regcomp.c - add optimistic eval (*{ ... }) and (**{ ... })

This adds (*{ ... }) and (**{ ... }) as equivalents to (?{ ... }) and
(??{ ... }). The only difference being that the star variants are
"optimisitic" and are defined to never disable optimisations. This is
especially relevant now that use of (?{ ... }) prevents important
optimisations anywhere in the pattern, instead of the older and inconsistent
rules where it only affected the parts that contained the EVAL.

It is also very useful for injecting debugging style expressions to the
pattern to understand what the regex engine is actually doing. The older
style (?{ ... }) variants would change the regex engines behavior, meaning
this was not as effective a tool as it could have been.

Similarly it is now possible to test that a given regex optimisation
works correctly using (*{ ... }), which was not possible with (?{ ... }).

1 files changed, 5 insertions, 0 deletions

diff --git a/regcomp.h b/regcomp.h
index 80d7dbe465..532c5e1327 100644
--- a/regcomp.h
+++ b/regcomp.h
@@ -108,6 +108,7 @@ typedef struct regexp_internal {
 #define PREGf_ANCH_SBOL         0x00000800
 #define PREGf_ANCH_GPOS         0x00001000
 #define PREGf_RECURSE_SEEN      0x00002000
+#define PREGf_PESSIMIZE_SEEN    0x00004000
 
 #define PREGf_ANCH              \
     ( PREGf_ANCH_SBOL | PREGf_ANCH_GPOS | PREGf_ANCH_MBOL )
@@ -976,6 +977,7 @@ ARGp_SET_inline(struct regnode *node, SV *ptr) {
 #define REG_UNFOLDED_MULTI_SEEN             0x00000400
 /* spare */
 #define REG_UNBOUNDED_QUANTIFIER_SEEN       0x00001000
+#define REG_PESSIMIZE_SEEN                  0x00002000
 
 
 START_EXTERN_C
@@ -1426,6 +1428,9 @@ typedef enum {
 #include "reginline.h"
 #endif
 
+#define EVAL_OPTIMISTIC_FLAG    128
+#define EVAL_FLAGS_MASK         (EVAL_OPTIMISTIC_FLAG-1)
+
 #endif /* PERL_REGCOMP_H_ */
 
 /*