFRb)) { flags = 0; bitmap = NULL; arg = 0; @@ -20694,7 +20711,7 @@ Perl_regprop(pTHX_ const regexp *prog, SV *sv, const regnode *o, const regmatch_ /* If there is stuff outside the bitmap, get it */ if (arg != ANYOF_ONLY_HAS_BITMAP) { - if (inRANGE(OP(o), ANYOFR, ANYOFR)) { + if (inRANGE(OP(o), ANYOFR, ANYOFRb)) { nonbitmap_invlist = _add_range_to_invlist(nonbitmap_invlist, ANYOFRbase(o), ANYOFRbase(o) + ANYOFRdelta(o)); @@ -20733,7 +20750,7 @@ Perl_regprop(pTHX_ const regexp *prog, SV *sv, const regnode *o, const regmatch_ /* ANYOFH by definition doesn't have anything that will fit inside the * bitmap; ANYOFR may or may not. */ if ( ! inRANGE(OP(o), ANYOFH, ANYOFHr) - && ( ! inRANGE(OP(o), ANYOFR, ANYOFR) + && ( ! inRANGE(OP(o), ANYOFR, ANYOFRb) || ANYOFRbase(o) < NUM_ANYOF_CODE_POINTS)) { /* Then all the things that could fit in the bitmap */ @@ -20749,7 +20766,7 @@ Perl_regprop(pTHX_ const regexp *prog, SV *sv, const regnode *o, const regmatch_ * are things that haven't * been resolved */ unresolved != NULL - || inRANGE(OP(o), ANYOFR, ANYOFR)); + || inRANGE(OP(o), ANYOFR, ANYOFRb)); SvREFCNT_dec(bitmap_range_not_in_bitmap); /* If there are user-defined properties which haven't been defined @@ -20835,7 +20852,7 @@ Perl_regprop(pTHX_ const regexp *prog, SV *sv, const regnode *o, const regmatch_ /* And finally the matching, closing ']' */ Perl_sv_catpvf(aTHX_ sv, "%s]", PL_colors[1]); - if (inRANGE(OP(o), ANYOFH, ANYOFR)) { + if (inRANGE(OP(o), ANYOFH, ANYOFRb)) { U8 lowest = (OP(o) != ANYOFHr) ? FLAGS(o) : LOWEST_ANYOF_HRx_BYTE(FLAGS(o)); diff --git a/regcomp.sym b/regcomp.sym index b664fc8f07..6ca83aeef1 100644 --- a/regcomp.sym +++ b/regcomp.sym @@ -82,7 +82,9 @@ ANYOFPOSIXL ANYOF, sv charclass_posixl S ; Like ANYOFL, but matches [[:p ANYOFH ANYOF, sv 1 S ; Like ANYOF, but only has "High" matches, none in the bitmap; the flags field contains the lowest matchable UTF-8 start byte ANYOFHb ANYOF, sv 1 S ; Like ANYOFH, but all matches share the same UTF-8 start byte, given in the flags field ANYOFHr ANYOF, sv 1 S ; Like ANYOFH, but the flags field contains packed bounds for all matchable UTF-8 start bytes. -ANYOFR ANYOFR, packed 1 S ; Matches any character in the range given by its packed args: upper 12 bits is the max delta from the base lower 20; the flags field contains the lowest matchable UTF-8 start byte +ANYOFR ANYOFR, packed 1 S ; Matches any character in the range given by its packed args: upper 12 bits is the max delta from the base lower 20; the flags field contains the lowest matchable UTF-8 start byte +ANYOFRb ANYOFR, packed 1 S ; Like ANYOFR, but all matches share the same UTF-8 start byte, given in the flags field +# There is no ANYOFRr because khw doesn't think there are likely to be real-world cases where such a large range is used. ANYOFM ANYOFM byte 1 S ; Like ANYOF, but matches an invariant byte as determined by the mask and arg NANYOFM ANYOFM byte 1 S ; complement of ANYOFM @@ -2220,6 +2220,24 @@ S_find_byclass(pTHX_ regexp * prog, const regnode *c, char *s, } break; + case ANYOFRb: + if (utf8_target) { + + /* We know what the first byte of any matched string should be */ + U8 first_byte = FLAGS(c); + + REXEC_FBC_FIND_NEXT_UTF8_BYTE_SCAN(first_byte, + withinCOUNT(utf8_to_uvchr_buf((U8 *) s, + (U8 *) strend, + NULL), + ANYOFRbase(c), ANYOFRdelta(c))); + } + else { + REXEC_FBC_CLASS_SCAN(0, withinCOUNT((U8) *s, + ANYOFRbase(c), ANYOFRdelta(c))); + } + break; + case EXACTFAA_NO_TRIE: /* This node only generated for non-utf8 patterns */ assert(! is_utf8_pat); /* FALLTHROUGH */ @@ -6914,6 +6932,31 @@ S_regmatch(pTHX_ regmatch_info *reginfo, char *startpos, regnode *prog) goto increment_locinput; break; + case ANYOFRb: + if (NEXTCHR_IS_EOS) { + sayNO; + } + + if (utf8_target) { + if ( ANYOF_FLAGS(scan) != (U8) *locinput + || ! withinCOUNT(utf8_to_uvchr_buf((U8 *) locinput, + (U8 *) reginfo->strend, + NULL), + ANYOFRbase(scan), ANYOFRdelta(scan))) + { + sayNO; + } + } + else { + if (! withinCOUNT((U8) *locinput, + ANYOFRbase(scan), ANYOFRdelta(scan))) + { + sayNO; + } + } + goto increment_locinput; + break; + /* The argument (FLAGS) to all the POSIX node types is the class number * */ @@ -9768,6 +9811,31 @@ S_regrepeat(pTHX_ regexp *prog, char **startposp, const regnode *p, } break; + case ANYOFRb: + if (utf8_target) { + while ( hardcount < max + && scan < this_eol + && (U8) *scan == ANYOF_FLAGS(p) + && withinCOUNT(utf8_to_uvchr_buf((U8 *) scan, + (U8 *) this_eol, + NULL), + ANYOFRbase(p), ANYOFRdelta(p))) + { + scan += UTF8SKIP(scan); + hardcount++; + } + } + else { + while ( hardcount < max + && scan < this_eol + && withinCOUNT((U8) *scan, ANYOFRbase(p), ANYOFRdelta(p))) + { + scan++; + hardcount++; + } + } + break; + /* The argument (FLAGS) to all the POSIX node types is the class number */ case NPOSIXL: diff --git a/regnodes.h b/regnodes.h index b7bf210f27..e902e99847 100644 --- a/regnodes.h +++ b/regnodes.h @@ -6,8 +6,8 @@ /* Regops and State definitions */ -#define REGNODE_MAX 106 -#define REGMATCH_STATE_MAX 146 +#define REGNODE_MAX 107 +#define REGMATCH_STATE_MAX 147 #define END 0 /* 0000 End of program. */ #define SUCCEED 1 /* 0x01 Return from a subroutine, basically. */ @@ -37,87 +37,88 @@ #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 ANYOFR 25 /* 0x19 Matches any character in the range given by its packed args: upper 12 bits is the max delta from the base lower 20; the flags field contains the lowest matchable UTF-8 start byte */ -#define ANYOFM 26 /* 0x1a Like ANYOF, but matches an invariant byte as determined by the mask and arg */ -#define NANYOFM 27 /* 0x1b complement of ANYOFM */ -#define POSIXD 28 /* 0x1c Some [[:class:]] under /d; the FLAGS field gives which one */ -#define POSIXL 29 /* 0x1d Some [[:class:]] under /l; the FLAGS field gives which one */ -#define POSIXU 30 /* 0x1e Some [[:class:]] under /u; the FLAGS field gives which one */ -#define POSIXA 31 /* 0x1f Some [[:class:]] under /a; the FLAGS field gives which one */ -#define NPOSIXD 32 /* 0x20 complement of POSIXD, [[:^class:]] */ -#define NPOSIXL 33 /* 0x21 complement of POSIXL, [[:^class:]] */ -#define NPOSIXU 34 /* 0x22 complement of POSIXU, [[:^class:]] */ -#define NPOSIXA 35 /* 0x23 complement of POSIXA, [[:^class:]] */ -#define CLUMP 36 /* 0x24 Match any extended grapheme cluster sequence */ -#define BRANCH 37 /* 0x25 Match this alternative, or the next... */ -#define EXACT 38 /* 0x26 Match this string (flags field is the length). */ -#define LEXACT 39 /* 0x27 Match this long string (preceded by length; flags unused). */ -#define EXACTL 40 /* 0x28 Like EXACT, but /l is in effect (used so locale-related warnings can be checked for) */ -#define EXACTF 41 /* 0x29 Like EXACT, but match using /id rules; (string not UTF-8, ASCII folded; non-ASCII not) */ -#define EXACTFL 42 /* 0x2a Like EXACT, but match using /il rules; (string not likely to be folded) */ -#define EXACTFU 43 /* 0x2b Like EXACT, but match using /iu rules; (string folded) */ -#define EXACTFAA 44 /* 0x2c Like EXACT, but match using /iaa rules; (string folded except in non-UTF8 patterns: MICRO, SHARP S; folded length <= unfolded) */ -#define EXACTFUP 45 /* 0x2d Like EXACT, but match using /iu rules; (string not UTF-8, folded except MICRO, SHARP S: hence Problematic) */ -#define EXACTFLU8 46 /* 0x2e Like EXACTFU, but use /il, UTF-8, (string is folded, and everything in it is above 255 */ -#define EXACTFAA_NO_TRIE 47 /* 0x2f Like EXACT, but match using /iaa rules (string not UTF-8, not guaranteed to be folded, not currently trie-able) */ -#define EXACT_REQ8 48 /* 0x30 Like EXACT, but only UTF-8 encoded targets can match */ -#define LEXACT_REQ8 49 /* 0x31 Like LEXACT, but only UTF-8 encoded targets can match */ -#define EXACTFU_REQ8 50 /* 0x32 Like EXACTFU, but only UTF-8 encoded targets can match */ -#define EXACTFU_S_EDGE 51 /* 0x33 /di rules, but nothing in it precludes /ui, except begins and/or ends with [Ss]; (string not UTF-8; compile-time only) */ -#define NOTHING 52 /* 0x34 Match empty string. */ -#define TAIL 53 /* 0x35 Match empty string. Can jump here from outside. */ -#define STAR 54 /* 0x36 Match this (simple) thing 0 or more times. */ -#define PLUS 55 /* 0x37 Match this (simple) thing 1 or more times. */ -#define CURLY 56 /* 0x38 Match this simple thing {n,m} times. */ -#define CURLYN 57 /* 0x39 Capture next-after-this simple thing */ -#define CURLYM 58 /* 0x3a Capture this medium-complex thing {n,m} times. */ -#define CURLYX 59 /* 0x3b Match this complex thing {n,m} times. */ -#define WHILEM 60 /* 0x3c Do curly processing and see if rest matches. */ -#define OPEN 61 /* 0x3d Mark this point in input as start of #n. */ -#define CLOSE 62 /* 0x3e Close corresponding OPEN of #n. */ -#define SROPEN 63 /* 0x3f Same as OPEN, but for script run */ -#define SRCLOSE 64 /* 0x40 Close preceding SROPEN */ -#define REF 65 /* 0x41 Match some already matched string */ -#define REFF 66 /* 0x42 Match already matched string, using /di rules. */ -#define REFFL 67 /* 0x43 Match already matched string, using /li rules. */ -#define REFFU 68 /* 0x44 Match already matched string, usng /ui. */ -#define REFFA 69 /* 0x45 Match already matched string, using /aai rules. */ -#define REFN 70 /* 0x46 Match some already matched string */ -#define REFFN 71 /* 0x47 Match already matched string, using /di rules. */ -#define REFFLN 72 /* 0x48 Match already matched string, using /li rules. */ -#define REFFUN 73 /* 0x49 Match already matched string, using /ui rules. */ -#define REFFAN 74 /* 0x4a Match already matched string, using /aai rules. */ -#define LONGJMP 75 /* 0x4b Jump far away. */ -#define BRANCHJ 76 /* 0x4c BRANCH with long offset. */ -#define IFMATCH 77 /* 0x4d Succeeds if the following matches; non-zero flags "f", next_off "o" means lookbehind assertion starting "f..(f-o)" characters before current */ -#define UNLESSM 78 /* 0x4e Fails if the following matches; non-zero flags "f", next_off "o" means lookbehind assertion starting "f..(f-o)" characters before current */ -#define SUSPEND 79 /* 0x4f "Independent" sub-RE. */ -#define IFTHEN 80 /* 0x50 Switch, should be preceded by switcher. */ -#define GROUPP 81 /* 0x51 Whether the group matched. */ -#define EVAL 82 /* 0x52 Execute some Perl code. */ -#define MINMOD 83 /* 0x53 Next operator is not greedy. */ -#define LOGICAL 84 /* 0x54 Next opcode should set the flag only. */ -#define RENUM 85 /* 0x55 Group with independently numbered parens. */ -#define TRIE 86 /* 0x56 Match many EXACT(F[ALU]?)? at once. flags==type */ -#define TRIEC 87 /* 0x57 Same as TRIE, but with embedded charclass data */ -#define AHOCORASICK 88 /* 0x58 Aho Corasick stclass. flags==type */ -#define AHOCORASICKC 89 /* 0x59 Same as AHOCORASICK, but with embedded charclass data */ -#define GOSUB 90 /* 0x5a recurse to paren arg1 at (signed) ofs arg2 */ -#define GROUPPN 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 (?!), but with verb arg */ -#define ACCEPT 96 /* 0x60 Accepts the current matched string, with verbar */ -#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 OPTIMIZED 105 /* 0x69 Placeholder for dump. */ -#define PSEUDO 106 /* 0x6a Pseudo opcode for internal use. */ +#define ANYOFRb 26 /* 0x1a Like ANYOFR, but all matches share the same UTF-8 start byte, given in the flags field */ +#define ANYOFM 27 /* 0x1b Like ANYOF, but matches an invariant byte as determined by the mask and arg */ +#define NANYOFM 28 /* 0x1c complement of ANYOFM */ +#define POSIXD 29 /* 0x1d Some [[:class:]] under /d; the FLAGS field gives which one */ +#define POSIXL 30 /* 0x1e Some [[:class:]] under /l; the FLAGS field gives which one */ +#define POSIXU 31 /* 0x1f Some [[:class:]] under /u; the FLAGS field gives which one */ +#define POSIXA 32 /* 0x20 Some [[:class:]] under /a; the FLAGS field gives which one */ +#define NPOSIXD 33 /* 0x21 complement of POSIXD, [[:^class:]] */ +#define NPOSIXL 34 /* 0x22 complement of POSIXL, [[:^class:]] */ +#define NPOSIXU 35 /* 0x23 complement of POSIXU, [[:^class:]] */ +#define NPOSIXA 36 /* 0x24 complement of POSIXA, [[:^class:]] */ +#define CLUMP 37 /* 0x25 Match any extended grapheme cluster sequence */ +#define BRANCH 38 /* 0x26 Match this alternative, or the next... */ +#define EXACT 39 /* 0x27 Match this string (flags field is the length). */ +#define LEXACT 40 /* 0x28 Match this long string (preceded by length; flags unused). */ +#define EXACTL 41 /* 0x29 Like EXACT, but /l is in effect (used so locale-related warnings can be checked for) */ +#define EXACTF 42 /* 0x2a Like EXACT, but match using /id rules; (string not UTF-8, ASCII folded; non-ASCII not) */ +#define EXACTFL 43 /* 0x2b Like EXACT, but match using /il rules; (string not likely to be folded) */ +#define EXACTFU 44 /* 0x2c Like EXACT, but match using /iu rules; (string folded) */ +#define EXACTFAA 45 /* 0x2d Like EXACT, but match using /iaa rules; (string folded except in non-UTF8 patterns: MICRO, SHARP S; folded length <= unfolded) */ +#define EXACTFUP 46 /* 0x2e Like EXACT, but match using /iu rules; (string not UTF-8, folded except MICRO, SHARP S: hence Problematic) */ +#define EXACTFLU8 47 /* 0x2f Like EXACTFU, but use /il, UTF-8, (string is folded, and everything in it is above 255 */ +#define EXACTFAA_NO_TRIE 48 /* 0x30 Like EXACT, but match using /iaa rules (string not UTF-8, not guaranteed to be folded, not currently trie-able) */ +#define EXACT_REQ8 49 /* 0x31 Like EXACT, but only UTF-8 encoded targets can match */ +#define LEXACT_REQ8 50 /* 0x32 Like LEXACT, but only UTF-8 encoded targets can match */ +#define EXACTFU_REQ8 51 /* 0x33 Like EXACTFU, but only UTF-8 encoded targets can match */ +#define EXACTFU_S_EDGE 52 /* 0x34 /di rules, but nothing in it precludes /ui, except begins and/or ends with [Ss]; (string not UTF-8; compile-time only) */ +#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 #n. */ +#define CLOSE 63 /* 0x3f Close corresponding OPEN of #n. */ +#define SROPEN 64 /* 0x40 Same as OPEN, but for script run */ +#define SRCLOSE 65 /* 0x41 Close preceding SROPEN */ +#define REF 66 /* 0x42 Match some already matched string */ +#define REFF 67 /* 0x43 Match already matched string, using /di rules. */ +#define REFFL 68 /* 0x44 Match already matched string, using /li rules. */ +#define REFFU 69 /* 0x45 Match already matched string, usng /ui. */ +#define REFFA 70 /* 0x46 Match already matched string, using /aai rules. */ +#define REFN 71 /* 0x47 Match some already matched string */ +#define REFFN 72 /* 0x48 Match already matched string, using /di rules. */ +#define REFFLN 73 /* 0x49 Match already matched string, using /li rules. */ +#define REFFUN 74 /* 0x4a Match already matched string, using /ui rules. */ +#define REFFAN 75 /* 0x4b Match already matched string, using /aai rules. */ +#define LONGJMP 76 /* 0x4c Jump far away. */ +#define BRANCHJ 77 /* 0x4d BRANCH with long offset. */ +#define IFMATCH 78 /* 0x4e Succeeds if the following matches; non-zero flags "f", next_off "o" means lookbehind assertion starting "f..(f-o)" characters before current */ +#define UNLESSM 79 /* 0x4f Fails if the following matches; non-zero flags "f", next_off "o" means lookbehind assertion starting "f..(f-o)" characters before current */ +#define SUSPEND 80 /* 0x50 "Independent" sub-RE. */ +#define IFTHEN 81 /* 0x51 Switch, should be preceded by switcher. */ +#define GROUPP 82 /* 0x52 Whether the group matched. */ +#define EVAL 83 /* 0x53 Execute some Perl code. */ +#define MINMOD 84 /* 0x54 Next operator is not greedy. */ +#define LOGICAL 85 /* 0x55 Next opcode should set the flag only. */ +#define RENUM 86 /* 0x56 Group with independently numbered parens. */ +#define TRIE 87 /* 0x57 Match many EXACT(F[ALU]?)? at once. flags==type */ +#define TRIEC 88 /* 0x58 Same as TRIE, but with embedded charclass data */ +#define AHOCORASICK 89 /* 0x59 Aho Corasick stclass. flags==type */ +#define AHOCORASICKC 90 /* 0x5a Same as AHOCORASICK, but with embedded charclass data */ +#define GOSUB 91 /* 0x5b recurse to paren arg1 at (signed) ofs arg2 */ +#define GROUPPN 92 /* 0x5c Whether the group matched. */ +#define INSUBP 93 /* 0x5d Whether we are in a specific recurse. */ +#define DEFINEP 94 /* 0x5e Never execute directly. */ +#define ENDLIKE 95 /* 0x5f Used only for the type field of verbs */ +#define OPFAIL 96 /* 0x60 Same as (?!), but with verb arg */ +#define ACCEPT 97 /* 0x61 Accepts the current matched string, with verbar */ +#define VERB 98 /* 0x62 Used only for the type field of verbs */ +#define PRUNE 99 /* 0x63 Pattern fails at this startpoint if no-backtracking through this */ +#define MARKPOINT 100 /* 0x64 Push the current location for rollback by cut. */ +#define SKIP 101 /* 0x65 On failure skip forward (to the mark) before retrying */ +#define COMMIT 102 /* 0x66 Pattern fails outright if backtracking through this */ +#define CUTGROUP 103 /* 0x67 On failure go to the next alternation in the group */ +#define KEEPS 104 /* 0x68 $& begins here. */ +#define LNBREAK 105 /* 0x69 generic newline pattern */ +#define OPTIMIZED 106 /* 0x6a Placeholder for dump. */ +#define PSEUDO 107 /* 0x6b 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 */ @@ -192,6 +193,7 @@ EXTCONST U8 PL_regkind[] = { ANYOF, /* ANYOFHb */ ANYOF, /* ANYOFHr */ ANYOFR, /* ANYOFR */ + ANYOFR, /* ANYOFRb */ ANYOFM, /* ANYOFM */ ANYOFM, /* NANYOFM */ POSIXD, /* POSIXD */ @@ -348,6 +350,7 @@ static const U8 regarglen[] = { EXTRA_SIZE(struct regnode_1), /* ANYOFHb */ EXTRA_SIZE(struct regnode_1), /* ANYOFHr */ EXTRA_SIZE(struct regnode_1), /* ANYOFR */ + EXTRA_SIZE(struct regnode_1), /* ANYOFRb */ EXTRA_SIZE(struct regnode_1), /* ANYOFM */ EXTRA_SIZE(struct regnode_1), /* NANYOFM */ 0, /* POSIXD */ @@ -460,6 +463,7 @@ static const char reg_off_by_arg[] = { 0, /* ANYOFHb */ 0, /* ANYOFHr */ 0, /* ANYOFR */ + 0, /* ANYOFRb */ 0, /* ANYOFM */ 0, /* NANYOFM */ 0, /* POSIXD */ @@ -578,87 +582,88 @@ EXTCONST char * const PL_reg_name[] = { "ANYOFHb", /* 0x17 */ "ANYOFHr", /* 0x18 */ "ANYOFR", /* 0x19 */ - "ANYOFM", /* 0x1a */ - "NANYOFM", /* 0x1b */ - "POSIXD", /* 0x1c */ - "POSIXL", /* 0x1d */ - "POSIXU", /* 0x1e */ - "POSIXA", /* 0x1f */ - "NPOSIXD", /* 0x20 */ - "NPOSIXL", /* 0x21 */ - "NPOSIXU", /* 0x22 */ - "NPOSIXA", /* 0x23 */ - "CLUMP", /* 0x24 */ - "BRANCH", /* 0x25 */ - "EXACT", /* 0x26 */ - "LEXACT", /* 0x27 */ - "EXACTL", /* 0x28 */ - "EXACTF", /* 0x29 */ - "EXACTFL", /* 0x2a */ - "EXACTFU", /* 0x2b */ - "EXACTFAA", /* 0x2c */ - "EXACTFUP", /* 0x2d */ - "EXACTFLU8", /* 0x2e */ - "EXACTFAA_NO_TRIE", /* 0x2f */ - "EXACT_REQ8", /* 0x30 */ - "LEXACT_REQ8", /* 0x31 */ - "EXACTFU_REQ8", /* 0x32 */ - "EXACTFU_S_EDGE", /* 0x33 */ - "NOTHING", /* 0x34 */ - "TAIL", /* 0x35 */ - "STAR", /* 0x36 */ - "PLUS", /* 0x37 */ - "CURLY", /* 0x38 */ - "CURLYN", /* 0x39 */ - "CURLYM", /* 0x3a */ - "CURLYX", /* 0x3b */ - "WHILEM", /* 0x3c */ - "OPEN", /* 0x3d */ - "CLOSE", /* 0x3e */ - "SROPEN", /* 0x3f */ - "SRCLOSE", /* 0x40 */ - "REF", /* 0x41 */ - "REFF", /* 0x42 */ - "REFFL", /* 0x43 */ - "REFFU", /* 0x44 */ - "REFFA", /* 0x45 */ - "REFN", /* 0x46 */ - "REFFN", /* 0x47 */ - "REFFLN", /* 0x48 */ - "REFFUN", /* 0x49 */ - "REFFAN", /* 0x4a */ - "LONGJMP", /* 0x4b */ - "BRANCHJ", /* 0x4c */ - "IFMATCH", /* 0x4d */ - "UNLESSM", /* 0x4e */ - "SUSPEND", /* 0x4f */ - "IFTHEN", /* 0x50 */ - "GROUPP", /* 0x51 */ - "EVAL", /* 0x52 */ - "MINMOD", /* 0x53 */ - "LOGICAL", /* 0x54 */ - "RENUM", /* 0x55 */ - "TRIE", /* 0x56 */ - "TRIEC", /* 0x57 */ - "AHOCORASICK", /* 0x58 */ - "AHOCORASICKC", /* 0x59 */ - "GOSUB", /* 0x5a */ - "GROUPPN", /* 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 */ - "OPTIMIZED", /* 0x69 */ - "PSEUDO", /* 0x6a */ + "ANYOFRb", /* 0x1a */ + "ANYOFM", /* 0x1b */ + "NANYOFM", /* 0x1c */ + "POSIXD", /* 0x1d */ + "POSIXL", /* 0x1e */ + "POSIXU", /* 0x1f */ + "POSIXA", /* 0x20 */ + "NPOSIXD", /* 0x21 */ + "NPOSIXL", /* 0x22 */ + "NPOSIXU", /* 0x23 */ + "NPOSIXA", /* 0x24 */ + "CLUMP", /* 0x25 */ + "BRANCH", /* 0x26 */ + "EXACT", /* 0x27 */ + "LEXACT", /* 0x28 */ + "EXACTL", /* 0x29 */ + "EXACTF", /* 0x2a */ + "EXACTFL", /* 0x2b */ + "EXACTFU", /* 0x2c */ + "EXACTFAA", /* 0x2d */ + "EXACTFUP", /* 0x2e */ + "EXACTFLU8", /* 0x2f */ + "EXACTFAA_NO_TRIE", /* 0x30 */ + "EXACT_REQ8", /* 0x31 */ + "LEXACT_REQ8", /* 0x32 */ + "EXACTFU_REQ8", /* 0x33 */ + "EXACTFU_S_EDGE", /* 0x34 */ + "NOTHING", /* 0x35 */ + "TAIL", /* 0x36 */ + "STAR", /* 0x37 */ + "PLUS", /* 0x38 */ + "CURLY", /* 0x39 */ + "CURLYN", /* 0x3a */ + "CURLYM", /* 0x3b */ + "CURLYX", /* 0x3c */ + "WHILEM", /* 0x3d */ + "OPEN", /* 0x3e */ + "CLOSE", /* 0x3f */ + "SROPEN", /* 0x40 */ + "SRCLOSE", /* 0x41 */ + "REF", /* 0x42 */ + "REFF", /* 0x43 */ + "REFFL", /* 0x44 */ + "REFFU", /* 0x45 */ + "REFFA", /* 0x46 */ + "REFN", /* 0x47 */ + "REFFN", /* 0x48 */ + "REFFLN", /* 0x49 */ + "REFFUN", /* 0x4a */ + "REFFAN", /* 0x4b */ + "LONGJMP", /* 0x4c */ + "BRANCHJ", /* 0x4d */ + "IFMATCH", /* 0x4e */ + "UNLESSM", /* 0x4f */ + "SUSPEND", /* 0x50 */ + "IFTHEN", /* 0x51 */ + "GROUPP", /* 0x52 */ + "EVAL", /* 0x53 */ + "MINMOD", /* 0x54 */ + "LOGICAL", /* 0x55 */ + "RENUM", /* 0x56 */ + "TRIE", /* 0x57 */ + "TRIEC", /* 0x58 */ + "AHOCORASICK", /* 0x59 */ + "AHOCORASICKC", /* 0x5a */ + "GOSUB", /* 0x5b */ + "GROUPPN", /* 0x5c */ + "INSUBP", /* 0x5d */ + "DEFINEP", /* 0x5e */ + "ENDLIKE", /* 0x5f */ + "OPFAIL", /* 0x60 */ + "ACCEPT", /* 0x61 */ + "VERB", /* 0x62 */ + "PRUNE", /* 0x63 */ + "MARKPOINT", /* 0x64 */ + "SKIP", /* 0x65 */ + "COMMIT", /* 0x66 */ + "CUTGROUP", /* 0x67 */ + "KEEPS", /* 0x68 */ + "LNBREAK", /* 0x69 */ + "OPTIMIZED", /* 0x6a */ + "PSEUDO", /* 0x6b */ /* ------------ States ------------- */ "TRIE_next", /* REGNODE_MAX +0x01 */ "TRIE_next_fail", /* REGNODE_MAX +0x02 */ @@ -793,7 +798,7 @@ EXTCONST U8 PL_varies[] __attribute__deprecated__ = { EXTCONST U8 PL_varies_bitmask[]; #else EXTCONST U8 PL_varies_bitmask[] = { - 0x00, 0x00, 0x00, 0x00, 0x30, 0x00, 0xC0, 0x1F, 0xFE, 0x97, 0x01, 0x00, 0x00, 0x00 + 0x00, 0x00, 0x00, 0x00, 0x60, 0x00, 0x80, 0x3F, 0xFC, 0x2F, 0x03, 0x00, 0x00, 0x00 }; #endif /* DOINIT */ @@ -806,8 +811,8 @@ EXTCONST U8 PL_simple[] __attribute__deprecated__; #else EXTCONST U8 PL_simple[] __attribute__deprecated__ = { REG_ANY, SANY, ANYOF, ANYOFD, ANYOFL, ANYOFPOSIXL, ANYOFH, ANYOFHb, - ANYOFHr, ANYOFR, ANYOFM, NANYOFM, POSIXD, POSIXL, POSIXU, POSIXA, - NPOSIXD, NPOSIXL, NPOSIXU, NPOSIXA, + ANYOFHr, ANYOFR, ANYOFRb, ANYOFM, NANYOFM, POSIXD, POSIXL, POSIXU, + POSIXA, NPOSIXD, NPOSIXL, NPOSIXU, NPOSIXA, 0 }; #endif /* DOINIT */ @@ -816,7 +821,7 @@ EXTCONST U8 PL_simple[] __attribute__deprecated__ = { EXTCONST U8 PL_simple_bitmask[]; #else EXTCONST U8 PL_simple_bitmask[] = { - 0x00, 0x00, 0xFF, 0xFF, 0x0F, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 + 0x00, 0x00, 0xFF, 0xFF, 0x1F, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }; #endif /* DOINIT */ diff --git a/t/re/anyof.t b/t/re/anyof.t index 2fa92cc0d9..9b9c030a18 100644 --- a/t/re/anyof.t +++ b/t/re/anyof.t @@ -487,19 +487,19 @@ my @tests = ( '[\x{102}\x{104}]' => 'ANYOFHb[0102 0104]', '[\x{102}-\x{104}{INFTY}]' => 'ANYOFH[0102-0104 INFTY-INFTY]', '[\x{102}-\x{104}{HIGHEST_CP}]' => 'ANYOFH[0102-0104 HIGHEST_CP]', - '[\x{102}-\x{104}\x{101}]' => 'ANYOFR[0101-0104]', + '[\x{102}-\x{104}\x{101}]' => 'ANYOFRb[0101-0104]', '[\x{102}-\x{104}\x{101}-{INFTY}]' => 'ANYOFH[0101-INFTY]', '[\x{102}-\x{104}\x{101}-{HIGHEST_CP}]' => 'ANYOFH[0101-HIGHEST_CP]', - '[\x{102}-\x{104}\x{102}]' => 'ANYOFR[0102-0104]', + '[\x{102}-\x{104}\x{102}]' => 'ANYOFRb[0102-0104]', '[\x{102}-\x{104}\x{102}-{INFTY}]' => 'ANYOFH[0102-INFTY]', '[\x{102}-\x{104}\x{102}-{HIGHEST_CP}]' => 'ANYOFH[0102-HIGHEST_CP]', - '[\x{102}-\x{104}\x{103}]' => 'ANYOFR[0102-0104]', + '[\x{102}-\x{104}\x{103}]' => 'ANYOFRb[0102-0104]', '[\x{102}-\x{104}\x{103}-{INFTY}]' => 'ANYOFH[0102-INFTY]', '[\x{102}-\x{104}\x{103}-{HIGHEST_CP}]' => 'ANYOFH[0102-HIGHEST_CP]', - '[\x{102}-\x{104}\x{104}]' => 'ANYOFR[0102-0104]', + '[\x{102}-\x{104}\x{104}]' => 'ANYOFRb[0102-0104]', '[\x{102}-\x{104}\x{104}-{INFTY}]' => 'ANYOFH[0102-INFTY]', '[\x{102}-\x{104}\x{104}-{HIGHEST_CP}]' => 'ANYOFH[0102-HIGHEST_CP]', - '[\x{102}-\x{104}\x{105}]' => 'ANYOFR[0102-0105]', + '[\x{102}-\x{104}\x{105}]' => 'ANYOFRb[0102-0105]', '[\x{102}-\x{104}\x{105}-{INFTY}]' => 'ANYOFH[0102-INFTY]', '[\x{102}-\x{104}\x{105}-{HIGHEST_CP}]' => 'ANYOFH[0102-HIGHEST_CP]', '[\x{102}-\x{104}\x{106}]' => 'ANYOFHb[0102-0104 0106]', @@ -515,11 +515,11 @@ my @tests = ( '[\x{102}-\x{104}\x{108}-\x{10A}\x{101}-\x{104}]' => 'ANYOFHb[0101-0104 0108-010A]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{101}-\x{105}]' => 'ANYOFHb[0101-0105 0108-010A]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{101}-\x{106}]' => 'ANYOFHb[0101-0106 0108-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{101}-\x{107}]' => 'ANYOFR[0101-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{101}-\x{108}]' => 'ANYOFR[0101-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{101}-\x{109}]' => 'ANYOFR[0101-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{101}-\x{10A}]' => 'ANYOFR[0101-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{101}-\x{10B}]' => 'ANYOFR[0101-010B]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{101}-\x{107}]' => 'ANYOFRb[0101-010A]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{101}-\x{108}]' => 'ANYOFRb[0101-010A]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{101}-\x{109}]' => 'ANYOFRb[0101-010A]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{101}-\x{10A}]' => 'ANYOFRb[0101-010A]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{101}-\x{10B}]' => 'ANYOFRb[0101-010B]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{102}]' => 'ANYOFHb[0102-0104 0108-010A]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{102}-{INFTY}]' => 'ANYOFH[0102-INFTY]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{102}-{HIGHEST_CP}]' => 'ANYOFH[0102-HIGHEST_CP]', @@ -528,45 +528,45 @@ my @tests = ( '[\x{102}-\x{104}\x{108}-\x{10A}\x{102}-\x{104}]' => 'ANYOFHb[0102-0104 0108-010A]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{102}-\x{105}]' => 'ANYOFHb[0102-0105 0108-010A]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{102}-\x{106}]' => 'ANYOFHb[0102-0106 0108-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{102}-\x{107}]' => 'ANYOFR[0102-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{102}-\x{108}]' => 'ANYOFR[0102-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{102}-\x{109}]' => 'ANYOFR[0102-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{102}-\x{10A}]' => 'ANYOFR[0102-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{102}-\x{10B}]' => 'ANYOFR[0102-010B]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{102}-\x{10C}]' => 'ANYOFR[0102-010C]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{102}-\x{107}]' => 'ANYOFRb[0102-010A]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{102}-\x{108}]' => 'ANYOFRb[0102-010A]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{102}-\x{109}]' => 'ANYOFRb[0102-010A]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{102}-\x{10A}]' => 'ANYOFRb[0102-010A]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{102}-\x{10B}]' => 'ANYOFRb[0102-010B]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{102}-\x{10C}]' => 'ANYOFRb[0102-010C]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{103}]' => 'ANYOFHb[0102-0104 0108-010A]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{103}-{INFTY}]' => 'ANYOFH[0102-INFTY]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{103}-{HIGHEST_CP}]' => 'ANYOFH[0102-HIGHEST_CP]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{103}-\x{104}]' => 'ANYOFHb[0102-0104 0108-010A]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{103}-\x{105}]' => 'ANYOFHb[0102-0105 0108-010A]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{103}-\x{106}]' => 'ANYOFHb[0102-0106 0108-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{103}-\x{107}]' => 'ANYOFR[0102-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{103}-\x{108}]' => 'ANYOFR[0102-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{103}-\x{109}]' => 'ANYOFR[0102-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{103}-\x{10A}]' => 'ANYOFR[0102-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{103}-\x{10B}]' => 'ANYOFR[0102-010B]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{103}-\x{10C}]' => 'ANYOFR[0102-010C]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{103}-\x{107}]' => 'ANYOFRb[0102-010A]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{103}-\x{108}]' => 'ANYOFRb[0102-010A]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{103}-\x{109}]' => 'ANYOFRb[0102-010A]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{103}-\x{10A}]' => 'ANYOFRb[0102-010A]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{103}-\x{10B}]' => 'ANYOFRb[0102-010B]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{103}-\x{10C}]' => 'ANYOFRb[0102-010C]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{104}]' => 'ANYOFHb[0102-0104 0108-010A]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{104}-{INFTY}]' => 'ANYOFH[0102-INFTY]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{104}-{HIGHEST_CP}]' => 'ANYOFH[0102-HIGHEST_CP]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{104}-\x{105}]' => 'ANYOFHb[0102-0105 0108-010A]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{104}-\x{106}]' => 'ANYOFHb[0102-0106 0108-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{104}-\x{107}]' => 'ANYOFR[0102-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{104}-\x{108}]' => 'ANYOFR[0102-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{104}-\x{109}]' => 'ANYOFR[0102-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{104}-\x{10A}]' => 'ANYOFR[0102-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{104}-\x{10B}]' => 'ANYOFR[0102-010B]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{104}-\x{10C}]' => 'ANYOFR[0102-010C]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{104}-\x{107}]' => 'ANYOFRb[0102-010A]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{104}-\x{108}]' => 'ANYOFRb[0102-010A]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{104}-\x{109}]' => 'ANYOFRb[0102-010A]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{104}-\x{10A}]' => 'ANYOFRb[0102-010A]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{104}-\x{10B}]' => 'ANYOFRb[0102-010B]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{104}-\x{10C}]' => 'ANYOFRb[0102-010C]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{105}]' => 'ANYOFHb[0102-0105 0108-010A]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{105}-{INFTY}]' => 'ANYOFH[0102-INFTY]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{105}-{HIGHEST_CP}]' => 'ANYOFH[0102-HIGHEST_CP]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{105}-\x{106}]' => 'ANYOFHb[0102-0106 0108-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{105}-\x{107}]' => 'ANYOFR[0102-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{105}-\x{108}]' => 'ANYOFR[0102-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{105}-\x{109}]' => 'ANYOFR[0102-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{105}-\x{10A}]' => 'ANYOFR[0102-010A]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{105}-\x{10B}]' => 'ANYOFR[0102-010B]', - '[\x{102}-\x{104}\x{108}-\x{10A}\x{105}-\x{10C}]' => 'ANYOFR[0102-010C]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{105}-\x{107}]' => 'ANYOFRb[0102-010A]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{105}-\x{108}]' => 'ANYOFRb[0102-010A]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{105}-\x{109}]' => 'ANYOFRb[0102-010A]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{105}-\x{10A}]' => 'ANYOFRb[0102-010A]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{105}-\x{10B}]' => 'ANYOFRb[0102-010B]', + '[\x{102}-\x{104}\x{108}-\x{10A}\x{105}-\x{10C}]' => 'ANYOFRb[0102-010C]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{106}]' => 'ANYOFHb[0102-0104 0106 0108-010A]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{106}-{INFTY}]' => 'ANYOFH[0102-0104 0106-INFTY]', '[\x{102}-\x{104}\x{108}-\x{10A}\x{106}-{HIGHEST_CP}]' => 'ANYOFH[0102-0104 0106-HIGHEST_CP]', @@ -583,7 +583,7 @@ my @tests = ( '[\x{102}-\x{104}\x{108}-\x{10A}\x{10B}]' => 'ANYOFHb[0102-0104 0108-010B]', '[\x{103}\x{102}]' => 'EXACTFU_REQ8 <\x{103}>', '[\x{104}\x{102}]' => 'ANYOFHb[0102 0104]', - '[\x{104}\x{102}\x{103}]' => 'ANYOFR[0102-0104]', + '[\x{104}\x{102}\x{103}]' => 'ANYOFRb[0102-0104]', '[\x{106}-{INFTY}\x{104}]' => 'ANYOFH[0104 0106-INFTY]', '[\x{106}-{INFTY}\x{104}-{INFTY}]' => 'ANYOFH[0104-INFTY]', '[\x{106}-{INFTY}\x{104}-{HIGHEST_CP}]' => 'ANYOFH[0104-INFTY]', |