What started as a small nit (the charnames test, nit found

be Hugo), ballooned a bit... the goal is Larry's wish that
illegal Unicode (such as U+FFFF) by default doesn't warn,
since what if somebody WANTS to create illegal Unicode?
Now getting close to this in the regex runtime.
(Also, fix more of my fixation that BOM would be U+FFFE.)

p4raw-id: //depot/perl@15689

1 files changed, 14 insertions, 12 deletions

diff --git a/lib/Unicode/Collate.pm b/lib/Unicode/Collate.pm
index 8522a79f2c..43446162a9 100644
--- a/lib/Unicode/Collate.pm
+++ b/lib/Unicode/Collate.pm
@@ -137,24 +137,26 @@ sub parseEntry
   # get element
   my($e, $k) = split /;/, $line;
   my @e = _getHexArray($e);
-  $ele = pack('U*', @e);
+  { no warnings 'utf8'; $ele = pack('U*', @e); }
   return if defined $self->{undefChar} && $ele =~ /$self->{undefChar}/;
 
   # get sort key
-  if(
+  { no warnings 'utf8';
+    if(
      defined $self->{ignoreName} && $name =~ /$self->{ignoreName}/ ||
      defined $self->{ignoreChar} && $ele  =~ /$self->{ignoreChar}/
-  )
-  {
-     $self->{entries}{$ele} = $self->{ignored}{$ele} = 1;
-  }
-  else
-  {
-    foreach my $arr ($k =~ /\[(\S+)\]/g) {
-      my $var = $arr =~ /\*/;
-      push @key, $self->altCE( $var, _getHexArray($arr) );
+       )
+    {
+	$self->{entries}{$ele} = $self->{ignored}{$ele} = 1;
+    }
+    else
+    {
+	foreach my $arr ($k =~ /\[(\S+)\]/g) {
+	    my $var = $arr =~ /\*/;
+	    push @key, $self->altCE( $var, _getHexArray($arr) );
+	}
+	$self->{entries}{$ele} = \@key;
     }
-    $self->{entries}{$ele} = \@key;
   }
   $self->{maxlength}{ord $ele} = scalar @e if @e > 1;
 }