-#define ROPT_ANCH (ROPT_ANCH_BOL|ROPT_ANCH_MBOL|ROPT_ANCH_GPOS|ROPT_ANCH_SBOL)
-#define ROPT_ANCH_SINGLE (ROPT_ANCH_SBOL|ROPT_ANCH_GPOS)
-#define ROPT_ANCH_BOL 0x00001
-#define ROPT_ANCH_MBOL 0x00002
-#define ROPT_ANCH_SBOL 0x00004
-#define ROPT_ANCH_GPOS 0x00008
-#define ROPT_SKIP 0x00010
-#define ROPT_IMPLICIT 0x00020 /* Converted .* to ^.* */
-#define ROPT_NOSCAN 0x00040 /* Check-string always at start. */
-#define ROPT_GPOS_SEEN 0x00080
-#define ROPT_CHECK_ALL 0x00100
-#define ROPT_LOOKBEHIND_SEEN 0x00200
-#define ROPT_EVAL_SEEN 0x00400
-#define ROPT_SANY_SEEN 0x00800
-#define ROPT_CANY_SEEN 0x01000
-
-/* 0xf800 of reganch is used by PMf_COMPILETIME */
-
-#define ROPT_UTF8 0x10000
-#define ROPT_NAUGHTY 0x20000 /* how exponential is this pattern? */
-#define ROPT_COPY_DONE 0x40000 /* subbeg is a copy of the string */
-#define ROPT_TAINTED_SEEN 0x80000
-
-#define RE_USE_INTUIT_NOML 0x0100000 /* Best to intuit before matching */
-#define RE_USE_INTUIT_ML 0x0200000
-#define REINT_AUTORITATIVE_NOML 0x0400000 /* Can trust a positive answer */
-#define REINT_AUTORITATIVE_ML 0x0800000
-#define REINT_ONCE_NOML 0x1000000 /* Intuit can succed once only. */
-#define REINT_ONCE_ML 0x2000000
-#define RE_INTUIT_ONECHAR 0x4000000
-#define RE_INTUIT_TAIL 0x8000000
-
-#define RE_USE_INTUIT (RE_USE_INTUIT_NOML|RE_USE_INTUIT_ML)
-#define REINT_AUTORITATIVE (REINT_AUTORITATIVE_NOML|REINT_AUTORITATIVE_ML)
-#define REINT_ONCE (REINT_ONCE_NOML|REINT_ONCE_ML)
-
-#define RX_MATCH_TAINTED(prog) ((prog)->reganch & ROPT_TAINTED_SEEN)
-#define RX_MATCH_TAINTED_on(prog) ((prog)->reganch |= ROPT_TAINTED_SEEN)
-#define RX_MATCH_TAINTED_off(prog) ((prog)->reganch &= ~ROPT_TAINTED_SEEN)
+/* used for high speed searches */
+typedef struct re_scream_pos_data_s
+{
+ char **scream_olds; /* match pos */
+ I32 *scream_pos; /* Internal iterator of scream. */
+} re_scream_pos_data;
+
+/* regexp_engine structure. This is the dispatch table for regexes.
+ * Any regex engine implementation must be able to build one of these.
+ */
+typedef struct regexp_engine {
+ REGEXP* (*comp) (pTHX_ const SV * const pattern, const U32 flags);
+ I32 (*exec) (pTHX_ REGEXP * const rx, char* stringarg, char* strend,
+ char* strbeg, I32 minend, SV* screamer,
+ void* data, U32 flags);
+ char* (*intuit) (pTHX_ REGEXP * const rx, SV *sv, char *strpos,
+ char *strend, const U32 flags,
+ re_scream_pos_data *data);
+ SV* (*checkstr) (pTHX_ REGEXP * const rx);
+ void (*free) (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,
+ SV const * const value);
+ I32 (*numbered_buff_LENGTH) (pTHX_ REGEXP * const rx, const SV * const sv,
+ const I32 paren);
+ SV* (*named_buff) (pTHX_ REGEXP * const rx, SV * const key,
+ SV * const value, const U32 flags);
+ SV* (*named_buff_iter) (pTHX_ REGEXP * const rx, const SV * const lastkey,
+ const U32 flags);
+ SV* (*qr_package)(pTHX_ REGEXP * const rx);
+#ifdef USE_ITHREADS
+ void* (*dupe) (pTHX_ REGEXP * const rx, CLONE_PARAMS *param);
+#endif
+} regexp_engine;
+
+/*
+ These are passed to the numbered capture variable callbacks as the
+ paren name. >= 1 is reserved for actual numbered captures, i.e. $1,
+ $2 etc.
+*/
+#define RX_BUFF_IDX_PREMATCH -2 /* $` / ${^PREMATCH} */
+#define RX_BUFF_IDX_POSTMATCH -1 /* $' / ${^POSTMATCH} */
+#define RX_BUFF_IDX_FULLMATCH 0 /* $& / ${^MATCH} */
+
+/*
+ Flags that are passed to the named_buff and named_buff_iter
+ callbacks above. Those routines are called from universal.c via the
+ Tie::Hash::NamedCapture interface for %+ and %- and the re::
+ functions in the same file.
+*/
+
+/* The Tie::Hash::NamedCapture operation this is part of, if any */
+#define RXapif_FETCH 0x0001
+#define RXapif_STORE 0x0002
+#define RXapif_DELETE 0x0004
+#define RXapif_CLEAR 0x0008
+#define RXapif_EXISTS 0x0010
+#define RXapif_SCALAR 0x0020
+#define RXapif_FIRSTKEY 0x0040
+#define RXapif_NEXTKEY 0x0080
+
+/* Whether %+ or %- is being operated on */
+#define RXapif_ONE 0x0100 /* %+ */
+#define RXapif_ALL 0x0200 /* %- */
+
+/* Whether this is being called from a re:: function */
+#define RXapif_REGNAME 0x0400
+#define RXapif_REGNAMES 0x0800
+#define RXapif_REGNAMES_COUNT 0x1000
+
+/*
+=head1 REGEXP Functions
+
+=for apidoc Am|REGEXP *|SvRX|SV *sv
+
+Convenience macro to get the REGEXP from a SV. This is approximately
+equivalent to the following snippet:
+
+ if (SvMAGICAL(sv))
+ mg_get(sv);
+ if (SvROK(sv) &&
+ (tmpsv = (SV*)SvRV(sv)) &&
+ SvTYPE(tmpsv) == SVt_PVMG &&
+ (tmpmg = mg_find(tmpsv, PERL_MAGIC_qr)))
+ {
+ return (REGEXP *)tmpmg->mg_obj;
+ }
+
+NULL will be returned if a REGEXP* is not found.
+
+=for apidoc Am|bool|SvRXOK|SV* sv
+
+Returns a boolean indicating whether the SV contains qr magic
+(PERL_MAGIC_qr).
+
+If you want to do something with the REGEXP* later use SvRX instead
+and check for NULL.
+
+=cut
+*/
+
+#define SvRX(sv) (Perl_get_re_arg(aTHX_ sv))
+#define SvRXOK(sv) (Perl_get_re_arg(aTHX_ sv) ? TRUE : FALSE)
+
+
+/* Flags stored in regexp->extflags
+ * These are used by code external to the regexp engine
+ *
+ * Note that flags starting with RXf_PMf_ have exact equivalents
+ * stored in op_pmflags and which are defined in op.h, they are defined
+ * numerically here only for clarity.
+ *
+ * NOTE: if you modify any RXf flags you should run regen.pl or regcomp.pl
+ * so that regnodes.h is updated with the changes.
+ *
+ */
+
+/* Anchor and GPOS related stuff */
+#define RXf_ANCH_BOL 0x00000001
+#define RXf_ANCH_MBOL 0x00000002
+#define RXf_ANCH_SBOL 0x00000004
+#define RXf_ANCH_GPOS 0x00000008
+#define RXf_GPOS_SEEN 0x00000010
+#define RXf_GPOS_FLOAT 0x00000020
+/* two bits here */
+#define RXf_ANCH (RXf_ANCH_BOL|RXf_ANCH_MBOL|RXf_ANCH_GPOS|RXf_ANCH_SBOL)
+#define RXf_GPOS_CHECK (RXf_GPOS_SEEN|RXf_ANCH_GPOS)
+#define RXf_ANCH_SINGLE (RXf_ANCH_SBOL|RXf_ANCH_GPOS)
+
+/* Flags indicating special patterns */
+#define RXf_SKIPWHITE 0x00000100 /* Pattern is for a split / / */
+#define RXf_START_ONLY 0x00000200 /* Pattern is /^/ */
+#define RXf_WHITE 0x00000400 /* Pattern is /\s+/ */
+#define RXf_NULL 0x40000000 /* Pattern is // */
+
+/* 0x1F800 of extflags is used by (RXf_)PMf_COMPILETIME */
+#define RXf_PMf_LOCALE 0x00000800 /* use locale */
+#define RXf_PMf_MULTILINE 0x00001000 /* /m */
+#define RXf_PMf_SINGLELINE 0x00002000 /* /s */
+#define RXf_PMf_FOLD 0x00004000 /* /i */
+#define RXf_PMf_EXTENDED 0x00008000 /* /x */
+#define RXf_PMf_KEEPCOPY 0x00010000 /* /p */
+/* these flags are transfered from the PMOP->op_pmflags member during compilation */
+#define RXf_PMf_STD_PMMOD (RXf_PMf_MULTILINE|RXf_PMf_SINGLELINE|RXf_PMf_FOLD|RXf_PMf_EXTENDED)
+#define RXf_PMf_COMPILETIME (RXf_PMf_MULTILINE|RXf_PMf_SINGLELINE|RXf_PMf_LOCALE|RXf_PMf_FOLD|RXf_PMf_EXTENDED|RXf_PMf_KEEPCOPY)
+
+#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
+
+/* chars and strings used as regex pattern modifiers
+ * Singlular is a 'c'har, plural is a "string"
+ *
+ * NOTE, KEEPCOPY was originally 'k', but was changed to 'p' for preserve
+ * for compatibility reasons with Regexp::Common which highjacked (?k:...)
+ * for its own uses. So 'k' is out as well.
+ */
+#define EXEC_PAT_MOD 'e'
+#define KEEPCOPY_PAT_MOD 'p'
+#define ONCE_PAT_MOD 'o'
+#define GLOBAL_PAT_MOD 'g'
+#define CONTINUE_PAT_MOD 'c'
+#define MULTILINE_PAT_MOD 'm'
+#define SINGLE_PAT_MOD 's'
+#define IGNORE_PAT_MOD 'i'
+#define XTENDED_PAT_MOD 'x'
+
+#define ONCE_PAT_MODS "o"
+#define KEEPCOPY_PAT_MODS "p"
+#define EXEC_PAT_MODS "e"
+#define LOOP_PAT_MODS "gc"
+
+#define STD_PAT_MODS "msix"
+
+#define INT_PAT_MODS STD_PAT_MODS KEEPCOPY_PAT_MODS
+
+#define EXT_PAT_MODS ONCE_PAT_MODS KEEPCOPY_PAT_MODS
+#define QR_PAT_MODS STD_PAT_MODS EXT_PAT_MODS
+#define M_PAT_MODS QR_PAT_MODS LOOP_PAT_MODS
+#define S_PAT_MODS M_PAT_MODS EXEC_PAT_MODS
+
+/*
+ * NOTE: if you modify any RXf flags you should run regen.pl or regcomp.pl
+ * so that regnodes.h is updated with the changes.
+ *
+ */
+
+/* What we have seen */
+#define RXf_LOOKBEHIND_SEEN 0x00020000
+#define RXf_EVAL_SEEN 0x00040000
+#define RXf_CANY_SEEN 0x00080000
+
+/* Special */
+#define RXf_NOSCAN 0x00100000
+#define RXf_CHECK_ALL 0x00200000
+
+/* UTF8 related */
+#define RXf_UTF8 0x00400000
+#define RXf_MATCH_UTF8 0x00800000
+
+/* Intuit related */
+#define RXf_USE_INTUIT_NOML 0x01000000
+#define RXf_USE_INTUIT_ML 0x02000000
+#define RXf_INTUIT_TAIL 0x04000000
+
+/*
+ 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
+*/
+#define RXf_SPLIT 0x08000000
+
+#define RXf_USE_INTUIT (RXf_USE_INTUIT_NOML|RXf_USE_INTUIT_ML)
+
+/* Copy and tainted info */
+#define RXf_COPY_DONE 0x10000000
+#define RXf_TAINTED_SEEN 0x20000000
+#define RXf_TAINTED 0x80000000 /* this pattern is tainted */
+
+/*
+ * NOTE: if you modify any RXf flags you should run regen.pl or regcomp.pl
+ * so that regnodes.h is updated with the changes.
+ *
+ */
+
+#define RX_HAS_CUTGROUP(prog) ((prog)->intflags & PREGf_CUTGROUP_SEEN)
+#define RX_MATCH_TAINTED(prog) ((prog)->extflags & RXf_TAINTED_SEEN)
+#define RX_MATCH_TAINTED_on(prog) ((prog)->extflags |= RXf_TAINTED_SEEN)
+#define RX_MATCH_TAINTED_off(prog) ((prog)->extflags &= ~RXf_TAINTED_SEEN)