Module:new-translit

From Wiktionary, the free dictionary
Jump to navigation Jump to search

This module will transliterate Newar language text. 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:new-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 Newar

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

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", ["ळ"] = "ḷ",
	["श"] = "ś", ["ष"] = "ṣ", ["स"] = "s", ["ह"] = "h", ["ऴ"] = "ḻ", ["ॽ"] = "ॽ",
	-- vowel diacritics
	["ि"] = "i", ["ु"] = "u", ["े"] = "e", ["ो"] = "o",
	["ा"] = "ā", ["ी"] = "ī", ["ू"] = "ū",
	["ृ"] = "r̥", ["ॄ"] = "r̥̄", ["ॢ"] = "l̥", ["ॣ"] = "l̥̄",
	["ै"] = "ai", ["ौ"] = "au", ["ॉ"] = "ô", ["ॅ"] = "â",
	-- 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"] = "ô", ["ॲ"] = "â", ["ऍ"] = "â",
	-- ZWNJ
	["‌"] = "",
	-- ZWJ
	["‍"] = "", -- chandrabindu
	["ँ"] = "̃",
	-- anusvara
	["ं"] = "ṃ",
	-- visarga (liphuti)
	["ः"] = ":",
	-- virama
	["्"] = "",
	-- om
	["ॐ"] = "oḥm",
	-- avagraha
	["ऽ"] = "’",
	-- 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"] = "ं", ["ख"] = "ं", ["ग"] = "ं", ["घ"] = "ं",
	["च"] = "ं", ["छ"] = "ं", ["ज"] = "ं", ["झ"] = "ं",
	["ट"] = "ं", ["ठ"] = "ं", ["ड"] = "ं", ["ढ"] = "ं",
	["त"] = "ं", ["थ"] = "ं", ["द"] = "ं", ["ध"] = "ं", ["न"] = "ं",
	["प"] = "ं", ["फ"] = "ं", ["ब"] = "ं", ["भ"] = "ं", ["म"] = "ं",
	["ष"] = "ं", ["श"] = "ं", ["स"] = "ं",
	["य"] = "ं", ["र"] = "ं", ["ल"] = "ं", ["व"] = "ं", ["ह"] = "ं"
}
local perm_cl = {
	["ज्ञ"] = true
}

local all_cons, special_cons = "कखगघङचछजझञटठडढणतथदधनपफबभमयरलवसशषह", "कखगघचछजझटठडढणतथदधनपफबभमयरलवशषसह"
local vowel, vowel_sign = "aिुृेोाीूैौॉॅॆॊॄॢॣ", "अइउएओआईऊऋॠॡऌऐऔऑऍ"

local function rev_string(text)

	local result, length = {}, mw.ustring.len(text)
	for i = length, 1, -1 do
		table.insert(result, mw.ustring.sub(text, i, i))
	end
	return table.concat(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
	)
	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 (((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 "a") ..
					opt .. first .. second .. third
			end
		)

		word = gsub(word, "(.?)ं(.)",
			function(succ, prev)
				return succ .. (succ .. prev == "" and "्म" or
					(succ == "" and match(prev, "[" .. vowel .. "]") and "ṃ" or nasal_assim[succ] or "ṃ")) .. prev
			end
		)

		local escaped_orig_word = gsub(orig_word, "%+", "")
		text = gsub(text, orig_word, rev_string(word))
		text = gsub(text, "आँय्", "æ̃")
		text = gsub(text, "आंय्", "æ̃")
		text = gsub(text, "आय्", "æ")
		text = gsub(text, "ाँय्", "æ̃")
		text = gsub(text, "ांय्", "æ̃")
		text = gsub(text, "ाय्", "æ")
		text = gsub(text, "अँय्", "ễ")
		text = gsub(text, "अंय्", "ễ")
		text = gsub(text, "अय्", "ê")
		text = gsub(text, "य्", "ê")
	end
	text = gsub(text, ".़?", conv)
	text = gsub(text, "a([iu])̃", "a͠%1")

	text = gsub(text, "([ptkbdgṭḍmṅṇñnlrhṣśs])([yw])([aāiīuūeēoōâ])ê", "%1%2%3ê")
	text = gsub(text, "([ptkbdgṭḍmṅṇñnlrhṣśs])([yw])([aāiīuūeēoōâ])ễ", "%1%2%3ễ")
	text = gsub(text, "([ptkbdgṭḍmṅṇñnlrhṣśs])([a])̃ê", "%1ễ")
	text = gsub(text, "([ptkbdgṭḍmṅṇñnlrhṣśs])([a])ê", "%1ê")

	text = gsub(text, "[<>]", "")
	return mw.ustring.toNFC(text)

end

return export