Modul:grc-translit

Ez a modul ógörög nyelvű szöveg átírására szolgál. Használatos cappadocian greek, paeonian, old ossetic, pontic greek, ancient macedonian és phrygian szöveg átírásához is.

Ezt a modult lehetőleg nem kellene közvetlenül más sablonokból vagy modulokból hívni. Sablonból az {{xlit}}^(?) segédsablon, modulból pedig a Module:languages#Language:transliterate metódus használandó.

Függvények

tr(text, lang, sc): Átírja a text szöveg sc kódú írásrendszerrel írott és lang nyelvű részét. Ha az átírás sikertelen, nilt ad vissza.

1 teszt sikertelen. (frissítés)

test_translit:
	Szöveg	Várt	Tényleges
	λόγος	lógos	lógos
	σφίγξ	sphínx	sphínx
	ϝάναξ	wánax	wánax
	οおみくろんἷαあるふぁιいおた	hoîai	hoîai
u/y
	τたうαあるふぁῦρος	taûros	taûros
	νにゅーηいーたῦς	nēûs	nēûs
	σしぐまῦς	sûs	sûs
	ὗς	hûs	hûs
	γがんまυうぷしろんῖοおみくろんνにゅー	guîon	guîon
	ἀνにゅーαあるふぁῡ̈τέω	anaṻtéō	anaṻtéō
	δαΐφρων	daḯphrōn	daḯphrōn
vowel length
	τたうῶνにゅー	tôn	tôn
	τたうοおみくろんὶ	toì	toì
	τたうῷ	tôi	tôi
	τούτῳ	toútōi	toútōi
	σοφίᾳ	sophíāi	sophíāi
	μみゅーᾱ̆νός	mānós	mānós
h (rough breathing)
	ὁ	ho	ho
	οおみくろんἱ	hoi	hoi
	εいぷしろんὕρισκε	heúriske	heúriske
	ὑϊκός	huïkós	huïkós
	πυρρός	purrhós	purrhós
	ῥέω	rhéō	rhéō
	σάἁμみゅーοおみくろんνにゅー	sáhamon	sáhamon
capitals
	Ὀδυσσεύς	Odusseús	Odusseús
	Εいぷしろんἵλως	Heílōs	Heílōs
	ᾍδης	Hā́idēs	Hā́idēs
	ἡ Ἑλήνη	hē Helḗnē	hē Helḗnē
	𐠠𐠒𐠯𐠗	pi-lo-ti-mo	𐠠𐠒𐠯𐠗
punctuation
	ἔχεις μみゅーοおみくろんιいおた εいぷしろんἰπぱいεいぷしろんῖνにゅー, ὦ Σώκρατες, ἆρろーαあるふぁ διδακτὸνにゅー ἡ ἀρετή;	ékheis moi eipeîn, ô Sṓkrates, âra didaktòn hē aretḗ?	ékheis moi eipeîn, ô Sṓkrates, âra didaktòn hē aretḗ?
	τί τηνικάδε ἀφふぁいῖξくしーαあるふぁιいおた, ὦ Κρίτων; ἢ οおみくろんὐ πぱいρろーῲ ἔτたうιいおた ἐστίν;	tí tēnikáde aphîxai, ô Krítōn? ḕ ou prṑi éti estín?	tí tēnikáde aphîxai, ô Krítōn? ḕ ou prṑi éti estín?
	τούτων φωνήεντα μέν ἐστιν ἑπτά· αあるふぁ εいぷしろん ηいーた ιいおた οおみくろん υうぷしろん ωおめが.	toútōn phōnḗenta mén estin heptá; a e ē i o u ō.	toútōn phōnḗenta mén estin heptá; a e ē i o u ō.
	πήγ(νにゅーῡμみゅーῐ)	pḗg(nūmi)	pḗg(nūmi)
HTML entities
	καλός κかっぱαあるふぁὶ ἀγαθός	kalós kaì agathós	kalós kaì agathós
	καλός κかっぱαあるふぁὶ ἀγαθός	kalós kaì agathós	kalós kaì agathós

local export = {}

local m_data = require('Module:grc-utilities/data')
local tokenize = require('Module:grc-utilities').tokenize

local ufind = mw.ustring.find
local ugsub = mw.ustring.gsub
local U = mw.ustring.char
local ulower = mw.ustring.lower
local uupper = mw.ustring.upper

local UTF8char = '[%z\1-\127\194-\244][\128-\191]*'

-- Diacritics
local diacritics = m_data.named

-- Greek
local acute = diacritics.acute
local grave = diacritics.grave
local circumflex = diacritics.circum
local diaeresis = diacritics.diaeresis
local smooth = diacritics.smooth
local rough = diacritics.rough
local macron = diacritics.macron
local breve = diacritics.breve
local subscript = diacritics.subscript

-- Latin
local hat = diacritics.Latin_circum

local macron_diaeresis = macron .. diaeresis .. "?" .. hat
local a_subscript = '^[αあるふぁΑあるふぁ].*' .. subscript .. '$'
local velar = 'κγχξ'

local tt = {
	-- Vowels
	["αあるふぁ"] = "a",
	["εいぷしろん"] = "e",
	["ηいーた"] = "e" .. macron,
	["ιいおた"] = "i",
	["οおみくろん"] = "o",
	["υうぷしろん"] = "u",
	["ωおめが"] = "o" .. macron,

	-- Consonants
	["βべーた"] = "b",
	["γがんま"] = "g",
	["δでるた"] = "d",
	["ζぜーた"] = "z",
	["θしーた"] = "th",
	["κかっぱ"] = "k",
	["λらむだ"] = "l",
	["μみゅー"] = "m",
	["νにゅー"] = "n",
	["ξくしー"] = "x",
	["πぱい"] = "p",
	["ρろー"] = "r",
	["σしぐま"] = "s",
	["ς"] = "s",
	["τたう"] = "t",
	["φふぁい"] = "ph",
	["χかい"] = "kh",
	["ψぷさい"] = "ps",
	
	-- Archaic letters
	["ϝ"] = "w",
	["ϻ"] = "ś",
	["ϙ"] = "q",
	["ϡ"] = "š",
	["ͷ"] = "v",
	
	-- Incorrect characters: see [[Wiktionary:About Ancient Greek#Miscellaneous]].
	-- These are tracked by [[Module:script utilities]].
	["ϐ"] = "b",
	["ϑ"] = "th",
	["ϰ"] = "k",
	["ϱ"] = "r",
	["ϲ"] = "s",
	["ϕ"] = "ph",
	
	-- Diacritics
	-- unchanged: macron, diaeresis, grave, acute
	[breve] = '',
	[smooth] = '',
	[rough] = '',
	[circumflex] = hat,
	[subscript] = 'i',
}

function export.tr(text, lang, sc)
	if text == '῾' then
		return 'h'
	end
	
	--[[
		Replace semicolon or Greek question mark with regular question mark,
		except after an ASCII alphanumeric character (to avoid converting
		semicolons in HTML entities).
	]]
	text = ugsub(text, "([^A-Za-z0-9])[;" .. U(0x37E) .. "]", "%1?")
	
	-- Handle the middle dot. It is equivalent to semicolon or colon, but semicolon is probably more common.
	text = text:gsub("·", ";")
	
	local tokens = tokenize(text)

	--now read the tokens
	local output = {}
	for i, token in pairs(tokens) do
		-- Convert token to lowercase and substitute each character
		-- for its transliteration
		local translit = ulower(token):gsub(UTF8char, tt)
		
		local next_token = tokens[i + 1]
		
		if token == 'γがんま' and next_token and velar:find(next_token, 1, true) then
			-- γがんま before a velar should be <n>
			translit = 'n'
		elseif token == 'ρろー' and tokens[i - 1] == 'ρろー' then
			-- ρろー after ρろー should be <rh>
			translit = 'rh'
		elseif ufind(token, a_subscript) then
			-- add macron to ᾳ
			translit = ugsub(translit, '([aA])', '%1' .. macron)
		end
		
		if token:find(rough) then
			if ufind(token, '^[Ρろーρろー]') then
				translit = translit .. 'h'
			else -- vowel
				translit = 'h' .. translit
			end
		end
		
		-- Remove macron from a vowel that has a circumflex.
		if ufind(translit, macron_diaeresis) then
			translit = translit:gsub(macron, '')
		end
		
		-- Capitalize first character of transliteration.
		if token ~= ulower(token) then
			translit = translit:gsub("^" .. UTF8char, uupper)
		end
		
		table.insert(output, translit)
	end
	output = table.concat(output)
	
	return output
end

return export