Module:Brah-translit: difference between revisions

From Wiktionary, the free dictionary
Jump to navigation Jump to search
Content deleted Content added
No edit summary
this shouldn't be necessary, but if a language whose script is not Brah calls this module, return nil
Line 39: Line 39:


function export.tr(text, lang, sc)
function export.tr(text, lang, sc)
if sc and sc.getCode and sc:getCode() ~= "Brah" then
return nil
end
text = mw.ustring.gsub(
text = mw.ustring.gsub(
text,
text,

Revision as of 21:32, 2 May 2017

This module will transliterate text in the Brahmi script. It is used to transliterate Ashokan Prakrit, Prakrit, Khotanese, Old Tamil, Pali, Sanskrit, and Tumshuqese. 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:Brah-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 = {
--consonants
	['𑀓']='k', ['𑀔']='kh', ['𑀕']='g', ['𑀖']='gh', ['𑀗']='ṅ',
	['𑀘']='c', ['𑀙']='ch', ['𑀚']='j', ['𑀛']='jh', ['𑀜']='ñ', 
	['𑀝']='ṭ', ['𑀞']='ṭh', ['𑀟']='ḍ', ['𑀠']='ḍh', ['𑀡']='ṇ', 
	['𑀢']='t', ['𑀣']='th', ['𑀤']='d', ['𑀥']='dh', ['𑀦']='n', 
	['𑀧']='p', ['𑀨']='ph', ['𑀩']='b', ['𑀪']='bh', ['𑀫']='m',
	['𑀬']='y', ['𑀭']='r', ['𑀮']='l', ['𑀯']='v', ['𑀴']='ḷ',
	['𑀰']='ś', ['𑀱']='ṣ', ['𑀲']='s', ['𑀳']='h',
}

local diacritics = {
--matras
	['𑀸']='ā', ['𑀺']='i', ['𑀻']='ī', ['𑀼']='u', ['𑀽']='ū', ['𑀾']='ṛ', ['𑀿']='ṝ', 
	['𑁀']='ḷ', ['𑁁']='ḹ', ['𑁂']='e', ['𑁃']='ai', ['𑁄']='o', ['𑁅']='au',  ['𑁆']='',
    --bhattiprolu aa
    ['𑀹']='ā',
}

local tt = {

--vowels
	['𑀅']='a', ['𑀆']='ā', ['𑀇']='i', ['𑀈']='ī', ['𑀉']='u', ['𑀊']='ū', ['𑀋']='ṛ', ['𑀌']='ṝ',
	['𑀍']='ḷ', ['𑀎']='ḹ', ['𑀏']='e', ['𑀐']='ai', ['𑀑']='o', ['𑀒']='au', 
	-- chandrabindu    
	['𑀀']='m̐', --until a better method is found
	-- anusvara    
	['𑀁']='ṃ', --until a better method is found
	-- visarga    
	['𑀂']='ḥ',
	--numerals
	['𑁦']='0', ['𑁧']='1', ['𑁨']='2', ['𑁩']='3', ['𑁪']='4', ['𑁫']='5', ['𑁬']='6', ['𑁭']='7', ['𑁮']='8', ['𑁯']='9',
	--punctuation        
	['𑁇']='.', --danda
    ['𑁈']='.' --double danda
}

function export.tr(text, lang, sc)
	if sc and sc.getCode and sc:getCode() ~= "Brah" then
		return nil
	end
	
	text = mw.ustring.gsub(
		text,
		'([𑀓-𑀳])'..
		'([𑀸𑀺𑀺𑀻𑀼𑀽𑀾𑀿𑁀𑁁𑁂𑁃𑁄𑁅𑁆𑀹]?)',
		function(c, d)
			if d == "" then        
				return consonants[c] .. 'a'
			else
				return consonants[c] .. diacritics[d]
			end
		end)

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