mktables: Update comments, variable names

[perl5.git] / regexp.h

diff --git a/regexp.h b/regexp.h
index 31b5be0..78fec57 100644 (file)
--- 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
@@ -233,7 +242,7 @@ and check for NULL.
     case SINGLE_PAT_MOD:    *(pmfl) |= RXf_PMf_SINGLELINE; break;   \
     case XTENDED_PAT_MOD:   *(pmfl) |= RXf_PMf_EXTENDED;   break
 
-/* Note, includes locale, unicode */
+/* 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)
 
@@ -276,13 +285,15 @@ and check for NULL.
  * 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
 
@@ -296,9 +307,10 @@ and check for NULL.
  * 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.
-*/
+/* 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__;
@@ -319,10 +331,11 @@ get_regex_charset_name(const U32 flags, STRLEN* const lenp)
         case REGEX_UNICODE_CHARSET: return UNICODE_PAT_MODS;
        case REGEX_ASCII_RESTRICTED_CHARSET: return ASCII_RESTRICT_PAT_MODS;
        case REGEX_ASCII_MORE_RESTRICTED_CHARSET:
-                                            return ASCII_MORE_RESTRICT_PAT_MODS;
+           *lenp = 2;
+           return ASCII_MORE_RESTRICT_PAT_MODS;
+        default:
+           return "?";     /* Unknown */
     }
-
-    return "?";            /* Unknown */
 }
 
 /* Anchor and GPOS related stuff */
@@ -365,14 +378,18 @@ get_regex_charset_name(const U32 flags, STRLEN* const lenp)
 
 /* 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))
-#define RXf_TAINTED            (1<<(RXf_BASE_SHIFT+18)) /* this pattern is tainted */
+/* 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 // */
+#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