unaccent 0.2.0 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 9659e66d5944e31de52b6ae6127f839eafffe2f0647705135d5d292913d5f0a0
-  data.tar.gz: d7c141e5078de647653ddcb88f21acd9fdcce8bc49f5e4f618d0371f159f00a8
+  metadata.gz: 850131686c6638f3c48c8441ab13c2b4a6220b752aaaab56e89fe19a274715fc
+  data.tar.gz: 2a026d497598b7303b6ee54b0d9f46b10d7015fff20ed2ad80b060448f638b42
 SHA512:
-  metadata.gz: d8791eb553569a93862373effcd0a3be832c05a85526c5b7d9d97218eab245b06c371eef607110958f1f8a12feef3af01d94f3b90bf892aa8c7e41c155d9d1bf
-  data.tar.gz: d3555caf43ca4d7d7e7ebbc526bd745482003d856cbc449183e031c30f53a3d33f975dc0070f17c9c85fd22068036e84617ded5031e063c19582272834aa8321
+  metadata.gz: dc135100fc86657bd4538ce6a9081a8e02e279d4903b52361b99b88d5d517a6247c08b2590abdbf726e3e27d4c77afb9036bdc2163cc1d1afc2ff541fafb895a
+  data.tar.gz: a52a5e96a933058c774dc4e35b5a12f9982597cdf3511a6e3db9c6d299f07e337e24ad5455e3cf5e2f33caf270ec0e4426230ef589ec5d022216724b0fb52a87

data/LICENSE.txt

@@ -1,6 +1,6 @@
 The MIT License (MIT)
 
-Copyright (c) 2010-2020 Joel Parker Henderson
+Copyright (c) 2010-2019 Joel Parker Henderson
 Copyright (c) 2022 Jonian Guveli
 
 Permission is hereby granted, free of charge, to any person obtaining a copy

data/README.md

@@ -1,6 +1,6 @@
 # Unaccent
 
-Ruby gem to replace a string's accent characters with ASCII characters. Based on [SixArm Ruby Unaccent](https://github.com/SixArm/sixarm_ruby_unaccent).
+Ruby gem to replace a string's accent characters with unaccented characters. Based on [SixArm Ruby Unaccent](https://github.com/SixArm/sixarm_ruby_unaccent).
 
 [![Gem Version](https://badge.fury.io/rb/unaccent.svg)](https://badge.fury.io/rb/unaccent)
 [![Build](https://github.com/hardpixel/unaccent/actions/workflows/build.yml/badge.svg)](https://github.com/hardpixel/unaccent/actions/workflows/build.yml)
@@ -39,24 +39,28 @@ require 'unaccent/string'
 ## Benchmark
 
 ```
-IPS Comparison:
-                gsub:    33804.1 i/s
-           each_char:    16639.9 i/s - 2.03x  (± 0.00) slower
-  each_char (sixarm):    13708.2 i/s - 2.47x  (± 0.00) slower
-                scan:    10390.0 i/s - 3.25x  (± 0.00) slower
-       scan (sixarm):     8765.8 i/s - 3.86x  (± 0.00) slower
-           split_map:     7800.9 i/s - 4.33x  (± 0.00) slower
-  split_map (sixarm):     6780.7 i/s - 4.99x  (± 0.00) slower
-
-
-Memory Comparison:
-                gsub:       5947 allocated
-           each_char:      10704 allocated - 1.80x more
-                scan:      15368 allocated - 2.58x more
-           split_map:      20582 allocated - 3.46x more
-  split_map (sixarm):      23185 allocated - 3.90x more
-  each_char (sixarm):      24979 allocated - 4.20x more
-       scan (sixarm):      29979 allocated - 5.04x more
+Warming up --------------------------------------
+            unaccent     3.259k i/100ms
+              sixarm   838.000  i/100ms
+Calculating -------------------------------------
+            unaccent     32.573k (± 2.1%) i/s -    162.950k in   5.004780s
+              sixarm      8.025k (± 4.6%) i/s -     40.224k in   5.023339s
+
+Comparison:
+            unaccent:    32573.1 i/s
+              sixarm:     8024.7 i/s - 4.06x  (± 0.00) slower
+
+Calculating -------------------------------------
+            unaccent     5.947k memsize (     0.000  retained)
+                        76.000  objects (     0.000  retained)
+                        42.000  strings (     0.000  retained)
+              sixarm    29.979k memsize (     0.000  retained)
+                       633.000  objects (     0.000  retained)
+                        50.000  strings (     0.000  retained)
+
+Comparison:
+            unaccent:       5947 allocated
+              sixarm:      29979 allocated - 5.04x more
 ```
 
 ## Development

data/lib/unaccent/accentmap.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Unaccent
   ACCENTMAP = {
     # 00A0 NO-BREAK SPACE

data/lib/unaccent/string.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require 'unaccent'
 
 module Unaccent
@@ -5,18 +7,6 @@ module Unaccent
     def unaccent
       Unaccent.unaccent(self)
     end
-
-    def unaccent_via_gsub
-      Unaccent.via_gsub(self)
-    end
-
-    def unaccent_via_each_char
-      Unaccent.via_each_char(self)
-    end
-
-    def unaccent_via_split_map
-      Unaccent.via_split_map(self)
-    end
   end
 end
 

data/lib/unaccent/version.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Unaccent
-  VERSION = '0.2.0'.freeze
+  VERSION = '0.3.0'
 end

data/lib/unaccent.rb

@@ -1,7 +1,10 @@
-require 'unaccent/accentmap'
+# frozen_string_literal: true
+
 require 'unaccent/version'
 
 module Unaccent
+  autoload :ACCENTMAP, 'unaccent/accentmap'
+
   class << self
     # Replace a string's accented characters with unaccented characters.
     #
@@ -12,67 +15,9 @@ module Unaccent
     # @return [String] a string that has no accents
 
     def unaccent(str)
-      via_gsub(str)
-    end
-
-    # Replace a string's accented characters with unaccented characters,
-    # by using string `#gsub` to replace non-ascii characters.
-    #
-    # @example
-    #   str = 'Å Ç ß'
-    #   Unaccent.via_gsub(str) = > 'AA C ss'
-    #
-    # @return [String] a string that has no accents
-
-    def via_gsub(str)
-      return str if str.ascii_only?
-
-      str.gsub(/[^[:ascii:]]/) { |c| ACCENTMAP.fetch(c, c) }
-    end
-
-    # Replace a string's accented characters with unaccented characters,
-    # by using string `#scan` to iterate on characters.
-    #
-    # @example
-    #   str = 'Å Ç ß'
-    #   Unaccent.via_scan(str) = > 'AA C ss'
-    #
-    # @return [String] a string that has no accents
-
-    def via_scan(str)
-      return str if str.ascii_only?
-
-      res = ''; str.scan(/./) { |c| res << ACCENTMAP.fetch(c, c) }; res
-    end
-
-    # Replace a string's accented characters with unaccented characters,
-    # by using string `#each_char` to iterate on characters.
-    #
-    # @example
-    #   str = 'Å Ç ß'
-    #   Unaccent.via_each_char(str) = > 'AA C ss'
-    #
-    # @return [String] a string that has no accents
-
-    def via_each_char(str)
-      return str if str.ascii_only?
-
-      res = ''; str.each_char { |c| res << ACCENTMAP.fetch(c, c) }; res
-    end
-
-    # Replace a string's accented characters with unaccented characters,
-    # by using string `#split` and `#map` to iterate on characters.
-    #
-    # @example
-    #   str = 'Å Ç ß'
-    #   Unaccent.via_split_map(str) = > 'AA C ss'
-    #
-    # @return [String] a string that has no accents
-
-    def via_split_map(str)
       return str if str.ascii_only?
 
-      str.split(//u).map { |c| ACCENTMAP.fetch(c, c) }.join
+      str.gsub(/[^[:ascii:]]/) { |char| ACCENTMAP.fetch(char, char) }
     end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: unaccent
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.3.0
 platform: ruby
 authors:
 - Jonian Guveli
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-08-27 00:00:00.000000000 Z
+date: 2022-08-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -59,22 +59,13 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- ".github/workflows/build.yml"
-- ".gitignore"
-- ".ruby-version"
 - ".yardopts"
-- Gemfile
 - LICENSE.txt
 - README.md
-- Rakefile
-- bin/benchmark
-- bin/console
-- bin/setup
 - lib/unaccent.rb
 - lib/unaccent/accentmap.rb
 - lib/unaccent/string.rb
 - lib/unaccent/version.rb
-- unaccent.gemspec
 homepage: https://github.com/hardpixel/unaccent
 licenses:
 - MIT
@@ -87,14 +78,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: '2.6'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.7
+rubygems_version: 3.3.14
 signing_key:
 specification_version: 4
 summary: Replace accented characters with unaccented characters

data/.github/workflows/build.yml

@@ -1,36 +0,0 @@
----
-name: Build
-
-on:
-  push:
-    branches: [master]
-    paths-ignore:
-      - 'README.md'
-      - 'LICENSE.txt'
-      - 'bin/**'
-  pull_request:
-    branches: [master]
-
-permissions:
-  contents: read
-
-jobs:
-  build:
-    strategy:
-      matrix:
-        os: [ubuntu-latest]
-        ruby: ['2.7', '3.1']
-    runs-on: ${{ matrix.os }}
-
-    steps:
-      - uses: actions/checkout@v3
-
-      - name: Set up Ruby
-        uses: ruby/setup-ruby@v1
-        with:
-          ruby-version: ${{ matrix.ruby }}
-          bundler-cache: true
-
-      - name: Run tests
-        run: |
-          bundle exec rake test

data/.gitignore

@@ -1,9 +0,0 @@
-/.bundle/
-/.yardoc
-/_yardoc/
-/coverage/
-/doc/
-/pkg/
-/spec/reports/
-/tmp/
-Gemfile.lock

data/.ruby-version

@@ -1 +0,0 @@
-3.1.2

data/Gemfile

@@ -1,4 +0,0 @@
-source 'https://rubygems.org'
-
-# Specify your gem's dependencies in buildex.gemspec
-gemspec

data/Rakefile

@@ -1,8 +0,0 @@
-require 'bundler/gem_tasks'
-require 'rake/testtask'
-
-Rake::TestTask.new(:test) do |t|
-  t.libs << 'test'
-  t.libs << 'lib'
-  t.test_files = FileList['test/**/*_test.rb']
-end

data/bin/benchmark

@@ -1,81 +0,0 @@
-#!/usr/bin/env ruby
-
-require 'bundler/inline'
-require 'tempfile'
-
-gemfile true, quiet: true do
-  source 'https://rubygems.org'
-  gemspec
-
-  gem 'benchmark-ips'
-  gem 'benchmark-memory'
-  gem 'sixarm_ruby_unaccent'
-end
-
-STRINGS = [
-  'String without accents in english',
-  'Streng med aksenter på norsk',
-  'Řetězec s akcenty v češtině',
-  'Chaîne avec accents en français',
-  'Cuerda con acentos en español',
-  'Corda amb accents en català',
-  'Stīga ar akcentiem latviešu valodā',
-  'Türkçe aksanlı dize',
-  'Varg me theks në shqip',
-  'Κείμενο με τόνους στα ελληνικά'
-]
-
-reports = lambda do |x|
-  x.report('gsub') do
-    STRINGS.each do |str|
-      Unaccent.via_gsub(str)
-    end
-  end
-
-  x.report('scan') do
-    STRINGS.each do |str|
-      Unaccent.via_scan(str)
-    end
-  end
-
-  x.report('each_char') do
-    STRINGS.each do |str|
-      Unaccent.via_each_char(str)
-    end
-  end
-
-  x.report('split_map') do
-    STRINGS.each do |str|
-      Unaccent.via_split_map(str)
-    end
-  end
-
-
-  x.report('scan (sixarm)') do
-    STRINGS.each do |str|
-      str.unaccent_via_scan
-    end
-  end
-
-  x.report('each_char (sixarm)') do
-    STRINGS.each do |str|
-      str.unaccent_via_each_char
-    end
-  end
-
-  x.report('split_map (sixarm)') do
-    STRINGS.each do |str|
-      str.unaccent_via_split_map
-    end
-  end
-end
-
-Benchmark.ips do |x|
-  reports.call(x)
-  x.compare!
-end
-
-Benchmark.memory do |x|
-  reports.call(x)
-  x.compare!
-end

data/bin/console

@@ -1,14 +0,0 @@
-#!/usr/bin/env ruby
-
-require 'bundler/setup'
-require 'unaccent'
-
-# 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/unaccent.gemspec

@@ -1,25 +0,0 @@
-require_relative 'lib/unaccent/version'
-
-Gem::Specification.new do |spec|
-  spec.name          = 'unaccent'
-  spec.version       = Unaccent::VERSION
-  spec.authors       = ['Jonian Guveli']
-  spec.email         = ['jonian@hardpixel.eu']
-
-  spec.summary       = 'Replace accented characters with unaccented characters'
-  spec.description   = 'Replace accented characters with unaccented characters.'
-  spec.homepage      = 'https://github.com/hardpixel/unaccent'
-  spec.license       = 'MIT'
-
-  # 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('..', __FILE__)) do
-    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
-  end
-
-  spec.require_paths = ['lib']
-
-  spec.add_development_dependency 'bundler', '~> 2.0'
-  spec.add_development_dependency 'minitest', '~> 5.0'
-  spec.add_development_dependency 'rake', '~> 13.0'
-end