twitter_cldr 3.0.4 → 3.0.5

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    ODMyYmYzMDM4ODg4NjY1OTIzOGMxNDY1MTRkNWI5YzU2Njg4ZDI1Yg==
+    ZDU2MmRkOWM4ZGYzOWVhM2E1M2ZmNWE3ZGMwYWNmOGVjYTY2ZGQ1Yw==
   data.tar.gz: !binary |-
-    N2YxZWZlMDNhZDRjODI3NGU1OGZlZWVhZjNhMDk0NzBhYjQ3ZGU5Mg==
+    ZDZkNWRmOGMyMTliZmI2ODMzZGYxMzIyNTNjMGRiNTFjOGZlYzYwMg==
 SHA512:
   metadata.gz: !binary |-
-    OGE2MTZmYTZhYTg2ZDBiZjA5MDk0YWQ1YTRlZjEzYjA5MzQ1ZDI2Y2IxYzg5
-    MjlhYjdhYmVkMzUyN2M4ZmU2NTljNzQ1YTUwZWIyNzFjYTYyODk1ZDdiZDA3
-    NzY4ZGJlNDIxOTdkYjhlMjRiMzNkYmQ5Njg0NDcxZjAzY2RiYjU=
+    ZDY2OTYwMjIxZDMxZTk0OTJhMDJmNjI2OGEzNjI2YTIwYTc2MDc4YWYxMzkz
+    NDI3YzBhMTE2YWZjODJkYTZlNWJiNDU2ZWEyMGYyMmEzNjY5ODM0YmM4YTll
+    NjQyNzIzMzJkN2EyODlkZThlNjFmNzA2Mzg2MGMzZWJlZDNmZWI=
   data.tar.gz: !binary |-
-    ODM4YjY1MmI1MzQ2MWRmZTZkYjIyYTk1MTU0NmU4ODNhNDAyZTRjMzJiY2Yw
-    MDM3NGUwNmNiODY4NGIwNjA1YmRhOGQ4YzNiZjE2YzU5OGE0NGE2NDlmMGIy
-    NmI3NGZiMTM5ODk0YWI5YThhZDBiYWM3NzBmODhmYTBkNzk5MjE=
+    OGQzNDRjYjQ0NjhjM2Q5MGJlZTQ0NmI3YWQ2YWZiMWVmY2IzNjgyN2Y2ZDli
+    ZjRjYTBlY2M5ZTdlNDc3YWYyZWI4NTdjZTE2NjA1ODA3N2QwNjMyZjQ1Nzkw
+    NjViNzc2OTkzNmI4OGI2YTY0MGI0YzIwMmQ3Yzk1YmY3OGVkNGQ=

data/History.txt

@@ -1,3 +1,8 @@
+== 3.0.5
+
+* Fixed short numbers formatting for ru and other locales that use patterns
+  with literal periods.
+
 == 3.0.4
 
 * Fixed short numbers formatting for ja, ko, af, and a few other locales.

data/lib/twitter_cldr/formatters/numbers/rbnf.rb

@@ -100,7 +100,6 @@ module TwitterCldr
         def rule_set_from_resource(rule_set_data)
           RuleSet.new(
             rule_set_data[:rules].map do |rule|
-              binding.pry unless rule[:rule].is_a?(String)
               Rule.new(rule[:value], rule[:rule], rule[:radix])
             end,
             rule_set_data[:type],

data/lib/twitter_cldr/resources/unicode_data_importer.rb

@@ -4,7 +4,6 @@
 # http://www.apache.org/licenses/LICENSE-2.0
 
 require 'twitter_cldr/resources/download'
-require 'pry-nav'
 
 module TwitterCldr
   module Resources

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

@@ -7,6 +7,22 @@ module TwitterCldr
   module Tokenizers
     class NumberTokenizer
 
+      SPECIAL_SYMBOLS_MAP = {
+        '.' => '{DOT}',
+        ',' => '{COMMA}',
+        '0' => '{ZERO}',
+        '#' => '{POUND}',
+        '¤' => '{CURRENCY}',
+        '%' => '{PERCENT}',
+        'E' => '{SCIENTIFIC}'
+      }
+
+      SPECIAL_SYMBOLS_REGEX = /'(?:#{SPECIAL_SYMBOLS_MAP.keys.map { |s| Regexp.escape(s) }.join('|')})'/
+
+      INVERSE_SPECIAL_SYMBOLS_MAP = SPECIAL_SYMBOLS_MAP.invert
+
+      INVERSE_SPECIAL_SYMBOLS_REGEX = /#{INVERSE_SPECIAL_SYMBOLS_MAP.keys.map { |s| Regexp.escape(s) }.join('|')}/
+
       attr_reader :data_reader
 
       def initialize(data_reader)
@@ -14,7 +30,17 @@ module TwitterCldr
       end
 
       def tokenize(pattern)
-        tokens = PatternTokenizer.new(data_reader, tokenizer).tokenize(pattern)
+        escaped_pattern = pattern.gsub(SPECIAL_SYMBOLS_REGEX) do |match|
+          SPECIAL_SYMBOLS_MAP[match[1..-2]]
+        end
+
+        tokens = PatternTokenizer.new(data_reader, tokenizer).tokenize(escaped_pattern)
+
+        tokens.each do |token|
+          token.value = token.value.gsub(INVERSE_SPECIAL_SYMBOLS_REGEX) do |match|
+            INVERSE_SPECIAL_SYMBOLS_MAP[match]
+          end
+        end
 
         if tokens.first.value == ""
           tokens[1..-1]

data/lib/twitter_cldr/tokenizers/token.rb

@@ -14,12 +14,17 @@ module TwitterCldr
         end
       end
 
+      def to_hash
+        { :value => @value, :type => @type }
+      end
+
       def to_s
         @value
       end
 
-      def to_hash
-        { :value => @value, :type => @type }
+      # overriding `to_s` also overrides `inspect`, so we have to redefine it manually
+      def inspect
+        "<#{self.class}: #{instance_variables.map {|v| "#{v}=#{instance_variable_get(v).inspect}" }.join(", ")}>"
       end
     end
   end

data/lib/twitter_cldr/version.rb

@@ -4,5 +4,5 @@
 # http://www.apache.org/licenses/LICENSE-2.0
 
 module TwitterCldr
-  VERSION = "3.0.4"
+  VERSION = "3.0.5"
 end

data/spec/formatters/numbers/abbreviated/short_decimal_formatter_spec.rb

@@ -67,4 +67,13 @@ describe ShortDecimalFormatter do
       expect(format_number(number)).to match_normalized("9300万")
     end
   end
+
+  context "with Russian locale" do
+    let(:locale) { :ru }
+
+    it "formats a number with a literal period" do
+      number = 1_000
+      expect(format_number(number)).to match_normalized("1 тыс.")
+    end
+  end
 end

data/spec/tokenizers/numbers/number_tokenizer_spec.rb

@@ -31,6 +31,22 @@ describe NumberTokenizer do
       check_token_list(got, expected)
     end
 
+    it "gets tokens for an abbreviated number pattern with a literal period (e.g., for Russian)" do
+      data_reader = TwitterCldr::DataReaders::NumberDataReader.new(:ru, :type => :short_decimal)
+      pattern = data_reader.pattern(1_000)
+
+      expect(pattern).to include("тыс'.'") # ensure that we test with the data we expect
+
+      got = data_reader.tokenizer.tokenize(pattern)
+
+      expected = [
+        { :value => "", :type => :plaintext },
+        { :value => "0", :type => :pattern },
+        { :value => " тыс.", :type => :plaintext }
+      ]
+      check_token_list(got, expected)
+    end
+
     it "correctly parses suffixes (i.e. Russian currency)" do
       data_reader = TwitterCldr::DataReaders::NumberDataReader.new(:ru, :type => :currency)
       got = data_reader.tokenizer.tokenize(data_reader.pattern(number))

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: twitter_cldr
 version: !ruby/object:Gem::Version
-  version: 3.0.4
+  version: 3.0.5
 platform: ruby
 authors:
 - Cameron Dutro
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-07-28 00:00:00.000000000 Z
+date: 2014-07-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: json