interscript 0.1.9 → 2.0.5

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

@@ -1,163 +0,0 @@
----
-authority_id: bgnpcgn
-id: 1981
-language: iso-639-2:mkd
-source_script: Cyrl
-destination_script: Latn
-name: Makedonian Romanization, BGN/PCGN 1981 System
-alias:
-  ogc11122:
-    code: mkd_Cyrl2Latn_BGN_1981
-    description: Macedonian US Board on Geographic Names(BGN)/Permanent Committee on Geographical Names for British Official Use(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.
-
-tests:
-  - source: Ѓол
-    expected: Đol
-  - source: Јусек Тепеси
-    expected: Jusek Tepesi
-  - source: Љуги Ќарит
-    expected: Ljugi Ćarit
-  - source: Ќафа Сан
-    expected: Ćafa San
-  - source: Агроплод Ресен
-    expected: Agroplod Resen
-  - source: Алта Чука
-    expected: Alta Čuka
-  - source: Баш Тепе
-    expected: Baš Tepe
-  - source: Браќам
-    expected: Braćam
-  - source: Винарска Визба Агропин
-    expected: Vinarska Vizba Agropin
-  - source: Галичица
-    expected: Galičica
-  - source: Дрењево
-    expected: Drenjevo
-  - source: Енешево
-    expected: Eneševo
-  - source: Иберлија
-    expected: Iberlija
-  - source: Крмзи Су
-    expected: Krmzi Su
-  - source: Лесноски Рид
-    expected: Lesnoski Rid
-  - source: Мала Корабска Врата
-    expected: Mala Korabska Vrata
-  - source: Низок Врв
-    expected: Nizok Vrv
-  - source: Охридско Езеро
-    expected: Ohridsko Ezero
-  - source: Прлиќ
-    expected: Prlić
-  - source: Равна Гора
-    expected: Ravna Gora
-  - source: Сеѓавечкиот Рид
-    expected: Seđavečkiot Rid
-  - source: Трновите Њиве
-    expected: Trnovite Njive
-  - source: Фасов Рид
-    expected: Fasov Rid
-  - source: Црни Камен
-    expected: Crni Kamen
-  - source: Чатал Чешми
-    expected: Čatal Češmi
-  - source: Шехово
-    expected: Šehovo
-
-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.
-
-map:
-  rules:
-    - pattern: "Ѓ(?=[еЕиИ])"
-      result: "G"
-    - pattern: "ѓ(?=[еЕиИ])"
-      result: "g"
-    - pattern: "Ќ(?=[еЕиИ])"
-      result: "K"
-    - pattern: "ќ(?=[еЕиИ])"
-      result: "k"
-
-  postrules:
-    # DZ
-    - pattern: "((?<=[[:upper:]])Dz(?=[[:upper:]])?|(?<=[[:upper:]])?Dz(?=[[:upper:]]))"
-      result: "DZ"
-    #LJ
-    - pattern: "((?<=[[:upper:]])Lj(?=[[:upper:]])?|(?<=[[:upper:]])?Lj(?=[[:upper:]]))"
-      result: "LJ"
-    #NJ
-    - pattern: "((?<=[[:upper:]])Nj(?=[[:upper:]])?|(?<=[[:upper:]])?Nj(?=[[:upper:]]))"
-      result: "NJ"
-    #DŽ
-    - pattern: "((?<=[[:upper:]])Dž(?=[[:upper:]])?|(?<=[[:upper:]])?Dž(?=[[:upper:]]))"
-      result: "DŽ"
-
-  characters:
-    "\u0410": "A"
-    "\u0411": "B"
-    "\u0412": "V"
-    "\u0413": "G"
-    "\u0414": "D"
-    "\u0403": "\u0110" # Đ
-    "\u0415": "E"
-    "\u0416": "\u005a\u030c" # Ž
-    "\u0417": "Z"
-    "\u0405": "Dz"
-    "\u0418": "I"
-    "\u0408": "J"
-    "\u041A": "K"
-    "\u041B": "L"
-    "\u0409": "Lj"
-    "\u041C": "M"
-    "\u041D": "N"
-    "\u040A": "Nj"
-    "\u041E": "O"
-    "\u041F": "P"
-    "\u0420": "R"
-    "\u0421": "S"
-    "\u0422": "T"
-    "\u040c": "\u0106" # Ć
-    "\u0423": "U"
-    "\u0424": "F"
-    "\u0425": "H"
-    "\u0426": "C"
-    "\u0427": "\u0043\u030c" # Č
-    "\u040F": "D\u007a\u030c" # Dž
-    "\u0428": "\u0053\u030c" # Š
-    "\u0430": "a"
-    "\u0431": "b"
-    "\u0432": "v"
-    "\u0433": "g"
-    "\u0434": "d"
-    "\u0453": "\u0111" # đ
-    "\u0435": "e"
-    "\u0436": "\u007a\u030c" # ž
-    "\u0437": "z"
-    "\u0455": "dz"
-    "\u0438": "i"
-    "\u0458": "j"
-    "\u043A": "k"
-    "\u043B": "l"
-    "\u0459": "lj"
-    "\u043C": "m"
-    "\u043D": "n"
-    "\u045A": "nj"
-    "\u043E": "o"
-    "\u043F": "p"
-    "\u0440": "r"
-    "\u0441": "s"
-    "\u0442": "t"
-    "\u045c": "\u0107" # ć
-    "\u0443": "u"
-    "\u0444": "f"
-    "\u0445": "h"
-    "\u0446": "c"
-    "\u0447": "\u0063\u030c" # č
-    "\u045F": "d\u007a\u030c" # dž
-    "\u0448": "\u0073\u030c" # š

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

@@ -1,190 +0,0 @@
----
-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:
-  - source: Ѓенови Ливаѓе
-    expected: Ǵenovi Livaǵe
-  - source: ЛУЃЕ луѓе
-    expected: LUǴE luǵe
-  - source: ЅВЕЗДА ѕвезда Ѕвезда
-    expected: DZVEZDA dzvezda Dzvezda
-  - source: Јабежица
-    expected: Jabežica
-  - source: Љиќен и Бард
-    expected: Ljiḱen i Bard
-  - source: Ќамилов Чукар
-    expected: Ḱamilov Čukar
-  - source: Џавидин Кајнак
-    expected: Džavidin Kajnak
-  - source: Џамалџи
-    expected: Džamaldži
-  - source: Џибра Гури и Зи
-    expected: Džibra Guri i Zi
-  - source: Абазова Куќарица
-    expected: Abazova Kuḱarica
-  - source: Баба Анѓина Маала
-    expected: Baba Anǵina Maala
-  - source: Ваљановец
-    expected: Valjanovec
-  - source: Галал Једи Дереш
-    expected: Galal Jedi Dereš
-  - source: Дванаесет Клајнци
-    expected: Dvanaeset Klajnci
-  - source: Електродистрибуција Струга
-    expected: Elektrodistribucija Struga
-  - source: Железничка Станица Рајко Жинзифов
-    expected: Železnička Stanica Rajko Žinzifov
-  - source: Заедничко Речиште
-    expected: Zaedničko Rečište
-  - source: Испраена Плоча
-    expected: Ispraena Ploča
-  - source: Казнено-Поправна Установа Идризово
-    expected: Kazneno-Popravna Ustanova Idrizovo
-  - source: Лази и Зејнелит
-    expected: Lazi i Zejnelit
-  - source: Мавровско Езеро
-    expected: Mavrovsko Ezero
-  - source: Национален Парк Галичица
-    expected: Nacionalen Park Galičica
-  - source: Одморалиште Свети Стефан
-    expected: Odmoralište Sveti Stefan
-  - source: Планинарски Дом Караџица
-    expected: Planinarski Dom Karadžica
-  - source: Раса е Лисењит
-    expected: Rasa e Lisenjit
-  - source: Скочивирска Клисура
-    expected: Skočivirska Klisura
-  - source: Термо-електроцентрала Неготино
-    expected: Termo-elektrocentrala Negotino
-  - source: Узуновско Бресје
-    expected: Uzunovsko Bresje
-  - source: Фабрика Југохром
-    expected: Fabrika Jugohrom
-  - source: Хидроелектрана Сапунџица
-    expected: Hidroelektrana Sapundžica
-  - source: Цветковско Рамниште
-    expected: Cvetkovsko Ramnište
-  - source: Чалтанова Пештера
-    expected: Čaltanova Peštera
-  - source: Шкемби Вишнејц
-    expected: Škembi Višnejc
-
-map:
-  postrules:
-    # DZ
-    - pattern: "((?<=[[:upper:]])Dz(?=[[:upper:]])?|(?<=[[:upper:]])?Dz(?=[[:upper:]]))"
-      result: "DZ"
-    #LJ
-    - pattern: "((?<=[[:upper:]])Lj(?=[[:upper:]])?|(?<=[[:upper:]])?Lj(?=[[:upper:]]))"
-      result: "LJ"
-    #NJ
-    - pattern: "((?<=[[:upper:]])Nj(?=[[:upper:]])?|(?<=[[:upper:]])?Nj(?=[[:upper:]]))"
-      result: "NJ"
-    #DŽ
-    - pattern: "((?<=[[:upper:]])Dž(?=[[:upper:]])?|(?<=[[:upper:]])?Dž(?=[[:upper:]]))"
-      result: "DŽ"
-
-  characters:
-    "\u0410": "A"
-    "\u0411": "B"
-    "\u0412": "V"
-    "\u0413": "G"
-    "\u0414": "D"
-    "\u0403": "\u01F4" # Ǵ
-    "\u0415": "E"
-    "\u0416": "\u005a\u030c" # Ž
-    "\u0417": "Z"
-    "\u0405": "Dz"
-    "\u0418": "I"
-    "\u0408": "J"
-    "\u041A": "K"
-    "\u041B": "L"
-    "\u0409": "Lj"
-    "\u041C": "M"
-    "\u041D": "N"
-    "\u040A": "Nj"
-    "\u041E": "O"
-    "\u041F": "P"
-    "\u0420": "R"
-    "\u0421": "S"
-    "\u0422": "T"
-    "\u040C": "\u004b\u0301" # Ḱ
-    "\u0423": "U"
-    "\u0424": "F"
-    "\u0425": "H"
-    "\u0426": "C"
-    "\u0427": "\u0043\u030c" # Č
-    "\u040F": "D\u007a\u030c" # Dž
-    "\u0428": "\u0053\u030c" # Š
-    "\u0430": "a"
-    "\u0431": "b"
-    "\u0432": "v"
-    "\u0433": "g"
-    "\u0434": "d"
-    "\u0453": "\u01F5" # ǵ
-    "\u0435": "e"
-    "\u0436": "\u007a\u030c" # ž
-    "\u0437": "z"
-    "\u0455": "dz"
-    "\u0438": "i"
-    "\u0458": "j"
-    "\u043A": "k"
-    "\u043B": "l"
-    "\u0459": "lj"
-    "\u043C": "m"
-    "\u043D": "n"
-    "\u045A": "nj"
-    "\u043E": "o"
-    "\u043F": "p"
-    "\u0440": "r"
-    "\u0441": "s"
-    "\u0442": "t"
-    "\u045C": "\u1E31" # ḱ
-    "\u0443": "u"
-    "\u0444": "f"
-    "\u0445": "h"
-    "\u0446": "c"
-    "\u0447": "\u0063\u030c" # č
-    "\u045F": "d\u007a\u030c" # dž
-    "\u0448": "\u0073\u030c" # š

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

@@ -1,223 +0,0 @@
----
-authority_id: bgnpcgn
-id: 1964
-language: iso-639-2:mon
-source_script: Cyrl
-destination_script: Latn
-name: BGN/PCGN 1964 System
-alias:
-  ogc11122:
-    code: mon_Cyrl2Latn_BGN_1964
-    description: Mongolian US Board on Geographic Names(BGN)/Permanent Committee on Geographical Names for British Official Use(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:
-  - source: Эрдэнэт Сум
-    expected: Erdenet Sum
-  - source: Эрдэнэт
-    expected: Erdenet
-  - source: Эрдэнэ
-    expected: Erdene
-  - source: Шивээговь Сум
-    expected: Shiveegovĭ Sum
-  - source: Шивээговь
-    expected: Shiveegovĭ
-  - source: Шарынгол Сум
-    expected: Sharïngol Sum
-  - source: Шарынгол
-    expected: Sharïngol
-  - source: Цагааннуур
-    expected: Tsagaannuur
-  - source: Хонгор Сум
-    expected: Hongor Sum
-  - source: Хонгор
-    expected: Hongor
-  - source: Хайлаастай
-    expected: Haylaastay
-  - source: Түнэл Сум
-    expected: Tünel Sum
-  - source: Түнэл
-    expected: Tünel
-  - source: Сүхбаатар
-    expected: Sühbaatar
-  - source: Сүмбэр Сум
-    expected: Sümber Sum
-  - source: Сүмбэр
-    expected: Sümber
-  - source: Сайншанд Сум
-    expected: Saynshand Sum
-  - source: Сайншанд
-    expected: Saynshand
-  - source: Орхон Сум
-    expected: Orhon Sum
-  - source: Орхон
-    expected: Orhon
-  - source: Нарст
-    expected: Narst
-  - source: Мөрөн Сум
-    expected: Mörön Sum
-  - source: Мөрөн
-    expected: Mörön
-  - source: Зүүнхөвөө
-    expected: Dzüünhövöö
-  - source: Жаргалант Сум
-    expected: Jargalant Sum
-  - source: Жаргалант
-    expected: Jargalant
-  - source: Дархан Сум
-    expected: Darhan Sum
-  - source: Даланзадгад Сум
-    expected: Dalandzadgad Sum
-  - source: Даланзадгад
-    expected: Dalandzadgad
-  - source: Давст Сум
-    expected: Davst Sum
-  - source: Давст
-    expected: Davst
-  - source: Говьсүмбэр Сум
-    expected: Govĭsümber Sum
-  - source: Говь
-    expected: Govĭ
-  - source: Буга
-    expected: Buga
-  - source: Бор-Өндөр Сум
-    expected: Bor-Öndör Sum
-  - source: Бор-Өндөр
-    expected: Bor-Öndör
-  - source: Баянхонгор
-    expected: Bayanhongor
-  - source: Баянтал
-    expected: Bayantal
-  - source: Баяндэлгэр Сум
-    expected: Bayandelger Sum
-  - source: Баяндэлгэр
-    expected: Bayandelger
-  - source: Баян-Өндөр Сум
-    expected: Bayan-Öndör Sum
-  - source: Баруун-Урт Сум
-    expected: Baruun-Urt Sum
-  - source: Баруун-Урт
-    expected: Baruun-Urt
-  - source: Архуст
-    expected: Arhust
-  - source: Арвайхээр Сум
-    expected: Arvayheer Sum
-  - source: Арвайхээр
-    expected: Arvayheer
-  - source: Есөнбулаг Сум
-    expected: Yösönbulag Sum
-  - source: Ерөө Сум
-    expected: Yöröö Sum
-  - source: Есөнзүйл Сум
-    expected: Yösöndzüyl Sum
-  - source: Ноён Сум
-    expected: Noyon Sum
-  - source: Родник Балянгийн-Булак
-    expected: Rodnik Balyangiyn-Bulak
-  - source: Замын-Үүд Сум
-    expected: Dzamïn-Üüd Sum
-  - source: Адаацаг Сум
-    expected: Adaatsag Sum
-  - source: Чандмань Сум
-    expected: Chandmanĭ Sum
-  - source: Хяргас Сум
-    expected: Hyargas Sum
-
-map:
-  rules:
-    - pattern: \u042e(?=[АаОоУу]) # Ю before а, о, or у
-      result: "Yu"
-    - pattern: \u044e(?=[АаОоУу]) # ю before а, о, or у
-      result: "yu"
-    - pattern: \u042e(?=[ИиЭэӨөҮү]) # Ю before и, э, ө, or ү
-      result: "Yü"
-    - pattern: \u044e(?=[ИиЭэӨөҮү]) # ю before и, э, ө, or ү
-      result: "yü"
-
-  characters:
-    "А": "A"      # \u0410
-    "Б": "B"      # \u0411
-    "В": "V"      # \u0412
-    "Г": "G"      # \u0413
-    "Д": "D"      # \u0414
-    "Е": "Yö"     # \u0415
-    "Ё": "Yo"     # \u0401
-    "Ж": "J"      # \u0416
-    "З": "Dz"     # \u0417
-    "И": "I"      # \u0418
-    "Й": "Y"      # \u0419
-    "К": "K"      # \u041a
-    "Л": "L"      # \u041b
-    "М": "M"      # \u041c
-    "Н": "N"      # \u041d
-    "О": "O"      # \u041e
-    "Ө": "Ö"      # \u04e8
-    "П": "P"      # \u041f
-    "Р": "R"      # \u0420
-    "С": "S"      # \u0421
-    "Т": "T"      # \u0422
-    "У": "U"      # \u0423
-    "Ү": "Ü"      # \u04ae
-    "Ф": "F"      # \u0424
-    "Х": "H"      # \u0425
-    "Ц": "Ts"     # \u0426
-    "Ч": "Ch"     # \u0427
-    "Ш": "Sh"     # \u0428
-    "Щ": "Shch"   # \u0429
-    "Ъ": "\u2019" # \u042a
-    "Ы": "Ï"      # \u042b
-    "Ь": "Ĭ"      # \u042c
-    "Э": "E"      # \u042d
-    "Ю": "Yu"     # \u042e
-    "Я": "Ya"     # \u042f
-    "а": "a"      # \u0430
-    "б": "b"      # \u0431
-    "в": "v"      # \u0432
-    "г": "g"      # \u0433
-    "д": "d"      # \u0434
-    "е": "yö"     # \u0435
-    "ё": "yo"     # \u0451
-    "ж": "j"      # \u0436
-    "з": "dz"     # \u0437
-    "и": "i"      # \u0438
-    "й": "y"      # \u0439
-    "к": "k"      # \u043a
-    "л": "l"      # \u043b
-    "м": "m"      # \u043c
-    "н": "n"      # \u043d
-    "о": "o"      # \u043e
-    "ө": "ö"      # \u04e9
-    "п": "p"      # \u043f
-    "р": "r"      # \u0440
-    "с": "s"      # \u0441
-    "т": "t"      # \u0442
-    "у": "u"      # \u0443
-    "ү": "ü"      # \u04af
-    "ф": "f"      # \u0444
-    "х": "h"      # \u0445
-    "ц": "ts"     # \u0446
-    "ч": "ch"     # \u0447
-    "ш": "sh"     # \u0448
-    "щ": "shch"   # \u0449
-    "ъ": "\u2019" # \u044a
-    "ы": "ï"      # \u044b
-    "ь": "ĭ"      # \u044c
-    "э": "e"      # \u044d
-    "ю": "yu"     # \u044e
-    "я": "ya"     # \u044f