Fix bug when there are unset groups prior to (*ACCEPT) within a capturing

group.


git-svn-id: svn://vcs.exim.org/pcre/code/trunk@1510 2f5784b3-3f2a-0410-8824-cb99058d5e15

4 files changed, 36 insertions, 1 deletions

diff --git a/ChangeLog b/ChangeLog
index 8abdfb5..06da1c4 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,6 +1,18 @@
 ChangeLog for PCRE
 ------------------
 
+Version 8.37 xx-xxx-201x
+------------------------
+
+1.  When an (*ACCEPT) is triggered inside capturing parentheses, it arranges 
+    for those parentheses to be closed with whatever has been captured so far. 
+    However, it was failing to mark any other groups between the hightest 
+    capture so far and the currrent group as "unset". Thus, the ovector for 
+    those groups contained whatever was previously there. An example is the 
+    pattern /(x)|((*ACCEPT))/ when matched against "abcd".
+
+
+
 Version 8.36 26-September-2014
 ------------------------------
 
diff --git a/pcre_exec.c b/pcre_exec.c
index 654eb9e..fdf7067 100644
--- a/pcre_exec.c
+++ b/pcre_exec.c
@@ -1474,7 +1474,18 @@ for (;;)
       md->offset_vector[offset] =
         md->offset_vector[md->offset_end - number];
       md->offset_vector[offset+1] = (int)(eptr - md->start_subject);
-      if (offset_top <= offset) offset_top = offset + 2;
+
+      /* If this group is at or above the current highwater mark, ensure that
+      any groups between the current high water mark and this group are marked
+      unset and then update the high water mark. */
+
+      if (offset >= offset_top)
+        {
+        register int *iptr = md->offset_vector + offset_top;
+        register int *iend = md->offset_vector + offset;
+        while (iptr < iend) *iptr++ = -1;
+        offset_top = offset + 2;
+        }
       }
     ecode += 1 + IMM2_SIZE;
     break;
diff --git a/testdata/testinput1 b/testdata/testinput1
index 123e3d3..091e307 100644
--- a/testdata/testinput1
+++ b/testdata/testinput1
@@ -5720,4 +5720,7 @@ AbcdCBefgBhiBqz
 /[\Q]a\E]+/
     aa]]
 
+/(?:((abcd))|(((?:(?:(?:(?:abc|(?:abcdef))))b)abcdefghi)abc)|((*ACCEPT)))/
+    1234abcd
+
 /-- End of testinput1 --/
diff --git a/testdata/testoutput1 b/testdata/testoutput1
index 5e71900..ba7ca37 100644
--- a/testdata/testoutput1
+++ b/testdata/testoutput1
@@ -9411,4 +9411,13 @@ No match
     aa]]
  0: aa]]
 
+/(?:((abcd))|(((?:(?:(?:(?:abc|(?:abcdef))))b)abcdefghi)abc)|((*ACCEPT)))/
+    1234abcd
+ 0: 
+ 1: <unset>
+ 2: <unset>
+ 3: <unset>
+ 4: <unset>
+ 5: 
+
 /-- End of testinput1 --/