yosina 0.1.0 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 79e70c5202973c9c7c6e2c5b5de4538422eb9323071dbaabc6563be241129a44
-  data.tar.gz: bf615675a3b77c5b330ac5da9132e2df90d92911d3763ae8c3bcc612aa894289
+  metadata.gz: e0feecfd822d02f104629ea622864a55c77771f2af69d54f19a564a06e45d6cf
+  data.tar.gz: 04fba6b2b2db15a96f9574771fbe8e4c71debacfa62b9d7480ed178ee96c3868
 SHA512:
-  metadata.gz: 9acbf40e48148bd8cd6db88b02df70364a840c5b8a283df61256e838db9990bff8b73b1a30e95e892c20cbe5542a8d21d870284a7779cbc833043fd3aef612b7
-  data.tar.gz: 64e0f480547d54d14318f677ac459905209b6365096623cfe849a21740a1150a3c263c950b37f62dd30b82dce55b1a2e89e2c5def130736a1ac4b44d1c21acc4
+  metadata.gz: 0aff88194c04e9316f69925fb4e6499d6e5dc7ae1c168136fdbc41ea01e38b2760cb9e2e2315879eb60eed18396f8405a2ac800e067469a1e9f6f015acc44010
+  data.tar.gz: 9212dc8a91402ef11255a33303a09a371a0a5ec15ec1d6f4d2b86f3f4afbfa62255ace9ee649e29425890c1c6df0085356680408c6faab4968c57f4daaf32275

data/README.md

@@ -192,6 +192,10 @@ Converts CJK radical characters to their corresponding ideographs.
 Normalizes various Unicode space characters to standard ASCII space.
 - Example: `A　B` (ideographic space) → `A B`
 
+### 15. **Roman Numerals** (`roman-numerals`)
+Converts Unicode Roman numeral characters to their ASCII letter equivalents.
+- Example: `Ⅰ Ⅱ Ⅲ` → `I II III`, `ⅰ ⅱ ⅲ` → `i ii iii`
+
 ## Development
 
 After checking out the repo, run `bundle install` to install dependencies.

data/codegen/dataset.rb

@@ -13,6 +13,7 @@ DatasetSourceDefs = Struct.new(
   :kanji_old_new,
   :combined,
   :circled_or_squared,
+  :roman_numerals,
   keyword_init: true
 )
 
@@ -27,6 +28,7 @@ Dataset = Struct.new(
   :kanji_old_new,
   :combined,
   :circled_or_squared,
+  :roman_numerals,
   keyword_init: true
 )
 
@@ -199,6 +201,34 @@ def load_circled_or_squared_data(filepath)
   mappings
 end
 
+# Load roman numerals data
+def load_roman_numerals_data(filepath)
+  data = JSON.parse(File.read(filepath))
+  mappings = {}
+
+  data.each do |record|
+    # Parse upper and lower codes
+    upper_char = unicode_to_char(record['codes']['upper'])
+    lower_char = unicode_to_char(record['codes']['lower'])
+
+    # Parse decomposed forms
+    decomposed_upper = record['decomposed']['upper'].map { |cp| unicode_to_char(cp) }
+    decomposed_lower = record['decomposed']['lower'].map { |cp| unicode_to_char(cp) }
+
+    # Store both upper and lower mappings
+    mappings[upper_char] = {
+      value: record['value'],
+      decomposed: decomposed_upper
+    }
+    mappings[lower_char] = {
+      value: record['value'],
+      decomposed: decomposed_lower
+    }
+  end
+
+  mappings
+end
+
 # Build dataset from data root directory
 def build_dataset_from_data_root(data_root, defs)
   Dataset.new(
@@ -210,6 +240,7 @@ def build_dataset_from_data_root(data_root, defs)
     ivs_svs_base: load_ivs_svs_base_data(data_root / defs.ivs_svs_base),
     kanji_old_new: load_kanji_old_new_data(data_root / defs.kanji_old_new),
     combined: load_combined_data(data_root / defs.combined),
-    circled_or_squared: load_circled_or_squared_data(data_root / defs.circled_or_squared)
+    circled_or_squared: load_circled_or_squared_data(data_root / defs.circled_or_squared),
+    roman_numerals: load_roman_numerals_data(data_root / defs.roman_numerals)
   )
 end

data/codegen/emitters/roman_numerals_transliterator_data.rb

@@ -0,0 +1,29 @@
+# frozen_string_literal: true
+
+require_relative 'utils'
+
+# Render a roman numerals transliterator
+def render_roman_numerals_transliterator_data(mappings)
+  # Generate mapping entries for roman numerals -> decomposed arrays
+  mapping_entries = mappings.map do |key, record|
+    decomposed_array = record[:decomposed]
+    value_repr = "[#{decomposed_array.map { |c| to_string_literal(c) }.join(', ')}]"
+    "            #{to_string_literal(key)} => #{value_repr}"
+  end.join(",\n")
+
+  dedent 4, <<~RUBY
+        # frozen_string_literal: true
+
+        module Yosina
+          module Transliterators
+            # Replace roman numeral characters with their ASCII letter equivalents
+            module RomanNumerals
+              # Generated mapping data from roman-numerals.json
+              ROMAN_NUMERAL_MAPPINGS = {
+    #{mapping_entries}
+              }.freeze
+            end
+          end
+        end
+  RUBY
+end

data/codegen/emitters.rb

@@ -6,3 +6,4 @@ require_relative 'emitters/hyphens_transliterator_data'
 require_relative 'emitters/ivs_svs_base_transliterator_data'
 require_relative 'emitters/combined_transliterator_data'
 require_relative 'emitters/circled_or_squared_transliterator_data'
+require_relative 'emitters/roman_numerals_transliterator_data'

data/codegen/main.rb

@@ -31,7 +31,8 @@ def main
     ivs_svs_base: 'ivs-svs-base-mappings.json',
     kanji_old_new: 'kanji-old-new-form.json',
     combined: 'combined-chars.json',
-    circled_or_squared: 'circled-or-squared.json'
+    circled_or_squared: 'circled-or-squared.json',
+    roman_numerals: 'roman-numerals.json'
   )
 
   # Load the dataset
@@ -98,6 +99,12 @@ def main
   puts 'Generating: circled_or_squared_data.rb'
   filepath.write(output)
 
+  # Generate roman numerals transliterator
+  output = render_roman_numerals_transliterator_data(dataset.roman_numerals)
+  filepath = dest_root / 'roman_numerals_data.rb'
+  puts 'Generating: roman_numerals_data.rb'
+  filepath.write(output)
+
   puts 'Code generation complete!'
 end
 

data/lib/yosina/recipes.rb

@@ -56,7 +56,7 @@ module Yosina
                   :replace_suspicious_hyphens_to_prolonged_sound_marks,
                   :replace_combined_characters, :replace_circled_or_squared_characters,
                   :replace_ideographic_annotations, :replace_radicals, :replace_spaces,
-                  :replace_hyphens, :replace_mathematical_alphanumerics,
+                  :replace_hyphens, :replace_mathematical_alphanumerics, :replace_roman_numerals,
                   :combine_decomposed_hiraganas_and_katakanas, :to_fullwidth, :to_halfwidth,
                   :remove_ivs_svs, :charset
 
@@ -123,6 +123,12 @@ module Yosina
     #     # Output: "ABC"
     #     # Input:  "𝟏𝟐𝟑" (mathematical bold digits)
     #     # Output: "123"
+    # @param replace_roman_numerals [Boolean] Replace roman numeral characters
+    #   @example
+    #     # Input:  "Ⅲ" (Roman numeral III)
+    #     # Output: "III"
+    #     # Input:  "ⅻ" (Roman numeral xii)
+    #     # Output: "xii"
     # @param combine_decomposed_hiraganas_and_katakanas [Boolean] Combine decomposed hiraganas/katakanas
     #   @example
     #     # Input:  "が" (か + ゙)
@@ -154,7 +160,7 @@ module Yosina
                    replace_combined_characters: false, replace_circled_or_squared_characters: false,
                    replace_ideographic_annotations: false, replace_radicals: false,
                    replace_spaces: false, replace_hyphens: false,
-                   replace_mathematical_alphanumerics: false,
+                   replace_mathematical_alphanumerics: false, replace_roman_numerals: false,
                    combine_decomposed_hiraganas_and_katakanas: false,
                    to_fullwidth: false, to_halfwidth: false, remove_ivs_svs: false,
                    charset: 'unijis_2004')
@@ -169,6 +175,7 @@ module Yosina
       @replace_spaces = replace_spaces
       @replace_hyphens = replace_hyphens
       @replace_mathematical_alphanumerics = replace_mathematical_alphanumerics
+      @replace_roman_numerals = replace_roman_numerals
       @combine_decomposed_hiraganas_and_katakanas = combine_decomposed_hiraganas_and_katakanas
       @to_fullwidth = to_fullwidth
       @to_halfwidth = to_halfwidth
@@ -200,6 +207,7 @@ module Yosina
       ctx = apply_replace_spaces(ctx)
       ctx = apply_replace_hyphens(ctx)
       ctx = apply_replace_mathematical_alphanumerics(ctx)
+      ctx = apply_replace_roman_numerals(ctx)
       ctx = apply_combine_decomposed_hiraganas_and_katakanas(ctx)
       ctx = apply_to_fullwidth(ctx)
       ctx = apply_hira_kata(ctx)
@@ -233,7 +241,7 @@ module Yosina
 
     def apply_hira_kata(ctx)
       if @hira_kata
-        ctx.insert_middle([:hira_kata, { mode: @hira_kata }])
+        ctx.insert_tail([:hira_kata, { mode: @hira_kata }])
       else
         ctx
       end
@@ -313,6 +321,14 @@ module Yosina
       end
     end
 
+    def apply_replace_roman_numerals(ctx)
+      if @replace_roman_numerals
+        ctx.insert_middle([:roman_numerals, {}])
+      else
+        ctx
+      end
+    end
+
     def apply_combine_decomposed_hiraganas_and_katakanas(ctx)
       if @combine_decomposed_hiraganas_and_katakanas
         ctx.insert_head([:hira_kata_composition, { compose_non_combining_marks: true }])

data/lib/yosina/transliterators/circled_or_squared_data.rb

@@ -132,11 +132,13 @@ module Yosina
         "\u{2791}" => { rendering: '8', type: 'c', emoji: false },
         "\u{2792}" => { rendering: '9', type: 'c', emoji: false },
         "\u{2793}" => { rendering: '10', type: 'c', emoji: false },
+        "\u{3036}" => { rendering: "\u{3012}", type: 'c', emoji: false },
         "\u{3244}" => { rendering: "\u{554f}", type: 'c', emoji: false },
         "\u{3245}" => { rendering: "\u{5e7c}", type: 'c', emoji: false },
         "\u{3246}" => { rendering: "\u{6587}", type: 'c', emoji: false },
         "\u{3247}" => { rendering: "\u{7b8f}", type: 'c', emoji: false },
-        "\u{3248}" => { rendering: '21', type: 'c', emoji: false },
+        "\u{3248}" => { rendering: '10', type: 'c', emoji: false },
+        "\u{3251}" => { rendering: '21', type: 'c', emoji: false },
         "\u{3252}" => { rendering: '22', type: 'c', emoji: false },
         "\u{3253}" => { rendering: '23', type: 'c', emoji: false },
         "\u{3254}" => { rendering: '24', type: 'c', emoji: false },
@@ -386,7 +388,7 @@ module Yosina
         "\u{1f1aa}" => { rendering: 'SHV', type: 's', emoji: false },
         "\u{1f1ab}" => { rendering: 'UHD', type: 's', emoji: false },
         "\u{1f1ac}" => { rendering: 'VOD', type: 's', emoji: false },
-        "\u{1f1ad}" => { rendering: 'VOD', type: 's', emoji: false },
+        "\u{1f1ad}" => { rendering: 'M', type: 'c', emoji: false },
         "\u{1f1e6}" => { rendering: 'A', type: 's', emoji: false },
         "\u{1f1e7}" => { rendering: 'B', type: 's', emoji: false },
         "\u{1f1e8}" => { rendering: 'C', type: 's', emoji: false },

data/lib/yosina/transliterators/hyphens_data.rb

@@ -27,6 +27,8 @@ module Yosina
         "\u{2014}" => HyphensRecord.new(ascii: '-', jisx0201: '-', jisx0208_90: "\u{2014}", jisx0208_90_windows: "\u{2015}"),
         "\u{2015}" => HyphensRecord.new(ascii: '-', jisx0201: '-', jisx0208_90: "\u{2015}", jisx0208_90_windows: "\u{2015}"),
         "\u{2016}" => HyphensRecord.new(jisx0208_90: "\u{2016}", jisx0208_90_windows: "\u{2225}"),
+        "\u{2032}" => HyphensRecord.new(ascii: "\'", jisx0201: "\'", jisx0208_90: "\u{2032}", jisx0208_90_windows: "\u{2032}"),
+        "\u{2033}" => HyphensRecord.new(ascii: "\"", jisx0201: "\"", jisx0208_90: "\u{2033}", jisx0208_90_windows: "\u{2033}"),
         "\u{203e}" => HyphensRecord.new(jisx0201: '~', jisx0208_90: "\u{ffe3}", jisx0208_90_windows: "\u{ffe3}"),
         "\u{2043}" => HyphensRecord.new(ascii: '-', jisx0201: '-', jisx0208_90: "\u{2010}", jisx0208_90_windows: "\u{2010}"),
         "\u{2053}" => HyphensRecord.new(ascii: '~', jisx0201: '~', jisx0208_90: "\u{301c}", jisx0208_90_windows: "\u{301c}"),

data/lib/yosina/transliterators/roman_numerals.rb

@@ -0,0 +1,49 @@
+# frozen_string_literal: true
+
+require_relative 'roman_numerals_data'
+
+module Yosina
+  module Transliterators
+    # Replace roman numeral characters with their ASCII letter equivalents
+    module RomanNumerals
+      # Transliterator for roman numerals
+      class Transliterator < Yosina::BaseTransliterator
+        # Initialize the transliterator
+        def initialize(_options = nil)
+          super()
+        end
+
+        # Convert roman numeral characters to ASCII equivalents
+        #
+        # @param input_chars [Enumerable<Char>] The characters to transliterate
+        # @return [Enumerable<Char>] The transliterated characters
+        def call(input_chars)
+          offset = 0
+
+          Chars.enum do |y|
+            input_chars.each do |char|
+              replacement = RomanNumerals::ROMAN_NUMERAL_MAPPINGS[char.c]
+              if replacement
+                replacement.each do |c|
+                  y << Char.new(c: c, offset: offset, source: char)
+                  offset += c.length
+                end
+              else
+                y << Char.new(c: char.c, offset: offset, source: char)
+                offset += char.c.length
+              end
+            end
+          end
+        end
+      end
+
+      # Factory method to create a transliterator
+      #
+      # @param options [Hash] Configuration options (currently unused)
+      # @return [Transliterator] A new transliterator instance
+      def self.call(options = {})
+        Transliterator.new(options)
+      end
+    end
+  end
+end

data/lib/yosina/transliterators/roman_numerals_data.rb

@@ -0,0 +1,44 @@
+# frozen_string_literal: true
+
+module Yosina
+  module Transliterators
+    # Replace roman numeral characters with their ASCII letter equivalents
+    module RomanNumerals
+      # Generated mapping data from roman-numerals.json
+      ROMAN_NUMERAL_MAPPINGS = {
+        "\u{2160}" => ['I'],
+        "\u{2170}" => ['i'],
+        "\u{2161}" => ['I', 'I'],
+        "\u{2171}" => ['i', 'i'],
+        "\u{2162}" => ['I', 'I', 'I'],
+        "\u{2172}" => ['i', 'i', 'i'],
+        "\u{2163}" => ['I', 'V'],
+        "\u{2173}" => ['i', 'v'],
+        "\u{2164}" => ['V'],
+        "\u{2174}" => ['v'],
+        "\u{2165}" => ['V', 'I'],
+        "\u{2175}" => ['v', 'i'],
+        "\u{2166}" => ['V', 'I', 'I'],
+        "\u{2176}" => ['v', 'i', 'i'],
+        "\u{2167}" => ['V', 'I', 'I', 'I'],
+        "\u{2177}" => ['v', 'i', 'i', 'i'],
+        "\u{2168}" => ['I', 'X'],
+        "\u{2178}" => ['i', 'x'],
+        "\u{2169}" => ['X'],
+        "\u{2179}" => ['x'],
+        "\u{216a}" => ['X', 'I'],
+        "\u{217a}" => ['x', 'i'],
+        "\u{216b}" => ['X', 'I', 'I'],
+        "\u{217b}" => ['x', 'i', 'i'],
+        "\u{216c}" => ['L'],
+        "\u{217c}" => ['l'],
+        "\u{216d}" => ['C'],
+        "\u{217d}" => ['c'],
+        "\u{216e}" => ['D'],
+        "\u{217e}" => ['d'],
+        "\u{216f}" => ['M'],
+        "\u{217f}" => ['m']
+      }.freeze
+    end
+  end
+end

data/lib/yosina/transliterators.rb

@@ -3,6 +3,7 @@
 require_relative 'transliterators/spaces'
 require_relative 'transliterators/kanji_old_new'
 require_relative 'transliterators/radicals'
+require_relative 'transliterators/roman_numerals'
 require_relative 'transliterators/ideographic_annotations'
 require_relative 'transliterators/mathematical_alphanumerics'
 require_relative 'transliterators/prolonged_sound_marks'
@@ -22,6 +23,7 @@ module Yosina
       spaces: Transliterators::Spaces,
       kanji_old_new: Transliterators::KanjiOldNew,
       radicals: Transliterators::Radicals,
+      roman_numerals: Transliterators::RomanNumerals,
       ideographic_annotations: Transliterators::IdeographicAnnotations,
       mathematical_alphanumerics: Transliterators::MathematicalAlphanumerics,
       prolonged_sound_marks: Transliterators::ProlongedSoundMarks,

data/lib/yosina/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Yosina
-  VERSION = '0.1.0'
+  VERSION = '1.0.0'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: yosina
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 1.0.0
 platform: ruby
 authors:
 - Moriyoshi Koizumi
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2025-08-19 00:00:00.000000000 Z
+date: 2025-09-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: minitest
@@ -99,6 +99,7 @@ files:
 - codegen/emitters/combined_transliterator_data.rb
 - codegen/emitters/hyphens_transliterator_data.rb
 - codegen/emitters/ivs_svs_base_transliterator_data.rb
+- codegen/emitters/roman_numerals_transliterator_data.rb
 - codegen/emitters/simple_transliterator.rb
 - codegen/emitters/utils.rb
 - codegen/main.rb
@@ -126,6 +127,8 @@ files:
 - lib/yosina/transliterators/mathematical_alphanumerics.rb
 - lib/yosina/transliterators/prolonged_sound_marks.rb
 - lib/yosina/transliterators/radicals.rb
+- lib/yosina/transliterators/roman_numerals.rb
+- lib/yosina/transliterators/roman_numerals_data.rb
 - lib/yosina/transliterators/spaces.rb
 - lib/yosina/version.rb
 - yosina.gemspec