regexec.c: utf8 doesn't match non-utf8 self

Some regex patterns don't match a character with itself when the target
string is in utf8 and the pattern isn't, and the character is variant
under utf8.  (This means only Latin1-range characters in the pattern are
affected.)

The solution is to test for this case and use the utf8 representation of
the pattern character for the comparison.

1 files changed, 13 insertions, 1 deletions

diff --git a/t/re/pat.t b/t/re/pat.t
index c007880b8c..46681040e5 100644
--- a/t/re/pat.t
+++ b/t/re/pat.t
@@ -23,7 +23,7 @@ BEGIN {
 }
 
 
-plan tests => 398;  # Update this when adding/deleting tests.
+plan tests => 402;  # Update this when adding/deleting tests.
 
 run_tests() unless caller;
 
@@ -1072,6 +1072,18 @@ sub run_tests {
 
     }
 
+    {   # Some constructs with Latin1 characters cause a utf8 string not to
+        # match itself in non-utf8
+        my $c = "\xc0";
+        my $pattern = my $utf8_pattern = qr/((\xc0)+,?)/;
+        utf8::upgrade($utf8_pattern);
+        ok $c =~ $pattern, "\\xc0 =~ $pattern; Neither pattern nor target utf8";
+        ok $c =~ $utf8_pattern, "\\xc0 =~ $pattern; pattern utf8, target not";
+        utf8::upgrade($c);
+        ok $c =~ $pattern, "\\xc0 =~ $pattern; target utf8, pattern not";
+        ok $c =~ $utf8_pattern, "\\xc0 =~ $pattern; Both target and pattern utf8";
+    }
+
     {
         # Test that a regex followed by an operator and/or a statement modifier work
         # These tests use string-eval so that it reports a clean error when it fails