- Timestamp:
- 2018-06-05T21:11:04+12:00 (6 years ago)
- File:
-
- 1 edited
Legend:
- Unmodified
- Added
- Removed
-
gs2-extensions/pdf-box/trunk/java/perllib/plugins/PDFBoxConverter.pm
r32090 r32193 127 127 my $pbajar = &FileUtils::filenameConcatenate($gextpb_home,"lib","java","pdfbox-app.jar"); 128 128 my $java = &util::get_java_command(); 129 my $launch_cmd = "$java -cp \"$pbajar\" -Dline.separator=\"<br />\" org.apache.pdfbox. ExtractText";129 my $launch_cmd = "$java -cp \"$pbajar\" -Dline.separator=\"<br />\" org.apache.pdfbox.tools.ExtractText"; 130 130 131 131 $self->{'pdfbox_launch_cmd'} = $launch_cmd; 132 $self->{'pdfbox_img_launch_cmd'} = "java -cp \"$pbajar\" org.apache.pdfbox.PDFToImage"; # cmd for converting pages to images (gif, jpg, png) 132 #$self->{'pdfbox_img_launch_cmd'} = "java -cp \"$pbajar\" org.apache.pdfbox.tools.PDFToImage"; # pdfbox 2.09 cmd for converting each PDF page to an image (gif, jpg, png) 133 # Now: use this cmd to launch our new custom PDFBox class (GS_PDFToImagesAndText.java) to convert each PDF page into an image (gif, jpg, png) 134 # AND its extracted text. An item file is still generated, but this time referring to txtfiles too, not just the images. Result: searchable paged output. 135 $self->{'pdfbox_img_launch_cmd'} = "java -cp \"$pbajar\" org.apache.pdfbox.tools.GS_PDFToImagesAndText"; 133 136 } 134 137 else { … … 311 314 312 315 313 1; 316 1;
Note:
See TracChangeset
for help on using the changeset viewer.