Module:tt-translit

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

Useful links: subpage list • links • transclusions • testcases • sandbox (diff)

This module will transliterate Tatar language text per WT:TT TR. This may not match the Latin spelling used in Tatar. Г is replaced by the module with ğ and к with q after а, о, у, ы or in word start before them, otherwise they are turned into g and k (only works for the preceding vowels) per WT:TT 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:tt-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 the transliteration fails, returns nil.

---

local export = {}

local rsubn = mw.ustring.gsub

-- version of rsubn() that discards all but the first return value
local function rsub(term, foo, bar)
	local retval = rsubn(term, foo, bar)
	return retval
end

-- apply rsub() repeatedly until no change
local function rsub_repeatedly(term, foo, bar)
	while true do
		local new_term = rsub(term, foo, bar)
		if new_term == term then
			return term
		end
		term = new_term
	end
end

local tt = {
	["ү"]="ü",['Ү']='Ü',   ["т"]="t",['Т']='T', ["р"]="r",['Р']='R',   ["ф"]="f",['Ф']='F',
	["ю"]="yu",['Ю']='Yu', ["ш"]="ş",['Ш']='Ş', ["ь"]="’",['Ь']='’',   ["ъ"]="ʺ",['Ъ']='ʺ', ["н"]="n",['Н']='N', 
	["п"]="p",['П']='P',   ["й"]="y",['Й']='Y', ["л"]="l",['Л']='L',   ["з"]="z",['З']='Z', ["е"]="e",['Е']='E', 
	["г"]="g",['Г']='G',   ["б"]="b",['Б']='B', ["у"]="u",['У']='U',   ["с"]="s",['С']='S', ["х"]="x",['Х']='X',
	["ч"]="ç",['Ч']='Ç', ["щ"]="şç",['Щ']='Şç', ["я"]="ya",['Я']='Ya', ["ы"]="ı",['Ы']='I', ["э"]="e",['Э']='E', 
	["м"]="m",['М']='M',   ["о"]="o",['О']='O', ["ө"]="ö",['Ө']='Ö',   ["и"]="i",['И']='İ', ["ё"]="yo",['Ё']='Yo',
	["ж"]="j",['Ж']='J',   ["к"]="k",['К']='K', ["д"]="d",['Д']='D',   ["в"]="w",['В']='W', ["ц"]="ts",['Ц']='Ts',
	["а"]="a",['А']='A',   ["ң"]="ñ",['Ң']='Ñ', ["җ"]="c",['Җ']='C',   ["һ"]="h",['Һ']='H', ["ә"]="ä",['Ә']='Ä'
};

function export.tr(text, lang, sc)
	text = rsub(
		text,
		"([АОӘУЫЕЯЁЮИЕаоәуыэяёюиеъь%A][́̀]?)([Ее])",
		function(a,e) return a..(e=='е' and 'ye' or 'Ye') end
	)
	
	-- ү/у should be transliterated as w after vowels (except у/ү itself)
	text = rsub_repeatedly(text, "([АаЕеЭэЯяӘәИиӨөЫы])[үу]", "%1w")
	text = rsub_repeatedly(text, "([УҮүу])([АаЫыОоУуӘәЕеИиӨөҮү])", "%1w%2")
	
	text = rsub(text, "^Е", "Ye")
	text = rsub(text, "^е","ye")
	text = rsub(text, "ия$", "iyä") --not last word end handled in code end
	
	-- Deal with dual nature of к, г, transliterated either to "front" variants
	-- k/g or "back" variants q/ğ. The back variants occur before hard signs
	-- (Ъ/ъ), which then disappear, and also in the vicinity of the back vowels
	-- а/о/у/ы (and their capital equivalents А/О/У/Ы). The code below that
	-- handles this appears to say that the sound of word-initial к/г is
	-- determined by the following vowel, and the sound of non-word-initial
	-- к/г is determined by the preceding vowel. FIXME: Not sure if this is
	-- correct.
	
	-- glottal stop
	text = rsub(text, "([АаЫыОоУуӘәЭэИиӨөҮүЕе])([ЪъЬьЭэ])", "%1'")
	
	local t = {['К']='Q',['к']='q',['Г']='Ğ',['г']='ğ'}
	text = rsub(text, "([КкГг])([Ъъ])", function(a,b) return t[a] end)
	text = rsub(text,
		"(%a?)([КкГг])(.?)",
		function(b,c,a)
			return b .. (mw.ustring.match(b>'' and b or a,"[АОУЫаоуы]") and t[c] or tt[c]) .. a
		end
	)

	text = rsub(text, "ия%A", "iyä")
	text = rsub(text, ".", tt)
	return text
end

return export