Jump to content

Module:mai-translit

Wiktionary වෙතින්

This module will transliterate Maithili භාෂාව text. 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:mai-translit/testcases.

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.

-- Transliteration for Maithili

local export = {}
local gsub = mw.ustring.gsub
local match = mw.ustring.match

local conv = {
	-- consonants
	["क"] = "k", ["ख"] = "kh", ["ग"] = "g", ["घ"] = "gh", ["ङ"] = "ṅ",
	["च"] = "c", ["छ"] = "ch", ["ज"] = "j", ["झ"] = "jh", ["ञ"] = "ñ",
	["ट"] = "ṭ", ["ठ"] = "ṭh", ["ड"] = "ḍ", ["ढ"] = "ḍh", ["ण"] = "ṇ",
	["त"] = "t", ["थ"] = "th", ["द"] = "d", ["ध"] = "dh", ["न"] = "n",
	["प"] = "p", ["फ"] = "ph", ["ब"] = "b", ["भ"] = "bh", ["म"] = "m",
	["य"] = "y", ["र"] = "r", ["ल"] = "l", ["व"] = "v", ["ळ"] = "ḷ",
	["श"] = "ś", ["ष"] = "ṣ", ["स"] = "s", ["ह"] = "h",
	["क़"] = "q", ["ख़"] = "x", ["ग़"] = "ġ", ["ऴ"] = "ḻ",
	["ज़"] = "z", ["झ़"] = "ž", ["ड़"] = "ṛ", ["ढ़"] = "ṛh",
	["फ़"] = "f", ["ऩ"] = "ṉ", ["ऱ"] = "ṟ",

	-- vowel diacritics
	["ि"] = "i", ["ु"] = "u", ["े"] = "ē", ["ॆ"] = "e", ["ो"] = "ō", ["ॊ"] = "o", ["ा"] = "ā", ["ी"] = "ī", ["ू"] = "ū",
	["ृ"] = "r̥", ["ॄ"] = "r̥̄", ["ै"] = "ai",["ौ"] = "au",["◌ꣿ"] = "ě", ["ꣿ"] = "ě", ["ॏ"] = "ǒ", ["ऺ"] = "â", ["ॅ"] = "ê",["ॉ"] = "ô",


	-- vowel signs
	["अ"] = "a", ["इ"] = "i", ["उ"] = "u", ["ए"] = "ē", ["ऎ"] = "e", ["ओ"] = "ō", ["आ"] = "ā", ["ई"] = "ī", ["ऊ"] = "ū", ["व़"] = "ö", ["य़"] = "ë",
	["ऋ"] = "r̥", ["ॠ"] = "r̥̄", ["ऐ"] = "ai", ["औ"] = "au", ["ꣾ"] = "ě",  ["ॵ"] = "ǒ", ["ऒ"] = "o", ["ॴ"] = "ä", ["ऍ"] = "ê", ["ऑ"] = "ô",



	["२"] = "²", ["ऽ"] = "²",
    ["꣱"] = "ô", 
	["ँ"] = "̃", -- chandrabindu
	["ं"] = "̃", -- anusvara
	["ः"] = "ḥ", -- visarga
	["्"] = "", -- virama
	["ॐ"] = "ōm̐", -- om

	-- numerals
	["०"] = "0", ["१"] = "1", ["२"] = "2", ["३"] = "3", ["४"] = "4", ["५"] = "5", ["६"] = "6", ["७"] = "7", ["८"] = "8", ["९"] = "9",

	-- punctuation
	["।"] = ".", -- danda
	["॥"] = ".", -- double danda
	["+"] = "", -- compound separator

	-- abbreviation sign
	["॰"] = "."
}

local nasal_assim = {
	["क"] = "ङ", ["ख"] = "ङ", ["ग"] = "ङ", ["घ"] = "ङ",
	["च"] = "ञ", ["छ"] = "ञ", ["ज"] = "ञ", ["झ"] = "ञ",
	["ट"] = "ण", ["ठ"] = "ण", ["ड"] = "ण", ["ढ"] = "ण",
	["प"] = "म", ["फ"] = "म", ["ब"] = "म", ["भ"] = "म", ["म"] = "म",
	["त"] = "न", ["थ"] = "न", ["द"] = "न", ["ध"] = "न", ["न"] = "न"
}
local perm_cl = {
	["म्ल"] = true, ["व्ल"] = true, ["न्ल"] = true
}

local all_cons, special_cons = "कखगघङचछजझञटठडढणतथदधनपफबभमयरलवसशषह", "छकखगतसहयथडढठपदणधरषटलवब भडचनशम"
local vowel, vowel_sign = "aिुृेोाीूैौॉॅॆॊऻऻॊॆॏ꣱’", "अइउएओआईऊऋॠऎऒॵॳॴऐऔऑऍ"
local syncope_pattern = '([' .. vowel .. vowel_sign .. '])(़?[' .. all_cons .. '])a(़?[' .. all_cons .. '])([ंँ]?[' .. vowel .. vowel_sign .. '])'


local function rev_string(text)
	local result, length = {}, mw.ustring.len(text)
	for i = length, 1, -1 do
		table.insert(result, mw.ustring.sub(text, i, i))
	end
	return table.concat(result)
end
function export.tr(text, lang, sc)
	text =
		gsub(
		text,
		"([" .. all_cons .. "]़?)([" .. vowel .. "्]?)",
		function(c, d)
			return c .. (d == "" and "a" or d)
		end
	)
	for word in mw.ustring.gmatch(text, "[ऀ-ॿa]+") do
		local orig_word = word
		word = rev_string(word)
		word = gsub(word, '^a(़?)([' .. all_cons .. '])(.)(.?)', function(opt, first, second, third)
			return (((match(first, '[' .. special_cons .. ']') and match(second, '्') and not perm_cl[first..second..third])
				or match(first .. second, 'य[ी]'))
				and 'a' or "") .. opt .. first .. second .. third end)

while match(word, syncope_pattern) do
																																																																																																																																																												word = gsub(word, syncope_pattern, '%1%2ᵊ%3%4')
end
	word =
			gsub(
			word,
			"(.?)ं(.)",
			function(succ, prev)
				return succ ..
					(succ .. prev == "a" and "्म" or
						(succ == "" and match(prev, "[" .. vowel .. "]") and "̃" or nasal_assim[succ] or "̃")) ..
						prev
			end
		)

		local escaped_orig_word = gsub(orig_word, "%+", "")
		text = gsub(text, orig_word, rev_string(word))
		text = gsub(text, "ज्ञ", "gy")
        text = gsub(text, "इऺ", "ï" )         
        text = gsub(text, "उऺ",  "ü" ) 
        text = gsub(text, "ॳ",  "â" )
        text = gsub(text, "अ꣱", "ô")
	end

	text = gsub(text, ".़?", conv)
	text = gsub(text, "ā([iu])̃", "ā͠%1")
	text = gsub(text, "uu", "u")
	text = gsub(text, "([iuïüëöīāūôûî])â", "%1")
    text = gsub(text, "([iuïüëöīāūôûî])ᵊ", "%1")
    text = gsub(text, "aᵊ", "ᵊ")
    text = gsub(text, "([îûëö])a", "%1")
    text = gsub(text, "aâ", "â")
	text = gsub(text, "ii", "i")
	text = gsub(text, "([iīaāuūeoâᵊ])a", "%1")
    text = gsub(text, "i$", "ɨ")
    text = gsub(text, "u$", "ʉ")
    text = gsub(text, "ᵊ$", "ᵊ̆")
	text = gsub(text, "[<>]", "")
	return mw.ustring.toNFC(text)
end
return export
"https://si.wiktionary.org/w/index.php?title=Module:mai-translit&oldid=29364" වෙතින් සම්ප්‍රවේශනය කෙරිණි