metadata {
authority_id: bgnpcgn id: 2008 language: iso-639-2:che source_script: Cyrl destination_script: Latn name: Table of Correspondences for Chechen (Cyrillic-Roman) (2008 Agreement) url: https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/835782/TABLE_OF_CORRESPONDENCES_FOR_CHECHEN.pdf creation_date: 2008 confirmation_date: 2019-07 description: | Chechen is an official language within Chechnya, one of the republics of the Russian Federation. It will normally be encountered in Cyrillic script, in which case it should be romanized by means of the Cyrillic-Roman table of correspondences given below. notes: - The letter ə is used to represent short a; a is used for long a. - Ye is used word- and syllable-initially. This Cyrillic letter may be encountered as the ligature ie in Chechen-Roman sources. - This character occurs only in loan words. - q in the combination ккх (qq) and q̇in the combination ккъ (q̇q̇) - ŋ when preceding vowel is nasalized. - This Cyrillic letter may be encountered as the ligature ꭣ [U+AB63] or the diphthong oa in Chechen Roman sources. - Unless in the combinations гӀ, кӀ, пӀ, тӀ, хӀ, цӀ and чӀ. - | An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the unmodified letters of the basic Roman script is: All apostrophes appearing in romanization are U+2019 Ə (U+018F) ə (U+0259) Ä (U+00C4) ä (U+00E4) Ġ (U+0047+0307) ġ (U+0067+0307) Z̵ (U+005A+0335) z̵ (U+007A+0335) Q̇ (U+0051+0307) q̇ (U+0071+0307) Ŋ (U+014A) ŋ (U+014B) Ö (U+00D6) ö (U+00F6) Ü (U+00DC) ü (U+00FC) Ẋ (U+0058+0307) ẋ (U+0078+0307) Ċ (U+0043+0307) ċ (U0063+0307) Ç (U+00C7) ç (U+00E7) Ç̇ (U+00C7+0307) ç̇ (U+00E7+0307) Ş (U+015E) ş (U+015F) - 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 "кӏант", "khant" test "зуда", "zuda" test "пхьагал", "pẋagal" test "наж", "naz̵" test "мангал", "mangal" test "Ӏаж", "Jaz̵" test "Нохчийн Википеди", "Noxçiyn Vikipedi" test "сагӏадаккхар", "saġadaqqar" test "йеза", "yeza" test "еара", "yeara" test "елха", "yelxa"
}
stage {
# RULES # note[2] sub boundary + "\u0415", "Ye", not_before: boundary + "\u2019" # Е in initial position -> Ye sub boundary + "\u0435", "ye", not_before: boundary + "\u2019" # е in initial position -> ye # note[4] sub "\u043A\u043A\u0445", "qq" sub "\u043A\u043A\u042A", "q̇q̇" sub "\u041A\u041A\u0445", "QQ" sub "\u041A\u041A\u042A", "Q̇Q̇" # CHARACTERS parallel { sub "\u0410", any(["A", "Ə"]) # А note[1] sub "\u0410\u044C", "Ä" # Аь -> Ä sub "\u0411", "B" # Б sub "\u0412", "V" # В sub "\u0413", "G" # Г sub "\u0413\u04C0", "Ġ" # ГӀ -> Ġ sub "\u0414", "D" # Д sub "\u0415", "E" # Е note[2] sub "\u0401", "Yo" # Ё note[3] sub "\u0416", "Z̵" # Ж -> Ƶ sub "\u0417", "Z" # З sub "\u0418", "I" # И sub "\u042B", "Y" # Й sub "\u041A", "K" # К note[4] sub "\u041A\u0445", "Q" # Кх note[4] sub "\u041A\u044A", "Q̇" # Къ -> Q̇ note[4] sub "\u041A\u04C0", "Kh" # КӀ note[4] sub "\u041B", "L" # Л sub "\u041C", "M" # М sub "\u041D", any(["N", "Ŋ"]) # Н note[5] sub "\u041E", "O" # О note[6] sub "\u041E\u044C", "Ö" # Оь -> Ö sub "\u041F", "P" # П sub "\u041F\u04C0", "Ph" # ПӀ sub "\u0420", "R" # Р sub "\u0421", "S" # С sub "\u0422", "T" # Т sub "\u0422\u04C0", "Th" # TӀ sub "\u0423", "U" # У sub "\u0423\u044C", "Ü" # Уь -> Ü sub "\u0424", "F" # Ф sub "\u0425", "X" # Х sub "\u0425\u044C", "Ẋ" # Хь -> Ẋ sub "\u0425\u04C0", "H" # ХӀ sub "\u04B8", "C" # Ц sub "\u04B8\u04C0", "Ċ" # ЦӀ -> Ċ sub "\u0427", "Ç" # Ч -> Ç sub "\u0427\u04C0", "Ç̇" # ЧӀ -> Ç̇ sub "\u0428", "Ş" # Ш -> Ş sub "\u0429", "ŞÇ" # Щ -> ŞÇ note[3] sub "\u042A", "’" # Ъ note[3] sub "\u042B", "Y" # Ы sub "\u042C", "" # Ь note[3] sub "\u042D", "E" # Э sub "\u042E", "Yu" # Ю sub "\u042E\u044C", "Yü" # Юь -> Yü sub "\u042F", "Ya" # Я sub "\u042F\u044C", "Yä" # Яь -> Yä sub "\u04C0", "J" # Ӏ note[7] sub "\u0430", any(["a", "ə"]) # а note[1] sub "\u0430\u044C", "ä" # аь -> ä sub "\u0431", "b" # б sub "\u0432", "v" # в sub "\u0433", "g" # г sub "\u0433\u04CF", "ġ" # гӏ -> ġ sub "\u0434", "d" # д sub "\u0435", "e" # е note[2] sub "\u0451", "yo" # ё note[3] sub "\u0436", "z̵" # ж -> ƶ sub "\u0437", "z" # з sub "\u0438", "i" # и sub "\u0439", "y" # й sub "\u043A", "k" # к note[4] sub "\u043A\u0445", "q" # кх note[4] sub "\u043A\u044A", "q̇" # къ -> q̇ note[4] sub "\u043A\u04CF", "kh" # кӏ note[4] sub "\u043B", "l" # л sub "\u043C", "m" # м sub "\u043D", any(["n", "ŋ"]) # н note[5] sub "\u043E", "o" # о note[6] sub "\u043E\u044C", "ö" # оь -> ö sub "\u043F", "p" # п sub "\u0440", "r" # р sub "\u0441", "s" # с sub "\u0442", "t" # т sub "\u0442\u04CF", "th" # тӏ sub "\u0443", "u" # у sub "\u0443\u044C", "ü" # Уь -> ü sub "\u0444", "f" # ф sub "\u0445", "x" # х sub "\u0445\u044C", "ẋ" # хь -> ẋ sub "\u0445\u04CF", "h" # хӏ sub "\u04B9", "c" # ц sub "\u04B9\u04CF", "с̇" # цӏ -> ċ sub "\u0447", "ç" # ч -> ç sub "\u0447\u04CF", "cç̇" # чӏ -> ç̇ sub "\u0448", "ş" # ш -> ş sub "\u0449", "şç" # щ -> şç note[3] sub "\u044A", "’" # ъ note[3] sub "\u044B", "y" # ы sub "\u044C", "" # ь note[3] sub "\u044D", "e" # э sub "\u044E", "yu" # ю sub "\u044E", "yü" # юь -> yü sub "\u044F", "ya" # я sub "\u044F", "yä" # яь -> yä sub "\u04CF", "j" # ӏ note[7] } compose
}