Module:Geor-translit

This module will transliterate text in the Georgian script per WT:GEOR TR. It is used to transliterate Abkhaz, Bats, Georgian, Old Georgian, Ossetian, Udi, and Mingrelian. The module should preferably not be called directly from templates or other modules. To use it from a template, use {{xlit}}. Within a module, use Module:languages#Language:transliterate.

For testcases, see Module:Geor-translit/testcases.

Functions

tr(text, lang, sc)
Transliterates a given piece of text written in the script specified by the code sc, and language specified by the code lang.
When the transliteration fails, returns nil.

local m_str_utils = require("Module:string utilities")

local codepoint = m_str_utils.codepoint
local gsub = m_str_utils.gsub
local u = m_str_utils.char
local upper = m_str_utils.upper

local export = {}

	-- Keep synchronized with [[Module:sva-translit]] and [[Module:Geok-translit]]
local tt = {
	["ა"]="a", ["ბ"]="b", ["გ"]="g", ["დ"]="d", ["ე"]="e", ["ვ"]="v", ["ზ"]="z", ["ჱ"]="ē",
	["თ"]="t", ["ი"]="i", ["კ"]="ḳ", ["ლ"]="l", ["მ"]="m", ["ნ"]="n", ["ჲ"]="y", ["ო"]="o",
	["პ"]="ṗ", ["ჟ"]="ž", ["რ"]="r", ["ს"]="s", ["ტ"]="ṭ", ["ჳ"]="wi", ["უ"]="u", ["ფ"]="p",
	["ქ"]="k", ["ღ"]="ɣ", ["ყ"]="q̇", ["შ"]="š", ["ჩ"]="č", ["ც"]="c",
	["ძ"]="ʒ", ["წ"]="c̣", ["ჭ"]="č̣", ["ხ"]="x", ["ჴ"]="q", ["ჯ"]="ǯ", ["ჰ"]="h", ["ჵ"]="'", ["ჶ"]="f", ["ჷ"]="ə", ["ჸ"]="ʾ", ["ჺ"]="ʿ", ["ʻ"]="ˢ",
};

function export.tr(text, lang, sc)
	-- Transliterating vowel nasalization in Bats
	text = gsub(text, 'ჼ', '̃')
	text = gsub(text, '<sup>ნ</sup>', '̃')
	
	-- Transliterate uppercase characters from the Georgian Extended block as
	-- the uppercase version of the transliteration of the lowercase  characters
	-- from the Georgian block.
	-- U+10D0: start of Georgian block
	-- U+1C90: start of Georgian Extended block
	text = gsub(
		text,
		'[' .. u(0x1C90) .. '-' .. u(0x1CBF) .. ']',
		function (char)
			local translit = tt[u(codepoint(char) - 0x1C90 + 0x10D0 )]
			return translit and upper(translit)
		end)
	text = gsub(text, '.', tt)
	return text
end

return export