emoji_data 0.0.3 → 0.1.0.rc1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: c7a2b01097e18162bdb426c05bfb76f871ca7f39
-  data.tar.gz: 5e75e18ab2252aab634cd17863a6b7cbb471119b
+  metadata.gz: 7c2cca7a834cd49e348c09b50c042596f93f5076
+  data.tar.gz: 8402df0f4d2d828ec9ed322d093da13602a4d64c
 SHA512:
-  metadata.gz: 23f834f7c47f8015bf14a80623cdaf95ebfd45a2d33f9eeeda0434232146311c439b895476ac7b65382e12c0a8b7038cd7508b6352871d643474acf20f32d838
-  data.tar.gz: 7a93b457a18d7bfec72cf3914527a9426abe03aab8b186812b6e7d8fd3cf3ee576cf57c1f88ba415862ce10dba388215e014e10f204ad625d52d6e1e2aeb6526
+  metadata.gz: 95dba4e1fbb80d741b5c535b091ecf60fd6666c0a810f6e69eaf15a64a13aab72eae8b1b5b1969b3b8d5894bf5f4dd646261a1560a28b02ef331678dbf8481c7
+  data.tar.gz: fdebfa5d68128ec34273fd4e21192e0203fd2f377a2c083b9282688bc205500b65f69fc410ffa6cc4f80133623bff0bac0e090352177f10cd5702b557ad86814

data/.coveralls.yml

@@ -0,0 +1,2 @@
+service_name: travis-ci
+

data/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## 0.1.0 (Pending)
+
+ * Add support for Unicode variant encodings, used by MacOSX 10.9 / iOS 7.
+   - For more info: http://www.unicode.org/L2/L2011/11438-emoji-var.pdf
+   - By default, `EmojiChar.to_s()` and `.char()` will now use the variant encoding.
+ * Import latest version of iamcal/emoji-data.
+ * 100% test coverage. :sunglasses:
+
 ## 0.0.3 (1 April 2013)
 
  * On initialization, create hashmaps to cache lookups for `.find_by_unified()`.

data/README.md

@@ -1,13 +1,17 @@
 # emoji_data.rb
 
-[![Gem Version](https://badge.fury.io/rb/emoji_data.png)](http://badge.fury.io/rb/emoji_data)
-[![Build Status](https://travis-ci.org/mroth/emoji_data.rb.png?branch=master)](https://travis-ci.org/mroth/emoji_data.rb)
+[![Gem Version](http://img.shields.io/gem/v/emoji_data.svg?style=flat)](https://rubygems.org/gems/emoji_data)
+[![Build Status](http://img.shields.io/travis/mroth/emoji_data.rb.svg?style=flat)](https://travis-ci.org/mroth/emoji_data.rb)
+[![Dependency Status](http://img.shields.io/gemnasium/mroth/emoji_data.rb.svg?style=flat)](https://gemnasium.com/mroth/emoji_data.rb)
+[![CodeClimate Status](http://img.shields.io/codeclimate/github/mroth/emoji_data.rb.svg?style=flat)](https://codeclimate.com/github/mroth/emoji_data.rb)
+[![Coverage Status](http://img.shields.io/coveralls/mroth/emoji_data.rb.svg?style=flat)](https://coveralls.io/r/mroth/emoji_data.rb)
+
 
 Provides classes and helpers for dealing with emoji character data as unicode.  Wraps a library of all known emoji characters and provides convenience methods.
 
-Note, this is mostly useful for low-level operations.  If you can avoid having to deal with unicode character data extensively and just want to encode/decode stuff, [rumoji](https://github.com/mwunsch/rumoji) might be a better bet for you.
+Note, this is mostly useful for low-level operations.  If you can avoid having to deal with unicode character data extensively and just want to encode/decode stuff, [rumoji](https://github.com/mwunsch/rumoji) might be a better bet for you.  If however, you are doing anything complicated involving emoji encoding/decoding, or you are just obsessed with understanding the details, this library is your new best friend.
 
-This library currently uses `iamcal/emoji-data` as it's library dataset, and thus considers it to be the "source of truth" regarding certain things, such as how to represent doublebyte unified codepoint IDs as strings (seperated by a dash).
+This library currently uses `iamcal/emoji-data` as it's dataset, and thus considers it to be the "source of truth" regarding certain things, such as how to represent doublebyte unified codepoint IDs as strings (seperated by a dash).
 
 This is basically a helper library for my [emojitrack](https://github.com/mroth/emojitrack) and [emojistatic](https://github.com/mroth/emojistatic) projects, but may be useful for other people.
 
@@ -25,7 +29,7 @@ Or install it yourself as:
 
     $ gem install emoji_data
 
-Currently requires Ruby 1.9 or more recent.
+Currently requires `RUBY_VERSION >= 1.9.2`.
 
 ## Library Usage
 
@@ -64,5 +68,3 @@ Some notable methods to call out:
   `EmojiData::EmojiChar` is a class representing a single emoji character.  All the variables from the `iamcal/emoji-data` dataset have dynamically generated getter methods.
 
 There are some additional convenience methods, such as `#doublebyte?` etc. Most important addition is the `#char` method which will output a properly unicode encoded string containing the character.
-
-

data/emoji_data.gemspec

@@ -21,6 +21,8 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "bundler", "~> 1.3"
   spec.add_development_dependency "rake"
   spec.add_development_dependency "rspec"
+  spec.add_development_dependency 'simplecov', '~> 0.7.1'
+  spec.add_development_dependency 'coveralls', '~> 0.7.0'
 
   spec.required_ruby_version = '>= 1.9.2'
 end

data/lib/emoji_data.rb

@@ -8,19 +8,48 @@ module EmojiData
   EMOJI_MAP = JSON.parse( RAW_JSON )
   EMOJI_CHARS = EMOJI_MAP.map { |em| EmojiChar.new(em) }
 
-  # hashmap for fast unified lookups
+  #
+  # construct hashmap for fast precached lookups for `.find_by_unified`
+  #
   EMOJICHAR_UNIFIED_MAP = Hash[EMOJI_CHARS.map { |u| [u.unified, u] }]
+  # merge variant encodings into map so we can look them up as well
+  EMOJI_CHARS.select(&:variant?).each do |char|
+    char.variations.each do |variant|
+      EMOJICHAR_UNIFIED_MAP.merge! Hash[variant,char]
+    end
+  end
 
   def self.all
     EMOJI_CHARS
   end
 
-  def self.chars
-    @chars ||= EMOJI_CHARS.map(&:char)
+  def self.all_doublebyte
+    EMOJI_CHARS.select(&:doublebyte?)
+  end
+
+  def self.all_with_variants
+    EMOJI_CHARS.select(&:variant?)
+  end
+
+  def self.chars(options={})
+    options = {include_variants: false}.merge(options)
+
+    normals = EMOJI_CHARS.map { |c| c.char({variant_encoding: false}) }
+    extras  = self.all_with_variants.map { |c| c.char({variant_encoding: true}) }
+
+    if options[:include_variants]
+      return normals + extras
+    end
+    normals
   end
 
-  def self.codepoints
-    @codepoints ||= EMOJI_CHARS.map(&:unified)
+  def self.codepoints(options={})
+    options = {include_variants: false}.merge(options)
+
+    if options[:include_variants]
+      return EMOJI_CHARS.map(&:unified) + self.all_with_variants.map {|c| c.variant}
+    end
+    EMOJI_CHARS.map(&:unified)
   end
 
   def self.char_to_unified(char)
@@ -28,26 +57,25 @@ module EmojiData
   end
 
   def self.unified_to_char(cp)
-    find_by_unified(cp).char
+    EmojiChar::unified_to_char(cp)
   end
 
   def self.find_by_unified(cp)
-    # EMOJI_CHARS.detect { |ec| ec.unified == cp.upcase }
     EMOJICHAR_UNIFIED_MAP[cp.upcase]
   end
 
   def self.find_by_str(str)
-    matches = EMOJI_CHARS.select { |ec| str.include? ec.char }
-    matches.sort_by { |matched_char| str.index(matched_char.char) }
+    str.extend EmojiData::StringUtils
+
+    matches = EMOJI_CHARS.select { |ec| str.include_any? ec.chars }
+    matches.sort_by { |mc| str.index_first(mc.chars) }
   end
 
   def self.find_by_name(name)
-    # self.all.select { |char| char.name.include? name.upcase }
     self.find_by_value(:name, name.upcase)
   end
 
   def self.find_by_short_name(short_name)
-    # self.all.select { |char| char.short_name.include? name.downcase }
     self.find_by_value(:short_name, short_name.downcase)
   end
 
@@ -56,4 +84,17 @@ module EmojiData
     self.all.select { |char| char.send(field).include? value }
   end
 
+  module StringUtils
+    def include_any?(charstr)
+      charstr.any? { |char| self.include? char }
+    end
+
+    def index_first(charstr)
+      charstr.each do |char|
+        return self.index(char) if !self.index(char).nil?
+      end
+      nil
+    end
+  end
+
 end

data/lib/emoji_data/emoji_char.rb

@@ -2,6 +2,11 @@ module EmojiData
 
   class EmojiChar
     def initialize(emoji_hash)
+      # work around inconsistency in emoji.json for now by just setting a blank
+      # array for instance value, and let it get overriden in main
+      # deserialization loop if variable is present.
+      @variations = []
+
       # http://stackoverflow.com/questions/1615190/declaring-instance-variables-iterating-over-a-hash
       emoji_hash.each do |k,v|
         instance_variable_set("@#{k}",v)
@@ -10,9 +15,25 @@ module EmojiData
       end
     end
 
-    # Public: Returns a version of the character for rendering to screen.
-    def char
-      @char ||= @unified.split('-').map { |i| i.hex }.pack("U*")
+    # Returns a version of the character for rendering to screen.
+    #
+    # By default this will now use the variant encoding if it exists.
+    def char(options = {})
+      options = {variant_encoding: true}.merge(options)
+      #decide whether to use the normal unified ID or the variant for encoding to str
+      target = (self.variant? && options[:variant_encoding]) ? self.variant : @unified
+      EmojiChar::unified_to_char(target)
+    end
+
+    # Return ALL known possible string encodings of the emoji char.
+    #
+    # Mostly useful for doing find operations when you need them all.
+    def chars
+      results = [self.char({variant_encoding: false})]
+      @variations.each do |variation|
+        results << EmojiChar::unified_to_char(variation)
+      end
+      @chars ||= results
     end
 
     # Public: Is the character represented by a doublebyte unicode codepoint in unicode?
@@ -20,7 +41,25 @@ module EmojiData
       @unified.match(/-/)
     end
 
+    # does the emojichar have an alternate variant encoding?
+    def variant?
+      @variations.length > 0
+    end
+
+    # return whatever is the most likely variant ID for the emojichar
+    # for now, there can only be one, so just return first.
+    # (in the future, there may be multiple variants, who knows!)
+    def variant
+      @variations.first
+    end
+
     alias_method :to_s, :char
+
+    protected
+    def self.unified_to_char(cps)
+      cps.split('-').map { |i| i.hex }.pack("U*")
+    end
+
   end
 
 end

data/lib/emoji_data/version.rb

@@ -1,3 +1,3 @@
 module EmojiData
-  VERSION = "0.0.3"
+  VERSION = "0.1.0.rc1"
 end

data/spec/emoji_char_spec.rb

@@ -4,18 +4,19 @@ require 'spec_helper'
 describe EmojiChar do
   describe ".new" do
     before(:all) do
-      poop_json = %q/{"name":"PILE OF POO","unified":"1F4A9","docomo":"","au":"E4F5","softbank":"E05A","google":"FE4F4","image":"1f4a9.png","sheet_x":13,"sheet_y":19,"short_name":"hankey","short_names":["hankey","poop","shit"],"text":null}/
+      poop_json = %q/{"name":"PILE OF POO","unified":"1F4A9","variations":[],"docomo":"","au":"E4F5","softbank":"E05A","google":"FE4F4","image":"1f4a9.png","sheet_x":11,"sheet_y":19,"short_name":"hankey","short_names":["hankey","poop","shit"],"text":null}/
       @poop = EmojiChar.new(JSON.parse poop_json)
     end
     it "should create instance getters for all key-values in emoji.json, with blanks as nil" do
       @poop.name.should eq('PILE OF POO')
       @poop.unified.should eq('1F4A9')
+      @poop.variations.should eq([])
       @poop.docomo.should eq('')
       @poop.au.should eq('E4F5')
       @poop.softbank.should eq('E05A')
       @poop.google.should eq('FE4F4')
       @poop.image.should eq('1f4a9.png')
-      @poop.sheet_x.should eq(13)
+      @poop.sheet_x.should eq(11)
       @poop.sheet_y.should eq(19)
       @poop.short_name.should eq('hankey')
       @poop.short_names.should eq(["hankey","poop","shit"])
@@ -25,8 +26,10 @@ describe EmojiChar do
 
   context "instance methods" do
     before(:all) do
-      @invader = EmojiChar.new({'unified' => '1F47E'})
-      @usflag = EmojiChar.new({'unified' => '1F1FA-1F1F8'})
+      @invader   = EmojiChar.new({'unified' => '1F47E'})
+      @usflag    = EmojiChar.new({'unified' => '1F1FA-1F1F8'})
+      @hourglass = EmojiChar.new({'unified' => '231B', 'variations' => ['231B-FE0F']})
+      @cloud     = EmojiChar.new({'unified' => '2601', 'variations' => ['2601-FE0F']})
     end
 
     describe "#to_s" do
@@ -42,6 +45,23 @@ describe EmojiChar do
       it "should render as happy shiny unicode for doublebyte chars too" do
         @usflag.char.should eq("🇺🇸")
       end
+      it "should have a flag to output forced emoji variant char encoding if requested" do
+        @cloud.char(    {variant_encoding: false}).should eq("\u{2601}")
+        @cloud.char(    {variant_encoding:  true}).should eq("\u{2601}\u{FE0F}")
+        @invader.char(  {variant_encoding: false}).should eq("\u{1F47E}")
+        @invader.char(  {variant_encoding:  true}).should eq("\u{1F47E}")
+      end
+      it "should default to variant encoding for chars with a variant present" do
+        @cloud.char.should eq("\u{2601}\u{FE0F}")
+        @hourglass.char.should eq("\u{231B}\u{FE0F}")
+      end
+    end
+
+    describe "#chars" do
+      it "should return an array of all possible string render variations" do
+        @invader.chars.should eq(["\u{1F47E}"])
+        @cloud.chars.should   eq(["\u{2601}","\u{2601}\u{FE0F}"])
+      end
     end
 
     describe "#doublebyte?" do
@@ -50,5 +70,21 @@ describe EmojiChar do
         @invader.doublebyte?.should be_false
       end
     end
+
+    describe "#variant?" do
+      it "should indicate when a character has an alternate variant encoding" do
+        @hourglass.variant?.should be_true
+        @usflag.variant?.should be_false
+      end
+    end
+
+    describe "#variant" do
+      it "should return the most likely variant encoding ID representation for the char" do
+        @hourglass.variant.should eq('231B-FE0F')
+      end
+      it "should return nil if no variant encoding for the char exists" do
+        @usflag.variant.should be_nil
+      end
+    end
   end
-end
+end

data/spec/emoji_data_spec.rb

@@ -3,18 +3,65 @@ require 'spec_helper'
 
 describe EmojiData do
   describe ".all" do
-    it "should return an array of all known emoji chars" do
-      EmojiData.all.count.should eq(842)
+    it "should return an array of all 845 known emoji chars" do
+      EmojiData.all.count.should eq(845)
     end
     it "should return all EmojiChar objects" do
       EmojiData.all.all? {|char| char.class == EmojiData::EmojiChar}.should be_true
     end
   end
 
+  describe ".all_doublebyte" do
+    it "should return an array of all 21 known emoji chars with doublebyte encoding" do
+      EmojiData.all_doublebyte.count.should eq(21)
+    end
+  end
+
+  describe ".all_with_variants" do
+    it "should return an array of all 107 known emoji chars with variant encodings" do
+      EmojiData.all_with_variants.count.should eq(107)
+    end
+  end
+
+  describe ".chars" do
+    it "should return an array of all chars in unicode string format" do
+      EmojiData.chars.all? {|char| char.class == String}.should be_true
+    end
+    it "should by default return one entry per known EmojiChar" do
+      EmojiData.chars.count.should eq(EmojiData.all.count)
+    end
+    it "should include variants in list when options {include_variants: true}" do
+      results = EmojiData.chars({include_variants: true})
+      numChars    = EmojiData.all.count
+      numVariants = EmojiData.all_with_variants.count
+      results.count.should eq(numChars + numVariants)
+    end
+    it "should not have any duplicates in list when variants are included" do
+      results = EmojiData.chars({include_variants: true})
+      results.count.should eq(results.uniq.count)
+    end
+  end
+
+  describe ".codepoints" do
+    it "should return an array of all known codepoints in dashed string representation" do
+      EmojiData.codepoints.all? {|cp| cp.class == String}.should be_true
+      EmojiData.codepoints.all? {|cp| cp.match(/^[0-9A-F\-]{4,11}$/)}.should be_true
+    end
+    it "should include variants in list when options {include_variants: true}" do
+      results = EmojiData.codepoints({include_variants: true})
+      numChars    = EmojiData.all.count
+      numVariants = EmojiData.all_with_variants.count
+      results.count.should eq(numChars + numVariants)
+      results.all? {|cp| cp.match(/^[0-9A-F\-]{4,16}$/)}.should be_true
+    end
+  end
+
   describe ".find_by_str" do
     before(:all) do
-      @exact_results = EmojiData.find_by_str("🚀")
-      @multi_results = EmojiData.find_by_str("flying on my 🚀 to visit the 👾 people.")
+      @exact_results   = EmojiData.find_by_str("🚀")
+      @multi_results   = EmojiData.find_by_str("flying on my 🚀 to visit the 👾 people.")
+      @variant_results = EmojiData.find_by_str("\u{0023}\u{FE0F}\u{20E3}")
+      @variant_multi   = EmojiData.find_by_str("first a \u{0023}\u{FE0F}\u{20E3} then a 🚀")
     end
     it "should find the proper EmojiChar object from a single string char" do
       @exact_results.should be_kind_of(Array)
@@ -22,6 +69,10 @@ describe EmojiData do
       @exact_results.first.should be_kind_of(EmojiChar)
       @exact_results.first.name.should eq('ROCKET')
     end
+    it "should find the proper EmojiChar object from a variant encoded char" do
+      @variant_results.length.should eq(1)
+      @variant_results.first.name.should eq('HASH KEY')
+    end
     it "should match multiple chars from within a string" do
       @multi_results.should be_kind_of(Array)
       @multi_results.length.should eq(2)
@@ -32,6 +83,10 @@ describe EmojiData do
       @multi_results[0].name.should eq('ROCKET')
       @multi_results[1].name.should eq('ALIEN MONSTER')
     end
+    it "should return multiple matches in the proper order for variant encodings" do
+      @variant_multi[0].name.should eq('HASH KEY')
+      @variant_multi[1].name.should eq('ROCKET')
+    end
   end
 
   describe ".find_by_unified" do
@@ -40,9 +95,14 @@ describe EmojiData do
       results.should be_kind_of(EmojiChar)
       results.name.should eq('ROCKET')
     end
-    it "should normallise capitalization for hex values" do
+    it "should normalise capitalization for hex values" do
       EmojiData.find_by_unified('1f680').should_not be_nil
     end
+    it "should find via variant encoding ID format as well" do
+      results = EmojiData.find_by_unified('2764-fe0f')
+      results.should_not be_nil
+      results.name.should eq('HEAVY BLACK HEART')
+    end
   end
 
   describe ".find_by_name" do
@@ -78,6 +138,9 @@ describe EmojiData do
       EmojiData.char_to_unified("🇺🇸").should eq('1F1FA-1F1F8')
       EmojiData.char_to_unified("#⃣").should eq('0023-20E3')
     end
+    it "converts variant encoded emoji to variant unified codepoint" do
+      EmojiData.char_to_unified("\u{2601}\u{FE0F}").should eq('2601-FE0F')
+    end
   end
 
   # TODO: below is kinda redundant but it is helpful as a helper method so maybe still test
@@ -90,5 +153,11 @@ describe EmojiData do
       EmojiData.unified_to_char('1F1FA-1F1F8').should eq("🇺🇸")
       EmojiData.unified_to_char('0023-20E3').should eq("#⃣")
     end
+    it "converts variant unified codepoints to unicode strings" do
+      EmojiData.unified_to_char('2764-fe0f').should eq("\u{2764}\u{FE0F}")
+    end
+    it "converts variant+doublebyte chars (triplets!) to unicode strings" do
+      EmojiData.unified_to_char('0030-FE0F-20E3').should eq("\u{0030}\u{FE0F}\u{20E3}")
+    end
   end
-end
+end