string_utils 1.0.3 → 1.0.4

data/.gitignore

@@ -1,3 +1,5 @@
 pkg/*
 *.gem
 .bundle
+.idea
+

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    string_utils (1.0.2)
+    string_utils (1.0.4)
       activesupport (>= 2.3.5)
       i18n
 

data/lib/string_utils.rb

@@ -4,11 +4,14 @@ if RUBY_VERSION < '1.9'
   require 'active_support/core_ext/string/multibyte'
 end
 
+require 'string_utils/transliteration'
 
-# StringUtils is a library that allows various string manipulation
+
+# StringUtils is a library that provides various handy string manipulation methods 
 # Example usage:
 #   * StringUtils.truncate("hello world", 10, "...") #=> "hello..."
 #   * StringUtils.normalize_name "\302\240  Gran Via/Avda.de Asturias " #=> :Gran Via / Avda. de Asturias"
+#   * StringUtils.urlify("waßer") #=> "wasser"
 module StringUtils
   extend self
 
@@ -19,6 +22,19 @@ module StringUtils
   WHITESPACES        = /#{WHITESPACE_MATCHER}+/
 
 
+  # Converts a string to a nicely readable URL
+  # opts:
+  # :default_replacement -- string to use for unknown characters (Default: "")
+  # :whitespace_replacement     -- string to use to replace whitespace+ (Default: "-")  
+  def urlify(string, opts = {})
+    opts = {:whitespace_replacement => '-', :default_replacement => ""}.merge(opts)
+    string = string.gsub(WHITESPACES, opts[:whitespace_replacement])
+    string.strip!
+    string.gsub!(/[^\x00-\x7f]/u) { |char| TRANSLITERATIONS[char] || opts[:default_replacement] }
+    string.gsub!(/[^a-z0-9\-+_]/, opts[:default_replacement])
+    string
+  end
+
   # Normalizes whitespace
   # "a , a" => "a, a"
   # "a ,a"  => "a, a"

data/lib/string_utils/transliteration.rb

@@ -0,0 +1,89 @@
+module StringUtils
+  # Based on transliteration table from i18n v0.5.0
+  TRANSLITERATIONS = {
+      # Latin      
+      "À" =>"A", "Á"=>"A", "Â"=>"A", "Ã"=>"A", "Ä"=>"A", "Å"=>"A", "Æ"=>"AE",
+      "Ç" =>"C", "È"=>"E", "É"=>"E", "Ê"=>"E", "Ë"=>"E", "Ì"=>"I", "Í"=>"I",
+      "Î" =>"I", "Ï"=>"I", "Ð"=>"D", "Ñ"=>"N", "Ò"=>"O", "Ó"=>"O", "Ô"=>"O",
+      "Õ" =>"O", "Ö"=>"O", "×"=>"x", "Ø"=>"O", "Ù"=>"U", "Ú"=>"U", "Û"=>"U",
+      "Ü" =>"U", "Ý"=>"Y", "Þ"=>"Th", "ß"=>"ss", "à"=>"a", "á"=>"a", "â"=>"a",
+      "ã" =>"a", "ä"=>"a", "å"=>"a", "æ"=>"ae", "ç"=>"c", "è"=>"e", "é"=>"e",
+      "ê" =>"e", "ë"=>"e", "ì"=>"i", "í"=>"i", "î"=>"i", "ï"=>"i", "ð"=>"d",
+      "ñ" =>"n", "ò"=>"o", "ó"=>"o", "ô"=>"o", "õ"=>"o", "ö"=>"o", "ø"=>"o",
+      "ù" =>"u", "ú"=>"u", "û"=>"u", "ü"=>"u", "ý"=>"y", "þ"=>"th", "ÿ"=>"y",
+      "Ā" =>"A", "ā"=>"a", "Ă"=>"A", "ă"=>"a", "Ą"=>"A", "ą"=>"a", "Ć"=>"C",
+      "ć" =>"c", "Ĉ"=>"C", "ĉ"=>"c", "Ċ"=>"C", "ċ"=>"c", "Č"=>"C", "č"=>"c",
+      "Ď" =>"D", "ď"=>"d", "Đ"=>"D", "đ"=>"d", "Ē"=>"E", "ē"=>"e", "Ĕ"=>"E",
+      "ĕ" =>"e", "Ė"=>"E", "ė"=>"e", "Ę"=>"E", "ę"=>"e", "Ě"=>"E", "ě"=>"e",
+      "Ĝ" =>"G", "ĝ"=>"g", "Ğ"=>"G", "ğ"=>"g", "Ġ"=>"G", "ġ"=>"g", "Ģ"=>"G",
+      "ģ" =>"g", "Ĥ"=>"H", "ĥ"=>"h", "Ħ"=>"H", "ħ"=>"h", "Ĩ"=>"I", "ĩ"=>"i",
+      "Ī" =>"I", "ī"=>"i", "Ĭ"=>"I", "ĭ"=>"i", "Į"=>"I", "į"=>"i", "İ"=>"I",
+      "ı" =>"i", "IJ"=>"IJ", "ij"=>"ij", "Ĵ"=>"J", "ĵ"=>"j", "Ķ"=>"K", "ķ"=>"k",
+      "ĸ" =>"k", "Ĺ"=>"L", "ĺ"=>"l", "Ļ"=>"L", "ļ"=>"l", "Ľ"=>"L", "ľ"=>"l",
+      "Ŀ" =>"L", "ŀ"=>"l", "Ł"=>"L", "ł"=>"l", "Ń"=>"N", "ń"=>"n", "Ņ"=>"N",
+      "ņ" =>"n", "Ň"=>"N", "ň"=>"n", "ʼn"=>"'n", "Ŋ"=>"NG", "ŋ"=>"ng",
+      "Ō" =>"O", "ō"=>"o", "Ŏ"=>"O", "ŏ"=>"o", "Ő"=>"O", "ő"=>"o", "Œ"=>"OE",
+      "œ" =>"oe", "Ŕ"=>"R", "ŕ"=>"r", "Ŗ"=>"R", "ŗ"=>"r", "Ř"=>"R", "ř"=>"r",
+      "Ś" =>"S", "ś"=>"s", "Ŝ"=>"S", "ŝ"=>"s", "Ş"=>"S", "ş"=>"s", "Š"=>"S",
+      "š" =>"s", "Ţ"=>"T", "ţ"=>"t", "Ť"=>"T", "ť"=>"t", "Ŧ"=>"T", "ŧ"=>"t",
+      "Ũ" =>"U", "ũ"=>"u", "Ū"=>"U", "ū"=>"u", "Ŭ"=>"U", "ŭ"=>"u", "Ů"=>"U",
+      "ů" =>"u", "Ű"=>"U", "ű"=>"u", "Ų"=>"U", "ų"=>"u", "Ŵ"=>"W", "ŵ"=>"w",
+      "Ŷ" =>"Y", "ŷ"=>"y", "Ÿ"=>"Y", "Ź"=>"Z", "ź"=>"z", "Ż"=>"Z", "ż"=>"z",
+      "Ž" =>"Z", "ž"=>"z",
+
+      # Cyrillic
+      "Ґ" =>"G", "Ё"=>"YO", "Є"=>"E", "Ї"=>"YI", "І"=>"I",
+      "А" =>"A", "Б"=>"B", "В"=>"V", "Г"=>"G",
+      "Д" =>"D", "Е"=>"E", "Ж"=>"ZH", "З"=>"Z", "И"=>"I",
+      "Й" =>"Y", "К"=>"K", "Л"=>"L", "М"=>"M", "Н"=>"N",
+      "О" =>"O", "П"=>"P", "Р"=>"R", "С"=>"S", "Т"=>"T",
+      "У" =>"U", "Ф"=>"F", "Х"=>"H", "Ц"=>"TS", "Ч"=>"CH",
+      "Ш" =>"SH", "Щ"=>"SCH", "Ъ"=>"'", "Ы"=>"Y", "Ь"=>"",
+      "Э" =>"E", "Ю"=>"YU", "Я"=>"YA", "і"=>"i",
+      "ґ" =>"g", "ё"=>"yo", "№"=>"#", "є"=>"e",
+      "ї" =>"yi", "а"=>"a", "б"=>"b",
+      "в" =>"v", "г"=>"g", "д"=>"d", "е"=>"e", "ж"=>"zh",
+      "з" =>"z", "и"=>"i", "й"=>"y", "к"=>"k", "л"=>"l",
+      "м" =>"m", "н"=>"n", "о"=>"o", "п"=>"p", "р"=>"r",
+      "с" =>"s", "т"=>"t", "у"=>"u", "ф"=>"f", "х"=>"h",
+      "ц" =>"ts", "ч"=>"ch", "ш"=>"sh", "щ"=>"sch", "ъ"=>"'",
+      "ы" =>"y", "ь"=>"", "э"=>"e", "ю"=>"yu", "я"=>"ya",
+
+      # Greek
+      'α' => 'a',
+      'η' => 'h',
+      'ν' => 'n',
+      'τ' => 't',
+      'β' => 'b',
+      'θ' => 'th',
+      'ξ' => 'x',
+      'υ' => 'y',
+      'γ' => 'g',
+      'ι' => 'i',
+      'ο' => 'o',
+      'φ' => 'f',
+      'δ' => 'd',
+      'κ' => 'k',
+      'π' => 'p',
+      'χ' => 'ch',
+      'ε' => 'e',
+      'λ' => 'l',
+      'ρ' => 'r',
+      'ψ' => 'ps',
+      'ζ' => 'z',
+      'μ' => 'm',
+      'σ' => 's',
+      'ω' => 'w',
+      'Θ' => 'Th',
+      'Ξ' => 'X',
+      'Γ' => 'G',
+      'Φ' => 'F',
+      'Δ' => 'D',
+      'Π' => 'P',
+      'Λ' => 'L',
+      'Ρ' => 'R',
+      'Ψ' => 'Ps',
+      'Σ' => 'S',
+      'Ω' => 'W'
+  }
+end

data/lib/string_utils/version.rb

@@ -1,3 +1,3 @@
 module StringUtils
-  VERSION = "1.0.3"
+  VERSION = "1.0.4"
 end

data/test/urlify_spec.rb

@@ -0,0 +1,19 @@
+# -*- coding: utf-8 -*-
+require "string_utils"
+
+describe "StringUtils" do
+  describe "#urlify" do
+
+    it 'replaces known entities' do
+      StringUtils.urlify("tschuß").should == "tschuss"
+    end
+
+    it 'uses :whitespace_replacement' do
+      StringUtils.urlify("a b", :whitespace_replacement => "-x-").should == "a-x-b"
+    end
+
+    it 'uses :default_replacement' do
+      StringUtils.urlify("%", :default_replacement => "A").should == "A"
+    end
+  end
+end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: string_utils
 version: !ruby/object:Gem::Version 
-  hash: 17
+  hash: 31
   prerelease: false
   segments: 
   - 1
   - 0
-  - 3
-  version: 1.0.3
+  - 4
+  version: 1.0.4
 platform: ruby
 authors: 
 - Gleb Mazovetskiy
@@ -88,10 +88,12 @@ files:
 - README
 - Rakefile
 - lib/string_utils.rb
+- lib/string_utils/transliteration.rb
 - lib/string_utils/version.rb
 - string_utils.gemspec
 - test/normalize_name_spec.rb
 - test/truncate_spec.rb
+- test/urlify_spec.rb
 has_rdoc: true
 homepage: http://github.com/glebm/string_utils
 licenses: []