မဝ်ဂျူ:kxv-translit

Testcases

Module:kxv-IPA/testcases:

All tests passed. (refresh)

test_translit_kuvi:

	လိက်	ဗွဲမရံၚ်လၟဳ	မဇေတ်ဍာံ	တၚ်လညာတ်ဂမၠိုၚ်
	ଅଡୁ	oḍu	oḍu	independent ଅ is o
	ଓଡୁ	oḍu	oḍu	independent ଓ is o
	ଅ୕ଡୁ	ōḍu	ōḍu	independent ଅ୕ is ō
	ଓଓଡୁ	ōḍu	ōḍu	independent ଓଓ is ō
	ଆକୁ	aku	aku	independent ଆ is a
	ଆ୕କୁ	āku	āku	independent ଆ୕ is ā
	ଆଆକୁ	āku	āku	independent ଆଆ is ā
	ଏସ୍କି	eski	eski	independent ଏ is e
	ଏ୕ସ୍କି	ēski	ēski	independent ଏ୕ is ē
	ଏଏସ୍କି	ēski	ēski	independent ଏଏ is ē
	କଡି	koḍi	koḍi	dependent ଅ/ଓ is o
	କ୕ଡି	kōḍi	kōḍi	dependent ଅ୕ is ō
	କୋଓଡି	kōḍi	kōḍi	dependent ଓଓ is ō
	ବାଲା	bala	bala	dependent ଆ is a
	ବା୕ଲା	bāla	bāla	dependent ଆ୕ is ā
	ବଆଲା	bāla	bāla	dependent ଆଆ is ā
	ମେଣ୍ଡା	meṇḍa	meṇḍa	dependent ଏ is e
	ମେ୕ଣ୍ଡା	mēṇḍa	mēṇḍa	dependent ଏ୕ is ē
	ମେଏଣ୍ଡା	mēṇḍa	mēṇḍa	dependent ଏଏ is ē
	ଇଇ	ī	ī	independent ଇଇ is ī
	ଉଉ	ū	ū	independent ଉଉ is ū
	କିଇ	kī	kī	dependent ଇଇ is ī
	କୁଉ	kū	kū	dependent ଉଉ is ū
	କୁଃଏ	kuʔe	kuʔe	glottal stop ʔ
	ବିସେୟିଁ	biseyĩ	biseyĩ	chandrabindu

---

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

local consonants = {
	--common
	["କ"]="k", ["ଖ"]="kh", ["ଗ"]="g", ["ଘ"]="gh", ["ଙ"]="ṅ",
	["ଚ"]="c", ["ଛ"]="ch", ["ଜ"]="j", ["ଝ"]="jh", ["ଞ"]="ñ", 
	["ଟ"]="ṭ", ["ଠ"]="ṭh", ["ଡ"]="ḍ", ["ଢ"]="ḍh", ["ଣ"]="ṇ", 
	["ତ"]="t", ["ଥ"]="th", ["ଦ"]="d", ["ଧ"]="dh", ["ନ"]="n", 
	["ପ"]="p", ["ଫ"]="ph", ["ବ"]="b", ["ଭ"]="bh", ["ମ"]="m",
	["ଯ"]="j", ["ୟ"]="y", ["ର"]="r", ["ଲ"]="l", ["ଳ"]="ḷ",
	["ଵ"]="v", ["ୱ"]="w", ["ଶ"]="ś", ["ଷ"]="ṣ", ["ସ"]="s", ["ହ"]="h",
	--nuktas
	["କ଼"]="q", ["ଖ଼"]="x", ["ଗ଼"]="ġ", ["ଜ଼"]="z", ["ଝ଼"]="ź",
	["ଡ଼"]="ṛ", ["ଢ଼"]="ṛh", ["ଫ଼"]="f",
}

local diacritics = {
	["ା"]="a", ["ି"]="i", ["ୀ"]="ī", ["ୁ"]="u", ["ୂ"]="ū", ["ୃ"]="ru", ["ୄ"]="rū", 
	["ୢ"]="lu", ["ୣ"]="lū", ["େ"]="e", ["ୈ"]="oi", ["ୖ"]="oi", ["ୋ"]="o", ["ୌ"]="ou", ["ୗ"]="ou",
	["୍"]="",
}

local tt = {
	-- vowels
	["ଅ"]="o", ["ଆ"]="a", ["ଇ"]="i", ["ଈ"]="ī", ["ଉ"]="u", ["ଊ"]="ū", ["ଋ"]="ru", ["ୠ"]="rū",
	["ଌ"]="lu", ["ୡ"]="lū", ["ଏ"]="e", ["ଐ"]="oi", ["ଓ"]="o", ["ଔ"]="ou",
	-- chandrabindu    
	["ଁ"]="̃", --until a better method is found
	-- anusvara    
	["ଂ"]="ṁ", --until a better method is found
	-- visarga    
	["ଃ"]="ʔ",
	-- avagraha
	["ଽ"]="’",
	--numerals
	["୦"]="0", ["୧"]="1", ["୨"]="2", ["୩"]="3", ["୪"]="4", ["୫"]="5", ["୬"]="6", ["୭"]="7", ["୮"]="8", ["୯"]="9",
	["୲"]="¼", ["୳"]="½", ["୴"]="¾", ["୵"]="¹⁄₁₆", ["୶"]="⅛", ["୷"]="³⁄₁₆",
	--punctuation        
	["।"]=".", --danda
}

function export.tr(text, lang, sc)
	text = gsub(
		text,
		"([କଖଗଘଙଚଛଜଝଞଟଠଡଢଣତଥଦଧନପଫବଵଭମଯୟରଲଳୱଶଷସହ]଼?)"..
		"([ାିୀୁୂୃୄେୈୖୋୌୗ୍ୢୣ]?)",
		function(c, d)
			if not consonants[c] then
				return c
			end
			if d == "" then
				return consonants[c] .. "o"
			else
				return consonants[c] .. diacritics[d]
			end
		end)

	text = mw.ustring.gsub(text, ".", tt)
	
	-- anusvara
	text = gsub(text, 'ṁ([kqxgġṅ])', 'ṅ%1')
	text = gsub(text, 'ṁ([cjźñ])', 'ñ%1')
	text = gsub(text, 'ṁ([ṭḍṇ])', 'ṇ%1')
	text = gsub(text, 'ṁ([tdnz])', 'n%1')
	text = gsub(text, 'ṁ([pfbm])', 'm%1')

	-- long vowels
	text = gsub(text, '([oaāiue])%1', '%1̄') -- VV → V̄ 
	text = gsub(text, '([oea])୕', '%1̄')
	text = gsub(text, 'oa', 'ā') 
	text = gsub(text, 'aā', 'ā')

	return mw.ustring.toNFC(text)
	
end
 
return export