interscript 0.1.7 → 2.1.0b1

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

@@ -1,166 +0,0 @@
----
-authority_id: bgnpcgn
-id: 1965
-language: iso-639-2:ukr
-source_script: Cyrl
-destination_script: Latn
-name: BGN/PCGN 1965 System
-alias:
-  ogc11122:
-    code: ukr_Cyrl2Latn_BGN_1965
-    description: Ukrainian Board on Geographic Names/Permanent Committee on Geographical Names for British Official Use(PCGN) 1965 System
-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:
-  - 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.
-  - All apostrophes appearing in romanization are Unicode encoding 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:
-  - source: Авдіївська Міськрада
-    expected: Avdiyivs’ka Mis’krada
-  - source: Бабаї
-    expected: Babayi
-  - source: Віленька
-    expected: Vilen’ka
-  - source: Гагарінський Район
-    expected: Haharins’kyy Rayon
-  - source: Довбушева Криниця
-    expected: Dovbusheva Krynytsya
-  - source: Дідівщина
-    expected: Didivshchyna
-  - source: Економічна
-    expected: Ekonomichna
-  - source: Єфросинівка
-    expected: Yefrosynivka
-  - source: Жигуліна Роща
-    expected: Zhyhulina Roshcha
-  - source: Загір’я
-    expected: Zahir”ya
-  - source: З’єднувальний Канал
-    expected: Z”yednuval’nyy Kanal
-  - source: Ивахи
-    expected: Yvakhy
-  - source: Івано-Франківська Міськрада
-    expected: Ivano-Frankivs’ka Mis’krada
-  - source: Їжаківка
-    expected: Yizhakivka
-  - source: Йосиповичі
-    expected: Yosypovychi
-  - source: Кабичівка
-    expected: Kabychivka
-  - source: Лазуровий Провулок
-    expected: Lazurovyy Provulok
-  - source: Мала Сейдеминуха
-    expected: Mala Seydemynukha
-  - source: Нагірний
-    expected: Nahirnyy
-  - source: Овер’янівське Озеро
-    expected: Over”yanivs’ke Ozero
-  - source: Павлопільське Водосховище
-    expected: Pavlopil’s’ke Vodoskhovyshche
-  - source: Приґородний
-    expected: Prygorodnyy
-  - source: Радгосп Правда
-    expected: Radhosp Pravda
-  - source: Садово-Хрустальненський
-    expected: Sadovo-Khrustal’nens’kyy
-  - source: Таратутине
-    expected: Taratutyne
-  - source: Улу-Узень
-    expected: Ulu-Uzen’
-  - source: Христофорівка
-    expected: Khrystoforivka
-  - source: Центральна Вулиця
-    expected: Tsentral’na Vulytsya
-  - source: Чайковичі
-    expected: Chaykovychi
-  - source: Шалаші
-    expected: Shalashi
-  - source: Щербинівка
-    expected: Shcherbynivka
-  - source: Южноукраїнська Міськрада
-    expected: Yuzhnoukrayins’ka Mis’krada
-  - source: Ясениця
-    expected: Yasenytsya
-
-map:
-  rules:
-    - pattern: \b\u2019\b # ’ in the middle of a word -> ”
-      result: "\u201d"
-
-  characters:
-    "\u0430": 'a'
-    "\u0431": 'b'
-    "\u0432": 'v'
-    "\u0433": 'h'
-    "\u0434": 'd'
-    "\u0435": 'e'
-    "\u0436": 'zh'
-    "\u0437": 'z'
-    "\u0438": 'y'
-    "\u0439": 'y'
-    "\u043a": 'k'
-    "\u043b": 'l'
-    "\u043c": 'm'
-    "\u043d": 'n'
-    "\u043e": 'o'
-    "\u043f": 'p'
-    "\u0440": 'r'
-    "\u0441": 's'
-    "\u0442": 't'
-    "\u0443": 'u'
-    "\u0444": 'f'
-    "\u0445": 'kh'
-    "\u0446": 'ts'
-    "\u0447": 'ch'
-    "\u0448": 'sh'
-    "\u0449": 'shch'
-    "\u044c": "\u2019"
-    "\u044e": 'yu'
-    "\u044f": 'ya'
-    "\u0454": 'ye'
-    "\u0456": 'i'
-    "\u0457": 'yi'
-    "\u0491": 'g'
-    "\ufeff": ' '
-    "\u0404": 'Ye'
-    "\u0406": 'I'
-    "\u0407": 'Yi'
-    "\u0410": 'A'
-    "\u0411": 'B'
-    "\u0412": 'V'
-    "\u0413": 'H'
-    "\u0414": 'D'
-    "\u0415": 'E'
-    "\u0416": 'Zh'
-    "\u0417": 'Z'
-    "\u0418": 'Y'
-    "\u0419": 'Y'
-    "\u041a": 'K'
-    "\u041b": 'L'
-    "\u041c": 'M'
-    "\u041d": 'N'
-    "\u041e": 'O'
-    "\u041f": 'P'
-    "\u0420": 'R'
-    "\u0421": 'S'
-    "\u0422": 'T'
-    "\u0423": 'U'
-    "\u0424": 'F'
-    "\u0425": 'Kh'
-    "\u0426": 'Ts'
-    "\u0427": 'Ch'
-    "\u0428": 'Sh'
-    "\u0429": 'Shch'
-    "\u042c": "\u2019"
-    "\u042e": 'Yu'
-    "\u042f": 'Ya'
-    "\u0490": 'G'

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

@@ -1,119 +0,0 @@
----
-authority_id: bgnpcgn
-id: 2019
-language: iso-639-2:ukr
-source_script: Cyrl
-destination_script: Latn
-name: BGN/PCGN 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:
-  - |
-    The 2019 system was adopted by BGN and PCGN after monitoring a good level of implementation
-    of the national system within Ukraine. Note, however, that this system is not recommended for
-    reverse transliteration; take caution when attempting to convert a romanized name back into Ukrainian.
-    This system also lacks the methodology outlined in the 1965 System to provide additional
-    differentiation between digraphs and individual character sequences.
-    For example, unlike the 1965 System, the 2019 System doesn’t differentiate the special character
-    sequences зг, кг, сг, тс, and тсг (previously romanized as z∙h, k∙h, s∙h, t∙s, and ts∙h)
-    from the digraphs zh, kh, sh, ts, and the letter sequence tsh, which are used to render
-    the characters ж, х, ш, ц and the character sequence тш.
-  - To use the keyboard Unicode function, hold ALT and enter in sequence listed in the table.
-  - The character sequence З Г, previously romanized as zh, is romanized zgh under the 2019 system.
-  - These characters differ significantly in romanization from the BGN/PCGN 1965 system.
-
-tests:
-  - source: Алушта
-    expected: Alushta
-  - source: Борщагівка
-    expected: Borshchahivka
-  - source: Вишгород
-    expected: Vyshhorod
-  - source: Гадяч
-    expected: Hadiach
-  - source: Згорани
-    expected: Zghorany
-  - source: Ґалаґан
-    expected: Galagan
-  - source: Дон
-    expected: Don
-  - source: Рівне
-    expected: Rivne
-  - source: Єнакієве
-    expected: Yenakiieve
-  - source: Наєнко
-    expected: Naienko
-  - source: Житомир
-    expected: Zhytomyr
-  - source: Запоріжжя
-    expected: Zaporizhzhia
-  - source: Закарпаття
-    expected: Zakarpattia
-  - source: Медвин
-    expected: Medvyn
-  - source: Іршава
-    expected: Irshava
-  - source: Їжакевич
-    expected: Yizhakevych
-  - source: Кадіївка
-    expected: Kadiivka
-  - source: Йосипівка
-    expected: Yosypivka
-  - source: Стрий
-    expected: Stryi
-  - source: Київ
-    expected: Kyiv
-  - source: Лебедин
-    expected: Lebedyn
-  - source: Миколаїв
-    expected: Mykolaiv
-  - source: Ніжин
-    expected: Nizhyn
-  - source: Одеса
-    expected: Odesa
-  - source: Полтава
-    expected: Poltava
-  - source: Ромни
-    expected: Romny
-  - source: Суми
-    expected: Sumy
-  - source: Тетерів
-    expected: Teteriv
-  - source: Ужгород
-    expected: Uzhhorod
-  - source: Фастів
-    expected: Fastiv
-  - source: Харків
-    expected: Kharkiv
-  - source: Біла Церква
-    expected: Bila Tserkva
-  - source: Чернівці
-    expected: Chernivtsi
-  - source: Шостка
-    expected: Shostka
-  - source: Гоща
-    expected: Hoshcha
-  - source: Русь
-    expected: Rus
-  - source: Юрій
-    expected: Yurii
-  - source: Крюківка
-    expected: Kriukivka
-  - source: Яготин
-    expected: Yahotyn
-  - source: Ічня
-    expected: Ichnia
-  - source: Знам’янка
-    expected: Znamianka
-
-map:
-  inherit: un-ukr-Cyrl-Latn-2012
-
-  characters:
-    "\u0027": ''     # ' ->

data/maps/bgnpcgn-uzb-Cyrl-Latn-1979.yaml

@@ -1,127 +0,0 @@
----
-authority_id: bgnpcgn
-id: 1979
-language: iso-639-2:uzb
-source_script: Cyrl
-destination_script: Latn
-name: BGN/PCGN Romanization System -- Uzbek Cyrillic (1979)
-url: http://transliteration.eki.ee/pdf/Uzbek.pdf
-creation_date: 1979
-
-notes:
-  - At the beginning of a syllable, after a vowel, ъ or ь.
-
-tests:
-  # https://ru.wikipedia.org/wiki/Узбекский_язык
-  - source: Ўзбек ёзуви
-    expected: Ŭzbek yozuwi
-  - source: Ўзбек тили
-    expected: Ŭzbek tili
-  - source: катта
-    expected: katta
-  - source: куп
-    expected: kup
-  - source: кальта
-    expected: kalʼta
-  - source: Бори элға яхшилик қилғилки, мундин яхши йўқ Ким, дегайлар даҳр аро қолди фалондин яхшилик
-    expected: Bori elgha yakhshilik qilghilki, mundin yakhshi yŭq Kim, degaylar dahr aro qoldi falondin yakhshilik
-  - source: Бахр ул-худо
-    expected: Bakhr ul-khudo
-  - source: Рисале-йи маариф-и Шейбани
-    expected: Risale-yi maarif-i Sheybani
-  - source: Карами Хакка нихоят йукдур
-    expected: Karami Khakka nikhoyat yukdur
-  - source: Йахши
-    expected: Yakhshi
-  - source: Тутук белгись
-    expected: Tutuk belgisʼ
-  - source: |
-      Барча одамлар эркин, қадр-қиммат ва ҳуқуқларда тенг бўлиб туғиладилар.
-      Улар ақл ва виждон соҳибидирлар ва бир-бирлари ила биродарларча муомала қилишлари зарур.
-    expected: |
-      Barcha odamlar erkin, qadr-qimmat wa huquqlarda teng bŭlib tughiladilar.
-      Ular aql wa wizhdon sohibidirlar wa bir-birlari ila birodarlarcha muomala qilishlari zarur.
-  - source: ПАПАПАЧУКА Респект!
-    expected: PAPAPACHUKA Respekt!
-
-map:
-  rules:
-    # note[1]
-    - pattern: (?<=[АаЕеЁёИиОоУуЭэЮюЯяЪъЬь])\u0415
-      result: Ye
-    - pattern: (?<=[АаЕеЁёИиОоУуЭэЮюЯяЪъЬь])\u0435
-      result: ye
-
-  characters:
-    '\u0410': 'A'        # А
-    '\u0411': 'B'        # Б
-    '\u0412': 'W'        # В
-    '\u0413': 'G'        # Г
-    '\u0492': 'Gh'       # Ғ
-    '\u0414': 'D'        # Д
-    '\u0415': 'E'        # Е
-    '\u0401': 'Yo'       # Ё
-    '\u0416': 'Zh'       # Ж
-    '\u0417': 'Z'        # З
-    '\u0418': 'I'        # И
-    '\u0419': 'Y'        # Й
-    '\u041A': 'K'        # К
-    '\u049A': 'Q'        # Қ
-    '\u041B': 'L'        # Л
-    '\u041C': 'M'        # М
-    '\u041D': 'N'        # Н
-    '\u041E': 'O'        # О
-    '\u041F': 'P'        # П
-    '\u0420': 'R'        # Р
-    '\u0421': 'S'        # С
-    '\u0422': 'T'        # Т
-    '\u0423': 'U'        # У
-    '\u040E': 'Ŭ'        # Ў
-    '\u0424': 'F'        # Ф
-    '\u0425': 'Kh'       # Х
-    '\u04B2': 'H'        # Ҳ
-    '\u0426': 'Ts'       # Ц
-    '\u0427': 'Ch'       # Ч
-    '\u0428': 'Sh'       # Ш
-    '\u042a': "\u02BC"   # Ъ
-    '\u042c': "\u02BC"   # Ь
-    '\u042D': 'E'        # Э
-    '\u042E': 'Yu'       # Ю
-    '\u042F': 'Ya'       # Я
-
-    '\u0430': 'a'        # а
-    '\u0431': 'b'        # б
-    '\u0432': 'w'        # в
-    '\u0433': 'g'        # г
-    '\u0493': 'gh'       # ғ
-    '\u0434': 'd'        # д
-    '\u0435': 'e'        # e
-    '\u0451': 'yo'       # ё
-    '\u0436': 'zh'       # ж
-    '\u0437': 'z'        # з
-    '\u0438': 'i'        # и
-    '\u0439': 'y'        # й
-    '\u043A': 'k'        # к
-    '\u049B': 'q'        # қ
-    '\u043B': 'l'        # л
-    '\u043C': 'm'        # м
-    '\u043D': 'n'        # н
-    '\u043E': 'o'        # о
-    '\u043F': 'p'        # п
-    '\u0440': 'r'        # р
-    '\u0441': 's'        # с
-    '\u0442': 't'        # т
-    '\u0443': 'u'        # у
-    '\u045E': 'ŭ'        # ў
-    '\u0444': 'f'        # ф
-    '\u0445': 'kh'       # х
-    '\u04B3': 'h'        # ҳ
-    '\u0446': 'ts'       # ц
-    '\u0447': 'ch'       # ч
-    '\u0448': 'sh'       # ш
-    '\u044a': "\u02BC"   # ъ
-    '\u044c': "\u02BC"   # ь
-    '\u044D': 'e'        # э
-    '\u044F': 'ya'       # я
-    '\u044E': 'yu'       # ю
-

data/maps/bgnpcgn-uzb-Cyrl-Latn-2000.yaml

@@ -1,82 +0,0 @@
----
-authority_id: bgnpcgn
-id: 2000
-language: iso-639-2:uzb
-source_script: Cyrl
-destination_script: Latn
-name: TABLE OF CORRESPONDENCES CYRILLIC - ROMAN BGN/PCGN 2000 Agreement
-description: |
-  In 1995, the Uzbek 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 Uzbek Roman-alphabet spellings are not available, this table can be used to
-  convert Uzbek Cyrillic spellings. This table of correspondences supersedes the BGN/PCGN 1979 romanization
-  system for Uzbek.
-url: http://transliteration.eki.ee/pdf/Uzbek.pdf
-creation_date: 2000
-confirmation_date: 2017-11
-
-notes:
-  - The letter sequence ye is used initially, after the vowel characters 1, 6, 7, 10, 16, 21, 29, 30, 31, and 32, and after characters 11 and 28.
-  - The Unicode encoding of the apostrophe appearing in rows 27 and 28 is U+2019. The inverted apostrophe appearing in rows 32 (o‘) and 34 (g‘) is U+2018.
-  - The Roman-script columns show only lowercase forms but, when applying the table, uppercase and lowercase Roman letters as appropriate should be used.
-
-tests:
-  # https://ru.wikipedia.org/wiki/Узбекский_язык
-  - source: Ўзбек ёзуви
-    expected: O‘zbek yozuwi
-  - source: Ўзбек тили
-    expected: O‘zbek tili
-  - source: катта
-    expected: katta
-  - source: куп
-    expected: kup
-  - source: кальта
-    expected: kal’ta
-  - source: Бори элға яхшилик қилғилки, мундин яхши йўқ Ким, дегайлар даҳр аро қолди фалондин яхшилик
-    expected: Bori elg‘a yaxshilik qilg‘ilki, mundin yaxshi yo‘q Kim, degaylar dahr aro qoldi falondin yaxshilik
-  - source: Бахр ул-худо
-    expected: Baxr ul-xudo
-  - source: Рисале-йи маариф-и Шейбани
-    expected: Risale-yi maarif-i Sheybani
-  - source: Карами Хакка нихоят йукдур
-    expected: Karami Xakka nixoyat yukdur
-  - source: Йахши
-    expected: Yaxshi
-  - source: Тутук белгись
-    expected: Tutuk belgis’
-  - source: |
-      Барча одамлар эркин, қадр-қиммат ва ҳуқуқларда тенг бўлиб туғиладилар.
-      Улар ақл ва виждон соҳибидирлар ва бир-бирлари ила биродарларча муомала қилишлари зарур.
-    expected: |
-      Barcha odamlar erkin, qadr-qimmat wa huquqlarda teng bo‘lib tug‘iladilar.
-      Ular aql wa wijdon sohibidirlar wa bir-birlari ila birodarlarcha muomala qilishlari zarur.
-  - source: ПАПАПАЧУКА Респект!
-    expected: PAPAPACHUKA Respekt!
-
-map:
-  inherit: bgnpcgn-uzb-Cyrl-Latn-1979
-
-  rules:
-    # note[1]
-    - pattern: (?<=[АаЕеЁёИиОоУуЭэЮюЯяЙйЬь])\u0415
-      result: Ye
-    - pattern: (?<=[АаЕеЁёИиОоУуЭэЮюЯяЙйЬь])\u0435
-      result: ye
-
-  characters:
-    '\u0412': 'V'        # В
-    '\u0492': "G\u2018"  # Ғ
-    '\u0416': 'J'        # Ж
-    '\u040E': "O\u2018"  # Ў
-    '\u0425': 'X'        # Х
-    '\u042a': "\u2019"   # Ъ note[2]
-    '\u042c': "\u2019"   # Ь note[2]
-
-    '\u0432': 'w'        # в
-    '\u0493': "g\u2018"  # ғ
-    '\u0436': 'j'        # ж
-    '\u045E': "o\u2018"  # ў
-    '\u0445': 'x'        # х
-    '\u044a': "\u2019"   # ъ note[2]
-    '\u044c': "\u2019"   # ь note[2]
-