article_json 0.1.0 → 0.2.0

data/lib/article_json/export/html/elements/image.rb

@@ -3,29 +3,7 @@ module ArticleJSON
     module HTML
       module Elements
         class Image < Base
-          include Shared::Caption
-          include Shared::Float
-
-          # @return [Nokogiri::HTML::Node]
-          def export
-            create_element(:figure, node_opts).tap do |figure|
-              figure.add_child(image_node)
-              figure.add_child(caption_node(:figcaption))
-            end
-          end
-
-          private
-
-          # @return [Nokogiri::HTML::Node]
-          def image_node
-            create_element(:img, src: @element.source_url)
-          end
-
-          # @return [Hash]
-          def node_opts
-            return if floating_class.nil?
-            { class: floating_class }
-          end
+          include ArticleJSON::Export::Common::HTML::Elements::Image
         end
       end
     end

data/lib/article_json/export/html/elements/list.rb

@@ -3,21 +3,7 @@ module ArticleJSON
     module HTML
       module Elements
         class List < Base
-          def export
-            create_element(tag_name).tap do |list|
-              @element.content.each do |child_element|
-                item = create_element(:li)
-                item.add_child(Paragraph.new(child_element).export)
-                list.add_child(item)
-              end
-            end
-          end
-
-          private
-
-          def tag_name
-            @element.list_type == :ordered ? :ol : :ul
-          end
+          include ArticleJSON::Export::Common::HTML::Elements::List
         end
       end
     end

data/lib/article_json/export/html/elements/paragraph.rb

@@ -3,13 +3,7 @@ module ArticleJSON
     module HTML
       module Elements
         class Paragraph < Base
-          def export
-            create_element(:p).tap do |p|
-              @element.content.each do |child_element|
-                p.add_child(Text.new(child_element).export)
-              end
-            end
-          end
+          include ArticleJSON::Export::Common::HTML::Elements::Paragraph
         end
       end
     end

data/lib/article_json/export/html/elements/quote.rb

@@ -3,25 +3,7 @@ module ArticleJSON
     module HTML
       module Elements
         class Quote < Base
-          include Shared::Caption
-          include Shared::Float
-
-          def export
-            create_element(:aside, node_opts).tap do |aside|
-              @element.content.each do |child_element|
-                aside.add_child(Base.new(child_element).export)
-              end
-              aside.add_child(caption_node(:small))
-            end
-          end
-
-          private
-
-          # @return [Hash]
-          def node_opts
-            return if floating_class.nil?
-            { class: floating_class }
-          end
+          include ArticleJSON::Export::Common::HTML::Elements::Quote
         end
       end
     end

data/lib/article_json/export/html/elements/text.rb

@@ -3,40 +3,7 @@ module ArticleJSON
     module HTML
       module Elements
         class Text < Base
-          # @return [Nokogiri::HTML::Node]
-          def export
-            return bold_and_italic_node if @element.bold && @element.italic
-            return bold_node if @element.bold
-            return italic_node if @element.italic
-            content_node
-          end
-
-          private
-
-          # @return [Nokogiri::HTML::Node]
-          def italic_node
-            create_element(:em).tap { |em| em.add_child(content_node) }
-          end
-
-          # @return [Nokogiri::HTML::Node]
-          def bold_node
-            create_element(:strong).tap do |strong|
-              strong.add_child(content_node)
-            end
-          end
-
-          # @return [Nokogiri::HTML::Node]
-          def bold_and_italic_node
-            create_element(:strong).tap do |strong|
-              strong.add_child(italic_node)
-            end
-          end
-
-          # @return [Nokogiri::HTML::Node]
-          def content_node
-            return create_text_node(@element.content) if @element.href.nil?
-            create_element(:a, @element.content, href: @element.href)
-          end
+          include ArticleJSON::Export::Common::HTML::Elements::Text
         end
       end
     end

data/lib/article_json/export/html/elements/text_box.rb

@@ -3,21 +3,7 @@ module ArticleJSON
     module HTML
       module Elements
         class TextBox < Base
-          include Shared::Float
-
-          def export
-            create_element(:div, node_opts).tap do |div|
-              @element.content.each do |child_element|
-                div.add_child(Base.new(child_element).export)
-              end
-            end
-          end
-
-          private
-
-          def node_opts
-            { class: ['text-box', floating_class].compact.join(' ') }
-          end
+          include ArticleJSON::Export::Common::HTML::Elements::TextBox
         end
       end
     end

data/lib/article_json/export/html/exporter.rb

@@ -2,19 +2,14 @@ module ArticleJSON
   module Export
     module HTML
       class Exporter
-        # @param [Array[ArticleJSON::Elements::Base]] elements
-        def initialize(elements)
-          @elements = elements
-        end
+        include ArticleJSON::Export::Common::HTML::Exporter
 
-        # Generate a string with the HTML representation of all elements
-        # @return [String]
-        def html
-          doc = Nokogiri::HTML.fragment('')
-          @elements.each do |element|
-            doc.add_child(Elements::Base.new(element).export)
+        class << self
+          # Return the module namespace this class is nested in
+          # @return [Module]
+          def namespace
+            ArticleJSON::Export::HTML
           end
-          doc.to_html(save_with: 0)
         end
       end
     end

data/lib/article_json/import/google_doc/html/embedded_vimeo_video_parser.rb

@@ -15,10 +15,10 @@ module ArticleJSON
             # @return [Regexp]
             def url_regexp
               %r{
-                ^\S*           # all protocols & sub domains
-                vimeo\.com     # domain
-                .*[\#/]        # optional path
-                (?<id>[\d]+)   # numerical id
+                ^\S*                # all protocols & sub domains
+                vimeo\.com          # domain
+                .*([\#/]|clip_id=)  # optional path & param
+                (?<id>[\d]+)        # numerical id
               }xi
             end
           end

data/lib/article_json/import/google_doc/html/node_analyzer.rb

@@ -23,14 +23,15 @@ module ArticleJSON
           # @return [Boolean]
           def empty?
             return @is_empty if defined? @is_empty
-            @is_empty = node.inner_text.strip.empty? && !image? && !hr?
+            @is_empty = node.inner_text.strip.empty? && !image? && !hr? && !br?
           end
 
           # Check if the node is a header tag between <h1> and <h5>
           # @return [Boolean]
           def heading?
             return @is_heading if defined? @is_heading
-            @is_heading = %w(h1 h2 h3 h4 h5).include?(node.name)
+            @is_heading =
+              !quote? && !text_box? && %w(h1 h2 h3 h4 h5).include?(node.name)
           end
 
           # Check if the node is a horizontal line (i.e. `<hr>`)
@@ -89,6 +90,14 @@ module ArticleJSON
             @is_embed = EmbeddedParser.supported?(node)
           end
 
+          # Check if the node is a linebreak. A span only containing whitespaces
+          # and <br> tags is considered a linebreak.
+          # @return [Boolean]
+          def br?
+            return @is_br if defined? @is_br
+            @is_br = node.name == 'br' || only_includes_brs?
+          end
+
           # Determine the type of this node
           # The type is one of the elements supported by article_json.
           # @return [Symbol]
@@ -104,6 +113,19 @@ module ArticleJSON
             return :embed if embed?
             :unknown
           end
+
+          private
+
+          # Return true if the node only contains <br> nodes and empty text
+          # @return [Boolean]
+          def only_includes_brs?
+            return false unless node.inner_text.strip.empty?
+            tags = node.children.map(&:name)
+            # Check if it only contains <br> and text nodes
+            return false unless tags.all? { |tag| %w(br text).include? tag }
+            # Check if at least one is a `<br>` node
+            tags.include?('br')
+          end
         end
       end
     end

data/lib/article_json/import/google_doc/html/parser.rb

@@ -53,11 +53,13 @@ module ArticleJSON
             HeadingParser.new(node: @current_node.node).element
           end
 
-          # @return [ArticleJSON::Elements::Paragraph]
+          # @return [ArticleJSON::Elements::Paragraph|nil]
           def parse_paragraph
-            ParagraphParser
-              .new(node: @current_node.node, css_analyzer: @css_analyzer)
-              .element
+            paragraph =
+              ParagraphParser
+                .new(node: @current_node.node, css_analyzer: @css_analyzer)
+                .element
+            paragraph unless paragraph.blank?
           end
 
           # @return [ArticleJSON::Elements::List]
@@ -72,7 +74,7 @@ module ArticleJSON
             ImageParser
               .new(
                 node: @current_node.node,
-                caption_node: @body_enumerator.next,
+                caption_node: next_node,
                 css_analyzer: @css_analyzer
               )
               .element
@@ -96,7 +98,7 @@ module ArticleJSON
           def parse_embed
             EmbeddedParser.build(
               node: @current_node.node,
-              caption_node: @body_enumerator.next,
+              caption_node: next_node,
               css_analyzer: @css_analyzer
             )
           end
@@ -105,12 +107,19 @@ module ArticleJSON
           # @return [Array[Nokogiri::HTML::Node]]
           def nodes_until_hr
             nodes = []
-            until NodeAnalyzer.new(@body_enumerator.peek).hr?
+            until !body_has_more_nodes? ||
+                NodeAnalyzer.new(@body_enumerator.peek).hr?
               nodes << @body_enumerator.next
             end
             nodes
           end
 
+          # Return the next node if available, and advance the enumerator
+          # @return [Nokogiri::HTML::Node]
+          def next_node
+            body_has_more_nodes? ? @body_enumerator.next : nil
+          end
+
           # @return [Boolean]
           def body_has_more_nodes?
             @body_enumerator.peek

data/lib/article_json/import/google_doc/html/shared/caption.rb

@@ -7,11 +7,18 @@ module ArticleJSON
             # Parse the caption node
             # @return [Array[ArticleJSON::Elements::Text]]
             def caption
+              return empty_caption if @caption_node.nil?
               ArticleJSON::Import::GoogleDoc::HTML::TextParser.extract(
                 node: @caption_node,
                 css_analyzer: @css_analyzer
               )
             end
+
+            private
+
+            def empty_caption
+              [ArticleJSON::Elements::Text.new(content: ' ')]
+            end
           end
         end
       end

data/lib/article_json/import/google_doc/html/text_parser.rb

@@ -13,7 +13,10 @@ module ArticleJSON
           # The content of the text node, w/o any markup
           # @return [String]
           def content
-            @node.inner_text
+            @node.children
+              .map { |child| child.name == 'br' ? "\n" : child.inner_text }
+              .join('')
+              .gsub(/\s*\n\s*/, "\n") # Only keep a single consecutive linebreak
           end
 
           # Check if the text node is styled as bold

data/lib/article_json/utils/additional_element_placer.rb

@@ -0,0 +1,66 @@
+module ArticleJSON
+  module Utils
+    # This class allows the user to place additional elements within an article.
+    # It distributes elements over the whole article and ensures that an
+    # additional element is only ever placed between two paragraph elements. If
+    # there are not enough spaces, the remaining additional elements will be
+    # appended to the existing article elements.
+    class AdditionalElementPlacer
+      # @param [ArticleJSON::Article] article
+      # @param [Array[Object]] additional_elements
+      def initialize(article, additional_elements)
+        @elements = article.elements.dup
+        @additional_elements = additional_elements
+      end
+
+      # Distribute additional elements evenly throughout the article elements
+      # @return [Array[ArticleJSON::Elements::Base|Object]]
+      def merge_elements
+        indexes = indexes_for_additional_elements
+
+        if indexes.count < @additional_elements.count
+          @elements.push(*@additional_elements[indexes.count..-1])
+        end
+
+        indexes
+          .reverse
+          .zip(@additional_elements[0...indexes.count].reverse)
+          .each { |index, element| @elements.insert(index, element) }
+
+        @elements
+      end
+
+      private
+
+      # Find indexes within article elements where there is a paragraph on the
+      # current and on the next node
+      # @return [Array[Integer]]
+      def indexes_between_paragraphs
+        @elements
+          .each_cons(2) # iterate over elements in consecutive sets of 2
+          .with_index
+          .each_with_object([]) do |((current, following), index), possibilities|
+          if current.type == :paragraph && following.type == :paragraph
+            possibilities << index + 1
+          end
+        end
+      end
+
+      # Return evenly spread indexes of positions to insert a given number of
+      # additional elements
+      # @return [Array[Integer]]
+      def indexes_for_additional_elements
+        indexes = indexes_between_paragraphs
+        insert_every = indexes.count / @additional_elements.count
+
+        # in case there are more elements to add than available positions:
+        insert_every = 1 if insert_every == 0
+
+        indexes
+          .reject
+          .with_index { |_, index| (index + 1) % insert_every != 0 }
+          .take(@additional_elements.count)
+      end
+    end
+  end
+end

data/lib/article_json/utils/o_embed_resolver/facebook_video.rb

@@ -13,7 +13,7 @@ module ArticleJSON
         # The video URL of the element
         # @return [String]
         def video_url
-          "facebook.com/facebook/videos/#{@element.embed_id}"
+          "https://www.facebook.com/facebook/videos/#{@element.embed_id}"
         end
       end
     end

data/lib/article_json/utils/o_embed_resolver/slideshare.rb

@@ -14,7 +14,7 @@ module ArticleJSON
         # @return [String]
         def slide_url
           handle, slug = @element.embed_id.split('/', 2)
-          "www.slideshare.net/#{handle}/#{slug}"
+          "https://www.slideshare.net/#{handle}/#{slug}"
         end
       end
     end

data/lib/article_json/utils/o_embed_resolver/youtube_video.rb

@@ -13,7 +13,7 @@ module ArticleJSON
         # The video URL of the element
         # @return [String]
         def video_url
-          "youtube.com/watch?v=#{@element.embed_id}"
+          "https://www.youtube.com/watch?v=#{@element.embed_id}"
         end
       end
     end

data/lib/article_json/utils.rb

@@ -9,3 +9,4 @@ require_relative 'utils/o_embed_resolver/slideshare'
 require_relative 'utils/o_embed_resolver/tweet'
 require_relative 'utils/o_embed_resolver/vimeo_video'
 require_relative 'utils/o_embed_resolver/youtube_video'
+require_relative 'utils/additional_element_placer'

data/lib/article_json/version.rb

@@ -1,3 +1,3 @@
 module ArticleJSON
-  VERSION = '0.1.0'
+  VERSION = '0.2.0'
 end

data/lib/article_json.rb

@@ -39,8 +39,19 @@ require_relative 'article_json/import/google_doc/html/embedded_slideshare_parser
 require_relative 'article_json/import/google_doc/html/embedded_tweet_parser'
 require_relative 'article_json/import/google_doc/html/parser'
 
-require_relative 'article_json/export/html/elements/shared/caption'
-require_relative 'article_json/export/html/elements/shared/float'
+require_relative 'article_json/export/common/html/elements/shared/caption'
+require_relative 'article_json/export/common/html/elements/shared/float'
+require_relative 'article_json/export/common/html/elements/base'
+require_relative 'article_json/export/common/html/elements/text'
+require_relative 'article_json/export/common/html/elements/heading'
+require_relative 'article_json/export/common/html/elements/paragraph'
+require_relative 'article_json/export/common/html/elements/list'
+require_relative 'article_json/export/common/html/elements/image'
+require_relative 'article_json/export/common/html/elements/quote'
+require_relative 'article_json/export/common/html/elements/text_box'
+require_relative 'article_json/export/common/html/elements/embed'
+require_relative 'article_json/export/common/html/exporter'
+
 require_relative 'article_json/export/html/elements/base'
 require_relative 'article_json/export/html/elements/text'
 require_relative 'article_json/export/html/elements/heading'
@@ -52,4 +63,16 @@ require_relative 'article_json/export/html/elements/quote'
 require_relative 'article_json/export/html/elements/embed'
 require_relative 'article_json/export/html/exporter'
 
+require_relative 'article_json/export/amp/elements/base'
+require_relative 'article_json/export/amp/elements/text'
+require_relative 'article_json/export/amp/elements/paragraph'
+require_relative 'article_json/export/amp/elements/list'
+require_relative 'article_json/export/amp/elements/heading'
+require_relative 'article_json/export/amp/elements/quote'
+require_relative 'article_json/export/amp/elements/text_box'
+require_relative 'article_json/export/amp/elements/image'
+require_relative 'article_json/export/amp/elements/embed'
+require_relative 'article_json/export/amp/custom_element_library_resolver'
+require_relative 'article_json/export/amp/exporter'
+
 require_relative 'article_json/article'

metadata

@@ -1,14 +1,16 @@
 --- !ruby/object:Gem::Specification
 name: article_json
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors:
-- "@dsager"
+- Daniel Sager
+- Manu Campos
+- Nicolas Fricke
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-09-20 00:00:00.000000000 Z
+date: 2017-11-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -106,6 +108,7 @@ extensions: []
 extra_rdoc_files: []
 files:
 - CHANGELOG.md
+- CODE_OF_CONDUCT.md
 - LICENSE
 - README.md
 - bin/article_json_export_google_doc.rb
@@ -124,6 +127,29 @@ files:
 - lib/article_json/elements/quote.rb
 - lib/article_json/elements/text.rb
 - lib/article_json/elements/text_box.rb
+- lib/article_json/export/amp/custom_element_library_resolver.rb
+- lib/article_json/export/amp/elements/base.rb
+- lib/article_json/export/amp/elements/embed.rb
+- lib/article_json/export/amp/elements/heading.rb
+- lib/article_json/export/amp/elements/image.rb
+- lib/article_json/export/amp/elements/list.rb
+- lib/article_json/export/amp/elements/paragraph.rb
+- lib/article_json/export/amp/elements/quote.rb
+- lib/article_json/export/amp/elements/text.rb
+- lib/article_json/export/amp/elements/text_box.rb
+- lib/article_json/export/amp/exporter.rb
+- lib/article_json/export/common/html/elements/base.rb
+- lib/article_json/export/common/html/elements/embed.rb
+- lib/article_json/export/common/html/elements/heading.rb
+- lib/article_json/export/common/html/elements/image.rb
+- lib/article_json/export/common/html/elements/list.rb
+- lib/article_json/export/common/html/elements/paragraph.rb
+- lib/article_json/export/common/html/elements/quote.rb
+- lib/article_json/export/common/html/elements/shared/caption.rb
+- lib/article_json/export/common/html/elements/shared/float.rb
+- lib/article_json/export/common/html/elements/text.rb
+- lib/article_json/export/common/html/elements/text_box.rb
+- lib/article_json/export/common/html/exporter.rb
 - lib/article_json/export/html/elements/base.rb
 - lib/article_json/export/html/elements/embed.rb
 - lib/article_json/export/html/elements/heading.rb
@@ -131,8 +157,6 @@ files:
 - lib/article_json/export/html/elements/list.rb
 - lib/article_json/export/html/elements/paragraph.rb
 - lib/article_json/export/html/elements/quote.rb
-- lib/article_json/export/html/elements/shared/caption.rb
-- lib/article_json/export/html/elements/shared/float.rb
 - lib/article_json/export/html/elements/text.rb
 - lib/article_json/export/html/elements/text_box.rb
 - lib/article_json/export/html/exporter.rb
@@ -155,6 +179,7 @@ files:
 - lib/article_json/import/google_doc/html/text_box_parser.rb
 - lib/article_json/import/google_doc/html/text_parser.rb
 - lib/article_json/utils.rb
+- lib/article_json/utils/additional_element_placer.rb
 - lib/article_json/utils/o_embed_resolver/base.rb
 - lib/article_json/utils/o_embed_resolver/facebook_video.rb
 - lib/article_json/utils/o_embed_resolver/slideshare.rb
@@ -182,7 +207,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.5.1
+rubygems_version: 2.6.12
 signing_key: 
 specification_version: 4
 summary: JSON Format for News Articles & Ruby Gem

data/lib/article_json/export/html/elements/shared/caption.rb

@@ -1,22 +0,0 @@
-module ArticleJSON
-  module Export
-    module HTML
-      module Elements
-        module Shared
-          module Caption
-            # Generate the caption node
-            # @param [String] tag_name
-            # @return [Nokogiri::HTML::Node]
-            def caption_node(tag_name)
-              create_element(tag_name).tap do |caption|
-                @element.caption.each do |child_element|
-                  caption.add_child(Text.new(child_element).export)
-                end
-              end
-            end
-          end
-        end
-      end
-    end
-  end
-end

data/lib/article_json/export/html/elements/shared/float.rb

@@ -1,17 +0,0 @@
-module ArticleJSON
-  module Export
-    module HTML
-      module Elements
-        module Shared
-          module Float
-            # The element's floating class, if necessary
-            # @return [String]
-            def floating_class
-              "float-#{@element.float}" unless @element.float.nil?
-            end
-          end
-        end
-      end
-    end
-  end
-end