Module:typing-aids/data/kn

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


local data = {}

local U = mw.ustring.char

local candrabindu = U(0xC81)
local anusvAra = U(0xC82)
local visarga = U(0xC83)
local virAma = U(0xCCD)
local avagraha = "ಽ"
local consonants = "ಕಖಗಘಙಚಛಜಝಞಟಠಡಢಣತಥದಧನಪಫಬಭಮಯರಱಲವಶಷಸಹಳೞ"
local consonant = "[" .. consonants .. "]"

local acute = U(0x301)		-- combining acute

data["kn"] = {
	-- Vowels and modifiers. Do the diphthongs and diaereses first.
	{"ai", "ಐ"},
	{"au", "ಔ"},
	{"ï", "ಇ"},
	{"ü", "ಉ"},
	{"a", "ಅ"},
	{"ā", "ಆ"},
	{"i", "ಇ"},
	{"ī", "ಈ"},
	{"u", "ಉ"},
	{"ū", "ಊ"},
	{"e", "ಎ"},
	{"ē", "ಏ"},
	{"o", "ಒ"},
	{"ō", "ಓ"},
	{"ṝ", "ೠ"},
	{"ṛ", "ಋ"},
	{"r̥", "ಋ"},
	{"ḹ", "ೡ"},
	{"l̥", "ಌ"},
	{"(ಅ)[%-/]([ಇಉ])", "%1%2"},		-- a-i, a-u for ಅಇ, ಅಉ; must follow rules for "ai", "au"
	{"(ಲ)[%-/]([ೃ ೄ])", "%1%2"},		-- l-R, l-RR for ಲೃ, ಲೄ; must follow rules for "lR", "lRR"

	-- Two-letter consonants must go before h.
	{"kh", "ಖ"},
	{"gh", "ಘ"},
	{"ch", "ಛ"},
	{"jh", "ಝ"},
	{"ṭh", "ಠ"},
	{"ḍh", "ಢ"},
	{"th", "ಥ"},
	{"dh", "ಧ"},
	{"ph", "ಫ"},
	{"bh", "ಭ"},
	{"h", "ಹ"},

	-- Other stops.
	{"k", "ಕ"},
	{"g", "ಗ"},
	{"c", "ಚ"},
	{"j", "ಜ"},
	{"ṭ", "ಟ"},
	{"ḍ", "ಡ"},
	{"t", "ತ"},
	{"d", "ದ"},
	{"p", "ಪ"},
	{"b", "ಬ"},

	-- Nasals.
	{"ṅ", "ಙ"},
	{"ñ", "ಞ"},
	{"ṇ", "ಣ"},
	{"n", "ನ"},
	{"m", "ಮ"},

	-- Remaining consonants.
	{"y", "ಯ"},
	{"r", "ರ"},
	{"l", "ಲ"},
	{"v", "ವ"},
	{"ś", "ಶ"},
	{"ṣ", "ಷ"},
	{"s", "ಸ"},
	{"ḷ", "ಳ"},

	{"m̐", candrabindu},
	{"ṃ", anusvAra},
	{"ḥ", visarga},
	{"'", avagraha},
	-- This rule must be applied twice because a consonant may only be in one capture per operation,
	-- so "CCC" will only recognize the first two consonants. Must follow all consonant conversions.
	{"(" .. consonant .. ")(" .. consonant .. ")", "%1" .. virAma .. "%2"},
	{"(" .. consonant .. ")(" .. consonant .. ")", "%1" .. virAma .. "%2"},
	{"(" .. consonant .. ")$", "%1" .. virAma},
	{acute, ""},
}

local vowels = {
	["ಇ"] = U(0xCBF),
	["ಉ"] = U(0xCC1),
	["ಋ"] = U(0xCC3),
	["ಌ"] = U(0xCE2),
	["ಎ"] = U(0xCC6),
	["ಏ"] = U(0xCC7),
	["ಎ"] = U(0xCCA),
	["ಓ"] = U(0xCCB),
	["ಆ"] = U(0xCBE),
	["ಈ"] = U(0xCC0),
	["ಊ"] = U(0xCC2),
	["ೠ"] = U(0xCC4),
	["ೡ"] = U(0xCE3),
	["ಐ"] = U(0xCC8),
	["ಔ"] = U(0xCCC),
}

-- Convert independent vowels to diacritics after consonants. Must go after all consonant conversions.
for independentForm, diacriticalForm in pairs(vowels) do
	table.insert(data["kn"], {"(" .. consonant .. ")" .. independentForm, "%1" .. diacriticalForm})
end

-- This must go last, after independent vowels are converted to diacritics, or "aï", "aü" won't work.
table.insert(data["kn"], {"(" .. consonant .. ")ಅ", "%1"})

data["kn-tr"] = {
	[1] = {
		["A"] = "ā",
		["I"] = "ī",
		["U"] = "ū",
		["E"] = "ē",
		["O"] = "ō",
		["J"] = "ñ",
		["T"] = "ṭ",
		["D"] = "ḍ",
		["L"] = "ḷ",
		["N"] = "ṇ",
		["G"] = "ṅ",
		["z"] = "ś",
		["S"] = "ṣ",
		["M"] = "ṃ",
		["H"] = "ḥ",
	},
	[2] = {
		["lR"] = "l̥",
		["lRR"] = "ḹ",
	},
	[3] = {
		["R"] = "ṛ",
		["RR"] = "ṝ",
	},
}

return data