Module:mai-Tirh-translit

From Wiktionary, the free dictionary
Jump to navigation Jump to search

This module will transliterate text in the Tirhuta script. 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-Tirh-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.

-- Transliteration for Maithili in Tirhuta script

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

local conv = {
	-- consonants
	["๐‘’"] = "k", ["๐‘’"] = "kh", ["๐‘’‘"] = "g", ["๐‘’’"] = "gh", ["๐‘’“"] = "แน…",
	["๐‘’”"] = "c", ["๐‘’•"] = "ch", ["๐‘’–"] = "j", ["๐‘’—"] = "jh", ["๐‘’˜"] = "รฑ",
	["๐‘’™"] = "แนญ", ["๐‘’š"] = "แนญ", ["๐‘’›"] = "แธ", ["๐‘’œ"] = "แธh", ["๐‘’"] = "แน‡",
	["๐‘’ž"] = "t", ["๐‘’Ÿ"] = "th", ["๐‘’ "] = "d", ["๐‘’ก"] = "dh", ["๐‘’ข"] = "n",
	["๐‘’ฃ"] = "p", ["๐‘’ค"] = "ph", ["๐‘’ฅ"] = "b", ["๐‘’ฆ"] = "bh", ["๐‘’ง"] = "m",
	["๐‘’จ"] = "y", ["๐‘’ฉ"] = "r", ["๐‘’ช"] = "l", ["๐‘’ซ"] = "v", ["๐‘’ช๐‘“ƒ"] = "แธท",
	["๐‘’ฌ"] = "ล›", ["๐‘’ญ"] = "แนฃ", ["๐‘’ฎ"] = "s", ["๐‘’ฏ"] = "h",
	["๐‘’›๐‘“ƒ"] = "แน›", ["๐‘’œ๐‘“ƒ"] = "แน›h",

	-- vowel diacritics
	["๐‘’ฑ"] = "i", ["๐‘’ณ"] = "u", ["๐‘’น"] = "ฤ“", ["๐‘’บ"] = "e", ["๐‘’ผ"] = "ล", ["๐‘’ฝ"] = "o", ["๐‘’ฐ"] = "ฤ", ["๐‘’ฒ"] = "ฤซ", ["๐‘’ด"] = "ลซ",
	["๐‘’ต"] = "rฬฅ", ["๐‘’ถ"] = "rฬฅฬ„", ["๐‘’ป"] = "ai", ["๐‘’พ"] = "au", ["๐‘’ท"] = "lฬฅ", ["๐‘’ธ"] = "lฬฅฬ„",
	
	-- vowels
	["๐‘’"] = "a", ["๐‘’‚"] = "ฤ", ["๐‘’ƒ"] = "i", ["๐‘’„"] = "ฤซ", ["๐‘’…"] = "u", ["๐‘’†"] = "ลซ",
	["๐‘’‡"] = "rฬฅ", ["๐‘’ˆ"] = "rฬฅฬ„", ["๐‘’‰"] = "lฬฅ", ["๐‘’Š"] = "lฬฅฬ„",
	["๐‘’‹"] = "ฤ“", ["๐‘’Œ"] = "ai", ["๐‘’"] = "ล", ["๐‘’Ž"] = "au", 
	 ["เฅจ"] = "โ€™", ["๐‘’๐‘’บ"] = "รช",["๐‘’๐‘’ฝ"] = "รด",

    ["เคฝ"] = "ยฒ", -- avagraha
	["๐‘’ฟ"] = "ฬƒ", -- chandrabindu
	["๐‘“€"] = "ฬƒ", -- anusvara
	["๐‘“…"] = "ฬƒ", -- gvang
	["๐‘“"] = "แธฅ", -- visarga
	["๐‘“‚"] = "", -- virama
	["๐‘“‡"] = "omฬ", -- om

	-- numerals
	["๐‘“"] = "0", ["๐‘“‘"] = "1", ["๐‘“’"] = "2", ["๐‘““"] = "3", ["๐‘“”"] = "4", ["๐‘“•"] = "5", ["๐‘“–"] = "6", ["๐‘“—"] = "7", ["๐‘“˜"] = "8", ["๐‘“™"] = "9",

	-- punctuation
	["เฅค"] = ".", -- danda
	["เฅฅ"] = ".", -- double danda
	["+"] = "", -- compound separator
	-- abbreviation sign
	["เฅฐ"] = "."
}

local nasal_assim = {
	["๐‘’"] = "๐‘’“", ["๐‘’"] = "๐‘’“", ["๐‘’‘"] = "๐‘’“", ["๐‘’’"] = "๐‘’“",
	["๐‘’”"] = "๐‘’˜", ["๐‘’•"] = "๐‘’˜", ["๐‘’–"] = "๐‘’˜", ["๐‘’—"] = "๐‘’˜", ["๐‘’˜"] = "๐‘’˜",
	["๐‘’™"] = "๐‘’", ["๐‘’š"] = "๐‘’", ["๐‘’›"] = "๐‘’", ["๐‘’œ"] = "๐‘’",
	["๐‘’ž"] = "๐‘’ข", ["๐‘’Ÿ"] = "๐‘’ข", ["๐‘’ "] = "๐‘’ข", ["๐‘’ก"] = "๐‘’ข", ["๐‘’ข"] = "๐‘’ข",
	["๐‘’ฃ"] = "๐‘’ง", ["๐‘’ค"] = "๐‘’ง", ["๐‘’ฅ"] = "๐‘’ง", ["๐‘’ฆ"] = "๐‘’ง", ["๐‘’ง"] = "๐‘’ง"
}
local perm_cl = {
	["๐‘’ง๐‘“‚๐‘’ช"] = true
}
local all_cons, special_cons = "๐‘’๐‘’๐‘’‘๐‘’’๐‘’“๐‘’”๐‘’•๐‘’–๐‘’—๐‘’˜๐‘’™๐‘’š๐‘’›๐‘’œ๐‘’๐‘’ž๐‘’Ÿ๐‘’ ๐‘’ก๐‘’ข๐‘’ฃ๐‘’ค๐‘’ฅ๐‘’ฆ๐‘’ง๐‘’จ๐‘’ฉ๐‘’ช๐‘’ซ๐‘’ฎ๐‘’ฌ๐‘’ญ๐‘’ฏ๐‘’ฉ", "๐‘’•๐‘’๐‘’๐‘’‘๐‘’ž๐‘’ฎ๐‘’ฏ๐‘’จ๐‘’Ÿ๐‘’›๐‘’œ๐‘’š๐‘’ฃ๐‘’ ๐‘’๐‘’ก๐‘’ฉ๐‘’ญ๐‘’™๐‘’ช๐‘’ซ๐‘’ฅ๐‘’ฆ๐‘’›๐‘’”๐‘’ข๐‘’ฌ๐‘’ง"
local vowel, vowel_sign = "a๐‘’ฑ๐‘’ณ๐‘’ต๐‘’น๐‘’ผ๐‘’ฐ๐‘’ฒ๐‘’ด๐‘’ป๐‘’พ๐‘’ฐ๐‘’ป๐‘’ฝ๐‘’ฐ๐‘’ฐ๐‘’ฝ๐‘’บ", "๐‘’๐‘’ƒ๐‘’…๐‘’‹๐‘’๐‘’‚๐‘’„๐‘’†๐‘’‡๐‘’ˆ๐‘’๐‘’บ๐‘’๐‘’ฝ๐‘’ซ๐‘“ƒ๐‘’จ๐‘“ƒ๐‘’๐‘’‚๐‘’Œ๐‘’Ž๐‘’‚๐‘’‹"
local syncope_pattern = '([' .. vowel .. vowel_sign .. '])(๐‘“ƒ?[' .. all_cons .. '])a(๐‘“ƒ?[' .. all_cons .. '])([๐‘“€๐‘’ฟ]?[' .. 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 .. "]๐‘“ƒ?)([" .. vowel .. "๐‘“‚]?)",
		function(c, d)
			return c .. (d == "" and "a" or d)
		end
	)

	for word in mw.ustring.gmatch(text, "[๐‘’ฟ-เฅฅa]+") do
		local orig_word = word

		word = rev_string(word)
		
		word = gsub(
			word,
			'^a(๐‘“ƒ?)([' .. all_cons .. '])(.)(.?)',
			function(opt, first, second, third)
				local a = ""
				if match(first, '[' .. special_cons .. ']')
					and match(second, '๐‘“‚')
					and not perm_cl[first..second..third]
					or match(first .. second, '๐‘’จ[๐‘’ฒ๐‘’บ]') then
						a = "a"
				end
				
				return a .. opt .. first .. second .. third
			end
		)

	while match(word, syncope_pattern) do
			word = gsub(word, syncope_pattern, "%1%2แตŠ%3%4")
		end

		word =
			gsub(
			word,
			"(.?)๐‘“€(.)",
			function(succ, prev)
				return succ ..
					(succ .. prev == "a" and "๐‘“‚๐‘’ง" or
						(succ == "" and match(prev, "[" .. vowel .. "]") and "ฬƒ" or nasal_assim[succ] or "ฬƒ")) ..
						prev
			end
		)

		local escaped_orig_word = gsub(orig_word, "%+", "")
		text = gsub(text, orig_word, rev_string(word))
		text = gsub(text, "๐‘’–๐‘“‚๐‘’˜", "gy")
	end
	text = gsub(text, "ฤ([iu])ฬƒ", "ฤอ %1")
	text = gsub(text, "uu", "u")
	text = gsub(text, "aรข", "รข")
	text = gsub(text, "ii", "i")
	text = gsub(text, "([iฤซaฤuลซeoรข])a", "%1")
	text = gsub(text, "[<>]", "")
	text = gsub(text, ".๐‘“ƒ?", conv)
	return mw.ustring.toNFC(text)
end

return export