charwidth 0.1.1 → 0.2.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 133819f5ab71a842c32836111306f610641d82cfd4a77c00bbcec383ac981ea7
+  data.tar.gz: a6b8a19034123788ae3954034d71fa3b58f25debf9e5501868b23fd6b9df1030
+SHA512:
+  metadata.gz: a3aaa79d412eb608c15d546c1b30e86b640ca9f3958665a656ca109fed36597879695d01dc39076088165ad00af307bfadd0a2f976edb502e23ad5b708b3ac1f
+  data.tar.gz: e02b783ac3c5b8d17488f2df375770232ad31b22c5bb43d7da0a946268a5a59b6188c34ca22ee310a144fb83405ec7ed1aa04c181ad5bdc84771162fa59fb7db

data/.gitignore

@@ -0,0 +1,18 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+.idea

data/.rubocop.yml

@@ -0,0 +1,127 @@
+AllCops:
+  Exclude:
+    - bin/*
+    - node_modules/**/*
+  NewCops: enable
+
+Layout/CaseIndentation:
+  EnforcedStyle: end
+
+Layout/EndAlignment:
+  EnforcedStyleAlignWith: variable
+
+Layout/LineLength:
+  Enabled: false
+
+Layout/EmptyLinesAroundAccessModifier:
+  EnforcedStyle: only_before
+
+Layout/SpaceInLambdaLiteral:
+  EnforcedStyle: require_space
+
+Layout/SpaceInsideBlockBraces:
+  SpaceBeforeBlockParameters: false
+
+Layout/SpaceInsideHashLiteralBraces:
+  EnforcedStyle: no_space
+
+Metrics/AbcSize:
+  Enabled: false
+
+Metrics/BlockLength:
+  Enabled: false
+
+Metrics/ClassLength:
+  Enabled: false
+
+Metrics/CyclomaticComplexity:
+  Enabled: false
+
+Metrics/MethodLength:
+  Enabled: false
+
+Metrics/ModuleLength:
+  Enabled: false
+
+Metrics/PerceivedComplexity:
+  Enabled: false
+
+Naming/HeredocDelimiterNaming:
+  Enabled: false
+
+Naming/MethodParameterName:
+  Enabled: false
+
+Naming/PredicateName:
+  Enabled: false
+
+Style/Alias:
+  EnforcedStyle: prefer_alias_method
+
+Style/AsciiComments:
+  Enabled: false
+
+Style/BlockDelimiters:
+  Enabled: false
+
+Style/Documentation:
+  Enabled: false
+
+Style/EmptyCaseCondition:
+  Enabled: false
+
+Style/EmptyMethod:
+  EnforcedStyle: expanded
+
+Style/FrozenStringLiteralComment:
+  Enabled: false
+
+Style/HashSyntax:
+  Exclude:
+    - Rakefile
+    - "**/*.rake"
+
+Style/Lambda:
+  EnforcedStyle: literal
+
+Style/IfUnlessModifier:
+  Enabled: false
+
+Style/MultilineBlockChain:
+  Enabled: false
+
+Style/NumericLiterals:
+  Enabled: false
+
+Style/NumericPredicate:
+  Enabled: false
+
+Style/PercentLiteralDelimiters:
+  PreferredDelimiters:
+    '%i': '()'
+    '%w': '()'
+    '%r': '()'
+
+Style/SpecialGlobalVars:
+  Enabled: false
+
+Style/StringLiterals:
+  EnforcedStyle: double_quotes
+
+Style/StringLiteralsInInterpolation:
+  EnforcedStyle: double_quotes
+
+Style/SymbolArray:
+  Enabled: false
+
+Style/TrailingCommaInArguments:
+  EnforcedStyleForMultiline: consistent_comma
+
+Style/TrailingCommaInArrayLiteral:
+  EnforcedStyleForMultiline: consistent_comma
+
+Style/TrailingCommaInHashLiteral:
+  EnforcedStyleForMultiline: consistent_comma
+
+Style/ZeroLengthPredicate:
+  Enabled: false

data/CHANGELOG.md

@@ -0,0 +1,27 @@
+### v0.2.1
+
+- Exclude dependency executables (rspec, rubocop). (Thank you @ta1kt0me for reporting an issue)
+
+### v0.2.0
+
+- Add `normalize_charwidth` method instead of problematic ActiveRecord integration.
+
+### v0.1.5
+
+- Fix active_record.rb to follow the change of AR after 5.2.
+
+### v0.1.4
+
+- Add Charwidth.to_full_width
+
+### v0.1.3
+
+- Change CLI behavier (Use ARGV as source text (not file name), show help for no augment with tty)
+
+### v0.1.1
+
+- Fix invalid convertion for harf-width katakana: TSU TE TO
+
+### v0.1.0
+
+- Initial release.

data/Gemfile

@@ -1,13 +1,12 @@
-source "http://rubygems.org"
-# Add dependencies required to use your gem here.
-# Example:
-#   gem "activesupport", ">= 2.3.5"
+source "https://rubygems.org"
 
-# Add dependencies to develop your gem here.
-# Include everything needed to run rake, tests, features, etc.
-group :development do
-  gem "rspec", "~> 2.3.0"
-  gem "bundler", "~> 1.0.0"
-  gem "jeweler", "~> 1.6.4"
-  gem "simplecov"
-end
+# Specify your gem's dependencies in charwidth_template.gemspec
+gemspec
+
+gem "activemodel", ">= 3"
+gem "bundler"
+gem "byebug"
+gem "rake"
+gem "rspec"
+gem "rspec-its"
+gem "rubocop"

data/Gemfile.lock

@@ -1,32 +1,78 @@
+PATH
+  remote: .
+  specs:
+    charwidth (0.2.1)
+
 GEM
-  remote: http://rubygems.org/
+  remote: https://rubygems.org/
   specs:
-    diff-lcs (1.1.3)
-    git (1.2.5)
-    jeweler (1.6.4)
-      bundler (~> 1.0)
-      git (>= 1.2.5)
-      rake
-    multi_json (1.0.4)
-    rake (0.9.2.2)
-    rspec (2.3.0)
-      rspec-core (~> 2.3.0)
-      rspec-expectations (~> 2.3.0)
-      rspec-mocks (~> 2.3.0)
-    rspec-core (2.3.1)
-    rspec-expectations (2.3.0)
-      diff-lcs (~> 1.1.2)
-    rspec-mocks (2.3.0)
-    simplecov (0.5.4)
-      multi_json (~> 1.0.3)
-      simplecov-html (~> 0.5.3)
-    simplecov-html (0.5.3)
+    activemodel (6.1.3.2)
+      activesupport (= 6.1.3.2)
+    activesupport (6.1.3.2)
+      concurrent-ruby (~> 1.0, >= 1.0.2)
+      i18n (>= 1.6, < 2)
+      minitest (>= 5.1)
+      tzinfo (~> 2.0)
+      zeitwerk (~> 2.3)
+    ast (2.4.2)
+    byebug (11.1.3)
+    concurrent-ruby (1.1.8)
+    diff-lcs (1.4.4)
+    i18n (1.8.10)
+      concurrent-ruby (~> 1.0)
+    minitest (5.14.4)
+    parallel (1.20.1)
+    parser (3.0.0.0)
+      ast (~> 2.4.1)
+    rainbow (3.0.0)
+    rake (13.0.3)
+    regexp_parser (2.1.1)
+    rexml (3.2.4)
+    rspec (3.10.0)
+      rspec-core (~> 3.10.0)
+      rspec-expectations (~> 3.10.0)
+      rspec-mocks (~> 3.10.0)
+    rspec-core (3.10.1)
+      rspec-support (~> 3.10.0)
+    rspec-expectations (3.10.1)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.10.0)
+    rspec-its (1.3.0)
+      rspec-core (>= 3.0.0)
+      rspec-expectations (>= 3.0.0)
+    rspec-mocks (3.10.2)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.10.0)
+    rspec-support (3.10.2)
+    rubocop (1.10.0)
+      parallel (~> 1.10)
+      parser (>= 3.0.0.0)
+      rainbow (>= 2.2.2, < 4.0)
+      regexp_parser (>= 1.8, < 3.0)
+      rexml
+      rubocop-ast (>= 1.2.0, < 2.0)
+      ruby-progressbar (~> 1.7)
+      unicode-display_width (>= 1.4.0, < 3.0)
+    rubocop-ast (1.4.1)
+      parser (>= 2.7.1.5)
+    ruby-progressbar (1.11.0)
+    tzinfo (2.0.4)
+      concurrent-ruby (~> 1.0)
+    unicode-display_width (2.0.0)
+    zeitwerk (2.4.2)
 
 PLATFORMS
   ruby
 
 DEPENDENCIES
-  bundler (~> 1.0.0)
-  jeweler (~> 1.6.4)
-  rspec (~> 2.3.0)
-  simplecov
+  activemodel (>= 3)
+  bundler
+  byebug
+  charwidth!
+  rake
+  rspec
+  rspec-its
+  rubocop
+
+BUNDLED WITH
+   2.1.2

data/LICENSE.txt

@@ -1,4 +1,6 @@
-Copyright (c) 2012 labocho
+Copyright (c) 2013 labocho
+
+MIT License
 
 Permission is hereby granted, free of charge, to any person obtaining
 a copy of this software and associated documentation files (the

data/README.md

@@ -4,7 +4,18 @@ Normalize Unicode fullwidth / halfwidth (zenkaku / hankaku) characters.
 
 # Installation
 
-    gem install charwidth
+Add this line to your application's Gemfile:
+
+    gem 'charwidth'
+
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install charwidth
 
 # Usage
 
@@ -19,19 +30,38 @@ Or extend String class.
     "Ｈｅｌｌｏ，　Ｗｏｒｌｄ！".normalize_charwidth # => "Hello, World!"
     "Ｈｅｌｌｏ，　Ｗｏｒｌｄ！".normalize_charwidth! # => destructive
     "｢ﾊﾛｰﾜｰﾙﾄﾞ｣".normalize_charwidth # => "「ハローワールド」"
-    
-# Contributing to charwidth
- 
-* Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet
-* Check out the issue tracker to make sure someone already hasn't requested it and/or contributed it
-* Fork the project
-* Start a feature/bugfix branch
-* Commit and push until you are happy with your contribution
-* Make sure to add tests for it. This is important so I don't break it in a future version unintentionally.
-* Please try not to mess with the Rakefile, version, or history. If you want to have your own version, or is otherwise necessary, that is fine, but please isolate to its own commit so I can cherry-pick around it.
-
-# Copyright
-
-Copyright (c) 2012 labocho. See LICENSE.txt for
-further details.
 
+# Rails integration
+
+Add lines below to `app/models/application_record.rb`.
+
+    require "charwidth/active_model"
+    class ApplicationRecord < ActiveRecord::Base
+      include Charwidth::ActiveModel
+    end
+
+And call `normalize_charwidth` class method in model class.
+
+    class Article < ActiveRecord::Base
+      normalize_charwidth :title, :body
+    end
+
+    a = Article.new(title: "Ｈｅｌｌｏ，　Ｗｏｒｌｄ！")
+    a.title # => "Hello, World!"
+
+# CLI
+
+    # Call charwidth command with arguments
+    $ charwidth "Ｈｅｌｌｏ，　Ｗｏｒｌｄ！"
+    Hello, World!
+    # Or as STDIN
+    $ echo "Ｈｅｌｌｏ，　Ｗｏｒｌｄ！" | charwidth
+    Hello, World!
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -1,51 +1 @@
-# encoding: utf-8
-
-require 'rubygems'
-require 'bundler'
-begin
-  Bundler.setup(:default, :development)
-rescue Bundler::BundlerError => e
-  $stderr.puts e.message
-  $stderr.puts "Run `bundle install` to install missing gems"
-  exit e.status_code
-end
-require 'rake'
-
-require 'jeweler'
-require "#{File.dirname(__FILE__)}/lib/charwidth/version"
-Jeweler::Tasks.new do |gem|
-  # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
-  gem.name = "charwidth"
-  gem.version = Charwidth::Version::STRING
-  gem.homepage = "http://github.com/labocho/charwidth"
-  gem.license = "MIT"
-  gem.summary = %Q{Normalize Japanese / Korean fullwidth (zenkaku) and halfwidth (hankaku) characters}
-  gem.description = %Q{Normalize Japanese / Korean fullwidth (zenkaku) and halfwidth (hankaku) characters}
-  gem.email = "labocho@penguinlab.jp"
-  gem.authors = ["labocho"]
-  # dependencies defined in Gemfile
-end
-Jeweler::RubygemsDotOrgTasks.new
-
-require 'rspec/core'
-require 'rspec/core/rake_task'
-RSpec::Core::RakeTask.new(:spec) do |spec|
-  spec.pattern = FileList['spec/**/*_spec.rb']
-end
-
-RSpec::Core::RakeTask.new(:rcov) do |spec|
-  spec.pattern = 'spec/**/*_spec.rb'
-  spec.rcov = true
-end
-
-task :default => :spec
-
-require 'rake/rdoctask'
-Rake::RDocTask.new do |rdoc|
-  version = File.exist?('VERSION') ? File.read('VERSION') : ""
-
-  rdoc.rdoc_dir = 'rdoc'
-  rdoc.title = "charwidth #{version}"
-  rdoc.rdoc_files.include('README*')
-  rdoc.rdoc_files.include('lib/**/*.rb')
-end
+require "bundler/gem_tasks"

data/bin/rspec

@@ -0,0 +1,29 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+#
+# This file was generated by Bundler.
+#
+# The application 'rspec' is installed as part of a gem, and
+# this file is here to facilitate running it.
+#
+
+require "pathname"
+ENV["BUNDLE_GEMFILE"] ||= File.expand_path("../../Gemfile",
+  Pathname.new(__FILE__).realpath)
+
+bundle_binstub = File.expand_path("../bundle", __FILE__)
+
+if File.file?(bundle_binstub)
+  if File.read(bundle_binstub, 300) =~ /This file was generated by Bundler/
+    load(bundle_binstub)
+  else
+    abort("Your `bin/bundle` was not generated by Bundler, so this binstub cannot run.
+Replace `bin/bundle` by running `bundle binstubs bundler --force`, then run this command again.")
+  end
+end
+
+require "rubygems"
+require "bundler/setup"
+
+load Gem.bin_path("rspec-core", "rspec")

data/bin/rubocop

@@ -0,0 +1,29 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+#
+# This file was generated by Bundler.
+#
+# The application 'rubocop' is installed as part of a gem, and
+# this file is here to facilitate running it.
+#
+
+require "pathname"
+ENV["BUNDLE_GEMFILE"] ||= File.expand_path("../../Gemfile",
+  Pathname.new(__FILE__).realpath)
+
+bundle_binstub = File.expand_path("../bundle", __FILE__)
+
+if File.file?(bundle_binstub)
+  if File.read(bundle_binstub, 300) =~ /This file was generated by Bundler/
+    load(bundle_binstub)
+  else
+    abort("Your `bin/bundle` was not generated by Bundler, so this binstub cannot run.
+Replace `bin/bundle` by running `bundle binstubs bundler --force`, then run this command again.")
+  end
+end
+
+require "rubygems"
+require "bundler/setup"
+
+load Gem.bin_path("rubocop", "rubocop")

data/charwidth.gemspec

@@ -1,63 +1,26 @@
-# Generated by jeweler
-# DO NOT EDIT THIS FILE DIRECTLY
-# Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
-# -*- encoding: utf-8 -*-
+require_relative "lib/charwidth/version"
 
-Gem::Specification.new do |s|
-  s.name = "charwidth"
-  s.version = "0.1.1"
+Gem::Specification.new do |spec|
+  spec.name          = "charwidth"
+  spec.version       = Charwidth::VERSION
+  spec.authors       = ["labocho"]
+  spec.email         = ["labocho@penguinlab.jp"]
+  spec.description   = "Normalize Japanese / Korean fullwidth (zenkaku) and halfwidth (hankaku) characters"
+  spec.summary       = "Normalize Japanese / Korean fullwidth (zenkaku) and halfwidth (hankaku) characters"
+  spec.homepage      = "https://github.com/labocho/charwidth"
+  spec.license       = "MIT"
+  spec.required_ruby_version = Gem::Requirement.new(">= 2.4.0")
 
-  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
-  s.authors = ["labocho"]
-  s.date = "2012-08-21"
-  s.description = "Normalize Japanese / Korean fullwidth (zenkaku) and halfwidth (hankaku) characters"
-  s.email = "labocho@penguinlab.jp"
-  s.extra_rdoc_files = [
-    "LICENSE.txt",
-    "README.md"
-  ]
-  s.files = [
-    ".cleancode",
-    ".document",
-    ".rspec",
-    "Gemfile",
-    "Gemfile.lock",
-    "LICENSE.txt",
-    "README.md",
-    "Rakefile",
-    "charwidth.gemspec",
-    "lib/charwidth.rb",
-    "lib/charwidth/characters.rb",
-    "lib/charwidth/string.rb",
-    "lib/charwidth/version.rb",
-    "spec/charwidth_spec.rb",
-    "spec/spec_helper.rb"
-  ]
-  s.homepage = "http://github.com/labocho/charwidth"
-  s.licenses = ["MIT"]
-  s.require_paths = ["lib"]
-  s.rubygems_version = "1.8.23"
-  s.summary = "Normalize Japanese / Korean fullwidth (zenkaku) and halfwidth (hankaku) characters"
+  spec.metadata["homepage_uri"] = spec.homepage
+  spec.metadata["source_code_uri"] = spec.homepage
+  spec.metadata["changelog_uri"] = "https://github.com/labocho/charwidth/blob/master/CHANGELOG.md"
 
-  if s.respond_to? :specification_version then
-    s.specification_version = 3
-
-    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
-      s.add_development_dependency(%q<rspec>, ["~> 2.3.0"])
-      s.add_development_dependency(%q<bundler>, ["~> 1.0.0"])
-      s.add_development_dependency(%q<jeweler>, ["~> 1.6.4"])
-      s.add_development_dependency(%q<simplecov>, [">= 0"])
-    else
-      s.add_dependency(%q<rspec>, ["~> 2.3.0"])
-      s.add_dependency(%q<bundler>, ["~> 1.0.0"])
-      s.add_dependency(%q<jeweler>, ["~> 1.6.4"])
-      s.add_dependency(%q<simplecov>, [">= 0"])
-    end
-  else
-    s.add_dependency(%q<rspec>, ["~> 2.3.0"])
-    s.add_dependency(%q<bundler>, ["~> 1.0.0"])
-    s.add_dependency(%q<jeweler>, ["~> 1.6.4"])
-    s.add_dependency(%q<simplecov>, [">= 0"])
+  # 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(File.expand_path(__dir__)) do
+    `git ls-files -z`.split("\x0").reject {|f| f.match(%r{^(test|spec|features)/}) }
   end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r(^exe/)) {|f| File.basename(f) }
+  spec.require_paths = ["lib"]
 end
-

data/exe/charwidth

@@ -0,0 +1,3 @@
+#!/usr/bin/env ruby
+require "charwidth"
+Charwidth::CLI.run(ARGV)

data/lib/charwidth.rb

@@ -1,9 +1,46 @@
+require "charwidth/version"
+
 module Charwidth
   autoload :String, "charwidth/string"
   autoload :Characters, "charwidth/characters"
-  autoload :Version, "charwidth/version"
+  autoload :CLI, "charwidth/cli"
 
   module ClassMethods
+    HALFWIDTH_TO_FULLWIDTH = {
+      ascii: [
+        Characters::ASCII_PUNCTUATION_AND_SYMBOLS,
+        Characters::FULLWIDTH_ASCII_VARIANTS,
+      ],
+      white_parenthesis: [
+        Characters::WHITE_PARENTHESIS,
+        Characters::FULLWIDTH_BRACKETS,
+      ],
+      cjk_punctuation: [
+        Characters::HALFWIDTH_CJK_PUCTUATION,
+        Characters::CJK_SYMBOLS_AND_PUNCTUATION,
+      ],
+      katakana: [
+        Characters::HALFWIDTH_KATAKANA_VARIANTS,
+        Characters::KATAKANA,
+      ],
+      hangul: [
+        Characters::HALFWIDTH_HANGUL_VARIANTS,
+        Characters::HANGUL,
+      ],
+      latin_1_punctuation_and_symbols: [
+        Characters::LATIN_1_PUNCTUATION_AND_SYMBOLS,
+        Characters::FULLWIDTH_SYMBOL_VARIANTS,
+      ],
+      mathematical_symbols: [
+        Characters::HALFWIDTH_SYMBOL_VARIANTS,
+        Characters::MATHEMATICAL_SYMBOLS,
+      ],
+      space: [
+        Characters::SPACE,
+        Characters::IDEOGRAPHIC_SPACE,
+      ],
+    }.transform_values(&:freeze).freeze
+
     # Normalize Unicode fullwidth / halfwidth (zenkaku / hankaku) characters
     # options: {
     #   only: [:ascii, :white_parenthesis, :cjk_punctuation, :katakana, :space],
@@ -19,10 +56,29 @@ module Charwidth
       normalize_charwidth!(string, options)
     end
 
+    def to_full_width(string)
+      to_full_width!(string.dup)
+    end
+
+    def to_full_width!(src)
+      unify_voiced_katakana!(src)
+
+      before = ""
+      after = ""
+      HALFWIDTH_TO_FULLWIDTH.each_value do |half, full|
+        before << half
+        after << full
+      end
+
+      escape_for_tr!(before)
+      escape_for_tr!(after)
+      src.tr!(before, after) || src
+    end
+
     private
     TYPES = [
       :ascii, :white_parenthesis, :cjk_punctuation, :katakana, :hangul,
-      :latin_1_punctuation_and_symbols, :mathematical_symbols, :space
+      :latin_1_punctuation_and_symbols, :mathematical_symbols, :space,
     ].freeze
     def normalize_charwidth!(src, options = {})
       types = TYPES.dup
@@ -36,47 +92,39 @@ module Charwidth
         unless (unexpected_types = options[:only] - TYPES).empty?
           raise "Unexpected normalize type(s): #{unexpected_types.inspect}"
         end
-        types = types & options[:only]
+
+        types &= options[:only]
       end
 
       if options[:expect]
         unless (unexpected_types = options[:expected] - TYPES).empty?
-          raise "Unexpected normalize type(s): #{t.inspect}"
+          raise "Unexpected normalize type(s): #{unexpected_types.inspect}"
         end
-        types = types - options[:expect]
+
+        types -= options[:expect]
       end
 
-      before, after = "", ""
+      before = ""
+      after = ""
       types.each do |type|
         case type
-        when :ascii
-          before << Characters::FULLWIDTH_ASCII_VARIANTS
-          after << Characters::ASCII_PUNCTUATION_AND_SYMBOLS
-        when :white_parenthesis
-          before << Characters::FULLWIDTH_BRACKETS
-          after << Characters::WHITE_PARENTHESIS
-        when :cjk_punctuation
-          before << Characters::HALFWIDTH_CJK_PUCTUATION
-          after << Characters::CJK_SYMBOLS_AND_PUNCTUATION
-        when :katakana
-          before << Characters::HALFWIDTH_KATAKANA_VARIANTS
-          after << Characters::KATAKANA
-        when :hangul
-          before << Characters::HALFWIDTH_HANGUL_VARIANTS
-          after << Characters::HANGUL
-        when :latin_1_punctuation_and_symbols
-          before << Characters::FULLWIDTH_SYMBOL_VARIANTS
-          after << Characters::LATIN_1_PUNCTUATION_AND_SYMBOLS
-        when :mathematical_symbols
-          before << Characters::HALFWIDTH_SYMBOL_VARIANTS
-          after << Characters::MATHEMATICAL_SYMBOLS
-        when :space
-          before << Characters::IDEOGRAPHIC_SPACE
-          after << Characters::SPACE
+        when :ascii, :white_parenthesis, :latin_1_punctuation_and_symbols, :space
+          # convert fullwidth to halfwidth
+          HALFWIDTH_TO_FULLWIDTH[type].tap {|half, full|
+            before << full
+            after << half
+          }
+        when :cjk_punctuation, :katakana, :hangul, :mathematical_symbols
+          # convert halfwidth to fullwidth
+          HALFWIDTH_TO_FULLWIDTH[type].tap {|half, full|
+            before << half
+            after << full
+          }
         end
       end
 
-      after.sub!('\\', '\\\\\\\\') # escape for tr
+      escape_for_tr!(before)
+      escape_for_tr!(after)
       src.tr!(before, after) || src
     end
 
@@ -92,6 +140,15 @@ module Charwidth
         str.gsub!(h, f) || str
       end
     end
+
+    def escape_for_tr!(s)
+      s.gsub!('\\', '\\\\')
+      s.gsub!("-", '\\-')
+      s.gsub!("^", '\\^')
+      s.gsub!("[", '\\[')
+      s.gsub!("]", '\\]')
+      s
+    end
   end
 
   extend ClassMethods

data/lib/charwidth/active_model.rb

@@ -0,0 +1,24 @@
+require "charwidth"
+
+module Charwidth
+  module ActiveModel
+    module ClassMethods
+      def normalize_charwidth(*attribute_names)
+        m = Module.new do
+          attribute_names.each do |attribute|
+            define_method "#{attribute}=" do |v|
+              super(v.nil? ? nil : Charwidth.normalize(v.to_s))
+            end
+          end
+        end
+        prepend m
+      end
+    end
+
+    def self.included(base)
+      base.class_eval do
+        extend ClassMethods
+      end
+    end
+  end
+end

data/lib/charwidth/characters.rb

@@ -10,7 +10,7 @@ module Charwidth
       (0xffc2..0xffc7).to_a,
       (0xffca..0xffcf).to_a,
       (0xffd2..0xffd7).to_a,
-      (0xffda..0xffdc).to_a
+      (0xffda..0xffdc).to_a,
     ].flatten.pack("U*").freeze
     FULLWIDTH_SYMBOL_VARIANTS = (0xffe0..0xffe6).to_a.pack("U*").freeze
     HALFWIDTH_SYMBOL_VARIANTS = (0xffe8..0xffee).to_a.pack("U*").freeze
@@ -39,7 +39,7 @@ module Charwidth
     ].flatten.pack("U*").freeze
     HANGUL = [
       0x3164, # HANGUL FILLER
-      (0x3131..0x3163).to_a # HANGUL LETTER KIYEOK to I
+      (0x3131..0x3163).to_a, # HANGUL LETTER KIYEOK to I
     ].flatten.pack("U*").freeze
     LATIN_1_PUNCTUATION_AND_SYMBOLS = [
       0x00a2, # CENT SIGN
@@ -48,33 +48,33 @@ module Charwidth
       0x00af, # MACRON
       0x00a6, # BROKEN BAR
       0x00a5, # YEN SIGN
-      0x20a9  # WON SIGN
+      0x20a9, # WON SIGN
     ].pack("U*").freeze
     MATHEMATICAL_SYMBOLS = [
       0x2502, # BOX DRAWINGS LIGHT VERTICAL
       (0x2190..0x2193).to_a, # LEFTWARDS, UPWARDS, RIGHTWARDS, DOWNWARDS ARROW
       0x25a0, # BLACK SQUARE
-      0x25cb  # WHITE CIRCLE
+      0x25cb, # WHITE CIRCLE
     ].flatten.pack("U*").freeze
     SPACE = "\u0020".freeze
 
-    HALFWIDTH_KATAKANA_VOICED_SOUND_MARK = "\uff9e"
+    HALFWIDTH_KATAKANA_VOICED_SOUND_MARK = "\uff9e".freeze
     HALFWIDTH_VOICED_KATAKANA = [
       (0xff76..0xff84).to_a, # HALFWIDTH KATAKANA LETTER KA to TO
       (0xff8a..0xff8e).to_a, # HALFWIDTH KATAKANA LETTER HA to HO
-      0xff73 # HALFWIDTH KATAKANA LETTER U
-    ].flatten.map{|k| ([k].pack("U") + HALFWIDTH_KATAKANA_VOICED_SOUND_MARK).freeze }.freeze
+      0xff73, # HALFWIDTH KATAKANA LETTER U
+    ].flatten.map {|k| ([k].pack("U") + HALFWIDTH_KATAKANA_VOICED_SOUND_MARK).freeze }.freeze
     VOICED_KATAKANA = [
       0x30ac.step(0x30be, 2).to_a, # KATAKANA LETTER GA to ZO
       [0x30c0, 0x30c2, 0x30c5, 0x30c7, 0x30c9], # KATAKANA LETTER DA to DO
       0x30d0.step(0x30dc, 3).to_a, # KATAKANA LETTER BA to BO
-      0x30f4 # KATAKANA LETTER VU
-    ].flatten.map{|c| [c].pack("U").freeze }.freeze
+      0x30f4, # KATAKANA LETTER VU
+    ].flatten.map {|c| [c].pack("U").freeze }.freeze
 
-    HALFWIDTH_KATAKANA_SEMI_VOICED_SOUND_MARK = "\uff9f"
+    HALFWIDTH_KATAKANA_SEMI_VOICED_SOUND_MARK = "\uff9f".freeze
     HALFWIDTH_SEMI_VOICED_KATAKANA = [
-      (0xff8a..0xff8e).to_a # HALFWIDTH KATAKANA LETTER HA to HO
-    ].flatten.map{|k| ([k].pack("U") + HALFWIDTH_KATAKANA_SEMI_VOICED_SOUND_MARK).freeze }.freeze
-    SEMI_VOICED_KATAKANA = 0x30d1.step(0x30dd, 3).map{|c| [c].pack("U").freeze }.flatten.freeze # KATAKANA LETTER PA to PO
+      (0xff8a..0xff8e).to_a, # HALFWIDTH KATAKANA LETTER HA to HO
+    ].flatten.map {|k| ([k].pack("U") + HALFWIDTH_KATAKANA_SEMI_VOICED_SOUND_MARK).freeze }.freeze
+    SEMI_VOICED_KATAKANA = 0x30d1.step(0x30dd, 3).map {|c| [c].pack("U").freeze }.flatten.freeze # KATAKANA LETTER PA to PO
   end
 end

data/lib/charwidth/cli.rb

@@ -0,0 +1,31 @@
+require "optparse"
+module Charwidth
+  class CLI
+    def self.run(argv)
+      new.run(argv)
+    end
+
+    def run(argv)
+      options = {}
+      optparse = OptionParser.new do |o|
+        o.banner += " TEXT\nNormalize character width in arguments or STDIN.\nAvailable character types are #{Charwidth::ClassMethods::TYPES.join(",")}."
+        o.on("--only=TYPES", "Comma separated character types that should be converted") {|types| options[:only] = types.split(",").map(&:to_sym) }
+        o.on("--except=TYPES", "Comma separated character types that should not be converted") {|types| options[:except] = types.split(",").map(&:to_sym) }
+        o.parse!(argv)
+      end
+      src = nil
+      if ARGV.empty?
+        if $stdin.tty?
+          warn optparse.banner
+          warn optparse.help
+          exit 1
+        else
+          src = $stdin.read
+        end
+      else
+        src = ARGV.join(" ")
+      end
+      print Charwidth.normalize(src, options)
+    end
+  end
+end

data/lib/charwidth/string.rb

@@ -8,6 +8,14 @@ module Charwidth
     def normalize_charwidth!(options = {})
       Charwidth.normalize!(self, options)
     end
+
+    def to_full_width
+      dup.to_full_width!
+    end
+
+    def to_full_width!
+      Charwidth.to_full_width!(self)
+    end
   end
 end
 

data/lib/charwidth/version.rb

@@ -1,9 +1,3 @@
 module Charwidth
-  module Version
-    MAJOR = 0
-    MINOR = 1
-    PATCH = 1
-    BUILD = nil
-    STRING = [MAJOR, MINOR, PATCH, BUILD].compact.join('.')
-  end
+  VERSION = "0.2.1".freeze
 end

metadata

@@ -1,130 +1,69 @@
 --- !ruby/object:Gem::Specification
 name: charwidth
 version: !ruby/object:Gem::Version
-  version: 0.1.1
-  prerelease: 
+  version: 0.2.1
 platform: ruby
 authors:
 - labocho
-autorequire: 
-bindir: bin
+autorequire:
+bindir: exe
 cert_chain: []
-date: 2012-08-21 00:00:00.000000000 Z
-dependencies:
-- !ruby/object:Gem::Dependency
-  name: rspec
-  requirement: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ~>
-      - !ruby/object:Gem::Version
-        version: 2.3.0
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ~>
-      - !ruby/object:Gem::Version
-        version: 2.3.0
-- !ruby/object:Gem::Dependency
-  name: bundler
-  requirement: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ~>
-      - !ruby/object:Gem::Version
-        version: 1.0.0
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ~>
-      - !ruby/object:Gem::Version
-        version: 1.0.0
-- !ruby/object:Gem::Dependency
-  name: jeweler
-  requirement: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ~>
-      - !ruby/object:Gem::Version
-        version: 1.6.4
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ~>
-      - !ruby/object:Gem::Version
-        version: 1.6.4
-- !ruby/object:Gem::Dependency
-  name: simplecov
-  requirement: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
+date: 2021-06-15 00:00:00.000000000 Z
+dependencies: []
 description: Normalize Japanese / Korean fullwidth (zenkaku) and halfwidth (hankaku)
   characters
-email: labocho@penguinlab.jp
-executables: []
+email:
+- labocho@penguinlab.jp
+executables:
+- charwidth
 extensions: []
-extra_rdoc_files:
-- LICENSE.txt
-- README.md
+extra_rdoc_files: []
 files:
-- .cleancode
-- .document
-- .rspec
+- ".cleancode"
+- ".document"
+- ".gitignore"
+- ".rspec"
+- ".rubocop.yml"
+- CHANGELOG.md
 - Gemfile
 - Gemfile.lock
 - LICENSE.txt
 - README.md
 - Rakefile
+- bin/rspec
+- bin/rubocop
 - charwidth.gemspec
+- exe/charwidth
 - lib/charwidth.rb
+- lib/charwidth/active_model.rb
 - lib/charwidth/characters.rb
+- lib/charwidth/cli.rb
 - lib/charwidth/string.rb
 - lib/charwidth/version.rb
-- spec/charwidth_spec.rb
-- spec/spec_helper.rb
-homepage: http://github.com/labocho/charwidth
+homepage: https://github.com/labocho/charwidth
 licenses:
 - MIT
-post_install_message: 
+metadata:
+  homepage_uri: https://github.com/labocho/charwidth
+  source_code_uri: https://github.com/labocho/charwidth
+  changelog_uri: https://github.com/labocho/charwidth/blob/master/CHANGELOG.md
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
-      segments:
-      - 0
-      hash: -548817087615038840
+      version: 2.4.0
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 1.8.23
-signing_key: 
-specification_version: 3
+rubygems_version: 3.1.2
+signing_key:
+specification_version: 4
 summary: Normalize Japanese / Korean fullwidth (zenkaku) and halfwidth (hankaku) characters
 test_files: []

data/spec/charwidth_spec.rb

@@ -1,44 +0,0 @@
-# encoding: UTF-8
-require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
-
-describe "Charwidth" do
-  it "should convert full-width alphabet to half-width" do
-    Charwidth.normalize("ＡＢＣａｂｃ").should == "ABCabc"
-  end
-  it "should convert full-width number to half-width" do
-    Charwidth.normalize("１２３").should == "123"
-  end
-  it "should convert full-width ASCII symbol before numbers to half-width" do
-    Charwidth.normalize("！＂＃").should == "!\"#"
-  end
-  it "should convert full-width ASCII symbol between numbers and upper-case to half-width" do
-    Charwidth.normalize("：；").should == ":;"
-  end
-  it "should convert full-width ASCII symbol between upper-case and lower-case to half-width" do
-    Charwidth.normalize("［＼］").should == "[\\]"
-  end
-  it "should convert full-width ASCII symbol after lower-case to half-width" do
-    Charwidth.normalize("｛｜｝").should == "{|}"
-  end
-
-  it "should convert half-width CJK punctuation to full-width" do
-    Charwidth.normalize("､｡｢｣").should == "、。「」"
-  end
-
-  it "should convert half-width katakana to full-width" do
-    Charwidth.normalize("ｱｶｻﾀﾅﾊﾏﾔﾗﾜｦﾝｧｬｯｰ･").should == "アカサタナハマヤラワヲンァャッー・"
-    Charwidth.normalize("ﾀﾁﾂﾃﾄﾅﾆﾇﾈﾉ").should == "タチツテトナニヌネノ"
-  end
-
-  it "should unify half-width (semi) voiced katakana with dakuon to full-width" do
-    Charwidth.normalize("ｶﾞｻﾞﾀﾞﾊﾞﾊﾟ").should == "ガザダバパ"
-  end
-
-  it "should convert half-width hangul to full-width" do
-    Charwidth.normalize("ｱｶｻﾀﾅﾊﾏﾔﾗﾜｦﾝｧｬｯｰ･").should == "アカサタナハマヤラワヲンァャッー・"
-  end
-
-  it "should convert IDIOGRAPHIC-SPACE to SPACE" do
-    Charwidth.normalize("\u3000").should == " "
-  end
-end

data/spec/spec_helper.rb

@@ -1,12 +0,0 @@
-$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
-$LOAD_PATH.unshift(File.dirname(__FILE__))
-require 'rspec'
-require 'charwidth'
-
-# Requires supporting files with custom matchers and macros, etc,
-# in ./support/ and its subdirectories.
-Dir["#{File.dirname(__FILE__)}/support/**/*.rb"].each {|f| require f}
-
-RSpec.configure do |config|
-
-end