+#define RXp_PAREN_NAMES(rx) ((rx)->paren_names)
+
+/* 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_ SV * const pattern, 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))
+ sv = MUTABLE_SV(SvRV(sv));
+ if (SvTYPE(sv) == SVt_REGEXP)
+ return (REGEXP*) sv;
+
+NULL will be returned if a REGEXP* is not found.
+
+=for apidoc Am|bool|SvRXOK|SV* sv
+
+Returns a boolean indicating whether the SV (or the one it references)
+is a REGEXP.
+
+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 the flags whose names start with RXf_PMf_ are defined in
+ * op_reg_common.h, being copied from the parallel flags of op_pmflags
+ *
+ * NOTE: if you modify any RXf flags you should run regen.pl or
+ * regen/regcomp.pl so that regnodes.h is updated with the changes.
+ *
+ */
+
+#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
+
+/* 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)
+
+/* chars and strings used as regex pattern modifiers
+ * Singular 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 DEFAULT_PAT_MOD '^' /* Short for all the default modifiers */
+#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 NONDESTRUCT_PAT_MOD 'r'
+#define LOCALE_PAT_MOD 'l'
+#define UNICODE_PAT_MOD 'u'
+#define DEPENDS_PAT_MOD 'd'
+#define ASCII_RESTRICT_PAT_MOD 'a'
+
+#define ONCE_PAT_MODS "o"
+#define KEEPCOPY_PAT_MODS "p"
+#define EXEC_PAT_MODS "e"
+#define LOOP_PAT_MODS "gc"
+#define NONDESTRUCT_PAT_MODS "r"
+#define LOCALE_PAT_MODS "l"
+#define UNICODE_PAT_MODS "u"
+#define DEPENDS_PAT_MODS "d"
+#define ASCII_RESTRICT_PAT_MODS "a"
+#define ASCII_MORE_RESTRICT_PAT_MODS "aa"
+
+/* 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 "msix"
+
+#define CHARSET_PAT_MODS ASCII_RESTRICT_PAT_MODS DEPENDS_PAT_MODS LOCALE_PAT_MODS UNICODE_PAT_MODS
+
+/* This string is expected by XS_re_regexp_pattern() in universal.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 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 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
+
+/*
+ * NOTE: if you modify any RXf flags you should run regen.pl or
+ * regen/regcomp.pl so that regnodes.h is updated with the changes.
+ *
+ */
+
+/* Leave some space, so future bit allocations can go either in the shared or
+ * unshared area without affecting binary compatibility */
+#define RXf_BASE_SHIFT (_RXf_PMf_SHIFT_NEXT+1)
+
+/* embed.pl doesn't yet know how to handle static inline functions, so
+ manually decorate them here with gcc-style attributes.
+*/
+PERL_STATIC_INLINE const char *
+get_regex_charset_name(const U32 flags, STRLEN* const lenp)
+ __attribute__warn_unused_result__;
+
+#define MAX_CHARSET_NAME_LENGTH 2
+
+PERL_STATIC_INLINE const char *
+get_regex_charset_name(const U32 flags, STRLEN* const lenp)
+{
+ /* Returns a string that corresponds to the name of the regex character set
+ * given by 'flags', and *lenp is set the length of that string, which
+ * cannot exceed MAX_CHARSET_NAME_LENGTH characters */
+
+ *lenp = 1;
+ switch (get_regex_charset(flags)) {
+ case REGEX_DEPENDS_CHARSET: return DEPENDS_PAT_MODS;
+ case REGEX_LOCALE_CHARSET: return LOCALE_PAT_MODS;
+ case REGEX_UNICODE_CHARSET: return UNICODE_PAT_MODS;
+ case REGEX_ASCII_RESTRICTED_CHARSET: return ASCII_RESTRICT_PAT_MODS;
+ case REGEX_ASCII_MORE_RESTRICTED_CHARSET:
+ *lenp = 2;
+ return ASCII_MORE_RESTRICT_PAT_MODS;
+ }
+
+ return "?"; /* Unknown */
+}
+
+/* Anchor and GPOS related stuff */
+#define RXf_ANCH_BOL (1<<(RXf_BASE_SHIFT+0))
+#define RXf_ANCH_MBOL (1<<(RXf_BASE_SHIFT+1))
+#define RXf_ANCH_SBOL (1<<(RXf_BASE_SHIFT+2))
+#define RXf_ANCH_GPOS (1<<(RXf_BASE_SHIFT+3))
+#define RXf_GPOS_SEEN (1<<(RXf_BASE_SHIFT+4))
+#define RXf_GPOS_FLOAT (1<<(RXf_BASE_SHIFT+5))
+/* 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)
+
+/* What we have seen */
+#define RXf_LOOKBEHIND_SEEN (1<<(RXf_BASE_SHIFT+6))
+#define RXf_EVAL_SEEN (1<<(RXf_BASE_SHIFT+7))
+#define RXf_CANY_SEEN (1<<(RXf_BASE_SHIFT+8))
+
+/* Special */
+#define RXf_NOSCAN (1<<(RXf_BASE_SHIFT+9))
+#define RXf_CHECK_ALL (1<<(RXf_BASE_SHIFT+10))
+
+/* UTF8 related */
+#define RXf_MATCH_UTF8 (1<<(RXf_BASE_SHIFT+11))
+
+/* Intuit related */
+#define RXf_USE_INTUIT_NOML (1<<(RXf_BASE_SHIFT+12))
+#define RXf_USE_INTUIT_ML (1<<(RXf_BASE_SHIFT+13))
+#define RXf_INTUIT_TAIL (1<<(RXf_BASE_SHIFT+14))
+
+/*
+ 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 (1<<(RXf_BASE_SHIFT+15))
+
+#define RXf_USE_INTUIT (RXf_USE_INTUIT_NOML|RXf_USE_INTUIT_ML)
+
+/* Copy and tainted info */
+#define RXf_COPY_DONE (1<<(RXf_BASE_SHIFT+16))
+
+/* during execution: pattern temporarily tainted by executing locale ops;
+ * post-execution: $1 et al are tainted */
+#define RXf_TAINTED_SEEN (1<<(RXf_BASE_SHIFT+17))
+/* this pattern was tainted during compilation */
+#define RXf_TAINTED (1<<(RXf_BASE_SHIFT+18))
+
+/* Flags indicating special patterns */
+#define RXf_START_ONLY (1<<(RXf_BASE_SHIFT+19)) /* Pattern is /^/ */
+#define RXf_SKIPWHITE (1<<(RXf_BASE_SHIFT+20)) /* Pattern is for a split / / */
+#define RXf_WHITE (1<<(RXf_BASE_SHIFT+21)) /* Pattern is /\s+/ */
+#define RXf_NULL (1<<(RXf_BASE_SHIFT+22)) /* Pattern is // */
+#if RXf_BASE_SHIFT+22 > 31
+# error Too many RXf_PMf bits used. See regnodes.h for any spare in middle
+#endif
+
+/*
+ * NOTE: if you modify any RXf flags you should run regen.pl or
+ * regen/regcomp.pl so that regnodes.h is updated with the changes.
+ *
+ */
+
+#define RX_HAS_CUTGROUP(prog) ((prog)->intflags & PREGf_CUTGROUP_SEEN)
+#define RXp_MATCH_TAINTED(prog) (RXp_EXTFLAGS(prog) & RXf_TAINTED_SEEN)
+#define RX_MATCH_TAINTED(prog) (RX_EXTFLAGS(prog) & RXf_TAINTED_SEEN)
+#define RX_MATCH_TAINTED_on(prog) (RX_EXTFLAGS(prog) |= RXf_TAINTED_SEEN)
+#define RX_MATCH_TAINTED_off(prog) (RX_EXTFLAGS(prog) &= ~RXf_TAINTED_SEEN)