jekyll-emoji 0.1.4 → 0.1.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 0de12d4ecb105bcf26e774bde5c75687cbee55a1
-  data.tar.gz: 23ea050f1423dedf1507d81750835f0203d274d1
+  metadata.gz: fa05cb9d3d721a154defea59300d2091a943aace
+  data.tar.gz: 5cdfae6341a486064fa2ab6abcdb05d3a6501d1d
 SHA512:
-  metadata.gz: c890340261e610a52aa13b0fb8bbc9aa0a8c1718e0596ffc4baa301c25676027f67f7f9bbb3d576bbc33480cedd39da6663ba3ded9a43257c229e2d347344284
-  data.tar.gz: 03a6b8eecb4329048c01ecd4d749924aaeca19230963ca923c83185a6e2600bb29ebac0f77524796f125a448bc71d8e8d04b7868821640a9f17f990ef91dc771
+  metadata.gz: 5279d5dd2b413b01fda17517d0b5a2402d29b99a2b444487d888bddb4fb1c9fa01b2689dfa00c8363283442d1096cd9ba41e22c7b7703b54835106444dcc58b2
+  data.tar.gz: 680a167683ebec39347fc7fe10d50f936ecff530b9caf00bb55a39538b0d7577f1d26fd24898e8c83243135766ebb0bf0bfbe225dc6caa0592c7e3043e21aa56

data/README.md

@@ -48,10 +48,6 @@ There's also a Liquid filter called `emojify`. It accepts three parameters: `for
 {{ ":kissing_heart: :heart: :stuck_out_tongue:" | emojify  }}
 ```
 
-## Development
-
-To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
-
 ## Known Issues
 
 ### `emojify` filter performance
@@ -74,10 +70,20 @@ When the `emojify` filter is used inside a markdown file (say, a blog post), and
 
 This is due to the fact that HTML encoding is done in a post-processing step to simplify and speed up the implementation.
 
+## Development
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
 ## Contributing
 
 Bug reports and pull requests are welcome on GitHub at https://github.com/omninonsense/jekyll-emoji. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](contributor-covenant.org) code of conduct.
 
+## Thanks
+
+The following parties deserve my gratitude:
+ - [Emoji One](http://emojione.com/) for creating emojis that I actually *like*, as opposed to not mind.
+ - [@YorickPeterse](https://github.com/YorickPeterse) for introducing me to [Oga](https://github.com/YorickPeterse).
+It was <3></3> at first sight!
 
 ## License
 

data/lib/jekyll/emoji.rb

@@ -1,245 +1,6 @@
-require "jekyll/emoji/version"
 require 'oga'
 require 'yajl'
 
-module Jekyll
-  module Emoji
-    class Converter < Converter
-      safe true
-      priority :lowest
-
-      Defaults = {
-        'format' => 'html',
-        'ascii' => false,
-        'shortname' => true
-      }.freeze
-
-      Attribute_blacklist = %w{
-        data-no-emoji
-        data-no-emojis
-      }
-
-      Class_blacklist = %w{
-        no-emoji
-        no-emojis
-
-        no_emoji
-        no_emojis
-      }
-
-      Element_blacklist = %w{
-        code
-        pre
-      }
-
-      def initialize(conf = nil)
-        parser = Yajl::Parser.new
-
-        @@site_conf = conf
-        configure(@@site_conf)
-
-        formats = %w{
-          html
-          unicode
-          emojione-png
-          emojione-svg
-        }
-
-        if !formats.include? @conf['format']
-          raise(ArgumentError, "Unknown emoji format: '#{@conf['format']}'; Supported formats are: #{formats}")
-        end
-
-        @emoji_map    = {}
-        @encoding_map = {}
-
-        @shortname_aliases = []
-        @ascii_aliases     = []
-
-        # This JSON file is nicked from the Emoji One project
-        # Go shower them in love (not that kinda love :smirk:).
-        emojione_json = nil
-        File.open(File.expand_path('../../../emoji.json', __FILE__), 'r') do |f|
-          emojione_json ||= parser.parse(f)
-        end
-
-        emojione_json.each_value do |v|
-          codepoints = v['unicode'].split('-')
-          unicode = codepoints.map(&:hex).pack("U*")
-
-          @shortname_aliases << v['shortname']
-          @emoji_map[v['shortname']] = v['unicode']
-
-          v['aliases'].each do |emoji_alias|
-            @shortname_aliases << emoji_alias
-            @emoji_map[emoji_alias] = v['unicode']
-          end
-
-          v['aliases_ascii'].each do |emoji_alias|
-            @ascii_aliases << emoji_alias
-            @emoji_map[emoji_alias] = v['unicode']
-          end
-
-          @encoding_map[unicode] = codepoints.map{|cp| "&#x#{cp};" }.join
-          @emoji_map[unicode] = v['unicode']
-        end
-
-        build_emoji_regexp
-
-        # @emoji_regexp = Regexp.new (@emoji_map.keys.map{|k| Regexp.quote(k) }).join('|')
-        @encoding_regexp = Regexp.new (@encoding_map.keys.map{|k| Regexp.quote(k) }).join('|')
-      end
-
-      def build_emoji_regexp(previous_conf = nil)
-        return if previous_conf == @conf
-
-        valid = @encoding_map.keys
-        valid += @shortname_aliases if @conf['shortname']
-        valid += @ascii_aliases if @conf['ascii']
-
-        @emoji_regexp = Regexp.union(valid)
-      end
-
-      def configure(h)
-        if h['emoji']
-          @conf = Defaults.merge(h['emoji'])
-        else
-          @conf = Defaults
-        end
-      end
-
-      def reconfigure(h)
-        previous_conf = @conf
-        @conf = configure(@@site_conf).merge(h){|k, o, n| n.nil? ? o : n }
-        build_emoji_regexp(previous_conf)
-      end
-
-      def matches(ext)
-        ext =~ /^\.(md|markdown)$/i
-      end
-
-      def output_ext(ext)
-        ".html"
-      end
-
-      ##
-      # Return whether whether `node` should contain emojis or not
-      #
-      # @param [Oga::XML::Node] node
-      #
-      # @return [Boolean]
-      #
-      def emoji_enabled?(node)
-
-        return true if node.is_a? Oga::XML::Document
-
-        if node.is_a? Oga::XML::Element
-          classes = node.get('class')
-
-          return false if Element_blacklist.any? {|e| e == node.name }
-          return false if Attribute_blacklist.any? {|a| node.attr(a) }
-          return false unless (Class_blacklist & classes.split).empty? unless classes.nil?
-
-        end
-
-        return true
-      end
-
-      ##
-      # Recursively add emojis to all child nodes
-      #
-      # @param [Oga::XML::Document|Oga::XML::Node|Oga::XML::Element] node
-      #
-      # @return [NilClass]
-      #
-      def add_emojis(node)
-        return unless emoji_enabled?(node)
-
-        node.children.each do |child|
-          if child.is_a?(Oga::XML::Text)
-            process_node(child)
-          else
-            add_emojis(child)
-          end
-        end
-
-        return nil
-      end
-
-      ##
-      # Add emojis to {Oga::XML::Text} node
-      #
-      # @param [Oga::XML::Text] node
-      #
-      # @return [NilClass]
-      #
-      def process_node(node)
-        str = node.text
-        str.gsub!(@emoji_regexp) do |m|
-          codepoints = @emoji_map[m]
-
-          unicode_emoji = codepoints.split('-').map(&:hex).pack("U*")
-
-          case @conf['format']
-          when 'unicode', 'html'
-            unicode_emoji
-          when 'emojione-png', 'emojione-svg'
-            vendor, ext = @conf['format'].split('-')
-            loc = str.index(m)
-
-            before = Oga::XML::Text.new
-            after = Oga::XML::Text.new
-
-            before.text = str[0...loc]
-            after.text = str[loc + m.length..-1]
-            img = Oga::XML::Element.new name: 'img'
-            img.set('class', vendor)
-            img.set('alt', unicode_emoji)
-            img.set('src', "https://cdn.jsdelivr.net/#{vendor}/assets/#{ext}/#{codepoints}.#{ext}")
-
-            if node.node_set
-              node.before(before)
-              node.after(after)
-              node.replace img
-            end
-
-          end
-        end
-
-        return nil
-      end
-
-      def convert(content)
-        document = Oga.parse_html(content)
-        add_emojis(document)
-        docstr = document.to_xml
-
-        # Now we only need to encode the Emojis into HTML Entities
-        if @conf['format'] == 'html'
-          docstr.gsub!(@encoding_regexp, @encoding_map)
-        end
-
-        return docstr
-      end # convert
-
-      def self.site_conf
-        @@site_conf
-      end
-    end #Converter
-
-    module Filter
-      def emojify(input, output_format = nil, ascii = nil, shortname = nil)
-        @@emoji_converter ||= Converter.new(Converter.site_conf)
-        @@emoji_converter.reconfigure('format' => output_format, 'ascii' => ascii, 'shortname' => shortname)
-
-        output = @@emoji_converter.convert(input)
-
-        # NOTE: This impacts performance in certain cases
-        @@emoji_converter.reconfigure(Converter.site_conf)
-
-        return output
-      end
-    end #Filter
-  end #Emoji
-end
-
-Liquid::Template.register_filter(Jekyll::Emoji::Filter)
+require "jekyll/emoji/version"
+require "jekyll/emoji/converter"
+require "jekyll/emoji/filter"

data/lib/jekyll/emoji/converter.rb

@@ -0,0 +1,386 @@
+require "jekyll/emoji/version"
+require 'oga'
+require 'yajl'
+
+module Jekyll
+  module Emoji
+    class Converter < Converter
+      safe true
+      priority :lowest
+
+      DEFAULTS = {
+        'format' => 'html',
+        'ascii' => false,
+        'shortname' => true
+      }.freeze
+
+      BLACKLIST_ATTRIBUTES = %w{
+        data-no-emoji
+        data-no-emojis
+      }
+
+      BLACKLIST_CLASSES = %w{
+        no-emoji
+        no-emojis
+
+        no_emoji
+        no_emojis
+      }
+
+      BLACKLIST_ELEMENTS = %w{
+        code
+        pre
+      }
+
+      SUPPORTED_FORMATS = %w{
+        html
+        unicode
+        emojione-png
+        emojione-svg
+      }
+
+      EMOJI_JSON_FILE = '../../../../emoji.json'
+
+      ##
+      # Initialize the object.
+      # conf Hash should be the following format:
+      #
+      #   {
+      #     ...
+      #     'emoji' => {
+      #       'format' => [String],
+      #       'ascii' => [TrueClass|FalseClass],
+      #       'shortcode' => [TrueClass|FalseClass]
+      #     }
+      #     ...
+      #   }
+      #
+      # @param [Hash] conf
+      #
+      def initialize(conf = {'emoji' => DEFAULTS})
+        @@site_conf = conf
+        configure(@@site_conf)
+
+        validate_format
+
+        @emoji_map    = {}
+        @encoding_map = {}
+
+        @shortname_aliases = []
+        @ascii_aliases     = []
+
+        load_emoji_data
+        build_emoji_regexp
+
+        @encoding_regexp = Regexp.new (@encoding_map.keys.map{|k| Regexp.quote(k) }).join('|')
+      end
+
+      ##
+      # Load up a JSON file containing emoji data, but discards the keys
+      # because the json file we're reading from contains names in keys
+      # which are surplus in our case.
+      #
+      # @param [String] path
+      # @return [Array]
+      #
+      def load_emoji_json(path)
+        parser = Yajl::Parser.new
+        emoji_hash = nil
+        File.open(File.expand_path(path, __FILE__), 'r') do |f|
+          emoji_hash = parser.parse(f)
+        end
+
+        # keys are emoji names, we don't need those.
+        return emoji_hash.values
+      end
+
+      ##
+      # Populates aliases, and reference maps for faster lookup during
+      # the encoding and decoding process. It acceps a path to a file
+      # from which the data should be loaded.
+      #
+      # @param [String] path
+      # @return [NilClass]
+      #
+      def load_emoji_data(path = EMOJI_JSON_FILE)
+        data = load_emoji_json(path)
+
+        data.each do |v|
+          codepoints = v['unicode'].split('-')
+          unicode = codepoints_to_unicode(codepoints)
+
+          @shortname_aliases << v['shortname']
+          @emoji_map[v['shortname']] = v['unicode']
+
+          v['aliases'].each do |emoji_alias|
+            @shortname_aliases << emoji_alias
+            @emoji_map[emoji_alias] = v['unicode']
+          end
+
+          v['aliases_ascii'].each do |emoji_alias|
+            @ascii_aliases << emoji_alias
+            @emoji_map[emoji_alias] = v['unicode']
+          end
+
+          @encoding_map[unicode] = codepoints.map{|cp| "&#x#{cp};" }.join
+          @emoji_map[unicode] = v['unicode']
+        end
+
+        return nil
+      end
+
+      ##
+      # Validates if desired format is supported. If it isn't supported
+      # an exception is raised.
+      #
+      # @param [String] f
+      # @return [TrueClass]
+      #
+      def validate_format(f = @conf['format'])
+        if !SUPPORTED_FORMATS.include? f
+          raise(ArgumentError, "Unknown emoji format: '#{f}'; Supported formats are: #{SUPPORTED_FORMATS}")
+        end
+
+        true
+      end
+
+      ##
+      # Rebuilds the cached Regexp object in case the converter was
+      # reconfigured.
+      #
+      # @param [Hash|NilClass]
+      # @return [Regexp]
+      #
+      def build_emoji_regexp(previous_conf = nil)
+        return if previous_conf == @conf
+
+        valid = @encoding_map.keys
+        valid += @shortname_aliases if @conf['shortname']
+        valid += @ascii_aliases if @conf['ascii']
+
+        @emoji_regexp = Regexp.union(valid)
+      end
+
+      ##
+      # Configure the internal state.
+      #
+      # @param [Hash] h
+      # @return [Hash]
+      #
+      def configure(h)
+        if h['emoji']
+          @conf = DEFAULTS.merge(h['emoji'])
+        else
+          @conf = DEFAULTS
+        end
+      end
+
+      ##
+      # Reconfigure the internal state.
+      #
+      # @param [Hash] h
+      # @return [Hash]
+      #
+      def reconfigure(h)
+        previous_conf = @conf
+        @conf = configure(@@site_conf).merge(h){|k, o, n| n.nil? ? o : n }
+        validate_format
+        build_emoji_regexp(previous_conf)
+
+        return @conf
+      end
+
+      ##
+      # Return whether we should convert a file based on its extension.
+      #
+      # @param [String] ext
+      # @return [TrueClass|FalseClass]
+      #
+      def matches(ext)
+        ext =~ /^\.(md|markdown)$/i
+      end
+      ##
+      # Returns the extension with the Converter should output.
+      #
+      # @param [String] ext
+      # @return [String]
+      #
+      def output_ext(ext)
+        ".html"
+      end
+
+      ##
+      # Return whether whether `node` should contain emojis or not.
+      #
+      # @param [Oga::XML::Node] node
+      # @return [TrueClass|FalseClass]
+      #
+      def emoji_enabled?(node)
+
+        return true if node.is_a? Oga::XML::Document
+
+        if node.is_a? Oga::XML::Element
+          classes = node.get('class')
+
+          return false if BLACKLIST_ELEMENTS.any? {|e| e == node.name }
+          return false if BLACKLIST_ATTRIBUTES.any? {|a| node.attr(a) }
+          return false unless (BLACKLIST_CLASSES & classes.split).empty? unless classes.nil?
+
+        end
+
+        return true
+      end
+
+      ##
+      # Recursively add emojis to all child nodes.
+      #
+      # @param [Oga::XML::Document|Oga::XML::Node|Oga::XML::Element] node
+      # @return [NilClass]
+      #
+      def add_emojis(node)
+        return unless emoji_enabled?(node)
+
+        node.children.each do |child|
+          if child.is_a?(Oga::XML::Text)
+            process_node(child)
+          else
+            add_emojis(child)
+          end
+        end
+
+        # return nil
+      end
+
+      ##
+      # Add emojis to {Oga::XML::Text} node.
+      #
+      # @param [Oga::XML::Text] node
+      # @return [NilClass]
+      #
+      def process_node(node)
+        str = node.text
+
+        str.gsub!(@emoji_regexp) do |m|
+          codepoints = @emoji_map[m]
+
+          case @conf['format']
+          when 'unicode', 'html'
+            codepoints_to_unicode(codepoints)
+          when 'emojione-png', 'emojione-svg'
+            before, after = split_to_nodes(str, m)
+            img = emojione_img_node(codepoints)
+
+            if node.node_set
+              node.before(before)
+              node.after(after)
+              node.replace img
+            end
+
+            return nil
+          end
+        end
+
+        return nil
+      end
+
+      ##
+      # Generates a populated {Oga::XML::Element} node.
+      #
+      # @param [String|Array] codepoints
+      # @return [Oga::XML::Element(name:img)]
+      #
+      def emojione_img_node(codepoints)
+        ext = @conf['format'].split('-').last
+        img = Oga::XML::Element.new name: 'img'
+        img.set('class', 'emojione')
+        img.set('alt', codepoints_to_unicode(codepoints))
+        img.set('src', "https://cdn.jsdelivr.net/emojione/assets/#{ext}/#{codepoints}.#{ext}")
+
+        return img
+      end
+
+      ##
+      # Splits `str` into an {Array} with two {Oga::XML::Text} nodes at
+      # `seperator`.
+      #
+      # @param [String] str
+      # @param [String] seperator
+      # @return [Array]
+      #
+      def split_to_nodes(str, seperator)
+
+        before, after = str.split(seperator)
+
+        node_before = Oga::XML::Text.new
+        node_after = Oga::XML::Text.new
+
+        node_before.text = before
+        node_after.text = after || ""
+
+        return [node_before, node_after ]
+      end
+
+      ##
+      # Convert `unicode` string into a `"HHHH-HHHH"` string, which represents
+      # the codepoints of the unicode string, but only if `unicode`
+      # is a valid emoji.
+      #
+      #
+      # @param [String] unicode
+      # @return [String]
+      #
+      def unicode_to_codepoints(unicode)
+        return unicode unless @encoding_map.key? unicode
+        unicode.codepoints.map {|cp| cp.to_s 16}.join('-')
+      end
+
+      ##
+      # Convert `codepoints` into an unicode string.
+      #
+      # @param [String|Array] codepoints
+      # @return [String]
+      #
+      def codepoints_to_unicode(codepoints)
+        if codepoints.is_a? String
+          codepoints.split('-').map(&:hex).pack("U*")
+        elsif codepoints.is_a? Array
+          codepoints.map {|cp| cp.is_a?(String) ? cp.hex : cp }.pack("U*")
+        else
+          raise(ArgumentError, "must be String or Array")
+        end
+      end
+
+      ##
+      # Emojify the string. If the string is an HTML strings, certain elements
+      # won't be emojified. Check the `BLACKLIST_*`` constants, or the docs for
+      # more information.
+      #
+      # @param [String] convert
+      # @return [String]
+      #
+      def convert(content)
+        document = Oga.parse_html(content)
+        add_emojis(document)
+        docstr = document.to_xml
+
+        # Now we only need to encode the Emojis into HTML Entities
+        if @conf['format'] == 'html'
+          docstr.gsub!(@encoding_regexp, @encoding_map)
+        end
+
+        return docstr
+      end # convert
+
+      def self.site_conf
+        @@site_conf
+      end
+
+      private :load_emoji_json, :load_emoji_data
+      private :validate_format
+      private :build_emoji_regexp
+      private :process_node
+      private :emojione_img_node, :split_to_nodes
+      private :unicode_to_codepoints, :codepoints_to_unicode
+    end #Converter
+  end #Emoji
+end

data/lib/jekyll/emoji/filter.rb

@@ -0,0 +1,30 @@
+module Jekyll
+  module Emoji
+    module Filter
+      ##
+      # Emojify the string. If the string is an HTML strings, certain elements
+      # won't be emojified. Check the `BLACKLIST_*`` constants, and/or the docs
+      # inside the README for more information.
+      #
+      # @param [String] input
+      # @param [String] output_format
+      # @param [FalseClass|TrueClass|NilClass] ascii
+      # @param [FalseClass|TrueClass|NilClass] shortname
+      # @return [String]
+      #
+      def emojify(input, output_format = nil, ascii = nil, shortname = nil)
+        @@emoji_converter ||= Converter.new(Converter.site_conf)
+        @@emoji_converter.reconfigure('format' => output_format, 'ascii' => ascii, 'shortname' => shortname)
+
+        output = @@emoji_converter.convert(input)
+
+        # NOTE: This impacts performance in certain cases
+        @@emoji_converter.reconfigure(Converter.site_conf)
+
+        return output
+      end
+    end #Filter
+  end #Emoji
+end
+
+Liquid::Template.register_filter(Jekyll::Emoji::Filter)

data/lib/jekyll/emoji/version.rb

@@ -1,5 +1,5 @@
 module Jekyll
   module Emoji
-    VERSION = "0.1.4"
+    VERSION = "0.1.5"
   end
 end

data/tests/conversion_test.rb

@@ -26,10 +26,10 @@ class TestConversion < MiniTest::Test
 
   def test_svg
     @converter.reconfigure 'format' => 'emojione-svg'
-    img = %q{<img class="emojione" alt="3⃣" src="https://cdn.jsdelivr.net/emojione/assets/svg/0033-20E3.svg" />}
-    assert_equal img, @converter.convert("\u{0033}\u{20E3}")
-    assert_equal img, @converter.convert(":three:")
-    assert_equal "3", @converter.convert("3")
+    img = %q{the number <img class="emojione" alt="3⃣" src="https://cdn.jsdelivr.net/emojione/assets/svg/0033-20E3.svg" /> is smaller than 4}
+    assert_equal img, @converter.convert("the number \u{0033}\u{20E3} is smaller than 4")
+    assert_equal img, @converter.convert("the number :three: is smaller than 4")
+    assert_equal "the number 3 is smaller than 4", @converter.convert("the number 3 is smaller than 4")
   end
 
   def test_reconfiguring_aliases
@@ -62,7 +62,7 @@ class TestConversion < MiniTest::Test
     assert_equal result2, @converter.convert(test2)
   end
 
-  def test_attr_blacklists
+  def test_node_blacklists
     test1 = %q{<code>:)</code>}
     result1 = %q{<code>:)</code>}
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: jekyll-emoji
 version: !ruby/object:Gem::Version
-  version: 0.1.4
+  version: 0.1.5
 platform: ruby
 authors:
 - Nino Miletich
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-08-10 00:00:00.000000000 Z
+date: 2015-08-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -125,6 +125,8 @@ files:
 - jekyll-emoji.gemspec
 - lib/jekyll-emoji.rb
 - lib/jekyll/emoji.rb
+- lib/jekyll/emoji/converter.rb
+- lib/jekyll/emoji/filter.rb
 - lib/jekyll/emoji/version.rb
 - tests/conversion_test.rb
 homepage: https://github.com/omninonsense/jekyll-emoji