hexapdf 0.11.9 → 0.13.0

data/lib/hexapdf/cli/files.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2019 Thomas Leitner
+# Copyright (C) 2014-2020 Thomas Leitner
 #
 # HexaPDF is free software: you can redistribute it and/or modify it
 # under the terms of the GNU Affero General Public License version 3 as

data/lib/hexapdf/cli/form.rb

@@ -0,0 +1,240 @@
+# -*- encoding: utf-8; frozen_string_literal: true -*-
+#
+#--
+# This file is part of HexaPDF.
+#
+# HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
+# Copyright (C) 2014-2020 Thomas Leitner
+#
+# HexaPDF is free software: you can redistribute it and/or modify it
+# under the terms of the GNU Affero General Public License version 3 as
+# published by the Free Software Foundation with the addition of the
+# following permission added to Section 15 as permitted in Section 7(a):
+# FOR ANY PART OF THE COVERED WORK IN WHICH THE COPYRIGHT IS OWNED BY
+# THOMAS LEITNER, THOMAS LEITNER DISCLAIMS THE WARRANTY OF NON
+# INFRINGEMENT OF THIRD PARTY RIGHTS.
+#
+# HexaPDF 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 Affero General Public
+# License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with HexaPDF. If not, see <http://www.gnu.org/licenses/>.
+#
+# The interactive user interfaces in modified source and object code
+# versions of HexaPDF must display Appropriate Legal Notices, as required
+# under Section 5 of the GNU Affero General Public License version 3.
+#
+# In accordance with Section 7(b) of the GNU Affero General Public
+# License, a covered work must retain the producer line in every PDF that
+# is created or manipulated using HexaPDF.
+#
+# If the GNU Affero General Public License doesn't fit your need,
+# commercial licenses are available at <https://gettalong.at/hexapdf/>.
+#++
+
+require 'hexapdf/cli/command'
+require 'strscan'
+
+module HexaPDF
+  module CLI
+
+    # Processes a PDF that contains an interactive form (AcroForm).
+    class Form < Command
+
+      def initialize #:nodoc:
+        super('form', takes_commands: false)
+        short_desc("Show form fields and fill out a form")
+        long_desc(<<~EOF)
+          Use this command to process interactive PDF forms.
+
+          If the the output file name is not given, all form fields are listed in page order. Use
+          the global --verbose option to show additional information like field type and location.
+
+          If the output file name is given, the fields can be interactively filled out. By
+          additionally using the --template option, the data for the fields is read from the given
+          template file instead of the standard input.
+        EOF
+
+        options.on("--password PASSWORD", "-p", String,
+                   "The password for decryption. Use - for reading from standard input.") do |pwd|
+          @password = (pwd == '-' ? read_password : pwd)
+        end
+        options.on("--template TEMPLATE_FILE", "-t TEMPLATE_FILE",
+                   "Use the template file for the field values") do |template|
+          @template = template
+        end
+        options.on("--[no-]viewer-override", "Let the PDF viewer override the visual " \
+                   "appearance. Default: use setting from input PDF") do |need_appearances|
+          @need_appearances = need_appearances
+        end
+        options.on("--[no-]incremental-save", "Append the changes instead of rewriting the " \
+                   "whole file. Default: true") do |incremental|
+          @incremental = incremental
+        end
+
+        @password = nil
+        @template = nil
+        @need_appearances = nil
+        @incremental = true
+      end
+
+      def execute(in_file, out_file = nil) #:nodoc:
+        maybe_raise_on_existing_file(out_file) if out_file
+        with_document(in_file, password: @password, out_file: out_file,
+                      incremental: @incremental) do |doc|
+          if !doc.acro_form
+            raise "This PDF doesn't contain an interactive form"
+          elsif out_file
+            doc.acro_form[:NeedAppearances] = @need_appearances unless @need_appearances.nil?
+            if @template
+              fill_form_with_template(doc)
+            else
+              fill_form(doc)
+            end
+          else
+            list_form_fields(doc)
+          end
+        end
+      end
+
+      private
+
+      # Lists all terminal form fields.
+      def list_form_fields(doc)
+        current_page_index = -1
+        each_field(doc) do |_page, page_index, field, widget|
+          if current_page_index != page_index
+            puts "Page #{page_index + 1}"
+            current_page_index = page_index
+          end
+
+          field_name = field.full_field_name +
+            (field.alternate_field_name ? " (#{field.alternate_field_name})" : '')
+          concrete_field_type = field.concrete_field_type
+          nice_field_type = concrete_field_type.to_s.split('_').map(&:capitalize).join(' ')
+          position = "(#{widget[:Rect].left}, #{widget[:Rect].bottom})"
+
+          puts "  #{field_name}"
+          if command_parser.verbosity_info?
+            printf("    └─ %-22s | %-20s\n", nice_field_type, position)
+          end
+          puts "    └─ #{field.field_value.inspect}"
+          if command_parser.verbosity_info?
+            if field.field_type == :Ch
+              puts "    └─ Options: #{field.option_items.map(&:inspect).join(', ')}"
+            elsif concrete_field_type == :radio_button
+              puts "    └─ Options: #{field.radio_button_values.map(&:inspect).join(', ')}"
+            end
+          end
+        end
+      end
+
+      # Fills out the form by interactively asking the user for field values.
+      def fill_form(doc)
+        current_page_index = -1
+        each_field(doc) do |_page, page_index, field, _widget|
+          if current_page_index != page_index
+            puts "Page #{page_index + 1}"
+            current_page_index = page_index
+          end
+
+          field_name = field.full_field_name +
+            (field.alternate_field_name ? " (#{field.alternate_field_name})" : '')
+          concrete_field_type = field.concrete_field_type
+
+          puts "  #{field_name}"
+          puts "    └─ Current value: #{field.field_value.inspect}"
+
+          if field.field_type == :Ch
+            puts "    └─ Possible values: #{field.option_items.map(&:inspect).join(', ')}"
+          elsif concrete_field_type == :radio_button
+            puts "    └─ Possible values: #{field.radio_button_values.map(&:inspect).join(', ')}"
+          elsif concrete_field_type == :check_box
+            puts "    └─ Possible values: y(es), t(rue); n(o), f(alse)"
+          end
+
+          begin
+            print "    └─ New value: "
+            value = $stdin.readline.chomp
+            next if value.empty?
+            apply_field_value(field, value)
+          rescue HexaPDF::Error => e
+            puts "       ⚠  #{e.message}"
+            retry
+          end
+        end
+      end
+
+      # Fills out the form using the data from the provided template file.
+      def fill_form_with_template(doc)
+        data = parse_template
+        form = doc.acro_form
+        data.each do |name, value|
+          field = form.field_by_name(name)
+          raise "Field '#{name}' not found in input PDF" unless field
+          apply_field_value(field, value)
+        end
+      end
+
+      # Parses the data from the given template file.
+      def parse_template
+        data = {}
+        scanner = StringScanner.new(File.read(@template))
+        until scanner.eos?
+          field_name = scanner.scan(/(\\:|[^:])*?:/)
+          break unless field_name
+          field_name.gsub!(/\\:/, ':')
+          field_value = scanner.scan(/.*?(?=^\S|\z)/m)
+          data[field_name.chop] = field_value.strip.gsub(/^\s*/, '') if field_value
+        end
+        if !scanner.eos? && command_parser.verbosity_warning?
+          $stderr.puts "Warning: Some template could not be parsed"
+        end
+        data
+      end
+
+      # Applies the given value to the field.
+      def apply_field_value(field, value)
+        case field.concrete_field_type
+        when :single_line_text_field
+          field.field_value = value
+        when :combo_box, :list_box
+          field.field_value = value
+        when :editable_combo_box
+          field.field_value = value
+        when :check_box
+          unless value.match?(/y(es)?|t(rue)?|f(alse)?|n(o)/)
+            raise HexaPDF::Error, "Invalid input, use one of the possible values"
+          end
+          field.field_value = value.match?(/y(es)?|t(rue)?/)
+        when :radio_button
+          field.field_value = value.intern
+        else
+          raise "Field type not yet supported"
+        end
+      end
+
+      # Iterates over all non-push button fields in page order. If a field appears on multiple
+      # pages, it is only yielded on the first page.
+      def each_field(doc) # :yields: page, page_index, field
+        seen = {}
+
+        doc.pages.each_with_index do |page, page_index|
+          page[:Annots]&.each do |annotation|
+            next unless annotation[:Subtype] == :Widget
+            field = annotation.form_field
+            next if field.concrete_field_type == :push_button
+            unless seen[field]
+              yield(page, page_index, field, annotation)
+              seen[field] = true
+            end
+          end
+        end
+      end
+
+    end
+
+  end
+end

data/lib/hexapdf/cli/image2pdf.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2019 Thomas Leitner
+# Copyright (C) 2014-2020 Thomas Leitner
 #
 # HexaPDF is free software: you can redistribute it and/or modify it
 # under the terms of the GNU Affero General Public License version 3 as
@@ -64,7 +64,8 @@ module HexaPDF
                            orientation = :landscape
                            page_size.delete_suffix!('-landscape')
                          end
-                         HexaPDF::Type::Page.media_box(page_size.to_sym, orientation: orientation)
+                         page_size = page_size.capitalize.to_sym
+                         HexaPDF::Type::Page.media_box(page_size, orientation: orientation)
                        end
         end
         options.on("--[no-]auto-rotate", "Automatically rotate pages based on image dimesions. " \

data/lib/hexapdf/cli/images.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2019 Thomas Leitner
+# Copyright (C) 2014-2020 Thomas Leitner
 #
 # HexaPDF is free software: you can redistribute it and/or modify it
 # under the terms of the GNU Affero General Public License version 3 as

data/lib/hexapdf/cli/info.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2019 Thomas Leitner
+# Copyright (C) 2014-2020 Thomas Leitner
 #
 # HexaPDF is free software: you can redistribute it and/or modify it
 # under the terms of the GNU Affero General Public License version 3 as
@@ -55,13 +55,21 @@ module HexaPDF
         long_desc(<<~EOF)
           This command extracts information from the Info dictionary of a PDF file as well
           as some other useful information like the used PDF version and encryption information.
+
+          If the --check option is specified, the PDF file will also be checked for parse and
+          validation errors. And if the process doesn't abort, HexaPDF is still able to handle the
+          file by correcting the errors.
         EOF
+        options.on("--check", "-c", "Check the PDF file for parse errors and validity") do |check|
+          @check_file = check
+        end
         options.on("--password PASSWORD", "-p", String,
                    "The password for decryption. Use - for reading from standard input.") do |pwd|
           @password = (pwd == '-' ? read_password : pwd)
         end
         @password = nil
         @auto_decrypt = true
+        @check_file = false
       end
 
       def execute(file) #:nodoc:
@@ -79,8 +87,30 @@ module HexaPDF
         options = pdf_options(@password)
         options[:config]['document.auto_decrypt'] = @auto_decrypt
         HexaPDF::Document.open(file, **options) do |doc|
+          if @check_file
+            indirect_object = nil
+            validation_block = lambda do |msg, correctable, object|
+              object = indirect_object unless object.indirect? || object.type == :XXTrailer
+              object_type = if object.type == :XXTrailer
+                              'trailer'
+                            elsif !object.type.to_s.start_with?("XX")
+                              "object type #{object.type} (#{object.oid},#{object.gen})"
+                            else
+                              "object (#{object.oid},#{object.gen})"
+                            end
+              object_type = "sub-object of #{object_type}" if object == indirect_object
+              puts "WARNING: Validation error for #{object_type}: #{msg} " \
+                "#{correctable ? '(correctable)' : ''}"
+            end
+            doc.trailer.validate(auto_correct: true, &validation_block)
+            doc.each(only_current: false, only_loaded: false) do |obj|
+              indirect_object = obj
+              obj.validate(auto_correct: true, &validation_block)
+            end
+          end
+
           output_line("File name", file)
-          output_line("File size", File.stat(file).size.to_s + " bytes")
+          output_line("File size", File.stat(file).size.to_s << " bytes")
           @auto_decrypt && INFO_KEYS.each do |name|
             next unless doc.trailer.info.key?(name)
             output_line(name.to_s, doc.trailer.info[name].to_s)
@@ -110,10 +140,29 @@ module HexaPDF
         else
           raise
         end
+      rescue HexaPDF::MalformedPDFError => e
+        $stderr.puts "Error: PDF file #{file} is damaged and cannot be recovered"
+        $stderr.puts "       #{e}"
+      end
+
+      # Use custom options if we are checking the PDF file for errors.
+      def pdf_options(password)
+        if @check_file
+          options = {decryption_opts: {password: password}, config: {}}
+          HexaPDF::GlobalConfiguration['filter.predictor.strict'] = false
+          options[:config]['parser.try_xref_reconstruction'] = true
+          options[:config]['parser.on_correctable_error'] = lambda do |_, msg, pos|
+            puts "WARNING: Parse error at position #{pos}: #{msg}"
+            false
+          end
+          options
+        else
+          super
+        end
       end
 
       def output_line(header, text) #:nodoc:
-        puts((header + ":").ljust(COLUMN_WIDTH) << text)
+        puts(("#{header}:").ljust(COLUMN_WIDTH) << text)
       end
 
     end

data/lib/hexapdf/cli/inspect.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2019 Thomas Leitner
+# Copyright (C) 2014-2020 Thomas Leitner
 #
 # HexaPDF is free software: you can redistribute it and/or modify it
 # under the terms of the GNU Affero General Public License version 3 as
@@ -122,22 +122,22 @@ module HexaPDF
           case command
           when /^\d+(,\d+)?$/, 'o', 'object'
             arg = (command.start_with?('o') ? data.shift : command)
-            obj = pdf_object_from_string_reference(arg) rescue puts($!.message)
-            if obj.data.stream && command_parser.verbosity_info?
+            obj = pdf_object_from_string_reference(arg) rescue $stderr.puts($!.message)
+            if obj&.data&.stream && command_parser.verbosity_info?
               $stderr.puts("Note: Object also has stream data")
             end
             serialize(obj.value, recursive: false) if obj
 
           when 'r', 'recursive'
             obj = if (obj = data.shift)
-                    pdf_object_from_string_reference(obj) rescue puts($!.message)
+                    pdf_object_from_string_reference(obj) rescue $stderr.puts($!.message)
                   else
                     @doc.trailer
                   end
             serialize(obj.value, recursive: true) if obj
 
           when 's', 'stream', 'raw', 'raw-stream'
-            if (obj = pdf_object_from_string_reference(data.shift) rescue puts($!.message)) &&
+            if (obj = pdf_object_from_string_reference(data.shift) rescue $stderr.puts($!.message)) &&
                 obj.kind_of?(HexaPDF::Stream)
               source = (command.start_with?('raw') ? obj.stream_source : obj.stream_decoder)
               while source.alive? && (stream_data = source.resume)
@@ -148,7 +148,7 @@ module HexaPDF
             end
 
           when 'x', 'xref'
-            if (obj = pdf_object_from_string_reference(data.shift) rescue puts($!.message))
+            if (obj = pdf_object_from_string_reference(data.shift) rescue $stderr.puts($!.message))
               @doc.revisions.reverse_each do |rev|
                 if (xref = rev.xref(obj))
                   puts xref
@@ -178,6 +178,26 @@ module HexaPDF
               puts str
             end
 
+          when 'po', 'ps'
+            page_number_str = data.shift
+            unless page_number_str
+              $stderr.puts("Error: Missing PAGE argument to #{command}")
+              next
+            end
+            page_number = parse_pages_specification(page_number_str, @doc.pages.count).first&.first
+            unless page_number
+              $stderr.puts("Error: Invalid page number #{page_number_str}")
+              next
+            end
+            page = @doc.pages[page_number]
+            if command.start_with?('ps')
+              $stdout.write(page.contents)
+            else
+              puts "#{page.oid} #{page.gen} obj"
+              serialize(page.value, recursive: false)
+              puts "endobj"
+            end
+
           when 'pc', 'page-count'
             puts @doc.pages.count
 
@@ -217,9 +237,9 @@ module HexaPDF
         if str.nil?
           raise "Error: Missing argument object identifier OID[,GEN]"
         elsif !str.match?(/^\d+(,\d+)?$/)
-          raise "Error: Invalid argument: Must be of form OID[,GEN]"
+          raise "Error: Invalid argument: Must be of form OID[,GEN], not '#{str}'"
         elsif !(obj = @doc.object(pdf_reference_from_string(str)))
-          raise "Error: No object with the given object identifier found"
+          raise "Error: No object with the given object identifier '#{str}' found"
         else
           obj
         end
@@ -240,7 +260,7 @@ module HexaPDF
           puts "<<"
           (recursive ? val.sort : val).each do |k, v|
             next if v.nil? || (v.respond_to?(:null?) && v.null?)
-            print '  ' * (indent + 1) + @serializer.serialize_symbol(k) + " "
+            print '%s%s ' % ['  ' * (indent + 1), @serializer.serialize_symbol(k)]
             serialize(v, recursive: recursive, seen: seen, indent: indent + 1)
             puts
           end
@@ -283,6 +303,8 @@ module HexaPDF
         ["c[atalog]", "Print the catalog dictionary"],
         ["t[railer]", "Print the trailer dictionary"],
         ["p[ages] [RANGE]",  "Print information about pages"],
+        ["po PAGE", "Print the page object"],
+        ["ps PAGE", "Print the content stream of the page"],
         ["pc | page-count", "Print the number of pages"],
         ["search REGEXP", "Print objects matching the pattern"],
         ["h[elp]", "Show the help"],