metadata {
authority_id: bgnpcgn id: 2005 language: iso-639-2:srp source_script: Cyrl destination_script: Latn name: Table of Correspondences for Serbian (Cyrillic-Roman) (2005 Agreement) url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/816783/TABLE_OF_CORRESPONDENCES_FOR_SERBIAN.pdf creation_date: 2005 confirmation_date: 2019-06 description: | The tabulation below reflects the Serbian Cyrillic alphabet and the standard Roman script equivalents used in both Serbia and Montenegro. notes: - The Serbian 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 digraph dj(Dj) will occasionally be found as an alternative form of đ(Đ). - The Serbian Cyrillic lowercase italic П may sometimes be seen as ӣ. There is no specific Unicode encoding for this variant form so a comparable character has been used here for illustrative purposes. - The Serbian Cyrillic lowercase italic Т may sometimes be seen as w. 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: | Đ (U+0110) | đ (U+0111) | | Ž (U+017D) | ž (U+017E) | | Lj (U+01C8)* | lj (U+01C9)* | | Ć (U+0106) | ć (U+0107) | | 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 Roman-script columns show only lowercase forms but, when applying the table, uppercase and lowercase Roman letters as appropriate should be used.
}
tests {
test "Шупља Стена", "Šuplja Stena" test "Чукарица", "Čukarica" test "Црна Трава", "Crna Trava" test "Херцег Нови", "Herceg Novi" test "Улцињ", "Ulcinj" test "Ужице", "Užice" test "Тресаначка Река", "Tresanačka Reka" test "Сјеница", "Sjenica" test "Рожаје", "Rožaje" test "Пљевља", "Pljevlja" test "Оџаци", "Odžaci" test "Никшић", "Nikšić" test "Медвеђа", "Medveđa" test "Лозница", "Loznica" test "Књажевац", "Knjaževac" test "Зрењанин", "Zrenjanin" test "Житорађа", "Žitorađa" test "Ервеник", "Ervenik" test "Доње Љупче", "Donje Ljupče" test "Гусиње", "Gusinje" test "ГУСИЊЕ", "GUSINJE" test "Врњачка Бања", "Vrnjačka Banja" test "Бијело Поље", "Bijelo Polje" test "Алибунар", "Alibunar"
}
aliases {
def_alias srp_multichar, any(["Lj", "Nj", "Dž"]) def_alias srp_latupper, any("A".."Z")
}
stage {
# CHARACTERS parallel { sub "А", "A" sub "Б", "B" sub "В", "V" sub "Г", "G" sub "Д", "D" sub "Ђ", "Đ" # Đ sub "Е", "E" sub "Ж", "Ž" # Ž sub "З", "Z" sub "И", "I" sub "Ј", "J" sub "К", "K" sub "Л", "L" sub "Љ", "Lj" sub "М", "M" sub "Н", "N" sub "Њ", "Nj" sub "О", "O" sub "П", "P" sub "Р", "R" sub "С", "S" sub "Т", "T" sub "Ћ", "Ć" # Ć sub "У", "U" sub "Ф", "F" sub "Х", "H" sub "Ц", "C" sub "Ч", "Č" # Č sub "Џ", "Dž" # Dž sub "Ш", "Š" # Š sub "а", "a" sub "б", "b" sub "в", "v" sub "г", "g" sub "д", "d" sub "ђ", "đ" # đ sub "е", "e" sub "ж", "ž" # ž sub "з", "z" sub "и", "i" sub "ј", "j" sub "к", "k" sub "л", "l" sub "љ", "lj" sub "м", "m" sub "н", "n" sub "њ", "nj" sub "о", "o" sub "п", "p" sub "р", "r" sub "с", "s" sub "т", "t" sub "ћ", "ć" # ć́ sub "у", "u" sub "ф", "f" sub "х", "h" sub "ц", "c" sub "ч", "č" # č sub "џ", "dž" # dž sub "ш", "š" # š } # POSTRULES sub srp_multichar, upcase, before: srp_latupper sub srp_multichar, upcase, after: srp_latupper compose
}