pcretest was not diagnosing characters > 0x7fffffff in 8-bit mode.

git-svn-id: svn://vcs.exim.org/pcre/code/trunk@1190 2f5784b3-3f2a-0410-8824-cb99058d5e15

4 files changed, 25 insertions, 0 deletions

diff --git a/ChangeLog b/ChangeLog
index 6d1fef4..606a2e4 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -137,6 +137,15 @@ Version 8.32
     provide fast pattern matching, so several sanity checks are not performed.
     However, feature tests are still performed. The new interface provides
     1.4x speedup compared to the old one.
+    
+29. If pcre_exec() or pcre_dfa_exec() was called with a negative value for
+    the subject string length, the error given was PCRE_ERROR_BADOFFSET, which 
+    was confusing. There is now a new error PCRE_ERROR_BADLENGTH for this case.
+    
+30. In 8-bit UTF-8 mode, pcretest failed to give an error for data codepoints
+    greater than 0x7fffffff (which cannot be represented in UTF-8, even under
+    the "old" RFC 2279). Instead, it ended up passing a negative length to 
+    pcre_exec().
 
 
 Version 8.31 06-July-2012
diff --git a/pcretest.c b/pcretest.c
index a503e59..6f768a7 100644
--- a/pcretest.c
+++ b/pcretest.c
@@ -4730,6 +4730,12 @@ while (!done)
 #ifndef NOUTF
         if (use_utf)
           {
+          if (c > 0x7fffffff)
+            {
+            fprintf(outfile, "** Character \\x{%x} is greater than 0x7fffffff "
+              "and so cannot be converted to UTF-8\n", c);
+            goto NEXT_DATA;     
+            }  
           q8 += ord2utf8(c, q8);
           }
         else
diff --git a/testdata/testinput15 b/testdata/testinput15
index c55f3a5..8753e5e 100644
--- a/testdata/testinput15
+++ b/testdata/testinput15
@@ -423,4 +423,8 @@ correctly, but that messes up comparisons). --/
 /\x{a0}+\s!/8BZT1
     \x{a0}\x20!
 
+/A/8
+  \x{ff000041}
+  \x{7f000041} 
+
 /-- End of testinput15 --/
diff --git a/testdata/testoutput15 b/testdata/testoutput15
index 9c99da2..b9d5aa2 100644
--- a/testdata/testoutput15
+++ b/testdata/testoutput15
@@ -1260,4 +1260,10 @@ Need char = \x{bf}
     \x{a0}\x20!
  0: \x{a0} !
 
+/A/8
+  \x{ff000041}
+** Character \x{ff000041} is greater than 0x7fffffff and so cannot be converted to UTF-8
+  \x{7f000041} 
+Error -10 (bad UTF-8 string) offset=0 reason=12
+
 /-- End of testinput15 --/