Changeset 32273 for main/trunk/greenstone2/perllib
- Timestamp:
- 2018-07-13T20:40:24+12:00 (6 years ago)
- Location:
- main/trunk/greenstone2/perllib
- Files:
-
- 1 added
- 2 edited
Legend:
- Unmodified
- Added
- Removed
-
main/trunk/greenstone2/perllib/plugins/PDFPlugin.pm
r32224 r32273 140 140 $self->{'file_type'} = "PDF"; 141 141 142 # PDFPlugin is deprecated and migrating users should hereafter choose between 143 # PDFv1Plugin, if they want to use the old pdftohtml tool's capabilities, 144 # and PDFv2Plugin, if they want to use pdfbox or the new xpdftools capabilities. 145 &gsprintf::gsprintf(STDERR, "{PDFPlugin.deprecated_plugin}"); 146 142 147 # these are passed through to gsConvert.pl by ConvertBinaryFile.pm 143 148 my $zoom = $self->{"zoom"}; 144 $self->{'convert_options'} = "-pdf_zoom $zoom"; 149 # By default, PDFPlugin assumes gsConvert.pl will run the old pdftohtml conversion tool, 150 # But if pdfbox conversion is turned on, the tool used is pdfbox (which is presently an 151 # AutoLoadConverter and therefore bypasses gsConvert.pl) 152 $self->{'convert_options'} = "-pdf_tool pdftohtml"; 153 $self->{'convert_options'} .= " -pdf_zoom $zoom"; 145 154 $self->{'convert_options'} .= " -pdf_complex" if $self->{"complex"}; 146 155 $self->{'convert_options'} .= " -pdf_nohidden" if $self->{"nohidden"}; … … 151 160 # TODO: Start supporting PDF to txt on Windows if we're going to be using XPDF Tools (incl pdftotext) on Windows/Linux/Mac 152 161 if ($self->{'convert_to'} eq "text" && $ENV{'GSDLOS'} =~ /^windows$/i) { 153 154 #print STDERR "Windows does not support pdf to text. PDFs will be converted to HTML instead\n";155 #$self->{'convert_to'} = "html";162 #print STDERR "On Windows, Greenstone now uses Xpdf tools to support pdf to text conversion.\n"; 163 print STDERR "Windows does not support pdf to text. PDFs will be converted to HTML instead\n"; 164 $self->{'convert_to'} = "html"; 156 165 } 157 166 elsif ($self->{'convert_to'} eq "auto") { … … 407 416 # Copying file open/close code from CommonUtil::utf8_write_file() 408 417 if (!open (OUTFILE, ">:utf8", $output_filename)) { 409 gsprintf(STDERR, "PDFPlugin::xpdftohtml_convert_post_process {Co nvertToPlug.could_not_open_for_writing} ($!)\n", $output_filename);418 gsprintf(STDERR, "PDFPlugin::xpdftohtml_convert_post_process {CommonUtil.could_not_open_for_writing} ($!)\n", $output_filename); 410 419 die "\n"; 411 420 } -
main/trunk/greenstone2/perllib/strings.properties
r32222 r32273 809 809 CommonUtil.block_exp:Files matching this regular expression will be blocked from being passed to any later plugins in the list. 810 810 811 CommonUtil.could_not_open_for_writing:could not open %s for writing 812 811 813 CommonUtil.desc:Base Utility plugin class that handles filename encoding and file blocking. 812 814 … … 1165 1167 PDFPlugin.convert_to.paged_html:A series of HTML pages, one for each page. Each HTML page contains selectable text positionally overlaid on top of a screenshot of the PDF page background comprising any images, tables and drawings. 1166 1168 1167 PDFPlugin.desc:Plugin that processes PDF documents. 1169 PDFPlugin.deprecated_plugin:*************IMPORTANT******************\nPDFPlugin is being deprecated.\nConsider upgrading to the recommended PDFv2Plugin, which supports newer versions of PDFs.\nAlternatively, if you wish to retain the old style of conversion and are NOT relying on PDFBox,\nchange to PDFv1Plugin.\nIf you are using PDFBox then upgrade to PDFv2Plugin.\n*****************************************\n 1170 1171 PDFPlugin.desc:Plugin that processes PDF documents using the older pdftohtml tool. Does not support newer PDF versions. 1168 1172 1169 1173 PDFPlugin.nohidden:Prevent pdftohtml from attempting to extract hidden text. This is only useful if the -complex option is also set.
Note:
See TracChangeset
for help on using the changeset viewer.