twitter_cldr 1.6.2 → 1.7.0

data/lib/twitter_cldr/shared/code_point.rb

@@ -27,6 +27,25 @@ module TwitterCldr
     CodePoint = Struct.new(*CODE_POINT_FIELDS) do
       DECOMPOSITION_DATA_INDEX = 5
 
+      DECOMPOSITION_REGEX = /^(?:<(.+)>\s+)?(.+)?$/
+
+      attr_accessor :compatibility_decomposition_tag
+
+      def initialize(*)
+        super
+
+        if decomposition =~ DECOMPOSITION_REGEX
+          self.compatibility_decomposition_tag = $1
+          self.decomposition = $2 && $2.split.map(&:hex)
+        else
+          raise ArgumentError, "decomposition #{decomposition.inspect} has invalid format"
+        end
+      end
+
+      def compatibility_decomposition?
+        !!compatibility_decomposition_tag
+      end
+
       def hangul_type
         CodePoint.hangul_type(code_point)
       end
@@ -37,49 +56,42 @@ module TwitterCldr
 
       class << self
 
-        def for_hex(code_point)
-          code_point = code_point.rjust(4, '0').upcase
-
+        def find(code_point)
           target = get_block(code_point)
 
-          if target && target.first
-            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) }
-            CodePoint.new(*code_point_data) if code_point_data
-          else
-            nil
-          end
+          return unless target && target.first
+
+          block_data      = TwitterCldr.get_resource(:unicode_data, :blocks, target.first)
+          code_point_data = block_data.fetch(code_point) { |cp| get_range_start(cp, block_data) }
+
+          CodePoint.new(*code_point_data) if code_point_data
         end
 
-        def for_decomposition(code_points)
-          @decomposition_map ||= TwitterCldr.get_resource(:unicode_data, :decomposition_map)
-          key = code_points.join(" ").to_sym
+        def for_canonical_decomposition(code_points)
+          find(canonical_compositions[code_points]) if canonical_compositions.has_key?(code_points)
+        end
 
-          if @decomposition_map.include?(key)
-            for_hex(@decomposition_map[key])
-          else
-            nil
-          end
+        def canonical_compositions
+          @canonical_compositions ||= TwitterCldr.get_resource(:unicode_data, :canonical_compositions)
         end
 
         def hangul_type(code_point)
-          if code_point
-            code_point_int = code_point.hex
-            [:lparts, :vparts, :tparts, :compositions].each do |type|
-              hangul_blocks[type].each do |range|
-                return type if range.include?(code_point_int)
-              end
+          return unless code_point
+
+          [:lparts, :vparts, :tparts, :compositions].each do |type|
+            hangul_blocks[type].each do |range|
+              return type if range.include?(code_point)
             end
           end
+
           nil
         end
 
         def excluded_from_composition?(code_point)
-          code_point_int = code_point.hex
-          composition_exclusions.any? { |excl| excl.include?(code_point_int) }
+          composition_exclusions.any? { |exclusion| exclusion.include?(code_point) }
         end
 
-        protected
+        private
 
         def hangul_blocks
           @hangul_blocks ||= TwitterCldr.get_resource(:unicode_data, :hangul_blocks)
@@ -90,23 +102,22 @@ module TwitterCldr
         end
 
         def get_block(code_point)
-          blocks = TwitterCldr.get_resource(:unicode_data, :blocks)
-          code_point_int = code_point.hex
+          blocks.detect { |_, range|  range.include?(code_point) }
+        end
 
-          # Find the target block
-          blocks.find do |block_name, range|
-            range.include?(code_point_int)
-          end
+        def blocks
+          TwitterCldr.get_resource(:unicode_data, :blocks)
         end
 
         # 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.hex }.first
-          start_data = block_data[start_code_point].clone
+          start_data = block_data[block_data.keys.min]
+
           if start_data[1] =~ /<.*, First>/
-            start_data[0] = code_point.to_s
+            start_data = start_data.clone
+            start_data[0] = code_point
             start_data[1] = start_data[1].sub(', First', '')
             start_data
           end

data/lib/twitter_cldr/shared/currencies.rb

@@ -7,36 +7,33 @@ module TwitterCldr
   module Shared
     module Currencies
 
-      @@resource = TwitterCldr.get_resource(:shared, :currencies)[:shared][:currencies]
-
       class << self
 
         def countries
-          @@resource.map { |country_name, data| country_name.to_s }
+          resource.keys.map(&:to_s)
         end
 
         def currency_codes
-          @@resource.map { |country_name, data| data[:code] }
+          resource.values.map { |data| data[:code] }
         end
 
         def for_country(country_name)
-          @@resource[country_name.to_sym]
+          resource[country_name.to_sym]
         end
 
         def for_code(currency_code)
-          final = nil
-          @@resource.each_pair do |country_name, data|
-            if data[:code] == currency_code
-              final = data.merge({ :country => country_name.to_s })
-              final.delete(:code)
-              break
-            end
-          end
-          final
+          country_name, data = resource.detect { |_, data| data[:code] == currency_code }
+          { :country => country_name.to_s, :currency => data[:currency], :symbol => data[:symbol] } if data
+        end
+
+        private
+
+        def resource
+          @resource ||= TwitterCldr.get_resource(:shared, :currencies)
         end
 
       end
 
     end
   end
-end
+end

data/lib/twitter_cldr/shared/phone_codes.rb

@@ -0,0 +1,30 @@
+# encoding: UTF-8
+
+# Copyright 2012 Twitter, Inc
+# http://www.apache.org/licenses/LICENSE-2.0
+
+module TwitterCldr
+  module Shared
+    module PhoneCodes
+
+      class << self
+
+        def territories
+          resource.keys
+        end
+
+        def code_for_territory(territory)
+          resource[territory.to_s.downcase.to_sym]
+        end
+
+        private
+
+        def resource
+          @resource ||= TwitterCldr.get_resource(:shared, :phone_codes)
+        end
+
+      end
+
+    end
+  end
+end

data/lib/twitter_cldr/shared/postal_codes.rb

@@ -0,0 +1,35 @@
+# encoding: UTF-8
+
+# Copyright 2012 Twitter, Inc
+# http://www.apache.org/licenses/LICENSE-2.0
+
+module TwitterCldr
+  module Shared
+    module PostalCodes
+
+      class << self
+
+        def territories
+          resource.keys
+        end
+
+        def regex_for_territory(territory)
+          resource[territory.to_s.downcase.to_sym]
+        end
+
+        def valid?(territory, postal_code)
+          regexp = regex_for_territory(territory)
+          !!(regexp && regexp =~ postal_code)
+        end
+
+        private
+
+        def resource
+          @resource ||= TwitterCldr.get_resource(:shared, :postal_codes)
+        end
+
+      end
+
+    end
+  end
+end

data/lib/twitter_cldr/tokenizers/calendars/timespan_tokenizer.rb

@@ -6,17 +6,21 @@
 module TwitterCldr
   module Tokenizers
     class TimespanTokenizer < Base
+
       VALID_UNITS = [:second, :minute, :hour, :day, :week, :month, :year]
 
       def initialize(options = {})
         super(options)
 
         @token_splitter_regex = /([^0*#,\.]*)([0#,\.]+)([^0*#,\.]*)$/ # creates spaces
-        @token_type_regexes   = [
+
+        @token_type_regexes = [
             { :type => :pattern, :regex => /[0?#,\.]*/ }, # splits token at right places
             { :type => :plaintext, :regex => // }
         ]
+
         @base_path = [:units]
+
         @paths = {
             :ago => {
                 :default => :'hour-past',
@@ -64,13 +68,13 @@ module TwitterCldr
             pluralization = 2 if token_exists(path + [2])
         end
         path << pluralization
+
         tokens_with_placeholders_for(path) if token_exists(path)
       end
 
       def token_exists(path)
-        @@token_cache ||= {}
         cache_key = compute_cache_key(@locale, path.join('.'))
-        true if @@token_cache.include?(cache_key) || traverse(path)
+        token_cache.include?(cache_key) || !!traverse(path)
       end
 
       def all_types_for(unit, direction)
@@ -79,6 +83,10 @@ module TwitterCldr
 
       protected
 
+      def token_cache
+        @token_cache ||= {}
+      end
+
       def full_path(direction, unit, type)
         @base_path + [@paths[direction][unit], type]
       end

data/lib/twitter_cldr/tokenizers/numbers/number_tokenizer.rb

@@ -6,6 +6,8 @@
 module TwitterCldr
   module Tokenizers
     class NumberTokenizer < Base
+      VALID_TYPES = [:decimal, :percent, :currency]
+
       def initialize(options = {})
         super(options)
 
@@ -32,7 +34,12 @@ module TwitterCldr
 
           insert_point = traverse(key_path[0..-2])
           insert_point[:positive] = positive
-          insert_point[:negative] = negative ? negative : "#{symbols[:minus] || '-'}#{positive}"
+
+          if negative
+            insert_point[:negative] = "#{symbols[:minus] || '-'}#{negative}"
+          else
+            insert_point[:negative] = "#{symbols[:minus] || '-'}#{positive}"
+          end
         end
 
         sign = options[:sign] || :positive

data/lib/twitter_cldr/utils/code_points.rb

@@ -10,11 +10,11 @@ module TwitterCldr
       class << self
 
         def to_char(code_point)
-          [code_point.hex].pack('U*')
+          [code_point].pack('U*')
         end
 
         def from_char(char)
-          char.unpack('U*').first.to_s(16).upcase.rjust(4, '0')
+          char.unpack('U*').first
         end
 
         def from_chars(chars)

data/lib/twitter_cldr/version.rb

@@ -4,5 +4,5 @@
 # http://www.apache.org/licenses/LICENSE-2.0
 
 module TwitterCldr
-  VERSION = "1.6.2"
+  VERSION = "1.7.0"
 end

data/resources/collation/tailoring/af.yml

@@ -1,4 +1,4 @@
 ---
-collator_options: {}
-tailored_table: 0149; [41, 5, 10]
-suppressed_contractions: ''
+:collator_options: {}
+:tailored_table: 0149; [41, 5, 10]
+:suppressed_contractions: ''

data/resources/collation/tailoring/ar.yml

@@ -1,6 +1,6 @@
 ---
-collator_options: {}
-tailored_table: 0629; [6144, 87, 5]
+:collator_options: {}
+:tailored_table: 0629; [6144, 87, 5]
 
   FE94; [6144, 87, 6]
 
@@ -19,4 +19,4 @@ tailored_table: 0629; [6144, 87, 5]
   FC90; [6287, 87, A]
 
   FC5D; [6287, 87, B]
-suppressed_contractions: ''
+:suppressed_contractions: ''

data/resources/collation/tailoring/ca.yml

@@ -1,10 +1,10 @@
 ---
-collator_options: {}
-tailored_table: 0140; [3D, 87, 5]
+:collator_options: {}
+:tailored_table: 0140; [3D, 87, 5]
 
   006C 00B7; [3D, 87, 5]
 
   013F; [3D, 87, 86]
 
   004C 00B7; [3D, 87, 86]
-suppressed_contractions: ''
+:suppressed_contractions: ''

data/resources/collation/tailoring/cs.yml

@@ -1,6 +1,6 @@
 ---
-collator_options: {}
-tailored_table: 0063 030C; [2C04, 5, 5]
+:collator_options: {}
+:tailored_table: 0063 030C; [2C04, 5, 5]
 
   0043 030C; [2C04, 5, 86]
 
@@ -23,4 +23,4 @@ tailored_table: 0063 030C; [2C04, 5, 5]
   007A 030C; [5A04, 5, 5]
 
   005A 030C; [5A04, 5, 86]
-suppressed_contractions: ''
+:suppressed_contractions: ''

data/resources/collation/tailoring/da.yml

@@ -1,7 +1,7 @@
 ---
-collator_options:
-  case_first: :upper
-tailored_table: 0111; [2D, 87, 5]
+:collator_options:
+  :case_first: :upper
+:tailored_table: 0111; [2D, 87, 5]
 
   0110; [2D, 87, 86]
 
@@ -58,4 +58,4 @@ tailored_table: 0111; [2D, 87, 5]
   0041 0061; [5AA1, 5, 48][6, 0, C0]
 
   0041 0041; [5AA1, 5, 89][6, 0, C0]
-suppressed_contractions: ''
+:suppressed_contractions: ''

data/resources/collation/tailoring/de.yml

@@ -1,4 +1,4 @@
 ---
-collator_options: {}
-tailored_table: ''
-suppressed_contractions: ''
+:collator_options: {}
+:tailored_table: ''
+:suppressed_contractions: ''

data/resources/collation/tailoring/el.yml

@@ -1,4 +1,4 @@
 ---
-collator_options: {}
-tailored_table: ''
-suppressed_contractions: ''
+:collator_options: {}
+:tailored_table: ''
+:suppressed_contractions: ''

data/resources/collation/tailoring/en.yml

@@ -1,4 +1,4 @@
 ---
-collator_options: {}
-tailored_table: ''
-suppressed_contractions: ''
+:collator_options: {}
+:tailored_table: ''
+:suppressed_contractions: ''

data/resources/collation/tailoring/es.yml

@@ -1,6 +1,6 @@
 ---
-collator_options: {}
-tailored_table: 006E 0303; [4204, 5, 5]
+:collator_options: {}
+:tailored_table: 006E 0303; [4204, 5, 5]
 
   004E 0303; [4204, 5, 86]
-suppressed_contractions: ''
+:suppressed_contractions: ''