interscript-maps 2.4.2 → 2.5.0

data/maps/bgnpcgn-rus-Cyrl-Latn-1947.imp

@@ -1,195 +0,0 @@
-metadata {
-  authority_id: bgnpcgn
-  id: 1947
-  language: iso-639-2:rus
-  source_script: Cyrl
-  destination_script: Latn
-  name: Romanization of Russian (1947)
-  url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/807920/ROMANIZATION_OF_RUSSIAN.pdf
-  creation_date: 1947
-  confirmation_date: 2019-06
-  description: |
-    The BGN/PCGN system for Russian was adopted by the BGN in 1944 and by the
-    PCGN in 1947 for use in romanizing names written in the Russian Cyrillic
-    alphabet.
-
-  notes:
-    - The character e should be romanized ye initially, after the vowel
-      characters a, e, ё, и, о, у, ы, э, ю, and я, and after й, ъ, and ь. In
-      all other instances, it should be romanized e.
-
-    - The character ё is not considered a separate character of the
-      Russian alphabet and the dieresis is generally not shown. When the
-      dieresis is shown, the character should be romanized yë initially,
-      after the vowel characters a, e, ё, и, о, у, ы, э, ю, and я, and after
-      й, ъ, and ь. In all other instances, it should be romanized ё. When the
-      dieresis is not shown, the character may still be romanized in the
-      preceding manner or, alternatively, in accordance with note 1.
-
-    - |
-      Unusual Russian character sequences occurring primarily in
-      non-Russian-language names may be romanized as shown below in order to
-      provide differentiation from regularly- occurring digraphs and
-      character sequences.
-        й before а, у, ы, or э у·
-        ы before а, у, ы, or э у·
-        ы after any vowel character ·у
-        э after any consonant character except й ·е
-        TC t·s шч sh·ch
-
-    - Unicode values are shown with the uppercase Cyrillic character first,
-      followed by the lowercase character.
-
-    - |
-      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 Ë (U+00CB)
-        ë (U+00EB)
-    - The Romanization column shows only lowercase forms but, when
-      romanizing, uppercase and lowercase Roman letters as appropriate should
-      be used.
-}
-
-tests {
-  test "Выборы депутатов Государственной Думы Федерального Собрания Российской Федерации седьмого созыва\nДата голосования: 18.09.2016\n\nНаименование Избирательной комиссии:    ЦИК России\n\nСводная таблица результатов выборов по федеральному избирательному округу\n\n\nЧисло избирателей, внесенных в список избирателей на момент окончания голосования\nЧисло избирательных бюллетеней, полученных участковой избирательной комиссией\nЧисло избирательных бюллетеней, выданных избирателям, проголосовавшим досрочно\nЧисло избирательных бюллетеней, выданных в помещении для голосования в день голосования\nЧисло избирательных бюллетеней, выданных вне помещения для голосования в день голосования\nЧисло погашенных избирательных бюллетеней\nЧисло избирательных бюллетеней, содержащихся в переносных ящиках для голосования\nЧисло избирательных бюллетеней, содержащихся в стационарных ящиках для голосования\nЧисло недействительных избирательных бюллетеней\nЧисло действительных избирательных бюллетеней\nЧисло открепительных удостоверений, полученных участковой избирательной комиссией\nЧисло открепительных удостоверений, выданных на избирательном участке до дня голосования\nЧисло избирателей, проголосовавших по открепительным удостоверениям на избирательном участке\nЧисло погашенных неиспользованных открепительных удостоверений\nЧисло открепительных удостоверений, выданных избирателям территориальной избирательной комиссией\nЧисло утраченных открепительных удостоверений\nЧисло утраченных избирательных бюллетеней\nЧисло избирательных бюллетеней, не учтенных при получении\n1. ВСЕРОССИЙСКАЯ ПОЛИТИЧЕСКАЯ ПАРТИЯ \"РОДИНА\"\n2. Политическая партия КОММУНИСТИЧЕСКАЯ ПАРТИЯ КОММУНИСТЫ РОССИИ\n3. Политическая партия \"Российская партия пенсионеров за справедливость\"\n4. Всероссийская политическая партия \"ЕДИНАЯ РОССИЯ\"\n5. Политическая партия \"Российская экологическая партия \"Зеленые\"\n6. Политическая партия \"Гражданская Платформа\"\n7. Политическая партия ЛДПР - Либерально-демократическая партия России\n8. Политическая партия \"Партия народной свободы\" (ПАРНАС)\n9. Всероссийская политическая партия \"ПАРТИЯ РОСТА\"\n10. Общественная организация Всероссийская политическая партия \"Гражданская Сила\"\n11. Политическая партия \"Российская объединенная демократическая партия \"ЯБЛОКО\"\n12. Политическая партия \"КОММУНИСТИЧЕСКАЯ ПАРТИЯ РОССИЙСКОЙ ФЕДЕРАЦИИ\"\n13. Политическая партия \"ПАТРИОТЫ РОССИИ\"\n14. Политическая партия СПРАВЕДЛИВАЯ РОССИЯ\n\nДанные окружных избирательных комиссий о числе открепительных удостоверений\n\n\nЧисло открепительных удостоверений, полученных окружной избирательной комиссией\nЧисло открепительных удостоверений, выданных территориальным избирательным комиссиям\nЧисло неиспользованных открепительных удостоверений, погашенных окружной избирательной комиссией\nЧисло открепительных удостоверений, утраченных в окружной избирательной комиссии", "Vybory deputatov Gosudarstvennoy Dumy Federal’nogo Sobraniya Rossiyskoy Federatsii sed’mogo sozyva\nData golosovaniya: 18.09.2016\n\nNaimenovaniye Izbiratel’noy komissii:    TSIK Rossii\n\nSvodnaya tablitsa rezul’tatov vyborov po federal’nomu izbiratel’nomu okrugu\n\n\nChislo izbirateley, vnesennykh v spisok izbirateley na moment okonchaniya golosovaniya\nChislo izbiratel’nykh byulleteney, poluchennykh uchastkovoy izbiratel’noy komissiyey\nChislo izbiratel’nykh byulleteney, vydannykh izbiratelyam, progolosovavshim dosrochno\nChislo izbiratel’nykh byulleteney, vydannykh v pomeshchenii dlya golosovaniya v den’ golosovaniya\nChislo izbiratel’nykh byulleteney, vydannykh vne pomeshcheniya dlya golosovaniya v den’ golosovaniya\nChislo pogashennykh izbiratel’nykh byulleteney\nChislo izbiratel’nykh byulleteney, soderzhashchikhsya v perenosnykh yashchikakh dlya golosovaniya\nChislo izbiratel’nykh byulleteney, soderzhashchikhsya v statsionarnykh yashchikakh dlya golosovaniya\nChislo nedeystvitel’nykh izbiratel’nykh byulleteney\nChislo deystvitel’nykh izbiratel’nykh byulleteney\nChislo otkrepitel’nykh udostovereniy, poluchennykh uchastkovoy izbiratel’noy komissiyey\nChislo otkrepitel’nykh udostovereniy, vydannykh na izbiratel’nom uchastke do dnya golosovaniya\nChislo izbirateley, progolosovavshikh po otkrepitel’nym udostovereniyam na izbiratel’nom uchastke\nChislo pogashennykh neispol’zovannykh otkrepitel’nykh udostovereniy\nChislo otkrepitel’nykh udostovereniy, vydannykh izbiratelyam territorial’noy izbiratel’noy komissiyey\nChislo utrachennykh otkrepitel’nykh udostovereniy\nChislo utrachennykh izbiratel’nykh byulleteney\nChislo izbiratel’nykh byulleteney, ne uchtennykh pri poluchenii\n1. VSEROSSIYSKAYA POLITICHESKAYA PARTIYA \"RODINA\"\n2. Politicheskaya partiya KOMMUNISTICHESKAYA PARTIYA KOMMUNISTY ROSSII\n3. Politicheskaya partiya \"Rossiyskaya partiya pensionerov za spravedlivost’\"\n4. Vserossiyskaya politicheskaya partiya \"YEDINAYA ROSSIYA\"\n5. Politicheskaya partiya \"Rossiyskaya ekologicheskaya partiya \"Zelenyye\"\n6. Politicheskaya partiya \"Grazhdanskaya Platforma\"\n7. Politicheskaya partiya LDPR - Liberal’no-demokraticheskaya partiya Rossii\n8. Politicheskaya partiya \"Partiya narodnoy svobody\" (PARNAS)\n9. Vserossiyskaya politicheskaya partiya \"PARTIYA ROSTA\"\n10. Obshchestvennaya organizatsiya Vserossiyskaya politicheskaya partiya \"Grazhdanskaya Sila\"\n11. Politicheskaya partiya \"Rossiyskaya ob\"yedinennaya demokraticheskaya partiya \"YABLOKO\"\n12. Politicheskaya partiya \"KOMMUNISTICHESKAYA PARTIYA ROSSIYSKOY FEDERATSII\"\n13. Politicheskaya partiya \"PATRIOTY ROSSII\"\n14. Politicheskaya partiya SPRAVEDLIVAYA ROSSIYA\n\nDannyye okruzhnykh izbiratel’nykh komissiy o chisle otkrepitel’nykh udostovereniy\n\n\nChislo otkrepitel’nykh udostovereniy, poluchennykh okruzhnoy izbiratel’noy komissiyey\nChislo otkrepitel’nykh udostovereniy, vydannykh territorial’nym izbiratel’nym komissiyam\nChislo neispol’zovannykh otkrepitel’nykh udostovereniy, pogashennykh okruzhnoy izbiratel’noy komissiyey\nChislo otkrepitel’nykh udostovereniy, utrachennykh v okruzhnoy izbiratel’noy komissii"
-  test "ДЛИННОЕ ПОКРЫВАЛО", "DLINNOYE POKRYVALO"
-  test "Еловая шишка", "Yelovaya shishka"
-  test "ЕЛОВАЯ ШИШКА", "YELOVAYA SHISHKA"
-  test "Длинное покрывало", "Dlinnoye pokryvalo"
-  test "В лесу еловые шишки", "V lesu yelovyye shishki"
-  test "OН ВИДЕЛ ЕЁ В ПЕРВЫЙ РАЗ", "ON VIDEL YEYË V PERVYY RAZ"
-  test "Ёж колючий", "Yëzh kolyuchiy"
-  test "ЁЖ КОЛЮЧИЙ", "YËZH KOLYUCHIY"
-  test "Он видел её в первый раз", "On videl yeyë v pervyy raz"
-  test "У ёжа колючки", "U yëzha kolyuchki"
-  test "ЙА Йа йа", "Y·A Y·a y·a"
-  test "ЫУ Ыу ыу", "Y·U Y·u y·u"
-  test "ОЫ Оы оы", "O·Y O·y o·y"
-  test "ОЫУ Оыу оыу", "O·Y·U O·y·u o·y·u"
-  test "СЭ Сэ сэ", "S·E S·e s·e"
-  test "ТС тс Тс тС", "T·S t·s T·s t·S"
-  test "ШЧ шч Шч шЧ", "SH·CH sh·ch Sh·ch sh·Ch"
-}
-
-aliases {
-  def_alias rus_extvowel, any("АаЕеЁёИиОоУуЫыЭэЮюЯяЙйЪъЬь")
-  def_alias rus_vowel, any("АаЕеЁёИиОоУуЫыЭэЮюЯя")
-  def_alias rus_limvowel, any("АаУуЫыЭэ")
-  def_alias rus_cons, any("БбВвГгДдЖжЗзКкЛлМмНнПпРрСсТтФфХхЦцЧчШшЩщ")
-
-  def_alias rus_latupper, any([any("A".."Z"), any("Ë")])
-
-  def_alias rus_multichar, any(["Ye", "Yë", "Sh", "Ch", "Shch", "Ya", "Zh", "Yu", "Ts"])
-}
-
-stage {
-
-  # RULES
-  sub "\u0401", "Yë", before: rus_extvowel # Ё after a, e, ё, и, о, у, ы, э, ю, я, й, ъ, ь
-  sub "\u0451", "yë", before: rus_extvowel # ё after a, e, ё, и, о, у, ы, э, ю, я, й, ъ, ь
-  sub "\u0415", "YЕ", before: rus_extvowel # Е after a, e, ё, и, о, у, ы, э, ю, я, й, ъ, ь
-  sub "\u0415", "Yе", before: boundary # Е initially
-  sub "\u0435", "yе", before: rus_extvowel # е after a, e, ё, и, о, у, ы, э, ю, я, й, ъ, ь
-  sub "\u0435", "yе", before: boundary # е initially
-  sub "\u0401", "Yë", before: rus_extvowel # Ё after a, e, ё, и, о, у, ы, э, ю, я, й, ъ, ь
-  sub "\u0401", "Yë", before: boundary
-  sub "\u0451", "yë", before: rus_extvowel # ё after a, e, ё, и, о, у, ы, э, ю, я, й, ъ, ь
-  sub "\u0451", "yë", before: boundary
-  sub "\u0419", "Y·", after: rus_limvowel # Й before а, у, ы, or э
-  sub "\u0439", "y·", after: rus_limvowel # й before а, у, ы, or э
-  sub "\u042b", "·Y·", before: rus_vowel, after: rus_limvowel # Ы after any vowel character and before а, у, ы, or э
-  sub "\u044b", "·y·", before: rus_vowel, after: rus_limvowel # ы after any vowel character and before а, у, ы, or э
-  sub "\u042b", "Ы·", after: rus_limvowel # Ы before а, у, ы, or э
-  sub "\u044b", "ы·", after: rus_limvowel # ы before а, у, ы, or э
-  sub "\u042b", "·Y", before: any("Оо") # Ы after о
-  sub "\u044b", "·y", before: any("Оо") # ы after о
-  sub "\u0401", "Yë", before: boundary
-  sub "\u0451", "yë", before: boundary
-  sub "\u042d", "·E", before: rus_cons # Э after any consonant character except й
-  sub "\u044d", "·e", before: rus_cons # э after any consonant character except й
-  sub none, "·", before: any("Тт"), after: any("Сс") # тс => t·s
-  sub none, "·", before: any("Шш"), after: any("Чч") # шч => sh·ch
-
-  # CHARACTERS
-  parallel {
-    sub "А", "A"
-    sub "Б", "B"
-    sub "В", "V"
-    sub "Г", "G"
-    sub "Д", "D"
-    sub "Е", "E"
-    sub "Ё", "Ë" # Ё
-    sub "Ж", "Zh"
-    sub "З", "Z"
-    sub "И", "I"
-    sub "Й", "Y"
-    sub "К", "K"
-    sub "Л", "L"
-    sub "М", "M"
-    sub "Н", "N"
-    sub "О", "O"
-    sub "П", "P"
-    sub "Р", "R"
-    sub "С", "S"
-    sub "Т", "T"
-    sub "У", "U"
-    sub "Ф", "F"
-    sub "Х", "Kh"
-    sub "Ц", "Ts"
-    sub "Ч", "Ch"
-    sub "Ш", "Sh"
-    sub "Щ", "Shch"
-    sub "Ъ", "\"" # Ъ
-    sub "Ы", "Y"
-    sub "Ь", "’" # Ь => ’
-    sub "Э", "E"
-    sub "Ю", "Yu"
-    sub "Я", "Ya"
-    sub "а", "a"
-    sub "б", "b"
-    sub "в", "v"
-    sub "г", "g"
-    sub "д", "d"
-    sub "е", "e"
-    sub "ё", "ë" # ё
-    sub "ж", "zh"
-    sub "з", "z"
-    sub "и", "i"
-    sub "й", "y"
-    sub "к", "k"
-    sub "л", "l"
-    sub "м", "m"
-    sub "н", "n"
-    sub "о", "o"
-    sub "п", "p"
-    sub "р", "r"
-    sub "с", "s"
-    sub "т", "t"
-    sub "у", "u"
-    sub "ф", "f"
-    sub "х", "kh"
-    sub "ц", "ts"
-    sub "ч", "ch"
-    sub "ш", "sh"
-    sub "щ", "shch"
-    sub "ъ", "\"" # ъ
-    sub "ы", "y"
-    sub "ь", "’" # ь => ’
-    sub "э", "e"
-    sub "ю", "yu"
-    sub "я", "ya"
-  }
-
-  # POSTRULES
-  sub rus_multichar, upcase, before: rus_latupper
-  sub rus_multichar, upcase, before: rus_latupper + "·"
-  sub rus_multichar, upcase, after: "·" + rus_latupper
-  sub rus_multichar, upcase, after: rus_latupper
-
-  # Run twice to find more cases
-  sub rus_multichar, upcase, before: rus_latupper
-  sub rus_multichar, upcase, before: rus_latupper + "·"
-  sub rus_multichar, upcase, after: "·" + rus_latupper
-  sub rus_multichar, upcase, after: rus_latupper
-}

data/maps/bgnpcgn-sme-Latn-Latn-1984.imp

@@ -1,48 +0,0 @@
-metadata {
-  authority_id: bgnpcgn
-  id: 1984
-  language: iso-639-2:sme
-  source_script: Latn
-  destination_script: Latn
-  name: Roman-Script Spelling Convention of Northern Sami (North Lappish) (1984 Agreement)
-  url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693794/ROMAN-SCRIPT_SPELLING_CONVENTIONS.pdf
-  creation_date: 1984
-
-  notes:
-    - |
-      The special letter Ŋ ŋ, known as eng, [Unicode: 014A, 014B] should be reproduced in that form whenever
-      encountered. In those instances when it cannot be reproduced, however, the letter Ń ń [Unicode: 0143, 0144]
-      may be substituted for it.
-    - |
-      In a further note additional to the 1984 agreement, other special letters should be retained as found:
-        Á á [Unicode: 00C1, 00E1],
-        Č č [Unicode: 010C, 010D],
-        Đ đ [Unicode: 0110, 0111],
-        Š š [Unicode: 0160, 0161],
-        Ŧ ŧ [Unicode: 0166, 0167],
-        Ž ž [Unicode: 017D, 017E].
-}
-
-tests {
-  # https://web.archive.org/web/20120918094122/http://www.uta.fi/~km56049/same/svocab.html
-  test "adjágas", "adjágas"
-  test "agálaš", "agálaš"
-  test "ÁEL", "ÁEL"
-  test "hčagastinárpu", "hčagastinárpu"
-  test "algŋa", "algńa"
-  test "Šveica", "Šveica"
-  test "MAŊŊIL", "MAŃŃIL"
-  test "giđa", "giđa"
-  test "ruoŧŧelaš", "ruoŧŧelaš"
-  test "skálžu", "skálžu"
-}
-
-stage {
-
-  # CHARACTERS
-  parallel {
-    sub "Ŋ", "Ń" # Ŋ => Ń
-    sub "ŋ", "ń" # ŋ => ń
-  }
-
-}

data/maps/bgnpcgn-srp-Cyrl-Latn-1962.imp

@@ -1,57 +0,0 @@
-metadata {
-  authority_id: bgnpcgn
-  id: 1962
-  language: iso-639-2:srp
-  source_script: Cyrl
-  destination_script: Latn
-  name: Transliteration of Serbian Cyrillic
-  creation_date: 1962
-  confirmation_date: 1962
-  description: |
-    Serbo-Croatian, the official national language of Yugoslavia, is a single literary language.
-
-    In Serbian areas it is written in the cyrillic (Serbian) alphabet, while in Croatian areas it is
-    written in the roman (Croatian) alphabet.
-
-    Both the BGN and PCGN use the standard Croatian equivalents for formalizing the Serbian cyrillic
-    alphabet whenever romanized names are not available.
-
-  notes:
-    - The digraph dj(Dj) will occasionally be found as the Croatian equivalent of ђ(Ђ),
-      but the use of dj should be limited to those instances where it is found in roman sources.
-}
-
-tests {
-  test "Шупља Стена", "Šuplja Stena"
-  test "Чукарица", "Čukarica"
-  test "Црна Трава", "Crna Trava"
-  test "Херцег Нови", "Herceg Novi"
-  test "Улцињ", "Ulcinj"
-  test "Ужице", "Užice"
-  test "Тресаначка Река", "Tresanačka Reka"
-  test "Сјеница", "Sjenica"
-  test "Рожаје", "Rožaje"
-  test "Пљевља", "Pljevlja"
-  test "Оџаци", "Odžaci"
-  test "Никшић", "Nikšić"
-  test "Медвеђа", "Medveđa"
-  test "Лозница", "Loznica"
-  test "Књажевац", "Knjaževac"
-  test "Зрењанин", "Zrenjanin"
-  test "Житорађа", "Žitorađa"
-  test "Ервеник", "Ervenik"
-  test "Доње Љупче", "Donje Ljupče"
-  test "Гусиње", "Gusinje"
-  test "ГУСИЊЕ", "GUSINJE"
-  test "Врњачка Бања", "Vrnjačka Banja"
-  test "Бијело Поље", "Bijelo Polje"
-  test "Алибунар", "Alibunar"
-}
-
-dependency "bgnpcgn-srp-Cyrl-Latn-2005", as: cyrllatn
-
-stage {
-
-  run map.cyrllatn.stage.main
-
-}

data/maps/bgnpcgn-srp-Cyrl-Latn-2005.imp

@@ -1,146 +0,0 @@
-metadata {
-  authority_id: bgnpcgn
-  id: 2005
-  language: iso-639-2:srp
-  source_script: Cyrl
-  destination_script: Latn
-  name: Table of Correspondences for Serbian (Cyrillic-Roman) (2005 Agreement)
-  url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/816783/TABLE_OF_CORRESPONDENCES_FOR_SERBIAN.pdf
-  creation_date: 2005
-  confirmation_date: 2019-06
-  description: |
-    The tabulation below reflects the Serbian Cyrillic alphabet and the standard Roman script equivalents
-    used in both Serbia and Montenegro.
-
-  notes:
-    - The Serbian Cyrillic lowercase italic Д may sometimes be seen as g.
-      There is no specific Unicode encoding for this variant form so a comparable character
-      has been used here for illustrative purposes.
-
-    - The digraph dj(Dj) will occasionally be found as an alternative form of đ(Đ).
-
-    - The Serbian Cyrillic lowercase italic П may sometimes be seen as ӣ.
-      There is no specific Unicode encoding for this variant form so a comparable character
-      has been used here for illustrative purposes.
-
-    - The Serbian Cyrillic lowercase italic Т may sometimes be seen as w.
-      There is no specific Unicode encoding for this variant form so a comparable character
-      has been used here for illustrative purposes.
-
-    - |
-      An inventory of letter-diacritic combinations, with their Unicode encoding,
-      in addition to the unmodified letters of the basic Roman script is:
-      | Đ (U+0110)   | đ (U+0111)   |
-      | Ž (U+017D)   | ž (U+017E)   |
-      | Lj (U+01C8)* | lj (U+01C9)* |
-      | Ć (U+0106)   | ć (U+0107)   |
-      | Dž (U+01C5)* | dž (U+01C6)* |
-      | Š (U+0160)   | š (U+0161)   |
-      * Note that these characters can also be reproduced with individual letters (e.g. l+j).
-
-    - 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 "Шупља Стена", "Šuplja Stena"
-  test "Чукарица", "Čukarica"
-  test "Црна Трава", "Crna Trava"
-  test "Херцег Нови", "Herceg Novi"
-  test "Улцињ", "Ulcinj"
-  test "Ужице", "Užice"
-  test "Тресаначка Река", "Tresanačka Reka"
-  test "Сјеница", "Sjenica"
-  test "Рожаје", "Rožaje"
-  test "Пљевља", "Pljevlja"
-  test "Оџаци", "Odžaci"
-  test "Никшић", "Nikšić"
-  test "Медвеђа", "Medveđa"
-  test "Лозница", "Loznica"
-  test "Књажевац", "Knjaževac"
-  test "Зрењанин", "Zrenjanin"
-  test "Житорађа", "Žitorađa"
-  test "Ервеник", "Ervenik"
-  test "Доње Љупче", "Donje Ljupče"
-  test "Гусиње", "Gusinje"
-  test "ГУСИЊЕ", "GUSINJE"
-  test "Врњачка Бања", "Vrnjačka Banja"
-  test "Бијело Поље", "Bijelo Polje"
-  test "Алибунар", "Alibunar"
-}
-
-aliases {
-  def_alias srp_multichar, any(["Lj", "Nj", "Dž"])
-  def_alias srp_latupper, any("A".."Z")
-}
-
-stage {
-  # CHARACTERS
-  parallel {
-    sub "А", "A"
-    sub "Б", "B"
-    sub "В", "V"
-    sub "Г", "G"
-    sub "Д", "D"
-    sub "Ђ", "Đ" # Đ
-    sub "Е", "E"
-    sub "Ж", "Ž" # Ž
-    sub "З", "Z"
-    sub "И", "I"
-    sub "Ј", "J"
-    sub "К", "K"
-    sub "Л", "L"
-    sub "Љ", "Lj"
-    sub "М", "M"
-    sub "Н", "N"
-    sub "Њ", "Nj"
-    sub "О", "O"
-    sub "П", "P"
-    sub "Р", "R"
-    sub "С", "S"
-    sub "Т", "T"
-    sub "Ћ", "Ć" # Ć
-    sub "У", "U"
-    sub "Ф", "F"
-    sub "Х", "H"
-    sub "Ц", "C"
-    sub "Ч", "Č" # Č
-    sub "Џ", "Dž" # Dž
-    sub "Ш", "Š" # Š
-    sub "а", "a"
-    sub "б", "b"
-    sub "в", "v"
-    sub "г", "g"
-    sub "д", "d"
-    sub "ђ", "đ" # đ
-    sub "е", "e"
-    sub "ж", "ž" # ž
-    sub "з", "z"
-    sub "и", "i"
-    sub "ј", "j"
-    sub "к", "k"
-    sub "л", "l"
-    sub "љ", "lj"
-    sub "м", "m"
-    sub "н", "n"
-    sub "њ", "nj"
-    sub "о", "o"
-    sub "п", "p"
-    sub "р", "r"
-    sub "с", "s"
-    sub "т", "t"
-    sub "ћ", "ć" # ć́
-    sub "у", "u"
-    sub "ф", "f"
-    sub "х", "h"
-    sub "ц", "c"
-    sub "ч", "č" # č
-    sub "џ", "dž" # dž
-    sub "ш", "š" # š
-  }
-
-  # POSTRULES
-  sub srp_multichar, upcase, before: srp_latupper
-  sub srp_multichar, upcase, after: srp_latupper
-  compose
-}

data/maps/bgnpcgn-tat-Cyrl-Latn-2007.imp

@@ -1,185 +0,0 @@
-metadata {
-  authority_id: bgnpcgn
-  id: 2007
-  language: iso-639-2:tat
-  source_script: Cyrl
-  destination_script: Latn
-  name: Table of Correspondences for Tatar (Cyrillic-Roman) (2007 Agreement)
-  url: https://geonames.nga.mil/gns/html/Romanization/TABLE%20OF%20CORRESPONDENCES%20FOR%20TATAR.pdf
-  creation_date: 2007
-  confirmation_date: 2017-11
-  description: |
-    Tatar is an official language within Respublika Tatarstan, 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 alphabet portrayed in the above table is referred to as yaꞑalif-2.
-      A set of simpler characters is also encountered; this is known as zamanalif.
-      In this latter set, the alternative characters ä, ñ and ö are used for letters
-      2, 17 and 19 respectively where the user has difficulty reproducing ə, ꞑ, and ө.
-      Please note that all three alternatives must be used as a set, and the letters should not be intermingled.
-    - Used only in borrowed words.
-    - The first option is used in words with back vowels, the second in words with front vowels (though this does not apply to borrowed words).
-    - yı/ye is used after a vowel (except и, ю), ъ and ь, also word-initially.
-    - w is used after a vowel.
-    - After ğ or q, ый is represented i
-    - Э is represented ’ after a vowel in words of Arabic origin.
-    - Ю and Я are represented ü and a/ä respectively after и.
-    - |
-      An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the unmodified letters
-      of the basic Roman script is:
-          Ə (U+018F) ə (U+0259)
-          Ğ (U+011E) ğ (U+011F)
-          İ (U+0130) ı (U+0131)
-          Ü (U+00DC) ü (U+00FC)
-          Ꞑ (U+A790) ꞑ (U+A791)
-          Ɵ (U+019F) ɵ (U+0275)
-          Ç (U+00C7) ç (U+00E7)
-          Ş (U+015E) ş (U+015F)
-          Ä (U+00C4) ä (U+00E4)
-          ’ (U+2019)
-    - |
-      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 "Гыйльмиев", "Ğil’miew" #  # note[6] in the note it's Ğilmiev which incorrect according to the rules
-  # https://en.wikipedia.org/wiki/Tatar_alphabet
-  test "баеды", "bayıdı" # note[4]
-  test "кардәш", "qardəş"
-  test "калынлык һәм аеру билгесе", "qalınlıq həm ayıru bilgese" # note[4]
-  test "Барлык кешеләр дә азат һәм үз абруйлары һәм хокуклары ягыннан тиң булып туалар.\nАларга акыл һәм вөҗдан бирелгән һәм бер-берсенә карата туганнарча мөнасәбәттә булырга тиешләр.", "Barlıq keşelər də azat həm üz abruyları həm xoquqları yağınnan tiꞑ bulıp tualar.\nAlarğa aqıl həm wocdan birelgən həm ber-bersenə qarata tuğannarça monasəbəttə bulırğa tieşlər."
-  # https://www.azatliq.org/a/30820571.html
-  test "Әлдермештән Әлмәндәр", "Əldermeştən Əlməndər"
-  test "Әссәламү галәйкүм", "Əssəlamü ğaləyküm"
-  test "Танымаган кешегә", "Tanımağan keşegə" # note[3]
-  test "Иң әүвәл кул бирешеп күрешик", "İꞑ əwwəl qul bireşep küreşiq" # note[5]
-  test "Ялгышмыйсың", "Yalğışmıysıꞑ"
-  test "Нәкъ үзе", "Nəq üze"
-  test "Кирәгеннән артыгын", "Kirəgennən artığın" # note[3]
-  test "мәңгелеккә килмәгән", "məꞑgeleqkə kilməgən"
-  test "кулыңны куй", "qulıꞑnı quy"
-  test "Өммия", "Ommiä" # note[8]
-  test "Җиһангир", "Cihangir" # note[3]
-}
-
-stage {
-
-  # RULES
-  # note[3] http://www.hintfox.com/article/sistema-glasnih-zvykov-na-tatarskom-i-anglijskom-jazikah.html
-  # back vowels: у, а, ы, о,
-  # front vowels: е, ә, и, ө, ү, э
-  sub "Г", "G", after: any("ЕеƏәИиӨөҮүЭэ")
-  sub "г", "g", after: any("ЕеƏәИиӨөҮүЭэ")
-  sub "К", "K", after: any("ЕеƏәИиӨөҮүЭэ")
-  sub "к", "k", after: any("ЕеƏәИиӨөҮүЭэ")
-  sub "Ю", "Yü", after: any("ЕеƏәИиӨөҮүЭэ")
-  sub "ю", "yü", after: any("ЕеƏәИиӨөҮүЭэ")
-  sub "Я", "Yä", after: any("ЕеƏәИиӨөҮүЭэ")
-  sub "я", "yä", after: any("ЕеƏәИиӨөҮүЭэ")
-
-  # note[4]
-  sub "\u0415", "Yı", before: any("АаЕеƏәОоӨөҮүУуЫыЭэЯяЪъЬь")
-  sub "\u0435", "yı", before: any("АаЕеƏәОоӨөҮүУуЫыЭэЯяЪъЬь")
-
-  # note[5]
-  sub "\u0423", "W", before: any("АаЕеƏәИиОоӨөҮүУуЫыЭэЮюЯяЪъЬь")
-  sub "\u0443", "w", before: any("АаЕеƏәИиОоӨөҮүУуЫыЭэЮюЯяЪъЬь")
-  sub "\u04AE", "W", before: any("АаЕеƏәИиОоӨөҮүУуЫыЭэЮюЯяЪъЬь")
-  sub "\u04AF", "w", before: any("АаЕеƏәИиОоӨөҮүУуЫыЭэЮюЯяЪъЬь")
-
-  # note[6]
-  sub "ый", "i", before: any("Гг")
-
-  # note[8]
-  sub "\u042E", "Ü", before: any("Ии")
-  sub "\u044E", "ü", before: any("Ии")
-  sub "\u042F", "Ä", before: any("Ии")
-  sub "\u044F", "ä", before: any("Ии")
-
-
-  # CHARACTERS
-  parallel {
-    sub "А", "A" # А
-    sub "Ә", any("ƏÄ") # Ә => [Ə, Ä] note[1]
-    sub "Б", "B" # Б
-    sub "В", any("WV") # В note[2]
-    sub "Г", "Ğ" # Г => Ğ note[3]
-    sub "Д", "D" # Д
-    sub "Е", "E" # Е note[3] note[4]
-    sub "Ж", "J" # Ж
-    sub "Җ", "C" # Җ
-    sub "З", "Z" # З
-    sub "И", "İ" # И => İ
-    sub "Й", "Y" # Й
-    sub "К", "Q" # К note[3]
-    sub "Л", "L" # Л
-    sub "М", "M" # М
-    sub "Н", "N" # Н
-    sub "Ң", any("ꞐÑ") # Ң => [Ꞑ, Ñ] note[1]
-    sub "О", "O" # О
-    sub "Ө", any("OÖ") # Ө => [O, Ö] note[1]
-    sub "П", "P" # П
-    sub "Р", "R" # Р
-    sub "С", "S" # С
-    sub "Т", "T" # Т
-    sub "У", "U" # У note[5]
-    sub "Ү", "Ü" # Ү => Ü note[5]
-    sub "Ф", "F" # Ф
-    sub "Х", "Х" # Х
-    sub "Һ", "H" # Һ
-    sub "Ц", "Ts" # Ц
-    sub "Ч", "Ç" # Ч => Ç
-    sub "Ш", "Ş" # Ш => Ş
-    sub "Щ", "ŞÇ" # Щ
-    sub "Ъ", "" # Ъ
-    sub "Ы", "I" # Ы => I note[2] note[6]
-    sub "Ь", "’" # Ь => ’
-    sub "Э", "E" # Э note[7]
-    sub "Ю", "Yu" # Ю note[3] note[8]
-    sub "Я", "Ya" # Я note[3] note[8]
-
-    sub "\u0430", "a" # а
-    sub "\u04D9", any("əä") # ә => [ə, ä] note[1]
-    sub "\u0431", "b" # б
-    sub "\u0432", any("wv") # в note[2]
-    sub "\u0433", "ğ" # г => ğ note[3]
-    sub "\u0434", "d" # д
-    sub "\u0435", "e" # e note[3] note[4]
-    sub "\u0436", "j" # ж
-    sub "\u0497", "c" # җ
-    sub "\u0437", "z" # з
-    sub "\u0438", "i" # и
-    sub "\u0439", "y" # й
-    sub "\u043A", "q" # к note[3]
-    sub "\u043B", "l" # л
-    sub "\u043C", "m" # м
-    sub "\u043D", "n" # н
-    sub "\u04A3", any("ꞑñ") # ң => [ꞑ, ñ] note[1]
-    sub "\u043E", "o" # о
-    sub "\u04E9", any("oö") # ө => [o, ö] note[1]
-    sub "\u043F", "p" # п
-    sub "\u0440", "r" # р
-    sub "\u0441", "s" # с
-    sub "\u0442", "t" # т
-    sub "\u0443", "u" # у note[5]
-    sub "\u04AF", "ü" # ү => ü note[5]
-    sub "\u0444", "f" # ф
-    sub "\u0445", "x" # х
-    sub "\u04BB", "h" # һ
-    sub "\u0446", "ts" # ц
-    sub "\u0447", "ç" # ч => ç
-    sub "\u0448", "ş" # ш => ş
-    sub "\u0449", "şç" # щ => şç
-    sub "ъ", "" # ъ
-    sub "\u044B", "ı" # ы => ı note[2] note[6]
-    sub "ь", "’" # ь => ’
-    sub "\u044D", "e" # э note[7]
-    sub "\u044E", "yu" # ю note[3] note[8]
-    sub "\u044F", "ya" # я note[3] note[8]
-  }
-
-}