Module:Sind-translit

The following documentation is located at Module:Sind-translit/documentation. ^[edit]

Useful links: subpage list • links • transclusions • testcases • sandbox

This module will transliterate text in the Khudawadi script. It is used to transliterate Kachchi and Sindhi. 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:Sind-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 = {
	['𑊺']='k', ['𑊻']='kh', ['𑊼']='g', ['𑊽']='g̈', ['𑊾']='gh', ['𑊿']='ṅ', 
	['𑋀']='c', ['𑋁']='ch', ['𑋂']='j', ['𑋃']='j̈', ['𑋄']='jh', ['𑋅']='ñ', 
	['𑋆']='ṭ', ['𑋇']='ṭh', ['𑋈']='ḍ', ['𑋉']='d̤', ['𑋊']='ṛ',['𑋋']='ḍh', ['𑋌']='ṇ', 
	['𑋍']='t', ['𑋎']='th', ['𑋏']='d', ['𑋐']='dh', ['𑋑']='n', 
	['𑋒']='p', ['𑋓']='ph', ['𑋔']='b', ['𑋕']='b̤', ['𑋖']='bh', ['𑋗']='m', 
	['𑋘']='y', ['𑋙']='r', ['𑋚']='l', ['𑋛']='v', ['𑋜']='ś', 
	['𑋝']='s', ['𑋞']='h', 

--consonants with nukta
	["𑊺𑋩"] = "q",
	["𑊻𑋩"] = "x",
	["𑊼𑋩"] = "ġ",
	["𑋂𑋩"] = "z",
	["𑋋𑋩"] = "ṛh",
	["𑋓𑋩"] = "f",
}

local diacritics = {
	['𑋠']= 'ā', ['𑋡']='i', ['𑋢']='ī', ['𑋣']='u', ['𑋤']='ū',
	['𑋥']='e', ['𑋦']='ai', ['𑋧']='o', ['𑋨']='au', ['𑋪']='', 
}

local nonconsonants = {
	-- vowels
	['𑊰']='a', ['𑊱']='ā', ['𑊲']='i', ['𑊳']='ī', ['𑊴']='u', ['𑊵']='ū', 
	['𑊶']='e', ['𑊷']='ai', ['𑊸']='o',['𑊹']='au',
	-- other symbols
	['𑋟']='ṁ', -- anusvara
	['𑋩']='.', -- nukta
	-- digits
	['𑋰'] = '0', ['𑋱'] = '1', ['𑋲'] = '2', ['𑋳'] = '3', ['𑋴'] = '4',
	['𑋵'] = '5', ['𑋶'] = '6', ['𑋷'] = '7', ['𑋸'] = '8', ['𑋹'] = '9',
}

local nasal_assim = {
	["[kg]h?"] = "ṅ",
	["[cj]h?"] = "ñ",
	["[ṭḍ]h?"] = "ṇ",
	["[td]h?"] = "n",
	["[pb]h?"] = "m",
	["n"] = "n",
	["m"] = "m",
    ["s"] = "n",
}

-- translit any words or phrases
function export.tr(text, lang, sc)
	local nukta = "([𑊻𑊼𑋂𑋓]𑋩)"
	text = mw.ustring.gsub(
		text,
		'([𑊺𑊻𑊼𑊽𑊾𑊿𑋀𑋁𑋂𑋃𑋄𑋅𑋆𑋇𑋈𑋉𑋊𑋋𑋌𑋍𑋎𑋏𑋐𑋑𑋒𑋓𑋔𑋕𑋖𑋗𑋘𑋙𑋚𑋛𑋜𑋝𑋞][𑋩]?)'..
		'([𑋠𑋡𑋢𑋣𑋤𑋥𑋦𑋧𑋨𑋪]?)',
		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,nukta,consonants)
	text = mw.ustring.gsub(text, '.', nonconsonants)
	for key,val in pairs(nasal_assim) do
		text = mw.ustring.gsub(text,"ṁ("..key..")",val.."%1")
	end
	text = mw.ustring.gsub(text,"([aiueēoāīū])ṁ ", "%1̃ ")
	text = mw.ustring.gsub(text,"(.?)ṁ", "%1̃")
	text = mw.ustring.gsub(text, 'a([iu])̃', 'a͠%1')

	return mw.ustring.toNFC(text)
end
 
return export