Initial setup to accommodate /aa regex modifier

This changes the bits to add a new charset type for /aa, and other bookkeeping
for it.

diff --git a/op.h b/op.h
index 43be1f7..35aa48d 100644 (file)
--- a/op.h
+++ b/op.h
@@ -367,7 +367,7 @@ struct pmop {
 
 /* Leave some space, so future bit allocations can go either in the shared or
  * unshared area without affecting binary compatibility */
-#define PMf_BASE_SHIFT (_RXf_PMf_SHIFT_NEXT+7)
+#define PMf_BASE_SHIFT (_RXf_PMf_SHIFT_NEXT+6)
 
 /* taint $1 etc. if target tainted */
 #define PMf_RETAINT    (1<<(PMf_BASE_SHIFT+0))

diff --git a/op_reg_common.h b/op_reg_common.h
index f509650..4c3fe2c 100644 (file)
--- a/op_reg_common.h
+++ b/op_reg_common.h
@@ -41,11 +41,12 @@ typedef enum {
     REGEX_DEPENDS_CHARSET = 0,
     REGEX_LOCALE_CHARSET,
     REGEX_UNICODE_CHARSET,
-    REGEX_ASCII_RESTRICTED_CHARSET
+    REGEX_ASCII_RESTRICTED_CHARSET,
+    REGEX_ASCII_MORE_RESTRICTED_CHARSET
 } regex_charset;
 
 #define _RXf_PMf_CHARSET_SHIFT ((RXf_PMf_STD_PMMOD_SHIFT)+5)
-#define RXf_PMf_CHARSET (3 << (_RXf_PMf_CHARSET_SHIFT)) /* 2 bits */
+#define RXf_PMf_CHARSET (7 << (_RXf_PMf_CHARSET_SHIFT)) /* 3 bits */
 
 /* embed.pl doesn't yet know how to handle static inline functions, so
    manually decorate them here with gcc-style attributes.
@@ -78,7 +79,7 @@ get_regex_charset(const U32 flags)
 
 /* Next available bit after the above.  Name begins with '_' so won't be
  * exported by B */
-#define _RXf_PMf_SHIFT_NEXT (RXf_PMf_STD_PMMOD_SHIFT+7)
+#define _RXf_PMf_SHIFT_NEXT (RXf_PMf_STD_PMMOD_SHIFT+8)
 
 /* Mask of the above bits.  These need to be transferred from op_pmflags to
  * re->extflags during compilation */

diff --git a/regexp.h b/regexp.h
index 9780297..31b5be0 100644 (file)
--- a/regexp.h
+++ b/regexp.h
@@ -269,6 +269,7 @@ and check for NULL.
 #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
@@ -293,7 +294,7 @@ and check for NULL.
 
 /* 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+2)
+#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.
@@ -302,7 +303,7 @@ PERL_STATIC_INLINE const char *
 get_regex_charset_name(const U32 flags, STRLEN* const lenp)
     __attribute__warn_unused_result__;
 
-#define MAX_CHARSET_NAME_LENGTH 1
+#define MAX_CHARSET_NAME_LENGTH 2
 
 PERL_STATIC_INLINE const char *
 get_regex_charset_name(const U32 flags, STRLEN* const lenp)
@@ -317,6 +318,8 @@ get_regex_charset_name(const U32 flags, STRLEN* const lenp)
         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:
+                                            return ASCII_MORE_RESTRICT_PAT_MODS;
     }
 
     return "?";            /* Unknown */

diff --git a/regnodes.h b/regnodes.h
index 72c93ff..b1cc6b3 100644 (file)
--- a/regnodes.h
+++ b/regnodes.h
@@ -715,15 +715,15 @@ EXTCONST char * const PL_reg_name[] = {
 EXTCONST char * PL_reg_extflags_name[];
 #else
 EXTCONST char * const PL_reg_extflags_name[] = {
-       /* Bits in extflags defined: 11111111111111111111111001111111 */
+       /* Bits in extflags defined: 11111111111111111111111011111111 */
        "MULTILINE",        /* 0x00000001 */
        "SINGLELINE",       /* 0x00000002 */
        "FOLD",             /* 0x00000004 */
        "EXTENDED",         /* 0x00000008 */
        "KEEPCOPY",         /* 0x00000010 */
-       "CHARSET",          /* 0x00000060 */
-       "CHARSET",          /* 0x00000060 */
-       "UNUSED_BIT_7",     /* 0x00000080 */
+       "CHARSET",          /* 0x000000e0 */
+       "CHARSET",          /* 0x000000e0 */
+       "CHARSET",          /* 0x000000e0 */
        "UNUSED_BIT_8",     /* 0x00000100 */
        "ANCH_BOL",         /* 0x00000200 */
        "ANCH_MBOL",        /* 0x00000400 */