regexec.c - teach BRANCH and BRANCHJ nodes to reset capture buffers

In /((a)(b)|(a))+/ we should not end up with $2 and $4 being set at
the same time. When a branch fails it should reset any capture buffers
that might be touched by its branch.

We change BRANCH and BRANCHJ to store the number of parens before the
branch, and the number of parens after the branch was completed. When
a BRANCH operation fails, we clear the buffers it contains before we
continue on.

It is a bit more complex than it should be because we have BRANCHJ
and BRANCH. (One of these days we should merge them together.)

This is also made somewhat more complex because TRIE nodes are actually
branches, and may need to track capture buffers also, at two levels.
The overall TRIE op, and for jump tries especially where we emulate
the behavior of branches. So we have to do the same clearing logic if
a trie branch fails as well.

1 files changed, 51 insertions, 4 deletions

diff --git a/regexec.c b/regexec.c
index 6d7f52cb33..b112e077d5 100644
--- a/regexec.c
+++ b/regexec.c
@@ -350,6 +350,29 @@ S_regcppush(pTHX_ const regexp *rex, I32 parenfloor, U32 maxopenparen _pDEPTH)
     rex->lastparen = n;                     \
     rex->lastcloseparen = lcp;
 
+#define CAPTURE_CLEAR(from_ix, to_ix, str)                              \
+STMT_START {                                                            \
+    U16 my_ix;                                                          \
+    if (from_ix) {                                                      \
+        for ( my_ix = from_ix; my_ix <= to_ix; my_ix++ ) {              \
+            DEBUG_BUFFERS_r(Perl_re_exec_indentf( aTHX_                 \
+                    "CAPTURE_CLEAR %s \\%" IVdf ": "                    \
+                    "%" IVdf "(%" IVdf ") .. %" IVdf                    \
+                    " => "                                              \
+                    "%" IVdf "(%" IVdf ") .. %" IVdf                    \
+                    "\n",                                               \
+                depth, str, (IV)my_ix,                                  \
+                (IV)rex->offs[my_ix].start,                             \
+                (IV)rex->offs[my_ix].start_tmp,                         \
+                (IV)rex->offs[my_ix].end,                               \
+                (IV)-1, (IV)-1, (IV)-1));                               \
+            rex->offs[my_ix].start = -1;                                \
+            rex->offs[my_ix].start_tmp = -1;                            \
+            rex->offs[my_ix].end = -1;                                  \
+        }                                                               \
+    }                                                                   \
+} STMT_END
+
 
 STATIC void
 S_regcppop(pTHX_ regexp *rex, U32 *maxopenparen_p _pDEPTH)
@@ -6640,6 +6663,11 @@ S_regmatch(pTHX_ regmatch_info *reginfo, char *startpos, regnode *prog)
                 /* what trie are we using right now */
                 reg_trie_data * const trie
                     = (reg_trie_data*)rexi->data->data[ ARG( scan ) ];
+                ST.before_paren = trie->before_paren;
+                ST.after_paren = trie->after_paren;
+                assert(ST.before_paren<=rex->nparens);
+                assert(ST.after_paren<=rex->nparens);
+
                 HV * widecharmap = MUTABLE_HV(rexi->data->data[ ARG( scan ) + 1 ]);
                 U32 state = trie->startstate;
 
@@ -6689,6 +6717,8 @@ S_regmatch(pTHX_ regmatch_info *reginfo, char *startpos, regnode *prog)
                 U32 accepted = 0; /* have we seen any accepting states? */
 
                 ST.jump = trie->jump;
+                ST.j_before_paren = trie->j_before_paren;
+                ST.j_after_paren= trie->j_after_paren;
                 ST.me = scan;
                 ST.firstpos = NULL;
                 ST.longfold = FALSE; /* char longer if folded => it's harder */
@@ -6800,6 +6830,10 @@ S_regmatch(pTHX_ regmatch_info *reginfo, char *startpos, regnode *prog)
                  * rest of the branch */
                 REGCP_UNWIND(ST.cp);
                 UNWIND_PAREN(ST.lastparen, ST.lastcloseparen);
+                if (ST.after_paren) {
+                    assert(ST.before_paren<=rex->nparens && ST.after_paren<=rex->nparens);
+                    CAPTURE_CLEAR(ST.before_paren+1, ST.after_paren,"TRIE_next_fail");
+                }
             }
             if (!--ST.accepted) {
                 DEBUG_EXECUTE_r({
@@ -6889,10 +6923,16 @@ S_regmatch(pTHX_ regmatch_info *reginfo, char *startpos, regnode *prog)
                         uc += chars;
                 }
             }
+            if (ST.jump && ST.jump[ST.nextword]) {
+                scan = ST.me + ST.jump[ST.nextword];
+                ST.before_paren = ST.j_before_paren[ST.nextword];
+                assert(ST.before_paren <= rex->nparens);
+                ST.after_paren = ST.j_after_paren[ST.nextword];
+                assert(ST.after_paren <= rex->nparens);
+            } else {
+                scan = ST.me + NEXT_OFF(ST.me);
+            }
 
-            scan = ST.me + ((ST.jump && ST.jump[ST.nextword])
-                            ? ST.jump[ST.nextword]
-                            : NEXT_OFF(ST.me));
 
             DEBUG_EXECUTE_r({
                 Perl_re_exec_indentf( aTHX_  "%sTRIE matched word #%d, continuing%s\n",
@@ -8957,9 +8997,15 @@ NULL
             next = scan + ARG(scan);
             if (next == scan)
                 next = NULL;
-            /* FALLTHROUGH */
+            ST.before_paren = ARG2La(scan);
+            ST.after_paren = ARG2Lb(scan);
+            goto branch_logic;
+            NOT_REACHED; /* NOTREACHED */
 
         case BRANCH:	    /*  /(...|A|...)/ */
+            ST.before_paren = ARGa(scan);
+            ST.after_paren = ARGb(scan);
+          branch_logic:
             scan = REGNODE_AFTER_opcode(scan,state_num); /* scan now points to inner node */
             assert(scan);
             ST.lastparen = rex->lastparen;
@@ -9004,6 +9050,7 @@ NULL
             }
             REGCP_UNWIND(ST.cp);
             UNWIND_PAREN(ST.lastparen, ST.lastcloseparen);
+            CAPTURE_CLEAR(ST.before_paren+1,ST.after_paren,"BRANCH_next_fail");
             scan = ST.next_branch;
             /* no more branches? */
             if (!scan || (OP(scan) != BRANCH && OP(scan) != BRANCHJ)) {