regcomp.c - track parens related to CURLYX and CURLYM

This was originally a patch which made somewhat drastic changes to how
we represent capture buffers, which Dave M and I and are still
discussing offline and which has a larger impact than is acceptable to
address at the current time. As such I have reverted the controversial
parts of this patch for now, while keeping most of it intact even if in
some cases the changes are unused except for debugging purposes.

This patch still contains valuable changes, for instance teaching CURLYX
and CURLYM about how many parens there are before the curly[1] (which
will be useful in follow up patches even if stricly speaking they are
not directly used yet), tests and other cleanups. Also this patch is
sufficiently large that reverting it out would have a large effect on
the patches that were made on top of it.

Thus keeping most of this patch while eliminating the controversial
parts of it for now seemed the best approach, especially as some of the
changes it introduces and the follow up patches based on it are very
useful in cleaning up the structures we use to represent regops.

[1] Curly is the regexp internals term for quantifiers, named after
x{min,max} "curly brace" quantifiers.

1 files changed, 13 insertions, 0 deletions

diff --git a/regcomp.c b/regcomp.c
index 698fac645c..ef3d2557f9 100644
--- a/regcomp.c
+++ b/regcomp.c
@@ -4603,6 +4603,7 @@ S_regpiece(pTHX_ RExC_state_t *pRExC_state, I32 *flagp, U32 depth)
     const char * const origparse = RExC_parse;
     I32 min;
     I32 max = REG_INFTY;
+    I32 npar_before = RExC_npar-1;
 
     /* Save the original in case we change the emitted regop to a FAIL. */
     const regnode_offset orig_emit = RExC_emit;
@@ -4618,6 +4619,7 @@ S_regpiece(pTHX_ RExC_state_t *pRExC_state, I32 *flagp, U32 depth)
         RETURN_FAIL_ON_RESTART_OR_FLAGS(flags, flagp, TRYAGAIN);
         FAIL2("panic: regatom returned failure, flags=%#" UVxf, (UV) flags);
     }
+    I32 npar_after = RExC_npar-1;
 
     op = *RExC_parse;
     switch (op) {
@@ -4783,6 +4785,17 @@ S_regpiece(pTHX_ RExC_state_t *pRExC_state, I32 *flagp, U32 depth)
     ARG1_SET(REGNODE_p(ret), min);
     ARG2_SET(REGNODE_p(ret), max);
 
+    /* if we had a npar_after then we need to increment npar_before,
+     * we want to track the range of parens we need to reset each iteration
+     */
+    if (npar_after!=npar_before) {
+        ARG3_SET(REGNODE_p(ret), (U16)npar_before+1);
+        ARG4_SET(REGNODE_p(ret), (U16)npar_after);
+    } else {
+        ARG3_SET(REGNODE_p(ret), 0);
+        ARG4_SET(REGNODE_p(ret), 0);
+    }
+
   done_main_op:
 
     /* Process any greediness modifiers */