isodoc-i18n 1.2.0 → 1.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 96eadaddf7790754bf2d333c123f56d49dec0adee80176425573a66c6316edf5
-  data.tar.gz: 7bfc57b834aeed6405a2c907414b36848642464a846fc8c2a96fe3156eac7784
+  metadata.gz: 7552e0a62364e47c4f8ea7b2810e1ba5d11e39d2a3711792c826412b1aef661f
+  data.tar.gz: 29d4eef4f2a07bcf6ad1de7ddc229cf7ff9b0ffa8e55c81652d2174165cf2214
 SHA512:
-  metadata.gz: 669699121ed0ad877eeab149c5ef807a885ad40fa9881b9204de39261a2769330d0946a5ee9c49d9845172f590a38b655973dec7e25d3d2a5187f964633e9950
-  data.tar.gz: '09fafa5d49dcc64631a2fa0bc67b70dcd7c3b2aefacd7ced507b429525fa91ca052de96e3bf9bcfb6e953fb72045b79edb6ba64f16d36f65f6af838512804f29'
+  metadata.gz: 220fddc821f5f00d4f1eecca1f7583b0236254bb0a5141c50d7583f4c725be2b4aca949ffc4f89ed390c01850f2912d86b9562959773efabf1a3df4838e8ec60
+  data.tar.gz: 59373ef3a3688bf4f382da1e2a5df55b3b7ae1615385bc04504faf9421e9c5e66333ed1859243f0e8a86d4f42724692ab1cd9b8f9f0bd62d4c4e70cceb7e93cd

data/Gemfile

@@ -6,6 +6,4 @@ git_source(:github) { |repo| "https://github.com/#{repo}" }
 
 gemspec
 
-if File.exist? 'Gemfile.devel'
-  eval File.read('Gemfile.devel'), nil, 'Gemfile.devel' # rubocop:disable Security/Eval
-end
+eval_gemfile("Gemfile.devel") rescue nil

data/isodoc-i18n.gemspec

@@ -23,7 +23,8 @@ Gem::Specification.new do |spec|
   spec.required_ruby_version = Gem::Requirement.new(">= 2.7.0")
 
   spec.add_dependency "htmlentities", "~> 4.3.4"
-  spec.add_dependency "metanorma-utils", ">= 1.6.0"
+  spec.add_dependency "liquid", "~> 5"
+  spec.add_dependency "metanorma-utils", ">= 1.7.0"
   spec.add_dependency "twitter_cldr"
 
   spec.add_development_dependency "debug"

data/lib/isodoc/i18n/version.rb

@@ -1,5 +1,5 @@
 module IsoDoc
   class I18n
-    VERSION = "1.2.0".freeze
+    VERSION = "1.2.1".freeze
   end
 end

data/lib/isodoc/i18n.rb

@@ -1,11 +1,16 @@
 require "htmlentities"
 require "twitter_cldr"
-require_relative "i18n/version"
 require_relative "i18n-yaml"
 require_relative "date"
+require_relative "l10n"
+require_relative "liquid/liquid"
+require "liquid"
+require_relative "i18n/version"
 
 module IsoDoc
   class I18n
+    attr_accessor :labels
+
     def initialize(lang, script, locale: nil, i18nyaml: nil, i18nhash: nil)
       @lang = lang
       @script = script
@@ -14,6 +19,12 @@ module IsoDoc
       @cal_en = TwitterCldr::Shared::Calendar.new(:en)
       @c = HTMLEntities.new
       init_labels(i18nyaml, i18nhash)
+      liquid_init
+    end
+
+    def liquid_init
+      ::IsoDoc::I18n::Liquid.set(self)
+      ::Liquid::Template.register_filter(::IsoDoc::I18n::Liquid)
     end
 
     def calendar_data
@@ -26,119 +37,15 @@ module IsoDoc
       @labels = load_yaml(@lang, @script, i18nyaml, i18nhash)
       @labels["language"] = @lang
       @labels["script"] = @script
-      @labels.each do |k, _v|
+      @labels.each_key do |k|
         self.class.send(:define_method, k.downcase) { get[k] }
       end
     end
 
-    def self.l10n(text, lang = @lang, script = @script, locale = @locale)
-      l10n(text, lang, script, locale)
-    end
-
-    # function localising spaces and punctuation.
-    # Not clear if period needs to be localised for zh
-    def l10n(text, lang = @lang, script = @script, locale = @locale)
-      lang == "zh" and text = l10n_zh(text, script)
-      lang == "fr" && text = l10n_fr(text, locale || "FR")
-      bidiwrap(text, lang, script)
-    end
-
-    def bidiwrap(text, lang, script)
-      my_script, my_rtl, outer_rtl = bidiwrap_vars(lang, script)
-      if my_rtl && !outer_rtl
-        mark = %w(Arab Aran).include?(my_script) ? "؜" : "‏"
-        "#{mark}#{text}#{mark}"
-      elsif !my_rtl && outer_rtl then "‎#{text}‎"
-      else text
-      end
-    end
-
-    def bidiwrap_vars(lang, script)
-      my_script = script || Metanorma::Utils.default_script(lang)
-      [my_script,
-       Metanorma::Utils.rtl_script?(my_script),
-       Metanorma::Utils.rtl_script?(@script || Metanorma::Utils
-         .default_script(@lang))]
-    end
-
-    def l10n_zh(text, script = "Hans")
-      xml = Nokogiri::XML::DocumentFragment.parse(text)
-      xml.traverse do |n|
-        next unless n.text?
-
-        n.replace(l10_zh1(cleanup_entities(n.text, is_xml: false), script))
-      end
-      xml.to_xml(encoding: "UTF-8").gsub(/<b>/, "").gsub("</b>", "")
-        .gsub(/<\?[^>]+>/, "")
-    end
-
-    def l10n_fr(text, locale)
-      xml = Nokogiri::XML::DocumentFragment.parse(text)
-      xml.traverse do |n|
-        next unless n.text?
-
-        n.replace(l10n_fr1(cleanup_entities(n.text, is_xml: false), locale))
-      end
-      xml.to_xml(encoding: "UTF-8")
-    end
-
-    ZH_CHAR = "\\p{Han}|\\p{In CJK Symbols And Punctuation}|" \
-              "\\p{In Halfwidth And Fullwidth Forms}".freeze
-
-    # note: we can't differentiate comma from enumeration comma 、
-    def l10_zh1(text, _script)
-      l10n_zh_remove_space(l10n_zh_punct(text))
-    end
-
-    def l10n_zh_punct(text)
-      [":：", ",，", ".．", ")）", "]］", ":：", ";；", "?？", "!！", "–～"].each do |m|
-        text = text.gsub(/#{Regexp.quote m[0]}/, m[1])
-      end
-      ["(（", "[［"].each do |m|
-        text = text.gsub(/#{Regexp.quote m[0]}/, m[1])
-      end
-      text
-    end
-
-    def l10n_zh_remove_space(text)
-      text.gsub(/(?<=#{ZH_CHAR}) (?=#{ZH_CHAR})/o, "")
-        .gsub(/(?<=\d) (?=#{ZH_CHAR})/o, "")
-        .gsub(/(?<=#{ZH_CHAR}) (?=\d)/o, "")
-        .gsub(/(?<=#{ZH_CHAR}) (?=[A-Za-z](#{ZH_CHAR}|$))/o, "")
-    end
-
-    def l10n_fr1(text, locale)
-      text = text.gsub(/(?<=\p{Alnum})([»›;?!])(?=\s)/, "\u202f\\1")
-      text = text.gsub(/(?<=\p{Alnum})([»›;?!])$/, "\u202f\\1")
-      text = text.gsub(/^([»›;?!])/, "\u202f\\1")
-      text = text.gsub(/([«‹])/, "\\1\u202f")
-      colonsp = locale == "CH" ? "\u202f" : "\u00a0"
-      text = text.gsub(/(?<=\p{Alnum})(:)(?=\s)/, "#{colonsp}\\1")
-      text = text.gsub(/(?<=\p{Alnum})(:)$/, "#{colonsp}\\1")
-      text.gsub(/^(:\s)/, "#{colonsp}\\1")
-    end
-
-    def self.cjk_extend(text)
-      cjk_extend(text)
-    end
-
-    def cjk_extend(title)
-      @c.decode(title).chars.map.with_index do |n, i|
-        if i.zero? || !interleave_space_cjk?(title[i - 1] + title[i])
-          n
-        else "\u3000#{n}"
-        end
-      end.join
-    end
-
-    def interleave_space_cjk?(text)
-      text.size == 2 or return
-      ["\u2014\u2014", "\u2025\u2025", "\u2026\u2026", "\u22ef\u22ef"].include?(text) ||
-        /\d\d|\p{Latin}\p{Latin}|[[:space:]]/.match?(text) ||
-        /^[\u2018\u201c(\u3014\[{\u3008\u300a\u300c\u300e\u3010\u2985\u3018\u3016\u00ab\u301d]/.match?(text) ||
-        /[\u2019\u201d)\u3015\]}\u3009\u300b\u300d\u300f\u3011\u2986\u3019\u3017\u00bb\u301f]$/.match?(text) ||
-        /[\u3002.\u3001,\u30fb:;\u2010\u301c\u30a0\u2013!?\u203c\u2047\u2048\u2049]/.match?(text) and return false
-      true
+    # populate with variables, Liquid, inflections, ordinals/spellout
+    def populate(keys, vars = {})
+      ::Liquid::Template.parse(@labels.dig(*Array(keys)))
+        .render(vars.merge("labels" => @labels))
     end
 
     def boolean_conj(list, conn)
@@ -190,7 +97,7 @@ module IsoDoc
     INFLECTIONS = {
       number: "sg",
       case: "nom",
-      gender: "masc",
+      gender: "m",
       person: "3rd",
       voice: "act",
       mood: "ind",
@@ -201,7 +108,7 @@ module IsoDoc
 
     def ordinal_key(term)
       @labels["ordinal_keys"].each_with_object([]) do |k, m|
-        m << (term[k] || INFLECTIONS[k.to_sym])
+        m << (term[k.to_s] || INFLECTIONS[k.to_sym])
       end.join(".")
     end
 
@@ -216,7 +123,6 @@ module IsoDoc
     def inflect(word, options)
       i = @labels.dig("inflection", word) or return word
       i.is_a? String and return i
-
       INFLECTION_ORDER.each do |x|
         infl = options[x] || INFLECTIONS[x]
         i = i[infl] if i[infl]

data/lib/isodoc/l10n.rb

@@ -0,0 +1,113 @@
+module IsoDoc
+  class I18n
+    def self.l10n(text, lang = @lang, script = @script, locale = @locale)
+      l10n(text, lang, script, locale)
+    end
+
+    # function localising spaces and punctuation.
+    # Not clear if period needs to be localised for zh
+    def l10n(text, lang = @lang, script = @script, locale = @locale)
+      lang == "zh" and text = l10n_zh(text, script)
+      lang == "fr" && text = l10n_fr(text, locale || "FR")
+      bidiwrap(text, lang, script)
+    end
+
+    def bidiwrap(text, lang, script)
+      my_script, my_rtl, outer_rtl = bidiwrap_vars(lang, script)
+      if my_rtl && !outer_rtl
+        mark = %w(Arab Aran).include?(my_script) ? "؜" : "‏"
+        "#{mark}#{text}#{mark}"
+      elsif !my_rtl && outer_rtl then "‎#{text}‎"
+      else text
+      end
+    end
+
+    def bidiwrap_vars(lang, script)
+      my_script = script || Metanorma::Utils.default_script(lang)
+      [my_script,
+       Metanorma::Utils.rtl_script?(my_script),
+       Metanorma::Utils.rtl_script?(@script || Metanorma::Utils
+         .default_script(@lang))]
+    end
+
+    def l10n_zh(text, script = "Hans")
+      xml = Nokogiri::XML::DocumentFragment.parse(text)
+      xml.traverse do |n|
+        next unless n.text?
+
+        n.replace(l10_zh1(cleanup_entities(n.text, is_xml: false), script))
+      end
+      xml.to_xml(encoding: "UTF-8").gsub(/<b>/, "").gsub("</b>", "")
+        .gsub(/<\?[^>]+>/, "")
+    end
+
+    def l10n_fr(text, locale)
+      xml = Nokogiri::XML::DocumentFragment.parse(text)
+      xml.traverse do |n|
+        next unless n.text?
+
+        n.replace(l10n_fr1(cleanup_entities(n.text, is_xml: false), locale))
+      end
+      xml.to_xml(encoding: "UTF-8")
+    end
+
+    ZH_CHAR = "\\p{Han}|\\p{In CJK Symbols And Punctuation}|" \
+              "\\p{In Halfwidth And Fullwidth Forms}".freeze
+
+    # note: we can't differentiate comma from enumeration comma 、
+    def l10_zh1(text, _script)
+      l10n_zh_remove_space(l10n_zh_punct(text))
+    end
+
+    def l10n_zh_punct(text)
+      [":：", ",，", ".．", ")）", "]］", ":：", ";；", "?？", "!！", "–～"].each do |m|
+        text = text.gsub(/#{Regexp.quote m[0]}/, m[1])
+      end
+      ["(（", "[［"].each do |m|
+        text = text.gsub(/#{Regexp.quote m[0]}/, m[1])
+      end
+      text
+    end
+
+    def l10n_zh_remove_space(text)
+      text.gsub(/(?<=#{ZH_CHAR}) (?=#{ZH_CHAR})/o, "")
+        .gsub(/(?<=\d) (?=#{ZH_CHAR})/o, "")
+        .gsub(/(?<=#{ZH_CHAR}) (?=\d)/o, "")
+        .gsub(/(?<=#{ZH_CHAR}) (?=[A-Za-z](#{ZH_CHAR}|$))/o, "")
+    end
+
+    def l10n_fr1(text, locale)
+      text = text.gsub(/(?<=\p{Alnum})([»›;?!])(?=\s)/, "\u202f\\1")
+      text = text.gsub(/(?<=\p{Alnum})([»›;?!])$/, "\u202f\\1")
+      text = text.gsub(/^([»›;?!])/, "\u202f\\1")
+      text = text.gsub(/([«‹])/, "\\1\u202f")
+      colonsp = locale == "CH" ? "\u202f" : "\u00a0"
+      text = text.gsub(/(?<=\p{Alnum})(:)(?=\s)/, "#{colonsp}\\1")
+      text = text.gsub(/(?<=\p{Alnum})(:)$/, "#{colonsp}\\1")
+      text.gsub(/^(:\s)/, "#{colonsp}\\1")
+    end
+
+    def self.cjk_extend(text)
+      cjk_extend(text)
+    end
+
+    def cjk_extend(title)
+      @c.decode(title).chars.map.with_index do |n, i|
+        if i.zero? || !interleave_space_cjk?(title[i - 1] + title[i])
+          n
+        else "\u3000#{n}"
+        end
+      end.join
+    end
+
+    def interleave_space_cjk?(text)
+      text.size == 2 or return
+      ["\u2014\u2014", "\u2025\u2025", "\u2026\u2026", "\u22ef\u22ef"].include?(text) ||
+        /\d\d|\p{Latin}\p{Latin}|[[:space:]]/.match?(text) ||
+        /^[\u2018\u201c(\u3014\[{\u3008\u300a\u300c\u300e\u3010\u2985\u3018\u3016\u00ab\u301d]/.match?(text) ||
+        /[\u2019\u201d)\u3015\]}\u3009\u300b\u300d\u300f\u3011\u2986\u3019\u3017\u00bb\u301f]$/.match?(text) ||
+        /[\u3002.\u3001,\u30fb:;\u2010\u301c\u30a0\u2013!?\u203c\u2047\u2048\u2049]/.match?(text) and return false
+      true
+    end
+  end
+end

data/lib/isodoc/liquid/liquid.rb

@@ -0,0 +1,38 @@
+module IsoDoc
+  class I18n
+    module Liquid
+      def self.set(i18n)
+        @@i18n = i18n
+      end
+
+      def parse_hash(str, symbol: true)
+        str.split(/,\s*/).each_with_object({}) do |e, m|
+          k, v = e.split(/:/, 2)
+          m[symbol ? k.to_sym : k.to_s] = v
+        end
+      end
+
+      # word | inflect: nom,sg,neut
+      def inflect(word, options)
+        @@i18n.inflect(word, parse_hash(options))
+      end
+
+      # num | ordinal_num: label, inflection
+      # e.g. "3" | ordinal: "edition", "case:acc"
+      # combines inflection information from label and inflection
+      def ordinal_num(num, label = "", infl = "")
+        l = @@i18n.labels[label]
+        h = @@i18n.labels["inflection"]&.dig(l, "grammar") || {}
+        grammar = h.merge(parse_hash(infl, symbol: false))
+        @@i18n.inflect_ordinal(num.to_i, grammar, "OrdinalRules")
+      end
+
+      def ordinal_word(num, label = "", infl = "")
+        l = @@i18n.labels[label]
+        h = @@i18n.labels["inflection"]&.dig(l, "grammar") || {}
+        grammar = h.merge(parse_hash(infl, symbol: false))
+        @@i18n.inflect_ordinal(num.to_i, grammar, "SpelloutRules")
+      end
+    end
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: isodoc-i18n
 version: !ruby/object:Gem::Version
-  version: 1.2.0
+  version: 1.2.1
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2023-10-09 00:00:00.000000000 Z
+date: 2024-02-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: htmlentities
@@ -24,20 +24,34 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 4.3.4
+- !ruby/object:Gem::Dependency
+  name: liquid
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5'
 - !ruby/object:Gem::Dependency
   name: metanorma-utils
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.6.0
+        version: 1.7.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.6.0
+        version: 1.7.0
 - !ruby/object:Gem::Dependency
   name: twitter_cldr
   requirement: !ruby/object:Gem::Requirement
@@ -214,6 +228,8 @@ files:
 - lib/isodoc/i18n-yaml.rb
 - lib/isodoc/i18n.rb
 - lib/isodoc/i18n/version.rb
+- lib/isodoc/l10n.rb
+- lib/isodoc/liquid/liquid.rb
 homepage: https://github.com/metanorma/isodoc-i18n
 licenses:
 - BSD-2-Clause