interscript 0.1.0 → 0.1.5

data/maps/elot-ell-Grek-Latn-743-2001-tl.yaml

@@ -0,0 +1,20 @@
+---
+authority_id: elot
+id: 2001
+language: ell
+source_script: Grek
+destination_script: Latn
+name: ELOT 743:2001
+url: https://docplayer.gr/docview/18/849832/#file=/storage/18/849832/849832.pdf
+creation_date: 2001
+description: |
+  Reversible transliteration standard, ELOT
+
+note:
+  - Transliteration standard (reversible): Clause 3.1, Table 1
+
+map:
+  character_separator: ""
+  word_separator: " "
+  inherit: "iso-ell-Grek-Latn-843-1997-t1"
+

data/maps/elot-ell-Grek-Latn-743-2001-ts.yaml

@@ -0,0 +1,32 @@
+---
+authority_id: elot
+id: 2001
+language: ell
+source_script: Grek
+destination_script: Latn
+name: ELOT 743:2001
+url: https://docplayer.gr/docview/18/849832/#file=/storage/18/849832/849832.pdf
+creation_date: 2001
+description: |
+  Reversible transliteration standard, ELOT
+
+note:
+  - Transcription standard (reversible): Clause 3.1, Table 2
+
+tests:
+
+  - source: |
+        Ένα πράμα μόνον με παρακίνησε κι εμένα να γράψω ότι τούτην την πατρίδα την έχομεν όλοι μαζί, και σοφοί κι αμαθείς και πλούσιοι και φτωχοί και πολιτικοί και στρατιωτικοί και οι πλέον μικρότεροι άνθρωποι· όσοι αγωνιστήκαμεν, αναλόγως ο καθείς, έχομεν να ζήσομεν εδώ. Το λοιπόν δουλέψαμεν όλοι μαζί, να την φυλάμεν κι όλοι μαζί και να μην λέγει ούτε ο δυνατός «εγώ» ούτε ο αδύνατος. Ξέρετε πότε να λέγει ο καθείς «εγώ»; Όταν αγωνιστεί μόνος του και φκιάσει ή χαλάσει, να λέγει «εγώ»· όταν όμως αγωνίζονται πολλοί και φκιάνουν, τότε να λένε «εμείς». Είμαστε εις το «εμείς» κι όχι εις το «εγώ». Και εις το εξής να μάθομεν γνώση, αν θέλομεν να φκιάσομεν χωριόν, να ζήσομεν όλοι μαζί.
+
+        Γιάννης Μακρυγιάννης.
+
+    expected: |
+        Éna práma mónon me parakínise ki eména na grápso óti toútin tin patrída tin échomen óloi mazí, kai sofoí ki amatheís kai ploúsioi kai ftochoí kai politikoí kai stratiotikoí kai oi pléon mikróteroi ánthropoi; ósoi agonistíkamen, analógos o katheís, échomen na zísomen edó. To loipón doulépsamen óloi mazí, na tin fylámen ki óloi mazí kai na min légei oúte o dynatós «egó» oúte o adýnatos. Xérete póte na légei o katheís «egó»? Ótan agonisteí mónos tou kai fkiásei í chalásei, na légei «egó»; ótan ómos agonízontai polloí kai fkiánoun, tóte na léne «emeís». Eímaste eis to «emeís» ki óchi eis to «egó». Kai eis to exís na máthomen gnósi, an thélomen na fkiásomen chorión, na zísomen óloi mazí.
+
+        Giánnis Makrygiánnis.
+
+map:
+  character_separator: ""
+  word_separator: " "
+  inherit: "iso-ell-Grek-Latn-843-1997-t2"
+

data/maps/ggg-kat-Geor-Latn-2002.yaml

@@ -0,0 +1,89 @@
+---
+authority_id: ggg
+id: 2002
+language: kat
+source_script: Geor
+destination_script: Latn
+name: Georgian State Department of Geodesy and Cartography 2002 System
+url: https://transliteration.eki.ee/pdf/Georgian.pdf
+creation_date: 1998
+confirmation_date: 2002
+description: |
+  The national system of romanization adopted in February 2002 by the State
+  Department of Geodesy and Cartography of Georgia and the Institute
+  of Linguistics, Georgian Academy of Sciences.
+
+notes:
+  - Georgian script refers in this document to the Mkhedruli alphabet.
+
+  - There is no case in Georgian.
+
+tests:
+  - source: თბილისი
+    expected: tbilisi
+
+  - source: მეღვინეთუხუცესი
+    expected: meghvinetukhutsesi
+
+  - source: ჭიანჭველა
+    expected: ch’ianch’vela
+
+  - source: ბაყაყი
+    expected: baq’aq’i
+
+  - source: ჩხალთის ქედი
+    expected: chkhaltis kedi
+
+  - source: აბჟააფთრა
+    expected: abzhaaptra
+
+  - source: ამბროლაურის მუნიციპალიტეტი
+    expected: ambrolauris munitsip’alit’et’i
+
+  - source: მარტვილის მუნიციპალიტეტი
+    expected: mart’vilis munitsip’alit’et’i
+
+  - source: ლეკუხონა
+    expected: lek’ukhona
+
+  - source: მყინვარი აღმოსავლეთი მაგუაშირხა
+    expected: mq’invari aghmosavleti maguashirkha
+
+
+
+map:
+  characters:
+    '\u10d0' : 'a' # ა
+    '\u10d1' : 'b' # ბ
+    '\u10d2' : 'g' # გ
+    '\u10d3' : 'd' # დ
+    '\u10d4' : 'e' # ე
+    '\u10d5' : 'v' # ვ
+    '\u10d6' : 'z' # ზ
+    '\u10d7' : 't' # თ
+    '\u10d8' : 'i' # ი
+    '\u10d9' : 'k’' # კ
+    '\u10da' : 'l' # ლ
+    '\u10db' : 'm' # მ
+    '\u10dc' : 'n' # ნ
+    '\u10dd' : 'o' # ო
+    '\u10de' : 'p’' # პ
+    '\u10df' : 'zh' # ჟ
+    '\u10e0' : 'r' # რ
+    '\u10e1' : 's' # ს
+    '\u10e2' : 't’' # ტ
+    '\u10e3' : 'u' # უ
+    '\u10e4' : 'p' # ფ
+    '\u10e5' : 'k' # ქ
+    '\u10e6' : 'gh' # ღ
+    '\u10e7' : 'q’' # ყ
+    '\u10e8' : 'sh' # შ
+    '\u10e9' : 'ch' # ჩ
+    '\u10ea' : 'ts' # ც
+    '\u10eb' : 'dz' # ძ
+    '\u10ec' : 'ts’' # წ
+    '\u10ed' : 'ch’' # ჭ
+    '\u10ee' : 'kh' # ხ
+    '\u10ef' : 'j' # ჯ
+    '\u10f0' : 'h' # ჰ
+

data/maps/gki-bel-cyrl-latn-1992.yaml

@@ -0,0 +1,33 @@
+---
+authority_id: gki
+id: 1992
+language: bel
+source_script: Cyrl
+destination_script: Latn
+name: Byelorussian National Cartographic Authority 1992-3 System (based on GOST 1983)
+url: https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/7th-uncsgn-docs/econf/7th_UNCSGN_econf.91_3_Add1.pdf
+creation_date: 1992
+
+tests:
+  - source: 'Сямашкі'
+    expected: 'Sjamaški'
+    # "Syamashki" in GNDB `bel_Cyrl2Latn_GBO_1992`, but that is clearly bgnpcgn-ukr-Cyrl-Latn-1965
+  - source: 'Старадворцы'
+    expected: 'Staradvorcy'
+    # "Staradvortsy" in GNDB `bel_Cyrl2Latn_GBO_1992`, but that is clearly bgnpcgn-ukr-Cyrl-Latn-1965
+  - source: 'Канюхі'
+    expected: 'Kanjuhi'
+    # "Kanyukhi" in GNDB `bel_Cyrl2Latn_GBO_1992`, but that is clearly bgnpcgn-ukr-Cyrl-Latn-1965
+
+map:
+  inherit: gost-rus-cyrl-latn-16876-71-1983
+
+  characters:
+    '\u0406' : 'I'  # І
+    '\u0456' : 'i'  # і
+
+    '\u0413' : 'G'  # Г
+    '\u0433' : 'g'  # г
+
+    '\U040E' : 'Ŭ'  # Ў
+    '\u045E' : 'ŭ'  # ў

data/maps/gki-bel-cyrl-latn-2000.yaml

@@ -0,0 +1,201 @@
+---
+authority_id: gki
+id: 2000
+language: bel
+source_script: Cyrl
+destination_script: Latn
+name: On approval of the Instructions for the transliteration of geographical names of the Republic of Belarus with letters of the Latin alphabet
+url: https://registr.by/doc/103003
+creation_date: 2000
+description: |
+  Act name: 
+    On approval of the Instructions for the transliteration of geographical names of
+    the Republic of Belarus in letters of the Latin alphabet
+  Type of act, adoption authority, date and number of adoption (publication):
+    Resolution of the State Committee for Land Resources, Geodesy and Cartography of
+    the Republic of Belarus of November 23, 2000 No. 15
+  National Registry Registration Number: 8/4488
+  Date of inclusion in the National Register: 11/30/2000
+  Source (s) of official publication:
+    National Register of Legal Acts of the Republic of Belarus, 2001,
+    No. 3, 8/4488 (published - January 11, 2001)
+tests:
+  - source: Аршанскi
+    expected: Aršanski
+  - source: Бешанковічы
+    expected: Biešankovičy
+  - source: Віцебск
+    expected: Viciebsk
+  - source: Гомель
+    expected: Homiel'
+  - source: Гаўя
+    expected: Haŭja
+  - source: Добруш
+    expected: Dobruš
+  - source: Ельск
+    expected: Jel'sk
+  - source: Бабаедава
+    expected: Babajedava
+  - source: Лепель
+    expected: Liepiel'
+  - source: Ёды
+    expected: Jody
+  - source: Вераб'ёвічы
+    expected: Vierabjovičy
+  - source: Мёры
+    expected: Miory
+  - source: Жодзiшкi
+    expected: Žodziški
+  - source: Зэльва
+    expected: Zel'va
+  - source: Iванава
+    expected: Ivanava
+  - source: Iўе
+    expected: Iŭje
+  - source: Лагойск
+    expected: Lahojsk
+  - source: Круглае
+    expected: Kruhlaje
+  - source: Любань
+    expected: Liuban'
+  - source: Магілёў
+    expected: Mahilioŭ
+  - source: Нясвіж
+    expected: Niasviž
+  - source: Орша
+    expected: Orša
+  - source: Паставы
+    expected: Pastavy
+  - source: Рагачоў
+    expected: Rahačoŭ
+  - source: Светлагорск
+    expected: Svietlahorsk # original doc Svetlahorsk but it looks like mistake https://en.wikipedia.org/wiki/Svietlahorsk
+  - source: Талачын
+    expected: Talačyn
+  - source: Узда
+    expected: Uzda
+  - source: Шаркаўшчына
+    expected: Šarkaŭščyna
+  - source: Фаніпаль
+    expected: Fanipal'
+  - source: Хоцімск
+    expected: Chocimsk
+  - source: Цёмны Лес
+    expected: Ciomny Lies
+  - source: Чавусы
+    expected: Čavusy
+  - source: Шумілiна
+    expected: Šumilina
+  - source: Раз'езд
+    expected: Razjezd
+  - source: Чыгірынка
+    expected: Čyhirynka
+  - source: Чэрвень
+    expected: Červien'
+  - source: Чачэрск
+    expected: Čačersk
+  - source: Юхнаўка
+    expected: Juchnaŭka
+  - source: Гаюціна
+    expected: Hajucina
+  - source: Любонічы
+    expected: Liuboničy
+  - source: Ямнае
+    expected: Jamnaje
+  - source: Баяры
+    expected: Bajary
+  - source: Вязынка
+    expected: Viazynka
+  - source: Валяр'яны
+    expected: Valiarjany
+
+map:
+  rules:
+    - pattern: (?<=[БбВвГгДдЖжЗзЙйКкЛлМмНнПпРрСсТтФфХхЦцЧчШш])\u0415 # Е after consonants
+      result: IE
+    - pattern: (?<=[БбВвГгДдЖжЗзЙйКкЛлМмНнПпРрСсТтФфХхЦцЧчШш])\u0435 # е after consonants
+      result: ie
+    - pattern: (?<=[БбВвГгДдЖжЗзЙйКкЛлМмНнПпРрСсТтФфХхЦцЧчШш])\u0401 # Ё after consonants
+      result: IO
+    - pattern: (?<=[БбВвГгДдЖжЗзЙйКкЛлМмНнПпРрСсТтФфХхЦцЧчШш])\u0451 # ё after consonants
+      result: io
+    - pattern: (?<=[БбВвГгДдЖжЗзЙйКкЛлМмНнПпРрСсТтФфХхЦцЧчШш])\u042E # Ю after consonants
+      result: IU
+    - pattern: (?<=[БбВвГгДдЖжЗзЙйКкЛлМмНнПпРрСсТтФфХхЦцЧчШш])\u044E # ю after consonants
+      result: iu
+    - pattern: (?<=[БбВвГгДдЖжЗзЙйКкЛлМмНнПпРрСсТтФфХхЦцЧчШш])\u042F # Я after consonants
+      result: IA
+    - pattern: (?<=[БбВвГгДдЖжЗзЙйКкЛлМмНнПпРрСсТтФфХхЦцЧчШш])\u044F # я after consonants
+      result: ia
+  postrules:
+    - pattern: '\u042C' # Ь
+      result: "'"
+    - pattern: '\u044C' # ь
+      result: "'"
+
+  characters:
+    '\u0027' : ''   # '
+
+    '\u0410' : 'A'  # A
+    '\u0411' : 'B'  # Б
+    '\u0412' : 'V'  # B
+    '\u0413' : 'H'  # Г
+    '\u0414' : 'D'  # Д
+    '\u0415' : 'Je' # Е
+    '\u0401' : 'Jo' # Ё
+    '\u0416' : 'Ž'  # Ж
+    '\u0417' : 'Z'  # З
+    '\u0406' : 'I'  # І
+    '\u0419' : 'J'  # Й
+    '\u041A' : 'K'  # К
+    '\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' : 'Ch' # Х
+    '\u0426' : 'C'  # Ц
+    '\u0427' : 'Č'  # Ч
+    '\u0428' : 'Š'  # Ш
+    '\u042B' : 'Y'  # Ы
+    '\u042D' : 'E'  # Э
+    '\u042E' : 'Ju' # Ю
+    '\u042F' : 'Ja' # Я
+
+    '\u0430' : 'a'  # а
+    '\u0431' : 'b'  # б
+    '\u0432' : 'v'  # в
+    '\u0433' : 'h'  # г
+    '\u0434' : 'd'  # д
+    '\u0435' : 'je' # е
+    '\u0451' : 'jo' # ё
+    '\u0436' : 'ž'  # ж
+    '\u0437' : 'z'  # з
+    '\u0456' : 'i'  # і
+    '\u0439' : 'j'  # й
+    '\u043A' : 'k'  # к
+    '\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' : 'ch' # х
+    '\u0446' : 'c'  # ц
+    '\u0447' : 'č'  # ч
+    '\u0448' : 'š'  # ш
+    '\u044B' : 'y'  # ы
+    '\u044D' : 'e'  # э
+    '\u044E' : 'ju' # ю
+    '\u044F' : 'ja' # я

data/maps/gost-rus-cyrl-latn-16876-71-1983.yaml

@@ -0,0 +1,186 @@
+---
+authority_id: gost
+id: 1983
+language: rus
+source_script: Cyrl
+destination_script: Latn
+name: LETTERS TRANSLATION RULES OF KIRILLOVSKY ALPHABET WITH LETTERS OF LATIN ALPHABET GOST 16876-71
+url: https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/7th-uncsgn-docs/econf/7th_UNCSGN_econf.91_3_Add1.pdf
+creation_date: 1978
+confirmation_date: 1982-04-16
+adoption_date: 1983-05-13
+description: |
+  GOST 16876-71 (Russian: ГОСТ 16876-71) is a romanization system (for transliteration of Russian Cyrillic alphabet texts into the Latin alphabet)
+  devised by the National Administration for Geodesy and Cartography of the Soviet Union.
+  It is based on the scientific transliteration system used in linguistics.
+  GOST was an international standard so it included provision for a number of the languages
+  of the Soviet Union.
+
+  GOST 16876-71 was used by the United Nations to develop its romanization system for geographical names,
+  which was adopted for official use by the United Nations at the Fifth United Nations Conference
+  on the Standardization of Geographical Names in Montreal, Quebec, Canada, in 1987.
+  UN system relies on diacritics to compensate for non-Russian Cyrillic alphabets.
+
+  In 1978, COMECON adopted GOST 16876-71 with minor modifications as its official transliteration standard,
+  under the name of SEV 1362-78 (Russian: СЭВ 1362-78).
+
+  In 1982, In accordance with Order No. 169 of April 16, 1982, GOST 16876-71 / ST SEV 1362-78 was put into effect on May 1, 1982. 
+
+  In 1983, In accordance with Order No. 231 of May 16, 1983, Additional guidelines was released (check notes[2])
+
+  In 2002, the Russian Federation along with a number of CIS countries abandoned the use of GOST 16876
+  in favor of ISO 9:1995, which was adopted as GOST 7.79-2000.
+
+notes:
+  - http://vsegost.com/Catalog/45/45002.shtml - original GOST
+  - https://rosreestr.ru/upload/documenty/doc_169.doc - orders for entry into force (with changes)
+
+tests:
+  - source: Анапа
+    expected: Anapa
+  - source: Бабушкин
+    expected: Babuškin
+  - source: Вавилово
+    expected: Vavilovo
+  - source: Гагарин
+    expected: Gagarin
+  - source: Дудинка
+    expected: Dudinka
+  - source: Елисеевка
+    expected: Eliseevka
+  - source: Ёлкино
+    expected: Ëlkino
+  - source: Псёл
+    expected: Psël
+  - source: Жужа
+    expected: Žuža
+  - source: Звёздный
+    expected: Zvëzdnyj
+  - source: Идрица
+    expected: Idrica
+  - source: Зарайск
+    expected: Zarajsk
+  - source: Коканд
+    expected: Kokand
+  - source: Лалвар
+    expected: Lalvar
+  - source: Маймак
+    expected: Majmak
+  - source: Нежин
+    expected: Nežin
+  - source: Ободовка
+    expected: Obodovka
+  - source: Пап
+    expected: Pap
+  - source: Ребриха
+    expected: Rebriha
+  - source: Сасово
+    expected: Sasovo
+  - source: Татта
+    expected: Tatta
+  - source: Уржум
+    expected: Uržum
+  - source: Фофаново
+    expected: Fofanovo
+  - source: Хохлома
+    expected: Hohloma
+  - source: Цветково
+    expected: Cvetkovo
+  - source: Чечельник
+    expected: Čečel´nik
+  - source: Шишкино
+    expected: Šiškino
+  - source: Щукино
+    expected: Ščukino
+  - source: Подъячево
+    expected: Pod"jačevo
+  - source: Ыныкчанский
+    expected: Ynykčanskij
+  - source: Параньга
+    expected: Paran´ga
+  - source: Щучье
+    expected: Ščuč´e
+  - source: Элиста
+    expected: Èlista
+  - source: Юрино
+    expected: Jurino
+  - source: Юхнов
+    expected: Juhnov
+  - source: Юрюзань
+    expected: Jurjuzan´
+  - source: Ямал
+    expected: Jamal
+  - source: Язъяван
+    expected: Jaz"javan
+  - source: Яя
+    expected: Jaja
+
+map:
+  characters:
+    '\u0410' : 'A'  # A
+    '\u0411' : 'B'  # Б
+    '\u0412' : 'V'  # B
+    '\u0413' : 'G'  # Г
+    '\u0414' : 'D'  # Д
+    '\u0415' : 'E'  # Е
+    '\u0401' : "\u00CB" # Ё
+    '\u0416' : 'Ž'  # Ж
+    '\u0417' : 'Z'  # З
+    '\u0418' : "I"  # И
+    '\u0419' : 'J'  # Й
+    '\u041A' : 'K'  # К
+    '\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
+    '\u0424' : 'F'  # Ф
+    '\u0425' : 'H'  # Х
+    '\u0426' : 'C'  # Ц
+    '\u0427' : 'Č'  # Ч
+    '\u0428' : 'Š'  # Ш
+    '\u0429' : 'Šč' # Щ
+    '\u042a' : '"'  # Ъ
+    '\u042B' : 'Y'  # Ы
+    '\u042C' : "\u00B4" # Ь => ’
+    '\u042D' : "E\u0300" # È
+    '\u042E' : 'Ju' # Ю
+    '\u042F' : 'Ja' # Я
+
+    '\u0430' : 'a'  # а
+    '\u0431' : 'b'  # б
+    '\u0432' : 'v'  # в
+    '\u0433' : 'g'  # г
+    '\u0434' : 'd'  # д
+    '\u0435' : 'e'  # е
+    '\u0451' : "\u00EB" # ё
+    '\u0436' : 'ž'  # ж
+    '\u0437' : 'z'  # з
+    '\u0438' : 'i'  # и
+    '\u0439' : 'j'  # й
+    '\u043A' : 'k'  # к
+    '\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
+    '\u0444' : 'f'  # ф
+    '\u0445' : 'h'  # х
+    '\u0446' : 'c'  # ц
+    '\u0447' : 'č'  # ч
+    '\u0448' : 'š'  # ш
+    '\u0449' : 'šč' # щ
+    '\u044A' : '"'  # ъ
+    '\u044B' : 'y'  # ы
+    '\u044C' : "\u00B4" # ь => ’
+    '\u044D' : "e\u0300" # è
+    '\u044E' : 'ju' # ю
+    '\u044F' : 'ja' # я