Modul:Umschrift

Die Dokumentation für dieses Modul kann unter Modul:Umschrift/Doku erstellt werden

-- Stand 5. August 2024, 17:12 Quelle nur für "function Umschrift.agrDIN(str)" in der Quelle "function Umschrift.grc(str)" siehe https://de.wiktionary.org/wiki/Modul:Umschrift
-- Erzeugt die lateinische Umschrift eines Textes in altgriechische Schriftart in den Funktionen nach DIN 31634:2011-10 agr.DIN, demgemäß Zahlen nach agrZZ, englischem Wiktonary agrEIN 
-- Ein weiteres Modul zur Umschrift ist Modul:Umschriftung mit Lua-Tabelle Modul:Umschriftung/agrie.

local Umschrift = {}

function Umschrift.main(frame)
	Sprachkuerzel = frame.args.spr
	if (Sprachkuerzel == "ab") then
		return Umschrift.ab(frame.args[1])
	elseif (Sprachkuerzel == "agrDIN") then
		return Umschrift.agrDIN(frame.args[1])
	elseif (Sprachkuerzel == "agrEIN") then
		return Umschrift.agrEIN(frame.args[1])
	end
end

-- Erzeugt die lateinische Umschrift eines Textes in altgriechischer Schrift
-- gemäß DIN 31634 (siehe auch Wikipedia:Griechisches Alphabet)
function Umschrift.agrDIN(str)
  local newstr = ""
  local newcp = 0
  local cp = 1
  local grb = "βΒδΔγΓϊΪκΚλΛμΜνΝπϖΠρῤϱΡσςΣτΤϋΫξΞζΖ;·Ϝϝ"
  local lat = "bBdDgGïÏkKlLmMnNppPrrrRssStTÿŸxXzZ?;Ww"
  local element = ""
  local strlen = mw.ustring.len(str)
  local j = 0
  local Kat = ""
  local possible2 = "y"
  local first = ""
  local second = ""
  local endgef = 0
  local Blank = "%s" -- whitespace
  local blgef = 0
  local pgef = 0

  while cp <= strlen do
-- Blank und Interpunktionen abarbeiten
	first = mw.ustring.sub(str, cp, cp)
	while (cp <= strlen and (first == " " or mw.ustring.find(first, "%p", 1))) do
		if first == ";" then
			newstr = newstr .. "?"
		elseif first == "·" then
			newstr = newstr .. ";"
		else
			newstr = newstr .. first
		end
		cp = cp + 1
		first = mw.ustring.sub(str, cp, cp)
	end
-- Zahlschrift überprüfen
	if cp <= strlen - 1 then
		blgef = mw.ustring.find(mw.ustring.sub(str, cp, strlen), Blank, 1)
		pgef = mw.ustring.find(mw.ustring.sub(str, cp, strlen), "%p", 1)
		endgef = strlen + 1
		if (blgef) then endgef = cp + blgef - 1 end
		if (pgef) then
			if pgef < endgef then endgef = cp + pgef - 1 end
		end
		local cpend = endgef - 1
		if (mw.ustring.sub(str, cpend, cpend) == "ʹ" or
			mw.ustring.sub(str, cp, cp) == "͵") then
			-- Zahlschrift ermitteln
			newstr = newstr .. Umschrift.grcZZ(mw.ustring.sub(str, cp, cpend))
			cp = endgef
		end
	end
-- zweistellige Buchstabenkominationen
	if (cp + 1 <= strlen and possible2 == "y") then
		element = (mw.ustring.sub(str, cp, cp+1))
		first = (mw.ustring.sub(str, cp, cp))
		second = (mw.ustring.sub(str, cp+1, cp+1))
  		if (first == "α" and mw.ustring.find("υύὺῠῡὐὔὒῦὖ", second, 1, true)) then
			newstr = newstr .. "au"
			cp = cp + 2
	  	elseif (first == "Α" and mw.ustring.find("υύὺῠῡὐὔὒῦὖ", second, 1, true)) then
			newstr = newstr .. "Au" 
			cp = cp + 2
		elseif (element == "αϋ") then
	  		newstr = newstr .. "aÿ"
			cp = cp + 2
		elseif (element == "Αϋ") then
  			newstr = newstr .. "Aÿ"
			cp = cp + 2
		elseif (first == "α" and mw.ustring.find("ἱἵἳἷ", second, 1, true)) then
			newstr = newstr .. "hai"
			cp = cp + 2
		elseif (first == "Α" and mw.ustring.find("ἱἵἳἷ", second, 1, true)) then
			newstr = newstr .. "Hai"
			cp = cp + 2
		elseif (first == "ε" and mw.ustring.find("ἱἵἳἷ", second, 1, true)) then
			newstr = newstr .. "hei"
			cp = cp + 2
		elseif (first == "Ε" and mw.ustring.find("ἱἵἳἷ", second, 1, true)) then
			newstr = newstr .. "Hei"
			cp = cp + 2
		elseif (first == "ε" and mw.ustring.find("ὑὕὓὗ", second, 1, true)) then
			newstr = newstr .. "heu"
			cp = cp + 2
		elseif (first == "Ε" and mw.ustring.find("ὑὕὓὗ", second, 1, true)) then
			newstr = newstr .. "Heu" 
			cp = cp + 2
		elseif (first == "ε" and mw.ustring.find("υύὺῠῡὐὔὒῦὖ", second, 1, true)) then
			newstr = newstr .. "eu"
			cp = cp + 2
		elseif (first == "Ε" and mw.ustring.find("υύὺῠῡὐὔὒῦὖ", second, 1, true)) then
			newstr = newstr .. "Eu" 
			cp = cp + 2
  		elseif (element == "ηυ") then
			newstr = newstr .. "ēu"
			cp = cp + 2
	  	elseif (element == "Ηυ") then
			newstr = newstr .. "Ēu" 
			cp = cp + 2
		elseif (element == "γγ") then
			newstr = newstr .. "ng"
			cp = cp + 2
		elseif (element == "Γγ") then
			newstr = newstr .. "Ng"
			cp = cp + 2
		elseif (element == "γκ") then
			if (cp == 1 or (cp > 1 and mw.ustring.sub(str, cp-1, cp-1) == " ")) then
				newstr = newstr .. "gk"
			else
				newstr = newstr .. "nk"
			end
			cp = cp + 2
		elseif (element == "Γk") then
			if (cp == 1 or (cp > 1 and mw.ustring.sub(str, cp-1, cp-1) == " ")) then
				newstr = newstr .. "Gk"
			else
				newstr = newstr .. "Nk"
			end
			cp = cp + 2
		elseif (element == "γξ") then
	  		newstr = newstr .. "nx"
			cp = cp + 2
		elseif (element == "Γξ") then
	  		newstr = newstr .. "Nx"
			cp = cp + 2
		elseif (element == "γχ") then
	  		newstr = newstr .. "nch"
	  		cp = cp + 2
		elseif (element == "Γχ") then
	  		newstr = newstr .. "Nch"
	  		cp = cp + 2
		elseif (element == "ηυ") then
	  		newstr = newstr .. "ēu"
	  		cp = cp + 2
		elseif (element == "Ηυ") then
	  		newstr = newstr .. "Ēu"
	  		cp = cp + 2
		elseif (first == "η" and mw.ustring.find("ὑὕὓὗ", second, 1, true)) then
	  		newstr = newstr .. "hēu"
	  		cp = cp + 2
		elseif (first == "Η" and mw.ustring.find("ὑὕὓὗ", second, 1, true)) then
	  		newstr = newstr .. "Hēu"
	  		cp = cp + 2
		elseif (first == "ο" and mw.ustring.find("ἱἵἳἷ", second, 1, true)) then
			newstr = newstr .. "hoi"
			cp = cp + 2
		elseif (first == "Ο" and mw.ustring.find("ἱἵἳἷ", second, 1, true)) then
			newstr = newstr .. "Hoi"
			cp = cp + 2
		elseif (first == "ο" and mw.ustring.find("ὑὕὓὗ", second, 1, true)) then
	  		newstr = newstr .. "hu"
	  		cp = cp + 2
		elseif (first == "Ο" and mw.ustring.find("ὑὕὓὗ", second, 1, true)) then
	  		newstr = newstr .. "Hu"
	  		cp = cp + 2
		elseif (first == "ο" and mw.ustring.find("υύὺῠῡὐὔὒῦὖ", second, 1, true)) then
			newstr = newstr .. "u"
			cp = cp + 2
		elseif (first == "Ο" and mw.ustring.find("υύὺῠῡὐὔὒῦὖ", second, 1, true)) then
			newstr = newstr .. "U"
			cp = cp + 2
		elseif (first == "υ" and mw.ustring.find("ἱἵἳἷ", second, 1, true)) then
			newstr = newstr .. "hyi"
			cp = cp + 2
		elseif (first == "Υ" and mw.ustring.find("ἱἵἳἷ", second, 1, true)) then
			newstr = newstr .. "Hyi"
			cp = cp + 2
		elseif (element == "ῤῥ") then
	  		newstr = newstr .. "rrh"
	  		cp = cp + 2
	  	else
	  		possible2 = "n"
		end
	elseif (cp <= strlen) then
-- einzelne Buchstaben
		local h_erwartet = ""
		element = mw.ustring.sub(str, cp, cp)
		if (cp == 1) then
			h_erwartet = "j"
		else
			local zuvor = mw.ustring.sub(str, cp-1, cp-1)
			if (zuvor == " " or mw.ustring.find(zuvor, "%p", 1)) then
				h_erwartet = "j"
			end
		end
		if (element == "θ" or element == "ϑ") then
			newstr = newstr .. "th"
		elseif (element == "Θ" or element == "ϴ") then
			newstr = newstr .. "Th"
		elseif (mw.ustring.find("αάὰᾰᾱᾷἀἄἂᾆᾶᾳᾴᾲἆᾀᾄᾂ", element, 1, true)) then
			newstr = newstr .. "a"
		elseif (mw.ustring.find("ΑΆᾺᾸᾹἈἌἊᾎᾼἎᾈᾌᾊ", element, 1, true)) then
			newstr = newstr .. "A"
		elseif (mw.ustring.find("εέὲἐἔἒ", element, 1, true)) then
			newstr = newstr .. "e"
		elseif (mw.ustring.find("ΕΈῈἘἜἚ", element, 1, true)) then
			newstr = newstr .. "E"
		elseif (mw.ustring.find("ηήὴῇἠἤἢᾖῆῃῄῂἦᾐᾔᾒ", element, 1, true)) then
			newstr = newstr .. "ē"
		elseif (mw.ustring.find("ΗΉῊἨἬἪᾞῌἮᾘᾜᾚ", element, 1, true)) then
			newstr = newstr .. "Ē"
		elseif (mw.ustring.find("ἁἅἃᾇἇᾁᾅᾃ", element, 1, true)) then
			if (h_erwartet ~= "") then
				newstr = newstr .. "ha"
			else
				newstr = newstr .. "a"
			end
		elseif (mw.ustring.find("ἉἍἋᾏἏᾉᾍᾋ", element, 1, true)) then
			if (h_erwartet ~= "") then
				newstr = newstr .. "Ha"
			else
				newstr = newstr .. "A"
			end
		elseif (mw.ustring.find("ἑἕἓ", element, 1, true)) then
			if (h_erwartet ~= "") then
				newstr = newstr .. "he"
			else
				newstr = newstr .. "e"
			end
		elseif (mw.ustring.find("ἙἝἛ", element, 1, true)) then
			if (h_erwartet ~= "") then
				newstr = newstr .. "He"
			else
				newstr = newstr .. "E"
			end
		elseif (mw.ustring.find("ἡἥἣᾗἧᾑᾕᾓ", element, 1, true)) then
			if (h_erwartet ~= "") then
				newstr = newstr .. "hē"
			else
				newstr = newstr .. "ē"
			end
		elseif (mw.ustring.find("ἩἭἫᾟἯᾙᾝᾛ", element, 1, true)) then
			if (h_erwartet ~= "") then
				newstr = newstr .. "Hē"
			else
				newstr = newstr .. "Ē"
			end
		elseif (mw.ustring.find("ἱἵἳἷ", element, 1, true)) then
			if (h_erwartet ~= "") then
				newstr = newstr .. "hi"
			else
				newstr = newstr .. "i"
			end
		elseif (mw.ustring.find("ἹἽἻἿ", element, 1, true)) then
			if (h_erwartet ~= "") then
				newstr = newstr .. "Hi"
			else
				newstr = newstr .. "I"
			end
		elseif (mw.ustring.find("ὁὅὃ", element, 1, true)) then
			if (h_erwartet ~= "") then
				newstr = newstr .. "ho"
			else
				newstr = newstr .. "o"
			end
		elseif (mw.ustring.find("ὉὍὋ", element, 1, true)) then
			if (h_erwartet ~= "") then
				newstr = newstr .. "Ho"
			else
				newstr = newstr .. "O"
			end
		elseif (mw.ustring.find("ὡὥὣᾧὧᾡᾥᾣ", element, 1, true)) then
			if (h_erwartet ~= "") then
				newstr = newstr .. "hō"
			else
				newstr = newstr .. "ō"
			end
		elseif (mw.ustring.find("ὩὭὫᾯὯᾩᾭᾫ", element, 1, true)) then
			if (h_erwartet ~= "") then
				newstr = newstr .. "Hō"
			else
				newstr = newstr .. "Ō"
			end
		elseif (mw.ustring.find("ὑὕὓὗ", element, 1, true)) then
			if (h_erwartet ~= "") then
				newstr = newstr .. "hy"
			else
				newstr = newstr .. "y"
			end
		elseif (mw.ustring.find("ὙὝὛὟ", element, 1, true)) then
			if (cp == 1) then
				newstr = newstr .. "Hy"
			else
				newstr = newstr .. "Y"
			end
		elseif (mw.ustring.find("ιίὶῐῑἰἴἲῖἶ", element, 1, true)) then
			newstr = newstr .. "i"
		elseif (mw.ustring.find("ΙΊῚῘῙἸἼἺἾ", element, 1, true)) then
			newstr = newstr .. "I"
		elseif (mw.ustring.find("ΐῒῗ", element, 1, true)) then
			newstr = newstr .. "ï"
		elseif (mw.ustring.find("οόὸὀὄὂ", element, 1, true)) then
			newstr = newstr .. "o"
		elseif (mw.ustring.find("ΟΌῸὈὌὊ", element, 1, true)) then
			newstr = newstr .. "O"
		elseif (mw.ustring.find("ωώὼῷὠὤὢᾦῶῳῴὦᾠᾤᾢ", element, 1, true)) then
			newstr = newstr .. "ō"
		elseif (mw.ustring.find("ΩΏῺὨὬὪᾮῼὮᾨᾬᾪ", element, 1, true)) then
			newstr = newstr .. "Ō"
		elseif (element == "φ") then
			newstr = newstr .. "ph"
		elseif (element == "Φ") then
			newstr = newstr .. "Ph"
		elseif (element == "χ") then
			newstr = newstr .. "ch"
		elseif (element == "Χ") then
			newstr = newstr .. "Ch"
		elseif (element == "ψ") then
			newstr = newstr .. "ps"
		elseif (element == "Ψ") then
			newstr = newstr .. "Ps"
		elseif (element == "ῥ") then
			newstr = newstr .. "rh"
		elseif (element == "Ῥ") then
			newstr = newstr .. "Rh"
		elseif (mw.ustring.find("υύὺῠῡὐὔὒῦὖ", element, 1, true)) then
			newstr = newstr .. "y"
		elseif (mw.ustring.find("ΥΎῪῨῩ", element, 1, true)) then
			newstr = newstr .. "Y"
		elseif (mw.ustring.find("ϋΰῢῧ", element, 1, true)) then
			newstr = newstr .. "ÿ"
		else
			newcp = mw.ustring.find(grb, element, 1, true)
	  		if (newcp) then
	  			newstr = newstr .. (mw.ustring.sub(lat, newcp, newcp))
	  		else
	  			j = mw.ustring.find(element, "%a", 1)
	  			if (j and Zeichensatz == "homogen") then
	  				newstr = newstr .. "■"
	  				Kat = "[[Kategorie:Wartung falsche Übersetzungen (Altgriechisch)]]"
	  			else	
	  				newstr = newstr .. (mw.ustring.sub(str, cp, cp))
	  			end
	  		end
		end
		cp = cp + 1
		possible2 = "y"
    end
  end
  return newstr .. Kat
end
-- Umschlüsselung altgriechischer Zahlzeichen in arabische Ziffern 
function Umschrift.agrZZ(str)
	local ZZ = "ΑΒΓΔΕϚΖΗΘΙΚΛΜΝΞΟΠϞΡΣΤΥΦΧΨΩϠ"
	local Zahlen = {1,2,3,4,5,6,7,8,9,10,20,30,40,50,60,70,80,90,100,200,300,400,500,600,700,800,900}
	local Suche = ""
	local strlen = mw.ustring.len(str)
	local mio = 0
	local tsd = 0
	local ezh = 0 -- Einer, Zehner, Hunderter
	local Summe = 0
	local Potenz_zuvor = -1
	local Potenz = 0
	local go_on = true
	local endcp = strlen
	local Bereich = ""
	local index = 0
	local cp = strlen
	if (mw.ustring.sub(str, cp, cp) == "ʹ") then
		cp = cp - 1
		while (cp >= 1 and go_on) do
			Suche = mw.ustring.upper(mw.ustring.sub(str,cp,cp))
			index = mw.ustring.find(ZZ, Suche, 1, true)
			if (index == nil) then
				if Suche == "Ϙ" then
					index = 18
				end
			end
			if (index) then
				Potenz = math.floor((index-1)/9)
				if Potenz_zuvor < 0 then
					ezh = Zahlen [index]
					cp = cp - 1
					Potenz_zuvor = Potenz
				elseif (Potenz > Potenz_zuvor) then
					if (cp == 1 or (cp > 1 and mw.ustring.sub(str, cp-1, cp-1) ~= "͵")) then
						ezh = ezh + Zahlen [index]
						cp = cp - 1
						Potenz_zuvor = Potenz
					else
						go_on = false -- Tausender- oder Million-Kennzeichen
					end
				else
					go_on = false -- vermutlicher Tausender-/Millionen-Wert 
				end
			else
				return "Falsches Zahlzeichen: " .. mw.ustring.sub(str,cp,cp)
			end
		end
		endcp = cp -- letztes Zeichen von Millionen oder Tausender
	end
	if cp >= 1 then
		cp = 1
		if mw.ustring.sub(str, 1, 1) ~= "͵" then
			return "Fehlendes Stellenwertsymbol am Beginn"
		end
	end
	while (cp > 0 and cp <= endcp) do
		if (mw.ustring.sub(str, cp, cp+1) == "͵͵" or 
			(mw.ustring.sub(str, cp, cp) ~= "͵" and Bereich == "M")) then -- Millionen
			if (mw.ustring.sub(str, cp, cp+1) == "͵͵") then cp = cp + 2 end
			Bereich = "M"
			Suche = mw.ustring.upper(mw.ustring.sub(str,cp,cp))
			index = mw.ustring.find(ZZ, Suche, 1, true)
			if (index == nil) then
				if Suche == "Ϙ" then
					index = 18
				end
			end
			if (index) then
				mio = mio + Zahlen [index]
				cp = cp + 1
			else
				return "Falsches Zahlzeichen: " .. mw.ustring.sub(str,cp,cp)
			end
		elseif (mw.ustring.sub(str, cp, cp) == "͵" or Bereich == "T") then -- Tausender
			if (mw.ustring.sub(str, cp, cp) == "͵") then cp = cp + 1 end
			Bereich = "T"
			Suche = mw.ustring.upper(mw.ustring.sub(str,cp,cp))
			index = mw.ustring.find(ZZ, Suche, 1, true)
			if (index == nil) then
				if Suche == "Ϙ" then
					index = 18
				end
			end
			if (index) then
				tsd = tsd + Zahlen [index]
				cp = cp + 1
			else
				return "Falsches Zahlzeichen: " .. mw.ustring.sub(str,cp,cp)
			end
		end
	end
	tsd = tsd * 1000
	mio = mio * 1000000
	Summe = mio + tsd + ezh
	Bereich = mw.ustring.format("%d", Summe)
	strlen = mw.ustring.len(Bereich)
	if strlen > 6 then
		return mw.ustring.sub(Bereich, 1, strlen-6) .. "." .. 
		mw.ustring.sub(Bereich, strlen-5, strlen-3) .. "." ..
		mw.ustring.sub(Bereich, strlen-2, strlen)
	elseif strlen > 4 then
		return mw.ustring.sub(Bereich, 1, strlen-3) .. "." ..
		mw.ustring.sub(Bereich, strlen-2, strlen)
	else
		return Bereich
	end
end
-- Rückgabe der Umschrift für agrDIN 
-- Hinweis: Doppelte Definitionen vermeiden. agrEIN ist bereits definiert.
-- Ende agrDIN


-- ab hier agrEIN Translitteration
function Umschrift.agrEIN(text)
	local ersetzungen_phon = {
		["γγ"] = "ng", ["γκ"] = "nk", ["γξ"] = "nx", ["γχ"] = "nch",
		["θ"] = "th", ["φ"] = "ph", ["χ"] = "kh",
		["α"] = "a", ["β"] = "b", ["γ"] = "g", ["δ"] = "d", ["ε"] = "e",
		["ζ"] = "z", ["η"] = "ē", ["ι"] = "i", ["κ"] = "k", ["λ"] = "l",
		["μ"] = "m", ["ν"] = "n", ["ξ"] = "x", ["ο"] = "o", ["π"] = "p",
		["ρ"] = "r", ["σ"] = "s", ["ς"] = "s", ["τ"] = "t", ["υ"] = "u",
		["ω"] = "ō",
		["Α"] = "A", ["Β"] = "B", ["Γ"] = "G", ["Δ"] = "D", ["Ε"] = "E",
		["Ζ"] = "Z", ["Η"] = "Ē", ["Ι"] = "I", ["Κ"] = "K", ["Λ"] = "L",
		["Μ"] = "M", ["Ν"] = "N", ["Ξ"] = "X", ["Ο"] = "O", ["Π"] = "P",
		["Ρ"] = "R", ["Σ"] = "S", ["Τ"] = "T", ["Υ"] = "U", ["Φ"] = "Ph",
		["Χ"] = "Kh", ["Θ"] = "Th", ["Ω"] = "Ō"
	}

	local diakritika_phon = {
		["ῐ"] = "ĭ", ["ῑ"] = "ī", ["ῠ"] = "ŭ", ["ῡ"] = "ū",
		["ά"] = "á", ["έ"] = "é", ["ή"] = "ḗ", ["ί"] = "í",
		["ό"] = "ó", ["ύ"] = "ú", ["ώ"] = "ṓ",
		["ὰ"] = "à", ["ὲ"] = "è", ["ὴ"] = "è", ["ὶ"] = "ì",
		["ὸ"] = "ò", ["ὺ"] = "ù", ["ὼ"] = "ò",
		["ᾶ"] = "â", ["ῖ"] = "î", ["ῦ"] = "û", ["ῶ"] = "ô",
		["ϊ"] = "ï", ["ϋ"] = "ü", ["ΐ"] = "ḯ", ["ΰ"] = "ǘ",
		["Ά"] = "Á", ["Έ"] = "É", ["Ή"] = "Ḗ", ["Ί"] = "Í",
		["Ό"] = "Ó", ["Ύ"] = "Ú", ["Ώ"] = "Ṓ"
	}

	local out = text
	for k, v in pairs(diakritika_phon) do
		out = mw.ustring.gsub(out, k, v)
	end
	for k, v in pairs(ersetzungen_phon) do
		out = mw.ustring.gsub(out, k, v)
	end
	return out
end

return Umschrift