Fix \C backtracking in UTF-8 issue for repeated character classes, wh…

…ich were

overlooked when it was fixed for other repeats. 


git-svn-id: svn:https://vcs.exim.org/pcre/code/trunk@1725 2f5784b3-3f2a-0410-8824-cb99058d5e15

ChangeLog

@@ -44,6 +44,11 @@ non-zero starting offset, unset capturing groups with lower numbers than a
 group that did capture something were not being correctly returned as "unset" 
 (that is, with offset values of -1).
 
+10. Matching the pattern /(*UTF)\C[^\v]+\x80/ against an 8-bit string
+containing multi-code-unit characters caused bad behaviour and possibly a
+crash. This issue was fixed for other kinds of repeat in release 8.37 by change
+38, but repeating character classes were overlooked.
+
 
 Version 8.41 05-July-2017
 -------------------------

pcre_exec.c

@@ -3053,7 +3053,7 @@ for (;;)
  {
  RMATCH(eptr, ecode, offset_top, md, eptrb, RM18);
  if (rrc != MATCH_NOMATCH) RRETURN(rrc);
- if (eptr-- == pp) break; /* Stop if tried at original pos */
+ if (eptr-- <= pp) break; /* Stop if tried at original pos */
  BACKCHAR(eptr);
  }
  }
@@ -3210,7 +3210,7 @@ for (;;)
  {
  RMATCH(eptr, ecode, offset_top, md, eptrb, RM21);
  if (rrc != MATCH_NOMATCH) RRETURN(rrc);
- if (eptr-- == pp) break; /* Stop if tried at original pos */
+ if (eptr-- <= pp) break; /* Stop if tried at original pos */
 #ifdef SUPPORT_UTF
  if (utf) BACKCHAR(eptr);
 #endif

testdata/testinput5

@@ -798,4 +798,10 @@
 /(?<=\K\x{17f})/8G+
  \x{17f}\x{17f}\x{17f}\x{17f}\x{17f}
 
+/\C[^\v]+\x80/8
+ [AΏBŀC]
+
+/\C[^\d]+\x80/8
+ [AΏBŀC]
+
 /-- End of testinput5 --/

testdata/testoutput5

@@ -1942,4 +1942,12 @@ Need char = 'z'
  0: \x{17f}
  0+ 
 
+/\C[^\v]+\x80/8
+ [AΏBŀC]
+No match
+
+/\C[^\d]+\x80/8
+ [AΏBŀC]
+No match
+
 /-- End of testinput5 --/