Modul:gu-translit

Berikut merupakan pendokumenan yang dijana oleh Modul:pendokumenan/functions/translit. ^[sunting]

Pautan berguna: senarai sublaman • pautan • transklusi • kes ujian • kotak pasir

Modul ini akan mentransliterasi Bahasa Gujarati teks. Ia juga digunakan untuk mentransliterasi Kachchi and Vaghri. 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:gu-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 gsub = mw.ustring.gsub
local match = mw.ustring.match

local conv = {
	-- consonants
	['ક']='k', ['ખ']='kh', ['ગ']='g', ['ઘ']='gh', ['ઙ']='ṅ',
	['ચ']='c', ['છ']='ch', ['જ']='j', ['ઝ']='jh', ['ઞ']='ñ', 
	['ટ']='ṭ', ['ઠ']='ṭh', ['ડ']='ḍ', ['ઢ']='ḍh', ['ણ']='ṇ', 
	['ત']='t', ['થ']='th', ['દ']='d', ['ધ']='dh', ['ન']='n', 
	['પ']='p', ['ફ']='ph', ['બ']='b', ['ભ']='bh', ['મ']='m',
	['ય']='y', ['ર']='r', ['લ']='l', ['વ']='v', ['ળ']='ḷ',
	['શ']='ś', ['ષ']='ṣ', ['સ']='s', ['હ']='h',
	['ત઼']='t̰', ['જ઼']='z', ['ંઘ઼']='ng', ['ડ઼']='ṛ', ['ઢ઼']='ṛh', ['ન઼']='ṉ', ['ફ઼']='f',

	--vowel diacritics
	['ા']='ā', ['િ']='i', ['ી']='ī', ['ુ']='u', ['ૂ']='ū', ['ૃ']='ru', ['ૄ']='ṝ', 
	['ે']='e', ['ૈ']='ai', ['ો']='o', ['ૌ']='au', ['ૅ']='ɛ', ['ૉ']='ɔ',

	-- vowel mātras
	['અ']='a', ['આ']='ā', ['ઇ']='i', ['ઈ']='ī', ['ઉ']='u', ['ઊ']='ū', ['ઋ']='ru', ['ૠ']='ṝ',
	['એ']='e', ['ઐ']='ai', ['ઓ']='o', ['ઔ']='au', ['ઍ']='ɛ', ['ઑ']='ɔ',

	-- chandrabindu    
	['ઁ']='m̐', --until a better method is found

	-- anusvara    
	['ં']='ṃ', --until a better method is found

	-- visarga
	['ઃ']='ḥ',

	-- virama
['્']='', 

	-- avagraha
	['ઽ']='’',

	--numerals
	['૦']='0', ['૧']='1', ['૨']='2', ['૩']='3', ['૪']='4', ['૫']='5', ['૬']='6', ['૭']='7', ['૮']='8', ['૯']='9',

	--punctuation        
	['।']='.', --danda
	['+'] = '', -- compound separator
}

local nasal_assim = {
	['ક'] = 'ઙ', ['ખ'] = 'ઙ', ['ગ'] = 'ઙ', ['ઘ'] = 'ઙ', 
	['ચ'] = 'ઞ', ['છ'] = 'ઞ', ['જ'] = 'ઞ', ['ઝ'] = 'ઞ',  
	['ટ'] = 'ણ', ['ઠ'] = 'ણ', ['ડ'] = 'ણ', ['ઢ'] = 'ણ',
	['પ'] = 'મ', 	['ફ'] = 'મ', 	['બ'] = 'મ', 	['ભ'] = 'મ', 	['મ'] = 'મ',
}

local all_cons, special_cons = 'કખગઘઙચછજઝઞટઠડઢતથદધપફબભશષસયરલવહણનમ', 'યરલવહનમ'
local vowel, vowel_sign = 'aાિીુૂેૈોૌૃૄૅૉ', 'અઆઇઈઉઊએઐઓઔઍઑઋૠ'
local syncope_pattern = '([' .. vowel .. vowel_sign .. '])([' .. all_cons .. '])a([' .. gsub(all_cons, "ય", "") .. '])(ं?[' .. vowel .. vowel_sign .. '])'

local function rev_string(text)
	local result, length = '', mw.ustring.len(text)
	for i = 1, length do
		result = result .. mw.ustring.sub(text, length - i + 1, length - i + 1)
	end
	return result
end

function export.tr(text, lang, sc)
	text = gsub(text, '([' .. all_cons .. ']઼?)([' .. vowel .. '્]?)', function(c, d)
		return c .. (d == "" and 'a' or d) end)
	local result = {}
	for word in mw.text.gsplit(text, " ", true) do
		word = rev_string(word)
		word = gsub(word, '^a(઼?)([' .. all_cons .. '])(.)', function(opt, first, second)
			return (((match(first, '[' .. special_cons .. ']') and match(second, '્')) or match(first .. second, 'ય[ીેૈ]'))
				and 'a' or "") .. opt .. first .. second end)
		while match(word, syncope_pattern) do
			word = gsub(word, syncope_pattern, '%1%2%3%4')
		end
		word = gsub(word, '(.?)ં(.)', function(succ, prev)
			return succ .. (succ..prev == "a" and "્મ" or 
				(succ == "" and match(prev, '[' .. vowel .. ']') and "̃" or nasal_assim[succ] or "n")) .. prev end)
		table.insert(result, rev_string(word))
	end
	text = table.concat(result, " ")
	text = gsub(text, '.઼?', conv)
	return mw.ustring.toNFC(text)
end

return export