Changeset 10451

Timestamp:

2005-08-10T12:51:42+12:00 (19 years ago)

Author:

kjdon

Message:

added pdf_allow_images_only option for conversion to html when there is no text that can be extracted (thanks to Doug Carter)

File:

• trunk/gsdl/bin/script/gsConvert.pl (modified) (4 diffs)

trunk/gsdl/bin/script/gsConvert.pl

@@ -63 +63 @@
 my $pdf_zoom;
 my $pdf_ignore_images;
+my $pdf_allow_images_only;
 my $windows_scripting;
 
@@ -81 +82 @@
     print STDERR "\t-pdf_ignore_images\tdon't attempt to extract images when\n";
     print STDERR "\t\tconverting PDF to HTML\n";
+    print STDERR "\t-pdf_allow_images_only\tallow images only (continue even if no text is present when converting to HTML)\n";
     print STDERR "\t-pdf_zoom\tfactor by which to zoom PDF (only useful if\n";
     print STDERR "\t\t-pdf_complex is set\n";
@@ -105 +107 @@
              'pdf_complex', \$pdf_complex,
              'pdf_ignore_images', \$pdf_ignore_images,
+             'pdf_allow_images_only', \$pdf_allow_images_only,
              'pdf_nohidden', \$pdf_nohidden,
              'pdf_zoom/\d+/2', \$pdf_zoom
@@ -760 +763 @@
     $cmd .= " -c" if ($pdf_complex);
     $cmd .= " -i" if ($pdf_ignore_images);
+    $cmd .= " -a" if ($pdf_allow_images_only);
     $cmd .= " -hidden" unless ($pdf_nohidden);
     $cmd .= " \"$input_filename\" \"$output_filestem\"";