refactor: replace I18n with a custom transliterator

matteoredz · Oct 23, 2023 · 2df1e72 · 2df1e72
1 parent 4e3eafb
commit 2df1e72
Show file tree

Hide file tree

Showing 5 changed files with 215 additions and 6 deletions.
diff --git a/.rubocop.yml b/.rubocop.yml
@@ -37,6 +37,7 @@ Metrics/BlockLength:
 Metrics/ClassLength:
   Enabled: true
   Exclude:
+    - 'lib/itax_code/transliterator.rb'
     - 'lib/itax_code/utils.rb'
     - 'test/**/*'
 

diff --git a/itax_code.gemspec b/itax_code.gemspec
@@ -25,5 +25,4 @@ Gem::Specification.new do |spec|
   spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ["lib"]
   spec.metadata["rubygems_mfa_required"] = "false"
-  spec.add_dependency "i18n", "~> 1.14", ">= 1.14.1"
 end
diff --git a/lib/itax_code/transliterator.rb b/lib/itax_code/transliterator.rb
@@ -0,0 +1,211 @@
+# frozen_string_literal: true
+
+module ItaxCode
+  # https://github.com/ruby-i18n/i18n/blob/master/lib/i18n/backend/transliterator.rb
+  class Transliterator
+    DEFAULT_REPLACEMENT_CHAR = "?"
+
+    def transliterate(string, replacement = nil)
+      replacement ||= DEFAULT_REPLACEMENT_CHAR
+      string.gsub(/[^\x00-\x7f]/u) { |char| approximations[char] || replacement }
+    end
+
+    private
+
+      def approximations
+        @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",
+          "×" => "x",
+          "Ø" => "O",
+          "Ù" => "U",
+          "Ú" => "U",
+          "Û" => "U",
+          "Ü" => "U",
+          "Ý" => "Y",
+          "Þ" => "Th",
+          "ß" => "ss",
+          "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"
+        }
+      end
+  end
+end
diff --git a/lib/itax_code/utils.rb b/lib/itax_code/utils.rb
@@ -1,7 +1,7 @@
 # frozen_string_literal: true
 
 require "csv"
-require "i18n"
+require "itax_code/transliterator"
 
 module ItaxCode
   class Utils
@@ -23,7 +23,8 @@ def slugged(string, separator = "-")
     def transliterate(string)
       return string if string.ascii_only?
 
-      I18n.transliterate(string.unicode_normalize(:nfc))
+      transliterator = Transliterator.new
+      transliterator.transliterate(string.unicode_normalize(:nfc))
     end
 
     def tax_code_sections_regex

diff --git a/test/test_helper.rb b/test/test_helper.rb
@@ -20,6 +20,3 @@
 Minitest::Test.class_eval do
   extend TestMacro
 end
-
-# Disable available locale checks to avoid warnings running the test suite.
-I18n.enforce_available_locales = false