X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/1ad4ec548311231461a68d0e66335fc3abf1540f..ce712c886b5979bd55a7bc9aa9140b5aa62f8f82:/regexp.h

diff --git a/regexp.h b/regexp.h
index f041177..78fec57 100644
--- a/regexp.h
+++ b/regexp.h
@@ -55,6 +55,15 @@ typedef struct regexp_paren_pair {
     I32 end;
 } regexp_paren_pair;
 
+#if defined(PERL_IN_REGCOMP_C) || defined(PERL_IN_UTF8_C)
+#define _invlist_union(a, b, output) _invlist_union_maybe_complement_2nd(a, b, FALSE, output)
+#define _invlist_intersection(a, b, output) _invlist_intersection_maybe_complement_2nd(a, b, FALSE, output)
+
+/* Subtracting b from a leaves in a everything that was there that isn't in b,
+ * that is the intersection of a with b's complement */
+#define _invlist_subtract(a, b, output) _invlist_intersection_maybe_complement_2nd(a, b, TRUE, output)
+#endif
+
 /*
   The regexp/REGEXP struct, see L<perlreapi> for further documentation
   on the individual fields. The struct is ordered so that the most
@@ -190,20 +199,17 @@ 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;
-    }
+    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.
@@ -221,8 +227,8 @@ and check for NULL.
  * 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.
  *
  */
 
@@ -236,13 +242,18 @@ and check for NULL.
     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'
@@ -253,35 +264,79 @@ and check for NULL.
 #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
+#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.
  *
  */
 
-#define RXf_BASE_SHIFT (_RXf_PMf_SHIFT_NEXT+2)
+/* 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_BASE_SHIFT+0))
@@ -305,39 +360,43 @@ and check for NULL.
 #define RXf_CHECK_ALL   	(1<<(RXf_BASE_SHIFT+10))
 
 /* UTF8 related */
-#define RXf_MATCH_UTF8  	(1<<(RXf_BASE_SHIFT+12))
+#define RXf_MATCH_UTF8  	(1<<(RXf_BASE_SHIFT+11))
 
 /* Intuit related */
-#define RXf_USE_INTUIT_NOML	(1<<(RXf_BASE_SHIFT+13))
-#define RXf_USE_INTUIT_ML	(1<<(RXf_BASE_SHIFT+14))
-#define RXf_INTUIT_TAIL 	(1<<(RXf_BASE_SHIFT+15))
+#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+16))
+#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+17))
-#define RXf_TAINTED_SEEN	(1<<(RXf_BASE_SHIFT+18))
-#define RXf_TAINTED		(1<<(RXf_BASE_SHIFT+19)) /* 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_BASE_SHIFT+20)) /* Pattern is /^/ */
-#define RXf_SKIPWHITE		(1<<(RXf_BASE_SHIFT+21)) /* Pattern is for a split / / */
-#define RXf_WHITE		(1<<(RXf_BASE_SHIFT+22)) /* Pattern is /\s+/ */
-#define RXf_NULL		(1<<(RXf_BASE_SHIFT+23)) /* Pattern is // */
-#if RXf_BASE_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.
  *
  */
 
@@ -423,7 +482,7 @@ and check for NULL.
 
 #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) \