contentful_converter 0.0.1.12

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 9bcee9dc48afd4c917fb46ba299eb5cad6030fac447ba86de0ae51ad03eef629
+  data.tar.gz: e51cd46ed8ec8eed058d2461d78c06f0de7128aaac5a7d867c4992d4cea41c88
+SHA512:
+  metadata.gz: f6d89e89940edeca060d2c2eab090b3518e87a7282cca6eb27f77978c400935cf40a34a8e355348032b624b936fded51206dfda82ab517acd9130ee1930b231c
+  data.tar.gz: c0c490af7c05434c146f198909e367f8ef861bdd87c126b77906b7e721262549025e39bb4239d73bac87a9af716978446a5b7dd5d283b32be89bbc1710e91a36

data/README.md

@@ -0,0 +1,84 @@
+## Contentful HTML to Rich Text converter
+
+[![Build Status](https://travis-ci.org/AlexAvlonitis/contentful_converter.svg?branch=master)](https://travis-ci.org/AlexAvlonitis/contentful_converter)
+
+Converts plain html string to contentful specific rich_text hash structure.
+
+*WIP, does not cover all html elements, contributions are welcome*
+
+### Install
+```ruby
+# Rails
+gem 'contentful_converter'
+
+# Ruby
+gem install 'contentful_converter'
+
+require 'contentful_converter
+
+```
+
+### Run
+
+```ruby
+ContentfulConverter.convert('<h3>hello world</h3>')
+
+# OUTPUT
+{
+  :nodeType=>"document",
+  :data=>{},
+  :content=>[
+    {
+      :nodeType=>"heading-3",
+      :data=>{},
+      :content=>[
+        {
+          :marks=>[],
+          :value=>"hello world",
+          :nodeType=>"text",
+          :data=>{}
+        }
+      ]
+    }
+  ]
+}
+```
+
+### Additional info
+**HREF links**
+
+* HTML hyperlinks with full URL e.g: (https://google.com), will be converted into URL hyperlinks
+
+* HTML hyperlinks without a scheme e.g: ('/aboutus/contact'), will be converted into ENTRY hyperlinks, with the href value as an ID
+
+* HTML hyperlinks without a scheme but with an extension e.g: ('myfile.docx'), will be converted into ASSET hyperlinks, with the href value as an ID, minus the extension.
+
+---
+
+### Tests
+```ruby
+# Unit tests
+rspec
+
+# Feature tests
+rspec ./spec/features/*
+```
+
+### Contributions
+* Fork it
+* Create a branch
+* Add your changes and tests
+* Submit a PR
+
+### License
+
+Copyright (C) 2019 Alex Avlonitis
+
+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, version 3.
+
+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.

data/lib/contentful_converter/converter.rb

@@ -0,0 +1,33 @@
+# frozen_string_literal: true
+
+require 'nokogiri'
+require 'contentful_converter/tree_cloner'
+require 'contentful_converter/nokogiri_builder'
+
+module ContentfulConverter
+  class Converter
+    class << self
+      def convert(html)
+        raise_error_unless_string(html)
+
+        convert_to_rich_text(nokogiri_fragment(html))
+      end
+
+      private
+
+      def raise_error_unless_string(param)
+        return if param.is_a?(String)
+
+        raise ArgumentError, 'Converter param needs to be a string'
+      end
+
+      def convert_to_rich_text(nokogiri_fragment)
+        TreeCloner.nokogiri_to_rich_text(nokogiri_fragment)
+      end
+
+      def nokogiri_fragment(html)
+        NokogiriBuilder.build(html)
+      end
+    end
+  end
+end

data/lib/contentful_converter/node_builder.rb

@@ -0,0 +1,57 @@
+# frozen_string_literal: true
+
+require 'contentful_converter/nodes/document'
+require 'contentful_converter/nodes/header'
+require 'contentful_converter/nodes/paragraph'
+require 'contentful_converter/nodes/blockquote'
+require 'contentful_converter/nodes/text'
+require 'contentful_converter/nodes/underline'
+require 'contentful_converter/nodes/italic'
+require 'contentful_converter/nodes/strong'
+require 'contentful_converter/nodes/code'
+require 'contentful_converter/nodes/ordered_list'
+require 'contentful_converter/nodes/unordered_list'
+require 'contentful_converter/nodes/horizontal_line'
+require 'contentful_converter/nodes/list_item'
+require 'contentful_converter/nodes/hyperlink'
+
+module ContentfulConverter
+  class NodeBuilder
+    DEFAULT_MAPPINGS = {
+      '#document-fragment' => Nodes::Document,
+      'h1' => Nodes::Header,
+      'h2' => Nodes::Header,
+      'h3' => Nodes::Header,
+      'h4' => Nodes::Header,
+      'h5' => Nodes::Header,
+      'h6' => Nodes::Header,
+      'text' => Nodes::Text,
+      'i' => Nodes::Italic,
+      'em' => Nodes::Italic,
+      'u' => Nodes::Underline,
+      'b' => Nodes::Strong,
+      'code' => Nodes::Code,
+      'strong' => Nodes::Strong,
+      'p' => Nodes::Paragraph,
+      'div' => Nodes::Paragraph,
+      'br' => Nodes::Paragraph,
+      'section' => Nodes::Paragraph,
+      'hr' => Nodes::HorizontalLine,
+      'blockquote' => Nodes::Blockquote,
+      'ul' => Nodes::UnorderedList,
+      'ol' => Nodes::OrderedList,
+      'li' => Nodes::ListItem,
+      'a' => Nodes::Hyperlink
+    }.freeze
+
+    def self.build(nokogiri_node, parent = nil)
+      rich_text_node = DEFAULT_MAPPINGS[nokogiri_node.name]
+
+      unless rich_text_node
+        raise "'#{nokogiri_node.name}' Node type, does not exist"
+      end
+
+      rich_text_node.new(nokogiri_node, parent)
+    end
+  end
+end

data/lib/contentful_converter/nodes/base.rb

@@ -0,0 +1,53 @@
+# frozen_string_literal: true
+
+module ContentfulConverter
+  module Nodes
+    class Base
+      attr_reader :node_type, :content, :nokogiri_node, :parent
+
+      def initialize(nokogiri_node = nil, parent = nil)
+        @nokogiri_node = nokogiri_node
+        @parent = parent
+        @node_type = type
+        @content = []
+      end
+
+      def add_content(node)
+        @content << node
+      end
+
+      def to_h(params = options)
+        params[:nodeType] = node_type
+        params[:data]     = params[:data] || {}
+        params[:content]  = content.map(&:to_h).compact
+        params
+      end
+
+      def needs_p_wrapping?
+        if parent.nil? ||
+            parent&.class == Nodes::Header ||
+            parent&.class == Nodes::Paragraph ||
+            parent&.class == Nodes::Hyperlink
+
+          return false
+        end
+
+        true
+      end
+
+      private
+
+      def value
+        nokogiri_node.content
+      end
+
+      def type
+        raise NotImplementedError
+      end
+
+      def options
+        {}
+      end
+    end
+  end
+end

data/lib/contentful_converter/nodes/blockquote.rb

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+
+require 'contentful_converter/nodes/base'
+
+module ContentfulConverter
+  module Nodes
+    class Blockquote < Base
+      def needs_p_wrapping?
+        false
+      end
+
+      private
+
+      def type
+        'blockquote'
+      end
+    end
+  end
+end

data/lib/contentful_converter/nodes/code.rb

@@ -0,0 +1,13 @@
+# frozen_string_literal: true
+
+require 'contentful_converter/nodes/text'
+
+module ContentfulConverter
+  module Nodes
+    class Code < Text
+      def marks
+        ['code']
+      end
+    end
+  end
+end

data/lib/contentful_converter/nodes/document.rb

@@ -0,0 +1,15 @@
+# frozen_string_literal: true
+
+require 'contentful_converter/nodes/base'
+
+module ContentfulConverter
+  module Nodes
+    class Document < Base
+      private
+
+      def type
+        'document'
+      end
+    end
+  end
+end

data/lib/contentful_converter/nodes/header.rb

@@ -0,0 +1,23 @@
+# frozen_string_literal: true
+
+require 'contentful_converter/nodes/base'
+
+module ContentfulConverter
+  module Nodes
+    class Header < Base
+      def needs_p_wrapping?
+        false
+      end
+
+      private
+
+      def type
+        "heading-#{header_size}"
+      end
+
+      def header_size
+        nokogiri_node.name.split('h').last
+      end
+    end
+  end
+end

data/lib/contentful_converter/nodes/horizontal_line.rb

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+
+require 'contentful_converter/nodes/base'
+
+module ContentfulConverter
+  module Nodes
+    class HorizontalLine < Base
+      def needs_p_wrapping?
+        false
+      end
+
+      private
+
+      def type
+        'hr'
+      end
+    end
+  end
+end

data/lib/contentful_converter/nodes/hyperlink.rb

@@ -0,0 +1,62 @@
+# frozen_string_literal: true
+
+require 'contentful_converter/nodes/base'
+require 'uri'
+
+module ContentfulConverter
+  module Nodes
+    class Hyperlink < Base
+      private
+
+      def type
+        return 'asset-hyperlink' if !(uri_scheme?) && uri_extension?
+        return 'entry-hyperlink' unless uri_scheme?
+
+        'hyperlink'
+      end
+
+      def options
+        return hyperlink_entry_option("Asset") if !(uri_scheme?) && uri_extension?
+        return hyperlink_entry_option("Entry") unless uri_scheme?
+
+        hyperlink_option
+      end
+
+      def hyperlink_option
+        { data: { uri: parsed_href.to_s } }
+      end
+
+      def hyperlink_entry_option(type)
+        {
+          data: {
+            target: {
+              sys: {
+                id: parsed_href.to_s.split('.').first,
+                type: "Link",
+                linkType: type
+              }
+            }
+          }
+        }
+      end
+
+      def uri_scheme?
+        parsed_href.scheme
+      end
+
+      def uri_extension?
+        parsed_href.to_s.split('.')[1]
+      end
+
+      def parsed_href
+        return URI(href_value) if href_value
+
+        URI('')
+      end
+
+      def href_value
+        nokogiri_node['href']
+      end
+    end
+  end
+end

data/lib/contentful_converter/nodes/italic.rb

@@ -0,0 +1,13 @@
+# frozen_string_literal: true
+
+require 'contentful_converter/nodes/text'
+
+module ContentfulConverter
+  module Nodes
+    class Italic < Text
+      def marks
+        ['italic']
+      end
+    end
+  end
+end

data/lib/contentful_converter/nodes/list_item.rb

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+
+require 'contentful_converter/nodes/base'
+
+module ContentfulConverter
+  module Nodes
+    class ListItem < Base
+      def needs_p_wrapping?
+        false
+      end
+
+      private
+
+      def type
+        'list-item'
+      end
+    end
+  end
+end

data/lib/contentful_converter/nodes/ordered_list.rb

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+
+require 'contentful_converter/nodes/base'
+
+module ContentfulConverter
+  module Nodes
+    class OrderedList < Base
+      def needs_p_wrapping?
+        false
+      end
+
+      private
+
+      def type
+        'ordered-list'
+      end
+    end
+  end
+end

data/lib/contentful_converter/nodes/paragraph.rb

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+
+require 'contentful_converter/nodes/base'
+
+module ContentfulConverter
+  module Nodes
+    class Paragraph < Base
+      def needs_p_wrapping?
+        false
+      end
+
+      private
+
+      def type
+        'paragraph'
+      end
+    end
+  end
+end

data/lib/contentful_converter/nodes/strong.rb

@@ -0,0 +1,13 @@
+# frozen_string_literal: true
+
+require 'contentful_converter/nodes/text'
+
+module ContentfulConverter
+  module Nodes
+    class Strong < Text
+      def marks
+        ['bold']
+      end
+    end
+  end
+end

data/lib/contentful_converter/nodes/text.rb

@@ -0,0 +1,32 @@
+# frozen_string_literal: true
+
+require 'contentful_converter/nodes/base'
+
+module ContentfulConverter
+  module Nodes
+    class Text < Base
+      def to_h(params = options)
+        super
+        params.delete(:content)
+        params
+      end
+
+      private
+
+      def type
+        'text'
+      end
+
+      def options
+        {
+          value: value,
+          marks: marks.map { |mark| { type: mark } }
+        }
+      end
+
+      def marks
+        []
+      end
+    end
+  end
+end

data/lib/contentful_converter/nodes/underline.rb

@@ -0,0 +1,13 @@
+# frozen_string_literal: true
+
+require 'contentful_converter/nodes/text'
+
+module ContentfulConverter
+  module Nodes
+    class Underline < Text
+      def marks
+        ['underline']
+      end
+    end
+  end
+end

data/lib/contentful_converter/nodes/unordered_list.rb

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+
+require 'contentful_converter/nodes/base'
+
+module ContentfulConverter
+  module Nodes
+    class UnorderedList < Base
+      def needs_p_wrapping?
+        false
+      end
+
+      private
+
+      def type
+        'unordered-list'
+      end
+    end
+  end
+end

data/lib/contentful_converter/nokogiri_builder.rb

@@ -0,0 +1,40 @@
+# frozen_string_literal: true
+
+require 'nokogiri'
+
+module ContentfulConverter
+  class NokogiriBuilder
+    class << self
+      def build(html)
+        doc = Nokogiri::HTML.fragment(sanitize(html))
+        doc = normalize_lists(doc) if find_li(doc).any?
+        doc
+      end
+
+      private
+
+      def sanitize(html)
+        html = html.dup
+        html.gsub!('div>', 'p>')
+        html.gsub!('section>', 'p>')
+        html
+      end
+
+      def normalize_lists(nokogiri_fragment)
+        find_li(nokogiri_fragment).each { |li_node| wrap_parents_in_ul(li_node) }
+
+        nokogiri_fragment
+      end
+
+      def find_li(nokogiri_fragment)
+        nokogiri_fragment.css('li')
+      end
+
+      def wrap_parents_in_ul(node)
+        return if node.parent.name == 'ul' || node.parent.name == 'ol'
+
+        node.wrap('<ul>')
+      end
+    end
+  end
+end

data/lib/contentful_converter/tree_cloner.rb

@@ -0,0 +1,53 @@
+# frozen_string_literal: true
+
+require 'contentful_converter/node_builder'
+
+module ContentfulConverter
+  class TreeCloner
+    class << self
+      def nokogiri_to_rich_text(nokogiri_fragment)
+        if nokogiri_fragment.children.empty?
+          return NodeBuilder.build(nokogiri_fragment).to_h
+        end
+
+        traverse_and_clone(nokogiri_fragment).to_h
+      end
+
+      private
+
+      def traverse_and_clone(nokogiri_fragment)
+        rich_root_node = NodeBuilder.build(nokogiri_fragment)
+
+        noko_stack = [nokogiri_fragment]
+        rich_stack = [rich_root_node]
+
+        while noko_stack.any?
+          noko_node = noko_stack.pop
+          rich_node = rich_stack.pop
+
+          next unless noko_node.children.any?
+
+          noko_node.children.each do |child_node|
+            rich_child_node = NodeBuilder.build(child_node, rich_node)
+
+            noko_stack << child_node
+            rich_stack << rich_child_node
+            rich_node.add_content(wrap_in_paragraph(rich_child_node))
+          end
+        end
+
+        rich_root_node
+      end
+
+      def wrap_in_paragraph(node)
+        node.needs_p_wrapping? ? p_wrapper(node) : node
+      end
+
+      def p_wrapper(node)
+        p_node = Nodes::Paragraph.new(nil, node.parent)
+        p_node.add_content(node)
+        p_node
+      end
+    end
+  end
+end

data/lib/contentful_converter/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module ContentfulConverter
+  VERSION = '0.0.1.12'
+end

data/lib/contentful_converter.rb

@@ -0,0 +1,9 @@
+# frozen_string_literal: true
+
+require 'contentful_converter/converter'
+
+module ContentfulConverter
+  def self.convert(html)
+    Converter.convert(html)
+  end
+end

metadata

@@ -0,0 +1,92 @@
+--- !ruby/object:Gem::Specification
+name: contentful_converter
+version: !ruby/object:Gem::Version
+  version: 0.0.1.12
+platform: ruby
+authors:
+- Alex Avlonitis
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2019-12-07 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.9'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.9'
+description: Converts HTML text to Rich Text Contentful specific JSON structure
+email: 
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- README.md
+- lib/contentful_converter.rb
+- lib/contentful_converter/converter.rb
+- lib/contentful_converter/node_builder.rb
+- lib/contentful_converter/nodes/base.rb
+- lib/contentful_converter/nodes/blockquote.rb
+- lib/contentful_converter/nodes/code.rb
+- lib/contentful_converter/nodes/document.rb
+- lib/contentful_converter/nodes/header.rb
+- lib/contentful_converter/nodes/horizontal_line.rb
+- lib/contentful_converter/nodes/hyperlink.rb
+- lib/contentful_converter/nodes/italic.rb
+- lib/contentful_converter/nodes/list_item.rb
+- lib/contentful_converter/nodes/ordered_list.rb
+- lib/contentful_converter/nodes/paragraph.rb
+- lib/contentful_converter/nodes/strong.rb
+- lib/contentful_converter/nodes/text.rb
+- lib/contentful_converter/nodes/underline.rb
+- lib/contentful_converter/nodes/unordered_list.rb
+- lib/contentful_converter/nokogiri_builder.rb
+- lib/contentful_converter/tree_cloner.rb
+- lib/contentful_converter/version.rb
+homepage: https://github.com/AlexAvlonitis/contentful_converter
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.0.3
+signing_key: 
+specification_version: 4
+summary: Contentful HTML to Rich Text Converter
+test_files: []