Module:inc-mas-translit

The following documentation is located at Module:inc-mas-translit/documentation. ^[edit]

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

This module will transliterate Middle Assamese language 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:inc-mas-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 Assamese

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

local conv = {
	-- consonants
	["ক্ষ"] = "kh",
	["ক"] = "k",	["খ"] = "kh",	["গ"] = "g",	["ঘ"] = "gh",	["ঙ"] = "ṅ",
	["চ"] = "s",	["ছ"] = "s",	["জ"] = "z",	["ঝ"] = "zh",	["ঞ"] = "ñ",
	["ট"] = "t",	["ঠ"] = "th",	["ড"] = "d",	["ঢ"] = "dh",	["ণ"] = "n",
	["ত"] = "t",	["থ"] = "th",	["দ"] = "d",	["ধ"] = "dh",	["ন"] = "n",
	["প"] = "p",	["ফ"] = "ph",	["ব"] = "b",	["ভ"] = "bh",	["ম"] = "m",
	["য"] = "z",	["ৰ"] = "r",	["ল"] = "l",	["ৱ"] = "w", 
	["শ"] = "x",	["ষ"] = "x",	["স"] = "x",	["হ"] = "h",	
	["য়"] = "y",	["ড়"] = "r",	["ঢ়"] = "rh",

	-- vowel diacritics
	["’"] = "ö",	["ি"] = "i",	["ু"] = "u",	
	["ৃ"] = "ri",	["ে"] = "e",	["ে’"] = "ë",	["ো"] = "ü",
	["া"] = "a",	["ী"] = "i",	["ূ"] = "u",	["ৈ"] = "oi",	["ৌ"] = "ou",

	-- visarga
	["ঃ"] = "o",

	-- vowel signs
	["অ"] = "o", 	["অ’"] = "ó",	["ই"] = "i",	["উ"] = "u",	
	["ঋ"] = "ri",	["এ"] = "e", 	["এ’"] = "é",	["ও"] = "ü",
	["আ"] = "a",	["ঈ"] = "i",	["ঊ"] = "u",	["ঐ"] = "oi",	["ঔ"] = "ou",

	--hosonto
	["্"] = "",

	-- sondrobindu
	["ঁ"] = "̃",
	
	-- owogroho
	['ঽ']='’',
		
	-- onusor
	["ং"] = "ṅ",

	-- hosonto to, 
	["ৎ"] = "t",

	-- numerals
	["০"] = "0", ["১"] = "1", ["২"] = "2", ["৩"] = "3", ["৪"] = "4", 
	["৫"] = "5", ["৬"] = "6", ["৭"] = "7", ["৮"] = "8", ["৯"] = "9",
 
	-- punctuation
	["।"] = ".", -- dari
}

local conv2 = {
	["ক্ষ"] = "ḱ",	["খ"] = "ḱ",
	["ঘ"] = "ǵ",
	["ঙ"] = "ŋ",	["ং"] = "ŋ",
	["ঝ"] = "ź",
	["ঠ"] = "ṫ",	["থ"] = "ṫ",
	["ঢ"] = "ḋ",	["ধ"] = "ḋ",
	["ফ"] = "ṗ",
	["ভ"] = "ḃ",
	["ঢ়"] = "ŕ",
	["ৃ"] = "ṙ",	["ঋ"] = "ṙ",
	["ৈ"] = "ʏ",	["ঐ"] = "ʏ",
	["ৌ"] = "ɵ",	["ঔ"] = "ɵ",
}

local consonant, vowel, vowel_sign = "ক-হড়-য়ৰৱ", "oা-ৌ’", "অ-ঔ"
local c = "[" .. consonant .. "]"
local cc = "়?" .. c
local v = "[" .. vowel .. vowel_sign .. "]"
local syncope_pattern = "(" .. v .. cc .. v .. cc .. ")o(" .. cc .. "ঁ?" .. v .. ")"

local function rev_string(text)
	local result, length = "", mw.ustring.len(text)
	for i = 1, length do
		result = result .. mw.ustring.sub(text, length - i + 1, length - i + 1)
	end
	return result
end

function export.tr(text, lang, sc, mode)
	text = gsub(text, "([^ৰ])্য", "%1্য়")
	text = gsub(text, "্ব", "্ৱ")
	text = gsub(text, "[শষস]্", "চ্")
	text = gsub(text, "্স", "্চ")
	text = gsub(text, "[োও]ৱ", "্ও") 
	text = gsub(text, "ক্ষ", "খ")
	text = gsub(text, "’ৱ", "্অ’")
	text = gsub(text, "[ুুউ]ৱ(.)", "্উ%1")
	text = gsub(text, "[োও]ৱ(.)", "্ও%1")
	text = gsub(text, "োঁৱ(.)", "্ওঁ%1")
	text = gsub(text, "[ৌঔ]ৱ", "্ঔ")
	text = gsub(text, "[িই]য়(.)", "্ই%1") 
	text = gsub(text, "ৃয়", "্ঋ")
	text = gsub(text, "[েএ]য়(.)", "্এ%1")
	text = gsub(text, "[ে’এ’]য়", "্এ’")
	text = gsub(text, "[ৈঐ]য়(.)", "্ঐ%1")
	text = gsub(text, "[ীঈ]য়(.)", "্ঈ%1") 
	text = gsub(text, "[ীঈ]য়", "্ঈঅ") -- end
	text = gsub(text, "[ূূঊ]ৱ", "্ঊ") 
	text = gsub(text, "݁", "্অ")
	text = gsub(text, "ঃ", "্অ")
	text = gsub(text, "[࣪ܿ]", "্")
	text = gsub(text, "বাৰ" , "্বাৰ")
	text = gsub(text, "বিলাক", "্বিলাক")
	text = gsub(text, "টো" , "্টো")
	text = gsub(text, "খন" , "্খন")
	text = gsub(text, "ডাল" , "্ডাল")
	text = gsub(text, "খিনি" , "্খিনি")
	text = gsub(text, "জন" , "্জন")
	text = gsub(text, "জনী" , "্জনী")
	text = gsub(text, "গৰাকী" , "্গৰাকী")
	text = gsub(text, "সকল" , "্সকল")
	text = gsub(text, "কৈ" , "্কৈ")
text = gsub(text, "কে" , "্কে")
	text = gsub(text, "ফাল" , "্ফাল")
	text = gsub(text, "কেই" , "্কেই")
	text = gsub(text, "মান" , "্মান")
	text = gsub(text, "[িীইঈ]ঞ", "্ইঅ͂")
	text = gsub(text, "ঞ্", "ন্̃")
	
	text = gsub(text, "(" .. c .. "়?)([" .. vowel .. "’?্]?)", function(a, b)
		return a .. (b == "" and "o" or b) end)
	
	for word in mw.ustring.gmatch(text, "[ঁ-৽o’]+") do
		local orig_word = word
		word = rev_string(word)
		word = gsub(word, "^o(়?" .. c .. ")(ঁ?" .. v .. ")", "%1%2")
		while match(word, syncope_pattern) do
			word = gsub(word, syncope_pattern, "%1%2")
		end
		text = gsub(text, orig_word, rev_string(word))
	end
	
	if mode == "IPA" then
		text = gsub(text, ".[়’]?", conv2)
		text = gsub(text, ".", conv2)
	end
	
	text = gsub(text, ".[়’]?", conv)
	text = gsub(text, ".", conv)
	
	local consonants_Latn_no_h = "[b-df-gj-np-tv-z]"

	-- Cw
	text = gsub(text, "mw", "mb") -- special case
	text = gsub(text, "^(" .. consonants_Latn_no_h .. "h?)w", "%1") -- initial
	text = gsub(text, "hw", "hb")
	text = gsub(text, "(" .. consonants_Latn_no_h .. ")w", "%1%1") -- medial
	
	-- zñ
	text = gsub(text, "^zñ", "gy") -- initial
	text = gsub(text, "zñ", "gg") -- medial
	
	-- Cy
	text = gsub(text, "^khy", "kh" )
	text = gsub(text, "([aéeióoüu])(" .. consonants_Latn_no_h .. ")y", "%1i%2%2")

	-- final "b" has inherent vowel
	text = gsub(text, "b$", "bo")
	text = gsub(text, "b ", "bo ")
	
	-- final r conjuncts
	text = gsub(text, "r([kszt])o$", "r%1")
	text = gsub(text, "r([kszt])o ", "r%1 ")
	text = gsub(text, "rkho$", "rkh")
	text = gsub(text, "rkho ", "rkh ")
	
	if match(text, "[ঁ-৽]") and mode ~= "debug" then
		return nil
	else
		return mw.ustring.toNFC(text)
	end
end
 
return export