Changeset 5066

Timestamp:

2003-07-30T10:46:47+12:00 (21 years ago)

Author:

kjdon

Message:

changed HTMLPLug to extract multiple values for the same metadata name

File:

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

trunk/gsdl/perllib/plugins/HTMLPlug.pm

@@ -594 +594 @@
     my ($textref, $metadata, $doc_obj, $section) = @_;
     my $outhandle = $self->{'outhandle'};
-
     # if we don't want metadata, we may as well not be here ...
     return if (!defined $self->{'metadata_fields'});
@@ -617 +616 @@
     }
     }
-
+    
     foreach my $field (split /,/, $self->{'metadata_fields'}) {
-
+    my $found = 0;
     # don't need to extract field if it was passed in from a previous 
     # (recursive) plugin
@@ -625 +624 @@
 
     # see if there's a <meta> tag for this field
-    if ($$textref =~ /<meta(\s*?)(?:name|http-equiv)\s*=\s*\"?$field\"?([^>]*)/is) {
+    while ($$textref =~ /<meta(\s*?)(?:name|http-equiv)\s*=\s*\"?$field\"?([^>]*)/isg) {
         my $content = $1 . $2;
         if ($content =~ /content\s*=\s*\"?(.*)\"?/is) {
@@ -636 +635 @@
             print $outhandle " extracted \"$field\" metadata \"$value\"\n" 
             if ($self->{'verbosity'} > 2);
-            next;
+            $found = 1;
         }
         }
     }
-    
+    next if $found;
     # TITLE: extract the document title
     
@@ -681 +680 @@
     }
 
-
         # tag: extract the text between the first <H1> and </H1> tags
         if ($field =~ /^tag[a-z0-9]+$/i) {
@@ -704 +702 @@
             }
             next;
-        }
+        }    
     }
 }