emoji_data 0.1.0.rc1 → 0.1.0.rc2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 7c2cca7a834cd49e348c09b50c042596f93f5076
-  data.tar.gz: 8402df0f4d2d828ec9ed322d093da13602a4d64c
+  metadata.gz: 671af8082390de92a6fe0d117ba06ac889432139
+  data.tar.gz: 8936a23eaae21c2de5c9c4ed7b64e8c65502c299
 SHA512:
-  metadata.gz: 95dba4e1fbb80d741b5c535b091ecf60fd6666c0a810f6e69eaf15a64a13aab72eae8b1b5b1969b3b8d5894bf5f4dd646261a1560a28b02ef331678dbf8481c7
-  data.tar.gz: fdebfa5d68128ec34273fd4e21192e0203fd2f377a2c083b9282688bc205500b65f69fc410ffa6cc4f80133623bff0bac0e090352177f10cd5702b557ad86814
+  metadata.gz: 48fd69617af75d22deadd75a6c3eefeea4e5614c8e8d2a93340a73d0a7b4a7aca9bc947c33e0c1d6f2d6dace4266ad8c647d0a449e0e68200d2732def98b748c
+  data.tar.gz: 54e3b3ce6716a80301dbc769061ac699c495c010c690e2a95467055fbb48f8c7b81563a178f3a5b4c080ca06f237554ad6be197239f59f4102bdc1d82775494b

data/CHANGELOG.md

@@ -5,6 +5,7 @@
  * 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.
+ * With adding support for variants, the speed of `find_by_str` regressed by approximately 20% (because there are more codepoints to match against). To counter this, we switched to a Regex based scan than improves performance of the method by over 250x(!).  A complete sorted search against 1000 strings now takes ~2ms where before it would take around a half second.
  * Import latest version of iamcal/emoji-data.
  * 100% test coverage. :sunglasses:
 

data/lib/emoji_data.rb

@@ -64,11 +64,10 @@ module EmojiData
     EMOJICHAR_UNIFIED_MAP[cp.upcase]
   end
 
+  FBS_REGEXP = Regexp.new("(?:#{EmojiData.chars({include_variants: true}).join("|")})")
   def self.find_by_str(str)
-    str.extend EmojiData::StringUtils
-
-    matches = EMOJI_CHARS.select { |ec| str.include_any? ec.chars }
-    matches.sort_by { |mc| str.index_first(mc.chars) }
+    matches = str.scan(FBS_REGEXP)
+    matches.map { |m| EmojiData.find_by_unified(EmojiData.char_to_unified(m)) }
   end
 
   def self.find_by_name(name)
@@ -84,17 +83,4 @@ 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/version.rb

@@ -1,3 +1,3 @@
 module EmojiData
-  VERSION = "0.1.0.rc1"
+  VERSION = "0.1.0.rc2"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: emoji_data
 version: !ruby/object:Gem::Version
-  version: 0.1.0.rc1
+  version: 0.1.0.rc2
 platform: ruby
 authors:
 - Matthew Rothenberg
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-04-28 00:00:00.000000000 Z
+date: 2014-05-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler