openwebslides-converter 0.1.0

data/lib/openwebslides/converter/pressbooks.rb

@@ -0,0 +1,181 @@
+# frozen_string_literal: true
+
+require 'nokogiri'
+require 'reverse_markdown'
+
+module OpenWebslides
+  module Converter
+    class Pressbooks
+      include Helpers::Sanitization
+
+      attr_accessor :html,
+                    :result
+
+      ##
+      # Convert an XHTML document to Open Webslides
+      #
+      # @param [String] html XHTML document string
+      # @return [Result] Result object containing all data
+      #
+      def from_xhtml(html)
+        @html = Nokogiri::HTML html
+        @result = Result.new
+
+        root = Content::Root.new
+
+        parse_metadata
+
+        root.child_item_ids << parse_matter('front').id
+        root.child_item_ids.concat parse_parts.map(&:id)
+        root.child_item_ids << parse_matter('back').id
+
+        result.content_items << root
+
+        result
+      end
+
+      protected
+
+      ##
+      # Find and parse metadata
+      #
+      def parse_metadata
+        result.title = html.at('meta[name="pb-title"]')['content']
+        result.author = html.at('meta[name="pb-authors"]')['content']
+        result.license = html.at('meta[name="pb-book-license"]')['content']
+      end
+
+      ##
+      # Find and parse matter
+      #
+      # @param [String] position 'front' or 'back'
+      #
+      def parse_matter(position)
+        # Create new heading
+        heading = Content::Heading.new
+
+        # Set title
+        heading.text = html.at(".#{position}-matter-title").content
+
+        # Parse front matter paragraphs
+        paragraphs = parse_paragraphs html.at(".#{position}-matter-ugc")
+
+        # Add paragraphs to the front matter header
+        heading.sub_item_ids = paragraphs.map(&:id)
+
+        # Add front matter heading to result
+        result.content_items << heading
+
+        heading
+      end
+
+      ##
+      # Find and parse parts
+      #
+      def parse_parts
+        parts = []
+
+        html.search('div.part, div.chapter').each do |div|
+          if div.classes.include? 'part'
+            # Create new part heading
+            parts << Content::Heading.new
+
+            # Set title
+            parts.last.text = div.at('.part-title').content
+
+            # Part intro (paragraphs under part header)
+            intro = parse_paragraphs div
+
+            # Add intro to part
+            parts.last.sub_item_ids = intro.map(&:id)
+          elsif div.classes.include? 'chapter'
+            chapter = parse_chapter div
+
+            # Add chapter heading to the part
+            parts.last.sub_item_ids << chapter.id
+          end
+        end
+
+        # Add parts to result
+        result.content_items.concat parts
+
+        parts
+      end
+
+      ##
+      # Parse chapter XHTML object into content item
+      def parse_chapter(html)
+        # Create new chapter
+        chapter = Content::Heading.new
+
+        # Set title
+        chapter.text = html.at('.chapter-title').content
+
+        # Add chapter heading to result
+        result.content_items << chapter
+
+        # Start with chapter heading as current heading
+        heading = chapter
+
+        # Parse chapter content
+        html.at('.chapter-ugc').children.each do |child|
+          if child.name == 'p'
+            # Parse paragraph
+            paragraph = parse_paragraph child
+
+            # Add paragraph to current heading
+            heading.sub_item_ids << paragraph.id if paragraph
+          elsif child.name == 'h4'
+            # Create new heading
+            h = Content::Heading.new
+
+            # Set title
+            h.text = child.content
+
+            # Add heading to result
+            result.content_items << h
+
+            # Add heading to current heading
+            chapter.sub_item_ids << h.id
+
+            # Replace current heading
+            heading = h
+          elsif child.name == 'ul' || child.name == 'ol'
+            # Extract list items
+            paragraphs = child.search('li').map { |l| parse_paragraph l }
+
+            # Add paragraphs to heading
+            heading.sub_item_ids.concat paragraphs.map(&:id)
+          end
+        end
+
+        chapter
+      end
+
+      ##
+      # Parse XHTML object into paragraph content items
+      #
+      def parse_paragraphs(html)
+        html.search('p').map { |p| parse_paragraph p }
+      end
+
+      ##
+      # Parse paragraph XHTML object into content item
+      #
+      def parse_paragraph(html)
+        # Create new paragraph
+        paragraph = Content::Paragraph.new
+
+        # Extract and sanitize paragraph contents
+        paragraph.text = sanitize ReverseMarkdown.convert html.to_xhtml
+
+        return nil if paragraph.text.empty?
+
+        # Add paragraph to result
+        result.content_items << paragraph
+
+        paragraph
+      end
+    end
+  end
+end

data/lib/openwebslides/converter/result.rb

@@ -0,0 +1,16 @@
+# frozen_string_literal: true
+
+module OpenWebslides
+  module Converter
+    class Result
+      attr_accessor :title,
+                    :author,
+                    :license,
+                    :content_items
+
+      def initialize
+        @content_items = []
+      end
+    end
+  end
+end

data/lib/openwebslides/converter/version.rb

@@ -0,0 +1,7 @@
+# frozen_string_literal: true
+
+module OpenWebslides
+  module Converter
+    VERSION = '0.1.0'
+  end
+end

data/openwebslides-converter.gemspec

@@ -0,0 +1,43 @@
+# frozen_string_literal: true
+
+lib = File.expand_path('lib', __dir__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'openwebslides/converter/version'
+
+Gem::Specification.new do |gem|
+  gem.name          = 'openwebslides-converter'
+  gem.version       = OpenWebslides::Converter::VERSION
+  gem.summary       = 'Open Webslides Converter'
+  gem.description   = 'Converts arbitrary content data formats to Open Webslides data format'
+  gem.license       = 'MIT'
+  gem.authors       = ['Florian Dejonckheere']
+  gem.email         = 'florian@floriandejonckheere.be'
+  gem.homepage      = 'https://rubygems.org/gems/openwebslides-converter'
+
+  gem.files         = `git ls-files`.split($INPUT_RECORD_SEPARATOR)
+
+  `git submodule --quiet foreach --recursive pwd`.split($INPUT_RECORD_SEPARATOR).each do |submodule|
+    submodule.sub!("#{Dir.pwd}/", '')
+
+    Dir.chdir(submodule) do
+      `git ls-files`.split($INPUT_RECORD_SEPARATOR).map do |subpath|
+        gem.files << File.join(submodule, subpath)
+      end
+    end
+  end
+
+  gem.executables   = gem.files.grep(%r{^bin/}).map { |f| File.basename(f) }
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.require_paths = ['lib']
+
+  gem.add_dependency 'nokogiri', '~> 1.8'
+  gem.add_dependency 'reverse_markdown', '~> 1.1'
+
+  gem.add_development_dependency 'bundler', '~> 1.10'
+  gem.add_development_dependency 'coveralls', '~> 0.8'
+  gem.add_development_dependency 'rake', '~> 10.0'
+  gem.add_development_dependency 'rdoc', '~> 4.0'
+  gem.add_development_dependency 'rspec', '~> 3.0'
+  gem.add_development_dependency 'rubocop', '~> 0.58'
+  gem.add_development_dependency 'rubygems-tasks', '~> 0.2'
+end

data/spec/content/content_item_spec.rb

@@ -0,0 +1,25 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+RSpec.describe Content::ContentItem do
+  ##
+  # Configuration
+  #
+  ##
+  # Stubs and mocks
+  #
+  ##
+  # Test variables
+  #
+  ##
+  # Subject
+  #
+  ##
+  # Tests
+  #
+  describe 'included properties' do
+    it { is_expected.to respond_to :id }
+    it { is_expected.to respond_to :type }
+  end
+end

data/spec/content/heading_spec.rb

@@ -0,0 +1,27 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+RSpec.describe Content::Heading do
+  ##
+  # Configuration
+  #
+  ##
+  # Stubs and mocks
+  #
+  ##
+  # Test variables
+  #
+  ##
+  # Subject
+  #
+  ##
+  # Tests
+  #
+  describe 'included properties' do
+    it { is_expected.to respond_to :id }
+    it { is_expected.to respond_to :type }
+    it { is_expected.to respond_to :text }
+    it { is_expected.to respond_to :sub_item_ids }
+  end
+end

data/spec/content/paragraph_spec.rb

@@ -0,0 +1,27 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+RSpec.describe Content::Paragraph do
+  ##
+  # Configuration
+  #
+  ##
+  # Stubs and mocks
+  #
+  ##
+  # Test variables
+  #
+  ##
+  # Subject
+  #
+  ##
+  # Tests
+  #
+  describe 'included properties' do
+    it { is_expected.to respond_to :id }
+    it { is_expected.to respond_to :type }
+    it { is_expected.to respond_to :text }
+    it { is_expected.to respond_to :sub_item_ids }
+  end
+end

data/spec/content/properties/container_spec.rb

@@ -0,0 +1,48 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+RSpec.describe Content::Properties::Container do
+  ##
+  # Configuration
+  #
+  ##
+  # Stubs and mocks
+  #
+  ##
+  # Test variables
+  #
+  let(:object) do
+    obj = Object.new
+    # Always include Identifier as top of the #to_h chain
+    obj.extend Content::Properties::Identifier
+    obj.extend described_class
+
+    obj
+  end
+
+  ##
+  # Subject
+  #
+  subject { object }
+
+  ##
+  # Tests
+  #
+  describe 'included properties' do
+    it { is_expected.to respond_to :child_item_ids }
+    it { is_expected.to respond_to :to_h }
+
+    it 'sets a default value for the property' do
+      expect(subject.child_item_ids).not_to be_nil
+    end
+  end
+
+  describe 'methods' do
+    describe '#to_h' do
+      it 'returns a hash with the property' do
+        expect(subject.to_h).to include :child_item_ids
+      end
+    end
+  end
+end

data/spec/content/properties/identifier_spec.rb

@@ -0,0 +1,51 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+RSpec.describe Content::Properties::Identifier do
+  ##
+  # Configuration
+  #
+  ##
+  # Stubs and mocks
+  #
+  ##
+  # Test variables
+  #
+  let(:object) do
+    obj = Object.new
+    obj.extend described_class
+  end
+
+  ##
+  # Subject
+  #
+  subject { object }
+
+  ##
+  # Tests
+  #
+  describe 'included properties' do
+    it { is_expected.to respond_to :id }
+    it { is_expected.to respond_to :to_h }
+
+    it 'sets a default value for the property' do
+      expect(subject.id).not_to be_nil
+    end
+  end
+
+  describe 'methods' do
+    describe '#to_h' do
+      it 'returns a hash with the property' do
+        expect(subject.to_h).to include :id
+      end
+    end
+
+    describe '#generate_id' do
+      it 'returns a 10-digit string' do
+        expect(subject.send :generate_id).to be_a String
+        expect(subject.send(:generate_id).length).to eq 10
+      end
+    end
+  end
+end

data/spec/content/properties/metadata_spec.rb

@@ -0,0 +1,48 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+RSpec.describe Content::Properties::Metadata do
+  ##
+  # Configuration
+  #
+  ##
+  # Stubs and mocks
+  #
+  ##
+  # Test variables
+  #
+  let(:object) do
+    obj = Object.new
+    # Always include Identifier as top of the #to_h chain
+    obj.extend Content::Properties::Identifier
+    obj.extend described_class
+
+    obj
+  end
+
+  ##
+  # Subject
+  #
+  subject { object }
+
+  ##
+  # Tests
+  #
+  describe 'included properties' do
+    it { is_expected.to respond_to :metadata }
+    it { is_expected.to respond_to :to_h }
+
+    it 'sets a default value for the property' do
+      expect(subject.metadata).not_to be_nil
+    end
+  end
+
+  describe 'methods' do
+    describe '#to_h' do
+      it 'returns a hash with the property' do
+        expect(subject.to_h).to include :metadata
+      end
+    end
+  end
+end