babosa 1.0.4 → 2.0.0.beta

data/spec/transliterators/turkish_spec.rb

@@ -1,24 +1,24 @@
-# encoding: utf-8
-require File.expand_path("../../spec_helper", __FILE__)
-
-describe Babosa::Transliterator::Turkish do
-
-  let(:t) { described_class.instance }
-  it_behaves_like "a latin transliterator"
-
-  it "should transliterate various characters" do
-    examples = {
-      "Nâzım"          => "Nazim",
-      "sükûnet"        => "sukunet",
-      "millîleştirmek" => "millilestirmek",
-      "mêmur"          => "memur",
-      "lôkman"         => "lokman",
-      "yoğurt"         => "yogurt",
-      "şair"           => "sair",
-      "İzmir"          => "Izmir",
-      "yığın"          => "yigin",
-      "çarşı"          => "carsi"
-    }
-    examples.each {|k, v| expect(t.transliterate(k)).to eql(v)}
-  end
-end
+# frozen_string_literal: true
+
+require "spec_helper"
+
+describe Babosa::Transliterator::Turkish do
+  let(:t) { described_class.instance }
+  it_behaves_like "a latin transliterator"
+
+  it "should transliterate various characters" do
+    examples = {
+      "Nâzım"          => "Nazim",
+      "sükûnet"        => "sukunet",
+      "millîleştirmek" => "millilestirmek",
+      "mêmur"          => "memur",
+      "lôkman"         => "lokman",
+      "yoğurt"         => "yogurt",
+      "şair"           => "sair",
+      "İzmir"          => "Izmir",
+      "yığın"          => "yigin",
+      "çarşı"          => "carsi"
+    }
+    examples.each { |k, v| expect(t.transliterate(k)).to eql(v) }
+  end
+end

data/spec/transliterators/ukrainian_spec.rb

@@ -1,88 +1,87 @@
-# encoding: utf-8
-require File.expand_path("../../spec_helper", __FILE__)
+# frozen_string_literal: true
 
-describe Babosa::Transliterator::Ukrainian do
+require "spec_helper"
 
+describe Babosa::Transliterator::Ukrainian do
   let(:t) { described_class.instance }
   it_behaves_like "a cyrillic transliterator"
 
   it "should transliterate Cyrillic characters" do
     examples = {
-      "Алушта" => "Alushta",
-      "Андрій" => "Andrii",
-      "Борщагівка" => "Borshchahivka",
-      "Борисенко" => "Borysenko",
-      "Вінниця" => "Vinnytsia",
-      "Володимир" => "Volodymyr",
-      "Гадяч" => "Hadiach",
-      "Богдан" => "Bohdan",
-      "Ґалаґан" => "Galagan",
-      "Ґорґани" => "Gorgany",
-      "Донецьк" => "Donetsk",
-      "Дмитро" => "Dmytro",
-      "Рівне" => "Rivne",
-      "Олег" => "Oleh",
-      "Есмань" => "Esman",
-      "Єнакієве" => "Yenakiieve",
-      "Гаєвич" => "Haievych",
-      "Короп'є" => "Koropie",
-      "Житомир" => "Zhytomyr",
-      "Жанна" => "Zhanna",
-      "Жежелів" => "Zhezheliv",
-      "Закарпаття" => "Zakarpattia",
-      "Казимирчук" => "Kazymyrchuk",
-      "Медвин" => "Medvyn",
-      "Михайленко" => "Mykhailenko",
-      "Іванків" => "Ivankiv",
-      "Іващенко" => "Ivashchenko",
-      "Їжакевич" => "Yizhakevych",
-      "Кадиївка" => "Kadyivka",
-      "Мар'їне" => "Marine",
-      "Йосипівка" => "Yosypivka",
-      "Стрий" => "Stryi",
-      "Олексій" => "Oleksii",
-      "Київ" => "Kyiv",
-      "Коваленко" => "Kovalenko",
-      "Лебедин" => "Lebedyn",
-      "Леонід" => "Leonid",
-      "Миколаїв" => "Mykolaiv",
-      "Маринич" => "Marynych",
-      "Ніжин" => "Nizhyn",
-      "Наталія" => "Nataliia",
-      "Одеса" => "Odesa",
-      "Онищенко" => "Onyshchenko",
-      "Полтава" => "Poltava",
-      "Петро" => "Petro",
+      "Алушта"      => "Alushta",
+      "Андрій"      => "Andrii",
+      "Борщагівка"  => "Borshchahivka",
+      "Борисенко"   => "Borysenko",
+      "Вінниця"     => "Vinnytsia",
+      "Володимир"   => "Volodymyr",
+      "Гадяч"       => "Hadiach",
+      "Богдан"      => "Bohdan",
+      "Ґалаґан"     => "Galagan",
+      "Ґорґани"     => "Gorgany",
+      "Донецьк"     => "Donetsk",
+      "Дмитро"      => "Dmytro",
+      "Рівне"       => "Rivne",
+      "Олег"        => "Oleh",
+      "Есмань"      => "Esman",
+      "Єнакієве"    => "Yenakiieve",
+      "Гаєвич"      => "Haievych",
+      "Короп'є"     => "Koropie",
+      "Житомир"     => "Zhytomyr",
+      "Жанна"       => "Zhanna",
+      "Жежелів"     => "Zhezheliv",
+      "Закарпаття"  => "Zakarpattia",
+      "Казимирчук"  => "Kazymyrchuk",
+      "Медвин"      => "Medvyn",
+      "Михайленко"  => "Mykhailenko",
+      "Іванків"     => "Ivankiv",
+      "Іващенко"    => "Ivashchenko",
+      "Їжакевич"    => "Yizhakevych",
+      "Кадиївка"    => "Kadyivka",
+      "Мар'їне"     => "Marine",
+      "Йосипівка"   => "Yosypivka",
+      "Стрий"       => "Stryi",
+      "Олексій"     => "Oleksii",
+      "Київ"        => "Kyiv",
+      "Коваленко"   => "Kovalenko",
+      "Лебедин"     => "Lebedyn",
+      "Леонід"      => "Leonid",
+      "Миколаїв"    => "Mykolaiv",
+      "Маринич"     => "Marynych",
+      "Ніжин"       => "Nizhyn",
+      "Наталія"     => "Nataliia",
+      "Одеса"       => "Odesa",
+      "Онищенко"    => "Onyshchenko",
+      "Полтава"     => "Poltava",
+      "Петро"       => "Petro",
       "Решетилівка" => "Reshetylivka",
       "Рибчинський" => "Rybchynskyi",
-      "Суми" => "Sumy",
-      "Соломія" => "Solomiia",
-      "Тернопіль" => "Ternopil",
-      "Троць" => "Trots",
-      "Ужгород" => "Uzhhorod",
-      "Уляна" => "Uliana",
-      "Фастів" => "Fastiv",
-      "Філіпчук" => "Filipchuk",
-      "Харків" => "Kharkiv",
-      "Христина" => "Khrystyna",
+      "Суми"        => "Sumy",
+      "Соломія"     => "Solomiia",
+      "Тернопіль"   => "Ternopil",
+      "Троць"       => "Trots",
+      "Ужгород"     => "Uzhhorod",
+      "Уляна"       => "Uliana",
+      "Фастів"      => "Fastiv",
+      "Філіпчук"    => "Filipchuk",
+      "Харків"      => "Kharkiv",
+      "Христина"    => "Khrystyna",
       "Біла Церква" => "Bila Tserkva",
-      "Стеценко" => "Stetsenko",
-      "Чернівці" => "Chernivtsi",
-      "Шевченко" => "Shevchenko",
-      "Шостка" => "Shostka",
-      "Кишеньки" => "Kyshenky",
-      "Щербухи" => "Shcherbukhy",
-      "Гоща" => "Hoshcha",
-      "Гаращенко" => "Harashchenko",
-      "Юрій" => "Yurii",
-      "Корюківка" => "Koriukivka",
-      "Яготин" => "Yahotyn",
-      "Ярошенко" => "Yaroshenko",
-      "Костянтин" => "Kostiantyn",
-      "Знам'янка" => "Znamianka",
-      "Феодосія" => "Feodosiia"
+      "Стеценко"    => "Stetsenko",
+      "Чернівці"    => "Chernivtsi",
+      "Шевченко"    => "Shevchenko",
+      "Шостка"      => "Shostka",
+      "Кишеньки"    => "Kyshenky",
+      "Щербухи"     => "Shcherbukhy",
+      "Гоща"        => "Hoshcha",
+      "Гаращенко"   => "Harashchenko",
+      "Юрій"        => "Yurii",
+      "Корюківка"   => "Koriukivka",
+      "Яготин"      => "Yahotyn",
+      "Ярошенко"    => "Yaroshenko",
+      "Костянтин"   => "Kostiantyn",
+      "Знам'янка"   => "Znamianka",
+      "Феодосія"    => "Feodosiia"
     }
     examples.each { |k, v| expect(t.transliterate(k)).to eql(v) }
   end
-
-end
+end

data/spec/transliterators/vietnamese_spec.rb

@@ -1,18 +1,18 @@
-# encoding: utf-8
-require File.expand_path("../../spec_helper", __FILE__)
+# frozen_string_literal: true
 
-describe Babosa::Transliterator::Vietnamese do
+require "spec_helper"
 
+describe Babosa::Transliterator::Vietnamese do
   let(:t) { described_class.instance }
   it_behaves_like "a latin transliterator"
 
   it "should transliterate various characters" do
-		examples = {
-			"làm"     => "lam",
-		  "đàn ông" => "dan ong",
-		  "thật"    => "that",
-		  "khổ"     => "kho"
-		}
-    examples.each {|k, v| expect(t.transliterate(k)).to eql(v)}
+    examples = {
+      "làm"     => "lam",
+      "đàn ông" => "dan ong",
+      "thật"    => "that",
+      "khổ"     => "kho"
+    }
+    examples.each { |k, v| expect(t.transliterate(k)).to eql(v) }
   end
 end

metadata

@@ -1,29 +1,29 @@
 --- !ruby/object:Gem::Specification
 name: babosa
 version: !ruby/object:Gem::Version
-  version: 1.0.4
+  version: 2.0.0.beta
 platform: ruby
 authors:
 - Norman Clarke
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-10-06 00:00:00.000000000 Z
+date: 2020-10-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: activesupport
+  name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 3.2.0
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 3.2.0
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -39,35 +39,21 @@ dependencies:
       - !ruby/object:Gem::Version
         version: 3.7.0
 - !ruby/object:Gem::Dependency
-  name: simplecov
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: rake
+  name: rubocop
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 0.93.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 0.93.0
 - !ruby/object:Gem::Dependency
-  name: unicode
+  name: simplecov
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -114,14 +100,8 @@ files:
 - lib/babosa/transliterator/turkish.rb
 - lib/babosa/transliterator/ukrainian.rb
 - lib/babosa/transliterator/vietnamese.rb
-- lib/babosa/utf8/active_support_proxy.rb
-- lib/babosa/utf8/dumb_proxy.rb
-- lib/babosa/utf8/java_proxy.rb
-- lib/babosa/utf8/mappings.rb
-- lib/babosa/utf8/proxy.rb
-- lib/babosa/utf8/unicode_proxy.rb
 - lib/babosa/version.rb
-- spec/babosa_spec.rb
+- spec/identifier_spec.rb
 - spec/spec_helper.rb
 - spec/transliterators/base_spec.rb
 - spec/transliterators/bulgarian_spec.rb
@@ -141,11 +121,10 @@ files:
 - spec/transliterators/turkish_spec.rb
 - spec/transliterators/ukrainian_spec.rb
 - spec/transliterators/vietnamese_spec.rb
-- spec/utf8_proxy_spec.rb
 homepage: http://github.com/norman/babosa
 licenses: []
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -153,15 +132,15 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.0.0
+      version: 2.5.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">="
+  - - ">"
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 1.3.1
 requirements: []
-rubygems_version: 3.1.2
-signing_key: 
+rubygems_version: 3.1.4
+signing_key:
 specification_version: 4
 summary: A library for creating slugs.
 test_files: []

data/lib/babosa/utf8/active_support_proxy.rb

@@ -1,38 +0,0 @@
-require 'active_support'
-require 'active_support/multibyte/unicode'
-
-module Babosa
-  module UTF8
-    # A UTF-8 proxy using Active Support's multibyte support.
-    module ActiveSupportProxy
-      extend ActiveSupport::Multibyte::Unicode
-      extend self
-
-      def self.normalize_utf8(string)
-        normalize(string, :c)
-      end
-
-      if ActiveSupport::VERSION::MAJOR == 3
-        def downcase(string)
-          ActiveSupport::Multibyte::Chars.new(string).downcase.to_s
-        end
-
-        def upcase(string)
-          ActiveSupport::Multibyte::Chars.new(string).upcase.to_s
-        end
-      elsif ActiveSupport::VERSION::MAJOR >= 6
-        def self.normalize_utf8(string)
-          string.unicode_normalize(:nfc).to_s
-        end
-
-        def downcase(string)
-          string.downcase.to_s
-        end
-
-        def upcase(string)
-          string.upcase.to_s
-        end
-      end
-    end
-  end
-end

data/lib/babosa/utf8/dumb_proxy.rb

@@ -1,49 +0,0 @@
-require File.expand_path("../mappings", __FILE__)
-
-module Babosa
-  module UTF8
-
-    # This module provides fallback UTF-8 support when nothing else is
-    # available. It does case folding for Roman alphabet-based characters
-    # commonly used by Western European languages and little else, making it
-    # useless for Russian, Bulgarian, Greek, etc. If at all possible, Unicode
-    # or ActiveSupport should be used instead because they support the full
-    # UTF-8 character range.
-    module DumbProxy
-      extend Proxy
-      extend self
-
-      def downcase(string)
-        string.downcase.unpack("U*").map {|char| Mappings::DOWNCASE[char] or char}.flatten.pack("U*")
-      end
-
-      def upcase(string)
-        string.upcase.unpack("U*").map {|char| Mappings::UPCASE[char] or char}.flatten.pack("U*")
-      end
-
-      if ''.respond_to?(:unicode_normalize)
-        def normalize_utf8(string)
-          string.unicode_normalize
-        end
-      else
-        # On Ruby 2.2, this uses the native Unicode normalize method. On all
-        # other Rubies, it does a very naive Unicode normalization, which should
-        # work for this library's purposes (i.e., Roman-based codepoints, up to
-        # U+017E).  Do not use reuse this as a general solution!  Use a real
-        # library like Unicode or ActiveSupport instead.
-        def normalize_utf8(string)
-          codepoints = string.unpack("U*")
-          new = []
-          until codepoints.empty? do
-            if Mappings::COMPOSITION[codepoints[0..1]]
-              new << Mappings::COMPOSITION[codepoints.slice!(0,2)]
-            else
-              new << codepoints.shift
-            end
-          end
-          new.compact.flatten.pack("U*")
-        end
-      end
-    end
-  end
-end