libis-format 1.1.0 → 1.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 40c91211db466867a86d905e707302783d77f8ce96bce970229294fc3506f4dd
-  data.tar.gz: 3254048984ba29c9c6a1d556f25e7dc346ba1c0fc2082b80562c3ae64f41dc8f
+  metadata.gz: c8f2304a5f189140ad867cb1d7d9d41f280f796992c84514316b7e584628a64b
+  data.tar.gz: ee097826d8e73fa7fa72167b4a3eaebef5992bba8fd78a6e0d454fe552730d6c
 SHA512:
-  metadata.gz: caa9a7a5cbc6e99c7d1afb8af83274b2db4de847fde394d3d9cdc1129019044353bdbe6527fb4aabbcb8817be175e99f6bac1eeef0b79eb3e7ab94b7594db4ce
-  data.tar.gz: f3ade6093b38aab4b8c529c0d80e5a822aa2042264efc8d076077f74ee0cd20ebd91dbe5b2d6d030394607fcde196b28c8dabc2659788308e926981cca880905
+  metadata.gz: 9fdb85d3847ba3ed08c96cc409b5e7f2c471d80edf61ab6581b28cb46380e1b48e8c65daf182717dd35cf216d91e50f1680d31a352d9aab557d54f7f3af61dc8
+  data.tar.gz: 0d8d4f7c29c0fa5da26a85eb82554796cb1ac18f98e00e3f1e700bd4eb79f647b8311f56e2eb7a46cc1679a2809fc140b1cc702856da1baacafd5127a65ea66f

data/.gitignore

@@ -18,3 +18,4 @@ mkmf.log
 *.pyc
 tools/pdf/
 /test*
+.rake_tasks~

data/data/PDFA_def.ps

@@ -5,10 +5,10 @@
 % unless the user modifies the corresponding line below.
 
 % Define entries in the document Info dictionary :
-/ICCProfile ([** Fill in ICC profile location **])
+/ICCProfile ([**ICC profile**])
 def
 
-[ /Title (Title)
+[ [**METADATA**]
   /DOCINFO pdfmark
 
 % Define an ICC profile :
@@ -35,6 +35,6 @@ def
   /Type /OutputIntent             % Must be so (the standard requires).
   /S /GTS_PDFA1                   % Must be so (the standard requires).
   /DestOutputProfile {icc_PDFA}            % Must be so (see above).
-  /OutputConditionIdentifier ([** Fill in ICC reference name **])
+  /OutputConditionIdentifier ([**ICC reference**])
 >> /PUT pdfmark
 [{Catalog} <</OutputIntents [ {OutputIntent_PDFA} ]>> /PUT pdfmark

data/lib/libis/format/config.rb

@@ -21,7 +21,7 @@ module Libis
     Config[:fido_formats] = [(File.join(Libis::Format::DATA_DIR, 'lias_formats.xml'))]
     Config[:pdf_tool] = File.join(Libis::Format::TOOL_DIR, 'PdfTool.jar')
     Config[:preflight_jar] = File.join(Libis::Format::TOOL_DIR, 'pdfbox', 'preflight-app-2.0.13.jar')
-    Config[:emai2pdf_jar] = File.join(Libis::Format::TOOL_DIR, 'emailconverter.jar')
+    Config[:email2pdf_jar] = File.join(Libis::Format::TOOL_DIR, 'emailconverter.jar')
     # noinspection RubyStringKeysInHashInspection
     Config[:xml_validations] = [['archive/ead', File.join(Libis::Format::DATA_DIR, 'ead.xsd')]]
     Config[:type_database] = File.join(Libis::Format::DATA_DIR, 'types.yml')

data/lib/libis/format/converter/pdf_converter.rb

@@ -5,6 +5,7 @@ require_relative 'base'
 require 'libis/tools/extend/hash'
 require 'libis/format/tool/pdf_copy'
 require 'libis/format/tool/pdf_to_pdfa'
+require 'libis/format/tool/pdfa_validator'
 require 'libis/format/tool/pdf_optimizer'
 
 module Libis
@@ -120,7 +121,7 @@ module Libis
           end
 
           { 
-            files: [result]
+            files: [result],
             converter: self.class.name
           }
 
@@ -163,11 +164,16 @@ module Libis
 
           using_temp(target) do |tmpname|
             result = Libis::Format::Tool::PdfToPdfa.run source, tmpname
-            if result[:status] != 0
-              error("Pdf/A conversion encountered errors:\n%s", result[:err].join("\n"))
+
+            if result[:command][:status] != 0
+              error("Pdf/A conversion encountered errors:\n%s", (result[:command][:out] + result[:command][:err]).join("\n"))
               next nil
             else
-              warn("Pdf/A conversion warnings:\n%s", result[:err].join("\n")) unless result[:err].empty?
+              r = Libis::Format::Tool::PdfaValidator.run tmpname
+              if r[:status] != 0
+                error "Pdf/A file failed to validate with following errors:\n%s", (r[:err] || r[:out] || []).join("\n")
+                next nil
+              end
             end
             tmpname
           end

data/lib/libis/format/converter/xslt_converter.rb

@@ -1,17 +1,17 @@
-require_relative 'base'
+require_relative "base"
 
 module Libis
   module Format
     module Converter
-
       class XsltConverter < Libis::Format::Converter::Base
-
         def self.input_types
           [:XML]
         end
 
         def self.output_types(format = nil)
-          return [] unless input_types.include?(format) if format
+          if format
+            return [] unless input_types.include?(format)
+          end
           [:XML, :HTML, :TXT]
         end
 
@@ -28,20 +28,20 @@ module Libis
           end
 
           unless @options[:xsl_file]
-            error 'No xsl_file supplied'
+            error "No xsl_file supplied"
             return nil
           end
 
           FileUtils.mkpath(File.dirname(target))
 
           if RUBY_PLATFORM == "java"
-            require 'saxon-xslt'
+            require "saxon-xslt"
             xsl = Saxon.XSLT(File.open(@options[:xsl_file]))
             xml = Saxon.XML(File.open(source))
             result = xsl.transform(xml)
-            File.open(target, 'w') {|f| f.write(result.to_s)}
+            File.write(target, result.to_s)
           else
-            require 'nokogiri'
+            require "nokogiri"
 
             doc = nil
             begin
@@ -65,7 +65,7 @@ module Libis
             xsl = nil
 
             begin
-              fp = File.open(file, 'r')
+              fp = File.open(file, "r")
               xsl = Nokogiri::XSLT(fp) do |config|
                 config.options = Nokogiri::XML::ParseOptions::STRICT | Nokogiri::XML::ParseOptions::NOBLANKS
               end
@@ -80,7 +80,7 @@ module Libis
 
             begin
               target_xml = xsl.transform(doc)
-              fp = File.open(target, 'w')
+              fp = File.open(target, "w")
               fp.write(target_xml)
             rescue Exception => e
               error "Error transforming '#{source}' with '#{file}': #{e.message} @ #{e.backtrace[0]}"
@@ -89,13 +89,14 @@ module Libis
               fp.close unless fp.nil? or fp.closed?
             end
 
-            target
-          end
+            {
+              command: {status: 0},
+              files: [target]
+            }
 
+          end
         end
-
       end
-
     end
   end
 end

data/lib/libis/format/tool/email_to_pdf.rb

@@ -26,8 +26,8 @@ module Libis
           timeout = Libis::Format::Config[:timeouts][:email2pdf] || 120
           result = Libis::Tools::Command.run(
             Libis::Format::Config[:java_cmd],
-            "-Duser.timezone=Europe/Brussels -Duser.language=nl -Duser.country=BE",
-            "jar", Libis::Format::Config[:email2pdf_cmd],
+            "-Duser.timezone=Europe/Brussels", "-Duser.language=nl", "-Duser.country=BE",
+            "-jar", Libis::Format::Config[:email2pdf_jar],
             "-e", "-hd", "-a",
             "-o", target,
             source,
@@ -35,7 +35,7 @@ module Libis
             kill_after: timeout * 2
           )
 
-          warn "EmailToPdf conversion messages: \n\t#{result[:out].join("\n\t")}" unless result[:out].empty?
+          warn "EmailToPdf conversion messages: \n\t#{result[:err].join("\n\t")}" unless result[:err].empty?
 
           raise "#{self.class} took too long (> #{timeout} seconds) to complete" if result[:timeout]
           raise "#{self.class} failed to generate target file #{target}" unless File.exist?(target)
@@ -59,7 +59,7 @@ module Libis
           return headers unless File.exist?(headers_file)
           doc = REXML::Document.new(File.new(headers_file))
           root = doc.root
-          root.elements("/emailheader/*").each do |element|
+          root.children.each do |element|
             case element.name
             when "attachments"
               headers[:attachments] = element.elements.map { |e| e.text }

data/lib/libis/format/tool/fop_pdf.rb

@@ -33,6 +33,7 @@ module Libis
           result = Libis::Tools::Command.run(
               Libis::Format::Config[:java_cmd],
               "-Dfop.home=#{File.dirname(Libis::Format::Config[:fop_jar])}",
+              '-Djava.awt.headless=true',
               '-jar', Libis::Format::Config[:fop_jar],
               '-fo', xml,
               '-pdf', target,

data/lib/libis/format/tool/office_to_pdf.rb

@@ -52,14 +52,14 @@ module Libis
 
           FileUtils.copy tgt_file, target, preserve: true
 
-        ensure
-          FileUtils.rmtree workdir rescue nil
-
           {
             command: result,
             files: [ target ]
           }
 
+        ensure
+          FileUtils.rmtree workdir rescue nil
+
         end
       end
 

data/lib/libis/format/tool/pdf_to_pdfa.rb

@@ -1,18 +1,18 @@
-require 'tempfile'
-require 'csv'
-require 'fileutils'
+require "tempfile"
+require "csv"
+require "fileutils"
+require 'pdfinfo'
 
-require 'libis/tools/extend/string'
-require 'libis/tools/logger'
-require 'libis/tools/command'
-require 'libis/tools/temp_file'
+require "libis/tools/extend/string"
+require "libis/tools/logger"
+require "libis/tools/command"
+require "libis/tools/temp_file"
 
-require 'libis/format'
+require "libis/format"
 
 module Libis
   module Format
     module Tool
-
       class PdfToPdfa
         include ::Libis::Tools::Logger
 
@@ -22,71 +22,78 @@ module Libis
         end
 
         def self.run(source, target = nil, options = {})
-          self.new.run source, target, options
+          new.run source, target, options
         end
 
         def run(source, target = nil, options = nil)
-
-          tmp_target = Tools::TempFile.name(File.basename(source, '.*'), '.pdf')
+          tmp_target = Tools::TempFile.name(File.basename(source, ".*"), ".pdf")
           target ||= tmp_target
 
+          metadata = get_metadata(source)
+
           icc_info = icc_options(options[:colorspace])
 
-          icc_file = Tools::TempFile.name(icc_info[:icc_name], '.icc')
+          icc_file = Tools::TempFile.name(icc_info[:icc_name], ".icc")
           FileUtils.cp(File.join(Libis::Format::DATA_DIR, "#{icc_info[:icc_name]}.icc"), icc_file)
 
-          def_filename = Tools::TempFile.name('PDFA_def', '.ps')
-          File.open(def_filename, 'w') do |f|
-            f.puts File.read(File.join(Libis::Format::DATA_DIR, 'PDFA_def.ps')).
-                gsub('[** Fill in ICC profile location **]', icc_file).
-                gsub('[** Fill in ICC reference name **]', icc_info[:icc_ref])
+          def_filename = Tools::TempFile.name("PDFA_def", ".ps")
+          File.open(def_filename, "w") do |f|
+            f.puts File.read(File.join(Libis::Format::DATA_DIR, "PDFA_def.ps"))
+              .gsub("[**ICC profile**]", icc_file)
+              .gsub("[**ICC reference**]", icc_info[:icc_ref])
+              .gsub("[**METADATA**]", metadata)
           end
 
           timeout = Libis::Format::Config[:timeouts][:pdf_to_pdfa]
           result = Libis::Tools::Command.run(
-              Libis::Format::Config[:ghostscript_cmd],
-              '-dBATCH', '-dNOPAUSE', '-dNOOUTERSAVE',
-              '-sColorConversionStrategy=/UseDeviceIndependentColor',
-              "-sProcessColorModel=#{icc_info[:device]}",
-              '-sDEVICE=pdfwrite', '-dPDFA', '-dPDFACompatibilityPolicy=1',
-              "-sOutputICCProfile=#{icc_file}",
-              '-o', File.absolute_path(target),
-              def_filename,
-              source,
-              timeout: timeout,
-              kill_after: timeout * 2
+            Libis::Format::Config[:ghostscript_cmd],
+            "-q",
+            "-dBATCH", "-dNOPAUSE", "-dNOOUTERSAVE", "-dNOSAFER",
+            # "-dNOPLATFONTS", "-dUseCIEColor=true",
+            # "-sColorConversionStrategy=/UseDeviceIndependentColor",
+            "-sProcessColorModel=#{icc_info[:device]}",
+            "-sOutputICCProfile=#{icc_file}",
+            "-dCompatibilityLevel=1.4",
+            "-sDEVICE=pdfwrite", "-dPDFA=1", "-dPDFACompatibilityPolicy=1",
+            "-o", File.absolute_path(target),
+            def_filename,
+            source,
+            timeout: timeout,
+            kill_after: timeout * 2
           )
 
-          raise RuntimeError, "#{self.class} took too long (> #{timeout} seconds) to complete" if result[:timeout]
+          raise "#{self.class} took too long (> #{timeout} seconds) to complete" if result[:timeout]
+          raise "#{self.class} failed with error #{result[:status]}: \n#{(result[:out] + result[:err]).join("\n")}" if result[:status] != 0
 
           FileUtils.rm [icc_file, def_filename].compact, force: true
 
-          unless Format::Tool::PdfaValidator.run(target)
-            result[:status] = -999
-            result[:err] << 'Failed to validate generated PDF/A file.'
-          end
-
           {
             command: result,
-            files: [ target ]
+            files: [target]
           }
-
         end
 
-
         private
 
+        def get_metadata(source)
+          info = Pdfinfo.new(source)
+          metadata = "/Title (#{info.title})"
+          metadata += "\n  /Author (#{info.author})" if info.author
+          metadata += "\n  /Subject (#{info.subject})" if info.subject
+          metadata += "\n  /Keywords (#{info.keywords})" if info.keywords
+          metadata += "\n  /Creator (#{info.creator})" if info.creator
+          metadata
+        end
+        
         def icc_options(colorspace)
           case colorspace.to_s.downcase
-            when 'cmyk'
-              {icc_name: 'ISOcoated_v2_eci', icc_ref: 'FOGRA39L', device: 'DeviceCMYK'}
-            else
-              {icc_name: 'eciRGB_v2', icc_ref: 'sRGB', device: 'DeviceRGB'}
+          when "cmyk"
+            {icc_name: "ISOcoated_v2_eci", icc_ref: "FOGRA39L", device: "DeviceCMYK"}
+          else
+            {icc_name: "AdobeRGB1998", icc_ref: "sRGB", device: "DeviceRGB"}
           end
         end
-
       end
-
     end
   end
 end

data/lib/libis/format/tool/pdfa_validator.rb

@@ -1,24 +1,22 @@
-require 'fileutils'
+require "fileutils"
 
-require 'libis/tools/extend/string'
-require 'libis/tools/logger'
-require 'libis/tools/command'
+require "libis/tools/extend/string"
+require "libis/tools/logger"
+require "libis/tools/command"
 
-require 'libis/format/config'
+require "libis/format/config"
 
 module Libis
   module Format
     module Tool
-
       class PdfaValidator
         include ::Libis::Tools::Logger
 
         def self.run(source)
-          self.new.run source
+          new.run source
         end
 
         def run(source)
-
           src_file = File.absolute_path(source)
 
           timeout = Libis::Format::Config[:timeouts][:pdfa_validator]
@@ -28,46 +26,41 @@ module Libis
             Dir.chdir(Dir.tmpdir)
 
             result = Libis::Tools::Command.run(
-                pdfa,
-                '--noxml',
-                '--level', 'B',
-                '--verb', '0',
-                src_file,
-                timeout: timeout,
-                kill_after: timeout * 2
+              pdfa,
+              "--noxml",
+              "--level", "B",
+              "--verb", "0",
+              src_file,
+              timeout: timeout,
+              kill_after: timeout * 2
             )
 
-            raise RuntimeError, "#{self.class} took too long (> #{timeout} seconds) to complete" if result[:timeout]
-            raise RuntimeError, "#{self.class} errors: #{result[:err].join("\n")}" unless result[:status] == 0 && result[:err].empty?
+            raise "#{self.class} took too long (> #{timeout} seconds) to complete" if result[:timeout]
+            raise "#{self.class} errors: #{result[:err].join("\n")}" unless result[:status] == 0 && result[:err].empty?
 
             Dir.chdir(previous_wd)
 
-            unless result[:out].any? {|line| line =~ /^VLD-\[PASS\]/}
-              warn "Validator failed to validate the PDF file '%s' against PDF/A-1B constraints:\n%s", source,
-                   result[:out].join("\n")
-              return false
-            end
+            out, err = result[:out].partition { |line| line =~ /^VLD-\[PASS\]/ }
+            result[:out] = out
+            result[:err] += err
+
+            result
           else
             jar = Libis::Format::Config[:preflight_jar]
             result = Libis::Tools::Command.run(
-                Libis::Format::Config[:java_cmd],
-                '-jar', jar,
-                src_file,
-                timeout: timeout,
-                kill_after: timeout * 2
+              Libis::Format::Config[:java_cmd],
+              "-jar", jar,
+              src_file,
+              timeout: timeout,
+              kill_after: timeout * 2
             )
-            raise RuntimeError, "#{self.class} took too long (> #{timeout} seconds) to complete" if result[:timeout]
 
-            unless result[:status] == 0
-              warn "Validator failed to validate the PDF file '%s' against PDF/A-1B constraints:\n%s", source,
-                   result[:out].join("\n")
-              return false
-            end
+            raise "#{self.class} took too long (> #{timeout} seconds) to complete" if result[:timeout]
+
+            result
           end
-          true
         end
       end
-
     end
   end
 end

data/lib/libis/format/tool/spreadsheet_to_ods.rb

@@ -53,14 +53,14 @@ module Libis
 
           FileUtils.copy tgt_file, target, preserve: true
 
-        ensure
-          FileUtils.rmtree workdir rescue nil
-
           {
             command: result,
             files: [ target ]
           }
 
+        ensure
+          FileUtils.rmtree workdir rescue nil
+
         end
       end
 

data/lib/libis/format/version.rb

@@ -1,5 +1,5 @@
 module Libis
   module Format
-    VERSION = '1.1.0'
+    VERSION = '1.2.0'
   end
 end

data/libis-format.gemspec

@@ -39,4 +39,6 @@ Gem::Specification.new do |spec|
   spec.add_runtime_dependency 'deep_dive', '~> 0.3'
   spec.add_runtime_dependency 'chromaprint', '~> 0.0.2'
   spec.add_runtime_dependency 'naturally', '~> 2.1'
+  spec.add_runtime_dependency 'pdfinfo', '~> 1.4'
+
 end

data/tools/pdf2pdfa

@@ -0,0 +1,395 @@
+#!/usr/bin/env bash
+
+# PDF2ARCHIVE 0.3.2
+# (C) 2018 Matteo Seclì <secli.matteo@gmail.com>
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+
+#=====# INITIALIZE VARIABLES #=====#
+VERSION="0.3.2"
+INPUT=""
+OUTPUT=""
+QUALITYOPTS=""
+DEBUG=false
+VALIDATE=false
+MSGOPTS="-dQUIET -sstdout=/dev/null"
+VERAMSGOPTS=""
+#ERROPTS="2>/dev/null"
+
+
+#=====# HELP FUNCTION #=====#
+help()
+{
+    TOTLEN="38"   # Adjust this
+    TITLESTRING="PDF2ARCHIVE, version $VERSION"
+    SPACEL=$(echo "($TOTLEN-${#TITLESTRING})/2 + (36-${#TITLESTRING})%2 - 1" | bc)
+    SPACER=$(echo "($TOTLEN-${#TITLESTRING})/2 - 1" | bc)
+    TITLESTRING=$(printf "|%-${SPACEL}s%s%-${SPACER}s|" "" "$TITLESTRING" "")
+    DASHSTRING=$(eval printf "%.0s-" {1..$TOTLEN})
+    echo \
+"$DASHSTRING
+$TITLESTRING
+$DASHSTRING
+
+OVERVIEW:
+  A simple Ghostscript-based PDF to PDF/A-1B converter.
+
+USAGE:
+  $0 [options] input.pdf [output.pdf]
+
+EXAMPLES:
+  Convert 'input.pdf' in PDF/A-1B format; the output is 'input-PDFA.pdf':
+      $0 input.pdf
+  Convert 'input.pdf' in PDF/A-1B format; the output is 'output.pdf':
+      $0 input.pdf output.pdf
+  Convert 'input.pdf' in PDF/A-1B format and perform a high-quality compression:
+      $0 --quality=high input.pdf
+  Convert 'input.pdf' in PDF/A-1B format and specify the document title:
+      $0 --title=\"Title of your nice document\" input.pdf
+  Convert 'input.pdf' in PDF/A-1B format and validate the result:
+      $0 --validate input.pdf
+
+OPTIONS:
+  -h, --help          Show the help
+  --quality=<value>   Set  the  quality of  the  output  when  downsampling. The
+                      possible values  are  'high',  'medium'  and  'low', where
+                      'high' gives the highest output  quality. By specifying no
+                      option, no additional downsampling is done.
+  --title=<value>     Title of the resulting PDF/A file
+  --author=<value>    Author of the resulting PDF/A file
+  --subject=<value>   Subject of the resulting PDF/A file
+  --keywords=<value>  Comma-separated keywords of the resulting PDF/A file
+  --cleanmetadata     Clean  all the standard  metadata  fields, except the ones
+                      specified via the command line options.
+  --validate          Validate  the resulting file. The  validation is done with
+                      VeraPDF, you need a working Java installation.
+  --validate-only     Perform only the validation on the input file, again using
+                      VeraPDF
+  --debug             Write additional debug information on screen
+  -v, --version       Show the program version
+
+LICENSE:
+  GPLv3
+
+AUTHORS:
+  (C) 2017-2018 Matteo Seclì"
+}
+
+
+#=====# RUN HELPER FUNCTION #=====#
+run() {
+    if $DEBUG; then
+        #v=$(exec 2>&1 && set -x && set -- "$@")
+        #echo "#${v#*--}"
+        "$@"
+    else
+        "$@" 2>/dev/null #>/dev/null 2>&1
+    fi
+}
+
+
+#=====# CHECKS #=====#
+if [ "$(which gs)" == "" ]; then
+    echo "  ERROR: Ghostscript is not installed or it's not in the path"
+    exit
+fi
+
+
+#=====# VALIDATION #=====#
+
+javaCheck() {
+    if [ "$(which java)" == "" ]; then
+        echo "  ERROR: Java is not installed or it's not in the path"
+        echo "  Cannot perform validation"
+        exit 1
+    fi
+}
+
+validate() {
+    echo "  Validating..."
+    echo "  $(./verapdf/verapdf "$1" --extract --flavour 1b --format text "$2")"
+}
+
+
+#=====# INPUT PARSER #=====#
+if [ "$1" == "" ]; then
+    help
+    exit
+fi
+while [ "$1" != "" ]; do
+    PARAM=`echo $1 | awk -F= '{print $1}'`
+    VALUE=`echo $1 | awk -F= '{print $2}'`
+    case $PARAM in
+        -h | --help)
+            help
+            exit
+            ;;
+        -v | --version)
+            echo $VERSION
+            exit
+            ;;
+        --debug)
+            DEBUG=true
+            MSGOPTS=""
+            VERAMSGOPTS="--verbose"
+            #ERROPTS=""
+            ;;
+        --quality)
+            if [ "$VALUE" == "high" ]; then
+                QUALITYOPTS="-dPDFSETTINGS=/printer"
+            elif [ "$VALUE" == "medium" ]; then
+                QUALITYOPTS="-dPDFSETTINGS=/ebook"
+            elif [ "$VALUE" == "low" ]; then
+                QUALITYOPTS="-dPDFSETTINGS=/screen"
+            else
+                echo "  ERROR: unknown quality option '$VALUE'"
+                help
+                exit 1
+            fi
+            ;;
+        --cleanmetadata)
+            [ -z ${PDFTITLE+x} ] && PDFTITLE=""
+            [ -z ${PDFAUTHOR+x} ] && PDFAUTHOR=""
+            [ -z ${PDFSUBJECT+x} ] && PDFSUBJECT=""
+            [ -z ${PDFKEYWORDS+x} ] && PDFKEYWORDS=""
+            [ -z ${PDFCREATOR+x} ] && PDFCREATOR=""
+            [ -z ${PDFPRODUCER+x} ] && PDFPRODUCER=""
+            [ -z ${PDFCREATIONDATE+x} ] && PDFCREATIONDATE=""
+            [ -z ${PDFMODDATE+x} ] && PDFMODDATE=""
+            [ -z ${PDFTRAPPED+x} ] && PDFTRAPPED=""
+            ;;
+        --title)
+            PDFTITLE=$VALUE
+            ;;
+        --author)
+            PDFAUTHOR=$VALUE
+            ;;
+        --subject)
+            PDFSUBJECT=$VALUE
+            ;;
+        --keywords)
+            PDFKEYWORDS=$VALUE
+            ;;
+        --validate)
+            javaCheck
+            VALIDATE=true
+            ;;
+        --validate-only)
+            javaCheck
+            validate $VERAMSGOPTS $2
+            exit
+            ;;
+        *.pdf)
+            if [ "$INPUT" == "" ]; then
+                INPUT=$PARAM
+            elif [ "$OUTPUT" == "" ]; then
+                OUTPUT=$PARAM
+            else
+                echo "  ERROR: too many PDF files as input!"
+                help
+                exit 1
+            fi
+            ;;
+        *)
+            echo "  ERROR: unknown parameter \"$PARAM\""
+            help
+            exit 1
+            ;;
+    esac
+    shift
+done
+
+#=====# SET UP ALL THE STUFF #=====#
+echo "=== Welcome to PDF2ARCHIVE ==="
+if [ "$OUTPUT" == "" ]; then
+    OUTPUT="${INPUT%.pdf}-PDFA.pdf"
+fi
+TMPFILE=$(mktemp)
+TMPDIR=$(mktemp -d)
+PSTMPFILE=$TMPDIR/PDFA_def.ps
+ICCTMPFILE=$TMPDIR/AdobeRGB1998.icc
+INFOTMPFILE=$TMPDIR/pdf_minimal_info.ps
+echo \
+"%!PS
+% Extract PDF info in a minimal way.
+% Inspired by 'toolbin/pdf_info.ps'.
+
+/QUIET true def
+File dup (r) file runpdfbegin
+Trailer /Info knownoget {
+dup /Title knownoget { (__knowninfoTitle: ) print = flush } if
+dup /Author knownoget { (__knowninfoAuthor: ) print = flush } if
+dup /Subject knownoget { (__knowninfoSubject: ) print = flush } if
+dup /Keywords knownoget { (__knowninfoKeywords: ) print = flush } if
+dup /Creator knownoget { (__knowninfoCreator: ) print = flush } if
+dup /Producer knownoget { (__knowninfoProducer: ) print = flush } if
+dup /CreationDate knownoget { (__knowninfoCreationDate: ) print = flush } if
+dup /ModDate knownoget { (__knowninfoModDate: ) print = flush } if
+dup /Trapped knownoget { (__knowninfoTrapped: ) print = flush } if
+} if
+quit
+" > $INFOTMPFILE
+
+
+#=====# PRESERVE UNSPECIFIED KNOWN STANDARD METADATA #=====#
+# Notes:
+#     'iconv' is necessary to filter out all the invalid bytes.
+#     If it's not used, sed (unless it's GNU sed) will fail with
+#     'RE error: illegal byte sequence'. A solution to this is to
+#     use 'LC_CTYPE=C && LANG=C && echo "$METADUMP" ...' in the
+#     variable assignments; however, this produces bad PDF files.
+#
+METADUMP=$(gs -dNOSAFER -dNODISPLAY -q -sFile="$INPUT" $INFOTMPFILE | iconv -f utf-8 -t utf-8 -c)
+[ -z ${PDFTITLE+x} ] && PDFTITLE=$(echo "$METADUMP" | grep "__knowninfoTitle: " | sed "s/^__knowninfoTitle: //g")
+[ -z ${PDFAUTHOR+x} ] && PDFAUTHOR=$(echo "$METADUMP" | grep "__knowninfoAuthor: " | sed "s/^__knowninfoAuthor: //g")
+[ -z ${PDFSUBJECT+x} ] && PDFSUBJECT=$(echo "$METADUMP" | grep "__knowninfoSubject: " | sed "s/^__knowninfoSubject: //g")
+[ -z ${PDFKEYWORDS+x} ] && PDFKEYWORDS=$(echo "$METADUMP" | grep "__knowninfoKeywords: " | sed "s/^__knowninfoKeywords: //g")
+[ -z ${PDFCREATOR+x} ] && PDFCREATOR=$(echo "$METADUMP" | grep "__knowninfoCreator: " | sed "s/^__knowninfoCreator: //g")
+[ -z ${PDFPRODUCER+x} ] && PDFPRODUCER=$(echo "$METADUMP" | grep "__knowninfoProducer: " | sed "s/^__knowninfoProducer: //g")
+[ -z ${PDFCREATIONDATE+x} ] && PDFCREATIONDATE=$(echo "$METADUMP" | grep "__knowninfoCreationDate: " | sed "s/^__knowninfoCreationDate: //g")
+[ -z ${PDFMODDATE+x} ] && PDFMODDATE=$(echo "$METADUMP" | grep "__knowninfoModDate: " | sed "s/^__knowninfoModDate: //g")
+[ -z ${PDFTRAPPED+x} ] && PDFTRAPPED=$(echo "$METADUMP" | grep "__knowninfoTrapped: " | sed "s/^__knowninfoTrapped: //g")
+# Replace "Trapped" string, if not empty, with an operator. Fixes 3Heights.
+if [ "$PDFTRAPPED" != "" ]; then
+  PDFTRAPPED="/$(tr '[:lower:]' '[:upper:]' <<< ${PDFTRAPPED:0:1})$(tr '[:upper:]' '[:lower:]' <<< ${PDFTRAPPED:1})"
+fi
+# Check if the operator is allowed, otherwise empty variable.
+if [ "$PDFTRAPPED" != "/True" ] && [ "$PDFTRAPPED" != "/False" ]; then
+  PDFTRAPPED=""
+fi
+
+
+#=====# PRINT DEBUG INFO #=====#
+if $DEBUG; then
+    echo "  DEBUG: running PDF2ARCHIVE, version $VERSION"
+    echo "  DEBUG: using Ghostscript binary at $(which gs), version $(gs --version)"
+    echo "  DEBUG: the input file is '$INPUT'"
+    echo "  DEBUG: the output file is '$OUTPUT'"
+    echo "  DEBUG: the intermediate processing file is $TMPFILE"
+    echo "  DEBUG: the temporary directory is $TMPDIR"
+    echo "  DEBUG: the current quality options are '$QUALITYOPTS'"
+    echo "  DEBUG: PDF title '$PDFTITLE'"
+    echo "  DEBUG: PDF author '$PDFAUTHOR'"
+    echo "  DEBUG: PDF subject '$PDFSUBJECT'"
+    echo "  DEBUG: PDF keywords '$PDFKEYWORDS'"
+    echo "  DEBUG: PDF creator '$PDFCREATOR'"
+    echo "  DEBUG: PDF producer '$PDFPRODUCER'"
+    echo "  DEBUG: PDF creation date '$PDFCREATIONDATE'"
+    echo "  DEBUG: PDF modification date '$PDFMODDATE'"
+    echo "  DEBUG: PDF trapping '$PDFTRAPPED'"
+fi
+
+
+#=====# CREATE THE PS DEFINITION FILE #=====#
+echo "  Creating the definition file..."
+echo \
+"%!
+% This prefix file for creating a PDF/A document is derived from
+% the sample included with Ghostscript 9.07, released under the
+% GNU Affero General Public License.
+% Modified 4/15/2013 by MCB Systems.
+
+% Feel free to modify entries marked with \"Customize\".
+
+% This assumes an ICC profile to reside in the file (AdobeRGB1998.icc),
+% unless the user modifies the corresponding line below.
+
+% The color space described by the ICC profile must correspond to the
+% ProcessColorModel specified when using this prefix file (GRAY with
+% DeviceGray, RGB with DeviceRGB, and CMYK with DeviceCMYK).
+
+% Define entries in the document Info dictionary :
+
+/ICCProfile ($ICCTMPFILE)   % Customize.
+def
+
+[ /Title ($PDFTITLE)                  % Customize." > $PSTMPFILE
+if [ "$PDFAUTHOR" != "" ]; then
+  echo "  /Author ($PDFAUTHOR)" >> $PSTMPFILE
+fi
+if [ "$PDFSUBJECT" != "" ]; then
+  echo "  /Subject ($PDFSUBJECT)" >> $PSTMPFILE
+fi
+if [ "$PDFKEYWORDS" != "" ]; then
+  echo "  /Keywords ($PDFKEYWORDS)" >> $PSTMPFILE
+fi
+if [ "$PDFCREATOR" != "" ]; then
+  echo "  /Creator ($PDFCREATOR)" >> $PSTMPFILE
+fi
+echo \
+"%  /Producer                          % Reserved to GS
+%  /CreationDate                      % Reserved to GS
+%  /ModDate                           % Reserved to GS" >> $PSTMPFILE
+if [ "$PDFTRAPPED" != "" ]; then
+  echo "  /Trapped $PDFTRAPPED" >> $PSTMPFILE
+fi
+echo \
+"  /DOCINFO pdfmark
+
+% Define an ICC profile :
+
+[/_objdef {icc_PDFA} /type /stream /OBJ pdfmark
+[{icc_PDFA} <</N systemdict /ProcessColorModel get /DeviceGray eq {1} {systemdict /ProcessColorModel get /DeviceRGB eq {3} {4} ifelse} ifelse >> /PUT pdfmark
+[{icc_PDFA} ICCProfile (r) file /PUT pdfmark
+
+% Define the output intent dictionary :
+
+[/_objdef {OutputIntent_PDFA} /type /dict /OBJ pdfmark
+[{OutputIntent_PDFA} <<
+  /Type /OutputIntent             % Must be so (the standard requires).
+  /S /GTS_PDFA1                   % Must be so (the standard requires).
+  /DestOutputProfile {icc_PDFA}            % Must be so (see above).
+  /OutputConditionIdentifier (AdobeRGB1998)      % Customize
+>> /PUT pdfmark
+[{Catalog} <</OutputIntents [ {OutputIntent_PDFA} ]>> /PUT pdfmark
+" >> $PSTMPFILE
+
+
+#=====# CREATE THE COLOR PROFILE FILE #=====#
+echo -n -e "\\x00\\x00\\x02\\x30\\x41\\x44\\x42\\x45\\x02\\x10\\x00\\x00\\x6d\\x6e\\x74\\x72\\x52\\x47\\x42\\x20\\x58\\x59\\x5a\\x20\\x07\\xd0\\x00\\x08\\x00\\x0b\\x00\\x13\\x00\\x33\\x00\\x3b\\x61\\x63\\x73\\x70\\x41\\x50\\x50\\x4c\\x00\\x00\\x00\\x00\\x6e\\x6f\\x6e\\x65\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\xf6\\xd6\\x00\\x01\\x00\\x00\\x00\\x00\\xd3\\x2d\\x41\\x44\\x42\\x45\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x0a\\x63\\x70\\x72\\x74\\x00\\x00\\x00\\xfc\\x00\\x00\\x00\\x32\\x64\\x65\\x73\\x63\\x00\\x00\\x01\\x30\\x00\\x00\\x00\\x6b\\x77\\x74\\x70\\x74\\x00\\x00\\x01\\x9c\\x00\\x00\\x00\\x14\\x62\\x6b\\x70\\x74\\x00\\x00\\x01\\xb0\\x00\\x00\\x00\\x14\\x72\\x54\\x52\\x43\\x00\\x00\\x01\\xc4\\x00\\x00\\x00\\x0e\\x67\\x54\\x52\\x43\\x00\\x00\\x01\\xd4\\x00\\x00\\x00\\x0e\\x62\\x54\\x52\\x43\\x00\\x00\\x01\\xe4\\x00\\x00\\x00\\x0e\\x72\\x58\\x59\\x5a\\x00\\x00\\x01\\xf4\\x00\\x00\\x00\\x14\\x67\\x58\\x59\\x5a\\x00\\x00\\x02\\x08\\x00\\x00\\x00\\x14\\x62\\x58\\x59\\x5a\\x00\\x00\\x02\\x1c\\x00\\x00\\x00\\x14\\x74\\x65\\x78\\x74\\x00\\x00\\x00\\x00\\x43\\x6f\\x70\\x79\\x72\\x69\\x67\\x68\\x74\\x20\\x32\\x30\\x30\\x30\\x20\\x41\\x64\\x6f\\x62\\x65\\x20\\x53\\x79\\x73\\x74\\x65\\x6d\\x73\\x20\\x49\\x6e\\x63\\x6f\\x72\\x70\\x6f\\x72\\x61\\x74\\x65\\x64\\x00\\x00\\x00\\x64\\x65\\x73\\x63\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x11\\x41\\x64\\x6f\\x62\\x65\\x20\\x52\\x47\\x42\\x20\\x28\\x31\\x39\\x39\\x38\\x29\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x58\\x59\\x5a\\x20\\x00\\x00\\x00\\x00\\x00\\x00\\xf3\\x51\\x00\\x01\\x00\\x00\\x00\\x01\\x16\\xcc\\x58\\x59\\x5a\\x20\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x63\\x75\\x72\\x76\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x01\\x02\\x33\\x00\\x00\\x63\\x75\\x72\\x76\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x01\\x02\\x33\\x00\\x00\\x63\\x75\\x72\\x76\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x01\\x02\\x33\\x00\\x00\\x58\\x59\\x5a\\x20\\x00\\x00\\x00\\x00\\x00\\x00\\x9c\\x18\\x00\\x00\\x4f\\xa5\\x00\\x00\\x04\\xfc\\x58\\x59\\x5a\\x20\\x00\\x00\\x00\\x00\\x00\\x00\\x34\\x8d\\x00\\x00\\xa0\\x2c\\x00\\x00\\x0f\\x95\\x58\\x59\\x5a\\x20\\x00\\x00\\x00\\x00\\x00\\x00\\x26\\x31\\x00\\x00\\x10\\x2f\\x00\\x00\\xbe\\x9c" > $ICCTMPFILE
+
+
+#=====# DO THE ACTUAL CONVERSION #=====#
+echo "  Compressing PDF & embedding fonts..."
+run gs $MSGOPTS \
+    -dBATCH -dNOPAUSE -dNOOUTERSAVE \
+    -dCompatibilityLevel=1.4 \
+    -dEmbedAllFonts=true -dSubsetFonts=true \
+    -dCompressFonts=true -dCompressPages=true \
+    -sColorConversionStrategy=RGB \
+    -dDownsampleMonoImages=false -dDownsampleGrayImages=false -dDownsampleColorImages=false \
+    -dAutoFilterColorImages=false -dAutoFilterGrayImages=false \
+    -sDEVICE=pdfwrite \
+    -sOutputFile="$TMPFILE" "$INPUT"
+echo "  Converting to PDF/A-1B..."
+run gs $MSGOPTS \
+    -dPDFA=1 -dBATCH -dNOPAUSE -dNOOUTERSAVE \
+    $QUALITYOPTS \
+    -dCompatibilityLevel=1.4 -dPDFACompatibilityPolicy=1 \
+    -sProcessColorModel=DeviceRGB -sColorConversionStrategy=RGB \
+    -sOutputICCProfile=$ICCTMPFILE \
+    -sDEVICE=pdfwrite \
+    -sOutputFile="$OUTPUT" "$TMPFILE" $PSTMPFILE
+echo "  Removing temporary files..."
+rm $TMPFILE
+echo "  Done, now ESSE3 is happy! ;)"
+
+
+#=====# VALIDATE THE RESULT #=====#
+if $VALIDATE; then
+    validate $VERAMSGOPTS "$OUTPUT"
+else
+    echo "  Suggestion: validate the resulting PDF to be sure it's PDF/A-1B compliant."
+fi

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: libis-format
 version: !ruby/object:Gem::Version
-  version: 1.1.0
+  version: 1.2.0
 platform: ruby
 authors:
 - Kris Dekeyser
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2023-05-08 00:00:00.000000000 Z
+date: 2023-05-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -164,6 +164,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '2.1'
+- !ruby/object:Gem::Dependency
+  name: pdfinfo
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.4'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.4'
 description: Collection of tools and classes that help to identify formats of binary
   files and create derivative copies (e.g. PDF from Word).
 email:
@@ -193,10 +207,10 @@ files:
 - bin/formatinfo
 - bin/libis_format
 - bin/pdf_copy
+- data/AdobeRGB1998.icc
 - data/ISOcoated_v2_eci.icc
 - data/PDFA_def.ps
 - data/ead.xsd
-- data/eciRGB_v2.icc
 - data/lias_formats.xml
 - data/types.yml
 - data/xlink.xsd
@@ -299,6 +313,7 @@ files:
 - tools/fop/lib/xmlgraphics-commons-2.3.jar
 - tools/fop/lib/xmlgraphics-commons.LICENSE.txt
 - tools/fop/lib/xmlgraphics-commons.NOTICE.txt
+- tools/pdf2pdfa
 - tools/pdfbox/pdfbox-app-2.0.13.jar
 - tools/pdfbox/preflight-app-2.0.13.jar
 homepage: ''