Module:si-translit

---

පහත දැක්වෙන උපදෙස්, Module:documentation/functions/translit මගින් ජනනය කොට ඇත. ^{[සංස්කරණය කරන්න]}

ප්‍රයෝජනවත් සබැඳි: උප පිටු ලැයිස්තුව • සබැඳි • transclusions • testcases • sandbox

This module will transliterate සිංහල භාෂාව text. It is also used to transliterate පාලි and සංස්කෘත. 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:si-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 m_str_utils = require("Module:string utilities")

local gsub = m_str_utils.gsub
local u = m_str_utils.char

local export = {}

local consonants = {
	['ක']='k' , ['ඛ']='kh' , ['ග']='g' , ['ඝ']='gh' , ['ඞ']='ṅ' , ['ඟ']='ⁿg' , ['ච']='c' , ['ඡ']='ch' , ['ජ']='j' , ['ඣ']='jh' , 
	['ඤ']='ñ' , ['ඥ']='gn' , ['ඦ']='ⁿj' , ['ට']='ṭ' , ['ඨ']='ṭh' , ['ඩ']='ḍ' , ['ඪ']='ḍh' , ['ණ']='ṇ' , ['ඬ']='ⁿḍ' ,
	['ත']='t' ,  ['ථ']='th' , ['ද']='d' , ['ධ']='dh' , ['න']='n' , ['ඳ']='ⁿd' , 
	['ප']='p' , ['ෆ']='f' , ['ඵ']='ph' , ['බ']='b' , ['භ']='bh' , ['ම']='m' , ['ඹ']='ᵐb' , ['ය']='y' , ['ර']='r' , ['ල']='l' , ['ව']='w' , 
	['ශ']='ś' , ['ෂ']='ṣ' , ['ස']='s' , ['හ']='h' , ['ළ']='ḷ' , ['ෆ']='f'
}

local diacritics = {
	['ා'] = 'ā',
	['ැ'] = 'æ',
	['ෑ'] = 'ǣ',
	['ි'] = 'i',
	['ී'] = 'ī',
	['ු'] = 'u',
	['ූ'] = 'ū',
	['ෙ'] = 'e',
	['ේ'] = 'ē', 
	['ෛ'] = 'ai', 
	['ො'] = 'o', 
	['ෝ'] = 'ō', 
	['ෞ'] = 'au',
	['ෘ'] = 'r̥',
	['ෟ'] = 'l̥', 
	['ෲ'] = 'r̥̄', 
	['ෳ'] = 'l̥̄',
	['්'] = ''
}
local tt = {
	-- vowels
	['අ']='a' ,  ['ආ']='ā' ,  ['ඇ']='æ' ,   ['ඈ']='ǣ' ,  ['ඉ']='i' ,  ['ඊ']='ī' ,  ['උ']='u' ,  ['ඌ']='ū' , 
	['එ']='e' ,  ['ඒ']='ē' ,  ['ඓ']='ai' ,  ['ඔ']='o' ,  ['ඕ']='ō' ,  ['ඖ']='au' , 
	['ඍ']='r̥' ,  ['ඎ']='r̥̄' ,  ['ඏ']='l̥' ,  ['ඐ']='l̥̄' ,     
	-- other symbols
	['ං']='ṁ' , -- anusvara
	['ඃ']='ḥ' ,  -- visarga
	['්']='' ,  --hal kirīma, suppresses the inherent vowel "a"
	-- punctuation
	['෴']='.' ,  -- kunddaliya (obsolete)    
}

-- translit any words or phrases
function export.tr(text, lang, sc)
	if type(text) == 'table' then
		text = text.args[1]
		lang = text.args[2]
		sc   = text.args[3]
	end
	if (lang == 'sa' or lang == 'pi') then
		text=string.gsub(text, 'ඥ', 'ජ‍්ඤ')
	end
	text = gsub(text, -- Handle conjunct and touching clusters.
		'['..u(0x200d, 0x0dca)..']['..u(0x200d, 0x0dca)..']',
		{[u(0x200d, 0x0dca)] = u(0x0dca), [u(0x0dca, 0x200d)] = u(0x0dca)})
	text = gsub(
		text,
		'([කඛගඝඞඟචඡජඣඤඥඦටඨඩඪණඬතථදධනඳපපඵබභමඹයරලවශෂසහළෆ])'..
		'([\224\183\153\224\183\146\224\183\156\224\183\148\224\183\144\224\183\146\224\183\143\224\183\154\224\183\157\224\183\150\224\183\145\224\183\147\224\183\152\224\183\159\224\183\178\224\183\179\224\183\155\224\183\158\224\183\138]?)',
		function(c, d)
			if d == "" then        
				return consonants[c] .. 'a'
			else
				return consonants[c] .. diacritics[d]
			end
		end)
	
	text = gsub(text, '.', tt)
	if (lang == 'pi' or lang =='sa') then -- Convert to IAST.
		text = gsub(text, '.'..u(0x325)..'?'..u(0x304)..'?',
                   {['ṁ'] = 'ṃ', ['w'] = 'v', ['r̥'] = 'ṛ', ['r̥̄']='ṝ', ['l̥']='ḷ', ['l̥̄']='ḹ'})
	end
	return text
end
 
return export