neologdish-normalizer 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: f2f96d57b26c4e44d37d47bcabcec5a820470d4e89beb59b709c2dc36ecd449b
+  data.tar.gz: fc7479594872db9c262cd13acf8e4f717936b289ead7fe136c65f0f211d32417
+SHA512:
+  metadata.gz: 84457e6fd2b5fae0b87d51a86b0e9a5c4aaf808b436ba97654c0939630fe19142c6bb2eb6729baeb0773882726aacffb62f67139be5c03b8c2404e74ca1b2408
+  data.tar.gz: 312f9993dceed61d3443f7ddb6c06904d49b21a52725be48721bf0683e75111b76b6b3bd53cde1d7a34315adb157f91306a75f3561f584af74d269bd71eb19aa

data/.rubocop.yml

@@ -0,0 +1,18 @@
+require:
+  - rubocop-rake
+  - rubocop-minitest
+
+AllCops:
+  NewCops: enable
+
+Metrics:
+  Enabled: false
+Layout/LineLength:
+  Max: 140
+Metrics/MethodLength:
+  Max: 14
+Layout/LeadingCommentSpace:
+  AllowRBSInlineAnnotation: true
+Minitest/MultipleAssertions:
+  Enabled: false
+

data/.ruby-version

@@ -0,0 +1 @@
+3.3

data/LICENSE

@@ -0,0 +1,8 @@
+Copyright 2024 Taiki Kawakami (a.k.a moznion) https://moznion.net
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the “Software”), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+

data/README.md

@@ -0,0 +1,53 @@
+# Neologdish::Normalizer for Ruby
+
+A Japanese text normalization library for Ruby follows the conventions of [neologd/mecab-ipadic-neologd](https://github.com/neologd/mecab-ipadic-neologd), with some performance optimizations, without external dependencies. It is designed to preprocess Japanese text before applying NLP techniques.
+
+The specific rules are documented here: https://github.com/neologd/mecab-ipadic-neologd/wiki/Regexp.ja
+
+## Usage
+
+```ruby
+require "neologdish-normalizer"
+
+Neologdish::Normalizer.normalize("南アルプスの　天然水-　Ｓｐａｒｋｉｎｇ*　Ｌｅｍｏｎ+　レモン一絞り")
+# => 南アルプスの天然水-Sparking*Lemon+レモン一絞り
+```
+
+## Benchmark
+
+The performance comparison between the official Ruby example (https://github.com/neologd/mecab-ipadic-neologd/wiki/Regexp.ja#ruby-written-by-kimoto-and-overlast) and this library is as follows:
+
+```
+                           user     system      total        real
+original normalizer:   4.200670   0.032004   4.232674 (  4.274573)
+this library:          1.158801   0.005238   1.164039 (  1.170226)
+```
+
+The benchmark script is here: [./scripts/benchmark.rb](./scripts/benchmark.rb)
+
+## Installation
+
+TODO: Replace `UPDATE_WITH_YOUR_GEM_NAME_IMMEDIATELY_AFTER_RELEASE_TO_RUBYGEMS_ORG` with your gem name right after releasing it to RubyGems.org. Please do not do it earlier due to security reasons. Alternatively, replace this section with instructions to install your gem from git if you don't plan to release to RubyGems.org.
+
+Install the gem and add to the application's Gemfile by executing:
+
+```bash
+bundle add UPDATE_WITH_YOUR_GEM_NAME_IMMEDIATELY_AFTER_RELEASE_TO_RUBYGEMS_ORG
+```
+
+If bundler is not being used to manage dependencies, install the gem by executing:
+
+```bash
+gem install UPDATE_WITH_YOUR_GEM_NAME_IMMEDIATELY_AFTER_RELEASE_TO_RUBYGEMS_ORG
+```
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and the created tag, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/moznion/neologdish-normalizer.
+

data/Rakefile

@@ -0,0 +1,20 @@
+# frozen_string_literal: true
+
+require 'bundler/gem_tasks'
+require 'rake/testtask'
+require 'rubocop/rake_task'
+
+task default: %i[]
+
+namespace :rbs do
+  task gen: %i[] do
+    sh 'rbs-inline --output --opt-out lib'
+  end
+end
+
+Rake::TestTask.new do |task|
+  task.libs = %w[lib test]
+  task.test_files = FileList['test/**/*.rb']
+end
+
+RuboCop::RakeTask.new

data/lib/neologdish/normalizer/version.rb

@@ -0,0 +1,7 @@
+# frozen_string_literal: true
+
+module Neologdish
+  module Normalizer
+    VERSION = '0.0.1' #: String
+  end
+end

data/lib/neologdish/normalizer.rb

@@ -0,0 +1,127 @@
+# frozen_string_literal: true
+
+require_relative 'normalizer/version'
+
+module Neologdish
+  # A Japanese text normalizer module according to the neologd convention.
+  module Normalizer
+    CONVERSION_MAP = {
+      # Normalize [0-9a-zA-Z] to half-width
+      '０' => '0', '１' => '1', '２' => '2', '３' => '3', '４' => '4', '５' => '5', '６' => '6', '７' => '7', '８' => '8', '９' => '9',
+      'Ａ' => 'A', 'Ｂ' => 'B', 'Ｃ' => 'C', 'Ｄ' => 'D', 'Ｅ' => 'E', 'Ｆ' => 'F', 'Ｇ' => 'G', 'Ｈ' => 'H', 'Ｉ' => 'I', 'Ｊ' => 'J',
+      'Ｋ' => 'K', 'Ｌ' => 'L', 'Ｍ' => 'M', 'Ｎ' => 'N', 'Ｏ' => 'O', 'Ｐ' => 'P', 'Ｑ' => 'Q', 'Ｒ' => 'R', 'Ｓ' => 'S', 'Ｔ' => 'T',
+      'Ｕ' => 'U', 'Ｖ' => 'V', 'Ｗ' => 'W', 'Ｘ' => 'X', 'Ｙ' => 'Y', 'Ｚ' => 'Z',
+      'ａ' => 'a', 'ｂ' => 'b', 'ｃ' => 'c', 'ｄ' => 'd', 'ｅ' => 'e', 'ｆ' => 'f', 'ｇ' => 'g', 'ｈ' => 'h', 'ｉ' => 'i', 'ｊ' => 'j',
+      'ｋ' => 'k', 'ｌ' => 'l', 'ｍ' => 'm', 'ｎ' => 'n', 'ｏ' => 'o', 'ｐ' => 'p', 'ｑ' => 'q', 'ｒ' => 'r', 'ｓ' => 's', 'ｔ' => 't',
+      'ｕ' => 'u', 'ｖ' => 'v', 'ｗ' => 'w', 'ｘ' => 'x', 'ｙ' => 'y', 'ｚ' => 'z',
+      # normalize the hyphen/minus-ish characters to '-'
+      '˗' => '-', '֊' => '-', '‐' => '-', '‑' => '-', '‒' => '-', '–' => '-', '⁃' => '-', '⁻' => '-', '₋' => '-', '−' => '-',
+      # normalize the long-vowel mark-ish characters to 'ー'
+      '﹣' => 'ー', '－' => 'ー', 'ｰ' => 'ー', '—' => 'ー', '―' => 'ー', '─' => 'ー', '━' => 'ー',
+      # remove the tilde-ish characters
+      '~' => '', '∼' => '', '∾' => '', '〜' => '', '〰' => '', '～' => '',
+      # normalize the full-width special symbol characters (/！”＃＄％＆’（）＊＋，−．／：；＜＞？＠［￥］＾＿｀｛｜｝) and space characters to half-width
+      '　' => ' ', '！' => '!', '”' => '"', '＃' => '#', '＄' => '$', '％' => '%', '＆' => '&', '’' => "'", '（' => '(', '）' => ')',
+      '＊' => '*', '＋' => '+', '，' => ',', '．' => '.', '／' => '/', '：' => ':', '；' => ';', '＜' => '<', '＞' => '>', '？' => '?',
+      '＠' => '@', '［' => '[', '￥' => '¥', '］' => ']', '＾' => '^', '＿' => '_', '｀' => '`', '｛' => '{', '｜' => '|', '｝' => '}',
+      # normalize the half-width special symbol characters (｡､･=｢｣) to full-width
+      '｡' => '。', '､' => '、', '･' => '・', '｢' => '「', '｣' => '」'
+    }.freeze #: Hash[String, String]
+
+    LATIN_MAP = {
+      '0' => true, '1' => true, '2' => true, '3' => true, '4' => true, '5' => true, '6' => true, '7' => true, '8' => true, '9' => true,
+      'A' => true, 'B' => true, 'C' => true, 'D' => true, 'E' => true, 'F' => true, 'G' => true, 'H' => true, 'I' => true, 'J' => true,
+      'K' => true, 'L' => true, 'M' => true, 'N' => true, 'O' => true, 'P' => true, 'Q' => true, 'R' => true, 'S' => true, 'T' => true,
+      'U' => true, 'V' => true, 'W' => true, 'X' => true, 'Y' => true, 'Z' => true,
+      'a' => true, 'b' => true, 'c' => true, 'd' => true, 'e' => true, 'f' => true, 'g' => true, 'h' => true, 'i' => true, 'j' => true,
+      'k' => true, 'l' => true, 'm' => true, 'n' => true, 'o' => true, 'p' => true, 'q' => true, 'r' => true, 's' => true, 't' => true,
+      'u' => true, 'v' => true, 'w' => true, 'x' => true, 'y' => true, 'z' => true
+    }.freeze #: Hash[String, bool]
+
+    HALF_WIDTH_KANA_MAP = {
+      'ｱ' => 'ア', 'ｲ' => 'イ', 'ｳ' => 'ウ', 'ｴ' => 'エ', 'ｵ' => 'オ',
+      'ｶ' => 'カ', 'ｷ' => 'キ', 'ｸ' => 'ク', 'ｹ' => 'ケ', 'ｺ' => 'コ',
+      'ｻ' => 'サ', 'ｼ' => 'シ', 'ｽ' => 'ス', 'ｾ' => 'セ', 'ｿ' => 'ソ',
+      'ﾀ' => 'タ', 'ﾁ' => 'チ', 'ﾂ' => 'ツ', 'ﾃ' => 'テ', 'ﾄ' => 'ト',
+      'ﾅ' => 'ナ', 'ﾆ' => 'ニ', 'ﾇ' => 'ヌ', 'ﾈ' => 'ネ', 'ﾉ' => 'ノ',
+      'ﾊ' => 'ハ', 'ﾋ' => 'ヒ', 'ﾌ' => 'フ', 'ﾍ' => 'ヘ', 'ﾎ' => 'ホ',
+      'ﾏ' => 'マ', 'ﾐ' => 'ミ', 'ﾑ' => 'ム', 'ﾒ' => 'メ', 'ﾓ' => 'モ',
+      'ﾔ' => 'ヤ', 'ﾕ' => 'ユ', 'ﾖ' => 'ヨ',
+      'ﾗ' => 'ラ', 'ﾘ' => 'リ', 'ﾙ' => 'ル', 'ﾚ' => 'レ', 'ﾛ' => 'ロ',
+      'ﾜ' => 'ワ', 'ｦ' => 'ヲ', 'ﾝ' => 'ン',
+      'ｧ' => 'ァ', 'ｨ' => 'ィ', 'ｩ' => 'ゥ', 'ｪ' => 'ェ', 'ｫ' => 'ォ',
+      'ｯ' => 'ッ', 'ｬ' => 'ヤ', 'ｭ' => 'ユ', 'ｮ' => 'ヨ'
+    }.freeze #: Hash[String, String]
+
+    DAKUON_KANA_MAP = {
+      'カ' => 'ガ', 'キ' => 'ギ', 'ク' => 'グ', 'ケ' => 'ゲ', 'コ' => 'ゴ',
+      'サ' => 'ザ', 'シ' => 'ジ', 'ス' => 'ズ', 'セ' => 'ゼ', 'ソ' => 'ゾ',
+      'タ' => 'ダ', 'チ' => 'ヂ', 'ツ' => 'ヅ', 'テ' => 'デ', 'ト' => 'ド',
+      'ハ' => 'バ', 'ヒ' => 'ビ', 'フ' => 'ブ', 'ヘ' => 'ベ', 'ホ' => 'ボ'
+    }.freeze #: Hash[String, String]
+
+    HANDAKUON_KANA_MAP = {
+      'ハ' => 'パ', 'ヒ' => 'ピ', 'フ' => 'プ', 'ヘ' => 'ペ', 'ホ' => 'ポ'
+    }.freeze #: Hash[String, String]
+
+    private_constant :CONVERSION_MAP, :LATIN_MAP, :HALF_WIDTH_KANA_MAP, :DAKUON_KANA_MAP, :HANDAKUON_KANA_MAP
+
+    # Normalize the given text.
+    #
+    # @rbs str: String
+    # @rbs return: String
+    def normalize(str)
+      squeezee = ''
+      prev_latin = false
+      whitespace_encountered = false
+      encountered_half_width_kana = nil
+      normalized = str.chars.map do |c|
+        prefix = ''
+        c = CONVERSION_MAP[c] || c
+
+        # normalize the Half-width kana to full-width
+        if encountered_half_width_kana
+          if (c == 'ﾞ' && (k = DAKUON_KANA_MAP[encountered_half_width_kana])) ||
+             (c == 'ﾟ' && (k = HANDAKUON_KANA_MAP[encountered_half_width_kana]))
+            c = ''
+            prefix = k
+          else
+            prefix = encountered_half_width_kana
+          end
+        end
+
+        if (encountered_half_width_kana = HALF_WIDTH_KANA_MAP[c])
+          c = ''
+        end
+
+        # squash consecutive special characters (space or long-vowel)
+        if [' ', 'ー'].include?(c)
+          if squeezee == c
+            c = ''
+          else
+            squeezee = c
+          end
+        else
+          squeezee = ''
+        end
+
+        # remove the white space character in the middle of non-latin characters
+        is_latin = LATIN_MAP[c] || false
+        if c == ' '
+          whitespace_encountered = prev_latin
+          c = ''
+        else
+          prefix = ' ' if is_latin && whitespace_encountered
+          whitespace_encountered = false
+        end
+        prev_latin = is_latin
+
+        prefix + c
+      end.join + (encountered_half_width_kana || '')
+
+      normalized.strip
+    end
+
+    module_function :normalize
+  end
+end

data/sig/generated/neologdish/normalizer/version.rbs

@@ -0,0 +1,7 @@
+# Generated from lib/neologdish/normalizer/version.rb with RBS::Inline
+
+module Neologdish
+  module Normalizer
+    VERSION: String
+  end
+end

data/sig/generated/neologdish/normalizer.rbs

@@ -0,0 +1,19 @@
+# Generated from lib/neologdish/normalizer.rb with RBS::Inline
+
+module Neologdish
+  module Normalizer
+    CONVERSION_MAP: Hash[String, String]
+
+    LATIN_MAP: Hash[String, bool]
+
+    HALF_WIDTH_KANA_MAP: Hash[String, String]
+
+    DAKUON_KANA_MAP: Hash[String, String]
+
+    HANDAKUON_KANA_MAP: Hash[String, String]
+
+    # @rbs str: String
+    # @rbs return: String
+    def normalize: (String str) -> String
+  end
+end

metadata

@@ -0,0 +1,57 @@
+--- !ruby/object:Gem::Specification
+name: neologdish-normalizer
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- moznion
+autorequire:
+bindir: exe
+cert_chain: []
+date: 2024-10-28 00:00:00.000000000 Z
+dependencies: []
+description: A Japanese text normalization library follows the conventions of neologd
+  with some performance optimizations. It is designed to preprocess Japanese text
+  before applying NLP techniques.
+email:
+- moznion@mail.moznion.net
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".rubocop.yml"
+- ".ruby-version"
+- LICENSE
+- README.md
+- Rakefile
+- lib/neologdish/normalizer.rb
+- lib/neologdish/normalizer/version.rb
+- sig/generated/neologdish/normalizer.rbs
+- sig/generated/neologdish/normalizer/version.rbs
+homepage: https://github.com/moznion/neologdish-normalizer
+licenses: []
+metadata:
+  homepage_uri: https://github.com/moznion/neologdish-normalizer
+  source_code_uri: https://github.com/moznion/neologdish-normalizer
+  changelog_uri: https://github.com/moznion/neologdish-normalizer/releases
+  rubygems_mfa_required: 'true'
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 3.0.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.5.22
+signing_key:
+specification_version: 4
+summary: A Japanese text normalization library follows the conventions of neologd
+test_files: []