Module:tcy-Tutg-translit

From Linguifex
Jump to navigation Jump to search

This module will transliterate Tulu 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:tcy-Tutg-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 gsub = mw.ustring.gsub
 
local consonants = {
	['𑎒'] = 'k', ['𑎓'] = 'kh', ['𑎔'] = 'g', ['𑎕'] = 'gh', ['𑎖']='ṅ',
	['𑎗'] = 'c', ['𑎘'] = 'ch', ['𑎙'] = 'j', ['𑎚'] = 'jh', ['𑎛']='ñ',
	['𑎜'] = 'ṭ', ['𑎝'] = 'ṭh', ['𑎞'] = 'ḍ', ['𑎟'] = 'ḍh', ['𑎠']='ṇ',
	['𑎡'] = 't',  ['𑎢'] = 'th', ['𑎣'] = 'd', ['𑎤'] = 'dh', ['𑎥']='n',
	['𑎦'] = 'p', ['𑎧'] = 'ph', ['𑎨'] = 'b', ['𑎩'] = 'bh' , ['𑎪']='m',
	['𑎫'] = 'y', ['𑎬'] = 'r', ['𑏑'] = 'r', ['𑎭'] = 'l',  ['𑎳'] = 'ḷ', ['𑎮'] = 'v',  ['𑎯'] = 'ś',  ['𑎰'] = 'ṣ', ['𑎱'] = 's', ['𑎲'] = 'h', 
}

local diacritics = {
	['𑎸'] = 'ā', ['𑎹'] = 'i',  ['𑎺'] =  'ī',['𑎻'] = 'u', ['𑎼'] = 'ū',
	['𑎽'] = 'r̥', ['𑎾'] ='r̥̄', ['𑎿'] ='l̥', ['𑏀'] = 'l̥̄', ['𑏂'] = 'ē', ['𑏅'] = 'ai', ['𑏇'] = 'ō', ['𑏈'] = 'au', ['𑏎'] = '', ['𑏏'] = '',
}
local tt = {
	-- vowels
	['𑎀'] = 'a', ['𑎁'] ='ā' , ['𑎂'] ='i' , ['𑎃'] = 'ī' , ['𑎄'] = 'u' , ['𑎅'] = 'ū' , 
	['𑎆'] = 'r̥', ['𑎇'] ='r̥̄', ['𑎈'] ='l̥', ['𑎉'] = 'l̥̄', ['𑎋'] = 'ē', ['𑎎'] ='ai', ['𑎐'] ='ō', ['𑎑'] = 'au',
	-- other symbols
	['𑎷'] = 'ṁ',-- avagraha
	['𑏌'] = 'ṁ',-- anusvara
	['𑏍'] = 'ḥ' ,  -- visarga
	['𑏗'] = 'ōm' , -- om
}

-- translit any words or phrases
function export.tr(text, lang, sc)
	local VIRAMA = '𑏎'
	
	-- final virama rules
	if lang == "tcy" then
		text = gsub(text, VIRAMA .. "([%,%.%!%?%:%;]?)$", VIRAMA .. "ŭ%1")
		text = gsub(text, VIRAMA .. "([%,%.%!%?%:%;]?) ", VIRAMA .. "ŭ%1 ")
	end
	text = gsub(
		text,
		'([𑎒𑎓𑎔𑎕𑎖𑎗𑎘𑎙𑎚𑎛𑎜𑎝𑎞𑎟𑎠𑎡𑎢𑎣𑎤𑎥𑎦𑎧𑎨𑎩𑎪𑎫𑎬𑎭𑎮𑎯𑎰𑎱𑎲𑎳𑎴])'..
		'([𑎸𑎹𑎺𑎻𑎼𑎽𑎾𑎿𑏀𑏅𑏅𑎸𑏈𑏎𑏏]?)',
		function(c, d)
			if d == "" then        
				return consonants[c] ..'a'
			else
				return consonants[c] .. diacritics[d]
			end
		end)
	
	text = gsub(text,'.', tt)
	
	-- anusvara
	text = gsub(text,'ṁ([kgṅ])','ṅ%1')
	text = gsub(text,'ṁ([cjñ])','ñ%1')
	text = gsub(text,'ṁ([ṭḍṇ])','ṇ%1')
	text = gsub(text,'ṁ([tdn])','n%1')
	text = gsub(text,'ṁ([pbm])','m%1')
	
	return text
end
 
return export