interscript-maps 2.4.2 → 2.5.0

data/maps/bgnpcgn-tuk-Cyrl-Latn-1979.isc

@@ -0,0 +1,154 @@
+system "BGN-PCGN:tuk-Cyrl:Latn:1979" {
+
+metadata {
+  authority_id bgnpcgn
+  id 1979
+  language iso-639-2:tuk
+  source_script Cyrl
+  destination_script Latn
+  name TURKMEN Cyrillic script
+  url https://transliteration.eki.ee/pdf/Turkmen.pdf
+  creation_date 1979
+
+  notes {
+    note "Ye/ye is used initially, after a vowel, й, ъ, and ь."
+  }
+}
+
+tests {
+  # adopted https://assets.publishing.service.gov.uk/media/6329b1638fa8f53cb45763b4/TABLE_OF_CORRESPONDENCES_FOR_TURKMEN_with_examples.pdf
+   "Aшгабат" ->  "Ashgabat"
+   "Лебап" ->  "Lebap"
+   "Ныязов" ->  "Nyyazov"
+   "Тагта" ->  "Tagta"
+   "Дашховуз" ->  "Dashkhovuz"
+   "Небитдаг" ->  "Nebitdag"
+   "Ёлөтен" ->  "Yolöten"
+   "Теҗен" ->  "Tejen"
+   "Газанҗык" ->  "Gazanjyk"
+   "Керки" ->  "Kerki"
+   "Бүзмейин" ->  "Büzmeyin"
+   "Кака" ->  "Kaka"
+   "Челекен" ->  "Cheleken"
+   "Түркменбашы" ->  "Türkmenbashy"
+   "Чаршаңңы" ->  "Charshangngy"
+   "Мургап" ->  "Murgap"
+   "Мары" ->  "Mary"
+   "Сарахс" ->  "Sarakhs"
+   "Фарап" ->  "Farap"
+   "Эсенгулы" ->  "Esenguly"
+   "Әнев" ->  "Änev"
+}
+
+stage main {
+  # RULES
+
+  # note[1]
+  sub {
+    from boundary + "\u0415"
+    to "Ye"
+  }
+  sub {
+    from boundary + "\u0435"
+    to "ye"
+  }
+  sub {
+    from "\u0415"
+    to "Ye"
+    before any("АаЕеЁёИиЙйОоӨөУуҮүЪъЫыЬьЭэӘәЮюЯя")
+    after boundary
+  }
+  sub {
+    from "\u0435"
+    to "ye"
+    before any("АаЕеЁёИиЙйОоӨөУуҮүЪъЫыЬьЭэӘәЮюЯя")
+    after boundary
+  }
+
+  # CHARACTERS
+  parallel {
+    sub "\u0410" "A"
+    sub "\u0411" "B"
+    sub "\u0412" "V"
+    sub "\u0413" "G"
+    sub "\u0414" "D"
+    sub "\u0415" "E"
+    sub "\u0401" "Yo"
+    sub "\u0416" "Zh"
+    sub "\u0496" "J"
+    sub "\u0417" "Z"
+    sub "\u0418" "I"
+    sub "\u0419" "Y"
+    sub "\u041A" "K"
+    sub "\u041B" "L"
+    sub "\u041C" "M"
+    sub "\u041D" "N"
+    sub "\u04A2" "Ng"
+    sub "\u041E" "O"
+    sub "\u04E8" "Ö"
+    sub "\u041F" "P"
+    sub "\u0420" "R"
+    sub "\u0421" "S"
+    sub "\u0422" "T"
+    sub "\u0423" "U"
+    sub "\u04AE" "Ü"
+    sub "\u0424" "F"
+    sub "\u0425" "Kh"
+    sub "\u0426" "Ts"
+    sub "\u0427" "Ch"
+    sub "\u0428" "Sh"
+    sub "\u0429" "Shch"
+    sub {
+    from "\u042A"
+    to "\""
+  }
+    sub "\u042B" "Y"
+    sub "\u042C" "'"
+    sub "\u042D" "E"
+    sub "\u04D8" "Ä"
+    sub "\u042E" "Yu"
+    sub "\u042F" "Ya"
+
+    sub "\u0430" "a"
+    sub "\u0431" "b"
+    sub "\u0432" "v"
+    sub "\u0433" "g"
+    sub "\u0434" "d"
+    sub "\u0435" "e"
+    sub "\u0451" "yo"
+    sub "\u0436" "zh"
+    sub "\u0497" "j"
+    sub "\u0437" "z"
+    sub "\u0438" "i"
+    sub "\u0439" "y"
+    sub "\u043A" "k"
+    sub "\u043B" "l"
+    sub "\u043C" "m"
+    sub "\u043D" "n"
+    sub "\u04A3" "ng"
+    sub "\u043E" "o"
+    sub "\u04E9" "ö"
+    sub "\u043F" "p"
+    sub "\u0440" "r"
+    sub "\u0441" "s"
+    sub "\u0442" "t"
+    sub "\u0443" "u"
+    sub "\u04af" "ü"
+    sub "\u0444" "f"
+    sub "\u0445" "kh"
+    sub "\u0446" "ts"
+    sub "\u0447" "ch"
+    sub "\u0448" "sh"
+    sub "\u0449" "shch"
+    sub {
+    from "\u044A"
+    to "\""
+  }
+    sub "\u044B" "y"
+    sub "\u044C" "'"
+    sub "\u044D" "e"
+    sub "\u04D9" "ä"
+    sub "\u044E" "yu"
+    sub "\u044F" "ya"
+  }
+}}

data/maps/bgnpcgn-tuk-Cyrl-Latn-1993.isc

@@ -0,0 +1,115 @@
+system "BGN-PCGN:tuk-Cyrl:Latn:1993" {
+
+metadata {
+  authority_id bgnpcgn
+  id 1993
+  language iso-639-2:tuk
+  source_script Cyrl
+  destination_script Latn
+  name Table of Correspondences for Turkmen (Cyrillic-Roman) (2000 Agreement)
+  url https://assets.publishing.service.gov.uk/media/6329b1638fa8f53cb45763b4/TABLE_OF_CORRESPONDENCES_FOR_TURKMEN_with_examples.pdf
+  creation_date 1993
+  confirmation_date 2022
+  description {    In 1993, the Turkmen government adopted the Roman alphabet to replace the existing Cyrillic alphabet. The presentation below provides a table of correspondences between the former Cyrillic alphabet and the current Roman alphabet.  When Turkmen Roman-alphabet spellings are not available, this table can be used to convert Turkmen Cyrillic spellings.  This table of correspondences supersedes the BGN/PCGN 1979 romanization system for Turkmen. 
+  }
+
+  notes {
+    note "The letter sequence ýe is used initially, after the vowel characters 33, 35, 37, and 38,"
+    note "and after character 12. 2 Rarely encountered."
+    note "      If the letter Ұ (Unicode 04BE) is encountered, it should be rendered Ý.\n      If the letter ÿ (Unicode 00FF) is encountered, it should be rendered ý."
+    note "      If the character £ (Unicode 00A3) is encountered, it should be rendered Ž.\n      If the character ſ (Unicode 017F) is encountered, it should be rendered ž."
+    note "If the letter-diacritic combination ñ (Unicode 00F1) is encountered, it should be rendered ň."
+    note "      An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the unmodified letters of the basic Roman script is:\n        Ý (U+00DD) ý (U+00FD)\n        Ž (U+017D) ž (U+017E)\n        Ü (U+00DC) ü (U+00FC)\n        Ç (U+00C7) ç (U+00E7)\n        Ş (U+015E) ş (U+015F)\n        Ň (U+0147) ň (U+0148)\n        Ö (U+00D6) ö (U+00F6)\n        Ä (U+00C4) ä (U+00E4)"
+    note "The Roman-script columns show only lowercase forms but, when applying the table, uppercase and lowercase Roman letters as appropriate should be used."
+  }
+}
+
+tests {
+   "Aшгабат" ->  "Aşgabat"
+   "Лебап" ->  "Lebap"
+   "Ныязов" ->  "Nyýazow"
+   "Тагта" ->  "Tagta"
+   "Дашховуз" ->  "Daşhowuz"
+   "Небитдаг" ->  "Nebitdag"
+   "Ёлөтен" ->  "Ýolöten"
+   "Теҗен" ->  "Tejen"
+   "Газанҗык" ->  "Gazanjyk"
+   "Керки" ->  "Kerki"
+   "Бүзмейин" ->  "Büzmeýin"
+   "Кака" ->  "Kaka"
+   "Челекен" ->  "Çeleken"
+   "Түркменбашы" ->  "Türkmenbaşy"
+   "Чаршаңңы" ->  "Çarşaňňy"
+   "Мургап" ->  "Murgap"
+   "Мары" ->  "Mary"
+   "Сарахс" ->  "Sarahs"
+   "Фарап" ->  "Farap"
+   "Эсенгулы" ->  "Esenguly"
+   "Әнев" ->  "Änew"
+}
+
+dependency "bgnpcgn-tuk-Cyrl-Latn-1979" as cyrllatn
+
+stage main {
+  # RULES
+
+  # note[1]
+  sub {
+    from boundary + "\u0415"
+    to "Ýe"
+  }
+  sub {
+    from boundary + "\u0435"
+    to "ýe"
+  }
+  sub {
+    from "\u0415"
+    to "Ýe"
+    before any("АаЕеЁёИиЙйОоӨөУуҮүЫыЭэӘәЮюЯя")
+    after boundary
+  }
+  sub {
+    from "\u0435"
+    to "ýe"
+    before any("АаЕеЁёИиЙйОоӨөУуҮүЫыЭэӘәЮюЯя")
+    after boundary
+  }
+
+  # CHARACTERS
+  parallel {
+    sub "\u0412" "W"
+    sub "\u0401" "Ýo"
+    sub "\u0416" "Ž"
+    sub "\u0419" "Ý"
+    sub "\u04A2" "Ň"
+    sub "\u0425" "H"
+    sub "\u0426" "S"
+    sub "\u0427" "Ç"
+    sub "\u0428" "Ş"
+    sub "\u0429" "ŞÇ"
+    sub "\u042A" ""
+    sub "\u042C" ""
+    sub "\u042E" "Ýu"
+    sub "\u042F" "Ýa"
+
+    sub "\u0432" "w"
+    sub "\u0451" "ýo"
+    sub "\u0436" "ž"
+    sub "\u0439" "ý"
+    sub "\u04A3" "ň"
+    sub "\u04af" "ü"
+    sub "\u0444" "f"
+    sub "\u0445" "h"
+    sub "\u0446" "s"
+    sub "\u0447" "ç"
+    sub "\u0448" "ş"
+    sub "\u0449" "şç"
+    sub "\u044A" ""
+    sub "\u044C" ""
+    sub "\u044E" "ýu"
+    sub "\u044F" "ýa"
+  }
+
+  run  map.cyrllatn.stage.main
+}
+}

data/maps/bgnpcgn-ukr-Cyrl-Latn-1965.isc

@@ -0,0 +1,143 @@
+system "BGN-PCGN:ukr-Cyrl:Latn:1965" {
+
+metadata {
+  authority_id bgnpcgn
+  id 1965
+  language iso-639-2:ukr
+  source_script Cyrl
+  destination_script Latn
+  name Romanization of Ukrainian (1965)
+  url https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/816788/ROMANIZATION_OF_UKRAINIAN.pdf
+  creation_date 1947
+  confirmation_date 2019-06
+  description {    The BGN/PCGN system for Ukrainian was designed for use in romanizing
+    names written in the Ukrainian alphabet. The Ukrainian alphabet
+    contains five characters not present in the Russian alphabet: ґ, є, і,
+    ї, and ’.
+  }
+
+  notes {
+    note "The character sequences з г, к г, с г, т с and ц г 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, ц, ш, and the character sequence тш."
+    note "All apostrophes appearing in romanization are Unicode encoding 2019."
+    note "The Roman‐script columns show only lowercase forms but, when applying the table, uppercase and lowercase Roman letters as appropriate should be used."
+  }
+}
+
+tests {
+   "Авдіївська Міськрада" ->  "Avdiyivs’ka Mis’krada"
+   "Бабаї" ->  "Babayi"
+   "Віленька" ->  "Vilen’ka"
+   "Гагарінський Район" ->  "Haharins’kyy Rayon"
+   "Довбушева Криниця" ->  "Dovbusheva Krynytsya"
+   "Дідівщина" ->  "Didivshchyna"
+   "Економічна" ->  "Ekonomichna"
+   "Єфросинівка" ->  "Yefrosynivka"
+   "Жигуліна Роща" ->  "Zhyhulina Roshcha"
+   "Загір’я" ->  "Zahir”ya"
+   "З’єднувальний Канал" ->  "Z”yednuval’nyy Kanal"
+   "Ивахи" ->  "Yvakhy"
+   "Івано-Франківська Міськрада" ->  "Ivano-Frankivs’ka Mis’krada"
+   "Їжаківка" ->  "Yizhakivka"
+   "Йосиповичі" ->  "Yosypovychi"
+   "Кабичівка" ->  "Kabychivka"
+   "Лазуровий Провулок" ->  "Lazurovyy Provulok"
+   "Мала Сейдеминуха" ->  "Mala Seydemynukha"
+   "Нагірний" ->  "Nahirnyy"
+   "Овер’янівське Озеро" ->  "Over”yanivs’ke Ozero"
+   "Павлопільське Водосховище" ->  "Pavlopil’s’ke Vodoskhovyshche"
+   "Приґородний" ->  "Prygorodnyy"
+   "Радгосп Правда" ->  "Radhosp Pravda"
+   "Садово-Хрустальненський" ->  "Sadovo-Khrustal’nens’kyy"
+   "Таратутине" ->  "Taratutyne"
+   "Улу-Узень" ->  "Ulu-Uzen’"
+   "Христофорівка" ->  "Khrystoforivka"
+   "Центральна Вулиця" ->  "Tsentral’na Vulytsya"
+   "Чайковичі" ->  "Chaykovychi"
+   "Шалаші" ->  "Shalashi"
+   "Щербинівка" ->  "Shcherbynivka"
+   "Южноукраїнська Міськрада" ->  "Yuzhnoukrayins’ka Mis’krada"
+   "Ясениця" ->  "Yasenytsya"
+}
+
+stage main {
+
+  # RULES
+  sub {
+    from boundary + "\u2019" + boundary
+    to "”"
+  }
+
+
+  # CHARACTERS
+  parallel {
+    sub "а" "a"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "h"
+    sub "д" "d"
+    sub "е" "e"
+    sub "ж" "zh"
+    sub "з" "z"
+    sub "и" "y"
+    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 "ь" "’"
+    sub "ю" "yu"
+    sub "я" "ya"
+    sub "є" "ye"
+    sub "і" "i"
+    sub "ї" "yi"
+    sub "ґ" "g"
+    sub "" " "
+    sub "Є" "Ye"
+    sub "І" "I"
+    sub "Ї" "Yi"
+    sub "А" "A"
+    sub "Б" "B"
+    sub "В" "V"
+    sub "Г" "H"
+    sub "Д" "D"
+    sub "Е" "E"
+    sub "Ж" "Zh"
+    sub "З" "Z"
+    sub "И" "Y"
+    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 "Ь" "’"
+    sub "Ю" "Yu"
+    sub "Я" "Ya"
+    sub "Ґ" "G"
+  }
+
+}
+}

data/maps/bgnpcgn-ukr-Cyrl-Latn-2019.isc

@@ -0,0 +1,83 @@
+system "BGN-PCGN:ukr-Cyrl:Latn:2019" {
+
+metadata {
+  authority_id bgnpcgn
+  id 2019
+  language iso-639-2:ukr
+  source_script Cyrl
+  destination_script Latn
+  name Romanization of Ukrainian (2019 Agreement)
+  url https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/864314/ROMANIZATION_OF_UKRAINIAN.pdf
+  creation_date 2019
+  confirmation_date 2020-01
+  description {    The BGN/PCGN system for Ukrainian was designed for use in romanizing names written
+    in the Ukrainian alphabet. It is an adoption of the Ukrainian national system in use
+    since 2010, and supersedes the BGN/PCGN 1965 System for Ukrainian.
+  }
+
+  notes {
+    note "      The 2019 system was adopted by BGN and PCGN after monitoring a good level of implementation\n      of the national system within Ukraine. Note, however, that this system is not recommended for\n      reverse transliteration; take caution when attempting to convert a romanized name back into Ukrainian.\n      This system also lacks the methodology outlined in the 1965 System to provide additional\n      differentiation between digraphs and individual character sequences.\n      For example, unlike the 1965 System, the 2019 System doesn’t differentiate the special character\n      sequences зг, кг, сг, тс, and тсг (previously romanized as z∙h, k∙h, s∙h, t∙s, and ts∙h)\n      from the digraphs zh, kh, sh, ts, and the letter sequence tsh, which are used to render\n      the characters ж, х, ш, ц and the character sequence тш."
+    note "To use the keyboard Unicode function, hold ALT and enter in sequence listed in the table."
+    note "The character sequence З Г, previously romanized as zh, is romanized zgh under the 2019 system."
+    note "These characters differ significantly in romanization from the BGN/PCGN 1965 system."
+  }
+}
+
+tests {
+   "Алушта" ->  "Alushta"
+   "Борщагівка" ->  "Borshchahivka"
+   "Вишгород" ->  "Vyshhorod"
+   "Гадяч" ->  "Hadiach"
+   "Згорани" ->  "Zghorany"
+   "Ґалаґан" ->  "Galagan"
+   "Дон" ->  "Don"
+   "Рівне" ->  "Rivne"
+   "Єнакієве" ->  "Yenakiieve"
+   "Наєнко" ->  "Naienko"
+   "Житомир" ->  "Zhytomyr"
+   "Запоріжжя" ->  "Zaporizhzhia"
+   "Закарпаття" ->  "Zakarpattia"
+   "Медвин" ->  "Medvyn"
+   "Іршава" ->  "Irshava"
+   "Їжакевич" ->  "Yizhakevych"
+   "Кадіївка" ->  "Kadiivka"
+   "Йосипівка" ->  "Yosypivka"
+   "Стрий" ->  "Stryi"
+   "Київ" ->  "Kyiv"
+   "Лебедин" ->  "Lebedyn"
+   "Миколаїв" ->  "Mykolaiv"
+   "Ніжин" ->  "Nizhyn"
+   "Одеса" ->  "Odesa"
+   "Полтава" ->  "Poltava"
+   "Ромни" ->  "Romny"
+   "Суми" ->  "Sumy"
+   "Тетерів" ->  "Teteriv"
+   "Ужгород" ->  "Uzhhorod"
+   "Фастів" ->  "Fastiv"
+   "Харків" ->  "Kharkiv"
+   "Біла Церква" ->  "Bila Tserkva"
+   "Чернівці" ->  "Chernivtsi"
+   "Шостка" ->  "Shostka"
+   "Гоща" ->  "Hoshcha"
+   "Русь" ->  "Rus"
+   "Юрій" ->  "Yurii"
+   "Крюківка" ->  "Kriukivka"
+   "Яготин" ->  "Yahotyn"
+   "Ічня" ->  "Ichnia"
+   "Знам’янка" ->  "Znamianka"
+}
+
+dependency "un-ukr-Cyrl-Latn-2012" as cyrllatn
+
+
+stage main {
+
+  run  map.cyrllatn.stage.main
+
+  # CHARACTERS
+  parallel {
+    sub "'" ""
+  }
+
+}
+}