Module:pra-Knda-translit

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

This module will transliterate Prakrit 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:pra-Knda-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 = {
--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', ['ಲ']='l', ['ವ']='v', ['ಳ']='ḷ',
	['ಶ']='ś', ['ಷ']='ṣ', ['ಸ']='s', ['ಹ']='h',
	['ಯ಼']='ẏ',
}

local diacritics = {
--matras
	['ಾ']='ā', ['ಿ']='i', ['ೀ']='ī', ['ು']='u', ['ೂ']='ū', ['ೃ']='ṛ', ['ೄ']='ṝ', 
	['ೢ']='l̥', ['ೣ']='l̥̄', ['ೆ']='ĕ', ['ೇ']='e', ['ೈ']='ai', ['ೊ']='ŏ', ['ೋ']='o', ['ೌ']='au',  ['್']='',
}

local tt = {

--vowels
	['ಅ']='a', ['ಆ']='ā', ['ಇ']='i', ['ಈ']='ī', ['ಉ']='u', ['ಊ']='ū', ['ಋ']='ṛ', ['ೠ']='ṝ',
	['ಌ']='l̥', ['ೡ']='l̥̄', ['ಎ']='ĕ', ['ಏ']='e', ['ಐ']='ai', ['ಒ']='ŏ', ['ಓ']='o', ['ಔ']='au', 
	-- chandrabindu    
	['ಁ']='m̐', --until a better method is found
	-- anusvara    
	['ಂ']='ṃ', --until a better method is found
	-- visarga    
	['ಃ']='ḥ',
	--numerals
	['೦']='0', ['೧']='1', ['೨']='2', ['೩']='3', ['೪']='4', ['೪']='5', ['೬']='6', ['೭']='7', ['೮']='8', ['೯']='9',
	--punctuation        
	['।']='.', --danda
    ['॥']='.' --double danda
}

local ttrema = { -- With diaeresis
	['ಇ']='ï', ['ಉ']='ü',
}

function export.tr(text, lang, sc)
	if sc ~= "Knda" then
		return nil
	end
	
	text = mw.ustring.gsub(
		text,
		'([ಕ-ಹ][಼]?)'..
		'([ಾ-ೣ]?)'..
		'([ಇಉ]?)',
		function(c, d, e)
			if d == "" and e ~= "" then        
				return consonants[c] .. 'a' .. ttrema[e]
			elseif e ~= "" then
				return consonants[c] .. diacritics[d] .. tt[e]
			elseif d == "" then        
				return consonants[c] .. 'a'
			else
				return consonants[c] .. diacritics[d]
			end
		end)

-- Adjacent vowel letters needing dieresis
	text = mw.ustring.gsub(
		text,
		'([ಅ])([ಇಉ])',
		function(a, b) return tt[a]..ttrema[b] end)

	text = mw.ustring.gsub(text, '.', tt)
	
	return text
end
 
return export