Fix bugs relating to the use of (*SKIP) etc in assertions.

git-svn-id: svn://vcs.exim.org/pcre/code/trunk@473 2f5784b3-3f2a-0410-8824-cb99058d5e15

7 files changed, 125 insertions, 10 deletions

diff --git a/ChangeLog b/ChangeLog
index d7adfca..fb86a98 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -5,17 +5,28 @@ Version 8.01 11-Dec-09
 ----------------------
 
 1.  If a pattern contained a conditional subpattern with only one branch (in
-    particular, this includes all (DEFINE) patterns), a call to pcre_study() 
-    computed the wrong minimum data length (which is of course zero for such 
+    particular, this includes all (DEFINE) patterns), a call to pcre_study()
+    computed the wrong minimum data length (which is of course zero for such
     subpatterns).
-    
-2.  For patterns such as (?i)a(?-i)b|c where an option setting at the start of 
+
+2.  For patterns such as (?i)a(?-i)b|c where an option setting at the start of
     the pattern is reset in the first branch, pcre_compile() failed with
     "internal error: code overflow at offset...". This happened only when
-    the reset was to the original external option setting. (An optimization 
-    abstracts leading options settings into an external setting, which was the 
+    the reset was to the original external option setting. (An optimization
+    abstracts leading options settings into an external setting, which was the
     cause of this.)
 
+3.  A pattern such as ^(?!a(*SKIP)b) where a negative assertion contained one
+    of the verbs SKIP, PRUNE, or COMMIT, did not work correctly. When the
+    assertion pattern did not match (meaning that the assertion was true), it
+    was incorrectly treated as false if the SKIP had been reached during the
+    matching. This also applied to assertions used as conditions.
+
+4.  If an item that is not supported by pcre_dfa_exec() was encountered in an
+    assertion subpattern, including such a pattern used as a condition,
+    unpredictable results occurred, instead of the error return
+    PCRE_ERROR_DFA_UITEM.
+
 
 Version 8.00 19-Oct-09
 ----------------------
diff --git a/pcre_dfa_exec.c b/pcre_dfa_exec.c
index a4a0ae2..5c1875a 100644
--- a/pcre_dfa_exec.c
+++ b/pcre_dfa_exec.c
@@ -7,7 +7,7 @@ and semantics are as close as possible to those of the Perl 5 language (but see
 below for why this module is different).
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2009 University of Cambridge
+           Copyright (c) 1997-2010 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -2298,7 +2298,8 @@ for (;;)
           ims,                                  /* the current ims flags */
           rlevel,                               /* function recursion level */
           recursing);                           /* pass on regex recursion */
-
+          
+        if (rc == PCRE_ERROR_DFA_UITEM) return rc;
         if ((rc >= 0) == (codevalue == OP_ASSERT || codevalue == OP_ASSERTBACK))
             { ADD_ACTIVE(endasscode + LINK_SIZE + 1 - start_code, 0); }
         }
@@ -2389,6 +2390,7 @@ for (;;)
             rlevel,                               /* function recursion level */
             recursing);                           /* pass on regex recursion */
 
+          if (rc == PCRE_ERROR_DFA_UITEM) return rc;
           if ((rc >= 0) ==
                 (condcode == OP_ASSERT || condcode == OP_ASSERTBACK))
             { ADD_ACTIVE(endasscode + LINK_SIZE + 1 - start_code, 0); }
diff --git a/pcre_exec.c b/pcre_exec.c
index fb27e17..fd6866b 100644
--- a/pcre_exec.c
+++ b/pcre_exec.c
@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2009 University of Cambridge
+           Copyright (c) 1997-2010 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -1133,7 +1133,9 @@ for (;;)
     offset_top = md->end_offset_top;
     continue;
 
-    /* Negative assertion: all branches must fail to match */
+    /* Negative assertion: all branches must fail to match. Encountering SKIP,
+    PRUNE, or COMMIT means we must assume failure without checking subsequent 
+    branches. */
 
     case OP_ASSERT_NOT:
     case OP_ASSERTBACK_NOT:
@@ -1142,6 +1144,11 @@ for (;;)
       RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, 0,
         RM5);
       if (rrc == MATCH_MATCH) RRETURN(MATCH_NOMATCH);
+      if (rrc == MATCH_SKIP || rrc == MATCH_PRUNE || rrc == MATCH_COMMIT)
+        {
+        do ecode += GET(ecode,1); while (*ecode == OP_ALT);
+        break; 
+        }  
       if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc);
       ecode += GET(ecode,1);
       }
diff --git a/testdata/testinput11 b/testdata/testinput11
index ad896fd..501ac3c 100644
--- a/testdata/testinput11
+++ b/testdata/testinput11
@@ -336,4 +336,25 @@
 /(?<pn> \( ( [^()]++ | (?&pn) )* \) )/x
     (ab(cd)ef)
 
+/^(?!a(*SKIP)b)/
+    ac
+    
+/^(?=a(*SKIP)b|ac)/
+    ** Failers
+    ac
+    
+/^(?=a(*THEN)b|ac)/
+    ac
+    
+/^(?=a(*PRUNE)b)/
+    ab  
+    ** Failers 
+    ac
+
+/^(?=a(*ACCEPT)b)/
+    ac
+
+/^(?(?!a(*SKIP)b))/
+    ac
+
 /-- End of testinput11 --/
diff --git a/testdata/testinput7 b/testdata/testinput7
index 710d9ee..5d27311 100644
--- a/testdata/testinput7
+++ b/testdata/testinput7
@@ -4542,4 +4542,22 @@
     CAD
     BAD    
 
+/^(?!a(*SKIP)b)/
+    ac
+    
+/^(?=a(*SKIP)b|ac)/
+    ** Failers
+    ac
+    
+/^(?=a(*THEN)b|ac)/
+    ac
+    
+/^(?=a(*PRUNE)b)/
+    ab  
+    ** Failers 
+    ac
+
+/^(?(?!a(*SKIP)b))/
+    ac
+
 /-- End of testinput7 --/
diff --git a/testdata/testoutput11 b/testdata/testoutput11
index e901e0b..e5d3df7 100644
--- a/testdata/testoutput11
+++ b/testdata/testoutput11
@@ -712,4 +712,34 @@ No match
  1: (ab(cd)ef)
  2: ef
 
+/^(?!a(*SKIP)b)/
+    ac
+ 0: 
+    
+/^(?=a(*SKIP)b|ac)/
+    ** Failers
+No match
+    ac
+No match
+    
+/^(?=a(*THEN)b|ac)/
+    ac
+ 0: 
+    
+/^(?=a(*PRUNE)b)/
+    ab  
+ 0: 
+    ** Failers 
+No match
+    ac
+No match
+
+/^(?=a(*ACCEPT)b)/
+    ac
+ 0: 
+
+/^(?(?!a(*SKIP)b))/
+    ac
+ 0: 
+
 /-- End of testinput11 --/
diff --git a/testdata/testoutput7 b/testdata/testoutput7
index c6c9df4..2aab80d 100644
--- a/testdata/testoutput7
+++ b/testdata/testoutput7
@@ -7584,4 +7584,30 @@ No match
     BAD    
 No match
 
+/^(?!a(*SKIP)b)/
+    ac
+Error -16
+    
+/^(?=a(*SKIP)b|ac)/
+    ** Failers
+No match
+    ac
+Error -16
+    
+/^(?=a(*THEN)b|ac)/
+    ac
+Error -16
+    
+/^(?=a(*PRUNE)b)/
+    ab  
+Error -16
+    ** Failers 
+No match
+    ac
+Error -16
+
+/^(?(?!a(*SKIP)b))/
+    ac
+Error -16
+
 /-- End of testinput7 --/