Changeset 4103

Timestamp:

2003-04-08T12:25:08+12:00 (21 years ago)

Author:

sjboddie

Message:

Added a -nohidden PDFPlug option and made it pass the -hidden option to pdftohtml
by default.

Location:

trunk/gsdl

Files:

• bin/script/gsConvert.pl (modified) (4 diffs)
• bin/script/pdftohtml.pl (modified) (4 diffs)
• perllib/plugins/PDFPlug.pm (modified) (5 diffs)

trunk/gsdl/bin/script/gsConvert.pl

@@ -60 +60 @@
 my $use_strings;
 my $pdf_complex;
+my $pdf_nohidden;
 my $pdf_zoom;
 my $pdf_ignore_images;
@@ -75 +76 @@
     print STDERR "\t-use_strings\tuse strings to extract text if conversion fails\n";
     print STDERR "\t-pdf_complex\tuse complex output when converting PDF to HTML\n";
+    print STDERR "\t-pdf_nohidden\tDon't attempt to extract hidden text from PDF files\n";
     print STDERR "\t-pdf_ignore_images\tdon't attempt to extract images when\n";
     print STDERR "\t\tconverting PDF to HTML\n";
@@ -99 +101 @@
              'use_strings', \$use_strings,
              'pdf_complex', \$pdf_complex,
+             'pdf_nohidden', \$pdf_nohidden,
              'pdf_zoom/\d+/2', \$pdf_zoom
              ))
@@ -642 +645 @@
     $cmd .= " -c" if ($pdf_complex);
     $cmd .= " -i" if ($pdf_ignore_images);
+    $cmd .= " -hidden" unless ($pdf_nohidden);
     $cmd .= " \"$input_filename\" \"$output_filestem\"";
     

trunk/gsdl/bin/script/pdftohtml.pl

@@ -51 +51 @@
      "\t-a\tallow images only (continue even if no text is present)\n",
      "\t-c\tproduce complex output (requires ghostscript)\n",
+     "\t-hidden\tExtract hidden text\n",
      "\t-zoom\tfactor by which to zoom the PDF (only useful if -c is set)\n"
      );
@@ -58 +59 @@
 sub main {
     my (@ARGV) = @_;
-    my ($allow_no_text, $ignore_images, $complex, $zoom);
+    my ($allow_no_text, $ignore_images, $complex, $zoom, $hidden);
     
     # read command-line arguments so that
@@ -66 +67 @@
              'i', \$ignore_images,
              'c', \$complex,
+             'hidden', \$hidden,
              'zoom/\d+/2', \$zoom,
              ))
@@ -115 +117 @@
     $cmd .= " -i" if ($ignore_images);
     $cmd .= " -c" if ($complex);
+    $cmd .= " -hidden" if ($hidden);
     $cmd .= " -zoom $zoom";
     $cmd .= " -noframes -p -enc UTF-8 \"$input_filename\" \"$output_filestem.html\"";

trunk/gsdl/perllib/plugins/PDFPlug.pm

@@ -45 +45 @@
             'type' => "flag" },
           { 'name' => "complex",
-            'desc' =>  "Create more complex output. With this option set the output html will look much more like the original PDF file. For this to function properly you Ghostscript installed (for *nix gs should be on your path while for windows you must have gswin32c.exe on your path).",
+            'desc' => "Create more complex output. With this option set the output html will look much more like the original PDF file. For this to function properly you Ghostscript installed (for *nix gs should be on your path while for windows you must have gswin32c.exe on your path).",
+            'type' => "flag" },
+          { 'name' => "nohidden",
+            'desc' => "Prevent pdftohtml from attempting to extract hidden text. This is only useful if the -complex option is also set.",
             'type' => "flag" },
           { 'name' => "zoom",
@@ -60 +63 @@
     my $class = shift (@_);
 
-    my ($noimages, $complex, $zoom, $use_sections);
+    my ($noimages, $complex, $zoom, $use_sections, $nohidden);
     
     if (!parsargv::parse(\@_, 
@@ -66 +69 @@
              q^complex^, \$complex,
              q^zoom/\d+/2^, \$zoom,
+             q^nohidden^, \$nohidden,
              q^use_sections/1?/^, \$use_sections,
              "allow_extra_options")) {
@@ -97 +101 @@
     $self->{'convert_options'} = "-pdf_zoom $zoom";
     $self->{'convert_options'} .= " -pdf_complex" if $complex;
+    $self->{'convert_options'} .= " -pdf_nohidden" if $nohidden;
     $self->{'convert_options'} .= " -pdf_ignore_images" if $noimages;
 
@@ -122 +127 @@
     print STDERR "                     gs should be on your path while for windows\n";
     print STDERR "                     you must have gswin32c.exe on your path).\n";
+    print STDERR "   -nohidden         Prevent pdftohtml from attempting to extract\n";
+    print STDERR "                     hidden text. This is only useful if the -complex\n";
+    print STDERR "                     option is also set.";
     print STDERR "   -zoom             The factor by which to zoomthe PDF for output\n";
     print STDERR "                     (this is only useful if -complex is set).\n\n";