Module:kn-translit

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

This module will transliterate Kannada language text per WT:KN TR. It is also used to transliterate Badaga, Bellari, Beary, Middle Kannada, Old Kannada, Kodava, Korra Koraga, Konkani, Sholaga, Tulu, Alu Kurumba, Betta Kurumba, Jennu Kurumba, and Ravula. 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:kn-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 consonants = {
	['ಕ']='k', ['ಖ']='kh', ['ಗ']='g', ['ಘ']='gh', ['ಙ']='ṅ', 
	['ಚ']='c', ['ಛ']='ch', ['ಜ']='j', ['ಝ']='jh', ['ಞ']='ñ', 
	['ಟ']='ṭ', ['ಠ']='ṭh', ['ಡ']='ḍ', ['ಢ']='ḍh', ['ಣ']='ṇ', 
	['ತ']='t', ['ಥ']='th', ['ದ']='d', ['ಧ']='dh', ['ನ']='n', 
	['ಪ']='p', ['ಫ']='ph', ['ಬ']='b', ['ಭ']='bh', ['ಮ']='m', 
	['ಯ']='y', ['ರ']='r', ['ಱ']='ṟ', ['ಲ']='l', ['ವ']='v', ['ಶ']='ś', 
	['ಷ']='ṣ', ['ಸ']='s', ['ಹ']='h', ['ಳ']='ḷ', ['ೞ']='ḻ', 
	['ಫ಼']='f', ['ಜ಼']='z', ['ಳ಼']='ḻ', 
}

local diacritics = {
	['ಾ']= 'ā' , ['ಿ']='i' , ['ೀ']='ī' , ['ು']='u' , ['ೂ']='ū' , ['ೃ']='ṛ' , ['ೄ']='r̥̄' ,
	['ೆ']='e' , ['ೇ']='ē' , ['ೈ']='ai' , ['ೊ']='o' , ['ೋ']='ō' , ['ೌ']='au', ['ೆ್']= 'è',
}

local nonconsonants = {
	-- vowels
	['ಅ']='a' , ['ಆ']='ā' , ['ಇ']='i' , ['ಈ']='ī' , ['ಉ']='u' , ['ಊ']='ū' , 
	['ಋ']='ṛ' , ['ೠ']='r̥̄' , ['ಌ']='l̥' , ['ೡ']='l̥̄', ['ಎ']='e' , ['ಏ']='ē' ,
	['ಐ']='ai' , ['ಒ']='o' , ['ಓ']='ō' , ['ಔ']='au' , ['ಅಂ']='aṃ' , ['ಅಃ']='ah' , 
	-- other symbols
	['ಂ']='ṃ', -- anusvara
	['ಃ']='ḥ',  -- visarga
	--halant, supresses the inherent vowel "a"
	['್']='',
	-- digits
	['೦'] = '0', ['೧'] = '1', ['೨'] = '2', ['೩'] = '3', ['೪'] = '4',
	['೫'] = '5', ['೬'] = '6', ['೭'] = '7', ['೮'] = '8', ['೯'] = '9',
}

-- translit any words or phrases
function export.tr(text, lang, sc)
	local VIRAMA = '್'
	
	-- final virama rules
	if lang == "tcy" or lang == "kfa" or lang == "kfd" or lang == "dra-bry" then
		text = mw.ustring.gsub(text, VIRAMA .. "([%,%.%!%?%:%;]?)$", VIRAMA .. "ŭ%1")
		text = mw.ustring.gsub(text, VIRAMA .. "([%,%.%!%?%:%;]?) ", VIRAMA .. "ŭ%1 ")
	end

	text = mw.ustring.gsub(
		text,
		'([ಕಖಗಘಙಚಛಜಝಞಟಠಡಢಣತಥದಧನಪಫಬಭಮಯರಱಲವಶಷಸಹಳೞಕಖ][಼]?)'..
		'([ಾಿೀುೂೃೆೇೈೊೋೌ್]?)',
		function(c, d)
			-- mw.log('match', c, d)
			c = consonants[c] or c
			if d == "" then        
				return c .. 'a'
			else
				return c .. (diacritics[d] or d)
			end
		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')
	
	return text
end
 
return export