twitter_cldr 1.3.6 → 1.4.0

data/lib/twitter_cldr/shared/unicode_data.rb

@@ -1,64 +0,0 @@
-# encoding: UTF-8
-
-# Copyright 2012 Twitter, Inc
-# http://www.apache.org/licenses/LICENSE-2.0
-
-module TwitterCldr
-  module Shared
-    module UnicodeData
-
-      class << self
-
-        def for_code_point(code_point)
-          blocks = TwitterCldr.get_resource(:unicode_data, :blocks)
-
-          #Find the target block
-          target = blocks.find do |block_name, range|
-            range.include? code_point.to_i(16)
-          end
-
-          if target
-            block_data = TwitterCldr.get_resource(:unicode_data, target.first)
-            code_point_data = block_data.fetch(code_point.to_sym) { |code_point_sym| get_range_start(code_point_sym, block_data) }
-            Attributes.new(*code_point_data) if code_point_data
-          end
-        end
-
-        private
-
-        # Check if block constitutes a range. The code point beginning a range will have a name enclosed in <>, ending with 'First'
-        # eg: <CJK Ideograph Extension A, First>
-        # http://unicode.org/reports/tr44/#Code_Point_Ranges
-        def get_range_start(code_point, block_data)
-          start_code_point = block_data.keys.sort_by { |key| key.to_s.to_i(16) }.first
-          start_data = block_data[start_code_point].clone
-          if start_data[1] =~ /<.*, First>/
-            start_data[0] = code_point.to_s
-            start_data[1] = start_data[1].sub(', First', '')
-            start_data
-          end
-        end
-
-      end
-
-      Attributes = Struct.new(
-          :code_point,
-          :name,
-          :category,
-          :combining_class,
-          :bidi_class,
-          :decomposition,
-          :digit_value,
-          :non_decimal_digit_value,
-          :numeric_value,
-          :bidi_mirrored,
-          :unicode1_name,
-          :iso_comment,
-          :simple_uppercase_map,
-          :simple_lowercase_map,
-          :simple_titlecase_map
-      )
-
-    end
-  end
-end

data/spec/normalizers/nfd_spec.rb

@@ -1,21 +0,0 @@
-# encoding: UTF-8
-
-# Copyright 2012 Twitter, Inc
-# http://www.apache.org/licenses/LICENSE-2.0
-
-require 'spec_helper'
-
-include TwitterCldr::Normalizers
-
-describe NFD do
-
-  describe "#normalize" do
-    NFD.normalize("庠摪饢鼢豦樄澸脧鱵礩翜艰").should == "庠摪饢鼢豦樄澸脧鱵礩翜艰"
-    NFD.normalize("䷙䷿").should == "䷙䷿"
-    NFD.normalize("ᎿᎲᎪᏨᎨᏪᎧᎵᏥ").should == "ᎿᎲᎪᏨᎨᏪᎧᎵᏥ"
-    NFD.normalize("ᆙᅓᆼᄋᇶ").should == "ᆙᅓᆼᄋᇶ"
-    NFD.normalize("…‾⁋
⁒‒′‾⁖").should == "…‾⁋
⁒‒′‾⁖"
-    NFD.normalize("ⶾⷕⶱⷀ").should == "ⶾⷕⶱⷀ"
-  end
-
-end

data/spec/shared/unicode_data_spec.rb

@@ -1,51 +0,0 @@
-# encoding: UTF-8
-
-# Copyright 2012 Twitter, Inc
-# http://www.apache.org/licenses/LICENSE-2.0
-
-require 'spec_helper'
-
-include TwitterCldr::Shared
-
-describe UnicodeData do
-  describe "#for_code_point" do
-    it "should retrieve information for any valid code point" do
-      data = UnicodeData.for_code_point('0301')
-      data.should be_a(Struct)
-      data.length.should == 15
-    end
-
-    it "should return nil for invalid code points" do
-      UnicodeData.for_code_point('abcd').should be_nil
-      UnicodeData.for_code_point('FFFFFFF').should be_nil
-      UnicodeData.for_code_point('uytukhil123').should be_nil
-    end
-
-    it "fetches valid information for the specified code point" do
-      test_data = {
-        '17D1' => ['17D1','KHMER SIGN VIRIAM','Mn','0','NSM',"","","","",'N',"","","","",""],
-        'FE91' => ['FE91','ARABIC LETTER BEH INITIAL FORM','Lo','0','AL','<initial> 0628',"","","",'N','GLYPH FOR INITIAL ARABIC BAA',"","","",""],
-        '24B5' => ['24B5','PARENTHESIZED LATIN SMALL LETTER Z','So','0','L','<compat> 0028 007A 0029',"","","",'N',"","","","",""],
-        '2128' => ['2128','BLACK-LETTER CAPITAL Z','Lu','0','L','<font> 005A',"","","",'N','BLACK-LETTER Z',"","","",""],
-        '1F241'=> ['1F241','TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-4E09','So','0','L','<compat> 3014 4E09 3015',"","","",'N',"","","","",""]
-      }
-      test_data.each_pair do |code_point, data|
-        UnicodeData.for_code_point(code_point).values.should == data
-      end
-    end
-
-    it "fetches valid information for a code point within a range" do
-      test_data = {
-        '4E11' => ["4E11","<CJK Ideograph>","Lo","0","L","","","","","N","","","","",""],
-        'AC55' => ["AC55","<Hangul Syllable>","Lo","0","L","","","","","N","","","","",""],
-        'D7A1' => ["D7A1","<Hangul Syllable>","Lo","0","L","","","","","N","","","","",""],
-        'DAAA' => ["DAAA","<Non Private Use High Surrogate>","Cs","0","L","","","","","N","","","","",""],
-        'F8FE' => ["F8FE","<Private Use>","Co","0","L","","","","","N","","","","",""]
-      }
-
-      test_data.each_pair do |code_point, data|
-        UnicodeData.for_code_point(code_point).values.should == data
-      end
-    end
-  end
-end