srbovanje 0.2.1 → 1.0.0

data/README.md

@@ -1,7 +1,7 @@
 srbovanje
 =========
 
-Ruby gem za transliteraciju ćirilice na latinicu i tzv. ASCII latinicu
+Ruby gem za preslovanjavanje ćirilice na latinicu i tzv. "ošišanu" latinicu
 
 
 ## Instaliranje
@@ -11,23 +11,35 @@ Ruby gem za transliteraciju ćirilice na latinicu i tzv. ASCII latinicu
 
 ## Korišćenje
 
-    >> "Ђурђевак".recode_sr_latin
+    >> "Ђурђевак".na_latinici
     => "Đurđevak"
 
-    >> "Железница Србије".recode_sr_ascii_latin
-    => "Zeleznica Srbije"
+    >> "Ђурђевак".na_latinici :ascii
+    => "Djurdjevak"
 
-    >> "Железница Србије".slugify
-    => "zeleznica-srbije"
-
-    >> String.abeceda
+    >> Srbovanje.abeceda
     => ["A", "B", "C", "Č", "Ć", "D", "DŽ", "Đ", "E", "F", "G", "H", "I", "J", "K", "L", "LJ", "M", "N", "NJ", "O", "P", "R", "S", "Š", "T", "U", "V", "Z", "Ž"]
 
-## Zašto "recode_sr_latin" kao naziv metode?
 
-Zbog <http://man.he.net/man1/recode-sr-latin>
+## MIT Licence
+
+Copyright (c) 2009 Dejan Simic
 
+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:
 
-## Autor
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
 
-[Dejan Simić](http://github.com/dejan)
+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/Rakefile

@@ -1,6 +1,11 @@
+#!/usr/bin/env rake
+require 'bundler/gem_tasks'
 require 'rake/testtask'
 
-desc 'Test srbovanje'
-Rake::TestTask.new(:test) do |t|
-  t.pattern = 'test/**/*_test.rb'
+Rake::TestTask.new do |t|
+  t.libs << "test"
+  t.test_files = FileList['test/**/*_test.rb']
+  t.verbose = true
 end
+
+task :default => :test

data/lib/srbovanje.rb

@@ -1,5 +1,6 @@
-# -*- encoding: utf-8 -*-
+# encoding: utf-8
 
 $KCODE = 'UTF8' if RUBY_VERSION.to_f < 1.9
 
-require 'srbovanje/string_ext.rb'
+require 'srbovanje/srbovanje.rb'
+require 'srbovanje/string_ext.rb'

data/lib/srbovanje/srbovanje.rb

@@ -0,0 +1,102 @@
+# encoding: utf-8
+
+class Srbovanje
+  def self.abeceda
+    %w(A B C Č Ć D DŽ Đ E F G H I J K L LJ M N NJ O P R S Š T U V Z Ž)
+  end
+
+  def self.latinica_map(charset)
+    charset.to_s == 'ascii' ? latinica_ascii_map : latinica_full_map
+  end
+
+  def self.latinica_full_map
+    @@latinica_map ||= {
+      'а' => 'a',
+      'А' => 'A',
+      'б' => 'b',
+      'Б' => 'B',
+      'в' => 'v',
+      'В' => 'V',
+      'г' => 'g',
+      'Г' => 'G',
+      'д' => 'd',
+      'Д' => 'D',
+      'ђ' => 'đ',
+      'Ђ' => 'Đ',
+      'е' => 'e',
+      'Е' => 'E',
+      'ж' => 'ž',
+      'Ж' => 'Ž',
+      'з' => 'z',
+      'З' => 'Z',
+      'и' => 'i',
+      'И' => 'I',
+      'ј' => 'j',
+      'Ј' => 'J',
+      'к' => 'k',
+      'К' => 'K',
+      'л' => 'l',
+      'Л' => 'L',
+      'љ' => 'lj',
+      'Љ' => 'LJ',
+      'м' => 'm',
+      'М' => 'M',
+      'н' => 'n',
+      'Н' => 'N',
+      'њ' => 'nj',
+      'Њ' => 'NJ',
+      'о' => 'o',
+      'О' => 'O',
+      'п' => 'p',
+      'П' => 'P',
+      'р' => 'r',
+      'Р' => 'R',
+      'с' => 's',
+      'С' => 'S',
+      'т' => 't',
+      'Т' => 'T',
+      'ћ' => 'ć',
+      'Ћ' => 'Ć',
+      'ц' => 'c',
+      'Ц' => 'C',
+      'у' => 'u',
+      'У' => 'U',
+      'ф' => 'f',
+      'Ф' => 'F',
+      'х' => 'h',
+      'Х' => 'H',
+      'ч' => 'č',
+      'Ч' => 'Č',
+      'џ' => 'dž',
+      'Џ' => 'DŽ',
+      'ш' => 'š',
+      'Ш' => 'Š' }
+  end
+
+  def self.latinica_ascii_map
+    @@latinica_ascii_map ||= latinica_full_map.merge(
+        'ћ' => 'c',
+        'ć' => 'c',
+        'ч' => 'c',
+        'č' => 'c',
+        'Ћ' => 'C',
+        'Ć' => 'C',
+        'Ч' => 'C',
+        'Č' => 'C',
+        'ж' => 'z',
+        'ž' => 'z',
+        'Ж' => 'Z',
+        'Ž' => 'Z',
+        'š' => 's',
+        'ш' => 's',
+        'Ш' => 'S',
+        'Š' => 'S',
+        'đ' => 'dj',
+        'ђ' => 'dj',
+        'Ђ' => 'DJ',
+        'Đ' => 'DJ', 
+        'џ' => 'dz',
+        'Џ' => 'DZ')
+  end
+
+end

data/lib/srbovanje/string_ext.rb

@@ -1,154 +1,15 @@
-# -*- encoding: utf-8 -*-
+# encoding: utf-8
 
 String.class_eval do
-  def self.recode_sr_latin_map
-    @@recode_sr_latin_map ||= {
-      'а' => 'a',
-      'А' => 'A',
-      'б' => 'b',
-      'Б' => 'B',
-      'в' => 'v',
-      'В' => 'V',
-      'г' => 'g',
-      'Г' => 'G',
-      'д' => 'd',
-      'Д' => 'D',
-      'ђ' => 'đ',
-      'Ђ' => 'Đ',
-      'е' => 'e',
-      'Е' => 'E',
-      'ж' => 'ž',
-      'Ж' => 'Ž',
-      'з' => 'z',
-      'З' => 'Z',
-      'и' => 'i',
-      'И' => 'I',
-      'ј' => 'j',
-      'Ј' => 'J',
-      'к' => 'k',
-      'К' => 'K',
-      'л' => 'l',
-      'Л' => 'L',
-      'љ' => 'lj',
-      'Љ' => 'LJ',
-      'м' => 'm',
-      'М' => 'M',
-      'н' => 'n',
-      'Н' => 'N',
-      'њ' => 'nj',
-      'Њ' => 'NJ',
-      'о' => 'o',
-      'О' => 'O',
-      'п' => 'p',
-      'П' => 'P',
-      'р' => 'r',
-      'Р' => 'R',
-      'с' => 's',
-      'С' => 'S',
-      'т' => 't',
-      'Т' => 'T',
-      'ћ' => 'ć',
-      'Ћ' => 'Ć',
-      'ц' => 'c',
-      'Ц' => 'C',
-      'у' => 'u',
-      'У' => 'U',
-      'ф' => 'f',
-      'Ф' => 'F',
-      'х' => 'h',
-      'Х' => 'H',
-      'ч' => 'č',
-      'Ч' => 'Č',
-      'џ' => 'dž',
-      'Џ' => 'DŽ',
-      'ш' => 'š',
-      'Ш' => 'Š' }
-  end
-  
-  def self.recode_sr_ascii_latin_map
-    @@recode_sr_ascii_latin_map ||= 
-      recode_sr_latin_map.merge(
-        'ћ' => 'c',
-        'ć' => 'c',
-        'ч' => 'c',
-        'č' => 'c',
-        'Ћ' => 'C',
-        'Ć' => 'C',
-        'Ч' => 'C',
-        'Č' => 'C',
-        'ж' => 'z',
-        'ž' => 'z',
-        'Ж' => 'Z',
-        'Ž' => 'Z',
-        'š' => 's',
-        'ш' => 's',
-        'Ш' => 'S',
-        'Š' => 'S',
-        'đ' => 'dj',
-        'ђ' => 'dj',
-        'Ђ' => 'DJ',
-        'Đ' => 'DJ', 
-        'џ' => 'dz',
-        'Џ' => 'DZ')
-  end
-
-  def self.abeceda
-    @@abeceda ||= %w(A B C Č Ć D DŽ Đ E F G H I J K L LJ M N NJ O P R S Š T U V Z Ž)
-  end
-
-  def recode_sr_latin
-    self.class.recode(self.dup, self.class.recode_sr_latin_map)
-  end
-
-  def recode_sr_latin!
-    self.class.recode(self, self.class.recode_sr_latin_map)
-  end
-
-  def recode_sr_ascii_latin
-    self.class.recode(self.dup, self.class.recode_sr_ascii_latin_map)
-  end
 
-  def recode_sr_ascii_latin!
-    self.class.recode(self, self.class.recode_sr_ascii_latin_map)
-  end
-
-  def slugify(separator = '-', return_separator_if_empty = true)
-    s = parameterize(self.recode_sr_ascii_latin, separator)
-    s.empty? && return_separator_if_empty ? separator : s
-  end
-
-private
-
-  # NOTE: slighlty modified after porting from ActiveSupport
-  #
-  # Replaces special characters in a string so that it may be used as part of a 'pretty' URL.
-  #
-  # ==== Examples
-  #
-  #   @person = Person.find(1)
-  #   # => #<Person id: 1, name: "Donald E. Knuth">
-  #
-  #   <%= link_to(@person.name, person_path(@person)) %>
-  #   # => <a href="/person/1-donald-e-knuth">Donald E. Knuth</a>
-  #
-  def parameterize(string, sep = '-')
-    # nil is same as blank
-    sep = sep || ''
-    parameterized_string = string.gsub(/[^a-z0-9\-_\+]+/i, sep)
-    # Turn unwanted chars into the seperator
-    unless sep.empty?
-      re_sep = Regexp.escape(sep)
-      # No more than one of the separator in a row.
-      parameterized_string.gsub!(/#{re_sep}{2,}/, sep)
-      # Remove leading/trailing separator.
-      parameterized_string.gsub!(/^#{re_sep}|#{re_sep}$/i, '')
-    end
-    parameterized_string.downcase
-  end
-
-  def self.recode(str, mapping)
-    str.gsub!(/.+?/) do |chr|
+  # Preslovljava na latinicu
+  # Params:
+  # +charset+:: ako je :ascii preslovljava u "ošišanju" latinicu.
+  def na_latinici(charset=:utf8)
+    mapping = Srbovanje.latinica_map(charset)
+    self.gsub(/.+?/) do |chr|
       mapping[chr] || chr
     end
   end
+
 end

data/test/srbovanje_test.rb

@@ -0,0 +1,28 @@
+# encoding: utf-8
+
+require 'test_helper'
+
+describe Srbovanje do
+  describe '::abeceda' do
+    it 'vraca abecedu kao niz' do
+      assert_equal 'B', Srbovanje.abeceda[1] 
+    end
+
+     it 'ima 30 slova' do
+        assert_equal 30, Srbovanje.abeceda.size
+     end
+  end
+
+  describe 'latinica_map' do
+    it 'vraca potpunu mapu latinice' do
+      assert_equal 'Š', Srbovanje.latinica_full_map['Ш']
+    end
+  end
+
+  describe 'latinica_ascii_map' do
+    it 'vraca mapu ascii latinice' do
+      assert_equal 'dj', Srbovanje.latinica_ascii_map['ђ']
+    end
+  end
+end
+

data/test/string_ext_test.rb

@@ -1,65 +1,18 @@
-# -*- encoding: utf-8 -*-
-$: << "." 
+# encoding: utf-8
 
-require File.dirname(__FILE__) + '/test_helper'
+require 'test_helper'
 
-class TestStringExt < Test::Unit::TestCase
-  def test_recode_sr_latin
-    # don't change argument
-    str = "ЊЕГОШ"
-    assert_equal("NJEGOŠ", str.recode_sr_latin)
-    assert_equal("ЊЕГОШ", str)
-    
-    # plain
-    assert_equal("NJEGOŠ", "ЊЕГОШ".recode_sr_latin)
-    assert_equal("Šaban Šaulić", "Шабан Шаулић".recode_sr_latin)
-    assert_equal("elektrodistribucija", "електродистрибуција".recode_sr_latin)
-    assert_equal("Đurđevak", "Ђурђевак".recode_sr_latin)
-    
-    # non_convertive_characters
-    assert_equal("Latinica", "Latinica".recode_sr_latin)
-    assert_equal('[]2#}(,.);2@$"', '[]2#}(,.);2@$"'.recode_sr_latin)
+describe String do
+  it 'preslovnjava u latinicu' do
+    assert_equal "NJEGOŠ", "ЊЕГОШ".na_latinici
+    assert_equal "Šaban Šaulić", "Шабан Шаулић".na_latinici
+    assert_equal "elektrodistribucija", "електродистрибуција".na_latinici
+    assert_equal "Đurđevak", "Ђурђевак".na_latinici
+    assert_equal "Latinica", "Latinica".na_latinici
+    assert_equal '[]2#}(,.);2@$"', '[]2#}(,.);2@$"'.na_latinici
   end
 
-  def test_recode_sr_latin!
-    str = "ноћ"
-    assert_equal("noć", str.recode_sr_latin!)
-    assert_equal("noć", str)
-  end
-
-  def test_recode_sr_ascii_latin
-    str = "Железница Србије"
-    assert_equal("Zeleznica Srbije", str.recode_sr_ascii_latin)
-    assert_equal("Железница Србије", str)
-  end
-
-  def test_recode_sr_ascii_latin!
-    str = "ноћ"
-    assert_equal("noc", str.recode_sr_ascii_latin!)
-    assert_equal("noc", str)
-  end
-
-  def test_abeceda
-    assert_equal(30, String.abeceda.size)
-  end
-  
-  def test_slugify
-    assert_equal("zeleznica-srbije", "Железница Србије".slugify)
-    assert_equal("kako-je", "Kako je?".slugify)
-    assert_equal("mis-zaba", "miš,žaba".slugify)
-    assert_equal("mis-zaba", "миш, жаба".slugify)
-    assert_equal("agencija", " aGenCIJa   ".slugify)
-    assert_equal("vamo-tamo", "vamo-tamo".slugify)
-    assert_equal("vamo-tamo", "vamo  tamo".slugify)
-    assert_equal("pokvarenspejs", "Pokvaren Spejs".slugify(nil))
-    assert_equal("abcdeavioni", "a b c d e avioni".slugify(''))
-    assert_equal("-", "び諸芸や奇抜な衣装".slugify)
-    assert_equal("-", "び諸芸や奇 抜な衣 装 び諸芸や 奇抜な衣装".slugify)
-    assert_equal("", "び諸芸や奇抜な衣装".slugify('-', false))
-    assert_equal("-", "び諸芸や奇抜な衣装".slugify('-', true))
-    assert_equal("+", "び諸芸や奇抜な衣装 び諸芸や奇抜な衣装".slugify('+'))
-    assert_equal("ako-ako", 'ako, ako'.slugify)
-    assert_equal("ako-ako", 'ako,ako'.slugify)
-    assert_equal("ako-ako", 'ako ako'.slugify)
+  it 'preslovanjava u ošišanu latinicu' do
+    assert_equal("Zeleznica Srbije", "Железница Србије".na_latinici(:ascii))
   end
 end

data/test/test_helper.rb

@@ -1,5 +1,4 @@
-# -*- encoding: utf-8 -*-
-
-require "test/unit"
-
-require File.dirname(__FILE__) + '/../lib/srbovanje'
+require 'rubygems'
+require 'bundler/setup'
+require 'srbovanje'
+require 'minitest/autorun'

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: srbovanje
 version: !ruby/object:Gem::Version 
-  hash: 21
-  prerelease: false
+  hash: 23
+  prerelease: 
   segments: 
-  - 0
-  - 2
   - 1
-  version: 0.2.1
+  - 0
+  - 0
+  version: 1.0.0
 platform: ruby
 authors: 
 - Dejan Simic
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-01-05 00:00:00 +01:00
+date: 2013-02-25 00:00:00 +01:00
 default_executable: 
 dependencies: []
 
@@ -29,13 +29,15 @@ extra_rdoc_files: []
 
 files: 
 - Rakefile
+- lib/srbovanje/srbovanje.rb
 - lib/srbovanje/string_ext.rb
 - lib/srbovanje.rb
+- test/srbovanje_test.rb
 - test/string_ext_test.rb
 - test/test_helper.rb
 - README.md
 has_rdoc: true
-homepage: http://github.com/dejan/srbovanje
+homepage: https://github.com/dejan/srbovanje
 licenses: []
 
 post_install_message: 
@@ -64,7 +66,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.3.7
+rubygems_version: 1.6.2
 signing_key: 
 specification_version: 3
 summary: "Ruby gem za transliteraciju \xC4\x87irilice na latinicu i tzv. ASCII latinicu."