Revert "Update Unicode-Collate to CPAN version 0.70 and enable XS version"

[perl5.git] / regcomp.h

diff --git a/regcomp.h b/regcomp.h
index 6adb47a..48e270f 100644 (file)
--- a/regcomp.h
+++ b/regcomp.h
@@ -272,8 +272,9 @@ struct regnode_charclass_class {
 #undef STRING
 
 #define        OP(p)           ((p)->type)
-#define FLAGS(p)       ((p)->flags)    /* Caution: Doesn't apply to all \
-                                          regnode types */
+#define FLAGS(p)       ((p)->flags)    /* Caution: Doesn't apply to all      \
+                                          regnode types.  For some, it's the \
+                                          character set of the regnode */
 #define        OPERAND(p)      (((struct regnode_string *)p)->string)
 #define MASK(p)                ((char*)OPERAND(p))
 #define        STR_LEN(p)      (((struct regnode_string *)p)->str_len)
@@ -313,11 +314,15 @@ struct regnode_charclass_class {
 #define USE_UNI                0x01
 
 /* Flags for node->flags of ANYOF.  These are in short supply, so some games
- * are done to share them, as described below.  For flags that are applicable
- * to the synthetic start class (stc) only, with some work, they could be put
- * in the next-node field, or in an unused bit of the classflags field.  Once
- * the planned change to compile all the above-latin1 code points is done, then
- * the UNICODE_ALL bit can be freed up */
+ * are done to share them, as described below.  If necessary, the ANYOF_LOCALE
+ * and ANYOF_CLASS bits could be shared with a space penalty for locale nodes
+ * (and the code at the time this comment was written, is written so that all
+ * that is necessary to make the change would be to redefine the ANYOF_CLASS
+ * define).  Once the planned change to compile all the above-latin1 code points
+ * is done, then the UNICODE_ALL bit can be freed up.  If flags need to be
+ * added that are applicable to the synthetic start class only, with some work,
+ * they could be put in the next-node field, or in an unused bit of the
+ * classflags field. */
 
 #define ANYOF_LOCALE            0x01
 
@@ -332,6 +337,14 @@ struct regnode_charclass_class {
 
 #define ANYOF_INVERT            0x04
 
+/* EOS, meaning that it can match an empty string too, is used for the
+ * synthetic start class (ssc) only.  It can share the INVERT bit, as the ssc
+ * is never inverted.  The bit just needs to be turned off before regexec.c
+ * gets a hold of it so that regexec.c doesn't think it's inverted, but this
+ * happens automatically, as if the ssc can match an EOS, the ssc is discarded,
+ * and never passed to regexec.c */
+#define ANYOF_EOS              ANYOF_INVERT
+
 /* CLASS is never set unless LOCALE is too: has runtime \d, \w, [:posix:], ...
  * The non-locale ones are resolved at compile-time */
 #define ANYOF_CLASS     0x08
@@ -350,8 +363,9 @@ struct regnode_charclass_class {
 /* Matches every code point 0x100 and above*/
 #define ANYOF_UNICODE_ALL      0x40
 
-/* EOS used for regstclass only */
-#define ANYOF_EOS              0x80    /* Can match an empty string too */
+/* Match all Latin1 characters that aren't ASCII when the target string is not
+ * in utf8. */
+#define ANYOF_NON_UTF8_LATIN1_ALL 0x80
 
 #define ANYOF_FLAGS_ALL                0xff