Fix bugs with \K in atomic groups, subroutines, and assertions.

git-svn-id: svn://vcs.exim.org/pcre/code/trunk@500 2f5784b3-3f2a-0410-8824-cb99058d5e15

9 files changed, 136 insertions, 12 deletions

diff --git a/ChangeLog b/ChangeLog
index 33d6ea0..f14172c 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -38,6 +38,13 @@ Version 8.02 01-Mar-2010
     counting zeros. There was no check for running off the end of the string,
     which could happen if a new error number was added without updating the
     string. 
+    
+10. \K gave a compile-time error if it appeared in a lookbehind assersion. 
+    
+11. \K was not working if it appeared in an atomic group or in a group that
+    was called as a "subroutine", or in an assertion. Perl 5.11 documents that 
+    \K is "not well defined" if used in an assertion. PCRE now accepts it if 
+    the assertion is positive, but not if it is negative. 
 
 
 Version 8.01 19-Jan-2010
diff --git a/doc/pcrepattern.3 b/doc/pcrepattern.3
index c5f20eb..8849872 100644
--- a/doc/pcrepattern.3
+++ b/doc/pcrepattern.3
@@ -737,6 +737,10 @@ For example, when the pattern
   (foo)\eKbar
 .sp
 matches "foobar", the first substring is still set to "foo".
+.P
+Perl documents that the use of \eK within assertions is "not well defined". In 
+PCRE, \eK is acted upon when it occurs inside positive assertions, but is 
+ignored in negative assertions.
 .
 .
 .\" HTML <a name="smallassertions"></a>
@@ -2453,6 +2457,6 @@ Cambridge CB2 3QH, England.
 .rs
 .sp
 .nf
-Last updated: 01 March 2010
+Last updated: 06 March 2010
 Copyright (c) 1997-2010 University of Cambridge.
 .fi
diff --git a/pcre_compile.c b/pcre_compile.c
index e89819a..b9cc701 100644
--- a/pcre_compile.c
+++ b/pcre_compile.c
@@ -1450,6 +1450,7 @@ for (;;)
     case OP_CALLOUT:
     case OP_SOD:
     case OP_SOM:
+    case OP_SET_SOM:
     case OP_EOD:
     case OP_EODN:
     case OP_CIRC:
diff --git a/pcre_exec.c b/pcre_exec.c
index c3bb970..2734723 100644
--- a/pcre_exec.c
+++ b/pcre_exec.c
@@ -1070,7 +1070,6 @@ for (;;)
       memmove(md->offset_vector, rec->offset_save,
         rec->saved_max * sizeof(int));
       offset_top = rec->save_offset_top;
-      mstart = rec->save_start;
       ims = original_ims;
       ecode = rec->after_call;
       break;
@@ -1114,7 +1113,11 @@ for (;;)
       {
       RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, 0,
         RM4);
-      if (rrc == MATCH_MATCH) break;
+      if (rrc == MATCH_MATCH) 
+        {
+        mstart = md->start_match_ptr;   /* In case \K reset it */
+        break;
+        } 
       if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc);
       ecode += GET(ecode, 1);
       }
@@ -1267,9 +1270,7 @@ for (;;)
 
       memcpy(new_recursive.offset_save, md->offset_vector,
             new_recursive.saved_max * sizeof(int));
-      new_recursive.save_start = mstart;
       new_recursive.save_offset_top = offset_top;
-      mstart = eptr;
 
       /* OK, now we can do the recursion. For each top-level alternative we
       restore the offset and recursion data. */
@@ -1316,7 +1317,8 @@ for (;;)
     a move back into the brackets. Friedl calls these "atomic" subpatterns.
     Check the alternative branches in turn - the matching won't pass the KET
     for this kind of subpattern. If any one branch matches, we carry on as at
-    the end of a normal bracket, leaving the subject pointer. */
+    the end of a normal bracket, leaving the subject pointer, but resetting
+    the start-of-match value in case it was changed by \K. */
 
     case OP_ONCE:
     prev = ecode;
@@ -1325,7 +1327,11 @@ for (;;)
     do
       {
       RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0, RM7);
-      if (rrc == MATCH_MATCH) break;
+      if (rrc == MATCH_MATCH) 
+        {
+        mstart = md->start_match_ptr;
+        break;
+        } 
       if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc);
       ecode += GET(ecode,1);
       }
@@ -1444,9 +1450,10 @@ for (;;)
       }
     else saved_eptr = NULL;
 
-    /* If we are at the end of an assertion group, stop matching and return
-    MATCH_MATCH, but record the current high water mark for use by positive
-    assertions. Do this also for the "once" (atomic) groups. */
+    /* If we are at the end of an assertion group or an atomic group, stop
+    matching and return MATCH_MATCH, but record the current high water mark for
+    use by positive assertions. We also need to record the match start in case
+    it was changed by \K. */
 
     if (*prev == OP_ASSERT || *prev == OP_ASSERT_NOT ||
         *prev == OP_ASSERTBACK || *prev == OP_ASSERTBACK_NOT ||
@@ -1454,6 +1461,7 @@ for (;;)
       {
       md->end_match_ptr = eptr;      /* For ONCE */
       md->end_offset_top = offset_top;
+      md->start_match_ptr = mstart;
       RRETURN(MATCH_MATCH);
       }
 
@@ -1490,7 +1498,6 @@ for (;;)
         recursion_info *rec = md->recursive;
         DPRINTF(("Recursion (%d) succeeded - continuing\n", number));
         md->recursive = rec->prevrec;
-        mstart = rec->save_start;
         memcpy(md->offset_vector, rec->offset_save,
           rec->saved_max * sizeof(int));
         offset_top = rec->save_offset_top;
diff --git a/pcre_internal.h b/pcre_internal.h
index 3cb8b46..67a3475 100644
--- a/pcre_internal.h
+++ b/pcre_internal.h
@@ -1617,7 +1617,6 @@ typedef struct recursion_info {
   struct recursion_info *prevrec; /* Previous recursion record (or NULL) */
   int group_num;                /* Number of group that was called */
   const uschar *after_call;     /* "Return value": points after the call in the expr */
-  USPTR save_start;             /* Old value of mstart */
   int *offset_save;             /* Pointer to start of saved offsets */
   int saved_max;                /* Number of saved offsets */
   int save_offset_top;          /* Current value of offset_top */
diff --git a/testdata/testinput11 b/testdata/testinput11
index 501ac3c..d1054ef 100644
--- a/testdata/testinput11
+++ b/testdata/testinput11
@@ -357,4 +357,26 @@
 /^(?(?!a(*SKIP)b))/
     ac
 
+/(?>a\Kb)/
+    ab
+
+/((?>a\Kb))/
+    ab
+
+/(a\Kb)/
+    ab
+    
+/^a\Kcz|ac/
+    ac
+    
+/(?>a\Kbz|ab)/
+    ab 
+
+/^(?&t)(?(DEFINE)(?<t>a\Kb))$/
+    ab
+
+/^([^()]|\((?1)*\))*$/
+    a(b)c
+    a(b(c)d)e 
+
 /-- End of testinput11 --/
diff --git a/testdata/testinput2 b/testdata/testinput2
index 5233183..dc20e82 100644
--- a/testdata/testinput2
+++ b/testdata/testinput2
@@ -3208,4 +3208,26 @@ a random value. /Ix
 
 /^(?&t)*(?(DEFINE)(?<t>.))$/BZ
 
+/ -- The first four of these are not in the Perl 5.10 test because Perl 
+     documents that the use of \K in assertions is "not well defined". The
+     last is here because Perl gives the match as "b" rather than "ab". I
+     believe this to be a Perl bug. --/  
+      
+/(?=a\Kb)ab/
+    ab 
+
+/(?!a\Kb)ac/
+    ac 
+    
+/^abc(?<=b\Kc)d/
+    abcd
+
+/^abc(?<!b\Kq)d/
+    abcd
+
+/(?>a\Kb)z|(ab)/
+    ab 
+
+/----------------------/
+
 /-- End of testinput2 --/
diff --git a/testdata/testoutput11 b/testdata/testoutput11
index e5d3df7..4fb5efd 100644
--- a/testdata/testoutput11
+++ b/testdata/testoutput11
@@ -742,4 +742,38 @@ No match
     ac
  0: 
 
+/(?>a\Kb)/
+    ab
+ 0: b
+
+/((?>a\Kb))/
+    ab
+ 0: b
+ 1: ab
+
+/(a\Kb)/
+    ab
+ 0: b
+ 1: ab
+    
+/^a\Kcz|ac/
+    ac
+ 0: ac
+    
+/(?>a\Kbz|ab)/
+    ab 
+ 0: ab
+
+/^(?&t)(?(DEFINE)(?<t>a\Kb))$/
+    ab
+ 0: b
+
+/^([^()]|\((?1)*\))*$/
+    a(b)c
+ 0: a(b)c
+ 1: c
+    a(b(c)d)e 
+ 0: a(b(c)d)e
+ 1: e
+
 /-- End of testinput11 --/
diff --git a/testdata/testoutput2 b/testdata/testoutput2
index 8271ca6..1b3c2f9 100644
--- a/testdata/testoutput2
+++ b/testdata/testoutput2
@@ -10637,4 +10637,32 @@ No match
         End
 ------------------------------------------------------------------
 
+/ -- The first four of these are not in the Perl 5.10 test because Perl 
+     documents that the use of \K in assertions is "not well defined". The
+     last is here because Perl gives the match as "b" rather than "ab". I
+     believe this to be a Perl bug. --/  
+      
+/(?=a\Kb)ab/
+    ab 
+ 0: b
+
+/(?!a\Kb)ac/
+    ac 
+ 0: ac
+    
+/^abc(?<=b\Kc)d/
+    abcd
+ 0: cd
+
+/^abc(?<!b\Kq)d/
+    abcd
+ 0: abcd
+
+/(?>a\Kb)z|(ab)/
+    ab 
+ 0: ab
+ 1: ab
+
+/----------------------/
+
 /-- End of testinput2 --/