interscript-maps 2.0.5

data/maps/ses-ara-Arab-Latn-1930.imp

@@ -0,0 +1,225 @@
+metadata {
+  authority_id: ungegn
+  id: 1930
+  language: iso-639-2:ara
+  source_script: Arab
+  destination_script: Latn
+  name: ROMANIZATION OF ARABIC -- UNGEGN 2017 System
+  url: http://www.eki.ee/wgrs/rom1_ar.pdf
+  creation_date: 1930
+  confirmation_date: 2018-06
+  description: |
+    The current United Nations recommended romanization
+    system was approved in 2017 (resolution XI/3), based on
+    the system adopted by Arabic experts at the conference
+    held in Beirut in 2007, the Unified Arabic
+    Transliteration System, taking into account the
+    practical amendments and corrections carried out and
+    agreed upon by the representatives of the Arabic-
+    speaking countries at the Fourth Arab Conference on
+    Geographical Names, held in Beirut in 2008, and some
+    clarifications and amendments agreed in Riyadh in 20171.
+    Previously, the United Nations had approved a
+    romanization system in 1972 (resolution II/8), based on the
+    system adopted by Arabic experts at the conference
+    held at Beirut in 1971 with the practical amendments carried out
+    and agreed upon by the representatives of the Arabic-speaking
+    countries at their conference. The table was published in volume
+    II of the conference report.
+    In UN resolution XI/3 it is specifically stated that the
+    system was recommended for the “romanization of the
+    geographical names within those Arabic-speaking countries
+    where this system is officially adopted”. There is
+    evidence of its partial implementation in Jordan, Oman and
+    Saudi Arabia. The UNGEGN Working Group on Romanization
+    Systems intends to continue monitoring the UN system’s
+    implementation across Arabic-speaking countries.
+    In some countries there exist local romanization schemes
+    or practices. The geographical names of Algeria, Djibouti,
+    Mauritania, Morocco and Tunisia are generally rendered in
+    the traditional manner which conforms to the principles of
+    the French orthography.
+    The previous UN-approved system is still found in
+    considerable international usage.
+    Arabic is written from right to left. The Arabic script
+    usually omits vowel points and diacritical marks from
+    writing which makes it difficult to obtain uniform results
+    in the romanization of Arabic. It is essential to identify
+    correctly the words which appear in any particular name
+    and to know the standard Arabic-script spelling including
+    the relevant vowels. One must also take into account
+    dialectal and idiosyncratic deviations. The romanization
+    is generally reversible though there may be some ambiguous
+    letter sequences (dh, kh, sh, th) which may also point to
+    combinations of Arabic characters in addition to the
+    respective single characters.
+  notes:
+    - |
+      The Survey of Egypt System (SES) of romanization has the following correspondences with
+      the UN system:
+      á = a #  ـَى fatha followed by ى which is ا not ي
+      ā = â (a) # ـَا fatha followed by alef // آ
+      -ah (ة- = (a # ة ta' marboota at the end of a sentence
+      aw = ô (au) # ـَوْ
+      ay = ei (ai) # ـَيْ
+      ḏ = ḍ # ض
+      dh = dh (z) # ذ
+      d͟h = ẓ (d) # ظ
+      ẖ = ḥ # ح
+      ī = î
+      j = g (j)
+      q = q (k)
+      s = s (c)
+      s̱ = ṣ
+      ṯ = ṭ
+      th = th (t)
+      ū = û
+      ‘ = ‛
+    - |
+      The variants in parentheses are used depending on pronunciation and tradition. Not all the
+      variations have been given above. The article is always written el- (El-Kafr el-Qadîm, Sharm
+      el-Sheikh).
+}
+
+tests {
+  # Examples taken from:
+  # https://unstats.un.org/unsd/geoinfo/geonames/
+  test "شَرم الشَيْخ", "Sharm el-Sheikh"
+  test "الكَفر القَدِيم", "El-Kafr el-Qadîm"
+}
+
+dependency "un-ara-Arab-Latn-2017", as: arablatn
+
+stage {
+
+
+  # CHARACTERS
+  parallel {
+
+
+    # special pointed letters
+    sub "\u0639\u064e", "‛a" # عَ
+    sub "\u0639\u0650", "‛i" # عِ
+    sub "\u0639\u064f", "‛û" # عُ
+    # handle MacOS regex difference
+    sub "\u0639\u064f\u0648", "‛û" # عُو damma followed by و
+    sub "\u0650\u064a", "î" # ـِي kasra followed by ي
+    sub "\u0650\u064a\u0651\u064e", "îy" # ـِيَّ
+    sub "\u064f\u0648", "û" # ـُو damma followed by و
+    sub "\u064e\u0627", any(["â", "a"]) # ـَا fatha followed by ا
+    sub "\u064e\u0649", "a" # ـَى fatha followed by ى which is ا not ي
+    sub "\u064e\u0648\u0652", any(["ô", "au"]) # ـَوْ
+    sub "\u064e\u064a\u0652", any(["ei", "ai"]) # ـَيْ
+    sub "\u0622", any(["â", "a"]) # آ
+
+    # ta' marboota  in iso-233-1984 is all the same `a`
+    sub "\u0629" + line_end, "a"
+    sub "\u0629", "a", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "a", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "a", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "a", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "a", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "a", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "a", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "a", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "a", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "a", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "a", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+    sub "\u0629", "a", before: boundary + "\u0627\u0644" + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff") + any("\u0600".."\u06ff")
+
+
+    # Sun letters
+    sub boundary + "\u0627\u0644\u062a", "el-t" # الت
+    sub boundary + "\u0627\u0644\u062b", any(["el-th", "el-t"]) # الث
+    sub boundary + "\u0627\u0644\u062f", "el-d" # الد
+    sub boundary + "\u0627\u0644\u0630", any(["el-dh", "el-z"]) # الذ
+    sub boundary + "\u0627\u0644\u0631", "el-r" # الر
+    sub boundary + "\u0627\u0644\u0632", "el-z" # الز
+    sub boundary + "\u0627\u0644\u0633", any(["el-s", "el-c"]) # الس
+    sub boundary + "\u0627\u0644\u0634", "el-sh" # الش
+    sub boundary + "\u0627\u0644\u0635", "el-ṣ" # الص
+    sub boundary + "\u0627\u0644\u0636", "el-ḍ" # الض
+    sub boundary + "\u0627\u0644\u0637", "el-ṭ" # الط
+    sub boundary + "\u0627\u0644\u0638", any(["el-ẓ", "el-d"]) # الظ
+    sub boundary + "\u0627\u0644\u0644", "el-l" # الل
+    sub boundary + "\u0627\u0644\u0646", "el-n" # الن
+
+
+    # shadda
+    sub "\u062b\u0651", any(["thth", "tt"]) # ث
+    sub "\u062c\u0651", any(["gg", "jj"]) # ج
+    sub "\u062d\u0651", "ḥḥ" # ح
+    sub "\u062e\u0651", "khkh" # خ
+
+    sub "\u0633\u0651", any(["ss", "cc"]) # س
+    sub "\u0635\u0651", "ṣṣ" # ص
+    sub "\u0636\u0651", "ḍḍ" # ض
+    sub "\u0637\u0651", "ṭṭ" # ط
+    sub "\u0638\u0651", any(["ẓẓ", "dd"]) # ظ
+    sub "\u0642\u0651", any(["qq", "kk"]) # ق
+
+    sub boundary + "\u0627\u0644", "el-" # ال
+
+    # normal letters
+    sub "\u062c", any(["g", "j"]) # ج
+    sub "\ufe9f", any(["g", "j"]) # ﺟ
+    sub "\ufea0", any(["g", "j"]) # ﺠ
+    sub "\ufe9e", any(["g", "j"]) # ﺞ
+
+    sub "\u062d", "ḥ" # ح
+    sub "\ufea3", "ḥ" # ﺣ
+    sub "\ufea4", "ḥ" # ﺤ
+    sub "\ufea2", "ḥ" # ﺢ
+
+    sub "\u062e", "kh" # خ
+    sub "\ufea7", "kh" # ﺧ
+    sub "\ufea8", "kh" # ﺨ
+    sub "\ufea6", "kh" # ﺦ
+
+    sub "\u0630", any(["dh", "z"]) # ذ
+    sub "\ufeac", any(["dh", "z"]) # ﺬ
+
+
+    sub "\u0633", any(["s", "c"]) # س
+    sub "\ufeb3", any(["s", "c"]) # ﺳ
+    sub "\ufeb4", any(["s", "c"]) # ﺴ
+    sub "\ufeb2", any(["s", "c"]) # ﺲ
+
+    sub "\u0635", "ṣ" # ص
+    sub "\ufebb", "ṣ" # ﺻ
+    sub "\ufebc", "ṣ" # ﺼ
+    sub "\ufeba", "ṣ" # ﺺ
+
+    sub "\u0636", "ḍ" # ض
+    sub "\ufebf", "ḍ" # ﺿ
+    sub "\ufec0", "ḍ" # ﻀ
+    sub "\ufebe", "ḍ" # ﺾ
+
+    sub "\u0637", "ṭ" # ط
+    sub "\ufec3", "ṭ" # ﻃ
+    sub "\ufec4", "ṭ" # ﻄ
+    sub "\ufec2", "ṭ" # ﻂ
+
+    sub "\u0639", "‛" # ع
+    sub "\ufecb", "‛" # ﻋ
+    sub "\ufecc", "‛" # ﻌ
+    sub "\ufeca", "‛" # ﻊ
+
+    sub "\u0638", any(["ẓ", "d"]) # ظ
+    sub "\ufec7", any(["ẓ", "d"]) # ظ
+    sub "\ufec8", any(["ẓ", "d"]) # ظ
+    sub "\ufec6", any(["ẓ", "d"]) # ظ
+
+    sub "\u0642", any(["q", "k"]) # ق
+    sub "\ufed7", any(["q", "k"]) # ﻗ
+    sub "\ufed8", any(["q", "k"]) # ﻘ
+    sub "\ufed6", any(["q", "k"]) # ﻖ
+  }
+
+  run map.arablatn.stage.main
+
+  # POSTRULES
+  sub " El-", " el-" # الص
+
+
+}

data/maps/stategeocadastre-ukr-Cyrl-Latn-1993.imp

@@ -0,0 +1,171 @@
+metadata {
+  authority_id: stategeocadastre
+  id: 1993
+  language: iso-639-2:ukr
+  source_script: Cyrl
+  destination_script: Latn
+  name: PROVISIONAL RULES OF REPRODUCING LETTERS OF THE UKRAINIAN ALPHABET WITH LATIN (ENGLISH) CHARACTERS
+  url: https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/17th-gegn-docs/17th_gegn_WP73.pdf
+  creation_date: 1993
+  description: |
+    These Rules are intended for Romanized transliteration of Ukrainian
+    geographic names in international cartographic editions.
+
+    Geographic names of Russia, Byelorussia, Bulgaria and other states
+    using the Cyrillic alphabet are transliterated according to rules
+    accepted in those states.
+
+    These Rules come into effect from the moment of their approval by
+    the Main Administration of Geodesy, Cartography and Cadastre and
+    will be effective until the introduction of a State standard of
+    Ukraine regulating the Romanized transliteration of the Ukrainian
+    alphabet.
+
+  notes:
+    - No apostrophe (’) is used in transliteration, the combination "ьо" is transliterated as "io"
+    - Use of capitals in Latin version of Ukrainian geographic names correspond to the Ukrainian spelling
+    - Generics geographical terms standing before or after a name in full or abbreviated form are transliterated
+    - Romanized versions of complex and compound Ukrainian toponyms (one word, hyphenated or separate words) will follow the Ukrainian spelling
+    - In indexes of Romanized geographical names entries must be arranged in the order of the Latin (English) alphabet
+    - Geographic names of Russia, Byelorussia, Bulgaria and other states using the Cyrillic alphabet are transliterated according to rules accepted in those states.
+    - "Ed: There seems to be a mistake in the source document. 'ц' should be replaced with ts instead 'tz'."
+}
+
+tests {
+  test "Кам’янка", "Kamianka" # note[1]
+  test "Сьомаки", "Siomaky" # note[1]
+  test "Усть-Чорна", "Ust’-Chorna" # note[2]
+  test "Чорне море", "Chorne more" # note[2]
+  test "оз. Сиваш", "oz. Syvash" # note[3]
+  test "Кримський канал", "Kryms’kyi kanal" # note[3] # ! Example had typo in original document "Krums’kyi kanal"
+  test "Гола Пристань", "Hola Prystan’"
+  test "Корсунь Шевченківський", "Korsun’ Shevchenkivs’kyi"
+  test "Верхньодніпровськ", "Verkhniodniprovs’k"
+  test "Варва", "Varva"
+  test "Броди", "Brody"
+  test "Верховина", "Verkhovyna"
+  test "Глухів", "Hlukhiv"
+  test "Великий", "Velykyi"
+  test "Ґрунь(гора)", "Grun’(hora)"
+  test "Димер", "Dymer"
+  test "Срібне", "Sribne"
+  test "Євпаторія", "Yevpatoriia"
+  test "Єнакієве", "Yenakiieve"
+  test "Жолква", "Zholkva"
+  test "Затока", "Zatoka"
+  test "Житомир", "Zhytomyr"
+  test "Інгул", "Inhul"
+  test "Зміїв", "Zmiïv"
+  test "Йосипівка", "Yosypivka"
+  test "Стрий", "Stryi"
+  test "Калуш", "Kalush"
+  test "Лубни", "Lubny"
+  test "Миколаїв", "Mykolaïv"
+  test "Ніжин", "Nizhyn"
+  test "Острог", "Ostroh"
+  test "Печеніги", "Pechenihy"
+  test "Рівне", "Rivne"
+  test "Сарата", "Sarata"
+  test "Тячів", "Tiachiv"
+  test "Узин", "Uzyn"
+  test "Форос", "Foros"
+  test "Харків", "Kharkiv"
+  test "Цюрупінськ", "Tsiurupins’k"
+  test "Черемош", "Cheremosh"
+  test "Шацьк", "Shats’k"
+  test "Щорс", "Shchors"
+  test "Хмельницький", "Khmel’nyts’kyi" # ! Example had typo in original document "Khmel’nyts’ky"
+  test "Юрівка", "Yurivka"
+  test "Любеч", "Liubech"
+  test "Ялта", "Yalta"
+  test "Ясіня", "Yasinia"
+}
+
+stage {
+
+  # RULES
+    sub boundary + "\u0404", "Ye", not_before: "\u2019" # Є in initial position -> Ye
+    sub boundary + "\u0454", "ye", not_before: "\u2019" # є in initial position -> ye
+    sub boundary + "\u0419", "Y", not_before: "\u2019" # Й in initial position -> Y
+    sub boundary + "\u0419", "y", not_before: "\u2019" # й in initial position -> y
+    sub boundary + "\u042e", "Yu", not_before: "\u2019" # Ю in initial position -> Yu
+    sub boundary + "\u044e", "yu", not_before: "\u2019" # ю in initial position -> yu
+    sub boundary + "\u042f", "Ya", not_before: "\u2019" # Я in initial position -> Ya
+    sub boundary + "\u044f", "ya", not_before: "\u2019" # я in initial position -> ya
+  # note[1]
+    sub boundary + "\u2019" + boundary, "" # remove ’
+    sub "\u042c\u041e", "IO"
+    sub "\u044c\u043e", "io"
+
+
+  # CHARACTERS
+  parallel {
+    sub "А", "A" # А
+    sub "Б", "B" # Б
+    sub "В", "V" # В
+    sub "Г", "H" # Г
+    sub "Ґ", "G" # Ґ
+    sub "Д", "D" # Д
+    sub "Е", "E" # Е
+    sub "Є", "Ie" # Є
+    sub "Ж", "Zh" # Ж
+    sub "З", "Z" # З
+    sub "И", "Y" # И
+    sub "І", "I" # І
+    sub "Ї", "Ï" # Ї
+    sub "Й", "I" # Й
+    sub "К", "K" # К
+    sub "Л", "L" # Л
+    sub "М", "M" # М
+    sub "Н", "N" # Н
+    sub "О", "O" # О
+    sub "П", "P" # П
+    sub "Р", "R" # Р
+    sub "С", "S" # С
+    sub "Т", "T" # Т
+    sub "У", "U" # У
+    sub "Ф", "F" # Ф
+    sub "Х", "Kh" # Х
+    sub "Ц", "Ts" # Ц note[7]
+    sub "Ч", "Ch" # Ч
+    sub "Ш", "Sh" # Ш
+    sub "Щ", "Shch" # Щ
+    sub "Ь", "’" # Ь
+    sub "Ю", "Iu" # Ю
+    sub "Я", "Ia" # Я
+    sub "а", "a" # а
+    sub "б", "b" # б
+    sub "в", "v" # в
+    sub "г", "h" # г
+    sub "ґ", "g" # ґ
+    sub "д", "d" # д
+    sub "е", "e" # е
+    sub "є", "ie" # є
+    sub "ж", "zh" # ж
+    sub "з", "z" # з
+    sub "и", "y" # и
+    sub "і", "i" # і
+    sub "ї", "i" # ї
+    sub "й", "i" # й
+    sub "к", "k" # к
+    sub "л", "l" # л
+    sub "м", "m" # м
+    sub "н", "n" # н
+    sub "о", "o" # о
+    sub "п", "p" # п
+    sub "р", "r" # р
+    sub "с", "s" # с
+    sub "т", "t" # т
+    sub "у", "u" # у
+    sub "ф", "f" # ф
+    sub "х", "kh" # х
+    sub "ц", "ts" # ц note[7]
+    sub "ч", "ch" # ч
+    sub "ш", "sh" # ш
+    sub "щ", "shch" # щ
+    sub "ю", "iu" # ю
+    sub "я", "ia" # я
+    sub "ь", "’" # ь
+  }
+
+}

data/maps/ua-ukr-Cyrl-Latn-1996.imp

@@ -0,0 +1,149 @@
+metadata {
+  authority_id: ua
+  id: 1996
+  language: iso-639-2:ukr
+  source_script: Cyrl
+  destination_script: Latn
+  name: Government of Ukraine Ukrainian System (1996)
+  url: http://transliteration.eki.ee/pdf/Ukrainian.pdf
+  creation_date: 1996
+  description: Romanization table for Ukrainian. The current national system of romanization.
+
+  notes:
+    - gh is used in the romanization of зг zgh.
+    - In initial position є -> ye, ї -> yi, й -> y, ю -> yu, я -> ya.
+}
+
+tests {
+  test "Алушта", "Alushta"
+  test "Борщагівка", "Borschahivka"
+  test "Вишгород", "Vyshhorod"
+  test "Гадяч", "Hadiach"
+  test "Згорани", "Zghorany"
+  test "Ґалаґан", "Galagan"
+  test "Дон", "Don"
+  test "Рівне", "Rivne"
+  test "Єнакієве", "Yenakiieve"
+  test "Наєнко", "Naienko"
+  test "Житомир", "Zhytomyr"
+  test "Запоріжжя", "Zaporizhzhia"
+  test "Закарпаття", "Zakarpattia"
+  test "Медвин", "Medvyn"
+  test "Іршава", "Irshava"
+  test "Їжакевич", "Yizhakevych"
+  test "Кадіївка", "Kadiivka"
+  test "Йосипівка", "Yosypivka"
+  test "Київ", "Kyiv"
+  test "Лебедин", "Lebedyn"
+  test "Миколаїв", "Mykolaiv"
+  test "Ніжин", "Nizhyn"
+  test "Одеса", "Odesa"
+  test "Полтава", "Poltava"
+  test "Ромни", "Romny"
+  test "Суми", "Sumy"
+  test "Тетерів", "Teteriv"
+  test "Ужгород", "Uzhhorod"
+  test "Фастів", "Fastiv"
+  test "Харків", "Kharkiv"
+  test "Біла Церква", "Bila Tserkva"
+  test "Чернівці", "Chernivtsi"
+  test "Шостка", "Shostka"
+  test "Гоща", "Hoscha"
+  test "Русь", "Rus’"
+  test "Юрій", "Yurii"
+  test "Крюківка", "Kriukivka"
+  test "Яготин", "Yahotyn"
+  test "Ічня", "Ichnia"
+  test "Знам’янка", "Znam”ianka"
+}
+
+stage {
+
+  # RULES
+  sub "\u0413", "Gh", before: any("Зз") # Г after З or з
+  sub "\u0433", "gh", before: any("Зз") # г after З or з
+  sub boundary + "\u0404", "Ye", not_before: boundary + "\u2019" # Є in initial position -> Ye
+  sub boundary + "\u0454", "ye", not_before: boundary + "\u2019" # є in initial position -> ye
+  sub boundary + "\u0407", "Yi", not_before: boundary + "\u2019" # Ї in initial position -> Yi
+  sub boundary + "\u0457", "yi", not_before: boundary + "\u2019" # ї in initial position -> yi
+  sub boundary + "\u0419", "Y", not_before: boundary + "\u2019" # Й in initial position -> Y
+  sub boundary + "\u0419", "y", not_before: boundary + "\u2019" # й in initial position -> y
+  sub boundary + "\u042e", "Yu", not_before: boundary + "\u2019" # Ю in initial position -> Yu
+  sub boundary + "\u044e", "yu", not_before: boundary + "\u2019" # ю in initial position -> yu
+  sub boundary + "\u042f", "Ya", not_before: boundary + "\u2019" # Я in initial position -> Ya
+  sub boundary + "\u044f", "ya", not_before: boundary + "\u2019" # я in initial position -> ya
+  sub boundary + "\u2019" + boundary, "”" # ’ in the middle of a word -> ”
+
+
+  # CHARACTERS
+  parallel {
+    sub "А", "A" # А
+    sub "Б", "B" # Б
+    sub "В", "V" # В
+    sub "Г", "H" # Г
+    sub "Ґ", "G" # Ґ
+    sub "Д", "D" # Д
+    sub "Е", "E" # Е
+    sub "Є", "Ie" # Є
+    sub "Ж", "Zh" # Ж
+    sub "З", "Z" # З
+    sub "И", "Y" # И
+    sub "І", "I" # І
+    sub "Ї", "I" # Ї
+    sub "Й", "I" # Й
+    sub "К", "K" # К
+    sub "Л", "L" # Л
+    sub "М", "M" # М
+    sub "Н", "N" # Н
+    sub "О", "O" # О
+    sub "П", "P" # П
+    sub "Р", "R" # Р
+    sub "С", "S" # С
+    sub "Т", "T" # Т
+    sub "У", "U" # У
+    sub "Ф", "F" # Ф
+    sub "Х", "Kh" # Х
+    sub "Ц", "Ts" # Ц
+    sub "Ч", "Ch" # Ч
+    sub "Ш", "Sh" # Ш
+    sub "Щ", "Sch" # Щ
+    sub "Ю", "Iu" # Ю
+    sub "Я", "Ia" # Я
+    sub "Ь", "’" # Ь -> ’
+    sub "а", "a" # а
+    sub "б", "b" # б
+    sub "в", "v" # в
+    sub "г", "h" # г
+    sub "ґ", "g" # ґ
+    sub "д", "d" # д
+    sub "е", "e" # е
+    sub "є", "ie" # є
+    sub "ж", "zh" # ж
+    sub "з", "z" # з
+    sub "и", "y" # и
+    sub "і", "i" # і
+    sub "ї", "i" # ї
+    sub "й", "i" # й
+    sub "к", "k" # к
+    sub "л", "l" # л
+    sub "м", "m" # м
+    sub "н", "n" # н
+    sub "о", "o" # о
+    sub "п", "p" # п
+    sub "р", "r" # р
+    sub "с", "s" # с
+    sub "т", "t" # т
+    sub "у", "u" # у
+    sub "ф", "f" # ф
+    sub "х", "kh" # х
+    sub "ц", "ts" # ц
+    sub "ч", "ch" # ч
+    sub "ш", "sh" # ш
+    sub "щ", "sch" # щ
+    sub "ю", "iu" # ю
+    sub "я", "ia" # я
+    sub "ь", "’" # ь -> ’
+  }
+
+}
+