babosa 0.2.2 → 0.3.0

data/lib/babosa/transliterator/danish.rb

@@ -0,0 +1,15 @@
+# encoding: utf-8
+module Babosa
+  module Transliterator
+    class Danish < Latin
+      APPROXIMATIONS = {
+        "æ" => "ae",
+        "ø" => "oe",
+        "å" => "aa",
+        "Ø" => "Oe",
+        "Å" => "Aa"
+      }
+    end
+  end
+end
+

data/lib/babosa/transliterator/german.rb

@@ -0,0 +1,15 @@
+# encoding: utf-8
+module Babosa
+  module Transliterator
+    class German < Latin
+      APPROXIMATIONS = {
+        "ä" => "ae",
+        "ö" => "oe",
+        "ü" => "ue",
+        "Ä" => "Ae",
+        "Ö" => "Oe",
+        "Ü" => "Ue"
+      }
+    end
+  end
+end

data/lib/babosa/transliterator/latin.rb

@@ -0,0 +1,199 @@
+# encoding: utf-8
+module Babosa
+  module Transliterator
+    class Latin < Base
+
+      APPROXIMATIONS = {
+        "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",
+        "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",
+        "Ă" => "A",
+        "Ą" => "A",
+        "Ć" => "C",
+        "Ĉ" => "C",
+        "Ċ" => "C",
+        "Č" => "C",
+        "Ď" => "D",
+        "Đ" => "D",
+        "Ē" => "E",
+        "Ĕ" => "E",
+        "Ė" => "E",
+        "Ę" => "E",
+        "Ě" => "E",
+        "Ĝ" => "G",
+        "Ğ" => "G",
+        "Ġ" => "G",
+        "Ģ" => "G",
+        "Ĥ" => "H",
+        "Ħ" => "H",
+        "Ĩ" => "I",
+        "Ī" => "I",
+        "Ĭ" => "I",
+        "Į" => "I",
+        "İ" => "I",
+        "IJ" => "Ij",
+        "Ĵ" => "J",
+        "Ķ" => "K",
+        "Ĺ" => "L",
+        "Ļ" => "L",
+        "Ľ" => "L",
+        "Ŀ" => "L",
+        "Ł" => "L",
+        "Ń" => "N",
+        "Ņ" => "N",
+        "Ň" => "N",
+        "Ŋ" => "Ng",
+        "Ō" => "O",
+        "Ŏ" => "O",
+        "Ő" => "O",
+        "Œ" => "OE",
+        "Ŕ" => "R",
+        "Ŗ" => "R",
+        "Ř" => "R",
+        "Ś" => "S",
+        "Ŝ" => "S",
+        "Ş" => "S",
+        "Š" => "S",
+        "Ţ" => "T",
+        "Ť" => "T",
+        "Ŧ" => "T",
+        "Ũ" => "U",
+        "Ū" => "U",
+        "Ŭ" => "U",
+        "Ů" => "U",
+        "Ű" => "U",
+        "Ų" => "U",
+        "Ŵ" => "W",
+        "Ŷ" => "Y",
+        "Ÿ" => "Y",
+        "Ź" => "Z",
+        "Ż" => "Z",
+        "Ž" => "Z",
+        "ā" => "a",
+        "ă" => "a",
+        "ą" => "a",
+        "ć" => "c",
+        "ĉ" => "c",
+        "ċ" => "c",
+        "č" => "c",
+        "ď" => "d",
+        "đ" => "d",
+        "ē" => "e",
+        "ĕ" => "e",
+        "ė" => "e",
+        "ę" => "e",
+        "ě" => "e",
+        "ĝ" => "g",
+        "ğ" => "g",
+        "ġ" => "g",
+        "ģ" => "g",
+        "ĥ" => "h",
+        "ħ" => "h",
+        "ĩ" => "i",
+        "ī" => "i",
+        "ĭ" => "i",
+        "į" => "i",
+        "ı" => "i",
+        "ij" => "ij",
+        "ĵ" => "j",
+        "ķ" => "k",
+        "ĸ" => "k",
+        "ĺ" => "l",
+        "ļ" => "l",
+        "ľ" => "l",
+        "ŀ" => "l",
+        "ł" => "l",
+        "ń" => "n",
+        "ņ" => "n",
+        "ň" => "n",
+        "ʼn" => "n",
+        "ŋ" => "ng",
+        "ō" => "o",
+        "ŏ" => "o",
+        "ő" => "o",
+        "œ" => "oe",
+        "ŕ" => "r",
+        "ŗ" => "r",
+        "ř" => "r",
+        "ś" => "s",
+        "ŝ" => "s",
+        "ş" => "s",
+        "š" => "s",
+        "ţ" => "t",
+        "ť" => "t",
+        "ŧ" => "t",
+        "ũ" => "u",
+        "ū" => "u",
+        "ŭ" => "u",
+        "ů" => "u",
+        "ű" => "u",
+        "ų" => "u",
+        "ŵ" => "w",
+        "ŷ" => "y",
+        "ž" => "z",
+        "ź" => "z",
+        "ż" => "z"
+      }
+    end
+  end
+end

data/lib/babosa/transliterator/russian.rb

@@ -0,0 +1,22 @@
+# encoding: utf-8
+module Babosa
+  module Transliterator
+    class Russian < Cyrillic
+      APPROXIMATIONS = {
+        "Й" => "I",
+        "М" => "M",
+        "Х" => "H",
+        "Ц" => "Ts",
+        "Ш" => "Sh",
+        "Щ" => "Sch",
+        "Ю" => "U",
+        "Я" => "Ya",
+        "й" => "i",
+        "х" => "h",
+        "ц" => "ts",
+        "щ" => "sch",
+        "ю" => "u"
+      }
+    end
+  end
+end

data/lib/babosa/transliterator/serbian.rb

@@ -0,0 +1,34 @@
+# encoding: utf-8
+
+module Babosa
+  module Transliterator
+    class Serbian < Latin
+      APPROXIMATIONS = Cyrillic.const_get(:APPROXIMATIONS).merge({
+        "Ð" => "Dj",
+        "Č" => "Ch",
+        "Š" => "Sh",
+        "č" => "ch",
+        "đ" => "dj",
+        "š" => "sh",
+        "Ћ" => "C",
+        "Ц" => "C",
+        "Ч" => "Ch",
+        "Ђ" => "Dj",
+        "Џ" => "Dz",
+        "Х" => "H",
+        "Ј" => "J",
+        "Љ" => "Lj",
+        "Њ" => "Nj",
+        "ц" => "c",
+        "ћ" => "c",
+        "ч" => "ch",
+        "ђ" => "dj",
+        "џ" => "dz",
+        "х" => "h",
+        "ј" => "j",
+        "љ" => "lj",
+        "њ" => "nj"
+      })
+    end
+  end
+end

data/lib/babosa/transliterator/spanish.rb

@@ -0,0 +1,9 @@
+# encoding: utf-8
+
+module Babosa
+  module Transliterator
+    class Spanish < Latin
+      APPROXIMATIONS = {"ñ" => "ni", "Ñ" => "Ni"}
+    end
+  end
+end

data/lib/babosa/transliterator/ukranian.rb

@@ -0,0 +1,11 @@
+# encoding: utf-8
+module Babosa
+  module Transliterator
+    class Ukranian < Cyrillic
+      APPROXIMATIONS = {
+        "И" => "Y",
+        "и" => "y",
+      }
+    end
+  end
+end

data/lib/babosa/utf8/dumb_proxy.rb

@@ -1,4 +1,5 @@
 require File.expand_path("../mappings", __FILE__)
+
 module Babosa
   module UTF8
 

data/lib/babosa/version.rb

@@ -1,5 +1,5 @@
 module Babosa
   module Version
-    STRING = "0.2.2"
+    STRING = "0.3.0"
   end
 end

data/spec/babosa_spec.rb

@@ -0,0 +1,131 @@
+# encoding: utf-8
+require File.expand_path("../spec_helper", __FILE__)
+
+describe Babosa::Identifier do
+
+  it "should respond_to :empty?" do
+    "".to_slug.should respond_to(:empty?)
+  end
+
+  %w[approximate_ascii clean downcase word_chars normalize to_ascii upcase with_dashes].each do |method|
+    describe "##{method}" do
+      it "should work with invalid UTF-8 strings" do
+        expect {"\x93abc".to_slug.send method}.not_to raise_exception
+      end
+    end
+  end
+
+  describe "#word_chars" do
+    it "word_chars! should leave only letters and spaces" do
+      string = "a*$%^$@!@b$%^&*()*!c"
+      string.to_slug.word_chars.should match(/[a-z ]*/i)
+    end
+  end
+
+  describe "#transliterate" do
+    it "should transliterate to ascii" do
+      slug = (0xC0..0x17E).to_a.each do |codepoint|
+        ss = [codepoint].pack("U*").to_slug
+        ss.approximate_ascii.should match(/[\x0-\x7f]/)
+      end
+    end
+
+    it "should transliterate uncomposed utf8" do
+      string = [117, 776].pack("U*") # "ü" as ASCII "u" plus COMBINING DIAERESIS
+      string.to_slug.approximate_ascii.should eql("u")
+    end
+  end
+
+  describe "#downcase" do
+    it "should lowercase strings" do
+      "FELIZ AÑO".to_slug.downcase.should eql("feliz año")
+    end
+  end
+
+  describe "#upcase" do
+    it "should uppercase strings" do
+      "feliz año".to_slug.upcase.should eql("FELIZ AÑO")
+    end
+  end
+
+  describe "#normalize" do
+    it "should replace whitespace with dashes" do
+      "a b".to_slug.clean.normalize.should eql("a-b")
+    end
+
+    it "should replace multiple spaces with 1 dash" do
+      "a    b".to_slug.clean.normalize.should eql("a-b")
+    end
+
+    it "should replace multiple dashes with 1 dash" do
+      "male - female".to_slug.normalize.should eql("male-female")
+    end
+
+    it "should strip trailing space" do
+      "ab ".to_slug.normalize.should eql("ab")
+    end
+
+    it "should strip leading space" do
+      " ab".to_slug.normalize.should eql("ab")
+    end
+
+    it "should strip trailing slashes" do
+      "ab-".to_slug.normalize.should eql("ab")
+    end
+
+    it "should strip leading slashes" do
+      "-ab".to_slug.normalize.should eql("ab")
+    end
+
+    it "should not modify valid name strings" do
+      "a-b-c-d".to_slug.normalize.should eql("a-b-c-d")
+    end
+
+    it "should work with non roman chars" do
+      "検 索".to_slug.normalize.should eql("検-索")
+    end
+
+    context "with to_ascii option" do
+      it "should approximate and strip non ascii" do
+        ss = "カタカナ: katakana is über cool".to_slug
+        ss.normalize(:to_ascii => true).should eql("katakana-is-uber-cool")
+      end
+    end
+  end
+
+  describe "#truncate_bytes" do
+    it "should by byte length" do
+      "üa".to_slug.truncate_bytes(2).should eql("ü")
+      "üa".to_slug.truncate_bytes(1).should eql("")
+      "üa".to_slug.truncate_bytes(100).should eql("üa")
+      "üéøá".to_slug.truncate_bytes(3).should eql("ü")
+    end
+  end
+
+  describe "#truncate" do
+    it "should truncate by char length" do
+      "üa".to_slug.truncate(2).should eql("üa")
+      "üa".to_slug.truncate(1).should eql("ü")
+      "üa".to_slug.truncate(100).should eql("üa")
+    end
+  end
+
+  describe "#with_dashes" do
+    it "should not change byte size when replacing spaces" do
+      "".to_slug.with_dashes.bytesize.should eql(0)
+      " ".to_slug.with_dashes.bytesize.should eql(1)
+      "-abc-".to_slug.with_dashes.bytesize.should eql(5)
+      " abc ".to_slug.with_dashes.bytesize.should eql(5)
+      " a  bc ".to_slug.with_dashes.bytesize.should eql(7)
+    end
+  end
+
+  describe "#to_ruby_method" do
+    it "should get a string suitable for use as a ruby method" do
+      "¿¿¿hello... world???".to_slug.to_ruby_method.should eql("hello_world?")
+      "カタカナ: katakana is über cool".to_slug.to_ruby_method.should eql("katakana_is_uber_cool")
+      "カタカナ: katakana is über cool!".to_slug.to_ruby_method.should eql("katakana_is_uber_cool!")
+      "カタカナ: katakana is über cool".to_slug.to_ruby_method(false).should eql("katakana_is_uber_cool")
+    end
+  end
+end