ke2daira 0.1.0 → 0.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c05a97016dd61db84acc369c2b97805265fb8d3c5b7db226d7058ab7d5708bdf
-  data.tar.gz: fac2bd729b6ef78fa148856e80c4c45d39d0a847696dd657429071a3d6339904
+  metadata.gz: c4aaa1e18e53c6f8aa6c87b8457da21af7212910cfa195993c19675e4ba7e70f
+  data.tar.gz: 4f547aa4bd60e8eea105883e08b29d7c19cdda509dff8cb0d7a472f3db715b1a
 SHA512:
-  metadata.gz: d061c43d6a5a339af1ac903741a474d05c56ede78407ba083a6cbb4f266a548d4eb02fe11a5ddffc3937e1758020e6e20281ba564ceb81d0d21b5fbc20adc5db
-  data.tar.gz: 0c8d094c9044eee27483ff9e121b646f0878f04de39c1584a312338bd57ad11900ca6b0bd6751ae8c5c2e4eaf248e8fa3f05e54089aa37cd6e5136f5c02cf3d4
+  metadata.gz: 0166f9cdce6444a1aa3e1bb80061d2d125eae8163a184c210cf0e77ca725b11a761bc76082f95c6b03060ef40f5cc26f883566ad023231a980914844d5ec2ee1
+  data.tar.gz: ddc9c67a576e5cfab2d7a330cfce56fbc13b79f3006ab3ac8906f9ee441087d5a764bddbdd88d368e342da591fb714cfda94372318fb875237940e4efa09507b

data/CHANGELOG.md

@@ -1,3 +1,11 @@
+## 0.2.1
+
+- Fixed uninitialized constants
+
+## 0.2.0
+
+- Added support for Yoon (拗音)
+
 ## 0.1.0
 
 - Initial release

data/Gemfile.lock

@@ -1,24 +1,27 @@
 PATH
   remote: .
   specs:
-    ke2daira (0.1.0)
+    ke2daira (0.2.1)
       suika (~> 0.3.2)
 
 GEM
   remote: https://rubygems.org/
   specs:
-    ast (2.4.2)
+    ast (2.4.3)
     dartsclone (0.3.2)
     diff-lcs (1.5.0)
-    json (2.6.3)
-    language_server-protocol (3.17.0.3)
-    parallel (1.22.1)
-    parser (3.2.2.0)
+    json (2.12.2)
+    language_server-protocol (3.17.0.5)
+    lint_roller (1.1.0)
+    parallel (1.27.0)
+    parser (3.3.8.0)
       ast (~> 2.4.1)
+      racc
+    prism (1.4.0)
+    racc (1.8.1)
     rainbow (3.1.1)
     rake (13.0.6)
-    regexp_parser (2.7.0)
-    rexml (3.2.5)
+    regexp_parser (2.10.0)
     rspec (3.12.0)
       rspec-core (~> 3.12.0)
       rspec-expectations (~> 3.12.0)
@@ -32,29 +35,42 @@ GEM
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.12.0)
     rspec-support (3.12.0)
-    rubocop (1.48.1)
+    rubocop (1.75.8)
       json (~> 2.3)
+      language_server-protocol (~> 3.17.0.2)
+      lint_roller (~> 1.1.0)
       parallel (~> 1.10)
-      parser (>= 3.2.0.0)
+      parser (>= 3.3.0.2)
       rainbow (>= 2.2.2, < 4.0)
-      regexp_parser (>= 1.8, < 3.0)
-      rexml (>= 3.2.5, < 4.0)
-      rubocop-ast (>= 1.26.0, < 2.0)
+      regexp_parser (>= 2.9.3, < 3.0)
+      rubocop-ast (>= 1.44.0, < 2.0)
       ruby-progressbar (~> 1.7)
-      unicode-display_width (>= 2.4.0, < 3.0)
-    rubocop-ast (1.28.0)
-      parser (>= 3.2.1.0)
-    rubocop-performance (1.16.0)
-      rubocop (>= 1.7.0, < 2.0)
-      rubocop-ast (>= 0.4.0)
+      unicode-display_width (>= 2.4.0, < 4.0)
+    rubocop-ast (1.45.1)
+      parser (>= 3.3.7.2)
+      prism (~> 1.4)
+    rubocop-performance (1.25.0)
+      lint_roller (~> 1.1)
+      rubocop (>= 1.75.0, < 2.0)
+      rubocop-ast (>= 1.38.0, < 2.0)
     ruby-progressbar (1.13.0)
-    standard (1.26.0)
+    standard (1.50.0)
       language_server-protocol (~> 3.17.0.2)
-      rubocop (~> 1.48.1)
-      rubocop-performance (~> 1.16.0)
+      lint_roller (~> 1.0)
+      rubocop (~> 1.75.5)
+      standard-custom (~> 1.0.0)
+      standard-performance (~> 1.8)
+    standard-custom (1.0.2)
+      lint_roller (~> 1.0)
+      rubocop (~> 1.50)
+    standard-performance (1.8.0)
+      lint_roller (~> 1.1)
+      rubocop-performance (~> 1.25.0)
     suika (0.3.2)
       dartsclone (>= 0.2.0)
-    unicode-display_width (2.4.2)
+    unicode-display_width (3.1.4)
+      unicode-emoji (~> 4.0, >= 4.0.4)
+    unicode-emoji (4.0.4)
 
 PLATFORMS
   x86_64-linux

data/ke2daira.gemspec

@@ -0,0 +1,40 @@
+# frozen_string_literal: true
+
+require_relative "lib/ke2daira/version"
+
+Gem::Specification.new do |spec|
+  spec.name = "ke2daira"
+  spec.version = Ke2daira::VERSION
+  spec.authors = ["otariidae"]
+  spec.email = ["otariidae@users.noreply.github.com"]
+
+  spec.summary = "ke2daira"
+  spec.description = "A Ruby implementation of ke2daira"
+  spec.homepage = "https://github.com/otariidae/ke2daira.rb"
+  spec.license = "MIT"
+  spec.required_ruby_version = ">= 3.2.0"
+
+  spec.metadata["allowed_push_host"] = "https://rubygems.org"
+
+  spec.metadata["homepage_uri"] = spec.homepage
+  spec.metadata["source_code_uri"] = spec.homepage
+  spec.metadata["changelog_uri"] = "https://github.com/otariidae/ke2daira.rb/blob/main/CHANGELOG.md"
+
+  # Specify which files should be added to the gem when it is released.
+  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
+  spec.files = Dir.chdir(__dir__) do
+    `git ls-files -z`.split("\x0").reject do |f|
+      (f == __FILE__) || f.match(%r{\A(?:(?:bin|test|spec|features)/|\.(?:git|travis|circleci)|appveyor)})
+    end
+  end
+  spec.bindir = "exe"
+  spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  # Uncomment to register a new dependency of your gem
+  spec.add_dependency "suika", "~> 0.3.2"
+
+  # For more information and examples about making a new gem, check out our
+  # guide at: https://bundler.io/guides/creating_gem.html
+  spec.metadata["rubygems_mfa_required"] = "true"
+end

data/lib/ke2daira/kana2mora.rb

@@ -0,0 +1,23 @@
+# frozen_string_literal: true
+
+module Ke2daira
+  module Kana2Mora
+    SUTEKANA = Set["ァ", "ィ", "ゥ", "ェ", "ォ", "ャ", "ュ", "ョ", "ヮ"]
+
+    # converts Katakana into a list of mora.
+    def self.katakana2mora(katakana)
+      chars = katakana.chars
+      moras = []
+      chars.each do |char|
+        if SUTEKANA.include?(char)
+          previous_char = moras.pop || ""
+          mora = previous_char + char
+          moras << mora
+          next
+        end
+        moras << char
+      end
+      moras
+    end
+  end
+end

data/lib/ke2daira/ke2dairanizer.rb

@@ -0,0 +1,71 @@
+# frozen_string_literal: true
+
+require "suika"
+
+module Ke2daira
+  class Ke2dairanizer
+    def initialize(tagger: ::Suika::Tagger.new, separator: " ")
+      @tagger = tagger
+      @separator = separator
+    end
+
+    attr_reader :tagger, :separator
+
+    # Ke2dairanize the givin name
+    # @param fullname [String]
+    # @return [String] ke2dairanized name
+    def ke2dairanize(fullname) # rubocop:disable Metrics/AbcSize
+      names = fullname.strip.split(separator)
+      yomis = names.map { |name| to_yomi(name) }
+
+      return yomis[0] if yomis.length == 1
+
+      first_word_moras = Kana2Mora.katakana2mora(yomis[0])
+      first_word_head = first_word_moras[0]
+      first_word_tail = first_word_moras[1..]
+
+      last_word_moras = Kana2Mora.katakana2mora(yomis[-1])
+      last_word_head = last_word_moras[0]
+      last_word_tail = last_word_moras[1..]
+
+      new_first_word = last_word_head + first_word_tail.join
+      new_last_word = first_word_head + last_word_tail.join
+
+      yomis[0] = new_first_word
+      yomis[-1] = new_last_word
+      yomis.join(separator)
+    end
+
+    private
+
+    # Tokenize the givin sentence
+    # @param sentence [String] Japanese text to be tokenized
+    # @return [Array<SuikaToken>]
+    def tokenize(sentence)
+      raw_tokens = tagger.parse(sentence)
+      raw_tokens.map { |raw_token| raw_token2suikatoken(raw_token) }
+    end
+
+    # Convert Suika raw token to SuikaToken
+    # @param raw_token [String] Suika raw token
+    # @return [SuikaToken]
+    def raw_token2suikatoken(raw_token)
+      surface_form, rest_raw_token = raw_token.split("\t")
+      pos, pos_detail1, pos_detail2, pos_detail3, conjugated_type, conjugated_form,
+        basic_form, reading, pronunciation = rest_raw_token.split(",")
+      SuikaToken.new(surface_form, pos, pos_detail1, pos_detail2, pos_detail3, conjugated_type,
+        conjugated_form, basic_form, reading, pronunciation)
+    end
+
+    # Convert the givin word to its reading
+    # @param word [String] a Japanese word
+    # @return [String] reading of the word
+    def to_yomi(word)
+      tokens = tokenize(word)
+      # fallback to the surface form when the reading is missing
+      tokens.map do |token|
+        token.reading || token.surface_form
+      end.join
+    end
+  end
+end

data/lib/ke2daira/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Ke2daira
-  VERSION = "0.1.0"
+  VERSION = "0.2.1"
 end

data/lib/ke2daira.rb

@@ -1,69 +1,15 @@
 # frozen_string_literal: true
 
+require_relative "ke2daira/kana2mora"
+require_relative "ke2daira/ke2dairanizer"
 require_relative "ke2daira/version"
-require "suika"
 
 # Ke2daira is a library to ke2dairanize
 module Ke2daira
-  SEPARATOR = " "
-  private_constant :SEPARATOR
+  SuikaToken = Data.define(:surface_form, :pos, :pos_detail1, :pos_detail2, :pos_detail3, :conjugated_type, :conjugated_form, :basic_form, :reading, :pronunciation)
 
-  TAGGER = Suika::Tagger.new
-  private_constant :TAGGER
-
-  SuikaToken = Data.define(:surface_form, :pos, :pos_detail1, :pos_detail2, :pos_detail3, :conjugated_type,
-    :conjugated_form, :basic_form, :reading, :pronunciation)
-  private_constant :SuikaToken
-
-  # Ke2dairanize the givin name
-  # @param fullname [String]
-  # @return [String] ke2dairanized name
-  def self.ke2dairanize(fullname) # rubocop:disable Metrics/AbcSize
-    names = fullname.strip.split(SEPARATOR)
-    yomis = names.map { |name| to_yomi(name) }
-
-    return yomis[0] if yomis.length == 1
-
-    first_word = yomis[0]
-    last_word = yomis[-1]
-
-    # swap first characters of first and last name
-    yomis[0] = last_word[0] + first_word[1..]
-    yomis[-1] = first_word[0] + last_word[1..]
-    yomis.join(SEPARATOR)
-  end
-
-  class << self
-    private
-
-    # Tokenize the givin sentence
-    # @param sentence [String] Japanese text to be tokenized
-    # @return [Array<SuikaToken>]
-    def tokenize(sentence)
-      raw_tokens = TAGGER.parse(sentence)
-      raw_tokens.map { |raw_token| raw_token2suikatoken(raw_token) }
-    end
-
-    # Convert Suika raw token to SuikaToken
-    # @param raw_token [String] Suika raw token
-    # @return [SuikaToken]
-    def raw_token2suikatoken(raw_token)
-      surface_form, rest_raw_token = raw_token.split("\t")
-      pos, pos_detail1, pos_detail2, pos_detail3, conjugated_type, conjugated_form,
-        basic_form, reading, pronunciation = rest_raw_token.split(",")
-      SuikaToken.new(surface_form, pos, pos_detail1, pos_detail2, pos_detail3, conjugated_type,
-        conjugated_form, basic_form, reading, pronunciation)
-    end
-
-    # Convert the givin word to its reading
-    # @param word [String] a Japanese word
-    # @return [String] reading of the word
-    def to_yomi(word)
-      tokens = tokenize(word)
-      # fallback to the surface form when the reading is missing
-      tokens.map do |token|
-        token.reading || token.surface_form
-      end.join
-    end
+  def self.ke2dairanize(fullname)
+    @ke2dairanizer ||= Ke2dairanizer.new
+    @ke2dairanizer.ke2dairanize(fullname)
   end
 end

metadata

@@ -1,14 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: ke2daira
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.1
 platform: ruby
 authors:
 - otariidae
-autorequire: 
 bindir: exe
 cert_chain: []
-date: 2023-04-16 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: suika
@@ -38,7 +37,10 @@ files:
 - LICENSE.txt
 - README.md
 - Rakefile
+- ke2daira.gemspec
 - lib/ke2daira.rb
+- lib/ke2daira/kana2mora.rb
+- lib/ke2daira/ke2dairanizer.rb
 - lib/ke2daira/version.rb
 - sig/ke2daira.rbs
 homepage: https://github.com/otariidae/ke2daira.rb
@@ -50,7 +52,6 @@ metadata:
   source_code_uri: https://github.com/otariidae/ke2daira.rb
   changelog_uri: https://github.com/otariidae/ke2daira.rb/blob/main/CHANGELOG.md
   rubygems_mfa_required: 'true'
-post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
@@ -65,8 +66,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.4.10
-signing_key: 
+rubygems_version: 3.6.7
 specification_version: 4
 summary: ke2daira
 test_files: []