twitter_cldr 6.5.0 → 6.7.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 837a383731a20ebacea14090a6189664506b5c76dd3da585e69566d314f17821
-  data.tar.gz: 17f2ef911ce4d96d87427cf8c9cf44d4c1c408eef150cb0bb893880575e9350b
+  metadata.gz: 58f751fe828d7674c9a144e80da29cfed3af2d3ede52b7328de26fedaa646a36
+  data.tar.gz: 6e0c9ba2a2a29be9ce172c606e25e3e3051c06cacc1f66c5d63eda5894ac25e3
 SHA512:
-  metadata.gz: ef45245e3218fedfc48185bb5495545049aa1774bf5ae68f2482433ba5411bc3d0a50734a8fafb964a289696f3fb2517aefd1dcd0eca873f3677181dfc6cace3
-  data.tar.gz: 3a448cc613123e355db6f218b06850ee599868f612e2a9e99ccc39668d45446d14a399660e8ab928f41c76c37a0a63112e182cc294e7e647c525e99116aa921a
+  metadata.gz: bf3fa11fb250fc73d1850732e058778c8afe8869e67135e1b44651543a20a3359e2d7dc76d7c20d115eb4cbd0ec30d7424dc4ba445f632b095b01a2e448d68d2
+  data.tar.gz: 49fe9d60d75ef8011104ff274ec9b6a2289bff5778418c7a2472a9487f6891e265237f9f1e80366b87bc0233339acd0de3f294e453ebeb3bf0b31f1e4539a293

data/Gemfile

@@ -4,7 +4,7 @@ gemspec
 
 group :development, :test do
   gem 'rake'
-  gem 'pry-nav'
+  gem 'pry-byebug' unless RUBY_PLATFORM == 'java'
   gem 'ruby-prof' unless RUBY_PLATFORM == 'java'
   gem 'regexp_parser', '~> 0.5'
   gem 'benchmark-ips'
@@ -13,7 +13,7 @@ group :development, :test do
   # gemspec allows any version, but most people are probably using 1.x, so
   # let's test and develop against that
   gem 'tzinfo', '< 2'
-  gem 'tzinfo-data', '= 1.2020.4'  # keep in sync with ICU
+  gem 'tzinfo-data', '= 1.2021.1'  # keep in sync with ICU
 end
 
 group :development do

data/README.md

@@ -1,4 +1,4 @@
-## twitter-cldr-rb [![Build Status](https://secure.travis-ci.org/twitter/twitter-cldr-rb.png?branch=master)](http://travis-ci.org/twitter/twitter-cldr-rb) [![Code Climate](https://codeclimate.com/github/twitter/twitter-cldr-rb.png)](https://codeclimate.com/github/twitter/twitter-cldr-rb) [![Coverage Status](https://coveralls.io/repos/twitter/twitter-cldr-rb/badge.png?branch=master)](https://coveralls.io/r/twitter/twitter-cldr-rb?branch=master)
+## twitter-cldr-rb ![Unit Tests](https://github.com/camertron/rux/actions/workflows/unit_tests.yml/badge.svg?branch=master) [![Code Climate](https://codeclimate.com/github/twitter/twitter-cldr-rb.png)](https://codeclimate.com/github/twitter/twitter-cldr-rb) [![Coverage Status](https://coveralls.io/repos/twitter/twitter-cldr-rb/badge.png?branch=master)](https://coveralls.io/r/twitter/twitter-cldr-rb?branch=master)
 
 TwitterCldr uses Unicode's Common Locale Data Repository (CLDR) to format certain types of text into their
 localized equivalents.  Currently supported types of text include dates, times, currencies, decimals, percentages, and symbols.
@@ -558,20 +558,20 @@ The CLDR contains postal code validation regexes for a number of countries.
 
 ```ruby
 # United States
-postal_code = TwitterCldr::Shared::PostalCodes.for_territory(:us) 
+postal_code = TwitterCldr::Shared::PostalCodes.for_territory(:us)
 postal_code.valid?("94103")     # true
 postal_code.valid?("9410")      # false
 
 # England (Great Britain)
-postal_code = TwitterCldr::Shared::PostalCodes.for_territory(:gb) 
+postal_code = TwitterCldr::Shared::PostalCodes.for_territory(:gb)
 postal_code.valid?("BS98 1TL")  # true
 
 # Sweden
-postal_code = TwitterCldr::Shared::PostalCodes.for_territory(:se) 
+postal_code = TwitterCldr::Shared::PostalCodes.for_territory(:se)
 postal_code.valid?("280 12")    # true
 
 # Canada
-postal_code = TwitterCldr::Shared::PostalCodes.for_territory(:ca) 
+postal_code = TwitterCldr::Shared::PostalCodes.for_territory(:ca)
 postal_code.valid?("V3H 1Z7")   # true
 ```
 
@@ -579,7 +579,7 @@ Match all valid postal codes in a string with the `#find_all` method:
 
 ```ruby
 # United States
-postal_code = TwitterCldr::Shared::PostalCodes.for_territory(:us) 
+postal_code = TwitterCldr::Shared::PostalCodes.for_territory(:us)
 postal_code.find_all("12345 23456")    # ["12345", "23456"]
 ```
 
@@ -592,7 +592,7 @@ TwitterCldr::Shared::PostalCodes.territories  # [:ac, :ad, :af, :ai, :al, ... ]
 Just want the regex?  No problem:
 
 ```ruby
-postal_code = TwitterCldr::Shared::PostalCodes.for_territory(:us) 
+postal_code = TwitterCldr::Shared::PostalCodes.for_territory(:us)
 postal_code.regexp  # /(\d{5})(?:[ \-](\d{4}))?/
 ```
 
@@ -1014,17 +1014,17 @@ The Psych gem that is the default YAML engine in Ruby 1.9 doesn't handle Unicode
 You can make use of TwitterCLDR's YAML dumper by calling `localize` and then `to_yaml` on an `Array`, `Hash`, or `String`:
 
 ```ruby
-{ :hello => "world" }.localize.to_yaml 
-["hello", "world"].localize.to_yaml 
-"hello, world".localize.to_yaml 
+{ :hello => "world" }.localize.to_yaml
+["hello", "world"].localize.to_yaml
+"hello, world".localize.to_yaml
 ```
 
 Behind the scenes, these convenience methods are using the `TwitterCldr::Shared::YAML` class.  You can do the same thing if you're feeling adventurous:
 
 ```ruby
-TwitterCldr::Shared::YAML.dump({ :hello => "world" }) 
-TwitterCldr::Shared::YAML.dump(["hello", "world"]) 
-TwitterCldr::Shared::YAML.dump("hello, world") 
+TwitterCldr::Shared::YAML.dump({ :hello => "world" })
+TwitterCldr::Shared::YAML.dump(["hello", "world"])
+TwitterCldr::Shared::YAML.dump("hello, world")
 ```
 
 ## Adding New Locales

data/Rakefile

@@ -13,7 +13,7 @@ require 'rubygems/package_task'
 
 require './lib/twitter_cldr'
 
-require 'pry-nav'
+require 'pry-byebug' unless RUBY_PLATFORM == 'java'
 
 Bundler::GemHelper.install_tasks
 
@@ -89,6 +89,11 @@ namespace :update do
     TwitterCldr::Resources::NumberFormatsImporter.new.import
   end
 
+  desc 'Import list formats'
+  task :list_formats do
+    TwitterCldr::Resources::ListFormatsImporter.new.import
+  end
+
   desc 'Import currency symbols'
   task :currency_symbols do
     TwitterCldr::Resources::CurrencySymbolsImporter.new.import
@@ -136,6 +141,11 @@ namespace :update do
     TwitterCldr::Resources::UnicodePropertyAliasesImporter.new.import
   end
 
+  desc 'Import unit data'
+  task :units do
+    TwitterCldr::Resources::UnitsImporter.new.import
+  end
+
   desc 'Generate the casefolder class. Depends on unicode data'
   task :casefolder do
     TwitterCldr::Resources::CasefolderClassGenerator.new.import

data/lib/twitter_cldr/core_ext.rb

@@ -1,9 +1,10 @@
 # encoding: UTF-8
+require "bigdecimal"
 
 # Copyright 2012 Twitter, Inc
 # http://www.apache.org/licenses/LICENSE-2.0
 
-[Integer, Float].each do |klass|
+[Integer, Float, BigDecimal].each do |klass|
   TwitterCldr::Localized::LocalizedNumber.localize(klass)
 end
 

data/lib/twitter_cldr/formatters/list_formatter.rb

@@ -62,7 +62,13 @@ module TwitterCldr
       end
 
       def resource_for_type(type)
-        resource[type]
+        loop do
+          if resource[type].is_a?(Symbol)
+            type = resource[:type].to_s.split('.').last
+          else
+            break resource[type]
+          end
+        end
       end
 
       def resource

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

@@ -69,24 +69,35 @@ module TwitterCldr
         precision = options[:precision] || precision_from(number)
         rounding = options[:rounding] || 0
 
-        number = "%.#{precision}f" % round_to(number, precision, rounding).abs
+        if number.is_a? BigDecimal
+          number = precision == 0 ?
+            round_to(number, precision, rounding).abs.fix.to_s("F") :
+            round_to(number, precision, rounding).abs.round(precision).to_s("F")
+        else
+          number = "%.#{precision}f" % round_to(number, precision, rounding).abs
+        end
         number.split(".")
       end
 
       def round_to(number, precision, rounding = 0)
         factor = 10 ** precision
-        result = (number * factor).round.to_f / factor
+        result = number.is_a?(BigDecimal) ?
+          ((number * factor).fix / factor) :
+          ((number * factor).round.to_f / factor)
 
         if rounding > 0
           rounding = rounding.to_f / factor
-          result = (result *  (1.0 / rounding)).round.to_f / (1.0 / rounding)
+          result = number.is_a?(BigDecimal) ?
+            ((result *  (1.0 / rounding)).fix / (1.0 / rounding)) :
+            ((result *  (1.0 / rounding)).round.to_f / (1.0 / rounding))
         end
 
         result
       end
 
       def precision_from(num)
-        parts = num.to_s.split(".")
+        return 0 if num.is_a?(BigDecimal) && num.fix == num
+        parts = (num.is_a?(BigDecimal) ? num.to_s("F") : num.to_s ).split(".")
         parts.size == 2 ? parts[1].size : 0
       end
 

data/lib/twitter_cldr/resources.rb

@@ -17,6 +17,7 @@ module TwitterCldr
     autoload :Importer,                       'twitter_cldr/resources/importer'
     autoload :ImportResolver,                 'twitter_cldr/resources/import_resolver'
     autoload :LanguageCodesImporter,          'twitter_cldr/resources/language_codes_importer'
+    autoload :ListFormatsImporter,            'twitter_cldr/resources/list_formats_importer'
     autoload :Loader,                         'twitter_cldr/resources/loader'
     autoload :LocalesResourcesImporter,       'twitter_cldr/resources/locales_resources_importer'
     autoload :NumberFormatsImporter,          'twitter_cldr/resources/number_formats_importer'
@@ -40,6 +41,7 @@ module TwitterCldr
     autoload :UnicodeDataImporter,            'twitter_cldr/resources/unicode_data_importer'
     autoload :UnicodeFileParser,              'twitter_cldr/resources/unicode_file_parser'
     autoload :UnicodePropertyAliasesImporter, 'twitter_cldr/resources/unicode_property_aliases_importer'
+    autoload :UnitsImporter,                  'twitter_cldr/resources/units_importer'
     autoload :ValidityDataImporter,           'twitter_cldr/resources/validity_data_importer'
 
     class << self
@@ -58,6 +60,7 @@ module TwitterCldr
           DayPeriodRulesImporter,
           HyphenationImporter,
           LanguageCodesImporter,
+          ListFormatsImporter,
           LocalesResourcesImporter,
           NumberFormatsImporter,
           ParentLocalesImporter,
@@ -75,6 +78,7 @@ module TwitterCldr
           TransformsImporter,
           UnicodeDataImporter,
           UnicodePropertyAliasesImporter,
+          UnitsImporter,
           ValidityDataImporter,
         ]
       end

data/lib/twitter_cldr/resources/list_formats_importer.rb

@@ -0,0 +1,140 @@
+# encoding: UTF-8
+
+# Copyright 2012 Twitter, Inc
+# http://www.apache.org/licenses/LICENSE-2.0
+
+require 'nokogiri'
+require 'parallel'
+require 'etc'
+require 'set'
+
+module TwitterCldr
+  module Resources
+
+    class ListFormatsImporter < Importer
+
+      requirement :cldr, Versions.cldr_version
+      output_path 'locales'
+      locales TwitterCldr.supported_locales
+      ruby_engine :mri
+
+      private
+
+      def execute
+        locales = Set.new
+
+        finish = -> (locale, *) do
+          locales.add(locale)
+          STDOUT.write "\rImported #{locale}, #{locales.size} of #{params[:locales].size} total"
+        end
+
+        Parallel.each(params[:locales], in_processes: Etc.nprocessors, finish: finish) do |locale|
+          import_locale(locale)
+          locales << locale
+        end
+
+        puts
+      end
+
+      def import_locale(locale)
+        # The merging that happens here works at the listPatternPart level of granularity.
+        # In other words, a missing part will be filled in by any part with the same key
+        # in the locale's ancestor chain. The raw CLDR data contains the inheritance marker
+        # (i.e. "↑↑↑") for listPatterns that are missing parts, but the expanded data we
+        # get in the downloadable CLDR zip file doesn't include them or the inherited data,
+        # making it impossible for TwitterCLDR to know how it should handle missing keys.
+        # I believe whatever massage tool the CLDR maintainers use to generate the final
+        # data set doesn't take aliases into account, which explains the holes in the data.
+        # By allowing individual listPatternParts to be populated by data from ancestor
+        # locales, we fill in any missing parts at the minor risk of being slightly wrong
+        # when formatting lists. In my opinion, it's far better to produce a slightly wrong
+        # string than to error or produce an entirely empty string.
+        data = requirements[:cldr].merge_each_ancestor(locale) do |ancestor_locale|
+          ListFormats.new(ancestor_locale, requirements[:cldr]).to_h
+        end
+
+        output_file = File.join(output_path, locale.to_s, 'lists.yml')
+
+        File.open(output_file, 'w:utf-8') do |output|
+          output.write(
+            TwitterCldr::Utils::YAML.dump(
+              TwitterCldr::Utils.deep_symbolize_keys(locale => data),
+              use_natural_symbols: true
+            )
+          )
+        end
+      end
+
+      def output_path
+        params.fetch(:output_path)
+      end
+
+    end
+
+
+    class ListFormats
+
+      attr_reader :locale, :cldr_req
+
+      def initialize(locale, cldr_req)
+        @locale = locale
+        @cldr_req = cldr_req
+      end
+
+      def to_h
+        { lists: lists }
+      end
+
+      def lists
+        doc.xpath('//ldml/listPatterns/listPattern').each_with_object({}) do |pattern_node, pattern_result|
+          pattern_type = if attribute = pattern_node.attribute('type')
+            attribute.value.to_sym
+          else
+            :default
+          end
+
+          pattern_node = pattern_for(pattern_type)
+
+          pattern_result[pattern_type] = pattern_node.xpath('listPatternPart').each_with_object({}) do |type_node, type_result|
+            type_result[type_node.attribute('type').value.to_sym] = type_node.content
+          end
+        end
+      end
+
+      def pattern_for(type)
+        xpath = xpath_for(type)
+        pattern_node = doc.xpath(xpath)[0]
+        alias_node = pattern_node.xpath('alias')[0]
+
+        if alias_node
+          alias_type = alias_node.attribute('path').value[/@type='([\w-]+)'/, 1] || :default
+          # follow aliases so we can fully expand them
+          pattern_node = pattern_for(alias_type)
+        end
+
+        pattern_node
+      end
+
+      def xpath_for(type)
+        if type == :default
+          '//ldml/listPatterns/listPattern[not(@type)]'
+        else
+          "//ldml/listPatterns/listPattern[@type='#{type}']"
+        end
+      end
+
+      def doc
+        @doc ||= begin
+          locale_fs = locale.to_s.gsub('-', '_')
+          Nokogiri.XML(File.read(File.join(cldr_main_path, "#{locale_fs}.xml")))
+        end
+      end
+
+      def cldr_main_path
+        @cldr_main_path ||= File.join(cldr_req.common_path, 'main')
+      end
+
+    end
+
+  end
+end