Ignore:
Timestamp:
2018-07-30T17:44:16+12:00 (6 years ago)
Author:
ak19
Message:

Followed Kathy's instructions on setting up the jbig2-imageio jar library to get PagedImagePlugin to work with some of Renate's pdfs: no longer are blank images produced for these special PDFs. Including the jbig2 jar library file and its Apache 2 license, and the update to PDFBoxConverter.pm

File:
1 edited

Legend:

Unmodified
Added
Removed
  • gs2-extensions/pdf-box/trunk/java/perllib/plugins/PDFBoxConverter.pm

    r32284 r32316  
    126126    my $gextpb_home = $ENV{'GEXT_PDFBOX'};
    127127    my $pbajar = &FileUtils::filenameConcatenate($gextpb_home,"lib","java","pdfbox-app.jar");
     128    my $pbjbigjar = &FileUtils::filenameConcatenate($gextpb_home,"lib","java","jbig2-imageio-3.0.1.jar");
     129    # Not including the following JPEG2000 jar, as it is under commercial license:
     130    # https://github.com/jai-imageio/jai-imageio-jpeg2000 leading to https://bintray.com/jai-imageio/maven/jai-imageio-jpeg2000# (Files tab)
     131    # my $pbjp2jar = &FileUtils::filenameConcatenate($gextpb_home,"lib","java","jai-imageio-jpeg2000-1.3.0.jar"); # jpeg2000
    128132    my $java = &util::get_java_command();
    129133    $self->{'pdfbox_txt_launch_cmd'} = "$java -cp \"$pbajar\" org.apache.pdfbox.tools.ExtractText";
    130134    $self->{'pdfbox_html_launch_cmd'} = "$java -cp \"$pbajar\" -Dline.separator=\"<br />\" org.apache.pdfbox.tools.ExtractText";
    131 #   $self->{'pdfbox_img_launch_cmd'} = "java -cp \"$pbajar\" org.apache.pdfbox.tools.PDFToImage"; # pdfbox 2.09 cmd for converting each PDF page to an image (jpg, png)
    132135
    133136    # We use this next cmd to launch our new custom PDFBox class (PDFBoxToImagesAndText.java) to convert each PDF page into an image (gif, jpg, png)
     
    136139    # Our new custom class PDFBoxToImagesAndText.java lives in the new build folder, so add that to the classpath for the launch cmd
    137140    my $pdfbox_build = &FileUtils::filenameConcatenate($gextpb_home,"build");
    138     my $classpath = &util::pathname_cat($pbajar,$pdfbox_build);
     141    # put the pdfbox jar, the jbig2-imageio library (Apache Software License 2.0)
     142    # and our build folder containing our custom PDFBox class on the classpath
     143    my $classpath = &util::pathname_cat($pbajar, $pbjbigjar, $pdfbox_build);
     144#   $self->{'pdfbox_img_launch_cmd'} = "java -cp \"$classpath\" org.apache.pdfbox.tools.PDFToImage"; # pdfbox 2.09 cmd for converting each PDF page to an image (jpg, png) 
    139145    $self->{'pdfbox_imgtxt_launch_cmd'} = "java -cp \"$classpath\" org.greenstone.pdfbox.PDFBoxToImagesAndText";
    140146    }
Note: See TracChangeset for help on using the changeset viewer.