interscript-maps 2.0.5

data/maps/bgnpcgn-mkd-Cyrl-Latn-1981.imp

@@ -0,0 +1,132 @@
+metadata {
+  authority_id: bgnpcgn
+  id: 1981
+  language: iso-639-2:mkd
+  source_script: Cyrl
+  destination_script: Latn
+  name: Makedonian Romanization, BGN/PCGN 1981 System
+  url: https://github.com/riboseinc/interscript/files/4247920/USBGN_romanization_Macedonian_1981.pdf
+  creation_date: 1981
+  description: BGN/PCGN Romanization table for Makedonian.
+
+  notes:
+    - The character ѓ should be romanized g when it occurs before е and и. In other
+      instances, it should be romanized ǵ (Ǵ).
+    - The character ќ should be romanized k when it occurs before е and и. In other
+      instances, it should be romanized ć.
+}
+
+tests {
+  test "Ѓол", "Đol"
+  test "Јусек Тепеси", "Jusek Tepesi"
+  test "Љуги Ќарит", "Ljugi Ćarit"
+  test "Ќафа Сан", "Ćafa San"
+  test "Агроплод Ресен", "Agroplod Resen"
+  test "Алта Чука", "Alta Čuka"
+  test "Баш Тепе", "Baš Tepe"
+  test "Браќам", "Braćam"
+  test "Винарска Визба Агропин", "Vinarska Vizba Agropin"
+  test "Галичица", "Galičica"
+  test "Дрењево", "Drenjevo"
+  test "Енешево", "Eneševo"
+  test "Иберлија", "Iberlija"
+  test "Крмзи Су", "Krmzi Su"
+  test "Лесноски Рид", "Lesnoski Rid"
+  test "Мала Корабска Врата", "Mala Korabska Vrata"
+  test "Низок Врв", "Nizok Vrv"
+  test "Охридско Езеро", "Ohridsko Ezero"
+  test "Прлиќ", "Prlić"
+  test "Равна Гора", "Ravna Gora"
+  test "Сеѓавечкиот Рид", "Seđavečkiot Rid"
+  test "Трновите Њиве", "Trnovite Njive"
+  test "Фасов Рид", "Fasov Rid"
+  test "Црни Камен", "Crni Kamen"
+  test "Чатал Чешми", "Čatal Češmi"
+  test "Шехово", "Šehovo"
+}
+
+dependency "var-Cyrl", import: true
+
+stage {
+
+  # RULES
+  sub "Ѓ", "G", after: "еЕиИ"
+  sub "ѓ", "g", after: "еЕиИ"
+  sub "Ќ", "K", after: "еЕиИ"
+  sub "ќ", "k", after: "еЕиИ"
+  # Those aren't tested.
+
+
+  # CHARACTERS
+  parallel {
+    sub "А", "A"
+    sub "Б", "B"
+    sub "В", "V"
+    sub "Г", "G"
+    sub "Д", "D"
+    sub "Ѓ", "Đ" # Đ
+    sub "Е", "E"
+    sub "Ж", "Ž" # Ž
+    sub "З", "Z"
+    sub "Ѕ", "Dz"
+    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 "Ќ", "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 "ѓ", "đ" # đ
+    sub "е", "e"
+    sub "ж", "ž" # ž
+    sub "з", "z"
+    sub "ѕ", "dz"
+    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 "ќ", "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
+  }
+
+  # POSTRULES
+  sub any(["Dz", "Lj", "Nj", "Dž"]), upcase, before: any("A".."Z")
+  sub any(["Dz", "Lj", "Nj", "Dž"]), upcase, after: any("A".."Z")
+  # Those aren't tested
+
+  compose
+}

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

@@ -0,0 +1,174 @@
+metadata {
+  authority_id: bgnpcgn
+  id: 2013
+  language: iso-639-2:mkd
+  source_script: Cyrl
+  destination_script: Latn
+  name: Makedonian Romanization, BGN/PCGN 2013 System
+  url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/811514/ROMANIZATION_OF_MACEDONIAN.pdf
+  creation_date: 2013
+  description: |
+    Macedonian was officially established as a written language in Yugoslavia during
+    World War II and is now the official language of North Macedonia.
+    This romanization system replaces the BGN/PCGN 1981 agreement and adheres
+    to the most widely-accepted standardization of Macedonian orthography.
+
+  notes:
+    - The Macedonian 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 Macedonian Cyrillic lowercase italic Ѓ may sometimes be seen as ī.
+      There is no specific Unicode encoding for this variant form so a comparable character
+      has been used here for illustrative purposes.
+    - The Macedonian Cyrillic lowercase italic П may sometimes be seen as ū.
+      There is no specific Unicode encoding for this variant form so a comparable character
+      has been used here for illustrative purposes.
+    - The Macedonian Cyrillic lowercase italic Т may sometimes be seen as w̄.
+      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:
+      | Ǵ (U+01F4)   | ǵ (U+01F5)   |
+      | Ž (U+017D)   | ž (U+017E)   |
+      | Dz (U+01F2)* | dz (U+01F3)* |
+      | Lj (U+01C8)* | lj (U+01C9)* |
+      | Nj (U+01CB)* | nj(U+01CC)*  |
+      | Ḱ (U+IE30)   | ḱ (U+IE31)   |
+      | Č (U+010C)   | č (U+010D)   |
+      | 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 Romanization column shows only lowercase forms but, when romanizing,
+      uppercase and lowercase Roman letters as appropriate should be used.
+}
+
+tests {
+  test "Ѓенови Ливаѓе", "Ǵenovi Livaǵe"
+  test "ЛУЃЕ луѓе", "LUǴE luǵe"
+  test "ЅВЕЗДА ѕвезда Ѕвезда", "DZVEZDA dzvezda Dzvezda"
+  test "Јабежица", "Jabežica"
+  test "Љиќен и Бард", "Ljiḱen i Bard"
+  test "Ќамилов Чукар", "Ḱamilov Čukar"
+  test "Џавидин Кајнак", "Džavidin Kajnak"
+  test "Џамалџи", "Džamaldži"
+  test "Џибра Гури и Зи", "Džibra Guri i Zi"
+  test "Абазова Куќарица", "Abazova Kuḱarica"
+  test "Баба Анѓина Маала", "Baba Anǵina Maala"
+  test "Ваљановец", "Valjanovec"
+  test "Галал Једи Дереш", "Galal Jedi Dereš"
+  test "Дванаесет Клајнци", "Dvanaeset Klajnci"
+  test "Електродистрибуција Струга", "Elektrodistribucija Struga"
+  test "Железничка Станица Рајко Жинзифов", "Železnička Stanica Rajko Žinzifov"
+  test "Заедничко Речиште", "Zaedničko Rečište"
+  test "Испраена Плоча", "Ispraena Ploča"
+  test "Казнено-Поправна Установа Идризово", "Kazneno-Popravna Ustanova Idrizovo"
+  test "Лази и Зејнелит", "Lazi i Zejnelit"
+  test "Мавровско Езеро", "Mavrovsko Ezero"
+  test "Национален Парк Галичица", "Nacionalen Park Galičica"
+  test "Одморалиште Свети Стефан", "Odmoralište Sveti Stefan"
+  test "Планинарски Дом Караџица", "Planinarski Dom Karadžica"
+  test "Раса е Лисењит", "Rasa e Lisenjit"
+  test "Скочивирска Клисура", "Skočivirska Klisura"
+  test "Термо-електроцентрала Неготино", "Termo-elektrocentrala Negotino"
+  test "Узуновско Бресје", "Uzunovsko Bresje"
+  test "Фабрика Југохром", "Fabrika Jugohrom"
+  test "Хидроелектрана Сапунџица", "Hidroelektrana Sapundžica"
+  test "Цветковско Рамниште", "Cvetkovsko Ramnište"
+  test "Чалтанова Пештера", "Čaltanova Peštera"
+  test "Шкемби Вишнејц", "Škembi Višnejc"
+}
+
+dependency "posix", import: true
+
+stage {
+
+
+
+  # CHARACTERS
+  parallel {
+    sub "А", "A"
+    sub "Б", "B"
+    sub "В", "V"
+    sub "Г", "G"
+    sub "Д", "D"
+    sub "Ѓ", "Ǵ" # Ǵ
+    sub "Е", "E"
+    sub "Ж", "Ž" # Ž
+    sub "З", "Z"
+    sub "Ѕ", "Dz"
+    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 "Ќ", "Ḱ" # Ḱ
+    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 "ѓ", "ǵ" # ǵ
+    sub "е", "e"
+    sub "ж", "ž" # ž
+    sub "з", "z"
+    sub "ѕ", "dz"
+    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 "ќ", "ḱ" # ḱ
+    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
+  # rewritten by hand to work properly
+  # DZ
+  sub capture(maybe(upper)) + "Dz" + capture(upper), ref(1) + "DZ" + ref(2)
+  sub capture(upper) + "Dz" +  capture(maybe(upper)), ref(1) + "DZ" + ref(2)
+
+  #LJ
+  sub capture(upper) + "Lj" + capture(maybe(upper)), ref(1) + "LJ" + ref(2)
+  sub capture(maybe(upper)) + "Lj" + capture(upper), ref(1) + "LJ" + ref(2)
+
+  #NJ
+  sub capture(upper) + "Nj" + capture(maybe(upper)), ref(1) + "NJ" + ref(2)
+  sub capture(maybe(upper)) + "Nj" + capture(upper), ref(1) + "NJ" + ref(2)
+
+  #DŽ
+  sub capture(upper) + "Dž" + capture(maybe(upper)), ref(1) + "DŽ" + ref(2)
+  sub capture(maybe(upper)) + "Dž" + capture(upper), ref(1) + "DŽ" + ref(2)
+
+  compose
+
+}
+

data/maps/bgnpcgn-mon-Cyrl-Latn-1964.imp

@@ -0,0 +1,168 @@
+metadata {
+  authority_id: bgnpcgn
+  id: 1964
+  language: iso-639-2:mon
+  source_script: Cyrl
+  destination_script: Latn
+  name: BGN/PCGN 1964 System
+  url: https://github.com/interscript/interscript/files/5180767/BGN_Romanization_Guide_1964_mongolian_1964.pdf
+  creation_date:
+  confirmation_date:
+  description: |
+    This system was originated by the PCGN in 1957 and adopted as a
+    BGN/PCGN System in 1964. It is intended for use in the romanization of
+    geographic names in the "Mongolian People's Republic" but not to romanize
+    Mongolian names in adjacent parts of China and the U.S.S.R.
+
+  notes: |
+    - b occurs initially and after л, м, and б.
+    - v occurs medially in Mongolian words and initially in foreign words.
+    - y occurs only as the second element of diphthongs.
+    - k, p, f, and shch occurs foreign words only.
+    - "\u2019" occurs only in Russion words.
+    - ï occurs only in suffixes to words containing back vowels (a, o, and u).
+    - In monosyllables yu or yü depending on pronunciation; in polysyllables yu when followed by a, o, or u, but yü when followed by i, e, ö, or ü.
+}
+
+tests {
+  test "Эрдэнэт Сум", "Erdenet Sum"
+  test "Эрдэнэт", "Erdenet"
+  test "Эрдэнэ", "Erdene"
+  test "Шивээговь Сум", "Shiveegovĭ Sum"
+  test "Шивээговь", "Shiveegovĭ"
+  test "Шарынгол Сум", "Sharïngol Sum"
+  test "Шарынгол", "Sharïngol"
+  test "Цагааннуур", "Tsagaannuur"
+  test "Хонгор Сум", "Hongor Sum"
+  test "Хонгор", "Hongor"
+  test "Хайлаастай", "Haylaastay"
+  test "Түнэл Сум", "Tünel Sum"
+  test "Түнэл", "Tünel"
+  test "Сүхбаатар", "Sühbaatar"
+  test "Сүмбэр Сум", "Sümber Sum"
+  test "Сүмбэр", "Sümber"
+  test "Сайншанд Сум", "Saynshand Sum"
+  test "Сайншанд", "Saynshand"
+  test "Орхон Сум", "Orhon Sum"
+  test "Орхон", "Orhon"
+  test "Нарст", "Narst"
+  test "Мөрөн Сум", "Mörön Sum"
+  test "Мөрөн", "Mörön"
+  test "Зүүнхөвөө", "Dzüünhövöö"
+  test "Жаргалант Сум", "Jargalant Sum"
+  test "Жаргалант", "Jargalant"
+  test "Дархан Сум", "Darhan Sum"
+  test "Даланзадгад Сум", "Dalandzadgad Sum"
+  test "Даланзадгад", "Dalandzadgad"
+  test "Давст Сум", "Davst Sum"
+  test "Давст", "Davst"
+  test "Говьсүмбэр Сум", "Govĭsümber Sum"
+  test "Говь", "Govĭ"
+  test "Буга", "Buga"
+  test "Бор-Өндөр Сум", "Bor-Öndör Sum"
+  test "Бор-Өндөр", "Bor-Öndör"
+  test "Баянхонгор", "Bayanhongor"
+  test "Баянтал", "Bayantal"
+  test "Баяндэлгэр Сум", "Bayandelger Sum"
+  test "Баяндэлгэр", "Bayandelger"
+  test "Баян-Өндөр Сум", "Bayan-Öndör Sum"
+  test "Баруун-Урт Сум", "Baruun-Urt Sum"
+  test "Баруун-Урт", "Baruun-Urt"
+  test "Архуст", "Arhust"
+  test "Арвайхээр Сум", "Arvayheer Sum"
+  test "Арвайхээр", "Arvayheer"
+  test "Есөнбулаг Сум", "Yösönbulag Sum"
+  test "Ерөө Сум", "Yöröö Sum"
+  test "Есөнзүйл Сум", "Yösöndzüyl Sum"
+  test "Ноён Сум", "Noyon Sum"
+  test "Родник Балянгийн-Булак", "Rodnik Balyangiyn-Bulak"
+  test "Замын-Үүд Сум", "Dzamïn-Üüd Sum"
+  test "Адаацаг Сум", "Adaatsag Sum"
+  test "Чандмань Сум", "Chandmanĭ Sum"
+  test "Хяргас Сум", "Hyargas Sum"
+}
+
+stage {
+
+  # RULES
+  sub "\u042e", "Yu", after: any("АаОоУу") # Ю before а, о, or у
+  sub "\u044e", "yu", after: any("АаОоУу") # ю before а, о, or у
+  sub "\u042e", "Yü", after: any("ИиЭэӨөҮү") # Ю before и, э, ө, or ү
+  sub "\u044e", "yü", after: any("ИиЭэӨөҮү") # ю before и, э, ө, or ү
+
+
+  # CHARACTERS
+  parallel {
+    sub "А", "A" # \u0410
+    sub "Б", "B" # \u0411
+    sub "В", "V" # \u0412
+    sub "Г", "G" # \u0413
+    sub "Д", "D" # \u0414
+    sub "Е", "Yö" # \u0415
+    sub "Ё", "Yo" # \u0401
+    sub "Ж", "J" # \u0416
+    sub "З", "Dz" # \u0417
+    sub "И", "I" # \u0418
+    sub "Й", "Y" # \u0419
+    sub "К", "K" # \u041a
+    sub "Л", "L" # \u041b
+    sub "М", "M" # \u041c
+    sub "Н", "N" # \u041d
+    sub "О", "O" # \u041e
+    sub "Ө", "Ö" # \u04e8
+    sub "П", "P" # \u041f
+    sub "Р", "R" # \u0420
+    sub "С", "S" # \u0421
+    sub "Т", "T" # \u0422
+    sub "У", "U" # \u0423
+    sub "Ү", "Ü" # \u04ae
+    sub "Ф", "F" # \u0424
+    sub "Х", "H" # \u0425
+    sub "Ц", "Ts" # \u0426
+    sub "Ч", "Ch" # \u0427
+    sub "Ш", "Sh" # \u0428
+    sub "Щ", "Shch" # \u0429
+    sub "Ъ", "’" # \u042a
+    sub "Ы", "Ï" # \u042b
+    sub "Ь", "Ĭ" # \u042c
+    sub "Э", "E" # \u042d
+    sub "Ю", "Yu" # \u042e
+    sub "Я", "Ya" # \u042f
+    sub "а", "a" # \u0430
+    sub "б", "b" # \u0431
+    sub "в", "v" # \u0432
+    sub "г", "g" # \u0433
+    sub "д", "d" # \u0434
+    sub "е", "yö" # \u0435
+    sub "ё", "yo" # \u0451
+    sub "ж", "j" # \u0436
+    sub "з", "dz" # \u0437
+    sub "и", "i" # \u0438
+    sub "й", "y" # \u0439
+    sub "к", "k" # \u043a
+    sub "л", "l" # \u043b
+    sub "м", "m" # \u043c
+    sub "н", "n" # \u043d
+    sub "о", "o" # \u043e
+    sub "ө", "ö" # \u04e9
+    sub "п", "p" # \u043f
+    sub "р", "r" # \u0440
+    sub "с", "s" # \u0441
+    sub "т", "t" # \u0442
+    sub "у", "u" # \u0443
+    sub "ү", "ü" # \u04af
+    sub "ф", "f" # \u0444
+    sub "х", "h" # \u0445
+    sub "ц", "ts" # \u0446
+    sub "ч", "ch" # \u0447
+    sub "ш", "sh" # \u0448
+    sub "щ", "shch" # \u0449
+    sub "ъ", "’" # \u044a
+    sub "ы", "ï" # \u044b
+    sub "ь", "ĭ" # \u044c
+    sub "э", "e" # \u044d
+    sub "ю", "yu" # \u044e
+    sub "я", "ya" # \u044f
+  }
+
+}