Delegate Inflector.transliterate to i18n. [#4508 state:resolved]

Ancillary changes: Moved Chars#normalize into a class method; removed
unused UTF_PAT constant.

Signed-off-by: José Valim <jose.valim@gmail.com>

1 files changed, 18 insertions, 33 deletions

diff --git a/activesupport/test/transliterate_test.rb b/activesupport/test/transliterate_test.rb
index d689b6be73..b054855d08 100644
--- a/activesupport/test/transliterate_test.rb
+++ b/activesupport/test/transliterate_test.rb
@@ -4,36 +4,6 @@ require 'active_support/inflector/transliterate'
 
 class TransliterateTest < Test::Unit::TestCase
 
-  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",
-    "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"
-  }
-
   def test_transliterate_should_not_change_ascii_chars
     (0..127).each do |byte|
       char = [byte].pack("U")
@@ -41,10 +11,25 @@ class TransliterateTest < Test::Unit::TestCase
     end
   end
 
-  def test_should_convert_accented_chars_to_approximate_ascii_chars
-    APPROXIMATIONS.each do |given, expected|
-      assert_equal expected, ActiveSupport::Inflector.transliterate(given)
+  def test_transliterate_should_approximate_ascii
+    # create string with range of Unicode"s western characters with
+    # diacritics, excluding the division and multiplication signs which for
+    # some reason or other are floating in the middle of all the letters.
+    string = (0xC0..0x17E).to_a.reject {|c| [0xD7, 0xF7].include? c}.pack("U*")
+    string.each_char do |char|
+      assert_match %r{^[a-zA-Z']*$}, ActiveSupport::Inflector.transliterate(string)
     end
   end
 
+  def test_transliterate_should_work_with_custom_i18n_rules_and_uncomposed_utf8
+    char = [117, 776].pack("U*") # "ü" as ASCII "u" plus COMBINING DIAERESIS
+    I18n.backend.store_translations(:de, :i18n => {:transliterate => {:rule => {"ü" => "ue"}}})
+    I18n.locale = :de
+    assert_equal "ue", ActiveSupport::Inflector.transliterate(char)
+  end
+
+  def test_transliterate_should_allow_a_custom_replacement_char
+    assert_equal "a*b", ActiveSupport::Inflector.transliterate("a索b", "*")
+  end
+
 end