Module:tevo-translit: Difference between revisions

← Older edit

@@ Line 1: / Line 1: @@
 local export = {}
-local tt = {}
+local m_str_utils = require("Module:string utilities")
-tt = {
+local gsub = m_str_utils.gsub
-    -- Short vowels
+local toNFC = mw.ustring.toNFC
-    { "ॅ", "e" },
+local U = m_str_utils.char
-    { "ॆ", "ei" },
-    { "ि", "i" },
+local grave = U(0x300)
-    { "ॉ", "o" },
+local acute = U(0x301)
-    { "ॊ", "ou" },
+local diaeresis = U(0x308)
-    { "ु", "u"},
+local svar = U(0x951)
+local anud = U(0x952)
-    { "अ", "a" },
+local d_svar = U(0x1CDA) -- double svarita, sometimes used for long vowel with svarita
-    { "ऍ", "e" },
-    { "ऎ", "ei" },
+local consonants = {
-    { "इ", "i" },
+	['क']='k',
-    { "ऑ", "o" },
+	['ख']='kh',
-    { "ऒ", "ou" },
+	['ग']='g',
-     { "उ", "u"},
+	['घ']='gh',
+	['च']='c',
+	['छ']='ch',
+	['ज']='j',
+	['झ']='jh',
+	['ञ']='ñ',
+	['श']='ś',
+	['झ़']='ź',
+	['ट']='ṭ',
+	['ठ']='ṭh',
+	['ड']='ḍ',
+	['ढ']='ḍh',
+	['ण']='ṇ',
+	['ष']='ṣ',
+	['ढ़']='ẓ',
+	['त']='t',
+	['थ']='th',
+	['द']='d',
+	['ध']='dh',
+	['न']='n',
+	['स']='s',
+	['ज़']='z',
+	['प']='p',
+	['फ']='ph',
+	['ब']='b',
+	['भ']='bh',
+	['म']='m',
+	['य']='y',
+	['र']='r',
+	['ल']='l',
+	['व']='v',
+	['ह']='h',
+}
+local diacritics = {
+	['ा']='ā',
+	['ि']='i',
+	['ी']='ī',
+	['ु']='u',
+	['ू']='ū',
+	['ॆ']='ei',
+	['े']='ēi',
+	['ॅ']='e',
+	['ै']='ē',
+	['ॊ']='ou',
+	['ो']='ōu',
+	['ॉ']='o',
+	['ौ']='ō',
+	['्']='',
+}
+local tt = {
+	-- vowels
+	['अ']='a',
+	['आ']='ā',
+	['इ']='i',
+	['ई']='ī',
+	['उ']='u',
+	['ऊ']='ū',
+	['ऎ']='ei',
+	['ए']='ēi',
+	['ऍ']='e',
+	['ऐ']='ē',
+	['ऒ']='ou',
+	['ओ']='ōu',
+	['ऑ']='o',
+	['औ']='ō',
+	-- anusvara
+	['ं']='̣',
+	-- visarga
+	['ः']='h',
+	-- avagraha
+	['ऽ']='ʼ',
+	['़']='',
+	--numerals
+	['०']='0', ['१']='1', ['२']='2', ['३']='3', ['४']='4', ['५']='5', ['६']='6', ['७']='7', ['८']='8', ['९']='9',
+	['॒']='́',
+	['॑']='́',
+	--punctuation
+--  ['॥']='.', --double danda
+--	['।']='.', --danda
+     --Om
+    ['ॐ']='oṃ',
+    --reconstructed
+--  ['*'] = '',
 }
 function export.tr(text, lang, sc)
-	text = mw.ustring.lower(text)
+	if sc ~= "Deva" then
+		return nil
+	end
+		text = gsub(text,'([क-ह]़?)'..'([ािीुूृॄॢॣेैोौ्ॅॆॊॉ]?)'..'([अ-औ]?)',function(c, d, e)
+			if d == "" and e ~= "" then
+				if tt[e] == "i" or tt[e] == "u" then return consonants[c] .. 'a' .. tt[e] .. diaeresis
+				else return consonants[c] .. 'a' .. tt[e] end
+            elseif e ~= "" then
+				return consonants[c] .. diacritics[d] .. tt[e]
+			elseif d == "" then
+				return consonants[c] .. 'a'
+			else
+				return consonants[c] .. diacritics[d]
+			end
+		end)
-	for _, rule in ipairs(tt) do
+	text = gsub(text, "ः॑","́h")
-		text = mw.ustring.gsub(text, rule[1], rule[2])
+	text = gsub(text, '([aअ][' .. acute .. grave .. ']?[इउ])', '%1' .. diaeresis)
-	end
+	text = gsub(text, '.', tt)
+	text = gsub(text, 'a([iu])([' .. acute .. grave .. '])', 'a%2%1')
-    return text
+	text = gsub(text, 'e([i])([' .. acute .. grave .. '])', 'e%2%1')
+	text = gsub(text, 'o([u])([' .. acute .. grave .. '])', 'o%2%1')
+	text = gsub(text, 'ē([i])([' .. acute .. grave .. '])', 'ē%2%1')
+	text = gsub(text, 'ō([u])([' .. acute .. grave .. '])', 'ō%2%1')
+	text = gsub(text, " ?[।॥]", ".")
+	text = gsub(text, "(ā" .. acute .. "3[iu])" .. acute, "%1") -- for pluti vowels
+	text = toNFC(text)
+	return text
 end
 return export