ultra-clean-kit 0.0.1

data/babosa-2.1.0/lib/babosa/transliterator/base.rb

@@ -0,0 +1,94 @@
+# frozen_string_literal: true
+
+require "singleton"
+
+module Babosa
+  module Transliterator
+    def self.get(symbol)
+      class_name = symbol.to_s.split("_").map { |a| a.gsub(/\b('?[a-z])/) { Regexp.last_match(1).upcase } }.join
+      const_get(class_name)
+    end
+
+    class Base
+      include Singleton
+
+      APPROXIMATIONS = {
+        "×" => "x",
+        "÷" => "/",
+        "‐" => "-",
+        "‑" => "-",
+        "‒" => "-",
+        "–" => "-",
+        "—" => "-",
+        "―" => "-",
+        "‘" => "'",
+        "‛" => "'",
+        "“" => '"',
+        "”" => '"',
+        "„" => '"',
+        "‟" => '"',
+        "’" => "'",
+        "，" => ",",
+        "。" => ".",
+        "！" => "!",
+        "？" => "?",
+        "、" => ",",
+        "（" => "(",
+        "）" => ")",
+        "【" => "[",
+        "】" => "]",
+        "；" => ";",
+        "：" => ":",
+        "《" => "<",
+        "》" => ">",
+        # various kinds of space characters
+        "\xc2\xa0" => " ",
+        "\xe2\x80\x80" => " ",
+        "\xe2\x80\x81" => " ",
+        "\xe2\x80\x82" => " ",
+        "\xe2\x80\x83" => " ",
+        "\xe2\x80\x84" => " ",
+        "\xe2\x80\x85" => " ",
+        "\xe2\x80\x86" => " ",
+        "\xe2\x80\x87" => " ",
+        "\xe2\x80\x88" => " ",
+        "\xe2\x80\x89" => " ",
+        "\xe2\x80\x8a" => " ",
+        "\xe2\x81\x9f" => " ",
+        "\xe3\x80\x80" => " "
+      }.freeze
+
+      attr_reader :approximations
+
+      def initialize
+        @approximations = if self.class < Base
+          self.class.superclass.instance.approximations.dup
+        else
+          {}
+        end
+        self.class.const_get(:APPROXIMATIONS).each_with_object(@approximations) do |object, memo|
+          index = object[0].codepoints.shift
+          value = object[1].codepoints
+          memo[index] = value.length == 1 ? value[0] : value
+        end
+        @approximations.freeze
+      end
+
+      # Accepts a single UTF-8 codepoint and returns the ASCII character code
+      # used as the transliteration value.
+      def [](codepoint)
+        @approximations[codepoint]
+      end
+
+      # Transliterates a string.
+      def transliterate(string)
+        string.codepoints.map { |char| self[char] || char }.flatten.pack("U*")
+      end
+    end
+  end
+end
+
+Dir[File.expand_path("*.rb", __dir__)]
+  .reject { |f| f.end_with?("base.rb") }
+  .sort
+  .each(&method(:require))

data/babosa-2.1.0/lib/babosa/transliterator/bulgarian.rb

@@ -0,0 +1,30 @@
+# frozen_string_literal: true
+
+require_relative "cyrillic"
+
+module Babosa
+  module Transliterator
+    class Bulgarian < Cyrillic
+      APPROXIMATIONS = {
+        "Ж" => "J",
+        "Й" => "I",
+        "Х" => "H",
+        "Ц" => "C",
+        "Щ" => "Sht",
+        "Ъ" => "U",
+        "Ь" => "I",
+        "Ю" => "Iu",
+        "Я" => "Ia",
+        "ж" => "j",
+        "й" => "i",
+        "х" => "h",
+        "ц" => "c",
+        "щ" => "sht",
+        "ъ" => "u",
+        "ь" => "i",
+        "ю" => "iu",
+        "я" => "ia"
+      }.freeze
+    end
+  end
+end

data/babosa-2.1.0/lib/babosa/transliterator/cyrillic.rb

@@ -0,0 +1,108 @@
+# frozen_string_literal: true
+
+module Babosa
+  module Transliterator
+    # Approximations are based on GOST 7.79, System B:
+    # http://en.wikipedia.org/wiki/ISO_9#GOST_7.79
+    class Cyrillic < Base
+      APPROXIMATIONS = {
+        "Ё" => "Yo",
+        "Ѓ" => "G",
+        "Є" => "Ye",
+        "Ї" => "Yi",
+        "Љ" => "L",
+        "Њ" => "N",
+        "Ќ" => "K",
+        "Ў" => "U",
+        "Џ" => "Dh",
+        "А" => "A",
+        "Б" => "B",
+        "В" => "V",
+        "Г" => "G",
+        "Д" => "D",
+        "Е" => "E",
+        "Ж" => "Zh",
+        "З" => "Z",
+        "И" => "I",
+        "Й" => "J",
+        "К" => "K",
+        "Л" => "L",
+        "М" => "M",
+        "Н" => "N",
+        "О" => "O",
+        "П" => "P",
+        "Р" => "R",
+        "С" => "S",
+        "Т" => "T",
+        "У" => "U",
+        "Ф" => "F",
+        "Х" => "X",
+        "Ц" => "Cz",
+        "Ч" => "Ch",
+        "Ш" => "Sh",
+        "Щ" => "Shh",
+        "Ъ" => "",
+        "Ы" => "Y",
+        "Ь" => "",
+        "Э" => "E",
+        "Ю" => "Yu",
+        "Я" => "Ya",
+        "а" => "a",
+        "б" => "b",
+        "в" => "v",
+        "г" => "g",
+        "д" => "d",
+        "е" => "e",
+        "ж" => "zh",
+        "з" => "z",
+        "и" => "i",
+        "й" => "j",
+        "к" => "k",
+        "л" => "l",
+        "м" => "m",
+        "н" => "n",
+        "о" => "o",
+        "п" => "p",
+        "р" => "r",
+        "с" => "s",
+        "т" => "t",
+        "у" => "u",
+        "ф" => "f",
+        "х" => "x",
+        "ц" => "cz",
+        "ч" => "ch",
+        "ш" => "sh",
+        "щ" => "shh",
+        "ъ" => "",
+        "ы" => "y",
+        "ь" => "",
+        "э" => "e",
+        "ю" => "yu",
+        "я" => "ya",
+        "ё" => "yo",
+        "ѓ" => "g",
+        "є" => "ye",
+        "ї" => "yi",
+        "љ" => "l",
+        "њ" => "n",
+        "ќ" => "k",
+        "ў" => "u",
+        "џ" => "dh",
+        "Ѣ" => "Ye",
+        "ѣ" => "ye",
+        "Ѫ" => "O",
+        "ѫ" => "o",
+        "Ѳ" => "Fh",
+        "ѳ" => "fh",
+        "Ѵ" => "Yh",
+        "ѵ" => "yh",
+        "Ґ" => "G",
+        "ґ" => "g"
+      }.freeze
+
+      def transliterate(string)
+        super.gsub(/(c)z([ieyj])/) { "#{Regexp.last_match(1)}#{Regexp.last_match(2)}" }
+      end
+    end
+  end
+end

data/babosa-2.1.0/lib/babosa/transliterator/danish.rb

@@ -0,0 +1,17 @@
+# frozen_string_literal: true
+
+require_relative "latin"
+
+module Babosa
+  module Transliterator
+    class Danish < Latin
+      APPROXIMATIONS = {
+        "æ" => "ae",
+        "ø" => "oe",
+        "å" => "aa",
+        "Ø" => "Oe",
+        "Å" => "Aa"
+      }.freeze
+    end
+  end
+end

data/babosa-2.1.0/lib/babosa/transliterator/german.rb

@@ -0,0 +1,18 @@
+# frozen_string_literal: true
+
+require_relative "latin"
+
+module Babosa
+  module Transliterator
+    class German < Latin
+      APPROXIMATIONS = {
+        "ä" => "ae",
+        "ö" => "oe",
+        "ü" => "ue",
+        "Ä" => "Ae",
+        "Ö" => "Oe",
+        "Ü" => "Ue"
+      }.freeze
+    end
+  end
+end

data/babosa-2.1.0/lib/babosa/transliterator/greek.rb

@@ -0,0 +1,78 @@
+# frozen_string_literal: true
+
+module Babosa
+  module Transliterator
+    class Greek < Base
+      APPROXIMATIONS = {
+        "Α" => "A",
+        "Ά" => "A",
+        "α" => "a",
+        "ά" => "a",
+        "Β" => "V",
+        "β" => "v",
+        "Γ" => "G",
+        "γ" => "g",
+        "Δ" => "D",
+        "δ" => "d",
+        "Ε" => "E",
+        "Έ" => "E",
+        "ε" => "e",
+        "έ" => "e",
+        "Ζ" => "Z",
+        "ζ" => "z",
+        "Η" => "I",
+        "Ή" => "i",
+        "η" => "i",
+        "ή" => "i",
+        "Θ" => "TH",
+        "θ" => "th",
+        "Ι" => "I",
+        "Ί" => "Ι",
+        "Î" => "I",
+        "ι" => "i",
+        "ί" => "i",
+        "ϊ" => "i",
+        "ΐ" => "i",
+        "Κ" => "K",
+        "κ" => "k",
+        "Λ" => "L",
+        "λ" => "l",
+        "Μ" => "M",
+        "μ" => "m",
+        "Ν" => "N",
+        "ν" => "n",
+        "Ξ" => "KS",
+        "ξ" => "ks",
+        "Ο" => "O",
+        "Ό" => "O",
+        "ο" => "o",
+        "ό" => "o",
+        "Π" => "P",
+        "π" => "p",
+        "Ρ" => "R",
+        "ρ" => "r",
+        "Σ" => "S",
+        "σ" => "s",
+        "ς" => "s",
+        "Τ" => "T",
+        "τ" => "t",
+        "Υ" => "Y",
+        "Ύ" => "Y",
+        "υ" => "y",
+        "ύ" => "y",
+        "ϋ" => "y",
+        "ΰ" => "y",
+        "Φ" => "F",
+        "φ" => "f",
+        "Χ" => "X",
+        "χ" => "x",
+        "Ψ" => "PS",
+        "ψ" => "ps",
+        "Ω" => "O",
+        "Ώ" => "O",
+        "ω" => "o",
+        "ώ" => "o"
+      }.freeze
+    end
+  end
+end

data/babosa-2.1.0/lib/babosa/transliterator/hindi.rb

@@ -0,0 +1,138 @@
+# frozen_string_literal: true
+
+module Babosa
+  module Transliterator
+    class Hindi < Base
+      APPROXIMATIONS = {
+        "ऀ" => "n",
+        "ँ" => "n",
+        "ं" => "n",
+        "ः" => "h",
+        "ऄ" => "a",
+        "अ" => "a",
+        "आ" => "aa",
+        "इ" => "i",
+        "ई" => "ii",
+        "उ" => "u",
+        "ऊ" => "uu",
+        "ऋ" => "ri",
+        "ऌ" => "lri",
+        "ऍ" => "e",
+        "ऎ" => "e",
+        "ए" => "e",
+        "ऐ" => "ei",
+        "ऑ" => "o",
+        "ऒ" => "o",
+        "ओ" => "o",
+        "औ" => "ou",
+        "क" => "k",
+        "ख" => "kh",
+        "ग" => "g",
+        "घ" => "gh",
+        "ङ" => "d",
+        "च" => "ch",
+        "छ" => "chh",
+        "ज" => "j",
+        "झ" => "jh",
+        "ञ" => "ny",
+        "ट" => "tt",
+        "ठ" => "tth",
+        "ड" => "dd",
+        "ढ" => "ddh",
+        "ण" => "nn",
+        "त" => "t",
+        "थ" => "th",
+        "द" => "d",
+        "ध" => "dh",
+        "न" => "n",
+        "ऩ" => "nnn",
+        "प" => "p",
+        "फ" => "ph",
+        "ब" => "b",
+        "भ" => "bh",
+        "म" => "m",
+        "य" => "y",
+        "र" => "r",
+        "ऱ" => "rr",
+        "ल" => "l",
+        "ळ" => "ll",
+        "ऴ" => "ll",
+        "व" => "v",
+        "श" => "sh",
+        "ष" => "ss",
+        "स" => "s",
+        "ह" => "h",
+        "ऺ" => "oe",
+        "ऻ" => "ooe",
+        "़" => "",
+        "ऽ" => "-",
+        "ा" => "aa",
+        "ि" => "i",
+        "ी" => "ii",
+        "ु" => "u",
+        "ू" => "uu",
+        "ृ" => "r",
+        "ॄ" => "rr",
+        "ॅ" => "e",
+        "ॆ" => "e",
+        "े" => "e",
+        "ै" => "ai",
+        "ॉ" => "o",
+        "ॊ" => "o",
+        "ो" => "o",
+        "ौ" => "au",
+        "्" => "",
+        "ॎ" => "e",
+        "ॏ" => "aw",
+        "ॐ" => "om",
+        "॑" => "",
+        "॒" => "_",
+        "॓" => "",
+        "॔" => "",
+        "ॕ" => "ee",
+        "ॖ" => "ue",
+        "ॗ" => "uue",
+        "क़" => "q",
+        "ख़" => "khh",
+        "ग़" => "ghh",
+        "ज़" => "za",
+        "ड़" => "dddh",
+        "ढ़" => "rh",
+        "फ़" => "f",
+        "य़" => "yy",
+        "ॠ" => "rri",
+        "ॡ" => "lr",
+        "ॢ" => "l",
+        "ॣ" => "l",
+        "।" => ".",
+        "॥" => "..",
+        "०" => "0",
+        "१" => "1",
+        "२" => "2",
+        "३" => "3",
+        "४" => "4",
+        "५" => "5",
+        "६" => "6",
+        "७" => "7",
+        "८" => "8",
+        "९" => "9",
+        "॰" => ".",
+        "ॱ" => ".",
+        "ॲ" => "a",
+        "ॳ" => "oe",
+        "ॴ" => "ooe",
+        "ॵ" => "aw",
+        "ॶ" => "ue",
+        "ॷ" => "uue",
+        "ॸ" => "dd",
+        "ॹ" => "zh",
+        "ॺ" => "y",
+        "ॻ" => "gg",
+        "ॼ" => "jj",
+        "ॽ" => "?",
+        "ॾ" => "ddd",
+        "ॿ" => "bb"
+      }.freeze
+    end
+  end
+end

data/babosa-2.1.0/lib/babosa/transliterator/latin.rb

@@ -0,0 +1,199 @@
+# frozen_string_literal: true
+
+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"
+      }.freeze
+    end
+  end
+end