# Exit points
- END no End of program.
- SUCCEED no Return from a subroutine, basically.
+ END no End of program.
+ SUCCEED no Return from a subroutine, basically.
# Anchors:
- BOL no Match "" at beginning of line.
- MBOL no Same, assuming multiline.
- SBOL no Same, assuming singleline.
- EOS no Match "" at end of string.
- EOL no Match "" at end of line.
- MEOL no Same, assuming multiline.
- SEOL no Same, assuming singleline.
- BOUND no Match "" at any word boundary using
- native charset semantics for non-utf8
- BOUNDL no Match "" at any locale word boundary
- BOUNDU no Match "" at any word boundary using
- Unicode semantics
- BOUNDA no Match "" at any word boundary using ASCII
- semantics
- NBOUND no Match "" at any word non-boundary using
- native charset semantics for non-utf8
- NBOUNDL no Match "" at any locale word non-boundary
- NBOUNDU no Match "" at any word non-boundary using
- Unicode semantics
- NBOUNDA no Match "" at any word non-boundary using
- ASCII semantics
- GPOS no Matches where last m//g left off.
+ BOL no Match "" at beginning of line.
+ MBOL no Same, assuming multiline.
+ SBOL no Same, assuming singleline.
+ EOS no Match "" at end of string.
+ EOL no Match "" at end of line.
+ MEOL no Same, assuming multiline.
+ SEOL no Same, assuming singleline.
+ BOUND no Match "" at any word boundary using native
+ charset semantics for non-utf8
+ BOUNDL no Match "" at any locale word boundary
+ BOUNDU no Match "" at any word boundary using Unicode
+ semantics
+ BOUNDA no Match "" at any word boundary using ASCII
+ semantics
+ NBOUND no Match "" at any word non-boundary using
+ native charset semantics for non-utf8
+ NBOUNDL no Match "" at any locale word non-boundary
+ NBOUNDU no Match "" at any word non-boundary using
+ Unicode semantics
+ NBOUNDA no Match "" at any word non-boundary using
+ ASCII semantics
+ GPOS no Matches where last m//g left off.
# [Special] alternatives:
- REG_ANY no Match any one character (except newline).
- SANY no Match any one character.
- CANY no Match any one byte.
- ANYOF sv Match character in (or not in) this
- class, single char match only
- ANYOF_WARN_SUPER sv Match character in (or not in) this
- class, warn (if enabled) upon matching a
- char above Unicode max;
- ANYOF_SYNTHETIC sv Synthetic start class
-
- POSIXD none Some [[:class:]] under /d; the FLAGS
- field gives which one
- POSIXL none Some [[:class:]] under /l; the FLAGS
- field gives which one
- POSIXU none Some [[:class:]] under /u; the FLAGS
- field gives which one
- POSIXA none Some [[:class:]] under /a; the FLAGS
- field gives which one
- NPOSIXD none complement of POSIXD, [[:^class:]]
- NPOSIXL none complement of POSIXL, [[:^class:]]
- NPOSIXU none complement of POSIXU, [[:^class:]]
- NPOSIXA none complement of POSIXA, [[:^class:]]
-
- CLUMP no Match any extended grapheme cluster
- sequence
+ REG_ANY no Match any one character (except newline).
+ SANY no Match any one character.
+ CANY no Match any one byte.
+ ANYOF sv Match character in (or not in) this class,
+ single char match only
+ ANYOF_WARN_SUPER sv Match character in (or not in) this class,
+ warn (if enabled) upon matching a char
+ above Unicode max;
+ ANYOF_SYNTHETIC sv Synthetic start class
+
+ POSIXD none Some [[:class:]] under /d; the FLAGS field
+ gives which one
+ POSIXL none Some [[:class:]] under /l; the FLAGS field
+ gives which one
+ POSIXU none Some [[:class:]] under /u; the FLAGS field
+ gives which one
+ POSIXA none Some [[:class:]] under /a; the FLAGS field
+ gives which one
+ NPOSIXD none complement of POSIXD, [[:^class:]]
+ NPOSIXL none complement of POSIXL, [[:^class:]]
+ NPOSIXU none complement of POSIXU, [[:^class:]]
+ NPOSIXA none complement of POSIXA, [[:^class:]]
+
+ CLUMP no Match any extended grapheme cluster
+ sequence
# Alternation
# pointer of each individual branch points; each branch
# starts with the operand node of a BRANCH node.
#
- BRANCH node Match this alternative, or the next...
+ BRANCH node Match this alternative, or the next...
# Back pointer
# BACK Normal "next" pointers all implicitly point forward;
# BACK exists to make loop structures possible.
# not used
- BACK no Match "", "next" ptr points backward.
+ BACK no Match "", "next" ptr points backward.
# Literals
- EXACT str Match this string (preceded by length).
- EXACTF str Match this non-UTF-8 string (not
- guaranteed to be folded) using /id rules
- (w/len).
- EXACTFL str Match this string (not guaranteed to be
- folded) using /il rules (w/len).
- EXACTFU str Match this string (folded iff in UTF-8,
- length in folding doesn't change if not
- in UTF-8) using /iu rules (w/len).
- EXACTFA str Match this string (not guaranteed to be
- folded) using /iaa rules (w/len).
- EXACTFU_SS str Match this string (folded iff in UTF-8,
- length in folding may change even if not
- in UTF-8) using /iu rules (w/len).
- EXACTFU_TRICKYFOLD str Match this folded UTF-8 string using /iu
- rules
+ EXACT str Match this string (preceded by length).
+ EXACTF str Match this non-UTF-8 string (not guaranteed
+ to be folded) using /id rules (w/len).
+ EXACTFL str Match this string (not guaranteed to be
+ folded) using /il rules (w/len).
+ EXACTFU str Match this string (folded iff in UTF-8,
+ length in folding doesn't change if not in
+ UTF-8) using /iu rules (w/len).
+ EXACTFA str Match this string (not guaranteed to be
+ folded) using /iaa rules (w/len).
+ EXACTFU_SS str Match this string (folded iff in UTF-8,
+ length in folding may change even if not in
+ UTF-8) using /iu rules (w/len).
# Do nothing types
- NOTHING no Match empty string.
+ NOTHING no Match empty string.
# A variant of above which delimits a group, thus stops optimizations
- TAIL no Match empty string. Can jump here from
- outside.
+ TAIL no Match empty string. Can jump here from
+ outside.
# Loops
# (one character per match) are implemented with STAR
# and PLUS for speed and to minimize recursive plunges.
#
- STAR node Match this (simple) thing 0 or more
- times.
- PLUS node Match this (simple) thing 1 or more
- times.
+ STAR node Match this (simple) thing 0 or more times.
+ PLUS node Match this (simple) thing 1 or more times.
- CURLY sv 2 Match this simple thing {n,m} times.
- CURLYN no 2 Capture next-after-this simple thing
- CURLYM no 2 Capture this medium-complex thing {n,m}
- times.
- CURLYX sv 2 Match this complex thing {n,m} times.
+ CURLY sv 2 Match this simple thing {n,m} times.
+ CURLYN no 2 Capture next-after-this simple thing
+ CURLYM no 2 Capture this medium-complex thing {n,m}
+ times.
+ CURLYX sv 2 Match this complex thing {n,m} times.
# This terminator creates a loop structure for CURLYX
- WHILEM no Do curly processing and see if rest
- matches.
+ WHILEM no Do curly processing and see if rest
+ matches.
# Buffer related
# OPEN,CLOSE,GROUPP ...are numbered at compile time.
- OPEN num 1 Mark this point in input as start of #n.
- CLOSE num 1 Analogous to OPEN.
-
- REF num 1 Match some already matched string
- REFF num 1 Match already matched string, folded
- using native charset semantics for non-
- utf8
- REFFL num 1 Match already matched string, folded in
- loc.
- REFFU num 1 Match already matched string, folded
- using unicode semantics for non-utf8
- REFFA num 1 Match already matched string, folded
- using unicode semantics for non-utf8, no
- mixing ASCII, non-ASCII
+ OPEN num 1 Mark this point in input as start of #n.
+ CLOSE num 1 Analogous to OPEN.
+
+ REF num 1 Match some already matched string
+ REFF num 1 Match already matched string, folded using
+ native charset semantics for non-utf8
+ REFFL num 1 Match already matched string, folded in
+ loc.
+ REFFU num 1 Match already matched string, folded using
+ unicode semantics for non-utf8
+ REFFA num 1 Match already matched string, folded using
+ unicode semantics for non-utf8, no mixing
+ ASCII, non-ASCII
# Named references. Code in regcomp.c assumes that these all are after
# the numbered references
- NREF no-sv 1 Match some already matched string
- NREFF no-sv 1 Match already matched string, folded
- using native charset semantics for non-
- utf8
- NREFFL no-sv 1 Match already matched string, folded in
- loc.
- NREFFU num 1 Match already matched string, folded
- using unicode semantics for non-utf8
- NREFFA num 1 Match already matched string, folded
- using unicode semantics for non-utf8, no
- mixing ASCII, non-ASCII
-
- IFMATCH off 1 2 Succeeds if the following matches.
- UNLESSM off 1 2 Fails if the following matches.
- SUSPEND off 1 1 "Independent" sub-RE.
- IFTHEN off 1 1 Switch, should be preceded by switcher.
- GROUPP num 1 Whether the group matched.
+ NREF no-sv 1 Match some already matched string
+ NREFF no-sv 1 Match already matched string, folded using
+ native charset semantics for non-utf8
+ NREFFL no-sv 1 Match already matched string, folded in
+ loc.
+ NREFFU num 1 Match already matched string, folded using
+ unicode semantics for non-utf8
+ NREFFA num 1 Match already matched string, folded using
+ unicode semantics for non-utf8, no mixing
+ ASCII, non-ASCII
+
+ IFMATCH off 1 2 Succeeds if the following matches.
+ UNLESSM off 1 2 Fails if the following matches.
+ SUSPEND off 1 1 "Independent" sub-RE.
+ IFTHEN off 1 1 Switch, should be preceded by switcher.
+ GROUPP num 1 Whether the group matched.
# Support for long RE
- LONGJMP off 1 1 Jump far away.
- BRANCHJ off 1 1 BRANCH with long offset.
+ LONGJMP off 1 1 Jump far away.
+ BRANCHJ off 1 1 BRANCH with long offset.
# The heavy worker
- EVAL evl 1 Execute some Perl code.
+ EVAL evl 1 Execute some Perl code.
# Modifiers
- MINMOD no Next operator is not greedy.
- LOGICAL no Next opcode should set the flag only.
+ MINMOD no Next operator is not greedy.
+ LOGICAL no Next opcode should set the flag only.
# This is not used yet
- RENUM off 1 1 Group with independently numbered parens.
+ RENUM off 1 1 Group with independently numbered parens.
# Trie Related
# have inline charclass data (ascii only), the 'C' store it in the
# structure.
- TRIE trie 1 Match many EXACT(F[ALU]?)? at once.
- flags==type
- TRIEC trie Same as TRIE, but with embedded charclass
- charclass data
+ TRIE trie 1 Match many EXACT(F[ALU]?)? at once.
+ flags==type
+ TRIEC trie Same as TRIE, but with embedded charclass
+ charclass data
- AHOCORASICK trie 1 Aho Corasick stclass. flags==type
- AHOCORASICKC trie Same as AHOCORASICK, but with embedded
- charclass charclass data
+ AHOCORASICK trie 1 Aho Corasick stclass. flags==type
+ AHOCORASICKC trie Same as AHOCORASICK, but with embedded
+ charclass charclass data
# Regex Subroutines
- GOSUB num/ofs 2L recurse to paren arg1 at (signed) ofs
- arg2
- GOSTART no recurse to start of pattern
+ GOSUB num/ofs 2L recurse to paren arg1 at (signed) ofs arg2
+ GOSTART no recurse to start of pattern
# Special conditionals
- NGROUPP no-sv 1 Whether the group matched.
- INSUBP num 1 Whether we are in a specific recurse.
- DEFINEP none 1 Never execute directly.
+ NGROUPP no-sv 1 Whether the group matched.
+ INSUBP num 1 Whether we are in a specific recurse.
+ DEFINEP none 1 Never execute directly.
# Backtracking Verbs
- ENDLIKE none Used only for the type field of verbs
- OPFAIL none Same as (?!)
- ACCEPT parno 1 Accepts the current matched string.
+ ENDLIKE none Used only for the type field of verbs
+ OPFAIL none Same as (?!)
+ ACCEPT parno 1 Accepts the current matched string.
# Verbs With Arguments
- VERB no-sv 1 Used only for the type field of verbs
- PRUNE no-sv 1 Pattern fails at this startpoint if no-
- backtracking through this
- MARKPOINT no-sv 1 Push the current location for rollback by
- cut.
- SKIP no-sv 1 On failure skip forward (to the mark)
- before retrying
- COMMIT no-sv 1 Pattern fails outright if backtracking
- through this
- CUTGROUP no-sv 1 On failure go to the next alternation in
- the group
+ VERB no-sv 1 Used only for the type field of verbs
+ PRUNE no-sv 1 Pattern fails at this startpoint if no-
+ backtracking through this
+ MARKPOINT no-sv 1 Push the current location for rollback by
+ cut.
+ SKIP no-sv 1 On failure skip forward (to the mark)
+ before retrying
+ COMMIT no-sv 1 Pattern fails outright if backtracking
+ through this
+ CUTGROUP no-sv 1 On failure go to the next alternation in
+ the group
# Control what to keep in $&.
- KEEPS no $& begins here.
+ KEEPS no $& begins here.
# New charclass like patterns
- LNBREAK none generic newline pattern
+ LNBREAK none generic newline pattern
# SPECIAL REGOPS
# This is not really a node, but an optimized away piece of a "long"
# node. To simplify debugging output, we mark it as if it were a node
- OPTIMIZED off Placeholder for dump.
+ OPTIMIZED off Placeholder for dump.
# Special opcode with the property that no opcode in a compiled program
# will ever be of this type. Thus it can be used as a flag value that
# no other opcode has been seen. END is used similarly, in that an END
# node cant be optimized. So END implies "unoptimizable" and PSEUDO
# mean "not seen anything to optimize yet".
- PSEUDO off Pseudo opcode for internal use.
+ PSEUDO off Pseudo opcode for internal use.
=for regcomp.pl end
case EXACT: break;
case EXACTFA:
case EXACTFU_SS:
- case EXACTFU_TRICKYFOLD:
case EXACTFU: folder = PL_fold_latin1; break;
case EXACTF: folder = PL_fold; break;
case EXACTFL: folder = PL_fold_locale; break;
} else if (maxbytes > trie->maxlen) {
trie->maxlen = maxbytes;
}
- if (OP( noper ) == EXACTFU_SS) {
- /* XXX: workaround - 'ss' could match "\x{DF}" so minlen could be 1 and not 2*/
- if (trie->minlen > 1)
- trie->minlen= 1;
- }
- if (OP( noper ) == EXACTFU_TRICKYFOLD) {
- /* XXX: workround - things like "\x{1FBE}\x{0308}\x{0301}" can match "\x{0390}"
- * - We assume that any such sequence might match a 2 byte string */
- if (trie->minlen > 2 )
- trie->minlen= 2;
- }
-
} /* end first pass */
DEBUG_TRIE_COMPILE_r(
PerlIO_printf( Perl_debug_log, "%*sTRIE(%s): W:%d C:%d Uq:%d Min:%d Max:%d\n",
* that is "sss".
*
* It turns out that there are problems with all multi-character folds, and not
- * just these three. Now the code is general, for all such cases, but the
- * three still have some special handling. The approach taken is:
+ * just these three. Now the code is general, for all such cases. The
+ * approach taken is:
* 1) This routine examines each EXACTFish node that could contain multi-
* character fold sequences. It returns in *min_subtract how much to
* subtract from the the actual length of the string to get a real minimum
* used by the caller to adjust the min length of the match, and the delta
* between min and max, so that the optimizer doesn't reject these
* possibilities based on size constraints.
- * 2) Certain of these sequences require special handling by the trie code,
- * so, if found, this code changes the joined node type to special ops:
- * EXACTFU_TRICKYFOLD and EXACTFU_SS.
- * 3) For the sequence involving the Sharp s (\xDF), the node type EXACTFU_SS
+ * 2) For the sequence involving the Sharp s (\xDF), the node type EXACTFU_SS
* is used for an EXACTFU node that contains at least one "ss" sequence in
* it. For non-UTF-8 patterns and strings, this is the only case where
* there is a possible fold length change. That means that a regular
OP(scan) = EXACTFU_SS;
s += 2;
}
- else if (len == 6 /* len is the same in both ASCII and EBCDIC
- for these */
- && (memEQ(s, GREEK_SMALL_LETTER_IOTA_UTF8
- COMBINING_DIAERESIS_UTF8
- COMBINING_ACUTE_ACCENT_UTF8,
- 6)
- || memEQ(s, GREEK_SMALL_LETTER_UPSILON_UTF8
- COMBINING_DIAERESIS_UTF8
- COMBINING_ACUTE_ACCENT_UTF8,
- 6)))
- {
- count = 3;
-
- /* These two folds require special handling by trie's, so
- * change the node type to indicate this. If EXACTFA and
- * EXACTFL were ever to be handled by trie's, this would
- * have to be changed. If this node has already been
- * changed to EXACTFU_SS in this loop, leave it as is. (I
- * (khw) think it doesn't matter in regexec.c for UTF
- * patterns, but no need to change it */
- if (OP(scan) == EXACTFU) {
- OP(scan) = EXACTFU_TRICKYFOLD;
- }
- s += 6;
- }
else { /* Here is a generic multi-char fold. */
const U8* multi_end = s + len;
EXACT | EXACT
EXACTFU | EXACTFU
EXACTFU_SS | EXACTFU
- EXACTFU_TRICKYFOLD | EXACTFU
EXACTFA | 0
*/
#define TRIE_TYPE(X) ( ( NOTHING == (X) ) ? NOTHING : \
( EXACT == (X) ) ? EXACT : \
- ( EXACTFU == (X) || EXACTFU_SS == (X) || EXACTFU_TRICKYFOLD == (X) ) ? EXACTFU : \
+ ( EXACTFU == (X) || EXACTFU_SS == (X) ) ? EXACTFU : \
0 )
/* dont use tail as the end marker for this traverse */
case EXACTFA:
case EXACTFU:
case EXACTFU_SS:
- case EXACTFU_TRICKYFOLD:
case EXACTFL:
if( exact == PSEUDO )
exact= OP(scan);
/* Regops and State definitions */
-#define REGNODE_MAX 95
-#define REGMATCH_STATE_MAX 135
+#define REGNODE_MAX 94
+#define REGMATCH_STATE_MAX 134
#define END 0 /* 0000 End of program. */
#define SUCCEED 1 /* 0x01 Return from a subroutine, basically. */
#define EXACTFU 38 /* 0x26 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 39 /* 0x27 Match this string (not guaranteed to be folded) using /iaa rules (w/len). */
#define EXACTFU_SS 40 /* 0x28 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 EXACTFU_TRICKYFOLD 41 /* 0x29 Match this folded UTF-8 string using /iu rules */
-#define NOTHING 42 /* 0x2a Match empty string. */
-#define TAIL 43 /* 0x2b Match empty string. Can jump here from outside. */
-#define STAR 44 /* 0x2c Match this (simple) thing 0 or more times. */
-#define PLUS 45 /* 0x2d Match this (simple) thing 1 or more times. */
-#define CURLY 46 /* 0x2e Match this simple thing {n,m} times. */
-#define CURLYN 47 /* 0x2f Capture next-after-this simple thing */
-#define CURLYM 48 /* 0x30 Capture this medium-complex thing {n,m} times. */
-#define CURLYX 49 /* 0x31 Match this complex thing {n,m} times. */
-#define WHILEM 50 /* 0x32 Do curly processing and see if rest matches. */
-#define OPEN 51 /* 0x33 Mark this point in input as start of #n. */
-#define CLOSE 52 /* 0x34 Analogous to OPEN. */
-#define REF 53 /* 0x35 Match some already matched string */
-#define REFF 54 /* 0x36 Match already matched string, folded using native charset semantics for non-utf8 */
-#define REFFL 55 /* 0x37 Match already matched string, folded in loc. */
-#define REFFU 56 /* 0x38 Match already matched string, folded using unicode semantics for non-utf8 */
-#define REFFA 57 /* 0x39 Match already matched string, folded using unicode semantics for non-utf8, no mixing ASCII, non-ASCII */
-#define NREF 58 /* 0x3a Match some already matched string */
-#define NREFF 59 /* 0x3b Match already matched string, folded using native charset semantics for non-utf8 */
-#define NREFFL 60 /* 0x3c Match already matched string, folded in loc. */
-#define NREFFU 61 /* 0x3d Match already matched string, folded using unicode semantics for non-utf8 */
-#define NREFFA 62 /* 0x3e Match already matched string, folded using unicode semantics for non-utf8, no mixing ASCII, non-ASCII */
-#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 LONGJMP 68 /* 0x44 Jump far away. */
-#define BRANCHJ 69 /* 0x45 BRANCH with long offset. */
-#define EVAL 70 /* 0x46 Execute some Perl code. */
-#define MINMOD 71 /* 0x47 Next operator is not greedy. */
-#define LOGICAL 72 /* 0x48 Next opcode should set the flag only. */
-#define RENUM 73 /* 0x49 Group with independently numbered parens. */
-#define TRIE 74 /* 0x4a Match many EXACT(F[ALU]?)? at once. flags==type */
-#define TRIEC 75 /* 0x4b Same as TRIE, but with embedded charclass data */
-#define AHOCORASICK 76 /* 0x4c Aho Corasick stclass. flags==type */
-#define AHOCORASICKC 77 /* 0x4d Same as AHOCORASICK, but with embedded charclass data */
-#define GOSUB 78 /* 0x4e recurse to paren arg1 at (signed) ofs arg2 */
-#define GOSTART 79 /* 0x4f recurse to start of pattern */
-#define NGROUPP 80 /* 0x50 Whether the group matched. */
-#define INSUBP 81 /* 0x51 Whether we are in a specific recurse. */
-#define DEFINEP 82 /* 0x52 Never execute directly. */
-#define ENDLIKE 83 /* 0x53 Used only for the type field of verbs */
-#define OPFAIL 84 /* 0x54 Same as (?!) */
-#define ACCEPT 85 /* 0x55 Accepts the current matched string. */
-#define VERB 86 /* 0x56 Used only for the type field of verbs */
-#define PRUNE 87 /* 0x57 Pattern fails at this startpoint if no-backtracking through this */
-#define MARKPOINT 88 /* 0x58 Push the current location for rollback by cut. */
-#define SKIP 89 /* 0x59 On failure skip forward (to the mark) before retrying */
-#define COMMIT 90 /* 0x5a Pattern fails outright if backtracking through this */
-#define CUTGROUP 91 /* 0x5b On failure go to the next alternation in the group */
-#define KEEPS 92 /* 0x5c $& begins here. */
-#define LNBREAK 93 /* 0x5d generic newline pattern */
-#define OPTIMIZED 94 /* 0x5e Placeholder for dump. */
-#define PSEUDO 95 /* 0x5f Pseudo opcode for internal use. */
+#define NOTHING 41 /* 0x29 Match empty string. */
+#define TAIL 42 /* 0x2a Match empty string. Can jump here from outside. */
+#define STAR 43 /* 0x2b Match this (simple) thing 0 or more times. */
+#define PLUS 44 /* 0x2c Match this (simple) thing 1 or more times. */
+#define CURLY 45 /* 0x2d Match this simple thing {n,m} times. */
+#define CURLYN 46 /* 0x2e Capture next-after-this simple thing */
+#define CURLYM 47 /* 0x2f Capture this medium-complex thing {n,m} times. */
+#define CURLYX 48 /* 0x30 Match this complex thing {n,m} times. */
+#define WHILEM 49 /* 0x31 Do curly processing and see if rest matches. */
+#define OPEN 50 /* 0x32 Mark this point in input as start of #n. */
+#define CLOSE 51 /* 0x33 Analogous to OPEN. */
+#define REF 52 /* 0x34 Match some already matched string */
+#define REFF 53 /* 0x35 Match already matched string, folded using native charset semantics for non-utf8 */
+#define REFFL 54 /* 0x36 Match already matched string, folded in loc. */
+#define REFFU 55 /* 0x37 Match already matched string, folded using unicode semantics for non-utf8 */
+#define REFFA 56 /* 0x38 Match already matched string, folded using unicode semantics for non-utf8, no mixing ASCII, non-ASCII */
+#define NREF 57 /* 0x39 Match some already matched string */
+#define NREFF 58 /* 0x3a Match already matched string, folded using native charset semantics for non-utf8 */
+#define NREFFL 59 /* 0x3b Match already matched string, folded in loc. */
+#define NREFFU 60 /* 0x3c Match already matched string, folded using unicode semantics for non-utf8 */
+#define NREFFA 61 /* 0x3d Match already matched string, folded using unicode semantics for non-utf8, no mixing ASCII, non-ASCII */
+#define IFMATCH 62 /* 0x3e Succeeds if the following matches. */
+#define UNLESSM 63 /* 0x3f Fails if the following matches. */
+#define SUSPEND 64 /* 0x40 "Independent" sub-RE. */
+#define IFTHEN 65 /* 0x41 Switch, should be preceded by switcher. */
+#define GROUPP 66 /* 0x42 Whether the group matched. */
+#define LONGJMP 67 /* 0x43 Jump far away. */
+#define BRANCHJ 68 /* 0x44 BRANCH with long offset. */
+#define EVAL 69 /* 0x45 Execute some Perl code. */
+#define MINMOD 70 /* 0x46 Next operator is not greedy. */
+#define LOGICAL 71 /* 0x47 Next opcode should set the flag only. */
+#define RENUM 72 /* 0x48 Group with independently numbered parens. */
+#define TRIE 73 /* 0x49 Match many EXACT(F[ALU]?)? at once. flags==type */
+#define TRIEC 74 /* 0x4a Same as TRIE, but with embedded charclass data */
+#define AHOCORASICK 75 /* 0x4b Aho Corasick stclass. flags==type */
+#define AHOCORASICKC 76 /* 0x4c Same as AHOCORASICK, but with embedded charclass data */
+#define GOSUB 77 /* 0x4d recurse to paren arg1 at (signed) ofs arg2 */
+#define GOSTART 78 /* 0x4e recurse to start of pattern */
+#define NGROUPP 79 /* 0x4f Whether the group matched. */
+#define INSUBP 80 /* 0x50 Whether we are in a specific recurse. */
+#define DEFINEP 81 /* 0x51 Never execute directly. */
+#define ENDLIKE 82 /* 0x52 Used only for the type field of verbs */
+#define OPFAIL 83 /* 0x53 Same as (?!) */
+#define ACCEPT 84 /* 0x54 Accepts the current matched string. */
+#define VERB 85 /* 0x55 Used only for the type field of verbs */
+#define PRUNE 86 /* 0x56 Pattern fails at this startpoint if no-backtracking through this */
+#define MARKPOINT 87 /* 0x57 Push the current location for rollback by cut. */
+#define SKIP 88 /* 0x58 On failure skip forward (to the mark) before retrying */
+#define COMMIT 89 /* 0x59 Pattern fails outright if backtracking through this */
+#define CUTGROUP 90 /* 0x5a On failure go to the next alternation in the group */
+#define KEEPS 91 /* 0x5b $& begins here. */
+#define LNBREAK 92 /* 0x5c generic newline pattern */
+#define OPTIMIZED 93 /* 0x5d Placeholder for dump. */
+#define PSEUDO 94 /* 0x5e 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 */
EXACT, /* EXACTFU */
EXACT, /* EXACTFA */
EXACT, /* EXACTFU_SS */
- EXACT, /* EXACTFU_TRICKYFOLD */
NOTHING, /* NOTHING */
NOTHING, /* TAIL */
STAR, /* STAR */
0, /* EXACTFU */
0, /* EXACTFA */
0, /* EXACTFU_SS */
- 0, /* EXACTFU_TRICKYFOLD */
0, /* NOTHING */
0, /* TAIL */
0, /* STAR */
0, /* EXACTFU */
0, /* EXACTFA */
0, /* EXACTFU_SS */
- 0, /* EXACTFU_TRICKYFOLD */
0, /* NOTHING */
0, /* TAIL */
0, /* STAR */
"EXACTFU", /* 0x26 */
"EXACTFA", /* 0x27 */
"EXACTFU_SS", /* 0x28 */
- "EXACTFU_TRICKYFOLD", /* 0x29 */
- "NOTHING", /* 0x2a */
- "TAIL", /* 0x2b */
- "STAR", /* 0x2c */
- "PLUS", /* 0x2d */
- "CURLY", /* 0x2e */
- "CURLYN", /* 0x2f */
- "CURLYM", /* 0x30 */
- "CURLYX", /* 0x31 */
- "WHILEM", /* 0x32 */
- "OPEN", /* 0x33 */
- "CLOSE", /* 0x34 */
- "REF", /* 0x35 */
- "REFF", /* 0x36 */
- "REFFL", /* 0x37 */
- "REFFU", /* 0x38 */
- "REFFA", /* 0x39 */
- "NREF", /* 0x3a */
- "NREFF", /* 0x3b */
- "NREFFL", /* 0x3c */
- "NREFFU", /* 0x3d */
- "NREFFA", /* 0x3e */
- "IFMATCH", /* 0x3f */
- "UNLESSM", /* 0x40 */
- "SUSPEND", /* 0x41 */
- "IFTHEN", /* 0x42 */
- "GROUPP", /* 0x43 */
- "LONGJMP", /* 0x44 */
- "BRANCHJ", /* 0x45 */
- "EVAL", /* 0x46 */
- "MINMOD", /* 0x47 */
- "LOGICAL", /* 0x48 */
- "RENUM", /* 0x49 */
- "TRIE", /* 0x4a */
- "TRIEC", /* 0x4b */
- "AHOCORASICK", /* 0x4c */
- "AHOCORASICKC", /* 0x4d */
- "GOSUB", /* 0x4e */
- "GOSTART", /* 0x4f */
- "NGROUPP", /* 0x50 */
- "INSUBP", /* 0x51 */
- "DEFINEP", /* 0x52 */
- "ENDLIKE", /* 0x53 */
- "OPFAIL", /* 0x54 */
- "ACCEPT", /* 0x55 */
- "VERB", /* 0x56 */
- "PRUNE", /* 0x57 */
- "MARKPOINT", /* 0x58 */
- "SKIP", /* 0x59 */
- "COMMIT", /* 0x5a */
- "CUTGROUP", /* 0x5b */
- "KEEPS", /* 0x5c */
- "LNBREAK", /* 0x5d */
- "OPTIMIZED", /* 0x5e */
- "PSEUDO", /* 0x5f */
+ "NOTHING", /* 0x29 */
+ "TAIL", /* 0x2a */
+ "STAR", /* 0x2b */
+ "PLUS", /* 0x2c */
+ "CURLY", /* 0x2d */
+ "CURLYN", /* 0x2e */
+ "CURLYM", /* 0x2f */
+ "CURLYX", /* 0x30 */
+ "WHILEM", /* 0x31 */
+ "OPEN", /* 0x32 */
+ "CLOSE", /* 0x33 */
+ "REF", /* 0x34 */
+ "REFF", /* 0x35 */
+ "REFFL", /* 0x36 */
+ "REFFU", /* 0x37 */
+ "REFFA", /* 0x38 */
+ "NREF", /* 0x39 */
+ "NREFF", /* 0x3a */
+ "NREFFL", /* 0x3b */
+ "NREFFU", /* 0x3c */
+ "NREFFA", /* 0x3d */
+ "IFMATCH", /* 0x3e */
+ "UNLESSM", /* 0x3f */
+ "SUSPEND", /* 0x40 */
+ "IFTHEN", /* 0x41 */
+ "GROUPP", /* 0x42 */
+ "LONGJMP", /* 0x43 */
+ "BRANCHJ", /* 0x44 */
+ "EVAL", /* 0x45 */
+ "MINMOD", /* 0x46 */
+ "LOGICAL", /* 0x47 */
+ "RENUM", /* 0x48 */
+ "TRIE", /* 0x49 */
+ "TRIEC", /* 0x4a */
+ "AHOCORASICK", /* 0x4b */
+ "AHOCORASICKC", /* 0x4c */
+ "GOSUB", /* 0x4d */
+ "GOSTART", /* 0x4e */
+ "NGROUPP", /* 0x4f */
+ "INSUBP", /* 0x50 */
+ "DEFINEP", /* 0x51 */
+ "ENDLIKE", /* 0x52 */
+ "OPFAIL", /* 0x53 */
+ "ACCEPT", /* 0x54 */
+ "VERB", /* 0x55 */
+ "PRUNE", /* 0x56 */
+ "MARKPOINT", /* 0x57 */
+ "SKIP", /* 0x58 */
+ "COMMIT", /* 0x59 */
+ "CUTGROUP", /* 0x5a */
+ "KEEPS", /* 0x5b */
+ "LNBREAK", /* 0x5c */
+ "OPTIMIZED", /* 0x5d */
+ "PSEUDO", /* 0x5e */
/* ------------ States ------------- */
"TRIE_next", /* REGNODE_MAX +0x01 */
"TRIE_next_fail", /* REGNODE_MAX +0x02 */
EXTCONST U8 PL_varies_bitmask[];
#else
EXTCONST U8 PL_varies_bitmask[] = {
- 0x00, 0x00, 0x00, 0x00, 0x07, 0xF0, 0xE7, 0x7F, 0x26, 0x00, 0x00, 0x00
+ 0x00, 0x00, 0x00, 0x00, 0x07, 0xF8, 0xF3, 0x3F, 0x13, 0x00, 0x00, 0x00
};
#endif /* DOINIT */
projects / platform / upstream / perl.git / commitdiff