Changeset 24476 for main/trunk

Timestamp:

2011-08-25T19:33:02+12:00 (13 years ago)

Author:

ak19

Message:

Number of pages calculated for PDFs when using PDFBox is now no longer twice the number it's supposed to be.

File:

• main/trunk/greenstone2/perllib/plugins/PDFPlugin.pm (modified) (3 diffs)

main/trunk/greenstone2/perllib/plugins/PDFPlugin.pm

@@ -285 +285 @@
     # embeds each page in an extra div. The div opener is: 
     # <div style=\"page-break-before:always; page-break-after:always\">
-    # The PDFPlugin now looks for this and prefix <a name=0></a> to each such div. (The 
+    # The PDFPlugin now looks for this and prefixes <a name=0></a> to each such div. (The 
     # pagenumber is fixed at 0 since I'm unable to work out how to increment the pagenum during 
     # a regex substitution even with regex extensions on.) Later, when we process each section 
@@ -299 +299 @@
     # for each page).  Metadata based on this calculation not set until process()
     # 
-    # Note: this is done even if we are not breaking to document into pages as it might
+    # Note: this is done even if we are not breaking the document into pages as it might
     # be useful to give an indication of document length in browser through setting
     # num_pages as metadata.
-    my @pages = ($text =~ m/(\<[Aa] name=\"?\w+\"?>|\<div style=\"page-break-before:always; page-break-after:always\">)/ig); #<div style=\"?page-break-before:always; page-break-after:always\"?>
+    my @pages = ($text =~ m/\<[Aa] name=\"?\w+\"?>/ig); #<div style=\"?page-break-before:always; page-break-after:always\"?>
     my $num_pages = scalar(@pages);
     $self->{'num_pages'} = $num_pages;
@@ -422 +422 @@
     }
 
-    $doc_obj->add_utf8_metadata($cursection, "NumPages", $self->{'num_pages'});
+    $doc_obj->add_utf8_metadata($cursection, "NumPages", $self->{'num_pages'}) if defined $self->{'num_pages'};
     
     if ($self->{'use_sections'} && $self->{'converted_to'} eq "HTML") {