Module:Wikt-lang/data/sandbox: Difference between revisions

Module documentation[view] [edit] [history] [purge]

The redirects table in Module:Wikt-lang/data connects Wikipedia language codes to the corresponding code used on the English Wiktionary. wikt:Wiktionary:Language treatment records this relationship for ISO codes. For instance, all of bs (Bosnian), hr (Croatian), sr (Serbian), cnr (Montenegrin), kjv (Kajkavian) are placed under the header for sh (Serbo-Croatian) in Wiktionary entries. See for instance wikt:kaj#Serbo-Croatian, the word that Kajkavian is named after. The subsumed codes should still be used in language-tagging on Wikipedia.

The above documentation is transcluded from Module:Wikt-lang/data/doc. (edit | history)
Editors can experiment in this module's sandbox (edit | diff) and testcases (create) pages.
Add categories to the /doc subpage. Subpages of this module.

local U = mw.ustring.char

-- Diacritics, from the [[Combining Diacritical Marks]] block.
local grave        = U(0x300)
local acute        = U(0x301)
local circumflex   = U(0x302)
local tilde        = U(0x303)
local macron       = U(0x304)
local breve        = U(0x306)
local dot          = U(0x307)
local diaeresis    = U(0x308)
local double_acute = U(0x30B)
local caron        = U(0x30C)
local double_grave = U(0x30F)
local invbreve     = U(0x311)
local dot_below    = U(0x323)
local undertie     = U(0x35C)

--[[
	This is a table of Wiktionary language codes with data belonging to them.
	Name is the "canonical name" used on Wiktionary.
	Script is the ISO 15924 code.
]]
local data = {
	["languages"] = {
		["aaq"] = {
			["name"] = "Penobscot",
		},
		["abe"] = {
			["name"] = "Abenaki",
		},
		["ang"] = {
			["name"] = "Old English",
			-- Remove macrons, acutes, and overdots
			["replacements"] = {
				decompose = true,
				from = { "[" .. macron .. acute .. dot .. "]" },
			},
		},
		["ar"] = {
			["name"] = "Arabic",
			["direction"] = "rtl", -- Should be in the script data module.
			["replacements"] = {
				-- ālif with wasla is replaced by ālif;
				[U(0x0671)] = U(0x0627),
				-- taṭwīl, fatḥatan, ḍammatan, kasratan,
				-- fatḥa, ḍamma, kasra,
				-- shadda, sukūn, and superscript (dagger) ālif are removed.
				["["..U(0x0640)..U(0x064B)..U(0x064C)..U(0x064D)
					..U(0x064E)..U(0x064F)..U(0x0650)
					..U(0x0651)..U(0x0652)..U(0x0670).."]"] = "",
			},
		},
		["arb"] = {
			["name"] = "Modern Standard Arabic",
			["direction"] = "rtl", -- Should be in the script data module.
			["replacements"] = {
				-- ālif with wasla is replaced by ālif;
				[U(0x0671)] = U(0x0627),
				-- taṭwīl, fatḥatan, ḍammatan, kasratan,
				-- fatḥa, ḍamma, kasra,
				-- shadda, sukūn, and superscript (dagger) ālif are removed.
				["["..U(0x0640)..U(0x064B)..U(0x064C)..U(0x064D)
					..U(0x064E)..U(0x064F)..U(0x0650)
					..U(0x0651)..U(0x0652)..U(0x0670).."]"] = "",
			},
		},
		["apc"] = {
			["name"] = "North Levantine Arabic",
			["direction"] = "rtl", -- Should be in the script data module.
			["replacements"] = {
				-- ālif with wasla is replaced by ālif;
				[U(0x0671)] = U(0x0627),
				-- taṭwīl, fatḥatan, ḍammatan, kasratan,
				-- fatḥa, ḍamma, kasra,
				-- shadda, sukūn, and superscript (dagger) ālif are removed.
				["["..U(0x0640)..U(0x064B)..U(0x064C)..U(0x064D)
					..U(0x064E)..U(0x064F)..U(0x0650)
					..U(0x0651)..U(0x0652)..U(0x0670).."]"] = "",
			},
		},
		["ajp"] = {
			["name"] = "South Levantine Arabic",
			["direction"] = "rtl", -- Should be in the script data module.
			["replacements"] = {
				-- ālif with wasla is replaced by ālif;
				[U(0x0671)] = U(0x0627),
				-- taṭwīl, fatḥatan, ḍammatan, kasratan,
				-- fatḥa, ḍamma, kasra,
				-- shadda, sukūn, and superscript (dagger) ālif are removed.
				["["..U(0x0640)..U(0x064B)..U(0x064C)..U(0x064D)
					..U(0x064E)..U(0x064F)..U(0x0650)
					..U(0x0651)..U(0x0652)..U(0x0670).."]"] = "",
			},
		},
		["arz"] = {
			["name"] = "Egyptian Arabic",
			["direction"] = "rtl", -- Should be in the script data module.
			["replacements"] = {
				-- ālif with wasla is replaced by ālif;
				[U(0x0671)] = U(0x0627),
				-- taṭwīl, fatḥatan, ḍammatan, kasratan,
				-- fatḥa, ḍamma, kasra,
				-- shadda, sukūn, and superscript (dagger) ālif are removed.
				["["..U(0x0640)..U(0x064B)..U(0x064C)..U(0x064D)
					..U(0x064E)..U(0x064F)..U(0x0650)
					..U(0x0651)..U(0x0652)..U(0x0670).."]"] = "",
			},
		},
		["be"] = {
			["replacements"] = {
				[acute] = "",
			},
		},
		["cel-x-bryproto"] = {
			["name"] = "Proto-Brythonic",
			["type"] = "reconstructed",
		},
		["cu"] = {
			["name"] = "Old Church Slavonic",
		},
		["egy"] = {
			["name"] = "Egyptian",
		},
		["frp"] = {
			["name"] = "Franco-Provençal",
		},
		["gem-x-proto"] = {
			["name"] = "Proto-Germanic",
			["type"] = "reconstructed",
		},
		["gmw-x-proto"] = {
			["name"] = "Proto-West Germanic",
			["type"] = "reconstructed",
		},
		["gmq-x-gut"] = {
			["name"] = "Gutnish",
		},
		["goh"] = {
			["replacements"] = {
				decompose = true,
				from = {
					"[" .. macron .. circumflex .. diaeresis .. "]",
				},
			},
		},
		["got"] = {
			["name"] = "Gothic",
			["replacements"] = {
				-- Latin to Gothic since people will not want to have to copy
				-- and paste Gothic letters in
				["[AÁaáĀā]"] = "𐌰",
				["[Bb]"]     = "𐌱",
				["[Gg]"]     = "𐌲",
				["[Dd]"]     = "𐌳",
				["[EeĒē]"]   = "𐌴",
				["[Qq]"]     = "𐌵",
				["[Zz]"]     = "𐌶",
				["[Hh]"]     = "𐌷",
				["[Þþ]"]     = "𐌸",
				["[IiÍí]"]   = "𐌹",
				["[Kk]"]     = "𐌺",
				["[Ll]"]     = "𐌻",
				["[Mm]"]     = "𐌼",
				["[Nn]"]     = "𐌽",
				["[Jj]"]     = "𐌾",		
				["[UuÚúŪū]"] = "𐌿",	
				["[Pp]"]     = "𐍀",		
				["[Rr]"]     = "𐍂",	
				["[Ss]"]     = "𐍃",	
				["[Tt]"]     = "𐍄",	
				["[WwYy]"]   = "𐍅",
				["[Ff]"]     = "𐍆",
				["[Xx]"]     = "𐍇",
				["[Ƕƕ]"]    = "𐍈", -- Not sure if "hw" and "hv" can safely be converted
				["[OoŌō]"]   = "𐍉",
			},
		},
		["grc"] = {
			["name"] = "Ancient Greek",
			["replacements"] = {
				decompose = true,
				from = {
					-- Replace variant letterforms with standard ones.
					"ϐ", "ϵ", "ϑ", "ϰ", "ϱ", "ϲ", "ϕ",
					-- Remove macrons and breves.
					"[" .. macron .. breve .. undertie .. "]"
				},
				to   = {
					"β", "ε", "θ", "κ", "ρ", "σ", "φ",
				}
			},
		},
		["grk-x-proto"] = {
			["name"] = "Proto-Hellenic",
			["Wikipedia_name"] = "Proto-Greek",
			["type"] = "reconstructed",
			["replacements"] = {},
		},
		["ha"] = {
			["name"] = "Hausa",
			-- remove tilde, grave, acute, macron, circumflex
			["replacements"] = {
				decompose = true,
				from = { "[" .. grave .. circumflex .. macron .. acute .. tilde .. "]" },
			},
		},
		["ine-x-bsproto"] = {
			["name"] = "Proto-Balto-Slavic",
			["type"] = "reconstructed",
		},
		["ine-x-proto"] = {
			["name"] = "Proto-Indo-European",
			["type"] = "reconstructed",
		},
		["jbo"] = { -- Lojban
			["type"] = "appendix",
		},
		["la"] = {
			["name"] = "Latin",
			["replacements"] = {
				decompose = true,
				from = { "[" .. macron .. breve .. diaeresis .. "]" },
			},
		},
		["lt"] = {
			["name"] = "Lithuanian",
			-- remove acute, tilde, grave
			["replacements"] = {
				decompose = true,
				from = { "[" .. acute .. tilde .. grave .. "]" },
			},
		},
		["moe"] = {
			["name"] = "Cree",
		},
		["mul"] = {
			["name"] = "Translingual",
		},
		["nci"] = {
			["name"] = "Classical Nahuatl",
			-- Remove macrons, acutes, circumflexes and graves
			["replacements"] = {
				decompose = true,
				-- Remove macrons, acutes, circumflexes, graves, and saltillo;
				-- see [[Saltillo (linguistics)]].
				from = { "[" .. grave .. acute .. macron .. circumflex .. "Ꞌꞌʻʼ'ʔ]" },
			},
		},
		["nds-de"] = {
			["name"] = "German Low German",
		},
		["non-x-proto"] = {
			["name"] = "Proto-Norse",
		},
		["orv"] = {
			["name"] = "Old East Slavic",
			["replacements"] = {
				[U(0x484)] = "",
			},
		},
		["poz-x-polproto"] = { -- is this even in use?
			["name"] = "Proto-Nuclear Polynesian",
			["type"] = "reconstructed",
		},
		["ru"] = {
			["name"] = "Russian",
			["replacements"] = {
				[acute] = "",
			},
		},
		["rw"] = {
			["name"] = "Rwanda-Rundi",
		},
		["se"] = {
			["replacements"] = {
				["([đflmnŋrsšŧv])'%1"] = "%1%1",
			},
		},
		["sem-x-proto"] = {
			["name"] = "Proto-Semitic",
			["type"] = "reconstructed",
		},
		["sh"] = {
			["replacements"] = {
				decompose = true,
				from =  { "([AaEeIiOoUuRrАаЕеИиОоУуРр])[" .. double_grave
					.. grave .. invbreve .. acute .. macron .. tilde .. "]" },
				to   = { "%1" },
			},
		},
		["sl"] = {
			["name"] = "Slovene",
			["replacements"] = {
				decompose = true,
				-- remove tonal orthography
				from = {"ł", "[" .. grave .. acute .. macron .. double_grave .. invbreve .. circumflex .. dot_below .. "]"},
				to = {"l"},
			},
		},
		["sla-x-proto"] = {
			["name"] = "Proto-Slavic", -- also Common Slavic
			["type"] = "reconstructed",
			["replacements"] = {
				["[ÀÁÃĀȀȂ]"] = "A",
				["[àáãāȁȃ]"] = "a",
				["[ÈÉẼĒȄȆ]"] = "E",
				["[èéẽēȅȇ]"] = "e",
				["[ÌÍĨĪȈȊ]"] = "I",
				["[ìíĩīȉȋ]"] = "i",
				["[ÒÓÕŌȌȎŐ]"] = "O", 
				["[òóõōȍȏő]"] = "o",
				["[ÙÚŨŪȔȖŰ]"] = "U",
				["[ùúũūȕȗű]"] = "u",
				["[ỲÝỸȲ]"] = "Y",
				["[ỳýỹȳ]"] = "y",
				["Ǭ"] = "Ǫ",
				["ǭ"] = "ǫ",
				["[" .. grave .. acute .. double_acute .. tilde .. macron .. double_grave .. invbreve .. "]"] = "",
				["ĭ"] = "ь",
				["ŭ"] = "ъ",
			},
		},
		["tts"] = {
			["name"] = "Isan", -- also "Northeastern Thai"
		},
		["uk"] = {
			["replacements"] = { [acute] = "", }
		},
		["xcl"] = {
			["name"] = "Old Armenian",
			["replacements"] = {
				["[՞՜՛՟]"] = "",
				["և"] = "եւ",
			},
		},
		["xgf"] = {
			["name"] = "Tongva", -- not ISO name "Gabrielino-Fernandeño"
			["replacements"] = {
				["['`ʔ]"] = "ʼ",
			},
		},
		["xlu"] = {
			["name"] = "Luwian", -- not ISO name "Cuneiform Luwian"
		},
		["zle-x-ort"] = {
			["name"] = "Old Ruthenian",
			["replacements"] = {
				[acute] = "",
			},
		},
	},
}

return data