Changeset 2845

Timestamp:

2001-11-23T12:38:00+13:00 (22 years ago)

Author:

sjboddie

Message:

Caught SplitPlug up with recent changes

File:

• trunk/gsdl/perllib/plugins/SplitPlug.pm (modified) (5 diffs)

trunk/gsdl/perllib/plugins/SplitPlug.pm

@@ -117 +117 @@
     my $plugin_name = ref ($self);
     $file =~ s/^[\/\\]+//; # $file often begins with / so we'll tidy it up
-    
-    my ($language, $encoding);
-    if ($self->{'input_encoding'} eq "auto") {
-    # use textcat to automatically work out the input encoding and language
-    ($language, $encoding) = $self->get_language_encoding ($filename);
-    
-    } elsif ($self->{'extract_language'}) {
-    # use textcat to get language metadata
-    ($language, $extracted_encoding) = $self->get_language_encoding ($filename);
-    $encoding = $self->{'input_encoding'};
-    
-    if ($extracted_encoding ne $encoding && $self->{'verbosity'}) {
-        print $outhandle "$plugin_name: WARNING: $file was read using $encoding encoding but ";
-        print $outhandle "appears to be encoded as $extracted_encoding.\n";
-    }
-    
-    } else {
-    $language = $self->{'default_language'};
-    $encoding = $self->{'input_encoding'};
-    }
+
+    # Do encoding stuff
+    my ($language, $encoding) = $self->textcat_get_language_encoding ($filename);
 
     # Read in file ($text will be in utf8)
@@ -146 +129 @@
     print $outhandle "$plugin_name: ERROR: $file contains no text\n" 
         if $self->{'verbosity'};
+
+    my $failhandle = $self->{'failhandle'};
+    print $failhandle "$file: " . ref($self) . ": file contains no text\n";
+    $self->{'num_not_processed'} ++;
+
     return 0;
     }
@@ -162 +150 @@
     foreach $segtext (@segments) {
     $segment++;
-    
+
     # create a new document
     my $doc_obj = new doc ($filename, "indexed_doc");
@@ -168 +156 @@
     $doc_obj->add_utf8_metadata($doc_obj->get_top_section(), "Language", $language);
     $doc_obj->add_utf8_metadata($doc_obj->get_top_section(), "Encoding", $encoding);
+    my ($filemeta) = $file =~ /([^\\\/]+)$/;
+    $doc_obj->add_utf8_metadata($doc_obj->get_top_section(), "Source", &ghtml::dmsafe($filemeta));
+    if ($self->{'cover_image'}) {
+      $self->associate_cover_image($doc_obj, $filename);
+    }
 
     # Calculate a "base" document ID.
@@ -195 +188 @@
     $self->set_OID($doc_obj, $id, $segment);
 
-    
     # process the document
     $processor->process($doc_obj);
+
+    $self->{'num_processed'} ++;
     }