Module:User:Erutuon/grc/Latin to Greek

---

The following documentation is located at Module:User:Erutuon/grc/Latin to Greek/documentation. ^[edit]

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

A function that converts from ASCII to Ancient Greek. Based on Module:typing-aids and Module:typing-aids/data/grc, but faster.

local reorder_diacritics = require("Module:grc-utilities").reorderDiacritics
local ustring = mw.ustring
local U = ustring.char
local ufind = ustring.find
local str_gsub = string.gsub

local UTF8_char = "[%z\1-\127\194-\244][\128-\191]*" -- roughly equivalent to "." in Ustring patterns
local one_UTF8_char_or_none = "[%z\1-\127\194-\244]?[\128-\191]*" -- roughly equivalent to ".?" in Ustring patterns

local subscript = U(0x345) -- iota subscript (ypogegrammeni)
local macron = U(0x304) -- macron
local spacing_macron = U(0xAF)
local modifier_macron = U(0x2C9) -- modifier letter macron
local breve = U(0x306) -- breve
local spacing_breve = "˘" -- spacing breve
local diaeresis = U(0x308) -- diaeresis
local rough = U(0x314) -- rough breathing (reversed comma)
local smooth = U(0x313) -- smooth breathing (comma)
local acute = U(0x301) -- acute
local grave = U(0x300) -- grave
local circumflex = U(0x342) -- Greek circumflex (perispomeni)
local question_mark = U(0x37E) -- Greek question mark
local spacing_rough = "῾" -- spacing rough breathing
local spacing_smooth = "᾿" -- spacing smooth breathing

local multiple = {
	["_i"] = subscript,
}

local single = {
	["a"] = "α", ["A"] = "Α",
	["b"] = "β", ["B"] = "Β",
	["c"] = "ξ", ["C"] = "Ξ",
	["d"] = "δ", ["D"] = "Δ",
	["e"] = "ε", ["E"] = "Ε",
	["f"] = "φ", ["F"] = "Φ",
	["g"] = "γ", ["G"] = "Γ",
	["h"] = "η", ["H"] = "Η",
	["i"] = "ι", ["I"] = "Ι",
	["k"] = "κ", ["K"] = "Κ",
	["l"] = "λ", ["L"] = "Λ",
	["m"] = "μ", ["M"] = "Μ",
	["n"] = "ν", ["N"] = "Ν",
	["o"] = "ο", ["O"] = "Ο",
	["p"] = "π", ["P"] = "Π",
	["q"] = "θ", ["Q"] = "Θ",
	["r"] = "ρ", ["R"] = "Ρ",
	["s"] = "σ", ["S"] = "Σ",
	["t"] = "τ", ["T"] = "Τ",
	["u"] = "υ", ["U"] = "Υ",
	["v"] = "ϝ", ["V"] = "Ϝ",
	["w"] = "ω", ["W"] = "Ω",
	["x"] = "χ", ["X"] = "Χ",
	["y"] = "ψ", ["Y"] = "Ψ",
	["z"] = "ζ", ["Z"] = "Ζ",
	
	-- vowel length
	["_"] = macron, [spacing_macron] = macron, [modifier_macron] = macron,
	["^"] = breve, [spacing_breve] = breve,
	
	-- diaeresis and breathings
	["+"] = diaeresis, ["("] = rough, [")"] = smooth,
	
	-- accents
	["/"] = acute, ["\\"] = grave,
	["="] = circumflex, ["{{=}}"] = circumflex, ["~"] = circumflex,
	
	-- punctuation
	["'"] = "’",
	["?"] = question_mark,
	[";"] = "·",
	["*"] = "", -- place after s to prevent it from turning into final sigma
	
	-- pipe
	["!"] = "|",
}

local function convert_s_to_sigma(text)
	text = str_gsub(text,
		"s(" .. one_UTF8_char_or_none .. ")",
		function (following)
			return ((following == ""
				or following ~= "*" and following ~= "-" and ufind(following, "[%s%p]"))
				and  "ς"
				or "σ") .. following
		end)
	return text
end

local function combining_to_spacing(text)
	for i, accents in ipairs{ { rough, spacing_rough }, { smooth, spacing_smooth } } do
		local combining, spacing = unpack(accents)
		text = str_gsub(text,
			"(" .. one_UTF8_char_or_none .. ")" .. combining,
			function (preceding)
				if preceding == "" then
					return spacing
				else
					return preceding .. combining
				end
			end)
	end
	
	return text
end

return function(text)
	text = convert_s_to_sigma(text)
	for k, v in pairs(multiple) do
		text = str_gsub(text, k, v)
	end
	text = str_gsub(text, UTF8_char, single)
	text = combining_to_spacing(text)
	return reorder_diacritics(text)
end