*
*/
-#include "op_reg_common.h"
-
/*
* Definitions etc. for regexp(3) routines.
*
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;
- }
+ 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 contains qr magic
-(PERL_MAGIC_qr).
+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.
/* 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 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 regcomp.pl
- * so that regnodes.h is updated with the changes.
+ * 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.
*
*/
-/* 0x3F of extflags is used by (RXf_)PMf_COMPILETIME
- * If you change these you need to change the equivalent flags in op.h, and
- * vice versa. These need to be ordered so that the msix are contiguous
- * starting at bit 0, followed by the p; bit 0 is because of the shift below
- * being 0; see STD_PAT_MODS and INT_PAT_MODS below for the contiguity cause */
-/* the flags above are transfered from the PMOP->op_pmflags member during
- * compilation */
-#define RXf_PMf_STD_PMMOD_SHIFT 0
+#include "op_reg_common.h"
+
#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 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
- * Singlular is a 'c'har, plural is a "string"
+ * 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 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 0 of extflags; the next character is bit 1,
- * etc. */
+ * 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 0 of extflags; the next
- * character is bit 1, etc. */
+ * 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
+#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 regcomp.pl
- * so that regnodes.h is updated with the changes.
+ * 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)
+
+/* Manually decorate this function with gcc-style attributes just to
+ * avoid having to restructure the header files and their called order,
+ * as proto.h would have to be included before this file, and isn't */
+
+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;
+ default:
+ return "?"; /* Unknown */
+ }
+}
+
/* Anchor and GPOS related stuff */
-#define RXf_ANCH_BOL (1<<(_RXf_PMf_SHIFT+3))
-#define RXf_ANCH_MBOL (1<<(_RXf_PMf_SHIFT+4))
-#define RXf_ANCH_SBOL (1<<(_RXf_PMf_SHIFT+5))
-#define RXf_ANCH_GPOS (1<<(_RXf_PMf_SHIFT+6))
-#define RXf_GPOS_SEEN (1<<(_RXf_PMf_SHIFT+7))
-#define RXf_GPOS_FLOAT (1<<(_RXf_PMf_SHIFT+8))
+#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_PMf_SHIFT+9))
-#define RXf_EVAL_SEEN (1<<(_RXf_PMf_SHIFT+10))
-#define RXf_CANY_SEEN (1<<(_RXf_PMf_SHIFT+11))
+#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_PMf_SHIFT+12))
-#define RXf_CHECK_ALL (1<<(_RXf_PMf_SHIFT+13))
+#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_PMf_SHIFT+15))
+#define RXf_MATCH_UTF8 (1<<(RXf_BASE_SHIFT+11))
/* Intuit related */
-#define RXf_USE_INTUIT_NOML (1<<(_RXf_PMf_SHIFT+16))
-#define RXf_USE_INTUIT_ML (1<<(_RXf_PMf_SHIFT+17))
-#define RXf_INTUIT_TAIL (1<<(_RXf_PMf_SHIFT+18))
+#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_PMf_SHIFT+19))
+#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_PMf_SHIFT+20))
-#define RXf_TAINTED_SEEN (1<<(_RXf_PMf_SHIFT+21))
-#define RXf_TAINTED (1<<(_RXf_PMf_SHIFT+22)) /* this pattern is tainted */
+#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_PMf_SHIFT+23)) /* Pattern is /^/ */
-#define RXf_SKIPWHITE (1<<(_RXf_PMf_SHIFT+24)) /* Pattern is for a split / / */
-#define RXf_WHITE (1<<(_RXf_PMf_SHIFT+25)) /* Pattern is /\s+/ */
-#define RXf_NULL (1<<(_RXf_PMf_SHIFT+26)) /* Pattern is // */
-#if _RXf_PMf_SHIFT+23 > 31
+#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 (1U<<(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 regcomp.pl
- * so that regnodes.h is updated with the changes.
+ * 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.
*
*/
#endif /* PLUGGABLE_RE_EXTENSION */
-/* Stuff that needs to be included in the plugable extension goes below here */
+/* Stuff that needs to be included in the pluggable extension goes below here */
#ifdef PERL_OLD_COPY_ON_WRITE
#define RX_MATCH_COPY_FREE(rx) \