Module:kdr-translit

---

The following documentation is located at Module:kdr-translit/documentation. ^[edit] Categories were auto-generated by Module:module categorization. ^[edit]

Useful links: subpage list • links • transclusions • testcases • sandbox

This module will transliterate Karaim text per WT:KDR TR. The module should preferably not be called directly from templates or other modules. To use it from a template, use {{xlit}}. Within a module, use Module:languages#Language:transliterate.

For testcases, see Module:kdr-translit/testcases.

Functions

tr(text, lang, sc)

Transliterates a given piece of text written in the script specified by the code sc, and language specified by the code lang.

When transliteration fails, returns nil.

local export = {}

-- Digraphs (processed first)
local digraphs = {
    ["Дж"] = "C",  ["дж"] = "c",
    ["Къ"] = "Q",  ["къ"] = "q",
    ["Нъ"] = "Ñ",  ["нъ"] = "ñ",
    ["Хъ"] = "X",  ["хъ"] = "x",
    ["Гъ"] = "Ğ",  ["гъ"] = "ğ"
}

-- Single characters
local single_chars = {
    ["А"] = "A",   ["а"] = "a",
    ["Б"] = "B",   ["б"] = "b",
    ["В"] = "V",   ["в"] = "v",
    ["Г"] = "G",   ["г"] = "g",
    ["Д"] = "D",   ["д"] = "d",
    ["Е"] = "Ye",  ["е"] = "ye",
    ["Ж"] = "J",   ["ж"] = "j",
    ["З"] = "Z",   ["з"] = "z",
    ["И"] = "I",   ["и"] = "i",
    ["Й"] = "Y",   ["й"] = "y",
    ["К"] = "K",   ["к"] = "k",
    ["Л"] = "L",   ["л"] = "l",
    ["М"] = "M",   ["м"] = "m",
    ["Н"] = "N",   ["н"] = "n",
    ["О"] = "O",   ["о"] = "o",
    ["Ӧ"] = "Ö",   ["ӧ"] = "ö",
    ["П"] = "P",   ["п"] = "p",
    ["Р"] = "R",   ["р"] = "r",
    ["С"] = "S",   ["с"] = "s",
    ["Т"] = "T",   ["т"] = "t",
    ["У"] = "U",   ["у"] = "u",
    ["Ӱ"] = "Ü",   ["ӱ"] = "ü",
    ["Ф"] = "F",   ["ф"] = "f",
    ["Х"] = "H",   ["х"] = "h",
    ["Ц"] = "Ts",  ["ц"] = "ts",
    ["Ч"] = "Ç",   ["ч"] = "ç",
    ["Ш"] = "Ş",   ["ш"] = "ş",
    ["Щ"] = "Şç",  ["щ"] = "şç",
    ["Ъ"] = "ʺ",   ["ъ"] = "ʺ",
    ["Ы"] = "I",   ["ы"] = "ı",
    ["Ь"] = "ʹ",   ["ь"] = "ʹ",
    ["Э"] = "E",   ["э"] = "e",
    ["Ю"] = "Yu",  ["ю"] = "yu",
    ["Я"] = "Ya",  ["я"] = "ya"
}

function export.tr(text, lang, sc)
    -- Handle template invocations vs direct module calls
    if type(text) == "table" then
        text = text.args[1]
    end

    if not text or text == "" then
        return ""
    end

    -- If script is provided as a string code or object, validate if necessary
    -- (In Wiktionary, if sc is passed and it's not 'Cyrl', we usually don't transliterate)
    if sc and sc ~= "Cyrl" and type(sc) == "string" then
        return nil
    end

    -- Normalize Unicode to NFC form
    text = mw.ustring.toNFC(text)

    -- Step 1: Replace digraphs (cyr = Cyrillic key, lat = Latin value)
    for cyr, lat in pairs(digraphs) do
        text = mw.ustring.gsub(text, cyr, lat)
    end

    -- Step 2: Replace individual characters
    text = mw.ustring.gsub(text, ".", single_chars)

    return text
end

return export