# 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_NON_UTF8_NON_ASCII_ALL sv like ANYOF, also matches any
- U+80 - U+FF when not in UTF-8
-
- 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
+
+ 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).
- EXACTFA_NO_TRIE str Match this string (which is not
- trie-able; not guaranteed to be
- folded) using /iaa rules
- (w/len).
+ 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).
+ EXACTFA_NO_TRIE str Match this string (which is not trie-able;
+ not guaranteed to be folded) using /iaa
+ 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.
-
- 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.
+ 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.
# 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
- charclass embedded 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
/* If this can match all upper Latin1 code points, have to add them
* as well */
- if (OP(node) == ANYOF_NON_UTF8_NON_ASCII_ALL) {
+ if (ANYOF_FLAGS(node) & ANYOF_NON_UTF8_NON_ASCII_ALL) {
_invlist_union(invlist, PL_UpperLatin1, &invlist);
}
}
break;
- case ANYOF_NON_UTF8_NON_ASCII_ALL:
case ANYOF:
if (flags & SCF_DO_STCLASS_AND)
ssc_and(pRExC_state, data->start_class,
if (DEPENDS_SEMANTICS) {
/* Under /d, everything in the upper half of the Latin1 range
* matches these complements */
- OP(ret) = ANYOF_NON_UTF8_NON_ASCII_ALL;
+ ANYOF_FLAGS(ret) |= ANYOF_NON_UTF8_NON_ASCII_ALL;
}
else if (AT_LEAST_ASCII_RESTRICTED) {
/* Under /a and /aa, everything above ASCII matches these
sv_catpvs(sv, "^");
}
- if (OP(o) == ANYOF_NON_UTF8_NON_ASCII_ALL) {
+ if (flags & ANYOF_NON_UTF8_NON_ASCII_ALL) {
sv_catpvs(sv, "{non-utf8-latin1-all}");
}
/* Flags for node->flags of ANYOF. These are in short supply, with one
* currently available. If more are needed, the ABOVE_LATIN1_ALL bit could be
* freed up by resorting to creating a swash containing everything above 255.
- * This introduces a performance penalty. An option that wouldn't slow things
- * down would be to split one of the LOC flags out into a separate node, like
- * what has been done with ANYOF_NON_UTF8_NON_ASCII_ALL. One of these is only
- * for /l nodes; the other only for /d, so there are no combinatorial issues.
+ * This introduces a performance penalty.
+ * shared should new flags be needed for SSCs, like ANYOF_EMPTY_STRING now. */
+
+/* Flags for node->flags of ANYOF. These are in short supply, with none
+ * currently available. The easiest solution for one more flag is to eliminate
+ * the ANYOF_LOCALE flag, because it doesn't add any extra information beyond
+ * the other two LOC flags. Also, the ABOVE_LATIN1_ALL bit could be freed up
+ * by resorting to creating a swash containing everything above 255. This
+ * introduces a performance penalty. An option that wouldn't slow things down
+ * would be to split one of the two remaining LOC flags out into a separate
+ * node, like what was done with ANYOF_NON_UTF8_NON_ASCII_ALL in commit
+ * 34fdef848b1687b91892ba55e9e0c3430e0770f6 (but which was reverted because it
+ * wasn't the best option available at the time), and using a LOC flag is
+ * probably better than that commit anyway. But it could be reinstated if we
+ * need a bit. The LOC flags are only for /l nodes; the reverted commit was
+ * only for /d, so there are no combinatorial issues.
* Several flags are not used in synthetic start class (SSC) nodes, so could be
* shared should new flags be needed for SSCs, like ANYOF_EMPTY_STRING now. */
#define ANYOF_ABOVE_LATIN1_ALL 0x40
#define ANYOF_UNICODE_ALL ANYOF_ABOVE_LATIN1_ALL
-#define ANYOF_FLAGS_ALL (0x7F)
+/* Match all Latin1 characters that aren't ASCII when the target string is not
+ * in utf8. */
+#define ANYOF_NON_UTF8_NON_ASCII_ALL 0x80
+
+#define ANYOF_FLAGS_ALL (0xff)
#define ANYOF_LOCALE_FLAGS (ANYOF_LOCALE \
|ANYOF_LOC_FOLD \
SANY REG_ANY, no 0 S ; Match any one character.
CANY REG_ANY, no 0 S ; Match any one byte.
ANYOF ANYOF, sv 0 S ; Match character in (or not in) this class, single char match only
-ANYOF_NON_UTF8_NON_ASCII_ALL ANYOF, sv 0 S ; like ANYOF, also matches any U+80 - U+FF when not in UTF-8
# Order of the below is important. See ordering comment above.
POSIXD POSIXD, none 0 S ; Some [[:class:]] under /d; the FLAGS field gives which one
/* We know what class it must start with. */
switch (OP(c)) {
- case ANYOF_NON_UTF8_NON_ASCII_ALL:
- if (! utf8_target && ! ANYOF_FLAGS(c)) {
- REXEC_FBC_CLASS_SCAN(! isASCII((U8) *s)
- || REGINCLASS(prog, c, (U8*)s));
- break;
- }
-
- /* FALL THROUGH */
case ANYOF:
if (utf8_target) {
REXEC_FBC_UTF8_CLASS_SCAN(
sayNO;
break;
- case ANYOF_NON_UTF8_NON_ASCII_ALL:
- if (! NEXTCHR_IS_EOS && ! utf8_target && ! ANYOF_FLAGS(scan)) {
- if ((isASCII((U8)(*locinput))
- && ! REGINCLASS(rex, scan, (U8*)locinput)))
- {
- sayNO;
- }
- locinput++;
- break;
- }
- /* FALLTHROUGH */
case ANYOF: /* /[abc]/ */
if (NEXTCHR_IS_EOS)
sayNO;
}
break;
}
- case ANYOF_NON_UTF8_NON_ASCII_ALL:
- if (! utf8_target && ! ANYOF_FLAGS(p)) {
- while (scan < loceol
- && (! isASCII((U8) *scan)
- || REGINCLASS(prog, p, (U8*)scan)))
- {
- scan++;
- }
- break;
- }
- /* FALLTHROUGH */
case ANYOF:
if (utf8_target) {
while (hardcount < max
if (c < 256) {
if (ANYOF_BITMAP_TEST(n, c))
match = TRUE;
- else if (OP(n) == ANYOF_NON_UTF8_NON_ASCII_ALL
+ else if (flags & ANYOF_NON_UTF8_NON_ASCII_ALL
&& ! utf8_target
&& ! isASCII(c))
{
/* Regops and State definitions */
-#define REGNODE_MAX 94
-#define REGMATCH_STATE_MAX 134
+#define REGNODE_MAX 93
+#define REGMATCH_STATE_MAX 133
#define END 0 /* 0000 End of program. */
#define SUCCEED 1 /* 0x01 Return from a subroutine, basically. */
#define SANY 19 /* 0x13 Match any one character. */
#define CANY 20 /* 0x14 Match any one byte. */
#define ANYOF 21 /* 0x15 Match character in (or not in) this class, single char match only */
-#define ANYOF_NON_UTF8_NON_ASCII_ALL 22 /* 0x16 like ANYOF, also matches any U+80 - U+FF when not in UTF-8 */
-#define POSIXD 23 /* 0x17 Some [[:class:]] under /d; the FLAGS field gives which one */
-#define POSIXL 24 /* 0x18 Some [[:class:]] under /l; the FLAGS field gives which one */
-#define POSIXU 25 /* 0x19 Some [[:class:]] under /u; the FLAGS field gives which one */
-#define POSIXA 26 /* 0x1a Some [[:class:]] under /a; the FLAGS field gives which one */
-#define NPOSIXD 27 /* 0x1b complement of POSIXD, [[:^class:]] */
-#define NPOSIXL 28 /* 0x1c complement of POSIXL, [[:^class:]] */
-#define NPOSIXU 29 /* 0x1d complement of POSIXU, [[:^class:]] */
-#define NPOSIXA 30 /* 0x1e complement of POSIXA, [[:^class:]] */
-#define CLUMP 31 /* 0x1f Match any extended grapheme cluster sequence */
-#define BRANCH 32 /* 0x20 Match this alternative, or the next... */
-#define BACK 33 /* 0x21 Match "", "next" ptr points backward. */
-#define EXACT 34 /* 0x22 Match this string (preceded by length). */
-#define EXACTF 35 /* 0x23 Match this non-UTF-8 string (not guaranteed to be folded) using /id rules (w/len). */
-#define EXACTFL 36 /* 0x24 Match this string (not guaranteed to be folded) using /il rules (w/len). */
-#define EXACTFU 37 /* 0x25 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 38 /* 0x26 Match this string (not guaranteed to be folded) using /iaa rules (w/len). */
-#define EXACTFU_SS 39 /* 0x27 Match this string (folded iff in UTF-8, length in folding may change even if not in UTF-8) using /iu rules (w/len). */
-#define EXACTFA_NO_TRIE 40 /* 0x28 Match this string (which is not trie-able; not guaranteed to be folded) using /iaa rules (w/len). */
-#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. */
+#define POSIXD 22 /* 0x16 Some [[:class:]] under /d; the FLAGS field gives which one */
+#define POSIXL 23 /* 0x17 Some [[:class:]] under /l; the FLAGS field gives which one */
+#define POSIXU 24 /* 0x18 Some [[:class:]] under /u; the FLAGS field gives which one */
+#define POSIXA 25 /* 0x19 Some [[:class:]] under /a; the FLAGS field gives which one */
+#define NPOSIXD 26 /* 0x1a complement of POSIXD, [[:^class:]] */
+#define NPOSIXL 27 /* 0x1b complement of POSIXL, [[:^class:]] */
+#define NPOSIXU 28 /* 0x1c complement of POSIXU, [[:^class:]] */
+#define NPOSIXA 29 /* 0x1d complement of POSIXA, [[:^class:]] */
+#define CLUMP 30 /* 0x1e Match any extended grapheme cluster sequence */
+#define BRANCH 31 /* 0x1f Match this alternative, or the next... */
+#define BACK 32 /* 0x20 Match "", "next" ptr points backward. */
+#define EXACT 33 /* 0x21 Match this string (preceded by length). */
+#define EXACTF 34 /* 0x22 Match this non-UTF-8 string (not guaranteed to be folded) using /id rules (w/len). */
+#define EXACTFL 35 /* 0x23 Match this string (not guaranteed to be folded) using /il rules (w/len). */
+#define EXACTFU 36 /* 0x24 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 37 /* 0x25 Match this string (not guaranteed to be folded) using /iaa rules (w/len). */
+#define EXACTFU_SS 38 /* 0x26 Match this string (folded iff in UTF-8, length in folding may change even if not in UTF-8) using /iu rules (w/len). */
+#define EXACTFA_NO_TRIE 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 semantics 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 semantics for non-utf8 */
+#define REFFA 55 /* 0x37 Match already matched string, folded using unicode semantics 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 semantics 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 semantics for non-utf8 */
+#define NREFFA 60 /* 0x3c Match already matched string, folded using unicode semantics for non-utf8, no mixing ASCII, non-ASCII */
+#define IFMATCH 61 /* 0x3d Succeeds if the following matches. */
+#define UNLESSM 62 /* 0x3e Fails if the following matches. */
+#define SUSPEND 63 /* 0x3f "Independent" sub-RE. */
+#define IFTHEN 64 /* 0x40 Switch, should be preceded by switcher. */
+#define GROUPP 65 /* 0x41 Whether the group matched. */
+#define LONGJMP 66 /* 0x42 Jump far away. */
+#define BRANCHJ 67 /* 0x43 BRANCH with long offset. */
+#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 (?!) */
+#define ACCEPT 83 /* 0x53 Accepts the current matched string. */
+#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. */
/* ------------ States ------------- */
#define TRIE_next (REGNODE_MAX + 1) /* state for TRIE */
#define TRIE_next_fail (REGNODE_MAX + 2) /* state for TRIE */
REG_ANY, /* SANY */
REG_ANY, /* CANY */
ANYOF, /* ANYOF */
- ANYOF, /* ANYOF_NON_UTF8_NON_ASCII_ALL */
POSIXD, /* POSIXD */
POSIXD, /* POSIXL */
POSIXD, /* POSIXU */
0, /* SANY */
0, /* CANY */
0, /* ANYOF */
- 0, /* ANYOF_NON_UTF8_NON_ASCII_ALL */
0, /* POSIXD */
0, /* POSIXL */
0, /* POSIXU */
0, /* SANY */
0, /* CANY */
0, /* ANYOF */
- 0, /* ANYOF_NON_UTF8_NON_ASCII_ALL */
0, /* POSIXD */
0, /* POSIXL */
0, /* POSIXU */
"SANY", /* 0x13 */
"CANY", /* 0x14 */
"ANYOF", /* 0x15 */
- "ANYOF_NON_UTF8_NON_ASCII_ALL", /* 0x16 */
- "POSIXD", /* 0x17 */
- "POSIXL", /* 0x18 */
- "POSIXU", /* 0x19 */
- "POSIXA", /* 0x1a */
- "NPOSIXD", /* 0x1b */
- "NPOSIXL", /* 0x1c */
- "NPOSIXU", /* 0x1d */
- "NPOSIXA", /* 0x1e */
- "CLUMP", /* 0x1f */
- "BRANCH", /* 0x20 */
- "BACK", /* 0x21 */
- "EXACT", /* 0x22 */
- "EXACTF", /* 0x23 */
- "EXACTFL", /* 0x24 */
- "EXACTFU", /* 0x25 */
- "EXACTFA", /* 0x26 */
- "EXACTFU_SS", /* 0x27 */
- "EXACTFA_NO_TRIE", /* 0x28 */
- "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 */
+ "POSIXD", /* 0x16 */
+ "POSIXL", /* 0x17 */
+ "POSIXU", /* 0x18 */
+ "POSIXA", /* 0x19 */
+ "NPOSIXD", /* 0x1a */
+ "NPOSIXL", /* 0x1b */
+ "NPOSIXU", /* 0x1c */
+ "NPOSIXA", /* 0x1d */
+ "CLUMP", /* 0x1e */
+ "BRANCH", /* 0x1f */
+ "BACK", /* 0x20 */
+ "EXACT", /* 0x21 */
+ "EXACTF", /* 0x22 */
+ "EXACTFL", /* 0x23 */
+ "EXACTFU", /* 0x24 */
+ "EXACTFA", /* 0x25 */
+ "EXACTFU_SS", /* 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 */
+ "IFMATCH", /* 0x3d */
+ "UNLESSM", /* 0x3e */
+ "SUSPEND", /* 0x3f */
+ "IFTHEN", /* 0x40 */
+ "GROUPP", /* 0x41 */
+ "LONGJMP", /* 0x42 */
+ "BRANCHJ", /* 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 */
/* ------------ 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, 0x80, 0x03, 0xF8, 0xF3, 0x3F, 0x13, 0x00, 0x00, 0x00
+ 0x00, 0x00, 0x00, 0xC0, 0x01, 0xFC, 0xF9, 0x9F, 0x09, 0x00, 0x00, 0x00
};
#endif /* DOINIT */
EXTCONST U8 PL_simple[] __attribute__deprecated__;
#else
EXTCONST U8 PL_simple[] __attribute__deprecated__ = {
- REG_ANY, SANY, CANY, ANYOF, ANYOF_NON_UTF8_NON_ASCII_ALL, POSIXD,
- POSIXL, POSIXU, POSIXA, NPOSIXD, NPOSIXL, NPOSIXU, NPOSIXA,
+ REG_ANY, SANY, CANY, ANYOF, POSIXD, POSIXL, POSIXU, POSIXA, NPOSIXD,
+ NPOSIXL, NPOSIXU, NPOSIXA,
0
};
#endif /* DOINIT */
EXTCONST U8 PL_simple_bitmask[];
#else
EXTCONST U8 PL_simple_bitmask[] = {
- 0x00, 0x00, 0xFC, 0x7F, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
+ 0x00, 0x00, 0xFC, 0x3F, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
};
#endif /* DOINIT */
pod/perlcall.pod Verbatim line length including indents exceeds 79 by 2
pod/perlce.pod Verbatim line length including indents exceeds 79 by 3
pod/perlcygwin.pod Verbatim line length including indents exceeds 79 by 25
-pod/perldebguts.pod Verbatim line length including indents exceeds 79 by 35
+pod/perldebguts.pod Verbatim line length including indents exceeds 79 by 34
pod/perldebtut.pod Verbatim line length including indents exceeds 79 by 22
pod/perldebug.pod Verbatim line length including indents exceeds 79 by 3
pod/perldelta.pod Apparent broken link 1
projects / platform / upstream / perl.git / commitdiff