Module:ne-translit

---

පහත දැක්වෙන උපදෙස්, Module:ne-translit/documentation හි පිහිටා ඇත. Module:ne-translit/documentation]]. ^{[සංස්කරණය]}

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

This module will transliterate Nepali භාෂාව text. It is also used to transliterate Doteli. 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:ne-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 Nepali
local export = {}

local m_str_utils = require("Module:string utilities")

local gmatch = m_str_utils.gmatch
local gsub = m_str_utils.gsub
local match = m_str_utils.match
local reverse = m_str_utils.reverse
local toNFC = mw.ustring.toNFC

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'] = 'w',
	['श'] = 'ś', ['ष'] = 'ṣ', ['स'] = 's', ['ह'] = 'h',

	['क़'] = 'q', ['ख़'] = 'x', ['ग़'] = 'ġ', ['ऴ'] = 'ḻ',
	['ळ'] = 'ḷ', ['ज़'] = 'z', ['श़'] = 'ž', ['झ़'] = 'ž',
	['ड़'] = 'ṛ', ['ढ़'] = 'ṛh', ['फ़'] = 'f', ['थ़'] = 'θ',
	['द़'] = 'ð', ['ऩ'] = 'ṉ', ['ऱ'] = 'ṟ', ['ॽ'] = "'",
	['व़'] = 'V', ['ॹ'] = 'ž',
	-- vowel diacritics
	['ि'] = 'i', ['ु'] = 'u', ['े'] = 'e', ['ो'] = 'o', ['ा'] = 'ā', ['ी'] = 'ī', ['ू'] = 'ū', ['ृ'] = 'r̥',
	['ॄ'] = 'r̥̄', ['ॢ'] = 'l̥', ['ॣ'] = 'l̥̄', ['ै'] = 'ai', ['ौ'] = 'au', ['ॉ'] = 'ŏ', ['ॅ'] = 'ĕ',
	-- vowel signs
	['अ'] = 'a', ['इ'] = 'i', ['उ'] = 'u', ['ए'] = 'e', ['ओ'] = 'o', ['आ'] = 'ā', ['ई'] = 'ī', ['ऊ'] = 'ū',
	['ऋ'] = 'r̥', ['ॠ'] = 'r̥̄', ['ऌ'] = 'l̥', ['ॡ'] = 'l̥̄', ['ऐ'] = 'ai', ['औ'] = 'au', ['ऑ'] = 'ŏ',
	['ॲ'] = 'ĕ', ['ऍ'] = 'ĕ',
	-- chandrabindu
	['ँ'] = '̃',
	-- anusvara
	['ं'] = '̃',
	-- visarga
	['ः'] = 'ḥ',
	-- virama
	['्'] = '',
	-- om
	['ॐ'] = 'om̐',
	-- zero-width non joiner
	['‌'] = '',
	-- zero-width joiner
	['‍'] = 'a',
	-- 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',
	['त'] = 'न', ['थ'] = 'न', ['द'] = 'न', ['ध'] = 'न', ['न'] = 'न', ['ष'] = 'न', ['श'] = 'ङ',
	['स'] = 'न',
	['य'] = 'म', ['र'] = 'म', ['ल'] = 'ँ', ['व'] = 'म', ['ह'] = 'ङ',
}
local perm_cl = {
	['ज्न'] = true, ['ज्ञ'] = true, ['ट्र'] = true, ['ड्र'] = true, ['ट्स'] = true,
	['ड्स'] = true, ['स्ड'] = true
}

local all_cons, special_cons = 'कखगघङचछजझञटठडढणतथदधनपफबभमयरलवसशषह'
	, 'कखगघचछजझटठडढणतथदधनपफबभमयरलवशषसह'
local vowel, vowel_sign = 'aिुृेोाीूैौॉॅॆॊॄॢॣ', 'अइउएओआईऊऋॠॡऌऐऔऑऍ'
local syncope_pattern = '(़?[' ..
	all_cons ..
	'])([ंँ]?[' ..
	vowel ..
	vowel_sign ..
	'])(़?[' ..
	all_cons ..
	'])([ंँ]?[' ..
	vowel ..
	vowel_sign ..
	'])(़?[' ..
	all_cons ..
	'])a(़?[' ..
	all_cons .. '])([ंँ]?[' .. vowel .. vowel_sign .. '])(़?[' ..
	all_cons .. '])([ंँ]?[' .. vowel .. vowel_sign .. '])'

local nor_cons, sp_cons = 'कखगघङचछजझञटठडढतथदधपफबभशषसयरलवणनमयरलवनम'
	, 'कलम'
local vowel, vowel_sign = 'aिुृेोाीूैौॉॅॆॊॄॢॣ', 'अइउएओआईऊऋॠॡऌऐऔऑऍ'
local koka_sign = 'ोीाैे'
local koka_pattern = '([' ..
	koka_sign .. '])(़?[' .. sp_cons .. '])a(़?[' ..
	gsub(nor_cons, "य", "") .. '])([ंँ]?[' .. vowel .. vowel_sign .. '])'

function export.tr(text, lang, sc)
	text = gsub(text, '([' .. all_cons .. ']़?)([' .. vowel .. '्]?)', function(c, d)
		return c .. (d == "" and 'a' or d)
	end)
	for word in gmatch(text, "[ऀ-ॿa]+") do
		local orig_word = word
		word = reverse(word)
		word = gsub(word, '^a(़?)([' .. all_cons .. '])(.)(.?)', function(opt, first, second, third)
			return (((match(first, '[' .. special_cons .. ']') and match(second, 'ं')
				or match(first, '[' .. special_cons .. ']') and match(second, '्') and not perm_cl[first .. second .. third])
				or match(first .. second, 'य[aिुृेोाीूैौॉॅॆॊआईउऊइएऐओऔ]') or
				match(first .. second, 'ह[अaिुृेोाीूैौॉॅॆॊआईउऊइएऐओऔ]'))
				and 'a' or "") .. opt .. first .. second .. third
		end)

		while match(word, syncope_pattern) do
			word = gsub(word, syncope_pattern, '%1%2%3%4%5%6%7%8%9')
		end
		while match(word, koka_pattern) do

			word = gsub(word, koka_pattern, '%1%2%3%4')
		end
		word = gsub(word, '(.?)ं(.)', function(succ, prev)
			return succ .. (succ .. prev == "a" and "्म" or
				(succ == "" and match(prev, '[' .. vowel .. ']') and "̃" or nasal_assim[succ] or "ṃ")) .. prev
		end)
		
		text = gsub(text, orig_word, reverse(word))
		text = gsub(text, '[इईउऊएऐिीुूेै]ँ?[छनर]%f[%z%s]', '%0a')
		text = gsub(text, 'बाट%f[%z%s]', 'bāṭa')
		text = gsub(text, 'ज्ञ', 'gy')
	end
	text = gsub(text, '.़?', conv)
	text = gsub(text, 'a([iu])̃', 'a͠%1')
	text = gsub(text, "[<>]", "")
	text = gsub(text, "ॱ", "")

	text = gsub(text, 'dach%f[%z%s]', 'dacha')
	text = gsub(text, 'ain%f[%z%s]', 'aina')
	text = gsub(text, 'nach%f[%z%s]', 'nacha')
	text = gsub(text, 'wai', 'vai')
	text = gsub(text, 'w%f[%z%s]', 'v')
	text = gsub(text, '([raäāiīuūeo]r)w', '%1v')
	text = gsub(text, 'w([iīewoy])', 'v%1')
	text = gsub(text, 'w([rl]̥̄?)', 'v%1')
	text = gsub(text, 'w(a[krjtcṅñysśdphṇn][tnrṇṣcśkghjsueoayd])', 'v%1')
	text = gsub(text, 'w(ā[cgjṇtdmyshśṣn])', 'v%1')
	text = gsub(text, 'w(ār[tdābuṇṣh])', 'v%1')
	text = gsub(text, 'w(ālm)', 'v%1')
	text = gsub(text, 'w(a[sśṣṅñṃypdtnc])', 'v%1')
	text = gsub(text, 'rh̥', 'hr̥')
	---text = gsub(text, 'kṣ', 'ch̥')
	text = gsub(text, 'a(har[uū])', '%1')
	text = gsub(text, 'abāṭa', 'bāṭa')

	text = gsub(text, 'kan%f[%z%s]', 'kana')
	text = gsub(text, '([ptkbdgṭṇñḍmṅnlrwyhṣśs][ptkbdgṭḍmṇñnlrwyṣśs])(har[uū])', '%1a%2')
	text = gsub(text, '([ptkbdgṭṇñḍmṅnlrwyhṣśs][ptkbdgṭḍmṇñnlrwyṣśs])bāṭa', '%1abāṭa')
	text = gsub(text, '([ptkbdgṭḍmṅṇñnlrwyhṣśs][ptkbdgṭḍmnlrṇñwyś])([mlk])', '%1a%2')
	text = gsub(text, 'ñz', 'nz')
	text = gsub(text, 'ñgy', 'ṅgy')
	text = gsub(text, 'ãla', 'amla') -- assim case l
	text = gsub(text, '([eāuūiīo][īuiū])mm', '%1ṃm') -- assim case m
	text = gsub(text, 'a([īuiū])mm', 'a͠%1m') -- assim case m2
	text = gsub(text, '([eāuūiīo][īuiū])n([st])', '%1ṃ%2') -- assim case s
	text = gsub(text, 'a([īuiū])n([st])', 'a͠%1%2') -- assim case s2
	text = gsub(text, 'a([uū])ṅ([hk])', 'a͠%1%2') -- assim case kh
	text = gsub(text, '([eāuūiīo][īuiū])ṅ([kh])', '%1ṃ%2') -- assim case kh2
	return toNFC(text)
end

return export