Changeset 16646 for gsdl/trunk/perllib/plugins/CJKTextSegmenter.pm

Timestamp:

2008-08-04T13:45:45+12:00 (16 years ago)

Author:

kjdon

Message:

now segments all metadata as well as text

File:

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

gsdl/trunk/perllib/plugins/CJKTextSegmenter.pm

@@ -73 +73 @@
     while (defined $thissection) {
         
+        # segment the text
         my $text = $doc_obj->get_text($thissection);
         $text = &cnseg::segment($text);
         $doc_obj->add_utf8_text($thissection, $text);
+
+        # and now the metadata
+        my $metadataref = $doc_obj->get_all_metadata($thissection);
+        foreach my $data (@$metadataref) {
+        $data->[1] = &cnseg::segment($data->[1]);
+        }
         $thissection = $doc_obj->get_next_section ($thissection);
     }