interscript-maps 2.0.5

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

@@ -0,0 +1,200 @@
+metadata {
+  authority_id: bgnpcgn
+  id: 1979
+  language: iso-639-2:bel
+  source_script: Cyrl
+  destination_script: Latn
+  name: United States Board on Geographic Names Foreign Names Committee Staff, 1994. Romanization Systems and Roman-Script Spelling Conventions, p. 23.
+  url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/811510/ROMANIZATION_OF_BELARUSIAN.pdf
+  creation_date: 1979
+  description: |
+    The BGN/PCGN system for Belarusian (formerly referred to as Byelorussian) was designed for use in
+    romanizing names written in the Belarusian Cyrillic alphabet. The Belarusian alphabet contains three
+    characters not present in the Russian alphabet: і, ў, and ’.
+
+  notes:
+   - The character sequences зг, кг, сг, тс and цг and may be romanized z·h, k·h, s·h, t·s and ts·h in order to differentiate those romanizations from the digraphs zh, kh, sh, ts, and the letter sequence tsh, which are used to render the characters ж, x, ш, ц, and the character sequence тш
+   - All apostrophes appearing in romanization are Unicode encoding 2019.
+}
+
+tests {
+  test "Антон", "Anton"
+  test "Вілейка", "Vilyeyka"
+  test "Брэст", "Brest"
+  test "Дубна", "Dubna"
+  test "Віцебск", "Vitsyebsk"
+  test "Асіповічы", "Asipovichy"
+  test "Гродна", "Hrodna"
+  test "Брагін", "Brahin"
+  test "Добруш", "Dobrush"
+  test "Ліда", "Lida"
+  test "Гомель", "Homyel’"
+  test "Беліца", "Byelitsa"
+  test "Ёдкавічы", "Yodkavichy"
+  test "Нёман", "Nyoman"
+  test "Жлобін", "Zhlobin"
+  test "Ружаны", "Ruzhany"
+  test "Зоя", "Zoya"
+  test "князь", "knyaz’"
+  test "Ігнат", "Ihnat"
+  test "Мінск", "Minsk"
+  test "Йосель", "Yosyel’"
+  test "Койданава", "Koydanava"
+  test "Крапіўна", "Krapiwna"
+  test "Менск", "Myensk"
+  test "Лаўна", "Lawna"
+  test "Лёсік", "Lyosik"
+  test "Купала", "Kupala"
+  test "Вілейка", "Vilyeyka"
+  test "Міхал", "Mikhal"
+  test "Вільня", "Vil’nya"
+  test "Лепель", "Lyepyel’"
+  test "Магілёў", "Mahilyow"
+  test "Няміга", "Nyamiha"
+  test "Наваградак", "Navahradak"
+  test "Баранавічы", "Baranavichy"
+  test "Орша", "Orsha"
+  test "Востраў", "Vostraw"
+  test "Пінск", "Pinsk"
+  test "Дняпро", "Dnyapro"
+  test "Рагачоў", "Rahachow"
+  test "Сураж", "Surazh"
+  test "Смаляны", "Smalyany"
+  test "Арэса", "Aresa"
+  test "Рось", "Ros’"
+  test "Талочын", "Talochyn"
+  test "Масты", "Masty"
+  test "Уладзімір", "Uladzimir"
+  test "Бабруйск", "Babruysk"
+  test "Быхаў", "Bykhaw"
+  test "Воўпа", "Vowpa"
+  test "Іўе", "Iwye"
+  test "Фолюш", "Folyush"
+  test "фортка", "fortka"
+  test "Хатынь", "Khatyn’"
+  test "Быхаў", "Bykhaw"
+  test "Ганцавічы", "Hantsavichy"
+  test "Стоўбцы", "Stowbtsy"
+  test "цьмяны", "ts’myany"
+  test "мясцовы", "myastsovy"
+  test "Астравец", "Astravyets"
+  test "Прыпяць", "Prypyats’"
+  test "Чэрыкаў", "Cherykaw"
+  test "Шчара", "Shchara"
+  test "Нарач", "Narach"
+  test "Шклоў", "Shklow"
+  test "Ашмяны", "Ashmyany"
+  test "Ыттык-Кёль", "Yttyk-Kyol’"
+  test "Кобрын", "Kobryn"
+  test "Солы", "Soly"
+  test "Копысь", "Kopys’"
+  test "рунь", "run’"
+  test "Эйсманты", "Eysmanty"
+  test "Крэва", "Kreva"
+  test "Юры", "Yury"
+  test "уюн", "uyun"
+  test "Язэп", "Yazep"
+  test "Івянец", "Ivyanyets"
+  test "з’езд", "z”yezd"
+  test "Вялiкiя Вераб’евічы", "Vyalikiya Vyerab”yevichy"
+  test "Дзям’янаўцы", "Dzyam”yanawtsy"
+  test "Задвор’е", "Zadvor”ye"
+  test "Гезгалы", "Hyez·haly"
+  test "Вадасховішча Гезгальскае", "Vadaskhovishcha Hyez·hal’skaye"
+}
+
+stage {
+
+  # RULES
+  parallel {
+    sub "\u0417\u0413", "Z·H" # ЗГ# Z·H
+    sub "\u0437\u0433", "z·h" # зг# z·h
+    sub "\u041A\u0413", "K·H" # КГ# K·H
+    sub "\u043A\u0433", "k·h" # кг# k·h
+    sub "\u0421\u0413", "S·H" # СГ# S·H
+    sub "\u0441\u0433", "s·h" # сг# s·h
+    sub "\u0422\u0421", "T·S" # ТС# T·S
+    sub "\u0442\u0441", "t·s" # тс# t·s
+    sub "\u0426\u0413", "TS·H" # ЦГ# TS·H
+    sub "\u0446\u0433", "ts·h" # цг# ts·h
+  }
+
+
+  # CHARACTERS
+  parallel {
+    sub "\u00B4", "”" # apostrophe according to spec
+    sub "\u02BC", "”" # apostrophe according to spec
+    sub "\u2019", "”" # apostrophe in actual examples
+
+    sub "\u0410", "A" # A
+    sub "\u0411", "B" # Б
+    sub "\u0412", "V" # B
+    sub "\u0413", "H" # Г
+    sub "\u0414", "D" # Д
+    sub "\u0415", "Ye" # Е
+    sub "\u0401", "Yo" # Ё
+    sub "\u0416", "Zh" # Ж
+    sub "\u0417", "Z" # З
+    sub "\u0406", "I" # І
+    sub "\u0419", "Y" # Й
+    sub "\u041A", "K" # К
+    sub "\u041B", "L" # Л
+    sub "\u041C", "M" # М
+    sub "\u041D", "N" # Н
+    sub "\u041E", "O" # О
+    sub "\u041F", "P" # П
+    sub "\u0420", "R" # Р
+    sub "\u0421", "S" # С
+    sub "\u0422", "T" # Т
+    sub "\u0423", "U" # У
+    sub "\\U040E", "W" # Ў
+    sub "\u0424", "F" # Ф
+    sub "\u0425", "Kh" # Х
+    sub "\u0426", "Ts" # Ц
+    sub "\u0427", "Ch" # Ч
+    sub "\u0428", "Sh" # Ш
+    sub "\u042B", "Y" # Ы
+    sub "\u042D", "E" # Э
+    sub "\u042E", "Yu" # Ю
+    sub "\u042F", "Ya" # Я
+    sub "\u0490", "G" # Ґ
+
+    sub "\u0430", "a" # а
+    sub "\u0431", "b" # б
+    sub "\u0432", "v" # в
+    sub "\u0433", "h" # г
+    sub "\u0434", "d" # д
+    sub "\u0435", "ye" # е
+    sub "\u0451", "yo" # ё
+    sub "\u0436", "zh" # ж
+    sub "\u0437", "z" # з
+    sub "\u0456", "i" # і
+    sub "\u0439", "y" # й
+    sub "\u043A", "k" # к
+    sub "\u043B", "l" # л
+    sub "\u043C", "m" # м
+    sub "\u043D", "n" # н
+    sub "\u043E", "o" # о
+    sub "\u043F", "p" # п
+    sub "\u0440", "r" # р
+    sub "\u0441", "s" # с
+    sub "\u0442", "t" # т
+    sub "\u0443", "u" # у
+    sub "\u045E", "w" # ў
+    sub "\u0444", "f" # ф
+    sub "\u0445", "kh" # х
+    sub "\u0446", "ts" # ц
+    sub "\u0447", "ch" # ч
+    sub "\u0448", "sh" # ш
+    sub "\u044B", "y" # ы
+    sub "\u044D", "e" # э
+    sub "\u044E", "yu" # ю
+    sub "\u044F", "ya" # я
+    sub "\u0491", "g" # ґ
+  }
+
+  # POSTRULES
+  sub "\u042C", "’" # Ь
+  sub "\u044C", "’" # ь
+  # Per documentation those rules are optional
+}

data/maps/bgnpcgn-bul-Cyrl-Latn-1952.imp

@@ -0,0 +1,137 @@
+metadata {
+  authority_id: bgnpcgn
+  id: 1952
+  language: iso-639-2:bul
+  source_script: Cyrl
+  destination_script: Latn
+  name: ROMANIZATION SYSTEM FOR BULGARIAN BGN/PCGN of 1952
+  url: https://libraries.ucsd.edu/bib/fed/USBGN_romanization.pdf
+  creation_date: 1945
+  confirmation_date: 1952
+  description: |
+    This system was adopted by the BGN in 1949 and by the PCGN in 1952. It
+    reflects the much simplified Bulgarian orthography as officially revised in
+    February 1945. The Bulgarian alphabet contains all of the characters present
+    in the Russian alphabet with the exception of ё, ы, and э. Notes 1, 2, and 3
+    are applicable to sources predating the orthographic reform of 1945.
+
+  notes:
+    - In modern Bulgarian orthography, the character ъ, does not occcur in word-final position. It should be omitted in romanization when found in word-final position on older sources
+    - The obsolete character ѫ, which was replaced by ъ in 1945, should be romanized ŭ
+    - The obsolete character ѣ, replaced in 1945 by е or я according to local pronunciation, should be romanized as e or ya, accordingly, if the pronunciation is known; otherwise, as ye
+    - The character sequence тс may be romanized t·s in order to differentiate that romanization from the regularly occurring digraph ts, which represents the character ц
+}
+
+tests {
+  test "София", "Sofiya"
+  test "София-Град", "Sofiya-Grad"
+  test "България", "Bŭlgariya"
+}
+
+stage {
+  # RULES
+  # note[1]
+  sub "\u042a", "", after: boundary
+  sub "\u044a", "", after: boundary
+  # note[4]
+  parallel {
+    sub "ТС", "T·S"
+    sub "Тс", "T·s"
+    sub "тс", "t·s"
+  }
+
+  # CHARACTERS
+  parallel {
+    sub "\u0410", "A"
+    sub "\u0411", "B"
+    sub "\u0412", "V"
+    sub "\u0413", "G"
+    sub "\u0414", "D"
+    sub "\u0415", "E"
+    sub "\u0416", "Zh"
+    sub "\u0416", "ZH", after: any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+    sub "\u0416", "ZH", before: any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+    sub "\u0417", "Z"
+    sub "\u0418", "I"
+    sub "\u0419", "Y"
+    sub "\u041a", "K"
+    sub "\u041b", "L"
+    sub "\u041c", "M"
+    sub "\u041d", "N"
+    sub "\u041e", "O"
+    sub "\u041f", "P"
+    sub "\u0420", "R"
+    sub "\u0421", "S"
+    sub "\u0422", "T"
+    sub "\u0423", "U"
+    sub "\u0424", "F"
+    sub "\u0425", "Kh"
+    sub "\u0425", "KH", after: any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+    sub "\u0425", "KH", before: any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+
+    sub "\u0426", "Ts"
+    sub "\u0426", "TS", after: any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+    sub "\u0426", "TS", before: any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+
+    sub "\u0427", "Ch"
+    sub "\u0427", "CH", after: any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+    sub "\u0427", "CH", before: any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+
+    sub "\u0428", "Sh"
+    sub "\u0428", "SH", after: any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+    sub "\u0428", "SH", before: any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+
+    sub "\u0429", "Sht"
+    sub "\u0429", "SHT", after: any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+    sub "\u0429", "SHT", before: any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+
+    sub "\u042a", "Ŭ"
+    sub "\u042c", "\\'"
+    sub "\u042e", "Yu"
+    sub "\u042e", "YU", after: any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+    sub "\u042e", "YU", before: any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+
+    sub "\u042f", "Ya"
+    sub "\u042f", "YA", after: any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+    sub "\u042f", "YA", before: any("АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЬЮЯ")
+
+    sub "\u0430", "a"
+    sub "\u0431", "b"
+    sub "\u0432", "v"
+    sub "\u0433", "g"
+    sub "\u0434", "d"
+    sub "\u0435", "e"
+    sub "\u0436", "zh"
+    sub "\u0437", "z"
+    sub "\u0438", "i"
+    sub "\u0439", "y"
+    sub "\u043a", "k"
+    sub "\u043b", "l"
+    sub "\u043c", "m"
+    sub "\u043d", "n"
+    sub "\u043e", "o"
+    sub "\u043f", "p"
+    sub "\u0440", "r"
+    sub "\u0441", "s"
+    sub "\u0442", "t"
+    sub "\u0443", "u"
+    sub "\u0444", "f"
+    sub "\u0445", "kh"
+    sub "\u0446", "ts"
+    sub "\u0447", "ch"
+    sub "\u0448", "sh"
+    sub "\u0449", "sht"
+    sub "\u044a", "ŭ"
+    sub "\u044c", "\\'"
+    sub "\u044e", "yu"
+    sub "\u044f", "ya"
+
+    # note 2
+    sub "\u046A", "Ŭ" # Ѫ
+    sub "\u046B", "ŭ" # ѫ
+
+    # note[3]
+    sub "\u0462", "Ye" # Ѣ
+    sub "\u0463", "ye" # ѣ
+  }
+}

data/maps/bgnpcgn-bul-Cyrl-Latn-2013.imp

@@ -0,0 +1,38 @@
+metadata {
+  authority_id: bgnpcgn
+  id: 2013
+  language: iso-639-2:bul
+  source_script: Cyrl
+  destination_script: Latn
+  name: BGN/PCGN 2013 Agreement
+  url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/811509/ROMANIZATION_OF_BULGARIAN.pdf
+  creation_date: 2013
+  confirmation_date: 2019-06
+  description: |
+    This system reflects the Bulgarian national system officially adopted
+    by state decree in March 2009. It was adopted by BGN and PCGN in 2013,
+    replacing the BGN/PCGN system of 1952.
+
+  notes:
+    - When in final position, “ия” is romanized as “ia” (e.g., София = Sofia; София-Град= Sofia-Grad).
+    - An exception to the romanization system is allowed for the name of the state. Thus, България is romanized as Bulgaria.
+    - The Romanization column shows only lowercase forms but, when romanizing, uppercase and lowercase Roman letters as appropriate should be used.
+}
+
+tests {
+  test "София", "Sofia"
+  test "София-Град", "Sofia-Grad"
+  test "България", "Bulgaria"
+}
+
+dependency "bgnpcgn-bul-Cyrl-Latn-1952", as: cyrllatn
+
+
+stage {
+  # RULES
+  sub "България", "Bulgaria"
+  sub "\u042f", "A", before: "\u0418", after: boundary # final position, “ИЯ” is romanized as “IA”
+  sub "\u044f", "a", before: "\u0438", after: boundary # final position, “ия” is romanized as “ia”
+
+  run map.cyrllatn.stage.main
+}

data/maps/bgnpcgn-che-Cyrl-Latn-2008.imp

@@ -0,0 +1,176 @@
+metadata {
+  authority_id: bgnpcgn
+  id: 2008
+  language: iso-639-2:che
+  source_script: Cyrl
+  destination_script: Latn
+  name: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/835782/TABLE_OF_CORRESPONDENCES_FOR_CHECHEN.pdf
+  creation_date: 2008
+  confirmation_date: 2019-07
+  description: |
+    Chechen is an official language within Chechnya, one of the republics of the Russian Federation.
+    It will normally be encountered in Cyrillic script, in which case it should be romanized by means of
+    the Cyrillic-Roman table of correspondences given below.
+
+  notes:
+    - The letter ə is used to represent short a; a is used for long a.
+    - Ye is used word- and syllable-initially. This Cyrillic letter may be encountered as the ligature ie in Chechen-Roman sources.
+    - This character occurs only in loan words.
+    - q in the combination ккх (qq) and q̇in the combination ккъ (q̇q̇)
+    - ŋ when preceding vowel is nasalized.
+    - This Cyrillic letter may be encountered as the ligature ꭣ [U+AB63] or the diphthong oa in Chechen Roman sources.
+    - Unless in the combinations гӀ, кӀ, пӀ, тӀ, хӀ, цӀ and чӀ.
+    - |
+      An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the
+      unmodified letters of the basic Roman script is:
+
+      All apostrophes appearing in romanization are U+2019
+
+          Ə (U+018F)       ə (U+0259)
+          Ä (U+00C4)       ä (U+00E4)
+          Ġ (U+0047+0307)  ġ (U+0067+0307)
+          Z̵ (U+005A+0335)  z̵ (U+007A+0335)
+          Q̇ (U+0051+0307)  q̇ (U+0071+0307)
+          Ŋ (U+014A)       ŋ (U+014B)
+          Ö (U+00D6)       ö (U+00F6)
+          Ü (U+00DC)       ü (U+00FC)
+          Ẋ (U+0058+0307)  ẋ (U+0078+0307)
+          Ċ (U+0043+0307)  ċ (U0063+0307)
+          Ç (U+00C7)       ç (U+00E7)
+          Ç̇ (U+00C7+0307)  ç̇ (U+00E7+0307)
+          Ş (U+015E)       ş (U+015F)
+
+    - The Roman-script columns show only lowercase forms but, when applying the table, uppercase and lowercase Roman letters as appropriate should be used
+}
+
+tests {
+  test "кӏант", "khant"
+  test "зуда", "zuda"
+  test "пхьагал", "pẋagal"
+  test "наж", "naz̵"
+  test "мангал", "mangal"
+  test "Ӏаж", "Jaz̵"
+  test "Нохчийн Википеди", "Noxçiyn Vikipedi"
+  test "сагӏадаккхар", "saġadaqqar"
+  test "йеза", "yeza"
+  test "еара", "yeara"
+  test "елха", "yelxa"
+}
+
+stage {
+
+  # RULES
+  # note[2]
+  sub boundary + "\u0415", "Ye", not_before: boundary + "\u2019" # Е in initial position -> Ye
+  sub boundary + "\u0435", "ye", not_before: boundary + "\u2019" # е in initial position -> ye
+  # note[4]
+  sub "\u043A\u043A\u0445", "qq"
+  sub "\u043A\u043A\u042A", "q̇q̇"
+  sub "\u041A\u041A\u0445", "QQ"
+  sub "\u041A\u041A\u042A", "Q̇Q̇"
+
+
+  # CHARACTERS
+  parallel {
+    sub "\u0410", any(["A", "Ə"]) # А note[1]
+    sub "\u0410\u044C", "Ä" # Аь -> Ä
+    sub "\u0411", "B" # Б
+    sub "\u0412", "V" # В
+    sub "\u0413", "G" # Г
+    sub "\u0413\u04C0", "Ġ" # ГӀ -> Ġ
+    sub "\u0414", "D" # Д
+    sub "\u0415", "E" # Е note[2]
+    sub "\u0401", "Yo" # Ё note[3]
+    sub "\u0416", "Z̵" # Ж -> Ƶ
+    sub "\u0417", "Z" # З
+    sub "\u0418", "I" # И
+    sub "\u042B", "Y" # Й
+    sub "\u041A", "K" # К note[4]
+    sub "\u041A\u0445", "Q" # Кх note[4]
+    sub "\u041A\u044A", "Q̇" # Къ -> Q̇ note[4]
+    sub "\u041A\u04C0", "Kh" # КӀ note[4]
+    sub "\u041B", "L" # Л
+    sub "\u041C", "M" # М
+    sub "\u041D", any(["N", "Ŋ"]) # Н note[5]
+    sub "\u041E", "O" # О note[6]
+    sub "\u041E\u044C", "Ö" # Оь -> Ö
+    sub "\u041F", "P" # П
+    sub "\u041F\u04C0", "Ph" # ПӀ
+    sub "\u0420", "R" # Р
+    sub "\u0421", "S" # С
+    sub "\u0422", "T" # Т
+    sub "\u0422\u04C0", "Th" # TӀ
+    sub "\u0423", "U" # У
+    sub "\u0423\u044C", "Ü" # Уь -> Ü
+    sub "\u0424", "F" # Ф
+    sub "\u0425", "X" # Х
+    sub "\u0425\u044C", "Ẋ" # Хь -> Ẋ
+    sub "\u0425\u04C0", "H" # ХӀ
+    sub "\u04B8", "C" # Ц
+    sub "\u04B8\u04C0", "Ċ" # ЦӀ -> Ċ
+    sub "\u0427", "Ç" # Ч -> Ç
+    sub "\u0427\u04C0", "Ç̇" # ЧӀ -> Ç̇
+    sub "\u0428", "Ş" # Ш -> Ş
+    sub "\u0429", "ŞÇ" # Щ -> ŞÇ note[3]
+    sub "\u042A", "’" # Ъ note[3]
+    sub "\u042B", "Y" # Ы
+    sub "\u042C", "" # Ь note[3]
+    sub "\u042D", "E" # Э
+    sub "\u042E", "Yu" # Ю
+    sub "\u042E\u044C", "Yü" # Юь -> Yü
+    sub "\u042F", "Ya" # Я
+    sub "\u042F\u044C", "Yä" # Яь -> Yä
+    sub "\u04C0", "J" # Ӏ note[7]
+
+    sub "\u0430", any(["a", "ə"]) # а note[1]
+    sub "\u0430\u044C", "ä" # аь -> ä
+    sub "\u0431", "b" # б
+    sub "\u0432", "v" # в
+    sub "\u0433", "g" # г
+    sub "\u0433\u04CF", "ġ" # гӏ -> ġ
+    sub "\u0434", "d" # д
+    sub "\u0435", "e" # е note[2]
+    sub "\u0451", "yo" # ё note[3]
+    sub "\u0436", "z̵" # ж -> ƶ
+    sub "\u0437", "z" # з
+    sub "\u0438", "i" # и
+    sub "\u0439", "y" # й
+    sub "\u043A", "k" # к note[4]
+    sub "\u043A\u0445", "q" # кх note[4]
+    sub "\u043A\u044A", "q̇" # къ -> q̇ note[4]
+    sub "\u043A\u04CF", "kh" # кӏ note[4]
+    sub "\u043B", "l" # л
+    sub "\u043C", "m" # м
+    sub "\u043D", any(["n", "ŋ"]) # н note[5]
+    sub "\u043E", "o" # о note[6]
+    sub "\u043E\u044C", "ö" # оь -> ö
+    sub "\u043F", "p" # п
+    sub "\u0440", "r" # р
+    sub "\u0441", "s" # с
+    sub "\u0442", "t" # т
+    sub "\u0442\u04CF", "th" # тӏ
+    sub "\u0443", "u" # у
+    sub "\u0443\u044C", "ü" # Уь -> ü
+    sub "\u0444", "f" # ф
+    sub "\u0445", "x" # х
+    sub "\u0445\u044C", "ẋ" # хь -> ẋ
+    sub "\u0445\u04CF", "h" # хӏ
+    sub "\u04B9", "c" # ц
+    sub "\u04B9\u04CF", "с̇" # цӏ -> ċ
+    sub "\u0447", "ç" # ч -> ç
+    sub "\u0447\u04CF", "cç̇" # чӏ -> ç̇
+    sub "\u0448", "ş" # ш -> ş
+    sub "\u0449", "şç" # щ -> şç note[3]
+    sub "\u044A", "’" # ъ note[3]
+    sub "\u044B", "y" # ы
+    sub "\u044C", "" # ь note[3]
+    sub "\u044D", "e" # э
+    sub "\u044E", "yu" # ю
+    sub "\u044E", "yü" # юь -> yü
+    sub "\u044F", "ya" # я
+    sub "\u044F", "yä" # яь -> yä
+    sub "\u04CF", "j" # ӏ note[7]
+  }
+  compose
+}
+