interscript 0.1.0 → 0.1.5

data/maps/alalc-srp-Cyrl-Latn-1997.yaml

@@ -0,0 +1,114 @@
+---
+authority_id: alalc
+id: 1997
+language: srp
+source_script: Cyrl
+destination_script: Latn
+name: Serbian and Makedonian Romanization, ALA-LC 1997 System
+url: http://catdir.loc.gov/catdir/cpso/romanization/serbian.pdf
+creation_date: 1997
+description: ALA-LC Romanization table for Serbian and Makedonian.
+
+notes:
+  - Special characters in romanization
+    Đ - D with crossbar (upper case). USMARC hexadecimal code A3.
+    đ - d with crossbar (upper case). USMARC hexadecimal code B3.
+
+  - Character modifiers in romanization
+    ´ - acute. USMARC hexadecimal code E2.
+    ˇ - hachek. USMARC hexadecimal code E9.
+
+tests:
+  - source: Општина Ердут
+    expected: Opština Erdut
+  - source: Општина Двор
+    expected: Opština Dvor
+  - source: ЛУЃЕ луѓе
+    expected: LUǴE luǵe
+  - source: ЅВЕЗДА ѕвезда Ѕвезда
+    expected: DZVEZDA dzvezda Dzvezda
+  - source: ЌАРУВАЊЕ ќарување
+    expected: ḰARUVANJE ḱaruvanje
+
+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"
+    "\u0403": "\u01F4" # Ǵ
+    "\u0414": "D"
+    "\u0402": "\u0110" # Đ
+    "\u0415": "E"
+    "\u0416": "\u005a\u030c" # Ž
+    "\u0417": "Z"
+    "\u0405": "Dz"
+    "\u0418": "I"
+    "\u0408": "J"
+    "\u041A": "K"
+    "\u040C": "\u1E30" # Ḱ
+    "\u041B": "L"
+    "\u0409": "Lj"
+    "\u041C": "M"
+    "\u041D": "N"
+    "\u040A": "Nj"
+    "\u041E": "O"
+    "\u041F": "P"
+    "\u0420": "R"
+    "\u0421": "S"
+    "\u0422": "T"
+    "\u040B": "\u0043\u0301" # 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"
+    "\u0453": "\u01F5" # ǵ
+    "\u0434": "d"
+    "\u0452": "\u0111" # đ
+    "\u0435": "e"
+    "\u0436": "\u007a\u030c" # ž
+    "\u0437": "z"
+    "\u0455": "dz"
+    "\u0438": "i"
+    "\u0458": "j"
+    "\u043A": "k"
+    "\u045C": "\u1E31" # ḱ
+    "\u043B": "l"
+    "\u0459": "lj"
+    "\u043C": "m"
+    "\u043D": "n"
+    "\u045A": "nj"
+    "\u043E": "o"
+    "\u043F": "p"
+    "\u0440": "r"
+    "\u0441": "s"
+    "\u0442": "t"
+    "\u045B": "\u0063\u0301" # ć
+    "\u0443": "u"
+    "\u0444": "f"
+    "\u0445": "h"
+    "\u0446": "c"
+    "\u0447": "\u0063\u030c" # č
+    "\u045F": "d\u007a\u030c" # dž
+    "\u0448": "\u0073\u030c" # š

data/maps/alalc-srp-cyrl-latn-2013.yaml

@@ -0,0 +1,135 @@
+---
+authority_id: alalc
+id: 2013
+language: srp
+source_script: Cyrl
+destination_script: Latn
+name: ROMANIZATION OF SERBIAN, ALA-LC 2013 System
+url: https://www.loc.gov/catdir/cpso/romanization/serbian.pdf
+creation_date: 2013
+description: |
+  Serbian uses the Cyrillic and Roman alphabets. When the Roman alphabet is used it is the same as Croatian.
+
+tests:
+  - source: Шупља Стена
+    expected: Šuplja Stena
+  - source: Чукарица
+    expected: Čukarica
+  - source: Црна Трава
+    expected: Crna Trava
+  - source: Херцег Нови
+    expected: Herceg Novi
+  - source: Улцињ
+    expected: Ulcinj
+  - source: Ужице
+    expected: Užice
+  - source: Тресаначка Река
+    expected: Tresanačka Reka
+  - source: Сјеница
+    expected: Sjenica
+  - source: Рожаје
+    expected: Rožaje
+  - source: Пљевља
+    expected: Pljevlja
+  - source: Оџаци
+    expected: Odžaci
+  - source: Никшић
+    expected: Nikšić
+  - source: Медвеђа
+    expected: Medveđa
+  - source: Лозница
+    expected: Loznica
+  - source: Књажевац
+    expected: Knjaževac
+  - source: Зрењанин
+    expected: Zrenjanin
+  - source: Житорађа
+    expected: Žitorađa
+  - source: Ервеник
+    expected: Ervenik
+  - source: Доње Љупче
+    expected: Donje Ljupče
+  - source: Гусиње
+    expected: Gusinje
+  - source: ГУСИЊЕ
+    expected: GUSINJE
+  - source: Врњачка Бања
+    expected: Vrnjačka Banja
+  - source: Бијело Поље
+    expected: Bijelo Polje
+  - source: Алибунар
+    expected: Alibunar
+
+map:
+  postrules:
+    #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"
+    "\u0402": "\u0110" # Đ
+    "\u0415": "E"
+    "\u0416": "\u005a\u030c" # Ž
+    "\u0417": "Z"
+    "\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"
+    "\u040B": "\u0043\u0301" # 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"
+    "\u0452": "\u0111" # đ
+    "\u0435": "e"
+    "\u0436": "\u007a\u030c" # ž
+    "\u0437": "z"
+    "\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"
+    "\u045B": "\u0063\u0301" # ć́
+    "\u0443": "u"
+    "\u0444": "f"
+    "\u0445": "h"
+    "\u0446": "c"
+    "\u0447": "\u0063\u030c" # č
+    "\u045F": "d\u007a\u030c" # dž
+    "\u0448": "\u0073\u030c" # š

data/maps/alalc-ukr-Cyrl-Latn-1997.yaml

@@ -0,0 +1,141 @@
+---
+authority_id: alalc
+id: 1997
+language: ukr
+source_script: Cyrl
+destination_script: Latn
+name: ALA-LC Romanization System 1997
+url: http://catdir.loc.gov/catdir/cpso/romanization/ukrainia.pdf
+creation_date: 1997
+description: |
+  The ALA-LC Romanization Tables, published by the American Library Association (1885)
+  and Library of Congress (1905). Used to represent bibliographic information by US and
+  Canadian libraries, by the British Library since 1975,[3] and in North American publications.
+  The latest 1997 revision is very similar to the 1905 version.
+
+notes:
+  - The z͡h ligature is necessary to distinguish ж from the combination зг.
+  - The t͡s ligature is necessary to distinguish ц from the combination тс.
+
+tests:
+  - source: Автономна Республіка Крим
+    expected: Avtonomna Respublika Krym
+  - source: Висунь
+    expected: Vysunʹ
+  - source: Долинське
+    expected: Dolynsʹke
+  - source: Дубище
+    expected: Dubyshche
+  - source: Єнакієве
+    expected: I͡enakii͡eve
+  - source: Зупиночний Пункт Мокіївці
+    expected: Zupynochnyĭ Punkt Mokiïvt͡si
+  - source: Іванівщина
+    expected: Ivanivshchyna
+  - source: Киликиїв
+    expected: Kylykyïv
+  - source: Кожанка
+    expected: Koz͡hanka
+  - source: Краснянка
+    expected: Krasni͡anka
+  - source: Краснівка
+    expected: Krasnivka
+  - source: Мале Микільське
+    expected: Male Mykilʹsʹke
+  - source: Маломиколаївка
+    expected: Malomykolaïvka
+  - source: Нове Село
+    expected: Nove Selo
+  - source: Новопавлівка
+    expected: Novopavlivka
+  - source: Новошичі
+    expected: Novoshychi
+  - source: Новоєфремівка
+    expected: Novoi͡efremivka
+  - source: Одеська Область
+    expected: Odesʹka Oblastʹ
+  - source: Орлівське
+    expected: Orlivsʹke
+  - source: Раневичі
+    expected: Ranevychi
+  - source: Рокувата
+    expected: Rokuvata
+  - source: Рудаєве
+    expected: Rudai͡eve
+  - source: Сахнівці
+    expected: Sakhnivt͡si
+  - source: Тернівка
+    expected: Ternivka
+  - source: Турбівка
+    expected: Turbivka
+  - source: Херсонська Область
+    expected: Khersonsʹka Oblastʹ
+
+map:
+  characters:
+    "\u0410": "A"        # А
+    "\u0411": "B"        # Б
+    "\u0412": "V"        # В
+    "\u0413": "H"        # Г
+    "\u0490": "G"        # Ґ
+    "\u0414": "D"        # Д
+    "\u0415": "E"        # Е
+    "\u0404": "I\u0361e" # Є -> I͡e
+    "\u0416": "Z\u0361h" # Ж -> Z͡h
+    "\u0417": "Z"        # З
+    "\u0418": "Y"        # И
+    "\u0406": "I"        # І
+    "\u0407": "I\u0308"  # Ї -> Ï
+    "\u0419": "I\u0306"  # Й -> Ĭ
+    "\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": "Kh"       # Х
+    "\u0426": "T\u0361s" # Ц -> T͡s
+    "\u0427": "Ch"       # Ч
+    "\u0428": "Sh"       # Ш
+    "\u0429": "Shch"     # Щ
+    "\u042e": "I\u0361u" # Ю -> I͡u
+    "\u042f": "I\u0361a" # Я -> I͡a
+    "\u042c": "\u02B9"   # Ь -> ʹ
+    "\u0430": "a"        # а
+    "\u0431": "b"        # б
+    "\u0432": "v"        # в
+    "\u0433": "h"        # г
+    "\u0491": "g"        # ґ
+    "\u0434": "d"        # д
+    "\u0435": "e"        # е
+    "\u0454": "i\u0361e" # є -> i͡e
+    "\u0436": "z\u0361h" # ж -> z͡h
+    "\u0437": "z"        # з
+    "\u0438": "y"        # и
+    "\u0456": "i"        # і
+    "\u0457": "i\u0308"  # ї -> ï
+    "\u0439": "i\u0306"  # й -> ĭ
+    "\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": "kh"       # х
+    "\u0446": "t\u0361s" # ц -> t͡s
+    "\u0447": "ch"       # ч
+    "\u0448": "sh"       # ш
+    "\u0449": "shch"     # щ
+    "\u044e": "i\u0361u" # ю -> i͡u
+    "\u044f": "i\u0361a" # я -> i͡a
+    "\u044c": "\u02B9"   # Ь -> ʹ

data/maps/alalc-ukr-Cyrl-Latn-2011.yaml

@@ -0,0 +1,16 @@
+---
+authority_id: alalc
+id: 2011
+language: ukr
+source_script: Cyrl
+destination_script: Latn
+name: ALA-LC Romanization System 1997
+url: https://www.loc.gov/catdir/cpso/romanization/ukrainia.pdf
+creation_date: 2011
+
+notes:
+  - The z͡h ligature is necessary to distinguish ж from the combination зг.
+  - The t͡s ligature is necessary to distinguish ц from the combination тс.
+
+map:
+  inherit: alalc-ukr-Cyrl-Latn-1997

data/maps/apcbg-bul-Cyrl-Latn-1995.yaml

@@ -0,0 +1,283 @@
+---
+authority_id: apcbg
+id: 1995
+language: bul
+source_script: Cyrl
+destination_script: Latn
+name: Toponymic Guidelines for Antarctica, Lyubomir Ivanov. Antarctic Place-names Commission of Bulgaria, Sofia, 1995.
+url: http://www.apcbg.org/Toponymic-Guidelines.htm
+creation_date: 1995
+description: |
+  In Antarctica geographical names are important elements of identification, orientation, localization and navigation,
+  providing an essential reference system for logistic operations, including search and rescue measures, and for
+  international scientific research.  They facilitate information exchange in the field, in scientific publications and in
+  administrative measures under the Antarctic Treaty System. Geographical names also reflect the history of Antarctic
+  exploration.
+
+tests:
+  - source: нунатак Абрит
+    expected: nunatak Abrit
+  - source: връх Академия
+    expected: vrah Akademiya
+  - source: връх Ами Буе
+    expected: vrah Ami Bue
+  - source: нос Айтос
+    expected: nos Aytos
+  - source: залив Баба Тонка
+    expected: zaliv Baba Tonka
+  - source: Балабански камък
+    expected: Balabanski kamak
+  - source: Бедечки поток
+    expected: Bedechki potok
+  - source: нос Бяга
+    expected: nos Byaga
+  - source: остров Качо
+    expected: ostrov Kacho # wiki ostrov Cacho
+  - source: Чакъров остров
+    expected: Chakarov ostrov
+  - source: връх Дъбник
+    expected: vrah Dabnik
+  - source: залив Десислава
+    expected: zaliv Desislava
+  - source: ледник Джераси
+    expected: lednik Dzherasi
+  - source: Джегова скала
+    expected: Dzhegova skala
+  - source: Нунатак Едуард
+    expected: Nunatak Eduard
+  - source: Елховска седловина
+    expected: Elhovska sedlovina
+  - source: ледник Етър
+    expected: lednik Etar
+  - source: нунатак Филип Тотю
+    expected: nunatak Filip Totyu
+  - source: ледник Габаре
+    expected: lednik Gabare
+  - source: риф Гергини
+    expected: rif Gergini
+  - source: Гяуров връх
+    expected: Gyaurov vrah
+  - source: Гуцалски рид
+    expected: Gutsalski rid # not found
+  - source: Хараламбиев остров
+    expected: Haralambiev ostrov
+  - source: връх Ичера
+    expected: vrah Ichera
+  - source: полуостров Йоан Павел II
+    expected: poluostrov Yoan Pavel II
+  - source: нос Иван Александър
+    expected: nos Ivan Aleksandar
+  - source: нос Иречек
+    expected: nos Irechek
+  - source: нос Кърджали
+    expected: nos Kardzhali
+  - source: седловина Кърнаре
+    expected: sedlovina Karnare
+  - source: нунатак Керсеблепт
+    expected: nunatak Kerseblept
+  - source: Кондофрейски възвишения
+    expected: Kondofreyski vazvisheniya
+  - source: Костинбродски проход
+    expected: Kostinbrodski prohod
+  - source: връх Кожух
+    expected: vrah Kozhuh
+  - source: Кукерски нунатаци
+    expected: Kukerski nunatatsi
+  - source: залив Лазурен бряг
+    expected: zaliv Lazuren bryag
+  - source: връх Лудогорие
+    expected: vrah Ludogorie
+  - source: Лютибродски скали
+    expected: Lyutibrodski skali
+  - source: Масларов нунатак
+    expected: Maslarov nunatak
+  - source: Михневски връх
+    expected: Mihnevski vrah
+  - source: рид Митино
+    expected: rid Mitino
+  - source: езеро Наяда
+    expected: ezero Nayada
+  - source: нос Никюп
+    expected: nos Nikyup
+  - source: рид Оборище
+    expected: rid Oborishte
+  - source: залив Олуша
+    expected: zaliv Olusha
+  - source: Оряховски възвишения
+    expected: Oryahovski vazvisheniya
+  - source: нунатак Памидово
+    expected: nunatak Pamidovo
+  - source: връх Парангалица
+    expected: vrah Parangalitsa
+  - source: Първомайски провлак
+    expected: Parvomayski provlak
+  - source: ледник Патлейна
+    expected: lednik Patleyna
+  - source: полуостров Перник
+    expected: poluostrov Pernik
+  - source: връх Петко Войвода
+    expected: vrah Petko Voyvoda
+  - source: остров Фанагория
+    expected: ostrov Fanagoriya
+  - source: нос Плас
+    expected: nos Plas
+  - source: Пресиянов рид
+    expected: Presiyanov rid
+  - source: връх Принсипе де Астуриас
+    expected: vrah Prinsipe de Asturias # wiki: vrah Príncipe de Asturias
+  - source: нунатак Ръченица
+    expected: nunatak Rachenitsa
+  - source: връх Райна Княгиня
+    expected: vrah Rayna Knyaginya
+  - source: Рид Ръжана
+    expected: Rid Razhana
+  - source: връх Ригс
+    expected: vrah Rigs
+  - source: остров Рогулят
+    expected: ostrov Rogulyat
+  - source: ледник Сабазий
+    expected: lednik Sabaziy
+  - source: ледник Съединение
+    expected: lednik Saedinenie
+  - source: нунатак Сенокос
+    expected: nunatak Senokos
+  - source: Сейдолски камък
+    expected: Seydolski kamak
+  - source: ледник Щерна
+    expected: lednik Shterna
+  - source: връх Шишман
+    expected: vrah Shishman
+  - source: ледник Сигмен
+    expected: lednik Sigmen
+  - source: Седловина Синитово
+    expected: Sedlovina Sinitovo
+  - source: Ледник Скаплизо
+    expected: Lednik Skaplizo
+  - source: залив Слънчев бряг
+    expected: zaliv Slanchev bryag
+  - source: остров Соатрис
+    expected: ostrov Soatris
+  - source: планина Софийски Университет
+    expected: planina Sofiyski Universitet
+  - source: ледник Сребърна
+    expected: lednik Srebarna
+  - source: Средногорски възвишения
+    expected: Srednogorski vazvisheniya
+  - source: Св. Евтимиев камък
+    expected: Sv. Evtimiev kamak
+  - source: база Св. Климент Охридски
+    expected: baza Sv. Kliment Ohridski
+  - source: връх Стъргел
+    expected: vrah Stargel
+  - source: нунатак Сторгозия
+    expected: nunatak Storgoziya # nunatak Storgozia according to wiki
+  - source: нунатак Сурвакари
+    expected: nunatak Survakari
+  - source: ледник Световрачене
+    expected: lednik Svetovrachene
+  - source: остров Теменуга
+    expected: ostrov Temenuga
+  - source: Тракийски възвишения
+    expected: Trakiyski vazvisheniya
+  - source: хълм Цамблак
+    expected: halm Tsamblak
+  - source: ледник Урдовиза
+    expected: lednik Urdoviza
+  - source: остров Вълчедръм
+    expected: ostrov Valchedram
+  - source: острови Вардим
+    expected: ostrovi Vardim
+  - source: Владигеров проток
+    expected: Vladigerov protok
+  - source: ледник Ябланица
+    expected: lednik Yablanitsa
+  - source: залив Ямфорина
+    expected: zaliv Yamforina
+  - source: Йовков нос
+    expected: Yovkov nos
+  - source: рид Заберново
+    expected: rid Zabernovo
+  - source: ледник Збелсурд
+    expected: lednik Zbelsurd
+  - source: Жефарович камък
+    expected: Zhefarovich kamak
+  - source: връх Зиези
+    expected: vrah Ziezi
+  - source: залив Златни пясъци
+    expected: zaliv Zlatni pyasatsi
+  - source: ледник Злокучене
+    expected: lednik Zlokuchene
+  - source: проток Злогош
+    expected: protok Zlogosh
+
+map:
+  characters:
+    '\u0410': 'A'
+    '\u0411': 'B'
+    '\u0412': 'V'
+    '\u0413': 'G'
+    '\u0414': 'D'
+    '\u0415': 'E'
+    '\u0416': 'Zh'
+    '\u0417': 'Z'
+    '\u0418': 'I'
+    '\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': 'H'
+    '\u0426': 'Ts'
+    '\u0427': 'Ch'
+    '\u0428': 'Sh'
+    '\u0429': 'Sht'
+    '\u042a': 'A'
+    '\u042c': 'Y'
+    '\u042e': 'Yu'
+    '\u042f': 'Ya'
+
+    '\u0430': 'a'
+    '\u0431': 'b'
+    '\u0432': 'v'
+    '\u0433': 'g'
+    '\u0434': 'd'
+    '\u0435': 'e'
+    '\u0436': 'zh'
+    '\u0437': 'z'
+    '\u0438': 'i'
+    '\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': 'h'
+    '\u0446': 'ts'
+    '\u0447': 'ch'
+    '\u0448': 'sh'
+    '\u0449': 'sht'
+    '\u044a': 'a'
+    '\u044c': 'y'
+    '\u044e': 'yu'
+    '\u044f': 'ya'
+
+    # note 2
+    '\u046A': "U\u0306" # Ѫ
+    '\u046B': "u\u0306" # ѫ
+
+    # note[3]
+    '\u0462': "YE" # Ѣ
+    '\u0463': "ye" # ѣ