# 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.
# Line Start Anchors:
- SBOL no Match "" at beginning of line: /^/, /\A/
- MBOL no Same, assuming multiline: /^/m
+ SBOL no Match "" at beginning of line: /^/, /\A/
+ MBOL no Same, assuming multiline: /^/m
# Line End Anchors:
- SEOL no Match "" at end of line: /$/
- MEOL no Same, assuming multiline: /$/m
- EOS no Match "" at end of string: /\z/
+ SEOL no Match "" at end of line: /$/
+ MEOL no Same, assuming multiline: /$/m
+ EOS no Match "" at end of string: /\z/
# Match Start Anchors:
- GPOS no Matches where last m//g left off.
+ GPOS no Matches where last m//g left off.
# Word Boundary Opcodes:
- BOUND no Like BOUNDA for non-utf8, otherwise match ""
- between any Unicode \w\W or \W\w
- BOUNDL no Like BOUND/BOUNDU, but \w and \W are defined
- by current locale
- BOUNDU no Match "" at any boundary of a given type
- using Unicode rules
- BOUNDA no Match "" at any boundary between \w\W or
- \W\w, where \w is [_a-zA-Z0-9]
- NBOUND no Like NBOUNDA for non-utf8, otherwise match
- "" between any Unicode \w\w or \W\W
- NBOUNDL no Like NBOUND/NBOUNDU, but \w and \W are
- defined by current locale
- NBOUNDU no Match "" at any non-boundary of a given type
- using using Unicode rules
- NBOUNDA no Match "" betweeen any \w\w or \W\W, where \w
- is [_a-zA-Z0-9]
+ BOUND no Like BOUNDA for non-utf8, otherwise match
+ "" between any Unicode \w\W or \W\w
+ BOUNDL no Like BOUND/BOUNDU, but \w and \W are
+ defined by current locale
+ BOUNDU no Match "" at any boundary of a given type
+ using Unicode rules
+ BOUNDA no Match "" at any boundary between \w\W or
+ \W\w, where \w is [_a-zA-Z0-9]
+ NBOUND no Like NBOUNDA for non-utf8, otherwise match
+ "" between any Unicode \w\w or \W\W
+ NBOUNDL no Like NBOUND/NBOUNDU, but \w and \W are
+ defined by current locale
+ NBOUNDU no Match "" at any non-boundary of a given
+ type using using Unicode rules
+ NBOUNDA no Match "" betweeen any \w\w or \W\W, where
+ \w is [_a-zA-Z0-9]
# [Special] alternatives:
- REG_ANY no Match any one character (except newline).
- SANY no Match any one character.
- ANYOF sv 1 Match character in (or not in) this class,
- single char match only
- ANYOFD sv 1 Like ANYOF, but /d is in effect
- ANYOFL sv 1 Like ANYOF, but /l is in effect
- ANYOFM byte 1 Like ANYOF, but matches an invariant byte as
- determined by the mask and arg
+ REG_ANY no Match any one character (except newline).
+ SANY no Match any one character.
+ ANYOF sv 1 Match character in (or not in) this class,
+ single char match only
+ ANYOFD sv 1 Like ANYOF, but /d is in effect
+ ANYOFL sv 1 Like ANYOF, but /l is in effect
+ ANYOFM byte 1 Like ANYOF, but matches an invariant byte
+ as determined by the mask and arg
# POSIX Character Classes:
- 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:]]
-
- ASCII none [[:ascii:]]
- NASCII none [[:^ascii:]]
-
- CLUMP no Match any extended grapheme cluster sequence
+ 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:]]
+
+ ASCII none [[:ascii:]]
+ NASCII none [[:^ascii:]]
+
+ 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...
# Literals
- EXACT str Match this string (preceded by length).
- EXACTL str Like EXACT, but /l is in effect (used so
- locale-related warnings can be checked for).
- 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).
- EXACTFLU8 str Rare cirucmstances: like EXACTFU, but is
- under /l, UTF-8, folded, and everything in
- it is above 255.
- 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).
+ EXACTL str Like EXACT, but /l is in effect (used so
+ locale-related warnings can be checked
+ for).
+ 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).
+ EXACTFAA 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).
+ EXACTFLU8 str Rare cirucmstances: like EXACTFU, but is
+ under /l, UTF-8, folded, and everything in
+ it is above 255.
+ EXACTFAA_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.
+ 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 Close corresponding OPEN of #n.
- SROPEN none Same as OPEN, but for script run
- SRCLOSE none Close preceding SROPEN
-
- REF num 1 Match some already matched string
- REFF num 1 Match already matched string, folded using
- native charset rules for non-utf8
- REFFL num 1 Match already matched string, folded in loc.
- REFFU num 1 Match already matched string, folded using
- unicode rules for non-utf8
- REFFA num 1 Match already matched string, folded using
- unicode rules for non-utf8, no mixing ASCII,
- non-ASCII
+ OPEN num 1 Mark this point in input as start of #n.
+ CLOSE num 1 Close corresponding OPEN of #n.
+ SROPEN none Same as OPEN, but for script run
+ SRCLOSE none Close preceding SROPEN
+
+ REF num 1 Match some already matched string
+ REFF num 1 Match already matched string, folded using
+ native charset rules for non-utf8
+ REFFL num 1 Match already matched string, folded in
+ loc.
+ REFFU num 1 Match already matched string, folded using
+ unicode rules for non-utf8
+ REFFA num 1 Match already matched string, folded using
+ unicode rules 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 rules for non-utf8
- NREFFL no-sv 1 Match already matched string, folded in loc.
- NREFFU num 1 Match already matched string, folded using
- unicode rules for non-utf8
- NREFFA num 1 Match already matched string, folded using
- unicode rules for non-utf8, no mixing ASCII,
- non-ASCII
+ NREF no-sv 1 Match some already matched string
+ NREFF no-sv 1 Match already matched string, folded using
+ native charset rules for non-utf8
+ NREFFL no-sv 1 Match already matched string, folded in
+ loc.
+ NREFFU num 1 Match already matched string, folded using
+ unicode rules for non-utf8
+ NREFFA num 1 Match already matched string, folded using
+ unicode rules for non-utf8, no mixing
+ ASCII, non-ASCII
# 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.
# Special Case Regops
- 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.
+ 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.
# The heavy worker
- EVAL evl/flags Execute some Perl code.
- 2L
+ EVAL evl/flags Execute some Perl code.
+ 2L
# 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
+ GOSUB num/ofs 2L recurse to paren arg1 at (signed) ofs arg2
# 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 no-sv 1 Same as (?!), but with verb arg
- ACCEPT no-sv/num Accepts the current matched string, with
- 2L verbar
+ ENDLIKE none Used only for the type field of verbs
+ OPFAIL no-sv 1 Same as (?!), but with verb arg
+ ACCEPT no-sv/num Accepts the current matched string, with
+ 2L verbar
# 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
switch (flags) {
case EXACT: case EXACTL: break;
- case EXACTFA:
+ case EXACTFAA:
case EXACTFU_SS:
case EXACTFU:
case EXACTFLU8: folder = PL_fold_latin1; break;
* described in the next item.
* 3) A problem remains for unfolded multi-char folds. (These occur when the
* validity of the fold won't be known until runtime, and so must remain
- * unfolded for now. This happens for the sharp s in EXACTF and EXACTFA
+ * unfolded for now. This happens for the sharp s in EXACTF and EXACTFAA
* nodes when the pattern isn't in UTF-8. (Note, BTW, that there cannot
* be an EXACTF node with a UTF-8 pattern.) They also occur for various
* folds in EXACTFL nodes, regardless of the UTF-ness of the pattern.)
* character in the target string. (And I do mean character, and not byte
* here, unlike other parts of the documentation that have never been
* updated to account for multibyte Unicode.) sharp s in EXACTF and
- * EXACTFL nodes can match the two character string 'ss'; in EXACTFA nodes
- * it can match "\x{17F}\x{17F}". These, along with other ones in EXACTFL
- * nodes, violate the assumption, and they are the only instances where it
- * is violated. I'm reluctant to try to change the assumption, as the
- * code involved is impenetrable to me (khw), so instead the code here
- * punts. This routine examines EXACTFL nodes, and (when the pattern
- * isn't UTF-8) EXACTF and EXACTFA for such unfolded folds, and returns a
+ * EXACTFL nodes can match the two character string 'ss'; in EXACTFAA
+ * nodes it can match "\x{17F}\x{17F}". These, along with other ones in
+ * EXACTFL nodes, violate the assumption, and they are the only instances
+ * where it is violated. I'm reluctant to try to change the assumption,
+ * as the code involved is impenetrable to me (khw), so instead the code
+ * here punts. This routine examines EXACTFL nodes, and (when the pattern
+ * isn't UTF-8) EXACTF and EXACTFAA for such unfolded folds, and returns a
* boolean indicating whether or not the node contains such a fold. When
* it is true, the caller sets a flag that later causes the optimizer in
* this file to not set values for the floating and fixed string lengths,
* and thus avoids the optimizer code in regexec.c that makes the invalid
* assumption. Thus, there is no optimization based on string lengths for
* EXACTFL nodes that contain these few folds, nor for non-UTF8-pattern
- * EXACTF and EXACTFA nodes that contain the sharp s. (The reason the
+ * EXACTF and EXACTFAA nodes that contain the sharp s. (The reason the
* assumption is wrong only in these cases is that all other non-UTF-8
* folds are 1-1; and, for UTF-8 patterns, we pre-fold all other folds to
* their expanded versions. (Again, we can't prefold sharp s to 'ss' in
* EXACTF nodes because we don't know at compile time if it actually
* matches 'ss' or not. For EXACTF nodes it will match iff the target
* string is in UTF-8. This is in contrast to EXACTFU nodes, where it
- * always matches; and EXACTFA where it never does. In an EXACTFA node in
- * a UTF-8 pattern, sharp s is folded to "\x{17F}\x{17F}, avoiding the
+ * always matches; and EXACTFAA where it never does. In an EXACTFAA node
+ * in a UTF-8 pattern, sharp s is folded to "\x{17F}\x{17F}, avoiding the
* problem; but in a non-UTF8 pattern, folding it to that above-Latin1
* string would require the pattern to be forced into UTF-8, the overhead
* of which we want to avoid. Similarly the unfolded multi-char folds in
*
* Similarly, the code that generates tries doesn't currently handle
* not-already-folded multi-char folds, and it looks like a pain to change
- * that. Therefore, trie generation of EXACTFA nodes with the sharp s
- * doesn't work. Instead, such an EXACTFA is turned into a new regnode,
- * EXACTFA_NO_TRIE, which the trie code knows not to handle. Most people
+ * that. Therefore, trie generation of EXACTFAA nodes with the sharp s
+ * doesn't work. Instead, such an EXACTFAA is turned into a new regnode,
+ * EXACTFAA_NO_TRIE, which the trie code knows not to handle. Most people
* using /iaa matching will be doing so almost entirely with ASCII
* strings, so this should rarely be encountered in practice */
}
/* Nodes with 'ss' require special handling, except for
- * EXACTFA-ish for which there is no multi-char fold to this */
+ * EXACTFAA-ish for which there is no multi-char fold to this */
if (len == 2 && *s == 's' && *(s+1) == 's'
- && OP(scan) != EXACTFA
- && OP(scan) != EXACTFA_NO_TRIE)
+ && OP(scan) != EXACTFAA
+ && OP(scan) != EXACTFAA_NO_TRIE)
{
count = 2;
if (OP(scan) != EXACTFL) {
/* Count how many characters are in it. In the case of
* /aa, no folds which contain ASCII code points are
* allowed, so check for those, and skip if found. */
- if (OP(scan) != EXACTFA && OP(scan) != EXACTFA_NO_TRIE) {
+ if (OP(scan) != EXACTFAA && OP(scan) != EXACTFAA_NO_TRIE) {
count = utf8_length(s, multi_end);
s = multi_end;
}
*min_subtract += total_count_delta;
Safefree(folded);
}
- else if (OP(scan) == EXACTFA) {
+ else if (OP(scan) == EXACTFAA) {
- /* Non-UTF-8 pattern, EXACTFA node. There can't be a multi-char
+ /* Non-UTF-8 pattern, EXACTFAA node. There can't be a multi-char
* fold to the ASCII range (and there are no existing ones in the
* upper latin1 range). But, as outlined in the comments preceding
* this function, we need to flag any occurrences of the sharp s.
|| UNICODE_DOT_DOT_VERSION > 0)
while (s < s_end) {
if (*s == LATIN_SMALL_LETTER_SHARP_S) {
- OP(scan) = EXACTFA_NO_TRIE;
+ OP(scan) = EXACTFAA_NO_TRIE;
*unfolded_multi_char = TRUE;
break;
}
}
else {
- /* Non-UTF-8 pattern, not EXACTFA node. Look for the multi-char
+ /* Non-UTF-8 pattern, not EXACTFAA node. Look for the multi-char
* folds that are all Latin1. As explained in the comments
* preceding this function, we look also for the sharp s in EXACTF
* and EXACTFL nodes; it can be in the final position. Otherwise
EXACT | EXACT
EXACTFU | EXACTFU
EXACTFU_SS | EXACTFU
- EXACTFA | EXACTFA
+ EXACTFAA | EXACTFAA
EXACTL | EXACTL
EXACTFLU8 | EXACTFLU8
? EXACT \
: ( EXACTFU == (X) || EXACTFU_SS == (X) ) \
? EXACTFU \
- : ( EXACTFA == (X) ) \
- ? EXACTFA \
+ : ( EXACTFAA == (X) ) \
+ ? EXACTFAA \
: ( EXACTL == (X) ) \
? EXACTL \
: ( EXACTFLU8 == (X) ) \
/* Some characters match above-Latin1 ones under /i. This
* is true of EXACTFL ones when the locale is UTF-8 */
if (HAS_NONLATIN1_SIMPLE_FOLD_CLOSURE(uc)
- && (! isASCII(uc) || (OP(node) != EXACTFA
- && OP(node) != EXACTFA_NO_TRIE)))
+ && (! isASCII(uc) || (OP(node) != EXACTFAA
+ && OP(node) != EXACTFAA_NO_TRIE)))
{
add_above_Latin1_folds(pRExC_state, (U8) uc, &invlist);
}
c = SvUV(*c_p);
/* /aa doesn't allow folds between ASCII and non- */
- if ((OP(node) == EXACTFA || OP(node) == EXACTFA_NO_TRIE)
+ if ((OP(node) == EXACTFAA || OP(node) == EXACTFAA_NO_TRIE)
&& isASCII(c) != isASCII(uc))
{
continue;
case EXACT:
case EXACTL:
case EXACTF:
- case EXACTFA_NO_TRIE:
- case EXACTFA:
+ case EXACTFAA_NO_TRIE:
+ case EXACTFAA:
case EXACTFU:
case EXACTFLU8:
case EXACTFU_SS:
/* Currently these are only used when PL_regkind[OP(rn)] == EXACT so
we don't need this definition. XXX These are now out-of-sync*/
#define IS_TEXT(rn) ( OP(rn)==EXACT || OP(rn)==REF || OP(rn)==NREF )
-#define IS_TEXTF(rn) ( OP(rn)==EXACTFU || OP(rn)==EXACTFU_SS || OP(rn)==EXACTFA || OP(rn)==EXACTFA_NO_TRIE || OP(rn)==EXACTF || OP(rn)==REFF || OP(rn)==NREFF )
+#define IS_TEXTF(rn) ( OP(rn)==EXACTFU || OP(rn)==EXACTFU_SS || OP(rn)==EXACTFAA || OP(rn)==EXACTFAA_NO_TRIE || OP(rn)==EXACTF || OP(rn)==REFF || OP(rn)==NREFF )
#define IS_TEXTFL(rn) ( OP(rn)==EXACTFL || OP(rn)==REFFL || OP(rn)==NREFFL )
#else
/* ... so we use this as its faster. */
#define IS_TEXT(rn) ( OP(rn)==EXACT || OP(rn)==EXACTL )
-#define IS_TEXTFU(rn) ( OP(rn)==EXACTFU || OP(rn)==EXACTFLU8 || OP(rn)==EXACTFU_SS || OP(rn) == EXACTFA || OP(rn) == EXACTFA_NO_TRIE)
+#define IS_TEXTFU(rn) ( OP(rn)==EXACTFU || OP(rn)==EXACTFLU8 || OP(rn)==EXACTFU_SS || OP(rn) == EXACTFAA || OP(rn) == EXACTFAA_NO_TRIE)
#define IS_TEXTF(rn) ( OP(rn)==EXACTF )
#define IS_TEXTFL(rn) ( OP(rn)==EXACTFL )
? (utf8_target ? trie_utf8 : trie_plain) \
: (scan->flags == EXACTL) \
? (utf8_target ? trie_utf8l : trie_plain) \
- : (scan->flags == EXACTFA) \
+ : (scan->flags == EXACTFAA) \
? (utf8_target \
? trie_utf8_exactfa_fold \
: trie_latin_utf8_exactfa_fold) \
find_next_masked(s, strend, ARG(c), FLAGS(c)));
break;
- case EXACTFA_NO_TRIE: /* This node only generated for non-utf8 patterns */
+ case EXACTFAA_NO_TRIE: /* This node only generated for non-utf8 patterns */
assert(! is_utf8_pat);
/* FALLTHROUGH */
- case EXACTFA:
+ case EXACTFAA:
if (is_utf8_pat || utf8_target) {
utf8_fold_flags = FOLDEQ_UTF8_NOMIX_ASCII;
goto do_exactf_utf8;
c2 = SvUV(*c_p);
/* Folds that cross the 255/256 boundary are forbidden
- * if EXACTFL (and isnt a UTF8 locale), or EXACTFA and
+ * if EXACTFL (and isnt a UTF8 locale), or EXACTFAA and
* one is ASCIII. Since the pattern character is above
* 255, and its only other match is below 256, the only
* legal match will be to itself. We have thrown away
if ((c1 < 256) != (c2 < 256)) {
if ((OP(text_node) == EXACTFL
&& ! IN_UTF8_CTYPE_LOCALE)
- || ((OP(text_node) == EXACTFA
- || OP(text_node) == EXACTFA_NO_TRIE)
+ || ((OP(text_node) == EXACTFAA
+ || OP(text_node) == EXACTFAA_NO_TRIE)
&& (isASCII(c1) || isASCII(c2))))
{
if (c1 < 256) {
if (utf8_target
&& HAS_NONLATIN1_FOLD_CLOSURE(c1)
&& ( ! (OP(text_node) == EXACTFL && ! IN_UTF8_CTYPE_LOCALE))
- && ((OP(text_node) != EXACTFA
- && OP(text_node) != EXACTFA_NO_TRIE)
+ && ((OP(text_node) != EXACTFAA
+ && OP(text_node) != EXACTFAA_NO_TRIE)
|| ! isASCII(c1)))
{
/* Here, there could be something above Latin1 in the target
}
/* FALLTHROUGH */
/* /u rules for all these. This happens to work for
- * EXACTFA as nothing in Latin1 folds to ASCII */
- case EXACTFA_NO_TRIE: /* This node only generated for
- non-utf8 patterns */
+ * EXACTFAA as nothing in Latin1 folds to ASCII */
+ case EXACTFAA_NO_TRIE: /* This node only generated for
+ non-utf8 patterns */
assert(! is_utf8_pat);
/* FALLTHROUGH */
- case EXACTFA:
+ case EXACTFAA:
case EXACTFU_SS:
case EXACTFU:
c2 = PL_fold_latin1[c1];
fold_utf8_flags = is_utf8_pat ? FOLDEQ_S1_ALREADY_FOLDED : 0;
goto do_exactf;
- case EXACTFA_NO_TRIE: /* This node only generated for non-utf8
+ case EXACTFAA_NO_TRIE: /* This node only generated for non-utf8
patterns */
assert(! is_utf8_pat);
/* FALLTHROUGH */
- case EXACTFA: /* /abc/iaa */
+ case EXACTFAA: /* /abc/iaa */
folder = foldEQ_latin1;
fold_array = PL_fold_latin1;
fold_utf8_flags = FOLDEQ_UTF8_NOMIX_ASCII;
}
break;
- case EXACTFA_NO_TRIE: /* This node only generated for non-utf8 patterns */
+ case EXACTFAA_NO_TRIE: /* This node only generated for non-utf8 patterns */
assert(! reginfo->is_utf8_pat);
/* FALLTHROUGH */
- case EXACTFA:
+ case EXACTFAA:
utf8_flags = FOLDEQ_UTF8_NOMIX_ASCII;
goto do_exactf;
https://perl5.git.perl.org / perl5.git / commitdiff