twitter_cldr 6.9.0 → 6.11.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c8aceda15c987295a62672bd4f7a78546b34eed2a83eb9178b58bd5a5efa49be
-  data.tar.gz: b179d63e855785bdd871b12dda0f7c0ecd67b91106510972d89f74ab93b8ec5d
+  metadata.gz: cbd2915afa874b800c57f2d808dfcf03218625b27c23ff6be37bf666cc9f6164
+  data.tar.gz: 32f81597c78d310f3030924001870e38137e7b0c4ab011c496167c2f0f3b8af1
 SHA512:
-  metadata.gz: 92f18ec12c13f8ed66b23a9453c9b932e502738266957b326a62493ef1062878ae29932d16f4963658f0b30591528de8415293f1e1c90e394a3e2b4fba2b1244
-  data.tar.gz: b34f99bbb5e5e37d3c95d63ce56d47c097d2aac14730ed56d72fc2f5e3c5a0db26b1ff0d20ea599a200d4e75bb3c38cd22ecf5321ece0a606967f0f49290738d
+  metadata.gz: df9df519e582bc1bfd6d3030fdb9a507c9e6aad2c3715434de1aa37c1f0ca3645d23945096264954b865b31a5500d13e578273d07d23415eabf382e591bdc583
+  data.tar.gz: 367934c47449765583e8b24778fb5c99b7cc88e215bd51de041899fb87cdf6f406ab156b7255581a69c6edf9bc17f9ebfb1c4be54875977fee1f9cdf88db9278

data/README.md

@@ -92,7 +92,7 @@ TwitterCLDR supports formatting numbers with an attached unit, for example "12 d
 
 ```ruby
 12.localize.to_unit.length_mile  # "12 miles"
-12.localize(:ru).to_unit.length_mile  # "12 миль"
+12.localize(:ru).to_unit.length_mile  # "12 милях"
 ```
 Units support a few different forms, long, short, and narrow:
 
@@ -177,8 +177,8 @@ For English (and other languages), you can also specify an ordinal spellout:
 ```ruby
 DateTime.now.localize(:es).to_full_s               # "viernes, 14 de febrero de 2014, 12:20:05 (tiempo universal coordinado)"
 DateTime.now.localize(:es).to_long_s               # "14 de febrero de 2014, 12:20:05 UTC"
-DateTime.now.localize(:es).to_medium_s             # "14 feb. 2014 12:20:05"
-DateTime.now.localize(:es).to_short_s              # "14/2/14 12:20"
+DateTime.now.localize(:es).to_medium_s             # "14 feb 2014, 12:20:05"
+DateTime.now.localize(:es).to_short_s              # "14/2/14, 12:20"
 
 Time.now.localize(:es).to_full_s                   # "12:20:05 (tiempo universal coordinado)"
 Time.now.localize(:es).to_long_s                   # "12:20:05 UTC"
@@ -187,7 +187,7 @@ Time.now.localize(:es).to_short_s                  # "12:20"
 
 DateTime.now.localize(:es).to_date.to_full_s       # "viernes, 14 de febrero de 2014"
 DateTime.now.localize(:es).to_date.to_long_s       # "14 de febrero de 2014"
-DateTime.now.localize(:es).to_date.to_medium_s     # "14 feb. 2014"
+DateTime.now.localize(:es).to_date.to_medium_s     # "14 feb 2014"
 DateTime.now.localize(:es).to_date.to_short_s      # "14/2/14"
 ```
 
@@ -239,6 +239,7 @@ It's important to know that, even though any given format may not be available a
 | GyMMM      | Feb 2014 CE            |
 | GyMMMEd    | Fri, Feb 14, 2014 CE   |
 | GyMMMd     | Feb 14, 2014 CE        |
+| GyMd       | 2/14/2014 Common Era   |
 | H          | 12                     |
 | Hm         | 12:20                  |
 | Hms        | 12:20:05               |
@@ -246,7 +247,7 @@ It's important to know that, even though any given format may not be available a
 | Hmv        | 12:20 GMT              |
 | M          | 2                      |
 | MEd        | Fri, 2/14              |
-| MMM        | Feb                    |
+| MMM        | M02                    |
 | MMMEd      | Fri, Feb 14            |
 | MMMMW      | week 3 of February     |
 | MMMMd      | February 14            |
@@ -366,6 +367,8 @@ tz.display_name_for(DateTime.new(2019, 11, 5), :generic_location)
 tz.display_name_for(DateTime.new(2019, 11, 5), :generic_long)
 ```
 
+`#display_name_for` also accepts arguments for resolving ambiguous times. See [TZInfo Documentation](https://www.rubydoc.info/gems/tzinfo/TZInfo/Timezone#period_for_local-instance_method) for more information.
+
 ### Calendar Data
 
 CLDR contains a trove of calendar data, much of which can be accessed. One example is names of months, days, years.
@@ -416,8 +419,8 @@ Behind the scenes, these convenience methods use the `TwitterCldr::Formatters::P
 TwitterCldr::Formatters::Plurals::Rules.all                # [:one, :other]
 
 # get all rules for a specific locale
-TwitterCldr::Formatters::Plurals::Rules.all_for(:es)       # [:one, :other]
-TwitterCldr::Formatters::Plurals::Rules.all_for(:ru)       # [:few, :many, :one, :other]
+TwitterCldr::Formatters::Plurals::Rules.all_for(:es)       # [:one, :many, :other]
+TwitterCldr::Formatters::Plurals::Rules.all_for(:ru)       # [:one, :few, :many, :other]
 
 # get the rule for a number in a specific locale
 TwitterCldr::Formatters::Plurals::Rules.rule_for(1, :ru)   # :one
@@ -498,21 +501,21 @@ In addition to translating language codes, TwitterCLDR provides access to the fu
 
 ```ruby
 # get all languages for the default locale
-TwitterCldr::Shared::Languages.all                                                  # { ... :vi => "Vietnamese", :"zh-Hant" => "Traditional Mandarin Chinese" ... }
+TwitterCldr::Shared::Languages.all                                                  # { ... :vi => "Vietnamese", :"zh-Hant" => "Traditional Chinese" ... }
 
 # get all languages for a specific locale
-TwitterCldr::Shared::Languages.all_for(:es)                                         # { ... :vi => "vietnamita", :"zh-Hant" => "chino mandarín tradicional" ... }
+TwitterCldr::Shared::Languages.all_for(:es)                                         # { ... :vi => "vietnamita", :"zh-Hant" => "chino tradicional" ... }
 
 # get a language by its code for the default locale
-TwitterCldr::Shared::Languages.from_code(:'zh-Hant')                                # "Traditional Mandarin Chinese"
+TwitterCldr::Shared::Languages.from_code(:'zh-Hant')                                # "Traditional Chinese"
 
 # get a language from its code for a specific locale
-TwitterCldr::Shared::Languages.from_code_for_locale(:'zh-Hant', :es)                # "chino mandarín tradicional"
+TwitterCldr::Shared::Languages.from_code_for_locale(:'zh-Hant', :es)                # "chino tradicional"
 
 # translate a language from one locale to another
 # signature: translate_language(lang, source_locale, destination_locale)
-TwitterCldr::Shared::Languages.translate_language("chino tradicional", :es, :en)    # "Traditional Mandarin Chinese"
-TwitterCldr::Shared::Languages.translate_language("Traditional Chinese", :en, :es)  # "chino mandarín tradicional"
+TwitterCldr::Shared::Languages.translate_language("chino tradicional", :es, :en)    # "Traditional Chinese"
+TwitterCldr::Shared::Languages.translate_language("Traditional Chinese", :en, :es)  # "chino tradicional"
 ```
 
 ### World Territories
@@ -558,20 +561,20 @@ 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 +582,7 @@ 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"]
 ```
 
@@ -592,14 +595,14 @@ 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}))?/
 ```
 
 Get a sample of valid postal codes with the `#sample` method:
 
 ```ruby
-postal_code.sample(5)  # ["29294", "22486-2369", "76632", "40800-9860", "06727-6194"]
+postal_code.sample(5)  # ["60668-3382", "36022", "22364-5670", "32142-1738", "32633-0502"]
 ```
 
 ### Phone Codes
@@ -1014,17 +1017,17 @@ 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
@@ -1070,7 +1073,7 @@ TwitterCldr.locale    # will return :ru
 
 ## Compatibility
 
-TwitterCLDR is fully compatible with Ruby 1.9.3, 2.0.0, 2.2.0.
+TwitterCLDR is fully compatible with Ruby 2.0, 2.1, 2.2, 2.3, 2.4, 2.5, 2.6, 2.7, 3.0.
 
 ## Requirements
 
@@ -1103,6 +1106,6 @@ TwitterCLDR currently supports localization of certain textual objects in JavaSc
 
 ## License
 
-Copyright 2019 Twitter, Inc.
+Copyright 2021 Twitter, Inc.
 
 Licensed under the Apache License, Version 2.0: http://www.apache.org/licenses/LICENSE-2.0

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

@@ -99,7 +99,7 @@ module TwitterCldr
             # the base value divided by the LCD.  Here we check to
             # see if that's an integer, and if not, how close it is
             # to being an integer.
-            temp_difference = numerator * BigDecimal.new(rules[i].base_value) % least_common_multiple
+            temp_difference = numerator * BigDecimal(rules[i].base_value) % least_common_multiple
 
             # normalize the result of the above calculation: we want
             # the numerator's distance from the CLOSEST multiple

data/lib/twitter_cldr/resources/calendars_importer.rb

@@ -36,11 +36,12 @@ module TwitterCldr
       end
 
       def import_locale(locale)
-        data = requirements[:cldr].merge_each_ancestor(locale) do |ancestor_locale|
+        data = requirements[:cldr].build_data(locale) do |ancestor_locale|
           GregorianCalendar.new(ancestor_locale, requirements[:cldr]).to_h
         end
 
         output_file = File.join(output_path, locale.to_s, 'calendars.yml')
+        FileUtils.mkdir_p(File.dirname(output_file))
 
         File.open(output_file, 'w:utf-8') do |output|
           output.write(
@@ -60,6 +61,8 @@ module TwitterCldr
 
 
     class GregorianCalendar
+      ERA_TAGS = ['eraNames', 'eraAbbr', 'eraNarrow'].freeze
+
       attr_reader :locale, :cldr_req
 
       def initialize(locale, cldr_req)
@@ -71,8 +74,8 @@ module TwitterCldr
         {
           calendars: {
             gregorian: {
-              months:   contexts('month'),
               days:     contexts('day'),
+              months:   contexts('month'),
               eras:     eras,
               quarters: contexts('quarter'),
               periods:  contexts('dayPeriod', group: "alt"),
@@ -91,42 +94,39 @@ module TwitterCldr
       private
 
       def calendar
-        @calendar ||= doc.xpath('//ldml/dates/calendars/calendar[@type="gregorian"]').first
+        @calendar ||= docset.xpath('//ldml/dates/calendars/calendar[@type="gregorian"]').first
       end
 
       def contexts(kind, options = {})
         return {} unless calendar
 
-        calendar.xpath("#{kind}s/#{kind}Context").each_with_object({}) do |node, result|
-          context = node.attribute('type').value.to_sym
+        dtd.find_attr("#{kind}Context", 'type').values.each_with_object({}) do |context, result|
+          node = calendar.xpath("#{kind}s/#{kind}Context[@type='#{context}']").first
+          next unless node
+
           result[context] = widths(node, kind, context, options)
         end
       end
 
       def widths(node, kind, context, options = {})
-        node.xpath("#{kind}Width").each_with_object({}) do |node, result|
-          width = node.attribute('type').value.to_sym
-          result[width] = elements(node, kind, context, width, options)
+        dtd.find_attr("#{kind}Width", 'type').values.each_with_object({}) do |width, result|
+          width_node = node.xpath("#{kind}Width[@type='#{width}']").first
+          next unless width_node
+
+          result[width] = elements(width_node, kind, context, width, options)
         end
       end
 
       def elements(node, kind, context, width, options = {})
-        aliased = node.xpath('alias').first
-
-        if aliased
-          alias_path = "#{node.path}/#{aliased.attribute('path').value}"
-          elements(doc.xpath(alias_path).first, kind, context, width, options)
-        else
-          node.xpath(kind).each_with_object({}) do |node, result|
-            key = node.attribute('type').value
-            key = key =~ /^\d*$/ ? key.to_i : key.to_sym
-
-            if options[:group] && found_group = node.attribute(options[:group])
-              result[found_group.value] ||= {}
-              result[found_group.value][key] = node.content
-            else
-              result[key] = node.content
-            end
+        node.xpath(kind).each_with_object({}) do |node, result|
+          key = node.attribute('type').value
+          key = key =~ /^\d*$/ ? key.to_i : key.to_sym
+
+          if options[:group] && found_group = node.attribute(options[:group])
+            result[found_group.value] ||= {}
+            result[found_group.value][key] = node.content
+          else
+            result[key] = node.content
           end
         end
       end
@@ -144,15 +144,14 @@ module TwitterCldr
       def eras
         return {} unless calendar
 
-        base_path = "#{calendar.path}/eras"
-        keys = doc.xpath("#{base_path}/*").map { |node| node.name }
+        ERA_TAGS.each_with_object({}) do |era_tag, result|
+          key  = era_tag.gsub('era', '').gsub(/s$/, '').downcase.to_sym
+          path = "eras/#{era_tag}"
 
-        keys.each_with_object({}) do |name, result|
-          path = "#{base_path}/#{name}/*"
-          key  = name.gsub('era', '').gsub(/s$/, '').downcase.to_sym
-          result[key] = doc.xpath(path).each_with_object({}) do |node, ret|
-            type = node.attribute('type').value.to_i rescue 0
-            ret[type] = node.content
+          result[key] = dtd.find_attr('era', 'type').values.each_with_object({}) do |type, ret|
+            node = calendar.xpath("#{path}/era[@type='#{type}' and @alt='variant']").first ||
+              calendar.xpath("#{path}/era[@type='#{type}']").first
+            ret[type] = node.content if node
             ret
           end
         end
@@ -161,22 +160,24 @@ module TwitterCldr
       def formats(type)
         return {} unless calendar
 
-        formats = calendar.xpath("#{type}Formats/#{type}FormatLength").each_with_object({}) do |node, result|
-          key = node.attribute('type').value.to_sym rescue :format
-          result[key] = pattern(node, type)
+        formats = dtd.find_attr("#{type}FormatLength", 'type').values.each_with_object({}) do |format_length, result|
+          node = calendar.xpath("#{type}Formats/#{type}FormatLength[@type='#{format_length}']").first
+          result[format_length] = pattern(node, type) if node
         end
+
         if default = default_format(type)
           formats = default.merge(formats)
         end
+
         formats
       end
 
       def additional_formats
         return {} unless calendar
 
-        calendar.xpath("dateTimeFormats/availableFormats/dateFormatItem").each_with_object({}) do |node, result|
-          key = node.attribute('id').value
-          result[key] = node.content
+        dtd.find_attr('dateFormatItem', 'id').values.each_with_object({}) do |id, result|
+          node = calendar.xpath("dateTimeFormats/availableFormats/dateFormatItem[@id='#{id}']").first
+          result[id] = node.content if node
         end
       end
 
@@ -196,24 +197,25 @@ module TwitterCldr
       end
 
       def fields
-        doc.xpath("//ldml/dates/fields/field").each_with_object({}) do |node, result|
-          key  = node.attribute('type').value.to_sym
+        dtd.find_attr('field', 'type').values.each_with_object({}) do |field, result|
+          node = docset.xpath("//ldml/dates/fields/field[@type='#{field}']").first
           name = node.xpath('displayName').first
-          result[key] = name.content if name
+          result[field] = name.content if name
         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
+      def docset
+        @docset ||= cldr_req.docset(cldr_main_path, locale)
       end
 
       def cldr_main_path
         @cldr_main_path ||= File.join(cldr_req.common_path, 'main')
       end
 
+      def dtd
+        cldr_req.dtd
+      end
+
     end
 
   end

data/lib/twitter_cldr/resources/cldr_data_builder.rb

@@ -0,0 +1,36 @@
+# encoding: UTF-8
+
+# Copyright 2012 Twitter, Inc
+# http://www.apache.org/licenses/LICENSE-2.0
+
+require 'nokogiri'
+
+module TwitterCldr
+  module Resources
+
+    class CldrDataBuilder
+      DEEP_MERGER = proc do |key, v1, v2|
+        Hash === v1 && Hash === v2 ? v1.merge(v2, &DEEP_MERGER) : (v2 || v1)
+      end
+
+      attr_reader :cldr_locale
+
+      def initialize(cldr_locale)
+        @cldr_locale = cldr_locale
+      end
+
+      def merge_each_ancestor
+        cldr_locale.ancestors.inject({}) do |result, ancestor_locale|
+          deep_merge(yield(ancestor_locale), result)
+        end
+      end
+
+      private
+
+      def deep_merge(h1, h2)
+        h1.merge(h2, &DEEP_MERGER)
+      end
+    end
+
+  end
+end

data/lib/twitter_cldr/resources/cldr_document_set.rb

@@ -0,0 +1,157 @@
+# encoding: UTF-8
+
+# Copyright 2012 Twitter, Inc
+# http://www.apache.org/licenses/LICENSE-2.0
+
+require 'forwardable'
+require 'nokogiri'
+
+module TwitterCldr
+  module Resources
+    class CldrDocumentSet
+
+      class Element
+        extend Forwardable
+
+        def_delegators :@element, :attribute, :content, :name, :path
+
+        attr_reader :docset, :element
+
+        def initialize(docset, element)
+          @docset = docset
+          @element = element
+        end
+
+        def xpath(path)
+          path = CldrDocumentSet.join_xpaths(docset.path_for(element), path)
+          docset.xpath(path)
+        end
+      end
+
+      class ElementList
+        include Enumerable
+        extend Forwardable
+
+        def_delegators :@elements, :size
+
+        attr_reader :docset, :elements
+
+        def initialize(docset, elements)
+          @docset = docset
+          @elements = elements
+        end
+
+        def [](idx)
+          return unless elements[idx]
+
+          Element.new(docset, elements[idx])
+        end
+
+        def first
+          self[0]
+        end
+
+        def each
+          return to_enum(__method__) unless block_given?
+
+          elements.size.times do |idx|
+            yield self[idx]
+          end
+        end
+      end
+
+
+      def self.join_xpaths(*paths)
+        segments = paths.flat_map { |a| a.chomp('/').split('/') }
+        segments = segments.each_with_object([]) do |segment, result|
+          if segment == '..'
+            result.pop
+          else
+            result << segment
+          end
+        end
+        segments.join('/')
+      end
+
+      attr_reader :path, :cldr_locale, :cldr_requirement
+
+      def initialize(path, cldr_locale, cldr_requirement)
+        @path = path
+        @cldr_locale = cldr_locale
+        @cldr_requirement = cldr_requirement
+      end
+
+
+      def xpath(path)
+        cldr_locale.ancestors.each do |ancestor_locale|
+          data = doc_for(ancestor_locale).xpath(path)
+
+          unless data.empty?
+            return ElementList.new(self, resolve_aliases_in(data))
+          end
+        end
+
+        ElementList.new(self, [])
+      end
+
+      def path_for(node)
+        orig_node = node
+        path = []
+
+        while node
+          path << selector_for(node)
+          node = node.parent
+          break if node.name == 'document'
+        end
+
+        "//#{path.reverse.join('/')}"
+      end
+
+      private
+
+      def resolve_aliases_in(data)
+        alias_nodes = data.xpath('.//alias')
+        alias_nodes.each do |alias_node|
+          alias_path = alias_node.attribute('path').value
+          full_path = join_xpaths(path_for(alias_node.parent), alias_path)
+
+          cldr_locale.ancestors.find do |ancestor_locale|
+            resolved_node = doc_for(ancestor_locale).xpath(full_path).first.dup
+
+            if resolved_node
+              resolved_copy = Nokogiri::XML(resolved_node.to_xml).children.first
+              parent = alias_node.parent
+              alias_node.replace(resolved_copy.children)
+              resolve_aliases_in(parent)
+              break
+            end
+          end
+        end
+
+        data
+      end
+
+      def join_xpaths(*paths)
+        self.class.join_xpaths(*paths)
+      end
+
+      def selector_for(node)
+        node.name.dup.tap do |selector|
+          if type = node.attribute('type')
+            selector << "[@type='#{type.value}']"
+          end
+        end
+      end
+
+      def doc_for(locale)
+        locale_fs = locale.to_s.gsub('-', '_')
+        docs[locale_fs] ||= Nokogiri.XML(File.read(File.join(path, "#{locale_fs}.xml")))
+      end
+
+      def docs
+        @docs ||= {}
+      end
+    end
+
+  end
+end