Module:typing-aids/data/sa-Gujr

---

This module lacks a documentation subpage. Please create it.

Useful links: root page • root page’s subpages • links • transclusions • testcases • sandbox

local data = {}

local U = require("Module:string/char")

local anusvAra = U(0x0A82)
local visarga = U(0x0A83)
local virAma = U(0x0ACD)
local avagraha = "ઽ"
local consonants = "કખગઘઙચછજઝઞટઠડઢણતથદધનપફબભમયરલવળશષસહ"
local consonant = "[" .. consonants .. "]"

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

data["sa-Gujr"] = {
	-- Vowels and modifiers. Do the diphthongs and diaereses first.
	{"ai", "ઐ"},
	{"au", "ઔ"},
	{"ä", "અ"},
	{"ö", "ઓ"},
	{"ï", "ઇ"},
	{"ü", "ઉ"},
	{"a", "અ"},
	{"ā", "આ"},
	{"i", "ઇ"},
	{"ī", "ઈ"},
	{"u", "ઉ"},
	{"ū", "ઊ"},
	{"e", "𑆍"},
	{"o", "ઓ"},
	{"ṝ", "ૠ"},
	{"ṛ", "ઋ"},
	{"r̥", "ઋ"},
	{"ḹ", "ૡ"},
	{"ḷ", "ઌ"},
	{"(અ)[%-/]([ઇઉ])", "%1%2"},		-- a-i, a-u for अइ, अउ; must follow rules for "ai", "au"

	-- Two-letter consonants must go before h.
	{"kh", "ખ"},
	{"gh", "ઘ"},
	{"ch", "છ"},
	{"jh", "ઝ"},
	{"ṭh", "ઠ"},
	{"ḍh", "ઢ"},
	{"th", "થ"},
	{"dh", "ધ"},
	{"ph", "ફ"},
	{"bh", "ભ"},
	{"h", "હ"},

	-- Other stops.
	{"k", "ક"},
	{"g", "ગ"},
	{"c", "ચ"},
	{"j", "જ"},
	{"ṭ", "ટ"},
	{"ḍ", "ડ"},
	{"t", "ત"},
	{"d", "દ"},
	{"p", "પ"},
	{"b", "બ"},

	-- Nasals.
	{"ṅ", "ઙ"},
	{"ñ", "ઞ"},
	{"ṇ", "ણ"},
	{"n", "ન"},
	{"m", "મ"},

	-- Remaining consonants.
	{"y", "ય"},
	{"r", "ર"},
	{"l", "લ"},
	{"v", "વ"},
	{"ś", "શ"},
	{"ṣ", "ષ"},
	{"s", "સ"},

	{"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 = {
	["આ"] = U(0x0ABE),
	["ઇ"] = U(0x0ABF),
	["ઈ"] = U(0x0AC0),
	["ઉ"] = U(0x0AC1),
	["ઊ"] = U(0x0AC2),
	["ઋ"] = U(0x0AC3),
	["ૠ"] = U(0x0AC4),
	["એ"] = U(0x0AC5),
	["ઐ"] = U(0x0AC8),
	["ઌ"] = U(0x0AE2),
	["ૡ"] = U(0x0AE3),
	["ઓ"] = U(0x0ACB),
	["ઔ"] = U(0x0ACC),
}

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

-- [[w:Harvard-Kyoto]] to [[w:International Alphabet of Sanskrit Transliteration]]
data["sa-Gujr-tr"] = {
	[1] = {
		["A"] = "ā",
		["I"] = "ī",
		["U"] = "ū",
		["J"] = "ñ",
		["T"] = "ṭ",
		["D"] = "ḍ",
		["N"] = "ṇ",
		["G"] = "ṅ",
		["z"] = "ś",
		["S"] = "ṣ",
		["M"] = "ṃ",
		["H"] = "ḥ",
		["lRR"] = "ḹ",
		["/"] = acute,
	},
	[2] = {
		["lR"] = "ḷ",
		["RR"] = "ṝ",
	},
	[3] = {
		["R"] = "ṛ",
	},
}

return data