Module:Brah-translit

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

This module will transliterate text in the Brahmi script. It is used to transliterate Ashokan Prakrit, Kamarupi Prakrit, Khotanese, Old Tamil, Pali, Prakrit, 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 m_str_utils = require("Module:string utilities")

local gsub = m_str_utils.gsub
local match = m_str_utils.match
local toNFC = mw.ustring.toNFC
local u = m_str_utils.char

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',
-- Old Tamil
	[u(0x11075)] = 'ḷ',
	['𑀵']='ḻ', ['𑀶']='ṟ', ['𑀷'] ='ṉ',
}

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

    --bhattiprolu aa
    ['𑀹']='ā',

     --Old Tamil
    ['𑁳']='ĕ', ['𑁴']='ŏ', [u(0x11070)]='',
    
    -- Old Tamil up to and including Unicode 13.0
    ['𑁂𑁆']='ĕ', ['𑁄𑁆']='ŏ', -- Two character vowels!
}

local diatrema = {
	['𑀇']='ï', ['𑀉']='ü',
}

local tt = {

--vowels
	['𑀅']='a', ['𑀆']='ā', ['𑀇']='i', ['𑀈']='ī', ['𑀉']='u', ['𑀊']='ū', ['𑀋']='ṛ', ['𑀌']='ṝ',
	['𑀍']='l̥', ['𑀎']='l̥̄', ['𑀏']='e', ['𑀐']='ai', ['𑀑']='o', ['𑀒']='au', 
    ['𑁱']='ĕ', ['𑁲']='ŏ', --Old Tamil

	-- 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 ~= "Brah" then
		return nil
	end

	if lang == "pra" then -- Route contextually shortened Prakrit vowels through Old Tamil short vowels
		text = gsub(text, '(𑁂)([𑀅-𑀳]?)(𑁆)([𑀅-𑀳]?)', '𑁳%2%3%4')
		text = gsub(text, '(𑀏)([𑀅-𑀳]?)(𑁆)([𑀅-𑀳]?)', '𑁱%2%3%4')
		text = gsub(text, '(𑁄)([𑀅-𑀳]?)(𑁆)([𑀅-𑀳]?)', '𑁴%2%3%4')
		text = gsub(text, '(𑀑)([𑀅-𑀳]?)(𑁆)([𑀅-𑀳]?)', '𑁲%2%3%4')
	end

	text = gsub(
		text,
		'([𑀓-𑀷'..u(0x11075)..'])'..
		'([𑀸𑀺𑀺𑀻𑀼𑀽𑀾𑀿𑁀𑁁𑁂𑁃𑁄𑁅𑁆𑀹𑁳𑁴'..u(0x11070)..']?𑁆?)'..
		'([𑀇𑀉]?)',
		function(c, d, e)
			if d == "" and e ~= "" then
				return consonants[c] .. 'a' .. diatrema[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 = gsub(text, '([𑀅])([𑀇𑀉])', function(a, b) return tt[a]..diatrema[b] end)

	text = gsub(text, '.', tt)
	if (lang == 'sa' or lang == 'pi') and match(text, 'l̥') then
		text = gsub(text, 'l̥', 'ḷ')
		text = toNFC(text)
	end
-- Old Tamil uses macron v. plain for 'e' and 'o'.
	if (lang == 'oty') then
		text = gsub(text, '.', {e='ē', o='ō', ['ĕ']='e', ['ŏ']='o'})
	end

	return text
end
 
return export