interscript-maps 2.0.5

data/maps/bgnpcgn-isl-Latn-Latn-1964.imp

@@ -0,0 +1,42 @@
+metadata {
+  authority_id: bgnpcgn
+  id: 1964
+  language: iso-639-2:isl
+  source_script: Latn
+  destination_script: Latn
+  name: TRANSLITERATION OF ICELANDIC BGN/PCGN 1947 System
+  url: https://github.com/interscript/interscript/files/5180785/BGN_Romanization_Guide_1964_icelandic_1947.pdf
+  creation_date: 1964
+  description: |
+    The BGN and the PCGn in 1947 jointly agreed to the transliteration of two letters of the Icelandic alphabet which,
+    although used in writing Old English, have disappeared from the modern English alphabet.
+
+    The transliterated letters are the edh (Ð ð) and the thorn (Þ þ), pronounved as th in "thus" and th in "think," respectively.
+
+    It was felt that it was better to transliterate these letters into familiar symbols than preserve such unfamiliar letters in the nomenclature.
+
+  notes:
+    - More about "edh" letter - https://en.wikipedia.org/wiki/Eth
+    - More about "thorn" letter - https://en.wikipedia.org/wiki/Thorn_(letter)
+}
+
+tests {
+  test "Fyrirgefðu", "Fyrirgefdhu"
+  test "þu ert velkominn", "thu ert velkominn"
+  test "GOÐAN DAGINN", "GODHAN DAGINN"
+  test "Þakka", "Thakka"
+}
+
+stage {
+
+  # CHARACTERS
+  parallel {
+    sub "Ð", "Dh" # Ð
+    sub "ð", "dh" # ð
+    sub "Þ", "Th" # Þ
+    sub "þ", "th" # þ
+  }
+
+  sub any(["Th", "Dh"]), upcase, before: any("A".."Z")
+  sub any(["Th", "Dh"]), upcase, after: any("A".."Z")
+}

data/maps/bgnpcgn-isl-Latn-Latn-1968.imp

@@ -0,0 +1,32 @@
+metadata {
+  authority_id: bgnpcgn
+  id: 1968
+  language: iso-639-2:isl
+  source_script: Latn
+  destination_script: Latn
+  name: BGN/PCGN Icelandic 1968 Roman-Script Spelling Convention Agreement
+  url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693794/ROMAN-SCRIPT_SPELLING_CONVENTIONS.pdf
+  creation_date: 1968
+
+  notes:
+    - |
+      The special letter Ð ð, known as edh, [Unicode: 00D0, 00F0] and the special letter Þ þ, known as thorn,
+      [Unicode: 00DE, 00FE] should be reproduced in those forms whenever encountered. In those instances
+      when they cannot be reproduced, however, the digraph Dh dh may be substituted for Ð ð and the digraph
+      Th th may be substituted for Þ þ.
+}
+
+tests {
+  test "Fyrirgefðu", "Fyrirgefdhu"
+  test "þu ert velkominn", "thu ert velkominn"
+  test "GOÐAN DAGINN", "GODHAN DAGINN"
+  test "Þakka", "Thakka"
+}
+
+dependency "bgnpcgn-isl-Latn-Latn-1964", as: latnlatn
+
+stage {
+
+  run map.latnlatn.stage.main
+
+}

data/maps/bgnpcgn-jpn-Hrkt-Latn-1976.imp

@@ -0,0 +1,191 @@
+metadata {
+  authority_id: bgnpcgn
+  id: 1930
+  language: iso-639-2:jpn
+  source_script: Hrkt
+  destination_script: Latn
+  name: Japanese Kana Modified Hepburn 1930 System
+  url:
+  creation_date:
+  adoption_date:
+  description:
+
+  notes:
+    - Segmentation needs to be done before using this map
+    - Note 5 in the specification states that when identical repeating vowels
+      belong to different kanji characters, they shall be romanized
+      individually and an apostrophe (’) shall be placed between the vowels.
+      However since this is a map from Kana to Hepburn, there is no way to
+      implement this feature.
+    - The documentation did not specify how the hyphen should be used.
+}
+
+tests {
+  test "てがた-からみでん", "Tegata-karamiden"
+  test "てがた-すみよしちょう", "Tegata-sumiyoshichō"
+  test "さいのはま", "Sainohama"
+  test "てがた-たなか", "Tegata-tanaka"
+  test "ほりおでん", "Horioden"
+  test "そえがわ", "Soegawa"
+  test "ふねがさわ", "Funegasawa"
+  test "とくまんだて", "Tokumandate"
+  test "たてない", "Tatenai"
+  test "つるがさき", "Tsurugasaki"
+  test "しもやつせ", "Shimoyatsuse"
+  test "かみやつせ", "Kamiyatsuse"
+  test "しんとうだ", "Shintōda"
+  test "かじのめ", "Kajinome"
+  test "まえぎ", "Maegi"
+  test "くろさわ やま", "Kurosawa Yama"
+  test "いちのさわ がわ", "Ichinosawa Gawa"
+  test "はちやまえ", "Hachiyamae"
+  test "やち", "Yachi"
+  test "たてぬま", "Tatenuma"
+  test "しらはま", "Shirahama"
+  test "けせんまち", "Kesenmachi"
+  test "けいだい-かわら", "Keidai-kawara"
+  test "いしやました", "Ishiyamashita"
+  test "なえひら-やち", "Naehira-yachi"
+  test "とみの", "Tomino"
+  test "あらや-たかみまち", "Araya-takamimachi"
+  test "ながた", "Nagata"
+  test "とどろき おんせん", "Todoroki Onsen"
+  test "かしわぎはら", "Kashiwagihara"
+  test "とやけもり やま", "Toyakemori Yama"
+  test "なかさい", "Nakasai"
+  test "たけした", "Takeshita"
+  test "みと", "Mito"
+  test "みなみなかさと", "Minaminakasato"
+  test "みずおし", "Mizuoshi"
+  test "なかさと", "Nakasato"
+  test "しんかりば", "Shinkariba"
+  test "しんかみぬま", "Shinkaminuma"
+  test "しんばし", "Shinbashi"
+  test "りくぜんやました えき", "Rikuzen’yamashita Eki"
+  test "うしじまにし", "Ushijimanishi"
+  test "はまえば", "Hamaeba"
+  test "ぬまむかい", "Numamukai"
+  test "さんげんやち", "Sangen’yachi"
+  test "にけんやち", "Niken’yachi"
+  test "やちなか", "Yachinaka"
+  test "なす がわ", "Nasu Gawa"
+  test "おおはらはま", "Ōharahama"
+  test "うるご がわ", "Urugo Gawa"
+  test "なかばせ", "Nakabase"
+  test "うと えき", "Uto Eki"
+  test "みずまち", "Mizumachi"
+  test "ごんげんどう", "Gongendō"
+  test "いとひさ", "Itohisa"
+  test "あらおい", "Araoi"
+  test "わんめ", "Wanme"
+  test "かじろ", "Kajiro"
+  test "みやばら", "Miyabara"
+  test "いまどみ", "Imadomi"
+  test "かいほ", "Kaiho"
+  test "かいほ ぼえん", "Kaiho Boen"
+  test "ひきだ", "Hikida"
+  test "あさい-こむかい", "Asai-komukai"
+  test "こうざか", "Kōzaka"
+  test "こうふうだい", "Kōfūdai"
+  test "たての", "Tateno"
+  test "センター", "Sentā"
+  test "フィリピン", "Firipin"
+  test "ヴィオリン", "Viorin"
+  test "クォーター", "Kwōtā"
+  test "パッチリ", "Patchiri"
+  test "ぽっぽっや", "Poppoyya"
+}
+
+dependency "var-jpn-Hrkt-Latn-hepburn-1954", as: hrktlatn
+
+
+stage {
+
+
+  # CHARACTERS
+  parallel {
+    # Rare sounds, Table 2 & 4
+
+    sub "くぁ", "kwa"
+    sub "クァ", "kwa"
+    sub "ぐぁ", "gwa"
+    sub "グァ", "gwa"
+    sub "くぃ", "kwi"
+    sub "クィ", "kwi"
+    sub "ぐぃ", "gwa"
+    sub "グィ", "gwa"
+    sub "きぇ", "kye"
+    sub "キェ", "kye"
+    sub "ぎぇ", "gye"
+    sub "ギェ", "gye"
+    sub "くぇ", "kwe"
+    sub "クェ", "kwe"
+    sub "ぐぇ", "gwe"
+    sub "グェ", "gwe"
+    sub "くぉ", "kwo"
+    sub "クォ", "kwo"
+    sub "ぐぉ", "gwo"
+    sub "グォ", "gwo"
+    sub "しぇ", "she"
+    sub "シェ", "she"
+    sub "じぇ", "je"
+    sub "ジェ", "je"
+    sub "つぁ", "tsa"
+    sub "ツァ", "tsa"
+    sub "てぃ", "ti"
+    sub "ティ", "ti"
+    sub "でぃ", "di"
+    sub "ディ", "di"
+    sub "てゅ", "tyu"
+    sub "テュ", "tyu"
+    sub "でゅ", "dyu"
+    sub "デュ", "dyu"
+    sub "とゅ", "tu"
+    sub "トュ", "tu"
+    sub "どゅ", "du"
+    sub "ドュ", "du"
+    sub "ちぇ", "che"
+    sub "チェ", "che"
+    sub "ぢぇ", "je"
+    sub "ヂェ", "je"
+    sub "つぇ", "tse"
+    sub "ツェ", "tse"
+    sub "つぉ", "tso"
+    sub "ツォ", "tso"
+    sub "にぇ", "nye"
+    sub "ニェ", "nye"
+    sub "ふぁ", "fa"
+    sub "ファ", "fa"
+    sub "ふぃ", "fi"
+    sub "フィ", "fi"
+    sub "ふぇ", "fe"
+    sub "フェ", "fe"
+    sub "ふぉ", "fo"
+    sub "フォ", "fo"
+    sub "みぇ", "mye"
+    sub "ミェ", "mye"
+    sub "ぃぇ", "ye"
+    sub "ィェ", "ye"
+    sub "りぇ", "rye"
+    sub "リェ", "rye"
+    sub "ゔぁ", "va"
+    sub "ヴァ", "va"
+    sub "うぃ", "wi"
+    sub "ウィ", "wi"
+    sub "ゔぃ", "vi"
+    sub "ヴィ", "vi"
+    sub "うぇ", "we"
+    sub "ウェ", "we"
+    sub "ゔぇ", "ve"
+    sub "ヴェ", "ve"
+    sub "うぉ", "wo"
+    sub "ウォ", "wo"
+    sub "ゔぉ", "vo"
+    sub "ヴォ", "vo"
+    sub "ゔ", "vu"
+    sub "ヴ", "vu"
+  }
+  run map.hrktlatn.stage.main
+
+  title_case
+}

data/maps/bgnpcgn-kat-Geor-Latn-1981.imp

@@ -0,0 +1,116 @@
+metadata {
+  authority_id: bgnpcgn
+  id: 1981
+  language: iso-639-2:kat
+  source_script: Geor
+  destination_script: Latn
+  name: ROMANIZATION OF GEORGIAN; BGN/PCGN 1981 System
+  url: https://transliteration.eki.ee/pdf/Georgian.pdf
+  creation_date: 1981
+  confirmation_date: 1981
+  description: |
+    BGN/PCGN system of 1981.
+  
+  notes:
+}
+
+tests {
+  test "ჰებუდი", "hebudi"
+  test "ჯვრის წყალსაცავი", "jvris tsqalsats’avi"
+  test "ჯვავიაკვარა", "jvaviak’vara"
+  test "ჯობრია", "jobria"
+  test "ძულუხირა", "dzulukhira"
+  test "ლეკუხონა", "lek’ukhona"
+  test "აბაშა", "abasha"
+  test "ააცი", "aats’i"
+  # TODO: This belongs to which system?!
+  # - source: აბააჟახვუ
+  #   expected: abaazhvakhu
+  # TODO: These examples from GNDB are clearly using the BGNPCGN 2009 system
+  #
+  # - source: ხობის მუნიციპალიტეტი
+  #   expected: khobis munitsip’alit’et’i
+  #
+  # - source: მყინვარი ჩრდილოეთი ლეადაშატი
+  #   expected: mq’invari chrdiloeti leadashat’i
+  #
+  # - source: ხეწკვარა
+  #   expected: khets’k’vara
+  #
+  # - source: ჯამპალი
+  #   expected: jamp’ali
+  #
+  # - source: ჯავის მუნიციპალიტეტი
+  #   expected: javis munitsip’alit’et’i
+  #
+  # - source: ხოიჯგეთა
+  #   expected: khoijgeta
+  #
+  # - source: ხობის მუნიციპალიტეტი
+  #   expected: khobis munitsip’alit’et’i
+  #
+  # - source: წვიშარხუ
+  #   expected: ts’visharkhu
+  # - source: აღმოსავლეთი გუმისთა
+  #   expected: aghmosavleti gumista
+  #
+  # - source: ქვემო ბირცხა
+  #   expected: kvemo birtskha
+  #
+  # - source: ზემო ბირცხა
+  #   expected: zemo birtskha
+  #
+  # - source: აბჟაყვა
+  #   expected: abzhaq’va
+}
+
+stage {
+
+  # CHARACTERS
+  parallel {
+    sub "\u10d0", "a" # ა
+    sub "\u10d1", "b" # ბ
+    sub "\u10d2", "g" # გ
+    sub "\u10d3", "d" # დ
+    sub "\u10d4", "e" # ე
+    sub "\u10d5", "v" # ვ
+    sub "\u10d6", "z" # ზ
+    
+    sub "\u10f1", "ey" # ჱ
+    
+    sub "\u10d7", "t’" # თ
+    sub "\u10d8", "i" # ი
+    sub "\u10d9", "k’" # კ
+    sub "\u10da", "l" # ლ
+    sub "\u10db", "m" # მ
+    sub "\u10dc", "n" # ნ
+    
+    sub "\u10f2", "j" # ჲ
+    
+    sub "\u10dd", "o" # ო
+    sub "\u10de", "p" # პ
+    sub "\u10df", "zh" # ჟ
+    sub "\u10e0", "r" # რ
+    sub "\u10e1", "s" # ს
+    sub "\u10e2", "t" # ტ
+    sub "\u10e3", "u" # უ
+    sub "\u10e4", "p’" # ფ
+    sub "\u10e5", "k’" # ქ
+    sub "\u10e6", "gh" # ღ
+    sub "\u10e7", "q" # ყ
+    sub "\u10e8", "sh" # შ
+    sub "\u10e9", "ch’" # ჩ
+    sub "\u10ea", "ts’" # ც
+    sub "\u10eb", "dz" # ძ
+    sub "\u10ec", "ts" # წ
+    sub "\u10ed", "ch" # ჭ
+    sub "\u10ee", "kh" # ხ
+    
+    sub "\u10f4", "q’" # ჴ
+    
+    sub "\u10ef", "j" # ჯ
+    sub "\u10f0", "h" # ჰ
+  }
+
+}
+

data/maps/bgnpcgn-kat-Geor-Latn-2009.imp

@@ -0,0 +1,43 @@
+metadata {
+  authority_id: bgnpcgn
+  id: 2009
+  language: iso-639-2:kat
+  source_script: Geor
+  destination_script: Latn
+  name: ROMANIZATION OF GEORGIAN; Georgia 2011 national system; BGN/PCGN 2009 Agreement
+  url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/810202/ROMANIZATION_OF_GEORGIAN.pdf
+  creation_date: 2009
+  confirmation_date: 2011
+  description: |
+    This romanization system corresponds to that devised in 2002 by the
+    State Department of Geodesy and Cartography of Georgia and the
+    Institute of Linguistics of the Georgian Academy of Sciences, and
+    approved by Presidential Decree 109 of 24 February 2011. It represents
+    the Mkhedruli alphabet, as presently used in Georgia. This system was
+    adopted by BGN and PCGN in 2009, superseding the BGN/PCGN system of
+    1981.
+  
+  notes:
+    - This system denotes ejective (glottalised) consonants by means of
+      an apostrophe. The BGN/PCGN 1981 system instead used the apostrophe to
+      denote aspirated consonants (letters 8, 21, 22, 26 & 27).
+    - The Romanization columns show only lowercase forms but, when
+      romanizing, uppercase and lowercase Roman letters as appropriate should
+      be used.
+}
+
+tests {
+  test "თბილისი", "tbilisi"
+  test "მეღვინეთუხუცესი", "meghvinetukhutsesi"
+  test "ჭიანჭველა", "ch’ianch’vela"
+  test "ბაყაყი", "baq’aq’i"
+}
+
+dependency "ggg-kat-Geor-Latn-2002", as: georlatn
+
+stage {
+
+  run map.georlatn.stage.main
+
+}
+

data/maps/bgnpcgn-kaz-Cyrl-Latn-1979.imp

@@ -0,0 +1,193 @@
+metadata {
+  
+  authority_id: bgnpcgn
+  id: 1979
+  language: iso-639-2:kaz
+  source_script: Cyrl
+  destination_script: Latn
+  name: Romanization of Kazakh
+  url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/811511/ROMANIZATION_OF_KAZAKH.pdf
+  creation_date: 1979
+  confirmation_date: 2019
+  description: |
+    The BGN/PCGN system for Kazakh was designed for use in romanizing names written in the Kazakh Cyrillic alphabet.
+    The Kazakh Cyrillic alphabet contains nine characters not present in the Russian alphabet: ә, ғ, қ, ң, ө, ұ, ү, һ and і.
+  
+  notes:
+    - The character sequences гһ, зһ, кһ, нг, сһ and цһ may be romanized g·h, z·h, k·h, n·g, s·h
+      and ts·h in order to differentiate those romanizations from from the digraphs gh, zh, kh, ng, sh,
+      and the letter sequence tsh, which are used to render the characters ғ, ж, х, ң, ш, and the character sequence тш.
+    - The character ы may be romanized i̵ (Unicode encoding 0069+0335) instead of у, if so desired.
+    - Unicode values are shown with the uppercase Cyrillic character first, followed by the lowercase character.
+    - The Kazakh government has adopted a programme to move to using the Roman-script as the principal writing system for Kazakh.
+    - 'An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the
+      unmodified letters of the basic Roman script is:
+      Ä (U+00C4)    ӓ (U+00E4)
+      Ī (U+012A)    ī (U+012B)
+      Ö (U+00D6)    ö (U+00F6)
+      Ū (U+016A)    ū (U+016B)
+      Ü (U+00DC)    ü (U+00FC)
+      ” (U+201D)    ’ (U+2019)
+      Ė (U+0116)    ė (U+0117)'
+    - The Romanization column shows only lowercase forms but, when romanizing, uppercase and
+      lowercase Roman letters as appropriate should be used.
+}
+
+tests {
+  test "Өңірек", "Öngirek"
+  test "Өтебас Артезиан Құдығы", "Ötebas Artezīan Qudyghy"
+  test "Өскенбай", "Öskenbay"
+  test "Өсек Көлі", "Ösek Köli"
+  test "Өрмексу", "Örmeksū"
+  test "Өмірзақ", "Ömirzaq"
+  test "Өлеңті", "Ölengti"
+  test "Өл-Фараби Даңғылы", "Öl-Farabī Dangghyly"
+  test "Өкпекті Тауы", "Ökpekti Taūy"
+  test "Өкенсоркен Қыстауы", "Ökensorken Qystaūy"
+  test "Өзен Ойысы", "Özen Oyysy"
+  test "Өзен", "Özen"
+  test "Өгізтөбе Тауы", "Ögiztöbe Taūy"
+  test "Өгізтау Қыстауы", "Ögiztaū Qystaūy"
+  test "Өгізмүйіз Тауы", "Ögizmüyiz Taūy"
+  test "Өгізбұлақ", "Ögizbulaq"
+  test "Өгіз Үреулі", "Ögiz Üreūli"
+  test "Өгем Жотасы", "Ögem Zhotasy"
+  test "Өгем", "Ögem"
+  test "Әшім", "Äshim"
+  test "Әулиетөбе Тауы", "Äūlīetöbe Taūy"
+  test "Әулиекөл", "Äūlīeköl"
+  test "Әндіжан Құдығы", "Ändizhan Qudyghy"
+  test "Ұясай", "Uyasay"
+  test "Ұялы Метеорологиялық Станциясы", "Uyaly Meteorologīyalyq Stantsīyasy"
+  test "Ұшқын Қыстауы", "Ushqyn Qystaūy"
+  test "Үңгіртас", "Ünggirtas"
+  test "Үшқұлын", "Üshqulyn"
+  test "Құтырғы Асуы", "Qutyrghy Asūy"
+  test "Ярмы Стансасы", "Yarmy Stansasy"
+  test "Юпитер Қыстауы", "Yupīter Qystaūy"
+  test "Энгельс Көшесi", "Ėngel’s Köshesi"
+  test "Ырғызбай Жайлауы", "Yrghyzbay Zhaylaūy"
+  test "Щебнюха Тауы", "Shchebnyukha Taūy"
+  test "Шөміштікөл Соры", "Shömishtiköl Sory"
+  test "Чалов Барак Қыстауы", "Chalov Barak Qystaūy"
+  test "Чайкино", "Chaykīno"
+  test "Цуриковка", "Tsūrīkovka"
+  test "Хамитқора Қыстауы", "Khamītqora Qystaūy"
+  test "Фыкалка", "Fykalka"
+  test "Уақбай Қыстауы", "Ūaqbay Qystaūy"
+  test "Төңірекшың Тоғайы", "Töngirekshyng Toghayy"
+  test "Сабағали Қыстауы", "Sabaghalī Qystaūy"
+  test "Рысқұлов Даңғылы", "Rysqulov Dangghyly"
+  test "Пірназар Құдығы", "Pirnazar Qudyghy"
+  test "Оңтүстік Қазақстан Облысы", "Ongtüstik Qazaqstan Oblysy"
+  test "Нөмір Үшінші Суторабының Бөгені", "Nömir Üshinshi Sūtorabynyng Bögeni"
+  test "Мәмбетқазған Құдығы", "Mämbetqazghan Qudyghy"
+  test "Мемлекеттік Аудандық Электр Стансасы - Бір", "Memlekettik Aūdandyq Ėlektr Stansasy - Bir"
+  test "Линейский Белок Тауы", "Līneyskīy Belok Taūy"
+  test "Көшердік Бөгені", "Kösherdik Bögeni"
+  test "Көлфонтан Артезиан Құдығы", "Kölfontan Artezīan Qudyghy"
+  test "Изендіарал Мүйісі", "Īzendiaral Müyisi"
+  test "Злиха Метеорологиялық Станциасы", "Zlīkha Meteorologīyalyq Stantsīasy"
+  test "Жұлжұрған Көлі", "Zhulzhurghan Köli"
+  test "Ескі Үшал Қыстауы", "Eski Üshal Qystaūy"
+  test "Дөңгелексор Қыстауы", "Dönggeleksor Qystaūy"
+  test "Горько-Солёное Көлі", "Gor’ko-Solyonoe Köli"
+  test "Вагулино", "Vagūlīno"
+  test "Бөстай Учаскесі", "Böstay Ūchaskesi"
+  test "Аққолқы Тоғайы", "Aqqolqy Toghayy"
+  test "Іңқардария", "Ingqardarīya"
+}
+
+stage {
+
+  # CHARACTERS
+  parallel {
+    sub "\u0410", "A" # А
+    sub "\u04D8", "Ä" # Ә
+    sub "\u0411", "B" # Б
+    sub "\u0412", "V" # В
+    sub "\u0413", "G" # Г
+    sub "\u0492", "Gh" # Ғ
+    sub "\u0414", "D" # Д
+    sub "\u0415", "E" # Е
+    sub "\u0401", "Yo" # Ё
+    sub "\u0416", "Zh" # Ж
+    sub "\u0417", "Z" # З
+    sub "\u0418", "Ī" # И
+    sub "\u0419", "Y" # Й
+    sub "\u041A", "K" # К
+    sub "\u049A", "Q" # Қ
+    sub "\u041B", "L" # Л
+    sub "\u041C", "M" # М
+    sub "\u041D", "N" # Н
+    sub "\u04A2", "Ng" # Ң
+    sub "\u041E", "O" # О
+    sub "\u04E8", "Ö" # Ө
+    sub "\u041F", "P" # П
+    sub "\u0420", "R" # Р
+    sub "\u0421", "S" # С
+    sub "\u0422", "T" # Т
+    sub "\u0423", "Ū" # У
+    sub "\u04B0", "U" # Ұ
+    sub "\u04AE", "Ü" # Ү
+    sub "\u0424", "F" # Ф
+    sub "\u0425", "Kh" # Х
+    sub "\u04BA", "H" # Һ
+    sub "\u0426", "Ts" # Ц
+    sub "\u0427", "Ch" # Ч
+    sub "\u0428", "Sh" # Ш
+    sub "\u0429", "Shch" # Щ
+    sub "\u042A", "”" # Ъ
+    sub "\u042B", "Y" # Ы
+    sub "\u0406", "I" # І
+    sub "\u042C", "’" # Ь
+    sub "\u042D", "Ė" # Э
+    sub "\u042E", "Yu" # Ю
+    sub "\u042F", "Ya" # Я
+    
+    sub "\u0430", "a" # а
+    sub "\u04D9", "ä" # ә
+    sub "\u0431", "b" # б
+    sub "\u0432", "v" # в
+    sub "\u0433", "g" # г
+    sub "\u0493", "gh" # ғ
+    sub "\u0434", "d" # д
+    sub "\u0435", "e" # e
+    sub "\u0451", "yo" # ё
+    sub "\u0436", "zh" # ж
+    sub "\u0437", "z" # з
+    sub "\u0438", "ī" # и
+    sub "\u0439", "y" # й
+    sub "\u043A", "k" # к
+    sub "\u049B", "q" # қ
+    sub "\u043B", "l" # л
+    sub "\u043C", "m" # м
+    sub "\u043D", "n" # н
+    sub "\u04A3", "ng" # ң
+    sub "\u043E", "o" # о
+    sub "\u04E9", "ö" # ө
+    sub "\u043F", "p" # п
+    sub "\u0440", "r" # р
+    sub "\u0441", "s" # с
+    sub "\u0442", "t" # т
+    sub "\u0443", "ū" # у
+    sub "\u04B1", "u" # ұ
+    sub "\u04AF", "ü" # ү
+    sub "\u0444", "f" # ф
+    sub "\u0445", "kh" # х
+    sub "\u04BB", "h" # һ
+    sub "\u0446", "ts" # ц
+    sub "\u0447", "ch" # ч
+    sub "\u0448", "sh" # ш
+    sub "\u0449", "shch" # щ
+    sub "\u044A", "”" # ъ
+    sub "\u044B", "y" # ы
+    sub "\u0456", "i" # і
+    sub "\u044C", "’" # ь
+    sub "\u044D", "ė" # э
+    sub "\u044E", "yu" # ю
+    sub "\u044F", "ya" # я
+  }
+
+}
+