implement EmojiData.from_short_name()

CHANGELOG.md

@@ -4,14 +4,15 @@
 
  * Rename a number of methods to be clearer and more consistent with that they
    actually do:
-     - `EmojiChar.char` → `EmojiChar.render`
-     - `EmojiData.find_by_unified` → `EmojiData.from_unified`
-     - `EmojiData.find_by_str` → `EmojiData.scan`
+     - `EmojiChar.char()` → `EmojiChar.render()`
+     - `EmojiData.find_by_unified()` → `EmojiData.from_unified()`
+     - `EmojiData.find_by_str()` → `EmojiData.scan()`
 
    Don't worry, the old names are still aliased in so you don't have to change
    anything in your existing code.  This change is make things clearer for
    people new to the library.
 
+ * Add new `.from_short_name()` library method for fast keyword lookups.
  * DEVELOPERS: Internal code cleanup and better comments.
  * DEVELOPERS: Add benchmark suite for comparing method implementation time
    across versions of this library.

lib/emoji_data.rb

@@ -15,7 +15,7 @@ module EmojiData
     vendordata.map { |em| EmojiChar.new(em) }
   end
 
-  # precomputed hashmap for fast precached lookups
+  # precomputed hashmap for fast precached lookups in .from_unified
   EMOJICHAR_UNIFIED_MAP = begin
     results = Hash[EMOJI_CHARS.map { |u| [u.unified, u] }]
     EMOJI_CHARS.select(&:variant?).each do |char|
@@ -26,8 +26,16 @@ module EmojiData
     results
   end
 
+  # precomputed hashmap for fast precached lookups in .from_short_name
+  EMOJICHAR_KEYWORD_MAP = {}
+  EMOJI_CHARS.each do |ec|
+    ec.short_names.each { |keyword| EMOJICHAR_KEYWORD_MAP[keyword] = ec }
+  end
+
+
   # our constants are only for usage internally
-  private_constant :GEM_ROOT, :VENDOR_DATA, :EMOJI_CHARS, :EMOJICHAR_UNIFIED_MAP
+  private_constant :GEM_ROOT, :VENDOR_DATA
+  private_constant :EMOJI_CHARS, :EMOJICHAR_UNIFIED_MAP, :EMOJICHAR_KEYWORD_MAP
 
 
   # Returns a list of all known Emoji characters as `EmojiChar` objects.
@@ -171,10 +179,15 @@ def self.find_by_short_name(short_name)
     self.find_by_value(:short_name, short_name.downcase)
   end
 
-
-  # TODO: port over .from_shortname from NodeJS version
-  # needs to be added to benchmarks for all versions too!
-
+  # Finds a specific `EmojiChar` based on the unified codepoint ID.
+  #
+  # Must be exact match.
+  #
+  # @param short_name [String]
+  # @return [EmojiChar]
+  def self.from_short_name(short_name)
+    EMOJICHAR_KEYWORD_MAP[short_name.downcase]
+  end
 
   # alias old method names for legacy apps
   class << self

spec/emoji_data_spec.rb

@@ -141,6 +141,25 @@
     end
   end
 
+  describe ".from_short_name" do
+    it "returns exact matches on a short name" do
+      results = EmojiData.from_short_name('scream')
+      results.should be_kind_of(EmojiChar)
+      results.name.should eq('FACE SCREAMING IN FEAR')
+    end
+    it "handles lowercasing input if required" do
+      EmojiData.from_short_name('SCREAM').should eq( EmojiData.from_short_name('scream') )
+    end
+    it "works on secondary keywords" do
+      primary = EmojiData.from_short_name('hankey')
+      EmojiData.from_short_name('poop').should eq(primary)
+      EmojiData.from_short_name('shit').should eq(primary)
+    end
+    it "returns nil if nothing matches" do
+      EmojiData.from_short_name('taco').should be_nil
+    end
+  end
+
   describe ".char_to_unified" do
     it "converts normal emoji to unified codepoint" do
       EmojiData.char_to_unified("👾").should eq('1F47E')