Add support for PDF/A-1b

lib/prawn/document.rb

@@ -66,7 +66,8 @@ class Document
       :page_size, :page_layout, :margin, :left_margin,
       :right_margin, :top_margin, :bottom_margin, :skip_page_creation,
       :compress, :background, :info,
-      :text_formatter, :print_scaling
+      :text_formatter, :print_scaling,
+      :enable_pdfa_1b
     ].freeze
 
     # Any module added to this array will be included into instances of
@@ -383,7 +384,7 @@ def render(*a, &b)
     #   pdf.render_file "foo.pdf"
     #
     def render_file(filename)
-      File.open(filename, 'wb') { |f| render(f) }
+      File.open(filename, 'rb+') { |f| render(f) }
     end
 
     # The bounds method returns the current bounding box you are currently in,

lib/prawn/vera_pdf.rb

@@ -0,0 +1,55 @@
+require 'nokogiri'
+require 'open3'
+
+module Prawn
+  module VeraPdf
+    VERA_PDF_EXECUTABLE = 'verapdf'.freeze
+    VERA_PDF_COMMAND = "#{VERA_PDF_EXECUTABLE} --flavour 1b --format xml".freeze
+
+    def which(cmd)
+      exts = ENV['PATHEXT'] ? ENV['PATHEXT'].split(';') : ['']
+      ENV['PATH'].split(File::PATH_SEPARATOR).each do |path|
+        exts.each do |ext|
+          exe = File.join(path, "#{cmd}#{ext}")
+          return exe if File.executable?(exe) && !File.directory?(exe)
+        end
+      end
+      return nil
+    end
+
+    def vera_pdf_available?
+      which VERA_PDF_EXECUTABLE
+    end
+
+    def valid_pdfa_1b?(pdf_data)
+      stdout, stderr, status = Open3.capture3(VERA_PDF_COMMAND, stdin_data: pdf_data)
+      raise Exception, "VeraPDF could not be run. #{stderr}" unless status.success?
+
+      reported_as_compliant? stdout.lines[4..-1].join
+    end
+
+    def reported_as_compliant?(xml_data)
+      xml_doc = Nokogiri::XML xml_data
+      raise Exception, 'The veraPDF xml report was not well formed.' unless xml_doc.errors.empty?
+
+      xml_doc.remove_namespaces!
+      validation_result = xml_doc.xpath('/processorResult/validationResult')
+      assertions = validation_result.xpath('assertions/assertion')
+      assertions.each do |assertion|
+        message = assertion.at_xpath('message').content
+        clause = assertion.at_xpath('ruleId').attribute('clause').content
+        test = assertion.at_xpath('ruleId').attribute('testNumber').content
+        context = assertion.at_xpath('location/context').content
+        url = 'https://github.com/veraPDF/veraPDF-validation-profiles/wiki/PDFA-Part-1-rules'
+        url_anchor = "rule-#{clause.delete('.')}-#{test}"
+        puts
+        puts 'PDF/A-1b VIOLATION'
+        puts "  Message: #{message}"
+        puts "  Context: #{context}"
+        puts "  Details: #{url}##{url_anchor}"
+        puts
+      end
+      validation_result.attribute('isCompliant').content == 'true'
+    end
+  end
+end

prawn.gemspec

@@ -46,6 +46,7 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency('pdf-reader', ['~> 1.4', '>= 1.4.1'])
   spec.add_development_dependency('rubocop', '~> 0.47.1')
   spec.add_development_dependency('rubocop-rspec', '~> 1.10')
+  spec.add_development_dependency('nokogiri', '~> 1.7')
 
   spec.homepage = 'http://prawnpdf.org'
   spec.description = <<END_DESC

spec/manual_spec.rb

@@ -5,7 +5,7 @@
 MANUAL_HASH =
   case RUBY_ENGINE
   when 'ruby'
-    'b55f154c9093c60f38051c75920c8157c775b946b0c77ffafc0a8a634ad5401e8ceafd0b96942839f82bacd726a690af3fdd1fd9e185616f67c6c0edfcfd0460'
+    'ac6e99bf22dd31c21c95295ae7b956a610ce98afcbae2e23df1648e0128b3be8728342d6d9622c73ff3702506e8b00d43557d19a77e7ebc313e8133155568efd'
   when 'jruby'
     'd2eb71ea3ddc35acb185de671a6fa48862ebad5727ce372e3a742f45d31447765c4004fbe5fbfdc1f5a32903ac87182c75e6abe021ab003c8af6e6cc33e0d01e'
   end

spec/prawn/document_spec.rb

@@ -455,7 +455,6 @@ def self.format(string)
 
     it 'is idempotent' do
       pdf = described_class.new
-
       contents = pdf.render
       contents2 = pdf.render
       expect(contents2).to eq(contents)
@@ -508,18 +507,18 @@ def self.format(string)
   end
 
   describe 'content stream characteristics' do
-    it 'has 1 single content stream for a single page PDF' do
+    it 'has 2 content streams for a single page PDF' do
       pdf = described_class.new
       pdf.text 'James'
       output = StringIO.new(pdf.render)
       hash = PDF::Reader::ObjectHash.new(output)
 
       streams = hash.values.select { |obj| obj.is_a?(PDF::Reader::Stream) }
 
-      expect(streams.size).to eq(1)
+      expect(streams.size).to eq(2)
     end
 
-    it 'has 1 single content stream for a single page PDF, even if go_to_page '\
+    it 'has 2 content streams for a single page PDF, even if go_to_page '\
       'is used' do
       pdf = described_class.new
       pdf.text 'James'
@@ -530,7 +529,7 @@ def self.format(string)
 
       streams = hash.values.select { |obj| obj.is_a?(PDF::Reader::Stream) }
 
-      expect(streams.size).to eq(1)
+      expect(streams.size).to eq(2)
     end
   end
 

spec/prawn/pdfa_1b_spec.rb

@@ -0,0 +1,11 @@
+require 'spec_helper'
+require 'prawn/vera_pdf'
+
+include Prawn::VeraPdf
+
+if vera_pdf_available?
+  require_relative 'pdfa_1b_spec_impl'
+else
+  puts 'NOTICE: Specs for PDF/A-1b are not run, because veraPDF ' \
+       'binary was not found in path.'
+end

spec/prawn/pdfa_1b_spec_impl.rb

@@ -0,0 +1,31 @@
+require 'spec_helper'
+require 'prawn/vera_pdf'
+
+describe Prawn::Document do
+  include Prawn::VeraPdf
+
+  let(:pdf) { described_class.new(enable_pdfa_1b: true) }
+
+  describe 'PDF/A 1b conformance' do
+    it 'empty document' do
+      expect(valid_pdfa_1b?(pdf.render)).to be true
+    end
+
+    it 'document with some text' do
+      pdf.font_families.update(
+        'DejaVuSans' => {
+          normal: "#{Prawn::DATADIR}/fonts/DejaVuSans.ttf"
+        }
+      )
+      pdf.font 'DejaVuSans' do
+        pdf.text_box 'Some text', at: [100, 100]
+      end
+      expect(valid_pdfa_1b?(pdf.render)).to be true
+    end
+
+    it 'document with some image' do
+      pdf.image "#{Prawn::DATADIR}/images/pigs.jpg"
+      expect(valid_pdfa_1b?(pdf.render)).to be true
+    end
+  end
+end

spec/prawn/stamp_spec.rb

@@ -95,7 +95,7 @@
         next unless obj =~ %r{/Type /Page$}
         # The page object must contain the annotation reference
         # to render a clickable link
-        expect(obj).to match(%r{^/Annots \[\d \d .\]$})
+        expect(obj).to match(%r{^/Annots \[\d+ \d .\]$})
       end
     end