REGEXP *src_regex;
};
+/* array of reg_code_block's plus header info */
+
+struct reg_code_blocks {
+ int refcnt; /* we may be pointed to from a regex and from the savestack */
+ int count; /* how many code blocks */
+ struct reg_code_block *cb; /* array of reg_code_block's */
+};
+
/*
The regexp/REGEXP struct, see L<perlreapi> for further documentation
const struct regexp_engine* engine; \
REGEXP *mother_re; /* what re is this a lightweight copy of? */ \
HV *paren_names; /* Optional hash of paren names */ \
+ /*--------------------------------------------------------*/ \
/* Information about the match that the perl core uses to */ \
/* manage things */ \
U32 extflags; /* Flags used both externally and internally */ \
U32 intflags; /* Engine Specific Internal flags */ \
void *pprivate; /* Data private to the regex engine which */ \
/* created this object. */ \
+ /*--------------------------------------------------------*/ \
/* Data about the last/current match. These are modified */ \
/* during matching */ \
U32 lastparen; /* last open paren matched */ \
U32 lastcloseparen; /* last close paren matched */ \
/* Array of offsets for (@-) and (@+) */ \
regexp_paren_pair *offs; \
+ char **recurse_locinput; /* used to detect infinite recursion, XXX: move to internal */ \
+ /*--------------------------------------------------------*/ \
/* saved or original string so \digit works forever. */ \
char *subbeg; \
SV_SAVED_COPY /* If non-NULL, SV which is COW from original */\
SSize_t subcoffset; /* suboffset equiv, but in chars (for @-/@+) */ \
/* Information about the match that isn't often used */ \
SSize_t maxlen; /* mininum possible number of chars in string to match */\
+ /*--------------------------------------------------------*/ \
/* offset from wrapped to the start of precomp */ \
PERL_BITFIELD32 pre_prefix:4; \
/* original flags used to compile the pattern, may differ */ \
/* from extflags in various ways */ \
PERL_BITFIELD32 compflags:9; \
+ /*--------------------------------------------------------*/ \
CV *qr_anoncv /* the anon sub wrapped round qr/(?{..})/ */
typedef struct regexp {
const U32 flags,
re_scream_pos_data *data);
SV* (*checkstr) (pTHX_ REGEXP * const rx);
- void (*free) (pTHX_ REGEXP * const rx);
+ void (*rxfree) (pTHX_ REGEXP * const rx);
void (*numbered_buff_FETCH) (pTHX_ REGEXP * const rx, const I32 paren,
SV * const sv);
void (*numbered_buff_STORE) (pTHX_ REGEXP * const rx, const I32 paren,
#endif
REGEXP* (*op_comp) (pTHX_ SV ** const patternp, int pat_count,
OP *expr, const struct regexp_engine* eng,
- REGEXP *VOL old_re,
+ REGEXP *old_re,
bool *is_bare_re, U32 orig_rx_flags, U32 pm_flags);
} regexp_engine;
if (SvTYPE(sv) == SVt_REGEXP)
return (REGEXP*) sv;
-NULL will be returned if a REGEXP* is not found.
+C<NULL> will be returned if a REGEXP* is not found.
=for apidoc Am|bool|SvRXOK|SV* sv
*/
#define SvRX(sv) (Perl_get_re_arg(aTHX_ sv))
-#define SvRXOK(sv) (Perl_get_re_arg(aTHX_ sv) ? TRUE : FALSE)
+#define SvRXOK(sv) cBOOL(Perl_get_re_arg(aTHX_ sv))
/* Flags stored in regexp->extflags
#include "op_reg_common.h"
-#define RXf_PMf_STD_PMMOD (RXf_PMf_MULTILINE|RXf_PMf_SINGLELINE|RXf_PMf_FOLD|RXf_PMf_EXTENDED)
-
-#define CASE_STD_PMMOD_FLAGS_PARSE_SET(pmfl) \
- case IGNORE_PAT_MOD: *(pmfl) |= RXf_PMf_FOLD; break; \
- case MULTILINE_PAT_MOD: *(pmfl) |= RXf_PMf_MULTILINE; break; \
- case SINGLE_PAT_MOD: *(pmfl) |= RXf_PMf_SINGLELINE; break; \
- case XTENDED_PAT_MOD: *(pmfl) |= RXf_PMf_EXTENDED; break
+#define RXf_PMf_STD_PMMOD (RXf_PMf_MULTILINE|RXf_PMf_SINGLELINE|RXf_PMf_FOLD|RXf_PMf_EXTENDED|RXf_PMf_EXTENDED_MORE|RXf_PMf_NOCAPTURE)
+
+#define CASE_STD_PMMOD_FLAGS_PARSE_SET(pmfl, x_count) \
+ case IGNORE_PAT_MOD: *(pmfl) |= RXf_PMf_FOLD; break; \
+ case MULTILINE_PAT_MOD: *(pmfl) |= RXf_PMf_MULTILINE; break; \
+ case SINGLE_PAT_MOD: *(pmfl) |= RXf_PMf_SINGLELINE; break; \
+ case XTENDED_PAT_MOD: if (x_count == 0) { \
+ *(pmfl) |= RXf_PMf_EXTENDED; \
+ *(pmfl) &= ~RXf_PMf_EXTENDED_MORE; \
+ } \
+ else { \
+ *(pmfl) |= RXf_PMf_EXTENDED \
+ |RXf_PMf_EXTENDED_MORE; \
+ } \
+ (x_count)++; break; \
+ case NOCAPTURE_PAT_MOD: *(pmfl) |= RXf_PMf_NOCAPTURE; break;
/* Note, includes charset ones, assumes 0 is the default for them */
#define STD_PMMOD_FLAGS_CLEAR(pmfl) \
- *(pmfl) &= ~(RXf_PMf_FOLD|RXf_PMf_MULTILINE|RXf_PMf_SINGLELINE|RXf_PMf_EXTENDED|RXf_PMf_CHARSET)
+ *(pmfl) &= ~(RXf_PMf_FOLD|RXf_PMf_MULTILINE|RXf_PMf_SINGLELINE|RXf_PMf_EXTENDED|RXf_PMf_EXTENDED_MORE|RXf_PMf_CHARSET|RXf_PMf_NOCAPTURE)
/* chars and strings used as regex pattern modifiers
* Singular is a 'c'har, plural is a "string"
#define DEFAULT_PAT_MOD '^' /* Short for all the default modifiers */
#define EXEC_PAT_MOD 'e'
#define KEEPCOPY_PAT_MOD 'p'
+#define NOCAPTURE_PAT_MOD 'n'
#define ONCE_PAT_MOD 'o'
#define GLOBAL_PAT_MOD 'g'
#define CONTINUE_PAT_MOD 'c'
#define ONCE_PAT_MODS "o"
#define KEEPCOPY_PAT_MODS "p"
+#define NOCAPTURE_PAT_MODS "n"
#define EXEC_PAT_MODS "e"
#define LOOP_PAT_MODS "gc"
#define NONDESTRUCT_PAT_MODS "r"
/* This string is expected by regcomp.c to be ordered so that the first
* character is the flag in bit RXf_PMf_STD_PMMOD_SHIFT of extflags; the next
* character is bit +1, etc. */
-#define STD_PAT_MODS "msixx"
+#define STD_PAT_MODS "msixxn"
#define CHARSET_PAT_MODS ASCII_RESTRICT_PAT_MODS DEPENDS_PAT_MODS LOCALE_PAT_MODS UNICODE_PAT_MODS
* extflags; the next character is in bit +1, etc. */
#define INT_PAT_MODS STD_PAT_MODS KEEPCOPY_PAT_MODS
-#define EXT_PAT_MODS ONCE_PAT_MODS KEEPCOPY_PAT_MODS
+#define EXT_PAT_MODS ONCE_PAT_MODS KEEPCOPY_PAT_MODS NOCAPTURE_PAT_MODS
#define QR_PAT_MODS STD_PAT_MODS EXT_PAT_MODS CHARSET_PAT_MODS
#define M_PAT_MODS QR_PAT_MODS LOOP_PAT_MODS
#define S_PAT_MODS M_PAT_MODS EXEC_PAT_MODS NONDESTRUCT_PAT_MODS
*/
/*
- Set in Perl_pmruntime if op_flags & OPf_SPECIAL, i.e. split. Will
- be used by regex engines to check whether they should set
- RXf_SKIPWHITE
+ Set in Perl_pmruntime for a split. Will be used by regex engines to
+ check whether they should set RXf_SKIPWHITE
*/
#define RXf_SPLIT RXf_PMf_SPLIT
* For the regexp bits, PL_reg_extflags_name[] in regnodes.h has a comment
* giving which bits are used/unused */
-#define RXf_BASE_SHIFT (_RXf_PMf_SHIFT_NEXT + 4)
+#define RXf_BASE_SHIFT (_RXf_PMf_SHIFT_NEXT + 2)
/* What we have seen */
-#define RXf_NO_INPLACE_SUBST (1<<(RXf_BASE_SHIFT+2))
-#define RXf_EVAL_SEEN (1<<(RXf_BASE_SHIFT+3))
+#define RXf_NO_INPLACE_SUBST (1U<<(RXf_BASE_SHIFT+2))
+#define RXf_EVAL_SEEN (1U<<(RXf_BASE_SHIFT+3))
/* Special */
-#define RXf_UNBOUNDED_QUANTIFIER_SEEN (1<<(RXf_BASE_SHIFT+4))
-#define RXf_CHECK_ALL (1<<(RXf_BASE_SHIFT+5))
+#define RXf_UNBOUNDED_QUANTIFIER_SEEN (1U<<(RXf_BASE_SHIFT+4))
+#define RXf_CHECK_ALL (1U<<(RXf_BASE_SHIFT+5))
/* UTF8 related */
-#define RXf_MATCH_UTF8 (1<<(RXf_BASE_SHIFT+6)) /* $1 etc are utf8 */
+#define RXf_MATCH_UTF8 (1U<<(RXf_BASE_SHIFT+6)) /* $1 etc are utf8 */
/* Intuit related */
-#define RXf_USE_INTUIT_NOML (1<<(RXf_BASE_SHIFT+7))
-#define RXf_USE_INTUIT_ML (1<<(RXf_BASE_SHIFT+8))
-#define RXf_INTUIT_TAIL (1<<(RXf_BASE_SHIFT+9))
+#define RXf_USE_INTUIT_NOML (1U<<(RXf_BASE_SHIFT+7))
+#define RXf_USE_INTUIT_ML (1U<<(RXf_BASE_SHIFT+8))
+#define RXf_INTUIT_TAIL (1U<<(RXf_BASE_SHIFT+9))
#define RXf_USE_INTUIT (RXf_USE_INTUIT_NOML|RXf_USE_INTUIT_ML)
/* Do we have some sort of anchor? */
-#define RXf_IS_ANCHORED (1<<(RXf_BASE_SHIFT+10))
+#define RXf_IS_ANCHORED (1U<<(RXf_BASE_SHIFT+10))
/* Copy and tainted info */
-#define RXf_COPY_DONE (1<<(RXf_BASE_SHIFT+11))
+#define RXf_COPY_DONE (1U<<(RXf_BASE_SHIFT+11))
/* post-execution: $1 et al are tainted */
-#define RXf_TAINTED_SEEN (1<<(RXf_BASE_SHIFT+12))
+#define RXf_TAINTED_SEEN (1U<<(RXf_BASE_SHIFT+12))
/* this pattern was tainted during compilation */
-#define RXf_TAINTED (1<<(RXf_BASE_SHIFT+13))
+#define RXf_TAINTED (1U<<(RXf_BASE_SHIFT+13))
/* Flags indicating special patterns */
-#define RXf_START_ONLY (1<<(RXf_BASE_SHIFT+14)) /* Pattern is /^/ */
-#define RXf_SKIPWHITE (1<<(RXf_BASE_SHIFT+15)) /* Pattern is for a split " " */
-#define RXf_WHITE (1<<(RXf_BASE_SHIFT+16)) /* Pattern is /\s+/ */
+#define RXf_START_ONLY (1U<<(RXf_BASE_SHIFT+14)) /* Pattern is /^/ */
+#define RXf_SKIPWHITE (1U<<(RXf_BASE_SHIFT+15)) /* Pattern is for a */
+ /* split " " */
+#define RXf_WHITE (1U<<(RXf_BASE_SHIFT+16)) /* Pattern is /\s+/ */
#define RXf_NULL (1U<<(RXf_BASE_SHIFT+17)) /* Pattern is // */
/* See comments at the beginning of these defines about adding bits. The
/* structures for holding and saving the state maintained by regmatch() */
#ifndef MAX_RECURSE_EVAL_NOCHANGE_DEPTH
-#define MAX_RECURSE_EVAL_NOCHANGE_DEPTH 1000
+#define MAX_RECURSE_EVAL_NOCHANGE_DEPTH 10
#endif
typedef I32 CHECKPOINT;
struct {
/* this first element must match u.yes */
struct regmatch_state *prev_yes_state;
- struct regmatch_state *prev_eval;
struct regmatch_state *prev_curlyx;
+ struct regmatch_state *prev_eval;
REGEXP *prev_rex;
CHECKPOINT cp; /* remember current savestack indexes */
CHECKPOINT lastcp;
- U32 close_paren; /* which close bracket is our end */
+ U32 close_paren; /* which close bracket is our end (+1) */
regnode *B; /* the node following us */
+ char *prev_recurse_locinput;
} eval;
struct {
} u;
} regmatch_state;
+
+
/* how many regmatch_state structs to allocate as a single slab.
* We do it in 4K blocks for efficiency. The "3" is 2 for the next/prev
* pointers, plus 1 for any mythical malloc overhead. */
/*
- * Local variables:
- * c-indentation-style: bsd
- * c-basic-offset: 4
- * indent-tabs-mode: nil
- * End:
- *
* ex: set ts=8 sts=4 sw=4 et:
*/
https://perl5.git.perl.org / perl5.git / blobdiff