suika 0.3.1 → 0.3.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 148e229070959a89197febf9bf9eabfdbe941f3c1cda66b75f87afb9371436c1
-  data.tar.gz: c6d4fa8c654144ad39e19ff23d63161ea193bd8760eb654635d36666bed6f2dd
+  metadata.gz: 7d6745438c0a8281903fe9cd22adb6db0b4226b3b8b0677e90ecba65fc287b8c
+  data.tar.gz: 4c512813f3c9b14083fa53c91dc8c95e570344c836c1303147f25c3e3eab35f9
 SHA512:
-  metadata.gz: dbe9535910050678c51c3ff2d95118959d3b4cdeb4fffb2fb405ad5871258f527d1fa3f36df59706b3cf3d8c6265f19bd5844d778273fc369fc763eec293cf89
-  data.tar.gz: 063ed20722d52ac97b4993093a60ad866fd744c8e74361b3934c1f96082523da510f8d7adcbb46e238aa03ba7dbf53539180215aa5475488294a77d92ea8633e
+  metadata.gz: 5b0f9ce528cb4751399e5976fb744c4eee8300044ca8dbe10f26b90e25ef9e63764ee7b2319ae0ab7dff63ad03449d88f0ccd7df89765db19cbcce7479480a7d
+  data.tar.gz: 828cdce758ac69c326a2d88dd8a72744434e2ac7eca70aa773b37f06a9f92fd3199963cb2b153ec8bfe4edecbfb0478676036a236514c69c6b1f799848a6fdbd

data/CHANGELOG.md

@@ -1,3 +1,12 @@
+## 0.3.3
+
+- Add csv and nkf gems to runtime dependencies for Ruby 3.4.
+- Refactor codes and configs with RuboCop.
+
+## 0.3.2
+
+- Refactor codes and configs with RuboCop.
+
 ## 0.3.1
 - Fix Tagger's inspect method not to expand instance variables for object creation on irb and pry.
 

data/LICENSE.txt

@@ -1,4 +1,4 @@
-Copyright (c) 2020-2021 Atsushi Tatsuma
+Copyright (c) 2020-2024 Atsushi Tatsuma
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without

data/README.md

@@ -1,7 +1,6 @@
 # Suika
 
 [![Build Status](https://github.com/yoshoku/suika/workflows/build/badge.svg)](https://github.com/yoshoku/suika/actions?query=workflow%3Abuild)
-[![Coverage Status](https://coveralls.io/repos/github/yoshoku/suika/badge.svg?branch=main)](https://coveralls.io/github/yoshoku/suika?branch=main)
 [![Gem Version](https://badge.fury.io/rb/suika.svg)](https://badge.fury.io/rb/suika)
 [![BSD 3-Clause License](https://img.shields.io/badge/License-BSD%203--Clause-orange.svg)](https://github.com/yoshoku/suika/blob/main/LICENSE.txt)
 [![Documentation](https://img.shields.io/badge/api-reference-blue.svg)](https://rubydoc.info/gems/suika)
@@ -75,7 +74,8 @@ end
 ## Contributing
 
 Bug reports and pull requests are welcome on GitHub at https://github.com/yoshoku/suika.
-This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [code of conduct](https://github.com/yoshoku/suika/blob/main/CODE_OF_CONDUCT.md).
+This project is intended to be a safe, welcoming space for collaboration,
+and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
 
 ## License
 
@@ -92,7 +92,3 @@ Suika is created with reference to [the book on morphological analysis](https://
 - [Tomoko Uchida](https://github.com/mocobeta) is the author of [Janome](https://github.com/mocobeta/janome) that is a Japanese morphological analysis engine written in pure Python.
 Suika is heavily influenced by Janome's idea to include the built-in dictionary and language model.
 Janome, a morphological analyzer written in scripting language, gives me the courage to develop Suika.
-
-## Code of Conduct
-
-Everyone interacting in the Suika project's codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/yoshoku/suika/blob/main/CODE_OF_CONDUCT.md).

data/lib/suika/tagger.rb

@@ -24,7 +24,7 @@ module Suika
   class Tagger
     # Create a new tagger by loading the built-in binary dictionary.
     def initialize
-      raise IOError, 'SHA1 digest of dictionary file does not match.' unless DICTIONARY_KEY == Digest::SHA1.file(DICTIONARY_PATH).to_s
+      raise IOError, 'SHA1 digest of dictionary file does not match.' unless Digest::SHA1.file(DICTIONARY_PATH).to_s == DICTIONARY_KEY
 
       @sysdic = Marshal.load(Zlib::GzipReader.open(DICTIONARY_PATH, &:read))
       @trie = DartsClone::DoubleArray.new
@@ -34,7 +34,7 @@ module Suika
     # Parse the given sentence.
     # @param sentence [String] Japanese text to be parsed.
     # @return [Array<String>]
-    def parse(sentence)
+    def parse(sentence) # rubocop:disable Metrics/AbcSize, Metrics/CyclomaticComplexity, Metrics/PerceivedComplexity
       lattice = Lattice.new(sentence.length)
       start = 0
       terminal = sentence.length

data/lib/suika/version.rb

@@ -3,5 +3,5 @@
 # Suika is a Japanese morphological analyzer written in pure Ruby.
 module Suika
   # The version of Suika you are using.
-  VERSION = '0.3.1'
+  VERSION = '0.3.3'
 end

metadata

@@ -1,15 +1,28 @@
 --- !ruby/object:Gem::Specification
 name: suika
 version: !ruby/object:Gem::Version
-  version: 0.3.1
+  version: 0.3.3
 platform: ruby
 authors:
 - yoshoku
-autorequire: 
 bindir: exe
 cert_chain: []
-date: 2021-07-03 00:00:00.000000000 Z
+date: 2024-12-29 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: csv
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 3.1.9
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 3.1.9
 - !ruby/object:Gem::Dependency
   name: dartsclone
   requirement: !ruby/object:Gem::Requirement
@@ -24,6 +37,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: 0.2.0
+- !ruby/object:Gem::Dependency
+  name: nkf
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.1.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.1.1
 description: Suika is a Japanese morphological analyzer written in pure Ruby.
 email:
 - yoshoku@outlook.com
@@ -31,22 +58,10 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- ".coveralls.yml"
-- ".github/workflows/build.yml"
-- ".github/workflows/coverage.yml"
-- ".gitignore"
-- ".rspec"
-- ".rubocop.yml"
 - CHANGELOG.md
-- CODE_OF_CONDUCT.md
-- Gemfile
 - LICENSE.txt
 - NOTICE.txt
 - README.md
-- Rakefile
-- Steepfile
-- bin/console
-- bin/setup
 - dict/sysdic.gz
 - lib/suika.rb
 - lib/suika/char_def.rb
@@ -59,7 +74,6 @@ files:
 - sig/suika/lattice.rbs
 - sig/suika/node.rbs
 - sig/suika/tagger.rbs
-- suika.gemspec
 homepage: https://github.com/yoshoku/suika
 licenses:
 - BSD-3-Clause
@@ -68,7 +82,7 @@ metadata:
   source_code_uri: https://github.com/yoshoku/suika
   changelog_uri: https://github.com/yoshoku/suika/blob/main/CHANGELOG.md
   documentation_uri: https://rubydoc.info/gems/suika
-post_install_message: 
+  rubygems_mfa_required: 'true'
 rdoc_options: []
 require_paths:
 - lib
@@ -83,8 +97,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.21
-signing_key: 
+rubygems_version: 3.6.2
 specification_version: 4
 summary: Suika is a Japanese morphological analyzer written in pure Ruby.
 test_files: []

data/.coveralls.yml

@@ -1 +0,0 @@
-service_name: github-ci

data/.github/workflows/build.yml

@@ -1,21 +0,0 @@
-name: build
-
-on: [push, pull_request]
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        ruby: [ '2.6', '2.7', '3.0' ]
-    steps:
-      - uses: actions/checkout@v2
-      - name: Set up Ruby ${{ matrix.ruby }}
-        uses: actions/setup-ruby@v1
-        with:
-          ruby-version: ${{ matrix.ruby }}
-      - name: Build and test with Rake
-        run: |
-          gem install --no-document bundler
-          bundle install --jobs 4 --retry 3
-          bundle exec rake

data/.github/workflows/coverage.yml

@@ -1,26 +0,0 @@
-name: coverage
-
-on:
-  push:
-    branches: [ main ]
-  pull_request:
-    branches: [ main ]
-
-jobs:
-  coverage:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v2
-      - name: Set up Ruby 2.7
-        uses: actions/setup-ruby@v1
-        with:
-          ruby-version: '2.7'
-      - name: Build and test with Rake
-        run: |
-          gem install --no-document bundler
-          bundle install --jobs 4 --retry 3
-          bundle exec rake
-      - name: Coveralls GitHub Action
-        uses: coverallsapp/github-action@v1.1.2
-        with:
-          github-token: ${{ secrets.GITHUB_TOKEN }}

data/.gitignore

@@ -1,16 +0,0 @@
-/.bundle/
-/.yardoc
-/_yardoc/
-/coverage/
-/doc/
-/pkg/
-/spec/reports/
-/tmp/
-
-# rspec failure tracking
-.rspec_status
-
-*.swp
-tags
-.DS_Store
-.ruby-version

data/.rspec

@@ -1,3 +0,0 @@
---format documentation
---color
---require spec_helper

data/.rubocop.yml

@@ -1,119 +0,0 @@
-require:
-  - rubocop-performance
-  - rubocop-rspec
-
-AllCops:
-  NewCops: enable
-  TargetRubyVersion: 2.5
-  DisplayCopNames: true
-  DisplayStyleGuide: true
-  Exclude:
-    - 'bin/*'
-    - 'suika.gemspec'
-    - 'Rakefile'
-    - 'Gemfile'
-
-Layout/EmptyLineAfterGuardClause:
-  Enabled: false
-
-Layout/EmptyLinesAroundAttributeAccessor:
-  Enabled: true
-
-Layout/LineLength:
-  Max: 145
-  IgnoredPatterns: ['(\A|\s)#']
-
-Layout/SpaceAroundMethodCallOperator:
-  Enabled: true
-
-Lint/DeprecatedOpenSSLConstant:
-  Enabled: true
-
-Lint/MixedRegexpCaptureTypes:
-  Enabled: true
-
-Lint/RaiseException:
-  Enabled: true
-
-Lint/StructNewOverride:
-  Enabled: true
-
-Metrics/ModuleLength:
-  Max: 200
-
-Metrics/ClassLength:
-  Max: 200
-
-Metrics/MethodLength:
-  Max: 50
-
-Metrics/AbcSize:
-  Max: 60
-
-Metrics/CyclomaticComplexity:
-  Max: 16
-
-Metrics/PerceivedComplexity:
-  Max: 16
-
-Metrics/BlockLength:
-  Max: 40
-  Exclude:
-    - 'spec/**/*'
-
-Metrics/ParameterLists:
-  Max: 12
-
-Naming/MethodParameterName:
-  Enabled: false
-
-Naming/ConstantName:
-  Enabled: false
-
-Security/MarshalLoad:
-  Enabled: false
-
-Style/AsciiComments:
-  Enabled: false
-
-Style/Documentation:
-  Enabled: false
-
-Style/ExponentialNotation:
-  Enabled: true
-
-Style/HashEachMethods:
-  Enabled: true
-
-Style/HashTransformKeys:
-  Enabled: true
-
-Style/HashTransformValues:
-  Enabled: true
-
-Style/RedundantRegexpCharacterClass:
-  Enabled: true
-
-Style/RedundantRegexpEscape:
-  Enabled: true
-
-Style/SlicingWithRange:
-  Enabled: true
-
-Style/FormatStringToken:
-  Enabled: false
-
-Style/NumericLiterals:
-  Enabled: false
-
-RSpec/MultipleExpectations:
-  Enabled: false
-
-RSpec/ExampleLength:
-  Max: 40
-
-RSpec/InstanceVariable:
-  Enabled: false
-
-RSpec/LeakyConstantDeclaration:
-  Enabled: false

data/CODE_OF_CONDUCT.md

@@ -1,74 +0,0 @@
-# Contributor Covenant Code of Conduct
-
-## Our Pledge
-
-In the interest of fostering an open and welcoming environment, we as
-contributors and maintainers pledge to making participation in our project and
-our community a harassment-free experience for everyone, regardless of age, body
-size, disability, ethnicity, gender identity and expression, level of experience,
-nationality, personal appearance, race, religion, or sexual identity and
-orientation.
-
-## Our Standards
-
-Examples of behavior that contributes to creating a positive environment
-include:
-
-* Using welcoming and inclusive language
-* Being respectful of differing viewpoints and experiences
-* Gracefully accepting constructive criticism
-* Focusing on what is best for the community
-* Showing empathy towards other community members
-
-Examples of unacceptable behavior by participants include:
-
-* The use of sexualized language or imagery and unwelcome sexual attention or
-advances
-* Trolling, insulting/derogatory comments, and personal or political attacks
-* Public or private harassment
-* Publishing others' private information, such as a physical or electronic
-  address, without explicit permission
-* Other conduct which could reasonably be considered inappropriate in a
-  professional setting
-
-## Our Responsibilities
-
-Project maintainers are responsible for clarifying the standards of acceptable
-behavior and are expected to take appropriate and fair corrective action in
-response to any instances of unacceptable behavior.
-
-Project maintainers have the right and responsibility to remove, edit, or
-reject comments, commits, code, wiki edits, issues, and other contributions
-that are not aligned to this Code of Conduct, or to ban temporarily or
-permanently any contributor for other behaviors that they deem inappropriate,
-threatening, offensive, or harmful.
-
-## Scope
-
-This Code of Conduct applies both within project spaces and in public spaces
-when an individual is representing the project or its community. Examples of
-representing a project or community include using an official project e-mail
-address, posting via an official social media account, or acting as an appointed
-representative at an online or offline event. Representation of a project may be
-further defined and clarified by project maintainers.
-
-## Enforcement
-
-Instances of abusive, harassing, or otherwise unacceptable behavior may be
-reported by contacting the project team at yoshoku@outlook.com. All
-complaints will be reviewed and investigated and will result in a response that
-is deemed necessary and appropriate to the circumstances. The project team is
-obligated to maintain confidentiality with regard to the reporter of an incident.
-Further details of specific enforcement policies may be posted separately.
-
-Project maintainers who do not follow or enforce the Code of Conduct in good
-faith may face temporary or permanent repercussions as determined by other
-members of the project's leadership.
-
-## Attribution
-
-This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
-available at [https://contributor-covenant.org/version/1/4][version]
-
-[homepage]: https://contributor-covenant.org
-[version]: https://contributor-covenant.org/version/1/4/

data/Gemfile

@@ -1,13 +0,0 @@
-# frozen_string_literal: true
-
-source 'https://rubygems.org'
-
-# Specify your gem's dependencies in suika.gemspec
-gemspec
-
-gem 'rake', '~> 13.0'
-gem 'rspec', '~> 3.0'
-gem 'simplecov', '~> 0.21'
-gem 'simplecov-lcov', '~> 0.8'
-gem 'rbs', '~> 1.2'
-gem 'steep', '~> 0.44'

data/Rakefile

@@ -1,79 +0,0 @@
-require 'bundler/gem_tasks'
-require 'rspec/core/rake_task'
-
-require 'csv'
-require 'dartsclone'
-require 'nkf'
-require 'rubygems/package'
-require 'zlib'
-
-RSpec::Core::RakeTask.new(:spec)
-
-task :default => :spec
-
-desc 'Build suika system dictionary'
-task :dictionary do
-  base_dir = "#{__dir__}/dict/mecab-ipadic-2.7.0-20070801"
-  unless File.directory?(base_dir)
-    puts "Download mecab-ipadic file and expand that under dict directory:  #{__dir__}/dict/mecab-ipadic-2.7.0-20070801"
-    puts
-    puts 'Example:'
-    puts 'wget -O dict/mecab-ipadic.tgz https://drive.google.com/uc?export=download&id=0B4y35FiV1wh7MWVlSDBCSXZMTXM'
-    puts 'cd dict'
-    puts 'tar xzf mecab-ipadic.tgz'
-    puts 'cd ../'
-    next # exit
-  end
-
-  File.open("#{__dir__}/dict/mecab-ipadic-2.7.0-20070801/Reiwa.csv", 'w') do |f|
-    f.puts('令和,1288,1288,5904,名詞,固有名詞,一般,*,*,*,令和,レイワ,レイワ')
-  end
-
-  unknowns = {}
-  File.open("#{base_dir}/unk.def") do |f|
-    f.each_line do |line|
-      row = NKF.nkf('-w', line.chomp).split(',')
-      unknowns[row[0]] ||= []
-      unknowns[row[0]] << [row[1].to_i, row[2].to_i, row[3].to_i, *row[4..-1]]
-    end
-  end
-
-  dict = {}
-  Dir.glob("#{base_dir}/*.csv").each do |filename|
-    File.open(filename) do |f|
-      f.each_line do |line|
-        row = NKF.nkf('-w', line.chomp).split(',')
-        dict[row[0]] ||= []
-        dict[row[0]] << [row[1].to_i, row[2].to_i, row[3].to_i, *row[4..-1]]
-      end
-    end
-  end
-
-  da = DartsClone::DoubleArray.new
-  words = dict.keys.sort
-  da.build(words)
-  features = words.map { |w| dict[w] }
-
-  concosts = nil
-  File.open("#{base_dir}/matrix.def") do |f|
-    n_entries = f.readline.chomp.split.map(&:to_i).first
-    concosts = Array.new(n_entries) { Array.new(n_entries) }
-    f.each_line do |line|
-      row, col, cost = line.chomp.split.map(&:to_i)
-      concosts[row][col] = cost
-    end
-  end
-
-  ipadic = {
-    trie: da.get_array,
-    features: features,
-    unknowns: unknowns,
-    concosts: concosts
-  }
-
-  Zlib::GzipWriter.open("#{__dir__}/dict/sysdic.gz", Zlib::BEST_SPEED) { |f| f.write(Marshal.dump(ipadic)) }
-
-  puts 'The system dictionary has been successfully built:'
-  puts "#{__dir__}/dict/sysdic.gz"
-  puts Digest::SHA1.file("#{__dir__}/dict/sysdic.gz").to_s
-end

data/Steepfile

@@ -1,20 +0,0 @@
-target :lib do
-  signature "sig"
-#
-  check "lib"                       # Directory name
-#   check "Gemfile"                   # File name
-#   check "app/models/**/*.rb"        # Glob
-#   # ignore "lib/templates/*.rb"
-#
-#   # library "pathname", "set"       # Standard libraries
-  library "dartsclone"           # Gems
-end
-
-# target :spec do
-#   signature "sig", "sig-private"
-#
-#   check "spec"
-#
-#   # library "pathname", "set"       # Standard libraries
-#   # library "rspec"
-# end

data/bin/console

@@ -1,14 +0,0 @@
-#!/usr/bin/env ruby
-
-require "bundler/setup"
-require "suika"
-
-# You can add fixtures and/or initialization code here to make experimenting
-# with your gem easier. You can also use a different console, if you like.
-
-# (If you use this, don't forget to add pry to your Gemfile!)
-# require "pry"
-# Pry.start
-
-require "irb"
-IRB.start(__FILE__)

data/bin/setup

@@ -1,8 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-IFS=$'\n\t'
-set -vx
-
-bundle install
-
-# Do any other automated setup that you need to do here

data/suika.gemspec

@@ -1,31 +0,0 @@
-# frozen_string_literal: true
-
-require_relative 'lib/suika/version'
-
-Gem::Specification.new do |spec|
-  spec.name          = 'suika'
-  spec.version       = Suika::VERSION
-  spec.authors       = ['yoshoku']
-  spec.email         = ['yoshoku@outlook.com']
-
-  spec.summary       = 'Suika is a Japanese morphological analyzer written in pure Ruby.'
-  spec.description   = 'Suika is a Japanese morphological analyzer written in pure Ruby.'
-  spec.homepage      = 'https://github.com/yoshoku/suika'
-  spec.license       = 'BSD-3-Clause'
-
-  spec.metadata['homepage_uri'] = spec.homepage
-  spec.metadata['source_code_uri'] = spec.homepage
-  spec.metadata['changelog_uri'] = 'https://github.com/yoshoku/suika/blob/main/CHANGELOG.md'
-  spec.metadata['documentation_uri'] = 'https://rubydoc.info/gems/suika'
-
-  # 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']
-
-  spec.add_runtime_dependency 'dartsclone', '>= 0.2.0'
-end