Module:Shrd-translit

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

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

This module will transliterate text in the Sharada script. It is used to transliterate Apabhramsa, Kashmiri, and Sanskrit. 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:Shrd-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 = {
	['𑆑']='k', ['𑆒']='kh', ['𑆓']='g', ['𑆔']='gh', ['𑆕']='ṅ',
	['𑆖']='c', ['𑆗']='ch', ['𑆘']='j', ['𑆙']='jh', ['𑆚']='ñ', 
	['𑆛']='ṭ', ['𑆜']='ṭh', ['𑆝']='ḍ', ['𑆞']='ḍh', ['𑆟']='ṇ', 
	['𑆠']='t', ['𑆡']='th', ['𑆢']='d', ['𑆣']='dh', ['𑆤']='n', 
	['𑆥']='p', ['𑆦']='ph', ['𑆧']='b', ['𑆨']='bh', ['𑆩']='m',
	['𑆪']='y', ['𑆫']='r', ['𑆬']='l', ['𑆮']='v', ['𑆭']='ḷ',
	['𑆯']='ś', ['𑆰']='ṣ', ['𑆱']='s', ['𑆲']='h',
}

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

local diatrema = {
	['𑆅']='ï', ['𑆇']='ü',
}

local tt = {
	-- vowels
	['𑆃']='a', ['𑆄']='ā', ['𑆅']='i', ['𑆆']='ī', ['𑆇']='u', ['𑆈']='ū', ['𑆉']='ṛ', ['𑆊']='ṝ',
	['𑆋']='ḷ', ['𑆌']='ḹ', ['𑆍']='e', ['𑆎']='ai', ['𑆏']='o', ['𑆐']='au', 
	-- chandrabindu    
	['𑆀']='m̐', --until a better method is found
	-- anusvara    
	['𑆁']='ṃ', --until a better method is found
	-- visarga    
	['𑆂']='ḥ',
	-- avagraha
	['𑇁']='’',
	--numerals
	['𑇐']='0', ['𑇑']='1', ['𑇒']='2', ['𑇓']='3', ['𑇔']='4', ['𑇕']='5', ['𑇖']='6', ['𑇗']='7', ['𑇘']='8', ['𑇙']='9',
	--punctuation        
    ['𑇆']='.', --double danda
	['𑇅']='.', --danda
    --Vedic extensions
    ['𑇂']='x', ['𑇃']='f',
    --Om
    ['𑇄']='oṃ',
    --reconstructed
    ['*'] = '',
}

function export.tr(text, lang, sc)
	text = mw.ustring.gsub(
		text,
		'([𑆑𑆒𑆓𑆔𑆕𑆖𑆗𑆘𑆙𑆚𑆛𑆜𑆝𑆞𑆟𑆠𑆡𑆢𑆣𑆤𑆥𑆦𑆧𑆨𑆩𑆪𑆫𑆬𑆮𑆭𑆯𑆰𑆱𑆲])'..
		'([𑆳𑆴𑆵𑆶𑆷𑆸𑆹𑆺𑆻𑆼𑆽𑆾𑆿𑇀]?)'..
		'([𑆅𑆇]?)',
		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, '([𑆃])([𑆅𑆇])', function(a, b) return tt[a]..diatrema[b] end)

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