Module:jv-translit

පහත දැක්වෙන උපදෙස්, Module:jv-translit/documentation හි පිහිටා ඇත. ^{[සංස්කරණය]}

ප්‍රයෝජනවත් සබැඳි: උප පිටු ලැයිස්තුව • සබැඳි • transclusions • testcases • sandbox

This module will transliterate ජාවා භාෂාව text. It is also used to transliterate Old Javanese. 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:jv-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 export = {}

local conv = {
	-- finals (U+A980 - U+A983):
	
	["ꦀ"] = "m",
	["ꦁ"] = "ng",
	["ꦂ"] = "r",
	["ꦃ"] = "h",
	
	-- independent vowels (U+A984 - U+A98E):
	
	["ꦄ"] = "a",   ["ꦄꦴ"] = "ā",
	["ꦅ"] = "i",
	["ꦆ"] = "ĩ",
	["ꦇ"] = "ī",
	["ꦈ"] = "u",   ["ꦈꦴ"] = "ū",
	["ꦉ"] = "re",  ["ꦉꦴ"] = "reu",
	["ꦊ"] = "le",
	["ꦋ"] = "leu",
	["ꦌ"] = "e",
	["ꦍ"] = "ai",
	["ꦎ"] = "o",
	
	-- independent consonants (U+A98F - U+A9B2):
	
	["ꦏ"] = "k",   ["ꦏ꦳"] = "ḳh",
	["ꦐ"] = "q",
	["ꦑ"] = "kh",
	["ꦒ"] = "g",   ["ꦒ꦳"] = "g̣h",
	["ꦓ"] = "gh",
	["ꦔ"] = "ng",  ["ꦔ꦳"] = "'",
	
	["ꦕ"] = "c",
	["ꦖ"] = "ch",
	["ꦗ"] = "j",   ["ꦗ꦳"] = "z",
	["ꦘ"] = "jñ",
	["ꦙ"] = "jh",
	["ꦚ"] = "ny",
	
	["ꦛ"] = "th",
	["ꦜ"] = "țh",
	["ꦝ"] = "dh",
	["ꦞ"] = "ḍh",
	["ꦟ"] = "nn",
	
	["ꦠ"] = "t",
	["ꦡ"] = "ț",
	["ꦢ"] = "d",   ["ꦢ꦳"] = "dz",
	["ꦣ"] = "ḍ",
	["ꦤ"] = "n",
	
	["ꦥ"] = "p",   ["ꦥ꦳"] = "f",
	["ꦦ"] = "ph",
	["ꦧ"] = "b",
	["ꦨ"] = "bh",
	["ꦩ"] = "m",
	
	["ꦪ"] = "y",
	["ꦫ"] = "r",
	["ꦬ"] = "r",
	["ꦭ"] = "l",
	["ꦮ"] = "w",   ["ꦮ꦳"] = "v",
	["ꦯ"] = "sh",
	["ꦰ"] = "ss",
	["ꦱ"] = "s",   ["ꦱ꦳"] = "sy",
	["ꦲ"] = "h",   ["ꦲ꦳"] = "ḥ",
	
	-- cecak_telu/nukta (U+A9B3):
	
	["꦳"] = "",
	
	-- dependent vowels (U+A9B4 - A9BD):
	
	["ꦴ"] = "ā", -- tarung
	["ꦵ"] = "eu", -- tolong
	["ꦶ"] = "i",
	["ꦷ"] = "ī",
	["ꦸ"] = "u",
	["ꦹ"] = "ū",
	["ꦺ"] = "é",   -- or "è", depends. Javanese script doesn't differentiate, while Latin differentiate them
	["ꦺꦴ"] = "o",
	["ꦻ"] = "ai",  
	["ꦻꦴ"] = "au",
	["ꦼ"] = "e",
	["ꦽ"] = "re",  ["ꦽꦴ"] = "reu",
	
	-- medials (U+A9BE - U+A9BF):
	["ꦾ"] = "y",
	["ꦿ"] = "r",
	
	-- pangkon/virama (U+A9C0):
	
	["꧀"] = "", -- it depends. if followed by a space, it became "," compound sentence separator
	
	-- punctuation (U+A9C1 - U+A9CF):
	
	["꧁"] = "", -- "(starts title)",
	["꧂"] = "", -- "(ends title)",
	["꧃"] = "", -- "(letter to younger age or lower rank)",
	["꧄"] = "", -- "(letter to equal age or equal rank)",
	["꧅"] = "", -- "(letter to older age or higher rank)",
	["꧆"] = "", -- "(pada windu)",
	["꧇"] = ":", -- number indicator
	["꧈"] = ",", -- it depends. if preceeded by a 'pangkon', it became "." end of sentence marker
	["꧉"] = ".",
	["꧊"] = "\"",
	["꧋"] = "¶", -- start of paragraph marker
	["꧌"] = "(",
	["꧍"] = ")",
	["ꧏ"] = "<sup>2</sup>",
	
	-- digits (U+A9D0 - U+A9D9):
	
	["꧐"] = "0",
	["꧑"] = "1",
	["꧒"] = "2",
	["꧓"] = "3",
	["꧔"] = "4",
	["꧕"] = "5",
	["꧖"] = "6",
	["꧗"] = "7",
	["꧘"] = "8",
	["꧙"] = "9",
	
	-- ellipsis (U+A9DE - U+A9DF):
	
	["꧞"] = "-",
	["꧟"] = "-",
}

function export.tr(text, lang, sc)
	local CSVC = {
		initial = "([ꦏ-ꦲ]꦳?)",
		medial = "([ꦾꦿ]?)",
		nucleus = "([ꦴ-ꦽ꧀]?ꦴ?)",
		final = "([ꦀ-ꦃ]?)",
	}
	local VC = {
		nucleus = "([ꦄ-ꦎ]ꦴ?)",
		final = "([ꦀ-ꦃ]*)",
	}
	
	local number_indicator = "꧇"
	local digits = "[꧐-꧙]"
	
	local initial = true
	
	text = mw.ustring.gsub(
		text,
		CSVC.initial .. CSVC.medial .. CSVC.nucleus.. CSVC.final,
		function(a, b, c, d)
			a = conv[a] or error("Initial not recognized: " .. a)
			b = b == "" and "" or conv[b] or error("Medial not recognized: " .. b)
			c = c == "" and "a" or conv[c] or error("Nucleus not recognized: " .. c)
			d = d == "" and "" or conv[d] or error("Final not recognized: " .. d)
			if initial and a == "h" then
				a = ""
			end
			initial = false
			return a .. b .. c .. d
		end
	)
	
	text = mw.ustring.gsub(
		text,
		VC.nucleus .. VC.final,
		function(a, b)
			a = conv[a]
			b = (b == "" and "" or conv[b])
			initial = false
			return a .. b
		end
	)
	
	text = mw.ustring.gsub(
		text,
		number_indicator .. "(" .. digits .. "+)" .. number_indicator,
		function(a)
			a = mw.ustring.gsub(a, ".", conv)
			initial = true
			return a
		end
	)
	
	text = mw.ustring.gsub(text, ".", conv)
	
	return text
end

return export