Changeset 1230

Timestamp:

2000-06-23T11:51:50+12:00 (24 years ago)

Author:

gwp

Message:

Added an additional H1 metadata field that extracts the text
between the the first <h1> and </H1> tags. Tidied up the
other metadata fields a little.

File:

• trunk/gsdl/perllib/plugins/HTMLPlug.pm (modified) (6 diffs)

trunk/gsdl/perllib/plugins/HTMLPlug.pm

@@ -69 +69 @@
     print STDERR "   -metadata_fields       Comma separated list of metadata fields to attempt to extract.\n";
     print STDERR "                          Defaults to 'Title'.\n";
-    print STDERR "                          Use `first200` to get the first 100 characters of the body.\n";
+    print STDERR "                          Use `first200` to get the first 200 characters of the body.\n";
+    print STDERR "                          Use `H1` to get the text inside the first <H1> and </H1> tags in the text.\n";
     print STDERR "   -w3mir                 Set if w3mir was used to generate input file structure.\n";
     print STDERR "                          w3mir \n";
@@ -350 +351 @@
 
     foreach my $field (split /,/, $self->{'metadata_fields'}) {
-    
+
     # don't need to extract field if it was passed in from a previous 
     # (recursive) plugin
@@ -368 +369 @@
     }
     
-    # special case for Title metadata - try <title> tags
-    # then first 100 characters of text
+    # TITLE: extract the document title
     
     if ($field =~ /^title$/i) {
@@ -379 +379 @@
             if ($title =~ /\w/) {
             $title =~ s/\s+/ /gs;
+            $title =~ s/^\s+//;
+            $title =~ s/\s+$//;
             $doc_obj->add_utf8_metadata ($section, $field, $title);
             next;
@@ -389 +391 @@
         $tmptext =~ s/\s+/ /gs;
         $tmptext =~ s/<[^>]*>//g;
-        my $title = substr ($tmptext, 0, 100);
-        $doc_obj->add_utf8_metadata ($section, $field, $title);
-    }
-
-    # if the user requests the first chars as metadata the extract it
+        $tmptext = substr ($tmptext, 0, 100);
+        $tmptext =~ s/^\s+//;
+        $tmptext =~ s/\s+$//;
+        $tmptext =~ s/\s\S*$/.../;
+        $doc_obj->add_utf8_metadata ($section, $field, $tmptext);
+        next;
+    }
+
+    # FIRST200: extract the first 200 characters as metadata
 
     if ($field =~ /^first200$/i) {
@@ -401 +407 @@
         $tmptext =~ s/<[^>]*>//g;
         $tmptext = substr ($tmptext, 0, 200);
+        $tmptext =~ s/^\s+//;
+        $tmptext =~ s/\s+$//;
         $tmptext =~ s/\s\S*$/.../;
         $doc_obj->add_utf8_metadata ($section, $field, $tmptext);
+        next;
+    }
+
+    # H1: extract the text between the first <H1> and </H1> tags
+    if ($field =~ /^H1$/i) {
+        my $tmptext = $$textref;
+        $tmptext =~ s/\s+/ /gs;
+        $tmptext =~ s/.*<H1[^>]*>//i;
+        $tmptext =~ s/<\/H1[^>]*>.*//i;
+        $tmptext =~ s/^\s+//;
+        $tmptext =~ s/\s+$//;
+        $doc_obj->add_utf8_metadata ($section, $field, $tmptext);
+        next;
     }
     }