Module:ml-translit

Definition from Wiktionary, the free dictionary
Jump to navigation Jump to search

This module will transliterate Malayalam 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:ml-translit/testcases.

Functions[edit]

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 consonants = {
	['ക']='k', ['ഖ']='kh', ['ഗ']='g', ['ഘ']='gh', ['ങ']='ṅ', 
	['ച']='c', ['ഛ']='ch', ['ജ']='j', ['ഝ']='jh', ['ഞ']='ñ', 
	['ട']='ṭ', ['ഠ']='ṭh', ['ഡ']='ḍ', ['ഢ']='ḍh', ['ണ']='ṇ', 
	['ത']='t', ['ഥ']='th', ['ദ']='d', ['ധ']='dh', ['ന']='n', 
	['പ']='p', ['ഫ']='ph', ['ബ']='b', ['ഭ']='bh', ['മ']='m', 
	['യ']='y', ['ര']='r', ['ല']='l', ['വ']='v', 
	['ശ']='ś', 	['ഷ']='ṣ', ['സ']='s', ['ഹ']='h',
	['ള']='ḷ', ['ഴ']='ḻ',  ['റ']='ṟ' , ['ഩ']='ṉ' , ['ഺ']='ṯ' ,
}

local diacritics = {
	['\224\181\129\224\181\141'] = 'ŭ',
	['\224\180\190'] = 'ā' ,
	['\224\180\191'] = 'i' ,
	['\224\181\128'] = 'ī' ,
	['\224\181\129'] = 'u' ,
	['\224\181\130'] = 'ū' ,
	['\224\181\131'] = 'r̥' ,
	['\224\181\132'] = 'r̥̄' ,
	['\224\181\134'] = 'e' ,
	['\224\181\135'] = 'ē' ,
	['\224\181\136'] = 'ai',
	['\224\181\138'] = 'o' ,
	['\224\181\139'] = 'ō' ,
	['\224\181\151'] = 'au',
	['\224\181\162'] = 'l̥ ',
	['\224\181\163'] = 'l̥̄' ,
	--virama, supresses the inherent vowel "a"
	['\224\181\141'] = '',
	-- no diacritic
	[''] = 'a'
}

local nonconsonants = {
	-- vowels
	['അ']='a' , ['ആ']='ā' , ['ഇ']='i' , ['ഈ']='ī' , ['ഉ']='u' , ['ഊ']='ū' , 
	['ഋ']='r̥' , ['ൠ']='r̥̄' , ['ഌ']='l̥' , ['ൡ']='l̥̄', ['എ']='e' , ['ഏ']='ē' ,
	['ഐ']='ai' , ['ഒ']='o' , ['ഓ']='ō' , ['ഔ']='au' ,
	-- other symbols
	['ം']='ṃ', -- anusvara
	['ഃ']='ḥ' ,  -- visarga
	['ഽ']='’', -- praślēṣam
	-- chillus, consonants that never take vowels
	['ൺ']='ṇ' , ['ൻ']='n' , ['ർ']='r' , ['ൽ']='l' , ['ൾ']='ḷ' , ['ൿ']='k' ,
	-- digits
	['൦'] = '0', ['൧'] = '1', ['൨'] = '2', ['൩'] = '3', ['൪'] = '4',
	['൫'] = '5', ['൬'] = '6', ['൭'] = '7', ['൮'] = '8', ['൯']= '9',
	['൰']='10', ['൱']='100', ['൲']='1000', ['൳']='¼', ['൴']='½', ['൵']='¾',
}

-- translit any words or phrases
function export.tr(text, lang, sc)
	local VIRAMA = '്'
	
	-- final virama rules
	text = mw.ustring.gsub(text, VIRAMA .. "([%,%.%!%?%:%;]?)$", VIRAMA .. "ŭ%1")
	text = mw.ustring.gsub(text, VIRAMA .. "([%,%.%!%?%:%;]?) ", VIRAMA .. "ŭ%1 ")
	
	text = mw.ustring.gsub(
		text,
		'([കഖഗഘങചഛജഝഞടഠഡഢണതഥദധനപഫബഭമയരലവശഷസഹളഴറഩഺ])'..
		'(\224\181\129?[\224\180\190\224\180\191\224\181\128\224\181\129\224\181\130\224\181\131\224\181\132\224\181\162\224\181\163\224\181\134\224\181\135\224\181\138\224\181\139\224\181\136\224\181\151\224\181\141]?)',
		function(c, d)
			return consonants[c] .. (diacritics[d] or d)
		end)
	
	text = mw.ustring.gsub(text, '.', nonconsonants)
	
	-- anusvara
	text = mw.ustring.gsub(text, 'ṃ([kgṅ])', 'ṅ%1')
	text = mw.ustring.gsub(text, 'ṃ([cjñ])', 'ñ%1')
	text = mw.ustring.gsub(text, 'ṃ([ṭḍṇ])', 'ṇ%1')
	text = mw.ustring.gsub(text, 'ṃ([tdn])', 'n%1')
	text = mw.ustring.gsub(text, 'ṃ([pbm])', 'm%1')
	
	text = mw.ustring.gsub(text, "ŭ ([%,%.%!%?%:%;]?)([aāiīuūeo])", " %1%2") -- ŭ is elided before vowels
	
	return text
end
 
return export