Module:mr-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 මරාථි භාෂාව text. It is also used to transliterate Ahirani, Konkani, සහ Varhadi. 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:mr-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.

-- Transliteration for Marathi (in progress)

local export = {}
local gsub = mw.ustring.gsub
local find = mw.ustring.find

local conv = {
	-- consonants
	['क'] = 'k', ['ख'] = 'kh', ['ग'] = 'g', ['घ'] = 'gh', ['ङ'] = 'ṅ', 
	['च'] = 'c', ['छ'] = 'ch', ['ज'] = 'j', ['झ'] = 'jh', ['ञ'] = 'ñ', 
	['ट'] = 'ṭ', ['ठ'] = 'ṭh', ['ड'] = 'ḍ', ['ढ'] = 'ḍh', ['ण'] = 'ṇ',
	['त'] = 't', ['थ'] = 'th', ['द'] = 'd', ['ध'] = 'dh', ['न'] = 'n',
	['प'] = 'p', ['फ'] = 'ph', ['ब'] = 'b', ['भ'] = 'bh', ['म'] = 'm', 
	['य'] = 'y', ['र'] = 'r', ['ल'] = 'l', ['व'] = 'v', ['ळ'] = 'ḷ',
	['श'] = 'ś', ['ष'] = 'ṣ', ['स'] = 's', ['ह'] = 'h',
	['ऱ'] = 'r',
	-- ['ज्ञ'] = 'dny',

	-- vowel diacritics
	['ि'] = 'i', ['ु'] = 'u', ['े'] = 'e', ['ो'] = 'o', 
	['ा'] = 'ā', ['ी'] = 'ī', ['ू'] = 'ū', 
	['ृ'] = 'ru',
	['ै'] = 'ai', ['ौ'] = 'au',
	['ॉ'] = 'ŏ',
	['ॅ'] = 'ĕ',

	-- vowel signs
	['अ'] = 'a', ['इ'] = 'i', ['उ'] = 'u', ['ए'] = 'e', ['ओ'] = 'o',
	['आ'] = 'ā', ['ई'] = 'ī', ['ऊ'] = 'ū', 
	['ऋ'] = 'ŕ', 
	['ऐ'] = 'ai', ['औ'] = 'au', 
	['ऑ'] = 'ŏ',
	['ॲ'] = 'ĕ', ['ऍ'] = 'ĕ',
	
	['ॐ'] = 'om',
	
	-- chandrabindu
	['ँ'] = '̃',
	
	-- anusvara
	['ं'] = 'ṁ',
	
	-- visarga
	['ः'] = 'ḥ',
	
	-- virama
	['्'] = '',
	
	-- numerals
	['०'] = '0', ['१'] = '1', ['२'] = '2', ['३'] = '3', ['४'] = '4',
	['५'] = '5', ['६'] = '6', ['७'] = '7', ['८'] = '8', ['९'] = '9',
	
	-- punctuation
	['।'] = '.', -- danda
	['॥'] = '.', -- double danda
	['+'] = '', -- compound separator
	
	-- abbreviation sign
	['॰'] = '.',
}

local nasal_assim = {
	['क'] = 'ङ', ['ख'] = 'ङ', ['ग'] = 'ङ', ['घ'] = 'ङ', 
	['च'] = 'ञ', ['छ'] = 'ञ', ['ज'] = 'ञ', ['झ'] = 'ञ',  
	['ट'] = 'ण', ['ठ'] = 'ण', ['ड'] = 'ण', ['ढ'] = 'ण',
	['प'] = 'म', ['फ'] = 'म', ['ब'] = 'म', ['भ'] = 'म', ['म'] = 'म',
	['य'] = 'इ', ['र'] = 'उ', ['ल'] = 'उ', ['व'] = 'उ',
}

local perm_cl = {
	['म्ल'] = true, ['व्ल'] = true, ['न्ल'] = true,
	
}

local all_cons, special_cons = 'कखगघङचछजझञटठडढतथदधपफबभशषसयरलवहणनमळ', 'यरलवहनम'
local vowel, vowel_sign = 'aिुृेोाीूैौॉॅ', 'अइउएओआईऊऋऐऔऑऍ'
local syncope_pattern = '([' .. vowel .. vowel_sign .. '])(़?[' .. all_cons .. '])a(़?[' .. gsub(all_cons, "य", "") .. '])([ंँ]?[' .. vowel .. vowel_sign .. '])'

local function rev_string(text)
	local char_array, i = {}, 1
	for char in string.gmatch(text, "[%z\1-\127\194-\244][\128-\191]*") do -- UTF-8 character pattern
		char_array[i] = char
		i = i + 1
	end
	return table.concat(require("Module:table").reverse(char_array))
end

function export.tr(text, lang, sc)
	text = gsub(text, 'ाँ', 'ॉ' .. 'ं')
	text = gsub(text, 'ँ', 'ॅ' .. 'ं')
	text = gsub(text, '([^' .. vowel .. vowel_sign .. '])ं ', '%1अ ')
	text = gsub(text, '([^' .. vowel .. vowel_sign .. '])ं$', '%1अ')
	text = gsub(text, '([' .. all_cons .. ']़?)([' .. vowel .. '्]?)', function(c, d)
		return c .. (d == "" and 'a' or d) end)
	for word in mw.ustring.gmatch(text, "[ऀ-ॿa]+") do
		local orig_word = word
		word = rev_string(word)
		word = gsub(word, '^a(़?)([' .. all_cons .. '])(.)(.?)', function(opt, first, second, third)
			return (((find(first, '[' .. special_cons .. ']') and find(second, '्') and not perm_cl[first..second..third])
				or find(first .. second, 'य[ीेै]'))
				and 'a' or "") .. opt .. first .. second .. third end)
		while find(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 "्म" or 
				(succ == "" and find(prev, '[' .. vowel .. ']') and "̃" or nasal_assim[succ] or "n")) .. prev end)
		text = gsub(text, orig_word, rev_string(word))
	end
	text = gsub(text, '.़?', conv)
	text = gsub(text, 'a([iu])̃', 'a͠%1')
	text = gsub(text, 'aa', 'a')
    text = gsub(text, 'ñjñ', 'ndny')
    text = gsub(text, 'jñ', 'dny')
	return mw.ustring.toNFC(text)
end

return export