[Pcre-svn] [103] code/trunk: Fix match_unset_backref bug.

Revision: 103

          http://www.exim.org/viewvc/pcre2?view=rev&revision=103
Author:   ph10
Date:     2014-10-10 17:42:03 +0100 (Fri, 10 Oct 2014)

Log Message:
-----------
Fix match_unset_backref bug.

Modified Paths:
--------------
    code/trunk/src/pcre2_match.c
    code/trunk/testdata/testinput2
    code/trunk/testdata/testoutput2

Modified: code/trunk/src/pcre2_match.c
===================================================================
--- code/trunk/src/pcre2_match.c    2014-10-10 16:16:44 UTC (rev 102)
+++ code/trunk/src/pcre2_match.c    2014-10-10 16:42:03 UTC (rev 103)
@@ -2763,19 +2763,20 @@
       continue;              /* With the main loop */
       }

-    /* Handle repeated back references. If a set group has length zero, just 
-    continue with the main loop, because it matches however many times. For an 
-    unset reference, in non-match-unset-backref mode, if the minimum is
-    zero, we can continue at the same level without recursion. For any other
-    minimum, carrying on will result in NOMATCH. */
+    /* Handle repeated back references. If a set group has length zero, just
+    continue with the main loop, because it matches however many times. For an
+    unset reference, if the minimum is zero, we can also just continue. We an
+    also continue if PCRE2_MATCH_UNSET_BACKREF is set, because this makes unset
+    group be have as a zero-length group. For any other unset cases, carrying
+    on will result in NOMATCH. */

     if (offset < offset_top && mb->ovector[offset] != PCRE2_UNSET)
       { 
       if (mb->ovector[offset] == mb->ovector[offset + 1]) continue;
       }
-    else
+    else  /* Group is not set */
       {
-      if (min == 0 && (mb->poptions & PCRE2_MATCH_UNSET_BACKREF) == 0)
+      if (min == 0 || (mb->poptions & PCRE2_MATCH_UNSET_BACKREF) != 0)
         continue; 
       }      

@@ -2856,7 +2857,7 @@
         eptr += slength;
         }

-      /* If the length matched for each repetiaion is the same as the length of 
+      /* If the length matched for each repetition is the same as the length of 
       the captured group, we can easily work backwards. This is the normal 
       case. However, in caseless UTF-8 mode there are pairs of case-equivalent 
       characters whose lengths (in terms of code units) differ. However, this

Modified: code/trunk/testdata/testinput2
===================================================================
--- code/trunk/testdata/testinput2    2014-10-10 16:16:44 UTC (rev 102)
+++ code/trunk/testdata/testinput2    2014-10-10 16:42:03 UTC (rev 103)
@@ -4003,4 +4003,7 @@
    abd
    xyd 

+/\k<A>*(?<A>aa)(?<A>bb)/match_unset_backref,dupnames
+    aabb
+
 # End of testinput2 

Modified: code/trunk/testdata/testoutput2
===================================================================
--- code/trunk/testdata/testoutput2    2014-10-10 16:16:44 UTC (rev 102)
+++ code/trunk/testdata/testoutput2    2014-10-10 16:42:03 UTC (rev 103)
@@ -13576,4 +13576,10 @@
    xyd 
  0: d

+/\k<A>*(?<A>aa)(?<A>bb)/match_unset_backref,dupnames
+    aabb
+ 0: aabb
+ 1: aa
+ 2: bb
+
 # End of testinput2