contentful_converter 0.0.1.22 → 0.0.1.27

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ff50772e7cf3d60d6587047360fd5f2aa1f87eb3e7110c731b1fdf6862b70cbe
-  data.tar.gz: 82c222abe96c9d3ac4ccf0e1e0f95f9dcc9d1e11dfda819bbd24737007b3512b
+  metadata.gz: a9ca6680d2a5379db77f5230554f63ee7a254c8b5ec96b347546759b9009ac94
+  data.tar.gz: e5a32099b44d7379deb294f23a97164c00e6e7f9ab97b016e6fc285f7f85472e
 SHA512:
-  metadata.gz: f9bc85b65ff13a53db3bc3c21050287799c273be82778d2a9378f18bc83d8b80af3d5b3b7f43db921743c66e3bd5125b26ce14252586c13b40938222f072d165
-  data.tar.gz: 37a4f52a6b29bad99ddfc7618b5706e6ae80512633993daf179b4f79810db54925b5c324bd6911015e5ce5b60abf5717e362ef6139091d51084984cda395d1d2
+  metadata.gz: f6a4fd4d43be7bb779e36ce9958f6b2f475a2a36cfa1e035dc7468d129fb02bd46bf42f5dc5c56043c9ea71ede9fdf94c8b56f3098cb5214d5ee8542d0bc7c21
+  data.tar.gz: c527b643b6249d90d6147b3242b7569a0a840ed349281d5c75ecae0e9cf5c056a3ed4577268dba0a3c1c8df50984310fd111c149ee586606a5090c068d75e7c9

data/README.md

@@ -2,7 +2,7 @@
 
 [![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.
+Converts plain html string to contentful specific rich text hash
 
 ### Install
 ```ruby
@@ -44,6 +44,16 @@ ContentfulConverter.convert('<h3>hello world</h3>')
 
 ### Additional info
 
+**Exclude Nodes**
+
+Add nodes to be removed from the conversion
+
+```ruby
+ContentfulConverter.configure do |config|
+  config.forbidden_nodes = ['table', 'script', 'iframe']
+end
+```
+
 **`<a>`**
 
 * HTML hyperlinks with full URL e.g: (`<a href="https://google.com"></a>`), will be converted into URL hyperlinks
@@ -100,7 +110,7 @@ ContentfulConverter.convert('<h3>hello world</h3>')
   }
   ```
 
-* HTML hyperlinks without a scheme but with an extension e.g: (`<a href="/path/to_file.docx">file</a>`), will be converted into ASSET hyperlinks, with the href value as an ID, excluding the extension.
+* HTML hyperlinks without a scheme but with an extension e.g: (`<a href="file.docx">file</a>`), will be converted into ASSET hyperlinks, with the href value as an ID.
   ```ruby
   {
     nodeType: "paragraph",
@@ -111,7 +121,7 @@ ContentfulConverter.convert('<h3>hello world</h3>')
         data: {
           target: {
             sys: {
-              id: "/path/to_file",
+              id: "file.docx",
               type: "Link",
               linkType: "Entry"
             }
@@ -190,13 +200,4 @@ rspec ./spec/features/*
 
 ### 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.
+[MIT LICENSE](LICENSE)

data/lib/contentful_converter/configuration.rb

@@ -0,0 +1,24 @@
+# frozen_string_literal: true
+
+module ContentfulConverter
+  class << self
+    attr_accessor :configuration
+  end
+
+  def self.configure
+    self.configuration ||= Configuration.new
+    yield(configuration) if block_given?
+  end
+
+  class Configuration
+    attr_reader :forbidden_nodes
+
+    def initialize
+      @forbidden_nodes = []
+    end
+
+    def forbidden_nodes=(*nodes)
+      @forbidden_nodes = nodes.flatten.uniq
+    end
+  end
+end

data/lib/contentful_converter/nodes/hyperlink.rb

@@ -10,14 +10,14 @@ module ContentfulConverter
 
       def type
         return 'asset-hyperlink' if !uri_scheme? && uri_extension?
-        return 'entry-hyperlink' unless uri_scheme?
+        return 'entry-hyperlink' if !uri_scheme? && !parsed_link.to_s.include?("#")
 
         'hyperlink'
       end
 
       def options
         return hyperlink_entry_option('Asset') if !uri_scheme? && uri_extension?
-        return hyperlink_entry_option('Entry') unless uri_scheme?
+        return hyperlink_entry_option('Entry') if !uri_scheme? && !parsed_link.to_s.include?("#")
 
         hyperlink_option
       end
@@ -31,7 +31,7 @@ module ContentfulConverter
           data: {
             target: {
               sys: {
-                id: parsed_link.to_s.split('.').first,
+                id: parsed_link.to_s,
                 type: 'Link',
                 linkType: type
               }

data/lib/contentful_converter/nokogiri_builder.rb

@@ -1,34 +1,58 @@
 # frozen_string_literal: true
 
 require 'nokogiri'
+require 'contentful_converter/configuration'
 
 module ContentfulConverter
   class NokogiriBuilder
     class << self
+      # By transforming the elements at this point,
+      # nokogiri creates a tree that is accepted by contentful.
       def build(html)
-        doc = create_nokogiri_fragment(transform(html))
-        normalize_lists(doc)
-        normalize_embeds(doc)
-        doc
+        html_node = nokogiri_fragment(html)
+        remove_forbidden_elements(html_node)
+        normalize_nodes(html_node)
+        html_node
       end
 
       private
 
-      # By transforming the elements at this point,
-      # nokogiri creates a tree that is accepted by contentful.
-      def transform(html)
-        doc = create_nokogiri_fragment(html)
-        find_nodes(doc, %w[section div]).each { |elem| elem.name = 'p' }
-        find_nodes(doc, 'img').each { |elem| elem.name = 'embed' }
-        doc.to_html
+      def nokogiri_fragment(html)
+        Nokogiri::HTML.fragment(html)
       end
 
-      def create_nokogiri_fragment(html)
-        Nokogiri::HTML.fragment(html)
+      def remove_forbidden_elements(html_node)
+        remove_empty_links(html_node)
+        return unless ContentfulConverter.configuration
+
+        forbidden_nodes = ContentfulConverter.configuration.forbidden_nodes
+        return if forbidden_nodes.empty?
+
+        find_nodes(html_node, forbidden_nodes).each(&:remove)
+      end
+
+      def normalize_nodes(html_node)
+        normalize_blocks(html_node)
+        normalize_imgs(html_node)
+        normalize_lists(html_node)
+        normalize_embeds(html_node)
+      end
+
+      def normalize_blocks(html_node)
+        find_nodes(html_node, %w[section div]).each do |elem|
+          elem.swap(elem.children)
+        end
+      end
+
+      def normalize_imgs(html_node)
+        find_nodes(html_node, 'img').each { |elem| elem.name = 'embed' }
       end
 
       def normalize_lists(nokogiri_fragment)
-        find_nodes(nokogiri_fragment, 'li').each { |li| wrap_parents_in_ul(li) }
+        find_nodes(nokogiri_fragment, 'li').each do |li|
+          wrap_parents_in_ul(li)
+          wrap_children_in_single_p(li)
+        end
       end
 
       def normalize_embeds(nokogiri_fragment)
@@ -37,8 +61,8 @@ module ContentfulConverter
         end
       end
 
-      def find_nodes(doc, element)
-        doc.css(*element)
+      def remove_empty_links(html_node)
+        find_nodes(html_node, 'a').each { |n| n.remove unless n['href'] }
       end
 
       def wrap_parents_in_ul(node)
@@ -46,6 +70,38 @@ module ContentfulConverter
 
         node.wrap('<ul>')
       end
+
+      def wrap_children_in_single_p(node)
+        return if node.children.count == 1 && node.children.first.name == 'p'
+
+        find_nodes(node, 'p').each { |p_node| p_node.swap(p_node.children) }
+        node_children = append_space_to_text_nodes(node.children.remove, node)
+
+        node.add_child('<p>')
+        node.at_css('p').children = node_children
+        merge_text_nodes(node)
+      end
+
+      def append_space_to_text_nodes(children, node)
+        children.each do |child|
+          next if child.text.chomp.empty? || child.text.end_with?(' ')
+
+          child.content = create_text_node("#{child.text} ", node)
+        end
+        children
+      end
+
+      def find_nodes(html_node, element)
+        html_node.css(*element)
+      end
+
+      def create_text_node(text, html_node)
+        Nokogiri::XML::Text.new(text, html_node)
+      end
+
+      def merge_text_nodes(node)
+        Nokogiri::XML(node.to_xml)
+      end
     end
   end
 end

data/lib/contentful_converter/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module ContentfulConverter
-  VERSION = '0.0.1.22'
+  VERSION = '0.0.1.27'
 end

metadata

@@ -1,11 +1,11 @@
 --- !ruby/object:Gem::Specification
 name: contentful_converter
 version: !ruby/object:Gem::Version
-  version: 0.0.1.22
+  version: 0.0.1.27
 platform: ruby
 authors:
 - Alex Avlonitis
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
 date: 2019-12-07 00:00:00.000000000 Z
@@ -39,13 +39,14 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '3.9'
 description: Converts HTML text to Rich Text Contentful specific JSON structure
-email: 
+email:
 executables: []
 extensions: []
 extra_rdoc_files: []
 files:
 - README.md
 - lib/contentful_converter.rb
+- lib/contentful_converter/configuration.rb
 - lib/contentful_converter/converter.rb
 - lib/contentful_converter/node_builder.rb
 - lib/contentful_converter/nodes/base.rb
@@ -68,11 +69,11 @@ files:
 - lib/contentful_converter/stack.rb
 - lib/contentful_converter/tree_cloner.rb
 - lib/contentful_converter/version.rb
-homepage: https://github.com/AlexAvlonitis/contentful_converter
+homepage: https://github.com/AlexAvlonitis/contentful_converter.git
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -87,8 +88,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.3
-signing_key: 
+rubygems_version: 3.1.4
+signing_key:
 specification_version: 4
 summary: Contentful HTML to Rich Text Converter
 test_files: []