Changeset 1694 for trunk/gsdl/perllib/mgppbuildproc.pm

Timestamp:

2000-11-23T11:55:50+13:00 (23 years ago)

Author:

kjm18

Message:

updated to resembled the corresponding mg updated versions

File:

• trunk/gsdl/perllib/mgppbuildproc.pm (modified) (9 diffs)

trunk/gsdl/perllib/mgppbuildproc.pm

@@ -42 +42 @@
 
 sub new {
-    my ($class, $collection, $source_dir, $build_dir, $verbosity) = @_;
+    my ($class, $collection, $source_dir, $build_dir, 
+    $verbosity, $outhandle) = @_;
     my $self = new docproc ();
+
+    # outhandle is where all the debugging info goes
+    # output_handle is where the output of the plugins is piped
+    # to (i.e. mg, gdbm etc.)
+    $outhandle = STDERR unless defined $outhandle;
 
     $self->{'collection'} = $collection;
@@ -59 +65 @@
     $self->{'num_sections'} = 0;
     $self->{'num_bytes'} = 0;
+    $self->{'num_processed_bytes'} = 0;
+    $self->{'outhandle'} = $outhandle;
 
     $self->{'indexing_text'} = 0;
@@ -70 +78 @@
     $self->{'num_docs'} = 0;
     $self->{'num_sections'} = 0;
+    $self->{'num_processed_bytes'} = 0;
     $self->{'num_bytes'} = 0;
 }
@@ -85 +94 @@
 }
 
+# num_bytes is the actual number of bytes in the collection
+# this is normally the same as what's processed during text compression
 sub get_num_bytes {
     my $self = shift (@_);
 
     return $self->{'num_bytes'};
+}
+
+# num_processed_bytes is the number of bytes actually passed
+# to mgpp for the current index
+sub get_num_processed_bytes {
+    my $self = shift (@_);
+
+    return $self->{'num_processed_bytes'};
 }
 
@@ -127 +146 @@
 }
 
+sub get_index {
+    my $self = shift (@_);
+
+    return $self->{'index'};
+}
+
 sub set_classifiers {
     my $self = shift (@_);
@@ -139 +164 @@
 
     $self->{'indexing_text'} = $indexing_text;
+}
+
+sub get_indexing_text {
+    my $self = shift (@_);
+
+    return $self->{'indexing_text'};
 }
 
@@ -240 +271 @@
     else { print $handle "[$doc_OID.$section]\n"; }
 
-    # output the fact that this document is a document
-    #print $handle "<doctype>doc\n";
+    # output the fact that this document is a document (unless doctype
+    # has been set to something else from within a plugin
+    my $dtype = $doc_obj->get_metadata_element ($section, "doctype");
+    if (!defined $dtype || $dtype !~ /\w/) {
+        print $handle "<doctype>doc\n";
+    }
 
     # output whether this node contains text
@@ -251 +286 @@
 
     # output all the section metadata
-    my $found_doctype = 0;
+    #my $found_doctype = 0;
     my $metadata = $doc_obj->get_all_metadata ($section);
     foreach $pair (@$metadata) {
         my ($field, $value) = (@$pair);
 
-        $found_doctype = 1 if $field eq "doctype";
+        #$found_doctype = 1 if $field eq "doctype";
         if ($field ne "Identifier" && $field !~ /^gsdl/ && 
         defined $value && $value ne "") {
@@ -282 +317 @@
     # (unless doctype was already output as part of 
     # metadata)
-    if (!$found_doctype && !defined $self->{'dontgdbm'}->{'doctype'}) {
-        print $handle "<doctype>doc\n";
-    }
+    #if (!$found_doctype && !defined $self->{'dontgdbm'}->{'doctype'}) {
+    #    print $handle "<doctype>doc\n";
+    #}