interscript 0.1.2 → 0.1.3

data/maps/alalc-mkd-cyrl-latn-1997.yaml

@@ -0,0 +1,114 @@
+---
+authority_id: alalc
+id: 1997
+language: mkd
+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-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