Changeset 3247

Timestamp:

2002-07-11T17:59:16+12:00 (22 years ago)

Author:

jrm21

Message:

Modified automatic title extraction to also recognise utf-8 nbsp as well as
just plain HTML  

File:

• trunk/gsdl/perllib/plugins/HTMLPlug.pm (modified) (1 diff)

trunk/gsdl/perllib/plugins/HTMLPlug.pm

@@ -579 +579 @@
         $tmptext =~ s/<\/([^>]+)><\1>//g; # (eg) </b><b> - no space
         $tmptext =~ s/<[^>]*>/ /g;
-        $tmptext =~ s/&nbsp;/ /g;
+        $tmptext =~ s/(?:&nbsp;|\xc2\xa0)/ /g; # utf-8 for nbsp...
         $tmptext =~ s/^\s+//s;
         $tmptext =~ s/\s+$//;
         $tmptext =~ s/\s+/ /gs;
-        $tmptext =~ s/$self->{'title_sub'}// if ($self->{'title_sub'});
+        $tmptext =~ s/^$self->{'title_sub'}// if ($self->{'title_sub'});
+        $tmptext =~ s/^\s+//s; # in case title_sub introduced any...
         $tmptext = substr ($tmptext, 0, 100);
         $tmptext =~ s/\s\S*$/.../;