byk 0.4.0 → 1.1.0

data/spec/byk_spec.rb

@@ -1,126 +1,240 @@
 # coding: utf-8
-
 require "spec_helper"
 
 describe Byk do
 
-  # See http://sr.wikipedia.org/wiki/Панграм
-  let(:pangram) { "фијуче ветар у шибљу, леди пасаже и куће иза њих и гунђа у оџацима." }
-  let(:pangram_latin) { "fijuče vetar u šiblju, ledi pasaže i kuće iza njih i gunđa u odžacima." }
-  let(:pangram_ascii_latin) { "fijuce vetar u siblju, ledi pasaze i kuce iza njih i gundja u odzacima." }
+  it "has a version number" do
+    expect(Byk::VERSION).not_to be nil
+  end
+
+  shared_examples :base do |method|
 
-  let(:pangram_caps) { "ФИЈУЧЕ ВЕТАР У ШИБЉУ, ЛЕДИ ПАСАЖЕ И КУЋЕ ИЗА ЊИХ И ГУНЂА У ОЏАЦИМА." }
-  let(:pangram_latin_caps) { "FIJUČE VETAR U ŠIBLJU, LEDI PASAŽE I KUĆE IZA NJIH I GUNĐA U ODŽACIMA." }
-  let(:pangram_ascii_latin_caps) { "FIJUCE VETAR U SIBLJU, LEDI PASAZE I KUCE IZA NJIH I GUNDJA U ODZACIMA." }
+    # See http://sr.wikipedia.org/wiki/Панграм
+    let(:pangram) { "фијуче ветар у шибљу, леди пасаже и куће иза њих и гунђа у оџацима." }
+    let(:pangram_latin) { "fijuče vetar u šiblju, ledi pasaže i kuće iza njih i gunđa u odžacima." }
+    let(:pangram_ascii_latin) { "fijuce vetar u siblju, ledi pasaze i kuce iza njih i gundja u odzacima." }
 
-  let(:ascii) { "The quick brown fox jumps over the lazy dog." }
-  let(:other) { "संस्कृतम् saṃskṛtam" }
+    let(:pangram_caps) { "ФИЈУЧЕ ВЕТАР У ШИБЉУ, ЛЕДИ ПАСАЖЕ И КУЋЕ ИЗА ЊИХ И ГУНЂА У ОЏАЦИМА." }
+    let(:pangram_latin_caps) { "FIJUČE VETAR U ŠIBLJU, LEDI PASAŽE I KUĆE IZA NJIH I GUNĐA U ODŽACIMA." }
+    let(:pangram_ascii_latin_caps) { "FIJUCE VETAR U SIBLJU, LEDI PASAZE I KUCE IZA NJIH I GUNDJA U ODZACIMA." }
 
-  let(:mixed) { "संस्कृतम् saṃskṛtam илити Sanskrit, obrati ПАЖЊУ." }
-  let(:mixed_latin) { "संस्कृतम् saṃskṛtam iliti Sanskrit, obrati PAŽNJU." }
-  let(:mixed_ascii_latin) { "संस्कृतम् saṃskṛtam iliti Sanskrit, obrati PAZNJU." }
+    let(:full_cyrillic_coderange) { (0x400..0x4ff).map { |i| i.chr(Encoding::UTF_8) } }
+    let(:non_serbian_cyrillic_coderange) { full_cyrillic_coderange - Byk::AZBUKA - Byk::AZBUKA_CAPS }
+    let(:non_serbian_cyrillic) { non_serbian_cyrillic_coderange.join }
 
-  it "has a version number" do
-    expect(Byk::VERSION).not_to be nil
+    let(:ascii) { "The quick brown fox jumps over the lazy dog." }
+    let(:other) { "संस्कृतम्" }
+
+    let(:mixed) { "संस्कृतम् илити Sanskrit, obrati ПАЖЊУ." }
+    let(:mixed_cyrillic) { "संस्कृतम् илити Санскрит, обрати ПАЖЊУ." }
+    let(:mixed_latin) { "संस्कृतम् iliti Sanskrit, obrati PAŽNJU." }
+    let(:mixed_ascii_latin) { "संस्कृतम् iliti Sanskrit, obrati PAZNJU." }
+
+    it "doesn't translate an empty string" do
+      expect(Byk.send(method, "")).to eq ""
+    end
+
+    it "doesn't translate foreign coderanges" do
+      expect(Byk.send(method, other)).to eq other
+    end
   end
 
-  describe "#to_latin" do
+  shared_examples :cyrillization_method do |method|
+    include_examples :base, method
 
-    it "doesn't modify an empty string" do
-      expect("".to_latin).to eq ""
+    let(:edge_cases) do
+      [
+        ["lJ", "љ"],
+        ["nJ", "њ"],
+        ["dŽ", "џ"]
+      ]
     end
 
-    it "doesn't modify ASCII text" do
-      expect(ascii.to_latin).to eq ascii
+    it "doesn't translate Cyrillic" do
+      expect(Byk.send(method, pangram)).to eq pangram
     end
 
-    it "doesn't modify latin" do
-      expect(pangram_latin.to_latin).to eq pangram_latin
+    it "doesn't translate non-Serbian Cyrillic" do
+      expect(Byk.send(method, non_serbian_cyrillic)).to eq non_serbian_cyrillic
     end
 
-    it "doesn't modify other scripts" do
-      expect(other.to_latin).to eq other
+    it "translates Latin to Cyrillic" do
+      expect(Byk.send(method, pangram_latin)).to eq pangram
     end
 
-    it "converts cyrillic to latin" do
-      expect(pangram.to_latin).to eq pangram_latin
+    it "translates Latin caps to Cyrillic caps" do
+      expect(Byk.send(method, pangram_latin_caps)).to eq pangram_caps
     end
 
-    it "converts cyrillic caps to latin caps" do
-      expect(pangram_caps.to_latin).to eq pangram_latin_caps
+    it "translates mixed text properly" do
+      expect(Byk.send(method, mixed)).to eq mixed_cyrillic
     end
 
-    it "converts mixed text properly" do
-      expect(mixed.to_latin).to eq mixed_latin
+    it "translates edge cases properly" do
+      edge_cases.each do |input, output|
+        expect(Byk.send(method, input)).to eq output
+      end
     end
 
-    it "converts AZBUKA to ABECEDA" do
-      expect(Byk::AZBUKA.map(&:to_latin)).to match_array(Byk::ABECEDA)
+    it "translates ABECEDA to AZBUKA" do
+      expect(Byk::ABECEDA.map { |l| l.dup.send(:to_cyrillic) }).to match_array(Byk::AZBUKA)
     end
 
-    it "converts AZBUKA_CAPS to ABECEDA_CAPS" do
-      expect(Byk::AZBUKA_CAPS.map(&:to_latin)).to match_array(Byk::ABECEDA_CAPS)
+    it "translates ABECEDA_CAPS to AZBUKA_CAPS" do
+      expect(Byk::ABECEDA_CAPS.map { |l| l.dup.send(:to_cyrillic) }).to match_array(Byk::AZBUKA_CAPS)
     end
   end
 
-  describe "#to_ascii_latin" do
+  shared_examples :latinization_method do |method|
+    include_examples :base, method
 
-    # Special care for Њ, Љ, Ђ, Đ
-    let(:edge_cases) {
-      {
-        "Њ" => "Nj",
-        "Љ" => "Lj",
-        "Ђ" => "Dj",
-        "Đ" => "Dj",
-        "ЊЊ" => "NJNJ",
-        "ЉЉ" => "LJLJ",
-        "ЂЂ" => "DJDJ",
-        "ĐĐ" => "DJDJ",
-        "ГУЊ" => "GUNJ",
-        "ПАСУЉ" => "PASULJ",
-        "ЂУРАЂ" => "DJURADJ",
-        "ĐURAĐ" => "DJURADJ",
-        "ĐURAĐ Đorđević" => "DJURADJ Djordjevic",
-        "ĐURAĐ. Đorđević" => "DJURADJ. Djordjevic"
-      }
-    }
+    let(:edge_cases) do
+      [
+        ["ЉЉ", "LJLJ"],
+        ["ЊЊ", "NJNJ"],
+        ["ЏЏ", "DŽDŽ"]
+      ]
+    end
 
-    it "doesn't modify an empty string" do
-      expect("".to_ascii_latin).to eq ""
+    it "doesn't translate ASCII" do
+      expect(Byk.send(method, ascii)).to eq ascii
     end
 
-    it "doesn't modify ASCII text" do
-      expect(ascii.to_ascii_latin).to eq ascii
+    it "doesn't translate Latin" do
+      expect(Byk.send(method, pangram_latin)).to eq pangram_latin
     end
 
-    it "doesn't modify other scripts" do
-      expect(other.to_ascii_latin).to eq other
+    it "doesn't translate non-Serbian Cyrillic" do
+      expect(Byk.send(method, non_serbian_cyrillic)).to eq non_serbian_cyrillic
     end
 
-    it "converts cyrillic to ASCII latin" do
-      expect(pangram.to_ascii_latin).to eq pangram_ascii_latin
+    it "translates Cyrillic to Latin" do
+      expect(Byk.send(method, pangram)).to eq pangram_latin
     end
 
-    it "converts cyrillic caps to ASCII latin caps" do
-      expect(pangram_caps.to_ascii_latin).to eq pangram_ascii_latin_caps
+    it "translates Cyrillic caps to Latin caps" do
+      expect(Byk.send(method, pangram_caps)).to eq pangram_latin_caps
+    end
+
+    it "translates mixed text properly" do
+      expect(Byk.send(method, mixed)).to eq mixed_latin
+    end
+
+    it "translates edge cases properly" do
+      edge_cases.each do |input, output|
+        expect(Byk.send(method, input)).to eq output
+      end
+    end
+
+    it "translates AZBUKA to ABECEDA" do
+      expect(Byk::AZBUKA.map { |l| l.dup.send(method) }).to match_array(Byk::ABECEDA)
+    end
+
+    it "translates AZBUKA_CAPS to ABECEDA_CAPS" do
+      expect(Byk::AZBUKA_CAPS.map { |l| l.dup.send(method) }).to match_array(Byk::ABECEDA_CAPS)
+    end
+  end
+
+  shared_examples :ascii_latinization_method do |method|
+    include_examples :base, method
+
+    let(:edge_cases) do
+      [
+        ["Њ", "Nj"],
+        ["Љ", "Lj"],
+        ["Џ", "Dz"],
+        ["Ђ", "Dj"],
+        ["Đ", "Dj"],
+        ["ЊЊ", "NJNJ"],
+        ["ЉЉ", "LJLJ"],
+        ["ЏЏ", "DZDZ"],
+        ["ЂЂ", "DJDJ"],
+        ["ĐĐ", "DJDJ"],
+        ["ЂУРАЂ Ђурђевић", "DJURADJ Djurdjevic"],
+        ["ĐURAĐ Đurđević", "DJURADJ Djurdjevic"]
+      ]
     end
 
-    it "converts latin to ASCII latin" do
-      expect(pangram_latin.to_ascii_latin).to eq pangram_ascii_latin
+    it "doesn't translate ASCII" do
+      expect(Byk.send(method, ascii)).to eq ascii
     end
 
-    it "converts latin caps to ASCII latin caps" do
-      expect(pangram_latin_caps.to_ascii_latin).to eq pangram_ascii_latin_caps
+    it "translates Latin to ASCII Latin" do
+      expect(Byk.send(method, pangram_latin)).to eq pangram_ascii_latin
     end
 
-    it "converts mixed text properly" do
-      expect(mixed.to_ascii_latin).to eq mixed_ascii_latin
+    it "translates Latin caps to ASCII Latin caps" do
+      expect(Byk.send(method, pangram_latin_caps)).to eq pangram_ascii_latin_caps
     end
 
-    it "converts edge cases properly" do
+    it "translates Cyrillic to ASCII Latin" do
+      expect(Byk.send(method, pangram)).to eq pangram_ascii_latin
+    end
+
+    it "translates Cyrillic caps to ASCII Latin caps" do
+      expect(Byk.send(method, pangram_caps)).to eq pangram_ascii_latin_caps
+    end
+
+    it "translates mixed text properly" do
+      expect(Byk.send(method, mixed)).to eq mixed_ascii_latin
+    end
+
+    it "translates edge cases properly" do
       edge_cases.each do |input, output|
-        expect(input.to_ascii_latin).to eq output
+        expect(Byk.send(method, input)).to eq output
       end
     end
   end
+
+  shared_examples :non_destructive_method do |method|
+    it "doesn't modify the arg" do
+      str = "ЖŽ"
+      expect { Byk.send(method, str) }.to_not change { str }
+    end
+  end
+
+  shared_examples :destructive_method do |method|
+    it "modifies the arg" do
+      str = "ЖŽ"
+      expect { Byk.send(method, str) }.to change { str }
+    end
+  end
+
+  describe ".to_cyrillic" do
+    it_behaves_like :cyrillization_method, :to_cyrillic
+    it_behaves_like :non_destructive_method, :to_cyrillic
+  end
+
+  describe ".to_cyrillic!" do
+    it_behaves_like :cyrillization_method, :to_cyrillic!
+    it_behaves_like :destructive_method, :to_cyrillic!
+  end
+
+  describe ".to_latin" do
+    it_behaves_like :latinization_method, :to_latin
+    it_behaves_like :non_destructive_method, :to_latin
+  end
+
+  describe ".to_latin!" do
+    it_behaves_like :latinization_method, :to_latin!
+    it_behaves_like :destructive_method, :to_latin!
+  end
+
+  describe ".to_ascii_latin" do
+    it_behaves_like :ascii_latinization_method, :to_ascii_latin
+    it_behaves_like :non_destructive_method, :to_ascii_latin
+  end
+
+  describe ".to_ascii_latin!" do
+    it_behaves_like :ascii_latinization_method, :to_ascii_latin!
+    it_behaves_like :destructive_method, :to_ascii_latin!
+  end
+end
+
+describe String do
+  it "responds to Byk methods" do
+    Byk.singleton_methods.each do |method|
+      expect("").to respond_to(method)
+    end
+  end
 end

metadata

@@ -1,47 +1,76 @@
 --- !ruby/object:Gem::Specification
 name: byk
 version: !ruby/object:Gem::Version
-  version: 0.4.0
+  version: 1.1.0
 platform: ruby
 authors:
 - Nikola Topalović
-autorequire: 
-bindir: bin
+autorequire:
+bindir: exe
 cert_chain: []
-date: 2015-04-17 00:00:00.000000000 Z
+date: 2022-02-02 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '13.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '13.0'
 - !ruby/object:Gem::Dependency
   name: rake-compiler
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.9'
+        version: '1.1'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.9'
+        version: '1.1'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.2'
+        version: '3.10'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.10'
+- !ruby/object:Gem::Dependency
+  name: benchmark-ips
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.9'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.2'
-description: Provides C-optimized methods for transliteration of Serbian Cyrillic
-  into Latin.
+        version: '2.9'
+description: Fast transliteration of Serbian Cyrillic to Latin and back. Brzo preslovljavanje
+  ćirilice u latinicu i obratno.
 email: nikola.topalovic@gmail.com
-executables: []
+executables:
+- byk
 extensions:
 - ext/byk/extconf.rb
 extra_rdoc_files: []
@@ -49,16 +78,19 @@ files:
 - CHANGELOG.md
 - LICENSE
 - README.md
+- exe/byk
 - ext/byk/byk.c
 - ext/byk/extconf.rb
 - lib/byk.rb
+- lib/byk/core_ext/string.rb
+- lib/byk/safe.rb
 - lib/byk/version.rb
 - spec/byk_spec.rb
 homepage: https://github.com/topalovic/byk
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -66,17 +98,16 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 1.9.2
+      version: 2.2.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.2.2
-signing_key: 
+rubygems_version: 3.3.3
+signing_key:
 specification_version: 4
-summary: Fast transliteration of Serbian Cyrillic into Latin.
+summary: Transliteration of Serbian Cyrillic <-> Latin
 test_files:
 - spec/byk_spec.rb