Wiktionary miwiktionary https://mi.wiktionary.org/wiki/Hau_K%C4%81inga MediaWiki 1.47.0-wmf.10 case-sensitive Media Special Talk User User talk Wiktionary Wiktionary talk File File talk MediaWiki MediaWiki talk Template Template talk Help Help talk Category Category talk TimedText TimedText talk Module Module talk Event Event talk 14 3013 17457 17310 2026-07-13T08:55:47Z Hiyuune 6766 done 17457 wikitext text/x-wiki {{auto cat|Āwherika ki te Tonga|Namīpia}} sy88j7zh24ronin5yv9jd95u121dd1n 828 5878 17410 17241 2026-07-13T08:26:38Z Hiyuune 6766 17410 Scribunto text/plain local export = {} local function_module = "Module:fun" local load_module = "Module:load" local memoize_module = "Module:memoize" local string_char_module = "Module:string/char" local string_charset_escape_module = "Module:string/charsetEscape" local mw = mw local string = string local table = table local ustring = mw.ustring local byte = string.byte local char = string.char local concat = table.concat local find = string.find local format = string.format local gmatch = string.gmatch local gsub = string.gsub local insert = table.insert local len = string.len local lower = string.lower local match = string.match local next = next local require = require local reverse = string.reverse local select = select local sort = table.sort local sub = string.sub local tonumber = tonumber local tostring = tostring local type = type local ucodepoint = ustring.codepoint local ufind = ustring.find local ugcodepoint = ustring.gcodepoint local ugmatch = ustring.gmatch local ugsub = ustring.gsub local ulower = ustring.lower local umatch = ustring.match local unpack = unpack or table.unpack -- Lua 5.2 compatibility local upper = string.upper local usub = ustring.sub local uupper = ustring.upper local memoize = require(memoize_module) -- Defined below. local codepoint local explode_utf8 local format_fun local get_charset local gsplit local pattern_escape local pattern_simplifier local replacement_escape local title_case local trim local ucfirst local ulen --[==[ Loaders for functions in other modules, which overwrite themselves with the target function when called. This ensures modules are only loaded when needed, retains the speed/convenience of locally-declared pre-loaded functions, and has no overhead after the first call, since the target functions are called directly in any subsequent calls. ]==] local function charset_escape(...) charset_escape = require(string_charset_escape_module) return charset_escape(...) end local function is_callable(...) is_callable = require(function_module).is_callable return is_callable(...) end local function load_data(...) load_data = require(load_module).load_data return load_data(...) end local function u(...) u = require(string_char_module) return u(...) end local function prepare_iter(str, pattern, str_lib, plain) local callable = is_callable(pattern) if str_lib or plain then return pattern, #str, string, callable elseif not callable then local simple = pattern_simplifier(pattern) if simple then return simple, #str, string, false end end return pattern, ulen(str), ustring, callable end --[==[ Returns {nil} if the input value is the empty string, or otherwise the same value. If the input is a string and `do_trim` is set, the input value will be trimmed before returning; if the trimmed value is the empty string, returns {nil}. If `quote_delimiters` is set, then any outer pair of quotation marks ({' '} or {" "}) surrounding the rest of the input string will be stripped, if present. The string will not be trimmed again, converted to {nil}, or have further quotation marks stripped, as it exists as a way to embed spaces or the empty string in an input. Genuine quotation marks may also be embedded this way (e.g. {"''foo''"} returns {"'foo'"}). ]==] function export.is_not_empty(str, do_trim, quote_delimiters) if str == "" then return nil elseif not (str and type(str) == "string") then return str elseif do_trim then str = trim(str) if str == "" then return nil end end return quote_delimiters and gsub(str, "^(['\"])(.*)%1$", "%2") or str end --[==[ Explodes a string into an array of UTF-8 characters. '''Warning''': this function assumes that the input is valid UTF-8 in order to optimize speed and memory use. Passing in an input containing non-UTF-8 byte sequences could result in unexpected behaviour. ]==] function export.explode_utf8(str) local text, i = {}, 0 for ch in gmatch(str, ".[\128-\191]*") do i = i + 1 text[i] = ch end return text end explode_utf8 = export.explode_utf8 --[==[ Returns {true} if `str` is a valid UTF-8 string. This is true if, for each character, all of the following are true: * It has the expected number of bytes, which is determined by value of the leading byte: 1-byte characters are `0x00` to `0x7F`, 2-byte characters start with `0xC2` to `0xDF`, 3-byte characters start with `0xE0` to `0xEF`, and 4-byte characters start with `0xF0` to `0xF4`. * The leading byte must not fall outside of the above ranges. * The trailing byte(s) (if any), must be between `0x80` to `0xBF`. * The character's codepoint must be between U+0000 (`0x00`) and U+10FFFF (`0xF4 0x8F 0xBF 0xBF`). * The character cannot have an overlong encoding: for each byte length, the lowest theoretical encoding is equivalent to U+0000 (e.g. `0xE0 0x80 0x80`, the lowest theoretical 3-byte encoding, is exactly equivalent to U+0000). Encodings that use more than the minimum number of bytes are not considered valid, meaning that the first valid 3-byte character is `0xE0 0xA0 0x80` (U+0800), and the first valid 4-byte character is `0xF0 0x90 0x80 0x80` (U+10000). Formally, 2-byte characters have leading bytes ranging from `0xC0` to `0xDF` (rather than `0xC2` to `0xDF`), but `0xC0 0x80` to `0xC1 0xBF` are overlong encodings, so it is simpler to say that the 2-byte range begins at `0xC2`. If `allow_surrogates` is set, surrogates (U+D800 to U+DFFF) will be treated as valid UTF-8. Surrogates are used in UTF-16, which encodes codepoints U+0000 to U+FFFF with 2 bytes, and codepoints from U+10000 upwards using a pair of surrogates, which are taken together as a 4-byte unit. Since surrogates have no use in UTF-8, as it encodes higher codepoints in a different way, they are not considered valid in UTF-8 text. However, there are limited circumstances where they may be necessary: for instance, JSON escapes characters using the format `\u0000`, which must contain exactly 4 hexadecimal digits; under the scheme, codepoints above U+FFFF must be escaped as the equivalent pair of surrogates, even though the text itself must be encoded in UTF-8 (e.g. U+10000 becomes `\uD800\uDC00`). ]==] function export.isutf8(str, allow_surrogates) for ch in gmatch(str, "[\128-\255][\128-\191]*") do if #ch > 4 then return false end local b1, b2, b3, b4 = byte(ch, 1, 4) if not (b2 and b2 >= 0x80 and b2 <= 0xBF) then return false -- 1-byte is always invalid, as gmatch excludes 0x00 to 0x7F elseif not b3 then -- 2-byte if not (b1 >= 0xC2 and b1 <= 0xDF) then -- b1 == 0xC0 or b1 == 0xC1 is overlong return false end elseif not (b3 >= 0x80 and b3 <= 0xBF) then -- trailing byte return false elseif not b4 then -- 3-byte if b1 > 0xEF then return false elseif b2 < 0xA0 then if b1 < 0xE1 then -- b1 == 0xE0 and b2 < 0xA0 is overlong return false end elseif b1 < 0xE0 or (b1 == 0xED and not allow_surrogates) then -- b1 == 0xED and b2 >= 0xA0 is a surrogate return false end elseif not (b4 >= 0x80 and b4 <= 0xBF) then -- 4-byte return false elseif b2 < 0x90 then if not (b1 >= 0xF1 and b1 <= 0xF4) then -- b1 == 0xF0 and b2 < 0x90 is overlong return false end elseif not (b1 >= 0xF0 and b1 <= 0xF3) then -- b1 == 0xF4 and b2 >= 0x90 is too high return false end end return true end do local charset_chars = { ["\0"] = "%z", ["%"] = "%%", ["-"] = "%-", ["]"] = "%]", ["^"] = "%^" } charset_chars.__index = charset_chars local chars = setmetatable({ ["$"] = "%$", ["("] = "%(", [")"] = "%)", ["*"] = "%*", ["+"] = "%+", ["."] = "%.", ["?"] = "%?", ["["] = "%[" }, charset_chars) --[==[ Escapes the magic characters used in a [[mw:Extension:Scribunto/Lua reference manual#Patterns|pattern]] (Lua's version of regular expressions): {$%()*+-.?[]^}, and converts the null character to {%z}. For example, {"^$()%.[]*+-?\0"} becomes {"%^%$%(%)%%%.%[%]%*%+%-%?%z"}. This is necessary when constructing a pattern involving arbitrary text (e.g. from user input). ]==] function export.pattern_escape(str) return (gsub(str, "[%z$%%()*+%-.?[%]^]", chars)) end pattern_escape = export.pattern_escape --[==[ Escapes only {%}, which is the only magic character used in replacement [[mw:Extension:Scribunto/Lua reference manual#Patterns|patterns]] with string.gsub and mw.ustring.gsub. ]==] function export.replacement_escape(str) return (gsub(str, "%%", "%%%%")) end replacement_escape = export.replacement_escape local function case_insensitive_char(ch) local upper_ch = uupper(ch) if upper_ch == ch then ch = ulower(ch) if ch == upper_ch then return chars[ch] or ch end end return "[" .. (charset_chars[upper_ch] or upper_ch) .. (charset_chars[ch] or ch) .. "]" end local function iterate(str, str_len, text, n, start, _gsub, _sub, loc1, loc2) if not (loc1 and start <= str_len) then -- Add final chunk and return. n = n + 1 text[n] = _gsub(_sub(str, start), ".", chars) return elseif loc2 < loc1 then if _sub == sub then local b = byte(str, loc1) if b and b >= 128 then loc1 = loc1 + (b < 224 and 1 or b < 240 and 2 or 3) end end n = n + 1 text[n] = _gsub(_sub(str, start, loc1), ".", chars) start = loc1 + 1 if start > str_len then return end else -- Add chunk up to the current match. n = n + 1 text[n] = _gsub(_sub(str, start, loc1 - 1), ".", chars) -- Add current match. n = n + 1 text[n] = _gsub(_sub(str, loc1, loc2), ".", case_insensitive_char) start = loc2 + 1 end return n, start end --[==[ Escapes the magic characters used in a [[mw:Extension:Scribunto/Lua reference manual#Patterns|pattern]], and makes all characters case-insensitive. An optional pattern or find function (see {split}) may be supplied as the second argument, the third argument (`str_lib`) forces use of the string library, while the fourth argument (`plain`) turns any pattern matching facilities off in the optional pattern supplied. ]==] function export.case_insensitive_pattern(str, pattern_or_func, str_lib, plain) if pattern_or_func == nil then return (gsub(str, str_lib and "[^\128-\255]" or ".[\128-\191]*", case_insensitive_char)) end local text, n, start, str_len, _string, callable = {}, 0, 1 pattern_or_func, str_len, _string, callable = prepare_iter(str, pattern_or_func, str_lib, plain) local _find, _gsub, _sub = _string.find, _string.gsub, _string.sub if callable then repeat n, start = iterate(str, str_len, text, n, start, _gsub, _sub, pattern_or_func(str, start)) until not start -- Special case if the pattern is anchored to the start: "^" always -- anchors to the start position, not the start of the string, so get -- around this by only attempting one match with the pattern, then match -- the end of the string. elseif byte(pattern_or_func) == 0x5E then -- ^ n, start = iterate(str, str_len, text, n, start, _gsub, _sub, _find(str, pattern_or_func, start, plain)) if start ~= nil then iterate(str, str_len, text, n, start, _gsub, _sub, _find(str, "$", start, plain)) end else repeat n, start = iterate(str, str_len, text, n, start, _gsub, _sub, _find(str, pattern_or_func, start, plain)) until not start end return concat(text) end end do local character_classes local function get_character_classes() character_classes, get_character_classes = { [0x41] = true, [0x61] = true, -- Aa [0x43] = true, [0x63] = true, -- Cc [0x44] = true, [0x64] = true, -- Dd [0x4C] = true, [0x6C] = true, -- Ll [0x50] = true, [0x70] = true, -- Pp [0x53] = true, [0x73] = true, -- Ss [0x55] = true, [0x75] = true, -- Uu [0x57] = true, [0x77] = true, -- Ww [0x58] = true, [0x78] = true, -- Xx [0x5A] = true, -- z dealt with separately. }, nil return character_classes end local function check_sets_equal(set1, set2) local k2 for k1, v1 in next, set1 do local v2 = set2[k1] if v1 ~= v2 and (v2 == nil or not check_sets_equal(v1, v2)) then return false end k2 = next(set2, k2) end return next(set2, k2) == nil end local function check_sets(bytes) local key, set1, set = next(bytes) if set1 == true then return true elseif not check_sets(set1) then return false end while true do key, set = next(bytes, key) if not key then return true elseif not check_sets_equal(set, set1) then return false end end end local function make_charset(range) if #range == 1 then return char(range[1]) end sort(range) local compressed, n, start = {}, 0, range[1] for i = 1, #range do local this, nxt = range[i], range[i + 1] if nxt ~= this + 1 then n = n + 1 compressed[n] = this == start and char(this) or char(start) .. "-" .. char(this) start = nxt end end return "[" .. concat(compressed) .. "]" end local function parse_1_byte_charset(pattern, pos) local ch while true do pos, ch = match(pattern, "()([%%%]\192-\255])", pos) if ch == "%" then local nxt = byte(pattern, pos + 1) if not nxt or nxt >= 128 or (character_classes or get_character_classes())[nxt] then -- acdlpsuwxACDLPSUWXZ, but not z return false end pos = pos + 2 elseif ch == "]" then pos = pos + 1 return pos else return false end end end --[==[ Parses `pattern`, a ustring library pattern, and attempts to convert it into a string library pattern. If conversion isn't possible, returns false. ]==] function pattern_simplifier(pattern) if type(pattern) == "number" then return tostring(pattern) end local pos, capture_groups, start, n, output, ch, nxt_pos = 1, 0, 1, 0 while true do -- FIXME: use "()([%%(.[\128-\255])[\128-\191]?[\128-\191]?[\128-\191]?()" and ensure non-UTF8 always fails. pos, ch, nxt_pos = match(pattern, "()([%%(.[\192-\255])[\128-\191]*()", pos) if not ch then break end local nxt = byte(pattern, nxt_pos) if ch == "%" then if nxt == 0x62 then -- b local nxt2, nxt3 = byte(pattern, pos + 2, pos + 3) if not (nxt2 and nxt2 < 128 and nxt3 and nxt3 < 128) then return false end pos = pos + 4 elseif nxt == 0x66 then -- f nxt_pos = nxt_pos + 2 local nxt2, nxt3 = byte(pattern, nxt_pos - 1, nxt_pos) -- Only possible to convert a positive %f charset which is -- all ASCII, so use parse_1_byte_charset. if not (nxt2 == 0x5B and nxt3 and nxt3 ~= 0x5E and nxt3 < 128) then -- [^ return false elseif nxt3 == 0x5D then -- Initial ] is non-magic. nxt_pos = nxt_pos + 1 end pos = parse_1_byte_charset(pattern, nxt_pos) if not pos then return false end elseif nxt == 0x5A then -- Z nxt = byte(pattern, nxt_pos + 1) if nxt == 0x2A or nxt == 0x2D then -- *- pos = pos + 3 else if output == nil then output = {} end local ins = sub(pattern, start, pos - 1) .. "[\1-\127\192-\255]" n = n + 1 if nxt == 0x2B then -- + output[n] = ins .. "%Z*" pos = pos + 3 elseif nxt == 0x3F then -- ? output[n] = ins .. "?[\128-\191]*" pos = pos + 3 else output[n] = ins .. "[\128-\191]*" pos = pos + 2 end start = pos end elseif not nxt or (character_classes or get_character_classes())[nxt] then -- acdlpsuwxACDLPSUWX, but not Zz return false -- Skip the next character if it's ASCII. Otherwise, we will -- still need to do length checks. else pos = pos + (nxt < 128 and 2 or 1) end elseif ch == "(" then if nxt == 0x29 or capture_groups == 32 then -- ) return false end capture_groups = capture_groups + 1 pos = pos + 1 elseif ch == "." then if nxt == 0x2A or nxt == 0x2D then -- *- pos = pos + 2 else if output == nil then output = {} end local ins = sub(pattern, start, pos - 1) .. "[^\128-\191]" n = n + 1 if nxt == 0x2B then -- + output[n] = ins .. ".*" pos = pos + 2 elseif nxt == 0x3F then -- ? output[n] = ins .. "?[\128-\191]*" pos = pos + 2 else output[n] = ins .. "[\128-\191]*" pos = pos + 1 end start = pos end elseif ch == "[" then -- Fail negative charsets. TODO: 1-byte charsets should be safe. if nxt == 0x5E then -- ^ return false -- If the first character is "%", ch_len is determined by the -- next one instead. elseif nxt == 0x25 then -- % nxt = byte(pattern, nxt_pos + 1) elseif nxt == 0x5D then -- Initial ] is non-magic. nxt_pos = nxt_pos + 1 end if not nxt then return false end local ch_len = nxt < 128 and 1 or nxt < 224 and 2 or nxt < 240 and 3 or 4 if ch_len == 1 then -- Single-byte charset. pos = parse_1_byte_charset(pattern, nxt_pos) if not pos then return false end else -- Multibyte charset. -- TODO: 1-byte chars should be safe to mix with multibyte chars. CONFIRM THIS FIRST. local charset_pos, bytes = pos pos = pos + 1 while true do -- TODO: non-ASCII charset ranges. pos, ch, nxt_pos = match(pattern, "^()([^\128-\191])[\128-\191]*()", pos) -- If escaped, get the next character. No need to -- distinguish magic characters or character classes, -- as they'll all fail for having the wrong length -- anyway. if ch == "%" then pos, ch, nxt_pos = match(pattern, "^()([^\128-\191])[\128-\191]*()", nxt_pos) elseif ch == "]" then pos = nxt_pos break end if not (ch and nxt_pos - pos == ch_len) then return false elseif bytes == nil then bytes = {} end local bytes, last = bytes, nxt_pos - 1 for i = pos, last - 1 do local b = byte(pattern, i) local bytes_b = bytes[b] if bytes_b == nil then bytes_b = {} bytes[b] = bytes_b end bytes[b], bytes = bytes_b, bytes_b end bytes[byte(pattern, last)] = true pos = nxt_pos end if not pos then return false end nxt = byte(pattern, pos) if ( (nxt == 0x2A or nxt == 0x2D or nxt == 0x3F) or -- *-? (nxt == 0x2B and ch_len > 2) or -- + not check_sets(bytes) ) then return false end local ranges, b, key, next_byte = {}, 0 repeat key, next_byte = next(bytes) local range, n = {key}, 1 -- Loop starts on the second iteration. for key in next, bytes, key do n = n + 1 range[n] = key end b = b + 1 ranges[b] = range bytes = next_byte until next_byte == true if nxt == 0x2B then -- + local range1, range2 = ranges[1], ranges[2] ranges[1], ranges[3] = make_charset(range1), make_charset(range2) local n = #range2 for i = 1, #range1 do n = n + 1 range2[n] = range1[i] end ranges[2] = make_charset(range2) .. "*" pos = pos + 1 else for i = 1, #ranges do ranges[i] = make_charset(ranges[i]) end end if output == nil then output = {} end nxt = byte(pattern, pos) n = n + 1 output[n] = sub(pattern, start, charset_pos - 1) .. concat(ranges) .. ((nxt == 0x2A or nxt == 0x2B or nxt == 0x2D or nxt == 0x3F) and "%" or "") -- following *+-? now have to be escaped start = pos end elseif not nxt then break elseif nxt == 0x2B then -- + if nxt_pos - pos ~= 2 then return false elseif output == nil then output = {} end pos, nxt_pos = pos + 1, nxt_pos + 1 nxt = byte(pattern, nxt_pos) local ch2 = sub(pattern, pos, pos) n = n + 1 output[n] = sub(pattern, start, pos - 1) .. "[" .. ch .. ch2 .. "]*" .. ch2 .. ((nxt == 0x2A or nxt == 0x2B or nxt == 0x2D or nxt == 0x3F) and "%" or "") -- following *+-? now have to be escaped pos, start = nxt_pos, nxt_pos elseif nxt == 0x2A or nxt == 0x2D or nxt == 0x3F then -- *-? return false else pos = nxt_pos end end if start == 1 then return pattern end return concat(output) .. sub(pattern, start) end pattern_simplifier = memoize(pattern_simplifier, true) export.pattern_simplifier = pattern_simplifier end --[==[ Parses `charset`, the interior of a string or ustring library character set, and normalizes it into a string or ustring library pattern (e.g. {"abcd-g"} becomes {"[abcd-g]"}, and {"[]"} becomes {"[[%]]"}). The negative (`^`), range (`-`) and literal (`%`) magic characters work as normal, and character classes may be used (e.g. `%d` and `%w`), but opening and closing square brackets are sanitized so that they behave like ordinary characters. ]==] function get_charset(charset) if type(charset) == "number" then return tostring(charset) end local pos, start, n, output = 1, 1, 0 if byte(charset) == 0x5E then -- ^ pos = pos + 1 end -- FIXME: "]" is non-magic if it's the first character in a charset. local nxt_pos, nxt while true do local new_pos, ch = match(charset, "()([%%%-%]])", pos) if not ch then break -- Skip percent escapes. Ranges can't start with them, either. elseif ch == "%" then pos = new_pos + 2 else -- If `ch` is a hyphen, get the character before iff it's at or ahead of `pos`. if ch == "-" and new_pos > pos then pos, nxt_pos, nxt = new_pos - 1, new_pos, ch ch = sub(charset, pos, pos) else pos, nxt_pos = new_pos, new_pos + 1 nxt = sub(charset, nxt_pos, nxt_pos) end -- Range. if nxt == "-" then if output == nil then output = {} end n = n + 1 output[n] = sub(charset, start, pos - 1) nxt_pos = nxt_pos + 1 nxt = sub(charset, nxt_pos, nxt_pos) -- Ranges fail if they end with a percent escape, so escape the hyphen to avoid undefined behaviour. if nxt == "" or nxt == "%" then n = n + 1 output[n] = (ch == "]" and "%]" or ch) .. "%-" start = nxt_pos nxt_pos = nxt_pos + 2 -- Since ranges can't contain "%]", since it's escaped, range inputs like "]-z" or "a-]" must be -- adjusted to the character before or after, plus "%]" (e.g. "%]^-z" or "a-\\%]"). The escaped "%]" is -- omitted if the range would be empty (i.e. if the first byte is greater than the second). else n = n + 1 output[n] = (ch == "]" and (byte(nxt) >= 0x5D and "%]^" or "^") or ch) .. "-" .. (nxt == "]" and (byte(ch) <= 0x5D and "\\%]" or "\\") or nxt) nxt_pos = nxt_pos + 1 start = nxt_pos end elseif ch == "-" or ch == "]" then if output == nil then output = {} end n = n + 1 output[n] = sub(charset, start, pos - 1) .. "%" .. ch start = nxt_pos end pos = nxt_pos end end if start == 1 then return "[" .. charset .. "]" end return "[" .. concat(output) .. sub(charset, start) .. "]" end get_charset = memoize(get_charset, true) export.get_charset = get_charset function export.len(str) return type(str) == "number" and len(str) or #str - #gsub(str, "[^\128-\191]+", "") end ulen = export.len function export.sub(str, i, j) str, i = type(str) == "number" and tostring(str) or str, i or 1 if i < 0 or j and j < 0 then return usub(str, i, j) elseif j and i > j or i > #str then return "" end local n, new_i = 0 for loc1, loc2 in gmatch(str, "()[^\128-\191]+()[\128-\191]*") do n = n + loc2 - loc1 if not new_i and n >= i then new_i = loc2 - (n - i) - 1 if not j then return sub(str, new_i) end end if j and n > j then return sub(str, new_i, loc2 - (n - j) - 1) end end return new_i and sub(str, new_i) or "" end do local function _find(str, loc1, loc2, ...) if loc1 and not match(str, "^()[^\128-\255]*$") then -- Use raw values of loc1 and loc2 to get loc1 and the length of the match. loc1, loc2 = ulen(sub(str, 1, loc1)), ulen(sub(str, loc1, loc2)) -- Offset length with loc1 to get loc2. loc2 = loc1 + loc2 - 1 end return loc1, loc2, ... end --[==[A version of find which uses string.find when possible, but otherwise uses mw.ustring.find.]==] function export.find(str, pattern, init, plain) init = init or 1 if init ~= 1 and not match(str, "^()[^\128-\255]*$") then return ufind(str, pattern, init, plain) elseif plain then return _find(str, find(str, pattern, init, true)) end local simple = pattern_simplifier(pattern) if simple then return _find(str, find(str, simple, init)) end return ufind(str, pattern, init) end end --[==[A version of match which uses string.match when possible, but otherwise uses mw.ustring.match.]==] function export.match(str, pattern, init) init = init or 1 if init ~= 1 and not match(str, "^()[^\128-\255]*$") then return umatch(str, pattern, init) end local simple = pattern_simplifier(pattern) if simple then return match(str, simple, init) end return umatch(str, pattern, init) end --[==[A version of gmatch which uses string.gmatch when possible, but otherwise uses mw.ustring.gmatch.]==] function export.gmatch(str, pattern) local simple = pattern_simplifier(pattern) if simple then return gmatch(str, simple) end return ugmatch(str, pattern) end --[==[A version of gsub which uses string.gsub when possible, but otherwise uses mw.ustring.gsub.]==] function export.gsub(str, pattern, repl, n) local simple = pattern_simplifier(pattern) if simple then return gsub(str, simple, repl, n) end return ugsub(str, pattern, repl, n) end --[==[ Like gsub, but pattern-matching facilities are turned off, so `pattern` and `repl` (if a string) are treated as literal. ]==] function export.plain_gsub(str, pattern, repl, n) return gsub(str, pattern_escape(pattern), type(repl) == "string" and replacement_escape(repl) or repl, n) end --[==[ Reverses a UTF-8 string; equivalent to string.reverse. ]==] function export.reverse(str) return reverse((gsub(str, "[\192-\255][\128-\191]*", reverse))) end function export.char(...) -- To be moved to [[Module:string/char]]. return u(...) end do local function utf8_err(func_name) error(format("bad argument #1 to '%s' (string is not UTF-8)", func_name), 4) end local function get_codepoint(func_name, b1, b2, b3, b4) if b1 <= 0x7F then return b1, 1 elseif not (b2 and b2 >= 0x80 and b2 <= 0xBF) then utf8_err(func_name) elseif b1 <= 0xDF then local cp = 0x40 * b1 + b2 - 0x3080 return cp >= 0x80 and cp or utf8_err(func_name), 2 elseif not (b3 and b3 >= 0x80 and b3 <= 0xBF) then utf8_err(func_name) elseif b1 <= 0xEF then local cp = 0x1000 * b1 + 0x40 * b2 + b3 - 0xE2080 return cp >= 0x800 and cp or utf8_err(func_name), 3 elseif not (b4 and b4 >= 0x80 and b4 <= 0xBF) then utf8_err(func_name) end local cp = 0x40000 * b1 + 0x1000 * b2 + 0x40 * b3 + b4 - 0x3C82080 return cp >= 0x10000 and cp <= 0x10FFFF and cp or utf8_err(func_name), 4 end function export.codepoint(str, i, j) if str == "" then return -- return nothing elseif type(str) == "number" then return byte(str, i, j) end i, j = i or 1, j == -1 and #str or i or 1 if i == 1 and j == 1 then return (get_codepoint("codepoint", byte(str, 1, 4))) elseif i < 0 or j < 0 then return ucodepoint(str, i, j) -- FIXME end local n, nb, ret, nr = 0, 1, {}, 0 while n < j do n = n + 1 if n < i then local b = byte(str, nb) nb = nb + (b < 128 and 1 or b < 224 and 2 or b < 240 and 3 or 4) else local b1, b2, b3, b4 = byte(str, nb, nb + 3) if not b1 then break end nr = nr + 1 local add ret[nr], add = get_codepoint("codepoint", b1, b2, b3, b4) nb = nb + add end end return unpack(ret) end codepoint = export.codepoint function export.gcodepoint(str, i, j) i, j = i or 1, j ~= -1 and j or nil if i < 0 or j and j < 0 then return ugcodepoint(str, i, j) -- FIXME end local n, nb = 1, 1 while n < i do local b = byte(str, nb) if not b then break end nb = nb + (b < 128 and 1 or b < 224 and 2 or b < 240 and 3 or 4) n = n + 1 end return function() if j and n > j then return nil end n = n + 1 local b1, b2, b3, b4 = byte(str, nb, nb + 3) if not b1 then return nil end local ret, add = get_codepoint("gcodepoint", b1, b2, b3, b4) nb = nb + add return ret end end end do local _ulower = ulower --[==[A version of lower which uses string.lower when possible, but otherwise uses mw.ustring.lower.]==] function export.lower(str) return (match(str, "^()[^\128-\255]*$") and lower or _ulower)(str) end end do local _uupper = uupper --[==[A version of upper which uses string.upper when possible, but otherwise uses mw.ustring.upper.]==] function export.upper(str) return (match(str, "^()[^\128-\255]*$") and upper or _uupper)(str) end end do local function add_captures(t, n, ...) if ... == nil then return end -- Insert any captures from the splitting pattern. local offset, capture = n - 1, ... while capture do n = n + 1 t[n] = capture capture = select(n - offset, ...) end return n end --[==[ Reimplementation of mw.text.split() that includes any capturing groups in the splitting pattern. This works like Python's re.split() function, except that it has Lua's behavior when the split pattern is empty (i.e. advancing by one character at a time; Python returns the whole remainder of the string). When possible, it will use the string library, but otherwise uses the ustring library. There are two optional parameters: `str_lib` forces use of the string library, while `plain` turns any pattern matching facilities off, treating `pattern` as literal. In addition, `pattern` may be a custom find function (or callable table), which takes the input string and start index as its two arguments, and must return the start and end index of the match, plus any optional captures, or nil if there are no further matches. By default, the start index will be calculated using the ustring library, unless `str_lib` or `plain` is set. ]==] function export.split(str, pattern_or_func, str_lib, plain) local iter, t, n = gsplit(str, pattern_or_func, str_lib, plain), {}, 0 repeat n = add_captures(t, n, iter()) until n == nil return t end export.capturing_split = export.split -- To be removed. end --[==[ Returns an iterator function, which iterates over the substrings returned by {split}. The first value returned is the string up the splitting pattern, with any capture groups being returned as additional values on that iteration. ]==] function export.gsplit(str, pattern_or_func, str_lib, plain) local start, final, str_len, _string, callable = 1 pattern_or_func, str_len, _string, callable = prepare_iter(str, pattern_or_func, str_lib, plain) local _find, _sub = _string.find, _string.sub local function iter(loc1, loc2, ...) -- If no match, or there is but we're past the end of the string -- (which happens when the match is the empty string), then return -- the final chunk. if not loc1 then final = true return _sub(str, start) end -- Special case: If we match the empty string, then eat the -- next character; this avoids an infinite loop, and makes -- splitting by the empty string work the way mw.text.gsplit() does -- (including non-adjacent empty string matches with %f). If we -- reach the end of the string this way, set `final` to true, so we -- don't get stuck matching the empty string at the end. local chunk if loc2 < loc1 then -- If using the string library, we need to make sure we advance -- by one UTF-8 character. if _sub == sub then local b = byte(str, loc1) if b and b >= 128 then loc1 = loc1 + (b < 224 and 1 or b < 240 and 2 or 3) end end chunk = _sub(str, start, loc1) if loc1 >= str_len then final = true else start = loc1 + 1 end -- Eat chunk up to the current match. else chunk = _sub(str, start, loc1 - 1) start = loc2 + 1 end return chunk, ... end if callable then return function() if not final then return iter(pattern_or_func(str, start)) end end -- Special case if the pattern is anchored to the start: "^" always -- anchors to the start position, not the start of the string, so get -- around this by only attempting one match with the pattern, then match -- the end of the string. elseif byte(pattern_or_func) == 0x5E then -- ^ local returned return function() if not returned then returned = true return iter(_find(str, pattern_or_func, start, plain)) elseif not final then return iter(_find(str, "$", start, plain)) end end end return function() if not final then return iter(_find(str, pattern_or_func, start, plain)) end end end gsplit = export.gsplit function export.count(str, pattern, plain) if plain then return select(2, gsub(str, pattern_escape(pattern), "")) end local simple = pattern_simplifier(pattern) if simple then return select(2, gsub(str, pattern, "")) end return select(2, ugsub(str, pattern, "")) end function export.trim(str, charset, str_lib, plain) if charset == nil then -- "^.*%S" is the fastest trim algorithm except when strings only consist of characters to be trimmed, which are -- very slow due to catastrophic backtracking. gsub with "^%s*" gets around this by trimming such strings to "" -- first. return match(gsub(str, "^%s*", ""), "^.*%S") or "" elseif charset == "" then return str end charset = plain and ("[" .. charset_escape(charset) .. "]") or get_charset(charset) -- The pattern uses a non-greedy quantifier instead of the algorithm used for %s, because negative character sets -- are non-trivial to compute (e.g. "[^^-z]" becomes "[%^_-z]"). Plus, if the ustring library has to be used, there -- would be two callbacks into PHP, which is slower. local pattern = "^" .. charset .. "*(.-)" .. charset .. "*$" if not str_lib then local simple = pattern_simplifier(pattern) if not simple then return umatch(str, pattern) end pattern = simple end return match(str, pattern) end trim = export.trim do local entities local function get_entities() entities, get_entities = load_data("Module:data/entities"), nil return entities end local function decode_entity(hash, x, code) if hash == "" then return (entities or get_entities())[x .. code] end local cp if x == "" then cp = match(code, "^()%d+$") and tonumber(code) else cp = match(code, "^()%x+$") and tonumber(code, 16) end return cp and (cp <= 0xD7FF or cp >= 0xE000 and cp <= 0x10FFFF) and u(cp) or nil end -- Non-ASCII characters aren't valid in proper HTML named entities, but MediaWiki uses them in some custom aliases -- which have also been included in [[Module:data/entities]]. function export.decode_entities(str) local amp = find(str, "&", nil, true) return amp and find(str, ";", amp, true) and gsub(str, "&(#?)([xX]?)([%w\128-\255]+);", decode_entity) or str end end do local entities local function get_entities() -- Memoized HTML entities (taken from mw.text.lua). entities, get_entities = { ["\""] = "&quot;", ["&"] = "&amp;", ["'"] = "&#039;", ["<"] = "&lt;", [">"] = "&gt;", ["\194\160"] = "&nbsp;", }, nil return entities end local function encode_entity(ch) local entity = (entities or get_entities())[ch] if entity == nil then local cp = codepoint(ch) -- U+D800 to U+DFFF are surrogates, so can't be encoded as entities. entity = cp and (cp <= 0xD7FF or cp >= 0xE000) and format("&#%d;", cp) or false entities[ch] = entity end return entity or nil end function export.encode_entities(str, charset, str_lib, plain) if charset == nil then return (gsub(str, "[\"&'<>\194]\160?", entities or get_entities())) elseif charset == "" then return str end local pattern = plain and ("[" .. charset_escape(charset) .. "]") or charset == "." and charset or get_charset(charset) if not str_lib then local simple = pattern_simplifier(pattern) if not simple then return (ugsub(str, pattern, encode_entity)) end pattern = simple end return (gsub(str, pattern, encode_entity)) end end do local function decode_path(code) return char(tonumber(code, 16)) end local function decode(lead, trail) if lead == "+" or lead == "_" then return " " .. trail elseif #trail == 2 then return decode_path(trail) end return lead .. trail end function export.decode_uri(str, enctype) enctype = enctype and upper(enctype) or "QUERY" if enctype == "PATH" then return find(str, "%", nil, true) and gsub(str, "%%(%x%x)", decode_path) or str elseif enctype == "QUERY" then return (find(str, "%", nil, true) or find(str, "+", nil, true)) and gsub(str, "([%%%+])(%x?%x?)", decode) or str elseif enctype == "WIKI" then return (find(str, "%", nil, true) or find(str, "_", nil, true)) and gsub(str, "([%%_])(%x?%x?)", decode) or str end error("bad argument #2 to 'decode_uri' (expected QUERY, PATH, or WIKI)", 2) end end do local function _remove_comments(str, pre) local head = find(str, "<!--", nil, true) if not head then return str end local ret, n = {sub(str, 1, head - 1)}, 1 while true do local loc = find(str, "-->", head + 4, true) if not loc then return pre and concat(ret) or concat(ret) .. sub(str, head) end head = loc + 3 loc = find(str, "<!--", head, true) if not loc then return concat(ret) .. sub(str, head) end n = n + 1 ret[n] = sub(str, head, loc - 1) head = loc end end --[==[ Removes any HTML comments from the input text. `stage` can be one of three options: * {"PRE"} (default) applies the method used by MediaWiki's preprocessor: all {{code|html|<nowiki><!-- ... --></nowiki>}} pairs are removed, as well as any text after an unclosed {{code|html|<nowiki><!--</nowiki>}}. This is generally suitable when parsing raw template or [[mw:Parser extension tags|parser extension tag]] code. (Note, however, that the actual method used by the preprocessor is considerably more complex and differs under certain conditions (e.g. comments inside nowiki tags); if full accuracy is absolutely necessary, use [[Module:template parser]] instead). * {"POST"} applies the method used to generate the final page output once all templates have been expanded: it loops over the text, removing any {{code|html|<nowiki><!-- ... --></nowiki>}} pairs until no more are found (e.g. {{code|html|<nowiki><!-<!-- ... -->- ... --></nowiki>}} would be fully removed), but any unclosed {{code|html|<nowiki><!--</nowiki>}} is ignored. This is suitable for handling links embedded in template inputs, where the {"PRE"} method will have already been applied by the native parser. * {"BOTH"} applies {"PRE"} then {"POST"}. ]==] function export.remove_comments(str, stage) if not stage or stage == "PRE" then return _remove_comments(str, true) end local processed = stage == "POST" and _remove_comments(str) or stage == "BOTH" and _remove_comments(str, true) or error("bad argument #2 to 'remove_comments' (expected PRE, POST, or BOTH)", 2) while processed ~= str do str = processed processed = _remove_comments(str) end return str end end do local byte_escapes local function get_byte_escapes() byte_escapes, get_byte_escapes = load_data("Module:string utilities/data").byte_escapes, nil return byte_escapes end local function escape_byte(b) return (byte_escapes or get_byte_escapes())[b] or format("\\%03d", byte(b)) end function export.escape_bytes(str) return (gsub(str, ".", escape_byte)) end end function export.format_fun(str, fun) return (gsub(str, "{(\\?)((\\?)[^{}]*)}", function(p1, name, p2) if #p1 + #p2 == 1 then return name == "op" and "{" or name == "cl" and "}" or error(mw.getCurrentFrame():getTitle() .. " format: unrecognized escape sequence '{\\" .. name .. "}'") elseif fun(name) and type(fun(name)) ~= "string" then error(mw.getCurrentFrame():getTitle() .. " format: \"" .. name .. "\" is a " .. type(fun(name)) .. ", not a string") end return fun(name) or error(mw.getCurrentFrame():getTitle() .. " format: \"" .. name .. "\" not found in table") end)) end format_fun = export.format_fun --[==[ This function, unlike {string.format} and {mw.ustring.format}, takes just two parameters, a format string and a table, and replaces all instances of { {param_name} } in the format string with the table's entry for {param_name}. The opening and closing brace characters can be escaped with { {\op} } and { {\cl} }, respectively. A table entry beginning with a slash can be escaped by doubling the initial slash. ====Examples==== * {string_utilities.format("{foo} fish, {bar} fish, {baz} fish, {quux} fish", {["foo"]="one", ["bar"]="two", ["baz"]="red", ["quux"]="blue"}) } *: produces: {"one fish, two fish, red fish, blue fish"} * {string_utilities.format("The set {\\op}1, 2, 3{\\cl} contains {\\\\hello} elements.", {["\\hello"]="three"})} *: produces: {"The set {1, 2, 3} contains three elements."} *:* Note that the single and double backslashes should be entered as double and quadruple backslashes when quoted in a literal string. ]==] function export.format(str, tbl) return format_fun(str, function(key) return tbl[key] end) end do local function do_uclcfirst(str, case_func) -- Re-case the first letter. local first, remainder = match(str, "^(.[\128-\191]*)(.*)") return first and (case_func(first) .. remainder) or "" end local function uclcfirst(str, case_func) -- Strip off any HTML tags at the beginning. This currently does not handle comments or <ref>...</ref> -- correctly; it's intended for text wrapped in <span> or the like, as happens when passing text through -- [[Module:links]]. local html_at_beginning = nil if str:match("^<") then while true do local html_tag, rest = str:match("^(<.->)(.*)$") if not html_tag then break end if not html_at_beginning then html_at_beginning = {} end insert(html_at_beginning, html_tag) str = rest end end -- If there's a link at the beginning, re-case the first letter of the -- link text. This pattern matches both piped and unpiped links. -- If the link is not piped, the second capture (linktext) will be empty. local link, linktext, remainder = match(str, "^%[%[([^|%]]+)%|?(.-)%]%](.*)$") local retval if link then retval = "[[" .. link .. "|" .. do_uclcfirst(linktext ~= "" and linktext or link, case_func) .. "]]" .. remainder else retval = do_uclcfirst(str, case_func) end if html_at_beginning then retval = concat(html_at_beginning) .. retval end return retval end --[==[ Uppercase the first character of the input string, correctly handling one-part and two-part links, optionally surrounded by HTML tags such as `<nowiki><span>...</span></nowiki>`, possibly nested. Intended to correctly uppercase the first character of text that may include links that have been passed through `full_link()` in [[Module:links]] or a similar function. ]==] function export.ucfirst(str) return uclcfirst(str, uupper) end ucfirst = export.ucfirst --[==[ Lowercase the first character of the input string, correctly handling one-part and two-part links, optionally surrounded by HTML tags such as `<nowiki><span>...</span></nowiki>`, possibly nested. Intended to correctly lowercase the first character of text that may include links that have been passed through `full_link()` in [[Module:links]] or a similar function. ]==] function export.lcfirst(str) return uclcfirst(str, ulower) end --[==[Capitalizes each word of the input string. WARNING: May be broken in the presence of multiword links.]==] function export.capitalize(str) -- Capitalize multi-word that is separated by spaces -- by uppercasing the first letter of each part. return (ugsub(str, "%w+", ucfirst)) end local function do_title_case(first, remainder) first = uupper(first) return remainder == "" and first or (first .. ulower(remainder)) end --[==[ Capitalizes each word of the input string, with any further letters in each word being converted to lowercase. ]==] function export.title_case(str) return str == "" and "" or ugsub(str, "(%w)(%w*)", do_title_case) end title_case = export.title_case --[==[ Converts the input string to {{w|Camel case|CamelCase}}. Any non-word characters are treated as breaks between words. If `lower_first` is set, then the first character of the string will be lowercase (e.g. camelCase). ]==] function export.camel_case(str, lower_first) str = ugsub(str, "%W*(%w*)", title_case) return lower_first and do_uclcfirst(str, ulower) or str end end do local function do_snake_case(nonword, word) return nonword == "" and word or "_" .. word end --[==[ Converts the input string to {{w|Snake case|snake_case}}. Any non-word characters are treated as breaks between words. ]==] function export.snake_case(str) return (ugsub(str, "(%W*)(%w*)", do_snake_case)) end end return export ndjfpg4lokleft04xzto19wigx7fczh 828 5900 17394 17343 2026-07-13T08:14:36Z Hiyuune 6766 17394 Scribunto text/plain --[=[ This module implements fetching of language-specific information and processing text in a given language. There are two types of languages: full languages and etymology-only languages. The essential difference is that only full languages appear in L2 headings in vocabulary entries, and hence categories like [[:Category:French nouns]] exist only for full languages. Etymology-only languages have either a full language or another etymology-only language as their parent (in the parent-child inheritance sense), and for etymology-only languages with another etymology-only language as their parent, a full language can always be derived by following the parent links upwards. For example, "Canadian French", code 'fr-CA', is an etymology-only language whose parent is the full language "French", code 'fr'. An example of an etymology-only language with another etymology-only parent is "Northumbrian Old English", code 'ang-nor', which has "Anglian Old English", code 'ang-ang' as its parent; this is an etymology-only language whose parent is "Old English", code "ang", which is a full language. (This is because Northumbrian Old English is considered a variety of Anglian Old English.) Sometimes the parent is the "Undetermined" language, code 'und'; this is the case, for example, for "substrate" languages such as "Pre-Greek", code 'qsb-grc', and "the BMAC substrate", code 'qsb-bma'. It is important to distinguish language ''parents'' from language ''ancestors''. The parent-child relationship is one of containment, i.e. if X is a child of Y, X is considered a variety of Y. On the other hand, the ancestor-descendant relationship is one of descent in time. For example, "Classical Latin", code 'la-cla', and "Late Latin", code 'la-lat', are both etymology-only languages with "Latin", code 'la', as their parents, because both of the former are varieties of Latin. However, Late Latin does *NOT* have Classical Latin as its parent because Late Latin is *not* a variety of Classical Latin; rather, it is a descendant. There is in fact a separate 'ancestors' field that is used to express the ancestor-descendant relationship, and Late Latin's ancestor is given as Classical Latin. It is also important to note that sometimes an etymology-only language is actually the conceptual ancestor of its parent language. This happens, for example, with "Old Italian" (code 'roa-oit'), which is an etymology-only variant of full language "Italian" (code 'it'), and with "Old Latin" (code 'itc-ola'), which is an etymology-only variant of Latin. In both cases, the full language has the etymology-only variant listed as an ancestor. This allows a Latin term to inherit from Old Latin using the {{tl|inh}} template (where in this template, "inheritance" refers to ancestral inheritance, i.e. inheritance in time, rather than in the parent-child sense); likewise for Italian and Old Italian. Full languages come in three subtypes: * {regular}: This indicates a full language that is attested according to [[WT:CFI]] and therefore permitted in the main namespace. There may also be reconstructed terms for the language, which are placed in the {Reconstruction} namespace and must be prefixed with * to indicate a reconstruction. Most full languages are natural (not constructed) languages, but a few constructed languages (e.g. Esperanto and Volapük, among others) are also allowed in the mainspace and considered regular languages. * {reconstructed}: This language is not attested according to [[WT:CFI]], and therefore is allowed only in the {Reconstruction} namespace. All terms in this language are reconstructed, and must be prefixed with *. Languages such as Proto-Indo-European and Proto-Germanic are in this category. * {appendix-constructed}: This language is attested but does not meet the additional requirements set out for constructed languages ([[WT:CFI#Constructed languages]]). Its entries must therefore be in the Appendix namespace, but they are not reconstructed and therefore should not have * prefixed in links. Most constructed languages are of this subtype. Both full languages and etymology-only languages have a {Language} object associated with them, which is fetched using the {getByCode} function in [[Module:languages]] to convert a language code to a {Language} object. Depending on the options supplied to this function, etymology-only languages may or may not be accepted, and family codes may be accepted (returning a {Family} object as described in [[Module:families]]). There are also separate {getByCanonicalName} functions in [[Module:languages]] and [[Module:etymology languages]] to convert a language's canonical name to a {Language} object (depending on whether the canonical name refers to a full or etymology-only language). Textual strings belonging to a given language come in several different ''text variants'': # The ''input text'' is what the user supplies in wikitext, in the parameters to {{tl|m}}, {{tl|l}}, {{tl|ux}}, {{tl|t}}, {{tl|lang}} and the like. # The ''display text'' is the text in the form as it will be displayed to the user. This can include accent marks that are stripped to form the entry text (see below), as well as embedded bracketed links that are variously processed further. The display text is generated from the input text by applying language-specific transformations; for most languages, there will be no such transformations. Examples of transformations are bad-character replacements for certain languages (e.g. replacing 'l' or '1' to [[palochka]] in certain languages in Cyrillic); and for Thai and Khmer, converting space-separated words to bracketed words and resolving respelling substitutions such as [กรีน/กฺรีน], which indicate how to transliterate given words. # The ''entry text'' is the text in the form used to generate a link to a Wiktionary entry. This is usually generated from the display text by stripping certain sorts of diacritics on a per-language basis, and sometimes doing other transformations. The concept of ''entry text'' only really makes sense for text that does not contain embedded links, meaning that display text containing embedded links will need to have the links individually processed to get per-link entry text in order to generate the resolved display text (see below). # The ''resolved display text'' is the result of resolving embedded links in the display text (e.g. converting them to two-part links where the first part has entry-text transformations applied, and adding appropriate language-specific fragments) and adding appropriate language and script tagging. This text can be passed directly to MediaWiki for display. # The ''source translit text'' is the text as supplied to the language-specific {transliterate()} method. The form of the source translit text may need to be language-specific, e.g Thai and Khmer will need the full unprocessed input text, whereas other languages may need to work off the display text. [FIXME: It's still unclear to me how embedded bracketed links are handled in the existing code.] In general, embedded links need to be removed (i.e. converted to their "bare display" form by taking the right part of two-part links and removing double brackets), but when this happens is unclear to me [FIXME]. Some languages have a chop-up-and-paste-together scheme that sends parts of the text through the transliterate mechanism, and for others (those listed with "cont" in {substition} in [[Module:languages/data]]) they receive the full input text, but preprocessed in certain ways. (The wisdom of this is still unclear to me.) # The ''transliterated text'' (or ''transliteration'') is the result of transliterating the source translit text. Unlike for all the other text variants except the transcribed text, it is always in the Latin script. # The ''transcribed text'' (or ''transcription'') is the result of transcribing the source translit text, where "transcription" here means a close approximation to the phonetic form of the language in languages (e.g. Akkadian, Sumerian, Ancient Egyptian, maybe Tibetan) that have a wide difference between the written letters and spoken form. Unlike for all the other text variants other than the transliterated text, it is always in the Latin script. Currently, the transcribed text is always supplied manually be the user; there is no such thing as a {lua|transcribe()} method on language objects. # The ''sort key'' is the text used in sort keys for determining the placing of pages in categories they belong to. The sort key is generated from the pagename or a specified ''sort base'' by lowercasing, doing language-specific transformations and then uppercasing the result. If the sort base is supplied and is generated from input text, it needs to be converted to display text, have embedded links removed (i.e. resolving them to their right side if they are two-part links) and have entry text transformations applied. # There are other text variants that occur in usexes (specifically, there are normalized variants of several of the above text variants), but we can skip them for now. The following methods exist on {Language} objects to convert between different text variants: # {makeDisplayText}: This converts input text to display text. # {lua|makeEntryName}: This converts input or display text to entry text. [FIXME: This needs some rethinking. In particular, {lua|makeEntryName} is sometimes called on display text (in some paths inside of [[Module:links]]) and sometimes called on input text (in other paths inside of [[Module:links]], and usually from other modules). We need to make sure we don't try to convert input text to display text twice, but at the same time we need to support calling it directly on input text since so many modules do this. This means we need to add a parameter indicating whether the passed-in text is input or display text; if that former, we call {lua|makeDisplayText} ourselves.] # {lua|transliterate}: This appears to convert input text with embedded brackets removed into a transliteration. [FIXME: This needs some rethinking. In particular, it calls {lua|processDisplayText} on its input, which won't work for Thai and Khmer, so we may need language-specific flags indicating whether to pass the input text directly to the language transliterate method. In addition, I'm not sure how embedded links are handled in the existing translit code; a lot of callers remove the links themselves before calling {lua|transliterate()}, which I assume is wrong.] # {lua|makeSortKey}: This converts entry text (?) to a sort key. [FIXME: Clarify this.] ]=] local export = {} local debug_track_module = "Module:debug/track" local etymology_languages_data_module = "Module:etymology languages/data" local families_module = "Module:families" local json_module = "Module:JSON" local language_like_module = "Module:language-like" local languages_data_module = "Module:languages/data" local languages_data_patterns_module = "Module:languages/data/patterns" local links_data_module = "Module:links/data" local load_module = "Module:load" local scripts_module = "Module:scripts" local scripts_data_module = "Module:scripts/data" local string_encode_entities_module = "Module:string/encode entities" local string_pattern_escape_module = "Module:string/patternEscape" local string_replacement_escape_module = "Module:string/replacementEscape" local string_utilities_module = "Module:string utilities" local table_module = "Module:table" local utilities_module = "Module:utilities" local wikimedia_languages_module = "Module:wikimedia languages" local mw = mw local string = string local table = table local char = string.char local concat = table.concat local find = string.find local floor = math.floor local get_by_code -- Defined below. local get_data_module_name -- Defined below. local get_extra_data_module_name -- Defined below. local getmetatable = getmetatable local gmatch = string.gmatch local gsub = string.gsub local insert = table.insert local ipairs = ipairs local is_known_language_tag = mw.language.isKnownLanguageTag local make_object -- Defined below. local match = string.match local next = next local pairs = pairs local remove = table.remove local require = require local select = select local setmetatable = setmetatable local sub = string.sub local type = type local unstrip = mw.text.unstrip -- Loaded as needed by findBestScript. local Hans_chars local Hant_chars local function check_object(...) check_object = require(utilities_module).check_object return check_object(...) end local function debug_track(...) debug_track = require(debug_track_module) return debug_track(...) end local function decode_entities(...) decode_entities = require(string_utilities_module).decode_entities return decode_entities(...) end local function decode_uri(...) decode_uri = require(string_utilities_module).decode_uri return decode_uri(...) end local function deep_copy(...) deep_copy = require(table_module).deepCopy return deep_copy(...) end local function encode_entities(...) encode_entities = require(string_encode_entities_module) return encode_entities(...) end local function get_script(...) get_script = require(scripts_module).getByCode return get_script(...) end local function find_best_script_without_lang(...) find_best_script_without_lang = require(scripts_module).findBestScriptWithoutLang return find_best_script_without_lang(...) end local function get_family(...) get_family = require(families_module).getByCode return get_family(...) end local function get_plaintext(...) get_plaintext = require(utilities_module).get_plaintext return get_plaintext(...) end local function get_wikimedia_lang(...) get_wikimedia_lang = require(wikimedia_languages_module).getByCode return get_wikimedia_lang(...) end local function keys_to_list(...) keys_to_list = require(table_module).keysToList return keys_to_list(...) end local function list_to_set(...) list_to_set = require(table_module).listToSet return list_to_set(...) end local function load_data(...) load_data = require(load_module).load_data return load_data(...) end local function make_family_object(...) make_family_object = require(families_module).makeObject return make_family_object(...) end local function pattern_escape(...) pattern_escape = require(string_pattern_escape_module) return pattern_escape(...) end local function remove_duplicates(...) remove_duplicates = require(table_module).removeDuplicates return remove_duplicates(...) end local function replacement_escape(...) replacement_escape = require(string_replacement_escape_module) return replacement_escape(...) end local function safe_require(...) safe_require = require(load_module).safe_require return safe_require(...) end local function shallow_copy(...) shallow_copy = require(table_module).shallowCopy return shallow_copy(...) end local function split(...) split = require(string_utilities_module).split return split(...) end local function to_json(...) to_json = require(json_module).toJSON return to_json(...) end local function u(...) u = require(string_utilities_module).char return u(...) end local function ugsub(...) ugsub = require(string_utilities_module).gsub return ugsub(...) end local function ulen(...) ulen = require(string_utilities_module).len return ulen(...) end local function ulower(...) ulower = require(string_utilities_module).lower return ulower(...) end local function umatch(...) umatch = require(string_utilities_module).match return umatch(...) end local function uupper(...) uupper = require(string_utilities_module).upper return uupper(...) end local function track(page) debug_track("languages/" .. page) return true end local function normalize_code(code) return load_data(languages_data_module).aliases[code] or code end local function check_inputs(self, check, default, ...) local n = select("#", ...) if n == 0 then return false end local ret = check(self, (...)) if ret ~= nil then return ret elseif n > 1 then local inputs = {...} for i = 2, n do ret = check(self, inputs[i]) if ret ~= nil then return ret end end end return default end local function make_link(self, target, display) local prefix, main if self:getFamilyCode() == "qfa-sub" then prefix, main = display:match("^(the )(.*)") if not prefix then prefix, main = display:match("^(a )(.*)") end end return (prefix or "") .. "[[" .. target .. "|" .. (main or display) .. "]]" end -- Convert risky characters to HTML entities, which minimizes interference once returned (e.g. for "sms:a", "<!-- -->" etc.). local function escape_risky_characters(text) -- Spacing characters in isolation generally need to be escaped in order to be properly processed by the MediaWiki software. if umatch(text, "^%s*$") then return encode_entities(text, text) end return encode_entities(text, "!#%&*+/:;<=>?@[\\]_{|}") end -- Temporarily convert various formatting characters to PUA to prevent them from being disrupted by the substitution process. local function doTempSubstitutions(text, subbedChars, keepCarets, noTrim) -- Clone so that we don't insert any extra patterns into the table in package.loaded. For some reason, using require seems to keep memory use down; probably because the table is always cloned. local patterns = shallow_copy(require(languages_data_patterns_module)) if keepCarets then insert(patterns, "((\\+)%^)") insert(patterns, "((%^))") end -- Ensure any whitespace at the beginning and end is temp substituted, to prevent it from being accidentally trimmed. We only want to trim any final spaces added during the substitution process (e.g. by a module), which means we only do this during the first round of temp substitutions. if not noTrim then insert(patterns, "^([\128-\191\244]*(%s+))") insert(patterns, "((%s+)[\128-\191\244]*)$") end -- Pre-substitution, of "[[" and "]]", which makes pattern matching more accurate. text = gsub(text, "%f[%[]%[%[", "\1") :gsub("%f[%]]%]%]", "\2") local i = #subbedChars for _, pattern in ipairs(patterns) do -- Patterns ending in \0 stand are for things like "[[" or "]]"), so the inserted PUA are treated as breaks between terms by modules that scrape info from pages. local term_divider pattern = gsub(pattern, "%z$", function(divider) term_divider = divider == "\0" return "" end) text = gsub(text, pattern, function(...) local m = {...} local m1New = m[1] for k = 2, #m do local n = i + k - 1 subbedChars[n] = m[k] local byte2 = floor(n / 4096) % 64 + (term_divider and 128 or 136) local byte3 = floor(n / 64) % 64 + 128 local byte4 = n % 64 + 128 m1New = gsub(m1New, pattern_escape(m[k]), "\244" .. char(byte2) .. char(byte3) .. char(byte4), 1) end i = i + #m - 1 return m1New end) end text = gsub(text, "\1", "%[%[") :gsub("\2", "%]%]") return text, subbedChars end -- Reinsert any formatting that was temporarily substituted. local function undoTempSubstitutions(text, subbedChars) for i = 1, #subbedChars do local byte2 = floor(i / 4096) % 64 + 128 local byte3 = floor(i / 64) % 64 + 128 local byte4 = i % 64 + 128 text = gsub(text, "\244[" .. char(byte2) .. char(byte2+8) .. "]" .. char(byte3) .. char(byte4), replacement_escape(subbedChars[i])) end text = gsub(text, "\1", "%[%[") :gsub("\2", "%]%]") return text end -- Check if the raw text is an unsupported title, and if so return that. Otherwise, remove HTML entities. We do the pre-conversion to avoid loading the unsupported title list unnecessarily. local function checkNoEntities(self, text) local textNoEnc = decode_entities(text) if textNoEnc ~= text and load_data(links_data_module).unsupported_titles[text] then return text else return textNoEnc end end -- If no script object is provided (or if it's invalid or None), get one. local function checkScript(text, self, sc) if not check_object("script", true, sc) or sc:getCode() == "None" then return self:findBestScript(text) end return sc end local function normalize(text, sc) text = sc:fixDiscouragedSequences(text) return sc:toFixedNFD(text) end local function doSubstitutions(self, text, sc, substitution_data, function_name, recursed) local fail, cats = nil, {} -- If there are language-specific substitutes given in the data module, use those. if type(substitution_data) == "table" then -- If a script is specified, run this function with the script-specific data before continuing. local sc_code = sc:getCode() if substitution_data[sc_code] then text, fail, cats = doSubstitutions(self, text, sc, substitution_data[sc_code], function_name, true) -- Hant, Hans and Hani are usually treated the same, so add a special case to avoid having to specify each one separately. elseif sc_code:match("^Han") and substitution_data.Hani then text, fail, cats = doSubstitutions(self, text, sc, substitution_data.Hani, function_name, true) -- Substitution data with key 1 in the outer table may be given as a fallback. elseif substitution_data[1] then text, fail, cats = doSubstitutions(self, text, sc, substitution_data[1], function_name, true) end -- Iterate over all strings in the "from" subtable, and gsub with the corresponding string in "to". We work with the NFD decomposed forms, as this simplifies many substitutions. if substitution_data.from then for i, from in ipairs(substitution_data.from) do -- Normalize each loop, to ensure multi-stage substitutions work correctly. text = sc:toFixedNFD(text) text = ugsub(text, sc:toFixedNFD(from), substitution_data.to[i] or "") end end if substitution_data.remove_diacritics then text = sc:toFixedNFD(text) -- Convert exceptions to PUA. local remove_exceptions, substitutes = substitution_data.remove_exceptions if remove_exceptions then substitutes = {} local i = 0 for _, exception in ipairs(remove_exceptions) do exception = sc:toFixedNFD(exception) text = ugsub(text, exception, function(m) i = i + 1 local subst = u(0x80000 + i) substitutes[subst] = m return subst end) end end -- Strip diacritics. text = ugsub(text, "[" .. substitution_data.remove_diacritics .. "]", "") -- Convert exceptions back. if remove_exceptions then text = text:gsub("\242[\128-\191]*", substitutes) end end elseif type(substitution_data) == "string" then -- If there is a dedicated function module, use that. local module = safe_require("Module:" .. substitution_data) if module then -- TODO: translit functions should take objects, not codes. -- TODO: translit functions should be called with form NFD. if function_name == "tr" then text, fail, cats = module[function_name](text, self._code, sc:getCode()) else text, fail, cats = module[function_name](sc:toFixedNFD(text), self, sc) end -- TODO: get rid of the `fail` and `cats` return values. if fail ~= nil then track("fail") track("fail/" .. self._code) end if cats ~= nil then track("cats") track("cats/" .. self._code) end else error("Substitution data '" .. substitution_data .. "' does not match an existing module.") end end -- Don't normalize to NFC if this is the inner loop or if a module returned nil. if recursed or not text then return text, fail, cats end -- Fix any discouraged sequences created during the substitution process, and normalize into the final form. return sc:toFixedNFC(sc:fixDiscouragedSequences(text)), fail, cats end -- Split the text into sections, based on the presence of temporarily substituted formatting characters, then iterate over each one to apply substitutions. This avoids putting PUA characters through language-specific modules, which may be unequipped for them. local function iterateSectionSubstitutions(self, text, sc, subbedChars, keepCarets, substitution_data, function_name) local fail, cats, sections = nil, {} -- See [[Module:languages/data]]. if not find(text, "\244") or (load_data(languages_data_module).substitution[self._code] == "cont") then sections = {text} else sections = split(text, "\244[\128-\143][\128-\191]*", true) end for _, section in ipairs(sections) do -- Don't bother processing empty strings or whitespace (which may also not be handled well by dedicated modules). if gsub(section, "%s+", "") ~= "" then local sub, sub_fail, sub_cats = doSubstitutions(self, section, sc, substitution_data, function_name) -- Second round of temporary substitutions, in case any formatting was added by the main substitution process. However, don't do this if the section contains formatting already (as it would have had to have been escaped to reach this stage, and therefore should be given as raw text). if sub and subbedChars then local noSub for _, pattern in ipairs(require(languages_data_patterns_module)) do if match(section, pattern .. "%z?") then noSub = true end end if not noSub then sub, subbedChars = doTempSubstitutions(sub, subbedChars, keepCarets, true) end end if (not sub) or sub_fail then text = sub fail = sub_fail cats = sub_cats or {} break end text = sub and gsub(text, pattern_escape(section), replacement_escape(sub), 1) or text if type(sub_cats) == "table" then for _, cat in ipairs(sub_cats) do insert(cats, cat) end end end end -- Trim, unless there are only spacing characters, while ignoring any final formatting characters. text = text and text:gsub("^([\128-\191\244]*)%s+(%S)", "%1%2") :gsub("(%S)%s+([\128-\191\244]*)$", "%1%2") -- Remove duplicate categories. if #cats > 1 then cats = remove_duplicates(cats) end return text, fail, cats, subbedChars end -- Process carets (and any escapes). Default to simple removal, if no pattern/replacement is given. local function processCarets(text, pattern, repl) local rep repeat text, rep = gsub(text, "\\\\(\\*^)", "\3%1") until rep == 0 return text:gsub("\\^", "\4") :gsub(pattern or "%^", repl or "") :gsub("\3", "\\") :gsub("\4", "^") end -- Remove carets if they are used to capitalize parts of transliterations (unless they have been escaped). local function removeCarets(text, sc) if not sc:hasCapitalization() and sc:isTransliterated() and text:find("^", 1, true) then return processCarets(text) else return text end end local Language = {} --[==[Returns the language code of the language. Example: {{code|lua|"fr"}} for French.]==] function Language:getCode() return self._code end --[==[Returns the canonical name of the language. This is the name used to represent that language on Wiktionary, and is guaranteed to be unique to that language alone. Example: {{code|lua|"French"}} for French.]==] function Language:getCanonicalName() local name = self._name if name == nil then name = self._data[1] self._name = name end return name end --[==[ Return the display form of the language. The display form of a language, family or script is the form it takes when appearing as the <code><var>source</var></code> in categories such as <code>English terms derived from <var>source</var></code> or <code>English given names from <var>source</var></code>, and is also the displayed text in {makeCategoryLink()} links. For full and etymology-only languages, this is the same as the canonical name, but for families, it reads <code>"<var>name</var> languages"</code> (e.g. {"Indo-Iranian languages"}), and for scripts, it reads <code>"<var>name</var> script"</code> (e.g. {"Arabic script"}). ]==] function Language:getDisplayForm() local form = self._displayForm if form == nil then form = self:getCanonicalName() -- Add article and " substrate" to substrates that lack them. if self:getFamilyCode() == "qfa-sub" then if not (sub(form, 1, 4) == "the " or sub(form, 1, 2) == "a ") then form = "a " .. form end if not match(form, " [Ss]ubstrate") then form = form .. " substrate" end end self._displayForm = form end return form end --[==[Returns the value which should be used in the HTML lang= attribute for tagged text in the language.]==] function Language:getHTMLAttribute(sc, region) local code = self._code if not find(code, "-", 1, true) then return code .. "-" .. sc:getCode() .. (region and "-" .. region or "") end local parent = self:getParent() region = region or match(code, "%f[%u][%u-]+%f[%U]") if parent then return parent:getHTMLAttribute(sc, region) end -- TODO: ISO family codes can also be used. return "mis-" .. sc:getCode() .. (region and "-" .. region or "") end --[==[Returns a table of the aliases that the language is known by, excluding the canonical name. Aliases are synonyms for the language in question. The names are not guaranteed to be unique, in that sometimes more than one language is known by the same name. Example: {{code|lua|{"High German", "New High German", "Deutsch"} }} for [[:Category:German language|German]].]==] function Language:getAliases() self:loadInExtraData() return require(language_like_module).getAliases(self) end --[==[ Return a table of the known subvarieties of a given language, excluding subvarieties that have been given explicit etymology-only language codes. The names are not guaranteed to be unique, in that sometimes a given name refers to a subvariety of more than one language. Example: {{code|lua|{"Southern Aymara", "Central Aymara"} }} for [[:Category:Aymara language|Aymara]]. Note that the returned value can have nested tables in it, when a subvariety goes by more than one name. Example: {{code|lua|{"North Azerbaijani", "South Azerbaijani", {"Afshar", "Afshari", "Afshar Azerbaijani", "Afchar"}, {"Qashqa'i", "Qashqai", "Kashkay"}, "Sonqor"} }} for [[:Category:Azerbaijani language|Azerbaijani]]. Here, for example, Afshar, Afshari, Afshar Azerbaijani and Afchar all refer to the same subvariety, whose preferred name is Afshar (the one listed first). To avoid a return value with nested tables in it, specify a non-{{code|lua|nil}} value for the <code>flatten</code> parameter; in that case, the return value would be {{code|lua|{"North Azerbaijani", "South Azerbaijani", "Afshar", "Afshari", "Afshar Azerbaijani", "Afchar", "Qashqa'i", "Qashqai", "Kashkay", "Sonqor"} }}. ]==] function Language:getVarieties(flatten) self:loadInExtraData() return require(language_like_module).getVarieties(self, flatten) end --[==[Returns a table of the "other names" that the language is known by, which are listed in the <code>otherNames</code> field. It should be noted that the <code>otherNames</code> field itself is deprecated, and entries listed there should eventually be moved to either <code>aliases</code> or <code>varieties</code>.]==] function Language:getOtherNames() -- To be eventually removed, once there are no more uses of the `otherNames` field. self:loadInExtraData() return require(language_like_module).getOtherNames(self) end --[==[ Return a combined table of the canonical name, aliases, varieties and other names of a given language.]==] function Language:getAllNames() self:loadInExtraData() return require(language_like_module).getAllNames(self) end --[==[Returns a table of types as a lookup table (with the types as keys). The possible types are * {language}: This is a language, either full or etymology-only. * {full}: This is a "full" (not etymology-only) language, i.e. the union of {regular}, {reconstructed} and {appendix-constructed}. Note that the types {full} and {etymology-only} also exist for families, so if you want to check specifically for a full language and you have an object that might be a family, you should use {{lua|hasType("language", "full")}} and not simply {{lua|hasType("full")}}. * {etymology-only}: This is an etymology-only (not full) language, whose parent is another etymology-only language or a full language. Note that the types {full} and {etymology-only} also exist for families, so if you want to check specifically for an etymology-only language and you have an object that might be a family, you should use {{lua|hasType("language", "etymology-only")}} and not simply {{lua|hasType("etymology-only")}}. * {regular}: This indicates a full language that is attested according to [[WT:CFI]] and therefore permitted in the main namespace. There may also be reconstructed terms for the language, which are placed in the {Reconstruction} namespace and must be prefixed with * to indicate a reconstruction. Most full languages are natural (not constructed) languages, but a few constructed languages (e.g. Esperanto and Volapük, among others) are also allowed in the mainspace and considered regular languages. * {reconstructed}: This language is not attested according to [[WT:CFI]], and therefore is allowed only in the {Reconstruction} namespace. All terms in this language are reconstructed, and must be prefixed with *. Languages such as Proto-Indo-European and Proto-Germanic are in this category. * {appendix-constructed}: This language is attested but does not meet the additional requirements set out for constructed languages ([[WT:CFI#Constructed languages]]). Its entries must therefore be in the Appendix namespace, but they are not reconstructed and therefore should not have * prefixed in links. ]==] function Language:getTypes() local types = self._types if types == nil then types = {language = true} if self:getFullCode() == self._code then types.full = true else types["etymology-only"] = true end for t in gmatch(self._data.type, "[^,]+") do types[t] = true end self._types = types end return types end --[==[Given a list of types as strings, returns true if the language has all of them.]==] function Language:hasType(...) Language.hasType = require(language_like_module).hasType return self:hasType(...) end --[==[Returns a table containing <code>WikimediaLanguage</code> objects (see [[Module:wikimedia languages]]), which represent languages and their codes as they are used in Wikimedia projects for interwiki linking and such. More than one object may be returned, as a single Wiktionary language may correspond to multiple Wikimedia languages. For example, Wiktionary's single code <code>sh</code> (Serbo-Croatian) maps to four Wikimedia codes: <code>sh</code> (Serbo-Croatian), <code>bs</code> (Bosnian), <code>hr</code> (Croatian) and <code>sr</code> (Serbian). The code for the Wikimedia language is retrieved from the <code>wikimedia_codes</code> property in the data modules. If that property is not present, the code of the current language is used. If none of the available codes is actually a valid Wikimedia code, an empty table is returned.]==] function Language:getWikimediaLanguages() local wm_langs = self._wikimediaLanguageObjects if wm_langs == nil then local codes = self:getWikimediaLanguageCodes() wm_langs = {} for i = 1, #codes do wm_langs[i] = get_wikimedia_lang(codes[i]) end self._wikimediaLanguageObjects = wm_langs end return wm_langs end function Language:getWikimediaLanguageCodes() local wm_langs = self._wikimediaLanguageCodes if wm_langs == nil then wm_langs = self._data.wikimedia_codes if wm_langs then wm_langs = split(wm_langs, ",", true, true) else local code = self._code if is_known_language_tag(code) then wm_langs = {code} else -- Inherit, but only if no codes are specified in the data *and* -- the language code isn't a valid Wikimedia language code. local parent = self:getParent() wm_langs = parent and parent:getWikimediaLanguageCodes() or {} end end self._wikimediaLanguageCodes = wm_langs end return wm_langs end --[==[ Returns the name of the Wikipedia article for the language. `project` specifies the language and project to retrieve the article from, defaulting to {"enwiki"} for the English Wikipedia. Normally if specified it should be the project code for a specific-language Wikipedia e.g. "zhwiki" for the Chinese Wikipedia, but it can be any project, including non-Wikipedia ones. If the project is the English Wikipedia and the property {wikipedia_article} is present in the data module it will be used first. In all other cases, a sitelink will be generated from {:getWikidataItem} (if set). The resulting value (or lack of value) is cached so that subsequent calls are fast. If no value could be determined, and `noCategoryFallback` is {false}, {:getCategoryName} is used as fallback; otherwise, {nil} is returned. Note that if `noCategoryFallback` is {nil} or omitted, it defaults to {false} if the project is the English Wikipedia, otherwise to {true}. In other words, under normal circumstances, if the English Wikipedia article couldn't be retrieved, the return value will fall back to a link to the language's category, but this won't normally happen for any other project. ]==] function Language:getWikipediaArticle(noCategoryFallback, project) Language.getWikipediaArticle = require(language_like_module).getWikipediaArticle return self:getWikipediaArticle(noCategoryFallback, project) end function Language:makeWikipediaLink() return make_link(self, "w:" .. self:getWikipediaArticle(), self:getCanonicalName()) end --[==[Returns the name of the Wikimedia Commons category page for the language.]==] function Language:getCommonsCategory() Language.getCommonsCategory = require(language_like_module).getCommonsCategory return self:getCommonsCategory() end --[==[Returns the Wikidata item id for the language or <code>nil</code>. This corresponds to the the second field in the data modules.]==] function Language:getWikidataItem() Language.getWikidataItem = require(language_like_module).getWikidataItem return self:getWikidataItem() end --[==[Returns a table of <code>Script</code> objects for all scripts that the language is written in. See [[Module:scripts]].]==] function Language:getScripts() local scripts = self._scriptObjects if scripts == nil then local codes = self:getScriptCodes() if codes[1] == "All" then scripts = load_data(scripts_data_module) else scripts = {} for i = 1, #codes do scripts[i] = get_script(codes[i]) end end self._scriptObjects = scripts end return scripts end --[==[Returns the table of script codes in the language's data file.]==] function Language:getScriptCodes() local scripts = self._scriptCodes if scripts == nil then scripts = self._data[4] if scripts then local codes, n = {}, 0 for code in gmatch(scripts, "[^,]+") do n = n + 1 -- Special handling of "Hants", which represents "Hani", "Hant" and "Hans" collectively. if code == "Hants" then codes[n] = "Hani" codes[n + 1] = "Hant" codes[n + 2] = "Hans" n = n + 2 else codes[n] = code end end scripts = codes else scripts = {"None"} end self._scriptCodes = scripts end return scripts end --[==[Given some text, this function iterates through the scripts of a given language and tries to find the script that best matches the text. It returns a {{code|lua|Script}} object representing the script. If no match is found at all, it returns the {{code|lua|None}} script object.]==] function Language:findBestScript(text, forceDetect) if not text or text == "" or text == "-" then return get_script("None") end -- Differs from table returned by getScriptCodes, as Hants is not normalized into its constituents. local codes = self._bestScriptCodes if codes == nil then codes = self._data[4] codes = codes and split(codes, ",", true, true) or {"None"} self._bestScriptCodes = codes end local first_sc = codes[1] if first_sc == "All" then return find_best_script_without_lang(text) end local codes_len = #codes if not (forceDetect or first_sc == "Hants" or codes_len > 1) then first_sc = get_script(first_sc) local charset = first_sc.characters return charset and umatch(text, "[" .. charset .. "]") and first_sc or get_script("None") end -- Remove all formatting characters. text = get_plaintext(text) -- Remove all spaces and any ASCII punctuation. Some non-ASCII punctuation is script-specific, so can't be removed. text = ugsub(text, "[%s!\"#%%&'()*,%-./:;?@[\\%]_{}]+", "") if #text == 0 then return get_script("None") end -- Try to match every script against the text, -- and return the one with the most matching characters. local bestcount, bestscript, length = 0 for i = 1, codes_len do local sc = codes[i] -- Special case for "Hants", which is a special code that represents whichever of "Hant" or "Hans" best matches, or "Hani" if they match equally. This avoids having to list all three. In addition, "Hants" will be treated as the best match if there is at least one matching character, under the assumption that a Han script is desirable in terms that contain a mix of Han and other scripts (not counting those which use Jpan or Kore). if sc == "Hants" then local Hani = get_script("Hani") if not Hant_chars then Hant_chars = load_data("Module:zh/data/ts") Hans_chars = load_data("Module:zh/data/st") end local t, s, found = 0, 0 -- This is faster than using mw.ustring.gmatch directly. for ch in gmatch(ugsub(text, "[" .. Hani.characters .. "]", "\255%0"), "\255(.[\128-\191]*)") do found = true if Hant_chars[ch] then t = t + 1 if Hans_chars[ch] then s = s + 1 end elseif Hans_chars[ch] then s = s + 1 else t, s = t + 1, s + 1 end end if found then if t == s then return Hani end return get_script(t > s and "Hant" or "Hans") end else sc = get_script(sc) if not length then length = ulen(text) end -- Count characters by removing everything in the script's charset and comparing to the original length. local charset = sc.characters local count = charset and length - ulen(ugsub(text, "[" .. charset .. "]+", "")) or 0 if count >= length then return sc elseif count > bestcount then bestcount = count bestscript = sc end end end -- Return best matching script, or otherwise None. return bestscript or get_script("None") end --[==[Returns a <code>Family</code> object for the language family that the language belongs to. See [[Module:families]].]==] function Language:getFamily() local family = self._familyObject if family == nil then family = self:getFamilyCode() -- If the value is nil, it's cached as false. family = family and get_family(family) or false self._familyObject = family end return family or nil end --[==[Returns the family code in the language's data file.]==] function Language:getFamilyCode() local family = self._familyCode if family == nil then -- If the value is nil, it's cached as false. family = self._data[3] or false self._familyCode = family end return family or nil end function Language:getFamilyName() local family = self._familyName if family == nil then family = self:getFamily() -- If the value is nil, it's cached as false. family = family and family:getCanonicalName() or false self._familyName = family end return family or nil end do local function check_family(self, family) if type(family) == "table" then family = family:getCode() end if self:getFamilyCode() == family then return true end local self_family = self:getFamily() if self_family:inFamily(family) then return true -- If the family isn't a real family (e.g. creoles) check any ancestors. elseif self_family:inFamily("qfa-not") then local ancestors = self:getAncestors() for _, ancestor in ipairs(ancestors) do if ancestor:inFamily(family) then return true end end end end --[==[Check whether the language belongs to `family` (which can be a family code or object). A list of objects can be given in place of `family`; in that case, return true if the language belongs to any of the specified families. Note that some languages (in particular, certain creoles) can have multiple immediate ancestors potentially belonging to different families; in that case, return true if the language belongs to any of the specified families.]==] function Language:inFamily(...) if self:getFamilyCode() == nil then return false end return check_inputs(self, check_family, false, ...) end end function Language:getParent() local parent = self._parentObject if parent == nil then parent = self:getParentCode() -- If the value is nil, it's cached as false. parent = parent and get_by_code(parent, nil, true, true) or false self._parentObject = parent end return parent or nil end function Language:getParentCode() local parent = self._parentCode if parent == nil then -- If the value is nil, it's cached as false. parent = self._data.parent or false self._parentCode = parent end return parent or nil end function Language:getParentName() local parent = self._parentName if parent == nil then parent = self:getParent() -- If the value is nil, it's cached as false. parent = parent and parent:getCanonicalName() or false self._parentName = parent end return parent or nil end function Language:getParentChain() local chain = self._parentChain if chain == nil then chain = {} local parent, n = self:getParent(), 0 while parent do n = n + 1 chain[n] = parent parent = parent:getParent() end self._parentChain = chain end return chain end do local function check_lang(self, lang) for _, parent in ipairs(self:getParentChain()) do if (type(lang) == "string" and lang or lang:getCode()) == parent:getCode() then return true end end end function Language:hasParent(...) return check_inputs(self, check_lang, false, ...) end end --[==[ If the language is etymology-only, this iterates through parents until a full language or family is found, and the corresponding object is returned. If the language is a full language, then it simply returns itself. ]==] function Language:getFull() local full = self._fullObject if full == nil then full = self:getFullCode() full = full == self._code and self or get_by_code(full) self._fullObject = full end return full end --[==[ If the language is an etymology-only language, this iterates through parents until a full language or family is found, and the corresponding code is returned. If the language is a full language, then it simply returns the language code. ]==] function Language:getFullCode() return self._fullCode or self._code end --[==[ If the language is an etymology-only language, this iterates through parents until a full language or family is found, and the corresponding canonical name is returned. If the language is a full language, then it simply returns the canonical name of the language. ]==] function Language:getFullName() local full = self._fullName if full == nil then full = self:getFull():getCanonicalName() self._fullName = full end return full end --[==[Returns a table of <code class="nf">Language</code> objects for all languages that this language is directly descended from. Generally this is only a single language, but creoles, pidgins and mixed languages can have multiple ancestors.]==] function Language:getAncestors() local ancestors = self._ancestorObjects if ancestors == nil then ancestors = {} local ancestor_codes = self:getAncestorCodes() if #ancestor_codes > 0 then for _, ancestor in ipairs(ancestor_codes) do insert(ancestors, get_by_code(ancestor, nil, true)) end else local fam = self:getFamily() local protoLang = fam and fam:getProtoLanguage() or nil -- For the cases where the current language is the proto-language -- of its family, or an etymology-only language that is ancestral to that -- proto-language, we need to step up a level higher right from the -- start. if protoLang and ( protoLang:getCode() == self._code or (self:hasType("etymology-only") and protoLang:hasAncestor(self)) ) then fam = fam:getFamily() protoLang = fam and fam:getProtoLanguage() or nil end while not protoLang and not (not fam or fam:getCode() == "qfa-not") do fam = fam:getFamily() protoLang = fam and fam:getProtoLanguage() or nil end insert(ancestors, protoLang) end self._ancestorObjects = ancestors end return ancestors end do -- Avoid a language being its own ancestor via class inheritance. We only need to check for this if the language has inherited an ancestor table from its parent, because we never want to drop ancestors that have been explicitly set in the data. -- Recursively iterate over ancestors until we either find self or run out. If self is found, return true. local function check_ancestor(self, lang) local codes = lang:getAncestorCodes() if not codes then return nil end for i = 1, #codes do local code = codes[i] if code == self._code then return true end local anc = get_by_code(code, nil, true) if check_ancestor(self, anc) then return true end end end --[==[Returns a table of <code class="nf">Language</code> codes for all languages that this language is directly descended from. Generally this is only a single language, but creoles, pidgins and mixed languages can have multiple ancestors.]==] function Language:getAncestorCodes() if self._ancestorCodes then return self._ancestorCodes end local data = self._data local codes = data.ancestors if codes == nil then codes = {} self._ancestorCodes = codes return codes end codes = split(codes, ",", true, true) self._ancestorCodes = codes -- If there are no codes or the ancestors weren't inherited data, there's nothing left to check. if #codes == 0 or self:getData(false, "raw").ancestors ~= nil then return codes end local i, code = 1 while i <= #codes do code = codes[i] if check_ancestor(self, self) then remove(codes, i) else i = i + 1 end end return codes end end --[==[Given a list of language objects or codes, returns true if at least one of them is an ancestor. This includes any etymology-only children of that ancestor. If the language's ancestor(s) are etymology-only languages, it will also return true for those language parent(s) (e.g. if Vulgar Latin is the ancestor, it will also return true for its parent, Latin). However, a parent is excluded from this if the ancestor is also ancestral to that parent (e.g. if Classical Persian is the ancestor, Persian would return false, because Classical Persian is also ancestral to Persian).]==] function Language:hasAncestor(...) local function iterateOverAncestorTree(node, func, parent_check) local ancestors = node:getAncestors() local ancestorsParents = {} for _, ancestor in ipairs(ancestors) do local ret = func(ancestor) or iterateOverAncestorTree(ancestor, func, parent_check) if ret then return ret end end -- Check the parents of any ancestors. We don't do this if checking the parents of the other language, so that we exclude any etymology-only children of those parents that are not directly related (e.g. if the ancestor is Vulgar Latin and we are checking New Latin, we want it to return false because they are on different ancestral branches. As such, if we're already checking the parent of New Latin (Latin) we don't want to compare it to the parent of the ancestor (Latin), as this would be a false positive; it should be one or the other). if not parent_check then return nil end for _, ancestor in ipairs(ancestors) do local ancestorParents = ancestor:getParentChain() for _, ancestorParent in ipairs(ancestorParents) do if ancestorParent:getCode() == self._code or ancestorParent:hasAncestor(ancestor) then break else insert(ancestorsParents, ancestorParent) end end end for _, ancestorParent in ipairs(ancestorsParents) do local ret = func(ancestorParent) if ret then return ret end end end local function do_iteration(otherlang, parent_check) -- otherlang can't be self if (type(otherlang) == "string" and otherlang or otherlang:getCode()) == self._code then return false end repeat if iterateOverAncestorTree( self, function(ancestor) return ancestor:getCode() == (type(otherlang) == "string" and otherlang or otherlang:getCode()) end, parent_check ) then return true elseif type(otherlang) == "string" then otherlang = get_by_code(otherlang, nil, true) end otherlang = otherlang:getParent() parent_check = false until not otherlang end local parent_check = true for _, otherlang in ipairs{...} do local ret = do_iteration(otherlang, parent_check) if ret then return true end end return false end do local function construct_node(lang, memo) local branch, ancestors = {lang = lang:getCode()} memo[lang:getCode()] = branch for _, ancestor in ipairs(lang:getAncestors()) do if ancestors == nil then ancestors = {} end insert(ancestors, memo[ancestor:getCode()] or construct_node(ancestor, memo)) end branch.ancestors = ancestors return branch end function Language:getAncestorChain() local chain = self._ancestorChain if chain == nil then chain = construct_node(self, {}) self._ancestorChain = chain end return chain end end function Language:getAncestorChainOld() local chain = self._ancestorChain if chain == nil then chain = {} local step = self while true do local ancestors = step:getAncestors() step = #ancestors == 1 and ancestors[1] or nil if not step then break end insert(chain, step) end self._ancestorChain = chain end return chain end local function fetch_descendants(self, fmt) local descendants, family = {}, self:getFamily() -- Iterate over all three datasets. for _, data in ipairs{ require("Module:languages/code to canonical name"), require("Module:etymology languages/code to canonical name"), require("Module:families/code to canonical name"), } do for code in pairs(data) do local lang = get_by_code(code, nil, true, true) -- Test for a descendant. Earlier tests weed out most candidates, while the more intensive tests are only used sparingly. if ( code ~= self._code and -- Not self. lang:inFamily(family) and -- In the same family. ( family:getProtoLanguageCode() == self._code or -- Self is the protolanguage. self:hasDescendant(lang) or -- Full hasDescendant check. (lang:getFullCode() == self._code and not self:hasAncestor(lang)) -- Etymology-only child which isn't an ancestor. ) ) then if fmt == "object" then insert(descendants, lang) elseif fmt == "code" then insert(descendants, code) elseif fmt == "name" then insert(descendants, lang:getCanonicalName()) end end end end return descendants end function Language:getDescendants() local descendants = self._descendantObjects if descendants == nil then descendants = fetch_descendants(self, "object") self._descendantObjects = descendants end return descendants end function Language:getDescendantCodes() local descendants = self._descendantCodes if descendants == nil then descendants = fetch_descendants(self, "code") self._descendantCodes = descendants end return descendants end function Language:getDescendantNames() local descendants = self._descendantNames if descendants == nil then descendants = fetch_descendants(self, "name") self._descendantNames = descendants end return descendants end do local function check_lang(self, lang) if type(lang) == "string" then lang = get_by_code(lang, nil, true) end if lang:hasAncestor(self) then return true end end function Language:hasDescendant(...) return check_inputs(self, check_lang, false, ...) end end local function fetch_children(self, fmt) local m_etym_data = require(etymology_languages_data_module) local self_code, children = self._code, {} for code, lang in pairs(m_etym_data) do local _lang = lang repeat local parent = _lang.parent if parent == self_code then if fmt == "object" then insert(children, get_by_code(code, nil, true)) elseif fmt == "code" then insert(children, code) elseif fmt == "name" then insert(children, lang[1]) end break end _lang = m_etym_data[parent] until not _lang end return children end function Language:getChildren() local children = self._childObjects if children == nil then children = fetch_children(self, "object") self._childObjects = children end return children end function Language:getChildrenCodes() local children = self._childCodes if children == nil then children = fetch_children(self, "code") self._childCodes = children end return children end function Language:getChildrenNames() local children = self._childNames if children == nil then children = fetch_children(self, "name") self._childNames = children end return children end function Language:hasChild(...) local lang = ... if not lang then return false elseif type(lang) == "string" then lang = get_by_code(lang, nil, true) end if lang:hasParent(self) then return true end return self:hasChild(select(2, ...)) end --[==[Returns the name of the main category of that language. Example: {{code|lua|"French language"}} for French, whose category is at [[:Category:French language]]. Unless optional argument <code>nocap</code> is given, the language name at the beginning of the returned value will be capitalized. This capitalization is correct for category names, but not if the language name is lowercase and the returned value of this function is used in the middle of a sentence.]==] function Language:getCategoryName(nocap) local name = self._categoryName if name == nil then name = self:getCanonicalName() -- If a substrate, omit any leading article. if self:getFamilyCode() == "qfa-sub" then name = name:gsub("^ ", ""):gsub("^ ", "") end -- Only add " language" if a full language. if self:hasType("full") then -- Unless the canonical name already ends with "language", "lect" or their derivatives, add " language". if not (match(name, "[Rr]eo$") or match(name, "[Ll]ect$")) then name = "Reo" .. name end end self._categoryName = name end if nocap then return name end return mw.getContentLanguage():ucfirst(name) end --[==[Creates a link to the category; the link text is the canonical name.]==] function Language:makeCategoryLink() return make_link(self, ":Category:" .. self:getCategoryName(), self:getDisplayForm()) end function Language:getStandardCharacters(sc) local standard_chars = self._data.standardChars if type(standard_chars) ~= "table" then return standard_chars elseif sc and type(sc) ~= "string" then check_object("script", nil, sc) sc = sc:getCode() end if (not sc) or sc == "None" then local scripts = {} for _, script in pairs(standard_chars) do insert(scripts, script) end return concat(scripts) end if standard_chars[sc] then return standard_chars[sc] .. (standard_chars[1] or "") end end --[==[Make the entry name (i.e. the correct page name).]==] function Language:makeEntryName(text, sc) if (not text) or text == "" then return text, nil, {} end -- Set `unsupported` as true if certain conditions are met. local unsupported -- Check if there's an unsupported character. \239\191\189 is the replacement character U+FFFD, which can't be typed directly here due to an abuse filter. Unix-style dot-slash notation is also unsupported, as it is used for relative paths in links, as are 3 or more consecutive tildes. -- Note: match is faster with magic characters/charsets; find is faster with plaintext. if ( match(text, "[#<>%[%]_{|}]") or find(text, "\239\191\189") or match(text, "%f[^%z/]%.%.?%f[%z/]") or find(text, "~~~") ) then unsupported = true -- If it looks like an interwiki link. elseif find(text, ":") then local prefix = gsub(text, "^:*(.-):.*", ulower) if ( load_data("Module:data/namespaces")[prefix] or load_data("Module:data/interwikis")[prefix] ) then unsupported = true end end -- Check if the text is a listed unsupported title. local unsupportedTitles = load_data(links_data_module).unsupported_titles if unsupportedTitles[text] then return "Unsupported titles/" .. unsupportedTitles[text], nil, {} end sc = checkScript(text, self, sc) local fail, cats text = normalize(text, sc) text, fail, cats = iterateSectionSubstitutions(self, text, sc, nil, nil, self._data.entry_name, "makeEntryName") text = umatch(text, "^[¿¡]?(.-[^%s%p].-)%s*[؟?!;՛՜ ՞ ՟？！︖︕।॥။၊་།]?$") or text -- Escape unsupported characters so they can be used in titles. ` is used as a delimiter for this, so a raw use of it in an unsupported title is also escaped here to prevent interference; this is only done with unsupported titles, though, so inclusion won't in itself mean a title is treated as unsupported (which is why it's excluded from the earlier test). if unsupported then local unsupported_characters = load_data(links_data_module).unsupported_characters text = text:gsub("[#<>%[%]_`{|}\239]\191?\189?", unsupported_characters) :gsub("%f[^%z/]%.%.?%f[%z/]", function(m) return gsub(m, "%.", "`period`") end) :gsub("~~~+", function(m) return gsub(m, "~", "`tilde`") end) text = "Unsupported titles/" .. text end return text, fail, cats end --[==[Generates alternative forms using a specified method, and returns them as a table. If no method is specified, returns a table containing only the input term.]==] function Language:generateForms(text, sc) local generate_forms = self._data.generate_forms if generate_forms == nil then return {text} end sc = checkScript(text, self, sc) return require("Module:" .. self._data.generate_forms).generateForms(text, self, sc) end --[==[Creates a sort key for the given entry name, following the rules appropriate for the language. This removes diacritical marks from the entry name if they are not considered significant for sorting, and may perform some other changes. Any initial hyphen is also removed, and anything parentheses is removed as well. The <code>sort_key</code> setting for each language in the data modules defines the replacements made by this function, or it gives the name of the module that takes the entry name and returns a sortkey.]==] function Language:makeSortKey(text, sc) if (not text) or text == "" then return text, nil, {} end if match(text, "<[^<>]+>") then track("track HTML tag") end -- Remove directional characters, soft hyphens, strip markers and HTML tags. text = ugsub(text, "[\194\173\226\128\170-\226\128\174\226\129\166-\226\129\169]", "") text = gsub(unstrip(text), "<[^<>]+>", "") text = decode_uri(text, "PATH") text = checkNoEntities(self, text) -- Remove initial hyphens and * unless the term only consists of spacing + punctuation characters. text = ugsub(text, "^([􀀀-􏿽]*)[-־ـ᠊*]+([􀀀-􏿽]*)(.*[^%s%p].*)", "%1%2%3") sc = checkScript(text, self, sc) text = normalize(text, sc) text = removeCarets(text, sc) -- For languages with dotted dotless i, ensure that "İ" is sorted as "i", and "I" is sorted as "ı". if self:hasDottedDotlessI() then text = gsub(text, "I\204\135", "i") -- decomposed "İ" :gsub("I", "ı") text = sc:toFixedNFD(text) end -- Convert to lowercase, make the sortkey, then convert to uppercase. Where the language has dotted dotless i, it is usually not necessary to convert "i" to "İ" and "ı" to "I" first, because "I" will always be interpreted as conventional "I" (not dotless "İ") by any sorting algorithms, which will have been taken into account by the sortkey substitutions themselves. However, if no sortkey substitutions have been specified, then conversion is necessary so as to prevent "i" and "ı" both being sorted as "I". -- An exception is made for scripts that (sometimes) sort by scraping page content, as that means they are sensitive to changes in capitalization (as it changes the target page). local fail, cats if not sc:sortByScraping() then text = ulower(text) end local sort_key = self._data.sort_key text, fail, cats = iterateSectionSubstitutions(self, text, sc, nil, nil, sort_key, "makeSortKey") if not sc:sortByScraping() then if self:hasDottedDotlessI() and not sort_key then text = gsub(gsub(text, "ı", "I"), "i", "İ") text = sc:toFixedNFC(text) end text = uupper(text) end -- Remove parentheses, as long as they are either preceded or followed by something. text = gsub(text, "(.)[()]+", "%1") :gsub("[()]+(.)", "%1") text = escape_risky_characters(text) return text, fail, cats end --[==[Create the form used as as a basis for display text and transliteration.]==] local function processDisplayText(text, self, sc, keepCarets, keepPrefixes) local subbedChars = {} text, subbedChars = doTempSubstitutions(text, subbedChars, keepCarets) text = decode_uri(text, "PATH") text = checkNoEntities(self, text) sc = checkScript(text, self, sc) local fail, cats text = normalize(text, sc) text, fail, cats, subbedChars = iterateSectionSubstitutions(self, text, sc, subbedChars, keepCarets, self._data.display_text, "makeDisplayText") text = removeCarets(text, sc) -- Remove any interwiki link prefixes (unless they have been escaped or this has been disabled). if find(text, ":") and not keepPrefixes then local rep repeat text, rep = gsub(text, "\\\\(\\*:)", "\3%1") until rep == 0 text = gsub(text, "\\:", "\4") while true do local prefix = gsub(text, "^(.-):.+", function(m1) return gsub(m1, "\244[\128-\191]*", "") end) -- Check if the prefix is an interwiki, though ignore capitalised Wiktionary:, which is a namespace. if not prefix or prefix == text or prefix == "Wiktionary" or not (load_data("Module:data/interwikis")[ulower(prefix)] or prefix == "") then break end text = gsub(text, "^(.-):(.*)", function(m1, m2) local ret = {} for subbedChar in gmatch(m1, "\244[\128-\191]*") do insert(ret, subbedChar) end return concat(ret) .. m2 end) end text = gsub(text, "\3", "\\") :gsub("\4", ":") end return text, fail, cats, subbedChars end --[==[Make the display text (i.e. what is displayed on the page).]==] function Language:makeDisplayText(text, sc, keepPrefixes) if (not text) or text == "" then return text, nil, {} end local fail, cats, subbedChars text, fail, cats, subbedChars = processDisplayText(text, self, sc, nil, keepPrefixes) text = escape_risky_characters(text) return undoTempSubstitutions(text, subbedChars), fail, cats end --[==[Transliterates the text from the given script into the Latin script (see [[Wiktionary:Transliteration and romanization]]). The language must have the <code>translit</code> property for this to work; if it is not present, {{code|lua|nil}} is returned. Returns three values: # The transliteration. # A boolean which indicates whether the transliteration failed for an unexpected reason. If {{code|lua|false}}, then the transliteration either succeeded, or the module is returning nothing in a controlled way (e.g. the input was {{code|lua|"-"}}). Generally, this means that no maintenance action is required. If {{code|lua|true}}, then the transliteration is {{code|lua|nil}} because either the input or output was defective in some way (e.g. [[Module:ar-translit]] will not transliterate non-vocalised inputs, and this module will fail partially-completed transliterations in all languages). Note that this value can be manually set by the transliteration module, so make sure to cross-check to ensure it is accurate. # A table of categories selected by the transliteration module, which should be in the format expected by {{code|lua|format_categories}} in [[Module:utilities]]. The <code>sc</code> parameter is handled by the transliteration module, and how it is handled is specific to that module. Some transliteration modules may tolerate {{code|lua|nil}} as the script, others require it to be one of the possible scripts that the module can transliterate, and will show an error if it's not one of them. For this reason, the <code>sc</code> parameter should always be provided when writing non-language-specific code. The <code>module_override</code> parameter is used to override the default module that is used to provide the transliteration. This is useful in cases where you need to demonstrate a particular module in use, but there is no default module yet, or you want to demonstrate an alternative version of a transliteration module before making it official. It should not be used in real modules or templates, only for testing. All uses of this parameter are tracked by [[Wiktionary:Tracking/languages/module_override]]. '''Known bugs''': * This function assumes {tr(s1) .. tr(s2) == tr(s1 .. s2)}. When this assertion fails, wikitext markups like <nowiki>'''</nowiki> can cause wrong transliterations. * HTML entities like <code>&amp;apos;</code>, often used to escape wikitext markups, do not work.]==] function Language:transliterate(text, sc, module_override) -- If there is no text, or the language doesn't have transliteration data and there's no override, return nil. if not (self._data.translit or module_override) then return nil, false, {} elseif (not text) or text == "" or text == "-" then return text, false, {} end -- If the script is not transliteratable (and no override is given), return nil. sc = checkScript(text, self, sc) if not (sc:isTransliterated() or module_override) then -- temporary tracking to see if/when this gets triggered track("non-transliterable") track("non-transliterable/" .. self._code) track("non-transliterable/" .. sc:getCode()) track("non-transliterable/" .. sc:getCode() .. "/" .. self._code) return nil, true, {} end -- Remove any strip markers. text = unstrip(text) -- Do not process the formatting into PUA characters for certain languages. local processed = load_data(languages_data_module).substitution[self._code] ~= "none" -- Get the display text with the keepCarets flag set. local fail, cats, subbedChars if processed then text, fail, cats, subbedChars = processDisplayText(text, self, sc, true) end -- Transliterate (using the module override if applicable). text, fail, cats, subbedChars = iterateSectionSubstitutions(self, text, sc, subbedChars, true, module_override or self._data.translit, "tr") if not text then return nil, true, cats end -- Incomplete transliterations return nil. local charset = sc.characters if charset and umatch(text, "[" .. charset .. "]") then -- Remove any characters in Latin, which includes Latin characters also included in other scripts (as these are false positives), as well as any PUA substitutions. Anything remaining should only be script code "None" (e.g. numerals). local check_text = ugsub(text, "[" .. get_script("Latn").characters .. "􀀀-􏿽]+", "") -- Set none_is_last_resort_only flag, so that any non-None chars will cause a script other than "None" to be returned. if find_best_script_without_lang(check_text, true):getCode() ~= "None" then return nil, true, cats end end if processed then text = escape_risky_characters(text) text = undoTempSubstitutions(text, subbedChars) end -- If the script does not use capitalization, then capitalize any letters of the transliteration which are immediately preceded by a caret (and remove the caret). if text and not sc:hasCapitalization() and text:find("^", 1, true) then text = processCarets(text, "%^([\128-\191\244]*%*?)([^\128-\191\244][\128-\191]*)", function(m1, m2) return m1 .. uupper(m2) end) end -- Track module overrides. if module_override ~= nil then track("module_override") end fail = text == nil and (not not fail) or false return text, fail, cats end do local function handle_language_spec(self, spec, sc) local ret = self["_" .. spec] if ret == nil then ret = self._data[spec] if type(ret) == "string" then ret = list_to_set(split(ret, ",", true, true)) end self["_" .. spec] = ret end if type(ret) == "table" then ret = ret[sc:getCode()] end return not not ret end function Language:overrideManualTranslit(sc) return handle_language_spec(self, "override_translit", sc) end function Language:link_tr(sc) return handle_language_spec(self, "link_tr", sc) end end --[==[Returns {{code|lua|true}} if the language has a transliteration module, or {{code|lua|false}} if it doesn't.]==] function Language:hasTranslit() return not not self._data.translit end --[==[Returns {{code|lua|true}} if the language uses the letters I/ı and İ/i, or {{code|lua|false}} if it doesn't.]==] function Language:hasDottedDotlessI() return not not self._data.dotted_dotless_i end function Language:toJSON(opts) local entry_name, entry_name_patterns, entry_name_remove_diacritics = self._data.entry_name if entry_name then if entry_name.from then entry_name_patterns = {} for i, from in ipairs(entry_name.from) do insert(entry_name_patterns, {from = from, to = entry_name.to[i] or ""}) end end entry_name_remove_diacritics = entry_name.remove_diacritics end -- mainCode should only end up non-nil if dontCanonicalizeAliases is passed to make_object(). local ret = { ancestors = self:getAncestorCodes(), canonicalName = self:getCanonicalName(), categoryName = self:getCategoryName("nocap"), code = self._code, mainCode = self._mainCode, parent = self:getParentCode(), full = self:getFullCode(), entryNamePatterns = entry_name_patterns, entryNameRemoveDiacritics = entry_name_remove_diacritics, family = self:getFamilyCode(), aliases = self:getAliases(), varieties = self:getVarieties(), otherNames = self:getOtherNames(), scripts = self:getScriptCodes(), type = keys_to_list(self:getTypes()), wikimediaLanguages = self:getWikimediaLanguageCodes(), wikidataItem = self:getWikidataItem(), wikipediaArticle = self:getWikipediaArticle(true), } -- Use `deep_copy` when returning a table, so that there are no editing restrictions imposed by `mw.loadData`. return opts and opts.lua_table and deep_copy(ret) or to_json(ret, opts) end function export.getDataModuleName(code) local letter = match(code, "^(%l)%l%l?$") return "Module:" .. ( letter == nil and "languages/data/exceptional" or #code == 2 and "languages/data/2" or "languages/data/3/" .. letter ) end get_data_module_name = export.getDataModuleName function export.getExtraDataModuleName(code) return get_data_module_name(code) .. "/extra" end get_extra_data_module_name = export.getExtraDataModuleName do local function make_stack(data) local key_types = { [2] = "unique", aliases = "unique", otherNames = "unique", type = "append", varieties = "unique", wikipedia_article = "unique", wikimedia_codes = "unique" } local function __index(self, k) local stack, key_type = getmetatable(self), key_types[k] -- Data that isn't inherited from the parent. if key_type == "unique" then local v = stack[stack[make_stack]][k] if v == nil then local layer = stack[0] if layer then -- Could be false if there's no extra data. v = layer[k] end end return v -- Data that is appended by each generation. elseif key_type == "append" then local parts, offset, n = {}, 0, stack[make_stack] for i = 1, n do local part = stack[i][k] if part == nil then offset = offset + 1 else parts[i - offset] = part end end return offset ~= n and concat(parts, ",") or nil end local n = stack[make_stack] while true do local layer = stack[n] if not layer then -- Could be false if there's no extra data. return nil end local v = layer[k] if v ~= nil then return v end n = n - 1 end end local function __newindex() error("table is read-only") end local function __pairs(self) -- Iterate down the stack, caching keys to avoid duplicate returns. local stack, seen = getmetatable(self), {} local n = stack[make_stack] local iter, state, k, v = pairs(stack[n]) return function() repeat repeat k = iter(state, k) if k == nil then n = n - 1 local layer = stack[n] if not layer then -- Could be false if there's no extra data. return nil end iter, state, k = pairs(layer) end until not (k == nil or seen[k]) -- Get the value via a lookup, as the one returned by the -- iterator will be the raw value from the current layer, -- which may not be the one __index will return for that -- key. Also memoize the key in `seen` (even if the lookup -- returns nil) so that it doesn't get looked up again. -- TODO: store values in `self`, avoiding the need to create -- the `seen` table. The iterator will need to iterate over -- `self` with `next` first to find these on future loops. v, seen[k] = self[k], true until v ~= nil return k, v end end local __ipairs = require(table_module).indexIpairs function make_stack(data) local stack = { data, [make_stack] = 1, -- stores the length and acts as a sentinel to confirm a given metatable is a stack. __index = __index, __newindex = __newindex, __pairs = __pairs, __ipairs = __ipairs, } stack.__metatable = stack return setmetatable({}, stack), stack end return make_stack(data) end local function get_stack(data) local stack = getmetatable(data) return stack and type(stack) == "table" and stack[make_stack] and stack or nil end --[==[ <span style="color: #BA0000">This function is not for use in entries or other content pages.</span> Returns a blob of data about the language. The format of this blob is undocumented, and perhaps unstable; it's intended for things like the module's own unit-tests, which are "close friends" with the module and will be kept up-to-date as the format changes. If `extra` is set, any extra data in the relevant `/extra` module will be included. (Note that it will be included anyway if it has already been loaded into the language object.) If `raw` is set, then the returned data will not contain any data inherited from parent objects. -- Do NOT use these methods! -- All uses should be pre-approved on the talk page! ]==] function Language:getData(extra, raw) if extra then self:loadInExtraData() end local data = self._data -- If raw is not set, just return the data. if not raw then return data end local stack = get_stack(data) -- If there isn't a stack or its length is 1, return the data. Extra data (if any) will be included, as it's stored at key 0 and doesn't affect the reported length. if stack == nil then return data end local n = stack[make_stack] if n == 1 then return data end local extra = stack[0] -- If there isn't any extra data, return the top layer of the stack. if extra == nil then return stack[n] end -- If there is, return a new stack which has the top layer at key 1 and the extra data at key 0. data, stack = make_stack(stack[n]) stack[0] = extra return data end function Language:loadInExtraData() -- Only full languages have extra data. if not self:hasType("language", "full") then return end local data = self._data -- If there's no stack, create one. local stack = get_stack(self._data) if stack == nil then data, stack = make_stack(data) -- If already loaded, return. elseif stack[0] ~= nil then return end self._data = data -- Load extra data from the relevant module and add it to the stack at key 0, so that the __index and __pairs metamethods will pick it up, since they iterate down the stack until they run out of layers. local code = self._code local modulename = get_extra_data_module_name(code) -- No data cached as false. stack[0] = modulename and load_data(modulename)[code] or false end --[==[Returns the name of the module containing the language's data. Currently, this is always [[Module:scripts/data]].]==] function Language:getDataModuleName() local name = self._dataModuleName if name == nil then name = self:hasType("etymology-only") and etymology_languages_data_module or get_data_module_name(self._mainCode or self._code) self._dataModuleName = name end return name end --[==[Returns the name of the module containing the language's data. Currently, this is always [[Module:scripts/data]].]==] function Language:getExtraDataModuleName() local name = self._extraDataModuleName if name == nil then name = not self:hasType("etymology-only") and get_extra_data_module_name(self._mainCode or self._code) or false self._extraDataModuleName = name end return name or nil end function export.makeObject(code, data, dontCanonicalizeAliases) local data_type = type(data) if data_type ~= "table" then error(("bad argument #2 to 'makeObject' (table expected, got %s)"):format(data_type)) end -- Convert any aliases. local input_code = code code = normalize_code(code) input_code = dontCanonicalizeAliases and input_code or code local parent if data.parent then parent = get_by_code(data.parent, nil, true, true) else parent = Language end parent.__index = parent local lang = {_code = input_code} -- This can only happen if dontCanonicalizeAliases is passed to make_object(). if code ~= input_code then lang._mainCode = code end local parent_data = parent._data if parent_data == nil then -- Full code is the same as the code. lang._fullCode = parent._code or code else -- Copy full code. lang._fullCode = parent._fullCode local stack = get_stack(parent_data) if stack == nil then parent_data, stack = make_stack(parent_data) end -- Insert the input data as the new top layer of the stack. local n = stack[make_stack] + 1 data, stack[n], stack[make_stack] = parent_data, data, n end lang._data = data return setmetatable(lang, parent) end make_object = export.makeObject end --[==[Finds the language whose code matches the one provided. If it exists, it returns a <code class="nf">Language</code> object representing the language. Otherwise, it returns {{code|lua|nil}}, unless <code class="n">paramForError</code> is given, in which case an error is generated. If <code class="n">paramForError</code> is {{code|lua|true}}, a generic error message mentioning the bad code is generated; otherwise <code class="n">paramForError</code> should be a string or number specifying the parameter that the code came from, and this parameter will be mentioned in the error message along with the bad code. If <code class="n">allowEtymLang</code> is specified, etymology-only language codes are allowed and looked up along with normal language codes. If <code class="n">allowFamily</code> is specified, language family codes are allowed and looked up along with normal language codes.]==] function export.getByCode(code, paramForError, allowEtymLang, allowFamily) -- Track uses of paramForError, ultimately so it can be removed, as error-handling should be done by [[Module:parameters]], not here. if paramForError ~= nil then track("paramForError") end if type(code) ~= "string" then local typ if not code then typ = "nil" elseif check_object("language", true, code) then typ = "a language object" elseif check_object("family", true, code) then typ = "a family object" else typ = "a " .. type(code) end error("The function getByCode expects a string as its first argument, but received " .. typ .. ".") end local m_data = load_data(languages_data_module) if m_data.aliases[code] or m_data.track[code] then track(code) end local norm_code = normalize_code(code) -- Get the data, checking for etymology-only languages if allowEtymLang is set. local data = load_data(get_data_module_name(norm_code))[norm_code] or allowEtymLang and load_data(etymology_languages_data_module)[norm_code] -- If no data was found and allowFamily is set, check the family data. If the main family data was found, make the object with [[Module:families]] instead, as family objects have different methods. However, if it's an etymology-only family, use make_object in this module (which handles object inheritance), and the family-specific methods will be inherited from the parent object. if data == nil and allowFamily then data = load_data("Module:families/data")[norm_code] if data ~= nil then if data.parent == nil then return make_family_object(norm_code, data) elseif not allowEtymLang then data = nil end end end local retval = code and data and make_object(code, data) if not retval and paramForError then require("Module:languages/errorGetBy").code(code, paramForError, allowEtymLang, allowFamily) end return retval end get_by_code = export.getByCode --[==[Finds the language whose canonical name (the name used to represent that language on Wiktionary) or other name matches the one provided. If it exists, it returns a <code class="nf">Language</code> object representing the language. Otherwise, it returns {{code|lua|nil}}, unless <code class="n">paramForError</code> is given, in which case an error is generated. If <code class="n">allowEtymLang</code> is specified, etymology-only language codes are allowed and looked up along with normal language codes. If <code class="n">allowFamily</code> is specified, language family codes are allowed and looked up along with normal language codes. The canonical name of languages should always be unique (it is an error for two languages on Wiktionary to share the same canonical name), so this is guaranteed to give at most one result. This function is powered by [[Module:languages/canonical names]], which contains a pre-generated mapping of full-language canonical names to codes. It is generated by going through the [[:Category:Language data modules]] for full languages. When <code class="n">allowEtymLang</code> is specified for the above function, [[Module:etymology languages/canonical names]] may also be used, and when <code class="n">allowFamily</code> is specified for the above function, [[Module:families/canonical names]] may also be used.]==] function export.getByCanonicalName(name, errorIfInvalid, allowEtymLang, allowFamily) local byName = load_data("Module:languages/canonical names") local code = byName and byName[name] if not code and allowEtymLang then byName = load_data("Module:etymology languages/canonical names") code = byName and byName[name] or byName[gsub(name, " [Ss]ubstrate$", "")] or byName[gsub(name, "^a ", "")] or byName[gsub(name, "^a ", ""):gsub(" [Ss]ubstrate$", "")] or -- For etymology families like "ira-pro". -- FIXME: This is not ideal, as it allows " languages" to be appended to any etymology-only language, too. byName[match(name, "^(.*) languages$")] end if not code and allowFamily then byName = load_data("Module:families/canonical names") code = byName[name] or byName[match(name, "^(.*) languages$")] end local retval = code and get_by_code(code, errorIfInvalid, allowEtymLang, allowFamily) if not retval and errorIfInvalid then require("Module:languages/errorGetBy").canonicalName(name, allowEtymLang, allowFamily) end return retval end --[==[Used by [[Module:languages/data/2]] (et al.) and [[Module:etymology languages/data]], [[Module:families/data]], [[Module:scripts/data]] and [[Module:writing systems/data]] to finalize the data into the format that is actually returned.]==] function export.finalizeData(data, main_type, variety) local fields = {"type"} if main_type == "language" then insert(fields, 4) -- script codes insert(fields, "ancestors") insert(fields, "link_tr") insert(fields, "override_translit") insert(fields, "wikimedia_codes") elseif main_type == "script" then insert(fields, 3) -- writing system codes end -- Families and writing systems have no extra fields to process. local fields_len = #fields for _, entity in next, data do if variety then -- Move parent from 3 to "parent" and family from "family" to 3. These are different for the sake of convenience, since very few varieties have the family specified, whereas all of them have a parent. entity.parent, entity[3], entity.family = entity[3], entity.family -- Give the type "regular" iff not a variety and no other types are assigned. elseif not (entity.type or entity.parent) then entity.type = "regular" end for i = 1, fields_len do local key = fields[i] local field = entity[key] if field and type(field) == "string" then entity[key] = gsub(field, "%s*,%s*", ",") end end end return data end --[==[For backwards compatibility only; modules should require the error themselves.]==] function export.err(lang_code, param, code_desc, template_tag, not_real_lang) return require("Module:languages/error")(lang_code, param, code_desc, template_tag, not_real_lang) end return export 75xk9yo1imdifdldjf0oz87cps9ioxq 17456 17394 2026-07-13T08:55:16Z Hiyuune 6766 17456 Scribunto text/plain --[=[ This module implements fetching of language-specific information and processing text in a given language. There are two types of languages: full languages and etymology-only languages. The essential difference is that only full languages appear in L2 headings in vocabulary entries, and hence categories like [[:Category:French nouns]] exist only for full languages. Etymology-only languages have either a full language or another etymology-only language as their parent (in the parent-child inheritance sense), and for etymology-only languages with another etymology-only language as their parent, a full language can always be derived by following the parent links upwards. For example, "Canadian French", code 'fr-CA', is an etymology-only language whose parent is the full language "French", code 'fr'. An example of an etymology-only language with another etymology-only parent is "Northumbrian Old English", code 'ang-nor', which has "Anglian Old English", code 'ang-ang' as its parent; this is an etymology-only language whose parent is "Old English", code "ang", which is a full language. (This is because Northumbrian Old English is considered a variety of Anglian Old English.) Sometimes the parent is the "Undetermined" language, code 'und'; this is the case, for example, for "substrate" languages such as "Pre-Greek", code 'qsb-grc', and "the BMAC substrate", code 'qsb-bma'. It is important to distinguish language ''parents'' from language ''ancestors''. The parent-child relationship is one of containment, i.e. if X is a child of Y, X is considered a variety of Y. On the other hand, the ancestor-descendant relationship is one of descent in time. For example, "Classical Latin", code 'la-cla', and "Late Latin", code 'la-lat', are both etymology-only languages with "Latin", code 'la', as their parents, because both of the former are varieties of Latin. However, Late Latin does *NOT* have Classical Latin as its parent because Late Latin is *not* a variety of Classical Latin; rather, it is a descendant. There is in fact a separate 'ancestors' field that is used to express the ancestor-descendant relationship, and Late Latin's ancestor is given as Classical Latin. It is also important to note that sometimes an etymology-only language is actually the conceptual ancestor of its parent language. This happens, for example, with "Old Italian" (code 'roa-oit'), which is an etymology-only variant of full language "Italian" (code 'it'), and with "Old Latin" (code 'itc-ola'), which is an etymology-only variant of Latin. In both cases, the full language has the etymology-only variant listed as an ancestor. This allows a Latin term to inherit from Old Latin using the {{tl|inh}} template (where in this template, "inheritance" refers to ancestral inheritance, i.e. inheritance in time, rather than in the parent-child sense); likewise for Italian and Old Italian. Full languages come in three subtypes: * {regular}: This indicates a full language that is attested according to [[WT:CFI]] and therefore permitted in the main namespace. There may also be reconstructed terms for the language, which are placed in the {Reconstruction} namespace and must be prefixed with * to indicate a reconstruction. Most full languages are natural (not constructed) languages, but a few constructed languages (e.g. Esperanto and Volapük, among others) are also allowed in the mainspace and considered regular languages. * {reconstructed}: This language is not attested according to [[WT:CFI]], and therefore is allowed only in the {Reconstruction} namespace. All terms in this language are reconstructed, and must be prefixed with *. Languages such as Proto-Indo-European and Proto-Germanic are in this category. * {appendix-constructed}: This language is attested but does not meet the additional requirements set out for constructed languages ([[WT:CFI#Constructed languages]]). Its entries must therefore be in the Appendix namespace, but they are not reconstructed and therefore should not have * prefixed in links. Most constructed languages are of this subtype. Both full languages and etymology-only languages have a {Language} object associated with them, which is fetched using the {getByCode} function in [[Module:languages]] to convert a language code to a {Language} object. Depending on the options supplied to this function, etymology-only languages may or may not be accepted, and family codes may be accepted (returning a {Family} object as described in [[Module:families]]). There are also separate {getByCanonicalName} functions in [[Module:languages]] and [[Module:etymology languages]] to convert a language's canonical name to a {Language} object (depending on whether the canonical name refers to a full or etymology-only language). Textual strings belonging to a given language come in several different ''text variants'': # The ''input text'' is what the user supplies in wikitext, in the parameters to {{tl|m}}, {{tl|l}}, {{tl|ux}}, {{tl|t}}, {{tl|lang}} and the like. # The ''display text'' is the text in the form as it will be displayed to the user. This can include accent marks that are stripped to form the entry text (see below), as well as embedded bracketed links that are variously processed further. The display text is generated from the input text by applying language-specific transformations; for most languages, there will be no such transformations. Examples of transformations are bad-character replacements for certain languages (e.g. replacing 'l' or '1' to [[palochka]] in certain languages in Cyrillic); and for Thai and Khmer, converting space-separated words to bracketed words and resolving respelling substitutions such as [กรีน/กฺรีน], which indicate how to transliterate given words. # The ''entry text'' is the text in the form used to generate a link to a Wiktionary entry. This is usually generated from the display text by stripping certain sorts of diacritics on a per-language basis, and sometimes doing other transformations. The concept of ''entry text'' only really makes sense for text that does not contain embedded links, meaning that display text containing embedded links will need to have the links individually processed to get per-link entry text in order to generate the resolved display text (see below). # The ''resolved display text'' is the result of resolving embedded links in the display text (e.g. converting them to two-part links where the first part has entry-text transformations applied, and adding appropriate language-specific fragments) and adding appropriate language and script tagging. This text can be passed directly to MediaWiki for display. # The ''source translit text'' is the text as supplied to the language-specific {transliterate()} method. The form of the source translit text may need to be language-specific, e.g Thai and Khmer will need the full unprocessed input text, whereas other languages may need to work off the display text. [FIXME: It's still unclear to me how embedded bracketed links are handled in the existing code.] In general, embedded links need to be removed (i.e. converted to their "bare display" form by taking the right part of two-part links and removing double brackets), but when this happens is unclear to me [FIXME]. Some languages have a chop-up-and-paste-together scheme that sends parts of the text through the transliterate mechanism, and for others (those listed with "cont" in {substition} in [[Module:languages/data]]) they receive the full input text, but preprocessed in certain ways. (The wisdom of this is still unclear to me.) # The ''transliterated text'' (or ''transliteration'') is the result of transliterating the source translit text. Unlike for all the other text variants except the transcribed text, it is always in the Latin script. # The ''transcribed text'' (or ''transcription'') is the result of transcribing the source translit text, where "transcription" here means a close approximation to the phonetic form of the language in languages (e.g. Akkadian, Sumerian, Ancient Egyptian, maybe Tibetan) that have a wide difference between the written letters and spoken form. Unlike for all the other text variants other than the transliterated text, it is always in the Latin script. Currently, the transcribed text is always supplied manually be the user; there is no such thing as a {lua|transcribe()} method on language objects. # The ''sort key'' is the text used in sort keys for determining the placing of pages in categories they belong to. The sort key is generated from the pagename or a specified ''sort base'' by lowercasing, doing language-specific transformations and then uppercasing the result. If the sort base is supplied and is generated from input text, it needs to be converted to display text, have embedded links removed (i.e. resolving them to their right side if they are two-part links) and have entry text transformations applied. # There are other text variants that occur in usexes (specifically, there are normalized variants of several of the above text variants), but we can skip them for now. The following methods exist on {Language} objects to convert between different text variants: # {makeDisplayText}: This converts input text to display text. # {lua|makeEntryName}: This converts input or display text to entry text. [FIXME: This needs some rethinking. In particular, {lua|makeEntryName} is sometimes called on display text (in some paths inside of [[Module:links]]) and sometimes called on input text (in other paths inside of [[Module:links]], and usually from other modules). We need to make sure we don't try to convert input text to display text twice, but at the same time we need to support calling it directly on input text since so many modules do this. This means we need to add a parameter indicating whether the passed-in text is input or display text; if that former, we call {lua|makeDisplayText} ourselves.] # {lua|transliterate}: This appears to convert input text with embedded brackets removed into a transliteration. [FIXME: This needs some rethinking. In particular, it calls {lua|processDisplayText} on its input, which won't work for Thai and Khmer, so we may need language-specific flags indicating whether to pass the input text directly to the language transliterate method. In addition, I'm not sure how embedded links are handled in the existing translit code; a lot of callers remove the links themselves before calling {lua|transliterate()}, which I assume is wrong.] # {lua|makeSortKey}: This converts entry text (?) to a sort key. [FIXME: Clarify this.] ]=] local export = {} local debug_track_module = "Module:debug/track" local etymology_languages_data_module = "Module:etymology languages/data" local families_module = "Module:families" local json_module = "Module:JSON" local language_like_module = "Module:language-like" local languages_data_module = "Module:languages/data" local languages_data_patterns_module = "Module:languages/data/patterns" local links_data_module = "Module:links/data" local load_module = "Module:load" local scripts_module = "Module:scripts" local scripts_data_module = "Module:scripts/data" local string_encode_entities_module = "Module:string/encode entities" local string_pattern_escape_module = "Module:string/patternEscape" local string_replacement_escape_module = "Module:string/replacementEscape" local string_utilities_module = "Module:string utilities" local table_module = "Module:table" local utilities_module = "Module:utilities" local wikimedia_languages_module = "Module:wikimedia languages" local mw = mw local string = string local table = table local char = string.char local concat = table.concat local find = string.find local floor = math.floor local get_by_code -- Defined below. local get_data_module_name -- Defined below. local get_extra_data_module_name -- Defined below. local getmetatable = getmetatable local gmatch = string.gmatch local gsub = string.gsub local insert = table.insert local ipairs = ipairs local is_known_language_tag = mw.language.isKnownLanguageTag local make_object -- Defined below. local match = string.match local next = next local pairs = pairs local remove = table.remove local require = require local select = select local setmetatable = setmetatable local sub = string.sub local type = type local unstrip = mw.text.unstrip -- Loaded as needed by findBestScript. local Hans_chars local Hant_chars local function check_object(...) check_object = require(utilities_module).check_object return check_object(...) end local function debug_track(...) debug_track = require(debug_track_module) return debug_track(...) end local function decode_entities(...) decode_entities = require(string_utilities_module).decode_entities return decode_entities(...) end local function decode_uri(...) decode_uri = require(string_utilities_module).decode_uri return decode_uri(...) end local function deep_copy(...) deep_copy = require(table_module).deepCopy return deep_copy(...) end local function encode_entities(...) encode_entities = require(string_encode_entities_module) return encode_entities(...) end local function get_script(...) get_script = require(scripts_module).getByCode return get_script(...) end local function find_best_script_without_lang(...) find_best_script_without_lang = require(scripts_module).findBestScriptWithoutLang return find_best_script_without_lang(...) end local function get_family(...) get_family = require(families_module).getByCode return get_family(...) end local function get_plaintext(...) get_plaintext = require(utilities_module).get_plaintext return get_plaintext(...) end local function get_wikimedia_lang(...) get_wikimedia_lang = require(wikimedia_languages_module).getByCode return get_wikimedia_lang(...) end local function keys_to_list(...) keys_to_list = require(table_module).keysToList return keys_to_list(...) end local function list_to_set(...) list_to_set = require(table_module).listToSet return list_to_set(...) end local function load_data(...) load_data = require(load_module).load_data return load_data(...) end local function make_family_object(...) make_family_object = require(families_module).makeObject return make_family_object(...) end local function pattern_escape(...) pattern_escape = require(string_pattern_escape_module) return pattern_escape(...) end local function remove_duplicates(...) remove_duplicates = require(table_module).removeDuplicates return remove_duplicates(...) end local function replacement_escape(...) replacement_escape = require(string_replacement_escape_module) return replacement_escape(...) end local function safe_require(...) safe_require = require(load_module).safe_require return safe_require(...) end local function shallow_copy(...) shallow_copy = require(table_module).shallowCopy return shallow_copy(...) end local function split(...) split = require(string_utilities_module).split return split(...) end local function to_json(...) to_json = require(json_module).toJSON return to_json(...) end local function u(...) u = require(string_utilities_module).char return u(...) end local function ugsub(...) ugsub = require(string_utilities_module).gsub return ugsub(...) end local function ulen(...) ulen = require(string_utilities_module).len return ulen(...) end local function ulower(...) ulower = require(string_utilities_module).lower return ulower(...) end local function umatch(...) umatch = require(string_utilities_module).match return umatch(...) end local function uupper(...) uupper = require(string_utilities_module).upper return uupper(...) end local function track(page) debug_track("languages/" .. page) return true end local function normalize_code(code) return load_data(languages_data_module).aliases[code] or code end local function check_inputs(self, check, default, ...) local n = select("#", ...) if n == 0 then return false end local ret = check(self, (...)) if ret ~= nil then return ret elseif n > 1 then local inputs = {...} for i = 2, n do ret = check(self, inputs[i]) if ret ~= nil then return ret end end end return default end local function make_link(self, target, display) local prefix, main if self:getFamilyCode() == "qfa-sub" then prefix, main = display:match("^(the )(.*)") if not prefix then prefix, main = display:match("^(a )(.*)") end end return (prefix or "") .. "[[" .. target .. "|" .. (main or display) .. "]]" end -- Convert risky characters to HTML entities, which minimizes interference once returned (e.g. for "sms:a", "<!-- -->" etc.). local function escape_risky_characters(text) -- Spacing characters in isolation generally need to be escaped in order to be properly processed by the MediaWiki software. if umatch(text, "^%s*$") then return encode_entities(text, text) end return encode_entities(text, "!#%&*+/:;<=>?@[\\]_{|}") end -- Temporarily convert various formatting characters to PUA to prevent them from being disrupted by the substitution process. local function doTempSubstitutions(text, subbedChars, keepCarets, noTrim) -- Clone so that we don't insert any extra patterns into the table in package.loaded. For some reason, using require seems to keep memory use down; probably because the table is always cloned. local patterns = shallow_copy(require(languages_data_patterns_module)) if keepCarets then insert(patterns, "((\\+)%^)") insert(patterns, "((%^))") end -- Ensure any whitespace at the beginning and end is temp substituted, to prevent it from being accidentally trimmed. We only want to trim any final spaces added during the substitution process (e.g. by a module), which means we only do this during the first round of temp substitutions. if not noTrim then insert(patterns, "^([\128-\191\244]*(%s+))") insert(patterns, "((%s+)[\128-\191\244]*)$") end -- Pre-substitution, of "[[" and "]]", which makes pattern matching more accurate. text = gsub(text, "%f[%[]%[%[", "\1") :gsub("%f[%]]%]%]", "\2") local i = #subbedChars for _, pattern in ipairs(patterns) do -- Patterns ending in \0 stand are for things like "[[" or "]]"), so the inserted PUA are treated as breaks between terms by modules that scrape info from pages. local term_divider pattern = gsub(pattern, "%z$", function(divider) term_divider = divider == "\0" return "" end) text = gsub(text, pattern, function(...) local m = {...} local m1New = m[1] for k = 2, #m do local n = i + k - 1 subbedChars[n] = m[k] local byte2 = floor(n / 4096) % 64 + (term_divider and 128 or 136) local byte3 = floor(n / 64) % 64 + 128 local byte4 = n % 64 + 128 m1New = gsub(m1New, pattern_escape(m[k]), "\244" .. char(byte2) .. char(byte3) .. char(byte4), 1) end i = i + #m - 1 return m1New end) end text = gsub(text, "\1", "%[%[") :gsub("\2", "%]%]") return text, subbedChars end -- Reinsert any formatting that was temporarily substituted. local function undoTempSubstitutions(text, subbedChars) for i = 1, #subbedChars do local byte2 = floor(i / 4096) % 64 + 128 local byte3 = floor(i / 64) % 64 + 128 local byte4 = i % 64 + 128 text = gsub(text, "\244[" .. char(byte2) .. char(byte2+8) .. "]" .. char(byte3) .. char(byte4), replacement_escape(subbedChars[i])) end text = gsub(text, "\1", "%[%[") :gsub("\2", "%]%]") return text end -- Check if the raw text is an unsupported title, and if so return that. Otherwise, remove HTML entities. We do the pre-conversion to avoid loading the unsupported title list unnecessarily. local function checkNoEntities(self, text) local textNoEnc = decode_entities(text) if textNoEnc ~= text and load_data(links_data_module).unsupported_titles[text] then return text else return textNoEnc end end -- If no script object is provided (or if it's invalid or None), get one. local function checkScript(text, self, sc) if not check_object("script", true, sc) or sc:getCode() == "None" then return self:findBestScript(text) end return sc end local function normalize(text, sc) text = sc:fixDiscouragedSequences(text) return sc:toFixedNFD(text) end local function doSubstitutions(self, text, sc, substitution_data, function_name, recursed) local fail, cats = nil, {} -- If there are language-specific substitutes given in the data module, use those. if type(substitution_data) == "table" then -- If a script is specified, run this function with the script-specific data before continuing. local sc_code = sc:getCode() if substitution_data[sc_code] then text, fail, cats = doSubstitutions(self, text, sc, substitution_data[sc_code], function_name, true) -- Hant, Hans and Hani are usually treated the same, so add a special case to avoid having to specify each one separately. elseif sc_code:match("^Han") and substitution_data.Hani then text, fail, cats = doSubstitutions(self, text, sc, substitution_data.Hani, function_name, true) -- Substitution data with key 1 in the outer table may be given as a fallback. elseif substitution_data[1] then text, fail, cats = doSubstitutions(self, text, sc, substitution_data[1], function_name, true) end -- Iterate over all strings in the "from" subtable, and gsub with the corresponding string in "to". We work with the NFD decomposed forms, as this simplifies many substitutions. if substitution_data.from then for i, from in ipairs(substitution_data.from) do -- Normalize each loop, to ensure multi-stage substitutions work correctly. text = sc:toFixedNFD(text) text = ugsub(text, sc:toFixedNFD(from), substitution_data.to[i] or "") end end if substitution_data.remove_diacritics then text = sc:toFixedNFD(text) -- Convert exceptions to PUA. local remove_exceptions, substitutes = substitution_data.remove_exceptions if remove_exceptions then substitutes = {} local i = 0 for _, exception in ipairs(remove_exceptions) do exception = sc:toFixedNFD(exception) text = ugsub(text, exception, function(m) i = i + 1 local subst = u(0x80000 + i) substitutes[subst] = m return subst end) end end -- Strip diacritics. text = ugsub(text, "[" .. substitution_data.remove_diacritics .. "]", "") -- Convert exceptions back. if remove_exceptions then text = text:gsub("\242[\128-\191]*", substitutes) end end elseif type(substitution_data) == "string" then -- If there is a dedicated function module, use that. local module = safe_require("Module:" .. substitution_data) if module then -- TODO: translit functions should take objects, not codes. -- TODO: translit functions should be called with form NFD. if function_name == "tr" then text, fail, cats = module[function_name](text, self._code, sc:getCode()) else text, fail, cats = module[function_name](sc:toFixedNFD(text), self, sc) end -- TODO: get rid of the `fail` and `cats` return values. if fail ~= nil then track("fail") track("fail/" .. self._code) end if cats ~= nil then track("cats") track("cats/" .. self._code) end else error("Substitution data '" .. substitution_data .. "' does not match an existing module.") end end -- Don't normalize to NFC if this is the inner loop or if a module returned nil. if recursed or not text then return text, fail, cats end -- Fix any discouraged sequences created during the substitution process, and normalize into the final form. return sc:toFixedNFC(sc:fixDiscouragedSequences(text)), fail, cats end -- Split the text into sections, based on the presence of temporarily substituted formatting characters, then iterate over each one to apply substitutions. This avoids putting PUA characters through language-specific modules, which may be unequipped for them. local function iterateSectionSubstitutions(self, text, sc, subbedChars, keepCarets, substitution_data, function_name) local fail, cats, sections = nil, {} -- See [[Module:languages/data]]. if not find(text, "\244") or (load_data(languages_data_module).substitution[self._code] == "cont") then sections = {text} else sections = split(text, "\244[\128-\143][\128-\191]*", true) end for _, section in ipairs(sections) do -- Don't bother processing empty strings or whitespace (which may also not be handled well by dedicated modules). if gsub(section, "%s+", "") ~= "" then local sub, sub_fail, sub_cats = doSubstitutions(self, section, sc, substitution_data, function_name) -- Second round of temporary substitutions, in case any formatting was added by the main substitution process. However, don't do this if the section contains formatting already (as it would have had to have been escaped to reach this stage, and therefore should be given as raw text). if sub and subbedChars then local noSub for _, pattern in ipairs(require(languages_data_patterns_module)) do if match(section, pattern .. "%z?") then noSub = true end end if not noSub then sub, subbedChars = doTempSubstitutions(sub, subbedChars, keepCarets, true) end end if (not sub) or sub_fail then text = sub fail = sub_fail cats = sub_cats or {} break end text = sub and gsub(text, pattern_escape(section), replacement_escape(sub), 1) or text if type(sub_cats) == "table" then for _, cat in ipairs(sub_cats) do insert(cats, cat) end end end end -- Trim, unless there are only spacing characters, while ignoring any final formatting characters. text = text and text:gsub("^([\128-\191\244]*)%s+(%S)", "%1%2") :gsub("(%S)%s+([\128-\191\244]*)$", "%1%2") -- Remove duplicate categories. if #cats > 1 then cats = remove_duplicates(cats) end return text, fail, cats, subbedChars end -- Process carets (and any escapes). Default to simple removal, if no pattern/replacement is given. local function processCarets(text, pattern, repl) local rep repeat text, rep = gsub(text, "\\\\(\\*^)", "\3%1") until rep == 0 return text:gsub("\\^", "\4") :gsub(pattern or "%^", repl or "") :gsub("\3", "\\") :gsub("\4", "^") end -- Remove carets if they are used to capitalize parts of transliterations (unless they have been escaped). local function removeCarets(text, sc) if not sc:hasCapitalization() and sc:isTransliterated() and text:find("^", 1, true) then return processCarets(text) else return text end end local Language = {} --[==[Returns the language code of the language. Example: {{code|lua|"fr"}} for French.]==] function Language:getCode() return self._code end --[==[Returns the canonical name of the language. This is the name used to represent that language on Wiktionary, and is guaranteed to be unique to that language alone. Example: {{code|lua|"French"}} for French.]==] function Language:getCanonicalName() local name = self._name if name == nil then name = self._data[1] self._name = name end return name end --[==[ Return the display form of the language. The display form of a language, family or script is the form it takes when appearing as the <code><var>source</var></code> in categories such as <code>English terms derived from <var>source</var></code> or <code>English given names from <var>source</var></code>, and is also the displayed text in {makeCategoryLink()} links. For full and etymology-only languages, this is the same as the canonical name, but for families, it reads <code>"<var>name</var> languages"</code> (e.g. {"Indo-Iranian languages"}), and for scripts, it reads <code>"<var>name</var> script"</code> (e.g. {"Arabic script"}). ]==] function Language:getDisplayForm() local form = self._displayForm if form == nil then form = self:getCanonicalName() -- Add article and " substrate" to substrates that lack them. if self:getFamilyCode() == "qfa-sub" then if not (sub(form, 1, 4) == "the " or sub(form, 1, 2) == "a ") then form = "a " .. form end if not match(form, " [Ss]ubstrate") then form = form .. " substrate" end end self._displayForm = form end return form end --[==[Returns the value which should be used in the HTML lang= attribute for tagged text in the language.]==] function Language:getHTMLAttribute(sc, region) local code = self._code if not find(code, "-", 1, true) then return code .. "-" .. sc:getCode() .. (region and "-" .. region or "") end local parent = self:getParent() region = region or match(code, "%f[%u][%u-]+%f[%U]") if parent then return parent:getHTMLAttribute(sc, region) end -- TODO: ISO family codes can also be used. return "mis-" .. sc:getCode() .. (region and "-" .. region or "") end --[==[Returns a table of the aliases that the language is known by, excluding the canonical name. Aliases are synonyms for the language in question. The names are not guaranteed to be unique, in that sometimes more than one language is known by the same name. Example: {{code|lua|{"High German", "New High German", "Deutsch"} }} for [[:Category:German language|German]].]==] function Language:getAliases() self:loadInExtraData() return require(language_like_module).getAliases(self) end --[==[ Return a table of the known subvarieties of a given language, excluding subvarieties that have been given explicit etymology-only language codes. The names are not guaranteed to be unique, in that sometimes a given name refers to a subvariety of more than one language. Example: {{code|lua|{"Southern Aymara", "Central Aymara"} }} for [[:Category:Aymara language|Aymara]]. Note that the returned value can have nested tables in it, when a subvariety goes by more than one name. Example: {{code|lua|{"North Azerbaijani", "South Azerbaijani", {"Afshar", "Afshari", "Afshar Azerbaijani", "Afchar"}, {"Qashqa'i", "Qashqai", "Kashkay"}, "Sonqor"} }} for [[:Category:Azerbaijani language|Azerbaijani]]. Here, for example, Afshar, Afshari, Afshar Azerbaijani and Afchar all refer to the same subvariety, whose preferred name is Afshar (the one listed first). To avoid a return value with nested tables in it, specify a non-{{code|lua|nil}} value for the <code>flatten</code> parameter; in that case, the return value would be {{code|lua|{"North Azerbaijani", "South Azerbaijani", "Afshar", "Afshari", "Afshar Azerbaijani", "Afchar", "Qashqa'i", "Qashqai", "Kashkay", "Sonqor"} }}. ]==] function Language:getVarieties(flatten) self:loadInExtraData() return require(language_like_module).getVarieties(self, flatten) end --[==[Returns a table of the "other names" that the language is known by, which are listed in the <code>otherNames</code> field. It should be noted that the <code>otherNames</code> field itself is deprecated, and entries listed there should eventually be moved to either <code>aliases</code> or <code>varieties</code>.]==] function Language:getOtherNames() -- To be eventually removed, once there are no more uses of the `otherNames` field. self:loadInExtraData() return require(language_like_module).getOtherNames(self) end --[==[ Return a combined table of the canonical name, aliases, varieties and other names of a given language.]==] function Language:getAllNames() self:loadInExtraData() return require(language_like_module).getAllNames(self) end --[==[Returns a table of types as a lookup table (with the types as keys). The possible types are * {language}: This is a language, either full or etymology-only. * {full}: This is a "full" (not etymology-only) language, i.e. the union of {regular}, {reconstructed} and {appendix-constructed}. Note that the types {full} and {etymology-only} also exist for families, so if you want to check specifically for a full language and you have an object that might be a family, you should use {{lua|hasType("language", "full")}} and not simply {{lua|hasType("full")}}. * {etymology-only}: This is an etymology-only (not full) language, whose parent is another etymology-only language or a full language. Note that the types {full} and {etymology-only} also exist for families, so if you want to check specifically for an etymology-only language and you have an object that might be a family, you should use {{lua|hasType("language", "etymology-only")}} and not simply {{lua|hasType("etymology-only")}}. * {regular}: This indicates a full language that is attested according to [[WT:CFI]] and therefore permitted in the main namespace. There may also be reconstructed terms for the language, which are placed in the {Reconstruction} namespace and must be prefixed with * to indicate a reconstruction. Most full languages are natural (not constructed) languages, but a few constructed languages (e.g. Esperanto and Volapük, among others) are also allowed in the mainspace and considered regular languages. * {reconstructed}: This language is not attested according to [[WT:CFI]], and therefore is allowed only in the {Reconstruction} namespace. All terms in this language are reconstructed, and must be prefixed with *. Languages such as Proto-Indo-European and Proto-Germanic are in this category. * {appendix-constructed}: This language is attested but does not meet the additional requirements set out for constructed languages ([[WT:CFI#Constructed languages]]). Its entries must therefore be in the Appendix namespace, but they are not reconstructed and therefore should not have * prefixed in links. ]==] function Language:getTypes() local types = self._types if types == nil then types = {language = true} if self:getFullCode() == self._code then types.full = true else types["etymology-only"] = true end for t in gmatch(self._data.type, "[^,]+") do types[t] = true end self._types = types end return types end --[==[Given a list of types as strings, returns true if the language has all of them.]==] function Language:hasType(...) Language.hasType = require(language_like_module).hasType return self:hasType(...) end --[==[Returns a table containing <code>WikimediaLanguage</code> objects (see [[Module:wikimedia languages]]), which represent languages and their codes as they are used in Wikimedia projects for interwiki linking and such. More than one object may be returned, as a single Wiktionary language may correspond to multiple Wikimedia languages. For example, Wiktionary's single code <code>sh</code> (Serbo-Croatian) maps to four Wikimedia codes: <code>sh</code> (Serbo-Croatian), <code>bs</code> (Bosnian), <code>hr</code> (Croatian) and <code>sr</code> (Serbian). The code for the Wikimedia language is retrieved from the <code>wikimedia_codes</code> property in the data modules. If that property is not present, the code of the current language is used. If none of the available codes is actually a valid Wikimedia code, an empty table is returned.]==] function Language:getWikimediaLanguages() local wm_langs = self._wikimediaLanguageObjects if wm_langs == nil then local codes = self:getWikimediaLanguageCodes() wm_langs = {} for i = 1, #codes do wm_langs[i] = get_wikimedia_lang(codes[i]) end self._wikimediaLanguageObjects = wm_langs end return wm_langs end function Language:getWikimediaLanguageCodes() local wm_langs = self._wikimediaLanguageCodes if wm_langs == nil then wm_langs = self._data.wikimedia_codes if wm_langs then wm_langs = split(wm_langs, ",", true, true) else local code = self._code if is_known_language_tag(code) then wm_langs = {code} else -- Inherit, but only if no codes are specified in the data *and* -- the language code isn't a valid Wikimedia language code. local parent = self:getParent() wm_langs = parent and parent:getWikimediaLanguageCodes() or {} end end self._wikimediaLanguageCodes = wm_langs end return wm_langs end --[==[ Returns the name of the Wikipedia article for the language. `project` specifies the language and project to retrieve the article from, defaulting to {"enwiki"} for the English Wikipedia. Normally if specified it should be the project code for a specific-language Wikipedia e.g. "zhwiki" for the Chinese Wikipedia, but it can be any project, including non-Wikipedia ones. If the project is the English Wikipedia and the property {wikipedia_article} is present in the data module it will be used first. In all other cases, a sitelink will be generated from {:getWikidataItem} (if set). The resulting value (or lack of value) is cached so that subsequent calls are fast. If no value could be determined, and `noCategoryFallback` is {false}, {:getCategoryName} is used as fallback; otherwise, {nil} is returned. Note that if `noCategoryFallback` is {nil} or omitted, it defaults to {false} if the project is the English Wikipedia, otherwise to {true}. In other words, under normal circumstances, if the English Wikipedia article couldn't be retrieved, the return value will fall back to a link to the language's category, but this won't normally happen for any other project. ]==] function Language:getWikipediaArticle(noCategoryFallback, project) Language.getWikipediaArticle = require(language_like_module).getWikipediaArticle return self:getWikipediaArticle(noCategoryFallback, project) end function Language:makeWikipediaLink() return make_link(self, "w:" .. self:getWikipediaArticle(), self:getCanonicalName()) end --[==[Returns the name of the Wikimedia Commons category page for the language.]==] function Language:getCommonsCategory() Language.getCommonsCategory = require(language_like_module).getCommonsCategory return self:getCommonsCategory() end --[==[Returns the Wikidata item id for the language or <code>nil</code>. This corresponds to the the second field in the data modules.]==] function Language:getWikidataItem() Language.getWikidataItem = require(language_like_module).getWikidataItem return self:getWikidataItem() end --[==[Returns a table of <code>Script</code> objects for all scripts that the language is written in. See [[Module:scripts]].]==] function Language:getScripts() local scripts = self._scriptObjects if scripts == nil then local codes = self:getScriptCodes() if codes[1] == "All" then scripts = load_data(scripts_data_module) else scripts = {} for i = 1, #codes do scripts[i] = get_script(codes[i]) end end self._scriptObjects = scripts end return scripts end --[==[Returns the table of script codes in the language's data file.]==] function Language:getScriptCodes() local scripts = self._scriptCodes if scripts == nil then scripts = self._data[4] if scripts then local codes, n = {}, 0 for code in gmatch(scripts, "[^,]+") do n = n + 1 -- Special handling of "Hants", which represents "Hani", "Hant" and "Hans" collectively. if code == "Hants" then codes[n] = "Hani" codes[n + 1] = "Hant" codes[n + 2] = "Hans" n = n + 2 else codes[n] = code end end scripts = codes else scripts = {"None"} end self._scriptCodes = scripts end return scripts end --[==[Given some text, this function iterates through the scripts of a given language and tries to find the script that best matches the text. It returns a {{code|lua|Script}} object representing the script. If no match is found at all, it returns the {{code|lua|None}} script object.]==] function Language:findBestScript(text, forceDetect) if not text or text == "" or text == "-" then return get_script("None") end -- Differs from table returned by getScriptCodes, as Hants is not normalized into its constituents. local codes = self._bestScriptCodes if codes == nil then codes = self._data[4] codes = codes and split(codes, ",", true, true) or {"None"} self._bestScriptCodes = codes end local first_sc = codes[1] if first_sc == "All" then return find_best_script_without_lang(text) end local codes_len = #codes if not (forceDetect or first_sc == "Hants" or codes_len > 1) then first_sc = get_script(first_sc) local charset = first_sc.characters return charset and umatch(text, "[" .. charset .. "]") and first_sc or get_script("None") end -- Remove all formatting characters. text = get_plaintext(text) -- Remove all spaces and any ASCII punctuation. Some non-ASCII punctuation is script-specific, so can't be removed. text = ugsub(text, "[%s!\"#%%&'()*,%-./:;?@[\\%]_{}]+", "") if #text == 0 then return get_script("None") end -- Try to match every script against the text, -- and return the one with the most matching characters. local bestcount, bestscript, length = 0 for i = 1, codes_len do local sc = codes[i] -- Special case for "Hants", which is a special code that represents whichever of "Hant" or "Hans" best matches, or "Hani" if they match equally. This avoids having to list all three. In addition, "Hants" will be treated as the best match if there is at least one matching character, under the assumption that a Han script is desirable in terms that contain a mix of Han and other scripts (not counting those which use Jpan or Kore). if sc == "Hants" then local Hani = get_script("Hani") if not Hant_chars then Hant_chars = load_data("Module:zh/data/ts") Hans_chars = load_data("Module:zh/data/st") end local t, s, found = 0, 0 -- This is faster than using mw.ustring.gmatch directly. for ch in gmatch(ugsub(text, "[" .. Hani.characters .. "]", "\255%0"), "\255(.[\128-\191]*)") do found = true if Hant_chars[ch] then t = t + 1 if Hans_chars[ch] then s = s + 1 end elseif Hans_chars[ch] then s = s + 1 else t, s = t + 1, s + 1 end end if found then if t == s then return Hani end return get_script(t > s and "Hant" or "Hans") end else sc = get_script(sc) if not length then length = ulen(text) end -- Count characters by removing everything in the script's charset and comparing to the original length. local charset = sc.characters local count = charset and length - ulen(ugsub(text, "[" .. charset .. "]+", "")) or 0 if count >= length then return sc elseif count > bestcount then bestcount = count bestscript = sc end end end -- Return best matching script, or otherwise None. return bestscript or get_script("None") end --[==[Returns a <code>Family</code> object for the language family that the language belongs to. See [[Module:families]].]==] function Language:getFamily() local family = self._familyObject if family == nil then family = self:getFamilyCode() -- If the value is nil, it's cached as false. family = family and get_family(family) or false self._familyObject = family end return family or nil end --[==[Returns the family code in the language's data file.]==] function Language:getFamilyCode() local family = self._familyCode if family == nil then -- If the value is nil, it's cached as false. family = self._data[3] or false self._familyCode = family end return family or nil end function Language:getFamilyName() local family = self._familyName if family == nil then family = self:getFamily() -- If the value is nil, it's cached as false. family = family and family:getCanonicalName() or false self._familyName = family end return family or nil end do local function check_family(self, family) if type(family) == "table" then family = family:getCode() end if self:getFamilyCode() == family then return true end local self_family = self:getFamily() if self_family:inFamily(family) then return true -- If the family isn't a real family (e.g. creoles) check any ancestors. elseif self_family:inFamily("qfa-not") then local ancestors = self:getAncestors() for _, ancestor in ipairs(ancestors) do if ancestor:inFamily(family) then return true end end end end --[==[Check whether the language belongs to `family` (which can be a family code or object). A list of objects can be given in place of `family`; in that case, return true if the language belongs to any of the specified families. Note that some languages (in particular, certain creoles) can have multiple immediate ancestors potentially belonging to different families; in that case, return true if the language belongs to any of the specified families.]==] function Language:inFamily(...) if self:getFamilyCode() == nil then return false end return check_inputs(self, check_family, false, ...) end end function Language:getParent() local parent = self._parentObject if parent == nil then parent = self:getParentCode() -- If the value is nil, it's cached as false. parent = parent and get_by_code(parent, nil, true, true) or false self._parentObject = parent end return parent or nil end function Language:getParentCode() local parent = self._parentCode if parent == nil then -- If the value is nil, it's cached as false. parent = self._data.parent or false self._parentCode = parent end return parent or nil end function Language:getParentName() local parent = self._parentName if parent == nil then parent = self:getParent() -- If the value is nil, it's cached as false. parent = parent and parent:getCanonicalName() or false self._parentName = parent end return parent or nil end function Language:getParentChain() local chain = self._parentChain if chain == nil then chain = {} local parent, n = self:getParent(), 0 while parent do n = n + 1 chain[n] = parent parent = parent:getParent() end self._parentChain = chain end return chain end do local function check_lang(self, lang) for _, parent in ipairs(self:getParentChain()) do if (type(lang) == "string" and lang or lang:getCode()) == parent:getCode() then return true end end end function Language:hasParent(...) return check_inputs(self, check_lang, false, ...) end end --[==[ If the language is etymology-only, this iterates through parents until a full language or family is found, and the corresponding object is returned. If the language is a full language, then it simply returns itself. ]==] function Language:getFull() local full = self._fullObject if full == nil then full = self:getFullCode() full = full == self._code and self or get_by_code(full) self._fullObject = full end return full end --[==[ If the language is an etymology-only language, this iterates through parents until a full language or family is found, and the corresponding code is returned. If the language is a full language, then it simply returns the language code. ]==] function Language:getFullCode() return self._fullCode or self._code end --[==[ If the language is an etymology-only language, this iterates through parents until a full language or family is found, and the corresponding canonical name is returned. If the language is a full language, then it simply returns the canonical name of the language. ]==] function Language:getFullName() local full = self._fullName if full == nil then full = self:getFull():getCanonicalName() self._fullName = full end return full end --[==[Returns a table of <code class="nf">Language</code> objects for all languages that this language is directly descended from. Generally this is only a single language, but creoles, pidgins and mixed languages can have multiple ancestors.]==] function Language:getAncestors() local ancestors = self._ancestorObjects if ancestors == nil then ancestors = {} local ancestor_codes = self:getAncestorCodes() if #ancestor_codes > 0 then for _, ancestor in ipairs(ancestor_codes) do insert(ancestors, get_by_code(ancestor, nil, true)) end else local fam = self:getFamily() local protoLang = fam and fam:getProtoLanguage() or nil -- For the cases where the current language is the proto-language -- of its family, or an etymology-only language that is ancestral to that -- proto-language, we need to step up a level higher right from the -- start. if protoLang and ( protoLang:getCode() == self._code or (self:hasType("etymology-only") and protoLang:hasAncestor(self)) ) then fam = fam:getFamily() protoLang = fam and fam:getProtoLanguage() or nil end while not protoLang and not (not fam or fam:getCode() == "qfa-not") do fam = fam:getFamily() protoLang = fam and fam:getProtoLanguage() or nil end insert(ancestors, protoLang) end self._ancestorObjects = ancestors end return ancestors end do -- Avoid a language being its own ancestor via class inheritance. We only need to check for this if the language has inherited an ancestor table from its parent, because we never want to drop ancestors that have been explicitly set in the data. -- Recursively iterate over ancestors until we either find self or run out. If self is found, return true. local function check_ancestor(self, lang) local codes = lang:getAncestorCodes() if not codes then return nil end for i = 1, #codes do local code = codes[i] if code == self._code then return true end local anc = get_by_code(code, nil, true) if check_ancestor(self, anc) then return true end end end --[==[Returns a table of <code class="nf">Language</code> codes for all languages that this language is directly descended from. Generally this is only a single language, but creoles, pidgins and mixed languages can have multiple ancestors.]==] function Language:getAncestorCodes() if self._ancestorCodes then return self._ancestorCodes end local data = self._data local codes = data.ancestors if codes == nil then codes = {} self._ancestorCodes = codes return codes end codes = split(codes, ",", true, true) self._ancestorCodes = codes -- If there are no codes or the ancestors weren't inherited data, there's nothing left to check. if #codes == 0 or self:getData(false, "raw").ancestors ~= nil then return codes end local i, code = 1 while i <= #codes do code = codes[i] if check_ancestor(self, self) then remove(codes, i) else i = i + 1 end end return codes end end --[==[Given a list of language objects or codes, returns true if at least one of them is an ancestor. This includes any etymology-only children of that ancestor. If the language's ancestor(s) are etymology-only languages, it will also return true for those language parent(s) (e.g. if Vulgar Latin is the ancestor, it will also return true for its parent, Latin). However, a parent is excluded from this if the ancestor is also ancestral to that parent (e.g. if Classical Persian is the ancestor, Persian would return false, because Classical Persian is also ancestral to Persian).]==] function Language:hasAncestor(...) local function iterateOverAncestorTree(node, func, parent_check) local ancestors = node:getAncestors() local ancestorsParents = {} for _, ancestor in ipairs(ancestors) do local ret = func(ancestor) or iterateOverAncestorTree(ancestor, func, parent_check) if ret then return ret end end -- Check the parents of any ancestors. We don't do this if checking the parents of the other language, so that we exclude any etymology-only children of those parents that are not directly related (e.g. if the ancestor is Vulgar Latin and we are checking New Latin, we want it to return false because they are on different ancestral branches. As such, if we're already checking the parent of New Latin (Latin) we don't want to compare it to the parent of the ancestor (Latin), as this would be a false positive; it should be one or the other). if not parent_check then return nil end for _, ancestor in ipairs(ancestors) do local ancestorParents = ancestor:getParentChain() for _, ancestorParent in ipairs(ancestorParents) do if ancestorParent:getCode() == self._code or ancestorParent:hasAncestor(ancestor) then break else insert(ancestorsParents, ancestorParent) end end end for _, ancestorParent in ipairs(ancestorsParents) do local ret = func(ancestorParent) if ret then return ret end end end local function do_iteration(otherlang, parent_check) -- otherlang can't be self if (type(otherlang) == "string" and otherlang or otherlang:getCode()) == self._code then return false end repeat if iterateOverAncestorTree( self, function(ancestor) return ancestor:getCode() == (type(otherlang) == "string" and otherlang or otherlang:getCode()) end, parent_check ) then return true elseif type(otherlang) == "string" then otherlang = get_by_code(otherlang, nil, true) end otherlang = otherlang:getParent() parent_check = false until not otherlang end local parent_check = true for _, otherlang in ipairs{...} do local ret = do_iteration(otherlang, parent_check) if ret then return true end end return false end do local function construct_node(lang, memo) local branch, ancestors = {lang = lang:getCode()} memo[lang:getCode()] = branch for _, ancestor in ipairs(lang:getAncestors()) do if ancestors == nil then ancestors = {} end insert(ancestors, memo[ancestor:getCode()] or construct_node(ancestor, memo)) end branch.ancestors = ancestors return branch end function Language:getAncestorChain() local chain = self._ancestorChain if chain == nil then chain = construct_node(self, {}) self._ancestorChain = chain end return chain end end function Language:getAncestorChainOld() local chain = self._ancestorChain if chain == nil then chain = {} local step = self while true do local ancestors = step:getAncestors() step = #ancestors == 1 and ancestors[1] or nil if not step then break end insert(chain, step) end self._ancestorChain = chain end return chain end local function fetch_descendants(self, fmt) local descendants, family = {}, self:getFamily() -- Iterate over all three datasets. for _, data in ipairs{ require("Module:languages/code to canonical name"), require("Module:etymology languages/code to canonical name"), require("Module:families/code to canonical name"), } do for code in pairs(data) do local lang = get_by_code(code, nil, true, true) -- Test for a descendant. Earlier tests weed out most candidates, while the more intensive tests are only used sparingly. if ( code ~= self._code and -- Not self. lang:inFamily(family) and -- In the same family. ( family:getProtoLanguageCode() == self._code or -- Self is the protolanguage. self:hasDescendant(lang) or -- Full hasDescendant check. (lang:getFullCode() == self._code and not self:hasAncestor(lang)) -- Etymology-only child which isn't an ancestor. ) ) then if fmt == "object" then insert(descendants, lang) elseif fmt == "code" then insert(descendants, code) elseif fmt == "name" then insert(descendants, lang:getCanonicalName()) end end end end return descendants end function Language:getDescendants() local descendants = self._descendantObjects if descendants == nil then descendants = fetch_descendants(self, "object") self._descendantObjects = descendants end return descendants end function Language:getDescendantCodes() local descendants = self._descendantCodes if descendants == nil then descendants = fetch_descendants(self, "code") self._descendantCodes = descendants end return descendants end function Language:getDescendantNames() local descendants = self._descendantNames if descendants == nil then descendants = fetch_descendants(self, "name") self._descendantNames = descendants end return descendants end do local function check_lang(self, lang) if type(lang) == "string" then lang = get_by_code(lang, nil, true) end if lang:hasAncestor(self) then return true end end function Language:hasDescendant(...) return check_inputs(self, check_lang, false, ...) end end local function fetch_children(self, fmt) local m_etym_data = require(etymology_languages_data_module) local self_code, children = self._code, {} for code, lang in pairs(m_etym_data) do local _lang = lang repeat local parent = _lang.parent if parent == self_code then if fmt == "object" then insert(children, get_by_code(code, nil, true)) elseif fmt == "code" then insert(children, code) elseif fmt == "name" then insert(children, lang[1]) end break end _lang = m_etym_data[parent] until not _lang end return children end function Language:getChildren() local children = self._childObjects if children == nil then children = fetch_children(self, "object") self._childObjects = children end return children end function Language:getChildrenCodes() local children = self._childCodes if children == nil then children = fetch_children(self, "code") self._childCodes = children end return children end function Language:getChildrenNames() local children = self._childNames if children == nil then children = fetch_children(self, "name") self._childNames = children end return children end function Language:hasChild(...) local lang = ... if not lang then return false elseif type(lang) == "string" then lang = get_by_code(lang, nil, true) end if lang:hasParent(self) then return true end return self:hasChild(select(2, ...)) end --[==[Returns the name of the main category of that language. Example: {{code|lua|"French language"}} for French, whose category is at [[:Category:French language]]. Unless optional argument <code>nocap</code> is given, the language name at the beginning of the returned value will be capitalized. This capitalization is correct for category names, but not if the language name is lowercase and the returned value of this function is used in the middle of a sentence.]==] function Language:getCategoryName(nocap) local name = self._categoryName if name == nil then name = self:getCanonicalName() -- If a substrate, omit any leading article. if self:getFamilyCode() == "qfa-sub" then name = name:gsub("^ ", ""):gsub("^ ", "") end -- Only add " language" if a full language. if self:hasType("full") then -- Unless the canonical name already ends with "language", "lect" or their derivatives, add " language". if not (match(name, "[Rr]eo$") or match(name, "[Ll]ect$")) then name = "Reo " .. name end end self._categoryName = name end if nocap then return name end return mw.getContentLanguage():ucfirst(name) end --[==[Creates a link to the category; the link text is the canonical name.]==] function Language:makeCategoryLink() return make_link(self, ":Category:" .. self:getCategoryName(), self:getDisplayForm()) end function Language:getStandardCharacters(sc) local standard_chars = self._data.standardChars if type(standard_chars) ~= "table" then return standard_chars elseif sc and type(sc) ~= "string" then check_object("script", nil, sc) sc = sc:getCode() end if (not sc) or sc == "None" then local scripts = {} for _, script in pairs(standard_chars) do insert(scripts, script) end return concat(scripts) end if standard_chars[sc] then return standard_chars[sc] .. (standard_chars[1] or "") end end --[==[Make the entry name (i.e. the correct page name).]==] function Language:makeEntryName(text, sc) if (not text) or text == "" then return text, nil, {} end -- Set `unsupported` as true if certain conditions are met. local unsupported -- Check if there's an unsupported character. \239\191\189 is the replacement character U+FFFD, which can't be typed directly here due to an abuse filter. Unix-style dot-slash notation is also unsupported, as it is used for relative paths in links, as are 3 or more consecutive tildes. -- Note: match is faster with magic characters/charsets; find is faster with plaintext. if ( match(text, "[#<>%[%]_{|}]") or find(text, "\239\191\189") or match(text, "%f[^%z/]%.%.?%f[%z/]") or find(text, "~~~") ) then unsupported = true -- If it looks like an interwiki link. elseif find(text, ":") then local prefix = gsub(text, "^:*(.-):.*", ulower) if ( load_data("Module:data/namespaces")[prefix] or load_data("Module:data/interwikis")[prefix] ) then unsupported = true end end -- Check if the text is a listed unsupported title. local unsupportedTitles = load_data(links_data_module).unsupported_titles if unsupportedTitles[text] then return "Unsupported titles/" .. unsupportedTitles[text], nil, {} end sc = checkScript(text, self, sc) local fail, cats text = normalize(text, sc) text, fail, cats = iterateSectionSubstitutions(self, text, sc, nil, nil, self._data.entry_name, "makeEntryName") text = umatch(text, "^[¿¡]?(.-[^%s%p].-)%s*[؟?!;՛՜ ՞ ՟？！︖︕।॥။၊་།]?$") or text -- Escape unsupported characters so they can be used in titles. ` is used as a delimiter for this, so a raw use of it in an unsupported title is also escaped here to prevent interference; this is only done with unsupported titles, though, so inclusion won't in itself mean a title is treated as unsupported (which is why it's excluded from the earlier test). if unsupported then local unsupported_characters = load_data(links_data_module).unsupported_characters text = text:gsub("[#<>%[%]_`{|}\239]\191?\189?", unsupported_characters) :gsub("%f[^%z/]%.%.?%f[%z/]", function(m) return gsub(m, "%.", "`period`") end) :gsub("~~~+", function(m) return gsub(m, "~", "`tilde`") end) text = "Unsupported titles/" .. text end return text, fail, cats end --[==[Generates alternative forms using a specified method, and returns them as a table. If no method is specified, returns a table containing only the input term.]==] function Language:generateForms(text, sc) local generate_forms = self._data.generate_forms if generate_forms == nil then return {text} end sc = checkScript(text, self, sc) return require("Module:" .. self._data.generate_forms).generateForms(text, self, sc) end --[==[Creates a sort key for the given entry name, following the rules appropriate for the language. This removes diacritical marks from the entry name if they are not considered significant for sorting, and may perform some other changes. Any initial hyphen is also removed, and anything parentheses is removed as well. The <code>sort_key</code> setting for each language in the data modules defines the replacements made by this function, or it gives the name of the module that takes the entry name and returns a sortkey.]==] function Language:makeSortKey(text, sc) if (not text) or text == "" then return text, nil, {} end if match(text, "<[^<>]+>") then track("track HTML tag") end -- Remove directional characters, soft hyphens, strip markers and HTML tags. text = ugsub(text, "[\194\173\226\128\170-\226\128\174\226\129\166-\226\129\169]", "") text = gsub(unstrip(text), "<[^<>]+>", "") text = decode_uri(text, "PATH") text = checkNoEntities(self, text) -- Remove initial hyphens and * unless the term only consists of spacing + punctuation characters. text = ugsub(text, "^([􀀀-􏿽]*)[-־ـ᠊*]+([􀀀-􏿽]*)(.*[^%s%p].*)", "%1%2%3") sc = checkScript(text, self, sc) text = normalize(text, sc) text = removeCarets(text, sc) -- For languages with dotted dotless i, ensure that "İ" is sorted as "i", and "I" is sorted as "ı". if self:hasDottedDotlessI() then text = gsub(text, "I\204\135", "i") -- decomposed "İ" :gsub("I", "ı") text = sc:toFixedNFD(text) end -- Convert to lowercase, make the sortkey, then convert to uppercase. Where the language has dotted dotless i, it is usually not necessary to convert "i" to "İ" and "ı" to "I" first, because "I" will always be interpreted as conventional "I" (not dotless "İ") by any sorting algorithms, which will have been taken into account by the sortkey substitutions themselves. However, if no sortkey substitutions have been specified, then conversion is necessary so as to prevent "i" and "ı" both being sorted as "I". -- An exception is made for scripts that (sometimes) sort by scraping page content, as that means they are sensitive to changes in capitalization (as it changes the target page). local fail, cats if not sc:sortByScraping() then text = ulower(text) end local sort_key = self._data.sort_key text, fail, cats = iterateSectionSubstitutions(self, text, sc, nil, nil, sort_key, "makeSortKey") if not sc:sortByScraping() then if self:hasDottedDotlessI() and not sort_key then text = gsub(gsub(text, "ı", "I"), "i", "İ") text = sc:toFixedNFC(text) end text = uupper(text) end -- Remove parentheses, as long as they are either preceded or followed by something. text = gsub(text, "(.)[()]+", "%1") :gsub("[()]+(.)", "%1") text = escape_risky_characters(text) return text, fail, cats end --[==[Create the form used as as a basis for display text and transliteration.]==] local function processDisplayText(text, self, sc, keepCarets, keepPrefixes) local subbedChars = {} text, subbedChars = doTempSubstitutions(text, subbedChars, keepCarets) text = decode_uri(text, "PATH") text = checkNoEntities(self, text) sc = checkScript(text, self, sc) local fail, cats text = normalize(text, sc) text, fail, cats, subbedChars = iterateSectionSubstitutions(self, text, sc, subbedChars, keepCarets, self._data.display_text, "makeDisplayText") text = removeCarets(text, sc) -- Remove any interwiki link prefixes (unless they have been escaped or this has been disabled). if find(text, ":") and not keepPrefixes then local rep repeat text, rep = gsub(text, "\\\\(\\*:)", "\3%1") until rep == 0 text = gsub(text, "\\:", "\4") while true do local prefix = gsub(text, "^(.-):.+", function(m1) return gsub(m1, "\244[\128-\191]*", "") end) -- Check if the prefix is an interwiki, though ignore capitalised Wiktionary:, which is a namespace. if not prefix or prefix == text or prefix == "Wiktionary" or not (load_data("Module:data/interwikis")[ulower(prefix)] or prefix == "") then break end text = gsub(text, "^(.-):(.*)", function(m1, m2) local ret = {} for subbedChar in gmatch(m1, "\244[\128-\191]*") do insert(ret, subbedChar) end return concat(ret) .. m2 end) end text = gsub(text, "\3", "\\") :gsub("\4", ":") end return text, fail, cats, subbedChars end --[==[Make the display text (i.e. what is displayed on the page).]==] function Language:makeDisplayText(text, sc, keepPrefixes) if (not text) or text == "" then return text, nil, {} end local fail, cats, subbedChars text, fail, cats, subbedChars = processDisplayText(text, self, sc, nil, keepPrefixes) text = escape_risky_characters(text) return undoTempSubstitutions(text, subbedChars), fail, cats end --[==[Transliterates the text from the given script into the Latin script (see [[Wiktionary:Transliteration and romanization]]). The language must have the <code>translit</code> property for this to work; if it is not present, {{code|lua|nil}} is returned. Returns three values: # The transliteration. # A boolean which indicates whether the transliteration failed for an unexpected reason. If {{code|lua|false}}, then the transliteration either succeeded, or the module is returning nothing in a controlled way (e.g. the input was {{code|lua|"-"}}). Generally, this means that no maintenance action is required. If {{code|lua|true}}, then the transliteration is {{code|lua|nil}} because either the input or output was defective in some way (e.g. [[Module:ar-translit]] will not transliterate non-vocalised inputs, and this module will fail partially-completed transliterations in all languages). Note that this value can be manually set by the transliteration module, so make sure to cross-check to ensure it is accurate. # A table of categories selected by the transliteration module, which should be in the format expected by {{code|lua|format_categories}} in [[Module:utilities]]. The <code>sc</code> parameter is handled by the transliteration module, and how it is handled is specific to that module. Some transliteration modules may tolerate {{code|lua|nil}} as the script, others require it to be one of the possible scripts that the module can transliterate, and will show an error if it's not one of them. For this reason, the <code>sc</code> parameter should always be provided when writing non-language-specific code. The <code>module_override</code> parameter is used to override the default module that is used to provide the transliteration. This is useful in cases where you need to demonstrate a particular module in use, but there is no default module yet, or you want to demonstrate an alternative version of a transliteration module before making it official. It should not be used in real modules or templates, only for testing. All uses of this parameter are tracked by [[Wiktionary:Tracking/languages/module_override]]. '''Known bugs''': * This function assumes {tr(s1) .. tr(s2) == tr(s1 .. s2)}. When this assertion fails, wikitext markups like <nowiki>'''</nowiki> can cause wrong transliterations. * HTML entities like <code>&amp;apos;</code>, often used to escape wikitext markups, do not work.]==] function Language:transliterate(text, sc, module_override) -- If there is no text, or the language doesn't have transliteration data and there's no override, return nil. if not (self._data.translit or module_override) then return nil, false, {} elseif (not text) or text == "" or text == "-" then return text, false, {} end -- If the script is not transliteratable (and no override is given), return nil. sc = checkScript(text, self, sc) if not (sc:isTransliterated() or module_override) then -- temporary tracking to see if/when this gets triggered track("non-transliterable") track("non-transliterable/" .. self._code) track("non-transliterable/" .. sc:getCode()) track("non-transliterable/" .. sc:getCode() .. "/" .. self._code) return nil, true, {} end -- Remove any strip markers. text = unstrip(text) -- Do not process the formatting into PUA characters for certain languages. local processed = load_data(languages_data_module).substitution[self._code] ~= "none" -- Get the display text with the keepCarets flag set. local fail, cats, subbedChars if processed then text, fail, cats, subbedChars = processDisplayText(text, self, sc, true) end -- Transliterate (using the module override if applicable). text, fail, cats, subbedChars = iterateSectionSubstitutions(self, text, sc, subbedChars, true, module_override or self._data.translit, "tr") if not text then return nil, true, cats end -- Incomplete transliterations return nil. local charset = sc.characters if charset and umatch(text, "[" .. charset .. "]") then -- Remove any characters in Latin, which includes Latin characters also included in other scripts (as these are false positives), as well as any PUA substitutions. Anything remaining should only be script code "None" (e.g. numerals). local check_text = ugsub(text, "[" .. get_script("Latn").characters .. "􀀀-􏿽]+", "") -- Set none_is_last_resort_only flag, so that any non-None chars will cause a script other than "None" to be returned. if find_best_script_without_lang(check_text, true):getCode() ~= "None" then return nil, true, cats end end if processed then text = escape_risky_characters(text) text = undoTempSubstitutions(text, subbedChars) end -- If the script does not use capitalization, then capitalize any letters of the transliteration which are immediately preceded by a caret (and remove the caret). if text and not sc:hasCapitalization() and text:find("^", 1, true) then text = processCarets(text, "%^([\128-\191\244]*%*?)([^\128-\191\244][\128-\191]*)", function(m1, m2) return m1 .. uupper(m2) end) end -- Track module overrides. if module_override ~= nil then track("module_override") end fail = text == nil and (not not fail) or false return text, fail, cats end do local function handle_language_spec(self, spec, sc) local ret = self["_" .. spec] if ret == nil then ret = self._data[spec] if type(ret) == "string" then ret = list_to_set(split(ret, ",", true, true)) end self["_" .. spec] = ret end if type(ret) == "table" then ret = ret[sc:getCode()] end return not not ret end function Language:overrideManualTranslit(sc) return handle_language_spec(self, "override_translit", sc) end function Language:link_tr(sc) return handle_language_spec(self, "link_tr", sc) end end --[==[Returns {{code|lua|true}} if the language has a transliteration module, or {{code|lua|false}} if it doesn't.]==] function Language:hasTranslit() return not not self._data.translit end --[==[Returns {{code|lua|true}} if the language uses the letters I/ı and İ/i, or {{code|lua|false}} if it doesn't.]==] function Language:hasDottedDotlessI() return not not self._data.dotted_dotless_i end function Language:toJSON(opts) local entry_name, entry_name_patterns, entry_name_remove_diacritics = self._data.entry_name if entry_name then if entry_name.from then entry_name_patterns = {} for i, from in ipairs(entry_name.from) do insert(entry_name_patterns, {from = from, to = entry_name.to[i] or ""}) end end entry_name_remove_diacritics = entry_name.remove_diacritics end -- mainCode should only end up non-nil if dontCanonicalizeAliases is passed to make_object(). local ret = { ancestors = self:getAncestorCodes(), canonicalName = self:getCanonicalName(), categoryName = self:getCategoryName("nocap"), code = self._code, mainCode = self._mainCode, parent = self:getParentCode(), full = self:getFullCode(), entryNamePatterns = entry_name_patterns, entryNameRemoveDiacritics = entry_name_remove_diacritics, family = self:getFamilyCode(), aliases = self:getAliases(), varieties = self:getVarieties(), otherNames = self:getOtherNames(), scripts = self:getScriptCodes(), type = keys_to_list(self:getTypes()), wikimediaLanguages = self:getWikimediaLanguageCodes(), wikidataItem = self:getWikidataItem(), wikipediaArticle = self:getWikipediaArticle(true), } -- Use `deep_copy` when returning a table, so that there are no editing restrictions imposed by `mw.loadData`. return opts and opts.lua_table and deep_copy(ret) or to_json(ret, opts) end function export.getDataModuleName(code) local letter = match(code, "^(%l)%l%l?$") return "Module:" .. ( letter == nil and "languages/data/exceptional" or #code == 2 and "languages/data/2" or "languages/data/3/" .. letter ) end get_data_module_name = export.getDataModuleName function export.getExtraDataModuleName(code) return get_data_module_name(code) .. "/extra" end get_extra_data_module_name = export.getExtraDataModuleName do local function make_stack(data) local key_types = { [2] = "unique", aliases = "unique", otherNames = "unique", type = "append", varieties = "unique", wikipedia_article = "unique", wikimedia_codes = "unique" } local function __index(self, k) local stack, key_type = getmetatable(self), key_types[k] -- Data that isn't inherited from the parent. if key_type == "unique" then local v = stack[stack[make_stack]][k] if v == nil then local layer = stack[0] if layer then -- Could be false if there's no extra data. v = layer[k] end end return v -- Data that is appended by each generation. elseif key_type == "append" then local parts, offset, n = {}, 0, stack[make_stack] for i = 1, n do local part = stack[i][k] if part == nil then offset = offset + 1 else parts[i - offset] = part end end return offset ~= n and concat(parts, ",") or nil end local n = stack[make_stack] while true do local layer = stack[n] if not layer then -- Could be false if there's no extra data. return nil end local v = layer[k] if v ~= nil then return v end n = n - 1 end end local function __newindex() error("table is read-only") end local function __pairs(self) -- Iterate down the stack, caching keys to avoid duplicate returns. local stack, seen = getmetatable(self), {} local n = stack[make_stack] local iter, state, k, v = pairs(stack[n]) return function() repeat repeat k = iter(state, k) if k == nil then n = n - 1 local layer = stack[n] if not layer then -- Could be false if there's no extra data. return nil end iter, state, k = pairs(layer) end until not (k == nil or seen[k]) -- Get the value via a lookup, as the one returned by the -- iterator will be the raw value from the current layer, -- which may not be the one __index will return for that -- key. Also memoize the key in `seen` (even if the lookup -- returns nil) so that it doesn't get looked up again. -- TODO: store values in `self`, avoiding the need to create -- the `seen` table. The iterator will need to iterate over -- `self` with `next` first to find these on future loops. v, seen[k] = self[k], true until v ~= nil return k, v end end local __ipairs = require(table_module).indexIpairs function make_stack(data) local stack = { data, [make_stack] = 1, -- stores the length and acts as a sentinel to confirm a given metatable is a stack. __index = __index, __newindex = __newindex, __pairs = __pairs, __ipairs = __ipairs, } stack.__metatable = stack return setmetatable({}, stack), stack end return make_stack(data) end local function get_stack(data) local stack = getmetatable(data) return stack and type(stack) == "table" and stack[make_stack] and stack or nil end --[==[ <span style="color: #BA0000">This function is not for use in entries or other content pages.</span> Returns a blob of data about the language. The format of this blob is undocumented, and perhaps unstable; it's intended for things like the module's own unit-tests, which are "close friends" with the module and will be kept up-to-date as the format changes. If `extra` is set, any extra data in the relevant `/extra` module will be included. (Note that it will be included anyway if it has already been loaded into the language object.) If `raw` is set, then the returned data will not contain any data inherited from parent objects. -- Do NOT use these methods! -- All uses should be pre-approved on the talk page! ]==] function Language:getData(extra, raw) if extra then self:loadInExtraData() end local data = self._data -- If raw is not set, just return the data. if not raw then return data end local stack = get_stack(data) -- If there isn't a stack or its length is 1, return the data. Extra data (if any) will be included, as it's stored at key 0 and doesn't affect the reported length. if stack == nil then return data end local n = stack[make_stack] if n == 1 then return data end local extra = stack[0] -- If there isn't any extra data, return the top layer of the stack. if extra == nil then return stack[n] end -- If there is, return a new stack which has the top layer at key 1 and the extra data at key 0. data, stack = make_stack(stack[n]) stack[0] = extra return data end function Language:loadInExtraData() -- Only full languages have extra data. if not self:hasType("language", "full") then return end local data = self._data -- If there's no stack, create one. local stack = get_stack(self._data) if stack == nil then data, stack = make_stack(data) -- If already loaded, return. elseif stack[0] ~= nil then return end self._data = data -- Load extra data from the relevant module and add it to the stack at key 0, so that the __index and __pairs metamethods will pick it up, since they iterate down the stack until they run out of layers. local code = self._code local modulename = get_extra_data_module_name(code) -- No data cached as false. stack[0] = modulename and load_data(modulename)[code] or false end --[==[Returns the name of the module containing the language's data. Currently, this is always [[Module:scripts/data]].]==] function Language:getDataModuleName() local name = self._dataModuleName if name == nil then name = self:hasType("etymology-only") and etymology_languages_data_module or get_data_module_name(self._mainCode or self._code) self._dataModuleName = name end return name end --[==[Returns the name of the module containing the language's data. Currently, this is always [[Module:scripts/data]].]==] function Language:getExtraDataModuleName() local name = self._extraDataModuleName if name == nil then name = not self:hasType("etymology-only") and get_extra_data_module_name(self._mainCode or self._code) or false self._extraDataModuleName = name end return name or nil end function export.makeObject(code, data, dontCanonicalizeAliases) local data_type = type(data) if data_type ~= "table" then error(("bad argument #2 to 'makeObject' (table expected, got %s)"):format(data_type)) end -- Convert any aliases. local input_code = code code = normalize_code(code) input_code = dontCanonicalizeAliases and input_code or code local parent if data.parent then parent = get_by_code(data.parent, nil, true, true) else parent = Language end parent.__index = parent local lang = {_code = input_code} -- This can only happen if dontCanonicalizeAliases is passed to make_object(). if code ~= input_code then lang._mainCode = code end local parent_data = parent._data if parent_data == nil then -- Full code is the same as the code. lang._fullCode = parent._code or code else -- Copy full code. lang._fullCode = parent._fullCode local stack = get_stack(parent_data) if stack == nil then parent_data, stack = make_stack(parent_data) end -- Insert the input data as the new top layer of the stack. local n = stack[make_stack] + 1 data, stack[n], stack[make_stack] = parent_data, data, n end lang._data = data return setmetatable(lang, parent) end make_object = export.makeObject end --[==[Finds the language whose code matches the one provided. If it exists, it returns a <code class="nf">Language</code> object representing the language. Otherwise, it returns {{code|lua|nil}}, unless <code class="n">paramForError</code> is given, in which case an error is generated. If <code class="n">paramForError</code> is {{code|lua|true}}, a generic error message mentioning the bad code is generated; otherwise <code class="n">paramForError</code> should be a string or number specifying the parameter that the code came from, and this parameter will be mentioned in the error message along with the bad code. If <code class="n">allowEtymLang</code> is specified, etymology-only language codes are allowed and looked up along with normal language codes. If <code class="n">allowFamily</code> is specified, language family codes are allowed and looked up along with normal language codes.]==] function export.getByCode(code, paramForError, allowEtymLang, allowFamily) -- Track uses of paramForError, ultimately so it can be removed, as error-handling should be done by [[Module:parameters]], not here. if paramForError ~= nil then track("paramForError") end if type(code) ~= "string" then local typ if not code then typ = "nil" elseif check_object("language", true, code) then typ = "a language object" elseif check_object("family", true, code) then typ = "a family object" else typ = "a " .. type(code) end error("The function getByCode expects a string as its first argument, but received " .. typ .. ".") end local m_data = load_data(languages_data_module) if m_data.aliases[code] or m_data.track[code] then track(code) end local norm_code = normalize_code(code) -- Get the data, checking for etymology-only languages if allowEtymLang is set. local data = load_data(get_data_module_name(norm_code))[norm_code] or allowEtymLang and load_data(etymology_languages_data_module)[norm_code] -- If no data was found and allowFamily is set, check the family data. If the main family data was found, make the object with [[Module:families]] instead, as family objects have different methods. However, if it's an etymology-only family, use make_object in this module (which handles object inheritance), and the family-specific methods will be inherited from the parent object. if data == nil and allowFamily then data = load_data("Module:families/data")[norm_code] if data ~= nil then if data.parent == nil then return make_family_object(norm_code, data) elseif not allowEtymLang then data = nil end end end local retval = code and data and make_object(code, data) if not retval and paramForError then require("Module:languages/errorGetBy").code(code, paramForError, allowEtymLang, allowFamily) end return retval end get_by_code = export.getByCode --[==[Finds the language whose canonical name (the name used to represent that language on Wiktionary) or other name matches the one provided. If it exists, it returns a <code class="nf">Language</code> object representing the language. Otherwise, it returns {{code|lua|nil}}, unless <code class="n">paramForError</code> is given, in which case an error is generated. If <code class="n">allowEtymLang</code> is specified, etymology-only language codes are allowed and looked up along with normal language codes. If <code class="n">allowFamily</code> is specified, language family codes are allowed and looked up along with normal language codes. The canonical name of languages should always be unique (it is an error for two languages on Wiktionary to share the same canonical name), so this is guaranteed to give at most one result. This function is powered by [[Module:languages/canonical names]], which contains a pre-generated mapping of full-language canonical names to codes. It is generated by going through the [[:Category:Language data modules]] for full languages. When <code class="n">allowEtymLang</code> is specified for the above function, [[Module:etymology languages/canonical names]] may also be used, and when <code class="n">allowFamily</code> is specified for the above function, [[Module:families/canonical names]] may also be used.]==] function export.getByCanonicalName(name, errorIfInvalid, allowEtymLang, allowFamily) local byName = load_data("Module:languages/canonical names") local code = byName and byName[name] if not code and allowEtymLang then byName = load_data("Module:etymology languages/canonical names") code = byName and byName[name] or byName[gsub(name, " [Ss]ubstrate$", "")] or byName[gsub(name, "^a ", "")] or byName[gsub(name, "^a ", ""):gsub(" [Ss]ubstrate$", "")] or -- For etymology families like "ira-pro". -- FIXME: This is not ideal, as it allows " languages" to be appended to any etymology-only language, too. byName[match(name, "^(.*) languages$")] end if not code and allowFamily then byName = load_data("Module:families/canonical names") code = byName[name] or byName[match(name, "^(.*) languages$")] end local retval = code and get_by_code(code, errorIfInvalid, allowEtymLang, allowFamily) if not retval and errorIfInvalid then require("Module:languages/errorGetBy").canonicalName(name, allowEtymLang, allowFamily) end return retval end --[==[Used by [[Module:languages/data/2]] (et al.) and [[Module:etymology languages/data]], [[Module:families/data]], [[Module:scripts/data]] and [[Module:writing systems/data]] to finalize the data into the format that is actually returned.]==] function export.finalizeData(data, main_type, variety) local fields = {"type"} if main_type == "language" then insert(fields, 4) -- script codes insert(fields, "ancestors") insert(fields, "link_tr") insert(fields, "override_translit") insert(fields, "wikimedia_codes") elseif main_type == "script" then insert(fields, 3) -- writing system codes end -- Families and writing systems have no extra fields to process. local fields_len = #fields for _, entity in next, data do if variety then -- Move parent from 3 to "parent" and family from "family" to 3. These are different for the sake of convenience, since very few varieties have the family specified, whereas all of them have a parent. entity.parent, entity[3], entity.family = entity[3], entity.family -- Give the type "regular" iff not a variety and no other types are assigned. elseif not (entity.type or entity.parent) then entity.type = "regular" end for i = 1, fields_len do local key = fields[i] local field = entity[key] if field and type(field) == "string" then entity[key] = gsub(field, "%s*,%s*", ",") end end end return data end --[==[For backwards compatibility only; modules should require the error themselves.]==] function export.err(lang_code, param, code_desc, template_tag, not_real_lang) return require("Module:languages/error")(lang_code, param, code_desc, template_tag, not_real_lang) end return export nutqytv8ahytd26v0jsf3or17u2wkj1 828 5908 17395 17319 2026-07-13T08:16:05Z Hiyuune 6766 17395 Scribunto text/plain local labels = {} local raw_categories = {} local handlers = {} local raw_handlers = {} local subpages = { -- It should not matter much what order we do the handlers in, but topic handling historically -- preceded "poscatboiler" handling (i.e. everything else), so keep it that way for the moment. "languages", "miscellaneous", "wiktionary maintenance", "wiktionary users", } -- Import subpages for _, subpage in ipairs(subpages) do local datamodule = "Module:category tree/" .. subpage local retval = require(datamodule) if retval["LABELS"] then for label, data in pairs(retval["LABELS"]) do if labels[label] and not retval["IGNOREDUP"] then error("Label " .. label .. " defined in both [[" .. datamodule .. "]] and [[" .. labels[label].module .. "]].") end data.module = datamodule labels[label] = data end end if retval["RAW_CATEGORIES"] then for category, data in pairs(retval["RAW_CATEGORIES"]) do if raw_categories[category] and not retval["IGNOREDUP"] then error("Raw category " .. category .. " defined in both [[" .. datamodule .. "]] and [[" .. raw_categories[category].module .. "]].") end data.module = datamodule raw_categories[category] = data end end if retval["HANDLERS"] then for _, handler in ipairs(retval["HANDLERS"]) do table.insert(handlers, { module = datamodule, handler = handler }) end end if retval["RAW_HANDLERS"] then for _, handler in ipairs(retval["RAW_HANDLERS"]) do table.insert(raw_handlers, { module = datamodule, handler = handler }) end end end -- Add child categories to their parents local function add_children_to_parents(hierarchy, raw) for key, data in pairs(hierarchy) do local parents = data.parents if parents then if type(parents) ~= "table" then parents = {parents} end if parents.name or parents.module then parents = {parents} end for _, parent in ipairs(parents) do if type(parent) ~= "table" or not parent.name and not parent.module then parent = {name = parent} end if parent.name and not parent.module and type(parent.name) == "string" and not parent.name:find("^Category:") then local parent_is_raw if raw then parent_is_raw = not parent.is_label else parent_is_raw = parent.raw end -- Don't do anything if the child is raw and the parent is lang-specific, otherwise e.g. -- "Lemmas subcategories by language" will be listed as a child of every "LANG lemmas" category. -- FIXME: We need to rethink this mechanism. if not raw or parent_is_raw then local child_hierarchy = parent_is_raw and raw_categories or labels if child_hierarchy[parent.name] then local child = {name = key, sort = parent.sort, raw = raw} if child_hierarchy[parent.name].children then table.insert(child_hierarchy[parent.name].children, child) else child_hierarchy[parent.name].children = {child} end end end end end end end end add_children_to_parents(labels) add_children_to_parents(raw_categories, true) return { LABELS = labels, RAW_CATEGORIES = raw_categories, HANDLERS = handlers, RAW_HANDLERS = raw_handlers } 5cposu2ohi51cpo2zekz21qhe5wu1wi 828 5912 17449 17278 2026-07-13T08:51:48Z Hiyuune 6766 + function: physical_to_logical_pagename_if_mammoth 17449 Scribunto text/plain local export = {} local string_utilities_module = "Module:string utilities" local concat = table.concat local find = string.find local format = string.format local getmetatable = getmetatable local get_current_section -- defined below local get_namespace_shortcut -- defined below local get_pagetype -- defined below local gsub = string.gsub local insert = table.insert local is_internal_title -- defined below local is_title -- defined below local lower = string.lower local match = string.match local new_title = mw.title.new local require = require local sub = string.sub local title_equals = mw.title.equals local tonumber = tonumber local type = type local ufind = mw.ustring.find local unstrip_nowiki = mw.text.unstripNoWiki --[==[ Loaders for functions in other modules, which overwrite themselves with the target function when called. This ensures modules are only loaded when needed, retains the speed/convenience of locally-declared pre-loaded functions, and has no overhead after the first call, since the target functions are called directly in any subsequent calls.]==] local function decode_entities(...) decode_entities = require(string_utilities_module).decode_entities return decode_entities(...) end local function ulower(...) ulower = require(string_utilities_module).lower return ulower(...) end local function trim(...) trim = require(string_utilities_module).trim return trim(...) end --[==[ Loaders for objects, which load data (or some other object) into some variable, which can then be accessed as "foo or get_foo()", where the function get_foo sets the object to "foo" and then returns it. This ensures they are only loaded when needed, and avoids the need to check for the existence of the object each time, since once "foo" has been set, "get_foo" will not be called again.]==] local current_frame local function get_current_frame() current_frame, get_current_frame = mw.getCurrentFrame(), nil return current_frame end local parent_frame local function get_parent_frame() parent_frame, get_parent_frame = (current_frame or get_current_frame()):getParent(), nil return parent_frame end local namespace_shortcuts local function get_namespace_shortcuts() namespace_shortcuts, get_namespace_shortcuts = { [4] = "WT", [10] = "T", [14] = "CAT", [100] = "AP", [110] = "WS", [118] = "RC", [828] = "MOD", }, nil return namespace_shortcuts end do local transcluded --[==[ Returns {true} if the current {{tl|#invoke:}} is being transcluded, or {false} if not. If the current {{tl|#invoke:}} is part of a template, for instance, this template will therefore return {true}. Note that if a template containing an {{tl|#invoke:}} is used on its own page (e.g. to display a demonstration), this function is still able to detect that this is transclusion. This is an improvement over the other method for detecting transclusion, which is to check the parent frame title against the current page title, which fails to detect transclusion in that instance.]==] function export.is_transcluded() if transcluded == nil then transcluded = (parent_frame or get_parent_frame()) and parent_frame:preprocess("<includeonly>1</includeonly>") == "1" or false end return transcluded end end do local preview --[==[ Returns {true} if the page is currently being viewed in preview, or {false} if not.]==] function export.is_preview() if preview == nil then preview = (current_frame or get_current_frame()):preprocess("{{REVISIONID}}") == "" end return preview end end --[==[ Returns {true} if the input is a title object, or {false} if not. This therefore '''includes''' external title objects (i.e. those for pages on other wikis), such as [[w:Example]], unlike `is_internal_title` below.]==] function export.is_title(val) if not (val and type(val) == "table") then return false end local mt = getmetatable(val) -- There's no foolproof method for checking for a title object, but the -- __eq metamethod should be mw.title.equals unless the object has been -- seriously messed around with. return mt and type(mt) == "table" and getmetatable(mt) == nil and mt.__eq == title_equals and true or false end is_title = export.is_title --[==[ Returns {true} if the input is an internal title object, or {false} if not. An internal title object is a title object for a page on this wiki, such as [[example]]. This therefore '''excludes''' external title objects (i.e. those for pages on other wikis), such as [[w:Example]], unlike `is_title` above.]==] function export.is_internal_title(title) -- Note: Mainspace titles starting with "#" should be invalid, but a bug in mw.title.new and mw.title.makeTitle means a title object is returned that has the empty string for prefixedText, so they need to be filtered out. return is_title(title) and #title.prefixedText > 0 and #title.interwiki == 0 end is_internal_title = export.is_internal_title --[==[ Returns {true} if the input string is a valid link target, or {false} if not. This therefore '''includes''' link targets to other wikis, such as [[w:Example]], unlike `is_valid_page_name` below.]==] function export.is_valid_link_target(target) local target_type = type(target) if target_type == "string" then return is_title(new_title(target)) end error(format("bad argument #1 to 'is_valid_link_target' (string expected, got %s)", target_type), 2) end --[==[ Returns {true} if the input string is a valid page name on this wiki, or {false} if not. This therefore '''excludes''' page names on other wikis, such as [[w:Example]], unlike `is_valid_link_target` above.]==] function export.is_valid_page_name(name) local name_type = type(name) if name_type == "string" then return is_internal_title(new_title(name)) end error(format("bad argument #1 to 'is_valid_page_name' (string expected, got %s)", name_type), 2) end --[==[ Given a title object, returns a full link target which will always unambiguously link to it. For instance, the input {"foo"} (for the page [[foo]]) returns {":foo"}, as a leading colon always refers to mainspace, even when other namespaces might be assumed (e.g. when transcluding using `{{ }}` syntax). If `shortcut` is set, then the returned target will use the namespace shortcut, if any; for example, the title for `Template:foo` would return {"T:foo"} instead of {"Template:foo"}.]==] function export.get_link_target(title, shortcut) if not is_title(title) then error(format("bad argument #1 to 'is_valid_link_target' (title object expected, got %s)", type(title))) elseif title.interwiki ~= "" then return title.fullText elseif shortcut then local fragment = title.fragment if fragment == "" then return get_namespace_shortcut(title) .. ":" .. title.text end return get_namespace_shortcut(title) .. ":" .. title.text .. "#" .. fragment elseif title.namespace == 0 then return ":" .. title.fullText end return title.fullText end do local function find_sandbox(text) return find(text, "^User:.") or find(lower(text), "sandbox", 1, true) end local function get_transclusion_subtypes(title, main_type, documentation, page_suffix) local text, subtypes = title.text, {main_type} -- Any template/module with "sandbox" in the title. These are impossible -- to screen for more accurately, as there's no consistent pattern. Also -- any user sandboxes in the form (e.g.) "Template:User:...". local sandbox = find_sandbox(text) if sandbox then insert(subtypes, "sandbox") end -- Any template/module testcases (which can be labelled and/or followed -- by further subpages). local testcase = find(text, "./[Tt]estcases?%f[%L]") if testcase then -- Order "testcase" and "sandbox" based on where the patterns occur -- in the title. local n = sandbox and sandbox < testcase and 3 or 2 insert(subtypes, n, "testcase") end -- Any template/module documentation pages. if documentation then insert(subtypes, "documentation") end local final = subtypes[#subtypes] if not (final == main_type and not page_suffix or final == "sandbox") then insert(subtypes, "page") end return concat(subtypes, " ") end local function get_snippet_subtypes(title, main_type, documentation) local ns = title.namespace return get_transclusion_subtypes(title, ( ns == 2 and "user " or ns == 8 and match(title.text, "^Gadget-.") and "gadget " or "" ) .. main_type, documentation) end --[==[ Returns the page type of the input title object in a format which can be used in running text.]==] function export.get_pagetype(title) if not is_internal_title(title) then error(mw.dumpObject(title.fullText) .. " is not a valid page name.") end -- If possibly a documentation page, get the base title and set the -- `documentation` flag. local content_model, text, documentation = title.contentModel if content_model == "wikitext" then text = title.text if title.isSubpage and title.subpageText == "documentation" then local base_title = title.basePageTitle if base_title then title, content_model, text, documentation = base_title, base_title.contentModel, base_title.text, true end end end -- Content models have overriding priority, as they can appear in -- nonstandard places due to page content model changes. if content_model == "css" or content_model == "sanitized-css" then return get_snippet_subtypes(title, "stylesheet", documentation) elseif content_model == "javascript" then return get_snippet_subtypes(title, "script", documentation) elseif content_model == "json" then return get_snippet_subtypes(title, "JSON data", documentation) elseif content_model == "MassMessageListContent" then return get_snippet_subtypes(title, "mass message delivery list", documentation) -- Modules. elseif content_model == "Scribunto" then return get_transclusion_subtypes(title, "module", documentation, false) elseif content_model == "text" then return "page" -- ??? -- Otherwise, the content model is "wikitext", so check namespaces. elseif title.isTalkPage then return "talk page" end local ns = title.namespace -- Main namespace. if ns == 0 then return "entry" -- Wiktionary: elseif ns == 4 then return find_sandbox(title.text) and "sandbox" or "project page" -- Template: elseif ns == 10 then return get_transclusion_subtypes(title, "template", documentation, false) end -- Convert the namespace to lowercase, unless it contains a capital -- letter after the initial letter (e.g. MediaWiki, TimedText). Also -- normalize any underscores. local ns_text = gsub(title.nsText, "_", " ") if ufind(ns_text, "^%U*$", 2) then ns_text = ulower(ns_text) end -- User: if ns == 2 then return ns_text .. " " .. (title.isSubpage and "subpage" or "page") -- Category: and Appendix: elseif ns == 14 or ns == 100 then return ns_text -- Thesaurus: and Reconstruction: elseif ns == 110 or ns == 118 then return ns_text .. " entry" end return ns_text .. " page" end get_pagetype = export.get_pagetype end --[==[ Returns {true} if the input title object is for a content page, or {false} if not. A content page is a page that is considered part of the dictionary itself, and excludes pages for discussion, administration, maintenance etc.]==] function export.is_content_page(title) if not is_internal_title(title) then error(mw.dumpObject(title.fullText) .. " is not a valid page name.") end local ns = title.namespace -- (main), Appendix, Thesaurus, Citations, Reconstruction. return (ns == 0 or ns == 100 or ns == 110 or ns == 114 or ns == 118) and title.contentModel == "wikitext" end --[==[ Returns {true} if the input title object is for a documentation page, or {false} if not.]==] function export.is_documentation(title) return match(get_pagetype(title), "%f[%w]documentation%f[%W]") and true or false end --[==[ Returns {true} if the input title object is for a sandbox, or {false} if not. By default, sandbox documentation pages are excluded, but this can be overridden with the `include_documentation` parameter.]==] function export.is_sandbox(title, include_documentation) local pagetype = get_pagetype(title) return match(pagetype, "%f[%w]sandbox%f[%W]") and ( include_documentation or not match(pagetype, "%f[%w]documentation%f[%W]") ) and true or false end --[==[ Returns {true} if the input title object is for a testcase page, or {false} if not. By default, testcase documentation pages are excluded, but this can be overridden with the `include_documentation` parameter.]==] function export.is_testcase_page(title, include_documentation) local pagetype = get_pagetype(title) return match(pagetype, "%f[%w]testcase%f[%W]") and ( include_documentation or not match(pagetype, "%f[%w]documentation%f[%W]") ) and true or false end --[==[ Returns the namespace shortcut for the input title object, or else the namespace text. For example, a `Template:` title returns {"T"}, a `Module:` title returns {"MOD"}, and a `User:` title returns {"User"}.]==] function export.get_namespace_shortcut(title) return (namespace_shortcuts or get_namespace_shortcuts())[title.namespace] or title.nsText end get_namespace_shortcut = export.get_namespace_shortcut do local function check_level(lvl) if type(lvl) ~= "number" then error("Heading levels must be numbers.") elseif lvl < 1 or lvl > 6 or lvl % 1 ~= 0 then error("Heading levels must be integers between 1 and 6.") end return lvl end --[==[ A helper function which iterates over the headings in `text`, which should be the content of a page or (main) section. Each iteration returns three values: `sec` (the section title), `lvl` (the section level) and `loc` (the index of the section in the given text, from the first equals sign). The section title will be automatically trimmed, and any HTML entities will be resolved. The optional parameter `a` (which should be an integer between 1 and 6) can be used to ensure that only headings of the specified level are iterated over. If `b` is also given, then they are treated as a range. The optional parameters `a` and `b` can be used to specify a range, so that only headings with levels in that range are returned.]==] local function find_headings(text, a, b) a = a and check_level(a) or nil b = b and check_level(b) or a or nil local start, loc, lvl, sec = 1 return function() repeat loc, lvl, sec, start = match(text, "()%f[^%z\n](==?=?=?=?=?)([^\n]+)%2[\t ]*%f[%z\n]()", start) lvl = lvl and #lvl until not (sec and a) or (lvl >= a and lvl <= b) return sec and trim(decode_entities(sec)) or nil, lvl, loc end end local function _get_section(content, name, level) if not (content and name) then return nil elseif find(name, "\n", 1, true) then error("Heading name cannot contain a newline.") end level = level and check_level(level) or nil name = trim(decode_entities(name)) local start for sec, lvl, loc in find_headings(content, level and 1 or nil, level) do if start and lvl <= level then return sub(content, start, loc - 1) elseif not start and (not level or lvl == level) and sec == name then start, level = loc, lvl end end return start and sub(content, start) end --[==[ A helper function to return the content of a page section. `content` is raw wikitext, `name` is the requested section, and `level` is an optional parameter that specifies the required section heading level. If `level` is not supplied, then the first section called `name` is returned. `name` can either be a string or table of section names. If a table, each name represents a section that has the next as a subsection. For example, { {"Spanish", "Noun"}} will return the first matching section called "Noun" under a section called "Spanish". These do not have to be at adjacent levels ("Noun" might be L4, while "Spanish" is L2). If `level` is given, it refers to the last name in the table (i.e. the name of the section to be returned). The returned section includes all of its subsections. If no matching section is found, return {nil}.]==] function export.get_section(content, names, level) if type(names) ~= "table" then return _get_section(content, names, level) end local i = 1 local name = names[i] if not name then error("Must specify at least 1 section.") end while true do local nxt_i = i + 1 local nxt = names[nxt_i] if nxt == nil then return _get_section(content, name, level) end content = _get_section(content, name) if content == nil then return nil elseif i == 6 then error("Not possible specify more than 6 sections: headings only go up to level 6.") end i = nxt_i name = names[i] end return content end end --[==[ Convert a physical pagename (or the current pagename, if {nil} is passed in) to its logical equivalent, but only if the physical pagename refers to one of the splits of a mammoth page such as [[a]]. Otherwise this simply returns the subpage (the part after the last slash in namespace other than the main one, otherwise the same as passed in), unless `include_base` is specified, in which case the return value will be the whole pagename minus the namespace, including the base (the part before the final slash). FIXME: This should be augmented with logic to handle unsupported titles, which is currently in process_page() in [[Module:headword/page]], so that it is a general physical-to-logical conversion function. Examples: * {physical_to_logical_pagename_if_mammoth("a")} → {"a"} * {physical_to_logical_pagename_if_mammoth("a/languages A to L")} → {"a"} (since [[a]] is marked as a mammoth page in [[Module:links/data]]) * {physical_to_logical_pagename_if_mammoth("50/50")} → {"50/50"} (since [[50/50]] is in the main namespace) * {physical_to_logical_pagename_if_mammoth("Appendix:Lojban/a")} → "a" * {physical_to_logical_pagename_if_mammoth("Appendix:Lojban/a", true)} → "Lojban/a" * {physical_to_logical_pagename_if_mammoth("Reconstruction:Proto-Slavic/a")} → "a" * {physical_to_logical_pagename_if_mammoth("Reconstruction:Proto-Slavic/a", true)} → "Proto-Slavic/a" * {physical_to_logical_pagename_if_mammoth("User:Example/sandbox/foo")} → "foo" * {physical_to_logical_pagename_if_mammoth("User:Example/sandbox/foo", true)} → "Example/sandbox/foo" ]==] function export.physical_to_logical_pagename_if_mammoth(title, include_base) if title == nil then title = mw.title.getCurrentTitle() elseif not is_title(title) then title = mw.title.new(title) end if title.nsText == "" then -- Formerly we checked for the specific known subpages of a given mammoth split page, e.g. we would convert -- [[a/languages M to Z]] to [[a]] assuming that [[a/languages M to Z]] was one of the splits, but not -- [[a/languages N to Z]]. To simplify this, we just convert anything with the right mammoth split page format -- on the assumption that it's unlikely we will ever have a legitimate non-mammoth-split pagename of this sort. local pagename = title.text local mammoth_root_page = pagename:match("^(.*)/languages [A-Z] to [A-Z]$") if mammoth_root_page then pagename = mammoth_root_page end return pagename elseif include_base then return title.text else return title.subpageText end end --[==[ Obsolete name for `physical_to_logical_pagename_if_mammoth`. FIXME: Replace all uses and remove. ]==] function export.safe_page_name(title) return export.physical_to_logical_pagename_if_mammoth(title) end do local current_section --[==[ A function which returns the number of the page section which contains the current {#invoke}.]==] function export.get_current_section() if current_section ~= nil then return current_section end local extension_tag = (current_frame or get_current_frame()).extensionTag -- We determine the section via the heading strip marker count, since they're numbered sequentially, but the only way to do this is to generate a fake heading via frame:preprocess(). The native parser assigns each heading a unique marker, but frame:preprocess() will return copies of older markers if the heading is identical to one further up the page, so the fake heading has to be unique to the page. The best way to do this is to feed it a heading containing a nowiki marker (which we will need later), since those are always unique. local nowiki_marker = extension_tag(current_frame, "nowiki") -- Note: heading strip markers have a different syntax to the ones used for tags. local h = tonumber(match( current_frame:preprocess("=" .. nowiki_marker .. "="), "\127'\"`UNIQ%-%-h%-(%d+)%-%-QINU`\"'\127" )) -- For some reason, [[Special:ExpandTemplates]] doesn't generate a heading strip marker, so if that happens we simply abort early. if not h then return 0 end -- The only way to get the section number is to increment the heading count, so we store the offset in nowiki strip markers which can be retrieved by procedurally unstripping nowiki markers, counting backwards until we find a match. local n, offset = tonumber(match( nowiki_marker, "\127'\"`UNIQ%-%-nowiki%-([%dA-F]+)%-QINU`\"'\127" ), 16) while not offset and n > 0 do n = n - 1 offset = match( unstrip_nowiki(format("\127'\"`UNIQ--nowiki-%08X-QINU`\"'\127", n)), "^HEADING\1(%d+)" -- Prefix "HEADING\1" prevents collisions. ) end offset = offset and (offset + 1) or 0 extension_tag(current_frame, "nowiki", "HEADING\1" .. offset) current_section = h - offset return current_section end get_current_section = export.get_current_section end do local L2_sections, current_L2 local function get_L2_sections() L2_sections, get_L2_sections = mw.loadData("Module:headword/data").page.L2_sections, nil return L2_sections end --[==[ A function which returns the name of the L2 language section which contains the current {#invoke}.]==] function export.get_current_L2() if current_L2 ~= nil then return current_L2 or nil -- Return nil if current_L2 is false (i.e. there's no L2). end local section = get_current_section() while section > 0 do local L2 = (L2_sections or get_L2_sections())[section] if L2 then current_L2 = L2 return L2 end section = section - 1 end current_L2 = false return nil end end return export dflgelqwqn49uq9wx18x5vggpgn6t4j 828 5929 17441 17342 2026-07-13T08:47:43Z Hiyuune 6766 17441 Scribunto text/plain local new_title = mw.title.new local ucfirst = require("Module:string utilities").ucfirst local split = require("Module:string utilities").split local raw_categories = {} local raw_handlers = {} local m_languages = require("Module:languages") local m_sc_getByCode = require("Module:scripts").getByCode local m_table = require("Module:table") local parse_utilities_module = "Module:parse utilities" local concat = table.concat local insert = table.insert local reverse_ipairs = m_table.reverseIpairs local serial_comma_join = m_table.serialCommaJoin local size = m_table.size local sorted_pairs = m_table.sortedPairs local to_json = require("Module:JSON").toJSON local Hang = m_sc_getByCode("Hang") local Hani = m_sc_getByCode("Hani") local Hira = m_sc_getByCode("Hira") local Hrkt = m_sc_getByCode("Hrkt") local Kana = m_sc_getByCode("Kana") local function track(page) -- [[Special:WhatLinksHere/Wiktionary:Tracking/category tree/languages/PAGE]] return require("Module:debug/track")("category tree/languages/" .. page) end -- This handles language categories of the form e.g. [[:Category:French language]] and -- [[:Category:British Sign Language]]; categories like [[:Category:Languages of Indonesia]]; categories like -- [[:Category:English-based creole or pidgin languages]]; and categories like -- [[:Category:English-based constructed languages]]. ----------------------------------------------------------------------------- -- -- -- RAW CATEGORIES -- -- -- ----------------------------------------------------------------------------- raw_categories["Reo"] = { topright = "{{commonscat|Languages}}\n[[File:Languages world map-transparent background.svg|thumb|right|250px|Rough world map of language families]]", description = "This category contains the categories for every language on Wiktionary.", additional = "Not all languages that Wiktionary recognises may have a category here yet. There are many that have " .. "not yet received any attention from editors, mainly because not all Wiktionary users know about every single " .. "language. See [[Wiktionary:List of languages]] for a full list.", parents = { "Whakaraparapa", }, } raw_categories["All extinct languages"] = { description = "This category contains the categories for every [[extinct language]] on Wiktionary.", additional = "Do not confuse this category with [[:Category:Extinct languages]], which is an umbrella category for the names of extinct languages in specific other languages (e.g. {{m+|de|Langobardisch}} for the ancient [[Lombardic]] language).", parents = { "Reo", }, } raw_categories["Languages by country"] = { topright = "{{commonscat|Languages by continent}}", description = "Categories that group languages by country.", additional = "{{{umbrella_meta_msg}}}", parents = { "Reo", }, } raw_categories["Language isolates"] = { topright = "{{wikipedia|Language isolate}}\n{{commonscat|Language isolates}}", description = "Languages with no known relatives.", parents = { {name = "Languages by family", sort = "*Isolates"}, {name = "All language families", sort = "Isolates"}, }, } raw_categories["Languages not sorted into a location category"] = { description = "Languages which do not specify (in their {{tl|auto cat}} call) the location(s) where they are spoken.", additional = "This excludes constructed and reconstructed languages; as a result, all languages in this category explicitly specify their location as {{cd|UNKNOWN}}.", parents = { {name = "Requests"}, }, hidden = true, } ----------------------------------------------------------------------------- -- -- -- RAW HANDLERS -- -- -- ----------------------------------------------------------------------------- -- Given a category (without the "Category:" prefix), look up the page defining the category, find the call to -- {{auto cat}} (if any), and return a table of its arguments. If the category page doesn't exist or doesn't have -- an {{auto cat}} invocation, return nil. -- -- FIXME: Duplicated in [[Module:category tree/lects]]. local function scrape_category_for_auto_cat_args(cat) local cat_page = mw.title.new("Category:" .. cat) if cat_page then local contents = cat_page:getContent() if contents then local frame = mw.getCurrentFrame() for template in require("Module:template parser").find_templates(contents) do -- The template parser automatically handles redirects and canonicalizes them, so uses of {{autocat}} -- will also be found. if template:get_name() == "auto cat" then return template:get_arguments() end end end end return nil end local function link_location(location) local location_no_the = location:match("^the (.*)$") local bare_location = location_no_the or location local location_link local bare_location_parts = split(bare_location, ", ") for i, part in ipairs(bare_location_parts) do bare_location_parts[i] = ("[[%s]]"):format(part) end location_link = concat(bare_location_parts, ", ") if location_no_the then location_link = "the " .. location_link end return location_link end local function linkbox(lang, setwiki, setwikt, setsister, entryname) local wiktionarylinks = {} local canonicalName = lang:getCanonicalName() local wikimediaLanguages = lang:getWikimediaLanguages() local wikipediaArticle = setwiki or lang:getWikipediaArticle() setsister = setsister and ucfirst(setsister) or nil if setwikt then track("setwikt") if setwikt == "-" then track("setwikt/hyphen") end end if setwikt ~= "-" and wikimediaLanguages and wikimediaLanguages[1] then for _, wikimedialang in ipairs(wikimediaLanguages) do local check = new_title(wikimedialang:getCode() .. ":") if check and check.isExternal then insert(wiktionarylinks, (wikimedialang:getCanonicalName() ~= canonicalName and "(''" .. wikimedialang:getCanonicalName() .. "'') " or "") .. "'''[[:" .. wikimedialang:getCode() .. ":|" .. wikimedialang:getCode() .. ".wiktionary.org]]'''") end end wiktionarylinks = concat(wiktionarylinks, "<br/>") end local wikt_plural = wikimediaLanguages[2] and "s" or "" if #wiktionarylinks == 0 then wiktionarylinks = "''None.''" end if setsister then track("setsister") if setsister == "-" then track("setsister/hyphen") else setsister = "Category:" .. setsister end else setsister = lang:getCommonsCategory() or "-" end return concat{ [=[<div class="wikitable" style="float: right; clear: right; margin: 0 0 0.5em 1em; width: 300px; padding: 5px;"> <div style="text-align: center; margin-bottom: 10px; margin-top: 5px">''']=], canonicalName, [=[ language links'''</div> {| style="font-size: 90%" |- | style="vertical-align: top; height: 35px; border-bottom: 1px solid lightgray;" | [[File:Wikipedia-logo.png|35px|none|Wikipedia]] | style="border-bottom: 1px solid lightgray;" | '''English Wikipedia''' has an article on: <div style="padding: 5px 10px">]=], (setwiki == "-" and "''None.''" or "'''[[w:" .. wikipediaArticle .. "|" .. wikipediaArticle .. "]]'''"), [=[</div> |- | style="vertical-align: top; height: 35px; border-bottom: 1px solid lightgray;" | [[File:Wikimedia-logo.svg|35px|none|Wikimedia Commons]] | style="border-bottom: 1px solid lightgray;" | '''Wikimedia Commons''' has links to ]=], canonicalName, [=[-related content in sister projects: <div style="padding: 5px 10px">]=], (setsister == "-" and "''None.''" or "'''[[commons:" .. setsister .. "|" .. setsister .. "]]'''"), [=[</div> |- | style="vertical-align: top; height: 35px; width: 40px; border-bottom: 1px solid lightgray;" | [[File:Wiktionary-logo-v2.svg|35px|none|Wiktionary]] |style="border-bottom: 1px solid lightgray;" | '''Wiktionary edition''']=], wikt_plural, [=[ written in ]=], canonicalName, [=[: <div style="padding: 5px 10px">]=], wiktionarylinks, [=[</div> |- | style="vertical-align: top; height: 35px; border-bottom: 1px solid lightgray;" | [[File:Open book nae 02.svg|35px|none|Entry]] | style="border-bottom: 1px solid lightgray;" | '''Wiktionary entry''' for the language's English name: <div style="padding: 5px 10px">''']=], require("Module:links").full_link({lang = m_languages.getByCode("en"), term = entryname or canonicalName}), [=['''</div> |- | style="vertical-align: top; height: 35px;" | [[File:Crystal kfind.png|35px|none|Considerations]] || '''Wiktionary resources''' for editors contributing to ]=], canonicalName, [=[ entries: <div style="padding: 5px 0"> * '''[[Wiktionary:]=], canonicalName, [=[ entry guidelines]]''' * '''[[:Category:]=], canonicalName, [=[ reference templates|Reference templates]] ({{PAGESINCAT:]=], canonicalName, [=[ reference templates}})''' * '''[[Appendix:]=], canonicalName, [=[ bibliography|Bibliography]]''' |} </div>]=] } end local function edit_link(title, text) return '<span class="plainlinks">[' .. tostring(mw.uri.fullUrl(title, { action = "edit" })) .. ' ' .. text .. ']</span>' end -- Should perhaps use wiki syntax. local function infobox(lang) local ret = {} insert(ret, '<table class="wikitable language-category-info"') local raw_data = lang:getData("extra") if raw_data then local replacements = { [1] = "canonical-name", [2] = "wikidata-item", [3] = "family", [4] = "scripts", } local function replacer(letter1, letter2) return letter1:lower() .. "-" .. letter2:lower() end -- For each key in the language data modules, returns a descriptive -- kebab-case version (containing ASCII lowercase words separated -- by hyphens). local function kebab_case(key) key = replacements[key] or key key = key:gsub("(%l)(%u)", replacer):gsub("(%l)_(%l)", replacer) return key end local compress = {compress = true} local function html_attribute_encode(str) str = to_json(str, compress) :gsub('"', "&quot;") -- & in attributes is automatically escaped. -- :gsub("&", "&amp;") :gsub("<", "&lt;") :gsub(">", "&gt;") return str end insert(ret, ' data-code="' .. lang:getCode() .. '"') for k, v in sorted_pairs(raw_data) do insert(ret, " data-" .. kebab_case(k) .. '="' .. html_attribute_encode(v) .. '"') end end insert(ret, '>\n') insert(ret, '<tr class="language-category-data">\n<th colspan="2">' .. edit_link(lang:getDataModuleName(), "Edit language data") .. "</th>\n</tr>\n") insert(ret, "<tr>\n<th>Canonical name</th><td>" .. lang:getCanonicalName() .. "</td>\n</tr>\n") local otherNames = lang:getOtherNames() if otherNames then local names = {} for _, name in ipairs(otherNames) do insert(names, "<li>" .. name .. "</li>") end if #names > 0 then insert(ret, "<tr>\n<th>Other names</th><td><ul>" .. concat(names, "\n") .. "</ul></td>\n</tr>\n") end end local aliases = lang:getAliases() if aliases then local names = {} for _, name in ipairs(aliases) do insert(names, "<li>" .. name .. "</li>") end if #names > 0 then insert(ret, "<tr>\n<th>Aliases</th><td><ul>" .. concat(names, "\n") .. "</ul></td>\n</tr>\n") end end local varieties = lang:getVarieties() if varieties then local names = {} for _, name in ipairs(varieties) do if type(name) == "string" then insert(names, "<li>" .. name .. "</li>") else assert(type(name) == "table") local first_var local subvars = {} for i, var in ipairs(name) do if i == 1 then first_var = var else insert(subvars, "<li>" .. var .. "</li>") end end if #subvars > 0 then insert(names, "<li><dl><dt>" .. first_var .. "</dt>\n<dd><ul>" .. concat(subvars, "\n") .. "</ul></dd></dl></li>") elseif first_var then insert(names, "<li>" .. first_var .. "</li>") end end end if #names > 0 then insert(ret, "<tr>\n<th>Varieties</th><td><ul>" .. concat(names, "\n") .. "</ul></td>\n</tr>\n") end end insert(ret, "<tr>\n<th>[[Wiktionary:Languages|Language code]]</th><td><code>" .. lang:getCode() .. "</code></td>\n</tr>\n") insert(ret, "<tr>\n<th>[[Wiktionary:Families|Language family]]</th>\n") local fam = lang:getFamily() local famCode = fam and fam:getCode() if not fam then insert(ret, "<td>unclassified</td>") elseif famCode == "qfa-iso" then insert(ret, "<td>[[:Category:Language isolates|language isolate]]</td>") elseif famCode == "qfa-mix" then insert(ret, "<td>[[:Category:Mixed languages|mixed language]]</td>") elseif famCode == "sgn" then insert(ret, "<td>[[:Category:Sign languages|sign language]]</td>") elseif famCode == "crp" then insert(ret, "<td>[[:Category:Creole or pidgin languages|creole or pidgin]]</td>") elseif famCode == "art" then insert(ret, "<td>[[:Category:Constructed languages|constructed language]]</td>") else insert(ret, "<td>" .. fam:makeCategoryLink() .. "</td>") end insert(ret, "\n</tr>\n<tr>\n<th>Ancestors</th>\n<td>") local ancestors = lang:getAncestors() if ancestors[2] then local ancestorList = {} for i, anc in ipairs(ancestors) do ancestorList[i] = "<li>" .. anc:makeCategoryLink() .. "</li>" end insert(ret, "<ul>\n" .. concat(ancestorList, "\n") .. "</ul>") else local ancestorChain = lang:getAncestorChainOld() if ancestorChain[1] then local chain = {} for _, anc in reverse_ipairs(ancestorChain) do insert(chain, "<li>" .. anc:makeCategoryLink() .. "</li>") end insert(ret, "<ul>\n" .. concat(chain, "\n<ul>\n") .. ("</ul>"):rep(#chain)) else insert(ret, "unknown") end end insert(ret, "</td>\n</tr>\n") local scripts = lang:getScripts() if scripts[1] then local script_text = {} local function makeScriptLine(sc) local code = sc:getCode() local url = tostring(mw.uri.fullUrl('Special:Search', { search = 'contentmodel:css insource:"' .. code .. '" insource:/\\.' .. code .. '/', ns8 = '1' })) return sc:makeCategoryLink() .. ' (<span class="plainlinks" title="Search for stylesheets referencing this script">[' .. url .. ' <code>' .. code .. '</code>]</span>)' end local function add_Hrkt(text) insert(text, "<li>" .. makeScriptLine(Hrkt)) insert(text, "<ul>") insert(text, "<li>" .. makeScriptLine(Hira) .. "</li>") insert(text, "<li>" .. makeScriptLine(Kana) .. "</li>") insert(text, "</ul>") insert(text, "</li>") end for _, sc in ipairs(scripts) do local text = {} local code = sc:getCode() if code == "Hrkt" then add_Hrkt(text) else insert(text, "<li>" .. makeScriptLine(sc)) if code == "Jpan" then insert(text, "<ul>") insert(text, "<li>" .. makeScriptLine(Hani) .. "</li>") add_Hrkt(text) insert(text, "</ul>") elseif code == "Kore" then insert(text, "<ul>") insert(text, "<li>" .. makeScriptLine(Hang) .. "</li>") insert(text, "<li>" .. makeScriptLine(Hani) .. "</li>") insert(text, "</ul>") end insert(text, "</li>") end insert(script_text, concat(text, "\n")) end insert(ret, "<tr>\n<th>[[Wiktionary:Scripts|Scripts]]</th>\n<td><ul>\n" .. concat(script_text, "\n") .. "</ul></td>\n</tr>\n") else insert(ret, "<tr>\n<th>[[Wiktionary:Scripts|Scripts]]</th>\n<td>not specified</td>\n</tr>\n") end local function add_module_info(raw_data, heading) if raw_data then local scripts = lang:getScriptCodes() local module_info, add = {}, false if type(raw_data) == "string" then insert(module_info, ("[[Module:%s]]"):format(raw_data)) add = true else local raw_data_type = type(raw_data) if raw_data_type == "table" and size(scripts) == 1 and type(raw_data[scripts[1]]) == "string" then insert(module_info, ("[[Module:%s]]"):format(raw_data[scripts[1]])) add = true elseif raw_data_type == "table" then insert(module_info, "<ul>") for script, data in sorted_pairs(raw_data) do if type(data) == "string" and m_sc_getByCode(script) then insert(module_info, ("<li><code>%s</code>: [[Module:%s]]</li>"):format(script, data)) end end insert(module_info, "</ul>") add = size(module_info) > 2 end end if add then insert(ret, [=[ <tr> <th>]=] .. heading .. [=[</th> <td>]=] .. concat(module_info) .. [=[</td> </tr> ]=]) end end end add_module_info(raw_data.generate_forms, "Form-generating<br>module") add_module_info(raw_data.translit, "[[Wiktionary:Transliteration and romanization|Transliteration<br>module]]") add_module_info(raw_data.display_text, "Display text<br>module") add_module_info(raw_data.entry_name, "Entry name<br>module") add_module_info(raw_data.sort_key, "[[sortkey|Sortkey]]<br>module") local wikidataItem = lang:getWikidataItem() if lang:getWikidataItem() and mw.wikibase then local URL = mw.wikibase.getEntityUrl(wikidataItem) local link if URL then link = '[' .. URL .. ' ' .. wikidataItem .. ']' else link = '<span class="error">Invalid Wikidata item: <code>' .. wikidataItem .. '</code></span>' end insert(ret, "<tr><th>Wikidata</th><td>" .. link .. "</td></tr>") end insert(ret, "</table>") return concat(ret) end local function NavFrame(content, title) return '<div class="NavFrame"><div class="NavHead">' .. (title or '{{{title}}}') .. '</div>' .. '<div class="NavContent" style="text-align: left;">' .. content .. '</div></div>' end local function get_description_topright_additional(lang, locations, extinct, setwiki, setwikt, setsister, entryname) local nameWithLanguage = lang:getCategoryName("nocap") if lang:getCode() == "und" then local description = "This is the main category of the '''" .. nameWithLanguage .. "''', represented in Wiktionary by the [[Wiktionary:Languages|code]] '''" .. lang:getCode() .. "'''. " .. "This language contains terms in historical writing, whose meaning has not yet been determined by scholars." return description, nil, nil end local canonicalName = lang:getCanonicalName() local topright = linkbox(lang, setwiki, setwikt, setsister, entryname) local the_prefix if canonicalName:find(" Language$") then the_prefix = "" else the_prefix = "the " end local description = "This is the main category of " .. the_prefix .. "'''" .. nameWithLanguage .. "'''." local location_links = {} local prep local saw_embedded_comma = false for _, location in ipairs(locations) do local this_prep if location == "the world" then this_prep = "across" insert(location_links, location) elseif location ~= "UNKNOWN" then this_prep = "in" if location:find(",") then saw_embedded_comma = true end insert(location_links, link_location(location)) end if this_prep then if prep and this_prep ~= prep then error("Can't handle location 'the world' along with another location (clashing prepositions)") end prep = this_prep end end local location_desc if #location_links > 0 then local location_link_text if saw_embedded_comma and #location_links >= 3 then location_link_text = mw.text.listToText(location_links, "; ", "; and ") else location_link_text = serial_comma_join(location_links) end location_desc = ("It is %s %s %s.\n\n"):format( extinct and "an [[extinct language]] that was formerly spoken" or "spoken", prep, location_link_text) elseif extinct then location_desc = "It is an [[extinct language]].\n\n" else location_desc = "" end local add = location_desc .. "Information about " .. canonicalName .. ":\n\n" .. infobox(lang) if lang:hasType("reconstructed") then add = add .. "\n\n" .. ucfirst(canonicalName) .. " is a reconstructed language. Its words and roots are not directly attested in any written works, but have been reconstructed through the ''comparative method'', " .. "which finds regular similarities between languages that cannot be explained by coincidence or word-borrowing, and extrapolates ancient forms from these similarities.\n\n" .. "According to our [[Wiktionary:Criteria for inclusion|criteria for inclusion]], terms in " .. canonicalName .. " should '''not''' be present in entries in the main namespace, but may be added to the Reconstruction: namespace." elseif lang:hasType("appendix-constructed") then add = add .. "\n\n" .. ucfirst(canonicalName) .. " is a constructed language that is only in sporadic use. " .. "According to our [[Wiktionary:Criteria for inclusion|criteria for inclusion]], terms in " .. canonicalName .. " should '''not''' be present in entries in the main namespace, but may be added to the Appendix: namespace. " .. "All terms in this language may be available at [[Appendix:" .. ucfirst(canonicalName) .. "]]." end local about = new_title("Wiktionary:About " .. canonicalName) if about.exists then add = add .. "\n\n" .. "Please see '''[[Wiktionary:About " .. canonicalName .. "]]''' for information and special considerations for creating " .. nameWithLanguage .. " entries." end local ok, tree_of_descendants = pcall( require("Module:family tree").print_children, lang:getCode(), { protolanguage_under_family = true, must_have_descendants = true }) if ok then if tree_of_descendants then add = add .. NavFrame( tree_of_descendants, "Family tree") else add = add .. "\n\n" .. ucfirst(lang:getCanonicalName()) .. " has no descendants or varieties listed in Wiktionary's language data modules." end else mw.log("error while generating tree: " .. tostring(tree_of_descendants)) end return description, topright, add end local function get_parents(lang, locations, extinct) local canonicalName = lang:getCanonicalName() local sortkey = {sort_base = canonicalName, lang = "mi"} local ret = {{name = "Reo", sort = sortkey}} local fam = lang:getFamily() local famCode = fam and fam:getCode() -- FIXME: Some of the following categories should be added to this module. if not fam then insert(ret, {name = "Category:Unclassified languages", sort = sortkey}) elseif famCode == "qfa-iso" then insert(ret, {name = "Category:Language isolates", sort = sortkey}) elseif famCode == "qfa-mix" then insert(ret, {name = "Category:Mixed languages", sort = sortkey}) elseif famCode == "sgn" then insert(ret, {name = "Category:All sign languages", sort = sortkey}) elseif famCode == "crp" then insert(ret, {name = "Category:Creole or pidgin languages", sort = sortkey}) for _, anc in ipairs(lang:getAncestors()) do -- Avoid Haitian Creole being categorised in [[:Category:Haitian Creole-based creole or pidgin languages]], as one of its ancestors is an etymology-only variety of it. -- Use that ancestor's ancestors instead. if anc:getFullCode() == lang:getCode() then for _, anc_extra in ipairs(anc:getAncestors()) do insert(ret, {name = "Category:" .. ucfirst(anc_extra:getFullName()) .. "-based creole or pidgin languages", sort = sortkey}) end else insert(ret, {name = "Category:" .. ucfirst(anc:getFullName()) .. "-based creole or pidgin languages", sort = sortkey}) end end elseif famCode == "art" then if lang:hasType("appendix-constructed") then insert(ret, {name = "Category:Appendix-only constructed languages", sort = sortkey}) else insert(ret, {name = "Category:Constructed languages", sort = sortkey}) end for _, anc in ipairs(lang:getAncestors()) do if anc:getFullCode() == lang:getCode() then for _, anc_extra in ipairs(anc:getAncestors()) do insert(ret, {name = "Category:" .. ucfirst(anc_extra:getFullName()) .. "-based constructed languages", sort = sortkey}) end else insert(ret, {name = "Category:" .. ucfirst(anc:getFullName()) .. "-based constructed languages", sort = sortkey}) end end else insert(ret, {name = "Category:" .. fam:getCategoryName(), sort = sortkey}) if lang:hasType("reconstructed") then insert(ret, { name = "Category:Reconstructed languages", sort = {sort_base = canonicalName:gsub("^Proto%-", ""), lang = "en"} }) end end local function add_sc_cat(sc) insert(ret, {name = "Category:Reo " .. sc:getCategoryName(), sort = sortkey}) end local function add_Hrkt() add_sc_cat(Hrkt) add_sc_cat(Hira) add_sc_cat(Kana) end for _, sc in ipairs(lang:getScripts()) do if sc:getCode() == "Hrkt" then add_Hrkt() else add_sc_cat(sc) if sc:getCode() == "Jpan" then add_sc_cat(Hani) add_Hrkt() elseif sc:getCode() == "Kore" then add_sc_cat(Hang) add_sc_cat(Hani) end end end if lang:hasTranslit() then insert(ret, {name = "Category:Languages with automatic transliteration", sort = sortkey}) end local function insert_location_language_cat(location) local cat = "Languages of " .. location insert(ret, {name = "Category:" .. cat, sort = sortkey}) local auto_cat_args = scrape_category_for_auto_cat_args(cat) local location_parent = auto_cat_args and auto_cat_args.parent if location_parent then local split_parents = require(parse_utilities_module).split_on_comma(location_parent) for _, parent in ipairs(split_parents) do parent = parent:match("^(.-):.*$") or parent insert_location_language_cat(parent) end end end local saw_location = false for _, location in ipairs(locations) do if location ~= "UNKNOWN" then saw_location = true insert_location_language_cat(location) end end if extinct then insert(ret, {name = "Category:All extinct languages", sort = sortkey}) end if not saw_location and not (lang:hasType("reconstructed") or (fam and fam:getCode() == "art")) then -- Constructed and reconstructed languages don't need a location specified and often won't have one, -- so don't put them in this maintenance category. insert(ret, {name = "Category:Languages not sorted into a location category", sort = sortkey}) end return ret end -- Handle language categories of the form e.g. [[:Category:French language]] and -- [[:Category:British Sign Language]]. insert(raw_handlers, function(data) local category = data.category if not (category:match("[Rr]eo") or category:match("[Ll]ect$")) then return nil end local lang = m_languages.getByCanonicalName(category) if not lang then local langname = category:match("^Reo (.*)") if langname then lang = m_languages.getByCanonicalName(langname) end if not lang then return nil end end local args = require("Module:parameters").process(data.args, { [1] = {list = true}, ["setwiki"] = true, ["setwikt"] = true, ["setsister"] = true, ["entryname"] = true, ["extinct"] = {type = "boolean"}, }) -- If called from inside, don't require any arguments, as they can't be known -- in general and aren't needed just to generate the first parent (used for -- breadcrumbs). if #args[1] == 0 and not data.called_from_inside then -- At least one location must be specified unless the language is constructed (e.g. Esperanto) or reconstructed (e.g. Proto-Indo-European). local fam = lang:getFamily() if not (lang:hasType("reconstructed") or (fam and fam:getCode() == "art")) then error("At least one location (param 1=) must be specified for language '" .. lang:getCanonicalName() .. "' (code '" .. lang:getCode() .. "'). " .. "Use the value UNKNOWN if the language's location is truly unknown.") end end local description, topright, additional = "", "", "" -- If called from inside the category tree system, it's called when generating -- parents or children, and we don't need to generate the description or additional -- text (which is very expensive in terms of memory because it calls [[Module:family tree]], -- which calls [[Module:languages/data/all]]). if not data.called_from_inside then description, topright, additional = get_description_topright_additional( lang, args[1], args.extinct, args.setwiki, args.setwikt, args.setsister, args.entryname ) end return { canonical_name = lang:getCategoryName(), description = description, lang = lang:getCode(), topright = topright, additional = additional, breadcrumb = lang:getCanonicalName(), parents = get_parents(lang, args[1], args.extinct), extra_children = get_children(lang), umbrella = false, can_be_empty = true, }, true end) -- Handle categories such as [[:Category:Languages of Indonesia]]. insert(raw_handlers, function(data) local location = data.category:match("^Languages of (.*)$") if location then local args = require("Module:parameters").process(data.args, { ["flagfile"] = true, ["commonscat"] = true, ["wp"] = true, ["basename"] = true, ["parent"] = true, ["locationcat"] = true, ["locationlink"] = true, }) local topright local basename = args.basename or location:gsub(", .*", "") if args.flagfile ~= "-" then local flagfile_arg = args.flagfile or ("Flag of %s.svg"):format(basename) local files = require(parse_utilities_module).split_on_comma(flagfile_arg) local topright_parts = {} for _, file in ipairs(files) do local flagfile = "File:" .. file local flagfile_page = new_title(flagfile) if flagfile_page and flagfile_page.file.exists then insert(topright_parts, ("[[%s|right|100px|border]]"):format(flagfile)) elseif args.flagfile then error(("Explicit flagfile '%s' doesn't exist"):format(flagfile)) end end topright = concat(topright_parts) end if args.wp then local wp = require("Module:yesno")(args.wp, "+") if wp == "+" or wp == true then wp = data.category end if wp then local wp_topright = ("{{wikipedia|%s}}"):format(wp) if topright then topright = topright .. wp_topright else topright = wp_topright end end end if args.commonscat then local commonscat = require("Module:yesno")(args.commonscat, "+") if commonscat == "+" or commonscat == true then commonscat = data.category end if commonscat then local commons_topright = ("{{commonscat|%s}}"):format(commonscat) if topright then topright = topright .. commons_topright else topright = commons_topright end end end local bare_location = location:match("^the (.*)$") or location local location_link = args.locationlink or link_location(location) local bare_basename = basename:match("^the (.*)$") or basename local parents = {} if args.parent then local explicit_parents = require(parse_utilities_module).split_on_comma(args.parent) for i, parent in ipairs(explicit_parents) do local actual_parent, sort_key = parent:match("^(.-):(.*)$") if actual_parent then parent = actual_parent sort_key = sort_key:gsub("%+", bare_location) else sort_key = " " .. bare_location end insert(parents, {name = "Languages of " .. parent, sort = sort_key}) end else insert(parents, {name = "Languages by country", sort = {sort_base = bare_location, lang = "en"}}) end if args.locationcat then local explicit_location_cats = require(parse_utilities_module).split_on_comma(args.locationcat) for i, locationcat in ipairs(explicit_location_cats) do insert(parents, {name = "Category:" .. locationcat, sort = " Languages"}) end else local location_cat = ("Category:%s"):format(bare_location) local location_page = new_title(location_cat) if location_page and location_page.exists then insert(parents, {name = location_cat, sort = "Languages"}) end end local description = ("Categories for languages of %s (including sublects)."):format(location_link) return { topright = topright, description = description, parents = parents, breadcrumb = bare_basename, additional = "{{{umbrella_msg}}}", }, true end end) -- Handle categories such as [[:Category:English-based creole or pidgin languages]]. insert(raw_handlers, function(data) local langname = data.category:match("(.*)%-based creole or pidgin languages$") if langname then local lang = m_languages.getByCanonicalName(langname) if lang then return { lang = lang:getCode(), description = "Languages which developed as a [[creole]] or [[pidgin]] from " .. lang:makeCategoryLink() .. ".", parents = {{name = "Creole or pidgin languages", sort = {sort_base = "*" .. langname, lang = "en"}}}, breadcrumb = lang:getCanonicalName() .. "-based", } end end end) -- Handle categories such as [[:Category:English-based constructed languages]]. insert(raw_handlers, function(data) local langname = data.category:match("(.*)%-based constructed languages$") if langname then local lang = m_languages.getByCanonicalName(langname) if lang then return { lang = lang:getCode(), description = "Constructed languages which are based on " .. lang:makeCategoryLink() .. ".", parents = {{name = "Constructed languages", sort = {sort_base = "*" .. langname, lang = "en"}}}, breadcrumb = lang:getCanonicalName() .. "-based", } end end end) return {RAW_CATEGORIES = raw_categories, RAW_HANDLERS = raw_handlers} 0ph7sc9rkrp14b8ohz7sdmrqddlv31z 17442 17441 2026-07-13T08:48:20Z Hiyuune 6766 17442 Scribunto text/plain local new_title = mw.title.new local ucfirst = require("Module:string utilities").ucfirst local split = require("Module:string utilities").split local raw_categories = {} local raw_handlers = {} local m_languages = require("Module:languages") local m_sc_getByCode = require("Module:scripts").getByCode local m_table = require("Module:table") local parse_utilities_module = "Module:parse utilities" local concat = table.concat local insert = table.insert local reverse_ipairs = m_table.reverseIpairs local serial_comma_join = m_table.serialCommaJoin local size = m_table.size local sorted_pairs = m_table.sortedPairs local to_json = require("Module:JSON").toJSON local Hang = m_sc_getByCode("Hang") local Hani = m_sc_getByCode("Hani") local Hira = m_sc_getByCode("Hira") local Hrkt = m_sc_getByCode("Hrkt") local Kana = m_sc_getByCode("Kana") local function track(page) -- [[Special:WhatLinksHere/Wiktionary:Tracking/category tree/languages/PAGE]] return require("Module:debug/track")("category tree/languages/" .. page) end -- This handles language categories of the form e.g. [[:Category:French language]] and -- [[:Category:British Sign Language]]; categories like [[:Category:Languages of Indonesia]]; categories like -- [[:Category:English-based creole or pidgin languages]]; and categories like -- [[:Category:English-based constructed languages]]. ----------------------------------------------------------------------------- -- -- -- RAW CATEGORIES -- -- -- ----------------------------------------------------------------------------- raw_categories["Reo"] = { topright = "{{commonscat|Languages}}\n[[File:Languages world map-transparent background.svg|thumb|right|250px|Rough world map of language families]]", description = "This category contains the categories for every language on Wiktionary.", additional = "Not all languages that Wiktionary recognises may have a category here yet. There are many that have " .. "not yet received any attention from editors, mainly because not all Wiktionary users know about every single " .. "language. See [[Wiktionary:List of languages]] for a full list.", parents = { "Whakaraparapa", }, } raw_categories["All extinct languages"] = { description = "This category contains the categories for every [[extinct language]] on Wiktionary.", additional = "Do not confuse this category with [[:Category:Extinct languages]], which is an umbrella category for the names of extinct languages in specific other languages (e.g. {{m+|de|Langobardisch}} for the ancient [[Lombardic]] language).", parents = { "Reo", }, } raw_categories["Languages by country"] = { topright = "{{commonscat|Languages by continent}}", description = "Categories that group languages by country.", additional = "{{{umbrella_meta_msg}}}", parents = { "Reo", }, } raw_categories["Language isolates"] = { topright = "{{wikipedia|Language isolate}}\n{{commonscat|Language isolates}}", description = "Languages with no known relatives.", parents = { {name = "Languages by family", sort = "*Isolates"}, {name = "All language families", sort = "Isolates"}, }, } raw_categories["Languages not sorted into a location category"] = { description = "Languages which do not specify (in their {{tl|auto cat}} call) the location(s) where they are spoken.", additional = "This excludes constructed and reconstructed languages; as a result, all languages in this category explicitly specify their location as {{cd|UNKNOWN}}.", parents = { {name = "Requests"}, }, hidden = true, } ----------------------------------------------------------------------------- -- -- -- RAW HANDLERS -- -- -- ----------------------------------------------------------------------------- -- Given a category (without the "Category:" prefix), look up the page defining the category, find the call to -- {{auto cat}} (if any), and return a table of its arguments. If the category page doesn't exist or doesn't have -- an {{auto cat}} invocation, return nil. -- -- FIXME: Duplicated in [[Module:category tree/lects]]. local function scrape_category_for_auto_cat_args(cat) local cat_page = mw.title.new("Category:" .. cat) if cat_page then local contents = cat_page:getContent() if contents then local frame = mw.getCurrentFrame() for template in require("Module:template parser").find_templates(contents) do -- The template parser automatically handles redirects and canonicalizes them, so uses of {{autocat}} -- will also be found. if template:get_name() == "auto cat" then return template:get_arguments() end end end end return nil end local function link_location(location) local location_no_the = location:match("^the (.*)$") local bare_location = location_no_the or location local location_link local bare_location_parts = split(bare_location, ", ") for i, part in ipairs(bare_location_parts) do bare_location_parts[i] = ("[[%s]]"):format(part) end location_link = concat(bare_location_parts, ", ") if location_no_the then location_link = "the " .. location_link end return location_link end local function linkbox(lang, setwiki, setwikt, setsister, entryname) local wiktionarylinks = {} local canonicalName = lang:getCanonicalName() local wikimediaLanguages = lang:getWikimediaLanguages() local wikipediaArticle = setwiki or lang:getWikipediaArticle() setsister = setsister and ucfirst(setsister) or nil if setwikt then track("setwikt") if setwikt == "-" then track("setwikt/hyphen") end end if setwikt ~= "-" and wikimediaLanguages and wikimediaLanguages[1] then for _, wikimedialang in ipairs(wikimediaLanguages) do local check = new_title(wikimedialang:getCode() .. ":") if check and check.isExternal then insert(wiktionarylinks, (wikimedialang:getCanonicalName() ~= canonicalName and "(''" .. wikimedialang:getCanonicalName() .. "'') " or "") .. "'''[[:" .. wikimedialang:getCode() .. ":|" .. wikimedialang:getCode() .. ".wiktionary.org]]'''") end end wiktionarylinks = concat(wiktionarylinks, "<br/>") end local wikt_plural = wikimediaLanguages[2] and "s" or "" if #wiktionarylinks == 0 then wiktionarylinks = "''None.''" end if setsister then track("setsister") if setsister == "-" then track("setsister/hyphen") else setsister = "Category:" .. setsister end else setsister = lang:getCommonsCategory() or "-" end return concat{ [=[<div class="wikitable" style="float: right; clear: right; margin: 0 0 0.5em 1em; width: 300px; padding: 5px;"> <div style="text-align: center; margin-bottom: 10px; margin-top: 5px">''']=], canonicalName, [=[ language links'''</div> {| style="font-size: 90%" |- | style="vertical-align: top; height: 35px; border-bottom: 1px solid lightgray;" | [[File:Wikipedia-logo.png|35px|none|Wikipedia]] | style="border-bottom: 1px solid lightgray;" | '''English Wikipedia''' has an article on: <div style="padding: 5px 10px">]=], (setwiki == "-" and "''None.''" or "'''[[w:" .. wikipediaArticle .. "|" .. wikipediaArticle .. "]]'''"), [=[</div> |- | style="vertical-align: top; height: 35px; border-bottom: 1px solid lightgray;" | [[File:Wikimedia-logo.svg|35px|none|Wikimedia Commons]] | style="border-bottom: 1px solid lightgray;" | '''Wikimedia Commons''' has links to ]=], canonicalName, [=[-related content in sister projects: <div style="padding: 5px 10px">]=], (setsister == "-" and "''None.''" or "'''[[commons:" .. setsister .. "|" .. setsister .. "]]'''"), [=[</div> |- | style="vertical-align: top; height: 35px; width: 40px; border-bottom: 1px solid lightgray;" | [[File:Wiktionary-logo-v2.svg|35px|none|Wiktionary]] |style="border-bottom: 1px solid lightgray;" | '''Wiktionary edition''']=], wikt_plural, [=[ written in ]=], canonicalName, [=[: <div style="padding: 5px 10px">]=], wiktionarylinks, [=[</div> |- | style="vertical-align: top; height: 35px; border-bottom: 1px solid lightgray;" | [[File:Open book nae 02.svg|35px|none|Entry]] | style="border-bottom: 1px solid lightgray;" | '''Wiktionary entry''' for the language's English name: <div style="padding: 5px 10px">''']=], require("Module:links").full_link({lang = m_languages.getByCode("en"), term = entryname or canonicalName}), [=['''</div> |- | style="vertical-align: top; height: 35px;" | [[File:Crystal kfind.png|35px|none|Considerations]] || '''Wiktionary resources''' for editors contributing to ]=], canonicalName, [=[ entries: <div style="padding: 5px 0"> * '''[[Wiktionary:]=], canonicalName, [=[ entry guidelines]]''' * '''[[:Category:]=], canonicalName, [=[ reference templates|Reference templates]] ({{PAGESINCAT:]=], canonicalName, [=[ reference templates}})''' * '''[[Appendix:]=], canonicalName, [=[ bibliography|Bibliography]]''' |} </div>]=] } end local function edit_link(title, text) return '<span class="plainlinks">[' .. tostring(mw.uri.fullUrl(title, { action = "edit" })) .. ' ' .. text .. ']</span>' end -- Should perhaps use wiki syntax. local function infobox(lang) local ret = {} insert(ret, '<table class="wikitable language-category-info"') local raw_data = lang:getData("extra") if raw_data then local replacements = { [1] = "canonical-name", [2] = "wikidata-item", [3] = "family", [4] = "scripts", } local function replacer(letter1, letter2) return letter1:lower() .. "-" .. letter2:lower() end -- For each key in the language data modules, returns a descriptive -- kebab-case version (containing ASCII lowercase words separated -- by hyphens). local function kebab_case(key) key = replacements[key] or key key = key:gsub("(%l)(%u)", replacer):gsub("(%l)_(%l)", replacer) return key end local compress = {compress = true} local function html_attribute_encode(str) str = to_json(str, compress) :gsub('"', "&quot;") -- & in attributes is automatically escaped. -- :gsub("&", "&amp;") :gsub("<", "&lt;") :gsub(">", "&gt;") return str end insert(ret, ' data-code="' .. lang:getCode() .. '"') for k, v in sorted_pairs(raw_data) do insert(ret, " data-" .. kebab_case(k) .. '="' .. html_attribute_encode(v) .. '"') end end insert(ret, '>\n') insert(ret, '<tr class="language-category-data">\n<th colspan="2">' .. edit_link(lang:getDataModuleName(), "Edit language data") .. "</th>\n</tr>\n") insert(ret, "<tr>\n<th>Canonical name</th><td>" .. lang:getCanonicalName() .. "</td>\n</tr>\n") local otherNames = lang:getOtherNames() if otherNames then local names = {} for _, name in ipairs(otherNames) do insert(names, "<li>" .. name .. "</li>") end if #names > 0 then insert(ret, "<tr>\n<th>Other names</th><td><ul>" .. concat(names, "\n") .. "</ul></td>\n</tr>\n") end end local aliases = lang:getAliases() if aliases then local names = {} for _, name in ipairs(aliases) do insert(names, "<li>" .. name .. "</li>") end if #names > 0 then insert(ret, "<tr>\n<th>Aliases</th><td><ul>" .. concat(names, "\n") .. "</ul></td>\n</tr>\n") end end local varieties = lang:getVarieties() if varieties then local names = {} for _, name in ipairs(varieties) do if type(name) == "string" then insert(names, "<li>" .. name .. "</li>") else assert(type(name) == "table") local first_var local subvars = {} for i, var in ipairs(name) do if i == 1 then first_var = var else insert(subvars, "<li>" .. var .. "</li>") end end if #subvars > 0 then insert(names, "<li><dl><dt>" .. first_var .. "</dt>\n<dd><ul>" .. concat(subvars, "\n") .. "</ul></dd></dl></li>") elseif first_var then insert(names, "<li>" .. first_var .. "</li>") end end end if #names > 0 then insert(ret, "<tr>\n<th>Varieties</th><td><ul>" .. concat(names, "\n") .. "</ul></td>\n</tr>\n") end end insert(ret, "<tr>\n<th>[[Wiktionary:Languages|Language code]]</th><td><code>" .. lang:getCode() .. "</code></td>\n</tr>\n") insert(ret, "<tr>\n<th>[[Wiktionary:Families|Language family]]</th>\n") local fam = lang:getFamily() local famCode = fam and fam:getCode() if not fam then insert(ret, "<td>unclassified</td>") elseif famCode == "qfa-iso" then insert(ret, "<td>[[:Category:Language isolates|language isolate]]</td>") elseif famCode == "qfa-mix" then insert(ret, "<td>[[:Category:Mixed languages|mixed language]]</td>") elseif famCode == "sgn" then insert(ret, "<td>[[:Category:Sign languages|sign language]]</td>") elseif famCode == "crp" then insert(ret, "<td>[[:Category:Creole or pidgin languages|creole or pidgin]]</td>") elseif famCode == "art" then insert(ret, "<td>[[:Category:Constructed languages|constructed language]]</td>") else insert(ret, "<td>" .. fam:makeCategoryLink() .. "</td>") end insert(ret, "\n</tr>\n<tr>\n<th>Ancestors</th>\n<td>") local ancestors = lang:getAncestors() if ancestors[2] then local ancestorList = {} for i, anc in ipairs(ancestors) do ancestorList[i] = "<li>" .. anc:makeCategoryLink() .. "</li>" end insert(ret, "<ul>\n" .. concat(ancestorList, "\n") .. "</ul>") else local ancestorChain = lang:getAncestorChainOld() if ancestorChain[1] then local chain = {} for _, anc in reverse_ipairs(ancestorChain) do insert(chain, "<li>" .. anc:makeCategoryLink() .. "</li>") end insert(ret, "<ul>\n" .. concat(chain, "\n<ul>\n") .. ("</ul>"):rep(#chain)) else insert(ret, "unknown") end end insert(ret, "</td>\n</tr>\n") local scripts = lang:getScripts() if scripts[1] then local script_text = {} local function makeScriptLine(sc) local code = sc:getCode() local url = tostring(mw.uri.fullUrl('Special:Search', { search = 'contentmodel:css insource:"' .. code .. '" insource:/\\.' .. code .. '/', ns8 = '1' })) return sc:makeCategoryLink() .. ' (<span class="plainlinks" title="Search for stylesheets referencing this script">[' .. url .. ' <code>' .. code .. '</code>]</span>)' end local function add_Hrkt(text) insert(text, "<li>" .. makeScriptLine(Hrkt)) insert(text, "<ul>") insert(text, "<li>" .. makeScriptLine(Hira) .. "</li>") insert(text, "<li>" .. makeScriptLine(Kana) .. "</li>") insert(text, "</ul>") insert(text, "</li>") end for _, sc in ipairs(scripts) do local text = {} local code = sc:getCode() if code == "Hrkt" then add_Hrkt(text) else insert(text, "<li>" .. makeScriptLine(sc)) if code == "Jpan" then insert(text, "<ul>") insert(text, "<li>" .. makeScriptLine(Hani) .. "</li>") add_Hrkt(text) insert(text, "</ul>") elseif code == "Kore" then insert(text, "<ul>") insert(text, "<li>" .. makeScriptLine(Hang) .. "</li>") insert(text, "<li>" .. makeScriptLine(Hani) .. "</li>") insert(text, "</ul>") end insert(text, "</li>") end insert(script_text, concat(text, "\n")) end insert(ret, "<tr>\n<th>[[Wiktionary:Scripts|Scripts]]</th>\n<td><ul>\n" .. concat(script_text, "\n") .. "</ul></td>\n</tr>\n") else insert(ret, "<tr>\n<th>[[Wiktionary:Scripts|Scripts]]</th>\n<td>not specified</td>\n</tr>\n") end local function add_module_info(raw_data, heading) if raw_data then local scripts = lang:getScriptCodes() local module_info, add = {}, false if type(raw_data) == "string" then insert(module_info, ("[[Module:%s]]"):format(raw_data)) add = true else local raw_data_type = type(raw_data) if raw_data_type == "table" and size(scripts) == 1 and type(raw_data[scripts[1]]) == "string" then insert(module_info, ("[[Module:%s]]"):format(raw_data[scripts[1]])) add = true elseif raw_data_type == "table" then insert(module_info, "<ul>") for script, data in sorted_pairs(raw_data) do if type(data) == "string" and m_sc_getByCode(script) then insert(module_info, ("<li><code>%s</code>: [[Module:%s]]</li>"):format(script, data)) end end insert(module_info, "</ul>") add = size(module_info) > 2 end end if add then insert(ret, [=[ <tr> <th>]=] .. heading .. [=[</th> <td>]=] .. concat(module_info) .. [=[</td> </tr> ]=]) end end end add_module_info(raw_data.generate_forms, "Form-generating<br>module") add_module_info(raw_data.translit, "[[Wiktionary:Transliteration and romanization|Transliteration<br>module]]") add_module_info(raw_data.display_text, "Display text<br>module") add_module_info(raw_data.entry_name, "Entry name<br>module") add_module_info(raw_data.sort_key, "[[sortkey|Sortkey]]<br>module") local wikidataItem = lang:getWikidataItem() if lang:getWikidataItem() and mw.wikibase then local URL = mw.wikibase.getEntityUrl(wikidataItem) local link if URL then link = '[' .. URL .. ' ' .. wikidataItem .. ']' else link = '<span class="error">Invalid Wikidata item: <code>' .. wikidataItem .. '</code></span>' end insert(ret, "<tr><th>Wikidata</th><td>" .. link .. "</td></tr>") end insert(ret, "</table>") return concat(ret) end local function NavFrame(content, title) return '<div class="NavFrame"><div class="NavHead">' .. (title or '{{{title}}}') .. '</div>' .. '<div class="NavContent" style="text-align: left;">' .. content .. '</div></div>' end local function get_description_topright_additional(lang, locations, extinct, setwiki, setwikt, setsister, entryname) local nameWithLanguage = lang:getCategoryName("nocap") if lang:getCode() == "und" then local description = "This is the main category of the '''" .. nameWithLanguage .. "''', represented in Wiktionary by the [[Wiktionary:Languages|code]] '''" .. lang:getCode() .. "'''. " .. "This language contains terms in historical writing, whose meaning has not yet been determined by scholars." return description, nil, nil end local canonicalName = lang:getCanonicalName() local topright = linkbox(lang, setwiki, setwikt, setsister, entryname) local the_prefix if canonicalName:find(" Language$") then the_prefix = "" else the_prefix = "the " end local description = "This is the main category of " .. the_prefix .. "'''" .. nameWithLanguage .. "'''." local location_links = {} local prep local saw_embedded_comma = false for _, location in ipairs(locations) do local this_prep if location == "the world" then this_prep = "across" insert(location_links, location) elseif location ~= "UNKNOWN" then this_prep = "in" if location:find(",") then saw_embedded_comma = true end insert(location_links, link_location(location)) end if this_prep then if prep and this_prep ~= prep then error("Can't handle location 'the world' along with another location (clashing prepositions)") end prep = this_prep end end local location_desc if #location_links > 0 then local location_link_text if saw_embedded_comma and #location_links >= 3 then location_link_text = mw.text.listToText(location_links, "; ", "; and ") else location_link_text = serial_comma_join(location_links) end location_desc = ("It is %s %s %s.\n\n"):format( extinct and "an [[extinct language]] that was formerly spoken" or "spoken", prep, location_link_text) elseif extinct then location_desc = "It is an [[extinct language]].\n\n" else location_desc = "" end local add = location_desc .. "Information about " .. canonicalName .. ":\n\n" .. infobox(lang) if lang:hasType("reconstructed") then add = add .. "\n\n" .. ucfirst(canonicalName) .. " is a reconstructed language. Its words and roots are not directly attested in any written works, but have been reconstructed through the ''comparative method'', " .. "which finds regular similarities between languages that cannot be explained by coincidence or word-borrowing, and extrapolates ancient forms from these similarities.\n\n" .. "According to our [[Wiktionary:Criteria for inclusion|criteria for inclusion]], terms in " .. canonicalName .. " should '''not''' be present in entries in the main namespace, but may be added to the Reconstruction: namespace." elseif lang:hasType("appendix-constructed") then add = add .. "\n\n" .. ucfirst(canonicalName) .. " is a constructed language that is only in sporadic use. " .. "According to our [[Wiktionary:Criteria for inclusion|criteria for inclusion]], terms in " .. canonicalName .. " should '''not''' be present in entries in the main namespace, but may be added to the Appendix: namespace. " .. "All terms in this language may be available at [[Appendix:" .. ucfirst(canonicalName) .. "]]." end local about = new_title("Wiktionary:About " .. canonicalName) if about.exists then add = add .. "\n\n" .. "Please see '''[[Wiktionary:About " .. canonicalName .. "]]''' for information and special considerations for creating " .. nameWithLanguage .. " entries." end local ok, tree_of_descendants = pcall( require("Module:family tree").print_children, lang:getCode(), { protolanguage_under_family = true, must_have_descendants = true }) if ok then if tree_of_descendants then add = add .. NavFrame( tree_of_descendants, "Family tree") else add = add .. "\n\n" .. ucfirst(lang:getCanonicalName()) .. " has no descendants or varieties listed in Wiktionary's language data modules." end else mw.log("error while generating tree: " .. tostring(tree_of_descendants)) end return description, topright, add end local function get_parents(lang, locations, extinct) local canonicalName = lang:getCanonicalName() local sortkey = {sort_base = canonicalName, lang = "mi"} local ret = {{name = "Reo", sort = sortkey}} local fam = lang:getFamily() local famCode = fam and fam:getCode() -- FIXME: Some of the following categories should be added to this module. if not fam then insert(ret, {name = "Category:Unclassified languages", sort = sortkey}) elseif famCode == "qfa-iso" then insert(ret, {name = "Category:Language isolates", sort = sortkey}) elseif famCode == "qfa-mix" then insert(ret, {name = "Category:Mixed languages", sort = sortkey}) elseif famCode == "sgn" then insert(ret, {name = "Category:All sign languages", sort = sortkey}) elseif famCode == "crp" then insert(ret, {name = "Category:Creole or pidgin languages", sort = sortkey}) for _, anc in ipairs(lang:getAncestors()) do -- Avoid Haitian Creole being categorised in [[:Category:Haitian Creole-based creole or pidgin languages]], as one of its ancestors is an etymology-only variety of it. -- Use that ancestor's ancestors instead. if anc:getFullCode() == lang:getCode() then for _, anc_extra in ipairs(anc:getAncestors()) do insert(ret, {name = "Category:" .. ucfirst(anc_extra:getFullName()) .. "-based creole or pidgin languages", sort = sortkey}) end else insert(ret, {name = "Category:" .. ucfirst(anc:getFullName()) .. "-based creole or pidgin languages", sort = sortkey}) end end elseif famCode == "art" then if lang:hasType("appendix-constructed") then insert(ret, {name = "Category:Appendix-only constructed languages", sort = sortkey}) else insert(ret, {name = "Category:Constructed languages", sort = sortkey}) end for _, anc in ipairs(lang:getAncestors()) do if anc:getFullCode() == lang:getCode() then for _, anc_extra in ipairs(anc:getAncestors()) do insert(ret, {name = "Category:" .. ucfirst(anc_extra:getFullName()) .. "-based constructed languages", sort = sortkey}) end else insert(ret, {name = "Category:" .. ucfirst(anc:getFullName()) .. "-based constructed languages", sort = sortkey}) end end else insert(ret, {name = "Category:" .. fam:getCategoryName(), sort = sortkey}) if lang:hasType("reconstructed") then insert(ret, { name = "Category:Reconstructed languages", sort = {sort_base = canonicalName:gsub("^Proto%-", ""), lang = "en"} }) end end local function add_sc_cat(sc) insert(ret, {name = "Category:Reo " .. sc:getCategoryName(), sort = sortkey}) end local function add_Hrkt() add_sc_cat(Hrkt) add_sc_cat(Hira) add_sc_cat(Kana) end for _, sc in ipairs(lang:getScripts()) do if sc:getCode() == "Hrkt" then add_Hrkt() else add_sc_cat(sc) if sc:getCode() == "Jpan" then add_sc_cat(Hani) add_Hrkt() elseif sc:getCode() == "Kore" then add_sc_cat(Hang) add_sc_cat(Hani) end end end if lang:hasTranslit() then insert(ret, {name = "Category:Languages with automatic transliteration", sort = sortkey}) end local function insert_location_language_cat(location) local cat = "Languages of " .. location insert(ret, {name = "Category:" .. cat, sort = sortkey}) local auto_cat_args = scrape_category_for_auto_cat_args(cat) local location_parent = auto_cat_args and auto_cat_args.parent if location_parent then local split_parents = require(parse_utilities_module).split_on_comma(location_parent) for _, parent in ipairs(split_parents) do parent = parent:match("^(.-):.*$") or parent insert_location_language_cat(parent) end end end local saw_location = false for _, location in ipairs(locations) do if location ~= "UNKNOWN" then saw_location = true insert_location_language_cat(location) end end if extinct then insert(ret, {name = "Category:All extinct languages", sort = sortkey}) end if not saw_location and not (lang:hasType("reconstructed") or (fam and fam:getCode() == "art")) then -- Constructed and reconstructed languages don't need a location specified and often won't have one, -- so don't put them in this maintenance category. insert(ret, {name = "Category:Languages not sorted into a location category", sort = sortkey}) end return ret end local function get_children() local ret = {} -- FIXME: We should work on the children mechanism so it isn't necessary to manually specify these. --for _, label in ipairs({"appendices", "entry maintenance", "lemmas", "names", "phrases", "rhymes", "symbols", "templates", "terms by etymology", "terms by usage"}) do -- insert(ret, {name = label, is_label = true}) --end --insert(ret, {name = "terms derived from {{{langname}}}", is_label = true, lang = false}) --insert(ret, {name = "{{{langcode}}}:All topics", sort = "all topics"}) --insert(ret, {name = "Varieties of {{{langname}}}"}) --insert(ret, {name = "Requests concerning {{{langname}}}"}) --insert(ret, {name = "Rhymes:{{{langname}}}", description = "Lists of {{{langname}}} words by their rhymes."}) --insert(ret, {name = "User {{{langcode}}}", description = "Wiktionary users categorized by fluency levels in {{{langdisp}}}."}) return ret end -- Handle language categories of the form e.g. [[:Category:French language]] and -- [[:Category:British Sign Language]]. insert(raw_handlers, function(data) local category = data.category if not (category:match("[Rr]eo") or category:match("[Ll]ect$")) then return nil end local lang = m_languages.getByCanonicalName(category) if not lang then local langname = category:match("^Reo (.*)") if langname then lang = m_languages.getByCanonicalName(langname) end if not lang then return nil end end local args = require("Module:parameters").process(data.args, { [1] = {list = true}, ["setwiki"] = true, ["setwikt"] = true, ["setsister"] = true, ["entryname"] = true, ["extinct"] = {type = "boolean"}, }) -- If called from inside, don't require any arguments, as they can't be known -- in general and aren't needed just to generate the first parent (used for -- breadcrumbs). if #args[1] == 0 and not data.called_from_inside then -- At least one location must be specified unless the language is constructed (e.g. Esperanto) or reconstructed (e.g. Proto-Indo-European). local fam = lang:getFamily() if not (lang:hasType("reconstructed") or (fam and fam:getCode() == "art")) then error("At least one location (param 1=) must be specified for language '" .. lang:getCanonicalName() .. "' (code '" .. lang:getCode() .. "'). " .. "Use the value UNKNOWN if the language's location is truly unknown.") end end local description, topright, additional = "", "", "" -- If called from inside the category tree system, it's called when generating -- parents or children, and we don't need to generate the description or additional -- text (which is very expensive in terms of memory because it calls [[Module:family tree]], -- which calls [[Module:languages/data/all]]). if not data.called_from_inside then description, topright, additional = get_description_topright_additional( lang, args[1], args.extinct, args.setwiki, args.setwikt, args.setsister, args.entryname ) end return { canonical_name = lang:getCategoryName(), description = description, lang = lang:getCode(), topright = topright, additional = additional, breadcrumb = lang:getCanonicalName(), parents = get_parents(lang, args[1], args.extinct), extra_children = get_children(lang), umbrella = false, can_be_empty = true, }, true end) -- Handle categories such as [[:Category:Languages of Indonesia]]. insert(raw_handlers, function(data) local location = data.category:match("^Languages of (.*)$") if location then local args = require("Module:parameters").process(data.args, { ["flagfile"] = true, ["commonscat"] = true, ["wp"] = true, ["basename"] = true, ["parent"] = true, ["locationcat"] = true, ["locationlink"] = true, }) local topright local basename = args.basename or location:gsub(", .*", "") if args.flagfile ~= "-" then local flagfile_arg = args.flagfile or ("Flag of %s.svg"):format(basename) local files = require(parse_utilities_module).split_on_comma(flagfile_arg) local topright_parts = {} for _, file in ipairs(files) do local flagfile = "File:" .. file local flagfile_page = new_title(flagfile) if flagfile_page and flagfile_page.file.exists then insert(topright_parts, ("[[%s|right|100px|border]]"):format(flagfile)) elseif args.flagfile then error(("Explicit flagfile '%s' doesn't exist"):format(flagfile)) end end topright = concat(topright_parts) end if args.wp then local wp = require("Module:yesno")(args.wp, "+") if wp == "+" or wp == true then wp = data.category end if wp then local wp_topright = ("{{wikipedia|%s}}"):format(wp) if topright then topright = topright .. wp_topright else topright = wp_topright end end end if args.commonscat then local commonscat = require("Module:yesno")(args.commonscat, "+") if commonscat == "+" or commonscat == true then commonscat = data.category end if commonscat then local commons_topright = ("{{commonscat|%s}}"):format(commonscat) if topright then topright = topright .. commons_topright else topright = commons_topright end end end local bare_location = location:match("^the (.*)$") or location local location_link = args.locationlink or link_location(location) local bare_basename = basename:match("^the (.*)$") or basename local parents = {} if args.parent then local explicit_parents = require(parse_utilities_module).split_on_comma(args.parent) for i, parent in ipairs(explicit_parents) do local actual_parent, sort_key = parent:match("^(.-):(.*)$") if actual_parent then parent = actual_parent sort_key = sort_key:gsub("%+", bare_location) else sort_key = " " .. bare_location end insert(parents, {name = "Languages of " .. parent, sort = sort_key}) end else insert(parents, {name = "Languages by country", sort = {sort_base = bare_location, lang = "en"}}) end if args.locationcat then local explicit_location_cats = require(parse_utilities_module).split_on_comma(args.locationcat) for i, locationcat in ipairs(explicit_location_cats) do insert(parents, {name = "Category:" .. locationcat, sort = " Languages"}) end else local location_cat = ("Category:%s"):format(bare_location) local location_page = new_title(location_cat) if location_page and location_page.exists then insert(parents, {name = location_cat, sort = "Languages"}) end end local description = ("Categories for languages of %s (including sublects)."):format(location_link) return { topright = topright, description = description, parents = parents, breadcrumb = bare_basename, additional = "{{{umbrella_msg}}}", }, true end end) -- Handle categories such as [[:Category:English-based creole or pidgin languages]]. insert(raw_handlers, function(data) local langname = data.category:match("(.*)%-based creole or pidgin languages$") if langname then local lang = m_languages.getByCanonicalName(langname) if lang then return { lang = lang:getCode(), description = "Languages which developed as a [[creole]] or [[pidgin]] from " .. lang:makeCategoryLink() .. ".", parents = {{name = "Creole or pidgin languages", sort = {sort_base = "*" .. langname, lang = "en"}}}, breadcrumb = lang:getCanonicalName() .. "-based", } end end end) -- Handle categories such as [[:Category:English-based constructed languages]]. insert(raw_handlers, function(data) local langname = data.category:match("(.*)%-based constructed languages$") if langname then local lang = m_languages.getByCanonicalName(langname) if lang then return { lang = lang:getCode(), description = "Constructed languages which are based on " .. lang:makeCategoryLink() .. ".", parents = {{name = "Constructed languages", sort = {sort_base = "*" .. langname, lang = "en"}}}, breadcrumb = lang:getCanonicalName() .. "-based", } end end end) return {RAW_CATEGORIES = raw_categories, RAW_HANDLERS = raw_handlers} 9f0i5jaq1j7omkh2erfeca1ltyz92tf 17453 17442 2026-07-13T08:53:55Z Hiyuune 6766 17453 Scribunto text/plain local new_title = mw.title.new local ucfirst = require("Module:string utilities").ucfirst local split = require("Module:string utilities").split local raw_categories = {} local raw_handlers = {} local m_languages = require("Module:languages") local m_sc_getByCode = require("Module:scripts").getByCode local m_table = require("Module:table") local parse_utilities_module = "Module:parse utilities" local concat = table.concat local insert = table.insert local reverse_ipairs = m_table.reverseIpairs local serial_comma_join = m_table.serialCommaJoin local size = m_table.size local sorted_pairs = m_table.sortedPairs local to_json = require("Module:JSON").toJSON local Hang = m_sc_getByCode("Hang") local Hani = m_sc_getByCode("Hani") local Hira = m_sc_getByCode("Hira") local Hrkt = m_sc_getByCode("Hrkt") local Kana = m_sc_getByCode("Kana") local function track(page) -- [[Special:WhatLinksHere/Wiktionary:Tracking/category tree/languages/PAGE]] return require("Module:debug/track")("category tree/languages/" .. page) end -- This handles language categories of the form e.g. [[:Category:French language]] and -- [[:Category:British Sign Language]]; categories like [[:Category:Languages of Indonesia]]; categories like -- [[:Category:English-based creole or pidgin languages]]; and categories like -- [[:Category:English-based constructed languages]]. ----------------------------------------------------------------------------- -- -- -- RAW CATEGORIES -- -- -- ----------------------------------------------------------------------------- raw_categories["Reo"] = { topright = "{{commonscat|Languages}}\n[[File:Languages world map-transparent background.svg|thumb|right|250px|Rough world map of language families]]", description = "This category contains the categories for every language on Wiktionary.", additional = "Not all languages that Wiktionary recognises may have a category here yet. There are many that have " .. "not yet received any attention from editors, mainly because not all Wiktionary users know about every single " .. "language. See [[Wiktionary:List of languages]] for a full list.", parents = { "Whakaraparapa", }, } raw_categories["All extinct languages"] = { description = "This category contains the categories for every [[extinct language]] on Wiktionary.", additional = "Do not confuse this category with [[:Category:Extinct languages]], which is an umbrella category for the names of extinct languages in specific other languages (e.g. {{m+|de|Langobardisch}} for the ancient [[Lombardic]] language).", parents = { "Reo", }, } raw_categories["Languages by country"] = { topright = "{{commonscat|Languages by continent}}", description = "Categories that group languages by country.", additional = "{{{umbrella_meta_msg}}}", parents = { "Reo", }, } raw_categories["Language isolates"] = { topright = "{{wikipedia|Language isolate}}\n{{commonscat|Language isolates}}", description = "Languages with no known relatives.", parents = { {name = "Languages by family", sort = "*Isolates"}, {name = "All language families", sort = "Isolates"}, }, } raw_categories["Languages not sorted into a location category"] = { description = "Languages which do not specify (in their {{tl|auto cat}} call) the location(s) where they are spoken.", additional = "This excludes constructed and reconstructed languages; as a result, all languages in this category explicitly specify their location as {{cd|UNKNOWN}}.", parents = { {name = "Requests"}, }, hidden = true, } ----------------------------------------------------------------------------- -- -- -- RAW HANDLERS -- -- -- ----------------------------------------------------------------------------- -- Given a category (without the "Category:" prefix), look up the page defining the category, find the call to -- {{auto cat}} (if any), and return a table of its arguments. If the category page doesn't exist or doesn't have -- an {{auto cat}} invocation, return nil. -- -- FIXME: Duplicated in [[Module:category tree/lects]]. local function scrape_category_for_auto_cat_args(cat) local cat_page = mw.title.new("Category:" .. cat) if cat_page then local contents = cat_page:getContent() if contents then local frame = mw.getCurrentFrame() for template in require("Module:template parser").find_templates(contents) do -- The template parser automatically handles redirects and canonicalizes them, so uses of {{autocat}} -- will also be found. if template:get_name() == "auto cat" then return template:get_arguments() end end end end return nil end local function link_location(location) local location_no_the = location:match("^the (.*)$") local bare_location = location_no_the or location local location_link local bare_location_parts = split(bare_location, ", ") for i, part in ipairs(bare_location_parts) do bare_location_parts[i] = ("[[%s]]"):format(part) end location_link = concat(bare_location_parts, ", ") if location_no_the then location_link = "the " .. location_link end return location_link end local function linkbox(lang, setwiki, setwikt, setsister, entryname) local wiktionarylinks = {} local canonicalName = lang:getCanonicalName() local wikimediaLanguages = lang:getWikimediaLanguages() local wikipediaArticle = setwiki or lang:getWikipediaArticle() setsister = setsister and ucfirst(setsister) or nil if setwikt then track("setwikt") if setwikt == "-" then track("setwikt/hyphen") end end if setwikt ~= "-" and wikimediaLanguages and wikimediaLanguages[1] then for _, wikimedialang in ipairs(wikimediaLanguages) do local check = new_title(wikimedialang:getCode() .. ":") if check and check.isExternal then insert(wiktionarylinks, (wikimedialang:getCanonicalName() ~= canonicalName and "(''" .. wikimedialang:getCanonicalName() .. "'') " or "") .. "'''[[:" .. wikimedialang:getCode() .. ":|" .. wikimedialang:getCode() .. ".wiktionary.org]]'''") end end wiktionarylinks = concat(wiktionarylinks, "<br/>") end local wikt_plural = wikimediaLanguages[2] and "s" or "" if #wiktionarylinks == 0 then wiktionarylinks = "''None.''" end if setsister then track("setsister") if setsister == "-" then track("setsister/hyphen") else setsister = "Category:" .. setsister end else setsister = lang:getCommonsCategory() or "-" end return concat{ [=[<div class="wikitable" style="float: right; clear: right; margin: 0 0 0.5em 1em; width: 300px; padding: 5px;"> <div style="text-align: center; margin-bottom: 10px; margin-top: 5px">''']=], canonicalName, [=[ language links'''</div> {| style="font-size: 90%" |- | style="vertical-align: top; height: 35px; border-bottom: 1px solid lightgray;" | [[File:Wikipedia-logo.png|35px|none|Wikipedia]] | style="border-bottom: 1px solid lightgray;" | '''English Wikipedia''' has an article on: <div style="padding: 5px 10px">]=], (setwiki == "-" and "''None.''" or "'''[[w:" .. wikipediaArticle .. "|" .. wikipediaArticle .. "]]'''"), [=[</div> |- | style="vertical-align: top; height: 35px; border-bottom: 1px solid lightgray;" | [[File:Wikimedia-logo.svg|35px|none|Wikimedia Commons]] | style="border-bottom: 1px solid lightgray;" | '''Wikimedia Commons''' has links to ]=], canonicalName, [=[-related content in sister projects: <div style="padding: 5px 10px">]=], (setsister == "-" and "''None.''" or "'''[[commons:" .. setsister .. "|" .. setsister .. "]]'''"), [=[</div> |- | style="vertical-align: top; height: 35px; width: 40px; border-bottom: 1px solid lightgray;" | [[File:Wiktionary-logo-v2.svg|35px|none|Wiktionary]] |style="border-bottom: 1px solid lightgray;" | '''Wiktionary edition''']=], wikt_plural, [=[ written in ]=], canonicalName, [=[: <div style="padding: 5px 10px">]=], wiktionarylinks, [=[</div> |- | style="vertical-align: top; height: 35px; border-bottom: 1px solid lightgray;" | [[File:Open book nae 02.svg|35px|none|Entry]] | style="border-bottom: 1px solid lightgray;" | '''Wiktionary entry''' for the language's English name: <div style="padding: 5px 10px">''']=], require("Module:links").full_link({lang = m_languages.getByCode("en"), term = entryname or canonicalName}), [=['''</div> |- | style="vertical-align: top; height: 35px;" | [[File:Crystal kfind.png|35px|none|Considerations]] || '''Wiktionary resources''' for editors contributing to ]=], canonicalName, [=[ entries: <div style="padding: 5px 0"> * '''[[Wiktionary:]=], canonicalName, [=[ entry guidelines]]''' * '''[[:Category:]=], canonicalName, [=[ reference templates|Reference templates]] ({{PAGESINCAT:]=], canonicalName, [=[ reference templates}})''' * '''[[Appendix:]=], canonicalName, [=[ bibliography|Bibliography]]''' |} </div>]=] } end local function edit_link(title, text) return '<span class="plainlinks">[' .. tostring(mw.uri.fullUrl(title, { action = "edit" })) .. ' ' .. text .. ']</span>' end -- Should perhaps use wiki syntax. local function infobox(lang) local ret = {} insert(ret, '<table class="wikitable language-category-info"') local raw_data = lang:getData("extra") if raw_data then local replacements = { [1] = "canonical-name", [2] = "wikidata-item", [3] = "family", [4] = "scripts", } local function replacer(letter1, letter2) return letter1:lower() .. "-" .. letter2:lower() end -- For each key in the language data modules, returns a descriptive -- kebab-case version (containing ASCII lowercase words separated -- by hyphens). local function kebab_case(key) key = replacements[key] or key key = key:gsub("(%l)(%u)", replacer):gsub("(%l)_(%l)", replacer) return key end local compress = {compress = true} local function html_attribute_encode(str) str = to_json(str, compress) :gsub('"', "&quot;") -- & in attributes is automatically escaped. -- :gsub("&", "&amp;") :gsub("<", "&lt;") :gsub(">", "&gt;") return str end insert(ret, ' data-code="' .. lang:getCode() .. '"') for k, v in sorted_pairs(raw_data) do insert(ret, " data-" .. kebab_case(k) .. '="' .. html_attribute_encode(v) .. '"') end end insert(ret, '>\n') insert(ret, '<tr class="language-category-data">\n<th colspan="2">' .. edit_link(lang:getDataModuleName(), "Edit language data") .. "</th>\n</tr>\n") insert(ret, "<tr>\n<th>Canonical name</th><td>" .. lang:getCanonicalName() .. "</td>\n</tr>\n") local otherNames = lang:getOtherNames() if otherNames then local names = {} for _, name in ipairs(otherNames) do insert(names, "<li>" .. name .. "</li>") end if #names > 0 then insert(ret, "<tr>\n<th>Other names</th><td><ul>" .. concat(names, "\n") .. "</ul></td>\n</tr>\n") end end local aliases = lang:getAliases() if aliases then local names = {} for _, name in ipairs(aliases) do insert(names, "<li>" .. name .. "</li>") end if #names > 0 then insert(ret, "<tr>\n<th>Aliases</th><td><ul>" .. concat(names, "\n") .. "</ul></td>\n</tr>\n") end end local varieties = lang:getVarieties() if varieties then local names = {} for _, name in ipairs(varieties) do if type(name) == "string" then insert(names, "<li>" .. name .. "</li>") else assert(type(name) == "table") local first_var local subvars = {} for i, var in ipairs(name) do if i == 1 then first_var = var else insert(subvars, "<li>" .. var .. "</li>") end end if #subvars > 0 then insert(names, "<li><dl><dt>" .. first_var .. "</dt>\n<dd><ul>" .. concat(subvars, "\n") .. "</ul></dd></dl></li>") elseif first_var then insert(names, "<li>" .. first_var .. "</li>") end end end if #names > 0 then insert(ret, "<tr>\n<th>Varieties</th><td><ul>" .. concat(names, "\n") .. "</ul></td>\n</tr>\n") end end insert(ret, "<tr>\n<th>[[Wiktionary:Languages|Language code]]</th><td><code>" .. lang:getCode() .. "</code></td>\n</tr>\n") insert(ret, "<tr>\n<th>[[Wiktionary:Families|Language family]]</th>\n") local fam = lang:getFamily() local famCode = fam and fam:getCode() if not fam then insert(ret, "<td>unclassified</td>") elseif famCode == "qfa-iso" then insert(ret, "<td>[[:Category:Language isolates|language isolate]]</td>") elseif famCode == "qfa-mix" then insert(ret, "<td>[[:Category:Mixed languages|mixed language]]</td>") elseif famCode == "sgn" then insert(ret, "<td>[[:Category:Sign languages|sign language]]</td>") elseif famCode == "crp" then insert(ret, "<td>[[:Category:Creole or pidgin languages|creole or pidgin]]</td>") elseif famCode == "art" then insert(ret, "<td>[[:Category:Constructed languages|constructed language]]</td>") else insert(ret, "<td>" .. fam:makeCategoryLink() .. "</td>") end insert(ret, "\n</tr>\n<tr>\n<th>Ancestors</th>\n<td>") local ancestors = lang:getAncestors() if ancestors[2] then local ancestorList = {} for i, anc in ipairs(ancestors) do ancestorList[i] = "<li>" .. anc:makeCategoryLink() .. "</li>" end insert(ret, "<ul>\n" .. concat(ancestorList, "\n") .. "</ul>") else local ancestorChain = lang:getAncestorChainOld() if ancestorChain[1] then local chain = {} for _, anc in reverse_ipairs(ancestorChain) do insert(chain, "<li>" .. anc:makeCategoryLink() .. "</li>") end insert(ret, "<ul>\n" .. concat(chain, "\n<ul>\n") .. ("</ul>"):rep(#chain)) else insert(ret, "unknown") end end insert(ret, "</td>\n</tr>\n") local scripts = lang:getScripts() if scripts[1] then local script_text = {} local function makeScriptLine(sc) local code = sc:getCode() local url = tostring(mw.uri.fullUrl('Special:Search', { search = 'contentmodel:css insource:"' .. code .. '" insource:/\\.' .. code .. '/', ns8 = '1' })) return sc:makeCategoryLink() .. ' (<span class="plainlinks" title="Search for stylesheets referencing this script">[' .. url .. ' <code>' .. code .. '</code>]</span>)' end local function add_Hrkt(text) insert(text, "<li>" .. makeScriptLine(Hrkt)) insert(text, "<ul>") insert(text, "<li>" .. makeScriptLine(Hira) .. "</li>") insert(text, "<li>" .. makeScriptLine(Kana) .. "</li>") insert(text, "</ul>") insert(text, "</li>") end for _, sc in ipairs(scripts) do local text = {} local code = sc:getCode() if code == "Hrkt" then add_Hrkt(text) else insert(text, "<li>" .. makeScriptLine(sc)) if code == "Jpan" then insert(text, "<ul>") insert(text, "<li>" .. makeScriptLine(Hani) .. "</li>") add_Hrkt(text) insert(text, "</ul>") elseif code == "Kore" then insert(text, "<ul>") insert(text, "<li>" .. makeScriptLine(Hang) .. "</li>") insert(text, "<li>" .. makeScriptLine(Hani) .. "</li>") insert(text, "</ul>") end insert(text, "</li>") end insert(script_text, concat(text, "\n")) end insert(ret, "<tr>\n<th>[[Wiktionary:Scripts|Scripts]]</th>\n<td><ul>\n" .. concat(script_text, "\n") .. "</ul></td>\n</tr>\n") else insert(ret, "<tr>\n<th>[[Wiktionary:Scripts|Scripts]]</th>\n<td>not specified</td>\n</tr>\n") end local function add_module_info(raw_data, heading) if raw_data then local scripts = lang:getScriptCodes() local module_info, add = {}, false if type(raw_data) == "string" then insert(module_info, ("[[Module:%s]]"):format(raw_data)) add = true else local raw_data_type = type(raw_data) if raw_data_type == "table" and size(scripts) == 1 and type(raw_data[scripts[1]]) == "string" then insert(module_info, ("[[Module:%s]]"):format(raw_data[scripts[1]])) add = true elseif raw_data_type == "table" then insert(module_info, "<ul>") for script, data in sorted_pairs(raw_data) do if type(data) == "string" and m_sc_getByCode(script) then insert(module_info, ("<li><code>%s</code>: [[Module:%s]]</li>"):format(script, data)) end end insert(module_info, "</ul>") add = size(module_info) > 2 end end if add then insert(ret, [=[ <tr> <th>]=] .. heading .. [=[</th> <td>]=] .. concat(module_info) .. [=[</td> </tr> ]=]) end end end add_module_info(raw_data.generate_forms, "Form-generating<br>module") add_module_info(raw_data.translit, "[[Wiktionary:Transliteration and romanization|Transliteration<br>module]]") add_module_info(raw_data.display_text, "Display text<br>module") add_module_info(raw_data.entry_name, "Entry name<br>module") add_module_info(raw_data.sort_key, "[[sortkey|Sortkey]]<br>module") local wikidataItem = lang:getWikidataItem() if lang:getWikidataItem() and mw.wikibase then local URL = mw.wikibase.getEntityUrl(wikidataItem) local link if URL then link = '[' .. URL .. ' ' .. wikidataItem .. ']' else link = '<span class="error">Invalid Wikidata item: <code>' .. wikidataItem .. '</code></span>' end insert(ret, "<tr><th>Wikidata</th><td>" .. link .. "</td></tr>") end insert(ret, "</table>") return concat(ret) end local function NavFrame(content, title) return '<div class="NavFrame"><div class="NavHead">' .. (title or '{{{title}}}') .. '</div>' .. '<div class="NavContent" style="text-align: left;">' .. content .. '</div></div>' end local function get_description_topright_additional(lang, locations, extinct, setwiki, setwikt, setsister, entryname) local nameWithLanguage = lang:getCategoryName("nocap") if lang:getCode() == "und" then local description = "This is the main category of the '''" .. nameWithLanguage .. "''', represented in Wiktionary by the [[Wiktionary:Languages|code]] '''" .. lang:getCode() .. "'''. " .. "This language contains terms in historical writing, whose meaning has not yet been determined by scholars." return description, nil, nil end local canonicalName = lang:getCanonicalName() local topright = linkbox(lang, setwiki, setwikt, setsister, entryname) local the_prefix if canonicalName:find(" Language$") then the_prefix = "" else the_prefix = "the " end local description = "This is the main category of " .. the_prefix .. "'''" .. nameWithLanguage .. "'''." local location_links = {} local prep local saw_embedded_comma = false for _, location in ipairs(locations) do local this_prep if location == "the world" then this_prep = "across" insert(location_links, location) elseif location ~= "UNKNOWN" then this_prep = "in" if location:find(",") then saw_embedded_comma = true end insert(location_links, link_location(location)) end if this_prep then if prep and this_prep ~= prep then error("Can't handle location 'the world' along with another location (clashing prepositions)") end prep = this_prep end end local location_desc if #location_links > 0 then local location_link_text if saw_embedded_comma and #location_links >= 3 then location_link_text = mw.text.listToText(location_links, "; ", "; and ") else location_link_text = serial_comma_join(location_links) end location_desc = ("It is %s %s %s.\n\n"):format( extinct and "an [[extinct language]] that was formerly spoken" or "spoken", prep, location_link_text) elseif extinct then location_desc = "It is an [[extinct language]].\n\n" else location_desc = "" end local add = location_desc .. "Information about " .. canonicalName .. ":\n\n" .. infobox(lang) if lang:hasType("reconstructed") then add = add .. "\n\n" .. ucfirst(canonicalName) .. " is a reconstructed language. Its words and roots are not directly attested in any written works, but have been reconstructed through the ''comparative method'', " .. "which finds regular similarities between languages that cannot be explained by coincidence or word-borrowing, and extrapolates ancient forms from these similarities.\n\n" .. "According to our [[Wiktionary:Criteria for inclusion|criteria for inclusion]], terms in " .. canonicalName .. " should '''not''' be present in entries in the main namespace, but may be added to the Reconstruction: namespace." elseif lang:hasType("appendix-constructed") then add = add .. "\n\n" .. ucfirst(canonicalName) .. " is a constructed language that is only in sporadic use. " .. "According to our [[Wiktionary:Criteria for inclusion|criteria for inclusion]], terms in " .. canonicalName .. " should '''not''' be present in entries in the main namespace, but may be added to the Appendix: namespace. " .. "All terms in this language may be available at [[Appendix:" .. ucfirst(canonicalName) .. "]]." end local about = new_title("Wiktionary:About " .. canonicalName) if about.exists then add = add .. "\n\n" .. "Please see '''[[Wiktionary:About " .. canonicalName .. "]]''' for information and special considerations for creating " .. nameWithLanguage .. " entries." end local ok, tree_of_descendants = pcall( require("Module:family tree").print_children, lang:getCode(), { protolanguage_under_family = true, must_have_descendants = true }) if ok then if tree_of_descendants then add = add .. NavFrame( tree_of_descendants, "Family tree") else add = add .. "\n\n" .. ucfirst(lang:getCanonicalName()) .. " has no descendants or varieties listed in Wiktionary's language data modules." end else mw.log("error while generating tree: " .. tostring(tree_of_descendants)) end return description, topright, add end local function get_parents(lang, locations, extinct) local canonicalName = lang:getCanonicalName() local sortkey = {sort_base = canonicalName, lang = "mi"} local ret = {{name = "Reo", sort = sortkey}} local fam = lang:getFamily() local famCode = fam and fam:getCode() -- FIXME: Some of the following categories should be added to this module. if not fam then insert(ret, {name = "Category:Unclassified languages", sort = sortkey}) elseif famCode == "qfa-iso" then insert(ret, {name = "Category:Language isolates", sort = sortkey}) elseif famCode == "qfa-mix" then insert(ret, {name = "Category:Mixed languages", sort = sortkey}) elseif famCode == "sgn" then insert(ret, {name = "Category:All sign languages", sort = sortkey}) elseif famCode == "crp" then insert(ret, {name = "Category:Creole or pidgin languages", sort = sortkey}) for _, anc in ipairs(lang:getAncestors()) do -- Avoid Haitian Creole being categorised in [[:Category:Haitian Creole-based creole or pidgin languages]], as one of its ancestors is an etymology-only variety of it. -- Use that ancestor's ancestors instead. if anc:getFullCode() == lang:getCode() then for _, anc_extra in ipairs(anc:getAncestors()) do insert(ret, {name = "Category:" .. ucfirst(anc_extra:getFullName()) .. "-based creole or pidgin languages", sort = sortkey}) end else insert(ret, {name = "Category:" .. ucfirst(anc:getFullName()) .. "-based creole or pidgin languages", sort = sortkey}) end end elseif famCode == "art" then if lang:hasType("appendix-constructed") then insert(ret, {name = "Category:Appendix-only constructed languages", sort = sortkey}) else insert(ret, {name = "Category:Constructed languages", sort = sortkey}) end for _, anc in ipairs(lang:getAncestors()) do if anc:getFullCode() == lang:getCode() then for _, anc_extra in ipairs(anc:getAncestors()) do insert(ret, {name = "Category:" .. ucfirst(anc_extra:getFullName()) .. "-based constructed languages", sort = sortkey}) end else insert(ret, {name = "Category:" .. ucfirst(anc:getFullName()) .. "-based constructed languages", sort = sortkey}) end end else insert(ret, {name = "Category:" .. fam:getCategoryName(), sort = sortkey}) if lang:hasType("reconstructed") then insert(ret, { name = "Category:Reconstructed languages", sort = {sort_base = canonicalName:gsub("^Proto%-", ""), lang = "en"} }) end end local function add_sc_cat(sc) insert(ret, {name = "Category:Reo " .. sc:getCategoryName(), sort = sortkey}) end local function add_Hrkt() add_sc_cat(Hrkt) add_sc_cat(Hira) add_sc_cat(Kana) end for _, sc in ipairs(lang:getScripts()) do if sc:getCode() == "Hrkt" then add_Hrkt() else add_sc_cat(sc) if sc:getCode() == "Jpan" then add_sc_cat(Hani) add_Hrkt() elseif sc:getCode() == "Kore" then add_sc_cat(Hang) add_sc_cat(Hani) end end end if lang:hasTranslit() then insert(ret, {name = "Category:Languages with automatic transliteration", sort = sortkey}) end local function insert_location_language_cat(location) local cat = "Languages of " .. location insert(ret, {name = "Category:" .. cat, sort = sortkey}) local auto_cat_args = scrape_category_for_auto_cat_args(cat) local location_parent = auto_cat_args and auto_cat_args.parent if location_parent then local split_parents = require(parse_utilities_module).split_on_comma(location_parent) for _, parent in ipairs(split_parents) do parent = parent:match("^(.-):.*$") or parent insert_location_language_cat(parent) end end end local saw_location = false for _, location in ipairs(locations) do if location ~= "UNKNOWN" then saw_location = true insert_location_language_cat(location) end end if extinct then insert(ret, {name = "Category:All extinct languages", sort = sortkey}) end if not saw_location and not (lang:hasType("reconstructed") or (fam and fam:getCode() == "art")) then -- Constructed and reconstructed languages don't need a location specified and often won't have one, -- so don't put them in this maintenance category. insert(ret, {name = "Category:Languages not sorted into a location category", sort = sortkey}) end return ret end local function get_children() local ret = {} -- FIXME: We should work on the children mechanism so it isn't necessary to manually specify these. --for _, label in ipairs({"appendices", "entry maintenance", "lemmas", "names", "phrases", "rhymes", "symbols", "templates", "terms by etymology", "terms by usage"}) do -- insert(ret, {name = label, is_label = true}) --end --insert(ret, {name = "terms derived from {{{langname}}}", is_label = true, lang = false}) --insert(ret, {name = "{{{langcode}}}:All topics", sort = "all topics"}) --insert(ret, {name = "Varieties of {{{langname}}}"}) --insert(ret, {name = "Requests concerning {{{langname}}}"}) --insert(ret, {name = "Rhymes:{{{langname}}}", description = "Lists of {{{langname}}} words by their rhymes."}) --insert(ret, {name = "User {{{langcode}}}", description = "Wiktionary users categorized by fluency levels in {{{langdisp}}}."}) return ret end -- Handle language categories of the form e.g. [[:Category:French language]] and -- [[:Category:British Sign Language]]. insert(raw_handlers, function(data) local category = data.category if not (category:match("[Rr]eo ") or category:match("[Ll]ect$")) then return nil end local lang = m_languages.getByCanonicalName(category) if not lang then local langname = category:match("^Reo (.*)") if langname then lang = m_languages.getByCanonicalName(langname) end if not lang then return nil end end local args = require("Module:parameters").process(data.args, { [1] = {list = true}, ["setwiki"] = true, ["setwikt"] = true, ["setsister"] = true, ["entryname"] = true, ["extinct"] = {type = "boolean"}, }) -- If called from inside, don't require any arguments, as they can't be known -- in general and aren't needed just to generate the first parent (used for -- breadcrumbs). if #args[1] == 0 and not data.called_from_inside then -- At least one location must be specified unless the language is constructed (e.g. Esperanto) or reconstructed (e.g. Proto-Indo-European). local fam = lang:getFamily() if not (lang:hasType("reconstructed") or (fam and fam:getCode() == "art")) then error("At least one location (param 1=) must be specified for language '" .. lang:getCanonicalName() .. "' (code '" .. lang:getCode() .. "'). " .. "Use the value UNKNOWN if the language's location is truly unknown.") end end local description, topright, additional = "", "", "" -- If called from inside the category tree system, it's called when generating -- parents or children, and we don't need to generate the description or additional -- text (which is very expensive in terms of memory because it calls [[Module:family tree]], -- which calls [[Module:languages/data/all]]). if not data.called_from_inside then description, topright, additional = get_description_topright_additional( lang, args[1], args.extinct, args.setwiki, args.setwikt, args.setsister, args.entryname ) end return { canonical_name = lang:getCategoryName(), description = description, lang = lang:getCode(), topright = topright, additional = additional, breadcrumb = lang:getCanonicalName(), parents = get_parents(lang, args[1], args.extinct), extra_children = get_children(lang), umbrella = false, can_be_empty = true, }, true end) -- Handle categories such as [[:Category:Languages of Indonesia]]. insert(raw_handlers, function(data) local location = data.category:match("^Languages of (.*)$") if location then local args = require("Module:parameters").process(data.args, { ["flagfile"] = true, ["commonscat"] = true, ["wp"] = true, ["basename"] = true, ["parent"] = true, ["locationcat"] = true, ["locationlink"] = true, }) local topright local basename = args.basename or location:gsub(", .*", "") if args.flagfile ~= "-" then local flagfile_arg = args.flagfile or ("Flag of %s.svg"):format(basename) local files = require(parse_utilities_module).split_on_comma(flagfile_arg) local topright_parts = {} for _, file in ipairs(files) do local flagfile = "File:" .. file local flagfile_page = new_title(flagfile) if flagfile_page and flagfile_page.file.exists then insert(topright_parts, ("[[%s|right|100px|border]]"):format(flagfile)) elseif args.flagfile then error(("Explicit flagfile '%s' doesn't exist"):format(flagfile)) end end topright = concat(topright_parts) end if args.wp then local wp = require("Module:yesno")(args.wp, "+") if wp == "+" or wp == true then wp = data.category end if wp then local wp_topright = ("{{wikipedia|%s}}"):format(wp) if topright then topright = topright .. wp_topright else topright = wp_topright end end end if args.commonscat then local commonscat = require("Module:yesno")(args.commonscat, "+") if commonscat == "+" or commonscat == true then commonscat = data.category end if commonscat then local commons_topright = ("{{commonscat|%s}}"):format(commonscat) if topright then topright = topright .. commons_topright else topright = commons_topright end end end local bare_location = location:match("^the (.*)$") or location local location_link = args.locationlink or link_location(location) local bare_basename = basename:match("^the (.*)$") or basename local parents = {} if args.parent then local explicit_parents = require(parse_utilities_module).split_on_comma(args.parent) for i, parent in ipairs(explicit_parents) do local actual_parent, sort_key = parent:match("^(.-):(.*)$") if actual_parent then parent = actual_parent sort_key = sort_key:gsub("%+", bare_location) else sort_key = " " .. bare_location end insert(parents, {name = "Languages of " .. parent, sort = sort_key}) end else insert(parents, {name = "Languages by country", sort = {sort_base = bare_location, lang = "en"}}) end if args.locationcat then local explicit_location_cats = require(parse_utilities_module).split_on_comma(args.locationcat) for i, locationcat in ipairs(explicit_location_cats) do insert(parents, {name = "Category:" .. locationcat, sort = " Languages"}) end else local location_cat = ("Category:%s"):format(bare_location) local location_page = new_title(location_cat) if location_page and location_page.exists then insert(parents, {name = location_cat, sort = "Languages"}) end end local description = ("Categories for languages of %s (including sublects)."):format(location_link) return { topright = topright, description = description, parents = parents, breadcrumb = bare_basename, additional = "{{{umbrella_msg}}}", }, true end end) -- Handle categories such as [[:Category:English-based creole or pidgin languages]]. insert(raw_handlers, function(data) local langname = data.category:match("(.*)%-based creole or pidgin languages$") if langname then local lang = m_languages.getByCanonicalName(langname) if lang then return { lang = lang:getCode(), description = "Languages which developed as a [[creole]] or [[pidgin]] from " .. lang:makeCategoryLink() .. ".", parents = {{name = "Creole or pidgin languages", sort = {sort_base = "*" .. langname, lang = "en"}}}, breadcrumb = lang:getCanonicalName() .. "-based", } end end end) -- Handle categories such as [[:Category:English-based constructed languages]]. insert(raw_handlers, function(data) local langname = data.category:match("(.*)%-based constructed languages$") if langname then local lang = m_languages.getByCanonicalName(langname) if lang then return { lang = lang:getCode(), description = "Constructed languages which are based on " .. lang:makeCategoryLink() .. ".", parents = {{name = "Constructed languages", sort = {sort_base = "*" .. langname, lang = "en"}}}, breadcrumb = lang:getCanonicalName() .. "-based", } end end end) return {RAW_CATEGORIES = raw_categories, RAW_HANDLERS = raw_handlers} cslq4xo9w4lnjx7egeec444bvzdtnbt 17454 17453 2026-07-13T08:54:18Z Hiyuune 6766 17454 Scribunto text/plain local new_title = mw.title.new local ucfirst = require("Module:string utilities").ucfirst local split = require("Module:string utilities").split local raw_categories = {} local raw_handlers = {} local m_languages = require("Module:languages") local m_sc_getByCode = require("Module:scripts").getByCode local m_table = require("Module:table") local parse_utilities_module = "Module:parse utilities" local concat = table.concat local insert = table.insert local reverse_ipairs = m_table.reverseIpairs local serial_comma_join = m_table.serialCommaJoin local size = m_table.size local sorted_pairs = m_table.sortedPairs local to_json = require("Module:JSON").toJSON local Hang = m_sc_getByCode("Hang") local Hani = m_sc_getByCode("Hani") local Hira = m_sc_getByCode("Hira") local Hrkt = m_sc_getByCode("Hrkt") local Kana = m_sc_getByCode("Kana") local function track(page) -- [[Special:WhatLinksHere/Wiktionary:Tracking/category tree/languages/PAGE]] return require("Module:debug/track")("category tree/languages/" .. page) end -- This handles language categories of the form e.g. [[:Category:French language]] and -- [[:Category:British Sign Language]]; categories like [[:Category:Languages of Indonesia]]; categories like -- [[:Category:English-based creole or pidgin languages]]; and categories like -- [[:Category:English-based constructed languages]]. ----------------------------------------------------------------------------- -- -- -- RAW CATEGORIES -- -- -- ----------------------------------------------------------------------------- raw_categories["Reo"] = { topright = "{{commonscat|Languages}}\n[[File:Languages world map-transparent background.svg|thumb|right|250px|Rough world map of language families]]", description = "This category contains the categories for every language on Wiktionary.", additional = "Not all languages that Wiktionary recognises may have a category here yet. There are many that have " .. "not yet received any attention from editors, mainly because not all Wiktionary users know about every single " .. "language. See [[Wiktionary:List of languages]] for a full list.", parents = { "Whakaraparapa", }, } raw_categories["All extinct languages"] = { description = "This category contains the categories for every [[extinct language]] on Wiktionary.", additional = "Do not confuse this category with [[:Category:Extinct languages]], which is an umbrella category for the names of extinct languages in specific other languages (e.g. {{m+|de|Langobardisch}} for the ancient [[Lombardic]] language).", parents = { "Reo", }, } raw_categories["Languages by country"] = { topright = "{{commonscat|Languages by continent}}", description = "Categories that group languages by country.", additional = "{{{umbrella_meta_msg}}}", parents = { "Reo", }, } raw_categories["Language isolates"] = { topright = "{{wikipedia|Language isolate}}\n{{commonscat|Language isolates}}", description = "Languages with no known relatives.", parents = { {name = "Languages by family", sort = "*Isolates"}, {name = "All language families", sort = "Isolates"}, }, } raw_categories["Languages not sorted into a location category"] = { description = "Languages which do not specify (in their {{tl|auto cat}} call) the location(s) where they are spoken.", additional = "This excludes constructed and reconstructed languages; as a result, all languages in this category explicitly specify their location as {{cd|UNKNOWN}}.", parents = { {name = "Requests"}, }, hidden = true, } ----------------------------------------------------------------------------- -- -- -- RAW HANDLERS -- -- -- ----------------------------------------------------------------------------- -- Given a category (without the "Category:" prefix), look up the page defining the category, find the call to -- {{auto cat}} (if any), and return a table of its arguments. If the category page doesn't exist or doesn't have -- an {{auto cat}} invocation, return nil. -- -- FIXME: Duplicated in [[Module:category tree/lects]]. local function scrape_category_for_auto_cat_args(cat) local cat_page = mw.title.new("Category:" .. cat) if cat_page then local contents = cat_page:getContent() if contents then local frame = mw.getCurrentFrame() for template in require("Module:template parser").find_templates(contents) do -- The template parser automatically handles redirects and canonicalizes them, so uses of {{autocat}} -- will also be found. if template:get_name() == "auto cat" then return template:get_arguments() end end end end return nil end local function link_location(location) local location_no_the = location:match("^the (.*)$") local bare_location = location_no_the or location local location_link local bare_location_parts = split(bare_location, ", ") for i, part in ipairs(bare_location_parts) do bare_location_parts[i] = ("[[%s]]"):format(part) end location_link = concat(bare_location_parts, ", ") if location_no_the then location_link = "the " .. location_link end return location_link end local function linkbox(lang, setwiki, setwikt, setsister, entryname) local wiktionarylinks = {} local canonicalName = lang:getCanonicalName() local wikimediaLanguages = lang:getWikimediaLanguages() local wikipediaArticle = setwiki or lang:getWikipediaArticle() setsister = setsister and ucfirst(setsister) or nil if setwikt then track("setwikt") if setwikt == "-" then track("setwikt/hyphen") end end if setwikt ~= "-" and wikimediaLanguages and wikimediaLanguages[1] then for _, wikimedialang in ipairs(wikimediaLanguages) do local check = new_title(wikimedialang:getCode() .. ":") if check and check.isExternal then insert(wiktionarylinks, (wikimedialang:getCanonicalName() ~= canonicalName and "(''" .. wikimedialang:getCanonicalName() .. "'') " or "") .. "'''[[:" .. wikimedialang:getCode() .. ":|" .. wikimedialang:getCode() .. ".wiktionary.org]]'''") end end wiktionarylinks = concat(wiktionarylinks, "<br/>") end local wikt_plural = wikimediaLanguages[2] and "s" or "" if #wiktionarylinks == 0 then wiktionarylinks = "''None.''" end if setsister then track("setsister") if setsister == "-" then track("setsister/hyphen") else setsister = "Category:" .. setsister end else setsister = lang:getCommonsCategory() or "-" end return concat{ [=[<div class="wikitable" style="float: right; clear: right; margin: 0 0 0.5em 1em; width: 300px; padding: 5px;"> <div style="text-align: center; margin-bottom: 10px; margin-top: 5px">''']=], canonicalName, [=[ language links'''</div> {| style="font-size: 90%" |- | style="vertical-align: top; height: 35px; border-bottom: 1px solid lightgray;" | [[File:Wikipedia-logo.png|35px|none|Wikipedia]] | style="border-bottom: 1px solid lightgray;" | '''English Wikipedia''' has an article on: <div style="padding: 5px 10px">]=], (setwiki == "-" and "''None.''" or "'''[[w:" .. wikipediaArticle .. "|" .. wikipediaArticle .. "]]'''"), [=[</div> |- | style="vertical-align: top; height: 35px; border-bottom: 1px solid lightgray;" | [[File:Wikimedia-logo.svg|35px|none|Wikimedia Commons]] | style="border-bottom: 1px solid lightgray;" | '''Wikimedia Commons''' has links to ]=], canonicalName, [=[-related content in sister projects: <div style="padding: 5px 10px">]=], (setsister == "-" and "''None.''" or "'''[[commons:" .. setsister .. "|" .. setsister .. "]]'''"), [=[</div> |- | style="vertical-align: top; height: 35px; width: 40px; border-bottom: 1px solid lightgray;" | [[File:Wiktionary-logo-v2.svg|35px|none|Wiktionary]] |style="border-bottom: 1px solid lightgray;" | '''Wiktionary edition''']=], wikt_plural, [=[ written in ]=], canonicalName, [=[: <div style="padding: 5px 10px">]=], wiktionarylinks, [=[</div> |- | style="vertical-align: top; height: 35px; border-bottom: 1px solid lightgray;" | [[File:Open book nae 02.svg|35px|none|Entry]] | style="border-bottom: 1px solid lightgray;" | '''Wiktionary entry''' for the language's English name: <div style="padding: 5px 10px">''']=], require("Module:links").full_link({lang = m_languages.getByCode("en"), term = entryname or canonicalName}), [=['''</div> |- | style="vertical-align: top; height: 35px;" | [[File:Crystal kfind.png|35px|none|Considerations]] || '''Wiktionary resources''' for editors contributing to ]=], canonicalName, [=[ entries: <div style="padding: 5px 0"> * '''[[Wiktionary:]=], canonicalName, [=[ entry guidelines]]''' * '''[[:Category:]=], canonicalName, [=[ reference templates|Reference templates]] ({{PAGESINCAT:]=], canonicalName, [=[ reference templates}})''' * '''[[Appendix:]=], canonicalName, [=[ bibliography|Bibliography]]''' |} </div>]=] } end local function edit_link(title, text) return '<span class="plainlinks">[' .. tostring(mw.uri.fullUrl(title, { action = "edit" })) .. ' ' .. text .. ']</span>' end -- Should perhaps use wiki syntax. local function infobox(lang) local ret = {} insert(ret, '<table class="wikitable language-category-info"') local raw_data = lang:getData("extra") if raw_data then local replacements = { [1] = "canonical-name", [2] = "wikidata-item", [3] = "family", [4] = "scripts", } local function replacer(letter1, letter2) return letter1:lower() .. "-" .. letter2:lower() end -- For each key in the language data modules, returns a descriptive -- kebab-case version (containing ASCII lowercase words separated -- by hyphens). local function kebab_case(key) key = replacements[key] or key key = key:gsub("(%l)(%u)", replacer):gsub("(%l)_(%l)", replacer) return key end local compress = {compress = true} local function html_attribute_encode(str) str = to_json(str, compress) :gsub('"', "&quot;") -- & in attributes is automatically escaped. -- :gsub("&", "&amp;") :gsub("<", "&lt;") :gsub(">", "&gt;") return str end insert(ret, ' data-code="' .. lang:getCode() .. '"') for k, v in sorted_pairs(raw_data) do insert(ret, " data-" .. kebab_case(k) .. '="' .. html_attribute_encode(v) .. '"') end end insert(ret, '>\n') insert(ret, '<tr class="language-category-data">\n<th colspan="2">' .. edit_link(lang:getDataModuleName(), "Edit language data") .. "</th>\n</tr>\n") insert(ret, "<tr>\n<th>Canonical name</th><td>" .. lang:getCanonicalName() .. "</td>\n</tr>\n") local otherNames = lang:getOtherNames() if otherNames then local names = {} for _, name in ipairs(otherNames) do insert(names, "<li>" .. name .. "</li>") end if #names > 0 then insert(ret, "<tr>\n<th>Other names</th><td><ul>" .. concat(names, "\n") .. "</ul></td>\n</tr>\n") end end local aliases = lang:getAliases() if aliases then local names = {} for _, name in ipairs(aliases) do insert(names, "<li>" .. name .. "</li>") end if #names > 0 then insert(ret, "<tr>\n<th>Aliases</th><td><ul>" .. concat(names, "\n") .. "</ul></td>\n</tr>\n") end end local varieties = lang:getVarieties() if varieties then local names = {} for _, name in ipairs(varieties) do if type(name) == "string" then insert(names, "<li>" .. name .. "</li>") else assert(type(name) == "table") local first_var local subvars = {} for i, var in ipairs(name) do if i == 1 then first_var = var else insert(subvars, "<li>" .. var .. "</li>") end end if #subvars > 0 then insert(names, "<li><dl><dt>" .. first_var .. "</dt>\n<dd><ul>" .. concat(subvars, "\n") .. "</ul></dd></dl></li>") elseif first_var then insert(names, "<li>" .. first_var .. "</li>") end end end if #names > 0 then insert(ret, "<tr>\n<th>Varieties</th><td><ul>" .. concat(names, "\n") .. "</ul></td>\n</tr>\n") end end insert(ret, "<tr>\n<th>[[Wiktionary:Languages|Language code]]</th><td><code>" .. lang:getCode() .. "</code></td>\n</tr>\n") insert(ret, "<tr>\n<th>[[Wiktionary:Families|Language family]]</th>\n") local fam = lang:getFamily() local famCode = fam and fam:getCode() if not fam then insert(ret, "<td>unclassified</td>") elseif famCode == "qfa-iso" then insert(ret, "<td>[[:Category:Language isolates|language isolate]]</td>") elseif famCode == "qfa-mix" then insert(ret, "<td>[[:Category:Mixed languages|mixed language]]</td>") elseif famCode == "sgn" then insert(ret, "<td>[[:Category:Sign languages|sign language]]</td>") elseif famCode == "crp" then insert(ret, "<td>[[:Category:Creole or pidgin languages|creole or pidgin]]</td>") elseif famCode == "art" then insert(ret, "<td>[[:Category:Constructed languages|constructed language]]</td>") else insert(ret, "<td>" .. fam:makeCategoryLink() .. "</td>") end insert(ret, "\n</tr>\n<tr>\n<th>Ancestors</th>\n<td>") local ancestors = lang:getAncestors() if ancestors[2] then local ancestorList = {} for i, anc in ipairs(ancestors) do ancestorList[i] = "<li>" .. anc:makeCategoryLink() .. "</li>" end insert(ret, "<ul>\n" .. concat(ancestorList, "\n") .. "</ul>") else local ancestorChain = lang:getAncestorChainOld() if ancestorChain[1] then local chain = {} for _, anc in reverse_ipairs(ancestorChain) do insert(chain, "<li>" .. anc:makeCategoryLink() .. "</li>") end insert(ret, "<ul>\n" .. concat(chain, "\n<ul>\n") .. ("</ul>"):rep(#chain)) else insert(ret, "unknown") end end insert(ret, "</td>\n</tr>\n") local scripts = lang:getScripts() if scripts[1] then local script_text = {} local function makeScriptLine(sc) local code = sc:getCode() local url = tostring(mw.uri.fullUrl('Special:Search', { search = 'contentmodel:css insource:"' .. code .. '" insource:/\\.' .. code .. '/', ns8 = '1' })) return sc:makeCategoryLink() .. ' (<span class="plainlinks" title="Search for stylesheets referencing this script">[' .. url .. ' <code>' .. code .. '</code>]</span>)' end local function add_Hrkt(text) insert(text, "<li>" .. makeScriptLine(Hrkt)) insert(text, "<ul>") insert(text, "<li>" .. makeScriptLine(Hira) .. "</li>") insert(text, "<li>" .. makeScriptLine(Kana) .. "</li>") insert(text, "</ul>") insert(text, "</li>") end for _, sc in ipairs(scripts) do local text = {} local code = sc:getCode() if code == "Hrkt" then add_Hrkt(text) else insert(text, "<li>" .. makeScriptLine(sc)) if code == "Jpan" then insert(text, "<ul>") insert(text, "<li>" .. makeScriptLine(Hani) .. "</li>") add_Hrkt(text) insert(text, "</ul>") elseif code == "Kore" then insert(text, "<ul>") insert(text, "<li>" .. makeScriptLine(Hang) .. "</li>") insert(text, "<li>" .. makeScriptLine(Hani) .. "</li>") insert(text, "</ul>") end insert(text, "</li>") end insert(script_text, concat(text, "\n")) end insert(ret, "<tr>\n<th>[[Wiktionary:Scripts|Scripts]]</th>\n<td><ul>\n" .. concat(script_text, "\n") .. "</ul></td>\n</tr>\n") else insert(ret, "<tr>\n<th>[[Wiktionary:Scripts|Scripts]]</th>\n<td>not specified</td>\n</tr>\n") end local function add_module_info(raw_data, heading) if raw_data then local scripts = lang:getScriptCodes() local module_info, add = {}, false if type(raw_data) == "string" then insert(module_info, ("[[Module:%s]]"):format(raw_data)) add = true else local raw_data_type = type(raw_data) if raw_data_type == "table" and size(scripts) == 1 and type(raw_data[scripts[1]]) == "string" then insert(module_info, ("[[Module:%s]]"):format(raw_data[scripts[1]])) add = true elseif raw_data_type == "table" then insert(module_info, "<ul>") for script, data in sorted_pairs(raw_data) do if type(data) == "string" and m_sc_getByCode(script) then insert(module_info, ("<li><code>%s</code>: [[Module:%s]]</li>"):format(script, data)) end end insert(module_info, "</ul>") add = size(module_info) > 2 end end if add then insert(ret, [=[ <tr> <th>]=] .. heading .. [=[</th> <td>]=] .. concat(module_info) .. [=[</td> </tr> ]=]) end end end add_module_info(raw_data.generate_forms, "Form-generating<br>module") add_module_info(raw_data.translit, "[[Wiktionary:Transliteration and romanization|Transliteration<br>module]]") add_module_info(raw_data.display_text, "Display text<br>module") add_module_info(raw_data.entry_name, "Entry name<br>module") add_module_info(raw_data.sort_key, "[[sortkey|Sortkey]]<br>module") local wikidataItem = lang:getWikidataItem() if lang:getWikidataItem() and mw.wikibase then local URL = mw.wikibase.getEntityUrl(wikidataItem) local link if URL then link = '[' .. URL .. ' ' .. wikidataItem .. ']' else link = '<span class="error">Invalid Wikidata item: <code>' .. wikidataItem .. '</code></span>' end insert(ret, "<tr><th>Wikidata</th><td>" .. link .. "</td></tr>") end insert(ret, "</table>") return concat(ret) end local function NavFrame(content, title) return '<div class="NavFrame"><div class="NavHead">' .. (title or '{{{title}}}') .. '</div>' .. '<div class="NavContent" style="text-align: left;">' .. content .. '</div></div>' end local function get_description_topright_additional(lang, locations, extinct, setwiki, setwikt, setsister, entryname) local nameWithLanguage = lang:getCategoryName("nocap") if lang:getCode() == "und" then local description = "This is the main category of the '''" .. nameWithLanguage .. "''', represented in Wiktionary by the [[Wiktionary:Languages|code]] '''" .. lang:getCode() .. "'''. " .. "This language contains terms in historical writing, whose meaning has not yet been determined by scholars." return description, nil, nil end local canonicalName = lang:getCanonicalName() local topright = linkbox(lang, setwiki, setwikt, setsister, entryname) local the_prefix if canonicalName:find(" Language$") then the_prefix = "" else the_prefix = "the " end local description = "This is the main category of " .. the_prefix .. "'''" .. nameWithLanguage .. "'''." local location_links = {} local prep local saw_embedded_comma = false for _, location in ipairs(locations) do local this_prep if location == "the world" then this_prep = "across" insert(location_links, location) elseif location ~= "UNKNOWN" then this_prep = "in" if location:find(",") then saw_embedded_comma = true end insert(location_links, link_location(location)) end if this_prep then if prep and this_prep ~= prep then error("Can't handle location 'the world' along with another location (clashing prepositions)") end prep = this_prep end end local location_desc if #location_links > 0 then local location_link_text if saw_embedded_comma and #location_links >= 3 then location_link_text = mw.text.listToText(location_links, "; ", "; and ") else location_link_text = serial_comma_join(location_links) end location_desc = ("It is %s %s %s.\n\n"):format( extinct and "an [[extinct language]] that was formerly spoken" or "spoken", prep, location_link_text) elseif extinct then location_desc = "It is an [[extinct language]].\n\n" else location_desc = "" end local add = location_desc .. "Information about " .. canonicalName .. ":\n\n" .. infobox(lang) if lang:hasType("reconstructed") then add = add .. "\n\n" .. ucfirst(canonicalName) .. " is a reconstructed language. Its words and roots are not directly attested in any written works, but have been reconstructed through the ''comparative method'', " .. "which finds regular similarities between languages that cannot be explained by coincidence or word-borrowing, and extrapolates ancient forms from these similarities.\n\n" .. "According to our [[Wiktionary:Criteria for inclusion|criteria for inclusion]], terms in " .. canonicalName .. " should '''not''' be present in entries in the main namespace, but may be added to the Reconstruction: namespace." elseif lang:hasType("appendix-constructed") then add = add .. "\n\n" .. ucfirst(canonicalName) .. " is a constructed language that is only in sporadic use. " .. "According to our [[Wiktionary:Criteria for inclusion|criteria for inclusion]], terms in " .. canonicalName .. " should '''not''' be present in entries in the main namespace, but may be added to the Appendix: namespace. " .. "All terms in this language may be available at [[Appendix:" .. ucfirst(canonicalName) .. "]]." end local about = new_title("Wiktionary:About " .. canonicalName) if about.exists then add = add .. "\n\n" .. "Please see '''[[Wiktionary:About " .. canonicalName .. "]]''' for information and special considerations for creating " .. nameWithLanguage .. " entries." end local ok, tree_of_descendants = pcall( require("Module:family tree").print_children, lang:getCode(), { protolanguage_under_family = true, must_have_descendants = true }) if ok then if tree_of_descendants then add = add .. NavFrame( tree_of_descendants, "Family tree") else add = add .. "\n\n" .. ucfirst(lang:getCanonicalName()) .. " has no descendants or varieties listed in Wiktionary's language data modules." end else mw.log("error while generating tree: " .. tostring(tree_of_descendants)) end return description, topright, add end local function get_parents(lang, locations, extinct) local canonicalName = lang:getCanonicalName() local sortkey = {sort_base = canonicalName, lang = "mi"} local ret = {{name = "Reo", sort = sortkey}} local fam = lang:getFamily() local famCode = fam and fam:getCode() -- FIXME: Some of the following categories should be added to this module. if not fam then insert(ret, {name = "Category:Unclassified languages", sort = sortkey}) elseif famCode == "qfa-iso" then insert(ret, {name = "Category:Language isolates", sort = sortkey}) elseif famCode == "qfa-mix" then insert(ret, {name = "Category:Mixed languages", sort = sortkey}) elseif famCode == "sgn" then insert(ret, {name = "Category:All sign languages", sort = sortkey}) elseif famCode == "crp" then insert(ret, {name = "Category:Creole or pidgin languages", sort = sortkey}) for _, anc in ipairs(lang:getAncestors()) do -- Avoid Haitian Creole being categorised in [[:Category:Haitian Creole-based creole or pidgin languages]], as one of its ancestors is an etymology-only variety of it. -- Use that ancestor's ancestors instead. if anc:getFullCode() == lang:getCode() then for _, anc_extra in ipairs(anc:getAncestors()) do insert(ret, {name = "Category:" .. ucfirst(anc_extra:getFullName()) .. "-based creole or pidgin languages", sort = sortkey}) end else insert(ret, {name = "Category:" .. ucfirst(anc:getFullName()) .. "-based creole or pidgin languages", sort = sortkey}) end end elseif famCode == "art" then if lang:hasType("appendix-constructed") then insert(ret, {name = "Category:Appendix-only constructed languages", sort = sortkey}) else insert(ret, {name = "Category:Constructed languages", sort = sortkey}) end for _, anc in ipairs(lang:getAncestors()) do if anc:getFullCode() == lang:getCode() then for _, anc_extra in ipairs(anc:getAncestors()) do insert(ret, {name = "Category:" .. ucfirst(anc_extra:getFullName()) .. "-based constructed languages", sort = sortkey}) end else insert(ret, {name = "Category:" .. ucfirst(anc:getFullName()) .. "-based constructed languages", sort = sortkey}) end end else insert(ret, {name = "Category:" .. fam:getCategoryName(), sort = sortkey}) if lang:hasType("reconstructed") then insert(ret, { name = "Category:Reconstructed languages", sort = {sort_base = canonicalName:gsub("^Proto%-", ""), lang = "en"} }) end end local function add_sc_cat(sc) insert(ret, {name = "Category:Reo " .. sc:getCategoryName(), sort = sortkey}) end local function add_Hrkt() add_sc_cat(Hrkt) add_sc_cat(Hira) add_sc_cat(Kana) end for _, sc in ipairs(lang:getScripts()) do if sc:getCode() == "Hrkt" then add_Hrkt() else add_sc_cat(sc) if sc:getCode() == "Jpan" then add_sc_cat(Hani) add_Hrkt() elseif sc:getCode() == "Kore" then add_sc_cat(Hang) add_sc_cat(Hani) end end end if lang:hasTranslit() then insert(ret, {name = "Category:Languages with automatic transliteration", sort = sortkey}) end local function insert_location_language_cat(location) local cat = "Languages of " .. location insert(ret, {name = "Category:" .. cat, sort = sortkey}) local auto_cat_args = scrape_category_for_auto_cat_args(cat) local location_parent = auto_cat_args and auto_cat_args.parent if location_parent then local split_parents = require(parse_utilities_module).split_on_comma(location_parent) for _, parent in ipairs(split_parents) do parent = parent:match("^(.-):.*$") or parent insert_location_language_cat(parent) end end end local saw_location = false for _, location in ipairs(locations) do if location ~= "UNKNOWN" then saw_location = true insert_location_language_cat(location) end end if extinct then insert(ret, {name = "Category:All extinct languages", sort = sortkey}) end if not saw_location and not (lang:hasType("reconstructed") or (fam and fam:getCode() == "art")) then -- Constructed and reconstructed languages don't need a location specified and often won't have one, -- so don't put them in this maintenance category. insert(ret, {name = "Category:Languages not sorted into a location category", sort = sortkey}) end return ret end local function get_children() local ret = {} -- FIXME: We should work on the children mechanism so it isn't necessary to manually specify these. --for _, label in ipairs({"appendices", "entry maintenance", "lemmas", "names", "phrases", "rhymes", "symbols", "templates", "terms by etymology", "terms by usage"}) do -- insert(ret, {name = label, is_label = true}) --end --insert(ret, {name = "terms derived from {{{langname}}}", is_label = true, lang = false}) --insert(ret, {name = "{{{langcode}}}:All topics", sort = "all topics"}) --insert(ret, {name = "Varieties of {{{langname}}}"}) --insert(ret, {name = "Requests concerning {{{langname}}}"}) --insert(ret, {name = "Rhymes:{{{langname}}}", description = "Lists of {{{langname}}} words by their rhymes."}) --insert(ret, {name = "User {{{langcode}}}", description = "Wiktionary users categorized by fluency levels in {{{langdisp}}}."}) return ret end -- Handle language categories of the form e.g. [[:Category:French language]] and -- [[:Category:British Sign Language]]. insert(raw_handlers, function(data) local category = data.category if not (category:match("[Rr]eo") or category:match("[Ll]ect$")) then return nil end local lang = m_languages.getByCanonicalName(category) if not lang then local langname = category:match("Reo (.*)") if langname then lang = m_languages.getByCanonicalName(langname) end if not lang then return nil end end local args = require("Module:parameters").process(data.args, { [1] = {list = true}, ["setwiki"] = true, ["setwikt"] = true, ["setsister"] = true, ["entryname"] = true, ["extinct"] = {type = "boolean"}, }) -- If called from inside, don't require any arguments, as they can't be known -- in general and aren't needed just to generate the first parent (used for -- breadcrumbs). if #args[1] == 0 and not data.called_from_inside then -- At least one location must be specified unless the language is constructed (e.g. Esperanto) or reconstructed (e.g. Proto-Indo-European). local fam = lang:getFamily() if not (lang:hasType("reconstructed") or (fam and fam:getCode() == "art")) then error("At least one location (param 1=) must be specified for language '" .. lang:getCanonicalName() .. "' (code '" .. lang:getCode() .. "'). " .. "Use the value UNKNOWN if the language's location is truly unknown.") end end local description, topright, additional = "", "", "" -- If called from inside the category tree system, it's called when generating -- parents or children, and we don't need to generate the description or additional -- text (which is very expensive in terms of memory because it calls [[Module:family tree]], -- which calls [[Module:languages/data/all]]). if not data.called_from_inside then description, topright, additional = get_description_topright_additional( lang, args[1], args.extinct, args.setwiki, args.setwikt, args.setsister, args.entryname ) end return { canonical_name = lang:getCategoryName(), description = description, lang = lang:getCode(), topright = topright, additional = additional, breadcrumb = lang:getCanonicalName(), parents = get_parents(lang, args[1], args.extinct), extra_children = get_children(lang), umbrella = false, can_be_empty = true, }, true end) -- Handle categories such as [[:Category:Languages of Indonesia]]. insert(raw_handlers, function(data) local location = data.category:match("^Languages of (.*)$") if location then local args = require("Module:parameters").process(data.args, { ["flagfile"] = true, ["commonscat"] = true, ["wp"] = true, ["basename"] = true, ["parent"] = true, ["locationcat"] = true, ["locationlink"] = true, }) local topright local basename = args.basename or location:gsub(", .*", "") if args.flagfile ~= "-" then local flagfile_arg = args.flagfile or ("Flag of %s.svg"):format(basename) local files = require(parse_utilities_module).split_on_comma(flagfile_arg) local topright_parts = {} for _, file in ipairs(files) do local flagfile = "File:" .. file local flagfile_page = new_title(flagfile) if flagfile_page and flagfile_page.file.exists then insert(topright_parts, ("[[%s|right|100px|border]]"):format(flagfile)) elseif args.flagfile then error(("Explicit flagfile '%s' doesn't exist"):format(flagfile)) end end topright = concat(topright_parts) end if args.wp then local wp = require("Module:yesno")(args.wp, "+") if wp == "+" or wp == true then wp = data.category end if wp then local wp_topright = ("{{wikipedia|%s}}"):format(wp) if topright then topright = topright .. wp_topright else topright = wp_topright end end end if args.commonscat then local commonscat = require("Module:yesno")(args.commonscat, "+") if commonscat == "+" or commonscat == true then commonscat = data.category end if commonscat then local commons_topright = ("{{commonscat|%s}}"):format(commonscat) if topright then topright = topright .. commons_topright else topright = commons_topright end end end local bare_location = location:match("^the (.*)$") or location local location_link = args.locationlink or link_location(location) local bare_basename = basename:match("^the (.*)$") or basename local parents = {} if args.parent then local explicit_parents = require(parse_utilities_module).split_on_comma(args.parent) for i, parent in ipairs(explicit_parents) do local actual_parent, sort_key = parent:match("^(.-):(.*)$") if actual_parent then parent = actual_parent sort_key = sort_key:gsub("%+", bare_location) else sort_key = " " .. bare_location end insert(parents, {name = "Languages of " .. parent, sort = sort_key}) end else insert(parents, {name = "Languages by country", sort = {sort_base = bare_location, lang = "en"}}) end if args.locationcat then local explicit_location_cats = require(parse_utilities_module).split_on_comma(args.locationcat) for i, locationcat in ipairs(explicit_location_cats) do insert(parents, {name = "Category:" .. locationcat, sort = " Languages"}) end else local location_cat = ("Category:%s"):format(bare_location) local location_page = new_title(location_cat) if location_page and location_page.exists then insert(parents, {name = location_cat, sort = "Languages"}) end end local description = ("Categories for languages of %s (including sublects)."):format(location_link) return { topright = topright, description = description, parents = parents, breadcrumb = bare_basename, additional = "{{{umbrella_msg}}}", }, true end end) -- Handle categories such as [[:Category:English-based creole or pidgin languages]]. insert(raw_handlers, function(data) local langname = data.category:match("(.*)%-based creole or pidgin languages$") if langname then local lang = m_languages.getByCanonicalName(langname) if lang then return { lang = lang:getCode(), description = "Languages which developed as a [[creole]] or [[pidgin]] from " .. lang:makeCategoryLink() .. ".", parents = {{name = "Creole or pidgin languages", sort = {sort_base = "*" .. langname, lang = "en"}}}, breadcrumb = lang:getCanonicalName() .. "-based", } end end end) -- Handle categories such as [[:Category:English-based constructed languages]]. insert(raw_handlers, function(data) local langname = data.category:match("(.*)%-based constructed languages$") if langname then local lang = m_languages.getByCanonicalName(langname) if lang then return { lang = lang:getCode(), description = "Constructed languages which are based on " .. lang:makeCategoryLink() .. ".", parents = {{name = "Constructed languages", sort = {sort_base = "*" .. langname, lang = "en"}}}, breadcrumb = lang:getCanonicalName() .. "-based", } end end end) return {RAW_CATEGORIES = raw_categories, RAW_HANDLERS = raw_handlers} nofxb9nojorf7mbqt89c9jj568kfqtb 17455 17454 2026-07-13T08:54:42Z Hiyuune 6766 17455 Scribunto text/plain local new_title = mw.title.new local ucfirst = require("Module:string utilities").ucfirst local split = require("Module:string utilities").split local raw_categories = {} local raw_handlers = {} local m_languages = require("Module:languages") local m_sc_getByCode = require("Module:scripts").getByCode local m_table = require("Module:table") local parse_utilities_module = "Module:parse utilities" local concat = table.concat local insert = table.insert local reverse_ipairs = m_table.reverseIpairs local serial_comma_join = m_table.serialCommaJoin local size = m_table.size local sorted_pairs = m_table.sortedPairs local to_json = require("Module:JSON").toJSON local Hang = m_sc_getByCode("Hang") local Hani = m_sc_getByCode("Hani") local Hira = m_sc_getByCode("Hira") local Hrkt = m_sc_getByCode("Hrkt") local Kana = m_sc_getByCode("Kana") local function track(page) -- [[Special:WhatLinksHere/Wiktionary:Tracking/category tree/languages/PAGE]] return require("Module:debug/track")("category tree/languages/" .. page) end -- This handles language categories of the form e.g. [[:Category:French language]] and -- [[:Category:British Sign Language]]; categories like [[:Category:Languages of Indonesia]]; categories like -- [[:Category:English-based creole or pidgin languages]]; and categories like -- [[:Category:English-based constructed languages]]. ----------------------------------------------------------------------------- -- -- -- RAW CATEGORIES -- -- -- ----------------------------------------------------------------------------- raw_categories["Reo"] = { topright = "{{commonscat|Languages}}\n[[File:Languages world map-transparent background.svg|thumb|right|250px|Rough world map of language families]]", description = "This category contains the categories for every language on Wiktionary.", additional = "Not all languages that Wiktionary recognises may have a category here yet. There are many that have " .. "not yet received any attention from editors, mainly because not all Wiktionary users know about every single " .. "language. See [[Wiktionary:List of languages]] for a full list.", parents = { "Whakaraparapa", }, } raw_categories["All extinct languages"] = { description = "This category contains the categories for every [[extinct language]] on Wiktionary.", additional = "Do not confuse this category with [[:Category:Extinct languages]], which is an umbrella category for the names of extinct languages in specific other languages (e.g. {{m+|de|Langobardisch}} for the ancient [[Lombardic]] language).", parents = { "Reo", }, } raw_categories["Languages by country"] = { topright = "{{commonscat|Languages by continent}}", description = "Categories that group languages by country.", additional = "{{{umbrella_meta_msg}}}", parents = { "Reo", }, } raw_categories["Language isolates"] = { topright = "{{wikipedia|Language isolate}}\n{{commonscat|Language isolates}}", description = "Languages with no known relatives.", parents = { {name = "Languages by family", sort = "*Isolates"}, {name = "All language families", sort = "Isolates"}, }, } raw_categories["Languages not sorted into a location category"] = { description = "Languages which do not specify (in their {{tl|auto cat}} call) the location(s) where they are spoken.", additional = "This excludes constructed and reconstructed languages; as a result, all languages in this category explicitly specify their location as {{cd|UNKNOWN}}.", parents = { {name = "Requests"}, }, hidden = true, } ----------------------------------------------------------------------------- -- -- -- RAW HANDLERS -- -- -- ----------------------------------------------------------------------------- -- Given a category (without the "Category:" prefix), look up the page defining the category, find the call to -- {{auto cat}} (if any), and return a table of its arguments. If the category page doesn't exist or doesn't have -- an {{auto cat}} invocation, return nil. -- -- FIXME: Duplicated in [[Module:category tree/lects]]. local function scrape_category_for_auto_cat_args(cat) local cat_page = mw.title.new("Category:" .. cat) if cat_page then local contents = cat_page:getContent() if contents then local frame = mw.getCurrentFrame() for template in require("Module:template parser").find_templates(contents) do -- The template parser automatically handles redirects and canonicalizes them, so uses of {{autocat}} -- will also be found. if template:get_name() == "auto cat" then return template:get_arguments() end end end end return nil end local function link_location(location) local location_no_the = location:match("^the (.*)$") local bare_location = location_no_the or location local location_link local bare_location_parts = split(bare_location, ", ") for i, part in ipairs(bare_location_parts) do bare_location_parts[i] = ("[[%s]]"):format(part) end location_link = concat(bare_location_parts, ", ") if location_no_the then location_link = "the " .. location_link end return location_link end local function linkbox(lang, setwiki, setwikt, setsister, entryname) local wiktionarylinks = {} local canonicalName = lang:getCanonicalName() local wikimediaLanguages = lang:getWikimediaLanguages() local wikipediaArticle = setwiki or lang:getWikipediaArticle() setsister = setsister and ucfirst(setsister) or nil if setwikt then track("setwikt") if setwikt == "-" then track("setwikt/hyphen") end end if setwikt ~= "-" and wikimediaLanguages and wikimediaLanguages[1] then for _, wikimedialang in ipairs(wikimediaLanguages) do local check = new_title(wikimedialang:getCode() .. ":") if check and check.isExternal then insert(wiktionarylinks, (wikimedialang:getCanonicalName() ~= canonicalName and "(''" .. wikimedialang:getCanonicalName() .. "'') " or "") .. "'''[[:" .. wikimedialang:getCode() .. ":|" .. wikimedialang:getCode() .. ".wiktionary.org]]'''") end end wiktionarylinks = concat(wiktionarylinks, "<br/>") end local wikt_plural = wikimediaLanguages[2] and "s" or "" if #wiktionarylinks == 0 then wiktionarylinks = "''None.''" end if setsister then track("setsister") if setsister == "-" then track("setsister/hyphen") else setsister = "Category:" .. setsister end else setsister = lang:getCommonsCategory() or "-" end return concat{ [=[<div class="wikitable" style="float: right; clear: right; margin: 0 0 0.5em 1em; width: 300px; padding: 5px;"> <div style="text-align: center; margin-bottom: 10px; margin-top: 5px">''']=], canonicalName, [=[ language links'''</div> {| style="font-size: 90%" |- | style="vertical-align: top; height: 35px; border-bottom: 1px solid lightgray;" | [[File:Wikipedia-logo.png|35px|none|Wikipedia]] | style="border-bottom: 1px solid lightgray;" | '''English Wikipedia''' has an article on: <div style="padding: 5px 10px">]=], (setwiki == "-" and "''None.''" or "'''[[w:" .. wikipediaArticle .. "|" .. wikipediaArticle .. "]]'''"), [=[</div> |- | style="vertical-align: top; height: 35px; border-bottom: 1px solid lightgray;" | [[File:Wikimedia-logo.svg|35px|none|Wikimedia Commons]] | style="border-bottom: 1px solid lightgray;" | '''Wikimedia Commons''' has links to ]=], canonicalName, [=[-related content in sister projects: <div style="padding: 5px 10px">]=], (setsister == "-" and "''None.''" or "'''[[commons:" .. setsister .. "|" .. setsister .. "]]'''"), [=[</div> |- | style="vertical-align: top; height: 35px; width: 40px; border-bottom: 1px solid lightgray;" | [[File:Wiktionary-logo-v2.svg|35px|none|Wiktionary]] |style="border-bottom: 1px solid lightgray;" | '''Wiktionary edition''']=], wikt_plural, [=[ written in ]=], canonicalName, [=[: <div style="padding: 5px 10px">]=], wiktionarylinks, [=[</div> |- | style="vertical-align: top; height: 35px; border-bottom: 1px solid lightgray;" | [[File:Open book nae 02.svg|35px|none|Entry]] | style="border-bottom: 1px solid lightgray;" | '''Wiktionary entry''' for the language's English name: <div style="padding: 5px 10px">''']=], require("Module:links").full_link({lang = m_languages.getByCode("en"), term = entryname or canonicalName}), [=['''</div> |- | style="vertical-align: top; height: 35px;" | [[File:Crystal kfind.png|35px|none|Considerations]] || '''Wiktionary resources''' for editors contributing to ]=], canonicalName, [=[ entries: <div style="padding: 5px 0"> * '''[[Wiktionary:]=], canonicalName, [=[ entry guidelines]]''' * '''[[:Category:]=], canonicalName, [=[ reference templates|Reference templates]] ({{PAGESINCAT:]=], canonicalName, [=[ reference templates}})''' * '''[[Appendix:]=], canonicalName, [=[ bibliography|Bibliography]]''' |} </div>]=] } end local function edit_link(title, text) return '<span class="plainlinks">[' .. tostring(mw.uri.fullUrl(title, { action = "edit" })) .. ' ' .. text .. ']</span>' end -- Should perhaps use wiki syntax. local function infobox(lang) local ret = {} insert(ret, '<table class="wikitable language-category-info"') local raw_data = lang:getData("extra") if raw_data then local replacements = { [1] = "canonical-name", [2] = "wikidata-item", [3] = "family", [4] = "scripts", } local function replacer(letter1, letter2) return letter1:lower() .. "-" .. letter2:lower() end -- For each key in the language data modules, returns a descriptive -- kebab-case version (containing ASCII lowercase words separated -- by hyphens). local function kebab_case(key) key = replacements[key] or key key = key:gsub("(%l)(%u)", replacer):gsub("(%l)_(%l)", replacer) return key end local compress = {compress = true} local function html_attribute_encode(str) str = to_json(str, compress) :gsub('"', "&quot;") -- & in attributes is automatically escaped. -- :gsub("&", "&amp;") :gsub("<", "&lt;") :gsub(">", "&gt;") return str end insert(ret, ' data-code="' .. lang:getCode() .. '"') for k, v in sorted_pairs(raw_data) do insert(ret, " data-" .. kebab_case(k) .. '="' .. html_attribute_encode(v) .. '"') end end insert(ret, '>\n') insert(ret, '<tr class="language-category-data">\n<th colspan="2">' .. edit_link(lang:getDataModuleName(), "Edit language data") .. "</th>\n</tr>\n") insert(ret, "<tr>\n<th>Canonical name</th><td>" .. lang:getCanonicalName() .. "</td>\n</tr>\n") local otherNames = lang:getOtherNames() if otherNames then local names = {} for _, name in ipairs(otherNames) do insert(names, "<li>" .. name .. "</li>") end if #names > 0 then insert(ret, "<tr>\n<th>Other names</th><td><ul>" .. concat(names, "\n") .. "</ul></td>\n</tr>\n") end end local aliases = lang:getAliases() if aliases then local names = {} for _, name in ipairs(aliases) do insert(names, "<li>" .. name .. "</li>") end if #names > 0 then insert(ret, "<tr>\n<th>Aliases</th><td><ul>" .. concat(names, "\n") .. "</ul></td>\n</tr>\n") end end local varieties = lang:getVarieties() if varieties then local names = {} for _, name in ipairs(varieties) do if type(name) == "string" then insert(names, "<li>" .. name .. "</li>") else assert(type(name) == "table") local first_var local subvars = {} for i, var in ipairs(name) do if i == 1 then first_var = var else insert(subvars, "<li>" .. var .. "</li>") end end if #subvars > 0 then insert(names, "<li><dl><dt>" .. first_var .. "</dt>\n<dd><ul>" .. concat(subvars, "\n") .. "</ul></dd></dl></li>") elseif first_var then insert(names, "<li>" .. first_var .. "</li>") end end end if #names > 0 then insert(ret, "<tr>\n<th>Varieties</th><td><ul>" .. concat(names, "\n") .. "</ul></td>\n</tr>\n") end end insert(ret, "<tr>\n<th>[[Wiktionary:Languages|Language code]]</th><td><code>" .. lang:getCode() .. "</code></td>\n</tr>\n") insert(ret, "<tr>\n<th>[[Wiktionary:Families|Language family]]</th>\n") local fam = lang:getFamily() local famCode = fam and fam:getCode() if not fam then insert(ret, "<td>unclassified</td>") elseif famCode == "qfa-iso" then insert(ret, "<td>[[:Category:Language isolates|language isolate]]</td>") elseif famCode == "qfa-mix" then insert(ret, "<td>[[:Category:Mixed languages|mixed language]]</td>") elseif famCode == "sgn" then insert(ret, "<td>[[:Category:Sign languages|sign language]]</td>") elseif famCode == "crp" then insert(ret, "<td>[[:Category:Creole or pidgin languages|creole or pidgin]]</td>") elseif famCode == "art" then insert(ret, "<td>[[:Category:Constructed languages|constructed language]]</td>") else insert(ret, "<td>" .. fam:makeCategoryLink() .. "</td>") end insert(ret, "\n</tr>\n<tr>\n<th>Ancestors</th>\n<td>") local ancestors = lang:getAncestors() if ancestors[2] then local ancestorList = {} for i, anc in ipairs(ancestors) do ancestorList[i] = "<li>" .. anc:makeCategoryLink() .. "</li>" end insert(ret, "<ul>\n" .. concat(ancestorList, "\n") .. "</ul>") else local ancestorChain = lang:getAncestorChainOld() if ancestorChain[1] then local chain = {} for _, anc in reverse_ipairs(ancestorChain) do insert(chain, "<li>" .. anc:makeCategoryLink() .. "</li>") end insert(ret, "<ul>\n" .. concat(chain, "\n<ul>\n") .. ("</ul>"):rep(#chain)) else insert(ret, "unknown") end end insert(ret, "</td>\n</tr>\n") local scripts = lang:getScripts() if scripts[1] then local script_text = {} local function makeScriptLine(sc) local code = sc:getCode() local url = tostring(mw.uri.fullUrl('Special:Search', { search = 'contentmodel:css insource:"' .. code .. '" insource:/\\.' .. code .. '/', ns8 = '1' })) return sc:makeCategoryLink() .. ' (<span class="plainlinks" title="Search for stylesheets referencing this script">[' .. url .. ' <code>' .. code .. '</code>]</span>)' end local function add_Hrkt(text) insert(text, "<li>" .. makeScriptLine(Hrkt)) insert(text, "<ul>") insert(text, "<li>" .. makeScriptLine(Hira) .. "</li>") insert(text, "<li>" .. makeScriptLine(Kana) .. "</li>") insert(text, "</ul>") insert(text, "</li>") end for _, sc in ipairs(scripts) do local text = {} local code = sc:getCode() if code == "Hrkt" then add_Hrkt(text) else insert(text, "<li>" .. makeScriptLine(sc)) if code == "Jpan" then insert(text, "<ul>") insert(text, "<li>" .. makeScriptLine(Hani) .. "</li>") add_Hrkt(text) insert(text, "</ul>") elseif code == "Kore" then insert(text, "<ul>") insert(text, "<li>" .. makeScriptLine(Hang) .. "</li>") insert(text, "<li>" .. makeScriptLine(Hani) .. "</li>") insert(text, "</ul>") end insert(text, "</li>") end insert(script_text, concat(text, "\n")) end insert(ret, "<tr>\n<th>[[Wiktionary:Scripts|Scripts]]</th>\n<td><ul>\n" .. concat(script_text, "\n") .. "</ul></td>\n</tr>\n") else insert(ret, "<tr>\n<th>[[Wiktionary:Scripts|Scripts]]</th>\n<td>not specified</td>\n</tr>\n") end local function add_module_info(raw_data, heading) if raw_data then local scripts = lang:getScriptCodes() local module_info, add = {}, false if type(raw_data) == "string" then insert(module_info, ("[[Module:%s]]"):format(raw_data)) add = true else local raw_data_type = type(raw_data) if raw_data_type == "table" and size(scripts) == 1 and type(raw_data[scripts[1]]) == "string" then insert(module_info, ("[[Module:%s]]"):format(raw_data[scripts[1]])) add = true elseif raw_data_type == "table" then insert(module_info, "<ul>") for script, data in sorted_pairs(raw_data) do if type(data) == "string" and m_sc_getByCode(script) then insert(module_info, ("<li><code>%s</code>: [[Module:%s]]</li>"):format(script, data)) end end insert(module_info, "</ul>") add = size(module_info) > 2 end end if add then insert(ret, [=[ <tr> <th>]=] .. heading .. [=[</th> <td>]=] .. concat(module_info) .. [=[</td> </tr> ]=]) end end end add_module_info(raw_data.generate_forms, "Form-generating<br>module") add_module_info(raw_data.translit, "[[Wiktionary:Transliteration and romanization|Transliteration<br>module]]") add_module_info(raw_data.display_text, "Display text<br>module") add_module_info(raw_data.entry_name, "Entry name<br>module") add_module_info(raw_data.sort_key, "[[sortkey|Sortkey]]<br>module") local wikidataItem = lang:getWikidataItem() if lang:getWikidataItem() and mw.wikibase then local URL = mw.wikibase.getEntityUrl(wikidataItem) local link if URL then link = '[' .. URL .. ' ' .. wikidataItem .. ']' else link = '<span class="error">Invalid Wikidata item: <code>' .. wikidataItem .. '</code></span>' end insert(ret, "<tr><th>Wikidata</th><td>" .. link .. "</td></tr>") end insert(ret, "</table>") return concat(ret) end local function NavFrame(content, title) return '<div class="NavFrame"><div class="NavHead">' .. (title or '{{{title}}}') .. '</div>' .. '<div class="NavContent" style="text-align: left;">' .. content .. '</div></div>' end local function get_description_topright_additional(lang, locations, extinct, setwiki, setwikt, setsister, entryname) local nameWithLanguage = lang:getCategoryName("nocap") if lang:getCode() == "und" then local description = "This is the main category of the '''" .. nameWithLanguage .. "''', represented in Wiktionary by the [[Wiktionary:Languages|code]] '''" .. lang:getCode() .. "'''. " .. "This language contains terms in historical writing, whose meaning has not yet been determined by scholars." return description, nil, nil end local canonicalName = lang:getCanonicalName() local topright = linkbox(lang, setwiki, setwikt, setsister, entryname) local the_prefix if canonicalName:find(" Language$") then the_prefix = "" else the_prefix = "the " end local description = "This is the main category of " .. the_prefix .. "'''" .. nameWithLanguage .. "'''." local location_links = {} local prep local saw_embedded_comma = false for _, location in ipairs(locations) do local this_prep if location == "the world" then this_prep = "across" insert(location_links, location) elseif location ~= "UNKNOWN" then this_prep = "in" if location:find(",") then saw_embedded_comma = true end insert(location_links, link_location(location)) end if this_prep then if prep and this_prep ~= prep then error("Can't handle location 'the world' along with another location (clashing prepositions)") end prep = this_prep end end local location_desc if #location_links > 0 then local location_link_text if saw_embedded_comma and #location_links >= 3 then location_link_text = mw.text.listToText(location_links, "; ", "; and ") else location_link_text = serial_comma_join(location_links) end location_desc = ("It is %s %s %s.\n\n"):format( extinct and "an [[extinct language]] that was formerly spoken" or "spoken", prep, location_link_text) elseif extinct then location_desc = "It is an [[extinct language]].\n\n" else location_desc = "" end local add = location_desc .. "Information about " .. canonicalName .. ":\n\n" .. infobox(lang) if lang:hasType("reconstructed") then add = add .. "\n\n" .. ucfirst(canonicalName) .. " is a reconstructed language. Its words and roots are not directly attested in any written works, but have been reconstructed through the ''comparative method'', " .. "which finds regular similarities between languages that cannot be explained by coincidence or word-borrowing, and extrapolates ancient forms from these similarities.\n\n" .. "According to our [[Wiktionary:Criteria for inclusion|criteria for inclusion]], terms in " .. canonicalName .. " should '''not''' be present in entries in the main namespace, but may be added to the Reconstruction: namespace." elseif lang:hasType("appendix-constructed") then add = add .. "\n\n" .. ucfirst(canonicalName) .. " is a constructed language that is only in sporadic use. " .. "According to our [[Wiktionary:Criteria for inclusion|criteria for inclusion]], terms in " .. canonicalName .. " should '''not''' be present in entries in the main namespace, but may be added to the Appendix: namespace. " .. "All terms in this language may be available at [[Appendix:" .. ucfirst(canonicalName) .. "]]." end local about = new_title("Wiktionary:About " .. canonicalName) if about.exists then add = add .. "\n\n" .. "Please see '''[[Wiktionary:About " .. canonicalName .. "]]''' for information and special considerations for creating " .. nameWithLanguage .. " entries." end local ok, tree_of_descendants = pcall( require("Module:family tree").print_children, lang:getCode(), { protolanguage_under_family = true, must_have_descendants = true }) if ok then if tree_of_descendants then add = add .. NavFrame( tree_of_descendants, "Family tree") else add = add .. "\n\n" .. ucfirst(lang:getCanonicalName()) .. " has no descendants or varieties listed in Wiktionary's language data modules." end else mw.log("error while generating tree: " .. tostring(tree_of_descendants)) end return description, topright, add end local function get_parents(lang, locations, extinct) local canonicalName = lang:getCanonicalName() local sortkey = {sort_base = canonicalName, lang = "mi"} local ret = {{name = "Reo", sort = sortkey}} local fam = lang:getFamily() local famCode = fam and fam:getCode() -- FIXME: Some of the following categories should be added to this module. if not fam then insert(ret, {name = "Category:Unclassified languages", sort = sortkey}) elseif famCode == "qfa-iso" then insert(ret, {name = "Category:Language isolates", sort = sortkey}) elseif famCode == "qfa-mix" then insert(ret, {name = "Category:Mixed languages", sort = sortkey}) elseif famCode == "sgn" then insert(ret, {name = "Category:All sign languages", sort = sortkey}) elseif famCode == "crp" then insert(ret, {name = "Category:Creole or pidgin languages", sort = sortkey}) for _, anc in ipairs(lang:getAncestors()) do -- Avoid Haitian Creole being categorised in [[:Category:Haitian Creole-based creole or pidgin languages]], as one of its ancestors is an etymology-only variety of it. -- Use that ancestor's ancestors instead. if anc:getFullCode() == lang:getCode() then for _, anc_extra in ipairs(anc:getAncestors()) do insert(ret, {name = "Category:" .. ucfirst(anc_extra:getFullName()) .. "-based creole or pidgin languages", sort = sortkey}) end else insert(ret, {name = "Category:" .. ucfirst(anc:getFullName()) .. "-based creole or pidgin languages", sort = sortkey}) end end elseif famCode == "art" then if lang:hasType("appendix-constructed") then insert(ret, {name = "Category:Appendix-only constructed languages", sort = sortkey}) else insert(ret, {name = "Category:Constructed languages", sort = sortkey}) end for _, anc in ipairs(lang:getAncestors()) do if anc:getFullCode() == lang:getCode() then for _, anc_extra in ipairs(anc:getAncestors()) do insert(ret, {name = "Category:" .. ucfirst(anc_extra:getFullName()) .. "-based constructed languages", sort = sortkey}) end else insert(ret, {name = "Category:" .. ucfirst(anc:getFullName()) .. "-based constructed languages", sort = sortkey}) end end else insert(ret, {name = "Category:" .. fam:getCategoryName(), sort = sortkey}) if lang:hasType("reconstructed") then insert(ret, { name = "Category:Reconstructed languages", sort = {sort_base = canonicalName:gsub("^Proto%-", ""), lang = "en"} }) end end local function add_sc_cat(sc) insert(ret, {name = "Category:Reo " .. sc:getCategoryName(), sort = sortkey}) end local function add_Hrkt() add_sc_cat(Hrkt) add_sc_cat(Hira) add_sc_cat(Kana) end for _, sc in ipairs(lang:getScripts()) do if sc:getCode() == "Hrkt" then add_Hrkt() else add_sc_cat(sc) if sc:getCode() == "Jpan" then add_sc_cat(Hani) add_Hrkt() elseif sc:getCode() == "Kore" then add_sc_cat(Hang) add_sc_cat(Hani) end end end if lang:hasTranslit() then insert(ret, {name = "Category:Languages with automatic transliteration", sort = sortkey}) end local function insert_location_language_cat(location) local cat = "Languages of " .. location insert(ret, {name = "Category:" .. cat, sort = sortkey}) local auto_cat_args = scrape_category_for_auto_cat_args(cat) local location_parent = auto_cat_args and auto_cat_args.parent if location_parent then local split_parents = require(parse_utilities_module).split_on_comma(location_parent) for _, parent in ipairs(split_parents) do parent = parent:match("^(.-):.*$") or parent insert_location_language_cat(parent) end end end local saw_location = false for _, location in ipairs(locations) do if location ~= "UNKNOWN" then saw_location = true insert_location_language_cat(location) end end if extinct then insert(ret, {name = "Category:All extinct languages", sort = sortkey}) end if not saw_location and not (lang:hasType("reconstructed") or (fam and fam:getCode() == "art")) then -- Constructed and reconstructed languages don't need a location specified and often won't have one, -- so don't put them in this maintenance category. insert(ret, {name = "Category:Languages not sorted into a location category", sort = sortkey}) end return ret end local function get_children() local ret = {} -- FIXME: We should work on the children mechanism so it isn't necessary to manually specify these. --for _, label in ipairs({"appendices", "entry maintenance", "lemmas", "names", "phrases", "rhymes", "symbols", "templates", "terms by etymology", "terms by usage"}) do -- insert(ret, {name = label, is_label = true}) --end --insert(ret, {name = "terms derived from {{{langname}}}", is_label = true, lang = false}) --insert(ret, {name = "{{{langcode}}}:All topics", sort = "all topics"}) --insert(ret, {name = "Varieties of {{{langname}}}"}) --insert(ret, {name = "Requests concerning {{{langname}}}"}) --insert(ret, {name = "Rhymes:{{{langname}}}", description = "Lists of {{{langname}}} words by their rhymes."}) --insert(ret, {name = "User {{{langcode}}}", description = "Wiktionary users categorized by fluency levels in {{{langdisp}}}."}) return ret end -- Handle language categories of the form e.g. [[:Category:French language]] and -- [[:Category:British Sign Language]]. insert(raw_handlers, function(data) local category = data.category if not (category:match("[Rr]eo") or category:match("[Ll]ect$")) then return nil end local lang = m_languages.getByCanonicalName(category) if not lang then local langname = category:match("^Reo (.*)") if langname then lang = m_languages.getByCanonicalName(langname) end if not lang then return nil end end local args = require("Module:parameters").process(data.args, { [1] = {list = true}, ["setwiki"] = true, ["setwikt"] = true, ["setsister"] = true, ["entryname"] = true, ["extinct"] = {type = "boolean"}, }) -- If called from inside, don't require any arguments, as they can't be known -- in general and aren't needed just to generate the first parent (used for -- breadcrumbs). if #args[1] == 0 and not data.called_from_inside then -- At least one location must be specified unless the language is constructed (e.g. Esperanto) or reconstructed (e.g. Proto-Indo-European). local fam = lang:getFamily() if not (lang:hasType("reconstructed") or (fam and fam:getCode() == "art")) then error("At least one location (param 1=) must be specified for language '" .. lang:getCanonicalName() .. "' (code '" .. lang:getCode() .. "'). " .. "Use the value UNKNOWN if the language's location is truly unknown.") end end local description, topright, additional = "", "", "" -- If called from inside the category tree system, it's called when generating -- parents or children, and we don't need to generate the description or additional -- text (which is very expensive in terms of memory because it calls [[Module:family tree]], -- which calls [[Module:languages/data/all]]). if not data.called_from_inside then description, topright, additional = get_description_topright_additional( lang, args[1], args.extinct, args.setwiki, args.setwikt, args.setsister, args.entryname ) end return { canonical_name = lang:getCategoryName(), description = description, lang = lang:getCode(), topright = topright, additional = additional, breadcrumb = lang:getCanonicalName(), parents = get_parents(lang, args[1], args.extinct), extra_children = get_children(lang), umbrella = false, can_be_empty = true, }, true end) -- Handle categories such as [[:Category:Languages of Indonesia]]. insert(raw_handlers, function(data) local location = data.category:match("^Languages of (.*)$") if location then local args = require("Module:parameters").process(data.args, { ["flagfile"] = true, ["commonscat"] = true, ["wp"] = true, ["basename"] = true, ["parent"] = true, ["locationcat"] = true, ["locationlink"] = true, }) local topright local basename = args.basename or location:gsub(", .*", "") if args.flagfile ~= "-" then local flagfile_arg = args.flagfile or ("Flag of %s.svg"):format(basename) local files = require(parse_utilities_module).split_on_comma(flagfile_arg) local topright_parts = {} for _, file in ipairs(files) do local flagfile = "File:" .. file local flagfile_page = new_title(flagfile) if flagfile_page and flagfile_page.file.exists then insert(topright_parts, ("[[%s|right|100px|border]]"):format(flagfile)) elseif args.flagfile then error(("Explicit flagfile '%s' doesn't exist"):format(flagfile)) end end topright = concat(topright_parts) end if args.wp then local wp = require("Module:yesno")(args.wp, "+") if wp == "+" or wp == true then wp = data.category end if wp then local wp_topright = ("{{wikipedia|%s}}"):format(wp) if topright then topright = topright .. wp_topright else topright = wp_topright end end end if args.commonscat then local commonscat = require("Module:yesno")(args.commonscat, "+") if commonscat == "+" or commonscat == true then commonscat = data.category end if commonscat then local commons_topright = ("{{commonscat|%s}}"):format(commonscat) if topright then topright = topright .. commons_topright else topright = commons_topright end end end local bare_location = location:match("^the (.*)$") or location local location_link = args.locationlink or link_location(location) local bare_basename = basename:match("^the (.*)$") or basename local parents = {} if args.parent then local explicit_parents = require(parse_utilities_module).split_on_comma(args.parent) for i, parent in ipairs(explicit_parents) do local actual_parent, sort_key = parent:match("^(.-):(.*)$") if actual_parent then parent = actual_parent sort_key = sort_key:gsub("%+", bare_location) else sort_key = " " .. bare_location end insert(parents, {name = "Languages of " .. parent, sort = sort_key}) end else insert(parents, {name = "Languages by country", sort = {sort_base = bare_location, lang = "en"}}) end if args.locationcat then local explicit_location_cats = require(parse_utilities_module).split_on_comma(args.locationcat) for i, locationcat in ipairs(explicit_location_cats) do insert(parents, {name = "Category:" .. locationcat, sort = " Languages"}) end else local location_cat = ("Category:%s"):format(bare_location) local location_page = new_title(location_cat) if location_page and location_page.exists then insert(parents, {name = location_cat, sort = "Languages"}) end end local description = ("Categories for languages of %s (including sublects)."):format(location_link) return { topright = topright, description = description, parents = parents, breadcrumb = bare_basename, additional = "{{{umbrella_msg}}}", }, true end end) -- Handle categories such as [[:Category:English-based creole or pidgin languages]]. insert(raw_handlers, function(data) local langname = data.category:match("(.*)%-based creole or pidgin languages$") if langname then local lang = m_languages.getByCanonicalName(langname) if lang then return { lang = lang:getCode(), description = "Languages which developed as a [[creole]] or [[pidgin]] from " .. lang:makeCategoryLink() .. ".", parents = {{name = "Creole or pidgin languages", sort = {sort_base = "*" .. langname, lang = "en"}}}, breadcrumb = lang:getCanonicalName() .. "-based", } end end end) -- Handle categories such as [[:Category:English-based constructed languages]]. insert(raw_handlers, function(data) local langname = data.category:match("(.*)%-based constructed languages$") if langname then local lang = m_languages.getByCanonicalName(langname) if lang then return { lang = lang:getCode(), description = "Constructed languages which are based on " .. lang:makeCategoryLink() .. ".", parents = {{name = "Constructed languages", sort = {sort_base = "*" .. langname, lang = "en"}}}, breadcrumb = lang:getCanonicalName() .. "-based", } end end end) return {RAW_CATEGORIES = raw_categories, RAW_HANDLERS = raw_handlers} 9f0i5jaq1j7omkh2erfeca1ltyz92tf 828 5960 17396 2026-07-13T08:16:38Z Hiyuune 6766 + 17396 Scribunto text/plain local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared -- Ideally, we want to move these into [[Module:languages/data]], but because (a) it's necessary to use require on that module, and (b) they're only used in this data module, it's less memory-efficient to do that at the moment. If it becomes possible to use mw.loadData, then these should be moved there. s["de-Latn-sortkey"] = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. c.ringabove, from = {"æ", "œ", "ß"}, to = {"ae", "oe", "ss"} } s["de-Latn-standardchars"] = "AaÄäBbCcDdEeFfGgHhIiJjKkLlMmNnOoÖöPpQqRrSsẞßTtUuÜüVvWwXxYyZz" s["ka-stripdiacritics"] = {remove_diacritics = c.circ} s["no-sortkey"] = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.dacute .. c.caron .. c.cedilla, remove_exceptions = {"å"}, from = {"æ", "ø", "å"}, to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]} } s["no-standardchars"] = "AaBbDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvYyÆæØøÅå" .. c.punc s["sa-Deva-stripdiacritics"] = { -- Don't use remove_diacritics for accent marks, as १ and ३ should also be removed if (and only if) they carry any. from = {"ॐ", "[१३]?[" .. c.anudatta .. c.udatta .. c.dsvarita .. c.tsvarita .. "]+"}, to = {"ओँ"}, } s["tg-stripdiacritics"] = {remove_diacritics = c.grave .. c.acute} s["tk-stripdiacritics"] = {remove_diacritics = c.macron} local m = {} m["aa"] = { "Afar", 27811, "cus-eas", "Latn, Ethi", strip_diacritics = { Latn = {remove_diacritics = c.acute}, }, } m["ab"] = { "Abkhaz", 5111, "cau-abz", "Cyrl, Geor, Latn", translit = { Cyrl = "ab-translit", -- Geor translit in [[Module:scripts/data]] }, override_translit = true, display_text = { Cyrl = s["cau-Cyrl-displaytext"] }, strip_diacritics = { Cyrl = { remove_diacritics = c.acute, from = {"^а%-"}, to = {"а"}, }, Latn = s["cau-Latn-stripdiacritics"], }, sort_key = { Cyrl = { from = { "х'ә", -- 3 chars "гь", "гә", "ӷь", "ҕь", "ӷә", "ҕә", "дә", "ё", "жь", "жә", "ҙә", "ӡә", "ӡ'", "кь", "кә", "қь", "қә", "ҟь", "ҟә", "ҫә", "тә", "ҭә", "ф'", "хь", "хә", "х'", "ҳә", "ць", "цә", "ц'", "ҵә", "ҵ'", "шь", "шә", "џь", -- 2 chars "ӷ", "ҕ", "ҙ", "ӡ", "қ", "ҟ", "ԥ", "ҧ", "ҫ", "ҭ", "ҳ", "ҵ", "ҷ", "ҽ", "ҿ", "ҩ", "џ", "ә", -- 1 char "^а", }, to = { "х" .. p[4], "г" .. p[1], "г" .. p[2], "г" .. p[5], "г" .. p[6], "г" .. p[7], "г" .. p[8], "д" .. p[1], "е" .. p[1], "ж" .. p[1], "ж" .. p[2], "з" .. p[2], "з" .. p[4], "з" .. p[5], "к" .. p[1], "к" .. p[2], "к" .. p[4], "к" .. p[5], "к" .. p[7], "к" .. p[8], "с" .. p[2], "т" .. p[1], "т" .. p[3], "ф" .. p[1], "х" .. p[1], "х" .. p[2], "х" .. p[3], "х" .. p[6], "ц" .. p[1], "ц" .. p[2], "ц" .. p[3], "ц" .. p[5], "ц" .. p[6], "ш" .. p[1], "ш" .. p[2], "ы" .. p[3], "г" .. p[3], "г" .. p[4], "з" .. p[1], "з" .. p[3], "к" .. p[3], "к" .. p[6], "п" .. p[1], "п" .. p[2], "с" .. p[1], "т" .. p[2], "х" .. p[5], "ц" .. p[4], "ч" .. p[1], "ч" .. p[2], "ч" .. p[3], "ы" .. p[1], "ы" .. p[2], "ь" .. p[1], "", } }, }, } m["ae"] = { "Avestan", 29572, "ira-cen", "Avst, Gujr, Deva", translit = { Avst = "Avst-translit" }, } m["af"] = { "Afrikaans", 14196, "gmw-frk", "Latn, Arab", ancestors = "nl", sort_key = { Latn = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.diaer .. c.ringabove .. c.cedilla .. "'", from = {"['ʼ]n"}, to = {"n" .. p[1]} } }, } m["ak"] = { "Akan", 28026, "alv-ctn", "Latn", } m["am"] = { "Amharic", 28244, "sem-eth", "Ethi", translit = "Ethi-translit", } m["an"] = { "Aragonese", 8765, "roa-nar", "Latn", } m["ar"] = { "Arabic", 13955, "sem-arb", "Arab, Hebr, Syrc, Brai, Nbat", translit = { Arab = "ar-translit" }, strip_diacritics = { Arab = "ar-stripdiacritics", }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["as"] = { "Assamese", 29401, "inc-bas", "as-Beng", ancestors = "inc-mas", translit = "as-translit", } m["av"] = { "Avar", 29561, "cau-ava", "Cyrl, Latn, Arab", ancestors = "oav", translit = { Cyrl = "cau-nec-translit", Arab = "ar-translit", }, override_translit = true, display_text = { Cyrl = s["cau-Cyrl-displaytext"], }, strip_diacritics = { Cyrl = s["cau-Cyrl-stripdiacritics"], Latn = s["cau-Latn-stripdiacritics"], }, sort_key = { Cyrl = { from = {"гъ", "гь", "гӏ", "ё", "кк", "къ", "кь", "кӏ", "лъ", "лӏ", "тӏ", "хх", "хъ", "хь", "хӏ", "цӏ", "чӏ"}, to = {"г" .. p[1], "г" .. p[2], "г" .. p[3], "е" .. p[1], "к" .. p[1], "к" .. p[2], "к" .. p[3], "к" .. p[4], "л" .. p[1], "л" .. p[2], "т" .. p[1], "х" .. p[1], "х" .. p[2], "х" .. p[3], "х" .. p[4], "ц" .. p[1], "ч" .. p[1]} }, }, } m["ay"] = { "Aymara", 4627, "sai-aym", "Latn", } m["az"] = { "Azerbaijani", 9292, "trk-ogz", "Latn, Cyrl, fa-Arab", ancestors = "trk-oat", dotted_dotless_i = true, strip_diacritics = { Latn = { from = {"ʼ"}, to = {"'"}, }, ["fa-Arab"] = { module = "ar-stripdiacritics", ["from"] = { "ۆ", "ۇ", "وْ", "ڲ", "ؽ", }, ["to"] = { "و", "و", "و", "گ", "ی", }, }, }, display_text = { Latn = { from = {"'"}, to = {"ʼ"} } }, sort_key = { Latn = { from = { "i", -- Ensure "i" comes after "ı". "ç", "ə", "ğ", "x", "ı", "q", "ö", "ş", "ü", "w" }, to = { "i" .. p[1], "c" .. p[1], "e" .. p[1], "g" .. p[1], "h" .. p[1], "i", "k" .. p[1], "o" .. p[1], "s" .. p[1], "u" .. p[1], "z" .. p[1] } }, Cyrl = { from = {"ғ", "ә", "ы", "ј", "ҝ", "ө", "ү", "һ", "ҹ"}, to = {"г" .. p[1], "е" .. p[1], "и" .. p[1], "и" .. p[2], "к" .. p[1], "о" .. p[1], "у" .. p[1], "х" .. p[1], "ч" .. p[1]} }, }, } m["ba"] = { "Bashkir", 13389, "trk-kbu", "Cyrl", translit = "ba-translit", override_translit = true, sort_key = { from = {"ғ", "ҙ", "ё", "ҡ", "ң", "ө", "ҫ", "ү", "һ", "ә"}, to = {"г" .. p[1], "д" .. p[1], "е" .. p[1], "к" .. p[1], "н" .. p[1], "о" .. p[1], "с" .. p[1], "у" .. p[1], "х" .. p[1], "э" .. p[1]} }, } m["be"] = { "Belarusian", 9091, "zle", "Cyrl, Latn", ancestors = "zle-mbe", translit = { Cyrl = "be-translit", }, strip_diacritics = { Cyrl = { remove_diacritics = c.grave .. c.acute, }, Latn = { remove_diacritics = c.grave .. c.acute, remove_exceptions = {"Ć", "ć", "Ń", "ń", "Ś", "ś", "Ź", "ź"}, }, }, sort_key = { Cyrl = { remove_diacritics = c.grave .. c.acute, from = {"ґ", "ё", "і", "ў"}, to = {"г" .. p[1], "е" .. p[1], "и" .. p[1], "у" .. p[1]} }, Latn = { remove_diacritics = c.grave .. c.acute, remove_exceptions = {"Ć", "ć", "Ń", "ń", "Ś", "ś", "Ź", "ź"}, from = {"ć", "č", "dz", "dź", "dž", "ch", "ł", "ń", "ś", "š", "ŭ", "ź", "ž"}, to = {"c" .. p[1], "c" .. p[2], "d" .. p[1], "d" .. p[2], "d" .. p[3], "h" .. p[1], "l" .. p[1], "n" .. p[1], "s" .. p[1], "s" .. p[2], "u" .. p[1], "z" .. p[1], "z" .. p[2]} }, }, standard_chars = { Cyrl = "АаБбВвГгДдЕеЁёЖжЗзІіЙйКкЛлМмНнОоПпРрСсТтУуЎўФфХхЦцЧчШшЫыЬьЭэЮюЯя", Latn = "AaBbCcĆćČčDdEeFfGgHhIiJjKkLlŁłMmNnŃńOoPpRrSsŚśŠšTtUuŬŭVvYyZzŹźŽž", (c.punc:gsub("'", "")) -- Exclude apostrophe. }, } m["bg"] = { "Bulgarian", 7918, "zls", "Cyrl", ancestors = "cu-bgm", translit = "bg-translit", strip_diacritics = { remove_diacritics = c.grave .. c.acute, remove_exceptions = {"%f[^%z%s]ѝ%f[%z%s]"}, }, sort_key = { remove_diacritics = c.grave .. c.acute, remove_exceptions = {"%f[^%z%s]ѝ%f[%z%s]"}, }, standard_chars = "АаБбВвГгДдЕеЖжЗзИиЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЩщЪъЬьЮюЯя" .. c.punc, } m["bh"] = { "Bihari", 135305, "inc-eas", "Deva", } m["bi"] = { "Bislama", 35452, "crp", "Latn", ancestors = "en", } m["bm"] = { "Bambara", 33243, "dmn-emn", "Latn, Nkoo", sort_key = { Latn = { from = {"ɛ", "ɲ", "ŋ", "ɔ"}, to = {"e" .. p[1], "n" .. p[1], "n" .. p[2], "o" .. p[1]} }, }, } m["bn"] = { "Bengali", 9610, "inc-bas", "Beng, Newa", ancestors = "inc-mbn", translit = { Beng = "bn-translit" }, } m["bo"] = { "Tibetan", 34271, "sit-tib", "Tibt", -- sometimes Deva? ancestors = "xct", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["br"] = { "Breton", 12107, "cel-brs", "Latn", ancestors = "xbm", sort_key = { from = {"ch", "c['ʼ’]h"}, to = {"c" .. p[1], "c" .. p[2]} }, } m["ca"] = { "Catalan", 7026, "roa-ocr", "Latn", ancestors = "roa-oca", sort_key = {remove_diacritics = c.grave .. c.acute .. c.diaer .. c.cedilla .. "·"}, standard_chars = "AaÀàBbCcÇçDdEeÉéÈèFfGgHhIiÍíÏïJjLlMmNnOoÓóÒòPpQqRrSsTtUuÚúÜüVvXxYyZz·" .. c.punc, } m["ce"] = { "Chechen", 33350, "cau-vay", "Cyrl, Latn, Arab", translit = { Cyrl = "cau-nec-translit", Arab = "ar-translit", }, override_translit = true, display_text = { Cyrl = s["cau-Cyrl-displaytext"] }, strip_diacritics = { Cyrl = s["cau-Cyrl-stripdiacritics"], Latn = s["cau-Latn-stripdiacritics"], }, sort_key = { Cyrl = { from = {"аь", "гӏ", "ё", "кх", "къ", "кӏ", "оь", "пӏ", "тӏ", "уь", "хь", "хӏ", "цӏ", "чӏ", "юь", "яь"}, to = {"а" .. p[1], "г" .. p[1], "е" .. p[1], "к" .. p[1], "к" .. p[2], "к" .. p[3], "о" .. p[1], "п" .. p[1], "т" .. p[1], "у" .. p[1], "х" .. p[1], "х" .. p[2], "ц" .. p[1], "ч" .. p[1], "ю" .. p[1], "я" .. p[1]} }, }, } m["ch"] = { "Chamorro", 33262, "poz", "Latn", sort_key = { remove_diacritics = "'", from = {"å", "ch", "ñ", "ng"}, to = {"a" .. p[1], "c" .. p[1], "n" .. p[1], "n" .. p[2]} }, } m["co"] = { "Corsican", 33111, "roa-itr", "Latn", sort_key = { from = {"chj", "ghj", "sc", "sg"}, to = {"c" .. p[1], "g" .. p[1], "s" .. p[1], "s" .. p[2]} }, standard_chars = "AaÀàBbCcDdEeÈèFfGgHhIiÌìÏïJjLlMmNnOoÒòPpQqRrSsTtUuÙùÜüVvZz" .. c.punc, } m["cr"] = { "Cree", 33390, "alg", "Latn, Cans", translit = { Cans = "cr-translit" }, } m["cs"] = { "Czech", 9056, "zlw", "Latn", ancestors = "cs-ear", sort_key = { from = {"á", "č", "ď", "é", "ě", "ch", "í", "ň", "ó", "ř", "š", "ť", "ú", "ů", "ý", "ž"}, to = {"a" .. p[1], "c" .. p[1], "d" .. p[1], "e" .. p[1], "e" .. p[2], "h" .. p[1], "i" .. p[1], "n" .. p[1], "o" .. p[1], "r" .. p[1], "s" .. p[1], "t" .. p[1], "u" .. p[1], "u" .. p[2], "y" .. p[1], "z" .. p[1]} }, standard_chars = "AaÁáBbCcČčDdĎďEeÉéĚěFfGgHhIiÍíJjKkLlMmNnŇňOoÓóPpRrŘřSsŠšTtŤťUuÚúŮůVvYyÝýZzŽž" .. c.punc, } m["cu"] = { "Old Church Slavonic", 35499, "zls", "Cyrs, Glag, Zname", translit = { Cyrs = "Cyrs-translit", Glag = "Glag-translit" }, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]] } m["cv"] = { "Chuvash", 33348, "trk-ogr", "Cyrl", ancestors = "cv-mid", translit = "cv-translit", override_translit = true, sort_key = { from = {"ӑ", "ё", "ӗ", "ҫ", "ӳ"}, to = {"а" .. p[1], "е" .. p[1], "е" .. p[2], "с" .. p[1], "у" .. p[1]} }, } m["cy"] = { "Welsh", 9309, "cel-brw", "Latn", ancestors = "wlm", sort_key = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. "'", from = {"ch", "dd", "ff", "ng", "ll", "ph", "rh", "th"}, to = {"c" .. p[1], "d" .. p[1], "f" .. p[1], "g" .. p[1], "l" .. p[1], "p" .. p[1], "r" .. p[1], "t" .. p[1]} }, standard_chars = "ÂâAaBbCcDdEeÊêFfGgHhIiÎîLlMmNnOoÔôPpRrSsTtUuÛûWwŴŵYyŶŷ" .. c.punc, } m["da"] = { "Danish", 9035, "gmq-eas", "Latn", ancestors = "gmq-oda", sort_key = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.dacute .. c.caron .. c.cedilla, remove_exceptions = {"å"}, from = {"æ", "ø", "å"}, to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]} }, standard_chars = "AaBbDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvYyÆæØøÅå" .. c.punc, } m["de"] = { "German", 188, "gmw-hgm", "Latn, Latf, Brai", ancestors = "de-ear", sort_key = { Latn = s["de-Latn-sortkey"], Latf = s["de-Latn-sortkey"], }, standard_chars = { Latn = s["de-Latn-standardchars"], Latf = s["de-Latn-standardchars"], Brai = c.braille, c.punc } } m["dv"] = { "Dhivehi", 32656, "inc-ins", "Thaa, Diak", translit = { Thaa = "dv-translit", Diak = "Diak-translit", }, ancestors = "dv-old", override_translit = true, } m["dz"] = { "Dzongkha", 33081, "sit-tib", "Tibt", ancestors = "xct", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["ee"] = { "Ewe", 30005, "alv-gbe", "Latn", sort_key = { remove_diacritics = c.tilde, from = {"ɖ", "dz", "ɛ", "ƒ", "gb", "ɣ", "kp", "ny", "ŋ", "ɔ", "ts", "ʋ"}, to = {"d" .. p[1], "d" .. p[2], "e" .. p[1], "f" .. p[1], "g" .. p[1], "g" .. p[2], "k" .. p[1], "n" .. p[1], "n" .. p[2], "o" .. p[1], "t" .. p[1], "v" .. p[1]} }, } m["el"] = { "Greek", 9129, "grk", "Grek, Polyt, Brai", ancestors = "el-kth", translit = "el-translit", override_translit = true, -- Grek and Polyt display_text, strip_diacritics, sort_key in [[Module:scripts/data]] standard_chars = { Grek = "΅·ͺ΄ΑαΆάΒβΓγΔδΕεέΈΖζΗηΉήΘθΙιΊίΪϊΐΚκΛλΜμΝνΞξΟοΌόΠπΡρΣσςΤτΥυΎύΫϋΰΦφΧχΨψΩωΏώ", Brai = c.braille, c.punc }, } m["en"] = { "English", 1860, "gmw-ang", "Latn, Brai, Shaw, Dsrt", -- entries in Shaw or Dsrt might require prior discussion wikimedia_codes = "en, simple", ancestors = "en-ear", sort_key = { Latn = { -- Many of these are needed for sorting language names. remove_diacritics = "'\"%-%.,%s·ʻʼ" .. c.diacritics, -- These are found in pagenames. from = {"[ɒæ🅱¢©ᴄðđəǝɜɡħʜıɨłŋɲøɔœꝑꝓꝕßʋ]"}, to = {{ ["ɒ"] = "a", ["æ"] = "ae", ["🅱"] = "b", ["¢"] = "c", ["©"] = "c", ["ᴄ"] = "c", ["ð"] = "d", ["đ"] = "d", ["ə"] = "e", ["ǝ"] = "e", ["ɜ"] = "e", ["ɡ"] = "g", ["ħ"] = "h", ["ʜ"] = "h", ["ı"] = "i", ["ɨ"] = "i", ["ł"] = "l", ["ŋ"] = "n", ["ɲ"] = "n", ["ø"] = "o", ["ɔ"] = "o", ["œ"] = "oe", ["ꝑ"] = "p", ["ꝓ"] = "p", ["ꝕ"] = "p", ["ß"] = "ss", ["ʋ"] = "v", }}, }, }, standard_chars = { Latn = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz", Brai = c.braille, c.punc }, } m["eo"] = { "Esperanto", 143, "art", "Latn", sort_key = { remove_diacritics = c.grave .. c.acute, from = {"ĉ", "ĝ", "ĥ", "ĵ", "ŝ", "ŭ"}, to = {"c" .. p[1], "g" .. p[1], "h" .. p[1], "j" .. p[1], "s" .. p[1], "u" .. p[1]} }, standard_chars = "AaBbCcĈĉDdEeFfGgĜĝHhĤĥIiJjĴĵKkLlMmNnOoPpRrSsŜŝTtUuŬŭVvZz" .. c.punc, } m["es"] = { "Spanish", 1321, "roa-cas", "Latn, Brai", ancestors = "es-ear", sort_key = { Latn = { remove_exceptions = {"ñ"}, remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.diaer .. c.cedilla, from = {"ª", "æ", "ñ", "º", "œ"}, to = {"a", "ae", "n" .. p[1], "o", "oe"} }, }, standard_chars = { Latn = "AaÁáBbCcDdEeÉéFfGgHhIiÍíJjLlMmNnÑñOoÓóPpQqRrSsTtUuÚúÜüVvXxYyZz", Brai = c.braille, c.punc }, } m["et"] = { "Estonian", 9072, "urj-fin", "Latn", sort_key = { from = { "š", "ž", "õ", "ä", "ö", "ü", -- 2 chars "z" -- 1 char }, to = { "s" .. p[1], "s" .. p[3], "w" .. p[1], "w" .. p[2], "w" .. p[3], "w" .. p[4], "s" .. p[2] } }, standard_chars = "AaBbDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvÕõÄäÖöÜü" .. c.punc, } m["eu"] = { "Basque", 8752, "euq", "Latn", sort_key = { from = {"ç", "ñ"}, to = {"c" .. p[1], "n" .. p[1]} }, standard_chars = "AaBbDdEeFfGgHhIiJjKkLlMmNnÑñOoPpRrSsTtUuXxZz" .. c.punc, } m["fa"] = { "Persian", 9168, "ira-swi", "fa-Arab, Hebr", ancestors = "fa-cls", strip_diacritics = { ["fa-Arab"] = { -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه"; hamzatu l-waṣli to a regular alif from = {"هٔ", "ٱ"}, -- character "ۂ" code U+06C2 to "ه"; hamzatu l-waṣli to a regular alif to = {"ه", "ا"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.superalef, }, }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["ff"] = { "Fula", 33454, "alv-fwo", "Latn, Adlm", } m["fi"] = { "Finnish", 1412, "urj-fin", "Latn", display_text = { from = {"'"}, to = {"’"} }, strip_diacritics = { -- used to indicate gemination of the next consonant remove_diacritics = "ˣ", from = {"’"}, to = {"'"}, }, sort_key = { -- [[Appendix:Finnish alphabet#Collation]] + "aͤ" and "oͤ" as historical variants of "ä" and "ö". remove_diacritics = "'’:" .. c.diacritics, remove_exceptions = { "a[" .. c.ringabove .. c.diaer .. c.small_e .. "]", -- åäaͤ "o[" .. c.diaer .. c.tilde .. c.dacute .. c.small_e .. "]", -- öõőoͤ "u[" .. c.diaer .. c.dacute .. "]" -- üű }, from = {"æ", "[ðđ]", "ł", "ŋ", "œ", "ß", "þ", "u[" .. c.diaer .. c.dacute .. "]", "å", "aͤ", "o[" .. c.tilde .. c.dacute .. c.small_e .. "]", "ø", "(.)['%-]"}, to = {"ae", "d", "l", "n", "oe", "ss", "th", "y", "z" .. p[1], "ä", "ö", "ö", "%1"} }, standard_chars = "AaBbDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvYyÄäÖö" .. c.punc, } m["fj"] = { "Fijian", 33295, "poz-pcc", "Latn", } m["fo"] = { "Faroese", 25258, "gmq-ins", "Latn", sort_key = { from = {"á", "ð", "í", "ó", "ú", "ý", "æ", "ø"}, to = {"a" .. p[1], "d" .. p[1], "i" .. p[1], "o" .. p[1], "u" .. p[1], "y" .. p[1], "z" .. p[1], "z" .. p[2]} }, standard_chars = "AaÁáBbDdÐðEeFfGgHhIiÍíJjKkLlMmNnOoÓóPpRrSsTtUuÚúVvYyÝýÆæØø" .. c.punc, } m["fr"] = { "French", 150, "roa-oil", "Latn, Brai", ancestors = "frm", sort_key = { Latn = s["roa-oil-sortkey"] }, standard_chars = { Latn = "AaÀàÂâBbCcÇçDdEeÉéÈèÊêËëFfGgHhIiÎîÏïJjLlMmNnOoÔôŒœPpQqRrSsTtUuÙùÛûÜüVvXxYyZz", Brai = c.braille, c.punc }, } m["fy"] = { "West Frisian", 27175, "gmw-fri", "Latn", sort_key = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer, from = {"y"}, to = {"i"} }, standard_chars = "AaâäàÆæBbCcDdEeéêëèFfGgHhIiïìYyỳJjKkLlMmNnOoôöòPpRrSsTtUuúûüùVvWwZz" .. c.punc, } m["ga"] = { "Irish", 9142, "cel-gae", "Latn, Latg", ancestors = "mga", sort_key = { remove_diacritics = c.acute, from = {"ḃ", "ċ", "ḋ", "ḟ", "ġ", "ṁ", "ṗ", "ṡ", "ṫ"}, to = {"bh", "ch", "dh", "fh", "gh", "mh", "ph", "sh", "th"} }, standard_chars = "AaÁáBbCcDdEeÉéFfGgHhIiÍíLlMmNnOoÓóPpRrSsTtUuÚúVv" .. c.punc, } m["gd"] = { "Scottish Gaelic", 9314, "cel-gae", "Latn, Latg", ancestors = "mga", sort_key = {remove_diacritics = c.grave .. c.acute}, standard_chars = "AaÀàBbCcDdEeÈèFfGgHhIiÌìLlMmNnOoÒòPpRrSsTtUuÙù" .. c.punc, } m["gl"] = { "Galician", 9307, "roa-gap", "Latn", sort_key = { remove_diacritics = c.acute, from = {"ñ"}, to = {"n" .. p[1]} }, standard_chars = "AaÁáBbCcDdEeÉéFfGgHhIiÍíÏïLlMmNnÑñOoÓóPpQqRrSsTtUuÚúÜüVvXxZz" .. c.punc, } m["gu"] = { "Gujarati", 5137, "inc-wes", "Arab, Gujr", ancestors = "inc-mgu", translit = { Gujr = "gu-translit", }, strip_diacritics = { Arab = {remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.kasra .. c.shadda .. c.sukun}, Gujr = {remove_diacritics = "઼"}, }, } m["gv"] = { "Manx", 12175, "cel-gae", "Latn", ancestors = "mga", sort_key = {remove_diacritics = c.cedilla .. "-"}, standard_chars = "AaBbCcÇçDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwYy" .. c.punc, } m["ha"] = { "Hausa", 56475, "cdc-wst", "Latn, Arab", strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron} }, sort_key = { Latn = { from = {"ɓ", "b'", "ɗ", "d'", "ƙ", "k'", "sh", "ƴ", "'y"}, to = {"b" .. p[1], "b" .. p[2], "d" .. p[1], "d" .. p[2], "k" .. p[1], "k" .. p[2], "s" .. p[1], "y" .. p[1], "y" .. p[2]} }, }, } m["he"] = { "Hebrew", 9288, "sem-can", "Hebr, Phnx, Brai, Samr", ancestors = "he-med", -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] -- Samr strip_diacritics, sort_key in [[Module:scripts/data]] -- Phnx translit in [[Module:scripts/data]] (NOTE: not present before, presumably an accidental omission) } m["hi"] = { "Hindi", 1568, "inc-hnd", "Deva, Kthi, Newa", translit = { Deva = "hi-translit" }, standard_chars = { Deva = "अआइईउऊएऐओऔकखगघङचछजझञटठडढणतथदधनपफबभमयरलवशषसहत्रज्ञक्षक़ख़ग़ज़झ़ड़ढ़फ़काखागाघाङाचाछाजाझाञाटाठाडाढाणाताथादाधानापाफाबाभामायारालावाशाषासाहात्राज्ञाक्षाक़ाख़ाग़ाज़ाझ़ाड़ाढ़ाफ़ाकिखिगिघिङिचिछिजिझिञिटिठिडिढिणितिथिदिधिनिपिफिबिभिमियिरिलिविशिषिसिहित्रिज्ञिक्षिक़िख़िग़िज़िझ़िड़िढ़िफ़िकीखीगीघीङीचीछीजीझीञीटीठीडीढीणीतीथीदीधीनीपीफीबीभीमीयीरीलीवीशीषीसीहीत्रीज्ञीक्षीक़ीख़ीग़ीज़ीझ़ीड़ीढ़ीफ़ीकुखुगुघुङुचुछुजुझुञुटुठुडुढुणुतुथुदुधुनुपुफुबुभुमुयुरुलुवुशुषुसुहुत्रुज्ञुक्षुक़ुख़ुग़ुज़ुझ़ुड़ुढ़ुफ़ुकूखूगूघूङूचूछूजूझूञूटूठूडूढूणूतूथूदूधूनूपूफूबूभूमूयूरूलूवूशूषूसूहूत्रूज्ञूक्षूक़ूख़ूग़ूज़ूझ़ूड़ूढ़ूफ़ूकेखेगेघेङेचेछेजेझेञेटेठेडेढेणेतेथेदेधेनेपेफेबेभेमेयेरेलेवेशेषेसेहेत्रेज्ञेक्षेक़ेख़ेग़ेज़ेझ़ेड़ेढ़ेफ़ेकैखैगैघैङैचैछैजैझैञैटैठैडैढैणैतैथैदैधैनैपैफैबैभैमैयैरैलैवैशैषैसैहैत्रैज्ञैक्षैक़ैख़ैग़ैज़ैझ़ैड़ैढ़ैफ़ैकोखोगोघोङोचोछोजोझोञोटोठोडोढोणोतोथोदोधोनोपोफोबोभोमोयोरोलोवोशोषोसोहोत्रोज्ञोक्षोक़ोख़ोग़ोज़ोझ़ोड़ोढ़ोफ़ोकौखौगौघौङौचौछौजौझौञौटौठौडौढौणौतौथौदौधौनौपौफौबौभौमौयौरौलौवौशौषौसौहौत्रौज्ञौक्षौक़ौख़ौग़ौज़ौझ़ौड़ौढ़ौफ़ौक्ख्ग्घ्ङ्च्छ्ज्झ्ञ्ट्ठ्ड्ढ्ण्त्थ्द्ध्न्प्फ्ब्भ्म्य्र्ल्व्श्ष्स्ह्त्र्ज्ञ्क्ष्क़्ख़्ग़्ज़्झ़्ड़्ढ़्फ़्।॥०१२३४५६७८९॰", c.punc }, } m["ho"] = { "Hiri Motu", 33617, "crp", "Latn", ancestors = "meu", } m["ht"] = { "Haitian Creole", 33491, "crp", "Latn", ancestors = "ht-sdm", sort_key = { from = { "oun", -- 3 chars "an", "ch", "è", "en", "ng", "ò", "on", "ou", "ui" -- 2 chars }, to = { "o" .. p[4], "a" .. p[1], "c" .. p[1], "e" .. p[1], "e" .. p[2], "n" .. p[1], "o" .. p[1], "o" .. p[2], "o" .. p[3], "u" .. p[1] } }, } m["hu"] = { "Hungarian", 9067, "urj-ugr", "Latn, Hung", ancestors = "ohu", sort_key = { Latn = { from = { "dzs", -- 3 chars "á", "cs", "dz", "é", "gy", "í", "ly", "ny", "ó", "ö", "ő", "sz", "ty", "ú", "ü", "ű", "zs", -- 2 chars }, to = { "d" .. p[2], "a" .. p[1], "c" .. p[1], "d" .. p[1], "e" .. p[1], "g" .. p[1], "i" .. p[1], "l" .. p[1], "n" .. p[1], "o" .. p[1], "o" .. p[2], "o" .. p[3], "s" .. p[1], "t" .. p[1], "u" .. p[1], "u" .. p[2], "u" .. p[3], "z" .. p[1], } }, }, standard_chars = { Latn = "AaÁáBbCcDdEeÉéFfGgHhIiÍíJjKkLlMmNnOoÓóÖöŐőPpQqRrSsTtUuÚúÜüŰűVvWwXxYyZz", c.punc }, } m["hy"] = { "Armenian", 8785, "hyx", "Armn, Brai", ancestors = "axm", -- Armn translit in [[Module:scripts/data]] override_translit = true, strip_diacritics = { Armn = { remove_diacritics = "՛՜՞՟", from = {"եւ", "^յ", "^ի", "^է", "յ̵", "ՙ", "՚"}, to = {"և", "յ", "ի", "է", "ֈ", "ʻ", "’"} }, }, sort_key = { Armn = { from = { "ու", "եւ", -- 2 chars "և" -- 1 char }, to = { "ւ", "եվ", "եվ" } }, }, } m["hz"] = { "Herero", 33315, "bnt-swb", "Latn", } m["ia"] = { "Interlingua", 35934, "art", "Latn", } m["id"] = { "Indonesian", 9240, "poz-mly", "Latn", ancestors = "ms", standard_chars = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz" .. c.punc, } m["ie"] = { "Interlingue", 35850, "art", "Latn", type = "appendix-constructed", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ}, } m["ig"] = { "Igbo", 33578, "alv-igb", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.macron}, sort_key = { from = {"gb", "gh", "gw", "ị", "kp", "kw", "ṅ", "nw", "ny", "ọ", "sh", "ụ"}, to = {"g" .. p[1], "g" .. p[2], "g" .. p[3], "i" .. p[1], "k" .. p[1], "k" .. p[2], "n" .. p[1], "n" .. p[2], "n" .. p[3], "o" .. p[1], "s" .. p[1], "u" .. p[1]} }, } m["ii"] = { "Nuosu", 34235, "tbq-nlo", "Yiii", translit = "ii-translit", } m["ik"] = { "Inupiaq", 27183, "esx-inu", "Latn", sort_key = { from = { "ch", "ġ", "dj", "ḷ", "ł̣", "ñ", "ng", "r̂", "sr", "zr", -- 2 chars "ł", "ŋ", "ʼ" -- 1 char }, to = { "c" .. p[1], "g" .. p[1], "h" .. p[1], "l" .. p[1], "l" .. p[3], "n" .. p[1], "n" .. p[2], "r" .. p[1], "s" .. p[1], "z" .. p[1], "l" .. p[2], "n" .. p[2], "z" .. p[2] } }, } m["io"] = { "Ido", 35224, "art", "Latn", } m["is"] = { "Icelandic", 294, "gmq-ins", "Latn", sort_key = { from = {"á", "ð", "é", "í", "ó", "ú", "ý", "þ", "æ", "ö"}, to = {"a" .. p[1], "d" .. p[1], "e" .. p[1], "i" .. p[1], "o" .. p[1], "u" .. p[1], "y" .. p[1], "z" .. p[1], "z" .. p[2], "z" .. p[3]} }, standard_chars = "AaÁáBbDdÐðEeÉéFfGgHhIiÍíJjKkLlMmNnOoÓóPpRrSsTtUuÚúVvXxYyÝýÞþÆæÖö" .. c.punc, } m["it"] = { "Italian", 652, "roa-itr", "Latn", ancestors = "roa-oit", sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. c.ringabove}, standard_chars = "AaÀàBbCcDdEeÈèÉéFfGgHhIiÌìLlMmNnOoÒòPpQqRrSsTtUuÙùVvZz" .. c.punc, } m["iu"] = { "Inuktitut", 29921, "esx-inu", "Cans, Latn", translit = { Cans = "cr-translit" }, override_translit = true, } m["ja"] = { "Japanese", 5287, "jpx", "Jpan, Latn, Brai", ancestors = "ja-ear", translit = s["jpx-translit"], link_tr = true, display_text = s["jpx-displaytext"], strip_diacritics = s["jpx-stripdiacritics"], sort_key = s["jpx-sortkey"], } m["jv"] = { "Javanese", 33549, "poz", "Latn, Java, Arab", ancestors = "kaw", translit = { Java = "jv-translit" }, link_tr = true, strip_diacritics = { Latn = {remove_diacritics = c.circ} -- Modern jv don't use ê }, sort_key = { Latn = { from = {"å", "dh", "é", "è", "ng", "ny", "th"}, to = {"a" .. p[1], "d" .. p[1], "e" .. p[1], "e" .. p[2], "n" .. p[1], "n" .. p[2], "t" .. p[1]} }, }, } m["ka"] = { "Georgian", 8108, "ccs-gzn", "Geor, Geok, Hebr", -- Hebr is used to write Judeo-Georgian ancestors = "ka-mid", -- Geor, Geok translit in [[Module:scripts/data]] override_translit = true, strip_diacritics = { Geor = s["ka-stripdiacritics"], Geok = s["ka-stripdiacritics"], }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["kg"] = { "Kongo", 33702, "bnt-kng", "Latn", } m["ki"] = { "Kikuyu", 33587, "bnt-kka", "Latn", } m["kj"] = { "Kwanyama", 1405077, "bnt-ova", "Latn", } m["kk"] = { "Kazakh", 9252, "trk-kno", "Cyrl, Latn, kk-Arab", translit = { Cyrl = { from = { "Ё", "ё", "Й", "й", "Нг", "нг", "Ӯ", "ӯ", -- 2 chars; are "Ӯ" and "ӯ" actually used? "А", "а", "Ә", "ә", "Б", "б", "В", "в", "Г", "г", "Ғ", "ғ", "Д", "д", "Е", "е", "Ж", "ж", "З", "з", "И", "и", "К", "к", "Қ", "қ", "Л", "л", "М", "м", "Н", "н", "Ң", "ң", "О", "о", "Ө", "ө", "П", "п", "Р", "р", "С", "с", "Т", "т", "У", "у", "Ұ", "ұ", "Ү", "ү", "Ф", "ф", "Х", "х", "Һ", "һ", "Ц", "ц", "Ч", "ч", "Ш", "ш", "Щ", "щ", "Ъ", "ъ", "Ы", "ы", "І", "і", "Ь", "ь", "Э", "э", "Ю", "ю", "Я", "я", -- 1 char }, to = { "E", "e", "İ", "i", "Ñ", "ñ", "U", "u", "A", "a", "Ä", "ä", "B", "b", "V", "v", "G", "g", "Ğ", "ğ", "D", "d", "E", "e", "J", "j", "Z", "z", "İ", "i", "K", "k", "Q", "q", "L", "l", "M", "m", "N", "n", "Ñ", "ñ", "O", "o", "Ö", "ö", "P", "p", "R", "r", "S", "s", "T", "t", "U", "u", "Ū", "ū", "Ü", "ü", "F", "f", "X", "x", "H", "h", "S", "s", "Ç", "ç", "Ş", "ş", "Ş", "ş", "", "", "Y", "y", "I", "ı", "", "", "É", "é", "Ü", "ü", "Ä", "ä", } } }, -- override_translit = true, sort_key = { Cyrl = { from = {"ә", "ғ", "ё", "қ", "ң", "ө", "ұ", "ү", "һ", "і"}, to = {"а" .. p[1], "г" .. p[1], "е" .. p[1], "к" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1], "у" .. p[2], "х" .. p[1], "ы" .. p[1]} }, }, standard_chars = { Cyrl = "АаӘәБбВвГгҒғДдЕеЁёЖжЗзИиЙйКкҚқЛлМмНнҢңОоӨөПпРрСсТтУуҰұҮүФфХхҺһЦцЧчШшЩщЪъЫыІіЬьЭэЮюЯя", c.punc }, } m["kl"] = { "Greenlandic", 25355, "esx-inu", "Latn", sort_key = { from = {"æ", "ø", "å"}, to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]} } } m["km"] = { "Khmer", 9205, "mkh-kmr", "Khmr", ancestors = "xhm", translit = "km-translit", --This might yield unwanted result unless its entry has {{km-IPA}}. } m["kn"] = { "Kannada", 33673, "dra-kan", "Knda, Tutg", ancestors = "dra-mkn", -- Knda translit in [[Module:scripts/data]] } m["ko"] = { "Korean", 9176, "qfa-kor", "Kore, Brai", ancestors = "ko-ear", translit = { Kore = "ko-translit", }, -- Kore strip_diacritics in [[Module:scripts/data]] } m["kr"] = { "Kanuri", 36094, "ssa-sah", "Latn, Arab", -- the sortkey and strip_diacritics are only for standard Kanuri; when dialectal entries get added, someone will have to work out how the dialects should be represented orthographically strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.breve} }, sort_key = { Latn = { from = {"ǝ", "ny", "ɍ", "sh"}, to = {"e" .. p[1], "n" .. p[1], "r" .. p[1], "s" .. p[1]} }, }, } m["ks"] = { "Kashmiri", 33552, "inc-kas", "ks-Arab, Deva, Shrd, Latn", translit = { ["ks-Arab"] = "ks-Arab-translit", Deva = "ks-Deva-translit", -- Shrd translit in [[Module:scripts/data]] }, } -- "kv" is treated as "koi", "kpv", see [[WT:LT]] m["kw"] = { "Cornish", 25289, "cel-brs", "Latn", ancestors = "cnx", sort_key = { from = {"ch"}, to = {"c" .. p[1]} }, } m["ky"] = { "Kyrgyz", 9255, "trk-kkp", "Cyrl, Latn, Arab", translit = { Cyrl = "ky-translit" }, override_translit = true, sort_key = { Cyrl = { from = {"ё", "ң", "ө", "ү"}, to = {"е" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1]} }, }, } m["la"] = { "Latin", 397, "itc-laf", "Latn, Ital", ancestors = "itc-ola", -- Ital translit in [[Module:scripts/data]] (NOTE: formerly not present, probably an accidental omission) display_text = { Latn = s["itc-Latn-displaytext"] }, strip_diacritics = { Latn = s["itc-Latn-stripdiacritics"] }, sort_key = { Latn = s["itc-Latn-sortkey"] }, standard_chars = { Latn = "AaBbCcDdEeFfGgHhIiLlMmNnOoPpQqRrSsTtUuVvXx", c.punc }, } m["lb"] = { "Luxembourgish", 9051, "gmw-hgm", "Latn, Brai", ancestors = "gmw-cfr", sort_key = { Latn = { from = {"ä", "ë", "é"}, to = {"z" .. p[1], "z" .. p[2], "z" .. p[3]} }, }, } m["lg"] = { "Luganda", 33368, "bnt-nyg", "Latn", strip_diacritics = {remove_diacritics = c.acute .. c.circ}, sort_key = { from = {"ŋ"}, to = {"n" .. p[1]} }, } m["li"] = { "Limburgish", 102172, "gmw-frk", "Latn", ancestors = "dum", } m["ln"] = { "Lingala", 36217, "bnt-bmo", "Latn", sort_key = { remove_diacritics = c.acute .. c.circ .. c.caron, from = {"ɛ", "gb", "mb", "mp", "nd", "ng", "nk", "ns", "nt", "ny", "nz", "ɔ"}, to = {"e" .. p[1], "g" .. p[1], "m" .. p[1], "m" .. p[2], "n" .. p[1], "n" .. p[2], "n" .. p[3], "n" .. p[4], "n" .. p[5], "n" .. p[6], "n" .. p[7], "o" .. p[1]} }, } m["lo"] = { "Lao", 9211, "tai-swe", "Laoo", -- also Tai Noi/Lao Buhan script translit = "lo-translit", sort_key = "Laoo-sortkey", standard_chars = "0-9ກຂຄງຈຊຍດຕຖທນບປຜຝພຟມຢຣລວສຫອຮຯ-ໝ" .. c.punc, } m["lt"] = { "Lithuanian", 9083, "bat-eas", "Latn", ancestors = "olt", display_text = "lt-common", strip_diacritics = "lt-common", sort_key = "lt-common", standard_chars = "AaĄąBbCcČčDdEeĘęĖėFfGgHhIiĮįYyJjKkLlMmNnOoPpRrSsŠšTtUuŲųŪūVvZzŽž" .. c.punc, } m["lu"] = { "Luba-Katanga", 36157, "bnt-lub", "Latn", } m["lv"] = { "Latvian", 9078, "bat-eas", "Latn", strip_diacritics = { -- This attempts to convert vowels with tone marks to vowels either with or without macrons. Specifically, there should be no macrons if the vowel is part of a diphthong (including resonant diphthongs such pìrksts -> pirksts not #pīrksts). What we do is first convert the vowel + tone mark to a vowel + tilde in a decomposed fashion, then remove the tilde in diphthongs, then convert the remaining vowel + tilde sequences to macroned vowels, then delete any other tilde. We leave already-macroned vowels alone: Both e.g. ar and ār occur before consonants. FIXME: This still might not be sufficient. from = {"([Ee])" .. c.cedilla, "[" .. c.grave .. c.circ .. c.tilde .."]", "([aAeEiIoOuU])" .. c.tilde .."?([lrnmuiLRNMUI])" .. c.tilde .. "?([^aAeEiIoOuU])", "([aAeEiIoOuU])" .. c.tilde .."?([lrnmuiLRNMUI])" .. c.tilde .."?$", "([iI])" .. c.tilde .. "?([eE])" .. c.tilde .. "?", "([aAeEiIuU])" .. c.tilde, c.tilde}, to = {"%1", c.tilde, "%1%2%3", "%1%2", "%1%2", "%1" .. c.macron} }, sort_key = { from = {"ā", "č", "ē", "ģ", "ī", "ķ", "ļ", "ņ", "š", "ū", "ž"}, to = {"a" .. p[1], "c" .. p[1], "e" .. p[1], "g" .. p[1], "i" .. p[1], "k" .. p[1], "l" .. p[1], "n" .. p[1], "s" .. p[1], "u" .. p[1], "z" .. p[1]} }, standard_chars = "AaĀāBbCcČčDdEeĒēFfGgĢģHhIiĪīJjKkĶķLlĻļMmNnŅņOoPpRrSsŠšTtUuŪūVvZzŽž" .. c.punc, } m["mg"] = { "Malagasy", 7930, "poz-bre", "Latn, Arab", } m["mh"] = { "Marshallese", 36280, "poz-mic", "Latn", sort_key = { from = {"ā", "ļ", "m̧", "ņ", "n̄", "o̧", "ō", "ū"}, to = {"a" .. p[1], "l" .. p[1], "m" .. p[1], "n" .. p[1], "n" .. p[2], "o" .. p[1], "o" .. p[2], "u" .. p[1]} }, } m["mi"] = { "Māori", 36451, "poz-pep", "Latn", sort_key = { remove_diacritics = c.macron, from = {"ng", "wh"}, to = {"n" .. p[1], "w" .. p[1]} }, } m["mk"] = { "Macedonian", 9296, "zls", "Cyrl, Polyt", ancestors = "cu", translit = { Cyrl = "mk-translit", -- FIXME: formerly no translit specified for Polyt; unclear if the default [[Module:grc-translit]] is -- acceptable, so we disable it for now Polyt = false, }, strip_diacritics = { Cyrl = { remove_diacritics = c.acute, remove_exceptions = {"Ѓ", "ѓ", "Ќ", "ќ"} }, }, sort_key = { Cyrl = { remove_diacritics = c.grave, remove_exceptions = {"ѓ", "ќ"}, from = {"ѓ", "ѕ", "ј", "љ", "њ", "ќ", "џ"}, to = {"д" .. p[1], "з" .. p[1], "и" .. p[1], "л" .. p[1], "н" .. p[1], "т" .. p[1], "ч" .. p[1]} }, }, -- Polyt display_text, strip_diacritics, sort_key in [[Module:scripts/data]] standard_chars = { Cyrl = "АаБбВвГгДдЃѓЕеЖжЗзЅѕИиЈјКкЛлЉљМмНнЊњОоПпРрСсТтЌќУуФфХхЦцЧчЏџШш", c.punc }, } m["ml"] = { "Malayalam", 36236, "dra-mal", "Mlym", override_translit = true, -- Mlym translit in [[Module:scripts/data]] } m["mn"] = { "Mongolian", 9246, "xgn-cen", "Cyrl, Mong, Latn, Brai", ancestors = "cmg", translit = { Cyrl = "mn-translit", -- Mong translit in [[Module:scripts/data]] }, override_translit = true, -- Mong display_text and strip_diacritics in [[Module:scripts/data]] strip_diacritics = { Cyrl = {remove_diacritics = c.grave .. c.acute}, }, sort_key = { Cyrl = { remove_diacritics = c.grave, from = {"ё", "ө", "ү"}, to = {"е" .. p[1], "о" .. p[1], "у" .. p[1]} }, }, standard_chars = { Cyrl = "АаБбВвГгДдЕеЁёЖжЗзИиЙйЛлМмНнОоӨөРрСсТтУуҮүХхЦцЧчШшЫыЬьЭэЮюЯя—", Brai = c.braille, c.punc }, } -- "mo" is treated as "ro", see [[WT:LT]] m["mr"] = { "Marathi", 1571, "inc-sou", "Deva, Modi", ancestors = "omr", translit = { Deva = "mr-translit", Modi = "mr-Modi-translit", }, strip_diacritics = { Deva = { from = {"च़", "ज़", "झ़"}, to = {"च", "ज", "झ"} }, }, } m["ms"] = { "Malay", 9237, "poz-mly", "Latn, ms-Arab", ancestors = "ms-cla", standard_chars = { Latn = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz", c.punc }, } m["mt"] = { "Maltese", 9166, "sem-arb", "Latn", display_text = { from = {"'"}, to = {"’"} }, strip_diacritics = { from = {"’"}, to = {"'"}, }, ancestors = "sqr", sort_key = { from = { "ċ", "ġ", "ż", -- Convert into PUA so that decomposed form does not get caught by the next step. "([cgz])", -- Ensure "c" comes after "ċ", "g" comes after "ġ" and "z" comes after "ż". "g" .. p[1] .. "ħ", -- "għ" after initial conversion of "g". p[3], p[4], "ħ", "ie", p[5] -- Convert "ċ", "ġ", "ħ", "ie", "ż" into final output. }, to = { p[3], p[4], p[5], "%1" .. p[1], "g" .. p[2], "c", "g", "h" .. p[1], "i" .. p[1], "z" } }, } m["my"] = { "Burmese", 9228, "tbq-brm", "Mymr", ancestors = "obr", translit = "my-translit", override_translit = true, sort_key = { from = {"ျ", "ြ", "ွ", "ှ", "ဿ"}, to = {"္ယ", "္ရ", "္ဝ", "္ဟ", "သ္သ"} }, } m["na"] = { "Nauruan", 13307, "poz-mic", "Latn", } m["nb"] = { "Norwegian Bokmål", 25167, "gmq", "Latn", wikimedia_codes = "no", ancestors = "gmq-mno, da", -- da as an (but not the) ancestor of nb was agreed on - do not change without discussion sort_key = s["no-sortkey"], standard_chars = s["no-standardchars"], } m["nd"] = { "Northern Ndebele", 35613, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } m["ne"] = { "Nepali", 33823, "inc-pah", "Deva, Newa", translit = { Deva = "ne-translit" }, } m["ng"] = { "Ndonga", 33900, "bnt-ova", "Latn", } m["nl"] = { "Dutch", 7411, "gmw-frk", "Latn, Brai", ancestors = "dum", sort_key = { Latn = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.diaer .. c.ringabove .. c.cedilla .. "'"}, }, standard_chars = { Latn = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZzÄäËëÏïÖöÜü", Brai = c.braille, c.punc }, } m["nn"] = { "Norwegian Nynorsk", 25164, "gmq-wes", "Latn", ancestors = "gmq-mno", strip_diacritics = { remove_diacritics = c.grave .. c.acute, }, sort_key = s["no-sortkey"], standard_chars = s["no-standardchars"], } m["no"] = { "Norwegian", 9043, "gmq-wes", "Latn", ancestors = "gmq-mno", sort_key = s["no-sortkey"], standard_chars = s["no-standardchars"], } m["nr"] = { "Southern Ndebele", 36785, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } m["nv"] = { "Navajo", 13310, "apa", "Latn, Brai", sort_key = { remove_diacritics = c.acute .. c.ogonek, from = { "chʼ", "tłʼ", "tsʼ", -- 3 chars "ch", "dl", "dz", "gh", "hw", "kʼ", "kw", "sh", "tł", "ts", "zh", -- 2 chars "ł", "ʼ" -- 1 char }, to = { "c" .. p[2], "t" .. p[2], "t" .. p[4], "c" .. p[1], "d" .. p[1], "d" .. p[2], "g" .. p[1], "h" .. p[1], "k" .. p[1], "k" .. p[2], "s" .. p[1], "t" .. p[1], "t" .. p[3], "z" .. p[1], "l" .. p[1], "z" .. p[2] } }, } m["ny"] = { "Chichewa", 33273, "bnt-nys", "Latn", strip_diacritics = {remove_diacritics = c.acute .. c.circ}, sort_key = { from = {"ng'"}, to = {"ng"} }, } m["oc"] = { "Occitan", 14185, "roa-ocr", "Latn, Hebr", ancestors = "pro", sort_key = { Latn = { remove_diacritics = c.grave .. c.acute .. c.diaer .. c.cedilla, from = {"([lns])·h"}, to = {"%1h"} }, }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["oj"] = { "Ojibwe", 33875, "alg", "Cans, Latn", sort_key = { Latn = { from = {"aa", "ʼ", "ii", "oo", "sh", "zh"}, to = {"a" .. p[1], "h" .. p[1], "i" .. p[1], "o" .. p[1], "s" .. p[1], "z" .. p[1]} }, }, } m["om"] = { "Oromo", 33864, "cus-eas", "Latn, Ethi", } m["or"] = { "Odia", 33810, "inc-eas", "Orya", ancestors = "inc-mor", translit = "or-translit", } m["os"] = { "Ossetian", 33968, "xsc-sar", "Cyrl, Geor, Latn", ancestors = "oos", translit = { Cyrl = "os-translit", -- Geor translit in [[Module:scripts/data]] }, override_translit = true, display_text = { Cyrl = { from = {"æ"}, to = {"ӕ"} }, Latn = { from = {"ӕ"}, to = {"æ"} }, }, strip_diacritics = { Cyrl = { remove_diacritics = c.grave .. c.acute, from = {"æ"}, to = {"ӕ"} }, Latn = { from = {"ӕ"}, to = {"æ"} }, }, sort_key = { Cyrl = { from = {"ӕ", "гъ", "дж", "дз", "ё", "къ", "пъ", "тъ", "хъ", "цъ", "чъ"}, to = {"а" .. p[1], "г" .. p[1], "д" .. p[1], "д" .. p[2], "е" .. p[1], "к" .. p[1], "п" .. p[1], "т" .. p[1], "х" .. p[1], "ц" .. p[1], "ч" .. p[1]} }, }, } m["pa"] = { "Punjabi", 58635, "inc-pan", "Guru, pa-Arab", translit = { Guru = "Guru-translit", ["pa-Arab"] = "pa-Arab-translit", }, strip_diacritics = { ["pa-Arab"] = { remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna, from = {"ݨ", "ࣇ"}, to = {"ن", "ل"} }, }, } m["pi"] = { "Pali", 36727, "inc-mid", "Latn, Brah, Deva, Beng, Sinh, Mymr, Thai, Lana, Laoo, Khmr, Cakm", --and also Khom ancestors = "sa", translit = { -- Brah translit in [[Module:scripts/data]] Deva = "sa-translit", Beng = "pi-translit", Sinh = "si-translit", Mymr = "pi-translit", Thai = "pi-translit", Lana = "pi-translit", Laoo = "pi-translit", Khmr = "pi-translit", Cakm = "Cakm-translit", }, strip_diacritics = { Thai = { from = {"ึ", u(0xF700), u(0xF70F)}, -- FIXME: Not clear what's going on with the PUA characters here. to = {"ิํ", "ฐ", "ญ"} }, Mymr = { remove_diacritics = c.VS01, }, }, sort_key = { -- FIXME: This needs to be converted into the current standardized format. from = {"ā", "ī", "ū", "ḍ", "ḷ", "m[" .. c.dotabove .. c.dotbelow .. "]", "ṅ", "ñ", "ṇ", "ṭ", "ॐ", "([เโ])([ก-ฮ])", "([ເໂ])([ກ-ຮ])", "ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ", u(0xFE00), u(0x200D)}, to = {"a~", "i~", "u~", "d~", "l~", "m~", "n~", "n~~", "n~~~", "t~", "ओँ", "%2%1", "%2%1", "ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"} }, } m["pl"] = { "Polish", 809, "zlw-lch", "Latn", ancestors = "zlw-mpl", sort_key = { from = {"ą", "ć", "ę", "ł", "ń", "ó", "ś", "ź", "ż"}, to = {"a" .. p[1], "c" .. p[1], "e" .. p[1], "l" .. p[1], "n" .. p[1], "o" .. p[1], "s" .. p[1], "z" .. p[1], "z" .. p[2]} }, standard_chars = "AaĄąBbCcĆćDdEeĘęFfGgHhIiJjKkLlŁłMmNnŃńOoÓóPpRrSsŚśTtUuWwYyZzŹźŻż" .. c.punc, } m["ps"] = { "Pashto", 58680, "ira-pat", "ps-Arab", strip_diacritics = {remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.zwarakay .. c.superalef}, } m["pt"] = { "Portuguese", 5146, "roa-gap", "Latn, Brai", sort_key = { Latn = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.diaer .. c.cedilla, from = {"ª", "æ", "º", "œ"}, to = {"a", "ae", "o", "oe"} }, }, standard_chars = { Latn = "AaÁáÂâÃãBbCcÇçDdEeÉéÊêFfGgHhIiÍíJjLlMmNnOoÓóÔôÕõPpQqRrSsTtUuÚúVvXxZz", Brai = c.braille, c.punc }, } m["qu"] = { "Quechua", 5218, "qwe", "Latn", } m["rm"] = { "Romansh", 13199, "roa-rhe", ancestors = "rm-old", "Latn", sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. c.small_e}, } m["ro"] = { "Romanian", 7913, "roa-eas", "Latn, Cyrl, Cyrs", translit = { Cyrl = "ro-translit" }, sort_key = { Latn = { remove_diacritics = c.grave .. c.acute, from = {"ă", "â", "î", "ș", "ț"}, to = {"a" .. p[1], "a" .. p[2], "i" .. p[1], "s" .. p[1], "t" .. p[1]} }, Cyrl = { from = {"ӂ"}, to = {"ж" .. p[1]} }, }, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]]; presumably not present standard_chars = { Latn = "AaĂăÂâBbCcDdEeFfGgHhIiÎîJjLlMmNnOoPpRrSsȘșTtȚțUuVvXxZz", Cyrl = "АаБбВвГгДдЕеЖжӁӂЗзИиЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЫыЬьЭэЮюЯя", c.punc }, } m["ru"] = { "Russian", 7737, "zle", "Cyrl, Brai", ancestors = "zle-mru", translit = { Cyrl = "ru-translit" }, display_text = { Cyrl = { from = {"'"}, to = {"’"} }, }, strip_diacritics = { Cyrl = { remove_diacritics = c.grave .. c.acute .. c.diaer, remove_exceptions = {"Ё", "ё", "Ѣ̈", "ѣ̈", "Я̈", "я̈"}, from = {"’"}, to = {"'"}, }, }, sort_key = { Cyrl = { remove_diacritics = c.grave .. c.acute .. c.diaer, from = { "і", "ѣ", "ѳ", "ѵ" }, to = { "и" .. p[1], "ь" .. p[1], "я" .. p[2], "я" .. p[3] } }, }, standard_chars = { Cyrl = "АаБбВвГгДдЕеЁёЖжЗзИиЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЩщЪъЫыЬьЭэЮюЯя—", Brai = c.braille, (c.punc:gsub("'", "")) -- Exclude apostrophe. }, } m["rw"] = { "Rwanda-Rundi", 3217514, "bnt-glb", "Latn", strip_diacritics = {remove_diacritics = c.acute .. c.circ .. c.macron .. c.caron}, } m["sa"] = { "Sanskrit", 11059, "inc", "as-Beng, Bali, Beng, Bhks, Brah, Mymr, xwo-Mong, Deva, Gujr, Guru, Gran, Hani, Java, Kthi, Knda, Kawi, Khar, Khmr, Laoo, Mlym, mnc-Mong, Marc, Modi, Mong, Nand, Newa, Orya, Phag, Ranj, Saur, Shrd, Sidd, Sinh, Soyo, Lana, Takr, Taml, Tang, Telu, Thai, Tibt, Tutg, Tirh, Zanb", --and also Khom; script codes sorted by canonical name rather than code for [[MOD:sa-convert]] translit = { Beng = "sa-Beng-translit", ["as-Beng"] = "sa-Beng-translit", -- Brah translit in [[Module:scripts/data]] Deva = "sa-translit", Gujr = "sa-Gujr-translit", Guru = "sa-Guru-translit", Java = "sa-Java-translit", Kthi = "sa-Kthi-translit", Khmr = "pi-translit", Knda = "sa-Knda-translit", Lana = "pi-translit", Laoo = "pi-translit", Mlym = "sa-Mlym-translit", Modi = "sa-Modi-translit", -- Mong, mnc-Mong, xwo-Mong translit in [[Module:scripts/data]] -- NOTE: Formerly used xal-translit for transliterating xwo-Mong but that only handles Cyrillic; it has -- code to transliterate xwo-Mong but it's broken so I've replaced it with the default xwo-translit. Mymr = "pi-translit", Orya = "sa-Orya-translit", -- Shrd translit in [[Module:scripts/data]] -- Sidd translit in [[Module:scripts/data]] Sinh = "si-translit", Taml = "sa-Taml-translit", Telu = "sa-Telu-translit", Thai = "pi-translit", -- Tibt translit in [[Module:scripts/data]] }, -- Mong display_text and strip_diacritics in [[Module:scripts/data]] -- Tibt display_text, strip_diacritics, sort_key in [[Module:scripts/data]] strip_diacritics = { Deva = s["sa-Deva-stripdiacritics"], Mymr = { remove_diacritics = c.VS01, }, Thai = { from = {"ึ", u(0xF700), u(0xF70F)}, -- FIXME: Not clear what's going on with the PUA characters here. to = {"ิํ", "ฐ", "ญ"} }, }, sort_key = { Deva = s["sa-Deva-stripdiacritics"], -- until we have a proper Sanskrit sorting algorithm. Lana = { -- Tai Tham from = {"ᩔ", "ᩕ", "ᩖ", "ᩘ", "([ᨭ-ᨱ])ᩛ", "([ᨷ-ᨾ])ᩛ", "ᩤ"}, to = {"ᩈ᩠ᩈ", "᩠ᩁ", "᩠ᩃ", "ᨦ᩠", "%1᩠ᨮ", "%1᩠ᨻ", "ᩣ"}, }, Laoo = "Laoo-sortkey", Latn = { from = {"ā", "ī", "ū", "ḍ", "ḷ", "ḹ", "m[" .. c.dotabove .. c.dotbelow .. "]", "ṅ", "ñ", "ṇ", "ṛ", "ṝ", "ś", "ṣ", "ṭ"}, to = {"a~", "i~", "u~", "d~", "l~", "l~~", "m~", "n~", "n~~", "n~~~", "r~", "r~~", "s~", "s~~", "t~"}, }, Mymr = { remove_diacritics = c.VS01, }, Thai = "Thai-sortkey", -- FIXME: The previous sort key which mixed all scripts removed ZWJ; I don't know which script(s) this was -- intended for and there are no other languages which remove it in the sort key AFAIK. If it needs to be -- removed, specify the script(s) it needs to be removed under or add handling for the "all" script that applies -- regardless of script. --all = { -- remove_diacritics = c.ZWJ, --}, }, } m["sc"] = { "Sardinian", 33976, "roa-sou", "Latn", ancestors = "sc-old", } m["sd"] = { "Sindhi", 33997, "inc-snd", "sd-Arab, Deva, Sind, Khoj", translit = { Sind = "Sind-translit", ["sd-Arab"] = "sd-Arab-translit" }, strip_diacritics = { ["sd-Arab"] = { remove_diacritics = c.kashida .. c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.superalef, from = {"ٱ"}, to = {"ا"} }, }, } m["se"] = { "Northern Sami", 33947, "smi", "Latn", display_text = { from = {"'"}, to = {"ˈ"} }, strip_diacritics = {remove_diacritics = c.macron .. c.dotbelow .. "'ˈ"}, sort_key = { from = {"á", "č", "đ", "ŋ", "š", "ŧ", "ž"}, to = {"a" .. p[1], "c" .. p[1], "d" .. p[1], "n" .. p[1], "s" .. p[1], "t" .. p[1], "z" .. p[1]} }, standard_chars = "AaÁáBbCcČčDdĐđEeFfGgHhIiJjKkLlMmNnŊŋOoPpRrSsŠšTtŦŧUuVvZzŽž" .. c.punc, } m["sg"] = { "Sango", 33954, "crp", "Latn", ancestors = "ngb", } m["sh"] = { "Serbo-Croatian", 9301, "zls", "Latn, Cyrl, Glag, Arab", ietf_subtag = "hbs", -- ISO 639-3 code, since "sh" is deprecated from ISO 639-1 wikimedia_codes = "sh, bs, hr, sr", strip_diacritics = { Latn = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {"Ć", "ć", "Ś", "ś", "Ź", "ź"} }, Cyrl = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {"З́", "з́", "С́", "с́"} }, }, sort_key = { Latn = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {"ć", "ś", "ź"}, from = {"č", "ć", "dž", "đ", "lj", "nj", "š", "ś", "ž", "ź"}, to = {"c" .. p[1], "c" .. p[2], "d" .. p[1], "d" .. p[2], "l" .. p[1], "n" .. p[1], "s" .. p[1], "s" .. p[2], "z" .. p[1], "z" .. p[2]} }, Cyrl = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {"з́", "с́"}, from = {"ђ", "з́", "ј", "љ", "њ", "с́", "ћ", "џ"}, to = {"д" .. p[1], "з" .. p[1], "и" .. p[1], "л" .. p[1], "н" .. p[1], "с" .. p[1], "т" .. p[1], "ч" .. p[1]} }, }, standard_chars = { Latn = "AaBbCcČčĆćDdĐđEeFfGgHhIiJjKkLlMmNnOoPpRrSsŠšTtUuVvZzŽž", Cyrl = "АаБбВвГгДдЂђЕеЖжЗзИиЈјКкЛлЉљМмНнЊњОоПпРрСсТтЋћУуФфХхЦцЧчЏџШш", c.punc }, } m["si"] = { "Sinhalese", 13267, "inc-ins", "Sinh", translit = "si-translit", override_translit = true, } m["sk"] = { "Slovak", 9058, "zlw", "Latn", ancestors = "zlw-osk", sort_key = {remove_diacritics = c.acute .. c.circ .. c.diaer .. c.caron}, standard_chars = "AaÁáÄäBbCcČčDdĎďEeÉéFfGgHhIiÍíJjKkLlĹ弾MmNnŇňOoÓóÔôPpRrŔŕSsŠšTtŤťUuÚúVvYyÝýZzŽž" .. c.punc, } m["sl"] = { "Slovene", 9063, "zls", "Latn", strip_diacritics = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.dgrave .. c.invbreve .. c.dotbelow, remove_exceptions = {"Ć", "ć", "Ǵ", "ǵ", "Ś", "ś", "Ź", "ź"}, from = {"Ə", "ə", "Ł", "ł"}, to = {"E", "e", "L", "l"}, }, sort_key = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.dotabove .. c.ringabove .. c.dgrave .. c.invbreve .. c.dotbelow .. c.ringbelow .. c.ogonek, remove_exceptions = {"ć", "ǵ", "ś", "ź"}, from = {"ä", "č", "ć", "đ", "ə", "ë", "ǧ", "ǵ", "ï", "ł", "ö", "š", "ś", "ü", "ž", "ź"}, to = {"a" .. p[1], "c" .. p[1], "c" .. p[2], "d" .. p[1], "e", "e" .. p[1], "g" .. p[1], "g" .. p[2], "i" .. p[1], "l", "o" .. p[1], "s" .. p[1], "s" .. p[2], "u" .. p[1], "z" .. p[1], "z" .. p[2]}, }, standard_chars = "AaBbCcČčDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsŠšTtUuVvZzŽž" .. c.punc, } m["sm"] = { "Samoan", 34011, "poz-pnp", "Latn", } m["sn"] = { "Shona", 34004, "bnt-sho", "Latn", strip_diacritics = {remove_diacritics = c.acute}, } m["so"] = { "Somali", 13275, "cus-som", "Latn, Arab, Osma", strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.circ} }, } m["sq"] = { "Albanian", 8748, "sqj", "Latn, Grek, ota-Arab, Elba, Todr, Vith", translit = { Elba = "Elba-translit", Vith = "Vith-translit", }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] strip_diacritics = { Latn = { remove_diacritics = c.acute .. c.circ .. c.macron, from = {'^[ie] (%w)', '^të (%w)'}, to = {'%1', '%1'}, }, }, sort_key = { Latn = { remove_diacritics = c.acute .. c.circ .. c.macron .. c.tilde .. c.breve .. c.caron, from = {'^[ie] (%w)', '^të (%w)', 'ç', 'dh', 'ë', 'gj', 'll', 'nj', 'rr', 'sh', 'th', 'xh', 'zh'}, to = {'%1', '%1', 'c'..p[1], 'd'..p[1], 'e'..p[1], 'g'..p[1], 'l'..p[1], 'n'..p[1], 'r'..p[1], 's'..p[1], 't'..p[1], 'x'..p[1], 'z'..p[1]}, } -- TODO: Grek if the default sort key is unsuitable }, standard_chars = { Latn = "AaBbCcÇçDdEeËëFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvXxYyZz", c.punc }, } m["ss"] = { "Swazi", 34014, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } m["st"] = { "Sotho", 34340, "bnt-sts", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } m["su"] = { "Sundanese", 34002, "poz-msa", "Latn, Sund, Arab", ancestors = "osn", translit = { Sund = "Sund-translit" }, } m["sv"] = { "Swedish", 9027, "gmq-eas", "Latn", ancestors = "gmq-osw-lat", sort_key = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron .. c.dacute .. c.caron .. c.cedilla .. "':", remove_exceptions = {"å"}, from = {"ø", "æ", "œ", "ß", "å", "aͤ", "oͤ"}, to = {"ö", "ae", "oe", "ss", "z" .. p[1], "ä", "ö"} }, standard_chars = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpRrSsTtUuVvXxYyÅåÄäÖö" .. c.punc, } m["sw"] = { "Swahili", 7838, "bnt-swh", "Latn, Arab", sort_key = { Latn = { from = {"ng'"}, to = {"ng" .. p[1]} }, }, } m["ta"] = { "Tamil", 5885, "dra-tam", "Taml", ancestors = "ta-mid", translit = "ta-translit", override_translit = true, } m["te"] = { "Telugu", 8097, "dra-tel", "Telu", translit = "te-translit", override_translit = true, } m["tg"] = { "Tajik", 9260, "ira-swi", "Cyrl, fa-Arab, Latn", ancestors = "fa-cls", translit = { Cyrl = "tg-translit" }, override_translit = true, strip_diacritics = { Cyrl = s["tg-stripdiacritics"], Latn = s["tg-stripdiacritics"], }, sort_key = { Cyrl = { from = {"ғ", "ё", "ӣ", "қ", "ӯ", "ҳ", "ҷ"}, to = {"г" .. p[1], "е" .. p[1], "и" .. p[1], "к" .. p[1], "у" .. p[1], "х" .. p[1], "ч" .. p[1]} }, }, } m["th"] = { "Thai", 9217, "tai-swe", "Thai, Khomt, Brai", translit = { Thai = "th-translit" }, sort_key = { Thai = "Thai-sortkey" }, } m["ti"] = { "Tigrinya", 34124, "sem-eth", "Ethi", translit = "Ethi-translit", } m["tk"] = { "Turkmen", 9267, "trk-ogz", "Latn, Cyrl, Arab", strip_diacritics = { Latn = s["tk-stripdiacritics"], Cyrl = s["tk-stripdiacritics"], }, sort_key = { Latn = { from = {"ç", "ä", "ž", "ň", "ö", "ş", "ü", "ý"}, to = {"c" .. p[1], "e" .. p[1], "j" .. p[1], "n" .. p[1], "o" .. p[1], "s" .. p[1], "u" .. p[1], "y" .. p[1]} }, Cyrl = { from = {"ё", "җ", "ң", "ө", "ү", "ә"}, to = {"е" .. p[1], "ж" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1], "э" .. p[1]} }, }, ancestors = "trk-eog", } m["tl"] = { "Tagalog", 34057, "phi", "Latn, Tglg", translit = { Tglg = "tl-translit" }, override_translit = true, strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.circ} }, standard_chars = { Latn = "AaBbKkDdEeGgHhIiLlMmNnOoPpRrSsTtUuWwYy", c.punc }, sort_key = { Latn = "tl-sortkey", }, } m["tn"] = { "Tswana", 34137, "bnt-sts", "Latn", } m["to"] = { "Tongan", 34094, "poz-ton", "Latn", strip_diacritics = {remove_diacritics = c.acute}, sort_key = {remove_diacritics = c.macron}, } m["tr"] = { "Turkish", 256, "trk-ogz", "Latn", ancestors = "ota", dotted_dotless_i = true, sort_key = { from = { -- Ignore circumflex, but account for capital Î wrongly becoming ı + circ due to dotted dotless I logic. "ı" .. c.circ, c.circ, "i", -- Ensure "i" comes after "ı". "ç", "ğ", "ı", "ö", "ş", "ü" }, to = { "i", "", "i" .. p[1], "c" .. p[1], "g" .. p[1], "i", "o" .. p[1], "s" .. p[1], "u" .. p[1] } }, standard_chars = "AaÂâBbCcÇçDdEeFfGgĞğHhIıİiÎîJjKkLlMmNnOoÖöPpRrSsŞşTtUuÛûÜüVvYyZz" .. c.punc, } m["ts"] = { "Tsonga", 34327, "bnt-tsr", "Latn", } m["tt"] = { "Tatar", 25285, "trk-kbu", "Cyrl, Latn, tt-Arab", translit = { Cyrl = "tt-translit", ["tt-Arab"] = "tt-translit" }, --override_translit = true, -- enable override until Module code can detect Russian loans such as [[аэропорт]] dotted_dotless_i = true, sort_key = { Cyrl = { from = {"ә", "ў", "ғ", "ё", "җ", "қ", "ң", "ө", "ү", "һ"}, to = {"а" .. p[1], "в" .. p[1], "г" .. p[1], "е" .. p[1], "ж" .. p[1], "к" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1], "х" .. p[1]} }, Latn = { from = { "i", -- Ensure "i" comes after "ı". "ä", "ə", "ç", "ğ", "ı", "ñ", "ŋ", "ö", "ɵ", "ş", "ü" }, to = { "i" .. p[1], "a" .. p[1], "a" .. p[2], "c" .. p[1], "g" .. p[1], "i", "n" .. p[1], "n" .. p[2], "o" .. p[1], "o" .. p[2], "s" .. p[1], "u" .. p[1] } }, }, } -- "tw" is treated as "ak", see [[WT:LT]] m["ty"] = { "Tahitian", 34128, "poz-pep", "Latn", } m["ug"] = { "Uyghur", 13263, "trk-kar", "ug-Arab, Latn, Cyrl", ancestors = "chg", translit = { ["ug-Arab"] = "ug-translit", Cyrl = "ug-translit", }, override_translit = true, } m["uk"] = { "Ukrainian", 8798, "zle", "Cyrl", ancestors = "zle-muk", translit = "uk-translit", strip_diacritics = {remove_diacritics = c.grave .. c.acute}, sort_key = { remove_diacritics = c.grave .. c.acute, from = { "ї", -- 2 chars "ґ", "є", "і" -- 1 char }, to = { "и" .. p[2], "г" .. p[1], "е" .. p[1], "и" .. p[1] } }, standard_chars = "АаБбВвГгДдЕеЄєЖжЗзИиІіЇїЙйКкЛлМмНнОоПпРрСсТтУуФфХхЦцЧчШшЩщЬьЮюЯя" .. c.punc:gsub("'", ""), -- Exclude apostrophe. } m["ur"] = { "Urdu", 1617, "inc-hnd", "ur-Arab, Hebr", translit = { ["ur-Arab"] = "ur-translit" }, strip_diacritics = { ["ur-Arab"] = { -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه"; hamzatu l-waṣli to a regular alif from = {"هٔ", "ۂ", "ٱ"}, to = {"ہ", "ہ", "ا"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef }, }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] standard_chars = { ["ur-Arab"] = "ایببپتثجچحخدذرزژسشصضطظعغفقکگلࣇڷمنݨوؤہھئٹڈڑآے", c.punc, }, } m["uz"] = { "Uzbek", 9264, "trk-kar", "Latn, Cyrl, fa-Arab", ancestors = "chg", translit = { Cyrl = "uz-translit" }, sort_key = { Latn = { from = {"oʻ", "gʻ", "sh", "ch", "ng"}, to = {"z" .. p[1], "z" .. p[2], "z" .. p[3], "z" .. p[4], "z" .. p[5]} }, Cyrl = { from = {"ё", "ў", "қ", "ғ", "ҳ"}, to = {"е" .. p[1], "я" .. p[1], "я" .. p[2], "я" .. p[3], "я" .. p[4]} }, }, strip_diacritics = { ["fa-Arab"] = "ar-stripdiacritics", }, } m["ve"] = { "Venda", 32704, "bnt-bso", "Latn", } m["vi"] = { "Vietnamese", 9199, "mkh-vie", "Latn, Hani", ancestors = "mkh-mvi", sort_key = { Latn = "vi-sortkey", Hani = "Hani-sortkey", }, } m["vo"] = { "Volapük", 36986, "art", "Latn", } m["wa"] = { "Walloon", 34219, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["wo"] = { "Wolof", 34257, "alv-fwo", "Latn, Arab, Gara", } m["xh"] = { "Xhosa", 13218, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } m["yi"] = { "Yiddish", 8641, "gmw-hgm", "Hebr, Latn", ancestors = "gmh", translit = { Hebr = "yi-translit", }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["yo"] = { "Yoruba", 34311, "alv-yor", "Latn, Arab", strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.macron} }, sort_key = { Latn = { from = {"ẹ", "ɛ", "gb", "ị", "kp", "ọ", "ɔ", "ṣ", "sh", "ụ"}, to = {"e" .. p[1], "e" .. p[1], "g" .. p[1], "i" .. p[1], "k" .. p[1], "o" .. p[1], "o" .. p[1], "s" .. p[1], "s" .. p[1], "u" .. p[1]} }, }, } m["za"] = { "Zhuang", 13216, "tai", "Latn, Hani", sort_key = { Latn = "za-sortkey", Hani = "Hani-sortkey", }, } m["zh"] = { "Chinese", 7850, "zhx", "Hants, Latn, Bopo, Nshu, Brai", ancestors = "ltc", generate_forms = "zh-generateforms", translit = { Hani = "zh-translit", Bopo = "zh-translit", }, sort_key = { Hani = "Hani-sortkey" }, } m["zu"] = { "Zulu", 10179, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.macron .. c.caron}, } return require("Module:languages").finalizeData(m, "language") gx8qxn372mvflpjmn7xexq2a14xa89o 828 5961 17397 2026-07-13T08:17:09Z Hiyuune 6766 + 17397 Scribunto text/plain local export = {} local families_by_name_module = "Module:families/canonical names" local families_data_module = "Module:families/data" local json_module = "Module:JSON" local language_like_module = "Module:language-like" local languages_module = "Module:languages" local load_module = "Module:load" local table_module = "Module:table" local get_by_code -- Defined below. local gmatch = string.gmatch local insert = table.insert local ipairs = ipairs local make_object -- Defined below. local pairs = pairs local require = require local setmetatable = setmetatable local type = type --[==[ Loaders for functions in other modules, which overwrite themselves with the target function when called. This ensures modules are only loaded when needed, retains the speed/convenience of locally-declared pre-loaded functions, and has no overhead after the first call, since the target functions are called directly in any subsequent calls.]==] local function category_name_has_suffix(...) category_name_has_suffix = require(language_like_module).categoryNameHasSuffix return category_name_has_suffix(...) end local function category_name_to_code(...) category_name_to_code = require(language_like_module).categoryNameToCode return category_name_to_code(...) end local function deep_copy(...) deep_copy = require(table_module).deepCopy return deep_copy(...) end local function get_lang(...) get_lang = require(languages_module).getByCode return get_lang(...) end local function keys_to_list(...) keys_to_list = require(table_module).keysToList return keys_to_list(...) end local function load_data(...) load_data = require(load_module).load_data return load_data(...) end local function make_lang_object(...) make_lang_object = require(languages_module).makeObject return make_lang_object(...) end local function to_json(...) to_json = require(json_module).toJSON return to_json(...) end --[==[ Loaders for objects, which load data (or some other object) into some variable, which can then be accessed as "foo or get_foo()", where the function get_foo sets the object to "foo" and then returns it. This ensures they are only loaded when needed, and avoids the need to check for the existence of the object each time, since once "foo" has been set, "get_foo" will not be called again.]==] local families_by_name local function get_families_by_name() families_by_name, get_families_by_name = load_data(families_by_name_module), nil return families_by_name end local families_data local function get_families_data() families_data, get_families_data = load_data(families_data_module), nil return families_data end local families_suffixes local function get_families_suffixes() families_suffixes, get_families_suffixes = { "languages", "lects" }, nil return families_suffixes end local Family = {} Family.__index = Family --[==[ Return the family code of the family, e.g. {"ine"} for the Indo-European languages. ]==] function Family:getCode() return self._code end --[==[ Return the canonical name of the family. This is the name used to represent that language family on Wiktionary, and is guaranteed to be unique to that family alone. Example: {"Indo-European"} for the Indo-European languages. ]==] function Family:getCanonicalName() local name = self._name if name == nil then name = self._data[1] self._name = name end return name end --[==[ Return the display form of the family. For families, this is usually the same as the value returned by {getCategoryName("nocap")}, i.e. it reads <code>"<var>name</var> languages"</code> (e.g. {"Indo-Iranian languages"}). For full and etymology-only languages, this is the same as the canonical name, and for scripts, it reads <code>"<var>name</var> script"</code> (e.g. {"Arabic script"}). The displayed text used in {makeCategoryLink()} is always the same as the display form. ]==] function Family:getDisplayForm() local name = self._data[1] if category_name_has_suffix(name, families_suffixes or get_families_suffixes()) then name = name .. " languages" end return name end function Family:getAliases() Family.getAliases = require(language_like_module).getAliases return self:getAliases() end function Family:getVarieties(flatten) Family.getVarieties = require(language_like_module).getVarieties return self:getVarieties(flatten) end function Family:getOtherNames() Family.getOtherNames = require(language_like_module).getOtherNames return self:getOtherNames() end function Family:getAllNames() Family.getAllNames = require(language_like_module).getAllNames return self:getAllNames() end --[==[Returns a table of types as a lookup table (with the types as keys). The possible types are * {family}: This object is a family. * {full}: This object is a "full" family. This includes all families but a couple of etymology-only families for Old and Middle Iranian languages. * {etymology-only}: This object is an etymology-only family, similar to etymology-only languages. There are currently only two such families, for Old Iranian languages and Middle Iranian languages (which do not represent proper clades and have no proto-languages, hence cannot be full families). ]==] function Family:getTypes() local types = self._types if types == nil then types = {family = true} if self:getFullCode() == self:getCode() then types.full = true else types["etymology-only"] = true end local rawtypes = self._data.type if rawtypes then for t in gmatch(rawtypes, "[^,]+") do types[t] = true end end self._types = types end return types end --[==[Given a list of types as strings, returns true if the family has all of them.]==] function Family:hasType(...) Family.hasType = require(language_like_module).hasType return self:hasType(...) end --[==[Returns a {Family} object for the superfamily that the family belongs to.]==] function Family:getFamily() if self._familyObject == nil then local familyCode = self:getFamilyCode() if familyCode then self._familyObject = get_by_code(familyCode) else self._familyObject = false end end return self._familyObject or nil end --[==[Returns the code of the family's superfamily.]==] function Family:getFamilyCode() if not self._familyCode then self._familyCode = self._data[3] end return self._familyCode end --[==[Returns the canonical name of the family's superfamily.]==] function Family:getFamilyName() if self._familyName == nil then local family = self:getFamily() if family then self._familyName = family:getCanonicalName() else self._familyName = false end end return self._familyName or nil end --[==[Check whether the family belongs to {superfamily} (which can be a family code or object), and returns a boolean. If more than one is given, returns {true} if the family belongs to any of them. A family is '''not''' considered to belong to itself.]==] function Family:inFamily(...) for _, superfamily in ipairs{...} do if type(superfamily) == "table" then superfamily = superfamily:getCode() end local family, code = self:getFamily() while family do code = family:getCode() if code == superfamily then return true end family = family:getFamily() -- If family is parent to itself, return false. if family and family:getCode() == code then return false end end return false end end function Family:getParent() if self._parentObject == nil then local parentCode = self:getParentCode() if parentCode then self._parentObject = get_lang(parentCode, nil, true, true) else self._parentObject = false end end return self._parentObject or nil end function Family:getParentCode() if not self._parentCode then self._parentCode = self._data.parent end return self._parentCode end function Family:getParentName() if self._parentName == nil then local parent = self:getParent() if parent then self._parentName = parent:getCanonicalName() else self._parentName = false end end return self._parentName or nil end function Family:getParentChain() if not self._parentChain then self._parentChain = {} local parent = self:getParent() while parent do insert(self._parentChain, parent) parent = parent:getParent() end end return self._parentChain end function Family:hasParent(...) --checkObject("family", nil, ...) for _, other_family in ipairs{...} do for _, parent in ipairs(self:getParentChain()) do if type(other_family) == "string" then if other_family == parent:getCode() then return true end else if other_family:getCode() == parent:getCode() then return true end end end end return false end --[==[ If the family is etymology-only, this iterates through its parents until a full family is found, and the corresponding object is returned. If the family is a full family, then it simply returns itself. ]==] function Family:getFull() if not self._fullObject then local fullCode = self:getFullCode() if fullCode ~= self:getCode() then self._fullObject = get_lang(fullCode, nil, nil, true) else self._fullObject = self end end return self._fullObject end --[==[ If the family is etymology-only, this iterates through its parents until a full family is found, and the corresponding code is returned. If the family is a full family, then it simply returns the family code. ]==] function Family:getFullCode() return self._fullCode or self:getCode() end --[==[ If the family is etymology-only, this iterates through its parents until a full family is found, and the corresponding canonical name is returned. If the family is a full family, then it simply returns the canonical name of the family. ]==] function Family:getFullName() if self._fullName == nil then local full = self:getFull() if full then self._fullName = full:getCanonicalName() else self._fullName = false end end return self._fullName or nil end --[==[ Return a {Language} object (see [[Module:languages]]) for the proto-language of this family, if one exists. Otherwise, return {nil}. ]==] function Family:getProtoLanguage() if self._protoLanguageObject == nil then self._protoLanguageObject = get_lang(self._data.protoLanguage or self:getCode() .. "-pro", nil, true) or false end return self._protoLanguageObject or nil end function Family:getProtoLanguageCode() if self._protoLanguageCode == nil then local protoLanguage = self:getProtoLanguage() self._protoLanguageCode = protoLanguage and protoLanguage:getCode() or false end return self._protoLanguageCode or nil end function Family:getProtoLanguageName() if not self._protoLanguageName then self._protoLanguageName = self:getProtoLanguage():getCanonicalName() end return self._protoLanguageName end function Family:hasAncestor(...) -- Go up the family tree until a protolanguage is found. local family = self local protolang = family:getProtoLanguage() while not protolang do family = family:getFamily() protolang = family:getProtoLanguage() -- Return false if the family is its own family, to avoid an infinite loop. if family:getFamilyCode() == family:getCode() then return false end end -- If the protolanguage is not in the family, it must therefore be ancestral to it. Check if it is a match. for _, otherlang in ipairs{...} do if ( type(otherlang) == "string" and protolang:getCode() == otherlang or type(otherlang) == "table" and protolang:getCode() == otherlang:getCode() ) and not protolang:inFamily(self) then return true end end -- If not, check the protolanguage's ancestry. return protolang:hasAncestor(...) end local function fetch_descendants(self, format) local languages = require("Module:languages/code to canonical name") local etymology_languages = require("Module:etymology languages/code to canonical name") local families = require("Module:families/code to canonical name") local descendants = {} -- Iterate over all three datasets. for _, data in ipairs{languages, etymology_languages, families} do for code in pairs(data) do local lang = get_lang(code, nil, true, true) if lang:inFamily(self) then if format == "object" then insert(descendants, lang) elseif format == "code" then insert(descendants, code) elseif format == "name" then insert(descendants, lang:getCanonicalName()) end end end end return descendants end function Family:getDescendants() if not self._descendantObjects then self._descendantObjects = fetch_descendants(self, "object") end return self._descendantObjects end function Family:getDescendantCodes() if not self._descendantCodes then self._descendantCodes = fetch_descendants(self, "code") end return self._descendantCodes end function Family:getDescendantNames() if not self._descendantNames then self._descendantNames = fetch_descendants(self, "name") end return self._descendantNames end function Family:hasDescendant(...) for _, lang in ipairs{...} do if type(lang) == "string" then lang = get_lang(lang, nil, true) end if lang:inFamily(self) then return true end end return false end --[==[ Return the name of the main category of that family. Example: {"Germanic languages"} for the Germanic languages, whose category is at [[:Category:Germanic languages]]. Unless optional argument `nocap` is given, the family name at the beginning of the returned value will be capitalized. This capitalization is correct for category names, but not if the family name is lowercase and the returned value of this function is used in the middle of a sentence. (For example, the pseudo-family with the code {qfa-mix} has the name {"mixed"}, which should remain lowercase when used as part of the category name [[:Category:Terms derived from mixed languages]] but should be capitalized in [[:Category:Mixed languages]].) If you are considering using {getCategoryName("nocap")}, use {getDisplayForm()} instead. ]==] function Family:getCategoryName(nocap) local name = self._data.categoryName or self:getDisplayForm() if not nocap then name = mw.getContentLanguage():ucfirst(name) end return name end function Family:makeCategoryLink() return "[[:Category:" .. self:getCategoryName() .. "|" .. self:getDisplayForm() .. "]]" end --[==[Returns the Wikidata item id for the family or <code>nil</code>. This corresponds to the the second field in the data modules.]==] function Family:getWikidataItem() Family.getWikidataItem = require(language_like_module).getWikidataItem return self:getWikidataItem() end --[==[ Returns the name of the Wikipedia article for the family. `project` specifies the language and project to retrieve the article from, defaulting to {"enwiki"} for the English Wikipedia. Normally if specified it should be the project code for a specific-language Wikipedia e.g. "zhwiki" for the Chinese Wikipedia, but it can be any project, including non-Wikipedia ones. If the project is the English Wikipedia and the property {wikipedia_article} is present in the data module it will be used first. In all other cases, a sitelink will be generated from {:getWikidataItem} (if set). The resulting value (or lack of value) is cached so that subsequent calls are fast. If no value could be determined, and `noCategoryFallback` is {false}, {:getCategoryName} is used as fallback; otherwise, {nil} is returned. Note that if `noCategoryFallback` is {nil} or omitted, it defaults to {false} if the project is the English Wikipedia, otherwise to {true}. In other words, under normal circumstances, if the English Wikipedia article couldn't be retrieved, the return value will fall back to a link to the family's category, but this won't normally happen for any other project. ]==] function Family:getWikipediaArticle(noCategoryFallback, project) Family.getWikipediaArticle = require(language_like_module).getWikipediaArticle return self:getWikipediaArticle(noCategoryFallback, project) end function Family:makeWikipediaLink() return "[[w:" .. self:getWikipediaArticle() .. "|" .. self:getCanonicalName() .. "]]" end --[==[Returns the name of the Wikimedia Commons category page for the family.]==] function Family:getCommonsCategory() Family.getCommonsCategory = require(language_like_module).getCommonsCategory return self:getCommonsCategory() end function Family:toJSON(opts) local ret = { canonicalName = self:getCanonicalName(), categoryName = self:getCategoryName("nocap"), code = self:getCode(), parent = self:getParentCode(), full = self:getFullCode(), family = self:getFamilyCode(), protoLanguage = self:getProtoLanguageCode(), aliases = self:getAliases(), varieties = self:getVarieties(), otherNames = self:getOtherNames(), type = keys_to_list(self:getTypes()), wikidataItem = self:getWikidataItem(), wikipediaArticle = self:getWikipediaArticle(true), } -- Use `deep_copy` when returning a table, so that there are no editing restrictions imposed by `mw.loadData`. return opts and opts.lua_table and deep_copy(ret) or to_json(ret, opts) end function Family:getData() return self._data end function export.makeObject(code, data) local data_type = type(data) if data_type ~= "table" then error(("bad argument #2 to 'makeObject' (table expected, got %s)"):format(data_type)) end return setmetatable({_data = data, _code = code, _fullCode = code}, Family) end make_object = export.makeObject --[==[ Finds the family whose code matches the one provided. If it exists, it returns a {Family} object representing the family. Otherwise, it returns {nil}.]==] function export.getByCode(code) local data = (families_data or get_families_data())[code] if data == nil then return nil elseif data.parent == nil then return make_object(code, data) end return make_lang_object(code, data) end get_by_code = export.getByCode --[==[ Look for the family whose canonical name (the name used to represent that family on Wiktionary) matches the one provided. If it exists, it returns a {Family} object representing the family. Otherwise, it returns {nil}. The canonical name of families should always be unique (it is an error for two families on Wiktionary to share the same canonical name), so this is guaranteed to give at most one result.]==] function export.getByCanonicalName(name) if name == nil then return nil end local code = (families_by_name or get_families_by_name())[name] if code == nil then return nil end return get_by_code(code) end --[==[ Look for the family whose category name (the name used in categories for that family) matches the one provided. If it exists, it returns a {Family} object representing the family. Otherwise, it returns {nil}. In almost all cases, the category name for a family is its canonical name plus the word "languages", e.g. "Indo-European" has the category name "Indo-European languages". Where a canonical name ends with "languages" or "lects", the category name is identical to the canonical name.]==] function export.getByCategoryName(name) if name == nil then return nil end local code = category_name_to_code( name, " languages", families_by_name or get_families_by_name(), families_suffixes or get_families_suffixes() ) if code == nil then return nil end return get_by_code(code) end return export lbb6204ki1w17483059izgsyw1n271z 828 5962 17398 2026-07-13T08:17:49Z Hiyuune 6766 + 17398 Scribunto text/plain --[=[ This module contains definitions for all language family codes on Wiktionary. ]=]-- local m = {} m["aav"] = { "Austroasiatic", 33199, aliases = {"Austro-Asiatic"}, } m["aav-khs"] = { "Khasian", 3073734, "aav", aliases = {"Khasic"}, } m["aav-nic"] = { "Nicobarese", 217380, "aav", } m["aav-pkl"] = { "Pnar-Khasi-Lyngngam", nil, "aav-khs", } m["afa"] = { "Afroasiatic", 25268, aliases = {"Afro-Asiatic"}, } m["alg"] = { "Algonquian", 33392, "aql", } m["alg-abp"] = { "Abenaki-Penobscot", 197936, "alg-eas", } m["alg-ara"] = { "Arapahoan", 2153686, "alg", } m["alg-eas"] = { "Eastern Algonquian", 2257525, "alg", } m["alg-sfk"] = { "Sac-Fox-Kickapoo", 1440172, "alg", } m["alv"] = { "Atlantic-Congo", 771124, "nic", } m["alv-aah"] = { "Ayere-Ahan", 750953, "alv-von", } m["alv-ada"] = { "Adamawa", 32906, "alv-sav", } m["alv-bag"] = { "Baga", 2746083, "alv-mel", } m["alv-bak"] = { "Bak", 1708174, "alv-sng", } m["alv-bam"] = { "Bambukic", 4853456, "alv-ada", aliases = {"Yungur-Jen"}, } m["alv-bny"] = { "Banyum", 2892477, "alv-nyn", } m["alv-bua"] = { "Bua", 4982094, "alv-mbd", } m["alv-bwj"] = { "Bikwin-Jen", 84542501, "alv-bam", } m["alv-cng"] = { "Cangin", 1033184, "alv-fwo", } m["alv-ctn"] = { "Central Tano", 1658486, "alv-ptn", aliases = {"Akan"}, } m["alv-dlt"] = { "Delta Edoid", nil, "alv-edo", } m["alv-dur"] = { "Duru", 5316788, "alv-lni", } m["alv-ede"] = { "Ede", 35368, "alv-yor", } m["alv-edk"] = { "Edekiri", 5336735, "alv-yrd", } m["alv-edo"] = { "Edoid", 1287469, "alv-von", } m["alv-eeo"] = { "Edo-Esan-Ora", 12630439, "alv-nce", } m["alv-fli"] = { "Fali", 3450166, "alv", } m["alv-fwo"] = { "Fula-Wolof", 12631267, "alv-sng", } m["alv-gbe"] = { "Gbe", 668284, "alv-von", } m["alv-gda"] = { "Ga-Dangme", 3443338, "alv-kwa", } m["alv-gng"] = { "Guang", 684009, "alv-ptn", } m["alv-gtm"] = { "Ghana-Togo Mountain", 493020, "alv-kwa", aliases = {"Togo Remnant", "Central Togo"}, } m["alv-hei"] = { "Heiban", 108752116, "alv-the", } m["alv-ido"] = { "Idomoid", 974196, "alv-von", } m["alv-igb"] = { "Igboid", 1429100, "alv-von", } m["alv-jfe"] = { "Jola-Felupe", 1708174, "alv-jol", aliases = {"Ejamat"}, } m["alv-jol"] = { "Jola", 35176, "alv-bak", aliases = {"Diola"}, } m["alv-kim"] = { "Kim", 6409701, "alv-mbd", } m["alv-kis"] = { "Kissi", 35696, "alv-mel", } m["alv-krb"] = { "Karaboro", 4213541, "alv-snf", } m["alv-ktg"] = { "Ka-Togo", 5972796, "alv-gtm", } m["alv-kul"] = { "Kulango", 16977424, "alv-sav", aliases = {"Kulango-Lorhon", "Kulango-Lorom"}, } m["alv-kwa"] = { "Kwa", 33430, "nic-vco", } m["alv-lag"] = { "Lagoon", 111210042, "alv-kwa", } m["alv-lek"] = { "Leko", 6520642, other_names = {"Sambaic"}, -- appears to be an alias in Glottolog "alv-lni", } m["alv-lim"] = { "Limba", 35825, "alv", } m["alv-lni"] = { "Leko-Nimbari", 1708170, "alv-ada", other_names = {"Central Adamawa"}, aliases = {"Chamba-Mumuye"}, } m["alv-mbd"] = { "Mbum-Day", 6799816, "alv-ada", } m["alv-mbm"] = { "Mbum", 6799814, "alv-mbd", } m["alv-mel"] = { "Mel", 12122355, "alv", } m["alv-mum"] = { "Mumuye", 84607009, "alv-mye", } m["alv-mye"] = { "Mumuye-Yendang", 6935539, "alv-lni", } m["alv-nal"] = { "Nalu", nil, "alv-sng", } m["alv-nce"] = { "North-Central Edoid", 16110869, "alv-edo", } m["alv-ngb"] = { "Nupe-Gbagyi", 12638649, "alv-nup", aliases = {"Nupe-Gbari"}, } m["alv-ntg"] = { "Na-Togo", nil, "alv-gtm", } m["alv-nup"] = { "Nupoid", 1429143, "alv-von", } m["alv-nwd"] = { "Northwestern Edoid", 16111012, "alv-edo", } m["alv-nyn"] = { "Nyun", nil, "alv-fwo", } m["alv-pap"] = { "Papel", 7132562, "alv-bak", } m["alv-pph"] = { "Phla-Pherá", 3849625, "alv-gbe", } m["alv-ptn"] = { "Potou-Tano", 1475003, "alv-kwa", } m["alv-sav"] = { "Savanna", 4403672, "nic-vco", aliases = {"Savannas"}, } m["alv-sma"] = { "Supyire-Mamara", 4446348, "alv-snf", aliases = {"Suppire-Mamara"}, } m["alv-snf"] = { "Senufo", 33795, "alv", aliases = {"Senufic", "Senoufo", "Sénoufo"}, } m["alv-sng"] = { "Senegambian", 1708753, "alv", } m["alv-snr"] = { "Senari", 4416084, "alv-snf", } m["alv-swd"] = { "Southwestern Edoid", 12633903, "alv-edo", } m["alv-tal"] = { "Talodi", 12643302, "alv-the", } m["alv-tdj"] = { "Tagwana-Djimini", 7675362, "alv-snf", } m["alv-ten"] = { "Tenda", 3217535, "alv-fwo", } m["alv-the"] = { "Talodi-Heiban", 1521145, "alv", } m["alv-von"] = { "Volta-Niger", 34177, "nic-vco", } m["alv-wan"] = { "Wara-Natyoro", 7968830, "alv-sav", } m["alv-wjk"] = { "Waja-Kam", nil, "alv-ada", } m["alv-yek"] = { "Yekhee", nil, "alv-nce", } m["alv-yor"] = { "Yoruba", nil, "alv-edk", } m["alv-yrd"] = { "Yoruboid", 1789745, "alv-von", } m["alv-yun"] = { "Yungur", 84601642, "alv-bam", aliases = {"Bena-Mboi"}, } m["apa"] = { "Apachean", 27758, "ath", aliases = {"Southern Athabaskan"}, } m["aqa"] = { "Alacalufan", 1288430, } m["aql"] = { "Algic", 721612, aliases = {"Algonquian-Ritwan", "Algonquian-Wiyot-Yurok"}, } m["art"] = { "constructed", 33215, "qfa-not", aliases = {"artificial", "planned"}, } m["ath"] = { "Athabaskan", 27475, "xnd", } m["ath-nor"] = { "North Athabaskan", 20738, "ath", aliases = {"Northern Athabaskan"}, } m["ath-pco"] = { "Pacific Coast Athabaskan", 20654, "ath", } m["auf"] = { "Arauan", 626772, aliases = {"Arahuan", "Arauán", "Arawa", "Arawan", "Arawán"}, } --[=[ Exceptional language and family codes for Australian Aboriginal languages can use the prefix "aus-", though "aus" is no longer itself a family code. ]=]-- m["aus-arn"] = { "Arnhem", 2581700, aliases = {"Gunwinyguan", "Macro-Gunwinyguan"}, } m["aus-bub"] = { "Bunuban", 2495148, aliases = {"Bunaban"}, } m["aus-cww"] = { "Central New South Wales", 5061507, "aus-pam", } m["aus-dal"] = { "Daly", 2478079, } m["aus-dyb"] = { "Dyirbalic", 1850666, "aus-pam", } m["aus-gar"] = { "Garawan", 5521951, } m["aus-gun"] = { "Gunwinyguan", 2581700, "aus-arn", aliases = {"Gunwingguan"}, } m["aus-jar"] = { "Jarrakan", 2039423, } m["aus-kar"] = { "Karnic", 4215578, "aus-pam", } m["aus-mir"] = { "Mirndi", 4294095, } m["aus-nga"] = { "Ngayarda", 16153490, "aus-psw", } m["aus-nyu"] = { "Nyulnyulan", 2039408, } m["aus-pam"] = { "Pama-Nyungan", 33942, } m["aus-pmn"] = { "Paman", 2640654, "aus-pam", } m["aus-psw"] = { "Southwest Pama-Nyungan", 2258160, "aus-pam", } m["aus-rnd"] = { "Arandic", 4784071, "aus-pam", } m["aus-tnk"] = { "Tangkic", 1823065, } m["aus-wdj"] = { "Iwaidjan", 4196968, aliases = {"Yiwaidjan"}, } m["aus-wor"] = { "Worrorran", 2038619, } m["aus-yid"] = { "Yidinyic", 4205849, "aus-pam", } m["aus-yng"] = { "Yangmanic", 42727644, } m["aus-yol"] = { "Yolngu", 2511254, "aus-pam", aliases = {"Yolŋu", "Yolngu Matha"}, } m["aus-yuk"] = { "Yuin-Kuric", 3833021, "aus-pam", } m["awd"] = { "Arawak", 626753, aliases = {"Arawakan", "Maipurean", "Maipuran"}, } m["awd-nwk"] = { "Nawiki", nil, "awd", aliases = {"Newiki"}, } m["awd-taa"] = { "Ta-Arawak", 7672731, "awd", aliases = {"Ta-Arawakan", "Ta-Maipurean"}, } m["azc"] = { "Uto-Aztecan", 34073, aliases = {"Uto-Aztekan"}, } m["azc-cup"] = { "Cupan", 19866871, "azc-tak", } m["azc-dur"] = { "Durango Nahuatl", 2386361, "azc-nah", aliases = {"Mexicanero"} } m["azc-hua"] = { "Huasteca Nahuatl", 3832950, "azc-nah", } m["azc-nah"] = { "Nahuan", 11965602, "azc", aliases = {"Aztecan"}, } m["azc-num"] = { "Numic", 2657541, "azc", } m["azc-pim"] = { "Piman", 7194600, "azc", aliases = {"Tepiman"}, } m["azc-tak"] = { "Takic", 1280305, "azc", } m["azc-trc"] = { "Taracahitic", 4245032, "azc", aliases = {"Taracahitan"}, } m["bad"] = { "Banda", 806234, "nic-ubg", } m["bad-cnt"] = { "Central Banda", 3438391, "bad", } m["bai"] = { "Bamileke", 806005, "nic-gre", } m["bat"] = { "Baltic", 33136, "ine-bsl", } m["bat-eas"] = { "East Baltic", 149944, "bat", } m["bat-wes"] = { "West Baltic", 149946, "bat", } m["ber"] = { "Berber", 25448, "afa", aliases = {"Tamazight"}, } m["bnt"] = { "Bantu", 33146, "nic-bds", } m["bnt-baf"] = { "Bafia", 799784, "bnt", } m["bnt-bbo"] = { "Bafo-Bonkeng", nil, "bnt-saw", } m["bnt-bdz"] = { "Boma-Dzing", 1729203, "bnt", } m["bnt-bek"] = { "Bekwilic", nil, "bnt-ndb", } m["bnt-bki"] = { "Bena-Kinga", 16113307, "bnt-bne", } m["bnt-bmo"] = { "Bangi-Moi", nil, "bnt-bnm", } m["bnt-bne"] = { "Northeast Bantu", 7057832, "bnt", } m["bnt-bnm"] = { "Bangi-Ntomba", 806477, "bnt-bte", } m["bnt-boa"] = { "Boan", 4931250, "bnt", aliases = {"Buan", "Ababuan"}, } m["bnt-bot"] = { "Botatwe", 4948532, "bnt", } m["bnt-bsa"] = { "Basaa", 809739, "bnt", } m["bnt-bsh"] = { "Bushoong", 5001551, "bnt-bte", } m["bnt-bso"] = { "Southern Bantu", 980498, "bnt", } m["bnt-bta"] = { "Bati-Angba", 4869303, "bnt-boa", other_names = {"Late Bomokandian"}, aliases = {"Bwa"}, } m["bnt-btb"] = { "Beti", 35118, "bnt", } m["bnt-bte"] = { "Bangi-Tetela", 4855181, "bnt", } m["bnt-bun"] = { "Buja-Ngombe", 4986733, "bnt-mbb", } m["bnt-chg"] = { "Chaga", 33016, "bnt-cht", } m["bnt-cht"] = { "Chaga-Taita", nil, "bnt-bne", } m["bnt-clu"] = { "Chokwe-Luchazi", 3339273, "bnt", } m["bnt-com"] = { "Comorian", 33077, "bnt-sab", } m["bnt-glb"] = { "Great Lakes Bantu", 5599420, "bnt-bne", } m["bnt-haj"] = { "Haya-Jita", 25502360, "bnt-glb", } m["bnt-kak"] = { "Kako", nil, "bnt-pob", } m["bnt-kav"] = { "Kavango", 116544179, "bnt-ksb", } m["bnt-kbi"] = { "Komo-Bira", 6428591, "bnt-boa", } m["bnt-kel"] = { "Kele", 1738162, "bnt-kts", aliases = {"Sheke"}, } m["bnt-kil"] = { "Kilombero", 6408121, "bnt", } m["bnt-kka"] = { "Kikuyu-Kamba", 16114410, "bnt-bne", aliases = {"Thagiicu"}, } m["bnt-kmb"] = { "Kimbundu", 16947687, "bnt", } m["bnt-kng"] = { "Kongo", 6429214, "bnt", } m["bnt-kpw"] = { "Kpwe", 36428, "bnt-saw", } m["bnt-ksb"] = { "Kavango-Southwest Bantu", 6379098, "bnt", } m["bnt-kts"] = { "Kele-Tsogo", 6385577, "bnt", } m["bnt-lbn"] = { "Luban", 4536504, "bnt", } m["bnt-leb"] = { "Lebonya", 6511395, "bnt", } m["bnt-lgb"] = { "Lega-Binja", 6517694, "bnt", } m["bnt-lok"] = { "Logooli-Kuria", nil, "bnt-glb", } m["bnt-lub"] = { "Luba", nil, "bnt-lbn", } m["bnt-lun"] = { "Lunda", 6704091, "bnt", } m["bnt-mak"] = { "Makua", 6740431, "bnt-bso", aliases = {"Makhuwa"}, } m["bnt-mbb"] = { "Mboshi-Buja", 6799764, "bnt", } m["bnt-mbe"] = { "Mbole-Enya", 6799728, "bnt", } m["bnt-mbi"] = { "Mbinga", nil, "bnt-rur", } m["bnt-mbo"] = { "Mboshi", 6799763, "bnt-mbb", } m["bnt-mbt"] = { "Mbete", 1346910, "bnt-tmb", aliases = {"Mbere"}, } m["bnt-mby"] = { "Mbeya", nil, "bnt-ruk", } m["bnt-mij"] = { "Mijikenda", 6845474, "bnt-sab", } m["bnt-mka"] = { "Makaa", nil, "bnt-ndb", } m["bnt-mne"] = { "Manenguba", 31147471, "bnt", aliases = {"Mbo", "Ngoe"}, } m["bnt-mnj"] = { "Makaa-Njem", 1603899, "bnt-pob", } m["bnt-mon"] = { "Mongo", nil, "bnt-bnm", } m["bnt-mra"] = { "Mbugwe-Rangi", 6799795, "bnt", } m["bnt-msl"] = { "Masaba-Luhya", 12636428, "bnt-glb", } m["bnt-mwi"] = { "Mwika", nil, "bnt-ruk", } m["bnt-ncb"] = { "Northeast Coast Bantu", 7057848, "bnt-bne", } m["bnt-ndb"] = { "Ndzem-Bomwali", nil, "bnt-mnj", } m["bnt-ngn"] = { "Ngondi-Ngiri", 7022532, "bnt-mbb", } m["bnt-ngu"] = { "Nguni", 961559, "bnt-bso", aliases = {"Ngoni"}, } m["bnt-nya"] = { "Nyali", 7070832, "bnt-leb", } m["bnt-nyb"] = { "Nyanga-Buyi", 7070882, "bnt", } m["bnt-nyg"] = { "Nyoro-Ganda", 12638666, "bnt-glb", } m["bnt-nys"] = { "Nyasa", 7070921, "bnt", } m["bnt-nze"] = { "Nzebi", 1755498, "bnt-tmb", aliases = {"Njebi"}, } m["bnt-ova"] = { "Ovambo", 36489, "bnt-swb", aliases = {"Oshivambo", "Oshiwambo", "Owambo"}, } m["bnt-par"] = { "Pare", nil, "bnt-ncb", } m["bnt-pen"] = { "Pende", 7162373, "bnt", } m["bnt-pob"] = { "Pomo-Bomwali", nil, "bnt", } m["bnt-ruk"] = { "Rukwa", 7378902, "bnt", } m["bnt-run"] = { "Rungwe", nil, "bnt-ruk", } m["bnt-rur"] = { "Rufiji-Ruvuma", 7377947, "bnt", } m["bnt-ruv"] = { "Ruvu", nil, "bnt-ncb", } m["bnt-rvm"] = { "Ruvuma", nil, "bnt-rur", } m["bnt-sab"] = { "Sabaki", 2209395, "bnt-ncb", } m["bnt-saw"] = { "Sawabantu", 532003, "bnt", } m["bnt-sbi"] = { "Sabi", 7396071, "bnt", } m["bnt-seu"] = { "Seuta", nil, "bnt-ncb", } m["bnt-shh"] = { "Shi-Havu", nil, "bnt-glb", } m["bnt-sho"] = { "Shona", 2904660, "bnt", } m["bnt-sir"] = { "Sira", 1436372, "bnt", aliases = {"Shira-Punu"}, } m["bnt-ske"] = { "Soko-Kele", nil, "bnt-bte", } m["bnt-sna"] = { "Sena", nil, "bnt-nys", } m["bnt-sts"] = { "Sotho-Tswana", 2038386, "bnt-bso", } m["bnt-swb"] = { "Southwest Bantu", 116543539, "bnt-ksb", } m["bnt-swh"] = { "Swahili", nil, "bnt-sab", } m["bnt-tek"] = { "Teke", 36528, "bnt-tmb", } m["bnt-tet"] = { "Tetela", 7706059, "bnt-bte", } m["bnt-tkc"] = { "Central Teke", 36473, "bnt-tek", } m["bnt-tkm"] = { "Takama", nil, "bnt-bne", } m["bnt-tmb"] = { "Teke-Mbede", 7695332, "bnt", aliases = {"Teke-Mbere"}, } m["bnt-tso"] = { "Tsogo", 2458420, other_names = {"Okani"}, --appears to be an alias in Glottolog "bnt-kts", } m["bnt-tsr"] = { "Tswa-Ronga", 12643962, "bnt-bso", } m["bnt-yak"] = { "Yaka", 8047027, "bnt", } m["bnt-yko"] = { "Yasa-Kombe", nil, "bnt-saw", } m["bnt-zbi"] = { "Zamba-Binza", nil, "bnt-bnm", } m["btk"] = { "Batak", 1998595, "poz-nws", } --[=[ Exceptional language and family codes for Central American Indian languages may use the prefix "cai-", though "cai" is no longer itself a family code. ]=]-- --[=[ Exceptional language and family codes for Caucasian languages can use the prefix "cau-", though "cau" is no longer itself a family code. ]=]-- m["cau-abz"] = { "Abkhaz-Abaza", 4663617, "cau-nwc", other_names = {"Abkhaz-Tapanta"}, aliases = {"Abazgi"}, } m["cau-and"] = { "Andian", 492152, "cau-ava", aliases = {"Andic"}, } m["cau-ava"] = { "Avaro-Andian", 4055404, "cau-nec", aliases = {"Avar-Andian", "Avar-Andi", "Avar-Andic"}, } m["cau-cir"] = { "Circassian", 858543, "cau-nwc", aliases = {"Cherkess"}, } m["cau-drg"] = { "Dargwa", 5222637, "cau-nec", other_names = {"Dargin"}, } m["cau-esm"] = { "Eastern Samur", nil, "cau-sam", } m["cau-ets"] = { "East Tsezian", 121437666, "cau-tsz", aliases = {"East Tsezic", "East Didoic"}, } m["cau-lzg"] = { "Lezghian", 2144370, "cau-nec", aliases = {"Lezgi", "Lezgian", "Lezgic"}, } m["cau-nkh"] = { "Nakh", 24441, "cau-nec", aliases = {"North-Central Caucasian"}, } m["cau-nec"] = { "Northeast Caucasian", 27387, aliases = {"Dagestanian", "Nakho-Dagestanian", "Caspian"}, } m["cau-nwc"] = { "Northwest Caucasian", 33852, aliases = {"Abkhazo-Adyghean", "Abkhaz-Adyghe", "Pontic"}, } m["cau-sam"] = { "Samur", 15229151, "cau-lzg", } m["cau-ssm"] = { "Southern Samur", nil, "cau-sam", } m["cau-tsz"] = { "Tsezian", 1651530, "cau-nec", aliases = {"Tsezic", "Didoic"}, } m["cau-vay"] = { "Vainakh", 4102486, "cau-nkh", aliases = {"Veinakh", "Vaynakh"}, } m["cau-wsm"] = { "Western Samur", nil, "cau-sam", } m["cau-wts"] = { "West Tsezian", 121437697, "cau-tsz", aliases = {"West Tsezic", "West Didoic"}, } m["cba"] = { "Chibchan", 520478, "qfa-mch", -- or none if Macro-Chibchan is considered undemonstrated } m["ccs"] = { "Kartvelian", 34030, aliases = {"South Caucasian"}, } m["ccs-gzn"] = { "Georgian-Zan", 34030, "ccs", aliases = {"Karto-Zan"}, } m["ccs-zan"] = { "Zan", 2606912, "ccs-gzn", aliases = {"Zanuri", "Colchian"}, } m["cdc"] = { "Chadic", 33184, "afa", } m["cdc-cbm"] = { "Central Chadic", 2251547, "cdc", aliases = {"Biu-Mandara"}, } m["cdc-est"] = { "East Chadic", 2276221, "cdc", } m["cdc-mas"] = { "Masa", 2136092, "cdc", } m["cdc-wst"] = { "West Chadic", 2447774, "cdc", } m["cdd"] = { "Caddoan", 1025090, } m["cel"] = { "Celtic", 25293, "ine", } m["cel-bry"] = { "Brythonic", 156877, "cel-ins", aliases = {"Brittonic"}, } m["cel-brs"] = { "Southwestern Brythonic", 2612853, "cel-bry", aliases = {"Southwestern Brittonic"}, } m["cel-brw"] = { "Western Brythonic", 593069, "cel-bry", aliases = {"Western Brittonic"}, } m["cel-gae"] = { "Goidelic", 56433, "cel-ins", aliases = {"Gaelic"}, protoLanguage = "pgl", } m["cel-his"] = { "Hispano-Celtic", 4204136, "cel", } m["cel-ins"] = { "Insular Celtic", 214506, "cel", } m["chi"] = { "Chimakuan", 1073088, } m["chm"] = { "Mari", 973685, "urj", } m["cmc"] = { "Chamic", 2997506, "poz-mcm", } m["crp"] = { "creole or pidgin", 19682167, "qfa-cnt", } m["csu"] = { "Central Sudanic", 190822, "ssa", } m["csu-bba"] = { "Bongo-Bagirmi", 3505042, "csu", } m["csu-bbk"] = { "Bongo-Baka", 4941917, "csu-bba", } m["csu-bgr"] = { "Bagirmi", 4841948, "csu-bba", aliases = {"Bagirmic"}, } m["csu-bkr"] = { "Birri-Kresh", nil, "csu", } m["csu-ecs"] = { "Eastern Central Sudanic", 16911698, "csu", aliases = {"East Central Sudanic", "Central Sudanic East", "Lendu-Mangbetu"}, } m["csu-kab"] = { "Kaba", 6343715, "csu-bba", } m["csu-lnd"] = { "Lendu", 6522357, "csu-ecs", aliases = {"Lenduic"}, } m["csu-maa"] = { "Mangbetu", 6748874, "csu-ecs", aliases = {"Mangbetu-Asoa", "Mangbetu-Asua"}, } m["csu-mle"] = { "Mangbutu-Lese", 17009406, "csu-ecs", aliases = {"Mangbutu-Efe", "Mangbutu", "Membi-Mangbutu-Efe"}, } m["csu-mma"] = { "Moru-Madi", 6915156, "csu-ecs", } m["csu-sar"] = { "Sara", 2036691, "csu-bba", } m["csu-val"] = { "Vale", 7909520, "csu-bba", } m["cus"] = { "Cushitic", 33248, "afa", } m["cus-cen"] = { "Central Cushitic", 56569, "cus", } m["cus-eas"] = { "East Cushitic", 56568, "cus", } m["cus-hec"] = { "Highland East Cushitic", 56524, "cus-eas", } m["cus-som"] = { "Somaloid", 56774, "cus-eas", aliases = {"Sam", "Macro-Somali"}, } m["cus-sou"] = { "South Cushitic", 56525, "cus", } m["day"] = { "Land Dayak", 2760613, "poz", } m["del"] = { "Lenape", 2665761, "alg-eas", aliases = {"Delaware"}, } m["den"] = { "Slavey", 13272, "ath-nor", aliases = {"Slave", "Slavé"}, } m["dmn"] = { "Mande", 33681, "nic", } m["dmn-bbu"] = { "Bisa-Busa", 12627956, "dmn-mde", } m["dmn-emn"] = { "East Manding", nil, "dmn-man", } m["dmn-jje"] = { "Jogo-Jeri", nil, "dmn-mjo", } m["dmn-man"] = { "Manding", 35772, "dmn-mmo", } m["dmn-mda"] = { "Mano-Dan", nil, "dmn-mse", } m["dmn-mdc"] = { "Central Mande", 5972907, "dmn-mdw", } m["dmn-mde"] = { "Eastern Mande", 12633080, "dmn", } m["dmn-mdw"] = { "Western Mande", 16113831, "dmn", } m["dmn-mjo"] = { "Manding-Jogo", 12636153, "dmn-mdc", } m["dmn-mmo"] = { "Manding-Mokole", nil, "dmn-mva", } m["dmn-mnk"] = { "Maninka", 36186, "dmn-emn", } m["dmn-mnw"] = { "Northwestern Mande", 5972910, "dmn-mdw", } m["dmn-mok"] = { "Mokole", 16935447, "dmn-mmo", } m["dmn-mse"] = { "Southeastern Mande", 5972912, "dmn-mde", } m["dmn-msw"] = { "Southwestern Mande", 12633904, "dmn-mdw", } m["dmn-mva"] = { "Manding-Vai", nil, "dmn-mjo", } m["dmn-nbe"] = { "Nwa-Beng", nil, "dmn-mse", } m["dmn-sam"] = { "Samo", 36327, "dmn-bbu", aliases = {"Samuic"}, } m["dmn-smg"] = { "Samogo", 7410000, "dmn-mnw", aliases = {"Duun-Seenku"}, } m["dmn-snb"] = { "Soninke-Bobo", 16111680, "dmn-mnw", } m["dmn-sya"] = { "Susu-Yalunka", nil, "dmn-mdc", } m["dmn-vak"] = { "Vai-Kono", nil, "dmn-mva", } m["dmn-wmn"] = { "West Manding", nil, "dmn-man", } m["dra"] = { "Dravidian", 33311, } m["dra-cen"] = { "Central Dravidian", 12628823, "dra", } m["dra-gki"] = { "Gondi-Kui", 12631610, "dra-sdt", } m["dra-gon"] = { "Gondi", 55639812, "dra-gki", } m["dra-imd"] = { "Irula-Muduga", nil, "dra-tkn", } m["dra-kan"] = { "Kannadoid", 6363888, "dra-tkn", protoLanguage = "dra-okn", } m["dra-kki"] = { "Konda-Kui", nil, "dra-gki", } m["dra-kml"] = { "Kurux-Malto", 68002822, "dra-nor", } m["dra-knk"] = { "Kolami-Naiki", 10547037, "dra-cen", } m["dra-kod"] = { "Kodagu", 67983106, "dra-tkd", } m["dra-kor"] = { "Koraga", 33394, "dra-tlk", } m["dra-mal"] = { "Malayalamoid", 6741581, "dra-tml", } m["dra-mdy"] = { "Madiya", 27602, "dra-gon", } m["dra-mlo"] = { "Malto", nil, "dra-kml", } m["dra-mur"] = { "Muria", 6938499, "dra-gon", } m["dra-nor"] = { "North Dravidian", 16110967, "dra", } m["dra-pgd"] = { "Parji-Gadaba", 10620428, "dra-cen", } m["dra-sdo"] = { "South Dravidian I", 16112843, -- Wikipedia's "South Dravidian" is South Dravidian I in this scheme. "dra-sou", aliases = {"South Dravidian"}, -- This is why I and II are used. } m["dra-sdt"] = { "South Dravidian II", 12633975, "dra-sou", aliases = {"South-Central Dravidian"}, } m["dra-sou"] = { "South Dravidian", 128886618, "dra", aliases = {"Southern Dravidian"}, } m["dra-tam"] = { "Tamiloid", 7681417, "dra-tml", protoLanguage = "oty", } m["dra-tel"] = { "Teluguic", nil, "dra-sdt", protoLanguage = "dra-ote", } m["dra-tkd"] = { "Tamil-Kodagu", 25494510, "dra-tkn", } m["dra-tkn"] = { "Tamil-Kannada", 6478506, "dra-sdo", } m["dra-tkt"] = { "Toda-Kota", 67983857, "dra-tkd", } m["dra-tlk"] = { "Tulu-Koraga", nil, "dra-sdo", } m["dra-tml"] = { "Tamil-Malayalam", 10690507, "dra-tkd", } m["egx"] = { "Egyptian", 50868, "afa", protoLanguage = "egy", } m["ero"] = { "Horpa", 56854, "sit-wgy", } m["esx"] = { "Eskimo-Aleut", 25946, } m["esx-esk"] = { "Eskimo", 25946, "esx", } m["esx-inu"] = { "Inuit", 27796, "esx-esk", } m["euq"] = { "Vasconic", 4669240, } m["gba"] = { "Gbaya", 3099986, "alv-sav", } m["gba-eas"] = { "Eastern Gbaya", nil, "gba", } m["gba-sou"] = { "Southern Gbaya", nil, "gba", } m["gba-wes"] = { "Western Gbaya", nil, "gba", } m["gem"] = { "Germanic", 21200, "ine", } m["gio"] = { "Gelao", 56401, "qfa-kra", } m["gme"] = { "East Germanic", 108662, "gem", } m["gmq"] = { "North Germanic", 106085, "gem", } m["gmq-eas"] = { "East Scandinavian", 3090263, "gmq", protoLanguage = "non-oen", } m["gmq-ins"] = { "Insular Scandinavian", nil, "gmq-wes", } m["gmq-wes"] = { "West Scandinavian", 1792570, "gmq", protoLanguage = "non-own", } m["gmw"] = { "West Germanic", 26721, "gem", } m["gmw-afr"] = { "Anglo-Frisian", 5329170, "gmw-nsg", } m["gmw-ang"] = { "Anglic", 1346342, "gmw-afr", protoLanguage = "ang", } m["gmw-fri"] = { "Frisian", 25325, "gmw-afr", protoLanguage = "ofs", } m["gmw-frk"] = { "Low Franconian", 153050, "gmw", protoLanguage = "frk", } m["gmw-hgm"] = { "High German", 52040, "gmw", protoLanguage = "goh", } m["gmw-ian"] = { "Irish Anglo-Norman", 120719384, "gmw-ang", protoLanguage = "enm", } m["gmw-lgm"] = { "Low German", 25433, "gmw-nsg", protoLanguage = "osx", } m["gmw-nsg"] = { "North Sea Germanic", 30134, "gmw", aliases = {"Ingvaeonic"}, } m["gn"] = { "Guarani", 35876, "tup-gua", aliases = {"Guaraní"}, } m["grb"] = { "Grebo proper", 35257, "kro-grb", } m["grk"] = { "Hellenic", 2042538, "ine-grp", aliases = {"Greek"}, } m["him"] = { "Western Pahari", 10939493, "inc-pah", aliases = {"Himachali"}, } m["hmn"] = { "Hmongic", 3307894, "hmx", } m["hmx"] = { "Hmong-Mien", 33322, aliases = {"Miao-Yao"}, } m["hmx-mie"] = { "Mienic", 7992695, "hmx", } m["hok"] = { "Hokan", 33406, } m["hyx"] = { "Armenian", 8785, "ine", } m["iir"] = { "Indo-Iranian", 33514, "ine", } m["iir-nur"] = { "Nuristani", 161804, "iir", } m["nur-nor"] = { "Northern Nuristani", nil, "iir-nur", } m["nur-sou"] = { "Southern Nuristani", nil, "iir-nur", } m["ijo"] = { "Ijoid", 1325759, "nic", other_names = {"Ijaw"}, -- Ijaw may be a subfamily } m["inc"] = { "Indo-Aryan", 33577, "iir", aliases = {"Indic"}, } m["inc-bas"] = { "Bengali-Assamese", 4179137, "inc-eas", aliases = {"Assamese-Bengali", "Gauda-Kamarupa"}, } m["inc-bhi"] = { "Bhil", 4901727, "inc-cen", } m["inc-bih"] = { "Bihari", 135305, "inc-eas", } m["inc-cen"] = { "Central Indo-Aryan", 10979187, "inc", protoLanguage = "inc-asa", } m["inc-chi"] = { "Chitrali", 11732797, "inc-dar", } m["inc-dar"] = { "Dardic", 161101, "inc", protoLanguage = "inc-ash", } m["inc-dre"] = { "Eastern Dardic", nil, "inc-dar", } m["inc-dng"] = { "Dangari", nil, "inc-shn", } m["inc-eas"] = { "Eastern Indo-Aryan", 12593391, "inc", protoLanguage = "inc-aav", } m["inc-hal"] = { "Halbic", 16910593, "inc-eas", aliases = {"Halbi"}, } m["inc-hie"] = { "Eastern Hindi", 4126648, "inc-cen", aliases = {"Purabiyā"}, protoLanguage = "inc-apa", } m["inc-hiw"] = { "Western Hindi", 12600937, "inc-cen", protoLanguage = "inc-ohi", } m["inc-hnd"] = { "Hindustani", 11051, "inc-hiw", aliases = {"Hindi-Urdu"}, protoLanguage = "hi-mid", } m["inc-ins"] = { "Insular Indo-Aryan", 12179302, "inc", protoLanguage = "inc-apa", } m["inc-kas"] = { "Kashmiric", nil, "inc-dre", aliases = {"Kashmiri"}, } m["inc-koh"] = { "Kohistani", 13018610, "inc-dre", } m["inc-krd"] = { "KRDS languages", 6356154, "inc-eas", aliases = {"Kamta, Rajbanshi, Deshi and Surjapuri", "KRNB languages", "Kamta, Rajbanshi and Northern Deshi Bangla"}, } m["inc-kun"] = { "Kunar", nil, "inc-dar", } m["inc-mid"] = { "Middle Indo-Aryan", 3236316, "inc", aliases = {"Middle Indic"}, } m["inc-nwe"] = { "Northwestern Indo-Aryan", 16111018, "inc", protoLanguage = "inc-apa", } m["inc-nor"] = { "Northern Indo-Aryan", 946077, "inc", protoLanguage = "inc-aka", } m["inc-old"] = { "Old Indo-Aryan", 118976896, "inc", aliases = {"Old Indic"}, } m["inc-pah"] = { "Pahari", 946077, "inc-nor", aliases = {"Pahadi"}, protoLanguage = "inc-aka", } m["inc-pan"] = { "Punjabic", 2656685, "inc-nwe", aliases = {"Greater Punjabic"}, protoLanguage = "inc-opa", } m["inc-pas"] = { "Pashayi", 36670, "inc-dar", aliases = {"Pashai"}, } m["inc-rom"] = { "Romani", 13201, "inc-wes", aliases = {"Romany", "Gypsy", "Gipsy"}, } m["inc-shn"] = { "Shinaic", 12646125, "inc-dre", } m["inc-snd"] = { "Sindhic", 7522212, "inc-nwe", protoLanguage = "inc-avr", } m["inc-sou"] = { "Southern Indo-Aryan", 10856062, "inc", protoLanguage = "inc-ama", } m["inc-tha"] = { "Tharu", 34035, "inc-eas", } m["inc-wes"] = { "Western Indo-Aryan", nil, "inc", protoLanguage = "inc-agu", } m["ine"] = { "Indo-European", 19860, aliases = {"Indo-Germanic"}, } m["ine-ana"] = { "Anatolian", 147085, "ine", } m["ine-bsl"] = { "Balto-Slavic", 147356, "ine", } m["ine-grp"] = { "Graeco-Phrygian", nil, "ine", } m["ine-luw"] = { "Luwic", 115748615, "ine-ana", aliases = {"Luvic"}, } m["ine-toc"] = { "Tocharian", 37029, "ine", aliases = {"Tokharian"}, } m["ira"] = { "Iranian", 33527, "iir", } m["ira-csp"] = { "Caspian", 5049123, "ira-mpr", } m["ira-cen"] = { "Central Iranian", nil, "ira", } m["ira-kms"] = { "Komisenian", nil, "ira-mpr", aliases = {"Semnani"}, } m["ira-mid"] = { "Middle Iranian", 6841465, "ira", } m["ira-mny"] = { "Munji-Yidgha", nil, "ira-sym", aliases = {"Yidgha-Munji"}, } m["ira-msh"] = { "Mazanderani-Shahmirzadi", nil, "ira-csp", } m["ira-nei"] = { "Northeastern Iranian", 10775567, "ira", } m["ira-nwi"] = { "Northwestern Iranian", 390576, "ira-wes", } m["ira-old"] = { "Old Iranian", 23301845, "ira", } m["ira-orp"] = { "Ormuri-Parachi", nil, "ira-sei", } m["ira-pat"] = { "Pathan", nil, "ira-sei", } m["ira-sbc"] = { "Sogdo-Bactrian", nil, "ira-nei", } m["ira-mpr"] = { "Medo-Parthian", nil, "ira-nwi", aliases = {"Partho-Median"}, } m["ira-sgi"] = { "Sanglechi-Ishkashimi", 18711232, "ira-sei", } m["ira-shr"] = { "Shughni-Roshani", 11732824, "ira-shy", } m["ira-shy"] = { "Shughni-Yazghulami", nil, "ira-sym", } m["ira-sgc"] = { "Sogdic", nil, "ira-sbc", aliases = {"Sogdian"}, } m["ira-sei"] = { "Southeastern Iranian", 3833002, "ira", } m["ira-swi"] = { "Southwestern Iranian", 390424, "ira-wes", } m["ira-sym"] = { "Shughni-Yazghulami-Munji", nil, "ira-sei", } m["ira-wes"] = { "Western Iranian", 129850, "ira", } m["ira-zgr"] = { "Zaza-Gorani", 167854, "ira-mpr", aliases = {"Zaza-Gurani", "Gorani-Zaza"}, } m["iro"] = { "Iroquoian", 33623, } m["iro-nor"] = { "North Iroquoian", nil, "iro", } m["itc"] = { "Italic", 131848, "ine", } m["itc-laf"] = { "Latino-Faliscan", 33478, "itc", aliases = {"Latinian"}, } m["itc-sbl"] = { "Osco-Umbrian", 515194, "itc", aliases = {"Sabellic", "Sabellian"}, } m["jpx"] = { "Japonic", 33612, aliases = {"Japanese", "Japanese-Ryukyuan"}, } m["jpx-nry"] = { "Northern Ryukyuan", 20862796, "jpx-ryu", } m["jpx-ryu"] = { "Ryukyuan", 56393, "jpx", } m["jpx-sry"] = { "Southern Ryukyuan", 18392243, "jpx-ryu", } m["kar"] = { "Karen", 1364815, "sit", } m["kca"] = { "Khanty", 33563, "urj-ugr", aliases = {"Khantyic", "Khantic"}, } --[=[ Exceptional language and family codes for Khoisan and Kordofanian languages can use the prefix "khi-" and "kdo-" respectively, though they are no longer family codes themselves. ]=]-- m["khi-kal"] = { "Kalahari Khoe", nil, "khi-kho", } m["khi-khk"] = { "Khoekhoe", nil, "khi-kho", } m["khi-kkw"] = { "Khoe-Kwadi", 60785084, aliases = {"Kwadi-Khoe"}, } m["khi-kho"] = { "Khoe", 2736449, "khi-kkw", aliases = {"Central Khoisan"}, } m["khi-kxa"] = { "Kx'a", 6450587, aliases = {"Kxa", "Ju-ǂHoan"}, } m["khi-tuu"] = { "Tuu", 631046, aliases = {"Kwi", "Taa-Kwi", "Southern Khoisan", "Taa-ǃKwi", "Taa-ǃUi", "ǃUi-Taa"}, } m["kro"] = { "Kru", 33535, "nic-vco", } m["kro-aiz"] = { "Aizi", 4699431, "kro", } m["kro-bet"] = { "Bété", 32956, "kro-ekr", } m["kro-did"] = { "Dida", 32685, "kro-ekr", } m["kro-ekr"] = { "Eastern Kru", 5972899, "kro", } m["kro-grb"] = { "Grebo", 5601537, "kro-wkr", } m["kro-wee"] = { "Wee", nil, "kro-wkr", } m["kro-wkr"] = { "Western Kru", 5972897, "kro", } m["ku"] = { "Kurdish", 36368, "ira-nwi", } m["kv"] = { "Komi", 36126, -- "Komi language" in Wikipedia but refers specifically to Komi-Zyrian; no Wikidata item for Komi family "urj-prm", } m["map"] = { "Austronesian", 49228, } m["map-ata"] = { "Atayalic", 716610, "map", } m["mjg"] = { "Monguor", 34214, "xgn-shr", } m["mkh"] = { "Mon-Khmer", 33199, "aav", } m["mkh-asl"] = { "Aslian", 3111082, "mkh", } m["mkh-ban"] = { "Bahnaric", 56309, "mkh", } m["mkh-kat"] = { "Katuic", 56697, "mkh", } m["mkh-khm"] = { "Khmuic", 1323245, "mkh", } m["mkh-kmr"] = { "Khmeric", nil, "mkh", } m["mkh-mnc"] = { "Monic", 3217497, "mkh", } m["mkh-mng"] = { "Mangic", 3509556, "mkh", } m["mkh-nbn"] = { "North Bahnaric", 56309, "mkh-ban", } m["mkh-pal"] = { "Palaungic", 2391173, "mkh", } m["mkh-pea"] = { "Pearic", 3073022, "mkh", } m["mkh-pkn"] = { "Pakanic", nil, "mkh-mng", } m["mkh-vie"] = { "Vietic", 2355546, "mkh", } m["mno"] = { "Manobo", 3217483, "phi", } m["mns"] = { "Mansi", 33759, "urj-ugr", aliases = {"Mansic"}, } m["mun"] = { "Munda", 33892, "aav", } m["myn"] = { "Mayan", 33738, } --[=[ Exceptional language and family codes for North American Indian languages can use the prefix "nai-", though "nai" is no longer itself a family code. ]=]-- m["nai-cat"] = { "Catawban", 3446638, "nai-sca", } m["nai-chu"] = { "Chumashan", 1288420, } m["nai-ckn"] = { "Chinookan", 610586, } m["nai-coo"] = { "Coosan", 940278, } m["nai-jcq"] = { "Jicaquean", 12179308, "hok" } m["nai-ker"] = { "Keresan", 35878, } m["nai-klp"] = { "Kalapuyan", 1569040, } m["nai-kta"] = { "Kiowa-Tanoan", 386288, } m["nai-len"] = { "Lencan", 36189, aliases = {"Lenca"}, } m["nai-mdu"] = { "Maiduan", 33502, } m["nai-miz"] = { "Mixe-Zoquean", 954016, aliases = {"Mixe-Zoque"}, } m["nai-min"] = { "Misumalpan", 281693, "qfa-mch", aliases = {"Misuluan", "Misumalpa"}, } m["nai-mus"] = { "Muskogean", 902978, aliases = {"Muskhogean"}, } m["nai-pak"] = { "Pakawan", 65085487, "hok", } m["nai-pal"] = { "Palaihnihan", 1288332, } m["nai-plp"] = { "Plateau Penutian", 2307476, } m["nai-pom"] = { "Pomoan", 2618420, "hok", aliases = {"Pomo", "Kulanapan"}, } m["nai-sca"] = { "Siouan-Catawban", 34181, } m["nai-shp"] = { "Sahaptian", 114782, "nai-plp", } m["nai-shs"] = { "Shastan", 2991735, "hok", } m["nai-tot"] = { "Totozoquean", 7828419, } m["nai-ttn"] = { "Totonacan", 34039, aliases = {"Totonac-Tepehua", "Totonacan-Tepehuan"}, varieties = {"Totonac"}, } m["nai-tqn"] = { "Tequistlatecan", 1568317, "hok", aliases = {"Tequistlatec", "Chontal", "Chontalan", "Oaxacan Chontal", "Chontal of Oaxaca"}, } m["nai-tsi"] = { "Tsimshianic", 34134, } m["nai-utn"] = { "Utian", 13371763, "nai-you", aliases = {"Miwok-Costanoan", "Mutsun"}, } m["nai-wtq"] = { "Wintuan", 1294259, aliases = {"Wintun"}, } m["nai-xin"] = { "Xincan", 1546494, aliases = {"Xinca"}, } m["nai-ykn"] = { "Yukian", 2406722, aliases = {"Yuki-Wappo"}, } m["nai-you"] = { "Yok-Utian", 2886186, } m["nai-yuc"] = { "Yuman-Cochimí", 579137, } m["ngf"] = { "Trans-New Guinea", 34018, } m["ngf-ais"] = { "Aisian", nil, "ngf-eso", } m["ngf-ang"] = { "Angan", 3217366, "ngf", aliases = {"Kratke Range"}, -- Usher } m["ngf-ank"] = { "Angal-Kewa", 12626916, -- exist in dewiki and hrwiki "ngf-sak", } m["ngf-ask"] = { "Asmat-Kamoro", 3031400, "ngf", -- Wikipedia uses Asmat-Kamoro to refer to a narrower group excluding the Sabakor languages (Buruwai and Kamberau, -- which Glottolog splits into North Kamrau and South Kamrau [sic]), and uses Asmat-Kamrau to refer to what we and -- Glottolog call Asmat-Kamoro. Glottolog does not recognize the narrower grouping. aliases = {"Asmat-Kamrau", -- Wikipedia "Asmat-Kamrau Bay", -- Usher }, } m["ngf-asm"] = { "Asmat", 4807421, "ngf-ask", } m["ngf-ata"] = { "Ankave-Tainae-Akoye", nil, "ngf-ang", aliases = {"Southwest Kratke Range"}, -- Usher } m["ngf-awd"] = { "Awyu-Dumut", -- [[w:Awyu-Dumut languages]] redirects to [[w:Greater Awyu languages]] 4830163, -- exist in eswiki, hrwiki and ruwiki "ngf-gaw", aliases = {"Central Digul River"}, -- Usher } m["ngf-awy"] = { "Awyu", 96372866, "ngf-awd", } m["ngf-bda"] = { "Becking-Dawi", nil, -- Q55993716 ([[Category:Becking–Dawi languages]]) exists in enwiki "ngf-gaw", aliases = {"Becking and Dawi Rivers"}, -- Usher } m["ngf-bin"] = { "Binanderean", 3217374, -- Wikidata doesn't distinguish Binanderean from Greater Binanderean "ngf-gbi", aliases = {"Oro"}, -- Usher (2020) } m["ngf-boa"] = { "Boane", nil, "ngf-era", aliases = {"Boana", -- Glottolog's name "Wain"}, -- not in Usher; "Wain" often excludes Mungkip, perhaps because it's poorly documented } m["ngf-bos"] = { "Bosavi", 4947122, "ngf", aliases = {"Papuan Plateau"}, -- alternative name given by Wikipedia } m["ngf-bsi"] = { "Baruya-Simbari", nil, "ngf-ang", aliases = {"Northwest Kratke Range"}, -- Usher } m["ngf-cda"] = { "Central Dani", nil, "ngf-dan", aliases = {"Dani"}, -- Usher } m["ngf-chw"] = { "Chimbu-Wahgi", 3217383, "ngf", aliases = {"Simbu-Western Highlands"}, -- alternative name given by Wikipedia } m["ngf-dag"] = { "Dagan", 5208454, "ngf", -- not accepted as TNG by Glottolog but accepted by all others aliases = {"Meneao Range"}, } m["ngf-dal"] = { "Dallman", nil, "ngf-huo", aliases = {"Kinalakna-Kumukio", -- Pawley-Hammarström, who exclude Nomu, but they only had a numeral list of that language to work from "Northeast Huon", -- Usher }, } m["ngf-dan"] = { "Dani", 3217389, "ngf", -- Wikipedia renames the Dani languages to the Baliem Valley languages and sometimes (but not consistently) -- reserves the name Dani (or "Dani proper") for a narrower group excluding Wano and the poorly attested Ngalik -- languages (Nduga, Silimo, and the Yali dialect cluster, which we, following Ethnologue and Glottolog, split into -- Anggurk Yali, Ninia Yali and Pass Valley Yali). Glottolog does not recognize the narrower grouping. aliases = {"Baliem Valley", -- Wikipedia "Balim Valley", -- Usher }, } m["ngf-dum"] = { "Dumut", -- [[w:Dumut languages]] redirects to [[w:Greater Awyu languages]] nil, "ngf-awd", aliases = {"Wambon"}, -- Usher } m["ngf-ehu"] = { "Eastern Huon", -- Glottolog adds Ono and Sialum, Pawley-Hammarström adds Dedua 10567087, "ngf-huo", aliases = {"East Huon"}, -- Usher } m["ngf-eku"] = { "East Kutubuan", 5328752, "ngf", -- Not in TNG per Glottolog but accepted by all others. Sometimes grouped with Fasu to form a Kutubuan family. aliases = {"East Kutubu"}, -- Glottolog's name } m["ngf-enc"] = { "Engic", nil, "ngf-eng", aliases = {"Engan", -- Glottolog "Engan proper", -- Wikipedia "North Engan", -- alternative name given by Wikipedia "Trans-Enga", -- Usher }, } m["ngf-eng"] = { "Engan", 3217449, "ngf", aliases = {"Enga-Kewa-Huli", -- Glottolog, Pawley-Hammarström "Enga-Southern Highlands", -- Usher }, } m["ngf-era"] = { "Erap", nil, "ngf-fin", aliases = {"Erap River"}, -- Usher? } m["ngf-eso"] = { "East Sogeram", nil, "ngf-sog", } m["ngf-est"] = { "East Strickland", 5329440, "ngf", aliases = {"Strickland River"}, -- alternative name given by Wikipedia } m["ngf-eva"] = { "Evapia", nil, "ngf-rai", aliases = {"Evapia River"}, -- Usher } m["ngf-fgi"] = { "Fore-Gimi", nil, "ngf-gor", aliases = {"South Goroka"}, -- Usher } m["ngf-fhu"] = { "Finisterre-Huon", 3217453, "ngf", aliases = {"Finisterre Range-Huon Peninsula"}, -- per Usher } m["ngf-fin"] = { "Finisterre", 5450373, "ngf-fhu", aliases = {"Finisterre-Saruwaged", -- Glottolog's name "Finisterre Range"}, -- per Usher } m["ngf-gah"] = { "Gahuku", nil, "ngf-gor", aliases = {"Alekano-Asaro River"}, -- Usher } m["ngf-gau"] = { "Gauwa", nil, "ngf-kai", aliases = {"West Kainantu"}, -- Usher } m["ngf-gaw"] = { "Greater Awyu", 12627424, "ngf", aliases = {"Digul River"}, -- used by Usher (2020) } m["ngf-gbi"] = { "Greater Binanderean", 3217374, -- Wikidata doesn't distinguish Binanderean from Greater Binanderean "ngf", -- not placed in Trans-New Guinea in Usher (2020) aliases = {"Guhu-Oro"}, -- Guhu-Oro is used in Usher (2020) } m["ngf-gko"] = { "Gaena-Korafe", 11732347, -- considered a single Korafe language by Wikipedia "ngf-bin", aliases = {"Gaina-Korafe"}, -- Usher } m["ngf-gmo"] = { "Gusap-Mot", 16110857, "ngf-fin", aliases = {"Mot River"}, -- Usher? } m["ngf-gor"] = { "Goroka", 15478597, "ngf-kgo", } m["ngf-gsu"] = { "Gogodala-Suki", 5577428, "ngf", -- Possibly in the proposed Papuan Gulf family. Not in TNG per Glottolog but accepted by all others. aliases = {"Suki-Gogodala", -- Glottolog's name "Suki-Aramia River", -- Used in Usher (2020) }, } m["ngf-gum"] = { "Gum", 5618008, "ngf-mab", } m["ngf-gvd"] = { "Grand Valley Dani", -- considered a single language by Wikipedia 5595219, "ngf-cda", } m["ngf-hag"] = { "Hagen", -- [[w:Hagen languages]] redirects to [[w:Chimbu–Wahgi languages]] nil, "ngf-chw", aliases = {"Melpa-Kaugel River"}, -- Usher } m["ngf-han"] = { "Hanseman", 5651020, "ngf-mab", aliases = {"Hansemann Range"}, -- Usher } m["ngf-huo"] = { "Huon", 5946109, "ngf-fhu", aliases = {"Huon Peninsula"}, -- per Usher } m["ngf-jim"] = { "Jimi", -- [[w:Jimi languages]] and [[w:Jimi River languages]] redirect to [[w:Chimbu–Wahgi languages]] nil, "ngf-chw", aliases = {"Jimi River"}, -- Usher } m["ngf-kab"] = { "Kabwum", nil, "ngf-huo", aliases = {"Timbe-Selepet-Komba", -- Pawley-Hammarström, "Northwest Huon", -- Usher }, } m["ngf-kai"] = { "Kainantu", -- Kambaira: under "unclassified Kainantu" (Glottolog), Tairora (Pawley-Hammarström), Gauwa (Usher) 15478590, "ngf-kgo", aliases = {"Gadsup-Auyana-Awa-Tairora"}, -- Wurm, } m["ngf-kak"] = { "Kalam-Kobon", 6350303, "ngf-ksa", aliases = {"Kalam", "Kaironk River"}, -- Usher (2020) } m["ngf-kau"] = { "Kaukombar", nil, "ngf-nad", aliases = {"Kaukombaran", -- Glottolog following Z'graggen (1975) "Kaukombar River"}, -- Usher's term } m["ngf-kbm"] = { "Kosorong-Burum-Mindik", nil, "ngf-huo", aliases = {"Bulum River"}, -- Usher } m["ngf-kgo"] = { "Kainantu-Goroka", 3217463, "ngf", aliases = {"Eastern Highlands"}, -- per Usher (2020) } m["ngf-khu"] = { "Kewa-Huli", nil, "ngf-eng", aliases = {"Huli-Southern Highlands"}, -- Usher } m["ngf-kma"] = { "Kâte-Mape", nil, "ngf-ehu", aliases = {"Kate-Mape-Sene", -- Pawley-Hammarström (with Sene), "Southeast Huon", -- Usher }, } m["ngf-kme"] = { "Kapau-Menya", nil, "ngf-ang", aliases = {"Southeast Kratke Range"}, -- Usher } m["ngf-koi"] = { "Koiarian", 11154240, "ngf", -- not accepted as TNG by Glottolog but accepted by all others aliases = {"Koiari-Managalas Plateau"}, } m["ngf-kok"] = { "Kokon", -- Usher calls it South Mabuso but includes Gum in it nil, "ngf-mab", } m["ngf-kow"] = { "Kowan", 6435004, "ngf-mad", aliases = {"Isumrud Strait"}, -- per Usher (2020) } m["ngf-ksa"] = { "Kalam-Southern Adelbert", nil, "ngf-mad", aliases = {"Kalamic-South Adelbert", -- Glottolog "West Madang"}, -- Usher (2020) } m["ngf-kto"] = { "Kube-Tobo", -- per Glottolog, one language "Kulungtfu-Yuanggeng-Tobo" 1173235, -- code for Tobo-Kube language "ngf-huo", aliases = {"Tobo-Kube"}, } m["ngf-kts"] = { "Komyandaret-Tsaukambo", nil, "ngf-bda", aliases = {"Becking River"}, -- Usher } m["ngf-kum"] = { "Kumil", nil, "ngf-nad", aliases = {"Kumilan", -- Pawley-Hammarström following Z'graggen (1975) "Kumil River"}, -- Usher's term } m["ngf-kya"] = { "Kamano-Yagaria", nil, "ngf-gor", aliases = {"Henganofi", -- Usher "Kamano-Yagaria-Keigana", }, } m["ngf-lok"] = { "Lowland Ok", nil, "ngf-okk", } m["ngf-mab"] = { "Mabuso", 6721668, "ngf-mad", } m["ngf-mad"] = { "Madang", 11217556, "ngf", aliases = {"Madang-Adelbert Range"}, -- Z'graggen (1975), corresponding to today's Madang except in lacking Kalam and Gants } m["ngf-mek"] = { "Mek", 6810515, "ngf", aliases = {"Goliath"}, -- outdated alternative name given by Wikipedia } m["ngf-min"] = { "Mindjim", 86749913, "ngf-mad", aliases = {"Lower Minjim", -- Glottolog, placed in Rai Coast by Glottolog and Pawley-Hammarström; Glottolog's -- Mindjim has 6 languages, including "Upper Minjim" (Rerau and Sgi Bara) "Mindjim River", -- Usher "Minjim", "Minjim River", }, } -- Add if Molet is separated from Asaro'o -- m["ngf-moa"] = { -- "Molet-Asaro'o", -- nil, -- "ngf-war", -- } m["ngf-mok"] = { "Mountain Ok", -- [[w:Mountain Ok languages]] redirects to [[w:Ok languages]] nil, "ngf-okk", } m["ngf-mom"] = { "Mombum", 6897077, "ngf", -- not accepted as TNG by Glottolog but accepted by all others aliases = {"Mombum-Koneraw", "Komolom", "Muli Strait"}, -- Pawley-Hammarström uses Komolom, Usher uses Muli Strait } m["ngf-msu"] = { "Mian-Suganga", -- considred a single Mian language by Wikipedia 12952846, "ngf-mok", aliases = {"Mianic"}, -- Glottolog } m["ngf-nad"] = { "Northern Adelbert", -- not accepted by Pawley-Hammarström 16952821, -- code for Croisilles linkage "ngf-mad", aliases = {"Adelbert Range-Isumrud Strait", -- Usher (2020) "North Adelbert", "Pihom-Isumrud"}, -- Ross? } m["ngf-nbi"] = { "North Binanderean", nil, "ngf-bin", aliases = {"Suena-Zia"}, -- Usher } m["ngf-nde"] = { "Ndeiram", -- [[w:Ndeiram River languages]] redirects to [[w:Greater Awyu languages]] nil, "ngf-awd", aliases = {"Ndeiram River"}, -- Usher? } m["ngf-ngn"] = { "Ngalik-Nduga", -- [[w:Ngalik languages]] redirects to [[w:Baliem Valley languages]] = Dani languages nil, "ngf-dan", aliases = {"Ngalik"}, -- Usher } m["ngf-nso"] = { "North Sogeram", nil, "ngf-sog", aliases = {"Mum-Sirva", -- Usher "North Central Sogeram", -- used by those who accept Central Sogeram (= North Sogeram + Apali and Manat) "North-Central Sogeram", -- rarer than without the dash "Sikan"}, -- Z’graggen (1975?) } m["ngf-num"] = { "Numugen", nil, "ngf-nad", aliases = {"Numugenan", -- Glottolog following Z'graggen 1975 "Numugen River"}, -- Usher's term } m["ngf-nur"] = { "Nuru", -- Usher excludes Yangulam, Pawley-Hammarström include Jilim and Rerau nil, "ngf-rai", aliases = {"Nuru River"}, -- Usher? } m["ngf-nwh"] = { "Northwest Hanseman", -- Usher nil, "ngf-han", aliases = {"Wamas-Samosa-Murupi-Mosimo"}, -- Glottolog, Greenhill, and Pawley-Hammarström following Z'graggen; the most common name, but very unwieldy } m["ngf-oen"] = { "Outer Engan", -- considered a single Nete language by Wikipedia 6998869, "ngf-enc", aliases = {"Nete-Bisorio"}, -- Usher } m["ngf-okk"] = { "Ok", 7081687, "ngf", } m["ngf-omo"] = { "Omosan", -- not included in (Greater) Northern Adelbert by Glottolog, but a sister nil, "ngf-nad", } m["ngf-oro"] = { "Orokaivic", 7103752, -- considered a single Orokaiva language by Wikipedia "ngf-bin", aliases = {"Central Oro"}, -- Usher } m["ngf-pan"] = { "Paniai Lakes", 6035631, "ngf", aliases = {"Wissel Lakes", "Wissel Lakes-Kemandoga River"}, -- alternative names given by Wikipedia } m["ngf-pek"] = { "Peka", nil, "ngf-rai", aliases = {"Peka River"}, -- Usher? } m["ngf-pom"] = { "Pomoikan", nil, "ngf-sad", } m["ngf-rai"] = { "Rai Coast", 7283663, "ngf-mad", aliases = {"South Madang"}, -- Usher } m["ngf-sab"] = { "Sabakor", -- [[w:Sabakor languages]] redirects to [[w:Asmat–Kamrau languages]] nil, -- 55994614 is for [[Category:Kamrau Bay languages]], which exists on enwiki "ngf-ask", aliases = {"Kamrau Bay"}, -- Usher } m["ngf-sad"] = { "Southern Adelbert", 12633980, "ngf-ksa", aliases = {"South Adelbert", -- Glottolog "Southern Adelbert Range", -- Z'graggen (1980) "Sogeram and Tomul Rivers"}, -- Usher (2020)? } m["ngf-sak"] = { "Sau-Angal-Kewa", nil, "ngf-khu", aliases = {"Southern Highlands"}, -- Usher } m["ngf-san"] = { "Sankwep", nil, "ngf-huo", aliases = {"Nabak-Momolili", -- Pawley-Hammarström, "Southwest Huon", -- Usher }, } m["ngf-sbh"] = { "South Bird's Head", 7566330, "ngf", } m["ngf-sim"] = { "Simbu", nil, "ngf-chw", } m["ngf-sog"] = { "Sogeram", 86750419, "ngf-sad", aliases = {"Sogeram River", -- Usher "Wanang"}, } m["ngf-sop"] = { "Sopac", nil, "ngf-ehu", aliases = {"Momare-Migabac", -- Pawley-Hammarström, "Masaweng River", -- Usher }, } m["ngf-taa"] = { "Tainae-Akoye", nil, "ngf-ata", aliases = {"Akoye-Tainae"}, -- Usher } m["ngf-tai"] = { "Tairora", nil, "ngf-kai", aliases = {"Tairoric", -- Glottolog, "East Kainantu", -- Usher }, } m["ngf-tib"] = { "Tiboran", nil, "ngf-nad", aliases = {"Nuclear Tibor", -- Glottolog, excluding Wanambre/Mokati "Tiboran River", -- Usher (2020) "Tibor", -- Pick (2020) and Glottolog including Wanambre/Mokati } } m["ngf-tna"] = { "Tangko-Nakai", nil, "ngf-okk", aliases = {"Central Ok"}, -- Usher } m["ngf-uru"] = { "Uruwa", nil, "ngf-fin", aliases = {"Uruwa River"}, -- Usher? } m["ngf-usi"] = { "Utu-Silopi", nil, "ngf-han", aliases = {"Silopi-Utu"}, -- Usher } m["ngf-waa"] = { "Wantoat-Awara", -- not in Usher but Wantoat and Awara form a dialect chain nil, "ngf-wan", aliases = {"Awara-Wantoat"}, -- per Wikipedia } m["ngf-wah"] = { "Wahgi", -- [[w:Wahgi languages]] redirects to [[w:Chimbu–Wahgi languages]] nil, "ngf-chw", aliases = {"Wahgi Valley"}, -- Usher } m["ngf-wan"] = { "Wantoatic", nil, "ngf-fin", aliases = {"Wantoat", "Wantoat River", -- Usher? }, } m["ngf-war"] = { "Warup", 12645082, "ngf-fin", aliases = {"Warup River"}, -- Usher? } m["ngf-woj"] = { "Wojokesic", nil, "ngf-ang", aliases = {"Northeast Kratke Range"}, -- Usher } m["ngf-wok"] = { "West Ok", nil, "ngf-okk", aliases = {"Kwer-Kopkaka-Burumakok"}, -- Glottolog, Pawley-Hammarström } m["ngf-wso"] = { "West Sogeram", nil, "ngf-sog", aliases = {"Mand-Nend", -- Usher "Atan", -- Wurm following Z'graggen }, } m["ngf-yag"] = { "Yaganon", -- placed in Rai Coast by Glottolog and Pawley-Hammarström 35323986, "ngf-mad", aliases = {"Yaganon River"}, -- Usher } m["ngf-yal"] = { "Yali", -- considered a single language by Wikipedia 8047468, "ngf-ngn", aliases = {"Ngalik"}, -- Glottolog, Pawley-Hammarström } m["ngf-yar"] = { "Yareban", 16977672, "ngf", -- not accepted as TNG by Glottolog but accepted by all others aliases = {"Musa River"}, } m["ngf-ynu"] = { "Yau-Nungon", 12953319, -- for the single Yau language in Wikipedia ([[w:Yau language (Trans–New Guinea)]]) "ngf-uru", } m["ngf-yup"] = { "Yupna", nil, "ngf-fin", aliases = {"Yupna River"}, -- Usher? } m["nic"] = { "Niger-Congo", 33838, aliases = {"Niger-Kordofanian"}, } m["nic-alu"] = { "Alumic", 4737355, "nic-plt", } m["nic-bas"] = { "Basa", 4866154, "nic-knj", } m["nic-bbe"] = { "Eastern Beboid", nil, "nic-beb", } m["nic-bco"] = { "Benue-Congo", 33253, "nic-vco", } m["nic-bcr"] = { "Bantoid-Cross", 806983, "nic-bco", } m["nic-bdn"] = { "Northern Bantoid", nil, "nic-bod", aliases = {"North Bantoid"}, } m["nic-bds"] = { "Southern Bantoid", 3183152, "nic-bod", aliases = {"Wide Bantu", "Bin"}, } m["nic-beb"] = { "Beboid", 813549, "nic-bds", } m["nic-ben"] = { "Bendi", 4887065, "nic-bcr", } m["nic-beo"] = { "Beromic", 4894642, "nic-plt", } m["nic-bod"] = { "Bantoid", 806992, "nic-bcr", } m["nic-buk"] = { "Buli-Koma", nil, "nic-ovo", } m["nic-bwa"] = { "Bwa", 12628562, "nic-gur", other_names = {"Bwamu", "Bomu"}, } m["nic-cde"] = { "Central Delta", 3813191, "nic-cri", } m["nic-cri"] = { "Cross River", 1141096, "nic-bcr", } m["nic-dag"] = { "Dagbani", nil, "nic-wov", } m["nic-dak"] = { "Dakoid", 1157745, "nic-bdn", } m["nic-dge"] = { "Escarpment Dogon", 5397128, "qfa-dgn", } m["nic-dgw"] = { "West Dogon", nil, "qfa-dgn", } m["nic-eko"] = { "Ekoid", 1323395, "nic-bds", } m["nic-eov"] = { "Eastern Oti-Volta", nil, "nic-ovo", aliases = {"Samba"}, } m["nic-fru"] = { "Furu", 5509783, "nic-bds", } m["nic-gne"] = { "Eastern Gurunsi", 12633072, "nic-gns", aliases = {"Eastern Grũsi"}, } m["nic-gnn"] = { "Northern Gurunsi", nil, "nic-gns", aliases = {"Northern Grũsi"}, } m["nic-gnw"] = { "Western Gurunsi", nil, "nic-gns", aliases = {"Western Grũsi"}, } m["nic-gns"] = { "Gurunsi", 721007, "nic-gur", aliases = {"Grũsi"}, } m["nic-gre"] = { "Eastern Grassfields", 5330160, "nic-grf", } m["nic-grf"] = { "Grassfields", 750932, "nic-bds", aliases = {"Grassfields Bantu", "Wide Grassfields"}, } m["nic-grm"] = { "Gurma", 30587833, "nic-ovo", } m["nic-grs"] = { "Southwest Grassfields", 7571285, "nic-grf", } m["nic-gur"] = { "Gur", 33536, "alv-sav", aliases = {"Voltaic"}, } m["nic-ief"] = { "Ibibio-Efik", 2743643, "nic-lcr", } m["nic-jer"] = { "Jera", nil, "nic-kne", } m["nic-jkn"] = { "Jukunoid", 1711622, "nic-pla", } m["nic-jrn"] = { "Jarawan", 1683430, "nic-mba", } m["nic-jrw"] = { "Jarawa", 35423, "nic-jrn", } m["nic-kam"] = { "Kambari", 6356294, "nic-knj", } m["nic-ktl"] = { "Katloid", nil, "nic", } m["nic-kau"] = { "Kauru", nil, "nic-kne", } m["nic-kmk"] = { "Kamuku", 6359821, "nic-knj", } m["nic-kne"] = { "East Kainji", 5328687, "nic-knj", } m["nic-knj"] = { "Kainji", 681495, "nic-pla", } m["nic-knn"] = { "Northwest Kainji", 7060098, "nic-knj", } m["nic-ktl"] = { "Katloid", 6377681, "nic", aliases = {"Katla", "Katla-Tima"}, } m["nic-lcr"] = { "Lower Cross River", 3813193, "nic-cri", } m["nic-mam"] = { "Mamfe", 2005898, "nic-bds", aliases = {"Nyang"}, } m["nic-mba"] = { "Mbam", 687826, "nic-bds", } m["nic-mbc"] = { "Mba", 6799561, "nic-ubg", } m["nic-mbw"] = { "West Mbam", nil, "nic-mba", } m["nic-mmb"] = { "Mambiloid", 1888151, other_names = {"North Bantoid"}, -- per Wikipedia, North Bantoid is the parent family "nic-bdn", } m["nic-mom"] = { "Momo", 6897393, "nic-grf", } m["nic-mre"] = { "Moré", nil, "nic-wov", } m["nic-ngd"] = { "Ngbandi", 36439, "nic-ubg", } m["nic-nge"] = { "Ngemba", 7022271, "nic-gre", } m["nic-ngk"] = { "Ngbaka", 3217499, "nic-ubg", } m["nic-nin"] = { "Ninzic", 7039282, "nic-plt", } m["nic-nka"] = { "Nkambe", 7042520, "nic-gre", } m["nic-nkb"] = { "Baka", nil, "nic-nkw", } m["nic-nke"] = { "Eastern Ngbaka", nil, "nic-ngk", } m["nic-nkg"] = { "Gbanziri", nil, "nic-nkw", } m["nic-nkk"] = { "Kpala", nil, "nic-nkw", } m["nic-nkm"] = { "Mbaka", nil, "nic-nkw", } m["nic-nkw"] = { "Western Ngbaka", nil, "nic-ngk", } m["nic-npd"] = { "North Plateau Dogon", nil, "qfa-dgn", } m["nic-nun"] = { "Nun", 13654297, "nic-gre", } m["nic-nwa"] = { "Nanga-Walo", nil, "qfa-dgn", } m["nic-ogo"] = { "Ogoni", 2350726, "nic-cri", aliases = {"Ogonoid"}, } m["nic-ovo"] = { "Oti-Volta", 1157178, "nic-gur", } m["nic-pla"] = { "Platoid", 453244, "nic-bco", aliases = {"Central Nigerian"}, } m["nic-plc"] = { "Central Plateau", 5061668, "nic-plt", } m["nic-pld"] = { "Plains Dogon", nil, "qfa-dgn", } m["nic-ple"] = { "East Plateau", 5329154, "nic-plt", } m["nic-pls"] = { "South Plateau", 7568236, "nic-plt", aliases = {"Jilic-Eggonic"}, } m["nic-plt"] = { "Plateau", 1267471, "nic-pla", } m["nic-ras"] = { "Rashad", 3401986, "nic", } m["nic-rnc"] = { "Central Ring", nil, "nic-rng", } m["nic-rng"] = { "Ring", 2269051, "nic-grf", aliases = {"Ring Road"}, } m["nic-rnn"] = { "Northern Ring", nil, "nic-rng", } m["nic-rnw"] = { "Western Ring", nil, "nic-rng", } m["nic-ser"] = { "Sere", 7453058, "nic-ubg", } m["nic-shi"] = { "Shiroro", 7498953, "nic-knj", aliases = {"Pongu"}, } m["nic-sis"] = { "Sisaala", 36532, "nic-gnw", } m["nic-tar"] = { "Tarokoid", 2394472, "nic-plt", } m["nic-tiv"] = { "Tivoid", 752377, "nic-bds", } m["nic-tvc"] = { "Central Tivoid", nil, "nic-tiv", } m["nic-tvn"] = { "Northern Tivoid", nil, "nic-tiv", } m["nic-ubg"] = { "Ubangian", 33932, "nic-vco", -- or none } m["nic-uce"] = { "East-West Upper Cross River", nil, "nic-ucr", } m["nic-ucn"] = { "North-South Upper Cross River", nil, "nic-ucr", } m["nic-ucr"] = { "Upper Cross River", 4108624, "nic-cri", aliases = {"Upper Cross"}, } m["nic-vco"] = { "Volta-Congo", 37228, "alv", } m["nic-wov"] = { "Western Oti-Volta", nil, "nic-ovo", aliases = {"Moré-Dagbani"} } m["nic-ykb"] = { "Yukubenic", 16909196, "nic-plt", aliases = {"Oohum"}, } m["nic-ymb"] = { "Yambasa", nil, "nic-mba", } m["nic-yon"] = { "Yom-Nawdm", nil, "nic-ovo", aliases = {"Moré-Dagbani"} } m["njo"] = { "Ao", 28433, "sit-aao", aliases = {"Ao Naga"}, } m["nub"] = { "Nubian", 1517194, "sdv-nes", } m["nub-hil"] = { "Hill Nubian", 5762211, "nub", aliases = {"Kordofan Nubian"}, } m["omq"] = { "Oto-Manguean", 33669, } m["omq-cha"] = { "Chatino", 35111, "omq-zap", } m["omq-chi"] = { "Chinantecan", 35828, "omq", } m["omq-cui"] = { "Cuicatec", 616024, "omq-mix", } m["omq-maz"] = { "Mazatecan", 36230, "omq", aliases = {"Mazatec"}, } m["omq-mix"] = { "Mixtecan", 21083066, "omq", } m["omq-mxt"] = { "Mixtec", 36363, "omq-mix", } m["omq-otp"] = { "Oto-Pamean", 1270220, "omq", } m["omq-pop"] = { "Popolocan", 5132273, "omq", } m["omq-tri"] = { "Triqui", 780200, "omq-mix", aliases = {"Trique"}, } m["omq-zap"] = { "Zapotecan", 8066463, "omq", } m["omq-zpc"] = { "Zapotec", 13214, "omq-zap", } m["omv"] = { "Omotic", 33860, "afa", } m["omv-aro"] = { "Aroid", 3699526, "omv", aliases = {"Ari-Banna", "South Omotic", "Somotic"}, } m["omv-diz"] = { "Dizoid", 430251, "omv", aliases = {"Maji", "Majoid"}, } m["omv-eom"] = { "East Ometo", 20527288, "omv-ome", } m["omv-gon"] = { "Gonga", 4143043, "omv", aliases = {"Kefoid"}, } m["omv-mao"] = { "Mao", 1351495, "omv", } m["omv-nom"] = { "North Ometo", nil, "omv-ome", } m["omv-ome"] = { "Ometo", 36310, "omv", } m["oto"] = { "Otomian", 130372545, "omq-otp", } m["oto-otm"] = { "Otomi", 36355, "oto", } m["paa"] = { "Papuan", 236425, "qfa-not", } m["paa-aia"] = { "Aian", 4767739, -- Annaberg languages "paa-ram", aliases = {"Middle Ramu", -- Foley (with Rao), "Annaberg", -- with Rao "Aram-Aren", -- Usher }, } m["paa-alp"] = { "Alor-Pantar", 3502429, "paa-tap", } m["paa-amu"] = { "Amto-Musan", 480281, aliases = {"Samaia River"}, } m["paa-ani"] = { "Anim", 55603991, aliases = {"Fly River"}, } m["paa-ara"] = { "Arapesh", 4784223, "paa-koa", aliases = {"Arapeshan"}, -- Foley } m["paa-arf"] = { "Arafundi", 4783702, } m["paa-ata"] = { "Ataitan", 4812652, "paa-ram", aliases = {"Tangu", -- Foley "Tanggu", -- alternative name given by Wikipedia "Moam River", -- Usher }, } m["paa-baa"] = { "Bayono-Awbono", 2424781, } m["paa-bai"] = { "Baining", 748487, aliases = {"East New Britain"}, } m["paa-baw"] = { "Bosngun-Awar", nil, "paa-ott", aliases = {"East Ramu Coast", -- Usher "Bosman-Awar", -- Wikipedia }, } m["paa-bew"] = { "Bewani", -- [[w:Bewani languages]] redirects to [[w:Border languages (New Guinea)]]; but Croatian Wikipedia has an entry 16113460, "paa-bor", aliases = {"Poal River"}, -- Usher } m["paa-boa"] = { "Boazi", 48803717, "paa-mby", aliases = {"Lake Murray"}, -- Usher } m["paa-bor"] = { "Border", 1752158, aliases = {"Upper Tami", "Tami River-Bewani Range", -- Usher }, } m["paa-bul"] = { "Bulaka River", 4987195, aliases = {"Yelmek-Maklew", "Jabga"}, -- Yelmek-Maklew in Evans (2018) and Gregor (2021) } m["paa-bvi"] = { "Betaf-Vitou", -- Glottolog nil, "paa-tor", aliases = {"Vitou-Betaf", -- Wikipedia "Fitou-Tena", -- Usher "Manirem", }, } m["paa-clp"] = { "Central Lakes Plain", -- [[w:Central Lakes Plain languages]] redirects to [[w:Lakes Plain languages]] nil, -- Q86780132 is for the corresponding category, which exists in enwiki "paa-lpl", aliases = {"East Tariku", -- Glottolog "Central Lakes Plains", -- Usher }, } m["paa-dtu"] = { "Doso-Turumsa", 16917784, -- possibly related to East Strickland languages aliases = {"Soari River"}, -- Usher's name } m["paa-ebh"] = { "East Bird's Head", 338064, aliases = {"Mantion-Meax", "Mantion-Meyah", -- Mantion-Meax is Wikipedia's term "Southeast Bird's Head", -- Usher (2020) }, } m["paa-eel"] = { "Eastern Eleman", nil, "paa-ele", aliases = {"East Eleman"}, } m["paa-egb"] = { "East Geelvink Bay", 1497678, aliases = {"Geelvink Bay", "East Cenderawasih"}, -- Geelvink Bay per Glottolog } m["paa-eke"] = { "East Keram", nil, "paa-ker", } m["paa-ele"] = { "Eleman", 3034298, aliases = {"Kerema Bay"}, } m["paa-elp"] = { "East Lakes Plain", -- [[w:East Lakes Plain languages]] redirects to [[w:Lakes Plain languages]]; but Croatian Wikipedia has an entry 12633078, "paa-lpl", aliases = {"East Lakes Plains"}, -- Usher } m["paa-epw"] = { "Eastern Pauwasi", 16115496, aliases = {"East Pauwasi"}, } m["paa-etf"] = { "Eastern Trans-Fly", 5330530, aliases = {"Oriomo"}, -- in increasing recent use, probably originating in Evans (2018) } m["paa-eti"] = { "East Timor", 15496066, "paa-tap", aliases = {"Oirata-Makasae", -- Wikipedia's name "Eastern Timor", -- alternative name given by Wikipedia "Fataluku-Makasai", "Oirata-Makasai", -- alternative names given by Wikidata }, } m["paa-fas"] = { "Fas", 3502658, aliases = {"Baibai-Fas"}, -- Glottolog's name } m["paa-flp"] = { "Far West Lakes Plain", -- [[w:Wapoga River languages]] redirects to [[w:Lakes Plain languages]] nil, -- Q86808337 is for the corresponding Wapoga languages category, which exists in enwiki "paa-lpl", aliases = {"Rasawa", -- Clouse (1997) "Wapoga River", -- Usher, including Kehu/Keuw (unclassified by others) }, } m["paa-gkw"] = { "Greater Kwerba", 12635134, aliases = {"West Foja Range", -- Usher "Kwerbic", -- Wikipedia "Kwerba", -- Foley (2018) }, } m["paa-gto"] = { "Galela-Tobelo", nil, "paa-nnh", aliases = {"Mainland North Halmaheran", -- Glottolog "Mainland North Halmahera", "Northeast Halmahera", -- alternative names "Northeast Halmaheran", -- Wikipedia, from Verhoeve 1988 }, } m["paa-hya"] = { "Heyo-Yahang", nil, "paa-mam", aliases = {"Yahang-Heyo"}, -- Wikipedia's name } m["paa-ing"] = { "Inland Gulf", 6034783, "paa-ani", aliases = {"Inland Gulf of Papua"}, -- Glottolog } m["paa-isk"] = { "Inner Sko", 65043889, "paa-sko", aliases = {"Skouic", -- Glottolog "West Vanimo Coast", -- Usher "Western Skou", -- Wikipedia "Inner Skou", "Nuclear Skou", -- alternative names given by Wikipedia }, } m["paa-iwa"] = { "Iwam", 15147853, "paa-sep", } m["paa-kae"] = { "Kamula-Elevala", 130390498, -- often placed in TNG aliases = {"Kamula-Elevala River"}, } m["paa-kan"] = { "Kanum", -- removed from Tonda by Glottolog nil, "paa-ton", } m["paa-kay"] = { "Kayagaric", 7566330, aliases = {"Kayagar", -- formerly common "Cook River"}, -- per Usher (2020) } m["paa-ker"] = { "Keram", 48768173, -- often grouped within or coordinate with the Ramu languages aliases = {"Keram River"}, } m["paa-kiw"] = { "Kiwaian", 338449, aliases = {"Kiwai"}, -- formerly common, still sees some use } m["paa-kko"] = { "Kaure-Kosare", -- rejected by Pawley-Hammarström but accepted by Glottolog, Foley (2018) and Usher (2020) 48767891, aliases = {"Nawa River"}, -- Usher's term } m["paa-koa"] = { "Kombio-Arapesh", 16115049, "paa-trr", aliases = {"Kombio-Arapeshan", -- Laycock, who includes Wom "Kombio-Arapesh-Urat", -- Glottolog, including Urat }, } m["paa-kol"] = { "Kolopom", 6427807, } m["paa-kom"] = { "Kombio", 65044238, "paa-koa", aliases = {"Kombian", -- Laycock "Kombio-Yambes", -- Glottolog }, } m["paa-kun"] = { "Kunimaipan", 134973258, aliases = {"Northwest Wharton Range"}, -- per Usher (2020) -- often considered a subfamily of Goilalan } m["paa-kwa"] = { "Kwalean", 6450053, aliases = {"Humene-Uare"}, } m["paa-kwe"] = { "Kwerba proper", 12635134, "paa-gkw", aliases = {"Kwerba", -- Usher "Kwerbaic", -- Glottolog }, } m["paa-kwo"] = { "Kwomtari", 2075415, aliases = {"Kwomtari-Nai"}, -- Senu River is a larger unproven proposal } m["paa-lla"] = { "Loloda-Laba", -- a single language in Glottolog (Loloda-Laba) and Wikipedia (Loloda) 11732388, -- for the Loloda language "paa-gto", aliases = {"Loloda"}, -- Wikipedia's name } m["paa-lma"] = { "Left May", 614468, aliases = {"Arai River"}, -- per Usher (2020) -- Sometimes in a putative Arai-Samaia family along with Amto-Musan and the Pyu language } m["paa-lmu"] = { "Lepki-Murkim", -- Kembra accepted by Glottolog and Usher; not by Foley (2020) but does not exclude the possibility -- of a relationship 85776285, -- independent family per Glottolog, part of South Pauwasi River family (under Pauwasi) per Usher (2020) aliases = {"Lepki-Murkim-Kembra"}, -- Glottolog } m["paa-lpl"] = { "Lakes Plain", 6478969, aliases = {"Lakes Plains"}, } m["paa-lra"] = { "Lower Ramu", 65089469, "paa-ram", aliases = {"Ottilien-Misegian"}, -- alternative name given by Wikipedia } m["paa-lse"] = { "Lower Sepik", 7061700, aliases = {"Nor-Pondo"}, } m["paa-mai"] = { "Mairasi", 6736896, aliases = {"Mairasic"}, -- per Glottolog } m["paa-mal"] = { "Mailuan", 6735839, aliases = {"Cloudy Bay"}, } m["paa-mam"] = { "Maimai", -- Foley's Maimai is expanded 53679325, -- this is the code for the expanded Maimai with 6 languages, as opposed to the 3 in "Nuclear Maimai" "paa-trr", aliases = {"Nuclear Maimai", -- Glottolog's name "Maimai proper", -- Wikipedia's name }, } m["paa-man"] = { "Manubaran", 6752335, aliases = {"Mount Brown"}, } m["paa-mar"] = { "Marienberg", 1570589, "paa-trr", aliases = {"Marienberg Hills"}, -- Usher } m["paa-may"] = { "Maybratic", 4830892, -- the code for the Maybrat language in Wikipedia, which subsumes the two languages of this family -- putatively included in West Papuan but generally considered an isolated family aliases = {"Maybrat-Karon"}, } m["paa-mbi"] = { "Mbaham-Iha", 85784512, "qfa-dis", -- Papuan languages; Glottolog groups Karas (Kalamang) with Mbaham-Iha into a (mainland) West Bomberai -- family and stops there; Wikipedia, following Usher and Schapper (2022), groups Karas, Mbaham-Iha -- and the large Timor-Alor-Pantar family into a (Greater) West Bomberai family, saying that Karas is no -- closer to Mbaham-Iha than to Timor-Alor-Pantar. aliases = {"Mbahaam-Iha", -- used by Wikidata "Nuclear West Bomberai", -- Glottolog's name }, } m["paa-mby"] = { "Marind-Boazi-Yaqay", 3217484, "paa-ani", aliases = {"Marind-Boazi-Yaqai", -- Glottolog "Marind-Yakhai", -- Usher, without Boazi "Marind-Yaqai", -- Wikidata "Marind", -- alternative name given by Wikipedia "Marind-Arandai", -- alternative name given by Spanish Wikipedia }, } m["paa-mmu"] = { "Mandi-Muniwara", nil, "paa-mar", aliases = {"West Marienberg Hills"}, -- Usher } m["paa-mon"] = { "Monumbo", -- per Glottolog: "No evidence for the Bogia (Monumbo) languages being related to other Torricelli languages was ever presented" 16928417, aliases = {"Bogia", -- Glottolog "Bogia Bay", -- Usher (2020) }, } m["paa-mri"] = { "Marindic", -- [[w:Marindic languages]] redirects to [[w:Marind–Yaqai languages]] nil, "paa-mby", aliases = {"Marind"}, -- Usher; a single language } m["paa-nam"] = { "Nambu", 6961418, "paa-yam", aliases = {"East Morehead River"}, -- Usher } m["paa-nbo"] = { "North Bougainville", 749496, } m["paa-ndu"] = { "Ndu", 3217498, "paa-sep", -- Not accepted by Glottolog aliases = {"Ndu-Nggala"}, -- Usher } m["paa-ngk"] = { "Ngkolmpu", -- considered a single language by Wikipedia 5908646, "paa-kan", aliases = {"Ngkantr", -- Glottolog "Ngkolmpu Kanum", -- Wikipedia "Ngkontar", -- alternative name given by Wikipedia "Kanum", -- used by Wikidata }, } m["paa-nha"] = { "North Halmahera", 3217358, -- possibly in a proposed West Papuan family or an independent family } m["paa-nim"] = { "Nimboran", 12638426, aliases = {"Nimboranic", -- per Glottolog "Grime River", -- per Usher (2020) } } m["paa-nnd"] = { "Nuclear Ndu", nil, "paa-ndu", aliases = {"Ndu", -- Usher, with Boiken/Boikin "Ndu proper", -- Wikipedia }, } m["paa-nnh"] = { "Northern North Halmahera", nil, "paa-nha", aliases = {"Northern North Halmaheran", -- Glottolog "Halmahera", -- Usher "Core Halmaheran", -- Wikipedia }, } m["paa-nto"] = { "Namla-Tofanma", 16918187, -- independent family per Glottolog and Foley (2018), part of West Pauwasi family (under Pauwasi) per Usher (2020) } m["paa-ott"] = { "Ottilien", 7109477, "paa-lra", aliases = {"Ramu Coast", -- Usher "Watam-Awar-Gamay", -- alternative name given by Wikipedia }, } m["paa-pah"] = { "Pahoturi River", 17049141, aliases = {"Pahoturi"}, -- per Glottolog } m["paa-pal"] = { "Palei", -- Laycock adds Agi and Nabi/Nambi(-Metan) 65089113, "paa-wpa", aliases = {"Nuclear Palai"}, } m["paa-pia"] = { "Piawi", -- per Wikipedia, grouped with Arafundi languages to form Upper Yuat, which is a sister to Madang 7190400, aliases = {"Schraeder Range", -- Usher? "Waibuk"}, } m["paa-pio"] = { "Piore River", 65043152, "paa-sko", aliases = {"Barupu Lagoon", -- Glottolog "Lagoon", -- alternative name given by Wikipedia }, } m["paa-por"] = { "Porapora", -- Foley includes Ambakich (which we, Glottolog, and Usher treat as Keram) 65044258, "paa-ram", aliases = {"Agoan", -- Glottolog "Porapora River", -- Usher "core Grass", -- alternative name given by Wikipedia }, } m["paa-ram"] = { "Ramu", 3442808, aliases = {"Ramu River"}, -- per Usher (2020) } m["paa-rsa"] = { "Rasawa-Saponi", -- [[w:Rasawa-Saponi languages]] redirects to [[w:Lakes Plain languages]] nil, -- Q9859418 is for the coresponding category, which exists in the Piedmontese Wikipedia (?!) "paa-flp", aliases = {"Rombak River"}, -- Usher } m["paa-rub"] = { "Ruboni", 6875319, "paa-lra", aliases = {"Misegian", -- Wikipedia's name "Mikarew", -- alternative name given by Wikipedia "Ruboni Range"}, -- Usher } m["paa-saa"] = { "Samarokena-Airoran", 96417699, "paa-gkw", aliases = {"Apauwar Coast"}, -- Usher } m["paa-sah"] = { "Sahu", nil, "paa-nnh", } m["paa-sbo"] = { "South Bougainville", 3217380, } m["paa-sen"] = { "Sentani", 17044584, -- no consensus on higher affiliations, if any aliases = {"Sentanic", "Demta-Sentani", "Demta-Lake Sentani"}, -- Sentanic per Glottolog, Demta-Sentani per Wikipedia } m["paa-sep"] = { "Sepik", 3508772, } m["paa-shi"] = { "Serra Hills", 65043154, "paa-sko", } m["paa-sko"] = { "Sko", 953509, aliases = {"Skou"}, } m["paa-sng"] = { "Senagi", 2066550, } m["paa-taa"] = { "Taikat-Awyi", -- [[w:Taikat languages]] redirects to [[w:Border languages (New Guinea)]]; but Croatian Wikipedia has an entry 12643265, "paa-bor", aliases = {"Taikat", -- Foley "Upper Tami River", -- Usher }, } m["paa-tam"] = { "Tamolan", 7681634, "paa-ram", aliases = {"Guam River"}, -- Usher } m["paa-tap"] = { "Timor-Alor-Pantar", 16590002, } m["paa-teb"] = { "Teberan", 7692052, -- Often grouped with Trans-New Guinea, but per Pawley-Hammarström (2018), it has "weaker or disputed claims to membership in TNG". aliases = {"Dadibi-Folopa"}, } m["paa-tir"] = { "Tirio", 7809225, "paa-ani", aliases = {"Nuclear Lower Fly", -- Pawley-Hammarström ("Lower Fly" includes Abom) "Nuclear Tirio", -- Glottolog ("Tirio" includes Abom) "Lower Fly River", -- Usher (without Abom) }, } m["paa-tki"] = { "Turama-Kikori", 7853680, aliases = {"Turama-Kikorian", "Rumu-Omati River"}, } m["paa-ton"] = { "Tonda", 8581005, "paa-yam", aliases = {"West Morehead River"}, -- Usher } m["paa-too"] = { "Tor-Orya", 16590099, aliases = {"Orya-Tor"}, } m["paa-tor"] = { "Tor", -- [[w:Tor languages]] redirects to [[w:Orya–Tor languages]] nil, "paa-too", } m["paa-trr"] = { "Torricelli", 1333831, } m["paa-tti"] = { "Ternate-Tidore", nil, "paa-nnh", } m["paa-wal"] = { "Walio", 16919872, -- Often placed in Sepik (e.g. by Laycock and Z'graggen (1975)), but not by Foley (2018), and not accepted by Glottolog. aliases = {"Walioic", -- Glottolog "Central Leonhard Schultze River", }, } m["paa-wap"] = { "Wapei", -- Glottolog includes Nabi/Nambi(-Metan) in Wapeic 65089115, "paa-wpa", aliases = {"Wapeic"}, -- Glottolog } m["paa-war"] = { "Waris", -- [[w:Waris languages]] redirects to [[w:Border languages (New Guinea)]]; but Croatian Wikipedia has an entry 12645076, "paa-bor", aliases = {"Warisic", -- Glottolog "Bapi River", -- Usher (without Manem or Senggi) }, } m["paa-wbh"] = { "West Bird's Head", 5330530, -- Kuwani is sometimes included; probably related to North Halmahera languages. } m["paa-wel"] = { "Western Eleman", nil, "paa-ele", aliases = {"West Eleman"}, } m["paa-wig"] = { "West Inland Gulf", nil, "paa-ing", aliases = {"West Inland Gulf of Papua"}, -- Glottolog } m["paa-wke"] = { "West Keram", nil, "paa-ker", aliases = {"Koam", "Mongol-Langam", "Ulmapo"}, -- Koam used by Foley, Ulmapo used by Glottolog } m["paa-wko"] = { "Wára-Kómnzo", -- since we split out Kómnzo as a separate language 11732474, -- for the Wara language "paa-ton", aliases = {"Anta-Komnzo-Wára-Wérè-Kémä", -- Glottolog's name "Wára", "Wara", -- Wikipedia }, } m["paa-wlp"] = { "West Lakes Plain", -- [[w:Tariku languages]] redirects to [[w:Lakes Plain languages]] 47007503, -- actually for "Tariku languages", which per Wikipedia covers Fayu, Kirikiri, Iau and Tause "paa-lpl", aliases = {"West Tariku", -- Glottolog "West Lakes Plains"}, -- Usher, with Edopi/Iau } m["paa-wpa"] = { "Wapei-Palei", 65043156, "paa-trr", } m["paa-wpw"] = { -- paa-wpa already used by Wapei-Palei "Western Pauwasi", -- 2 langs per Glottolog and Pawley-Hammarström; Usher also includes Namla-Tofanma and Usku 85815062, aliases = {"West Pauwasi", -- Wikipedia, Usher "Tebi-Towe", "Dubu-Towei"}, } m["paa-yam"] = { "Yam", 15062272, aliases = {"Morehead and Upper Maro River", "Morehead River", -- Usher }, } m["paa-yaq"] = { "Yaqayic", -- [[w:Yaqai languages]] redirects to [[w:Marind–Yaqai languages]] nil, "paa-mby", aliases = {"Yakhai-Warkay"}, -- Usher } m["paa-ysa"] = { "Yawa-Saweru", 3217545, aliases = {"Yawa", "Yawan", "Yapen"}, } m["paa-yua"] = { "Yuat", 8060096, } m["phi"] = { "Philippine", 947858, "poz", } m["phi-kal"] = { "Kalamian", 3217466, "phi", aliases = {"Calamian"}, } m["poz"] = { "Malayo-Polynesian", 143158, "map", } m["poz-aay"] = { "Admiralty Islands", 2701306, "poz-oce", } m["poz-bnn"] = { "North Bornean", 1427907, "poz", } m["poz-bre"] = { "East Barito", 2701314, "poz", } m["poz-brw"] = { "West Barito", 2761679, "poz", } m["poz-bss"] = { "Bali-Sasak-Sumbawa", 3396043, "poz-msa", } m["poz-btk"] = { "Bungku-Tolaki", 3217381, "poz-clb", } m["poz-cet"] = { "Central-Eastern Malayo-Polynesian", 2269883, "poz", } m["poz-clb"] = { "Celebic", 1078041, "poz", } m["poz-cln"] = { "New Caledonian", 3091221, "poz-ocs", } m["poz-cma"] = { "Central Maluku", 3217479, "poz-cet", } m["poz-hce"] = { "Halmahera-Cenderawasih", 2526616, "pqe", } m["poz-kal"] = { "Kaili-Pamona", 3217465, "poz-clb", } m["poz-lgx"] = { "Lampungic", 49215, "poz", } m["poz-mcm"] = { "Malayo-Chamic", nil, "poz-msa", } m["poz-mic"] = { "Micronesian", 420591, "poz-occ", } m["poz-mly"] = { "Malayic", 662628, "poz-mcm", } m["poz-msa"] = { "Malayo-Sumbawan", 1363818, "poz", } m["poz-mun"] = { "Muna-Buton", 3037924, "poz-clb", } m["poz-nws"] = { "Northwest Sumatran", 2071308, "poz", } m["poz-occ"] = { "Central-Eastern Oceanic", 2068435, "poz-oce", } m["poz-oce"] = { "Oceanic", 324457, "pqe", } m["poz-ocs"] = { "Southern Oceanic", 3039118, "poz-occ", } m["poz-ocw"] = { "Western Oceanic", 2701282, "poz-oce", } m["poz-pcc"] = { "Central Pacific", 3130237, "poz-occ", } m["poz-pep"] = { "Eastern Polynesian", 390979, "poz-pnp", } m["poz-pnp"] = { "Nuclear Polynesian", 743851, "poz-pol", } m["poz-pol"] = { "Polynesian", 390979, "poz-pcc", } m["poz-san"] = { "Sabahan", 3217517, "poz-bnn", } m["poz-sbj"] = { "Sama-Bajaw", 2160409, "poz", } m["poz-slb"] = { "Saluan-Banggai", 3217519, "poz-clb", } m["poz-sls"] = { "Southeast Solomonic", 3119671, "poz-occ", } m["poz-ssw"] = { "South Sulawesi", 2778190, "poz", } m["poz-stm"] = { "St. Matthias", 6484143, "poz-oce", aliases = {"St Matthias"}, } m["poz-swa"] = { "North Sarawakan", 538569, "poz-bnn", } m["poz-tem"] = { "Temotu", 3075769, "poz-oce", } m["poz-tim"] = { "Timoric", 7806987, "poz-cet", } m["poz-ton"] = { "Tongic", 3397263, "poz-pol", } m["poz-tot"] = { "Tomini-Tolitoli", 3217541, "poz-clb", } m["poz-vnc"] = { "Central Vanuatu", 5061988, "poz-ocs", } m["poz-vnn"] = { "North Vanuatu", 85789650, "poz-ocs", } m["poz-vns"] = { "South Vanuatu", 3070173, "poz-ocs", } m["poz-wot"] = { "Wotu-Wolio", 1041317, "poz-clb", aliases = {"Island Kaili-Wolio"}, -- Glottolog } m["pqe"] = { "Eastern Malayo-Polynesian", 2269883, "poz-cet", } m["qfa-adc"] = { "Central Great Andamanese", nil, "qfa-adm", } m["qfa-adm"] = { "Great Andamanese", 3515103, } m["qfa-adn"] = { "Northern Great Andamanese", nil, "qfa-adm", } m["qfa-ads"] = { "Southern Great Andamanese", nil, "qfa-adm", } m["qfa-ain"] = { "Ainuic", 50111972, aliases = {"Ainu"}, } m["qfa-bej"] = { "Be-Jizhao", nil, "qfa-bet", } m["qfa-bet"] = { "Be-Tai", 12627719, "qfa-tak", aliases = {"Tai-Be", "Daic-Beic", "Beic-Daic"}, } m["qfa-buy"] = { "Buyang", 1109927, "qfa-kra", } m["qfa-cka"] = { "Chukotko-Kamchatkan", 33255, } m["qfa-cre"] = { "creole", 33289, "crp", } m["qfa-ckn"] = { "Chukotkan", 2606732, "qfa-cka", } m["qfa-cnt"] = { "contact", 133253514, "qfa-not", } m["qfa-dis"] = { -- Languages that are not unclassifiable (qfa-unc) but where there is no consensus on classification. Usually -- this is because the languages are divergent and it's disputed whether they are isolates or distantly related -- to other languages. "disputed affiliation", nil, "qfa-not", categoryName = "Languages of disputed affiliation", } m["qfa-dgn"] = { "Dogon", 1234776, "nic", } m["qfa-dny"] = { "Dene-Yeniseian", 21103, aliases = {"Dené-Yeniseian"}, } m["qfa-hur"] = { "Hurro-Urartian", 1144159, } m["qfa-iso"] = { "isolate", 33648, "qfa-not", categoryName = "Language isolates", } m["qfa-kad"] = { "Kadu", -- considered either Nilo-Saharan or independent/none 1720989, } m["qfa-kms"] = { "Kam-Sui", 1023641, "qfa-tak", } m["qfa-kor"] = { "Koreanic", 11263525, } m["qfa-kra"] = { "Kra", 1022087, "qfa-tak", } m["qfa-lic"] = { "Hlai", 1023648, "qfa-tak", aliases = {"Hlaic"}, } m["qfa-mch"] = { -- used in both N and S America "Macro-Chibchan", 3438062, } m["qfa-mix"] = { "mixed", 33694, "qfa-cnt", } m["qfa-not"] = { "not a family", nil, "qfa-not", } m["qfa-onb"] = { "Be", nil, "qfa-bej", aliases = {"Ong-Be", "Beic"}, } m["qfa-ong"] = { "Ongan", 2090575, aliases = {"Angan", "South Andamanese", "Jarawa-Onge"}, } m["qfa-pid"] = { "pidgin", 33831, "crp", } m["qfa-sub"] = { "substrate", 20730913, "qfa-not", } m["qfa-tak"] = { "Kra-Dai", 34171, aliases = {"Tai-Kadai", "Kadai"}, } m["qfa-tyn"] = { "Tyrsenian", 1344038, } m["qfa-unc"] = { -- This corresponds to languages normally called "unclassified", i.e. there is insufficient data or research to -- classify them, whereas our [[:Category:Unclassified languages]] is just languages that no Wiktionary editor -- has classified yet (the family code in the language data is missing). "unclassifiable", 33956, "qfa-not", } m["qfa-xgs"] = { "Serbi-Mongolic", 108887939, } m["qfa-xgx"] = { "Para-Mongolic", 107619002, "qfa-xgs", } m["qfa-yen"] = { "Yeniseian", 27639, "qfa-dny", aliases = {"Yeniseic", "Yenisei-Ostyak"}, } m["qfa-yke"] = { "Ketic", nil, "qfa-yen", } m["qfa-yko"] = { "Kottic", nil, "qfa-yen", } m["qfa-yrn"] = { "Arinic", nil, "qfa-yen", } m["qfa-ypm"] = { "Pumpokolic", nil, "qfa-yen", } m["qfa-yuk"] = { "Yukaghir", 34164, aliases = {"Yukagir", "Jukagir"}, } m["qwe"] = { "Quechuan", 5218, } m["raj"] = { "Rajasthani", 13196, "inc-wes", protoLanguage = "inc-ogu", } m["roa"] = { "Romance", 19814, "itc", aliases = {"Romanic", "Latin", "Neolatin", "Neo-Latin"}, protoLanguage = "la", } m["roa-asl"] = { "Asturleonese", 35390, "roa-ibe", protoLanguage = "roa-ole", } m["roa-cas"] = { "Castilian", 71924, "roa-ibe", aliases = {"Castillian", "Castilic", "Castillic"}, protoLanguage = "osp", } m["roa-dal"] = { "Dalmatian Romance", 97646077, "roa-itd", } m["roa-eas"] = { "Eastern Romance", 147576, "roa", } m["roa-emr"] = { "Emilian-Romagnol", 242648, "roa-git", } m["roa-gap"] = { "Galician-Portuguese", 9080204, "roa-ibe", aliases = {"Galician Romance", "Galaic-Portuguese"}, protoLanguage = "roa-opt", } m["roa-gar"] = { "Gallo-Romance", 500394, "roa-wes", } m["roa-itd"] = { "Italo-Dalmatian", 3313381, "roa-iwr", aliases = {"Central Romance"} } m["roa-itr"] = { "Italo-Romance", 3356483, "roa-itd", } m["roa-iwr"] = { "Italo-Western Romance", 112608, "roa", aliases = {"Italo-Western"}, } m["roa-git"] = { "Gallo-Italic", 516074, "roa-gar", aliases = {"Gallo-Italian", "Gallo-Cisalpine", "Cisalpine"}, } m["roa-grh"] = { "Gallo-Rhaetian", 97646466, "roa-gar", } m["roa-ibe"] = { "Ibero-Romance", 749533, "roa-wes", aliases = {"Iberian Romance", "West Ibero-Romance", "Western Ibero-Romance", "West Iberian Romance", "Western Iberian Romance"} } m["roa-nar"] = { "Navarro-Aragonese", 133252927, "roa-ibe", protoLanguage = "roa-ona", } m["roa-oil"] = { "Oïl", 37351, "roa-grh", aliases = {"langues d'oïl", "langue d'oïl", "Cisalpine"}, protoLanguage = "fro", } m["roa-ocr"] = { "Occitano-Romance", 599958, "roa-gar", aliases = {"Gallo-Narbonnese", "East Iberian", "Eastern Iberian"}, } m["roa-rhe"] = { "Rhaeto-Romance", 515593, "roa-grh", aliases = {"langues d'oïl", "langue d'oïl", "Cisalpine"}, } m["roa-sou"] = { "Southern Romance", 145345, "roa", } m["roa-wes"] = { "Western Romance", 2714388, "roa-iwr", } --[=[ Exceptional language and family codes for South American Indian languages can use the prefix "sai-", though "sai" is no longer itself a family code. ]=]-- m["sai-ara"] = { "Araucanian", 626630, } m["sai-aym"] = { "Aymaran", 33010, } m["sai-bar"] = { "Barbacoan", 807304, aliases = {"Barbakoan"}, } m["sai-bor"] = { "Boran", 5371776, } m["sai-cah"] = { "Cahuapanan", 1025793, } m["sai-car"] = { "Cariban", 33090, aliases = {"Carib"}, } m["sai-cer"] = { "Cerrado", 98078151, "sai-jee", aliases = {"Amazonian Jê"}, } m["sai-chc"] = { "Chocoan", 1075616, aliases = {"Choco", "Chocó"}, } m["sai-cho"] = { "Chonan", 33019, aliases = {"Chon"}, } m["sai-cje"] = { "Central Jê", 18010843, "sai-cer", aliases = {"Akuwẽ"}, } m["sai-cpc"] = { "Chapacuran", 1062626, } m["sai-crn"] = { "Charruan", 3112423, aliases = {"Charrúan"}, } m["sai-ctc"] = { "Catacaoan", 5051139, } m["sai-guc"] = { "Guaicuruan", 1974973, "sai-mgc", aliases = {"Guaicurú", "Guaycuruana", "Guaikurú", "Guaycuruano", "Guaykuruan", "Waikurúan"}, } m["sai-guh"] = { "Guahiban", 944056, aliases = {"Guahiboan", "Guajiboan", "Wahivoan"}, } m["sai-gui"] = { "Guianan", nil, "sai-car", aliases = {"Guianan Carib", "Guiana Carib"}, } m["sai-har"] = { "Harákmbut", 1584402, "sai-hkt", aliases = {"Harákmbet"}, } m["sai-hkt"] = { "Harákmbut-Katukinan", 17107635, } m["sai-hrp"] = { "Huarpean", 1578336, aliases = {"Warpean", "Huarpe", "Warpe"}, } m["sai-jee"] = { "Jê", 1483594, "sai-mje", aliases = {"Gê", "Jean", "Gean", "Jê-Kaingang", "Ye"}, } m["sai-jir"] = { "Jirajaran", 3028651, aliases = {"Hiraháran"}, } m["sai-jiv"] = { "Jivaroan", 1393074, aliases = {"Hívaro", "Jibaro", "Jibaroan", "Jibaroana", "Jívaro"}, } m["sai-ktk"] = { "Katukinan", 2636000, "sai-hkt", aliases = {"Catuquinan"}, } m["sai-kui"] = { "Kuikuroan", nil, "sai-car", aliases = {"Kuikuro", "Nahukwa"}, } m["sai-map"] = { "Mapoyan", 61096301, "sai-ven", aliases = {"Mapoyo", "Mapoyo-Yabarana", "Mapoyo-Yavarana", "Mapoyo-Yawarana"}, } m["sai-mas"] = { "Mascoian", 1906952, aliases = {"Mascoyan", "Maskoian", "Enlhet-Enenlhet"}, } m["sai-mgc"] = { "Mataco-Guaicuru", 255512, } m["sai-mje"] = { "Macro-Jê", 887133, aliases = {"Macro-Gê"}, } m["sai-mtc"] = { "Matacoan", 2447424, "sai-mgc", } m["sai-mur"] = { "Muran", 33826, aliases = {"Mura"}, } m["sai-nad"] = { "Nadahup", 1856439, aliases = {"Makú", "Macú", "Vaupés-Japurá"}, } m["sai-nje"] = { "Northern Jê", 98078225, "sai-cer", aliases = {"Core Jê"}, } m["sai-nmk"] = { "Nambikwaran", 15548027, aliases = {"Nambicuaran", "Nambiquaran", "Nambikuaran"}, } m["sai-otm"] = { "Otomacoan", 3217503, aliases = {"Otomákoan", "Otomakoan"}, } m["sai-pan"] = { "Panoan", 1544537, "sai-pat", aliases = {"Pano"}, } m["sai-pat"] = { "Pano-Tacanan", 2475746, aliases = {"Pano-Tacana", "Pano-Takana", "Páno-Takána", "Pano-Takánan"}, } m["sai-pek"] = { "Pekodian", 107451736, "sai-car", aliases = {"South Amazonian Carib", "Southern Cariban", "Pekodi"}, } m["sai-pem"] = { "Pemongan", nil, "sai-ven", aliases = {"Pemong", "Pemóng", "Purukoto"}, } m["sai-pey"] = { "Peba-Yaguan", 174015, aliases = {"Peba-Yagua", "Yaguan", "Peban", "Yáwan"}, } m["sai-prk"] = { "Parukotoan", 107451482, "sai-car", aliases = {"Parukoto"}, } m["sai-sje"] = { "Southern Jê", 98078245, "sai-jee", } m["sai-tac"] = { "Tacanan", 3113762, "sai-pat", } m["sai-tar"] = { "Taranoan", 105097814, "sai-gui", aliases = {"Trio", "Tarano"}, } m["sai-tin"] = { "Tiniguan", 2892258, aliases = {"Tinigua"}, } m["sai-tuc"] = { "Tucanoan", 788144, } m["sai-tyu"] = { "Ticuna-Yuri", 4467010, } m["sai-ucp"] = { "Uru-Chipaya", 2475488, aliases = {"Uru-Chipayan"}, } m["sai-ven"] = { "Venezuelan Cariban", nil, "sai-car", aliases = {"Venezuelan Carib", "Venezuelan", "Venezuelano"}, } m["sai-wic"] = { "Wichí", 3027047, } m["sai-wit"] = { "Witotoan", 43079317, aliases = {"Huitotoan", "Uitotoan"}, } m["sai-ynm"] = { "Yanomami", nil, aliases = {"Yanomam", "Shamatari", "Yamomami", "Yanomaman"}, } m["sai-yuk"] = { "Yukpan", nil, "sai-car", aliases = {"Yukpa", "Yukpano", "Yukpa-Japreria"}, } m["sai-zam"] = { "Zamucoan", 3048461, aliases = {"Samúkoan"}, } m["sai-zap"] = { "Zaparoan", 33911, aliases = {"Záparoan", "Saparoan", "Sáparoan", "Záparo", "Zaparoano", "Zaparoana"}, } m["sal"] = { "Salish", 33985, } m["sdv"] = { "Eastern Sudanic", 2036148, "ssa", } m["sdv-bri"] = { "Bari", nil, "sdv-nie", } m["sdv-daj"] = { "Daju", 956724, "sdv", } m["sdv-dnu"] = { "Dinka-Nuer", nil, "sdv-niw", } m["sdv-eje"] = { "Eastern Jebel", 3408878, "sdv", } m["sdv-kln"] = { "Kalenjin", 637228, "sdv-nis", } m["sdv-lma"] = { "Lotuko-Maa", nil, "sdv-nie", } m["sdv-lon"] = { "Northern Luo", nil, "sdv-luo", } m["sdv-los"] = { "Southern Luo", 7570103, "sdv-luo", } m["sdv-luo"] = { "Luo", nil, "sdv-niw", } m["sdv-nes"] = { "Northern Eastern Sudanic", 4810496, "sdv", aliases = {"Astaboran", "Ek Sudanic"}, } m["sdv-nie"] = { "Eastern Nilotic", 153795, "sdv-nil", } m["sdv-nil"] = { "Nilotic", 513408, "sdv", } m["sdv-nis"] = { "Southern Nilotic", 1552410, "sdv-nil", } m["sdv-niw"] = { "Western Nilotic", 3114989, "sdv-nil", } m["sdv-nma"] = { "Nandi-Markweta", nil, "sdv-kln", } m["sdv-nyi"] = { "Nyima", 11688746, "sdv-nes", aliases = {"Nyimang"}, } m["sdv-tmn"] = { "Taman", 3408873, "sdv-nes", aliases = {"Tamaic"}, } m["sdv-ttu"] = { "Teso-Turkana", 7705551, "sdv-nie", aliases = {"Ateker"}, } m["sel"] = { "Selkup", 34008, "syd", } m["sem"] = { "Semitic", 34049, "afa", } m["sem-ara"] = { "Aramaic", 28602, "sem-nwe", protoLanguage = "arc", } m["sem-arb"] = { "Arabic", 164667, "sem-cen", protoLanguage = "ar", } m["sem-are"] = { "Eastern Aramaic", 3410322, "sem-ara", } m["sem-arw"] = { "Western Aramaic", 3394214, "sem-ara", } m["sem-ase"] = { "Southeastern Aramaic", 3410322, "sem-are", } m["sem-can"] = { "Canaanite", 747547, "sem-nwe", } m["sem-cen"] = { "Central Semitic", 3433228, "sem-wes", } m["sem-cna"] = { "Central Neo-Aramaic", 3410322, "sem-are", } m["sem-eas"] = { "East Semitic", 164273, "sem", } m["sem-eth"] = { "Ethiopian Semitic", 163629, "sem-wes", aliases = {"Afro-Semitic", "Ethiopian", "Ethiopic", "Ethiosemitic"}, } m["sem-nna"] = { "Northeastern Neo-Aramaic", 2560578, "sem-are", } m["sem-nwe"] = { "Northwest Semitic", 162996, "sem-cen", } m["sem-osa"] = { "Old South Arabian", 35025, "sem-cen", aliases = {"Epigraphic South Arabian", "Sayhadic"}, } m["sem-sar"] = { "Modern South Arabian", 1981908, "sem-wes", } m["sem-wes"] = { "West Semitic", 124901, "sem", } m["sgn"] = { "sign", 34228, "qfa-not", } m["sgn-asl"] = { "American Sign Languages", nil, "sgn-fsl", } m["sgn-fsl"] = { "French Sign Languages", 5501921, "sgn", } m["sgn-gsl"] = { "German Sign Languages", 5551235, "sgn", } m["sgn-jsl"] = { "Japanese Sign Languages", 11722508, "sgn", } m["sio"] = { "Siouan", 34181, "nai-sca", } m["sio-dhe"] = { "Dhegihan", 3217420, "sio-msv", } m["sio-dkt"] = { "Dakotan", 4154122, "sio-msv", } m["sio-mor"] = { "Missouri River Siouan", 26807266, "sio", } m["sio-msv"] = { "Mississippi Valley Siouan", 12637104, "sio", } m["sio-ohv"] = { "Ohio Valley Siouan", 21070931, "sio", } m["sit"] = { "Sino-Tibetan", 45961, aliases = {"Trans-Himalayan"}, } m["sit-aao"] = { "Central Naga", 615474, "sit", } m["sit-alm"] = { "Almora", nil, "sit-whm", } m["sit-bai"] = { "Bai", 35103, "sit-mba", } m["sit-bdi"] = { "Bodish", 1814078, "sit", } m["sit-cln"] = { "Cai-Long", 107182612, "sit-mba", aliases = {"Ta-Li"}, } m["sit-dhi"] = { "Dhimalish", 1207648, "sit", } m["sit-ebo"] = { "East Bodish", 56402, "sit-bdi", } m["sit-egy"] = { "East rGyalrongic", 832026, "sit-rgy", } m["sit-ers"] = { "Ersuic", 56335, "sit", } m["sit-gma"] = { "Greater Magaric", 55612963, "sit", } m["sit-gsi"] = { "Greater Siangic", 52698851, "sit", } m["sit-hrs"] = { "Hrusish", 1632501, "sit", aliases = {"Southeast Kamengic"}, } m["sit-jnp"] = { "Jingphoic", nil, "sit-jpl", aliases = {"Jingpho"}, } m["sit-jpl"] = { "Kachin-Luic", 1515454, "tbq-bkj", aliases = {"Jingpho-Luish", "Jingpho-Asakian", "Kachinic"}, } m["sit-kch"] = { "Konyak-Chang", nil, "sit-kon", } m["sit-kha"] = { "Kham", 33305, "sit-gma", } m["sit-khb"] = { "Kho-Bwa", 6401917, "sit", aliases = {"Bugunish", "Kamengic"}, } m["sit-khw"] = { "Western Kho-Bwa", nil, "sit-khb", } m["sit-khc"] = { "Chug-Lish", nil, "sit-khw", aliases = {"Duhumbi-Khispi"}, } m["sit-khm"] = { "Mey-Sartang", nil, "sit-khw", aliases = {"Sartang-Sherdukpen"}, } m["sit-kic"] = { "Central Kiranti", nil, "sit-kir", } m["sit-kie"] = { "Eastern Kiranti", nil, "sit-kir", } m["sit-kin"] = { "Kinnauric", nil, "sit-whm", aliases = {"Kinnauri"}, } m["sit-kir"] = { "Kiranti", 922148, "sit", } m["sit-kiw"] = { "Western Kiranti", 922148, "sit-kir", } m["sit-kon"] = { "Northern Naga", 774590, "tbq-bkj", aliases = {"Konyakian", "Konyak"}, } m["sit-kyk"] = { "Kyirong-Kagate", 6450957, "sit-tib", } m["sit-lab"] = { "Ladakhi-Balti", 6450957, "sit-tib", } m["sit-las"] = { "Lahuli-Spiti", 6473510, "sit-tib", } m["sit-luu"] = { "Luish", 55621439, "sit-jpl", aliases = {"Asakian", "Sak"}, } m["sit-mar"] = { "Maringic", nil, "sit-tma", } m["sit-mba"] = { "Macro-Bai", 16963847, "sit-sba", aliases = {"Greater Bai"}, } m["sit-mdz"] = { "Midzu", 6843504, "sit", aliases = {"Geman", "Midzuish", "Miju-Meyor", "Southern Mishmi"}, } m["sit-mnz"] = { "Mondzish", 6898839, "tbq-lob", aliases = {"Mangish"}, } m["sit-mru"] = { "Mruic", 16908870, "sit", aliases = {"Mru-Hkongso"}, } m["sit-nas"] = { "Naish", 25047956, "sit-nax", } m["sit-nax"] = { "Naic", 6982999, "tbq-buq", aliases = {"Naxish"}, } m["sit-nba"] = { "Northern Bai", 122463830, "sit-bai", } m["sit-new"] = { "Newaric", 55625069, "sit", } m["sit-nng"] = { "Nungish", 1515482, "sit", aliases = {"Nung"}, } m["sit-qia"] = { "Qiangic", 1636765, "tbq-buq", } m["sit-rgy"] = { "Rgyalrongic", 56936, "sit-qia", aliases = {"Jiarongic"}, } m["sit-sba"] = { "Sino-Bai", nil, "sit", aliases = {"Greater Bai"}, } m["sit-tam"] = { "Tamangic", 3309439, "sit", aliases = {"West Bodish"}, } m["sit-tan"] = { "Tani", 3217538, "sit", } m["sit-tib"] = { "Tibetic", 1641150, "sit-bdi", protoLanguage = "otb", } m["sit-tja"] = { "Tujia", nil, "sit", } m["sit-tma"] = { "Tangkhul-Maring", nil, "sit", } m["sit-tng"] = { "Tangkhulic", 1516657, "sit-tma", aliases = {"Tangkhul"}, } m["sit-tno"] = { "Tangsa-Nocte", nil, "sit-kon", } m["sit-tsk"] = { "Tshangla", nil, "sit", } m["sit-wgy"] = { "West rGyalrongic", nil, "sit-rgy" } m["sit-whm"] = { "West Himalayish", 2301695, "sit", } m["sit-zem"] = { "Zeme", 189291, "sit", aliases = {"Zeliangrong", "Zemeic"}, } m["sla"] = { "Slavic", 23526, "ine-bsl", aliases = {"Slavonic"}, } m["smi"] = { "Sami", 56463, "urj", aliases = {"Saami", "Samic", "Saamic"}, } m["son"] = { "Songhay", 505198, "ssa", aliases = {"Songhai"}, } m["sqj"] = { "Albanian", 8748, "ine", } m["ssa"] = { "Nilo-Saharan", -- possibly not a genetic grouping 33705, } m["ssa-fur"] = { "Fur", 2989512, "ssa", } m["ssa-klk"] = { "Kuliak", 1791476, "ssa", aliases = {"Rub"}, } m["ssa-kom"] = { "Koman", 1781084, "ssa", } m["ssa-sah"] = { "Saharan", 1757661, "ssa", } m["syd"] = { "Samoyedic", 34005, "urj", aliases = {"Samoyed", "Samodeic"}, } m["syd-ene"] = { "Enets", 29942, "syd", } m["tai"] = { "Tai", 749720, "qfa-bet", aliases = {"Daic"}, } m["tai-wen"] = { "Wenma-Southwestern Tai", nil, "tai", } m["tai-tay"] = { "Tày", nil, "tai-wen", } m["tai-sap"] = { "Sapa-Southwestern Tai", nil, "tai-wen", aliases = {"Sapa-Thai"}, } m["tai-swe"] = { "Southwestern Tai", 10889250, "tai-sap", } m["tai-cho"] = { "Chongzuo Tai", 13216, "tai", } m["tai-cen"] = { "Central Tai", 5061891, "tai", } m["tai-nor"] = { "Northern Tai", 7059014, "tai", } m["tbq"] = { "Tibeto-Burman", 34064, "sit", } m["tbq-anp"] = { "Angami-Pochuri", 530460, "sit", } m["tbq-axi"] = { "Axioid", nil, "tbq-sel", } m["tbq-bdg"] = { "Bodo-Garo", 4090000, "tbq-bkj", } m["tbq-bis"] = { "Bisoid", 48844742, "tbq-slo", } m["tbq-bka"] = { "Bi-Ka", 12627890, "tbq-slo", } m["tbq-bkj"] = { "Sal", 889900, "sit", -- Brahmaputran appears to be Glottolog's term aliases = {"Bodo-Konyak-Jinghpaw", "Brahmaputran", "Jingpho-Konyak-Bodo"}, } m["tbq-brm"] = { "Burmish", 865713, "tbq-lob", } m["tbq-buq"] = { "Burmo-Qiangic", 16056278, "sit", aliases = {"Eastern Tibeto-Burman"}, } m["tbq-drp"] = { "Downriver Phula", 7188378, "tbq-rph", } m["tbq-han"] = { "Hanoid", 17004185, "tbq-slo", } m["tbq-hph"] = { "Highland Phula", nil, "tbq-sel", } m["tbq-jin"] = { "Jino", 6202716, "tbq-slo", } m["tbq-kzh"] = { "Kazhuoish", 48834669, "tbq-lol", } m["tbq-kuk"] = { "Kuki-Chin", 832413, "sit", aliases = {"Kukish", "South-Central Tibeto-Burman"}, } m["tbq-lal"] = { "Lalo", 56548, "tbq-lso", } m["tbq-lho"] = { "Lahoish", nil, "tbq-lol", } m["tbq-llo"] = { "Lipo-Lolopo", nil, "tbq-lso", } m["tbq-lob"] = { "Lolo-Burmese", 1635712, "tbq-buq", } m["tbq-lol"] = { "Loloish", 37035, "tbq-lob", aliases = {"Yi", "Ngwi", "Nisoic"}, } m["tbq-lso"] = { "Lisoish", 6559055, "tbq-lol", } m["tbq-lwo"] = { "Lawoish", 48847673, "tbq-lol", } m["tbq-muj"] = { "Muji", 11221327, "tbq-hph", } m["tbq-nas"] = { "Nasoid", nil, "tbq-nlo", } m["tbq-nis"] = { "Nisu", 56404, "tbq-nlo", } m["tbq-nlo"] = { "Northern Loloish", 7058676, "tbq-nso", } m["tbq-nso"] = { "Nisoish", 56990, "tbq-lol", } m["tbq-nus"] = { "Nusoish", 114245231, "tbq-lol", } m["tbq-phw"] = { "Phowa", 7187959, "tbq-hph", } m["tbq-rph"] = { "Riverine Phula", nil, "tbq-sel", } m["tbq-sel"] = { "Southeastern Loloish", 16111894, "tbq-nso", } m["tbq-sil"] = { "Siloid", 60787071, "tbq-slo", } m["tbq-slo"] = { "Southern Loloish", 5649340, "tbq-lol", } m["tbq-tal"] = { "Taloid", 48804018, "tbq-lso", } m["tbq-urp"] = { "Upriver Phula", 7187058, "tbq-rph", } m["trk"] = { "Turkic", 34090, } m["trk-cmn"] = { "Common Turkic", 1126028, "trk", aliases = {"Shaz Turkic", "Shaz-Turkic"}, } m["trk-kar"] = { "Karluk", 703173, "trk-cmn", aliases = {"Qarluq", "Uyghur-Uzbek", "Southeastern Turkic"}, } m["trk-kbu"] = { "Kipchak-Bulgar", 3512539, "trk-kip", aliases = {"Uralian", "Uralo-Caspian"}, } m["trk-kcu"] = { "Kipchak-Cuman", 4370412, "trk-kip", aliases = {"Ponto-Caspian"}, } m["trk-kip"] = { "Kipchak", 1339898, "trk-cmn", -- Russian Wikipedia article [[w:ru:Западнотюркские_языки]] says "Western Turkic" is used by N.A. Baskakov and includes Oghuz, Kipchak and Karluk. -- Azerbaijani Wikipedia article [[w:az:Qərbi_türk_dilləri]] clarifies that "Western Turkic" is not a clade. other_names = {"Western Turkic"}, aliases = {"Kypchak", "Qypchaq", "Northwestern Turkic"}, protoLanguage = "qwm", } m["trk-kkp"] = { "Kyrgyz-Kipchak", 4221189, "trk-kip", } m["trk-kno"] = { "Kipchak-Nogai", 4326954, "trk-kip", aliases = {"Aralo-Caspian"}, } m["trk-nsb"] = { "North Siberian Turkic", 4537269, "trk-sib", aliases = {"Northern Siberian Turkic"}, } m["trk-ogr"] = { "Oghur", 1422731, "trk", aliases = {"Lir-Turkic", "r-Turkic"}, } m["trk-ogz"] = { "Oghuz", 494600, "trk-cmn", aliases = {"Southwestern Turkic"}, } m["trk-sib"] = { "Siberian Turkic", 354353, "trk-cmn", other_names = {"Northern Turkic"}, -- per [[w:ru:Восточнотюркские_языки]], "Eastern Turkic" is an alias for Siberian Turkic in the work of O.A. Mudrak, -- but has a different non-clade meaning in the older work of N.A. Baskakov. aliases = {"Eastern Turkic", "Northeastern Turkic"}, } m["trk-ssb"] = { "South Siberian Turkic", nil, "trk-sib", aliases = {"Southern Siberian Turkic"}, } m["tup"] = { "Tupian", 34070, aliases = {"Tupi"}, } m["tup-gua"] = { "Tupi-Guarani", 148610, "tup", aliases = {"Tupí-Guaraní"}, } m["tuw"] = { "Tungusic", 34230, aliases = {"Manchu-Tungus", "Tungus"}, } m["tuw-ewe"] = { "Ewenic", 105889448, "tuw", aliases = {"Northern Tungusic"}, } m["tuw-jrc"] = { "Jurchenic", 105889432, "tuw", aliases = {"Manchuric"}, } m["tuw-nan"] = { "Nanaic", 105889264, "tuw", } m["tuw-udg"] = { "Udegheic", 105889266, "tuw", } m["urj"] = { "Uralic", 34113, varieties = {"Finno-Ugric"}, } m["urj-fin"] = { "Finnic", 33328, "urj", aliases = {"Baltic-Finnic", "Balto-Finnic", "Fennic"}, } m["urj-mdv"] = { "Mordvinic", 627313, "urj", } m["urj-prm"] = { "Permic", 161493, "urj", } m["urj-ugr"] = { "Ugric", 156631, "urj", } m["wak"] = { "Wakashan", 60069, } m["wen"] = { "Sorbian", 25442, "zlw", aliases = {"Lusatian", "Wendish"}, } m["xgn"] = { "Mongolic", 33750, "qfa-xgs", aliases = {"Mongolian"}, } m["xgn-cen"] = { "Central Mongolic", 28719447, "xgn", protoLanguage = "xng-lat", } m["xgn-sou"] = { "Southern Mongolic", nil, "xgn", protoLanguage = "xng-ear", } m["xgn-shr"] = { "Shirongolic", 107539435, "xgn-sou", } m["xme"] = { "Median", nil, "ira-mpr", protoLanguage = "xme-old", } m["xme-ttc"] = { "Tatic", nil, "xme", } m["xnd"] = { "Na-Dene", 26986, "qfa-dny", aliases = {"Na-Dené"}, } m["xsc"] = { "Scythian", nil, "ira-nei", } m["xsc-sak"] = { "Saka", nil, "xsc-skw", aliases = {"Sakan"}, } m["xsc-sar"] = { "Sarmatian", nil, "xsc", } m["xsc-skw"] = { "Saka-Wakhi", nil, "xsc", } m["yok"] = { "Yokuts", 34249, "nai-you", aliases = {"Yokutsan", "Mariposan", "Mariposa"}, } m["ypk"] = { "Yupik", 27970, "esx-esk", aliases = {"Yup'ik", "Yuit"}, } m["yrk"] = { "Nenets", 36452, "syd", } m["zhx"] = { "Sinitic", 33857, "sit-sba", aliases = {"Chinese"}, protoLanguage = "och", } m["zhx-com"] = { "Coastal Min", 20667215, "zhx-min", } m["zhx-inm"] = { "Inland Min", 20667237, "zhx-min", } m["zhx-man"] = { "Mandarinic", nil, "zhx", protoLanguage = "cmn-ear", } m["zhx-min"] = { "Min", 56504, "zhx", } m["zhx-nan"] = { "Southern Min", 36495, "zhx-com", } m["zhx-pin"] = { "Pinghua", 2735715, "zhx", protoLanguage = "ltc", } m["zhx-yue"] = { "Yue", 7033959, "zhx", protoLanguage = "ltc", } m["zle"] = { "East Slavic", 144713, "sla", } m["zls"] = { "South Slavic", 146665, "sla", } m["zlw"] = { "West Slavic", 145852, "sla", } m["zlw-lch"] = { "Lechitic", 742782, "zlw", aliases = {"Lekhitic"}, } m["zlw-pom"] = { "Pomeranian", nil, "zlw-lch", } m["znd"] = { "Zande", 8066072, "nic-ubg", } return require("Module:languages").finalizeData(m, "family") 3btxhofjv1yzvyhvihh8364k1f3zzw6 828 5963 17399 2026-07-13T08:18:24Z Hiyuune 6766 + 17399 Scribunto text/plain local export = {} local string_utilities_module = "Module:string utilities" local table_module = "Module:table" -- In a locally installed Docker container containing Wiktionary, Wikibase is typically not installed because it's -- a real pain to get working properly. In such a case, `mw.wikibase` returns nil. We now have checks in the code -- below so it does reasonable things in the absence of Wikibase. local wikibase = mw.wikibase local category_name_has_suffix -- defined as export.categoryNameHasSuffix below local get_entity = wikibase and wikibase.getEntity or nil local get_entity_id_for_title = wikibase and wikibase.getEntityIdForTitle or nil local gsub = string.gsub local ipairs = ipairs local match = string.match local select = select local sitelink = wikibase and wikibase.sitelink or nil local type = type local umatch = mw.ustring.match --[==[ Loaders for functions in other modules, which overwrite themselves with the target function when called. This ensures modules are only loaded when needed, retains the speed/convenience of locally-declared pre-loaded functions, and has no overhead after the first call, since the target functions are called directly in any subsequent calls.]==] local function case_insensitive_pattern(...) case_insensitive_pattern = require(string_utilities_module).case_insensitive_pattern return case_insensitive_pattern(...) end local function table_flatten(...) table_flatten = require(table_module).flatten return table_flatten(...) end --[==[ Loaders for objects, which load data (or some other object) into some variable, which can then be accessed as "foo or get_foo()", where the function get_foo sets the object to "foo" and then returns it. This ensures they are only loaded when needed, and avoids the need to check for the existence of the object each time, since once "foo" has been set, "get_foo" will not be called again.]==] local content_lang local function get_content_lang() content_lang, get_content_lang = mw.getContentLanguage(), nil return content_lang end -- Implementation of getAliases() for languages, etymology languages, -- families, scripts and writing systems. function export.getAliases(self) local aliases = self._aliases if aliases == nil then aliases = (self._data or self).aliases or {} self._aliases = aliases end return aliases end -- Implementation of getVarieties() for languages, etymology languages, -- families, scripts and writing systems. If `flatten` is passed in, -- flatten down to a list of strings; otherwise, keep the structure. function export.getVarieties(self, flatten) local varieties = self._varieties if varieties == nil then varieties = (self._data or self).varieties or {} self._varieties = varieties end if not flatten then return varieties end local flattened_varieties = self._flattened_varieties if flattened_varieties == nil then flattened_varieties = table_flatten(varieties) self._flattened_varieties = flattened_varieties end return flattened_varieties end -- Implementation of getOtherNames() for languages, etymology languages, -- families, scripts and writing systems. function export.getOtherNames(self) local other_names = self._other_names if other_names == nil then other_names = (self._data or self).other_names or {} self._other_names = other_names end return other_names end -- Implementation of getAllNames() for languages, etymology languages, -- families, scripts and writing systems. If `notCanonical` is set, -- the canonical name will be excluded. function export.getAllNames(self) local all_names = self._allNames if all_names == nil then all_names = table_flatten{ self:getCanonicalName(), self:getAliases(), self:getVarieties(), self:getOtherNames(), } self._allNames = all_names end return all_names end function export.hasType(self, ...) local n = select("#", ...) if n == 0 then error("Must specify at least one type.") end local types = self:getTypes() if not types[...] then return false elseif n == 1 then return true end local args = {...} for i = 2, n do if not types[args[i]] then return false end end return true end -- Implementation of template-callable getByCode() function for languages, -- etymology languages, families and scripts. `item` is the language, -- family or script in question; `args` is the arguments passed in by the -- module invocation; `extra_processing`, if specified, is a function of -- one argument (the requested property) and should return the value to -- be returned to the caller, or nil if the property isn't recognized. -- `extra_processing` is called after special-cased properties are handled -- and before general-purpose processing code that works for all string -- properties. function export.templateGetByCode(args, extra_processing) -- The item that the caller wanted to look up. local item, itemname, list = args[1], args[2] if itemname == "getAllNames" then list = item:getAllNames() elseif itemname == "getOtherNames" then list = item:getOtherNames() elseif itemname == "getAliases" then list = item:getAliases() elseif itemname == "getVarieties" then list = item:getVarieties(true) end if list then local index = args[3]; if index == "" then index = nil end index = tonumber(index or error("Numeric index of the desired item in the list (parameter 3) has not been specified.")) return list[index] or "" end if itemname == "getFamily" and item.getFamily then return item:getFamily():getCode() end if extra_processing then local retval = extra_processing(itemname) if retval then return retval end end if item[itemname] then local ret = item[itemname](item) if type(ret) == "string" then return ret end error("The function \"" .. itemname .. "\" did not return a string value.") end error("Requested invalid item name \"" .. itemname .. "\".") end -- Implementation of getCommonsCategory() for languages, etymology languages, -- families, scripts and writing systems. function export.getWikidataItem(self) local item = self._WikidataItem if item == nil then item = (self._data or self)[2] -- If the value is nil, it's cached as false. item = item ~= nil and (type(item) == "number" and "Q" .. item or item) or false self._WikidataItem = item end return item or nil end do local function get_wiki_article(self, project) local article -- If the project is enwiki, check the language data. if project == "enwiki" then article = (self._data or self).wikipedia_article if article then return article end end -- Otherwise, check the Wikidata item for a sitelink. local item = self:getWikidataItem() article = item and sitelink and sitelink(item, project) or false if article then return article end -- If there's still no article, try the parent (if any). local get_parent = self.getParent if get_parent then local parent = get_parent(self) if parent then return get_wiki_article(parent, project) end end return false end -- Implementation of getWikipediaArticle() for languages, etymology languages, -- families, scripts and writing systems. function export.getWikipediaArticle(self, noCategoryFallback, project) if project == nil then project = "enwiki" end local article if project == "enwiki" then article = self._wikipedia_article if article == nil then article = get_wiki_article(self, project) self._wikipedia_article = article end else -- If the project isn't enwiki, default to no category fallback, but -- this can be overridden by specifying the value `false`. if noCategoryFallback == nil then noCategoryFallback = true end local non_en_wikipedia_articles = self._non_en_wikipedia_articles if non_en_wikipedia_articles == nil then non_en_wikipedia_articles = {} self._non_en_wikipedia_articles = non_en_wikipedia_articles else article = non_en_wikipedia_articles[project] end if article == nil then article = get_wiki_article(self, project) non_en_wikipedia_articles[project] = article end end if article or noCategoryFallback then return article or nil end return (gsub(self:getCategoryName(), "Creole language", "Creole")) end end do local function get_commons_cat_claim(item) if item then local entity = get_entity and get_entity(item) or nil if entity then -- P373 is the "Commons category" property. local claim = entity:getBestStatements("P373")[1] return claim and ("Category:" .. claim.mainsnak.datavalue.value) or nil end end end local function get_commons_cat_sitelink(item) if item then local commons_sitelink = sitelink and sitelink(item, "commonswiki") or nil -- Reject any sitelinks that aren't categories. return commons_sitelink and match(commons_sitelink, "^Category:") and commons_sitelink or nil end end local function get_commons_cat(self) -- Checks are in decreasing order of likelihood for a useful match. -- Get the Commons Category claim from the object's item. local lang_item = self:getWikidataItem() local category = get_commons_cat_claim(lang_item) if category then return category end -- Otherwise, try the object's category's item. local langcat_item = get_entity_id_for_title and get_entity_id_for_title("Category:" .. self:getCategoryName()) or nil category = get_commons_cat_claim(langcat_item) if category then return category end -- If there's no P373 claim, there might be a sitelink on the -- object's category's item. category = get_commons_cat_sitelink(langcat_item) if category then return category end -- Otherwise, try for a sitelink on the object's own item. category = get_commons_cat_sitelink(lang_item) if category then return category end -- If there's still no category, try the parent (if any). local get_parent = self.getParent if get_parent then local parent = get_parent(self) if parent then return get_commons_cat(parent) end end return false end -- Implementation of getCommonsCategory() for languages, etymology -- languages, families, scripts and writing systems. function export.getCommonsCategory(self) local category category = self._commons_category -- Nil values cached as false. if category ~= nil then return category or nil end category = get_commons_cat(self) self._commons_category = category return category or nil end end function export.categoryNameHasSuffix(name, suffixes) for _, suffix in ipairs(suffixes) do if umatch(name, "%f[%w]" .. case_insensitive_pattern(suffix, "^.") .. "$") then return false end end return true end category_name_has_suffix = export.categoryNameHasSuffix function export.categoryNameToCode(name, suffix, data, suffixes) local truncated = match(name, "(.*)" .. suffix .. "$") if truncated and category_name_has_suffix(truncated, suffixes) then local code = data[truncated] or data[(content_lang or get_content_lang()):lcfirst(truncated)] if code ~= nil then return code end end if not category_name_has_suffix(name, suffixes) then return data[name] or data[(content_lang or get_content_lang()):lcfirst(name)] end return nil end return export a3jnrcv48h961dt8eg59fpggk4e1nkk 828 5964 17400 2026-07-13T08:19:38Z Hiyuune 6766 + 17400 Scribunto text/plain local debug_track_module = "Module:debug/track" local string_gline_module = "Module:string/gline" local match = string.match local new_title = mw.title.new local require = require local traceback = debug.traceback local function debug_track(...) debug_track = require(debug_track_module) return debug_track(...) end local function gline(...) gline = require(string_gline_module) return gline(...) end local params_title local function get_params_title() params_title, get_params_title = new_title("parameters", 828), nil return params_title end return function(page, param_name) debug_track("parameters/" .. page) if param_name ~= nil then debug_track("parameters/" .. page .. "/" .. param_name .. "=") end -- Check through the traceback to get the calling module and function. local mod_title for line in gline((traceback())) do local mod, func = match(line, "^\t*(.-):%d+: in function (.*)$") -- Must match a conventional module, not a tail call, C function, in- -- built Scribunto file etc. If `mod` matches `mod_title`, it means the -- module has been seen before, so there is nothing else to check. if mod and not (mod_title and mod == mod_title.prefixedText) then mod_title = new_title(mod) if mod_title and mod_title.namespace == 828 and not ( mod_title == (params_title or get_params_title()) or mod_title:isSubpageOf(params_title) ) then mod = mod_title.text debug_track("parameters/" .. page .. "/" .. mod) -- traceback() encloses function names in single quotes. local funcname = match(func, "^'(.*)'$") if funcname then debug_track("parameters/" .. page .. "/" .. mod .. "/" .. funcname) return end -- WHen a function is unnamed, line numbers are given after the -- module name in angle brackets, directly after a separating -- colon. local funcline = match(func, "^<.-:(%d+)>$") if funcline then debug_track("parameters/" .. page .. "/" .. mod .. ":" .. funcline) end return end end end end ep6rfkuslbwvncu36j3fa17iqe4seb6 828 5965 17401 2026-07-13T08:20:42Z Hiyuune 6766 + 17401 Scribunto text/plain local error = error local find = string.find local gmatch = string.gmatch local match = string.match local sub = string.sub --[==[ Iterates over the lines in a string, treating {"\n"}, {"\r"} and {"\r\n"} as new lines. The optional {skip} parameter determines whether certain lines are skipped: * {NONE}: none (default). * {EMPTY}: empty lines: lines with a length of 0, consisting of no characters. * {BLANK}: blank lines: empty lines and lines which only consist of whitespace characters.]==] return function(str, skip) -- Use gmatch() for EMPTY and BLANK, for speed. if skip == "EMPTY" then return gmatch(str, "[^\n\r]+") elseif skip == "BLANK" then return gmatch(str, "[^\n\r]-%S[^\n\r]*") elseif not (skip == nil or skip == "NONE") then error("bad argument #2 to 'string/gline' (expected NONE, EMPTY or BLANK)", 2) end local start, linechar, flag = 1 if not find(str, "\n", nil, true) then if not find(str, "\r", nil, true) then -- No newlines: return `str` on the first iteration then end. return function() if flag then return end flag = true return str end end linechar = "\r" elseif find(str, "\r", nil, true) then -- Newline could be "\n", "\r" or "\r\n" (but not "\n\r"). return function() if not flag then local line, nl, pos = match(str, "^([^\n\r]*)([\n\r]\n?)()", start) if not line then flag = true return sub(str, start) end -- If `nl` is "\r\n" it should be treated as a single newline, -- but if it's "\n\n" it needs to be treated as two separate -- newlines, so set `flag` to 2 to avoid an unnecessary match() -- call on the next iteration. if nl == "\n\n" then flag = 2 end start = pos return line elseif flag == 2 then flag = nil return "" end end else linechar = "\n" end -- Newline is either "\n" or "\r", depending on which has been found. return function() if flag then return end local pos = find(str, linechar, start, true) if not pos then flag = true return sub(str, start) end local line = sub(str, start, pos - 1) start = pos + 1 return line end end r6wdku3u8kbsa2pnl1f07kxp328mzdt 828 5966 17402 2026-07-13T08:21:07Z Hiyuune 6766 + 17402 Scribunto text/plain local export = {} local languages_module = "Module:languages" local language_like_module = "Module:language-like" local load_module = "Module:load" local wm_languages_data_module = "Module:wikimedia languages/data" local get_by_code -- Defined below. local gmatch = string.gmatch local is_known_language_tag = mw.language.isKnownLanguageTag local make_object -- Defined below. local require = require local setmetatable = setmetatable local type = type --[==[ Loaders for functions in other modules, which overwrite themselves with the target function when called. This ensures modules are only loaded when needed, retains the speed/convenience of locally-declared pre-loaded functions, and has no overhead after the first call, since the target functions are called directly in any subsequent calls.]==] local function get_lang(...) get_lang = require(languages_module).getByCode return get_lang(...) end local function get_lang_data_module_name(...) get_lang_data_module_name = require(languages_module).getDataModuleName return get_lang_data_module_name(...) end local function load_data(...) load_data = require(load_module).load_data return load_data(...) end --[==[ Loaders for objects, which load data (or some other object) into some variable, which can then be accessed as "foo or get_foo()", where the function get_foo sets the object to "foo" and then returns it. This ensures they are only loaded when needed, and avoids the need to check for the existence of the object each time, since once "foo" has been set, "get_foo" will not be called again.]==] local wm_languages_data local function get_wm_languages_data() wm_languages_data, get_wm_languages_data = load_data(wm_languages_data_module), nil return wm_languages_data end local WikimediaLanguage = {} WikimediaLanguage.__index = WikimediaLanguage function WikimediaLanguage:getCode() return self._code end function WikimediaLanguage:getCanonicalName() return self._data[1] end --function WikimediaLanguage:getAllNames() -- return self._data.names --end --[==[Returns a table of types as a lookup table (with the types as keys). Currently, the only possible type is {Wikimedia language}.]==] function WikimediaLanguage:getTypes() local types = self._types if types == nil then types = {["Wikimedia language"] = true} local rawtypes = self._data.type if rawtypes then for t in gmatch(rawtypes, "[^,]+") do types[t] = true end end self._types = types end return types end --[==[Given a list of types as strings, returns true if the Wikimedia language has all of them.]==] function WikimediaLanguage:hasType(...) WikimediaLanguage.hasType = require(language_like_module).hasType return self:hasType(...) end function WikimediaLanguage:getWiktionaryLanguage() local object = self._wiktionaryLanguageObject if object == nil then object = get_lang(self._data.wiktionary_code, nil, "allow etym") self._wiktionaryLanguageObject = object end return object end -- Do NOT use this method! -- All uses should be pre-approved on the talk page! function WikimediaLanguage:getData() return self._data end --[==[Returns the name of the module containing the Wikimedia language's data (if any). Currently, this is always [[Module:wikimedia languages/data]].]==] function WikimediaLanguage:getDataModuleName() return wm_languages_data_module end function export.makeObject(code, data) local data_type = type(data) if data_type ~= "table" then error(("bad argument #2 to 'makeObject' (table expected, got %s)"):format(data_type)) end return setmetatable({_data = data, _code = code}, WikimediaLanguage) end make_object = export.makeObject function export.getByCode(code) -- Only accept codes the software recognises. if not is_known_language_tag(code) then return nil end local data = (wm_languages_data or get_wm_languages_data())[code] -- If there is no specific Wikimedia code, then "borrow" the information -- from the general Wiktionary language code. local name, wiktionary_code if data ~= nil then name, wiktionary_code = data[1], data.wiktionary_code if not (name == nil or wiktionary_code == nil) then return make_object(code, data) end end -- Get the associated Wiktionary language, using the wiktionary_code key or -- else the input code. if wiktionary_code == nil then wiktionary_code = code end local lang = get_lang(wiktionary_code, nil, "allow etym", "allow family") if lang ~= nil then return make_object(code, { name == nil and lang:getCanonicalName() or name, wiktionary_code = wiktionary_code, }) end -- If there's no Wiktionary language for the relevant code, throw an error. -- This should never happen. local msg, arg3 if data == nil then msg = "code '%s' is a valid Wikimedia language code, but there is no corresponding data in [[%s]], [[%s]] or [[Module:families/data]]" elseif wiktionary_code ~= code then msg = "code '%s' is a valid Wikimedia language code and has data in [[%s]], but its 'wiktionary_code' key '%s' is not valid" arg3 = wiktionary_code else msg = "code '%s' is a valid Wikimedia language code and has data in [[%s]], but no corresponding data in [[%s]] or [[Module:families/data]]" end error(msg:format(code, wm_languages_data_module, arg3 or get_lang_data_module_name(code))) end get_by_code = export.getByCode function export.getByCodeWithFallback(code) local object = get_by_code(code) if object ~= nil then return object end local lang = get_lang(code, nil, "allow etym") return lang ~= nil and lang:getWikimediaLanguages()[1] or nil end return export ef45ys2do2au63pewsjhq7qzjxsy1nr 828 5967 17403 2026-07-13T08:21:48Z Hiyuune 6766 + eo 17403 Scribunto text/plain local m = {} --[=[ This table maps *FROM* Wikimedia language codes (used in lang-specific Wikipedias and Wiktionaries) into English Wiktionary language codes. See also the following: * `interwiki_langs` in [[Module:translations/data]], which maps in the other direction (from English Wiktionary codes to foreign Wiktionaries), specifically for {{t+}}; * the `wiktprefix` field of the `metadata` variable in [[MediaWiki:Gadget-TranslationAdder-Data.js]], which also maps from English Wiktionary codes to foreign Wiktionaries for use with the TranslationAdder gadget; * the `clean` variable in [[MediaWiki:Gadget-TranslationAdder-Data.js]], which maps from user-entered foreign Wiktionary codes or names to English Wiktionary codes for use with the TranslationAdder gadget; * the `wikimedia_codes` field of the language data in e.g. [[Module:languages/data/2]], which also maps from English Wiktionary codes to Wikimedia language codes. ]=] m["als"] = { wiktionary_code = "gsw", } m["azb"] = { "South Azerbaijani", wiktionary_code = "az", } m["bat-smg"] = { wiktionary_code = "sgs", } m["be-tarask"] = { "Taraškievica Belarusian", wiktionary_code = "be", } m["bs"] = { "Bosnian", wiktionary_code = "sh", } m["bxr"] = { wiktionary_code = "bua", } m["diq"] = { wiktionary_code = "zza", } m["eml"] = { "Emiliano-Romagnolo", wiktionary_code = "egl", } m["fiu-vro"] = { wiktionary_code = "vro", } m["gn"] = { "Guarani", wiktionary_code = "gug", } m["gom"] = { "Goan Konkani", wiktionary_code = "kok", } m["hr"] = { "Croatian", wiktionary_code = "sh", } m["hu-formal"] = { "Formal Hungarian", wiktionary_code = "hu", } m["ksh"] = { wiktionary_code = "gmw-cfr", } m["ku"] = { "Kurdish", wiktionary_code = "kmr", } m["kv"] = { "Komi", wiktionary_code = "kpv", } m["nrm"] = { wiktionary_code = "nrf", } m["prs"] = { wiktionary_code = "fa", } m["roa-rup"] = { wiktionary_code = "rup", } m["roa-tara"] = { wiktionary_code = "roa-tar", } m["simple"] = { "Simple English", wiktionary_code = "en", } m["sr"] = { "Serbian", wiktionary_code = "sh", } m["zh-classical"] = { wiktionary_code = "ltc", } m["zh-min-nan"] = { "Southern Min", wiktionary_code = "nan-hbl", } m["zh-yue"] = { wiktionary_code = "yue", } return m lmump47f458boo0u2lfz8extxjktqmm 828 5968 17404 2026-07-13T08:22:36Z Hiyuune 6766 + 17404 Scribunto text/plain local export = {} --[=[ [[Unsupported titles]], pages with high memory usage, extraction modules and part-of-speech names are listed at [[Module:links/data]]. Other modules used: [[Module:script utilities]] [[Module:scripts]] [[Module:languages]] and its submodules [[Module:gender and number]] [[Module:debug/track]] ]=] local anchors_module = "Module:anchors" local debug_track_module = "Module:debug/track" local form_of_module = "Module:form of" local gender_and_number_module = "Module:gender and number" local languages_module = "Module:languages" local load_module = "Module:load" local memoize_module = "Module:memoize" local pages_module = "Module:pages" local pron_qualifier_module = "Module:pron qualifier" local scripts_module = "Module:scripts" local script_utilities_module = "Module:script utilities" local string_encode_entities_module = "Module:string/encode entities" local string_utilities_module = "Module:string utilities" local table_module = "Module:table" local utilities_module = "Module:utilities" local concat = table.concat local find = string.find local get_current_title = mw.title.getCurrentTitle local insert = table.insert local ipairs = ipairs local match = string.match local new_title = mw.title.new local pairs = pairs local remove = table.remove local sub = string.sub local toNFC = mw.ustring.toNFC local tostring = tostring local type = type local unstrip = mw.text.unstrip local NAMESPACE = get_current_title().nsText local function anchor_encode(...) anchor_encode = require(memoize_module)(mw.uri.anchorEncode, true) return anchor_encode(...) end local function debug_track(...) debug_track = require(debug_track_module) return debug_track(...) end local function decode_entities(...) decode_entities = require(string_utilities_module).decode_entities return decode_entities(...) end local function decode_uri(...) decode_uri = require(string_utilities_module).decode_uri return decode_uri(...) end -- Can't yet replace, as the [[Module:string utilities]] version no longer has automatic double-encoding prevention, which requires changes here to account for. local function encode_entities(...) encode_entities = require(string_encode_entities_module) return encode_entities(...) end local function extend(...) extend = require(table_module).extend return extend(...) end local function find_best_script_without_lang(...) find_best_script_without_lang = require(scripts_module).findBestScriptWithoutLang return find_best_script_without_lang(...) end local function format_categories(...) format_categories = require(utilities_module).format_categories return format_categories(...) end local function format_genders(...) format_genders = require(gender_and_number_module).format_genders return format_genders(...) end local function format_qualifiers(...) format_qualifiers = require(pron_qualifier_module).format_qualifiers return format_qualifiers(...) end local function get_current_L2(...) get_current_L2 = require(pages_module).get_current_L2 return get_current_L2(...) end local function get_lang(...) get_lang = require(languages_module).getByCode return get_lang(...) end local function get_script(...) get_script = require(scripts_module).getByCode return get_script(...) end local function language_anchor(...) language_anchor = require(anchors_module).language_anchor return language_anchor(...) end local function load_data(...) load_data = require(load_module).load_data return load_data(...) end local function request_script(...) request_script = require(script_utilities_module).request_script return request_script(...) end local function shallow_copy(...) shallow_copy = require(table_module).shallowCopy return shallow_copy(...) end local function split(...) split = require(string_utilities_module).split return split(...) end local function tag_text(...) tag_text = require(script_utilities_module).tag_text return tag_text(...) end local function tag_translit(...) tag_translit = require(script_utilities_module).tag_translit return tag_translit(...) end local function trim(...) trim = require(string_utilities_module).trim return trim(...) end local function u(...) u = require(string_utilities_module).char return u(...) end local function ulower(...) ulower = require(string_utilities_module).lower return ulower(...) end local function umatch(...) umatch = require(string_utilities_module).match return umatch(...) end local m_headword_data local function get_headword_data() m_headword_data = load_data("Module:headword/data") return m_headword_data end local function track(page, code) local tracking_page = "links/" .. page debug_track(tracking_page) if code then debug_track(tracking_page .. "/" .. code) end end local function selective_trim(...) -- Unconditionally trimmed charset. local always_trim = "\194\128-\194\159" .. -- U+0080-009F (C1 control characters) "\194\173" .. -- U+00AD (soft hyphen) "\226\128\170-\226\128\174" .. -- U+202A-202E (directionality formatting characters) "\226\129\166-\226\129\169" -- U+2066-2069 (directionality formatting characters) -- Standard trimmed charset. local standard_trim = "%s" .. -- (default whitespace charset) "\226\128\139-\226\128\141" .. -- U+200B-200D (zero-width spaces) always_trim -- If there are non-whitespace characters, trim all characters in `standard_trim`. -- Otherwise, only trim the characters in `always_trim`. selective_trim = function(text) if text == "" then return text end local trimmed = trim(text, standard_trim) if trimmed ~= "" then return trimmed end return trim(text, always_trim) end return selective_trim(...) end local function escape(text, str) local rep repeat text, rep = text:gsub("\\\\(\\*" .. str .. ")", "\5%1") until rep == 0 return (text:gsub("\\" .. str, "\6")) end local function unescape(text, str) return (text :gsub("\5", "\\") :gsub("\6", str)) end -- Remove bold, italics, soft hyphens, strip markers and HTML tags. local function remove_formatting(str) str = str :gsub("('*)'''(.-'*)'''", "%1%2") :gsub("('*)''(.-'*)''", "%1%2") :gsub("­", "") return (unstrip(str) :gsub("<[^<>]+>", "")) end --[==[Takes an input and splits on a double slash (taking account of escaping backslashes).]==] function export.split_on_slashes(text) if text:find("\\", nil, true) then track("escaped", "split_on_slashes") end text = split(escape(text, "//"), "//", true) or {} for i, v in ipairs(text) do text[i] = unescape(v, "//") if v == "" then text[i] = false end end return text end --[==[Takes a wikilink and outputs the link target and display text. By default, the link target will be returned as a title object, but if `allow_bad_target` is set it will be returned as a string, and no check will be performed as to whether it is a valid link target.]==] function export.get_wikilink_parts(text, allow_bad_target) -- TODO: replace `allow_bad_target` with `allow_unsupported`, with support for links to unsupported titles, including escape sequences. if ( -- Filters out anything but "[[...]]" with no intermediate "[[" or "]]". not match(text, "^()%[%[") or -- Faster than sub(text, 1, 2) ~= "[[". find(text, "[[", 3, true) or find(text, "]]", 3, true) ~= #text - 1 ) then return nil, nil end local pipe, title, display = find(text, "|", 3, true) if pipe then title, display = sub(text, 3, pipe - 1), sub(text, pipe + 1, -3) else title = sub(text, 3, -3) display = title end if allow_bad_target then return title, display end title = new_title(title) -- No title object means the target is invalid. if title == nil then return nil, nil -- If the link target starts with "#" then mw.title.new returns a broken -- title object, so grab the current title and give it the correct fragment. elseif title.prefixedText == "" then local fragment = title.fragment if fragment == "" then -- [[#]] isn't valid return nil, nil end title = get_current_title() title.fragment = fragment end return title, display end -- Does the work of export.get_fragment, but can be called directly to avoid unnecessary checks for embedded links. local function get_fragment(text) text = escape(text, "#") -- Replace numeric character references with the corresponding character (&#39; → '), -- as they contain #, which causes the numeric character reference to be -- misparsed (wa'a → wa&#39;a → pagename wa&, fragment 39;a). text = decode_entities(text) local target, fragment = text:match("^(.-)#(.+)$") target = target or text target = unescape(target, "#") fragment = fragment and unescape(fragment, "#") return target, fragment end --[==[Takes a link target and outputs the actual target and the fragment (if any).]==] function export.get_fragment(text) if text:find("\\", nil, true) then track("escaped", "get_fragment") end -- If there are no embedded links, process input. local open = find(text, "[[", nil, true) if not open then return get_fragment(text) end local close = find(text, "]]", open + 2, true) if not close then return get_fragment(text) -- If there is one, but it's redundant (i.e. encloses everything with no pipe), remove and process. elseif open == 1 and close == #text - 1 and not find(text, "|", 3, true) then return get_fragment(sub(text, 3, -3)) end -- Otherwise, return the input. return text end --[==[ Given a link target as passed to `full_link()`, get the actual page that the target refers to. This removes bold, italics, strip markets and HTML; calls `makeEntryName()` for the language in question; converts targets beginning with `*` to the Reconstruction namespace; and converts appendix-constructed languages to the Appendix namespace. Returns up to three values: # the actual page to link to, or {nil} to not link to anything; # how the target should be displayed as, if the user didn't explicitly specify any display text; generally the same as the original target, but minus any anti-asterisk !!; # the value `true` if the target had a backslash-escaped * in it (FIXME: explain this more clearly). ]==] function export.get_link_page_with_auto_display(target, lang, sc, plain) local orig_target = target if not target then return nil elseif target:find("\\", nil, true) then track("escaped", "get_link_page") end target = remove_formatting(target) if target:sub(1, 1) == ":" then track("initial colon") -- FIXME, the auto_display (second return value) should probably remove the colon return target:sub(2), orig_target end local prefix = target:match("^(.-):") -- Convert any escaped colons target = target:gsub("\\:", ":") if prefix then -- If this is an a link to another namespace or an interwiki link, ensure there's an initial colon and then -- return what we have (so that it works as a conventional link, and doesn't do anything weird like add the term -- to a category.) prefix = ulower(trim(prefix)) if prefix ~= "" and ( load_data("Module:data/namespaces")[prefix] or load_data("Module:data/interwikis")[prefix] ) then return target, orig_target end end -- Check if the term is reconstructed and remove any asterisk. Also check for anti-asterisk (!!). -- Otherwise, handle the escapes. local reconstructed, escaped, anti_asterisk if not plain then target, reconstructed = target:gsub("^%*(.)", "%1") if reconstructed == 0 then target, anti_asterisk = target:gsub("^!!(.)", "%1") if anti_asterisk == 1 then -- Remove !! from original. FIXME! We do it this way because the call to remove_formatting() above -- may cause non-initial !! to be interpreted as anti-asterisks. We should surely move the -- remove_formatting() call later. orig_target = orig_target:gsub("^!!", "") end end end target, escaped = target:gsub("^(\\-)\\%*", "%1*") if not (sc and sc:getCode() ~= "None") then sc = lang:findBestScript(target) end -- Remove carets if they are used to capitalize parts of transliterations (unless they have been escaped). if (not sc:hasCapitalization()) and sc:isTransliterated() and target:match("%^") then target = escape(target, "^") :gsub("%^", "") target = unescape(target, "^") end -- Get the entry name for the language. target = lang:makeEntryName(target, sc, reconstructed == 1 or lang:hasType("appendix-constructed")) -- If the link contains unexpanded template parameters, then don't create a link. if target:match("{{{.-}}}") then -- FIXME: Should we return the original target as the default display value (second return value)? return nil end -- Link to appendix for reconstructed terms and terms in appendix-only languages. Plain links interpret * -- literally, however. if reconstructed == 1 then if lang:getFullCode() == "und" then -- Return the original target as default display value. If we don't do this, we wrongly get -- [Term?] displayed instead. return nil, orig_target end target = "Reconstruction:" .. lang:getFullName() .. "/" .. target -- Reconstructed languages and substrates require an initial *. elseif anti_asterisk ~= 1 and (lang:hasType("reconstructed") or lang:getFamilyCode() == "qfa-sub") then error(("The specified language %s is unattested, while the term '%s' does not begin with '*' to indicate that it is reconstructed.") : format(lang:getCanonicalName(), orig_target)) elseif lang:hasType("appendix-constructed") then target = "Appendix:" .. lang:getFullName() .. "/" .. target else target = target end return target, orig_target, escaped > 0 end function export.get_link_page(target, lang, sc, plain) local target, auto_display, escaped = export.get_link_page_with_auto_display(target, lang, sc, plain) return target, escaped end -- Make a link from a given link's parts local function make_link(link, lang, sc, id, isolated, cats, no_alt_ast, plain) -- Convert percent encoding to plaintext. link.target = link.target and decode_uri(link.target, "PATH") link.fragment = link.fragment and decode_uri(link.fragment, "PATH") -- Find fragments (if one isn't already set). -- Prevents {{l|en|word#Etymology 2|word}} from linking to [[word#Etymology 2#English]]. -- # can be escaped as \#. if link.target and link.fragment == nil then link.target, link.fragment = get_fragment(link.target) end -- Process the target local auto_display, escaped link.target, auto_display, escaped = export.get_link_page_with_auto_display(link.target, lang, sc, plain) -- Create a default display form. -- If the target is "" then it's a link like [[#English]], which refers to the current page. if auto_display == "" then auto_display = (m_headword_data or get_headword_data()).pagename end -- If the display is the target and the reconstruction * has been escaped, remove the escaping backslash. if escaped then auto_display = auto_display:gsub("\\([^\\]*%*)", "%1", 1) end -- Process the display form. if link.display then local orig_display = link.display link.display = lang:makeDisplayText(link.display, sc, true) if cats then auto_display = lang:makeDisplayText(auto_display, sc) -- If the alt text is the same as what would have been automatically generated, then the alt parameter is redundant (e.g. {{l|en|foo|foo}}, {{l|en|w:foo|foo}}, but not {{l|en|w:foo|w:foo}}). -- If they're different, but the alt text could have been entered as the term parameter without it affecting the target page, then the target parameter is redundant (e.g. {{l|ru|фу|фу́}}). -- If `no_alt_ast` is true, use pcall to catch the error which will be thrown if this is a reconstructed lang and the alt text doesn't have *. if link.display == auto_display then insert(cats, lang:getFullName() .. " links with redundant alt parameters") else local ok, check if no_alt_ast then ok, check = pcall(export.get_link_page, orig_display, lang, sc, plain) else ok = true check = export.get_link_page(orig_display, lang, sc, plain) end if ok and link.target == check then insert(cats, lang:getFullName() .. " links with redundant target parameters") end end end else link.display = lang:makeDisplayText(auto_display, sc) end if not link.target then return link.display end -- If the target is the same as the current page, there is no sense id -- and either the language code is "und" or the current L2 is the current -- language then return a "self-link" like the software does. if link.target == get_current_title().prefixedText then local fragment, current_L2 = link.fragment, get_current_L2() if ( fragment and fragment == current_L2 or not (id or fragment) and (lang:getFullCode() == "und" or lang:getFullName() == current_L2) ) then return tostring(mw.html.create("strong") :addClass("selflink") :wikitext(link.display)) end end -- Add fragment. Do not add a section link to "Undetermined", as such sections do not exist and are invalid. -- TabbedLanguages handles links without a section by linking to the "last visited" section, but adding -- "Undetermined" would break that feature. For localized prefixes that make syntax error, please use the -- format: ["xyz"] = true. local prefix = link.target:match("^:*([^:]+):") prefix = prefix and ulower(prefix) if prefix ~= "category" and not (prefix and load_data("Module:data/interwikis")[prefix]) then if (link.fragment or link.target:sub(-1) == "#") and not plain then track("fragment", lang:getFullCode()) if cats then insert(cats, lang:getFullName() .. " links with manual fragments") end end if not link.fragment then if id then link.fragment = lang:getFullCode() == "und" and anchor_encode(id) or language_anchor(lang, id) elseif lang:getFullCode() ~= "und" and not (link.target:match("^Appendix:") or link.target:match("^Reconstruction:")) then link.fragment = anchor_encode(lang:getFullName()) end end end -- Put inward-facing square brackets around a link to isolated spacing character(s). if isolated and #link.display > 0 and not umatch(decode_entities(link.display), "%S") then link.display = "&#x5D;" .. link.display .. "&#x5B;" end link.target = link.target:gsub("^(:?)(.*)", function(m1, m2) return m1 .. encode_entities(m2, "#%&+/:<=>@[\\]_{|}") end) link.fragment = link.fragment and encode_entities(remove_formatting(link.fragment), "#%&+/:<=>@[\\]_{|}") return "[[" .. link.target:gsub("^[^:]", ":%0") .. (link.fragment and "#" .. link.fragment or "") .. "|" .. link.display .. "]]" end -- Split a link into its parts local function parse_link(linktext) local link = { target = linktext } local target = link.target link.target, link.display = target:match("^(..-)|(.+)$") if not link.target then link.target = target link.display = target end -- There's no point in processing these, as they aren't real links. local target_lower = link.target:lower() for _, false_positive in ipairs({ "category", "cat", "file", "image" }) do if target_lower:match("^" .. false_positive .. ":") then return nil end end link.display = decode_entities(link.display) link.target, link.fragment = get_fragment(link.target) -- So that make_link does not look for a fragment again. if not link.fragment then link.fragment = false end return link end local function check_params_ignored_when_embedded(alt, lang, id, cats) if alt then track("alt-ignored") if cats then insert(cats, lang:getFullName() .. " links with ignored alt parameters") end end if id then track("id-ignored") if cats then insert(cats, lang:getFullName() .. " links with ignored id parameters") end end end -- Find embedded links and ensure they link to the correct section. local function process_embedded_links(text, alt, lang, sc, id, cats, no_alt_ast, plain) -- Process the non-linked text. text = lang:makeDisplayText(text, sc, true) -- If the text begins with * and another character, then act as if each link begins with *. However, don't do this if the * is contained within a link at the start. E.g. `|*[[foo]]` would set all_reconstructed to true, while `|[[*foo]]` would not. local all_reconstructed = false if not plain then -- anchor_encode removes links etc. if anchor_encode(text):sub(1, 1) == "*" then all_reconstructed = true end -- Otherwise, handle any escapes. text = text:gsub("^(\\-)\\%*", "%1*") end check_params_ignored_when_embedded(alt, lang, id, cats) local function process_link(space1, linktext, space2) local capture = "[[" .. linktext .. "]]" local link = parse_link(linktext) -- Return unprocessed false positives untouched (e.g. categories). if not link then return capture end if all_reconstructed then if link.target:find("^!!") then -- Check for anti-asterisk !! at the beginning of a target, indicating that a reconstructed term -- wants a part of the term to link to a non-reconstructed term, e.g. Old English -- {{ang-noun|m|head=*[[!!Crist|Cristes]] [[!!mæsseǣfen]]}}. link.target = link.target:sub(3) -- Also remove !! from the display, which may have been copied from the target (as in mæsseǣfen in -- the example above). link.display = link.display:gsub("^!!", "") elseif not link.target:match("^%*") then link.target = "*" .. link.target end end linktext = make_link(link, lang, sc, id, false, nil, no_alt_ast, plain) :gsub("^%[%[", "\3") :gsub("%]%]$", "\4") return space1 .. linktext .. space2 end -- Use chars 1 and 2 as temporary substitutions, so that we can use charsets. These are converted to chars 3 and 4 by process_link, which means we can convert any remaining chars 1 and 2 back to square brackets (i.e. those not part of a link). text = text :gsub("%[%[", "\1") :gsub("%]%]", "\2") -- If the script uses ^ to capitalize transliterations, make sure that any carets preceding links are on the inside, so that they get processed with the following text. if ( text:find("^", nil, true) and not sc:hasCapitalization() and sc:isTransliterated() ) then text = escape(text, "^") :gsub("%^\1", "\1%^") text = unescape(text, "^") end text = text:gsub("\1(%s*)([^\1\2]-)(%s*)\2", process_link) -- Remove the extra * at the beginning of a language link if it's immediately followed by a link whose display begins with * too. if all_reconstructed then text = text:gsub("^%*\3([^|\1-\4]+)|%*", "\3%1|*") end return (text :gsub("[\1\3]", "[[") :gsub("[\2\4]", "]]") ) end local function simple_link(term, fragment, alt, lang, sc, id, cats, no_alt_ast, srwc) local plain if lang == nil then lang, plain = get_lang("und"), true end -- Get the link target and display text. If the term is the empty string, treat the input as a link to the current page. if term == "" then term = get_current_title().prefixedText elseif term then local new_term, new_alt = export.get_wikilink_parts(term, true) if new_term then check_params_ignored_when_embedded(alt, lang, id, cats) -- [[|foo]] links are treated as plaintext "[[|foo]]". -- FIXME: Pipes should be handled via a proper escape sequence, as they can occur in unsupported titles. if new_term == "" then term, alt = nil, term else local title = new_title(new_term) if title then local ns = title.namespace -- File: and Category: links should be returned as-is. if ns == 6 or ns == 14 then return term end end term, alt = new_term, new_alt if cats then if not (srwc and srwc(term, alt)) then insert(cats, lang:getFullName() .. " links with redundant wikilinks") end end end end end if alt then alt = selective_trim(alt) if alt == "" then alt = nil end end -- If there's nothing to process, return nil. if not (term or alt) then return nil end -- If there is no script, get one. if not sc then sc = lang:findBestScript(alt or term) end -- Embedded wikilinks need to be processed individually. if term then local open = find(term, "[[", nil, true) if open and find(term, "]]", open + 2, true) then return process_embedded_links(term, alt, lang, sc, id, cats, no_alt_ast, plain) end term = selective_trim(term) end -- If not, make a link using the parameters. return make_link({ target = term, display = alt, fragment = fragment }, lang, sc, id, true, cats, no_alt_ast, plain) end --[==[Creates a basic link to the given term. It links to the language section (such as <code>==English==</code>), but it does not add language and script wrappers, so any code that uses this function should call the <code class="n">[[Module:script utilities#tag_text|tag_text]]</code> from [[Module:script utilities]] to add such wrappers itself at some point. The first argument, <code class="n">data</code>, may contain the following items, a subset of the items used in the <code class="n">data</code> argument of <code class="n">full_link</code>. If any other items are included, they are ignored. { { term = entry_to_link_to, alt = link_text_or_displayed_text, lang = language_object, id = sense_id, } } ; <code class="n">term</code> : Text to turn into a link. This is generally the name of a page. The text can contain wikilinks already embedded in it. These are processed individually just like a single link would be. The <code class="n">alt</code> argument is ignored in this case. ; <code class="n">alt</code> (''optional'') : The alternative display for the link, if different from the linked page. If this is {{code|lua|nil}}, the <code class="n">text</code> argument is used instead (much like regular wikilinks). If <code class="n">text</code> contains wikilinks in it, this argument is ignored and has no effect. (Links in which the alt is ignored are tracked with the tracking template {{whatlinkshere|tracking=links/alt-ignored}}.) ; <code class="n">lang</code> : The [[Module:languages#Language objects|language object]] for the term being linked. If this argument is defined, the function will determine the language's canonical name (see [[Template:language data documentation]]), and point the link or links in the <code class="n">term</code> to the language's section of an entry, or to a language-specific senseid if the <code class="n">id</code> argument is defined. ; <code class="n">id</code> (''optional'') : Sense id string. If this argument is defined, the link will point to a language-specific sense id ({{ll|en|identifier|id=HTML}}) created by the template {{temp|senseid}}. A sense id consists of the language's canonical name, a hyphen (<code>-</code>), and the string that was supplied as the <code class="n">id</code> argument. This is useful when a term has more than one sense in a language. If the <code class="n">term</code> argument contains wikilinks, this argument is ignored. (Links in which the sense id is ignored are tracked with the tracking template {{whatlinkshere|tracking=links/id-ignored}}.) The second argument is as follows: ; <code class="n">allow_self_link</code> : If {{code|lua|true}}, the function will also generate links to the current page. The default ({{code|lua|false}}) will not generate a link but generate a bolded "self link" instead. The following special options are processed for each link (both simple text and with embedded wikilinks): * The target page name will be processed to generate the correct entry name. This is done by the [[Module:languages#makeEntryName|makeEntryName]] function in [[Module:languages]], using the <code class="n">entry_name</code> replacements in the language's data file (see [[Template:language data documentation]] for more information). This function is generally used to automatically strip dictionary-only diacritics that are not part of the normal written form of a language. * If the text starts with <code class="n">*</code>, then the term is considered a reconstructed term, and a link to the Reconstruction: namespace will be created. If the text contains embedded wikilinks, then <code class="n">*</code> is automatically applied to each one individually, while preserving the displayed form of each link as it was given. This allows linking to phrases containing multiple reconstructed terms, while only showing the * once at the beginning. * If the text starts with <code class="n">:</code>, then the link is treated as "raw" and the above steps are skipped. This can be used in rare cases where the page name begins with <code class="n">*</code> or if diacritics should not be stripped. For example: ** {{temp|l|en|*nix}} links to the nonexistent page [[Reconstruction:English/nix]] (<code class="n">*</code> is interpreted as a reconstruction), but {{temp|l|en|:*nix}} links to [[*nix]]. ** {{temp|l|sl|Franche-Comté}} links to the nonexistent page [[Franche-Comte]] (<code>é</code> is converted to <code>e</code> by <code class="n">makeEntryName</code>), but {{temp|l|sl|:Franche-Comté}} links to [[Franche-Comté]].]==] function export.language_link(data) if type(data) ~= "table" then error( "The first argument to the function language_link must be a table. See Module:links/documentation for more information.") elseif data.term and data.term:find("\\", nil, true) or data.alt and data.alt:find("\\", nil, true) then track("escaped", "language_link") end -- Categorize links to "und". local lang, cats = data.lang, data.cats if cats and lang:getCode() == "und" then insert(cats, "Undetermined language links") end return simple_link( data.term, data.fragment, data.alt, lang, data.sc, data.id, cats, data.no_alt_ast, data.suppress_redundant_wikilink_cat ) end function export.plain_link(data) if type(data) ~= "table" then error( "The first argument to the function plain_link must be a table. See Module:links/documentation for more information.") elseif data.term and data.term:find("\\", nil, true) or data.alt and data.alt:find("\\", nil, true) then track("escaped", "plain_link") end return simple_link( data.term, data.fragment, data.alt, nil, data.sc, data.id, data.cats, data.no_alt_ast, data.suppress_redundant_wikilink_cat ) end --[==[Replace any links with links to the correct section, but don't link the whole text if no embedded links are found. Returns the display text form.]==] function export.embedded_language_links(data) if type(data) ~= "table" then error( "The first argument to the function embedded_language_links must be a table. See Module:links/documentation for more information.") elseif data.term and data.term:find("\\", nil, true) or data.alt and data.alt:find("\\", nil, true) then track("escaped", "embedded_language_links") end local term, lang, sc = data.term, data.lang, data.sc -- If we don't have a script, get one. if not sc then sc = lang:findBestScript(term) end -- Do we have embedded wikilinks? If so, they need to be processed individually. local open = find(term, "[[", nil, true) if open and find(term, "]]", open + 2, true) then return process_embedded_links(term, data.alt, lang, sc, data.id, data.cats, data.no_alt_ast) end -- If not, return the display text. term = selective_trim(term) -- FIXME: Double-escape any percent-signs, because we don't want to treat non-linked text as having percent-encoded characters. This is a hack: percent-decoding should come out of [[Module:languages]] and only dealt with in this module, as it's specific to links. term = term:gsub("%%", "%%25") return lang:makeDisplayText(term, sc, true) end function export.mark(text, item_type, face, lang) local tag = { "", "" } if item_type == "gloss" then tag = { '<span class="mention-gloss-double-quote">“</span><span class="mention-gloss">', '</span><span class="mention-gloss-double-quote">”</span>' } if type(text) == "string" and text:match("^''[^'].*''$") then -- Temporary tracking for mention glosses that are entirely italicized or bolded, which is probably -- wrong. (Note that this will also find bolded mention glosses since they use triple apostrophes.) track("italicized-mention-gloss", lang and lang:getFullCode() or nil) end elseif item_type == "tr" then if face == "term" then tag = { '<span lang="' .. lang:getFullCode() .. '" class="tr mention-tr Latn">', '</span>' } else tag = { '<span lang="' .. lang:getFullCode() .. '" class="tr Latn">', '</span>' } end elseif item_type == "ts" then -- \226\129\160 = word joiner (zero-width non-breaking space) U+2060 tag = { '<span class="ts mention-ts Latn">/\226\129\160', '\226\129\160/</span>' } elseif item_type == "pos" then tag = { '<span class="ann-pos">', '</span>' } elseif item_type == "non-gloss" then tag = { '<span class="ann-non-gloss">', '</span>' } elseif item_type == "annotations" then tag = { '<span class="mention-gloss-paren annotation-paren">(</span>', '<span class="mention-gloss-paren annotation-paren">)</span>' } elseif item_type == "infl" then tag = { '<span class="ann-infl">', '</span>' } end if type(text) == "string" then return tag[1] .. text .. tag[2] else return "" end end local pos_tags --[==[Formats the annotations that are displayed with a link created by {{code|lua|full_link}}. Annotations are the extra bits of information that are displayed following the linked term, and include things such as gender, transliteration, gloss and so on. * The first argument is a table possessing some or all of the following keys: *:; <code class="n">genders</code> *:: Table containing a list of gender specifications in the style of [[Module:gender and number]]. *:; <code class="n">tr</code> *:: Transliteration. *:; <code class="n">gloss</code> *:: Gloss that translates the term in the link, or gives some other descriptive information. *:; <code class="n">pos</code> *:: Part of speech of the linked term. If the given argument matches one of the aliases in `pos_aliases` in [[Module:headword/data]], or consists of a part of speech or alias followed by `f` (for a non-lemma form), expand it appropriately. Otherwise, just show the given text as it is. *:; <code class="n">ng</code> *:: Arbitrary non-gloss descriptive text for the link. This should be used in preference to putting descriptive text in `gloss` or `pos`. *:; <code class="n">lit</code> *:: Literal meaning of the term, if the usual meaning is figurative or idiomatic. *:; <code class="n">infl</code> *:: Table containing a list of grammar tags in the style of [[Module:form of]] `tagged_inflections`. *:Any of the above values can be omitted from the <code class="n">info</code> argument. If a completely empty table is given (with no annotations at all), then an empty string is returned. * The second argument is a string. Valid values are listed in [[Module:script utilities/data]] "data.translit" table.]==] function export.format_link_annotations(data, face) local output = {} -- Interwiki link if data.interwiki then insert(output, data.interwiki) end -- Genders if type(data.genders) ~= "table" then data.genders = { data.genders } end if data.genders and #data.genders > 0 then local genders, gender_cats = format_genders(data.genders, data.lang) insert(output, "&nbsp;" .. genders) if gender_cats then local cats = data.cats if cats then extend(cats, gender_cats) end end end local annotations = {} -- Transliteration and transcription if data.tr and data.tr[1] or data.ts and data.ts[1] then local kind if face == "term" then kind = face else kind = "default" end if data.tr[1] and data.ts[1] then insert(annotations, tag_translit(data.tr[1], data.lang, kind) .. " " .. export.mark(data.ts[1], "ts")) elseif data.ts[1] then insert(annotations, export.mark(data.ts[1], "ts")) else insert(annotations, tag_translit(data.tr[1], data.lang, kind)) end end -- Gloss/translation if data.gloss then insert(annotations, export.mark(data.gloss, "gloss")) end -- Part of speech if data.pos then -- debug category for pos= containing transcriptions if data.pos:match("/[^><]-/") then data.pos = data.pos .. "[[Category:links likely containing transcriptions in pos]]" end -- Canonicalize part of speech aliases as well as non-lemma aliases like 'nf' or 'nounf' for "noun form". pos_tags = pos_tags or (m_headword_data or get_headword_data()).pos_aliases local pos = pos_tags[data.pos] if not pos and data.pos:find("f$") then local pos_form = data.pos:sub(1, -2) -- We only expand something ending in 'f' if the result is a recognized non-lemma POS. pos_form = (pos_tags[pos_form] or pos_form) .. " form" if (m_headword_data or get_headword_data()).nonlemmas[pos_form .. "s"] then pos = pos_form end end insert(annotations, export.mark(pos or data.pos, "pos")) end -- Inflection data if data.infl then local m_form_of = require(form_of_module) -- Split tag sets manually, since tagged_inflections creates a numbered list, and we do not want that. local infl_outputs = {} local tag_sets = m_form_of.split_tag_set(data.infl) for _, tag_set in ipairs(tag_sets) do table.insert(infl_outputs, m_form_of.tagged_inflections({ tags = tag_set, lang = data.lang, nocat = true, nolink = true, nowrap = true })) end insert(annotations, export.mark(table.concat(infl_outputs, "; "), "infl")) end -- Non-gloss text if data.ng then insert(annotations, export.mark(data.ng, "non-gloss")) end -- Literal/sum-of-parts meaning if data.lit then insert(annotations, "literally " .. export.mark(data.lit, "gloss")) end -- Provide a hook to insert additional annotations such as nested inflections. if data.postprocess_annotations then data.postprocess_annotations { data = data, annotations = annotations } end if #annotations > 0 then insert(output, " " .. export.mark(concat(annotations, ", "), "annotations")) end return concat(output) end -- Encode certain characters to avoid various delimiter-related issues at various stages. We need to encode < and > -- because they end up forming part of CSS class names inside of <span ...> and will interfere with finding the end -- of the HTML tag. I first tried converting them to URL encoding, i.e. %3C and %3E; they then appear in the URL as -- %253C and %253E, which get mapped back to %3C and %3E when passed to [[Module:accel]]. But mapping them to &lt; -- and &gt; somehow works magically without any further work; they appear in the URL as < and >, and get passed to -- [[Module:accel]] as < and >. I have no idea who along the chain of calls is doing the encoding and decoding. If -- someone knows, please modify this comment appropriately! local accel_char_map local function get_accel_char_map() accel_char_map = { ["%"] = ".", [" "] = "_", ["_"] = u(0xFFF0), ["<"] = "&lt;", [">"] = "&gt;", } return accel_char_map end local function encode_accel_param_chars(param) return (param:gsub("[% <>_]", accel_char_map or get_accel_char_map())) end local function encode_accel_param(prefix, param) if not param then return "" end if type(param) == "table" then local filled_params = {} -- There may be gaps in the sequence, especially for translit params. local maxindex = 0 for k in pairs(param) do if type(k) == "number" and k > maxindex then maxindex = k end end for i = 1, maxindex do filled_params[i] = param[i] or "" end -- [[Module:accel]] splits these up again. param = concat(filled_params, "*~!") end -- This is decoded again by [[WT:ACCEL]]. return prefix .. encode_accel_param_chars(param) end local function insert_if_not_blank(list, item) if item == "" then return end insert(list, item) end local function get_class(lang, tr, accel, nowrap) if not accel and not nowrap then return "" end local classes = {} if accel then insert(classes, "form-of lang-" .. lang:getFullCode()) local form = accel.form if form then insert(classes, encode_accel_param_chars(form) .. "-form-of") end insert_if_not_blank(classes, encode_accel_param("gender-", accel.gender)) insert_if_not_blank(classes, encode_accel_param("pos-", accel.pos)) insert_if_not_blank(classes, encode_accel_param("transliteration-", accel.translit or (tr ~= "-" and tr or nil))) insert_if_not_blank(classes, encode_accel_param("target-", accel.target)) insert_if_not_blank(classes, encode_accel_param("origin-", accel.lemma)) insert_if_not_blank(classes, encode_accel_param("origin_transliteration-", accel.lemma_translit)) if accel.no_store then insert(classes, "form-of-nostore") end end if nowrap then insert(classes, nowrap) end return concat(classes, " ") end -- Add any left or right regular or accent qualifiers, labels or references to a formatted term. `data` is the object -- specifying the term, which should optionally contain: -- * a language object in `lang`; required if any accent qualifiers or labels are given; -- * left regular qualifiers in `q` (an array of strings or a single string); an empty array or blank string will be -- ignored; -- * right regular qualifiers in `qq` (an array of strings or a single string); an empty array or blank string will be -- ignored; -- * left accent qualifiers in `a` (an array of strings); an empty array will be ignored; -- * right accent qualifiers in `aa` (an array of strings); an empty array will be ignored; -- * left labels in `l` (an array of strings); an empty array will be ignored; -- * right labels in `ll` (an array of strings); an empty array will be ignored; -- * references in `refs`, an array either of strings (formatted reference text) or objects containing fields `text` -- (formatted reference text) and optionally `name` and/or `group`. -- `formatted` is the formatted version of the term itself. local function add_qualifiers_and_refs_to_term(data, formatted) local q = data.q if type(q) == "string" then q = { q } end local qq = data.qq if type(qq) == "string" then qq = { qq } end if q and q[1] or qq and qq[1] or data.a and data.a[1] or data.aa and data.aa[1] or data.l and data.l[1] or data.ll and data.ll[1] or data.refs and data.refs[1] then formatted = format_qualifiers { lang = data.lang, text = formatted, q = q, qq = qq, a = data.a, aa = data.aa, l = data.l, ll = data.ll, refs = data.refs, } end return formatted end --[==[ Creates a full link, with annotations (see `[[#format_link_annotations|format_link_annotations]]`), in the style of {{tl|l}} or {{tl|m}}. The first argument, `data`, must be a table. It contains the various elements that can be supplied as parameters to {{tl|l}} or {{tl|m}}: { { term = entry_to_link_to, alt = link_text_or_displayed_text, lang = language_object, sc = script_object, track_sc = boolean, no_nonstandard_sc_cat = boolean, fragment = link_fragment, id = sense_id, genders = { "gender1", "gender2", ... }, tr = transliteration, respect_link_tr = boolean, ts = transcription, gloss = gloss, pos = part_of_speech_tag, ng = non-gloss text, lit = literal_translation, infl = { "form_of_grammar_tag1", "form_of_grammar_tag2", ... }, no_alt_ast = boolean, accel = {accelerated_creation_tags}, interwiki = interwiki, pretext = "text_at_beginning" or nil, posttext = "text_at_end" or nil, q = { "left_qualifier1", "left_qualifier2", ...} or "left_qualifier", qq = { "right_qualifier1", "right_qualifier2", ...} or "right_qualifier", l = { "left_label1", "left_label2", ...}, ll = { "right_label1", "right_label2", ...}, a = { "left_accent_qualifier1", "left_accent_qualifier2", ...}, aa = { "right_accent_qualifier1", "right_accent_qualifier2", ...}, refs = { "formatted_ref1", "formatted_ref2", ...} or { {text = "text", name = "name", group = "group"}, ... }, show_qualifiers = boolean, } } Any one of the items in the `data` table may be {nil}, but an error will be shown if neither `term` nor `alt` nor `tr` is present. Thus, calling {full_link{ term = term, lang = lang, sc = sc }}, where `term` is the page to link to (which may have diacritics that will be stripped and/or embedded bracketed links) and `lang` is a [[Module:languages#Language objects|language object]] from [[Module:languages]], will give a plain link similar to the one produced by the template {{tl|l}}, and calling {full_link( { term = term, lang = lang, sc = sc }, "term" )} will give a link similar to the one produced by the template {{tl|m}}. The function will: * Try to determine the script, based on the characters found in the `term` or `alt` argument, if the script was not given. If a script is given and `track_sc` is {true}, it will check whether the input script is the same as the one which would have been automatically generated and add the category [[:Category:LANG terms with redundant script codes]] if yes, or [[:Category:LANG terms with non-redundant manual script codes]] if no. This should be used when the input script object is directly determined by a template's `sc` parameter. * Call `[[#language_link|language_link]]` on the `term` or `alt` forms, to remove diacritics in the page name, process any embedded wikilinks and create links to Reconstruction or Appendix pages when necessary. * Call `[[Module:script utilities#tag_text]]` to add the appropriate language and script tags to the term and italicize terms written in the Latin script if necessary. Accelerated creation tags, as used by [[WT:ACCEL]], are included. * Generate a transliteration, based on the `alt` or `term` arguments, if the script is not Latin, no transliteration was provided in `tr` and the combination of the term's language and script support automatic transliteration. The transliteration itself will be linked if both `.respect_link_tr` is specified and the language of the term has the `link_tr` property set for the script of the term; but not otherwise. * Add the annotations (transliteration, gender, gloss, etc.) after the link. * If `no_alt_ast` is specified, then the `alt` text does not need to contain an asterisk if the language is reconstructed. This should only be used by modules which really need to allow links to reconstructions that don't display asterisks (e.g. number boxes). * If `pretext` or `posttext` is specified, this is text to (respectively) prepend or append to the output, directly before processing qualifiers, labels and references. This can be used to add arbitrary extra text inside of the qualifiers, labels and references. * If `show_qualifiers` is specified or the `show_qualifiers` argument is given, then left and right qualifiers, accent qualifiers, labels and references will be displayed, otherwise they will be ignored. (This is because a fair amount of code stores qualifiers, labels and/or references in these fields and displays them itself, rather than expecting {full_link()} to display them.)]==] function export.full_link(data, face, allow_self_link, show_qualifiers) if type(data) ~= "table" then error("The first argument to the function full_link must be a table. " .. "See Module:links/documentation for more information.") elseif data.term and data.term:find("\\", nil, true) or data.alt and data.alt:find("\\", nil, true) then track("escaped", "full_link") end -- Prevent data from being destructively modified. local data = shallow_copy(data) -- FIXME: this shouldn't be added to `data`, as that means the input table needs to be cloned. data.cats = {} -- Categorize links to "und". local lang, cats = data.lang, data.cats if cats and lang:getCode() == "und" then insert(cats, "Undetermined language links") end local terms = { true } -- Generate multiple forms if applicable. for _, param in ipairs { "term", "alt" } do if type(data[param]) == "string" and data[param]:find("//", nil, true) then data[param] = export.split_on_slashes(data[param]) elseif type(data[param]) == "string" and not (type(data.term) == "string" and data.term:find("//", nil, true)) then if not data.no_generate_forms then data[param] = lang:generateForms(data[param]) else data[param] = { data[param] } end else data[param] = {} end end for _, param in ipairs { "sc", "tr", "ts" } do data[param] = { data[param] } end for _, param in ipairs { "term", "alt", "sc", "tr", "ts" } do for i in pairs(data[param]) do terms[i] = true end end -- Create the link local output = {} local id, no_alt_ast, srwc, accel, nevercalltr = data.id, data.no_alt_ast, data.suppress_redundant_wikilink_cat, data.accel, data.never_call_transliteration_module local link_tr = data.respect_link_tr and lang:link_tr(data.sc[1]) for i in ipairs(terms) do local link -- Is there any text to show? if (data.term[i] or data.alt[i]) then -- Try to detect the script if it was not provided local display_term = data.alt[i] or data.term[i] local best = lang:findBestScript(display_term) -- no_nonstandard_sc_cat is intended for use in [[Module:interproject]] if ( not data.no_nonstandard_sc_cat and best:getCode() == "None" and find_best_script_without_lang(display_term):getCode() ~= "None" ) then insert(cats, lang:getFullName() .. " terms in nonstandard scripts") end if not data.sc[i] then data.sc[i] = best -- Track uses of sc parameter. elseif data.track_sc then if data.sc[i]:getCode() == best:getCode() then insert(cats, lang:getFullName() .. " terms with redundant script codes") else insert(cats, lang:getFullName() .. " terms with non-redundant manual script codes") end end -- If using a discouraged character sequence, add to maintenance category if data.sc[i]:hasNormalizationFixes() == true then if (data.term[i] and data.sc[i]:fixDiscouragedSequences(toNFC(data.term[i])) ~= toNFC(data.term[i])) or (data.alt[i] and data.sc[i]:fixDiscouragedSequences(toNFC(data.alt[i])) ~= toNFC(data.alt[i])) then insert(cats, "Pages using discouraged character sequences") end end link = simple_link( data.term[i], data.fragment, data.alt[i], lang, data.sc[i], id, cats, no_alt_ast, srwc ) end -- simple_link can return nil, so check if a link has been generated. if link then -- Add "nowrap" class to prefixes in order to prevent wrapping after the hyphen local nowrap local display_term = data.alt[i] or data.term[i] if display_term and (display_term:find("^%-") or display_term:find("^־")) then -- Hebrew maqqef -- FIXME, use hyphens from [[Module:affix]] nowrap = "nowrap" end link = tag_text(link, lang, data.sc[i], face, get_class(lang, data.tr[i], accel, nowrap)) else --[[ No term to show. Is there at least a transliteration we can work from? ]] link = request_script(lang, data.sc[i]) -- No link to show, and no transliteration either. Show a term request (unless it's a substrate, as they rarely take terms). if (link == "" or (not data.tr[i]) or data.tr[i] == "-") and lang:getFamilyCode() ~= "qfa-sub" then -- If there are multiple terms, break the loop instead. if i > 1 then remove(output) break elseif NAMESPACE ~= "Template" then insert(cats, lang:getFullName() .. " term requests") end link = "<small>[Term?]</small>" end end insert(output, link) if i < #terms then insert(output, "<span class=\"Zsym mention\" style=\"font-size:100%;\">&nbsp;/ </span>") end end -- When suppress_tr is true, do not show or generate any transliteration if data.suppress_tr then data.tr[1] = nil else -- TODO: Currently only handles the first transliteration, pending consensus on how to handle multiple translits for multiple forms, as this is not always desirable (e.g. traditional/simplified Chinese). if data.tr[1] == "" or data.tr[1] == "-" then data.tr[1] = nil else local phonetic_extraction = load_data("Module:links/data").phonetic_extraction phonetic_extraction = phonetic_extraction[lang:getCode()] or phonetic_extraction[lang:getFullCode()] if phonetic_extraction then data.tr[1] = data.tr[1] or require(phonetic_extraction).getTranslit(export.remove_links(data.alt[1] or data.term[1])) elseif (data.term[1] or data.alt[1]) and data.sc[1]:isTransliterated() then -- Track whenever there is manual translit. The categories below like 'terms with redundant transliterations' -- aren't sufficient because they only work with reference to automatic translit and won't operate at all in -- languages without any automatic translit, like Persian and Hebrew. if data.tr[1] then local full_code = lang:getFullCode() track("manual-tr", full_code) end if not nevercalltr then -- Try to generate a transliteration. local text = data.alt[1] or data.term[1] if not link_tr then text = export.remove_links(text, true) end local automated_tr = lang:transliterate(text, data.sc[1]) if automated_tr then local manual_tr = data.tr[1] if manual_tr then if export.remove_links(manual_tr) == export.remove_links(automated_tr) then insert(cats, lang:getFullName() .. " terms with redundant transliterations") else -- Prevents Arabic root categories from flooding the tracking categories. if NAMESPACE ~= "Category" then insert(cats, lang:getFullName() .. " terms with non-redundant manual transliterations") end end end if not manual_tr or lang:overrideManualTranslit(data.sc[1]) then data.tr[1] = automated_tr end end end end end end -- Link to the transliteration entry for languages that require this if data.tr[1] and link_tr and not data.tr[1]:match("%[%[(.-)%]%]") then data.tr[1] = simple_link( data.tr[1], nil, nil, lang, get_script("Latn"), nil, cats, no_alt_ast, srwc ) elseif data.tr[1] and not link_tr then -- Remove the pseudo-HTML tags added by remove_links. data.tr[1] = data.tr[1]:gsub("</?link>", "") end if data.tr[1] and not umatch(data.tr[1], "[^%s%p]") then data.tr[1] = nil end insert(output, export.format_link_annotations(data, face)) if data.pretext then insert(output, 1, data.pretext) end if data.posttext then insert(output, data.posttext) end local categories = cats[1] and format_categories(cats, lang, "-", nil, nil, data.sc) or "" output = concat(output) if show_qualifiers or data.show_qualifiers then output = add_qualifiers_and_refs_to_term(data, output) end return output .. categories end --[==[Replaces all wikilinks with their displayed text, and removes any categories. This function can be invoked either from a template or from another module. -- Strips links: deletes category links, the targets of piped links, and any double square brackets involved in links (other than file links, which are untouched). If `tag` is set, then any links removed will be given pseudo-HTML tags, which allow the substitution functions in [[Module:languages]] to properly subdivide the text in order to reduce the chance of substitution failures in modules which scrape pages like [[Module:zh-translit]]. -- FIXME: This is quite hacky. We probably want this to be integrated into [[Module:languages]], but we can't do that until we know that nothing is pushing pipe linked transliterations through it for languages which don't have link_tr set. * <code><nowiki>[[page|displayed text]]</nowiki></code> &rarr; <code><nowiki>displayed text</nowiki></code> * <code><nowiki>[[page and displayed text]]</nowiki></code> &rarr; <code><nowiki>page and displayed text</nowiki></code> * <code><nowiki>[[Category:English lemmas|WORD]]</nowiki></code> &rarr; ''(nothing)'']==] function export.remove_links(text, tag) if type(text) == "table" then text = text.args[1] end if not text or text == "" then return "" end text = text :gsub("%[%[", "\1") :gsub("%]%]", "\2") -- Parse internal links for the display text. text = text:gsub("(\1)([^\1\2]-)(\2)", function(c1, c2, c3) -- Don't remove files. for _, false_positive in ipairs({ "file", "image" }) do if c2:lower():match("^" .. false_positive .. ":") then return c1 .. c2 .. c3 end end -- Remove categories completely. for _, false_positive in ipairs({ "category", "cat" }) do if c2:lower():match("^" .. false_positive .. ":") then return "" end end -- In piped links, remove all text before the pipe, unless it's the final character (i.e. the pipe trick), in which case just remove the pipe. c2 = c2:match("^[^|]*|(.+)") or c2:match("([^|]+)|$") or c2 if tag then return "<link>" .. c2 .. "</link>" else return c2 end end) text = text :gsub("\1", "[[") :gsub("\2", "]]") return text end function export.section_link(link) if type(link) ~= "string" then error("The first argument to section_link was a " .. type(link) .. ", but it should be a string.") elseif link:find("\\", nil, true) then track("escaped", "section_link") end local target, section = get_fragment((link:gsub("_", " "))) if not section then error("No \"#\" delineating a section name") end return simple_link( target, section, target .. " §&nbsp;" .. section ) end return export go1a5j6fymqq8baizjbz87vusf7r536 828 5969 17405 2026-07-13T08:23:22Z Hiyuune 6766 + 17405 Scribunto text/plain local next = next local pairs = pairs local type = type --[==[ Returns a clone of an object. If the object is a table, the value returned is a new table, but all subtables and functions are shared. Metamethods are respected unless the `raw` flag is set, but the returned table will have no metatable of its own.]==] return function(orig, raw) if type(orig) ~= "table" then return orig end local copy, iter, state, init = {} if raw then iter, state = next, orig else iter, state, init = pairs(orig) end for k, v in iter, state, init do copy[k] = v end return copy end t51fcj6fuqkknha7dzzm33l4y4ohb22 828 5970 17406 2026-07-13T08:24:04Z Hiyuune 6766 + 17406 Scribunto text/plain local data = {} local unpack = unpack or table.unpack -- Lua 5.2 compatibility local u = require("Module:string utilities").char data.phonetic_extraction = { ["th"] = "Module:th", ["km"] = "Module:km", } data.ignored_prefixes = { ["cat"] = true, ["category"] = true, ["file"] = true, ["image"] = true } -- Scheme for using unsupported characters in titles. data.unsupported_characters = { ["#"] = "`num`", ["%"] = "`percnt`", -- only escaped in percent encoding ["&"] = "`amp`", -- only escaped in HTML entities ["."] = "`period`", -- only escaped in dot-slash notation ["<"] = "`lt`", [">"] = "`gt`", ["["] = "`lsqb`", ["]"] = "`rsqb`", ["_"] = "`lowbar`", ["`"] = "`grave`", -- used to enclose unsupported characters in the scheme, so a raw use in an unsupported title must be escaped to prevent interference ["{"] = "`lcub`", ["|"] = "`vert`", ["}"] = "`rcub`", ["~"] = "`tilde`", -- only escaped when 3 or more are consecutive ["\239\191\189"] = "`repl`" -- replacement character U+FFFD, which can't be typed directly here due to an abuse filter } -- Manually specified unsupported titles. Only put titles here if there is a different reason why they are unsupported, and not just because they contain one of the unsupported characters above. data.unsupported_titles = { [" "] = "Space", ["&amp;"] = "`amp`amp;", ["λοπαδοτεμαχοσελαχογαλεοκρανιολειψανοδριμυποτριμματοσιλφιοκαραβομελιτοκατακεχυμενοκιχλεπικοσσυφοφαττοπεριστεραλεκτρυονοπτοκεφαλλιοκιγκλοπελειολαγῳοσιραιοβαφητραγανοπτερύγων"] = "Ancient Greek dish", ["กรุงเทพมหานคร อมรรัตนโกสินทร์ มหินทรายุธยา มหาดิลกภพ นพรัตนราชธานีบูรีรมย์ อุดมราชนิเวศน์มหาสถาน อมรพิมานอวตารสถิต สักกะทัตติยวิษณุกรรมประสิทธิ์"] = "Thai name of Bangkok", [u(0x1680)] = "Ogham space", [u(0x3000)] = "Ideographic space" } -- Mammoth pages contain only Translingual and English entries, if present. The remaining L2s are placed on subpages. -- The same subpage titles are used across all mammoth pages for the convenience of bot and script operators. -- Assuming that most mammoth pages will be Latin-script terms, the subpage groupings are determined by dividing the -- list of Latin-script languages known to Wiktionary into two (three, ...) roughly equal alphabetic divisions. This is -- easily done by looking at Petscan's output: -- https://petscan.wmcloud.org/?sortby=title&language=en&ns%5B14%5D=1&categories=Latin+script+languages&project=wiktionary&doit= -- This data structure contains types of splits, each of which is a list of names of splits and Lua patterns applied to -- the decomposed L2 name (with apostrophes and double quotes removed and certain other transformations applied; see -- get_L2_sort_key() in [[Module:headword/page]]), or "true" for the final catch-all subpage (which includes anything -- not beginning with a Latin letter after the transformations are applied; this includes e.g. ǃKung but not 'Are'are, -- which sorts with A, and not Àhàn, which likewise sorts with A). The patterns must be suitable for use with plain -- string functions, not their mw.ustring equivalents. data.mammoth_page_subpage_types = { twos = { {"languages A to L", "^[A-L]"}, {"languages M to Z", true}, }, threes = { {"languages A to I", "^[A-I]"}, {"languages J to Q", "^[J-Q]"}, {"languages R to Z", true}, }, CJK = { {"languages A to C", "^[A-C]"}, -- Translingual and Chinese on one page {"languages D to Z", true}, -- all the remainder (mostly Japanese, Korean, Vietnamese) on the other }, } -- "Mammoth pages" are pages whose entries cannot be housed on a single page because of MediaWiki limits. The key is -- the page and the value is the subpage type, as defined above in `mammoth_page_subpage_types`. data.mammoth_pages = { ["a"] = "twos", -- FIXME: change to threes ["mammoth page test"] = "twos", -- required for testing purposes - please leave here } return data q02q3zllkyysivftvjq4h2gli665cgv 828 5971 17407 2026-07-13T08:24:46Z Hiyuune 6766 + 17407 Scribunto text/plain -- Capture patterns used by [[Module:languages]] to prevent formatting from being disrupted while text is being processed. -- Certain character sequences are substituted beforehand to make pattern matching more straightforward: -- "\1" = "[[" -- "\2" = "]]" return { "((</?link>))\0", -- Special link formatting added by [[Module:links]] "((<[^<>\1\2]+>))", -- HTML tag "((\1[Ff][Ii][Ll][Ee]:[^\1\2]+\2))\0", -- File "((\1[Ii][Mm][Aa][Gg][Ee]:[^\1\2]+\2))\0", -- Image "((\1[Cc][Aa][Tt][Ee][Gg][Oo][Rr][Yy]:[^\1\2]+\2))\0", -- Category "((\1[Cc][Aa][Tt]:[^\1\2]+\2))\0", -- Category "((\1)[^\1\2|]+(\2))\0", -- Bare internal link "((\1)[^\1\2|]-(|)[^\1\2]-(\2))\0", -- Piped internal link "((%[https?://[^[%] ]+)[^[%]]*(%]))\0", -- External link "((\127'\"`UNIQ%-%-%l+%-%x+%-+QINU`\"'\127))", -- Strip marker "('*(''').-'*('''))", -- Bold "('*('').-'*(''))" -- Italics } 0asj561c1s2otij1k07cuhwmbvhewr9 828 5972 17408 2026-07-13T08:25:18Z Hiyuune 6766 + 17408 Scribunto text/plain -- TO BE REPLACED BY encode_entities in [[Module:string utilities]]. This function decodes on input by default to prevent double-encoding, which the new function does not, so implementations need to take this into account when being converted. local debug_track_module = "Module:debug/track" local string_decode_entities_module = "Module:string/decodeEntities" local string_utilities_module = "Module:string utilities" local require = require local function decode_entities(...) decode_entities = require(string_decode_entities_module) return decode_entities(...) end local function encode_entities(...) encode_entities = require(string_utilities_module).encode_entities return encode_entities(...) end local function track(...) track = require(debug_track_module) return track(...) end return function(str, charset, raw) if not raw then local decoded = decode_entities(str) if decoded ~= str then track("string/encode entities/decoded first") end str = decoded end return encode_entities(str, charset, nil, true) end bvh4hqobw96dy8gcuv3yoq2nlvj06si 828 5973 17409 2026-07-13T08:25:40Z Hiyuune 6766 + 17409 Scribunto text/plain local load_module = "Module:load" local string_char_module = "Module:string/char" local find = string.find local gsub = string.gsub local match = string.match local require = require local tonumber = tonumber local function u(...) u = require(string_char_module) return u(...) end local entities local function get_entities() entities, get_entities = require(load_module).load_data("Module:data/entities"), nil return entities end local function decode_entity(hash, x, code) -- "#" isn't included in "[%w\128-\255]", so if no "#" is found then it's a -- a named entity or a false match. if hash == "" then return (entities or get_entities())[x .. code] end -- Exclude numbers that don't fit the expected format. local cp if x == "" then cp = match(code, "^()%d+$") and tonumber(code) else cp = match(code, "^()%x+$") and tonumber(code, 16) end -- Exclude surrogates (U+D800 to U+DFFF) and codepoints that are too high. return cp and ( cp <= 0xD7FF or cp >= 0xE000 and cp <= 0x10FFFF ) and u(cp) or nil end return function(str) -- As an optimisation, only do a full search with gsub() if plain searches -- for "&" and ";" find anything. local amp = find(str, "&", nil, true) -- Search for ";" after the point "&" was found. return amp and find(str, ";", amp + 1, true) and -- Non-ASCII characters aren't valid in proper HTML named entities, but -- MediaWiki uses them in some nonstandard aliases (which have also been -- included in [[Module:data/entities]]), so include them anyway. gsub(str, "&(#?)([xX]?)([%w\128-\255]+);", decode_entity) or str end 1ehplvn1q6ksitguquhvf1khnaq3mxd 828 5974 17411 2026-07-13T08:27:02Z Hiyuune 6766 Created page with "local gsub = string.gsub local chars local function get_chars() chars, get_chars = { ["\000"] = "%z", ["%"] = "%%", ["-"] = "%-", ["]"] = "%]", ["^"] = "%^", }, nil return chars end --[==[Escapes the magic characters used in pattern character sets: {%-]^}, and converts the null character to {%z}.]==] return function(str) return (gsub(str, "[%z%%%-%]^]", chars or get_chars())) end" 17411 Scribunto text/plain local gsub = string.gsub local chars local function get_chars() chars, get_chars = { ["\000"] = "%z", ["%"] = "%%", ["-"] = "%-", ["]"] = "%]", ["^"] = "%^", }, nil return chars end --[==[Escapes the magic characters used in pattern character sets: {%-]^}, and converts the null character to {%z}.]==] return function(str) return (gsub(str, "[%z%%%-%]^]", chars or get_chars())) end jrbz2u5ynegbco1b6oqpnqiz7xje0en 828 5975 17412 2026-07-13T08:27:54Z Hiyuune 6766 + 17412 Scribunto text/plain local export = {} local anchors_module = "Module:anchors" local debug_track_module = "Module:debug/track" local links_module = "Module:links" local munge_text_module = "Module:munge text" local parameters_module = "Module:parameters" local scripts_module = "Module:scripts" local string_utilities_module = "Module:string utilities" local utilities_module = "Module:utilities" local concat = table.concat local insert = table.insert local require = require local toNFD = mw.ustring.toNFD local dump = mw.dumpObject --[==[ Loaders for functions in other modules, which overwrite themselves with the target function when called. This ensures modules are only loaded when needed, retains the speed/convenience of locally-declared pre-loaded functions, and has no overhead after the first call, since the target functions are called directly in any subsequent calls.]==] local function embedded_language_links(...) embedded_language_links = require(links_module).embedded_language_links return embedded_language_links(...) end local function find_best_script_without_lang(...) find_best_script_without_lang = require(scripts_module).findBestScriptWithoutLang return find_best_script_without_lang(...) end local function format_categories(...) format_categories = require(utilities_module).format_categories return format_categories(...) end local function get_script(...) get_script = require(scripts_module).getByCode return get_script(...) end local function language_anchor(...) language_anchor = require(anchors_module).language_anchor return language_anchor(...) end local function munge_text(...) munge_text = require(munge_text_module) return munge_text(...) end local function process_params(...) process_params = require(parameters_module).process return process_params(...) end local function track(...) track = require(debug_track_module) return track(...) end local function u(...) u = require(string_utilities_module).char return u(...) end local function ugsub(...) ugsub = require(string_utilities_module).gsub return ugsub(...) end local function umatch(...) umatch = require(string_utilities_module).match return umatch(...) end --[==[ Loaders for objects, which load data (or some other object) into some variable, which can then be accessed as "foo or get_foo()", where the function get_foo sets the object to "foo" and then returns it. This ensures they are only loaded when needed, and avoids the need to check for the existence of the object each time, since once "foo" has been set, "get_foo" will not be called again.]==] local m_data local function get_data() m_data, get_data = mw.loadData("Module:script utilities/data"), nil return m_data end --[=[ Modules used: [[Module:script utilities/data]] [[Module:scripts]] [[Module:anchors]] (only when IDs present) [[Module:string utilities]] (only when hyphens in Korean text or spaces in vertical text) [[Module:languages]] [[Module:parameters]] [[Module:utilities]] [[Module:debug/track]] ]=] function export.is_Latin_script(sc) -- Latn, Latf, Latg, pjt-Latn return sc:getCode():find("Lat") and true or false end --[==[{{temp|#invoke:script utilities|lang_t}} This is used by {{temp|lang}} to wrap portions of text in a language tag. See there for more information.]==] do local function get_args(frame) return process_params(frame:getParent().args, { [1] = {required = true, type = "language", default = "und"}, [2] = {required = true, allow_empty = true, default = ""}, ["sc"] = {type = "script"}, ["face"] = true, ["class"] = true, }) end function export.lang_t(frame) local args = get_args(frame) local lang = args[1] local sc = args["sc"] local text = args[2] local cats = {} if sc then -- Track uses of sc parameter. if sc:getCode() == lang:findBestScript(text):getCode() then insert(cats, lang:getFullName() .. " terms with redundant script codes") else insert(cats, lang:getFullName() .. " terms with non-redundant manual script codes") end else sc = lang:findBestScript(text) end text = embedded_language_links{ term = text, lang = lang, sc = sc } cats = #cats > 0 and format_categories(cats, lang, "-", nil, nil, sc) or "" local face = args["face"] local class = args["class"] return export.tag_text(text, lang, sc, face, class) .. cats end end -- Ustring turns on the codepoint-aware string matching. The basic string function -- should be used for simple sequences of characters, Ustring function for -- sets – []. local function trackPattern(text, pattern, tracking) if pattern and umatch(text, pattern) then track("script/" .. tracking) end end local function track_text(text, lang, sc) if lang and text then local langCode = lang:getFullCode() -- [[Special:WhatLinksHere/Wiktionary:Tracking/script/ang/acute]] if langCode == "ang" then local decomposed = toNFD(text) local acute = u(0x301) trackPattern(decomposed, acute, "ang/acute") --[=[ [[Special:WhatLinksHere/Wiktionary:Tracking/script/Greek/wrong-phi]] [[Special:WhatLinksHere/Wiktionary:Tracking/script/Greek/wrong-theta]] [[Special:WhatLinksHere/Wiktionary:Tracking/script/Greek/wrong-kappa]] [[Special:WhatLinksHere/Wiktionary:Tracking/script/Greek/wrong-rho]] ϑ, ϰ, ϱ, ϕ should generally be replaced with θ, κ, ρ, φ. ]=] elseif langCode == "el" or langCode == "grc" then trackPattern(text, "ϑ", "Greek/wrong-theta") trackPattern(text, "ϰ", "Greek/wrong-kappa") trackPattern(text, "ϱ", "Greek/wrong-rho") trackPattern(text, "ϕ", "Greek/wrong-phi") --[=[ [[Special:WhatLinksHere/Wiktionary:Tracking/script/Ancient Greek/spacing-coronis]] [[Special:WhatLinksHere/Wiktionary:Tracking/script/Ancient Greek/spacing-smooth-breathing]] [[Special:WhatLinksHere/Wiktionary:Tracking/script/Ancient Greek/wrong-apostrophe]] When spacing coronis and spacing smooth breathing are used as apostrophes, they should be replaced with right single quotation marks (’). ]=] if langCode == "grc" then trackPattern(text, u(0x1FBD), "Ancient Greek/spacing-coronis") trackPattern(text, u(0x1FBF), "Ancient Greek/spacing-smooth-breathing") trackPattern(text, "[" .. u(0x1FBD) .. u(0x1FBF) .. "]", "Ancient Greek/wrong-apostrophe", true) end -- [[Special:WhatLinksHere/Wiktionary:Tracking/script/Russian/grave-accent]] elseif langCode == "ru" then local decomposed = toNFD(text) trackPattern(decomposed, u(0x300), "Russian/grave-accent") -- [[Special:WhatLinksHere/Wiktionary:Tracking/script/Chuvash/latin-homoglyph]] elseif langCode == "cv" then trackPattern(text, "[ĂăĔĕÇçŸÿ]", "Chuvash/latin-homoglyph") -- [[Special:WhatLinksHere/Wiktionary:Tracking/script/Tibetan/trailing-punctuation]] elseif langCode == "bo" then trackPattern(text, "[་།]$", "Tibetan/trailing-punctuation") trackPattern(text, "[་།]%]%]$", "Tibetan/trailing-punctuation") --[=[ [[Special:WhatLinksHere/Wiktionary:Tracking/script/Thai/broken-ae]] [[Special:WhatLinksHere/Wiktionary:Tracking/script/Thai/broken-am]] [[Special:WhatLinksHere/Wiktionary:Tracking/script/Thai/wrong-rue-lue]] ]=] elseif langCode == "th" then trackPattern(text, "เ".."เ", "Thai/broken-ae") trackPattern(text, "ํ[่้๊๋]?า", "Thai/broken-am") trackPattern(text, "[ฤฦ]า", "Thai/wrong-rue-lue") --[=[ [[Special:WhatLinksHere/Wiktionary:Tracking/script/Lao/broken-ae]] [[Special:WhatLinksHere/Wiktionary:Tracking/script/Lao/broken-am]] [[Special:WhatLinksHere/Wiktionary:Tracking/script/Lao/possible-broken-ho-no]] [[Special:WhatLinksHere/Wiktionary:Tracking/script/Lao/possible-broken-ho-mo]] [[Special:WhatLinksHere/Wiktionary:Tracking/script/Lao/possible-broken-ho-lo]] ]=] elseif langCode == "lo" then trackPattern(text, "ເ".."ເ", "Lao/broken-ae") trackPattern(text, "ໍ[່້໊໋]?າ", "Lao/broken-am") trackPattern(text, "ຫນ", "Lao/possible-broken-ho-no") trackPattern(text, "ຫມ", "Lao/possible-broken-ho-mo") trackPattern(text, "ຫລ", "Lao/possible-broken-ho-lo") --[=[ [[Special:WhatLinksHere/Wiktionary:Tracking/script/Lü/broken-ae]] [[Special:WhatLinksHere/Wiktionary:Tracking/script/Lü/possible-wrong-sequence]] ]=] elseif langCode == "khb" then trackPattern(text, "ᦵ".."ᦵ", "Lü/broken-ae") trackPattern(text, "[ᦀ-ᦫ][ᦵᦶᦷᦺ]", "Lü/possible-wrong-sequence") end end end local function Kore_ruby(...) -- Cache character sets on the first call. local Hang_chars = get_script("Hang"):getCharacters() local Hani_chars = get_script("Hani"):getCharacters() -- Overwrite with the actual function, which is called directly on subsequent calls. function Kore_ruby(txt) return (ugsub(txt, "([%-".. Hani_chars .. "]+)%(([%-" .. Hang_chars .. "]+)%)", "<ruby>%1<rp>(</rp><rt>%2</rt><rp>)</rp></ruby>")) end return Kore_ruby(...) end --[==[Wraps the given text in HTML tags with appropriate CSS classes (see [[WT:CSS]]) for the [[Module:languages#Language objects|language]] and script. This is required for all non-English text on Wiktionary. The actual tags and CSS classes that are added are determined by the <code>face</code> parameter. It can be one of the following: ; {{code|lua|"term"}} : The text is wrapped in {{code|html|2=<i class="(sc) mention" lang="(lang)">...</i>}}. ; {{code|lua|"head"}} : The text is wrapped in {{code|html|2=<strong class="(sc) headword" lang="(lang)">...</strong>}}. ; {{code|lua|"hypothetical"}} : The text is wrapped in {{code|html|2=<span class="hypothetical-star">*</span><i class="(sc) hypothetical" lang="(lang)">...</i>}}. ; {{code|lua|"bold"}} : The text is wrapped in {{code|html|2=<b class="(sc)" lang="(lang)">...</b>}}. ; {{code|lua|nil}} : The text is wrapped in {{code|html|2=<span class="(sc)" lang="(lang)">...</span>}}. The optional <code>class</code> parameter can be used to specify an additional CSS class to be added to the tag.]==] function export.tag_text(text, lang, sc, face, class, id) if not sc then if lang then sc = lang:findBestScript(text) else sc = find_best_script_without_lang(text) end end track_text(text, lang, sc) -- Replace space characters with newlines in Mongolian-script text, which is written top-to-bottom. if sc:getDirection():find("vertical", nil, true) and text:find(" ", nil, true) then text = munge_text(text, function(txt) -- having extra parentheses makes sure only the first return value gets through return (txt:gsub(" +", "<br>")) end) end -- Hack Korean script text to remove hyphens. -- FIXME: This should be handled in a more general fashion, but needs to -- be efficient by not doing anything if no hyphens are present, and currently this is the only -- language needing such processing. -- 20220221: Also convert 漢字(한자) to ruby, instead of needing [[Template:Ruby]]. if sc:getCode() == "Kore" and text:match("[%-()g]") then local title, display = require("Module:links").get_wikilink_parts(text, true) if title ~= nil then -- special case that the text is a single link, do not munge and preserve affix hyphens if lang and lang:getCode() == "okm" then -- Middle Korean code from [[User:Chom.kwoy]] -- Comment from [[User:Lunabunn]]: -- In Middle Korean orthography, syllable formation is phonemic as opposed to morpheme-boundary-based a la -- modern Korean. As such, for example, if you were to write nam-i, it would be rendered as na.mi so if you -- then put na-mi to indicate particle boundaries as in modern Korean, the hyphen would be misplaced. -- Previously, this was alleviated by specialcasing na--mi but [[User:Theknightwho]] made that resolve to - -- in the Hangul (previously we used to just delete all -s in Hangul processing), so it broke. -- [[User:Chom.kwoy]] implemented a different solution, which is writing -> instead using however many >s to -- shift the hyphen by that number of letters in the romanization. -- By the time we are called, > signs have been converted to &gt; by a call to encode_entities() in -- make_link() in [[Module:links]] (near the bottom of the function). -- 'g' in Middle Korean is a special sign to treat the following ㅇ sign as /G/ instead of null. display = display:gsub("&gt;", ""):gsub("g", "") end if display:find("<") then display = munge_text(display, function(txt) txt = txt:gsub("(.)%-(%-?)(.)", "%1%2%3") return Kore_ruby(txt) end) else display = display:gsub("(.)%-(%-?)(.)", "%1%2%3") display = Kore_ruby(display) end text = "[[" .. title .. "|" .. display .. "]]" else text = munge_text(text, function(txt) if lang and lang:getCode() == "okm" then txt = txt:gsub("&gt;", ""):gsub("g", "") end if txt == text then -- special case for the entire text being plain txt = txt:gsub("(.)%-(%-?)(.)", "%1%2%3") else txt = txt:gsub("%-(%-?)", "%1") end return Kore_ruby(txt) end) end end if sc:getCode() == "Image" then face = nil end if face == "hypothetical" then -- [[Special:WhatLinksHere/Wiktionary:Tracking/script-utilities/face/hypothetical]] track("script-utilities/face/hypothetical") end local data = (m_data or get_data()).faces[face or "plain"] if data == nil then error('Invalid script face "' .. face .. '".') end local tag = data.tag local opening_tag = {tag} if lang and id then insert(opening_tag, 'id="' .. language_anchor(lang, id) .. '"') end local classes = {data.class} -- if the script code is hyphenated (i.e. language code-script code, add the last component as a class as well) -- e.g. ota-Arab adds both Arab and ota-Arab as classes if sc:getCode():find("-", nil, true) then insert(classes, 1, (ugsub(sc:getCode(), ".+%-", ""))) insert(classes, 2, sc:getCode()) else insert(classes, 1, sc:getCode()) end if class and class ~= '' then insert(classes, class) end insert(opening_tag, 'class="' .. concat(classes, ' ') .. '"') -- FIXME: Is it OK to insert the etymology-only lang code and have it fall back to the first part of the -- lang code (by chopping off the '-...' part)? It seems the :lang() selector does this; not sure about -- [lang=...] attributes. if lang then insert(opening_tag, 'lang="' .. lang:getFullCode() .. '"') end -- Add a script wrapper return (data.prefix or "") .. "<" .. concat(opening_tag, " ") .. ">" .. text .. "</" .. tag .. ">" end --[==[Tags the transliteration for given text {translit} and language {lang}. It will add the language, script subtag (as defined in [https://www.rfc-editor.org/rfc/bcp/bcp47.txt BCP 47 2.2.3]) and [https://developer.mozilla.org/en-US/docs/Web/HTML/Global_attributes/dir dir] (directional) attributes as needed. The optional <code>kind</code> parameter can be one of the following: ; {{code|lua|"term"}} : tag transliteration for {{temp|mention}} ; {{code|lua|"usex"}} : tag transliteration for {{temp|usex}} ; {{code|lua|"head"}} : tag transliteration for {{temp|head}} ; {{code|lua|"default"}} : default The optional <code>attributes</code> parameter is used to specify additional HTML attributes for the tag.]==] function export.tag_translit(translit, lang, kind, attributes, is_manual) if type(lang) == "table" then -- FIXME: Do better support for etym languages; see https://www.rfc-editor.org/rfc/bcp/bcp47.txt lang = lang.getFullCode and lang:getFullCode() or error("Second argument to tag_translit should be a language code or language object.") end local data = (m_data or get_data()).translit[kind or "default"] local tag = data.tag local opening_tag = {tag} local class = data.class if lang == "ja" then insert(opening_tag, 'class="' .. (class and (class .. " ") or "") .. (is_manual and "manual-tr " or "") .. 'tr"') else insert(opening_tag, 'lang="' .. lang .. '-Latn"') insert(opening_tag, 'class="' .. (class and (class .. " ") or "") .. (is_manual and "manual-tr " or "") .. 'tr Latn"') end local dir = data.dir if dir then insert(opening_tag, 'dir="' .. dir .. '"') end if attributes then track("tag_translit/attributes") insert(opening_tag, attributes) end return "<" .. concat(opening_tag, " ") .. ">" .. translit .. "</" .. tag .. ">" end function export.tag_transcription(transcription, lang, kind, attributes) if type(lang) == "table" then -- FIXME: Do better support for etym languages; see https://www.rfc-editor.org/rfc/bcp/bcp47.txt lang = lang.getFullCode and lang:getFullCode() or error("Second argument to tag_transcription should be a language code or language object.") end local data = (m_data or get_data()).transcription[kind or "default"] local tag = data.tag local opening_tag = {tag} local class = data.class if lang == "ja" then insert(opening_tag, 'class="' .. (class and (class .. " ") or "") .. 'ts"') else insert(opening_tag, 'lang="' .. lang .. '-Latn"') insert(opening_tag, 'class="' .. (class and (class .. " ") or "") .. 'ts Latn"') end local dir = data.dir if dir then insert(opening_tag, 'dir="' .. dir .. '"') end if attributes then track("tag_transcription/attributes") insert(opening_tag, attributes) end return "<" .. concat(opening_tag, " ") .. ">" .. transcription .. "</" .. tag .. ">" end --[==[Tags {def} as a definition. The <code>def</code> parameter must be one of the following: ; {{code|lua|"gloss"}} : The text is wrapped in {{code|html|2=<span class="(mention-gloss">...</span>}}. ; {{code|lua|"non-gloss"}} : The text is wrapped in {{code|html|2=<span class="use-with-mention">...</span>}}. The optional <code>attributes</code> parameter is used to specify additional HTML attributes for the tag.]==] function export.tag_definition(def, kind, attributes) local data = (m_data or get_data()).definition[kind] if data == nil then error("Second argument to tag_definition should specify the kind of definition from the list in [[Module:script utilities/data]].") end local tag = data.tag local opening_tag = {tag} local class = data.class if class then insert(opening_tag, 'class="' .. class .. '"') end if attributes then insert(opening_tag, attributes) end return "<" .. concat(opening_tag, " ") .. ">" .. def .. "</" .. tag .. ">" end --[==[Generates a request to provide a term in its native script, if it is missing. This is used by the {{temp|rfscript}} template as well as by the functions in [[Module:links]]. The function will add entries to one of the subcategories of [[:Category:Requests for native script by language]], and do several checks on the given language and script. In particular: * If the script was given, a subcategory named "Requests for (script) script" is added, but only if the language has more than one script. Otherwise, the main "Requests for native script" category is used. * Nothing is added at all if the language has no scripts other than Latin and its varieties.]==] function export.request_script(lang, sc, usex, nocat, sort_key) local scripts = lang.getScripts and lang:getScripts() or error('The language "' .. lang:getCode() .. '" does not have the method getScripts. It may be unwritten.') -- By default, request for "native" script local cat_script = "native" local disp_script = "script" -- If the script was not specified, and the language has only one script, use that. if not sc and #scripts == 1 then sc = scripts[1] end -- Is the script known? if sc and sc:getCode() ~= "None" then -- If the script is Latin, return nothing. if export.is_Latin_script(sc) then return "" end if (not scripts[1]) or sc:getCode() ~= scripts[1]:getCode() then disp_script = sc:getCanonicalName() end -- The category needs to be specific to script only if there is chance of ambiguity. This occurs when when the language has multiple scripts (or with codes such as "und"). if (not scripts[1]) or scripts[2] then cat_script = sc:getCanonicalName() end else -- The script is not known. -- Does the language have at least one non-Latin script in its list? local has_nonlatin = false for _, val in ipairs(scripts) do if not export.is_Latin_script(val) then has_nonlatin = true break end end -- If there are no non-Latin scripts, return nothing. if not has_nonlatin and lang:getCode() ~= "und" then return "" end end -- Etymology languages have their own categories, whose parents are the regular language. return "<small>[" .. disp_script .. " needed]</small>" .. (nocat and "" or format_categories("Requests for " .. cat_script .. " script " .. (usex and "in" or "for") .. " " .. lang:getCanonicalName() .. " " .. (usex == "quote" and "quotations" or usex and "usage examples" or "terms"), lang, sort_key ) ) end --[==[This is used by {{temp|rfscript}}. See there for more information.]==] function export.template_rfscript(frame) local boolean = {type = "boolean"} local args = process_params(frame:getParent().args, { [1] = {required = true, type = "language", default = "und"}, ["sc"] = {type = "script"}, ["usex"] = boolean, ["quote"] = boolean, ["nocat"] = boolean, ["sort"] = true, }) local ret = export.request_script(args[1], args["sc"], args.quote and "quote" or args.usex, args.nocat, args.sort) if ret == "" then error("This language is written in the Latin alphabet. It does not need a native script.") end return ret end function export.checkScript(text, scriptCode, result) local scriptObject = get_script(scriptCode) if not scriptObject then error('The script code "' .. scriptCode .. '" is not recognized.') end local originalText = text -- Remove non-letter characters. text = ugsub(text, "%A+", "") -- Remove all characters of the script in question. text = ugsub(text, "[" .. scriptObject:getCharacters() .. "]+", "") if text ~= "" then if type(result) == "string" then error(result) else error('The text "' .. originalText .. '" contains the letters "' .. text .. '" that do not belong to the ' .. scriptObject:getDisplayForm() .. '.', 2) end end end return export 7960wdva9og3gbbozo010obcpp5re6e 828 5976 17413 2026-07-13T08:28:17Z Hiyuune 6766 + 17413 Scribunto text/plain local export = {} local string_utilities_module = "Module:string utilities" local anchor_encode = mw.uri.anchorEncode local concat = table.concat local insert = table.insert local language_anchor -- Defined below. local function decode_entities(...) decode_entities = require(string_utilities_module).decode_entities return decode_entities(...) end local function encode_entities(...) encode_entities = require(string_utilities_module).encode_entities return encode_entities(...) end -- Returns the anchor text to be used as the fragment of a link to a language section. function export.language_anchor(lang, id) return anchor_encode(lang:getFullName() .. ": " .. id) end language_anchor = export.language_anchor -- Normalizes input text (removes formatting etc.), which can then be used as an anchor in an `id=` field. function export.normalize_anchor(str) return decode_entities(anchor_encode(str)) end function export.make_anchors(ids) local anchors = {} for i = 1, #ids do local id = ids[i] local el = mw.html.create("span") :addClass("template-anchor") :attr("id", anchor_encode(id)) :attr("data-id", id) insert(anchors, tostring(el)) end return concat(anchors) end function export.senseid(lang, id, tag_name) -- The following tag is opened but never closed, where is it supposed to be closed? -- with <li> it doesn't matter, as it is closed automatically. -- with <p> it is a problem -- Cannot use mw.html here as it always closes tags return "<" .. tag_name .. " class=\"senseid\" id=\"" .. language_anchor(lang, id) .. "\" data-lang=\"" .. lang:getCode() .. "\" data-id=\"" .. encode_entities(id) .. "\">" end function export.etymid(lang, id) -- Use a <ul> tag to ensure spacing doesn't get messed up. local el = mw.html.create("ul") :addClass("etymid") :attr("id", language_anchor(lang, id)) :attr("data-lang", lang:getCode()) :attr("data-id", id) return tostring(el) end function export.etymonid(lang, id, opts) opts = opts or {} -- Use a <ul> tag to ensure spacing doesn't get messed up. local el = mw.html.create("ul") :addClass("etymonid") :attr("data-lang", lang:getCode()) if id then el:attr("id", language_anchor(lang, id)) el:attr("data-id", id) end if opts.no_tree then el:attr("data-no-tree", "1") end if opts.title then el:attr("data-title", opts.title) end if opts.empty_tree then el:attr("data-empty-tree", "1") end if opts.ety_tree_json then el:attr("data-ety-tree-json", opts.ety_tree_json) end return tostring(el) end return export 2o0jqln8y0bxvpfhe66eogs2k88qkap 828 5977 17414 2026-07-13T08:28:58Z Hiyuune 6766 + 17414 Scribunto text/plain local data = {} local translit = { ["term"] = { --[=[ can't be done until Kana transliterations are correctly parsed by [[Module:links]] ["tag"] = "i", ]=] ["class"] = "mention-tr", }, ["usex"] = { ["tag"] = "i", ["class"] = "e-transliteration", }, ["head"] = { ["class"] = "headword-tr", ["dir"] = "ltr", }, ["default"] = {}, } for _, v in next, translit do if not v.tag then v.tag = "span" end end data.translit = translit data.transcription = { ["head"] = { ["tag"] = "span", ["class"] = "headword-ts", ["dir"] = "ltr", }, ["usex"] = { ["tag"] = "span", ["class"] = "e-transcription", }, ["default"] = {}, } data.definition = { ["gloss"] = { ["tag"] = "span", ["class"] = "mention-gloss", }, ["non-gloss"] = { ["tag"] = "span", ["class"] = "use-with-mention", }, } local faces = { ["term"] = { ["tag"] = "i", ["class"] = "mention", }, ["head"] = { ["tag"] = "strong", ["class"] = "headword", }, ["hypothetical"] = { ["prefix"] = '<span class="hypothetical-star">*</span>', ["tag"] = "i", ["class"] = "hypothetical", }, ["bold"] = { ["tag"] = "b", }, ["plain"] = { ["tag"] = "span", } } faces["translation"] = faces["plain"] data.faces = faces return data glatf44lq0ipqkut0sozbs72zba142n 828 5978 17415 2026-07-13T08:29:56Z Hiyuune 6766 + 17415 Scribunto text/plain local m = {} m["aa"] = { aliases = {"Qafar"}, } m["ab"] = { aliases = {"Abkhazian", "Abxazo"}, } m["ae"] = { aliases = {"Zend", "Old Bactrian"}, } m["af"] = { } m["ak"] = { varieties = {"Twi-Fante", "Twi", {"Fante", "Fanti"}, "Asante", "Akuapem", "Abron", "Brong", "Wasa"}, } m["am"] = { } m["an"] = { } m["ar"] = { -- FIXME, some of the following are varieties but it's not clear which ones aliases = {"Standard Arabic", "Literary Arabic", "High Arabic"}, varieties = {"Modern Standard Arabic", "Classical Arabic", "Judeo-Arabic"}, } m["as"] = { aliases = {"Asamiya"}, } m["av"] = { aliases = {"Avaric"}, } m["ay"] = { varieties = {"Southern Aymara", "Central Aymara"}, } m["az"] = { aliases = {"Azeri", "Azari", "Azeri Turkic", "Azerbaijani Turkic"}, varieties = {"North Azerbaijani", "South Azerbaijani", {"Afshar", "Afshari", "Afshar Azerbaijani", "Afchar"}, {"Qashqa'i", "Qashqai", "Kashkay"}, "Sonqor" }, } m["ba"] = { } m["be"] = { aliases = {"Belorussian", "Belarusan", "Bielorussian", "Byelorussian", "Belarussian", "White Russian"}, } m["bg"] = { } m["bh"] = { } m["bi"] = { } m["bm"] = { aliases = {"Bamanankan"}, } m["bn"] = { aliases = {"Bangla"}, } m["bo"] = { varieties = { {"Amdo Tibetan", "Amdo"}, "Dolpo", {"Khams", "Khams Tibetan"}, "Khamba", "Gola", "Humla", "Limi", {"Lhasa", "Lhasa Tibetan"}, "Lhomi", "Loke", "Lowa", "Mugom", "Mugu", "Mustang", "Nubri", "Panang", "Shing Saapa", "Thudam", "Tichurong", "Tseku", {"Ü", "Dbus"}, "Walungge"}, -- and "Gyalsumdo", "Lower Manang"? "Kyirong"? } m["br"] = { varieties = {{"Gwenedeg", "Vannetais"}, {"Kerneveg", "Cornouaillais"}, {"Leoneg", "Léonard"}, {"Tregerieg", "Trégorrois"}}, } m["ca"] = { -- don't list varieties here that are in [[Module:etymology languages/data]] } m["ce"] = { } m["ch"] = { aliases = {"Chamoru"}, } m["co"] = { aliases = {"Corsu"}, } m["cr"] = { } m["cs"] = { } m["cu"] = { aliases = {"Old Church Slavic"}, } m["cv"] = { } m["cy"] = { varieties = {"Cofi Welsh", {"Dyfedeg", "Dyfed Welsh", "Demetian"}, {"Gwenhwyseg", "Gwent Welsh", "Gwentian"}, {"Gwyndodeg", "Gwynedd Welsh", "Venedotian"}, {"Powyseg", "Powys Welsh", "Powysian"}, "Patagonian Welsh"}, } m["da"] = { } m["de"] = { aliases = {"High German", "New High German", "Deutsch"}, varieties = {"Alsatian German", "American German", "Bavarian German", "Belgian German", "Central German", "DDR German", "East African German", "German German", "Hessian German", "Indiana German", "Liechtenstein German", "Lorraine German", "Luxembourgish German", "Namibian German", "Northern German", "Prussian German", "Silesia German", "South African German", "Southern German", "South Tyrolean German", "Switzerland German", "Texan German"}, } m["dv"] = { aliases = {"Divehi", "Maldivian"}, varieties = {{"Mahal", "Mahl"}}, } m["dz"] = { } m["ee"] = { } m["el"] = { aliases = {"Modern Greek", "Neo-Hellenic"}, } m["en"] = { aliases = {"Modern English", "New English"}, varieties = {"Polari", "Yinglish"}, } m["eo"] = { } m["es"] = { aliases = {"Castilian"}, varieties = {{"Amazonian Spanish", "Amazonic Spanish"}, "Loreto-Ucayali Spanish"}, } m["et"] = { } m["eu"] = { aliases = {"Euskara"}, } m["fa"] = { aliases = {"Farsi", "New Persian", "Modern Persian"}, varieties = {{"Western Persian", "Iranian Persian"}, {"Eastern Persian", "Dari"}, {"Aimaq", "Aimak", "Aymaq", "Eimak"}}, } m["ff"] = { aliases = {"Fulani"}, varieties = {"Adamawa Fulfulde", "Bagirmi Fulfulde", "Borgu Fulfulde", "Central-Eastern Niger Fulfulde", "Fulfulde", "Maasina Fulfulde", "Nigerian Fulfulde", "Pular", "Pulaar", "Western Niger Fulfulde"}, -- Maasina, etc are dialects, subsumed into this code; Pular and Pulaar are distinct } m["fi"] = { aliases = {"Suomi"}, } m["fj"] = { } m["fo"] = { aliases = {"Faeroese"}, } m["fr"] = { aliases = {"Modern French"}, varieties = {"African French", "Algerian French", "Alsatian French", "Antilles French", "Atlantic Canadian French", "Belgian French", "Congolese French", "European French", "French French", "Haitian French", "Ivorian French", "Lorraine French", "Louisiana French", "Luxembourgish French", "Malian French", "Marseille French", "Missourian French", "Moroccan French", "Newfoundland French", "North American French", "Picard French", "Provençal French", "Quebec French", "Réunion French", "Rwandan French", "Tunisian French", "West African French"}, } m["fy"] = { aliases = {"Western Frisian"}, } m["ga"] = { aliases = {"Irish Gaelic", "Gaelic"}, -- calling it simply "Gaelic" is rare in Ireland, but relatively common in the Irish diaspora varieties = {{"Cois Fharraige Irish", "Cois Fhairrge Irish"}, {"Connacht Irish", "Connaught Irish"}, "Cork Irish", "Donegal Irish", "Galway Irish", "Kerry Irish", "Mayo Irish", "Munster Irish", "Ulster Irish", "Waterford Irish", "West Muskerry Irish"}, } m["gd"] = { aliases = {"Gaelic", "Gàidhlig", "Scots Gaelic", "Scottish"}, varieties = {"Argyll Gaelic", "Arran Scottish Gaelic", {"Canadian Gaelic", "Canadian Scottish Gaelic", "Cape Breton Gaelic"}, "East Sutherland Gaelic", {"Galwegian Gaelic", "Gallovidian Gaelic", "Gallowegian Gaelic", "Galloway Gaelic"}, "Hebridean Gaelic", "Highland Gaelic"}, } m["gl"] = { } m["gu"] = { } m["gv"] = { aliases = {"Manx Gaelic"}, varieties = {"Northern Manx", "Southern Manx"}, } m["ha"] = { } m["he"] = { aliases = {"Ivrit"}, } m["hi"] = { other_names = {"Hindavi"}, } m["ho"] = { aliases = {"Pidgin Motu", "Police Motu"}, } m["ht"] = { aliases = {"Creole", "Haitian", "Kreyòl"}, } m["hu"] = { aliases = {"Magyar"}, } m["hy"] = { aliases = {"Modern Armenian"}, varieties = {"Eastern Armenian", "Western Armenian"}, } m["hz"] = { } m["ia"] = { } m["id"] = { } m["ie"] = { aliases = {"Occidental"}, } m["ig"] = { } m["ii"] = { aliases = { "Nosu", "Nuosu Yi", "Nosu Yi", "Sichuan Yi", "Northern Yi", "Liangshan Yi", }, } m["ik"] = { aliases = {"Inupiak", "Iñupiaq", "Inupiatun"}, } m["io"] = { } m["is"] = { } m["it"] = { } m["iu"] = { varieties = { "Aivilimmiut", {"Eastern Canadian Inuktitut", "Eastern Canadian Inuit"}, {"Inuinnaq", "Inuinnaqtun"}, {"Inuvialuktun", "Inuvialuk", "Western Canadian Inuktitut", "Western Canadian Inuit", "Western Canadian Inuktun"}, "Kivallirmiut", "Natsilingmiut", "Nunavimmiutit", "Nunatsiavummiut", {"Siglitun", "Siglit"}}, } m["ja"] = { aliases = {"Modern Japanese", "Nipponese", "Nihongo"}, } m["jv"] = { } m["ka"] = { varieties = {{"Judeo-Georgian", "Kivruli", "Gruzinic"}}, } m["kg"] = { aliases = {"Kikongo"}, varieties = {"Koongo", "Laari", "San Salvador Kongo", "Yombe"}, } m["ki"] = { aliases = {"Gikuyu", "Gĩkũyũ"}, } m["kj"] = { aliases = {"Kuanyama", "Oshikwanyama"}, } m["kk"] = { } m["kl"] = { aliases = {"Kalaallisut"}, } m["km"] = { aliases = {"Cambodian", "Central Khmer", "Modern Khmer"}, } m["kn"] = { } m["ko"] = { aliases = {"Modern Korean"}, } m["kr"] = { varieties = {"Kanembu", "Bilma Kanuri", "Central Kanuri", "Manga Kanuri", "Tumari Kanuri"}, } m["ks"] = { aliases = {"Koshur"}, } -- "kv" is treated as "koi", "kpv", see [[WT:LT]] m["kw"] = { } m["ky"] = { aliases = {"Kirghiz", "Kirgiz"}, } m["la"] = { } m["lb"] = { } m["lg"] = { aliases = {"Ganda", "Oluganda"}, } m["li"] = { aliases = {"Limburgan", "Limburgian", "Limburgic"}, } m["ln"] = { aliases = {"Ngala"}, } m["lo"] = { aliases = {"Laotian"}, } m["lt"] = { } m["lu"] = { } m["lv"] = { aliases = {"Lettish", "Lett"}, } m["mg"] = { varieties = { {"Antankarana", "Antankarana Malagasy"}, {"Bara Malagasy", "Bara"}, {"Betsimisaraka Malagasy", "Betsimisaraka"}, {"Northern Betsimisaraka Malagasy", "Northern Betsimisaraka"}, {"Southern Betsimisaraka Malagasy", "Southern Betsimisaraka"}, {"Bushi", "Shibushi", "Kibushi"}, {"Masikoro Malagasy", "Masikoro"}, "Plateau Malagasy", "Sakalava", {"Tandroy Malagasy", "Tandroy"}, {"Tanosy", "Tanosy Malagasy"}, "Tesaka", {"Tsimihety", "Tsimihety Malagasy"}}, } m["mh"] = { } m["mi"] = { aliases = {"Maori"}, } m["mk"] = { } m["ml"] = { } m["mn"] = { varieties = {"Khalkha Mongolian"}, } -- "mo" is treated as "ro", see [[WT:LT]] m["mr"] = { } m["ms"] = { aliases = {"Malaysian", "Standard Malay"}, } m["mt"] = { } m["my"] = { aliases = {"Myanmar"}, varieties = {"Mandalay Burmese", "Myeik Burmese", "Palaw Burmese", {"Rangoon Burmese", "Yangon Burmese"}, "Yaw Burmese"}, } m["na"] = { aliases = {"Nauru"}, } m["nb"] = { aliases = {"Bokmål"}, } m["nd"] = { aliases = {"North Ndebele"}, } m["ne"] = { aliases = {"Nepalese"}, varieties = {"Palpa"}, -- 3832956, former "plp", retired by ISO as spurious } m["ng"] = { } m["nl"] = { varieties = {"Netherlandic", "Flemish"}, -- FIXME, check this } m["nn"] = { aliases = {"New Norwegian", "Nynorsk"}, } m["no"] = { } m["nr"] = { aliases = {"South Ndebele"}, } m["nv"] = { aliases = {"Navaho", "Diné bizaad"}, } m["ny"] = { aliases = {"Chicheŵa", "Chinyanja", "Nyanja", "Chewa", "Cicewa", "Cewa", "Cinyanja"}, } m["oc"] = { -- don't list varieties here that are in [[Module:etymology languages/data]] } m["oj"] = { aliases = {"Ojibway", "Ojibwa"}, varieties = {{"Chippewa", "Ojibwemowin", "Southwestern Ojibwa"}}, } m["om"] = { varieties = {"Orma", "Borana-Arsi-Guji Oromo", "West Central Oromo"}, } m["or"] = { aliases = {"Oriya", "Oorya"}, } m["os"] = { aliases = {"Ossete", "Ossetic"}, varieties = {"Digor", "Iron"}, } m["pa"] = { aliases = {"Panjabi"}, } m["pi"] = { } m["pl"] = { } m["ps"] = { aliases = {"Pashtun", "Pushto", "Pashtu", "Afghani"}, varieties = {"Central Pashto", "Northern Pashto", "Southern Pashto", {"Pukhto", "Pakhto", "Pakkhto"}}, } m["pt"] = { aliases = {"Modern Portuguese"}, } m["qu"] = { } m["rm"] = { aliases = {"Romansch", "Rumantsch", "Romanche"}, -- don't list varieties here that are in [[Module:etymology languages/data]] varieties = {"Sursilvan-Oberland"}, -- extra variety in Glottolog; main varieties have their own etym codes } m["ro"] = { aliases = {"Daco-Romanian", "Roumanian", "Rumanian"}, } m["ru"] = { } m["rw"] = { -- don't list varieties here that are in [[Module:etymology languages/data]] varieties = {{"Ha", "Giha"}, "Hangaza", "Vinza", "Shubi"}, -- Deleted "Subi", which normally refers to a different language } m["sa"] = { } m["sc"] = { -- don't list varieties here that are in [[Module:etymology languages/data]] } m["sd"] = { } m["se"] = { aliases = {"North Sami", "Northern Saami", "North Saami"}, } m["sg"] = { } m["sh"] = { aliases = {"BCS", "Croato-Serbian", "Serbocroatian"}, -- don't list varieties here that are in [[Module:etymology languages/data]] varieties = {"Bosnian", "Croatian", "Montenegrin", "Serbian", "Shtokavian"}, } m["si"] = { aliases = {"Singhalese", "Sinhala"}, } m["sk"] = { } m["sl"] = { aliases = {"Slovenian"}, } m["sm"] = { } m["sn"] = { } m["so"] = { } m["sq"] = { -- don't list varieties here that are in [[Module:etymology languages/data]] } m["ss"] = { aliases = {"Swati"}, } m["st"] = { aliases = {"Sesotho", "Southern Sesotho", "Southern Sotho"}, } m["su"] = { } m["sv"] = { } m["sw"] = { varieties = {{"Settler Swahili", "KiSetla", "KiSettla", "Setla", "Settla", "Kitchen Swahili"}, {"Kihindi", "Indian Swahili"}, {"KiShamba", "Kishamba", "Field Swahili"}, {"Kibabu", "Asian Swahili"}, {"Kimanga", "Arab Swahili"}, {"Kitvita", "Army Swahili"}}, } m["ta"] = { } m["te"] = { } m["tg"] = { aliases = {"Eastern Persian", "Tadjik", "Tadzhik", "Tajiki", "Tajik Persian", "Tajiki Persian"}, } m["th"] = { aliases = {"Central Thai", "Siamese"}, } m["ti"] = { aliases = {"Tigrigna"}, } m["tk"] = { } m["tl"] = { } m["tn"] = { aliases = {"Setswana"}, } m["to"] = { } m["tr"] = { } m["ts"] = { aliases = {"Xitsonga"}, } m["tt"] = { } -- "tw" is treated as "ak", see [[WT:LT]] m["ty"] = { } m["ug"] = { aliases = {"Uigur", "Uighur", "Uygur"}, } m["uk"] = { } m["ur"] = { } m["uz"] = { varieties = {"Northern Uzbek", "Southern Uzbek"}, } m["ve"] = { } m["vi"] = { aliases = {"Annamese", "Annamite"}, } m["vo"] = { } m["wa"] = { varieties = {"Liégeois", "Namurois", "Wallo-Picard", "Wallo-Lorrain"}, } m["wo"] = { varieties = {"Gambian Wolof"}, -- the subsumed dialect 'wof' } m["xh"] = { } m["yi"] = { varieties = {"American Yiddish", "Daytshmerish Yiddish", "Mideastern Yiddish", "Galitzish", {"Northeastern Yiddish", "Litvish", "Lithuanian Yiddish"}, {"Northwestern Yiddish", "Netherlandic Yiddish"}, {"Polish Yiddish", "Poylish"}, "South African Yiddish", {"Southeastern Yiddish", "Ukrainian Yiddish", "Ukrainish"}, {"Southwestern Yiddish", "Judeo-Alsatian"}, "Udmurtish" }, } m["yo"] = { } m["za"] = { -- FIXME, are all of the following distinct? varieties = { "Chongzuo Zhuang", "Guibei Zhuang", "Guibian Zhuang", "Central Hongshuihe Zhuang", "Eastern Hongshuihe Zhuang", "Lianshan Zhuang", "Liujiang Zhuang", "Liuqian Zhuang", {"Min Zhuang", "Minz Zhuang"}, "Nong Zhuang", -- see zhn "Qiubei Zhuang", "Shangsi Zhuang", {"Dai Zhuang", "Wenma", "Wenma Thu", "Wenma Zhuang"}, "Yang Zhuang", {"Yongbei Zhuang", "Wuming Zhuang", "Standard Zhuang"}, "Yongnan Zhuang", "Youjiang Zhuang", "Zuojiang Zhuang"}, } m["zh"] = { } m["zu"] = { aliases = {"isiZulu"}, } return m 8dzyaary1ol9c8nzyck3kxai4c2ysq5 828 5979 17416 2026-07-13T08:30:36Z Hiyuune 6766 Created page with "local table_keys_to_list_module = "Module:table/keysToList" local function keys_to_list(...) keys_to_list = require(table_keys_to_list_module) return keys_to_list(...) end --[==[ Iterates through a table, with the keys sorted using the keysToList function. If there are only numerical keys, `export.sparseIpairs` is probably faster.]==] return function(t, key_sort) local list, i = keys_to_list(t, key_sort), 0 return function() i = i + 1 local k = list[i] if k..." 17416 Scribunto text/plain local table_keys_to_list_module = "Module:table/keysToList" local function keys_to_list(...) keys_to_list = require(table_keys_to_list_module) return keys_to_list(...) end --[==[ Iterates through a table, with the keys sorted using the keysToList function. If there are only numerical keys, `export.sparseIpairs` is probably faster.]==] return function(t, key_sort) local list, i = keys_to_list(t, key_sort), 0 return function() i = i + 1 local k = list[i] if k ~= nil then return k, t[k] end end end k9kspqkam96jj5np6nfk0sg15yvnnd3 828 5980 17417 2026-07-13T08:31:08Z Hiyuune 6766 + 17417 Scribunto text/plain local compare_module = "Module:compare" local pairs = pairs local sort = table.sort local compare local function get_compare() compare, get_compare = require(compare_module), nil return compare end --[==[ Returns a list of the keys in a table, sorted using either the default `table.sort` function or a custom `key_sort` function. If there are only numerical keys, [[Module:table/numKeys]] is probably faster.]==] return function(t, key_sort) local list, i = {}, 0 for key in pairs(t) do i = i + 1 list[i] = key end -- Use specified sort function, or otherwise `compare`. sort(list, key_sort == nil and (compare or get_compare()) or key_sort) return list end db7h2mui4n7duv8tkb39qolcbe3t8rm 828 5981 17418 2026-07-13T08:31:41Z Hiyuune 6766 + 17418 Scribunto text/plain local math_compare_module = "Module:math/compare" local string_compare_module = "Module:string/compare" local table_compare_module = "Module:table/compare" local require = require local type = type local types local function get_types() types, get_types = { ["nil"] = "\1", ["boolean"] = "\2", ["number"] = "\3", ["string"] = "\4", }, nil return types end local compare_funcs local function get_compare_funcs() compare_funcs = {} function compare_funcs.boolean(a, b) return a == true and b == false end function compare_funcs.number(...) local math_compare = require(math_compare_module) compare_funcs.number = math_compare return math_compare(...) end function compare_funcs.string(...) local string_compare = require(string_compare_module) compare_funcs.string = string_compare return string_compare(...) end function compare_funcs.table(...) local table_compare = require(table_compare_module) compare_funcs.table = table_compare return table_compare(...) end get_compare_funcs = nil return compare_funcs end --[==[ A general comparison function, which returns {true} if {a} sorts before {b}, or otherwise {false}; it can be used as the sort function with {table.sort}. This function is roughly equivalent to the {<} operator, but is capable of comparing a mix of types, using the following rules: * When items of different types are compared, the type-order is {"nil"}, {"boolean"}, {"number"}, {"string"}, then alphabetical order by type name for all other types. * Numbers are compared with [[Module:math/compare]]. * Strings are compared with [[Module:string/compare]]. * Tables are compared with [[Module:table/compare]]. * Boolean {true} sorts before {false}. * All other types always return {false}.]==] return function(a, b) local type_a, type_b = type(a), type(b) if type_a == type_b then local func = (compare_funcs or get_compare_funcs())[type_a] return func and func(a, b) or false end return ((types or get_types())[type_a] or type_a) < (types[type_b] or type_b) end fs82yur52kblfpa4j6uwsb5dbcxr7em 828 5982 17419 2026-07-13T08:32:02Z Hiyuune 6766 + 17419 Scribunto text/plain local math_module = "Module:math" local function is_NaN(...) is_NaN = require(math_module).is_NaN return is_NaN(...) end local function sign(...) sign = require(math_module).sign return sign(...) end --[==[ A comparison function for numbers, which returns {true} if {a} sorts before {b}, or otherwise {false}; it can be used as the sort function with {table.sort}. This function is roughly equivalent to the {<} operator, but contains the following special considerations in accordance with the {{w|IEEE 754}} standard: * {{w|NaN}} is sorted as though it has a larger absolute value than infinity ({-NaN < -Inf}; {+Inf < +NaN}). * {{w|Signed zero}} is acknowledged, with {-0 < +0}.]==] return function(a, b) -- <, > and == canot return true if either `a` or `b` are NaN. if a < b then return true -- Use > then == instead of >=, so that the ±0 check is only done when `a` -- and `b` are equal. elseif a > b then return false elseif a == b then -- 1/(+0) is Inf; 1/(-0) is -Inf. return a == 0 and b == 0 and 1 / a < 1 / b or false -- One or both must be NaN, and NaN is the only number that returns false -- to a self-equality check, so if `a` == `a` then `b` is NaN (and vice- -- versa). -NaN sorts before everything and +NaN after everything, so the -- sign determines the result. elseif not is_NaN(a) then -- `b` is NaN return sign(b) == 1 elseif not is_NaN(b) then -- `a` is NaN return sign(a) == -1 end -- If both are NaN, only return true if `a` is -NaN and `b` is +NaN. return sign(a) < sign(b) end 632obodjr2zjfbz9zpr3erx1io9vwm4 828 5983 17420 2026-07-13T08:34:07Z Hiyuune 6766 + 17420 Scribunto text/plain local pairs = pairs --[==[ Returns true if all keys in the table are consecutive integers starting from 1.]==] return function(t) -- pairs() is unordered, but can be assumed to return every key in `t`, so -- if every integer key from 1 to n (the number of keys in `t`) is in use, -- then all the keys in `t` form an integer range from 1 to n, making `t` -- a contiguous array. local i = 0 for _ in pairs(t) do i = i + 1 if t[i] == nil then return false end end return true end g82iokgqr1uqfaagx0is49bas3cpq0c 828 5984 17421 2026-07-13T08:34:38Z Hiyuune 6766 + 17421 Scribunto text/plain local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared local m = {} m["daa"] = { "Dangaléat", 942591, "cdc-est", "Latn", } m["dac"] = { "Dambi", 12629491, "poz-ocw", "Latn", } m["dad"] = { "Marik", 6763404, "poz-ocw", "Latn", } m["dae"] = { "Duupa", 35263, "alv-dur", "Latn", } m["dag"] = { "Dagbani", 32238, "nic-dag", "Latn", } m["dah"] = { "Gwahatike", 5623246, "ngf-war", "Latn", } m["dai"] = { "Day", 35163, "alv-mbd", "Latn", } m["daj"] = { "Dar Fur Daju", 56370, "sdv-daj", "Latn", } m["dak"] = { "Dakota", 530384, "sio-dkt", "Latn", } m["dal"] = { "Dahalo", 35143, "cus", "Latn", } m["dam"] = { "Damakawa", 1158134, "nic-knn", "Latn", } m["dao"] = { "Daai Chin", 860029, "tbq-kuk", "Latn", } m["daq"] = { "Dandami Maria", 12952805, "dra-mdy", "Deva", } m["dar"] = { "Dargwa", 32332, "cau-drg", "Cyrl, Latn, Arab", translit = {Cyrl = "dar-translit"}, override_translit = true, display_text = {Cyrl = s["cau-Cyrl-displaytext"]}, strip_diacritics = { Cyrl = s["cau-Cyrl-stripdiacritics"], Latn = s["cau-Latn-stripdiacritics"], }, sort_key = { Cyrl = { from = { "къкъ", "хьхь", -- 4 chars "гъ", "гь", "гӏ", "ё", "къ", "кь", "кӏ", "пп", "пӏ", "сс", "тт", "тӏ", "хх", "хъ", "хь", "хӏ", "цц", "цӏ", "чч", "чӏ" -- 2 chars }, to = { "к" .. p[2], "х" .. p[4], "г" .. p[1], "г" .. p[2], "г" .. p[3], "е" .. p[1], "к" .. p[1], "к" .. p[3], "к" .. p[4], "п" .. p[1], "п" .. p[2], "с" .. p[1], "т" .. p[1], "т" .. p[2], "х" .. p[1], "х" .. p[2], "х" .. p[3], "х" .. p[5], "ц" .. p[1], "ц" .. p[2], "ч" .. p[1], "ч" .. p[2] } }, }, } m["das"] = { "Daho-Doo", 3915369, "kro-wee", "Latn", } m["dau"] = { "Dar Sila Daju", 7514020, "sdv-daj", "Latn", } m["dav"] = { "Taita", 2387274, "bnt-cht", "Latn", } m["daw"] = { "Davawenyo", 5228174, "phi", "Latn", } m["dax"] = { "Dayi", 10467281, "aus-yol", "Latn", } m["daz"] = { "Dao", 5221513, "ngf-pan", "Latn", } m["dba"] = { "Bangime", 1982696, "qfa-iso", -- southern Mali "Latn", } m["dbb"] = { "Deno", 56275, "cdc-wst", "Latn", } m["dbd"] = { "Dadiya", 3914436, "alv-wjk", "Latn", } m["dbe"] = { "Dabe", 5207451, "paa-tor", "Latn", } m["dbf"] = { "Edopi", 12953516, "paa-lpl", "Latn", } m["dbg"] = { "Dogul Dom", 3912880, "nic-npd", "Latn", } m["dbi"] = { "Doka", 3913293, "nic-plc", "Latn", } m["dbj"] = { "Ida'an", 3041552, "poz-san", "Latn", } m["dbl"] = { "Dyirbal", 35465, "aus-dyb", "Latn", } m["dbm"] = { "Duguri", 7194057, "nic-jrw", "Latn", } m["dbn"] = { "Duriankere", 5316627, "ngf-sbh", "Latn", } m["dbo"] = { "Dulbu", 5313310, "nic-jrn", "Latn", } m["dbp"] = { "Duwai", 56301, "cdc-wst", "Latn", } m["dbq"] = { "Daba", 3913342, "cdc-cbm", "Latn", } m["dbr"] = { "Dabarre", 3447286, "cus-som", "Latn", } m["dbt"] = { "Ben Tey", 4886561, "nic-nwa", "Latn", } m["dbu"] = { "Bondum Dom Dogon", 3912758, "nic-npd", "Latn", } m["dbv"] = { "Dungu", 5315230, "nic-kau", "Latn", } m["dbw"] = { "Bankan Tey Dogon", 4856243, "nic-nwa", "Latn", } m["dby"] = { "Dibiyaso", 5272268, "qfa-dis", -- Papuan; isolate per Glottolog, unclassified per Pawley and Hammarström (2018), sometimes classified with Bosavi languages "Latn", } m["dcc"] = { "Deccani", 669431, "inc-hnd", "ur-Arab", ancestors = "ur", } m["dcr"] = { "Negerhollands", 1815830, "crp", "Latn", ancestors = "nl", } m["dda"] = { "Dadi Dadi", 50207890, "aus-pam", "Latn", } m["ddd"] = { "Dongotono", 56676, "sdv-lma", "Latn", } m["dde"] = { "Doondo", 11003401, "bnt-kng", "Latn", } m["ddg"] = { "Fataluku", 35353, "paa-eti", "Latn", } m["ddi"] = { "Diodio", 3028668, "poz-ocw", "Latn", } m["ddj"] = { "Jaru", 3162806, "aus-pam", "Latn", } m["ddn"] = { "Dendi", 35164, "son", "Latn", } m["ddo"] = { "Tsez", 34033, "cau-wts", "Cyrl", translit = "ddo-translit", display_text = {Cyrl = s["cau-Cyrl-displaytext"]}, strip_diacritics = {Cyrl = s["cau-Cyrl-stripdiacritics"]}, } m["ddr"] = { "Dhudhuroa", 5269842, "aus-pam", "Latn", } m["dds"] = { "Donno So Dogon", 1234776, "nic-dge", "Latn", } m["ddw"] = { "Dawera-Daweloor", 5242304, "poz-tim", "Latn", } m["dec"] = { "Dagik", 35125, "alv-tal", "Latn", } m["ded"] = { "Dedua", 5249850, "ngf-huo", "Latn", } m["dee"] = { "Dewoin", 3914892, "kro-wkr", "Latn", } m["def"] = { "Dezfuli", 4115412, "ira-swi", "Arab", } m["deg"] = { "Degema", 35182, "alv-dlt", "Latn", } m["deh"] = { "Dehwari", 5704314, "ira-swi", "fa-Arab", ancestors = "fa", } m["dei"] = { "Demisa", 56380, "paa-egb", "Latn", } -- "dek" is no longer an ISO code; spurious m["dem"] = { "Dem", 5254989, "qfa-dis", -- Papuan; isolate in Glottolog; unclassified in Palmer (2018); grouped with Amung by Usher, ultimately in TNG "Latn", } m["dep"] = { "Pidgin Delaware", 1183938, "crp", "Latn", ancestors = "unm", } -- deq is not included, see [[WT:LT]] m["der"] = { "Deori", 56478, "tbq-bdg", "Beng, Latn", } m["des"] = { "Desano", 962392, "sai-tuc", "Latn", } m["dev"] = { "Domung", 5291378, "ngf-yup", "Latn", } m["dez"] = { "Dengese", 2909984, "bnt-tet", "Latn", } m["dga"] = { "Southern Dagaare", 35159, "nic-mre", "Latn", } m["dgb"] = { "Bunoge", 4985178, "nic-dgw", "Latn", } m["dgc"] = { "Casiguran Dumagat Agta", 5313599, "phi", "Latn", } m["dgd"] = { "Dagaari Dioula", 11153465, "nic-mre", "Latn", } m["dge"] = { "Degenan", 5251770, "ngf-war", "Latn", } m["dgg"] = { "Doga", 3033726, "poz-ocw", "Latn", } m["dgh"] = { "Dghwede", 56293, "cdc-cbm", "Latn", } m["dgi"] = { "Northern Dagara", 11004218, "nic-mre", "Latn", } m["dgk"] = { "Dagba", 12952357, "csu-sar", "Latn", } m["dgn"] = { "Dagoman", 10465931, "aus-yng", "Latn", } m["dgo"] = { "Hindi Dogri", nil, "him", "Deva, Arab, Takr", ancestors = "doi", } m["dgr"] = { "Dogrib", 20979, "ath-nor", "Latn", } m["dgs"] = { "Dogoso", 35343, "nic-gur", } m["dgt"] = { "Ntra'ngith", 6983809, "aus-pam", "Latn", } -- dgu is not a language; see [[w:Dhekaru]] m["dgw"] = { "Daungwurrung", 5228050, "aus-pam", "Latn", } m["dgx"] = { "Doghoro", 12952392, "ngf-bin", "Latn", } m["dgz"] = { "Daga", 5208442, "ngf-dag", "Latn", } m["dhg"] = { "Dhangu", 5268960, "aus-yol", "Latn", } m["dhd"] = { "Dhundhari", 633359, "raj", "Deva", translit = "hi-translit", } m["dhi"] = { "Dhimal", 35229, "sit-dhi", "Deva", } m["dhl"] = { "Dhalandji", 5268787, "aus-psw", "Latn", } m["dhm"] = { "Zemba", 3502283, "bnt-swb", "Latn", ancestors = "hz", } m["dhn"] = { "Dhanki", 5268992, "inc-bhi", } m["dho"] = { "Dhodia", 5269658, "inc-bhi", "Deva", } m["dhr"] = { "Tharrgari", 10470289, "aus-psw", "Latn", } m["dhs"] = { "Dhaiso", 11001788, "bnt-kka", "Latn", } m["dhu"] = { "Dhurga", 1285318, "aus-yuk", "Latn", } m["dhv"] = { "Drehu", 3039319, "poz-cln", "Latn", } m["dhw"] = { "Danuwar", 3522797, "inc-bhi", "Deva", } m["dhx"] = { "Dhungaloo", 16960599, "aus-pam", "Latn", } m["dia"] = { "Dia", 3446591, "paa-wap", "Latn", } m["dib"] = { "South Central Dinka", 35154, "sdv-dnu", "Latn", ancestors = "din", } m["dic"] = { "Lakota Dida", 11001730, "kro-did", "Latn", } m["did"] = { "Didinga", 56365, "sdv", "Latn", } m["dif"] = { "Dieri", 25559563, "aus-kar", "Latn", } m["dig"] = { "Digo", 3362072, "bnt-mij", "Latn", } -- "dih" is split into nai-ipa, nai-kum, nai-tip, see [[WT:LT]] m["dii"] = { "Dimbong", 35196, "bnt-baf", "Latn", } m["dij"] = { "Dai", 5209056, "poz-tim", "Latn", } m["dik"] = { "Southwestern Dinka", 36540, "sdv-dnu", "Latn", ancestors = "din", } m["dil"] = { "Dilling", 35152, "nub-hil", "Latn", } m["dim"] = { "Dime", 35311, "omv-aro", } m["din"] = { "Dinka", 56466, "sdv-dnu", "Latn", } m["dio"] = { "Dibo", 3914891, "alv-ngb", "Latn", } m["dip"] = { "Northeastern Dinka", 36246, "sdv-dnu", "Latn", ancestors = "din", } m["dir"] = { "Dirim", 11130804, "nic-dak", "Latn", } m["dis"] = { "Dimasa", 56664, "tbq-bdg", "Latn, Beng", } m["diu"] = { "Gciriku", 3780954, "bnt-kav", "Latn", } m["diw"] = { "Northwestern Dinka", 36249, "sdv-dnu", "Latn", ancestors = "din", } m["dix"] = { "Dixon Reef", 5284967, "poz-vnc", "Latn", } m["diy"] = { "Diuwe", 5283765, "ngf-asm", "Latn", } m["diz"] = { "Ding", 35202, "bnt-bdz", "Latn", } m["dja"] = { "Djadjawurrung", 5285190, "aus-pam", "Latn", } m["djb"] = { "Djinba", 5285351, "aus-yol", "Latn", } m["djc"] = { "Dar Daju Daju", 5209890, "sdv-daj", "Latn", } m["djd"] = { "Jaminjung", 6147825, "aus-mir", "Latn", } m["dje"] = { "Zarma", 36990, "son", "Latn, Arab, Brai", } m["djf"] = { "Djangun", 10474818, "aus-pmn", "Latn", } m["dji"] = { "Djinang", 5285350, "aus-yol", "Latn", } m["djj"] = { "Ndjébbana", 5285274, "aus-arn", "Latn", } m["djk"] = { "Aukan", 2659044, "crp", "Latn, Afak", ancestors = "en", } m["djl"] = { "Djiwarli", 2669569, "aus-psw", "Latn", } m["djm"] = { "Jamsay", 3913290, "nic-pld", "Latn", } m["djn"] = { "Djauan", 13553748, "aus-gun", "Latn", } m["djo"] = { "Jangkang", 12952388, "day", } m["djr"] = { "Djambarrpuyngu", 3915679, "aus-yol", "Latn", } m["dju"] = { "Kapriman", 6367199, "paa-sep", "Latn", } m["djw"] = { "Djawi", 3913844, "aus-nyu", "Latn", ancestors = "bcj", } m["dka"] = { "Dakpa", 3695189, "sit-ebo", "Tibt", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["dkk"] = { "Dakka", 5209962, "poz-ssw", "Latn", } m["dkr"] = { "Kuijau", 13580777, "poz-bnn", "Latn", } m["dks"] = { "Southeastern Dinka", 36538, "sdv-dnu", "Latn", ancestors = "din", } m["dkx"] = { "Mazagway", 6798209, "cdc-cbm", "Latn", } m["dlg"] = { "Dolgan", 32878, "trk-nsb", "Cyrl", sort_key = { from = {"ё", "һ", "ӈ", "ө", "ү"}, to = {"е" .. p[1], "к" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1]} }, } m["dlk"] = { "Dahalik", 32260, "sem-eth", "Ethi", translit = "Ethi-translit", } m["dlm"] = { "Dalmatian", 35527, "roa-dal", "Latn", } m["dln"] = { "Darlong", 5224029, "tbq-kuk", "Latn", } m["dma"] = { "Duma", 35319, "bnt-nze", "Latn", } m["dmb"] = { "Mombo Dogon", 6897074, "nic-dgw", "Latn", } m["dmc"] = { "Gavak", 5277406, "ngf-nad", "Latn", } m["dmd"] = { "Madhi Madhi", 6727353, "aus-pam", "Latn", } m["dme"] = { "Dugwor", 56313, "cdc-cbm", "Latn", } m["dmf"] = { "Medefaidrin", 1519764, "art", "Medf", type = "appendix-constructed", } m["dmg"] = { "Upper Kinabatangan", 16109975, "poz-san", "Latn", } m["dmk"] = { "Domaaki", 32900, "inc-wes", "Arab", } m["dml"] = { "Dameli", 32288, "inc-kun", } m["dmm"] = { "Dama (Nigeria)", 5211865, "alv-mbm", "Latn", } m["dmo"] = { "Kemezung", 35562, "nic-bbe", "Latn", } m["dmr"] = { "East Damar", 5328200, "poz-cet", "Latn", } m["dms"] = { "Dampelas", 5212928, "poz-tot", "Latn", } m["dmu"] = { "Dubu", 7692059, "paa-wpw", "Latn", } m["dmv"] = { "Dumpas", 12953512, "poz-san", "Latn", } m["dmw"] = { "Mudburra", 6931573, "aus-pam", "Latn", } m["dmx"] = { "Dema", 3553423, "bnt-sho", "Latn", } m["dmy"] = { "Demta", 14466283, "paa-sen", "Latn", } m["dna"] = { "Upper Grand Valley Dani", 12952361, "ngf-gvd", "Latn", } m["dnd"] = { "Daonda", 5221528, "paa-war", "Latn", } m["dne"] = { "Ndendeule", 6983725, "bnt-mbi", "Latn", } m["dng"] = { "Dungan", 33050, "zhx-man", "Cyrl, Latn, Hants", generate_forms = "zh-generateforms", translit = {Cyrl = "dng-translit"}, sort_key = { Cyrl = { from = {"ё", "ә", "җ", "ң", "ў", "ү"}, to = {"е" .. p[1], "е" .. p[2], "ж" .. p[1], "н" .. p[1], "у" .. p[1], "у" .. p[2]} }, Hani = "Hani-sortkey", }, } m["dni"] = { "Lower Grand Valley Dani", 12635807, "ngf-gvd", "Latn", } m["dnj"] = { "Dan", 1158971, "dmn-mda", "Latn", } m["dnk"] = { "Dengka", 5256954, "poz-tim", "Latn", } m["dnn"] = { "Dzuun", 10973260, "dmn-smg", "Latn", } m["dno"] = { "Ndrulo", 60785094, "csu-lnd", } m["dnr"] = { "Danaru", 5214932, "ngf-pek", "Latn", } m["dnt"] = { "Mid Grand Valley Dani", 12952359, "ngf-gvd", "Latn", } m["dnu"] = { "Danau", 5013745, "mkh-pal", "Mymr", } m["dnv"] = { "Danu", 5221251, "tbq-brm", "Mymr", ancestors = "obr", } m["dnw"] = { "Western Dani", 7987774, "ngf-cda", "Latn", } m["dny"] = { "Dení", 56562, "auf", "Latn", } m["doa"] = { "Dom", 5289770, "ngf-sim", "Latn", } m["dob"] = { "Dobu", 952133, "poz-ocw", "Latn", } m["doc"] = { "Northern Kam", 17195499, "qfa-tak", "Latn", } m["doe"] = { "Doe", 5288055, "bnt-ruv", "Latn", } m["dof"] = { "Domu", 5291375, "paa-mal", "Latn", } m["doh"] = { "Dong", 3438405, "nic-dak", "Latn", } m["doi"] = { "Dogri", 32730, "him", "Deva, Takr, fa-Arab, Dogr", translit = { Deva = "hi-translit", Dogr = "Dogr-translit", }, } m["dok"] = { "Dondo", 5295571, "poz-tot", "Latn", } m["dol"] = { "Doso", 4167202, "paa-dtu", "Latn", } m["don"] = { "Doura", 7829037, "poz-ocw", "Latn", } m["doo"] = { "Dongo", 35303, "nic-mbc", "Latn", } m["dop"] = { "Lukpa", 3258739, "nic-gne", "Latn", } m["doq"] = { "Dominican Sign Language", 5290820, "sgn", "Latn", -- when documented } m["dor"] = { "Dori'o", 3037084, "poz-sls", "Latn", } m["dos"] = { "Dogosé", 3913314, "nic-gur", "Latn", } m["dot"] = { "Dass", 3441293, "cdc-wst", "Latn", } m["dov"] = { "Toka-Leya", 11001779, "bnt-bot", "Latn", ancestors = "toi", } m["dow"] = { "Doyayo", 35299, "alv-dur", "Latn", } m["dox"] = { "Bussa", 35123, "cus-eas", "Latn", } m["doy"] = { "Dompo", 35270, "alv-gng", "Latn", } m["doz"] = { "Dorze", 56336, "omv-nom", "Latn", } m["dpp"] = { "Papar", 7132487, "poz-san", "Latn", } m["drb"] = { "Dair", 12952360, "nub-hil", "Latn", } m["drc"] = { "Minderico", 6863806, "roa-gap", "Latn", ancestors = "pt", } m["drd"] = { "Darmiya", 5224058, "sit-alm", } m["drg"] = { "Rungus", 6897407, "poz-san", "Latn", } m["dri"] = { "Lela", 3914004, "nic-knn", "Latn", } m["drl"] = { "Baagandji", 5223941, "aus-pam", "Latn", } m["drn"] = { "West Damar", 3450459, "poz-tim", "Latn", } m["dro"] = { "Daro-Matu Melanau", 5224156, "poz-bnn", "Latn", } m["drq"] = { "Dura", 3449842, "sit-gma", "Deva", } m["drs"] = { "Gedeo", 56622, "cus-hec", "Ethi", } m["dru"] = { "Rukai", 49232, "map", "Latn", ancestors = "dru-pro", } m["dry"] = { "Darai", 46995026, "inc-bhi", "Deva", } m["dsb"] = { "Lower Sorbian", 13286, "wen", "Latn", sort_key = s["wen-sortkey"], standard_chars = "AaBbCcČčĆćDdEeĚěFfGgHhIiJjKkŁłLlMmNnŃńOoÓóPpRrŔŕSsŠšŚśTtUuWwYyZzŽžŹź" .. c.punc, } m["dse"] = { "Dutch Sign Language", 2201099, "sgn", "Latn", -- when documented } m["dsh"] = { "Daasanach", 56637, "cus-eas", "Latn", } m["dsi"] = { "Disa", 3914455, "csu-bgr", "Latn", } m["dsl"] = { "Danish Sign Language", 2605298, "sgn", "Latn", -- when documented } m["dsn"] = { "Dusner", 5316948, "poz-hce", "Latn", } m["dso"] = { "Desiya", 12629755, "inc-eas", "Orya", ancestors = "or", } m["dsq"] = { "Tadaksahak", 36568, "son", "Arab, Latn", } m["dta"] = { "Daur", 32430, "xgn", "Latn, Hani, Cyrl, Mong", ancestors = "xng", -- Mong translit, display_text and strip_diacritics in [[Module:scripts/data]] sort_key = {Hani = "Hani-sortkey"}, } m["dtb"] = { "Labuk-Kinabatangan Kadazan", 5330240, "poz-san", "Latn", } m["dtd"] = { "Ditidaht", 13728042, "wak", "Latn", } m["dth"] = { -- contrast 'rrt' "Adithinngithigh", 4683034, "aus-pmn", "Latn", } m["dti"] = { "Ana Tinga Dogon", 4750346, "qfa-dgn", "Latn", } m["dtk"] = { "Tene Kan Dogon", 11018863, "nic-pld", "Latn", } m["dtm"] = { "Tomo Kan Dogon", 11137719, "nic-pld", "Latn", } m["dto"] = { "Tommo So", 47012992, "nic-dge", "Latn", } m["dtp"] = { "Central Dusun", 5317225, "poz-san", "Latn", } m["dtr"] = { "Lotud", 6685078, "poz-san", "Latn", } m["dts"] = { "Toro So Dogon", 11003311, "nic-dge", "Latn", } m["dtt"] = { "Toro Tegu Dogon", 3913924, "nic-pld", "Latn", } m["dtu"] = { "Tebul Ure Dogon", 7692089, "qfa-dgn", "Latn", } m["dty"] = { "Doteli", 18415595, "inc-pah", "Deva", translit = "ne-translit", } m["dua"] = { "Duala", 33013, "bnt-saw", "Latn", } m["dub"] = { "Dubli", 5310792, "inc-bhi", } m["duc"] = { "Duna", 5314039, "qfa-dis", -- Papuan; isolate in Glottolog; tentatively grouped with Bogaya into a Duna-Pogaya [sic] family, -- ultimately in TNG "Latn", } m["due"] = { "Umiray Dumaget Agta", 7881585, "phi", "Latn", } m["duf"] = { "Dumbea", 6983819, "poz-cln", "Latn", } m["dug"] = { "Chiduruma", 35614, "bnt-mij", "Latn", } m["duh"] = { "Dungra Bhil", 12953513, "inc-bhi", "Deva, Gujr", } m["dui"] = { "Dumun", 5314004, "ngf-yag", "Latn", } m["duk"] = { "Uyajitaya", 7904085, "ngf-nur", "Latn", } m["dul"] = { "Alabat Island Agta", 3399709, "phi", "Latn", } m["dum"] = { "Middle Dutch", 178806, "gmw-frk", "Latn", ancestors = "odt", strip_diacritics = {remove_diacritics = c.circ .. c.macron .. c.diaer}, } m["dun"] = { "Dusun Deyah", 2784033, "poz-bre", "Latn", } m["duo"] = { "Dupaningan Agta", 5315912, "phi", "Latn", } m["dup"] = { "Duano", 3040468, "poz-mly", "Latn", } m["duq"] = { "Dusun Malang", 3041711, "poz-bre", "Latn", } m["dur"] = { "Dii", 35208, "alv-dur", "Latn", } m["dus"] = { "Dumi", 56315, "sit-kiw", "Deva", } m["duu"] = { "Drung", 56406, "sit-nng", "Latn", } m["duv"] = { "Duvle", 56364, "paa-lpl", "Latn", } m["duw"] = { "Dusun Witu", 2381310, "poz-bre", "Latn", } m["dux"] = { "Duun", 3914880, "dmn-smg", "Latn", } m["duy"] = { "Dicamay Agta", 5272321, "phi", "Latn", } m["duz"] = { "Duli", 5313405, "alv-ada", "Latn", } m["dva"] = { "Duau", 5310448, "poz-ocw", "Latn", } m["dwa"] = { "Diri", 56286, "cdc-wst", "Latn", } m["dwr"] = { "Dawro", 12629647, "omv-nom", "Ethi, Latn", } m["dwu"] = { "Dhuwal", 3120791, "aus-yol", "Latn", } m["dww"] = { "Dawawa", 5242286, "poz-ocw", "Latn", } m["dwy"] = { "Dhuwaya", 63348560, "aus-yol", "Latn", } m["dwz"] = { "Dewas Rai", 62663667, "inc-bhi", } m["dya"] = { "Dyan", 35340, "nic-gur", "Latn", } m["dyb"] = { "Dyaberdyaber", 5285185, "aus-nyu", "Latn", } m["dyd"] = { "Dyugun", 3913785, "aus-nyu", "Latn", } -- dyg (Villa Viciosa Agta) deleted as extinct and unattested; per Wikipedia: "Villa Viciosa Atta, supposed once spoken -- in Villaviciosa, Abra, is presumed to be related, but is unattested." m["dyi"] = { "Djimini", 35336, "alv-tdj", "Latn", } m["dym"] = { "Yanda Dogon", 8048316, "qfa-dgn", "Latn", } m["dyn"] = { "Dyangadi", 3913820, "aus-cww", "Latn", } m["dyo"] = { "Jola-Fonyi", 3507832, "alv-jol", "Latn", } m["dyu"] = { "Dyula", 32706, "dmn-man", "Latn", } m["dyy"] = { "Dyaabugay", 2591320, "aus-yid", "Latn", } m["dza"] = { "Tunzu", 3915845, "nic-jer", "Latn", } m["dzg"] = { "Dazaga", 35244, "ssa-sah", "Latn", } m["dzl"] = { "Dzala", 56607, "sit-ebo", "Tibt", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["dzn"] = { "Dzando", 5319622, "bnt-bun", "Latn", } return require("Module:languages").finalizeData(m, "language") n65t4o1m4kbkc28bw1wn38wd8cty7ir 828 5985 17422 2026-07-13T08:35:01Z Hiyuune 6766 + 17422 Scribunto text/plain local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared local m = {} m["oaa"] = { "Orok", 33928, "tuw-nan", "Cyrl, Latn", translit = "oaa-translit", } m["oac"] = { "Oroch", 33650, "tuw-udg", "Latn, Cyrl", } m["oak"] = { "Noakhali", 107548681, "inc-bas", "Beng", } m["oav"] = { "Old Avar", 65455879, "cau-ava", "Geor", -- Geor translit in [[Module:scripts/data]] (NOTE: formerly not present, probably an accidental omission) } m["obi"] = { "Obispeño", 1288385, "nai-chu", "Latn", } m["obk"] = { "Southern Bontoc", 63308144, "phi", "Latn", } m["obl"] = { "Oblo", 36309, } m["obm"] = { "Moabite", 36385, "sem-can", -- Phnx translit in [[Module:scripts/data]] } m["obo"] = { "Obo Manobo", 12953699, "mno", "Latn", } m["obr"] = { "Old Burmese", 17006600, "tbq-brm", "Mymr, Latn", --and also Pallava } m["obt"] = { "Old Breton", 3558112, "cel-brs", "Latn", } m["obu"] = { "Obulom", 3813403, "nic-cde", "Latn", } m["oca"] = { "Ocaina", 3182577, "sai-wit", "Latn", } m["och"] = { "Old Chinese", 35137, "zhx", "Hant", translit = "zh-translit", sort_key = "Hani-sortkey", } m["ocm"] = { "Old Cham", 105197086, "cmc", "Latn", -- the script in which entries are currently entered in Wiktionary; its native script is not in ISO or Unicode yet } m["oco"] = { "Old Cornish", 48304520, "cel-brs", "Latn", } m["ocu"] = { "Tlahuica", 10751739, "omq", "Latn", } m["oda"] = { "Odut", 3915388, "nic-uce", "Latn", ancestors = "mfn", } m["odk"] = { "Od", 7077191, "inc-wes", "Arab", } m["odt"] = { "Old Dutch", 443089, "gmw-frk", "Latn, Runr", strip_diacritics = {remove_diacritics = c.circ .. c.macron}, } m["odu"] = { "Odual", 3813392, "nic-cde", "Latn", } m["ofo"] = { "Ofo", 3349758, "sio-ohv", } m["ofs"] = { "Old Frisian", 35133, "gmw-fri", "Latn", strip_diacritics = {remove_diacritics = c.circ .. c.macron}, sort_key = { from = {"æ", "ð", "þ"}, to = {"ae", "t" .. p[1], "t" .. p[2]} }, } m["ofu"] = { "Efutop", 35297, "nic-eko", "Latn", } m["ogb"] = { "Ogbia", 3813400, "nic-cde", "Latn", } m["ogc"] = { "Ogbah", 36291, "alv-igb", "Latn", } m["oge"] = { "Old Georgian", 34834, "ccs-gzn", "Geor, Geok", -- Geor, Geok translit in [[Module:scripts/data]] override_translit = true, strip_diacritics = {remove_diacritics = c.circ}, } m["ogg"] = { "Ogbogolo", 3813405, "nic-cde", "Latn", } m["ogo"] = { "Khana", 3914409, "nic-ogo", "Latn", } m["ogu"] = { "Ogbronuagum", 3914485, "nic-cde", "Latn", } m["ohu"] = { "Old Hungarian", 65455880, "urj-ugr", "Latn, Hung", } m["oia"] = { "Oirata", 56738, "paa-eti", "Latn", } m["oin"] = { "Inebu One", 12953782, "paa-trr", "Latn", } m["ojb"] = { "Northwestern Ojibwa", 7060356, "alg", "Latn", ancestors = "oj", } m["ojc"] = { "Central Ojibwa", 5061548, "alg", "Latn", ancestors = "oj", } m["ojg"] = { "Eastern Ojibwa", 5330342, "alg", "Latn", ancestors = "oj", } m["ojp"] = { "Old Japanese", 5736700, "jpx", "Jpan", display_text = s["jpx-displaytext"], strip_diacritics = s["jpx-stripdiacritics"], sort_key = s["jpx-sortkey"], } m["ojs"] = { "Severn Ojibwa", 56494, "alg", "Latn", ancestors = "oj", } m["ojv"] = { "Ontong Java", 7095071, "poz-pnp", "Latn", } m["ojw"] = { "Western Ojibwa", 3474222, "alg", "Latn", ancestors = "oj", } m["oka"] = { "Okanagan", 2984602, "sal", "Latn", } m["okb"] = { "Okobo", 3813398, "nic-lcr", "Latn", } m["okd"] = { "Okodia", 36300, "ijo", "Latn", } m["oke"] = { "Okpe (Southwestern Edo)", 268924, "alv-swd", "Latn", } m["okg"] = { "Kok-Paponk", 55254102, "aus-pmn", "Latn", } m["okh"] = { "Koresh-e Rostam", 6432160, "xme-ttc", ancestors = "xme-ttc-cen", } m["oki"] = { "Okiek", 56367, "sdv-kln", "Latn", } m["okj"] = { "Oko-Juwoi", 3436832, "qfa-adc", } m["okk"] = { "Kwamtim One", 19830649, "paa-trr", "Latn", } m["okl"] = { "Old Kentish Sign Language", 7084319, "sgn", } m["okm"] = { "Middle Korean", 715339, "qfa-kor", "Kore, Latn", ancestors = "oko", translit = "okm-translit", sort_key = "okm-sortkey", -- Kore strip_diacritics in [[Module:scripts/data]] } m["okn"] = { "Okinoerabu", 3350036, "jpx-nry", "Jpan", translit = s["jpx-translit"], display_text = s["jpx-displaytext"], strip_diacritics = s["jpx-stripdiacritics"], sort_key = s["jpx-sortkey"], } m["oko"] = { "Old Korean", 715364, "qfa-kor", "Kore", -- Kore strip_diacritics in [[Module:scripts/data]] } m["okr"] = { "Kirike", 11006763, "ijo", "Latn", } m["oks"] = { "Oko-Eni-Osayen", 36302, "alv-von", "Latn", } m["oku"] = { "Oku", 36289, "nic-rnc", "Latn", } m["okv"] = { "Orokaiva", 7103752, "ngf-oro", "Latn", } m["okx"] = { "Okpe (Northwestern Edo)", 7082547, "alv-nwd", "Latn", } m["okz"] = { "Old Khmer", 9205, "mkh-kmr", "Latn, Khmr", --and also Khom, Pallava } m["old"] = { "Mochi", 12952852, "bnt-chg", "Latn", } m["ole"] = { "Olekha", 3695204, "sit", "Tibt, Latn", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["olm"] = { "Oloma", 3441166, "alv-nwd", "Latn", } m["olo"] = { "Livvi", 36584, "urj-fin", "Latn", } m["olr"] = { "Olrat", 3351562, "poz-vnn", "Latn", } m["olt"] = { "Old Lithuanian", 17417801, "bat-eas", "Latn", display_text = "lt-common", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.tilde}, } m["olu"] = { "Kuvale", 6448765, "bnt-swb", "Latn", } m["oma"] = { "Omaha-Ponca", 2917968, "sio-dhe", "Latn", } m["omb"] = { "Omba", 2841471, "poz-vnn", "Latn", } m["omc"] = { "Mochica", 1951641, "qfa-iso", "Latn", } m["omg"] = { "Omagua", 33663, "tup-gua", "Latn", } m["omi"] = { "Omi", 56795, "csu-mma", } m["omk"] = { "Omok", 4334657, "qfa-yuk", "Cyrl", translit = "omk-translit", } m["oml"] = { "Ombo", 7089928, "bnt-tet", "Latn", } m["omn"] = { "Minoan", 1669994, "qfa-unc", -- undeciphered "Lina", } m["omo"] = { "Utarmbung", 7902577, "ngf-sad", "Latn", } m["omp"] = { "Old Manipuri", 105953310, "sit", "Mtei", translit = "Mtei-translit", } m["omr"] = { "Old Marathi", 65455881, "inc-sou", "Deva, Modi", translit = { Deva = "sa-translit", Modi = "Modi-translit", }, } m["omt"] = { "Omotik", 36313, "sdv-nis", } m["omu"] = { "Omurano", 1957612, } m["omw"] = { "South Tairora", 20210553, "ngf-tai", "Latn", } m["omx"] = { "Old Mon", 111364697, "mkh-mnc", "Mymr, Latn", --and also Pallava } m["ona"] = { "Selk'nam", 2721227, "sai-cho", "Latn", } m["onb"] = { "Lingao", 7093790, "qfa-onb", "Latn", } m["one"] = { "Oneida", 857858, "iro-nor", "Latn", } m["ong"] = { "Olo", 592162, "paa-wap", "Latn", } m["oni"] = { "Onin", 7093910, "poz-cet", "Latn", } m["onj"] = { "Onjob", 7093968, "ngf-dag", "Latn", } m["onk"] = { "Kabore One", 12953783, "paa-trr", "Latn", } m["onn"] = { "Onobasulu", 7094437, "ngf-bos", "Latn", } m["ono"] = { "Onondaga", 1077450, "iro-nor", "Latn", ancestors = "iro-oon", } m["onp"] = { "Sartang", 7424639, "sit-khm", "Latn, Deva", } m["onr"] = { "Northern One", 19830648, "paa-trr", "Latn", } m["ons"] = { "Ono", 11732548, "ngf-ehu", "Latn", } --ont (Ontenu) treated as variety of gaj (Gadsup) per [[Wiktionary:Language_treatment_requests#Merge_Ontenu_into_Gadsup]] m["onu"] = { "Unua", 3552042, "poz-vnc", "Latn", } m["onw"] = { "Old Nubian", 2268, "nub", "Copt", translit = "Copt-translit", sort_key = "Copt-sortkey", } m["onx"] = { "Pidgin Onin", 12953788, "crp", "Latn", ancestors = "oni", } m["ood"] = { "O'odham", 2393095, "azc-pim", "Latn", } m["oog"] = { "Ong", 12953787, "mkh-kat", } m["oon"] = { "Önge", 2475551, "qfa-ong", "Latn", } m["oor"] = { "Oorlams", 2484337, } m["opa"] = { "Okpamheri", 3913331, "alv-nwd", "Latn", } m["opk"] = { "Kopkaka", 6431129, "ngf-wok", "Latn", } m["opm"] = { "Oksapmin", 1068097, "ngf", -- per Glottolog, in an Ok-Oksapmin family, under Awyu-Ok, under Asmat-Awyu-Ok, but we don't have these "Latn", } m["opo"] = { "Opao", 7095585, "paa-wel", "Latn", } m["opt"] = { "Opata", 2304583, "azc-trc", "Latn", } m["opy"] = { "Ofayé", 3446691, "sai-mje", "Latn", } m["ora"] = { "Oroha", 36298, "poz-sls", "Latn", } m["ore"] = { "Orejón", 3355834, "sai-tuc", "Latn", } m["org"] = { "Oring", 3915308, "nic-ucn", "Latn", } m["orh"] = { "Oroqen", 1367309, "tuw-ewe", "Latn", } m["oro"] = { "Orokolo", 7103758, "paa-wel", "Latn", } m["orr"] = { "Oruma", 36299, "ijo", "Latn", } m["ort"] = { "Adivasi Odia", 12953791, "inc-eas", "Orya", ancestors = "or", } m["oru"] = { "Ormuri", 33740, "ira-orp", "fa-Arab", } m["orv"] = { "Old East Slavic", 35228, "zle", "Cyrs", translit = {Cyrs = "Cyrs-translit"}, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]] } m["orw"] = { "Oro Win", 3450423, "sai-cpc", "Latn", } m["orx"] = { "Oro", 3813396, "nic-lcr", "Latn", } m["orz"] = { "Ormu", 7103494, "poz-ocw", "Latn", } m["osa"] = { "Osage", 2600085, "sio-dhe", "Latn, Osge", } m["osc"] = { "Oscan", 36653, "itc-sbl", "Ital, Latn, Polyt", display_text = { Latn = s["itc-Latn-displaytext"], }, strip_diacritics = { Latn = s["itc-Latn-stripdiacritics"], }, sort_key = { Latn = s["itc-Latn-sortkey"], }, -- Ital translit in [[Module:scripts/data]] -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["osi"] = { "Osing", 2701322, "poz", "Latn", } m["osn"] = { "Old Sundanese", 56197074, "poz-msa", "Latn, Sund, Kawi", } m["oso"] = { "Ososo", 3913398, "alv-yek", "Latn", } m["osp"] = { "Old Spanish", 1088025, "roa-cas", "Latn", } m["ost"] = { "Osatu", 36243, "nic-grs", "Latn", } m["osu"] = { "Southern One", 12953785, "paa-trr", "Latn", } m["osx"] = { "Old Saxon", 35219, "gmw-lgm", "Latn", strip_diacritics = {remove_diacritics = c.circ .. c.macron}, } m["ota"] = { "Ottoman Turkish", 36730, "trk-ogz", "ota-Arab, Armn", ancestors = "trk-oat", strip_diacritics = { ["ota-Arab"] = { remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.superalef, from = {"گ", "ڭ", "ۀ"}, to = {"ك", "ك", "ه"} }, Armn = { from = {"՚"}, to = {"’"} }, }, translit = {Armn = "ota-Armn-translit"}, standard_chars = { ["ota-Arab"] = "آاأبپتثجچحخدذرزژسشصضطظعغفقكلمنوؤهیئةءـ‌", c.punc }, } m["otb"] = { "Old Tibetan", 7085214, "sit-tib", "Tibt", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["otd"] = { "Ot Danum", 3033781, "poz-brw", "Latn", } m["ote"] = { "Mezquital Otomi", 23755711, "oto-otm", "Latn", } m["oti"] = { "Oti", 3357881, } m["otk"] = { "Old Turkic", 34988, "trk-sib", "Orkh, Sogd", -- Orkh translit in [[Module:scripts/data]] } m["otl"] = { "Tilapa Otomi", 7802050, "oto-otm", "Latn", } m["otm"] = { "Eastern Highland Otomi", 13581718, "oto-otm", "Latn", } m["otn"] = { "Tenango Otomi", 25559589, "oto-otm", "Latn", } m["otq"] = { "Querétaro Otomi", 23755688, "oto-otm", "Latn", } m["otr"] = { "Otoro", 36328, "alv-hei", } m["ots"] = { "Estado de México Otomi", 7413841, "oto-otm", "Latn", } m["ott"] = { "Temoaya Otomi", 7698191, "oto-otm", "Latn", } m["otu"] = { "Otuke", 7110049, "sai-mje", "Latn", } m["otw"] = { "Ottawa", 133678, "alg", "Latn", ancestors = "oj", } m["otx"] = { "Texcatepec Otomi", 25559590, "oto-otm", "Latn", } m["oty"] = { "Old Tamil", 20987452, "dra-tam", "Brah", -- Brah translit in [[Module:scripts/data]] } m["otz"] = { "Ixtenco Otomi", 6101171, "oto-otm", "Latn", } m["oub"] = { "Glio-Oubi", 3914977, "kro-grb", } m["oue"] = { "Oune", 7110521, "paa-sbo", "Latn", } m["oui"] = { "Old Uyghur", 428299, "trk-ssb", "Ougr, Latn, Hani, Phag, Brah, Mani, Syrc, Orkh, Sogd, Arab, mnc-Mong, Sogo, Tibt", ancestors = "otk", translit = { Ougr = "Ougr-translit", -- Orkh translit in [[Module:scripts/data]] -- Mani translit in [[Module:scripts/data]] -- mnc-Mong translit in [[Module:scripts/data]] (NOTE: Formerly not present; I assume accidentally left out) -- Brah translit in [[Module:scripts/data]] }, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] -- NOTE: Formerly there was only a sort_key for Tibetan. I assume the other three were left out accidentally. sort_key = { Hani = "Hani-sortkey", }, } m["oum"] = { "Ouma", 7110494, "poz-ocw", "Latn", } m["ovd"] = { "Elfdalian", 254950, "gmq-eas", ancestors = "gmq-osw", "Latn, Runr", } m["owi"] = { "Owiniga", 56454, "paa-lma", "Latn", } m["owl"] = { "Old Welsh", 2266723, "cel-brw", "Latn", } m["oyb"] = { "Oy", 13593748, "mkh-ban", } m["oyd"] = { "Oyda", 7116251, "omv-nom", "Latn", } m["oym"] = { "Wayampi", 7975842, "tup-gua", "Latn", } m["oyy"] = { "Oya'oya", 7116243, "poz-ocw", "Latn", } m["ozm"] = { "Koonzime", 35566, "bnt-ndb", "Latn", } return require("Module:languages").finalizeData(m, "language") o4fme5na31kfl6hsjv83lay69byr3v7 828 5986 17423 2026-07-13T08:38:13Z Hiyuune 6766 + 17423 Scribunto text/plain local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared local m = {} m["faa"] = { "Fasu", 3446687, "qfa-dis", -- Papuan; isolate or in the proposed Kutubuan family "Latn", } m["fab"] = { "Annobonese", 34992, "crp", "Latn", ancestors = "pt", } m["fad"] = { "Wagi", 7959569, "ngf-han", "Latn", } m["faf"] = { "Fagani", 3063759, "poz-sls", "Latn", } m["fag"] = { "Finongan", 3450761, "ngf-era", "Latn", } m["fah"] = { "Baissa Fali", 3446632, "nic-bco", "Latn", } m["fai"] = { "Faiwol", 3501773, "ngf-mok", "Latn", } m["faj"] = { "Kursav", 976953, "ngf-eso", "Latn", } m["fak"] = { "Fang (Beboid)", 5433811, "nic-beb", "Latn", } m["fal"] = { "South Fali", 15637351, "alv-fli", "Latn", } m["fam"] = { "Fam", 35290, "nic-mmb", "Latn", } m["fan"] = { "Fang (Bantu)", 33484, "bnt-btb", "Latn", } m["fap"] = { "Palor", 36318, "alv-cng", "Latn", } m["far"] = { "Fataleka", 3067168, "poz-sls", "Latn", } -- "fat" is treated as "ak", see [[WT:LT]] m["fau"] = { "Fayu", 5439113, "paa-wlp", "Latn", } m["fax"] = { "Fala", 300402, "roa-gap", "Latn", } m["fay"] = { "Southwestern Fars", 5228140, "ira-swi", "Arab", } m["faz"] = { "Northwestern Fars", 7060307, "ira-swi", } m["fbl"] = { "West Miraya Bikol", 18603801, "phi", "Latn", } m["fcs"] = { "Quebec Sign Language", 13193, "sgn", "Latn", -- when documented } m["fer"] = { "Feroge", 35287, "nic-ser", "Latn", } m["ffi"] = { "Foia Foia", 8564176, "paa-wig", "Latn", } -- "ffm" is treated as "ff", see [[WT:LT]] m["fgr"] = { "Fongoro", 3437645, "csu", "Latn", } m["fia"] = { "Nobiin", 36503, "nub", "Latn, Arab, Copt", ancestors = "onw", translit = { Copt = "Copt-translit", }, sort_key = { Copt = "Copt-sortkey", }, } m["fie"] = { "Fyer", 56273, "cdc-wst", "Latn", } m["fif"] = { "Faifi", 85760309, "sem-cen", -- conservatively putting undifferentiated sem-cen, there's debate over if it's OSA or Arabic "Arab", -- or IPA/Latn; mostly it is unwritten -- ancestors = "sem-srb", if one accepts the view that like Razihi it is sem-osa } -- "fil" is treated as "tl", see [[WT:LT]] m["fip"] = { "Fipa", 667747, "bnt-mwi", "Latn", } m["fir"] = { "Firan", 3915847, "nic-plc", "Latn", } m["fit"] = { "Meänkieli", 13357, "urj-fin", "Latn", ancestors = "fi", } m["fiw"] = { "Fiwaga", 5456292, "ngf-eku", "Latn", } m["fkk"] = { "Kirya-Konzel", 6416310, "cdc-cbm", "Latn", } m["fkv"] = { "Kven", 165795, "urj-fin", "Latn", ancestors = "fi", } m["fla"] = { "Montana Salish", 3111983, "sal", "Latn", } m["flh"] = { "Foau", 5463819, "paa-elp", "Latn", } m["fli"] = { "Fali", 56244, "cdc-cbm", "Latn", } m["fll"] = { "North Fali", 12952419, "alv-fli", "Latn", } m["fln"] = { "Flinders Island", 3915702, "aus-pmn", "Latn", } m["flr"] = { "Fuliiru", 7166821, "bnt-shh", "Latn", } m["fly"] = { "Tsotsitaal", 12643960, "crp", "Latn", ancestors = "af", } m["fmp"] = { "Fe'fe'", 35276, "bai", "Latn", } m["fmu"] = { "Far Western Muria", 42589412, "dra-mur", "Deva", } m["fng"] = { "Fanagalo", 35727, "crp", "Latn", ancestors = "zu", } m["fni"] = { "Fania", 317642, "alv-bua", "Latn", } m["fod"] = { "Foodo", 5465566, "alv-gng", "Latn", } m["foi"] = { "Foi", 5464146, "ngf-eku", "Latn", } m["fom"] = { "Foma", 5464911, "bnt-ske", "Latn", ancestors = "khy", } m["fon"] = { "Fon", 33291, "alv-gbe", "Latn", } m["for"] = { "Fore", 3077126, "ngf-fgi", "Latn", } m["fos"] = { "Siraya", 716604, "map", "Latn", } m["fpe"] = { "Pichinglis", 35288, "crp", "Latn", ancestors = "en", } m["fqs"] = { "Fas", 56320, "paa-fas", "Latn", } -- "frc" is treated as "fr" (or as etymology-only), see [[WT:LT]] m["frd"] = { "Fordata", 5468035, "poz-cet", "Latn", } m["frm"] = { "Middle French", 1473289, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["fro"] = { "Old French", 35222, "roa-oil", "Latn, Hebr", sort_key = { Latn = s["roa-oil-sortkey"], }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["frp"] = { "Franco-Provençal", 15087, "roa-grh", "Latn", ancestors = "frp-old", sort_key = { remove_diacritics = c.grave .. c.acute .. c.circ .. c.diaer .. c.cedilla .. "'", from = {"æ", "œ"}, to = {"ae", "oe"} }, } m["frq"] = { "Forak", 5467173, "ngf-war", "Latn", } m["frr"] = { "North Frisian", 28224, "gmw-fri", "Latn", } -- "frs" is not used, see [[WT:LT]] m["frt"] = { "Fortsenal", 2666835, "poz-vnn", "Latn", } m["fse"] = { "Finnish Sign Language", 33225, "sgn", "Latn", -- when documented } m["fsl"] = { "French Sign Language", 33302, "sgn-fsl", "Latn", -- when documented } m["fss"] = { "Finnish-Swedish Sign Language", 5450448, "sgn", "Latn", -- when documented } -- "fub" is treated as "ff", see [[WT:LT]] -- "fuc" is treated as "ff", see [[WT:LT]] m["fud"] = { "East Futuna", 35334, "poz-pnp", "Latn", } -- "fue" is treated as "ff", see [[WT:LT]] -- "fuf" is treated as "ff", see [[WT:LT]] -- "fuh" is treated as "ff", see [[WT:LT]] -- "fui" is treated as "ff", see [[WT:LT]] m["fuj"] = { "Ko", 35693, "alv-hei", "Latn", } m["fum"] = { "Fum", 11011870, "nic-nka", "Latn", } m["fun"] = { "Fulniô", 774441, "qfa-iso", "Latn", } -- "fuq" is treated as "ff", see [[WT:LT]] m["fur"] = { "Friulian", 33441, "roa-rhe", ancestors = "fur-old", "Latn", } m["fut"] = { "Futuna-Aniwa", 3064409, "poz-pnp", "Latn", } m["fuu"] = { "Furu", 3441160, "csu-bkr", "Latn", } -- "fuv" is treated as "ff", see [[WT:LT]] m["fuy"] = { "Fuyug", 3073472, "qfa-dis", -- Papuan; isolate per Glottolog and Usher (2020), only tentatively retained in putative Goilalan family -- within TNG by Ross (2005) "Latn", } m["fvr"] = { "Fur", 33364, "ssa-fur", "Latn", } m["fwa"] = { "Fwâi", 3091331, "poz-cln", "Latn", } m["fwe"] = { "Fwe", 5511159, "bnt-bot", "Latn", } return require("Module:languages").finalizeData(m, "language") 86w2rcjby61acjk04sf0woez7t69z0g 828 5987 17424 2026-07-13T08:38:41Z Hiyuune 6766 + 17424 Scribunto text/plain local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared local m = {} ---------------------------------------------------------------------------------------------------------------------- -- Afroasiatic varieties -- ---------------------------------------------------------------------------------------------------------------------- -------------------------------------------------------------------------------------- -- Berber varieties -- -------------------------------------------------------------------------------------- m["shi-med"] = { "Medieval Tashelhit", 34152, "shi", } -- Tuareg lects m["thv"] = { "Tamahaq", 56703, "tmh", } m["ttq"] = { "Tawellemmet", 56390, "tmh", } m["taq"] = { "Tamasheq", 4670066, "tmh", } m["thz"] = { "Tayert", 56388, "tmh", } m["thv-ght"] = { "Ghat", 47012900, "thv", } -------------------------------------------------------------------------------------- -- Cushitic varieties -- -------------------------------------------------------------------------------------- -- Oromo varieties m["hae"] = { "Harar Oromo", 5330355, "om", aliases = {"Eastern Oromo"}, } m["gax"] = { "Borana", 2910610, "om", aliases = {"Southern Oromo"}, } m["orc"] = { "Orma", 2919128, "om", } m["ssn"] = { "Waata", 3501553, "om", } -------------------------------------------------------------------------------------- -- Egyptian varieties -- -------------------------------------------------------------------------------------- ----------------------------------------------------- -- Ancient Egyptian varieties -- ----------------------------------------------------- m["egy-old"] = { "Old Egyptian", 447117, "egy", } m["egy-mid"] = { "Middle Egyptian", 657330, "egy", aliases = {"Classical Egyptian"}, } m["egy-nmi"] = { "Neo-Middle Egyptian", 123735278, "egy", aliases = {"Égyptien de tradition", "Traditional Egyptian"}, } m["egy-lat"] = { "Late Egyptian", 1852329, "egy", } ----------------------------------------------------- -- Coptic varieties -- ----------------------------------------------------- m["cop-akh"] = { "Akhmimic Coptic", 125176464, "cop", aliases = {"Akhmimic"}, } m["cop-boh"] = { "Bohairic Coptic", 890733, "cop", aliases = {"Bohairic", "Memphitic Coptic", "Memphitic"}, } m["cop-ggg"] = { "Coptic Dialect G", nil, "cop", aliases = {"Dialect G", "Mansuric Coptic", "Mansuric"}, } m["cop-jjj"] = { "Coptic Dialect J", nil, "cop", } m["cop-kkk"] = { "Coptic Dialect K", nil, "cop", } m["cop-ppp"] = { "Coptic Dialect P", nil, "cop", aliases = {"Proto-Theban Coptic", "Palaeo-Theban Coptic"}, } m["cop-fay"] = { "Fayyumic Coptic", 1399115, "cop", aliases = {"Fayyumic", "Faiyumic Coptic", "Faiyumic", "Fayumic Coptic", "Fayumic", "Bashmuric Coptic", "Bashmuric"}, } m["cop-her"] = { "Hermopolitan Coptic", nil, "cop", aliases = {"Hermopolitan", "Coptic Dialect H", "Ashmuninic", "Ashmuninic Coptic"}, } m["cop-lyc"] = { "Lycopolitan Coptic", nil, "cop", aliases = { "Lycopolitan", "Assiutic Coptic", "Asyutic Coptic", "Assiutic", "Asyutic", "Lyco-Diospolitan Coptic", "Lyco-Diospolitan", "Subakhmimic Coptic", "Subakhmimic" }, } m["cop-old"] = { "Old Coptic", 115518040, "cop", } m["cop-oxy"] = { "Oxyrhynchite Coptic", nil, "cop", aliases = {"Oxyrhynchite", "Mesokemic Coptic", "Mesokemic", "Middle Egyptian Coptic"}, } m["cop-ply"] = { "Proto-Lycopolitan Coptic", nil, "cop", aliases = {"Coptic Dialect i", "Proto-Lyco-Diospolitan Coptic"}, } m["cop-sah"] = { "Sahidic Coptic", 2645851, "cop", aliases = {"Sahidic", "Saidic Coptic", "Saidic", "Thebaic Coptic", "Thebaic"}, } -------------------------------------------------------------------------------------- -- Semitic varieties -- -------------------------------------------------------------------------------------- ----------------------------------------------------- -- Akkadian varieties -- ----------------------------------------------------- m["akk-old"] = { "Old Akkadian", nil, "akk", } m["akk-obb"] = { "Old Babylonian", nil, "akk", } m["akk-oas"] = { "Old Assyrian", nil, "akk", } m["akk-mbb"] = { "Middle Babylonian", nil, "akk", } m["akk-mas"] = { "Middle Assyrian", nil, "akk", } m["akk-nbb"] = { "Neo-Babylonian", nil, "akk", } m["akk-nas"] = { "Neo-Assyrian", nil, "akk", } m["akk-lbb"] = { "Late Babylonian", nil, "akk", } m["akk-stb"] = { "Standard Babylonian", nil, "akk", } ----------------------------------------------------- -- Arabic varieties -- ----------------------------------------------------- m["jrb"] = { "Judeo-Arabic", 37733, "ar", pseudo_families = "qfa-jew", } m["apc-leb"] = { "Lebanese North Levantine Arabic", 1516642, "apc", aliases = {"Lebanese Arabic"}, } m["apc-sle"] = { "South Lebanese North Levantine Arabic", 14206590, "apc", aliases = {"South Lebanese Arabic"}, } m["apc-nle"] = { "North Lebanese North Levantine Arabic", nil, "apc", aliases = {"North Lebanese Arabic"}, } m["apc-syr"] = { "Syrian North Levantine Arabic", 2143071, "apc", aliases = {"Syrian Arabic"}, } m["apc-ale"] = { "Aleppine North Levantine Arabic", 7056921, "apc-syr", aliases = {"Aleppo Arabic", "Aleppine Arabic"}, } m["apc-dam"] = { "Damascene North Levantine Arabic", 12237466, "apc-syr", aliases = {"Damascus Arabic", "Damascene Arabic"}, } m["acm-khu"] = { "Khuzestani Arabic", 1040944, "acm", } ----------------------------------------------------- -- Aramaic varieties -- ----------------------------------------------------- m["arc-bib"] = { "Biblical Aramaic", 843235, "arc", family = "sem-are", } m["arc-cpa"] = { "Christian Palestinian Aramaic", 60790119, "arc", family = "sem-arw", aliases = {"Melkite Aramaic", "Palestinian Syriac", "Syropalestinian Aramaic"}, } m["arc-imp"] = { "Imperial Aramaic", 7079491, "arc", aliases = {"Official Aramaic"}, } m["arc-hat"] = { "Hatran Aramaic", 3832926, "arc", family = "sem-are", } m["arc-jla"] = { "Jewish Literary Aramaic", 105952842, "arc", pseudo_families = "qfa-jew", } m["arc-nab"] = { "Nabataean Aramaic", 36178, "arc", } m["arc-old"] = { "Old Aramaic", 3398392, "arc", } m["arc-pal"] = { "Palmyrene Aramaic", 1510113, "arc", family = "sem-arw", } m["tmr"] = { "Jewish Babylonian Aramaic", 33407, "arc", family = "sem-ase", pseudo_families = "qfa-jew", } m["jpa"] = { "Jewish Palestinian Aramaic", 948909, "arc", family = "sem-arw", aliases = {"Galilean Aramaic"}, pseudo_families = "qfa-jew", } ----------------------------------------------------- -- Hebrew varieties -- ----------------------------------------------------- m["hbo"] = { "Biblical Hebrew", 1982248, "he", aliases = {"Classical Hebrew"}, } m["he-mis"] = { "Mishnaic Hebrew", 1649362, "he", ancestors = "hbo", } m["he-med"] = { "Medieval Hebrew", 2712572, "he", ancestors = "he-mis", } m["he-IL"] = { "Israeli Hebrew", 8141, "he", } ---------------------------------------------------------------------------------------------------------------------- -- Ainu varieties -- ---------------------------------------------------------------------------------------------------------------------- m["ain-hok"] = { "Hokkaido Ainu", 20968488, "ain", aliases = {"Hokkaidō Ainu"}, } m["ain-kur"] = { "Kuril Ainu", 20967012, "ain", } m["ain-sak"] = { "Sakhalin Ainu", 20747371, "ain", } ---------------------------------------------------------------------------------------------------------------------- -- American indigenous varieties -- ---------------------------------------------------------------------------------------------------------------------- ----------------------------------------------------- -- Inuit varieties -- ----------------------------------------------------- m["esi"] = { "North Alaskan Inupiatun", nil, "ik" } m["esk"] = { "Northwest Alaskan Inupiatun", 25559714, "ik" } ----------------------------------------------------- -- Iroquoian varieties -- ----------------------------------------------------- m["iro-ohu"] = { "Old Wendat", nil, "wdt", } m["iro-omo"] = { "Old Mohawk", nil, "moh", } m["iro-oon"] = { "Old Onondaga", nil, "ono", } ----------------------------------------------------- -- Tupi-Guarani varieties -- ----------------------------------------------------- -- Old Tupi varieties m["tpw-lga"] = { "Língua Geral Amazônica", 18275323, "tpw", aliases = {"Língua Geral"}, } m["tpw-lgp"] = { "Língua Geral Paulista", 2669239, "tpw", } ---------------------------------------------------------------------------------------------------------------------- -- Austroasiatic varieties -- ---------------------------------------------------------------------------------------------------------------------- -- Khmer varieties m["okz-ang"] = { "Angkorian Old Khmer", nil, "okz", wikipedia_article = "Khmer language#Historical periods", } m["okz-pre"] = { "Pre-Angkorian Old Khmer", nil, "okz", wikipedia_article = "Khmer language#Historical periods", } -- Central Nicobarese varieties m["ncb-cam"] = { "Camorta", 5026908, "ncb", aliases = {"Kamorta"}, } m["ncb-kat"] = { "Katchal", 17064263, "ncb", aliases = {"Tehnu"}, } m["ncb-nan"] = { "Nancowry", 6962504, "ncb", aliases = {"Nankwari"}, } ---------------------------------------------------------------------------------------------------------------------- -- Austronesian varieties -- ---------------------------------------------------------------------------------------------------------------------- -- Malay and related varieties m["ms-old"] = { -- this has the ISO code 'omy' "Old Malay", nil, "ms", } m["ms-cla"] = { "Classical Malay", nil, "ms", ancestors = "ms-old", } m["pse-bsm"] = { "Besemah", nil, "pse", } m["bew-kot"] = { "Betawi Kota", nil, "bew", aliases = {"Urban Betawi"}, -- in Jakarta } -- Philippine varieties m["xnn"] = { "Northern Kankanaey", 12953609, "kne", aliases = {"Northern Kankanay", "Northern Kankana-ey"}, } m["tl-old"] = { "Old Tagalog", 12967437, "tl", } m["tl-cls"] = { "Classical Tagalog", nil, "tl", } ---------------------------------------------------------------------------------------------------------------------- -- Caucasian varieties -- ---------------------------------------------------------------------------------------------------------------------- -- Kartvelian varieties m["ka-mid"] = { "Middle Georgian", nil, "ka", ancestors = "oge", } ---------------------------------------------------------------------------------------------------------------------- -- Dravidian varieties -- ---------------------------------------------------------------------------------------------------------------------- m["ta-mid"] = { "Middle Tamil", 20987434, "ta", } m["kn-hav"] = { "Havigannada", 24276369, "kn", } m["kn-kun"] = { "Kundagannada", 6444255, "kn", } ---------------------------------------------------------------------------------------------------------------------- -- Indo-European varieties -- ---------------------------------------------------------------------------------------------------------------------- -------------------------------------------------------------------------------------- -- Albanian varieties -- -------------------------------------------------------------------------------------- m["aln"] = { "Gheg Albanian", 181037, "sq", aliases = {"Gheg"}, } m["aae"] = { "Arbëresh Albanian", 1075302, "als", aliases = {"Arbëreshë", "Arbëresh"}, } m["aat"] = { "Arvanitika Albanian", 29347, "als", aliases = {"Arvanitika"}, } m["als"] = { "Tosk Albanian", 180937, "sq", aliases = {"Tosk"}, } -------------------------------------------------------------------------------------- -- Armenian varieties -- -------------------------------------------------------------------------------------- m["hyw"] = { "Western Armenian", 180945, "hy", } m["hye"] = { "Eastern Armenian", 181059, "hy", } -------------------------------------------------------------------------------------- -- Balto-Slavic varieties -- -------------------------------------------------------------------------------------- ------------------------------------------------------------------------- -- Baltic varieties -- ------------------------------------------------------------------------- m["bat-pro"] = { "Proto-Baltic", 1703347, "ine-bsl-pro", } m["bat-dni"] = { "Dnieper Baltic", 4163178, "bat-pro", family = "bat", aliases = {"Dniepr Baltic", "Dnieper-Oka Baltic", "Dniepr-Oka Baltic"}, } m["bat-gol"] = { "Golyad", 4142855, "bat-dni", aliases = {"Eastern Galindian", "East Galindian"}, } ------------------------------------------------------------------------- -- Slavic varieties -- ------------------------------------------------------------------------- ----------------------------------------------------- -- Bulgarian varieties -- ----------------------------------------------------- m["cu-bgm"] = { "Middle Bulgarian", 12294897, "cu", ancestors = "cu" } ----------------------------------------------------- -- Church Slavonic varieties -- ----------------------------------------------------- -- Old Moscow Church Slavonic deleted as it seems not distinct enough from Russian (Synodal) Church Slavonic. m["zls-chs-ru"] = { "Russian Church Slavonic", 21662400, "zls-chs", aliases = {"Synodal Church Slavonic", "New Moscow Church Slavonic", "Novomoskovsk Church Slavonic"}, } m["zls-chs-uk"] = { "Ukrainian Church Slavonic", 12153548, "zls-chs", aliases = {"Rusyn Church Slavonic", "Belarusian Church Slavonic"}, } --[=[ -- Not sure about these yet. m["zls-chs-bg"] = { "Bulgarian Church Slavonic", nil, "zls-chs", } m["zls-chs-cs"] = { "Czech Church Slavonic", nil, "zls-chs", } m["zls-chs-hr"] = { "Croatian Church Slavonic", nil, "zls-chs", } m["zls-chs-mk"] = { "Macedonian Church Slavonic", nil, "zls-chs", } m["zls-chs-ro"] = { "Romanian Church Slavonic", nil, "zls-chs", } m["zls-chs-sr"] = { "Serbian Church Slavonic", nil, "zls-chs", } ]=] ----------------------------------------------------- -- Czech varieties -- ----------------------------------------------------- m["cs-ear"] = { "Early Modern Czech", nil, "cs", ancestors = "zlw-ocs" } ----------------------------------------------------- -- East Slavic varieties -- ----------------------------------------------------- m["zle-ops"] = { "Old Pskovian", 4167885, "zle-ono", } m["zle-mru"] = { "Middle Russian", 35228, "ru", "Cyrs", ancestors = "orv", translit = "ru-translit", strip_diacritics = { Cyrs = { remove_diacritics = c.grave .. c.acute .. c.diaer, }, }, } m["zle-mbe"] = { "Middle Belarusian", 13211, "zle-ort", ancestors = "zle-ort", } m["zle-muk"] = { "Middle Ukrainian", 13211, "zle-ort", ancestors = "zle-ort", } m["uk-CA"] = { "Canadian Ukrainian", 4161010, "uk", } m["crp-cpr-kya"] = { "Kyakhta Chinese Pidgin Russian", 1062960, "crp-cpr", } ----------------------------------------------------- -- Polish varieties -- ----------------------------------------------------- m["zlw-mpl"] = { "Middle Polish", 402878, "pl", ancestors = "zlw-opl", strip_diacritics = { remove_diacritics = c.acute, remove_exceptions = {"Ć", "ć", "Ń", "ń", "Ó", "ó", "Ś", "ś", "Ź", "ź"}, }, } m["pl-gre"] = { "Greater Polish", 4106789, "pl", } m["pl-les"] = { "Lesser Polish", 361709, "pl", } m["pl-mas"] = { "Masovian Polish", 4274559, "pl", } m["pl-gor"] = { "Goral", 452889, "pl", } ----------------------------------------------------- -- Serbo-Croatian varieties -- ----------------------------------------------------- m["ckm"] = { "Chakavian Serbo-Croatian", 337565, "sh", aliases = {"Čakavian"}, } m["kjv"] = { "Kajkavian Serbo-Croatian", 838165, "sh", } m["sh-tor"] = { -- Linguist code srp-tor "Torlakian Serbo-Croatian", 1078803, "sh", aliases = {"Torlak"}, } -------------------------------------------------------------------------------------- -- Celtic varieties -- -------------------------------------------------------------------------------------- ----------------------------------------------------- -- Brythonic varieties -- ----------------------------------------------------- m["bry-ear"] = { "Early Brythonic", nil, "cel-bry-pro", } m["bry-lat"] = { "Late Brythonic", nil, "cel-bry-pro", } ----------------------------------------------------- -- Gaulish varieties -- ----------------------------------------------------- m["xcg"] = { "Cisalpine Gaulish", 3832927, "cel-gau", } m["xtg"] = { "Transalpine Gaulish", 29977, "cel-gau", } ----------------------------------------------------- -- Welsh varieties -- ----------------------------------------------------- m["cy-nor"] = { "North Wales Welsh", 13127692, "cy", aliases = {"North Walian Welsh", "Northern Welsh"}, } m["cy-sou"] = { "South Wales Welsh", 13127689, "cy", aliases = {"South Walian Welsh", "Southern Welsh"}, } -------------------------------------------------------------------------------------- -- Germanic varieties -- -------------------------------------------------------------------------------------- -- Proto-West Germanic varieties m["frk"] = { "Frankish", 10860505, "gmw-pro", family = "gmw-frk", aliases = {"Old Frankish"}, } m["gem-sue"] = { "Suevic", 134600275, "gmw-pro", aliases = {"Suebian"}, } m["gmw-afr-pro"] = { "Proto-Anglo-Frisian", 134603379, "gmw-nsg-pro", family = "gmw-afr", } m["gmw-nsg-pro"] = { "Proto-North Sea Germanic", 134603374, "gmw-pro", family = "gmw-nsg", aliases = {"Proto-Ingvaeonic"}, } ----------------------------------------------------- -- Dutch varieties -- ----------------------------------------------------- m["nl-BE"] = { "Belgian Dutch", 34147, "nl", aliases = {"Flemish", "Flemish Dutch", "Southern Dutch"}, } ----------------------------------------------------- -- English and Scots varieties -- ----------------------------------------------------- -- English varieties m["en-AU"] = { "Australian English", 44679, "en", } m["en-GB"] = { "British English", 7979, "en", } m["en-GB-SCT"] = { "Scottish English", 1553250, "en-GB", } m["en-GB-WLS"] = { "Welsh English", 2363292, "en-GB", } m["en-IM"] = { "Manx English", 6753295, "en-GB", } m["en-aae"] = { "Australian Aboriginal English", 783347, "en-AU", } m["en-ear"] = { "Early Modern English", 1472196, "en", ancestors = "enm", aliases = {"Early New English"}, } m["en-geo"] = { "Geordie", 653421, "en", ancestors = "enm-nor", } m["en-IE"] = { -- FIXME: "IE" doesn't cover Northern Ireland "Irish English", 665624, "en", } m["en-uls"] = { "Ulster English", 6840826, "en-IE", } m["en-GB-NIR"] = { "Northern Irish English", 6840826, -- actually the code for Ulster English "en-uls", } m["en-NNN"] = { -- NA = Namibia; NNN is NATO 3-letter code for North America "North American English", 7053766, "en", ietf_subtag = "en-021" -- 021 = UN M49 code for "Northern America" (i.e. North America wihout Central America or the Caribbean) } m["en-US"] = { "American English", 7976, "en-NNN", } m["en-NZ"] = { "New Zealand English", 44661, "en" } m["en-ZA"] = { "South African English", 1156228, "en" } m["en-US-CA"] = { "California English", 1026812, "en-US", } m["en-CA"] = { "Canadian English", 44676, "en-US", } m["en-HK"] = { "Hong Kong English", 1068863, "en", } m["en-IN"] = { "Indian English", 1348800, "en", } m["pld"] = { "Polari", 1359130, "en", } -- Scots varieties m["sco-ins"] = { "Insular Scots", 16919205, "sco", } m["sco-uls"] = { "Ulster Scots", 201966, "sco", } m["sco-nor"] = { "Northern Scots", 16928150, "sco", } m["sco-sou"] = { "Southern Scots", 7570457, "sco", aliases = {"South Scots", "Borders Scots"}, } -- Middle English varieties m["enm-esc"] = { -- Part of Middle English until it developed into Middle Scots. "Early Scots", 5326738, "enm", ancestors = "enm-nor", aliases = {"Old Scots", "Scottish Middle English"}, } m["enm-emi"] = { "East Midland Middle English", 134238810, "enm", ancestors = "ang-ang", -- Technically ang-mer, but attested Mercian is mostly WM IIRC } m["enm-ken"] = { "Kentish Middle English", 134238532, "enm", ancestors = "ang-ken", } m["enm-nor"] = { "Northern Middle English", 134238541, "enm", ancestors = "ang-nor", } m["enm-sou"] = { "Southern Middle English", 134238528, "enm", ancestors = "ang-wsx", } m["enm-wmi"] = { "West Midland Middle English", 134238824, "enm", ancestors = "ang-mer", } -- Old English varieties -- Includes both Mercian and Northumbrian. m["ang-ang"] = { "Anglian Old English", 121142917, "ang", } m["ang-ken"] = { "Kentish Old English", 11687485, "ang", } m["ang-mer"] = { "Mercian Old English", 602072, "ang-ang", } m["ang-nor"] = { "Northumbrian Old English", 1798915, "ang-ang", } m["ang-wsx"] = { "West Saxon Old English", 2658603, "ang", } ----------------------------------------------------- -- High German varieties -- ----------------------------------------------------- -- (modern) German varieties m["de-AT"] = { "Austrian German", 306626, "de", } m["de-AT-vie"] = { "Viennese German", 56474, "de-AT", } m["de-CH"] = { "Switzerland German", 1366643, "de", aliases = {"Schweizer Hochdeutsch", "Swiss Standard German", "Swiss High German"}, } m["de-bal"] = { "Baltic German", 15785413, "de", } m["de-ear"] = { "Early New High German", 1472199, "de", ancestors = "gmh", aliases = {"Early Modern High German"}, } m["ksh"] = { "Kölsch", 4624, "gmw-cfr", } m["pfl"] = { "Palatine German", 23014, "gmw-rfr", aliases = {"Pfälzisch", "Pälzisch", "Palatinate German"}, } m["sli"] = { "Silesian East Central German", 152965, "gmw-ecg", aliases = {"Silesian"}, } m["sxu"] = { "Upper Saxon German", 699284, "gmw-ecg", } -- Old High German varieties m["lng"] = { "Lombardic", 35972, "goh", } -- Alemannic German varieties m["gsw-low"] = { "Low Alemannic German", 503724, "gsw", } m["gsw-FR-als"] = { "Alsatian Alemannic German", 8786, "gsw-low", } m["gsw-hig"] = { "High Alemannic German", 503728, "gsw", } m["gsw-hst"] = { "Highest Alemannic German", 687538, "gsw", } m["wae"] = { "Walser German", 680517, "gsw-hst", } ----------------------------------------------------- -- Low German varieties -- ----------------------------------------------------- m["nds-de"] = { "German Low German", 25433, "nds", ietf_subtag = "nds-DE", -- should we make this the actual code? wikimedia_codes = "nds", } m["nds-nl"] = { "Dutch Low Saxon", 516137, "nds", ietf_subtag = "nds-NL", -- should we make this the actual code? wikimedia_codes = "nds-nl", } m["act"] = { "Achterhoeks", 153627, "nds-nl", aliases = {"Achterhoek", "Achterhooks"}, } m["drt"] = { "Drents", 2736709, "nds-nl", aliases = {"Drèents", "Dreins", "Dreints", "Drints"}, } m["frs"] = { "East Frisian Low German", 149208, "nds-de", aliases = {"East Frisian", "East Frisian Low Saxon"}, } m["gos"] = { "Gronings", 508854, "nds-nl", aliases = {"Grunnegs", "Grönnegs"}, } m["nds-lpr"] = { "Low Prussian", 33982, "nds-de", } m["sdz"] = { "Sallands", 3436668, "nds-nl", aliases = {"Sallaans", "Sallaands"}, } m["stl"] = { "Stellingwerfs", 506010, "nds-nl", aliases = {"Stellingwarfs"}, } m["twd"] = { "Twents", 497363, "nds-nl", aliases = {"Tweants"}, } m["vel"] = { "Veluws", 2484810, "nds-nl", } m["wep"] = { "Westphalian", 505655, "nds-de", aliases = {"Westfalish", "Westphalien"}, } ----------------------------------------------------- -- North Frisian varieties -- ----------------------------------------------------- m["frr-ins"] = { "Insular North Frisian", 110629610, "frr", } m["frr-fam"] = { "Föhr-Amrum North Frisian", 110629601, "frr-ins", } m["frr-foh"] = { "Föhr North Frisian", 28185, "frr-fam", aliases = {"Föhr Frisian", "Fering", "Ferring", -- Glottolog }, varieties = {"Aasdring", "Weesdring"}, } m["frr-amr"] = { "Amrum North Frisian", 28192, "frr-fam", aliases = {"Amrum Frisian", "Amrum", "Öömrang"}, } m["frr-hel"] = { "Heligoland North Frisian", 28086, "frr-ins", aliases = {"Heligoland Frisian", "Halunder", "Heligolandic Frisian", "Heligolandic North Frisian", "Helgoland Frisian", "Helgoland North Frisian", "Helgoland"}, } m["frr-syl"] = { "Sylt North Frisian", 28181, "frr-ins", aliases = {"Sylt Frisian", "Söl'ring", "Sölreng", -- Glottolog }, } m["frr-mai"] = { "Mainland North Frisian", 110629626, "frr", } m["frr-hal"] = { "Halligen North Frisian", 28177, "frr-mai", aliases = {"Halligen Frisian", "Halifreesk", "Hallingen Frisian", "Hallingen North Frisian", "Hallingen", -- Glottolog }, } m["frr-moo"] = { "Mooring North Frisian", 28187, "frr-mai", aliases = {"Bökingharde North Frisian", "Bökingharde Frisian", "Böökinghiirder frasch", "Mooring", "Moring", }, varieties = {{"East Mooring", "Ostermooring"}, {"West Mooring", "Westermooring"}}, } m["frr-kar"] = { "Karrharde North Frisian", 28191, "frr-mai", aliases = {"Karrharde Frisian", "Karrharder", }, } m["frr-goe"] = { -- Technically this refers to three adjacent dialects (Northern, Central and Southern), the latter of which went -- extinct in 1980-1981. As a result, Glottolog speaks of "Norder-Mittelgoesharde", referring to the remaining two. "Goesharde North Frisian", 28183, "frr-mai", aliases = {"Norder-Mittelgoesharde North Frisian", "Norder-Mittelgoesharde Frisian", "Norder-Mittelgoesharde", "Goesharde Frisian", "Goesharde", "Gooshiirder", }, } m["frr-wie"] = { "Wiedingharde North Frisian", 28171, "frr-mai", aliases = {"Wiedingharde Frisian", "Wiedingharde", "Wiringhiirder freesk", }, } ----------------------------------------------------- -- Old Norse varieties -- ----------------------------------------------------- m["non-grn"] = { "Greenlandic Norse", 855236, "non-own", } m["non-oen"] = { "Old East Norse", 10498031, "non", ancestors = "non", } m["non-own"] = { "Old West Norse", 2377483, "non", ancestors = "non", } ----------------------------------------------------- -- Old Swedish varieties -- ----------------------------------------------------- m["gmq-osw-lat"] = { "Late Old Swedish", 10723594, "gmq-osw", ancestors = "gmq-osw", } -------------------------------------------------------------------------------------- -- Greek varieties -- -------------------------------------------------------------------------------------- m["qsb-grc"] = { "Pre-Greek", 965052, "und", family = "qfa-sub", } m["grc-aeo"] = { "Aeolic Greek", 406373, "grc", aliases = {"Lesbic Greek", "Lesbian Greek", "Aeolian Greek"}, } m["grc-arc"] = { "Arcadian Greek", nil, "grc-arp", } m["grc-arp"] = { "Arcadocypriot Greek", 499602, "grc", } m["grc-att"] = { "Attic Greek", 506588, "grc", } m["grc-boi"] = { "Boeotian Greek", 406373, "grc-aeo", } m["grc-cyp"] = { "Cypriot Ancient Greek", -- to distinguish from Cypriot Greek below nil, "grc-arp", } m["grc-dor"] = { "Doric Greek", 285494, "grc", } m["grc-ela"] = { "Elean Greek", nil, "grc", } m["grc-epi"] = { "Epic Greek", 990062, "grc", aliases = {"Homeric Greek"}, } m["grc-ion"] = { "Ionic Greek", 504165, "grc", } m["grc-koi"] = { "Koine Greek", 107358, "grc", ancestors = "grc-att", aliases = {"Hellenistic Greek"}, } m["grc-kre"] = { "Cretan Ancient Greek", -- to distinguish from Cretan Greek below nil, "grc-dor", } m["grc-opl"] = { "Opuntian Locrian", nil, "grc", } m["grc-ozl"] = { "Ozolian Locrian", nil, "grc", } m["grc-pam"] = { "Pamphylian Greek", 2271793, "grc", } m["grc-ths"] = { "Thessalian Greek", 406373, "grc-aeo", } m["gkm"] = { "Byzantine Greek", 36387, "grc", ancestors = "grc-koi", aliases = {"Medieval Greek"}, } m["el-cyp"] = { "Cypriot Greek", 245899, "el", aliases = {"Cypriotic Greek"}, } m["el-pap"] = { "Paphian Greek", nil, "el", } m["el-crt"] = { "Cretan Greek", 588306, "el", } m["el-kth"] = { "Katharevousa", 35961, "el", "Polyt", ancestors = "gkm", aliases = {"Katharevousa Greek"}, -- Polyt display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["el-kal"] = { "Kaliarda", 12878658, "el", } -------------------------------------------------------------------------------------- -- Indo-Iranian varieties -- -------------------------------------------------------------------------------------- ------------------------------------------------------------------------- -- Indo-Aryan varieties -- ------------------------------------------------------------------------- -- reconstructed intermediate stages m["pra-pro"] = { "Proto-New Indo-Aryan", nil, "pra", } m["inc-ash-pro"] = { "Proto-Middle Indo-Aryan", nil, "inc-ash", } m["inc-mit"] = { "Mitanni", 1986700, "inc-pro", } m["bra-old"] = { "Old Braj", nil, "bra", } -- Apabhramsas m["inc-aav"] = { "Avahattha", nil, "inc-apa", aliases = {"Abahattha"}, } m["inc-asa"] = { "Sauraseni Apabhramsa", nil, "inc-apa", } m["inc-agu"] = { "Gurjara Apabhramsa", nil, "inc-apa", } m["inc-aka"] = { "Kasmiri Apabhramsa", nil, "inc-apa", } m["inc-ama"] = { "Maharastri Apabhramsa", nil, "inc-apa", } m["inc-ata"] = { "Takka Apabhramsa", nil, "inc-apa", } m["inc-avr"] = { "Vracada Apabhramsa", nil, "inc-apa", } -- Assamese varieties m["as-bkm"] = { "Barpetia Kamrupi Assamese", 30642960, "as", } m["as-nkm"] = { "Nalbaria Kamrupi Assamese", 85787678, "as", } m["as-pkm"] = { "Palasbaria Kamrupi Assamese", nil, "as", } -- Bengali varieties m["bn-dvn"] = { "Dhakaiya Vaṅga Bengali", 48726851, "bn", -- Eastern Bengali variety } m["bn-nvn"] = { "Noakhailla Vaṅga Bengali", 107548681, "bn", -- Eastern Bengali variety } -- Dhivehi varieties m["dv-old"] = { "Old Dhivehi", 117790875, "dv", } m["dv-mul"] = { "Mulaku Dhivehi", nil, "dv", aliases = {"Mulaku Divehi", "Mulaku Bas"}, } m["dv-huv"] = { "Huvadhu Dhivehi", nil, "dv", aliases = {"Huvadhu Divehi", "Huvadhu Bas"}, } m["dv-add"] = { "Addu Dhivehi", nil, "dv", aliases = {"Addu Divehi", "Addu Bas"}, } -- Gujarati varieties m["gu-kat"] = { "Kathiyawadi", nil, "gu", aliases = {"Kathiyawadi Gujarati", "Kathiawadi"}, } m["gu-lda"] = { "Lisan ud-Dawat Gujarati", nil, "gu", aliases = {"Lisan ud-Dawat", "LDA"}, } -- Hindi varieties m["hi-mum"] = { "Bombay Hindi", 3543151, "hi", aliases = {"Mumbai Hindi", "Bambaiyya Hindi"}, } m["hi-mid"] = { "Middle Hindi", nil, "inc-ohi", ancestors = "inc-ohi", } -- Konkani varieties m["kok-mid"] = { "Middle Konkani", nil, "kok", aliases = {"Medieval Konkani"}, } m["kok-old"] = { "Old Konkani", nil, "kok", aliases = {"Early Konkani"}, } -- Prakrits m["pra-ard"] = { "Ardhamagadhi Prakrit", 35217, "pra", aliases = {"Ardhamagadhi"}, } m["pra-hel"] = { "Helu Prakrit", 15080869, "pra", aliases = {"Elu", "Elu Prakrit", "Helu"}, } m["pra-kha"] = { "Khasa Prakrit", nil, "pra", aliases = {"Khasa"}, } m["pra-mag"] = { "Magadhi Prakrit", -- Not to be confused with Magahi (mag) 2652214, "pra", aliases = {"Magadhi"}, } m["pra-mah"] = { "Maharastri Prakrit", 2586773, "pra", aliases = {"Maharashtri Prakrit", "Maharastri", "Maharashtri"}, } m["pra-pai"] = { "Paisaci Prakrit", 2995607, "pra-sau", aliases = {"Paisaci", "Paisachi"}, ancestors = "pra-sau" } m["pra-sau"] = { "Sauraseni Prakrit", 2452885, "pra", aliases = {"Sauraseni", "Shauraseni"}, } m["pra-ava"] = { "Avanti", nil, "pra", aliases = {"Avanti Prakrit"}, } m["pra-pra"] = { "Pracya", nil, "pra", aliases = {"Pracya Prakrit"}, } m["pra-bah"] = { "Bahliki", nil, "pra", aliases = {"Bahliki Prakrit"}, } m["pra-dak"] = { "Daksinatya", nil, "pra", aliases = {"Daksinatya Prakrit"}, } m["pra-sak"] = { "Sakari", nil, "pra", aliases = {"Sakari Prakrit"}, } m["pra-can"] = { "Candali", nil, "pra", aliases = {"Candali Prakrit"}, } m["pra-sab"] = { "Sabari", nil, "pra", aliases = {"Sabari Prakrit"}, } m["pra-abh"] = { "Abhiri", nil, "pra", aliases = {"Abhiri Prakrit"}, } m["pra-dra"] = { "Dramili", nil, "pra", aliases = {"Dramili Prakrit"}, } m["pra-odr"] = { "Odri", nil, "pra", aliases = {"Odri Prakrit"}, } -- Punjabi varieties m["pnb"] = { "Western Punjabi", 58635, "pa", "pa-Arab", } -- Sanskrit varieties m["vsn"] = { "Vedic Sanskrit", 36858, "sa", } m["cls"] = { "Classical Sanskrit", 9333703, "sa", } m["sa-bhs"] = { "Buddhist Hybrid Sanskrit", 248758, "sa", } m["sa-bra"] = { "Brahmanic Sanskrit", 139822891, "vsn", } m["sa-epi"] = { "Epic Sanskrit", 56702805, "cls", } m["sa-neo"] = { "New Sanskrit", nil, "sa", } m["sa-rig"] = { "Rigvedic Sanskrit", 139822680, "vsn", } -- Sinhalese varieties m["si-med"] = { "Medieval Sinhalese", nil, "si", aliases = {"Medieval Sinhala"}, } ------------------------------------------------------------------------- -- Iranian varieties -- ------------------------------------------------------------------------- m["qsb-bma"] = { "the BMAC substrate", 133187435, "und", family = "qfa-sub", aliases = {"the Bactria-Margiana substrate", "the Bactria-Margiana Archaeological Complex substrate"}, } -- Historical and current Iranian dialects m["ae-old"] = { "Old Avestan", 29572, "ae", aliases = {"Gathic Avestan"}, } m["ae-yng"] = { "Younger Avestan", 29572, "ae-old", aliases = {"Young Avestan"}, } m["bcc"] = { "Southern Balochi", 33049, "bal", aliases = {"Southern Baluchi"}, } m["bgp"] = { "Eastern Balochi", 33049, "bal", aliases = {"Eastern Baluchi"}, } m["bgn"] = { "Western Balochi", 33049, "bal", aliases = {"Western Baluchi"}, } m["bsg-ban"] = { "Bandari", nil, "bsg", } m["bsg-hor"] = { "Hormozi", nil, "bsg", } m["bsg-min"] = { "Minabi", nil, "bsg", } m["kho-old"] = { "Old Khotanese", nil, "kho", } m["kho-lat"] = { "Late Khotanese", nil, "kho-old", } m["peo-ear"] = { "Early Old Persian", nil, "peo", } m["peo-lat"] = { "Late Old Persian", nil, "peo", } m["pal-ear"] = { "Early Middle Persian", nil, "pal", } m["pal-lat"] = { "Late Middle Persian", nil, "pal", ancestors = "pal-ear", } m["ps-nwe"] = { "Northwestern Pashto", nil, "ps", } m["ps-cgi"] = { "Central Ghilzay", nil, "ps-nwe", } m["ps-mah"] = { "Mahsudi", nil, "ps-nwe", } m["ps-nea"] = { "Northeastern Pashto", nil, "ps", } m["ps-afr"] = { "Afridi", nil, "ps-nea", } m["ps-bng"] = { "Bangash", nil, "ps-nea", } m["ps-xat"] = { "Khatak", nil, "ps-nea", } m["ps-pes"] = { "Peshawari", nil, "ps-nea", } m["ps-sea"] = { "Southeastern Pashto", nil, "ps", } m["ps-ban"] = { "Bannu", nil, "ps-sea", } m["ps-kak"] = { "Kakari", nil, "ps-sea", } m["ps-ser"] = { "Sher", nil, "ps-sea", } m["ps-waz"] = { "Waziri", 12274473, "ps-sea", } m["ps-swe"] = { "Southwestern Pashto", nil, "ps", } m["ps-kan"] = { "Kandahari", nil, "ps-swe", } m["ps-jad"] = { "Jadrani", nil, "ps", ancestors = "ira-pat-pro" } m["xme-azr"] = { "Old Azari", nil, "xme-ott", aliases = {"Old Azeri", "Azari", "Azeri", "Āḏarī", "Adari", "Adhari"}, } m["xme-ttc-cen"] = { "Central Tati", nil, "xme-ott", } m["xme-ttc-eas"] = { "Eastern Tati", nil, "xme-ott", } m["xme-ttc-nor"] = { "Northern Tati", nil, "xme-ott", } m["xme-ttc-sou"] = { "Southern Tati", nil, "xme-ott", } m["xme-ttc-wes"] = { "Western Tati", nil, "xme-ott", } m["xmn"] = { "Manichaean Middle Persian", nil, "pal-lat", } m["fa-ear"] = { "Early New Persian", 127413796, "fa", ancestors = "pal-lat", translit = "fa-cls-translit", } m["fa-cls"] = { "Classical Persian", 9168, "fa", ancestors = "fa-ear", translit = "fa-cls-translit", } m["fa-ira"] = { "Iranian Persian", 3513637, "fa", aliases = {"Modern Persian", "Western Persian"}, translit = "fa-ira-translit", } m["prs"] = { "Dari", 178440, "fa", aliases = {"Dari Persian", "Central Persian", "Eastern Persian", "Afghan Persian"}, translit = "fa-cls-translit", } m["haz"] = { "Hazaragi", 33398, "prs", translit = "fa-cls-translit", } m["os-dig"] = { "Digor Ossetian", 3027861, "os", aliases = {"Digoron", "Digor"}, } m["os-iro"] = { "Iron Ossetian", nil, "os", aliases = {"Iron"}, } m["sog-ear"] = { "Early Sogdian", nil, "sog", } m["sog-lat"] = { "Late Sogdian", nil, "sog-ear", } m["ro-MD"] = { "Moldovan", 36392, "ro", aliases = {"Moldavian"}, } m["oru-kan"] = { "Kaniguram", 6363164, "oru", } m["oru-log"] = { "Logar", nil, "oru", } m["oos"] = { "Old Ossetic", 65455882, "xln", } m["oos-ear"] = { "Early Old Ossetic", nil, "oos", } m["oos-lat"] = { "Late Old Ossetic", nil, "oos", } m["rdb-jir"] = { "Jirofti", nil, "rdb", } m["rdb-kah"] = { "Kahnuji", nil, "rdb", } -- Southwestern Fars lects m["fay-bur"] = { "Burenjani", nil, "fay", } m["fay-bsh"] = { "Bushehri", nil, "fay", } m["fay-dsh"] = { "Dashtaki", nil, "fay", } m["fay-dav"] = { "Davani", 5228140, "fay", } m["fay-eze"] = { "Emamzada Esmaili", nil, "fay", } m["fay-gav"] = { "Gavkoshaki", nil, "fay", } m["fay-kho"] = { "Khollari", nil, "fay", } m["fay-kon"] = { "Kondazi", nil, "fay", } m["fay-kzo"] = { "Old Kazeruni", nil, "fay", } m["fay-mas"] = { "Masarami", nil, "fay", } m["fay-pap"] = { "Papuni", nil, "fay", } m["fay-sam"] = { "Samghani", nil, "fay", } m["fay-shr"] = { "Shirazi", nil, "fay", } m["fay-sho"] = { "Old Shirazi", nil, "fay", } m["fay-kar"] = { "Khargi", nil, "fay", } m["fay-sor"] = { "Sorkhi", nil, "fay", } -- Talysh lects m["tly-cen"] = { "Central Talysh", nil, "tly", } m["tly-asa"] = { "Asalemi", nil, "tly-cen", } m["tly-kar"] = { "Karganrudi", nil, "tly-cen", } m["tly-tul"] = { "Tularudi", nil, "tly-cen", } m["tly-tal"] = { "Taleshdulabi", nil, "tly-cen", } m["tly-nor"] = { "Northern Talysh", nil, "tly", } m["tly-aze"] = { "Azerbaijani Talysh", nil, "tly-nor", } m["tly-anb"] = { "Anbarani", nil, "tly-nor", } m["tly-sou"] = { "Southern Talysh", nil, "tly", } m["tly-fum"] = { "Fumani", nil, "tly-sou", } m["tly-msu"] = { "Masulei", nil, "tly-sou", } m["tly-msa"] = { "Masali", nil, "tly-sou", } m["tly-san"] = { "Shandarmani", nil, "tly-sou", } -- Tafreshi lects m["xme-amo"] = { "Amorehi", nil, "xme-taf", } m["atn"] = { "Ashtiani", 3436590, "xme-taf", } m["xme-bor"] = { "Borujerdi", nil, "xme-taf", } m["xme-ham"] = { "Hamadani", 6302426, "xme-taf", } m["xme-kah"] = { "Kahaki", nil, "xme-taf", } m["vaf"] = { "Vafsi", 32611, "xme-taf", } -- Kermanic lects m["kfm"] = { "Khunsari", 6403030, "xme-ker", } m["xme-mah"] = { "Mahallati", nil, "xme-ker", } m["xme-von"] = { "Vonishuni", nil, "xme-ker", } m["xme-bdr"] = { "Badrudi", nil, "xme-ker", } m["xme-del"] = { "Delijani", nil, "xme-ker", } m["xme-kas"] = { "Kashani", nil, "xme-ker", } m["xme-kes"] = { "Kesehi", nil, "xme-ker", } m["xme-mey"] = { "Meymehi", nil, "xme-ker", } m["ntz"] = { "Natanzi", 6968399, "xme-ker", } m["xme-abz"] = { "Abuzeydabadi", nil, "xme-ker", } m["xme-aby"] = { "Abyanehi", nil, "xme-ker", } m["xme-far"] = { "Farizandi", nil, "xme-ker", } m["xme-jow"] = { "Jowshaqani", nil, "xme-ker", } m["xme-nas"] = { "Nashalji", nil, "xme-ker", } m["xme-qoh"] = { "Qohrudi", nil, "xme-ker", } m["xme-yar"] = { "Yarandi", nil, "xme-ker", } m["soj"] = { "Soi", 7930463, "xme-ker", aliases = {"Sohi"}, } m["xme-tar"] = { "Tari", nil, "xme-ker", } m["gzi"] = { "Gazi", 5529130, "xme-ker", } m["xme-sed"] = { "Sedehi", nil, "xme-ker", } m["xme-ard"] = { "Ardestani", nil, "xme-ker", } m["xme-zef"] = { "Zefrehi", nil, "xme-ker", } m["xme-isf"] = { "Isfahani", nil, "xme-ker", } m["xme-kaf"] = { "Kafroni", nil, "xme-ker", } m["xme-vrz"] = { "Varzenehi", nil, "xme-ker", } m["xme-xur"] = { "Khuri", nil, "xme-ker", } m["nyq"] = { "Nayini", 6983146, "xme-ker", } m["xme-ana"] = { "Anaraki", nil, "xme-ker", } m["gbz"] = { "Zoroastrian Dari", 32389, "xme-ker", aliases = {"Behdināni", "Gabri", "Gavrŭni", "Gabrōni"}, } m["xme-krm"] = { "Kermani", nil, "xme-ker", } m["xme-yaz"] = { "Yazdi", nil, "xme-ker", } m["xme-bid"] = { "Bidhandi", nil, "xme-ker", } m["xme-bij"] = { "Bijagani", nil, "xme-ker", } m["xme-cim"] = { "Chimehi", nil, "xme-ker", } m["xme-han"] = { "Hanjani", nil, "xme-ker", } m["xme-kom"] = { "Komjani", nil, "xme-ker", } m["xme-nar"] = { "Naraqi", nil, "xme-ker", } m["xme-nus"] = { "Nushabadi", nil, "xme-ker", } m["xme-qal"] = { "Qalhari", nil, "xme-ker", } m["xme-trh"] = { "Tarehi", nil, "xme-ker", } m["xme-val"] = { "Valujerdi", nil, "xme-ker", } m["xme-var"] = { "Varani", nil, "xme-ker", } m["xme-zor"] = { "Zori", nil, "xme-ker", } -- Ramandi lects m["tks-ebr"] = { "Ebrahimabadi", nil, "tks", } m["tks-sag"] = { "Sagzabadi", nil, "tks", } m["tks-esf"] = { "Esfarvarini", nil, "tks", } m["tks-tak"] = { "Takestani", nil, "tks", } m["tks-cal"] = { "Chali Tati", nil, "tks", aliases = {"Chāli"}, } m["tks-dan"] = { "Danesfani", nil, "tks", } m["tks-xia"] = { "Khiaraji", nil, "tks", } m["tks-xoz"] = { "Khoznini", nil, "tks", } -- Shughni dialects m["sgh-bro"] = { "Bartangi-Oroshori", nil, "sgh", } m["sgh-bar"] = { "Bartangi", nil, "sgh-bro", } m["sgh-oro"] = { "Oroshori", nil, "sgh-bro", aliases = {"Roshorvi"}, } m["sgh-rsx"] = { "Roshani-Khufi", nil, "sgh", } m["sgh-xuf"] = { "Khufi", 2562249, "sgh-rsx", aliases = {"Xufi", "Xūfī"}, } m["sgh-ros"] = { "Roshani", 2597566, "sgh-rsx", aliases = {"Rushani", "Rōšāni"}, } m["sgh-xgb"] = { "Khughni-Bajui", nil, "sgh", } m["sgh-xug"] = { "Khughni", nil, "sgh-xgb", } m["sgh-baj"] = { "Bajui", nil, "sgh-xgb", } ------------------------------------------------------------------------- -- Nuristani varieties -- ------------------------------------------------------------------------- m["bsh-kat"] = { "Kativiri", 2605045, "bsh", aliases = {"Katə́viri"}, } m["xvi"] = { "Kamviri", 1193495, "bsh", aliases = {"Kamvíri"}, } m["bsh-mum"] = { "Mumviri", nil, "bsh", aliases = {"Mumvíri"}, } -------------------------------------------------------------------------------------- -- Italic varieties -- -------------------------------------------------------------------------------------- ------------------------------------------------------------------------- -- Latin varieties -- ------------------------------------------------------------------------- -- Latin varieties by period m["itc-ola"] = { "Old Latin", 12289, "la", "Latn, Ital", translit = { Ital = "Ital-translit" }, } m["itc-lan"] = { "Lanuvian", 16890829, "itc-ola", aliases = {"Lanuvine"}, } m["itc-pra"] = { "Praenestine", 16889772, "itc-ola", aliases = {"Praenestinian"}, } m["la-cla"] = { "Classical Latin", 253854, "la", } m["la-vul"] = { "Vulgar Latin", 37560, "la-cla", } m["la-afr"] = { "African Romance", 162064, "roa-pro", } m["la-lat"] = { "Late Latin", 1503113, "la", ancestors = "la-cla", } m["la-med"] = { "Medieval Latin", 1163234, "la", ancestors = "la-lat", } m["la-eme"] = { "Early Medieval Latin", nil, "la-med", } m["la-ecc"] = { "Ecclesiastical Latin", 1247932, "la", aliases = {"Church Latin", "Liturgical Latin"}, ancestors = "la-lat", } m["la-ren"] = { "Renaissance Latin", 499083, "la", ancestors = "la-med", } m["la-new"] = { "New Latin", 1248221, "la", aliases = {"Modern Latin"}, ancestors = "la-ren", } m["la-con"] = { "Contemporary Latin", 1246397, "la-new", } ------------------------------------------------------------------------- -- Miscellaneous Italic varieties -- ------------------------------------------------------------------------- m["xfa-cap"] = { "Capenate", 133182969, "xfa", } m["osc-luc"] = { "Lucanian", 3265025, "osc", } m["osc-sam"] = { "Samnite", 133184287, "osc", } ------------------------------------------------------------------------- -- Romance varieties -- ------------------------------------------------------------------------- m["roa-pro"] = { "Proto-Romance", 3408029, "la-lat", ancestors = "la-vul", } ----------------------------------------------------- -- Catalan varieties -- ----------------------------------------------------- m["ca-val"] = { "Valencian", 32641, "ca", } ----------------------------------------------------- -- Franco-Provençal varieties -- ----------------------------------------------------- m["frp-old"] = { "Old Franco-Provençal", nil, "frp", } ----------------------------------------------------- -- French and derived creole varieties -- ----------------------------------------------------- m["fro-nor"] = { "Old Northern French", 2044917, "fro", aliases = {"Old Norman", "Old Norman French"}, } m["fro-pic"] = { "Picard Old French", nil, "fro", } m["xno"] = { "Anglo-Norman", 35214, "fro-nor", } m["xno-law"] = { "Law French", 2044323, "xno", } m["zrp"] = { "Zarphatic", 36994, "fro", aliases = {"Judeo-French"}, pseudo_families = "qfa-jew", } m["fr-CA"] = { "Canadian French", 1450506, "fr", } m["fr-CH"] = { "Swiss French", 1480152, "fr", } m["fr-aca"] = { "Acadian French", 415109, "fr", } m["fr-lou"] = { "Louisiana French", 3083213, "fr", } m["fr-mis"] = { "Missouri French", 3083210, "fr", } m["frc"] = { "Cajun French", 880301, "fr-lou", } m["ht-sdm"] = { "Saint Dominican Creole French", nil, "ht", ancestors = "fr", } -- Norman varieties m["nrf-grn"] = { "Guernsey Norman", 56428, "nrf", aliases = {"Guernsey"}, } m["nrf-jer"] = { "Jersey Norman", 56430, "nrf", aliases = {"Jersey"}, } ----------------------------------------------------- -- Gallo-Italic varieties -- ----------------------------------------------------- m["egl-old"] = { "Old Emilian", nil, "egl", } m["lij-old"] = { "Old Ligurian", nil, "lij", aliases = {"Old Genoese"}, } m["lmo-old"] = { "Old Lombard", 97165320, "lmo", } m["pms-old"] = { "Old Piedmontese", nil, "pms", aliases = {"Old Piemontese"}, } m["vec-old"] = { "Old Venetan", nil, "vec", aliases = {"Old Venetian"}, } m["rgn-old"] = { "Old Romagnol", nil, "rgn", } ----------------------------------------------------- -- Italo-Romance varieties -- ----------------------------------------------------- -- Italian varieties m["roa-oit"] = { "Old Italian", nil, "it", } m["it-CH"] = { "Switzerland Italian", 672147, "it", } -- Other Italo-Romance varieties m["nap-old"] = { "Old Neapolitan", nil, "nap", } m["scn-old"] = { "Old Sicilian", nil, "scn", } ----------------------------------------------------- -- Occitan varieties -- ----------------------------------------------------- m["oc-auv"] = { "Auvergnat", 35359, "oc", aliases = {"Auvernhat", "Auvergnese"}, } m["oc-gas"] = { "Gascon", 35735, "oc", } -- standardized dialect of Gascon m["oc-ara"] = { "Aranese", 10196, "oc-gas", } m["oc-lan"] = { "Languedocien", 942602, "oc", aliases = {"Lengadocian"}, } m["oc-lim"] = { "Limousin", 427614, "oc", } m["oc-pro"] = { "Provençal", 241243, "oc", aliases = {"Provencal"}, } m["oc-pro-old"] = { "Old Provençal", 2779185, "pro", } m["oc-viv"] = { "Vivaro-Alpine", 1649613, "oc", } m["oc-jud"] = { "Shuadit", 56472, "oc", aliases = { "Chouhadite", "Chouhadit", "Chouadite", "Chouadit", "Shuhadit", "Judeo-Occitan", "Judæo-Occitan", "Judaeo-Occitan", "Judeo-Provençal", "Judæo-Provençal", "Judaeo-Provençal", "Judeo-Provencal", "Judaeo-Provencal", "Judeo-Comtadin", "Judæo-Comtadin", "Judaeo-Comtadin", }, pseudo_families = "qfa-jew", } ----------------------------------------------------- -- Portuguese and derived creole varieties -- ----------------------------------------------------- -- Portuguese m["pt-BR"] = { "Brazilian Portuguese", 750553, "pt", } m["pt-PT"] = { "European Portuguese", 922399, "pt", } -- Kabuverdianu (Cape Verde Creole, Cape Verdean Creole) m["kea-bar"] = { "Barlavento Kabuverdianu", 2217638, "kea", aliases = {"Barlavento", "Barlavento Creole", "Sampadjudu"}, } m["kea-bvi"] = { "Boa Vista Kabuverdianu", 16501837, "kea-bar", aliases = {"Boa Vista Creole"}, } m["kea-sal"] = { "Sal Kabuverdianu", 18707467, "kea-bar", aliases = {"Sal Creole"}, } m["kea-saa"] = { "Santo Antão Kabuverdianu", 18707472, "kea-bar", aliases = {"Santo Antão Creole"}, } m["kea-sni"] = { "São Nicolau Kabuverdianu", 18707549, "kea-bar", aliases = {"São Nicolau Creole"}, } m["kea-svi"] = { "São Vicente Kabuverdianu", 18707550, "kea-bar", aliases = {"São Vicente Creole"}, } m["kea-sot"] = { "Sotavento Kabuverdianu", 10261559, "kea", aliases = {"Sotavento", "Sotavento Creole", "Badiu"}, } m["kea-bra"] = { "Brava Kabuverdianu", 18670181, "kea-sot", aliases = {"Brava Creole"}, } m["kea-fog"] = { "Fogo Kabuverdianu", 18706861, "kea-sot", aliases = {"Fogo Creole"}, } m["kea-mai"] = { "Maio Kabuverdianu", 18707286, "kea-sot", aliases = {"Maio Creole"}, } m["kea-san"] = { "Santiago Kabuverdianu", 35117, "kea-sot", aliases = {"Santiago Creole"}, } m["kea-alu"] = { "ALUPEC Kabuverdianu", 375704, "kea", aliases = {"ALUPEC", "Alfabeto Unificado para a Escrita do Cabo-Verdiano"}, } ----------------------------------------------------- -- Rhaeto-Romance varieties -- ----------------------------------------------------- -- Friulian varieties m["fur-old"] = { "Old Friulian", nil, "fur", } -- Ladin varieties m["lld-amp"] = { "Ampezan Ladin", 25617466, "lld", aliases = {"Anpezan", "Ampezan", "Ampezzan", "Ampezzano"}, } m["lld-bad"] = { "Badiot Ladin", 3706562, "lld", aliases = {"Badiot", "Badioto", "Badiotto"}, } m["lld-cad"] = { "Cadorino Ladin", 3706570, "lld", aliases = {"Cadorino"}, } m["lld-fas"] = { "Fascian Ladin", 742627, "lld", aliases = {"Fascian", "Fassano"}, } m["lld-fod"] = { "Fodom Ladin", 3706605, "lld", aliases = {"Fodom", "Livinallese"}, } m["lld-for"] = { "Fornes Ladin", 5470374, "lld", aliases = {"Fornes"}, } m["lld-ghe"] = { "Gherdëina Ladin", 3706597, "lld", aliases = {"Gherdëina", "Gardenese", "Val Gardena"}, } m["lld-non"] = { "Nones Ladin", 1055027, "lld", aliases = {"Nones", "Noneso"}, } -- Romansh varieties m["rm-old"] = { "Old Romansh", nil, "rm", } m["rm-put"] = { "Puter Romansh", 688309, "rm", aliases = {"Puter", "Putèr", "Upper Engadine", "rm-puter"}, } m["rm-srm"] = { "Surmiran Romansh", 690216, "rm", aliases = {"Surmiran", "rm-surmiran", "Surmiran-Albula", -- Glottolog }, } m["rm-srs"] = { "Sursilvan Romansh", 688348, "rm", aliases = {"Sursilvan", "rm-sursilv"}, } m["rm-sut"] = { "Sutsilvan Romansh", 688272, "rm", aliases = {"Sutsilvan", "rm-sutsilv"}, varieties = {"Scharans Sutsilvan"}, -- per Glottolog } m["rm-val"] = { "Vallader Romansh", 690226, "rm", aliases = {"Vallader", "Putèr", "Lower Engadine", "rm-vallader"}, } m["rm-gri"] = { "Rumantsch Grischun", 688873, "rm", aliases = {"rm-rumgr"}, } ----------------------------------------------------- -- Sardinian varieties -- ----------------------------------------------------- m["sc-old"] = { "Old Sardinian", nil, "sc", } m["sc-src"] = { "Logudorese", 777974, "sc", aliases = {"Logudorese Sardinian"}, } m["sc-nuo"] = { "Nuorese", nil, "sc-src", aliases = {"Nuorese Sardinian"}, } m["sc-sro"] = { "Campidanese", 35348, "sc", aliases = {"Campidanese Sardinian"}, } ----------------------------------------------------- -- Spanish varieties -- ----------------------------------------------------- m["es-ear"] = { "Early Modern Spanish", 5364419, "es", } m["es-AR"] = { "Rioplatense Spanish", 509780, "es", } m["es-BO"] = { "Bolivian Spanish", 510730, "es", } m["es-CL"] = { "Chilean Spanish", 857295, "es", } m["es-CO"] = { "Colombian Spanish", 1115875, "es", } m["es-CU"] = { "Cuban Spanish", 824909, "es", } m["es-MX"] = { "Mexican Spanish", 616620, "es", } m["es-PE"] = { "Peruvian Spanish", 736236, "es", } m["es-PH"] = { "Philippine Spanish", 22091406, "es", } m["es-US"] = { "United States Spanish", 2301077, "es", aliases = {"US Spanish"}, } --use label "US Spanish" to put Spanish terms in this category m["es-PR"] = { "Puerto Rican Spanish", 7258609, "es", } m["es-VE"] = { "Venezuelan Spanish", 840017, "es", } m["es-lun"] = { "Lunfardo", 1401612, "es", } ---------------------------------------------------------------------------------------------------------------------- -- Japonic varieties -- ---------------------------------------------------------------------------------------------------------------------- -- Japanese varieties m["ja-mid"] = { "Middle Japanese", 6841474, "ojp", ancestors = "ojp", } m["ja-mid-ear"] = { "Early Middle Japanese", 182695, "ja-mid", } m["ja-mid-lat"] = { "Late Middle Japanese", 1816184, "ja-mid", ancestors = "ja-mid-ear", } m["ja-ear"] = { "Early Modern Japanese", 5326692, "ja", ancestors = "ja-mid-lat", } m["ojp-eas"] = { "Eastern Old Japanese", 65247957, "ojp", } m["ja-cla"] = { "Classical Japanese", 1332057, "ja", -- FIXME: This is redundant because Classical Japanese is considered a child of (Modern) Japanese, which has ja-mid-ear -- (as well as ja-mid-lat) as ancestors. However, the intent here is that the *direct* ancestor of ja-cla is ja-mid-ear -- and ja-mid-lat is not an ancestor. Need to rethink ancestor handling. -- ancestors = "ja-mid-ear", } ---------------------------------------------------------------------------------------------------------------------- -- Koreanic varieties -- ---------------------------------------------------------------------------------------------------------------------- -- Korean varieties m["oko-lat"] = { "Late Old Korean", nil, "oko", } m["okm-ear"] = { "Early Middle Korean", nil, "okm", } m["ko-cen"] = { "Central Korean", nil, "ko", } m["ko-gyg"] = { "Gyeonggi Korean", 485492, "ko-cen", aliases = {"Seoul Korean"}, } m["ko-chu"] = { "Chungcheong Korean", 625800, "ko-cen", aliases = {"Hoseo Korean"}, } m["ko-hwa"] = { "Hwanghae Korean", 16183706, "ko-cen", } m["ko-gan"] = { "Gangwon Korean", 11260444, "ko-cen", aliases = {"Yeongdong Korean"}, } m["ko-gys"] = { "Gyeongsang Korean", 488002, "ko", aliases = {"Southeastern Korean"}, } m["ko-jeo"] = { "Jeolla Korean", 11250166, "ko", aliases = {"Southwestern Korean"}, } m["ko-pyo"] = { "Pyongan Korean", 7263142, "ko", aliases = {"Northwestern Korean"}, } m["ko-ham"] = { "Hamgyong Korean", 860702, "ko", aliases = {"Northeastern Korean"}, } m["ko-yuk"] = { "Yukjin Korean", 16171275, "ko", aliases = {"Yukchin Korean", "Ryukjin Korean", "Ryukchin Korean"}, } ---------------------------------------------------------------------------------------------------------------------- -- Mongolic varieties -- ---------------------------------------------------------------------------------------------------------------------- m["xng-ear"] = { "Early Middle Mongol", nil, "xng", } m["xng-lat"] = { "Late Middle Mongol", nil, "xng", ancestors = "xng-ear", } m["mn-kha"] = { "Khalkha Mongolian", 6399808, "mn", aliases = {"Khalkha"}, } m["mn-ord"] = { "Ordos Mongolian", 716904, "mn", aliases = {"Ordos"}, } m["mn-cha"] = { "Chakhar Mongolian", 907425, "mn", aliases = {"Chakhar"}, } m["mn-khr"] = { "Khorchin Mongolian", 3196210, "mn", aliases = {"Khorchin"}, } ---------------------------------------------------------------------------------------------------------------------- -- Niger-Congo varieties -- ---------------------------------------------------------------------------------------------------------------------- ----------------------------------------------------- -- Akan varieties -- ----------------------------------------------------- m["tw"] = { "Twi Akan", 36850, "ak", aliases = {"Twi"}, } m["abr"] = { "Abron", 34831, "tw", aliases = {"Brong", "Bono", "Bono Twi"}, } m["tw-asa"] = { "Asante Twi", 19261685, "tw", aliases = {"Asante", "Ashanti", "Ashante"}, } m["tw-aku"] = { "Akuapem Twi", 31150449, "tw", aliases = {"Akuapem", "Akuapim", "Akwapem Twi", "Akwapi"}, } m["fat"] = { "Fante Akan", 35570, "ak", aliases = {"Fante", "Fanti", "Fantse", "Mfantse"}, } m["wss"] = { "Wasa", 36914, "ak", } -- creole m["alv-kro"] = { "Kromanti", 1093206, "crp-mar", } ----------------------------------------------------- -- Bantu varieties -- ----------------------------------------------------- m["bnt-cmn"] = { "Common Bantu", nil, "bnt-pro", } m["xh-bha"] = { "Bhaca", 4900493, "xh", aliases = {"isiBhaca", "IsiBhaca"}, } -- Rwanda-Rundi varieties m["rw-kin"] = { "Kinyarwanda", 33573, "rw", aliases = {"Rwanda"}, } m["rw-run"] = { "Kirundi", 33583, "rw", aliases = {"Rundi"}, } ----------------------------------------------------- -- Fula varieties -- ----------------------------------------------------- m["fuc"] = { "Pulaar", 1420205, "ff", } m["fuf"] = { "Pular", 3915357, "ff", } m["ffm"] = { "Maasina Fulfulde", 3915322, "ff", } m["fue"] = { -- no enwiki entry as of yet but frwiki and pmswiki have one "Borgu Fulfulde", 12952426, "ff", } m["fuh"] = { -- no enwiki entry as of yet but frwiki and pmswiki have one "Western Niger Fulfulde", 12952430, "ff", } m["fuq"] = { -- no enwiki entry as of yet but frwiki, hrwiki and pmswiki have one "Central-Eastern Niger Fulfulde", 12628799, "ff", } m["fuv"] = { -- no enwiki entry as of yet but dewiki, frwiki, hrwiki, pmswiki and swwiki have one "Nigerian Fulfulde", 36129, "ff", } m["fub"] = { -- no enwiki entry as of yet but dewiki, frwiki, hrwiki, pmswiki, ptwiki, swwiki and yowiki have one "Adamawa Fulfulde", 34776, "ff", } m["fui"] = { -- no enwiki entry as of yet but pmswiki and swwiki have one "Bagirmi Fulfulde", 11003859, "ff", } ---------------------------------------------------------------------------------------------------------------------- -- Papuan varieties -- ---------------------------------------------------------------------------------------------------------------------- m["kze"] = { "Kosena", 12952663, "auy", } m["ont"] = { "Ontenu", 3352827, "gaj", aliases = {"Ontena"}, } ---------------------------------------------------------------------------------------------------------------------- -- Salishan varieties -- ---------------------------------------------------------------------------------------------------------------------- m["lut-nor"] = { "Northern Lushootseed", nil, "lut", aliases = {"Northern Puget Sound Salish"}, } m["slh"] = { "Southern Lushootseed", 7997684, "lut", aliases = {"Southern Puget Sound Salish", "Twulshootseed", "Whulshootseed"}, } m["ska"] = { "Skagit", 12642471, "lut-nor", } m["sno"] = { "Snohomish", 25559662, "lut-nor", } ---------------------------------------------------------------------------------------------------------------------- -- Sino-Tibetan varieties -- ---------------------------------------------------------------------------------------------------------------------- m["tbq-pro"] = { "Proto-Tibeto-Burman", 7251864, "sit-pro", } ----------------------------------------------------- -- Chinese varieties -- ----------------------------------------------------- ------------- Old Chinese, Middle Chinese ------------- m["och-ear"] = { "Early Old Chinese", nil, "och", } m["och-lat"] = { "Late Old Chinese", nil, "och", } m["ltc-ear"] = { "Early Middle Chinese", nil, "ltc", } m["ltc-lat"] = { "Late Middle Chinese", nil, "ltc", } ------------- Classical/Literary varieties ------------- -- FIXME: Temporary. m["lzh-shi"] = { "Traditional Chinese poetry", 1759242, "lzh", } -- FIXME: Temporary. m["lzh-cii"] = { "Ci", 1091366, "lzh", } -- FIXME: Temporary. m["lzh-yue"] = { "Classical Cantonese", nil, "lzh", } -- FIXME: Temporary. m["lzh-cmn"] = { "Classical Mandarin", nil, "lzh", } -- FIXME: Temporary. m["lzh-tai"] = { "Classical Taishanese", nil, "lzh", } -- FIXME: Temporary. m["lzh-cmn-TW"] = { "Classical Taiwanese Mandarin", nil, "lzh-cmn", } -- FIXME: Temporary. m["lzh-VI"] = { "Vietnamese Classical Chinese", 17034227, "lzh", } -- FIXME: Temporary. m["lzh-KO"] = { "Korean Classical Chinese", 10496257, "lzh", ietf_subtag = "lzh-KR" -- KR = South Korea, as there is no code for Korea as a whole } -- FIXME: Temporary. m["lzh-lit"] = { "Literary Chinese", nil, "lzh", } -- FIXME: Temporary. FIXME: Do we need this? How does it differ from Old Chinese? m["lzh-pre"] = { "Pre-Classical Chinese", nil, "lzh", } ------------- Written Vernacular varieties ------------- -- FIXME: Temporary. m["cmn-wvc"] = { "Written vernacular Mandarin", 783605, "cmn", } -- FIXME: Temporary. FIXME: How does this differ from "Literary Cantonese"? m["yue-wvc"] = { "Written vernacular Cantonese", nil, "yue", } -- FIXME: Temporary. m["zhx-tai-wvc"] = { "Written vernacular Taishanese", nil, "zhx-tai", } ------------- Mandarin varieties ------------- -- FIXME: Temporary. NOTE: The Linguist List assigns the "w:Beijing dialect" (Wikidata 1147606) the code "cmn-bej" and -- the larger "w:Beijing Mandarin (division of Mandarin)" dialect group (Wikidata 2169652; what we call "Beijingic -- Mandarin", after Glottolog) the code "cmn-bei". m["cmn-bei"] = { "Beijing Mandarin", 1147606, "cmn-bec", } -- FIXME: Temporary. m["cmn-bec"] = { "Beijingic Mandarin", 2169652, "cmn", } -- FIXME: Temporary. NOTE: The Linguist List uses the code cmn-zho. m["cmn-cep"] = { "Central Plains Mandarin", 3048775, "cmn", aliases = {"Zhongyuan Mandarin"}, } m["cmn-ear"] = { "Early Mandarin", 837169, "cmn", ancestors = "ltc", } -- FIXME: Temporary. m["cmn-gua"] = { "Guanzhong Mandarin", 3431648, "cmn-cep", } -- FIXME: Temporary. Appears to be a subdialect of Guiliu Mandarin, which in turn is a subdialect of Southwestern Mandarin. m["cmn-gui"] = { "Guilin Mandarin", 11111636, "cmn-sow", } m["cmn-jhu"] = { "Jianghuai Mandarin", 2128953, "cmn", aliases = {"Lower Yangtze Mandarin"}, } -- FIXME: Temporary. m["cmn-lan"] = { "Lanyin Mandarin", 662754, "cmn", } -- FIXME: Temporary. m["cmn-MY"] = { "Malaysian Mandarin", 13646143, "cmn", } -- FIXME: Temporary. m["cmn-nan"] = { "Nanjing Mandarin", 2681098, "cmn-jhu", } -- FIXME: Temporary. m["cmn-noe"] = { "Northeastern Mandarin", 1064504, "cmn", } -- FIXME: Temporary. m["cmn-PH"] = { "Philippine Mandarin", 7185155, "cmn", } -- FIXME: Temporary. m["cmn-SG"] = { "Singapore Mandarin", 1048980, "cmn", } -- FIXME: Temporary. m["cmn-sow"] = { "Southwestern Mandarin", 2609239, "cmn", } -- FIXME: Temporary. Appears to be a subdialect of Jilu Mandarin. m["cmn-tia"] = { "Tianjin Mandarin", 7800220, "cmn", } -- FIXME: Temporary. NOTE: Wikidata also has Q4380827 "Taiwanese Mandarin", defined as "rare dialect of Standard Chinese -- (Mandarin) used in Taiwan, which is strongly influenced by Taiwanese Hokkien; mostly used by elderlies" and having no -- English Wikipedia article (but see w:zh:臺灣國語). m["cmn-TW"] = { "Taiwanese Mandarin", 262828, "cmn", } -- FIXME: Temporary. Appears to be a subdialect of Wu-Tian Mandarin, in turn a subdialect of Southwestern Mandarin. -- Given the code cmn-xwu in the Linguist List. m["cmn-wuh"] = { "Wuhan Mandarin", 11124731, "cmn-sow", aliases = {"Wuhanese"}, } -- FIXME: Temporary. Appears to be a subdialect of Lanyin Mandarin. m["cmn-xin"] = { "Xining Mandarin", nil, "cmn-lan", } -- FIXME: Temporary. m["cmn-yan"] = { "Yangzhou Mandarin", nil, "cmn-jhu", } ------------- Cantonese varieties ------------- -- FIXME: Temporary. m["yue-gua"] = { "Guangzhou Cantonese", nil, "yue", } -- FIXME: Temporary. Given the codes yue-yue or yue-can in the Linguist List. m["yue-HK"] = { "Hong Kong Cantonese", 5894342, "yue", } -- FIXME: Temporary. FIXME: How does this differ from "Written vernacular Cantonese"? m["yue-lit"] = { "Literary Cantonese", 2472605, "yue", } ------------- Wu varieties ------------- m["wuu-han"] = { "Hangzhounese", 5648144, "wuu", } m["wuu-nin"] = { "Ningbonese", 3972199, "wuu", } -- FIXME: Temporary. m["wuu-nor"] = { "Northern Wu", 7675988, "wuu", aliases = {"Taihu Wu"}, } -- FIXME: Temporary? Subvariety of Taihu Wu. NOTE: "chm" stands for Chongming, the main dialect, to avoid a conflict -- with Shanghainese. m["wuu-chm"] = { "Shadi Wu", 6112340, "wuu-nor", } m["wuu-sha"] = { "Shanghainese", 36718, "wuu-nor", } m["wuu-suz"] = { "Suzhounese", 831744, "wuu-nor", } -- FIXME: Temporary. May be converted into a full language and/or split. m["wuu-wen"] = { "Wenzhounese", 710218, "wuu", } ------------- Xiang varieties ------------- m["hsn-lou"] = { "Loudi Xiang", 10943823, "hsn-old", } m["hsn-hya"] = { "Hengyang Xiang", 20689035, "hsn-hzh", } m["hsn-hzh"] = { "Hengzhou Xiang", nil, "hsn", } m["hsn-new"] = { "New Xiang", 7012696, "hsn", aliases = {"Chang-Yi"}, } m["hsn-old"] = { "Old Xiang", 7085453, "hsn", aliases = {"Lou-Shao"}, } ------------- Hakka varieties ------------- -- FIXME: Temporary. m["hak-dab"] = { "Dabu Hakka", 19855566, "hak", -- formerly hak-TW but seems to be spoken primary in Dabu County in Guangdong } -- FIXME: Temporary. m["hak-eam"] = { "Early Modern Hakka", nil, "hak", } -- FIXME: Temporary. m["hak-hai"] = { "Hailu Hakka", 17038519, "hak", -- often considered a Taiwanese lect but also spoken in [[Shanwei]], [[Guangdong]] } -- FIXME: Temporary. m["hak-HK"] = { "Hong Kong Hakka", 2675834, "hak", } -- FIXME: Temporary. m["hak-hui"] = { "Huiyang Hakka", 16873881, "hak", } -- FIXME: Temporary. m["hak-hui-MY"] = { "Malaysian Huiyang Hakka", nil, "hak-hui", } -- FIXME: Temporary. Similar to and possibly the parent of Sixian Hakka in Taiwan. m["hak-mei"] = { "Meixian Hakka", 839295, "hak", aliases = {"Moiyan Hakka", "Meizhou Hakka"}, } -- FIXME: Temporary. m["hak-six"] = { "Sixian Hakka", 9668261, "hak-TW", } -- FIXME: Temporary. m["hak-TW"] = { "Taiwanese Hakka", 2391532, "hak", } -- FIXME: Temporary. m["hak-zha"] = { "Zhao'an Hakka", 6703311, "hak", aliases = {"Zhangzhou Hakka"}, } -- Southern Min varieties -- m["nan-anx"] = { "Anxi Hokkien", 97064149, "nan-qua", } m["nan-cha"] = { "Changtai Hokkien", nil, "nan-zha", } m["nan-hou"] = { "Houlu Min", 19855492, "nan-dat", } m["nan-hui"] = { "Hui'an Hokkien", 16241797, "nan-qua", } m["nan-jin"] = { "Jinjiang Hokkien", 11089375, "nan-qua", } m["nan-kin"] = { "Kinmenese Hokkien", 56278342, "nan-xia", aliases = {"Kinmen Hokkien"}, } m["nan-med"] = { "Medan Hokkien", 6805114, "nan-zha", } m["nan-pen"] = { "Penang Hokkien", 11120689, "nan-zha", } m["nan-hbl-PH"] = { "Philippine Hokkien", 3236692, "nan-qua", } m["nan-qia"] = { "Qianlu Min", 19842517, "nan-dat", } m["nan-qua"] = { "Quanzhou Hokkien", 2251677, "nan-hbl", aliases = {"Chinchew", "Choanchew"}, } -- FIXME: Temporary? Derived from both Quanzhou and Zhangzhou Hokkien. m["nan-hbl-SG"] = { "Singapore Hokkien", 3846528, "nan-hbl", } m["nan-spm"] = { "Southern Malaysian Hokkien", 7570322, "nan-qua", aliases = {"Southern Malaysia Hokkien", "Southern Peninsular Malaysian Hokkien", "Southern Peninsular Malaysia Hokkien"} } m["nan-hbl-TW"] = { "Taiwanese Hokkien", 36778, "nan-hbl", } m["nan-ton"] = { "Tong'an Hokkien", nil, "nan-xia", } m["nan-xia"] = { "Xiamen Hokkien", 68744, "nan-hbl", aliases = {"Amoy", "Amoyese", "Amoynese", "Xiamenese"}, } m["nan-yon"] = { "Yongchun Hokkien", 65118728, "nan-qua", } m["nan-zha"] = { "Zhangzhou Hokkien", 8070492, "nan-hbl", aliases = {"Changchew", "Chiangchew", "Changchow"}, } m["nan-zho"] = { "Zhao'an Hokkien", 65118728, "nan-zha", aliases = {"Zhao'an", "Chawan", "Chawan Hokkien"}, } m["nan-zhp"] = { "Zhangping Hokkien", 15937822, "nan-zha", } ------------- Other Min varieties ------------- -- FIXME: Temporary. Affiliation within Min uncertain; some combination of Eastern and Southern. m["zhx-zho"] = { "Zhongshan Min", 8070958, "zh", } ------------- Other Chinese varieties ------------- -- FIXME: Temporary. Affiliation within Chinese uncertain; possibly Yue. m["zhx-dan"] = { "Danzhou Chinese", 2578935, "zh", } ------------- Chinese romanization varieties ------------- -- [[Wiktionary:Information desk/2022/June#Etymology Coding Issue]] -- [[Wiktionary:Grease pit/2022/June#Transliteration Systems in Etymologies 2]] m["cmn-pinyin"] = { "Hanyu Pinyin", 42222, "cmn", aliases = {"Pinyin"}, } m["cmn-tongyong"] = { "Tongyong Pinyin", 700739, "cmn", } m["cmn-wadegiles"] = { "Wade–Giles", 208442, "cmn", aliases = {"Wade-Giles", "Wade Giles"}, } m["zh-postal"] = { "Postal Romanization", 151868, "zh", } -- Chinese cyrillization m["cmn-palladius"] = { "Palladius", 1234239, "cmn", aliases = {"Palladius system"}, } ----------------------------------------------------- -- Tibetic varieties -- ----------------------------------------------------- m["adx"] = { "Amdo Tibetan", 56509, "bo", } m["kbg"] = { "Khamba", 12952626, "bo", } m["khg"] = { "Khams Tibetan", 56601, "bo", } m["tsk"] = { "Tseku", 11159532, "bo", } ---------------------------------------------------------------------------------------------------------------------- -- Tai-Kadai varieties -- ---------------------------------------------------------------------------------------------------------------------- m["th-old"] = { "Old Thai", nil, "tai-swe-pro", wikipedia_article = "Thai language#Old Thai", } m["th-suk"] = { "Sukhothai Old Thai", -- 1238-1438. Cannot use "Sukhothai Thai" as Sukhothai is the current city and "Sukhothai Thai" is a lect. nil, "th-old", aliases = {"Sukhothai Siamese"}, wikipedia_article = "Thai language#Old Thai", } m["th-ayu"] = { "Ayutthaya Old Thai", -- 1351-1767. Cannot use "Ayutthaya Thai" as Ayutthaya is the current city. nil, "th-old", aliases = {"Ayutthaya Siamese"}, wikipedia_article = "Thai language#Old Thai", } --[[ m["th-new"] = { "Hacked Thai", -- temporary for testing new translit/display methods nil, "th", translit = "User:Benwing2/th-scraping-translit", display_text = "User:Benwing2/th-scraping-translit", strip_diacritics = "User:Benwing2/th-scraping-translit", preprocess_links = "User:Benwing2/th-scraping-translit", } ]] m["tai-shz"] = { "Shangsi Zhuang", 13216, "za", } ---------------------------------------------------------------------------------------------------------------------- -- Turkic varieties -- ---------------------------------------------------------------------------------------------------------------------- m["trk-cmn-pro"] = { "Proto-Common Turkic", 1126028, "trk-pro", } m["trk-ogr-pro"] = { "Proto-Oghur", 1422731, "trk-pro", family = "trk-ogr", } m["trk-bul-pro"] = { "Proto-Bulgar", nil, "trk-ogr-pro", } m["trk-ogz-pro"] = { "Proto-Oghuz", 494600, "trk-pro", family = "trk-ogz", aliases = {"Southwestern Common Turkic"}, } m["crh-dbj"] = { "Dobrujan Tatar", 12811566, "crh", aliases = {"Romanian Tatar"}, } m["cv-ana"] = { "Anatri Chuvash", nil, "cv", aliases = {"Anatri", "Lower Chuvash"}, } m["cv-mid"] = { "Middle Chuvash", nil, "cv", ancestors = "cv-old", } m["cv-old"] = { "Old Chuvash", nil, "cv", ancestors = "xbo-vol", } m["cv-vir"] = { "Viryal Chuvash", 4278332, "cv", aliases = {"Viryal", "Upper Chuvash"}, } m["kjh-fyu"] = { "Fuyu Kyrgyz", 2598963, "kjh", aliases = {"Fuyu Kirgiz", "Fuyu Kirghiz", "Manchurian Kyrgyz", "Manchurian Kirgiz", "Manchurian Kirghiz"}, } m["klj-arg"] = { "Arghu", 33455, "klj", ancestors = "trk-cmn-pro", } m["otk-kir"] = { "Old Kirghiz", 83142, "otk", aliases = {"Yenisei Turkic", "Yenisei Kyrgyz"}, } m["otk-ork"] = { "Orkhon Turkic", 31295480, "otk", } m["qwm-cum"] = { "Cuman", 1075050, "qwm", aliases = {"Kuman", "Polovtsian", "Polovcian"}, } m["qwm-arm"] = { "Armeno-Kipchak", 2027503, "qwm", ancestors = "qwm-cum", aliases = {"Xıpçaχ tili", "Tatarça"}, } m["qwm-mam"] = { "Mamluk-Kipchak", 4279942, "qwm", aliases = {"Mameluk-Kipchak"}, } m["az-cls"] = { "Classical Azerbaijani", nil, "az", aliases = {"Classical Azeri"}, } m["qxq"] = { "Qashqai", 13192, "az", aliases = {"Qaşqay", "Qashqayi", "Kashkai", "Kashkay"}, } m["tr-CY"] = { "Cypriot Turkish", 7917392, "tr", } m["uz-afg"] = { -- NOTE: has ISO 639-3 code uzs assigned to it. "Afghan Uzbek", 1066787, "uz", aliases = {"Southern Uzbek"}, translit = "uz-afg-translit", } m["xbo-dan"] = { "Danube Bulgar", nil, "xbo", } m["xbo-vol"] = { "Volga Bulgar", nil, "xbo", } ---------------------------------------------------------------------------------------------------------------------- -- Uralic varieties -- ---------------------------------------------------------------------------------------------------------------------- m["fiu-pro"] = { "Proto-Finno-Ugric", 79890, "urj-pro", } m["urj-fpr-pro"] = { "Proto-Finno-Permic", nil, "urj-pro", } m["krl-nor"] = { "North Karelian", 125501196, "krl", } m["krl-sou"] = { "South Karelian", 129812730, "krl", } m["mns-eas"] = { "Eastern Mansi", 30311755, "mns-cen", } m["mns-wes"] = { "Western Mansi", 30311756, "mns-cen", } ---------------------------------------------------------------------------------------------------------------------- -- Yeneseian varieties -- ---------------------------------------------------------------------------------------------------------------------- m["qfa-yke-pro"] = { "Proto-Ketic", nil, "qfa-yen-pro", family = "qfa-yke", } m["qfa-yko-pro"] = { "Proto-Kottic", nil, "qfa-yen-pro", family = "qfa-yko", } m["qfa-yrn-pro"] = { "Proto-Arinic", nil, "qfa-yen-pro", family = "qfa-yrn", } m["qfa-ypm-pro"] = { "Proto-Pumpokolic", nil, "qfa-yen-pro", family = "qfa-ypm", } ---------------------------------------------------------------------------------------------------------------------- -- Miscellaneous varieties -- ---------------------------------------------------------------------------------------------------------------------- m["mul-tax"] = { "taxonomic name", 522190, "mul", } ----------------------------------------------------- -- Elamite varieties -- ----------------------------------------------------- m["elx-old"] = { "Old Elamite", nil, "elx", } m["elx-mid"] = { "Middle Elamite", nil, "elx", } m["elx-neo"] = { "Neo-Elamite", nil, "elx", } m["elx-ach"] = { "Achaemenid Elamite", nil, "elx", } ----------------------------------------------------- -- Substrates -- ----------------------------------------------------- -- Pre-Roman substrates m["qsb-ibe"] = { "Paleo-Hispanic", 246801, "und", family = "qfa-sub", aliases = {"Palaeo-Hispanic", "Paleohispanic", "Palaeohispanic", "Paleo-Iberian", "Palaeo-Iberian"}, } m["qsb-bal"] = { "Paleo-Balkan", 1815070, "und", family = "qfa-sub", aliases = {"Palaeo-Balkan", "Paleobalkan", "Palaeobalkan"}, } m["xaq"] = { "Aquitanian", 500522, "euq-pro", family = "euq", } return require("Module:languages").finalizeData(m, "language", true) 83dn29jlgbktzhj3fbjqygqjhl86u5c 828 5988 17425 2026-07-13T08:39:04Z Hiyuune 6766 + 17425 Scribunto text/plain local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared local m = {} m["aav-khs-pro"] = { "Proto-Khasian", 116773216, "aav-khs", "Latn", type = "reconstructed", } m["aav-nic-pro"] = { "Proto-Nicobarese", 116773793, "aav-nic", "Latn", type = "reconstructed", } m["aav-pkl-pro"] = { "Proto-Pnar-Khasi-Lyngngam", 116773259, "aav-pkl", "Latn", type = "reconstructed", } m["aav-pro"] = { -- mkh-pro will merge into this "Proto-Austroasiatic", 116773186, "aav", "Latn", type = "reconstructed", } m["afa-pro"] = { "Proto-Afroasiatic", 269125, "afa", "Latn", type = "reconstructed", } m["alg-aga"] = { "Agawam", nil, "alg-eas", "Latn", } m["alg-pro"] = { "Proto-Algonquian", 7251834, "alg", "Latn", type = "reconstructed", sort_key = {remove_diacritics = "·"}, } m["alv-ama"] = { "Amasi", 4740400, "nic-grs", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.macron}, } m["alv-bgu"] = { "Bainouk Gubeeher", 17002646, "alv-bny", "Latn", } m["alv-bua-pro"] = { "Proto-Bua", 116773723, "alv-bua", "Latn", type = "reconstructed", } m["alv-cng-pro"] = { "Proto-Cangin", 116773726, "alv-cng", "Latn", type = "reconstructed", } m["alv-edo-pro"] = { "Proto-Edoid", 116773206, "alv-edo", "Latn", type = "reconstructed", } m["alv-fli-pro"] = { "Proto-Fali", 116773754, "alv-fli", "Latn", type = "reconstructed", } m["alv-gbe-pro"] = { "Proto-Gbe", 116773208, "alv-gbe", "Latn", type = "reconstructed", } m["alv-gng-pro"] = { "Proto-Guang", 116773757, "alv-gng", "Latn", type = "reconstructed", } m["alv-gtm-pro"] = { "Proto-Central Togo", 116773732, "alv-gtm", "Latn", type = "reconstructed", } m["alv-gwa"] = { "Gwara", 16945580, "nic-pla", "Latn", } m["alv-hei-pro"] = { "Proto-Heiban", 116773760, "alv-hei", "Latn", type = "reconstructed", } m["alv-ido-pro"] = { "Proto-Idomoid", 116773764, "alv-ido", "Latn", type = "reconstructed", } m["alv-igb-pro"] = { "Proto-Igboid", 116773765, "alv-igb", "Latn", type = "reconstructed", } m["alv-kwa-pro"] = { "Proto-Kwa", 116773780, "alv-kwa", "Latn", type = "reconstructed", } m["alv-mum-pro"] = { "Proto-Mumuye", 116773791, "alv-mum", "Latn", type = "reconstructed", } m["alv-nup-pro"] = { "Proto-Nupoid", 116773795, "alv-nup", "Latn", type = "reconstructed", } m["alv-pro"] = { "Proto-Atlantic-Congo", 116732838, "alv", "Latn", type = "reconstructed", } m["alv-edk-pro"] = { "Proto-Edekiri", nil, "alv-edk", "Latn", type = "reconstructed", } m["alv-yor-pro"] = { "Proto-Yoruba", nil, "alv-yor", "Latn", type = "reconstructed", } m["alv-yrd-pro"] = { "Proto-Yoruboid", 116773824, "alv-yrd", "Latn", type = "reconstructed", } m["alv-von-pro"] = { "Proto-Volta-Niger", 116773820, "alv-von", "Latn", type = "reconstructed", } m["apa-pro"] = { "Proto-Apachean", 116773135, "apa", "Latn", type = "reconstructed", } m["aql-pro"] = { "Proto-Algic", 18389588, "aql", "Latn", type = "reconstructed", sort_key = {remove_diacritics = "·"}, } m["art-adu"] = { "Adûni", 1232159, "art", "Latn", type = "appendix-constructed", } m["art-bel"] = { "Belter Creole", 108055510, "art", "Latn", type = "appendix-constructed", sort_key = { remove_diacritics = c.acute, from = {"ɒ"}, to = {"a"}, }, } m["art-blk"] = { "Bolak", 2909283, "art", "Latn", type = "appendix-constructed", } m["art-bsp"] = { "Black Speech", 686210, "art", "Latn, Teng", type = "appendix-constructed", } m["art-com"] = { "Communicationssprache", 35227, "art", "Latn", type = "appendix-constructed", } m["art-dtk"] = { "Dothraki", 2914733, "art", "Latn", type = "appendix-constructed", } m["art-elo"] = { "Eloi", nil, "art", "Latn", type = "appendix-constructed", } m["art-gld"] = { "Goa'uld", 19823, "art", "Latn, Egyp, Mero", type = "appendix-constructed", } m["art-lap"] = { "Lapine", 6488195, "art", "Latn", type = "appendix-constructed", } m["art-man"] = { "Mandalorian", 54289, "art", "Latn", type = "appendix-constructed", } m["art-mun"] = { "Mundolinco", 851355, "art", "Latn", type = "appendix-constructed", } m["art-nav"] = { "Naʼvi", 316939, "art", "Latn", type = "appendix-constructed", } m["art-vlh"] = { "High Valyrian", 64483808, "art", "Latn", type = "appendix-constructed", } m["ath-nic"] = { "Nicola", 20609, "ath-nor", "Latn", } m["ath-pro"] = { "Proto-Athabaskan", 104841722, "ath", "Latn", type = "reconstructed", } m["auf-pro"] = { "Proto-Arawa", 116773706, "auf", "Latn", type = "reconstructed", } m["aus-alu"] = { "Alungul", 16827670, "aus-pmn", "Latn", } m["aus-and"] = { "Andjingith", 4754509, "aus-pmn", "Latn", } m["aus-ang"] = { "Angkula", 16828520, "aus-pmn", "Latn", } m["aus-arn-pro"] = { "Proto-Arnhem", 116773720, "aus-arn", "Latn", type = "reconstructed", } m["aus-bra"] = { "Barranbinya", 4863220, "aus-pmn", "Latn", } m["aus-brm"] = { "Barunggam", 4865914, "aus-pmn", "Latn", } m["aus-cww-pro"] = { "Proto-Central New South Wales", 116773199, "aus-cww", "Latn", type = "reconstructed", } m["aus-dal-pro"] = { "Proto-Daly", 116773743, "aus-dal", "Latn", type = "reconstructed", } m["aus-guw"] = { "Guwar", 6652138, "aus-pam", "Latn", } m["aus-lsw"] = { "Little Swanport", 6652138, "qfa-unc", "Latn", } m["aus-mbi"] = { "Mbiywom", 6799701, "aus-pmn", "Latn", } m["aus-ngk"] = { "Ngkoth", 7022405, "aus-pmn", "Latn", } m["aus-nyu-pro"] = { "Proto-Nyulnyulan", 116773797, "aus-nyu", "Latn", type = "reconstructed", } m["aus-pam-pro"] = { "Proto-Pama-Nyungan", 33942, "aus-pam", "Latn", type = "reconstructed", } m["aus-tul"] = { "Tulua", 16938541, "aus-pam", "Latn", } m["aus-uwi"] = { "Uwinymil", 7903995, "aus-arn", "Latn", } m["aus-wdj-pro"] = { "Proto-Iwaidjan", 116773767, "aus-wdj", "Latn", type = "reconstructed", } m["aus-won"] = { "Wong-gie", nil, "aus-pam", "Latn", } m["aus-wul"] = { "Wulguru", 8039196, "aus-dyb", "Latn", } m["aus-ynk"] = { -- contrast nny "Yangkaal", 3913770, "aus-tnk", "Latn", } m["awd-amc-pro"] = { "Proto-Amuesha-Chamicuro", nil, "awd", "Latn", type = "reconstructed", } m["awd-kmp-pro"] = { "Proto-Kampa", nil, "awd", "Latn", type = "reconstructed", } m["awd-prw-pro"] = { "Proto-Paresi-Waura", nil, "awd", "Latn", type = "reconstructed", } m["awd-ama"] = { "Amarizana", 16827787, "awd", "Latn", } m["awd-ana"] = { "Anauyá", 16828252, "awd", "Latn", } m["awd-apo"] = { "Apolista", 16916645, "awd", "Latn", } m["awd-cab"] = { "Cabre", 16850160, "awd", "Latn", } m["awd-gnu"] = { "Guinau", 3504087, "awd", "Latn", } m["awd-kar"] = { "Cariay", 16920253, "awd", "Latn", } m["awd-kaw"] = { "Kawishana", 6379993, "awd-nwk", "Latn", } m["awd-kus"] = { "Kustenau", 5196293, "awd", "Latn", } m["awd-man"] = { "Manao", 6746920, "awd", "Latn", } m["awd-mar"] = { "Marawan", 6755108, "awd", "Latn", } m["awd-mpr"] = { "Maipure", 6736872, "awd", "Latn", } m["awd-mrt"] = { "Mariaté", 16910017, "awd-nwk", "Latn", } m["awd-nwk-pro"] = { "Proto-Nawiki", 116773234, "awd-nwk", "Latn", type = "reconstructed", } m["awd-pai"] = { "Paikoneka", 128807835, "awd", "Latn", } m["awd-pas"] = { "Pasé", 7143168, "awd-nwk", "Latn", } m["awd-pro"] = { "Proto-Arawak", 97573478, "awd", "Latn", type = "reconstructed", } m["awd-she"] = { "Shebayo", 7492248, "awd", "Latn", } m["awd-taa-pro"] = { "Proto-Ta-Arawak", 116773282, "awd-taa", "Latn", type = "reconstructed", } m["awd-wai"] = { "Wainumá", 16910017, "awd-nwk", "Latn", } m["awd-yum"] = { "Yumana", 8061062, "awd-nwk", "Latn", } m["azc-caz"] = { "Cazcan", 5055514, "azc", "Latn", } m["azc-cup-pro"] = { "Proto-Cupan", 116773738, "azc-cup", "Latn", type = "reconstructed", } m["azc-ktn"] = { "Kitanemuk", 3197558, "azc-tak", "Latn", } m["azc-nah-pro"] = { "Proto-Nahuan", 7251860, "azc-nah", "Latn", type = "reconstructed", } m["azc-num-pro"] = { "Proto-Numic", 116773247, "azc-num", "Latn", type = "reconstructed", } m["azc-pro"] = { "Proto-Uto-Aztecan", 96400333, "azc", "Latn", type = "reconstructed", } m["azc-tak-pro"] = { "Proto-Takic", 116773283, "azc-tak", "Latn", type = "reconstructed", } m["azc-tat"] = { "Tataviam", 743736, "azc", "Latn", } m["ber-pro"] = { "Proto-Berber", 2855698, "ber", "Latn", type = "reconstructed", } m["ber-fog"] = { "Fogaha", 107610173, "ber", "Latn", } m["ber-zuw"] = { "Zuwara", 4117169, "ber", "Latn", } m["bnt-bal"] = { "Balong", 93935237, "bnt-bbo", "Latn", } m["bnt-bon"] = { "Boma Nkuu", nil, "bnt", "Latn", } m["bnt-boy"] = { "Boma Yumu", nil, "bnt", "Latn", } m["bnt-bwa"] = { "Bwala", 128810345, "bnt-tek", "Latn", } m["bnt-cmw"] = { "Chimwiini", 4958328, "bnt-swh", "Latn", } m["bnt-ind"] = { "Indanga", 51412803, "bnt", "Latn", } m["bnt-lal"] = { "Lala (South Africa)", 6480154, "bnt-ngu", "Latn", } m["bnt-mpi"] = { "Mpiin", 93937013, "bnt-bdz", "Latn", } m["bnt-mpu"] = { "Mpuono", -- not to be confused with Mbuun zmp 36056, "bnt", "Latn", } m["bnt-ngu-pro"] = { "Proto-Nguni", 961559, "bnt-ngu", "Latn", type = "reconstructed", sort_key = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.caron}, } m["bnt-phu"] = { "Phuthi", 33796, "bnt-ngu", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute}, } m["bnt-pro"] = { "Proto-Bantu", 3408025, "bnt", "Latn", type = "reconstructed", sort_key = "bnt-pro-sortkey", } m["bnt-sab-pro"] = { "Proto-Sabaki", nil, -- Q2209395 is the code for the Sabaki family "bnt-sab", "Latn", type = "reconstructed", } m["bnt-sbo"] = { "South Boma", nil, "bnt", "Latn", } m["bnt-sts-pro"] = { "Proto-Sotho-Tswana", 116773278, "bnt-sts", "Latn", type = "reconstructed", } m["btk-pro"] = { "Proto-Batak", 116773191, "btk", "Latn", type = "reconstructed", } m["cau-abz-pro"] = { "Proto-Abkhaz-Abaza", 7251831, "cau-abz", "Latn", type = "reconstructed", } m["cau-and-pro"] = { "Proto-Andian", nil, "cau-and", "Latn", type = "reconstructed", } m["cau-ava-pro"] = { "Proto-Avaro-Andian", 116773187, "cau-ava", "Latn", type = "reconstructed", } m["cau-cir-pro"] = { "Proto-Circassian", 7251838, "cau-cir", "Latn", type = "reconstructed", } m["cau-drg-pro"] = { "Proto-Dargwa", 116773205, "cau-drg", "Latn", type = "reconstructed", } m["cau-lzg-pro"] = { "Proto-Lezghian", 116773223, "cau-lzg", "Latn", type = "reconstructed", } m["cau-nec-pro"] = { "Proto-Northeast Caucasian", 116773244, "cau-nec", "Latn", type = "reconstructed", } m["cau-nkh-pro"] = { "Proto-Nakh", 108032840, "cau-nkh", "Latn", type = "reconstructed", } m["cau-nwc-pro"] = { "Proto-Northwest Caucasian", 7251861, "cau-nwc", "Latn", type = "reconstructed", } m["cau-tsz-pro"] = { "Proto-Tsezian", 116773287, "cau-tsz", "Latn", type = "reconstructed", } m["cba-ata"] = { "Atanques", 4812783, "cba", "Latn", } m["cba-cat"] = { "Catío Chibcha", 7083619, "cba", "Latn", } m["cba-dor"] = { "Dorasque", 5297532, "cba", "Latn", } m["cba-dui"] = { "Duit", 3041061, "cba", "Latn", } m["cba-hue"] = { "Huetar", 35514, "cba", "Latn", } m["cba-nut"] = { "Nutabe", 7070405, "cba", "Latn", } m["cba-pro"] = { "Proto-Chibchan", 116773203, "cba", "Latn", type = "reconstructed", } m["ccs-pro"] = { "Proto-Kartvelian", 2608203, "ccs", "Latn", type = "reconstructed", strip_diacritics = { from = {"q̣", "p̣", "ʓ", "ċ"}, to = {"q̇", "ṗ", "ʒ", "c̣"} }, } m["ccs-gzn-pro"] = { "Proto-Georgian-Zan", 23808119, "ccs-gzn", "Latn", type = "reconstructed", strip_diacritics = { from = {"q̣", "p̣", "ʓ", "ċ"}, to = {"q̇", "ṗ", "ʒ", "c̣"} }, } m["cdc-cbm-pro"] = { "Proto-Central Chadic", 116773197, "cdc-cbm", "Latn", type = "reconstructed", } m["cdc-mas-pro"] = { "Proto-Masa", 116773789, "cdc-mas", "Latn", type = "reconstructed", } m["cdc-pro"] = { "Proto-Chadic", 116773201, "cdc", "Latn", type = "reconstructed", } m["cdd-pro"] = { "Proto-Caddoan", 116773725, "cdd", "Latn", type = "reconstructed", } m["cel-bry-pro"] = { "Proto-Brythonic", 1248800, "cel-bry", "Latn, Polyt", sort_key = { Latn = "cel-bry-pro-sortkey", }, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["cel-gal"] = { "Gallaecian", 3094789, "cel-his", } m["cel-gau"] = { "Gaulish", 29977, "cel", "Latn, Polyt, Ital", strip_diacritics = { Latn = {remove_diacritics = c.macron .. c.breve .. c.diaer}, }, sort_key = { Latn = "cel-bry-pro-sortkey", }, -- Ital translit in [[Module:scripts/data]] -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["cel-pro"] = { "Proto-Celtic", 653649, "cel", "Latn", type = "reconstructed", sort_key = "cel-pro-sortkey", } m["chi-pro"] = { "Proto-Chimakuan", 116773734, "chi", "Latn", type = "reconstructed", } m["chm-pro"] = { "Proto-Mari", 116773788, "chm", "Latn", type = "reconstructed", } m["cmc-pro"] = { "Proto-Chamic", 114793834, "cmc", "Latn", type = "reconstructed", } m["crp-bip"] = { "Basque-Icelandic Pidgin", 810378, "crp", "Latn", ancestors = "eu", } m["crp-cpr"] = { "Chinese Pidgin Russian", nil, "crp", "Hani, Cyrl, Latn", ancestors = "ru, zh", translit = {Cyrl = "ru-translit"}, strip_diacritics = { Cyrl = {remove_diacritics = c.acute .. c.grave .. c.macron}, }, } m["crp-gep"] = { "West Greenlandic Pidgin", 17036301, "crp", "Latn", ancestors = "kl", } m["crp-kia"] = { "Kiautschou German Pidgin", 108314615, "crp", "Latn", ancestors = "de", } m["crp-mar"] = { "Maroon Spirit Language", 1093206, "crp", "Latn", ancestors = "en", } m["crp-mpp"] = { "Macau Pidgin Portuguese", 128804537, "crp", "Hant, Latn", ancestors = "pt", sort_key = {Hant = "Hani-sortkey"}, } m["crp-rsn"] = { "Russenorsk", 505125, "crp", "Cyrl, Latn", ancestors = "nn, ru", translit = {Cyrl = "ru-translit"}, } m["crp-spp"] = { "Samoan Plantation Pidgin", 7409948, "crp", "Latn", ancestors = "en", } m["crp-slb"] = { "Solombala English", 7558525, "crp", "Cyrl, Latn", ancestors = "en, ru", translit = {Cyrl = "ru-translit"}, } m["crp-tpr"] = { "Taimyr Pidgin Russian", 16930506, "crp", "Cyrl", ancestors = "ru", translit = "ru-translit", } m["csu-bba-pro"] = { "Proto-Bongo-Bagirmi", 116773722, "csu-bba", "Latn", type = "reconstructed", } m["csu-maa-pro"] = { "Proto-Mangbetu", 116773786, "csu-maa", "Latn", type = "reconstructed", } m["csu-pro"] = { "Proto-Central Sudanic", 116773730, "csu", "Latn", type = "reconstructed", } m["csu-sar-pro"] = { "Proto-Sara", 116773809, "csu-sar", "Latn", type = "reconstructed", } m["cus-ash"] = { "Ashraaf", 4805855, "cus-som", "Latn", } m["cus-hec-pro"] = { "Proto-Highland East Cushitic", 116773761, "cus-hec", "Latn", type = "reconstructed", } m["cus-som-pro"] = { "Proto-Somaloid", nil, "cus-som", "Latn", type = "reconstructed", } m["cus-sou-pro"] = { "Proto-South Cushitic", 126081567, "cus-sou", "Latn", type = "reconstructed", } m["cus-pro"] = { "Proto-Cushitic", 116773204, "cus", "Latn", type = "reconstructed", } m["dmn-dam"] = { "Dama (Sierra Leone)", 19601574, "dmn", "Latn", } m["dra-bry"] = { "Beary", 1089116, "qfa-mix", "Mlym, Knda", ancestors = "ml, tcy", -- Knda translit in [[Module:scripts/data]] -- Mlym translit in [[Module:scripts/data]] } m["dra-cen-pro"] = { "Proto-Central Dravidian", nil, "dra-cen", "Latn", type = "reconstructed", } m["dra-mkn"] = { "Middle Kannada", 128810572, "dra-kan", "Knda", -- Knda translit in [[Module:scripts/data]] } m["dra-nor-pro"] = { "Proto-North Dravidian", 124433593, "dra-nor", "Latn", type = "reconstructed", } m["dra-okn"] = { "Old Kannada", 15723156, "dra-kan", "Knda", -- Knda translit in [[Module:scripts/data]] } m["dra-ote"] = { "Old Telugu", 126720868, "dra-tel", "Telu", translit = "te-translit", } m["dra-pro"] = { "Proto-Dravidian", 1702853, "dra", "Latn", type = "reconstructed", } m["dra-sdo-pro"] = { "Proto-South Dravidian I", 104847952, -- Wikipedia's "Proto-South Dravidian" is Proto-South Dravidian I in this scheme. "dra-sdo", "Latn", type = "reconstructed", } m["dra-sdt-pro"] = { "Proto-South Dravidian II", 128885257, "dra-sdt", "Latn", type = "reconstructed", } m["dra-sou-pro"] = { "Proto-South Dravidian", 128886121, "dra-sou", "Latn", type = "reconstructed", } m["egx-dem"] = { "Demotic Egyptian", 36765, "egx", "Latn, Egyd, Polyt", sort_key = { Latn = { remove_diacritics = "'%-%s", from = {"ꜣ", "j", "e", "ꜥ", "y", "w", "b", "p", "f", "m", "n", "r", "l", "ḥ", "ḫ", "h̭", "ẖ", "h", "š", "s", "q", "k", "g", "ṱ", "ṯ", "t", "ḏ", "%.", "⸗"}, to = {p[1], p[2], p[3], p[4], p[5], p[6], p[7], p[8], p[9], p[10], p[11], p[12], p[13], p[15], p[16], p[16], p[17], p[14], p[19], p[18], p[20], p[21], p[22], p[23], p[24], p[23], p[25], p[26], p[26]} }, }, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["dmn-pro"] = { "Proto-Mande", 116773785, "dmn", "Latn", type = "reconstructed", } m["dmn-mdw-pro"] = { "Proto-Western Mande", 116773822, "dmn-mdw", "Latn", type = "reconstructed", } m["dru-pro"] = { "Proto-Rukai", 116773807, "map", "Latn", type = "reconstructed", } m["ero-gsz"] = { "Geshiza", nil, "ero", "Latn", } m["ero-nya"] = { "Nyagrong Minyag", nil, "ero", "Latn", } m["ero-tau"] = { "Stau", nil, "ero", "Latn", } m["esx-esk-pro"] = { "Proto-Eskimo", 7251842, "esx-esk", "Latn", type = "reconstructed", } m["esx-ink"] = { "Inuktun", 1671647, "esx-inu", "Latn", } m["esx-inq"] = { "Inuinnaqtun", 28070, "esx-inu", "Latn", } m["esx-inu-pro"] = { "Proto-Inuit", 60785588, "esx-inu", "Latn", type = "reconstructed", } m["esx-pro"] = { "Proto-Eskimo-Aleut", 7251843, "esx", "Latn", type = "reconstructed", } m["esx-tut"] = { "Tunumiisut", 15665389, "esx-inu", "Latn", } m["euq-pro"] = { "Proto-Basque", 938011, "euq", "Latn", type = "reconstructed", } m["gba-pro"] = { "Proto-Gbaya", nil, "gba", "Latn", type = "reconstructed", } m["gem-pro"] = { "Proto-Germanic", 669623, "gem", "Latn", type = "reconstructed", sort_key = "gem-pro-sortkey", } m["gme-bur"] = { "Burgundian", 47625, "gme", "Latn", } m["gme-cgo"] = { "Crimean Gothic", 36211, "gme", "Latn", } m["gmq-gut"] = { "Gutnish", 1256646, "gmq", "Latn", ancestors = "gmq-ogt", } m["gmq-jmk"] = { "Jamtish", 35512, "gmq-eas", "Latn", } m["gmq-mno"] = { "Middle Norwegian", 3417070, "gmq-wes", "Latn", } m["gmq-oda"] = { "Old Danish", 12330003, "gmq-eas", "Latn, Runr", strip_diacritics = {remove_diacritics = c.macron}, } m["gmq-ogt"] = { "Old Gutnish", 1133488, "gmq", "Latn, Runr", ancestors = "non", } m["gmq-osw"] = { "Old Swedish", 2417210, "gmq-eas", "Latn, Runr", strip_diacritics = {remove_diacritics = c.macron}, } m["gmq-pro"] = { "Proto-Norse", 1671294, "gmq", "Runr", translit = "Runr-translit", } m["gmq-scy"] = { "Scanian", 768017, "gmq-eas", "Latn", } m["gmw-bgh"] = { "Bergish", 329030, "gmw-frk", "Latn", } m["gmw-cfr"] = { "Central Franconian", 572197, "gmw-hgm", "Latn", ancestors = "gmh", wikimedia_codes = "ksh", } m["gmw-ecg"] = { "East Central German", 499344, -- subsumes Q699284, Q152965 "gmw-hgm", "Latn", ancestors = "gmh", } m["gmw-fin"] = { "Fingallian", 3072588, "gmw-ian", "Latn", } m["gmw-gts"] = { "Gottscheerish", 533109, "gmw-hgm", "Latn", ancestors = "bar", } m["gmw-jdt"] = { "Jersey Dutch", 1687911, "gmw-frk", "Latn", ancestors = "nl", } m["gmw-msc"] = { "Middle Scots", 3327000, "gmw-ang", "Latn", ancestors = "enm-esc", } m["gmw-pro"] = { "Proto-West Germanic", 78079021, "gmw", "Latn, Runr", -- type = "reconstructed", -- largely but not entirely reconstructed (like Proto-Norse); see April '24 BP, set back to reconstructed (?) if 'anti-asterisk' is added sort_key = "gmw-pro-sortkey", } m["gmw-rfr"] = { "Rhine Franconian", 707007, "gmw-hgm", "Latn", ancestors = "gmh", } m["gmw-stm"] = { "Sathmar Swabian", 2223059, "gmw-hgm", "Latn", ancestors = "swg", } m["gmw-tsx"] = { "Transylvanian Saxon", 260942, "gmw-hgm", "Latn", ancestors = "gmw-cfr", } m["gmw-vog"] = { "Volga German", 312574, "gmw-hgm", "Latn", ancestors = "gmw-rfr", } m["gmw-zps"] = { "Zipser German", 205548, "gmw-hgm", "Latn", ancestors = "gmh", } m["gn-cls"] = { "Classical Guarani", 17478065, "gn", "Latn", } m["grk-cal"] = { "Calabrian Greek", 1146398, "grk", "Latn, Grek", ancestors = "grk-ita", translit = { Grek = "el-translit", }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["grk-ita"] = { "Italiot Greek", 19720507, "grk", "Latn, Grek", ancestors = "gkm", translit = { Grek = "el-translit", }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["grk-mar"] = { "Mariupol Greek", 4400023, "grk", "Cyrl, Latn, Grek", ancestors = "gkm", translit = { Cyrl = "grk-mar-translit", Grek = "grk-mar-translit", }, override_translit = true, strip_diacritics = { Cyrl = {remove_diacritics = c.acute}, }, -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["grk-pro"] = { "Proto-Hellenic", 1231805, "grk", "Latn, Polyt", type = "reconstructed", sort_key = {Latn = { from = {"ʰ", "ʷ"}, to = {"h", "w"}, remove_diacritics = c.grave .. c.acute .. c.macron .. c.breve .. c.caron }}, -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] -- NOTE: formerly no translit specified for Polyt; presumably an accidental omission; if not, set Polyt = false in -- the translit section } m["hmn-pro"] = { "Proto-Hmongic", 116773210, "hmn", "Latn", type = "reconstructed", } m["hmx-mie-pro"] = { "Proto-Mienic", 116773229, "hmx-mie", "Latn", type = "reconstructed", } m["hmx-pro"] = { "Proto-Hmong-Mien", 7251846, "hmx", "Latn", type = "reconstructed", } m["hyx-pro"] = { "Proto-Armenian", 3848498, "hyx", "Latn", type = "reconstructed", } m["iir-nur-pro"] = { "Proto-Nuristani", 116773248, "iir-nur", "Latn", type = "reconstructed", } m["iir-pro"] = { "Proto-Indo-Iranian", 966439, "iir", "Latn", type = "reconstructed", } m["ijo-pro"] = { "Proto-Ijoid", 116773766, "ijo", "Latn", type = "reconstructed", } m["inc-apa"] = { "Apabhramsa", 616419, "inc-mid", "Deva, Shrd, Sidd", ancestors = "pra", translit = { Deva = "sa-translit", -- Shrd translit in [[Module:scripts/data]] -- Sidd translit in [[Module:scripts/data]] }, } m["inc-ash"] = { "Ashokan Prakrit", 104854379, "inc-mid", "Brah, Khar", ancestors = "sa", translit = { -- Brah translit in [[Module:scripts/data]] Khar = "Khar-translit", }, } m["inc-dng-pro"] = { "Proto-Dangari", nil, "inc-dng", "Latn", type = "reconstructed", } m["inc-kam"] = { "Kamarupi Prakrit", 6356097, "inc-bas", "Brah, Sidd", -- Brah, Sidd translit in [[Module:scripts/data]] } m["inc-kho"] = { "Kholosi", 24952008, "inc-snd", "Latn", } m["inc-krd-pro"] = { "Proto-Kamta", 128816843, "inc-bas", "Latn", ancestors = "inc-kam", type = "reconstructed", } m["inc-mas"] = { "Middle Assamese", 128806836, "inc-bas", "as-Beng", ancestors = "inc-oas", translit = "inc-mas-translit", } m["inc-mbn"] = { "Middle Bengali", 113559927, "inc-bas", "Beng", ancestors = "inc-obn", translit = "inc-mbn-translit", } m["inc-mgu"] = { "Middle Gujarati", 24907429, "inc-wes", "Deva", ancestors = "inc-ogu", } m["inc-mor"] = { "Middle Odia", 128810882, "inc-eas", "Orya", ancestors = "inc-oor", } m["inc-oas"] = { "Early Assamese", 85758237, "inc-bas", "as-Beng", ancestors = "inc-kam", translit = "inc-oas-translit", } m["inc-oaw"] = { "Old Awadhi", nil, "inc-hie", "Deva, Kthi, ur-Arab", strip_diacritics = { from = {"هٔ", "ۂ"}, -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه" to = {"ہ", "ہ"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef }, translit = { Deva = "sa-translit", Kthi = "sa-Kthi-translit", ["ur-Arab"] = "inc-ohi-translit", }, } m["inc-obn"] = { "Old Bengali", 113559926, "inc-bas", "Beng", } m["inc-ogu"] = { "Old Gujarati", 24907427, "inc-wes", "Deva", translit = "sa-translit", } m["inc-ohi"] = { "Old Hindi", 48767781, "inc-hiw", "Deva, ur-Arab", strip_diacritics = { from = {"هٔ", "ۂ"}, -- character "ۂ" code U+06C2 to "ه" and "هٔ" (U+0647 + U+0654) to "ه" to = {"ہ", "ہ"}, remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun .. c.nunghunna .. c.superalef }, translit = { Deva = "sa-translit", ["ur-Arab"] = "inc-ohi-translit", }, } m["inc-oor"] = { "Old Odia", 128807801, "inc-eas", "Orya", } m["inc-opa"] = { "Old Punjabi", 115270971, "inc-pan", "Guru, pa-Arab", translit = { Guru = "inc-opa-Guru-translit", ["pa-Arab"] = "pa-Arab-translit", }, strip_diacritics = {remove_diacritics = c.fathatan .. c.dammatan .. c.kasratan .. c.fatha .. c.damma .. c.kasra .. c.shadda .. c.sukun}, } m["inc-pro"] = { "Proto-Indo-Aryan", 23808344, "inc", "Latn", type = "reconstructed", } m["ine-ana-pro"] = { "Proto-Anatolian", 7251833, "ine-ana", "Latn", type = "reconstructed", } m["ine-bsl-pro"] = { "Proto-Balto-Slavic", 1703347, "ine-bsl", "Latn", type = "reconstructed", sort_key = { from = {"[áā]", "[éēḗ]", "[íī]", "[óōṓ]", "[úū]", c.acute, c.macron, "ˀ"}, to = {"a", "e", "i", "o", "u"} }, } m["ine-grp-pro"] = { "Proto-Graeco-Phrygian", nil, "ine-grp", "Latn", type = "reconstructed", } m["ine-kal"] = { "Kalašma", 122770439, "ine-ana", "Xsux", } m["ine-pae"] = { "Paeonian", 2705672, "ine", "Polyt", -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["ine-pro"] = { "Proto-Indo-European", 37178, "ine", "Latn", type = "reconstructed", sort_key = { from = {"[áā]", "[éēḗ]", "[íī]", "[óōṓ]", "[úū]", "ĺ", "ḿ", "ń", "ŕ", "ǵ", "ḱ", "ʰ", "ʷ", "₁", "₂", "₃", c.ringbelow, c.acute, c.macron}, to = {"a", "e", "i", "o", "u", "l", "m", "n", "r", "g'", "k'", "¯h", "¯w", "1", "2", "3"} }, } m["ine-toc-pro"] = { "Proto-Tocharian", 104841462, "ine-toc", "Latn", type = "reconstructed", } m["xme-old"] = { "Old Median", 36461, "xme", "Polyt, Latn", -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["xme-mid"] = { "Middle Median", 12836150, "xme", "Latn", } m["xme-ker"] = { "Kermanic", 129850, "xme", "fa-Arab, Latn, Hebr", ancestors = "xme-mid", -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["xme-taf"] = { "Tafreshi", nil, "xme", "fa-Arab, Latn", ancestors = "xme-mid", } m["xme-ttc-pro"] = { "Proto-Tatic", 122973870, "xme-ttc", "Latn", ancestors = "xme-mid", } m["xme-kls"] = { "Kalasuri", nil, "xme-ttc", ancestors = "xme-ttc-nor", } m["xme-klt"] = { "Kilit", 3612452, "xme-ttc", "Cyrl", -- and fa-Arab? } m["xme-ott"] = { "Old Tati", 434697, "xme-ttc", "fa-Arab, Latn", } m["ira-kms-pro"] = { "Proto-Komisenian", 116773777, "ira-kms", "Latn", type = "reconstructed", } m["ira-mpr-pro"] = { "Proto-Medo-Parthian", 116773227, "ira-mpr", "Latn", type = "reconstructed", } m["ira-pat-pro"] = { "Proto-Pathan", 116773255, "ira-pat", "Latn", type = "reconstructed", } m["ira-pro"] = { "Proto-Iranian", 4167865, "ira", "Latn", type = "reconstructed", } m["ira-zgr-pro"] = { "Proto-Zaza-Gorani", 116775031, "ira-zgr", "Latn", type = "reconstructed", } m["xsc-pro"] = { "Proto-Scythian", 116773273, "xsc", "Latn", type = "reconstructed", } m["xsc-sar-pro"] = { "Proto-Sarmatian", 116773249, "xsc-sar", "Latn", type = "reconstructed", } m["xsc-skw-pro"] = { "Proto-Saka-Wakhi", 116773267, "xsc-skw", "Latn", type = "reconstructed", } m["xsc-sak-pro"] = { "Proto-Saka", 116773264, "xsc-sak", "Latn", type = "reconstructed", } m["ira-sym-pro"] = { "Proto-Shughni-Yazghulami-Munji", 116773813, "ira-sym", "Latn", type = "reconstructed", } m["ira-sgi-pro"] = { "Proto-Sanglechi-Ishkashimi", 116773808, "ira-sgi", "Latn", type = "reconstructed", } m["ira-mny-pro"] = { "Proto-Munji-Yidgha", 116773792, "ira-mny", "Latn", type = "reconstructed", } m["ira-shy-pro"] = { "Proto-Shughni-Yazghulami", 116773812, "ira-shy", "Latn", type = "reconstructed", } m["ira-shr-pro"] = { "Proto-Shughni-Roshani", 116773811, "ira-shr", "Latn", type = "reconstructed", } m["ira-sgc-pro"] = { "Proto-Sogdic", 116773276, "ira-sgc", "Latn", type = "reconstructed", } m["ira-wnj"] = { "Vanji", 3398419, "ira-shy", "Latn", } m["iro-ere"] = { "Erie", 5388365, "iro-nor", "Latn", } m["iro-min"] = { "Mingo", 128531, "iro-nor", "Latn", ietf_subtag = "i-mingo", -- grandfathered IETF tag } m["iro-nor-pro"] = { "Proto-North Iroquoian", 116773242, "iro-nor", "Latn", type = "reconstructed", } m["iro-pro"] = { "Proto-Iroquoian", 7251852, "iro", "Latn", type = "reconstructed", } m["itc-pro"] = { "Proto-Italic", 17102720, "itc", "Latn", type = "reconstructed", } m["itc-psa"] = { "Pre-Samnite", 7239186, "itc-sbl", "Ital, Polyt, Latn", -- Ital translit in [[Module:scripts/data]] (NOTE: formerly not present, probably an accidental omission) -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["jpx-hcj"] = { "Hachijō", 5637049, "jpx", "Jpan", ancestors = "ojp-eas", translit = s["jpx-translit"], display_text = s["jpx-displaytext"], strip_diacritics = s["jpx-stripdiacritics"], sort_key = s["jpx-sortkey"], } m["jpx-pro"] = { "Proto-Japonic", 3924309, "jpx", "Latn", type = "reconstructed", } m["jpx-ryu-pro"] = { "Proto-Ryukyuan", 56349069, "jpx-ryu", "Latn", type = "reconstructed", } m["kar-pro"] = { "Proto-Karen", 85794783, "kar", "Latn", type = "reconstructed", } m["kca-eas"] = { "Eastern Khanty", 30304622, "kca", "Cyrl", translit = "kca-translit", override_translit = true, -- TODO temporary until MediaWiki supports Unicode 16 (probably requires a PHP update from their side) sort_key = { Cyrl = { from = {"ᲊ"}, to = {"Ᲊ"} } }, } m["kca-nor"] = { "Northern Khanty", 30304527, "kca", "Cyrl", translit = "kca-translit", override_translit = true, -- TODO temporary until MediaWiki supports Unicode 16 (probably requires a PHP update from their side) sort_key = { Cyrl = { from = {"ᲊ"}, to = {"Ᲊ"} } }, } m["kca-pro"] = { "Proto-Khanty", 127505171, "kca", "Latn", type = "reconstructed", } m["kca-sou"] = { "Southern Khanty", 30304618, "kca", "Cyrl", translit = "kca-translit", override_translit = true, } m["khi-kho-pro"] = { "Proto-Khoe", 116773218, "khi-kho", "Latn", type = "reconstructed", } m["khi-kun"] = { "ǃKung", 32904, "khi-kxa", "Latn", } m["ko-ear"] = { "Early Modern Korean", 756014, "qfa-kor", "Kore", ancestors = "okm", translit = "okm-translit", -- Kore strip_diacritics in [[Module:scripts/data]] } m["kro-pro"] = { "Proto-Kru", 116773778, "kro", "Latn", type = "reconstructed", } m["ku-pro"] = { "Proto-Kurdish", 116773221, "ku", "Latn", type = "reconstructed", } m["map-ata-pro"] = { "Proto-Atayalic", 116773151, "map-ata", "Latn", type = "reconstructed", } m["map-bms"] = { "Banyumasan", 33219, "map", "Latn, Java", } m["map-pro"] = { "Proto-Austronesian", 49230, "map", "Latn", type = "reconstructed", } m["mis-hkl"] = { "Kelantan Peranakan Hokkien", 108794818, "qfa-mix", ancestors = "nan-hbl, sou, mfa", } m["mis-idn"] = { "Idiom Neutral", 35847, "art", "Latn", type = "appendix-constructed", } m["mis-isa"] = { "Isaurian", 16956868, nil, -- "Xsux, Hluw, Latn", } m["mis-jie"] = { "Jie", 124424186, nil, "Hani", sort_key = "Hani-sortkey", } m["mis-jzh"] = { "Jizhao", 45242758, "qfa-bej", "Latn", } m["mis-kas"] = { "Kassite", 35612, nil, "Xsux", } m["mis-mmd"] = { "Mimi of Decorse", 6862206, nil, "Latn", } m["mis-mmn"] = { "Mimi of Nachtigal", 6862207, nil, "Latn", } m["mis-phi"] = { "Philistine", 2230924, nil, "Phnx", -- Phnx translit in [[Module:scripts/data]] (NOTE: not present before, presumably an accidental omission) } m["mis-rou"] = { "Rouran", 48816637, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-tdl"] = { "Turdulian", 133176492, } m["mis-tdt"] = { "Turdetanian", 133176461, } m["mis-tnw"] = { "Tangwang", 7683179, "qfa-mix", "Latn", ancestors = "cmn, sce", } m["mis-tuh"] = { "Tuyuhun", 48816625, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-tuo"] = { "Tuoba", 48816629, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-wuh"] = { "Wuhuan", 118976867, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-xbi"] = { "Xianbei", 4448647, "qfa-xgx", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mis-xnu"] = { "Xiongnu", 10901674, nil, "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mjg-mgl"] = { "Mongghul", 53765528, "mjg", "Latn", -- also Mong, Cyrl ? } m["mjg-mgr"] = { "Mangghuer", 56285392, "mjg", "Latn", -- also Mong, Cyrl ? } m["mkh-asl-pro"] = { "Proto-Aslian", 55630680, "mkh-asl", "Latn", type = "reconstructed", } m["mkh-ban-pro"] = { "Proto-Bahnaric", 116773189, "mkh-ban", "Latn", type = "reconstructed", } m["mkh-kat-pro"] = { "Proto-Katuic", 116773772, "mkh-kat", "Latn", type = "reconstructed", } m["mkh-khm-pro"] = { "Proto-Khmuic", 116773774, "mkh-khm", "Latn", type = "reconstructed", } m["mkh-kmr-pro"] = { "Proto-Khmeric", 55630684, "mkh-kmr", "Latn", type = "reconstructed", } m["mkh-mmn"] = { "Middle Mon", 121337926, "mkh-mnc", "Latn, Mymr", --and also Pallava ancestors = "omx", } m["mkh-mnc-pro"] = { "Proto-Monic", 116773231, "mkh-mnc", "Latn", type = "reconstructed", } m["mkh-mvi"] = { "Middle Vietnamese", 9199, "mkh-vie", "Hani, Latn", sort_key = {Hani = "Hani-sortkey"}, } m["mkh-pal-pro"] = { "Proto-Palaungic", 104847372, "mkh-pal", "Latn", type = "reconstructed", } m["mkh-pea-pro"] = { "Proto-Pearic", 116773804, "mkh-pea", "Latn", type = "reconstructed", } m["mkh-pkn-pro"] = { "Proto-Pakanic", 116773803, "mkh-pkn", "Latn", type = "reconstructed", } m["mkh-pro"] = { --This will be merged into 2015 aav-pro. "Proto-Mon-Khmer", 7251859, "mkh", "Latn", type = "reconstructed", } m["mnw-tha"] = { -- To be removed. "Thai Mon", nil, "mkh-mnc", "Mymr, Thai", ancestors = "mkh-mmn", sort_key = { from = {"[%p]", "ျ", "ြ", "ွ", "ှ", "ၞ", "ၟ", "ၠ", "ၚ", "ဿ", "[็-๎]", "([เแโใไ])([ก-ฮ])ฺ?"}, to = {"", "္ယ", "္ရ", "္ဝ", "္ဟ", "္န", "္မ", "္လ", "င", "သ္သ", "", "%2%1"} }, } m["mkh-vie-pro"] = { "Proto-Vietic", 109432616, "mkh-vie", "Latn", type = "reconstructed", } m["mns-cen"] = { "Central Mansi", 128810384, "mns", "Cyrl", translit = "mns-translit", override_translit = true, } m["mns-nor"] = { "Northern Mansi", 30304537, "mns", "Cyrl", translit = "mns-translit", override_translit = true, } m["mns-pro"] = { "Proto-Mansi", 128883093, "mns", "Latn", type = "reconstructed", } m["mns-sou"] = { "Southern Mansi", 30304629, "mns", "Cyrl", translit = "mns-translit", override_translit = true, } m["mun-pro"] = { "Proto-Munda", 105102373, "mun", "Latn", type = "reconstructed", } m["myn-chl"] = { -- the stage after ''emy'' "Ch'olti'", 873995, "myn", "Latn", } m["myn-pro"] = { "Proto-Mayan", 3321532, "myn", "Latn", type = "reconstructed", } m["nai-ala"] = { "Alazapa", 128810233, nil, "Latn", } m["nai-bay"] = { "Bayogoula", 1563704, nil, "Latn", } m["nai-cal"] = { "Calusa", 51782, nil, "Latn", } m["nai-chi"] = { "Chiquimulilla", 25339627, "nai-xin", "Latn", } m["nai-chu-pro"] = { "Proto-Chumash", 116773736, "nai-chu", "Latn", type = "reconstructed", } m["nai-cig"] = { "Ciguayo", 20741700, nil, "Latn", } m["nai-ckn-pro"] = { "Proto-Chinookan", 116773735, "nai-ckn", "Latn", type = "reconstructed", } m["nai-guz"] = { "Guazacapán", 19572028, "nai-xin", "Latn", } m["nai-hit"] = { "Hitchiti", 1542882, "nai-mus", "Latn", } m["nai-ipa"] = { "Ipai", 3027474, "nai-yuc", "Latn", } m["nai-jtp"] = { "Jutiapa", nil, "nai-xin", "Latn", } m["nai-jum"] = { "Jumaytepeque", 25339626, "nai-xin", "Latn", } m["nai-kat"] = { "Kathlamet", 6376639, "nai-ckn", "Latn", } m["nai-klp-pro"] = { "Proto-Kalapuyan", 116773771, "nai-klp", "Latn", type = "reconstructed", } m["nai-knm"] = { "Konomihu", 3198734, "nai-shs", "Latn", } m["nai-kum"] = { "Kumeyaay", 4910139, "nai-yuc", "Latn", } m["nai-mac"] = { "Macoris", 21070851, nil, "Latn", } m["nai-mdu-pro"] = { "Proto-Maidun", 116773784, "nai-mdu", "Latn", type = "reconstructed", } m["nai-miz-pro"] = { "Proto-Mixe-Zoque", 7251858, "nai-miz", "Latn", type = "reconstructed", } m["nai-mus-pro"] = { "Proto-Muskogean", 116775368, "nai-mus", "Latn", type = "reconstructed", } m["nai-nao"] = { "Naolan", 6964594, nil, "Latn", } m["nai-nrs"] = { "New River Shasta", 7011254, "nai-shs", "Latn", } m["nai-okw"] = { "Okwanuchu", 3350126, "nai-shs", "Latn", } m["nai-per"] = { "Pericú", 3375369, nil, "Latn", } m["nai-pic"] = { "Picuris", 7191257, "nai-kta", "Latn", } m["nai-plp-pro"] = { "Proto-Plateau Penutian", 116773806, "nai-plp", "Latn", type = "reconstructed", } m["nai-pom-pro"] = { "Proto-Pomo", 116773262, "nai-pom", "Latn", type = "reconstructed", } m["nai-qng"] = { "Quinigua", 36360, nil, "Latn", } m["nai-sca-pro"] = { -- NB 'sio-pro' "Proto-Siouan" which is Proto-Western Siouan "Proto-Siouan-Catawban", 116773275, "nai-sca", "Latn", type = "reconstructed", } m["nai-sin"] = { "Sinacantán", 24190249, "nai-xin", "Latn", } m["nai-sln"] = { "Salvadoran Lenca", 3229434, "nai-len", "Latn", } m["nai-spt"] = { "Sahaptin", 3833015, "nai-shp", "Latn", } m["nai-tap"] = { "Tapachultec", 7684401, "nai-miz", "Latn", } m["nai-taw"] = { "Tawasa", 7689233, nil, "Latn", } m["nai-teq"] = { "Tequistlatec", 2964454, "nai-tqn", "Latn", } m["nai-tip"] = { "Tipai", 3027471, "nai-yuc", "Latn", } m["nai-tot-pro"] = { "Proto-Totozoquean", 116773285, "nai-tot", "Latn", type = "reconstructed", } m["nai-tsi-pro"] = { "Proto-Tsimshianic", nil, "nai-tsi", "Latn", type = "reconstructed", } m["nai-utn-pro"] = { "Proto-Utian", 116773290, "nai-utn", "Latn", type = "reconstructed", } m["nai-wai"] = { "Waikuri", 3118702, nil, "Latn", } m["nai-wji"] = { "Western Jicaque", 3178610, "nai-jcq", "Latn", } m["nai-yup"] = { "Yupiltepeque", 25339628, "nai-xin", "Latn", } m["nan-dat"] = { "Datian Min", 19855572, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-hbl"] = { "Hokkien", 1624231, "zhx-nan", "Hants, Latn, Bopo, Kana", wikimedia_codes = "zh-min-nan", generate_forms = "zh-generateforms", sort_key = { Hani = "Hani-sortkey", Kana = "Kana-sortkey" }, } m["nan-hlh"] = { "Hailufeng Min", 120755728, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-lnx"] = { "Longyan Min", 6674568, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-tws"] = { "Teochew", 36759, "zhx-nan", "Hants", generate_forms = "zh-generateforms", translit = "zh-translit", sort_key = "Hani-sortkey", } m["nan-zhe"] = { "Zhenan Min", 3846710, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["nan-zsh"] = { "Sanxiang Min", 7420769, "zhx-nan", "Hants", generate_forms = "zh-generateforms", sort_key = "Hani-sortkey", } m["ngf-bin-pro"] = { "Proto-Binanderean", 137881672, "ngf-bin", "Latn", type = "reconstructed", } m["ngf-pro"] = { "Proto-Trans-New Guinea", 85794785, "ngf", "Latn", type = "reconstructed", } m["nic-bco-pro"] = { "Proto-Benue-Congo", 116773194, "nic-bco", "Latn", type = "reconstructed", } m["nic-bod-pro"] = { "Proto-Bantoid", 116773190, "nic-bod", "Latn", type = "reconstructed", } m["nic-eov-pro"] = { "Proto-Eastern Oti-Volta", 116773753, "nic-eov", "Latn", type = "reconstructed", } m["nic-gns-pro"] = { "Proto-Gurunsi", 116773759, "nic-gns", "Latn", type = "reconstructed", } m["nic-grf-pro"] = { "Proto-Grassfields", 116773755, "nic-grf", "Latn", type = "reconstructed", } m["nic-gur-pro"] = { "Proto-Gur", 116773758, "nic-gur", "Latn", type = "reconstructed", } m["nic-jkn-pro"] = { "Proto-Jukunoid", 116773769, "nic-jkn", "Latn", type = "reconstructed", } m["nic-lcr-pro"] = { "Proto-Lower Cross River", 116773782, "nic-lcr", "Latn", type = "reconstructed", } m["nic-ogo-pro"] = { "Proto-Ogoni", 116773799, "nic-ogo", "Latn", type = "reconstructed", } m["nic-ovo-pro"] = { "Proto-Oti-Volta", 116773802, "nic-ovo", "Latn", type = "reconstructed", } m["nic-plt-pro"] = { "Proto-Plateau", 116773805, "nic-plt", "Latn", type = "reconstructed", } m["nic-pro"] = { "Proto-Niger-Congo", 108000748, "nic", "Latn", type = "reconstructed", } m["nic-ubg-pro"] = { "Proto-Ubangian", 116773818, "nic-ubg", "Latn", type = "reconstructed", } m["nic-ucr-pro"] = { "Proto-Upper Cross River", 116773819, "nic-ucr", "Latn", type = "reconstructed", } m["nic-vco-pro"] = { "Proto-Volta-Congo", 116773293, "nic-vco", "Latn", type = "reconstructed", } m["njo-jgl"] = { "Chungli Ao", 55607615, "njo", "Latn", } m["njo-mng"] = { "Mongsen Ao", 85383221, "njo", "Latn", } m["nub-har"] = { "Haraza", 19572059, "nub", "Arab, Latn", } m["nub-pro"] = { "Proto-Nubian", 116773246, "nub", "Latn", type = "reconstructed", } m["omq-cha-pro"] = { "Proto-Chatino", 116773202, "omq-cha", "Latn", type = "reconstructed", } m["omq-maz-pro"] = { "Proto-Mazatec", 116773790, "omq-maz", "Latn", type = "reconstructed", } m["omq-mix-pro"] = { "Proto-Mixtecan", 21573423, "omq-mix", "Latn", type = "reconstructed", } m["omq-mxt-pro"] = { "Proto-Mixtec", 21573424, "omq-mxt", "Latn", type = "reconstructed", } m["omq-otp-pro"] = { "Proto-Oto-Pamean", 116773251, "omq-otp", "Latn", type = "reconstructed", } m["omq-pro"] = { "Proto-Oto-Manguean", 33669, "omq", "Latn", type = "reconstructed", } m["omq-sjq"] = { "San Juan Quiahije Chatino", 138330751, "omq-cha", "Latn", } m["omq-tel"] = { "Teposcolula Mixtec", nil, "omq-mxt", "Latn", } m["omq-teo"] = { "Teojomulco Chatino", 25340451, "omq-cha", "Latn", } m["omq-tri-pro"] = { "Proto-Triqui", 116773817, "omq-tri", "Latn", type = "reconstructed", } m["omq-zap-pro"] = { "Proto-Zapotecan", 116773297, "omq-zap", "Latn", type = "reconstructed", } m["omq-zpc-pro"] = { "Proto-Zapotec", 116773296, "omq-zpc", "Latn", type = "reconstructed", } m["omv-aro-pro"] = { "Proto-Aroid", 116773721, "omv-aro", "Latn", type = "reconstructed", } m["omv-diz-pro"] = { "Proto-Dizoid", 116773750, "omv-diz", "Latn", type = "reconstructed", } m["omv-pro"] = { "Proto-Omotic", 116773800, "omv", "Latn", type = "reconstructed", } m["oto-otm-pro"] = { "Proto-Otomi", 5908710, "oto-otm", "Latn", type = "reconstructed", } m["oto-pro"] = { "Proto-Otomian", 116773252, "oto", "Latn", type = "reconstructed", } m["paa-kmn"] = { "Kómnzo", 18344310, "paa-wko", "Latn", } m["paa-kwn"] = { "Kuwani", 6449056, "qfa-unc", -- poorly attested, possibly the same as or related to Kalabra "Latn", } m["paa-lei"] = { "Leitre", 85776228, "paa-isk", } m["paa-nha-pro"] = { "Proto-North Halmahera", 116773241, "paa-nha", "Latn", type = "reconstructed" } m["paa-nun"] = { "Nungon", 128807788, "ngf-ynu", "Latn", } m["phi-din"] = { "Dinapigue Agta", 16945774, "phi", "Latn", } m["phi-kal-pro"] = { "Proto-Kalamian", 116773213, "phi-kal", "Latn", type = "reconstructed", } m["phi-nag"] = { "Nagtipunan Agta", 16966111, "phi", "Latn", } m["phi-pro"] = { "Proto-Philippine", 18204898, "phi", "Latn", type = "reconstructed", } m["poz-abi"] = { "Abai", 19570729, "poz-san", "Latn", } m["poz-bal"] = { "Baliledo", 4850912, "poz", "Latn", } m["poz-btk-pro"] = { "Proto-Bungku-Tolaki", 116773724, "poz-btk", "Latn", type = "reconstructed", } m["poz-cet-pro"] = { "Proto-Central-Eastern Malayo-Polynesian", 2269883, "poz-cet", "Latn", type = "reconstructed", } m["poz-hce-pro"] = { "Proto-Halmahera-Cenderawasih", 116773209, "poz-hce", "Latn", type = "reconstructed", } m["poz-lgx-pro"] = { "Proto-Lampungic", 116773222, "poz-lgx", "Latn", type = "reconstructed", } m["poz-mcm-pro"] = { "Proto-Malayo-Chamic", 116773225, "poz-mcm", "Latn", type = "reconstructed", } m["poz-mic-pro"] = { "Proto-Micronesian", 111939079, "poz-mic", "Latn", type = "reconstructed", } m["poz-mly-pro"] = { "Proto-Malayic", 98057728, "poz-mly", "Latn", type = "reconstructed", } m["poz-msa-pro"] = { "Proto-Malayo-Sumbawan", 116773226, "poz-msa", "Latn", type = "reconstructed", } m["poz-oce-pro"] = { "Proto-Oceanic", 141741, "poz-oce", "Latn", type = "reconstructed", } m["poz-pep-pro"] = { "Proto-Eastern Polynesian", 113988745, "poz-pep", "Latn", type = "reconstructed", } m["poz-pnp-pro"] = { "Proto-Nuclear Polynesian", 113988746, "poz-pnp", "Latn", type = "reconstructed", } m["poz-pol-pro"] = { "Proto-Polynesian", 1658709, "poz-pol", "Latn", type = "reconstructed", } m["poz-pro"] = { "Proto-Malayo-Polynesian", 3832960, "poz", "Latn", type = "reconstructed", } m["poz-sml"] = { "Sarawak Malay", 4251702, "poz-mly", "Latn, ms-Arab", } m["poz-ssw-pro"] = { "Proto-South Sulawesi", 116773279, "poz-ssw", "Latn", type = "reconstructed", } m["poz-swa-pro"] = { "Proto-North Sarawak", 116773243, "poz-swa", "Latn", type = "reconstructed", } m["poz-ter"] = { "Terengganu Malay", 4207412, "poz-mly", "Latn, ms-Arab", } m["pqe-pro"] = { "Proto-Eastern Malayo-Polynesian", 2269883, "pqe", "Latn", type = "reconstructed", } m["pra-niy"] = { "Niya Prakrit", 11991601, "inc-mid", "Khar", ancestors = "inc-ash", translit = "Khar-translit", } m["qfa-adm-pro"] = { "Proto-Great Andamanese", 116773756, "qfa-adm", "Latn", type = "reconstructed", } m["qfa-bet-pro"] = { "Proto-Be-Tai", 116773193, "qfa-bet", "Latn", type = "reconstructed", } m["qfa-cka-pro"] = { "Proto-Chukotko-Kamchatkan", 7251837, "qfa-cka", "Latn", type = "reconstructed", } m["qfa-hur-pro"] = { "Proto-Hurro-Urartian", 116773211, "qfa-hur", "Latn", type = "reconstructed", } m["qfa-kad-pro"] = { "Proto-Kadu", 116773770, "qfa-kad", "Latn", type = "reconstructed", } m["qfa-kms-pro"] = { "Proto-Kam-Sui", 55630682, "qfa-kms", "Latn", type = "reconstructed", } m["qfa-kor-pro"] = { "Proto-Koreanic", 467883, "qfa-kor", "Latn", type = "reconstructed", } m["qfa-kra-pro"] = { "Proto-Kra", 7251854, "qfa-kra", "Latn", type = "reconstructed", } m["qfa-lic-pro"] = { "Proto-Hlai", 7251845, "qfa-lic", "Latn", type = "reconstructed", } m["qfa-onb-pro"] = { "Proto-Be", 116773192, "qfa-onb", "Latn", type = "reconstructed", } m["qfa-ong-pro"] = { "Proto-Ongan", 116773801, "qfa-ong", "Latn", type = "reconstructed", } m["qfa-tak-pro"] = { "Proto-Kra-Dai", 104901616, "qfa-tak", "Latn", type = "reconstructed", } m["qfa-yen-pro"] = { "Proto-Yeniseian", 27639, "qfa-yen", "Latn", type = "reconstructed", } m["qfa-yuk-pro"] = { "Proto-Yukaghir", 116773294, "qfa-yuk", "Latn", type = "reconstructed", } m["qwe-kch"] = { "Kichwa", 1740805, "qwe", "Latn", ancestors = "qu", } m["qwe-pro"] = { "Proto-Quechuan", 5575757, "qwe", "Latn", type = "reconstructed", } m["roa-ang"] = { "Angevin", 56782, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-bbn"] = { "Bourbonnais-Berrichon", 2899128, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-brg"] = { "Bourguignon", 508332, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-can"] = { "Cantabrian", 917021, "roa-asl", "Latn", } m["roa-cha"] = { "Champenois", 430018, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-fcm"] = { "Franc-Comtois", 510561, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-gal"] = { "Gallo", 37300, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-gib"] = { "Gallo-Italic of Basilicata", 3094838, "roa-git", ancestors = "pms-old", "Latn", } m["roa-gis"] = { "Gallo-Italic of Sicily", 2629019, "roa-git", "Latn", ancestors = "pms-old", } m["roa-leo"] = { "Leonese", 34108, "roa-asl", "Latn", } m["roa-lor"] = { "Lorrain", 671198, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-oca"] = { "Old Catalan", 15478520, "roa-ocr", "Latn", sort_key = {remove_diacritics = c.grave .. c.acute .. c.diaer .. c.cedilla .. "·"}, } m["roa-ole"] = { "Old Leonese", 125977465, "roa-asl", "Latn", } m["roa-ona"] = { "Old Navarro-Aragonese", 2736184, "roa-nar", "Latn", } m["roa-opt"] = { "Old Galician-Portuguese", 1072111, "roa-gap", "Latn", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.circ}, } m["roa-orl"] = { "Orléanais", 28497058, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-poi"] = { "Poitevin-Saintongeais", 514123, "roa-oil", "Latn", sort_key = s["roa-oil-sortkey"], } m["roa-tar"] = { "Tarantino", 695526, "roa-itr", "Latn", wikimedia_codes = "roa-tara", } m["sai-all"] = { "Allentiac", 19570789, "sai-hrp", "Latn", } m["sai-and"] = { -- not to be confused with 'cbc' or 'ano' "Andoquero", 16828359, "sai-wit", "Latn", } m["sai-ayo"] = { "Ayomán", 16937754, "sai-jir", "Latn", } m["sai-bae"] = { "Baenan", 3401998, "qfa-unc", -- extinct, poorly attested; only known through 9 words "Latn", } m["sai-bag"] = { "Bagua", 5390321, "qfa-unc", -- extinct, poorly attested; possibly Cariban "Latn", } m["sai-bet"] = { "Betoi", 926551, "qfa-iso", "Latn", } m["sai-bor-pro"] = { "Proto-Boran", nil, "sai-bor", "Latn", } m["sai-cac"] = { "Cacán", 945482, "qfa-unc", -- extinct, poorly attested; no consensus on classification "Latn", } m["sai-caq"] = { "Caranqui", 2937753, "sai-bar", "Latn", } m["sai-car-pro"] = { "Proto-Cariban", 116773196, "sai-car", "Latn", type = "reconstructed", } m["sai-cat"] = { "Catacao", 5051136, "sai-ctc", "Latn", } m["sai-cer-pro"] = { "Proto-Cerrado", 116773200, "sai-cer", "Latn", type = "reconstructed", } m["sai-chi"] = { "Chirino", 5390321, "qfa-unc", -- extinct, only four words known; possibly related to Candoshi-Shapra (cbu) "Latn", } m["sai-chn"] = { "Chaná", 5072718, "sai-crn", "Latn", } m["sai-chp"] = { "Chapacura", 5072884, "sai-cpc", "Latn", } m["sai-chr"] = { "Charrua", 5086680, "sai-crn", "Latn", } m["sai-chu"] = { "Churuya", 5118339, "sai-guh", "Latn", } m["sai-cje-pro"] = { "Proto-Central Jê", 116773198, "sai-cje", "Latn", type = "reconstructed", } m["sai-cmg"] = { "Comechingon", 6644203, "qfa-unc", -- extinct, poorly attested; no consensus on classification "Latn", } m["sai-cno"] = { "Chono", 5104704, "qfa-unc", -- extinct, poorly attested; no consensus on classification, possibly spurious "Latn", } m["sai-cnr"] = { "Cañari", 5055572, "qfa-unc", -- extinct, poorly attested; possibly Chimuan or Barbacoan "Latn", } m["sai-coe"] = { "Coeruna", 6425639, "sai-wit", "Latn", } m["sai-col"] = { "Colán", 5141893, "sai-ctc", "Latn", } m["sai-cop"] = { "Copallén", 5390321, "qfa-unc", -- extinct, only four words attested; possibly Cholonan "Latn", } m["sai-crd"] = { "Coroado Puri", 24191321, "sai-mje", "Latn", } m["sai-ctq"] = { "Catuquinaru", 16858455, "qfa-unc", -- extinct, poorly attested; vocabulary does not resemble other languages "Latn", } m["sai-cul"] = { "Culli", 2879660, "qfa-unc", -- extinct, poorly attested; often considered an isolate "Latn", } m["sai-cva"] = { "Cueva", 5192644, "qfa-unc", -- extinct, poorly attested; possibly Chocoan "Latn", } m["sai-esm"] = { "Esmeralda", 3058083, "qfa-unc", -- extinct, poorly attested; possibly related to Yaruro "Latn", } m["sai-ewa"] = { "Ewarhuyana", 16898104, nil, "Latn", } m["sai-gam"] = { "Gamela", 5403661, "qfa-unc", -- extinct, poorly attested; possibly an isolate "Latn", } m["sai-gay"] = { "Gayón", 5528902, "sai-jir", "Latn", } m["sai-gmo"] = { "Guamo", 5613495, "qfa-unc", -- extinct; "Kaufman (1990) finds a connection with the Chapacuran languages convincing." [Wikipedia] Considered an isolate by Campbell (2024). "Latn", } m["sai-gua"] = { "Guachí", 5613172, "sai-guc", "Latn", } m["sai-gue"] = { "Güenoa", 5626799, "sai-crn", "Latn", } m["sai-hau"] = { "Haush", 3128376, "sai-cho", "Latn", } m["sai-jee-pro"] = { "Proto-Jê", 116773212, "sai-jee", "Latn", type = "reconstructed", } m["sai-jko"] = { "Jeikó", 6176527, "sai-mje", "Latn", } m["sai-jrj"] = { "Jirajara", 6202966, "sai-jir", "Latn", } m["sai-kat"] = { -- contrast xoo, kzw, sai-xoc "Katembri", 6375925, "qfa-unc", -- extinct, poorly attested; "Kaufman (1990) has linked it with the nearly extinct Taruma, although this has not been accepted by other scholars." [Wikipedia] "Latn", } m["sai-mal"] = { "Malalí", 6741212, "sai-mje", -- considered the most divergent Maxakalían language (a subdivision of Macro-Jê), for which we have no entry "Latn", } m["sai-mar"] = { "Maratino", 6755055, "qfa-unc", -- extinct, poorly attested; possibly Uto-Aztecan "Latn", } m["sai-mat"] = { "Matanawi", 6786047, "qfa-unc", -- extinct; either an isolate or distantly related to the Muran languages; Campbell (2024) lists it as an isolate, Glottolog gives it as unclassified "Latn", } m["sai-mcn"] = { "Mocana", 3402048, "qfa-unc", -- extinct, poorly attested; given as part of the Malibu languages (geographic grouping; not a clade) "Latn", } m["sai-men"] = { "Menien", 16890110, "sai-mje", "Latn", } m["sai-mil"] = { "Millcayac", 19573012, "sai-hrp", "Latn", } m["sai-mlb"] = { "Malibu", 134374036, "qfa-unc", -- extinct, poorly attested; given as part of the Malibu languages (geographic grouping; not a clade) "Latn", } m["sai-msk"] = { "Masakará", 6782426, "sai-mje", "Latn", } m["sai-muc"] = { "Mucuchí", 6931290, nil, -- generally considered Timotean, for which we have no entry "Latn", } m["sai-mue"] = { "Muellama", 16886936, "sai-bar", "Latn", } m["sai-muz"] = { "Muzo", 6644203, "qfa-unc", -- extinct language of Colombia, poorly attested; may be Pijao (Cariban) "Latn", } m["sai-mys"] = { "Maynas", 16919393, "sai-cah", -- per Campbell (2024); formerly considered unclassified "Latn", } m["sai-nat"] = { "Natú", 9006749, "qfa-unc", -- extinct, poorly attested; "only Greenberg dares to classify [it]".[Wikipedia, quoting Moseley, Christopher; Asher, R. E.; Tait, Mary (1994), Atlas of the world's languages] "Latn", } m["sai-nje-pro"] = { "Proto-Northern Jê", 116773245, "sai-nje", "Latn", type = "reconstructed", } m["sai-opo"] = { "Opón", 7099152, "sai-car", "Latn", } m["sai-oto"] = { "Otomaco", 16879234, "sai-otm", "Latn", } m["sai-pal"] = { "Palta", 3042978, "qfa-unc", -- extinct, unclassified; possibly Chicham "Latn", } m["sai-pam"] = { "Pamigua", 5908689, "sai-tin", "Latn", } m["sai-par"] = { "Paratió", 16890038, "qfa-unc", -- extinct, poorly attested; possibly Xukuruan "Latn", } m["sai-peb"] = { "Peba", 3373890, "sai-pey", "Latn", } m["sai-pnz"] = { "Panzaleo", 3123275, "qfa-unc", -- extinct, unclassified; possibly Paezan "Latn", } m["sai-prh"] = { "Puruhá", 3410994, "qfa-unc", -- extinct, poorly attested; possibly in a famil with Cañari "Latn", } m["sai-ptg"] = { "Patagón", 128807870, "sai-tar", -- extinct, only known from 4 words, which suggest Cariban lineage (Campbell 2024) "Latn", } m["sai-pur"] = { "Purukotó", 7261622, "sai-pem", "Latn", } m["sai-pyg"] = { "Payaguá", 7156643, "sai-guc", "Latn", } m["sai-pyk"] = { "Pykobjê", 98113977, "sai-nje", "Latn", } m["sai-qmb"] = { "Quimbaya", 7272043, "qfa-unc", -- extinct, might not exist; few known words "Latn", } m["sai-qtm"] = { "Quitemo", 7272651, "sai-cpc", "Latn", } m["sai-rab"] = { "Rabona", 6644203, "qfa-unc", -- extinct, poorly attested, mostly plant names; possibly Candoshi-Shapra "Latn", } m["sai-ram"] = { "Ramanos", 16902824, "qfa-unc", -- extinct, poorly attested, possibly an isolate; per Glottolog: "the minuscule wordlist ... shows no convincing resemblances to surrounding languages" "Latn", } m["sai-sac"] = { "Sácata", 5390321, "qfa-unc", -- extinct, only 3 words known; possibly Candoshí or Arawakan "Latn", } m["sai-san"] = { "Sanaviron", 16895999, "qfa-unc", -- extinct, unclassified; no consensus on classification "Latn", } m["sai-sap"] = { "Sapará", 7420922, "sai-car", "Latn", } m["sai-sec"] = { "Sechura", 7442912, "qfa-unc", -- extinct, poorly attested; possibly Catacaoan "Latn", } m["sai-sin"] = { "Sinúfana", 7525275, "qfa-unc", -- moribund, poorly attested; possibly Chocoan "Latn", } m["sai-sje-pro"] = { "Proto-Southern Jê", 116773814, "sai-sje", "Latn", type = "reconstructed", } m["sai-tab"] = { "Tabancale", 5390321, "qfa-unc", -- extinct, only 5 words known; no obvious connections, might be an isolate "Latn", } m["sai-tal"] = { "Tallán", 16910468, "qfa-unc", -- extinct, poorly attested; might be Catacaoan "Latn", } m["sai-tap"] = { "Tapayuna", 30719984, "sai-nje", "Latn", } m["sai-tar-pro"] = { "Proto-Taranoan", 116773816, "sai-tar", "Latn", type = "reconstructed", } m["sai-teu"] = { "Teushen", 3519243, "qfa-unc", -- probably extinct by the 1950's; possibly Chonan "Latn", } m["sai-tim"] = { "Timote", 7806995, nil, -- possibly in a small Timotean family "Latn", } m["sai-tpr"] = { "Taparita", 7684460, "sai-otm", "Latn", } m["sai-trr"] = { "Tarairiú", 7685313, "qfa-unc", -- extinct, too poorly attested to classify "Latn", } m["sai-wai"] = { "Waitaká", 16918610, "qfa-unc", -- extinct, possibly Purian "Latn", } m["sai-way"] = { "Wayumara", 7960726, "sai-car", "Latn", } m["sai-wit-pro"] = { "Proto-Witotoan", 116773823, "sai-wit", "Latn", type = "reconstructed", } m["sai-wnm"] = { "Wanham", 16879440, "sai-cpc", "Latn", } m["sai-xoc"] = { -- contrast xoo, kzw, sai-kat "Xocó", 12953620, "qfa-unc", -- extinct and poorly attested; not clear if one or three languages "Latn", } m["sai-yao"] = { "Yao (South America)", 16979655, "sai-ven", "Latn", } m["sai-yar"] = { -- not the same family as 'suy' "Yarumá", 3505859, "sai-pek", "Latn", } m["sai-yri"] = { "Yuri", 2669157, "sai-tyu", "Latn", } m["sai-yup"] = { "Yupua", 8061430, "sai-tuc", "Latn", } m["sai-yur"] = { "Yurumanguí", 1281291, "qfa-unc", -- extinct, too poorly attested to classify "Latn", } m["sal-pro"] = { "Proto-Salish", 116773269, "sal", "Latn", type = "reconstructed", } m["sdv-daj-pro"] = { "Proto-Daju", 116773739, "sdv-daj", "Latn", type = "reconstructed", } m["sdv-eje-pro"] = { "Proto-Eastern Jebel", 116773751, "sdv-eje", "Latn", type = "reconstructed", } m["sdv-nil-pro"] = { "Proto-Nilotic", 116773794, "sdv-nil", "Latn", type = "reconstructed", } m["sdv-nyi-pro"] = { "Proto-Nyima", 116773796, "sdv-nyi", "Latn", type = "reconstructed", } m["sdv-tmn-pro"] = { "Proto-Taman", 116773815, "sdv-tmn", "Latn", type = "reconstructed", } m["sel-nor"] = { "Northern Selkup", 30304565, "sel", "Cyrl", translit = "sel-nor-translit", } m["sel-pro"] = { "Proto-Selkup", 128884235, "sel", "Latn", type = "reconstructed", } m["sel-sou"] = { "Southern Selkup", 30304639, "sel", "Cyrl", translit = "sel-sou-translit", } m["sem-amm"] = { "Ammonite", 279181, "sem-can", "Phnx", -- Phnx translit in [[Module:scripts/data]] } m["sem-amo"] = { "Amorite", 35941, "sem-nwe", "Xsux, Latn", } m["sem-cha"] = { "Chaha", 35543, "sem-eth", "Ethi", translit = "Ethi-translit", } m["sem-dad"] = { "Dadanitic", 21838040, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-dum"] = { "Dumaitic", 128810397, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-has"] = { "Hasaitic", 3541433, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-his"] = { "Hismaic", 22948260, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-mhr"] = { "Muher", 33743, "sem-eth", "Latn", } m["sem-pro"] = { "Proto-Semitic", 1658554, "sem", "Latn", type = "reconstructed", } m["sem-saf"] = { "Safaitic", 472586, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-sam"] = { "Samalian", 85847147, "sem-nwe", "Phnx", -- Phnx translit in [[Module:scripts/data]] } m["sem-srb"] = { "Old South Arabian", 35025, "sem-osa", "Sarb", -- Sarb translit in [[Module:scripts/data]] } m["sem-tay"] = { "Taymanitic", 24912301, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-tha"] = { "Thamudic", 843030, "sem-cen", "Narb", -- Narb translit in [[Module:scripts/data]] } m["sem-wes-pro"] = { "Proto-West Semitic", 98021726, "sem-wes", "Latn", type = "reconstructed", } m["sio-pro"] = { -- NB this is not Proto-Siouan-Catawban 'nai-sca-pro' "Proto-Siouan", 34181, "sio", "Latn", type = "reconstructed", } m["sit-aao-pro"] = { "Proto-Central Naga", nil, "sit-aao", "Latn", type = "reconstructed", } m["sit-bai-pro"] = { "Proto-Bai", nil, "sit-bai", "Latn", type = "reconstructed", } m["sit-ban"] = { "Bangru", 56071779, "sit-hrs", "Latn", } m["sit-bdi-pro"] = { "Proto-Bodish", nil, "sit-bdi", "Latn", type = "reconstructed", } m["sit-bok"] = { "Bokar", 4938727, "sit-tan", "Latn, Tibt", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["sit-cai"] = { "Caijia", 5017528, "sit-cln", "Latn" } m["sit-cha"] = { "Chairel", 5068066, "sit-luu", "Latn", } m["sit-ers-pro"] = { "Proto-Ersuic", nil, "sit-ers", "Latn", type = "reconstructed", } m["sit-hrs-pro"] = { "Proto-Hrusish", 116773762, "sit-hrs", "Latn", type = "reconstructed", } m["sit-jap"] = { "Japhug", 3162245, "sit-egy", "Latn", } m["sit-kha-pro"] = { "Proto-Kham", 116773773, "sit-kha", "Latn", type = "reconstructed", } m["sit-khb-pro"] = { "Proto-Kho-Bwa", nil, "sit-khb", "Latn", type = "reconstructed", } m["sit-khp-pro"] = { "Proto-Puroik", nil, "sit-khb", "Latn", type = "reconstructed", } m["sit-khw-pro"] = { "Proto-Western Kho-Bwa", nil, "sit-khw", "Latn", type = "reconstructed", } m["sit-kon-pro"] = { "Proto-Northern Naga", nil, "sit-kon", "Latn", type = "reconstructed", } m["sit-liz"] = { "Lizu", 6660653, "sit-ers", "Latn", -- and Ersu Shaba } m["sit-lnj"] = { "Longjia", 17096251, "sit-cln", "Latn" } m["sit-lrn"] = { "Luren", 16946370, "sit-cln", "Latn" } m["sit-luu-pro"] = { "Proto-Luish", 116773783, "sit-luu", "Latn", type = "reconstructed", } m["sit-nas-pro"] = { "Proto-Naish", nil, "sit-nas", "Latn", type = "reconstructed", } m["sit-prn"] = { "Puiron", 7259048, "sit-zem", } m["sit-pro"] = { "Proto-Sino-Tibetan", 24839178, "sit", "Latn", type = "reconstructed", } m["sit-sit"] = { "Situ", 19840830, "sit-egy", "Latn", } m["sit-tam-pro"] = { "Proto-Tamangic", 117469295, "sit-tam", "Latn", type = "reconstructed", } m["sit-tan-pro"] = { "Proto-Tani", 116773284, "sit-tan", "Latn", -- needs verification type = "reconstructed", } m["sit-tgm"] = { "Tangam", 17041370, "sit-tan", "Latn", } m["sit-tng-pro"] = { "Proto-Tangkhulic", nil, "sit-tng", "Latn", type = "reconstructed" } m["sit-tos"] = { "Tosu", 7827899, "sit-ers", "Latn", -- also Ersu Shaba } m["sit-tsh"] = { "Tshobdun", 19840950, "sit-egy", "Latn", } m["sit-zbu"] = { "Zbu", 19841106, "sit-egy", "Latn", } m["sla-pro"] = { "Proto-Slavic", 747537, "sla", "Latn", type = "reconstructed", strip_diacritics = { remove_diacritics = c.grave .. c.acute .. c.tilde .. c.macron .. c.dgrave .. c.invbreve, remove_exceptions = {'ś'}, }, sort_key = { from = {"č", "ď", "ě", "ę", "ь", "ľ", "ň", "ǫ", "ř", "š", "ś", "ť", "ъ", "ž"}, to = {"c²", "d²", "e²", "e³", "i²", "l²", "nj", "o²", "r²", "s²", "s³", "t²", "u²", "z²"}, } } m["smi-pro"] = { "Proto-Samic", 7251862, "smi", "Latn", type = "reconstructed", sort_key = { from = {"ā", "č", "δ", "[ëē]", "ŋ", "ń", "ō", "š", "θ", "%([^()]+%)"}, to = {"a", "c²", "d", "e", "n²", "n³", "o", "s²", "t²"} }, } m["son-pro"] = { "Proto-Songhay", 116773277, "son", "Latn", type = "reconstructed", } m["sqj-pro"] = { "Proto-Albanian", 18210846, "sqj", "Latn", type = "reconstructed", } m["ssa-klk-pro"] = { "Proto-Kuliak", 116773779, "ssa-klk", "Latn", type = "reconstructed", } m["ssa-kom-pro"] = { "Proto-Koman", 116773775, "ssa-kom", "Latn", type = "reconstructed", } m["ssa-pro"] = { "Proto-Nilo-Saharan", 116773236, "ssa", "Latn", type = "reconstructed", } m["syd-pro"] = { "Proto-Samoyedic", 7251863, "syd", "Latn", type = "reconstructed", } m["tai-pro"] = { "Proto-Tai", 6583709, "tai", "Latn", type = "reconstructed", } m["tai-swe-pro"] = { "Proto-Southwestern Tai", 116773280, "tai-swe", "Latn", type = "reconstructed", } m["tbq-bdg-pro"] = { "Proto-Bodo-Garo", 116773195, "tbq-bdg", "Latn", type = "reconstructed", } m["tbq-blg"] = { "Bailang", 2879843, "tbq-lob", "Hani", sort_key = "Hani-sortkey", } m["tbq-brm-pro"] = { "Proto-Burmish", nil, "tbq-brm", "Latn", type = "reconstructed", } m["tbq-gkh"] = { "Gokhy", 5578069, "tbq-sil", "Latn", } m["tbq-kuk-pro"] = { "Proto-Kuki-Chin", 116773220, "tbq-kuk", "Latn", type = "reconstructed", } m["tbq-lal-pro"] = { "Proto-Lalo", 116773781, "tbq-lal", "Latn", type = "reconstructed", } m["tbq-laz"] = { "Laze", 17007626, "sit-nas", "Latn", } m["tbq-lob-pro"] = { "Proto-Lolo-Burmese", 116773224, "tbq-lob", "Latn", type = "reconstructed", } m["tbq-lol-pro"] = { "Proto-Loloish", 7251855, "tbq-lol", "Latn", type = "reconstructed", } m["tbq-mil"] = { "Milang", 6850761, "sit-gsi", "Deva, Latn", } m["tbq-mor"] = { "Moran", 6909216, "tbq-bdg", "Latn", } m["tbq-ngo"] = { "Ngochang", 56582, "tbq-brm", "Latn", } -- tbq-pro is now etymology-only m["trk-dkh"] = { "Dukhan", 12809273, "trk-ssb", "Latn, Cyrl, Mong", -- Mong translit, display_text and strip_diacritics in [[Module:scripts/data]] } -- As described in Mahmud al-Kashgari's 11th century ''Dīwān Lughāt al-Turk''. m["trk-eog"] = { "Early Old Oghuz", nil, "trk-ogz", "ota-Arab", strip_diacritics = {["ota-Arab"] = "ar-stripdiacritics"}, } m["trk-oat"] = { "Old Anatolian Turkish", 7083390, "trk-ogz", "ota-Arab", strip_diacritics = {["ota-Arab"] = "ar-stripdiacritics"}, ancestors = "trk-eog", } m["trk-pro"] = { "Proto-Turkic", 3657773, "trk", "Latn", type = "reconstructed", standard_chars = { Latn = " ()-abdegiklmnoprstuxyzïöüāčēīĺŋōŕšūǖȫẹ" .. c.macron, } } m["tup-gua-pro"] = { "Proto-Tupi-Guarani", 116773288, "tup-gua", "Latn", type = "reconstructed", } m["tup-kab"] = { "Kabishiana", 15302988, "tup", "Latn", } m["tup-pro"] = { "Proto-Tupian", 10354700, "tup", "Latn", type = "reconstructed", } m["tuw-alk"] = { "Alchuka", 113553616, "tuw-jrc", "Latn, Hans", sort_key = {Hans = "Hani-sortkey"}, } m["tuw-bal"] = { "Bala", 86730632, "tuw-jrc", "Latn, Hans", sort_key = {Hans = "Hani-sortkey"}, } m["tuw-kkl"] = { "Kyakala", 118875708, "tuw-jrc", "Latn, Hans", sort_key = {Hans = "Hani-sortkey"}, } m["tuw-kli"] = { "Kili", 6406892, "tuw-ewe", "Cyrl", } m["tuw-pro"] = { "Proto-Tungusic", 85872335, "tuw", "Latn", type = "reconstructed", } m["tuw-sol"] = { "Solon", 30004, "tuw-ewe", } m["urj-fin-pro"] = { "Proto-Finnic", 11883720, "urj-fin", "Latn", type = "reconstructed", } m["urj-koo"] = { "Old Komi", 86679962, "kv", "Perm, Cyrs", translit = "urj-koo-translit", -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]]; previously, Cyrs strip_diacritics not present } m["urj-kuk"] = { "Kukkuzi", 107410460, "urj-fin", "Latn", ancestors = "vot", } m["urj-kya"] = { "Komi-Yazva", 2365210, "kv", "Cyrl", translit = "kv-translit", override_translit = true, strip_diacritics = {remove_diacritics = c.acute}, } m["urj-mdv-pro"] = { "Proto-Mordvinic", 116773232, "urj-mdv", "Latn", type = "reconstructed", } m["urj-prm-pro"] = { "Proto-Permic", 116773257, "urj-prm", "Latn", type = "reconstructed", } m["urj-pro"] = { "Proto-Uralic", 288765, "urj", "Latn", type = "reconstructed", } m["urj-ugr-pro"] = { "Proto-Ugric", 156631, "urj-ugr", "Latn", type = "reconstructed", } m["xnd-pro"] = { "Proto-Na-Dene", 116773233, "xnd", "Latn", type = "reconstructed", } m["xgn-pro"] = { "Proto-Mongolic", 2493677, "xgn", "Latn", type = "reconstructed", sort_key = { from = {"č", "i", "ï", "ǰ", "ŋ", "ö", "š", "ü"}, to = {"c", "i" .. p[1], "i", "j", "n" .. p[1], "o" .. p[1], "s" .. p[1], "u" .. p[1]}, }, } m["yok-bvy"] = { "Buena Vista Yokuts", 4985474, "yok", "Latn", } m["yok-dly"] = { "Delta Yokuts", 70923266, "yok", "Latn", } m["yok-gsy"] = { "Gashowu Yokuts", 3098708, "yok", "Latn", } m["yok-kry"] = { "Kings River Yokuts", 6413014, "yok", "Latn", } m["yok-nvy"] = { "Northern Valley Yokuts", 85789777, "yok", "Latn", } m["yok-ply"] = { "Palewyami Yokuts", 2387391, "yok", "Latn", } m["yok-svy"] = { "Southern Valley Yokuts", 12642473, "yok", "Latn", } m["yok-tky"] = { "Tule-Kaweah Yokuts", 7851988, "yok", "Latn", } m["ypk-pro"] = { "Proto-Yupik", 116773295, "ypk", "Latn", type = "reconstructed", } m["yrk-for"] = { "Forest Nenets", 1295107, "yrk", "Cyrl", translit = "yrk-for-translit", strip_diacritics = {remove_diacritics = c.grave .. c.acute .. c.macron .. c.breve .. c.dotabove}, } m["yrk-tun"] = { "Tundra Nenets", 36452, "yrk", "Cyrl", strip_diacritics = { from = {"ӑ", "а̄", "э̇", "ӣ", "ы̄", "ӯ", "ю̄", "я̆", "я̄"}, to = {"а", "а", "э", "и", "ы", "у", "ю", "я", "я"}, }, translit = "yrk-tun-translit", } m["zhx-min-pro"] = { "Proto-Min", 19646347, "zhx-min", "Latn", type = "reconstructed", } m["zhx-sht"] = { "Shaozhou Tuhua", 1920769, "zhx", "Nshu, Hants", generate_forms = "zh-generateforms", sort_key = {Hani = "Hani-sortkey"}, } m["zhx-sic"] = { "Sichuanese", 2278732, "zhx-man", "Hants", generate_forms = "zh-generateforms", translit = "zh-translit", sort_key = "Hani-sortkey", } m["zhx-tai"] = { "Taishanese", 2208940, "zhx-yue", "Hants", generate_forms = "zh-generateforms", translit = "zh-translit", sort_key = "Hani-sortkey", } m["zle-ono"] = { "Old Novgorodian", 162013, "zle", "Cyrs, Glag", translit = {Cyrs = "Cyrs-translit", Glag = "Glag-translit"}, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]] } m["zle-ort"] = { "Old Ruthenian", 13211, "zle", "Arab, Cyrs, Latn", ancestors = "orv", translit = { Cyrs = "zle-ort-translit", Arab = "zle-ort-Arab-translit", }, strip_diacritics = { Cyrs = { remove_diacritics = m_langdata.chars_substitutions["Cyrs_remove_diacritics"], remove_exceptions = {"Ї", "ї"}, }, Arab = "ar-stripdiacritics", }, -- Cyrs sort_key in [[Module:scripts/data]] } m["zls-chs"] = { "Church Slavonic", 33251, "zls", "Cyrs, Glag, Latn", ancestors = "cu", translit = { Cyrs = "Cyrs-translit", Glag = "Glag-translit" }, -- Cyrs strip_diacritics, sort_key in [[Module:scripts/data]] } m["zlw-ocs"] = { "Old Czech", 593096, "zlw", "Latn", } m["zlw-opl"] = { "Old Polish", 149838, "zlw-lch", "Latn", strip_diacritics = {remove_diacritics = c.ringabove}, } m["zlw-osk"] = { "Old Slovak", 12776676, "zlw", "Latn", } m["zlw-slv"] = { "Slovincian", 36822, "zlw-pom", "Latn", strip_diacritics = {remove_diacritics = c.macron .. c.breve}, } return require("Module:languages").finalizeData(m, "language") dta3mfxmgotlnmw6jci99rv4a6o9oox 828 5989 17426 2026-07-13T08:39:35Z Hiyuune 6766 + 17426 Scribunto text/plain local ipairs = ipairs --[==[ Iterates through a table using `ipairs` in reverse. `__ipairs` metamethods will be used, including those which return arbitrary (i.e. non-array) keys, but note that this function assumes that the first return value is a key which can be used to retrieve a value from the input table via a table lookup. As such, `__ipairs` metamethods for which this assumption is not true will not work correctly. If the value `nil` is encountered early (e.g. because the table has been modified), the loop will terminate early.]==] return function(t) -- `__ipairs` metamethods can return arbitrary keys, so compile a list. local keys, i = {}, 0 for k in ipairs(t) do i = i + 1 keys[i] = k end return function() if i == 0 then return nil end local k = keys[i] -- Retrieve `v` from the table. These aren't stored during the initial -- ipairs loop, so that they can be modified during the loop. local v = t[k] -- Return if not an early nil. if v ~= nil then i = i - 1 return k, v end end end g7u5t487acciyypwe4jwka7ibmfy9m2 828 5990 17427 2026-07-13T08:39:58Z Hiyuune 6766 + 17427 Scribunto text/plain local m = {} m["abjad"] = { "abjad", 185087, otherNames = {"consonantary", "consonantal alphabet"}, } m["abugida"] = { "abugida", 335806, otherNames = {"alphasyllabary"}, } m["alphabet"] = { "alphabet", 9779, category = "alphabetic writing system", } m["logography"] = { "logography", 3953107, otherNames = {"ideography"}, category = "logographic writing system", } m["pictography"] = { "pictography", 860735, category = "pictographic writing system", } m["semisyllabary"] = { "semisyllabary", 3781304, otherNames = {"semi-syllabary"}, } m["syllabary"] = { "syllabary", 182133, } return require("Module:languages").finalizeData(m, "writing system") kg18gfc02y6mi29hadprv64y8e0afuo 828 5991 17428 2026-07-13T08:40:40Z Hiyuune 6766 + 17428 Scribunto text/plain local next = next local pairs = pairs --[==[ This returns the size of a key/value pair table. If `raw` is set, then metamethods will be ignored, giving the true table size. For arrays, it is faster to use `export.length`.]==] return function(t, raw) local i, iter, state, init = 0 if raw then iter, state, init = next, t, nil else iter, state, init = pairs(t) end for _ in iter, state, init do i = i + 1 end return i end cngitqlralebfbp34hnb48xd0vu0xxk 828 5992 17429 2026-07-13T08:41:03Z Hiyuune 6766 + 17429 Scribunto text/plain --[=[ Authors: [[User:kc_kennylau]], [[User:JohnC5]], [[User:Erutuon]], [[User:Suzukaze-c]], [[User:Theknightwho]], [[User:AryamanA]] --]=] local export = {} local regular_languages = require("Module:languages/code to canonical name") local etymology_languages = require("Module:etymology languages/code to canonical name") local families = require("Module:families/code to canonical name") function export.find_subtree(t, code) for _, val in ipairs(t) do if val.name == code then -- "name" is really code return {val} end local result = export.find_subtree(val, code) if result ~= nil then return result end end end local family_icon = "F" local variety_icon = "V" local proto_language_icon = family_icon local family_with_proto_language_icon = family_icon local function format_node(code, is_protolanguage_or_has_protolanguage, options) local canonical_name, category_name, class, icon, tooltip, lemma_count_text if regular_languages[code] then canonical_name = regular_languages[code] category_name = canonical_name:match(" [Ll]anguage$") and canonical_name or canonical_name .. " language" class = "familytree-lang" if is_protolanguage_or_has_protolanguage then class = class .. ' familytree-protolang' icon = proto_language_icon end -- Add lemma count if the lemma_count option is set and category name exists if options and options.lemma_count and category_name then page_count = mw.site.stats.pagesInCategory( canonical_name .. " lemmas", "pages" ) lemma_count_text = ' (' .. page_count .. ')' end elseif etymology_languages[code] then canonical_name = etymology_languages[code] class = "familytree-etymlang" icon = variety_icon tooltip = "Variety" elseif families[code] then canonical_name = families[code] category_name = (canonical_name:match(" [Ll]anguages$") or canonical_name:match(" [Ll]ects$")) and canonical_name or canonical_name .. " languages" class = "familytree-family" if is_protolanguage_or_has_protolanguage then class = class .. ' familytree-hasprotolang' icon = family_with_proto_language_icon else icon = family_icon end tooltip = "Language family" end return '<span class="' .. class .. '" ' .. (tooltip and 'title="' .. tooltip .. '"' or '') .. '>' .. '[[:Category:' .. (category_name or canonical_name) .. '|' .. canonical_name .. ' <span class="familytree-code">(' .. code .. ')</span>]]' .. (icon and ' <span class="familytree-icon">' .. icon .. '</span>' or '') -- Include lemma count text if available .. (lemma_count_text or '') .. '</span>' end -- If neither options.show_all_families or options.show_etymology_languages is -- falsy, then this function does nothing. local function filter_nested_data(nested_data, options, protolanguage_of, is_protolanguage) if not nested_data then -- ??? return nil else local name = nested_data.name local first_child = nested_data[1] -- This indicates that new_nested_data below should only be returned -- if it contains non-etymology languages. local check_for_non_etymology_children = false -- If `show_all_families` is false and this is a family and its only -- child is its proto-language, then replace the family with the -- proto-language. if options.hide_families_with_protolanguages and name and families[name] and first_child and not nested_data[2] and protolanguage_of[name] == first_child.name then is_protolanguage[first_child.name] = true return filter_nested_data(first_child, options, protolanguage_of, is_protolanguage) elseif options.hide_etymology_languages and etymology_languages[name] then if nested_data[1] then check_for_non_etymology_children = true else return nil end end local new_nested_data = { name = name } local i = 0 for _, subtable in ipairs(nested_data) do subtable = filter_nested_data(subtable, options, protolanguage_of, is_protolanguage) if subtable then i = i + 1 new_nested_data[i] = subtable end end if not check_for_non_etymology_children or new_nested_data[1] then return new_nested_data end end end local function make_node(code, is_protolanguage, protolanguage_of, options) return '</span> ' .. format_node(code, is_protolanguage[code] or protolanguage_of[code] ~= nil, options) end local function only_child_is_protolanguage(tree, options, protolanguage_of) return (options.family_under_protolanguage or options.protolanguage_under_family) and tree[1] and protolanguage_of[tree.name] == tree[1].name end export.are_all_children_etymology_languages = require("Module:memoize")(function (nested_data) if not nested_data[1] then return nil end for _, child in ipairs(nested_data) do if not etymology_languages[child.name] or export.are_all_children_etymology_languages(child) == false then return false end end return true end) local customcollapsible_number = 0 local customcollapsible_prefix = "familytree" local function get_customcollapsible_id() customcollapsible_number = customcollapsible_number + 1 return customcollapsible_prefix .. customcollapsible_number end local no_break_space = "\194\160" local level_separator = (no_break_space):rep(3) local expandtext, collapsetext = "[+]─", "[-]┬" local function make_tree(data, is_protolanguage, protolanguage_of, options, prefix) local result = {} local function ins(val) table.insert(result, val) end -- This tag is closed in the node generated by make_node. prefix = prefix or '<span class="familytree-linedrawing">' local branch = "├" local next_level = prefix .. "│" .. level_separator local length = #data for i, val in ipairs(data) do if i == length then branch = "└" next_level = prefix .. level_separator .. no_break_space end local code = val.name local language_or_family_node = make_node(code, is_protolanguage, protolanguage_of, options) if not val[1] then ins('<li>' .. prefix .. branch .. options.sterile_branch_text .. language_or_family_node .. '</li>') else local customcollapsible_id = get_customcollapsible_id() ins('<li>' .. prefix .. branch .. '<span class="familytree-toggle mw-customtoggle-' .. customcollapsible_id .. '">───┬</span>') -- name me! local flag = (options.family_under_protolanguage or options.protolanguage_under_family) and only_child_is_protolanguage(val, options, protolanguage_of) local top_node if flag then code = val[1].name val = val[1] top_node = make_node(code, is_protolanguage, protolanguage_of, options) if options.protolanguage_under_family then top_node, language_or_family_node = language_or_family_node, top_node end end local all_children_are_etymology_languages = export.are_all_children_etymology_languages(val) local collapsible_ul = '<ul class="mw-collapsible' .. (all_children_are_etymology_languages and ' familytree-only-etym-children' or '') .. '" ' .. 'id="mw-customcollapsible-' .. customcollapsible_id .. '" data-expandtext="' .. expandtext .. '" data-collapsetext="' .. collapsetext .. '">' if flag then ins(top_node .. collapsible_ul .. '<li>' .. prefix .. (i == length and no_break_space or "│") .. level_separator .. "│") end ins(language_or_family_node) if not flag then ins(collapsible_ul) end -- Can't get default collapsibility script to apply the data-expandtext -- and data-collapsetext attribute values to the custom toggle, -- so have to have a custom script do it. ins(make_tree(val, is_protolanguage, protolanguage_of, options, next_level)) ins('</ul></li>') end end return table.concat(result) end local function get_number_parameter_in_range(args, arg, low, high) local val = args[arg] if val == "" or val == nil then val = nil else val = tonumber(val) if not (type(val) == "number" and 0 <= val and val <= 6) then error("Expected nothing or number between " .. low .. " and " .. high .. " in parameter |" .. arg .. "=.") end end return val end function export.show(frame) local args = frame.args local descendants_of = args[1] local to_boolean = require("Module:yesno") -- Determines whether families that have proto-languages will be shown. local show_all_families = to_boolean(args[2] or args.fam) -- Determines whether all etymology languages will be shown. local show_etymology_languages = to_boolean(args[3] or args.etym) -- Get the value for lemma_count argument local lemma_count = to_boolean(args.lemma_count) -- help! parameter name too long! local sterile_branch_length = get_number_parameter_in_range(args, "sterile_branch_length", 0, 6) -- Determines whether (if all families are shown) a family will be shown -- on a line directly under and at the same level as its proto-language, -- or the proto-language on a line directly under and at the same level as -- its family. local family_under_protolanguage = to_boolean(args.famunderproto) local protolanguage_under_family = to_boolean(args.protounderfam) if family_under_protolanguage and protolanguage_under_family then error("Kindly choose between proto-language under family and family under proto-language.") end return export.print_children(descendants_of, { hide_families_with_protolanguages = not show_all_families, hide_etymology_languages = not show_etymology_languages, family_under_protolanguage = family_under_protolanguage, protolanguage_under_family = protolanguage_under_family, sterile_branch_length = sterile_branch_length, collapsed = require("Module:yesno")(args.collapsed), lemma_count = lemma_count }) end function export.print_children(descendants_of, options) local m_languages = require("Module:languages") local m_table = require("Module:table") local make_auto_subtabler = require("Module:auto-subtable") descendants_of = m_languages.getByCode(descendants_of, nil, true, true) local names = {} local protolanguage_of = {} local children = make_auto_subtabler{} local descendants = descendants_of:getDescendantCodes() table.insert(descendants, descendants_of:getCode()) if descendants_of:hasType("family") then protolanguage_of[descendants_of:getCode()] = descendants_of:getProtoLanguageCode() end local memoized = {} local get = function(code, func, ...) local ret = memoized[code] or func(...) if code then memoized[code] = ret end return ret end for _, descendant_code in ipairs(descendants) do -- Inner "repeat until true" loop allows break to work like continue, as it will always only run once. repeat local descendant = get(descendant_code, m_languages.getByCode, descendant_code, nil, true, true) names[descendant_code] = descendant:getCanonicalName():gsub("Proto%-", "") if descendant:hasType("language") then local ancestors = m_table.shallowCopy(descendant:getAncestorCodes()) local parent_code = descendant:getParentCode() if parent_code and descendant:hasType("etymology-only") then local parent = get(parent_code, descendant.getParent, descendant) if m_table.deepEquals(parent:getAncestorCodes(), ancestors) and descendant:getFamilyCode() == parent:getFamilyCode() then table.insert(children[parent:getCode()], descendant_code) break end end if #ancestors > 0 then for _, ancestor in ipairs(ancestors) do table.insert(children[ancestor], descendant_code) end break end else local protolang = descendant:getProtoLanguageCode() protolanguage_of[descendant_code] = protolang if protolang and descendant:hasAncestor(protolang) then table.insert(children[protolang], descendant_code) break end end local family_code = descendant:getFamilyCode() if family_code then local family = get(family_code, descendant.getFamily, descendant) local protolang = get(family:getProtoLanguageCode(), family.getProtoLanguage, family) if not protolanguage_of[family] then protolanguage_of[family] = protolang and protolang:getCode() end if protolang and protolang:inFamily(family) and protolang:getCode() ~= descendant_code then table.insert(children[protolang:getCode()], descendant_code) else table.insert(children[family:getCode()], descendant_code) end end until true end -- No more auto subtabling needed. children = children:un_auto_subtable() -- Copy to new table, to filter out unwanted ancestors from descendants with multiple ancestors, where some are not descendants of the target language. local parent_to_children_map = {} for _, code in ipairs(descendants) do parent_to_children_map[code] = children[code] end local function make_nested(data, children) local make_nil = {} for key, val in pairs(data) do if type(key) == "number" then if children[val] then data[val] = make_nested(children[val], children) table.insert(make_nil, key) end else data[key] = make_nested(val, children) end end if make_nil[2] then -- Make sure larger keys are removed first. table.sort(make_nil, function (a, b) return a > b end) end for _, key in ipairs(make_nil) do table.remove(data, key) end return data end local nested = make_nested(parent_to_children_map, parent_to_children_map) local function deep_sort(current) local result = {} local is_table = {} for key, val in pairs(current) do if type(key) == "number" then table.insert(result, val) else is_table[key] = true table.insert(result, key) end end table.sort(result, function(code1, code2) return names[code1] < names[code2] end) for i = 1, #result do if is_table[result[i]] then local name = result[i] result[i] = deep_sort(current[result[i]]) result[i].name = name else result[i] = { name = result[i] } end end return result end nested = deep_sort(nested) data = { nested = nested, protolanguage_of = protolanguage_of } local nested_data, protolanguage_of = data.nested, data.protolanguage_of nested_data = export.find_subtree(nested_data, descendants_of:getCode()) -- Return nil instead of a tree with only the root node. if options.must_have_descendants and (nested_data == nil or #nested_data == 0 or nested_data[1] and #nested_data[1] == 0) then return nil end local is_protolanguage = {} if options.hide_families_with_protolanguages or options.hide_etymology_languages then nested_data = filter_nested_data(nested_data, { hide_families_with_protolanguages = options.hide_families_with_protolanguages, hide_etymology_languages = options.hide_etymology_languages, }, protolanguage_of, is_protolanguage) end if not nested_data or not next(nested_data) then return nil end local result = {'<div class="familytree"><ul>'} local function ins(val) table.insert(result, val) end local tree_options = { sterile_branch_text = '<span class="familytree-branch">' .. ("─"):rep(options.sterile_branch_length or 4) .. '</span>', family_under_protolanguage = options.family_under_protolanguage, protolanguage_under_family = options.protolanguage_under_family, lemma_count = options.lemma_count, } local collapsetext, expandtext = 'Collapse', 'Expand' for i, subtable in ipairs(nested_data) do -- top language name ins('<li>') -- name me! local flag = (options.family_under_protolanguage or options.protolanguage_under_family) and only_child_is_protolanguage(subtable, options, protolanguage_of) local top_node = format_node(subtable.name) local next_node if flag then subtable = subtable[1] next_node = format_node(subtable.name) if options.family_under_protolanguage then top_node, next_node = next_node, top_node end end ins(top_node) -- top toggle local customcollapsible_id = get_customcollapsible_id() ins('<span class="familytree-toptoggle mw-customtoggle-' .. customcollapsible_id .. '" style="display: none;">') ins(options.collapsed and expandtext or collapsetext) ins('</span>') if flag then ins('<li>') ins(next_node) end -- tree ins('<ul class="mw-collapsible') if options.collapsed then ins(' mw-collapsed') end ins('" id="mw-customcollapsible-' .. customcollapsible_id) ins('" data-expandtext="' .. expandtext) ins('" data-collapsetext="' .. collapsetext .. '">') ins(make_tree(subtable, is_protolanguage, protolanguage_of, tree_options)) if flag then ins('</li>') end ins('</ul></li>') end ins('</ul></div>') ins(require("Module:TemplateStyles")("Module:family tree/style.css")) return table.concat(result) end return export mnzwouf6sh0nymoc4nm2adgw0g71cs1 828 5993 17430 2026-07-13T08:41:27Z Hiyuune 6766 + 17430 Scribunto text/plain return { ["aa"] = "Afar", ["aaa"] = "Ghotuo", ["aab"] = "Alumu-Tesu", ["aac"] = "Ari", ["aad"] = "Amal", ["aaf"] = "Aranadan", ["aag"] = "Ambrak", ["aah"] = "Abu'", ["aai"] = "Arifama-Miniafia", ["aak"] = "Ankave", ["aal"] = "Afade", ["aan"] = "Anambé", ["aap"] = "Arára (Pará)", ["aaq"] = "Penobscot", ["aas"] = "Aasax", ["aau"] = "Abau", ["aav-khs-pro"] = "Proto-Khasian", ["aav-nic-pro"] = "Proto-Nicobarese", ["aav-pkl-pro"] = "Proto-Pnar-Khasi-Lyngngam", ["aav-pro"] = "Proto-Austroasiatic", ["aaw"] = "Solong", ["aax"] = "Upper Mandobo", ["aaz"] = "Amarasi", ["ab"] = "Abkhaz", ["aba"] = "Abé", ["abb"] = "Bankon", ["abc"] = "Ambala Ayta", ["abd"] = "Camarines Norte Agta", ["abe"] = "Abenaki", ["abf"] = "Abai Sungai", ["abg"] = "Abaga", ["abh"] = "Tajiki Arabic", ["abi"] = "Abidji", ["abj"] = "Aka-Bea", ["abl"] = "Abung", ["abm"] = "Abanyom", ["abn"] = "Abua", ["abo"] = "Abon", ["abp"] = "Abenlen Ayta", ["abq"] = "Abaza", ["abs"] = "Ambonese Malay", ["abt"] = "Ambulas", ["abu"] = "Abure", ["abv"] = "Baharna Arabic", ["abw"] = "Pal", ["abx"] = "Inabaknon", ["aby"] = "Aneme Wake", ["abz"] = "Abui", ["aca"] = "Achagua", ["acb"] = "Áncá", ["acd"] = "Gikyode", ["ace"] = "Acehnese", ["ach"] = "Acholi", ["aci"] = "Aka-Cari", ["ack"] = "Aka-Kora", ["acl"] = "Akar-Bale", ["acm"] = "Iraqi Arabic", ["acn"] = "Achang", ["acp"] = "Eastern Acipa", ["acr"] = "Achi", ["acs"] = "Acroá", ["acu"] = "Achuar", ["acv"] = "Achumawi", ["acw"] = "Hijazi Arabic", ["acx"] = "Omani Arabic", ["acy"] = "Cypriot Arabic", ["acz"] = "Acheron", ["ada"] = "Adangme", ["adb"] = "Atauran", ["add"] = "Dzodinka", ["ade"] = "Adele", ["adf"] = "Dhofari Arabic", ["adg"] = "Andegerebinha", ["adh"] = "Adhola", ["adi"] = "Adi", ["adj"] = "Adioukrou", ["adl"] = "Galo", ["adn"] = "Adang", ["ado"] = "Abu", ["adp"] = "Adap", ["adq"] = "Adangbe", ["adr"] = "Adonara", ["ads"] = "Adamorobe Sign Language", ["adt"] = "Adnyamathanha", ["adu"] = "Aduge", ["adw"] = "Amondawa", ["ady"] = "West Circassian", ["adz"] = "Adzera", ["ae"] = "Avestan", ["aea"] = "Areba", ["aeb"] = "Tunisian Arabic", ["aed"] = "Argentine Sign Language", ["aee"] = "Northeast Pashayi", ["aek"] = "Haeke", ["ael"] = "Ambele", ["aem"] = "Arem", ["aen"] = "Armenian Sign Language", ["aeq"] = "Aer", ["aer"] = "Eastern Arrernte", ["aes"] = "Alsea", ["aeu"] = "Akeu", ["aew"] = "Ambakich", ["aey"] = "Amele", ["aez"] = "Aeka", ["af"] = "Afrikaans", ["afa-pro"] = "Proto-Afroasiatic", ["afb"] = "Gulf Arabic", ["afd"] = "Andai", ["afe"] = "Putukwam", ["afg"] = "Afghan Sign Language", ["afh"] = "Afrihili", ["afi"] = "Akrukay", ["afk"] = "Nanubae", ["afn"] = "Defaka", ["afo"] = "Eloyi", ["afp"] = "Tapei", ["afs"] = "Afro-Seminole Creole", ["aft"] = "Afitti", ["afu"] = "Awutu", ["afz"] = "Obokuitai", ["aga"] = "Aguano", ["agb"] = "Legbo", ["agc"] = "Agatu", ["agd"] = "Agarabi", ["age"] = "Angal", ["agf"] = "Arguni", ["agg"] = "Angor", ["agh"] = "Ngelima", ["agi"] = "Agariya", ["agj"] = "Argobba", ["agk"] = "Isarog Agta", ["agl"] = "Fembe", ["agm"] = "Angaataha", ["agn"] = "Agutaynen", ["ago"] = "Tainae", ["agq"] = "Aghem", ["agr"] = "Aguaruna", ["ags"] = "Esimbi", ["agt"] = "Central Cagayan Agta", ["agu"] = "Aguacateca", ["agv"] = "Remontado Agta", ["agw"] = "Kahua", ["agx"] = "Aghul", ["agy"] = "Southern Alta", ["agz"] = "Mount Iriga Agta", ["aha"] = "Ahanta", ["ahb"] = "Axamb", ["ahg"] = "Qimant", ["ahh"] = "Aghu", ["ahi"] = "Tiagba", ["ahk"] = "Akha", ["ahl"] = "Igo", ["ahm"] = "Mobu", ["ahn"] = "Àhàn", ["aho"] = "Ahom", ["ahp"] = "Apro", ["ahr"] = "Ahirani", ["ahs"] = "Ashe", ["aht"] = "Ahtna", ["aia"] = "Arosi", ["aib"] = "Äynu", ["aic"] = "Ainbai", ["aid"] = "Alngith", ["aie"] = "Amara", ["aif"] = "Agi", ["aig"] = "Antigua and Barbuda Creole English", ["aih"] = "Ai-Cham", ["aii"] = "Assyrian Neo-Aramaic", ["aij"] = "Lishanid Noshan", ["aik"] = "Ake", ["ail"] = "Aimele", ["aim"] = "Aimol", ["ain"] = "Ainu", ["aio"] = "Aiton", ["aip"] = "Burumakok", ["air"] = "Airoran", ["ait"] = "Arikem", ["aiw"] = "Aari", ["aix"] = "Aighon", ["aiy"] = "Ali", ["aja"] = "Aja (East Africa)", ["ajg"] = "Aja (West Africa)", ["aji"] = "Ajië", ["ajn"] = "Andajin", ["ajp"] = "South Levantine Arabic", ["ajw"] = "Ajawa", ["ajz"] = "Amri Karbi", ["ak"] = "Akan", ["akb"] = "Angkola Batak", ["akc"] = "Mpur", ["akd"] = "Ukpet-Ehom", ["ake"] = "Akawaio", ["akf"] = "Akpa", ["akg"] = "Anakalangu", ["akh"] = "Angal Heneng", ["aki"] = "Aiome", ["akj"] = "Jeru", ["akk"] = "Akkadian", ["akl"] = "Aklanon", ["akm"] = "Aka-Bo", ["ako"] = "Akurio", ["akp"] = "Siwu", ["akq"] = "Ak", ["akr"] = "Araki", ["aks"] = "Akaselem", ["akt"] = "Akolet", ["aku"] = "Akum", ["akv"] = "Akhvakh", ["akw"] = "Akwa", ["akx"] = "Aka-Kede", ["aky"] = "Aka-Kol", ["akz"] = "Alabama", ["ala"] = "Alago", ["alc"] = "Kawésqar", ["ald"] = "Alladian", ["ale"] = "Aleut", ["alf"] = "Alege", ["alg-aga"] = "Agawam", ["alg-pro"] = "Proto-Algonquian", ["alh"] = "Alawa", ["ali"] = "Amaimon", ["alj"] = "Alangan", ["alk"] = "Alak", ["all"] = "Allar", ["alm"] = "Amblong", ["alo"] = "Larike-Wakasihu", ["alp"] = "Alune", ["alq"] = "Algonquin", ["alr"] = "Alutor", ["alt"] = "Southern Altai", ["alu"] = "'Are'are", ["alv-ama"] = "Amasi", ["alv-bgu"] = "Bainouk Gubeeher", ["alv-bua-pro"] = "Proto-Bua", ["alv-cng-pro"] = "Proto-Cangin", ["alv-edk-pro"] = "Proto-Edekiri", ["alv-edo-pro"] = "Proto-Edoid", ["alv-fli-pro"] = "Proto-Fali", ["alv-gbe-pro"] = "Proto-Gbe", ["alv-gng-pro"] = "Proto-Guang", ["alv-gtm-pro"] = "Proto-Central Togo", ["alv-gwa"] = "Gwara", ["alv-hei-pro"] = "Proto-Heiban", ["alv-ido-pro"] = "Proto-Idomoid", ["alv-igb-pro"] = "Proto-Igboid", ["alv-kwa-pro"] = "Proto-Kwa", ["alv-mum-pro"] = "Proto-Mumuye", ["alv-nup-pro"] = "Proto-Nupoid", ["alv-pro"] = "Proto-Atlantic-Congo", ["alv-von-pro"] = "Proto-Volta-Niger", ["alv-yor-pro"] = "Proto-Yoruba", ["alv-yrd-pro"] = "Proto-Yoruboid", ["alw"] = "Alaba", ["alx"] = "Amol", ["aly"] = "Alyawarr", ["alz"] = "Alur", ["am"] = "Amharic", ["ama"] = "Amanayé", ["amb"] = "Ambo", ["amc"] = "Amahuaca", ["ame"] = "Yanesha'", ["amf"] = "Hamer-Banna", ["amg"] = "Amurdag", ["ami"] = "Amis", ["amj"] = "Amdang", ["amk"] = "Ambai", ["aml"] = "War-Jaintia", ["amm"] = "Ama", ["amn"] = "Amanab", ["amo"] = "Amo", ["amp"] = "Alamblak", ["amq"] = "Amahai", ["amr"] = "Amarakaeri", ["ams"] = "Southern Amami Ōshima", ["amt"] = "Amto", ["amu"] = "Guerrero Amuzgo", ["amv"] = "Ambelau", ["amw"] = "Western Neo-Aramaic", ["amx"] = "Anmatyerre", ["amy"] = "Ami", ["amz"] = "Atampaya", ["an"] = "Aragonese", ["ana"] = "Andaqui", ["anb"] = "Andoa", ["anc"] = "Ngas", ["and"] = "Ansus", ["ane"] = "Xârâcùù", ["anf"] = "Animere", ["ang"] = "Old English", ["anh"] = "Nend", ["ani"] = "Andi", ["anj"] = "Anor", ["ank"] = "Goemai", ["anl"] = "Anu", ["anm"] = "Anāl", ["ann"] = "Obolo", ["ano"] = "Andoque", ["anp"] = "Angika", ["anq"] = "Jarawa", ["anr"] = "Andh", ["ans"] = "Anserma", ["ant"] = "Antakarinya", ["anu"] = "Anuak", ["anv"] = "Denya", ["anw"] = "Anaang", ["anx"] = "Andra-Hus", ["any"] = "Anyi", ["anz"] = "Anem", ["aoa"] = "Angolar", ["aob"] = "Abom", ["aoc"] = "Pemon", ["aod"] = "Andarum", ["aoe"] = "Angal Enen", ["aof"] = "Bragat", ["aog"] = "Angoram", ["aoi"] = "Anindilyakwa", ["aoj"] = "Mufian", ["aok"] = "Arhö", ["aol"] = "Alorese", ["aom"] = "Ömie", ["aon"] = "Bumbita Arapesh", ["aor"] = "Aore", ["aos"] = "Taikat", ["aot"] = "Atong (India)", ["aou"] = "A'ou", ["aox"] = "Atorada", ["aoz"] = "Uab Meto", ["apa-pro"] = "Proto-Apachean", ["apb"] = "Sa'a", ["apc"] = "North Levantine Arabic", ["apd"] = "Sudanese Arabic", ["ape"] = "Bukiyip", ["apf"] = "Pahanan Agta", ["apg"] = "Ampanang", ["aph"] = "Athpare", ["api"] = "Apiaká", ["apj"] = "Jicarilla", ["apk"] = "Plains Apache", ["apl"] = "Lipan", ["apm"] = "Chiricahua", ["apn"] = "Apinayé", ["apo"] = "Ambul", ["app"] = "Apma", ["apq"] = "A-Pucikwar", ["apr"] = "Arop-Lokep", ["aps"] = "Arop-Sissano", ["apt"] = "Apatani", ["apu"] = "Apurinã", ["apv"] = "Alapmunte", ["apw"] = "Western Apache", ["apx"] = "Aputai", ["apy"] = "Apalaí", ["apz"] = "Safeyoka", ["aqc"] = "Archi", ["aqd"] = "Ampari Dogon", ["aqg"] = "Arigidi", ["aql-pro"] = "Proto-Algic", ["aqm"] = "Atohwaim", ["aqn"] = "Northern Alta", ["aqp"] = "Atakapa", ["aqr"] = "Arhâ", ["aqt"] = "Angaité", ["aqz"] = "Akuntsu", ["ar"] = "Arabic", ["arc"] = "Aramaic", ["ard"] = "Arabana", ["are"] = "Western Arrernte", ["arh"] = "Arhuaco", ["ari"] = "Arikara", ["arj"] = "Arapaso", ["ark"] = "Arikapú", ["arl"] = "Arabela", ["arn"] = "Mapudungun", ["aro"] = "Araona", ["arp"] = "Arapaho", ["arq"] = "Algerian Arabic", ["arr"] = "Arara-Karo", ["ars"] = "Najdi Arabic", ["art-adu"] = "Adûni", ["art-bel"] = "Belter Creole", ["art-blk"] = "Bolak", ["art-bsp"] = "Black Speech", ["art-com"] = "Communicationssprache", ["art-dtk"] = "Dothraki", ["art-elo"] = "Eloi", ["art-gld"] = "Goa'uld", ["art-lap"] = "Lapine", ["art-man"] = "Mandalorian", ["art-mun"] = "Mundolinco", ["art-nav"] = "Naʼvi", ["art-vlh"] = "High Valyrian", ["aru"] = "Arua", ["arv"] = "Arbore", ["arw"] = "Lokono", ["arx"] = "Aruá", ["ary"] = "Moroccan Arabic", ["arz"] = "Egyptian Arabic", ["as"] = "Assamese", ["asa"] = "Pare", ["asb"] = "Assiniboine", ["asc"] = "Casuarina Coast Asmat", ["ase"] = "American Sign Language", ["asf"] = "Auslan", ["asg"] = "Cishingini", ["ash"] = "Abishira", ["asi"] = "Buruwai", ["asj"] = "Nsari", ["ask"] = "Ashkun", ["asl"] = "Asilulu", ["asn"] = "Xingú Asuriní", ["aso"] = "Dano", ["asp"] = "Algerian Sign Language", ["asq"] = "Austrian Sign Language", ["asr"] = "Asuri", ["ass"] = "Ipulo", ["ast"] = "Asturian", ["asu"] = "Tocantins Asurini", ["asv"] = "Asoa", ["asw"] = "Australian Aboriginal Sign Language", ["asx"] = "Muratayak", ["asy"] = "Yaosakor Asmat", ["asz"] = "As", ["ata"] = "Pele-Ata", ["atb"] = "Zaiwa", ["atc"] = "Atsahuaca", ["atd"] = "Ata Manobo", ["ate"] = "Atemble", ["atg"] = "Okpela", ["ath-nic"] = "Nicola", ["ath-pro"] = "Proto-Athabaskan", ["ati"] = "Attié", ["atj"] = "Atikamekw", ["atk"] = "Ati", ["atl"] = "Mount Iraya Agta", ["atm"] = "Ata", ["ato"] = "Atong (Cameroon)", ["atp"] = "Pudtol Atta", ["atq"] = "Aralle-Tabulahan", ["atr"] = "Waimiri-Atroari", ["ats"] = "Gros Ventre", ["att"] = "Pamplona Atta", ["atu"] = "Reel", ["atv"] = "Northern Altai", ["atw"] = "Atsugewi", ["atx"] = "Arutani", ["aty"] = "Aneityum", ["atz"] = "Arta", ["aua"] = "Asumboa", ["aub"] = "Alugu", ["auc"] = "Huaorani", ["aud"] = "Anuta", ["auf-pro"] = "Proto-Arawa", ["aug"] = "Aguna", ["auh"] = "Aushi", ["aui"] = "Anuki", ["auj"] = "Awjila", ["auk"] = "Heyo", ["aul"] = "Aulua", ["aum"] = "Asu", ["aun"] = "Molmo One", ["auo"] = "Auyokawa", ["aup"] = "Makayam", ["auq"] = "Anus", ["aur"] = "Aruek", ["aus-alu"] = "Alungul", ["aus-and"] = "Andjingith", ["aus-ang"] = "Angkula", ["aus-arn-pro"] = "Proto-Arnhem", ["aus-bra"] = "Barranbinya", ["aus-brm"] = "Barunggam", ["aus-cww-pro"] = "Proto-Central New South Wales", ["aus-dal-pro"] = "Proto-Daly", ["aus-guw"] = "Guwar", ["aus-lsw"] = "Little Swanport", ["aus-mbi"] = "Mbiywom", ["aus-ngk"] = "Ngkoth", ["aus-nyu-pro"] = "Proto-Nyulnyulan", ["aus-pam-pro"] = "Proto-Pama-Nyungan", ["aus-tul"] = "Tulua", ["aus-uwi"] = "Uwinymil", ["aus-wdj-pro"] = "Proto-Iwaidjan", ["aus-won"] = "Wong-gie", ["aus-wul"] = "Wulguru", ["aus-ynk"] = "Yangkaal", ["aut"] = "Austral", ["auu"] = "Auye", ["auw"] = "Awyi", ["aux"] = "Aurá", ["auy"] = "Auyana", ["auz"] = "Uzbeki Arabic", ["av"] = "Avar", ["avb"] = "Avau", ["avd"] = "Alviri-Vidari", ["avi"] = "Avikam", ["avk"] = "Kotava", ["avm"] = "Angkamuthi", ["avn"] = "Avatime", ["avo"] = "Agavotaguerra", ["avs"] = "Aushiri", ["avt"] = "Au", ["avu"] = "Avokaya", ["avv"] = "Avá-Canoeiro", ["awa"] = "Awadhi", ["awb"] = "Awa (New Guinea)", ["awc"] = "Cicipu", ["awd-ama"] = "Amarizana", ["awd-amc-pro"] = "Proto-Amuesha-Chamicuro", ["awd-ana"] = "Anauyá", ["awd-apo"] = "Apolista", ["awd-cab"] = "Cabre", ["awd-gnu"] = "Guinau", ["awd-kar"] = "Cariay", ["awd-kaw"] = "Kawishana", ["awd-kmp-pro"] = "Proto-Kampa", ["awd-kus"] = "Kustenau", ["awd-man"] = "Manao", ["awd-mar"] = "Marawan", ["awd-mpr"] = "Maipure", ["awd-mrt"] = "Mariaté", ["awd-nwk-pro"] = "Proto-Nawiki", ["awd-pai"] = "Paikoneka", ["awd-pas"] = "Pasé", ["awd-pro"] = "Proto-Arawak", ["awd-prw-pro"] = "Proto-Paresi-Waura", ["awd-she"] = "Shebayo", ["awd-taa-pro"] = "Proto-Ta-Arawak", ["awd-wai"] = "Wainumá", ["awd-yum"] = "Yumana", ["awe"] = "Awetí", ["awg"] = "Anguthimri", ["awh"] = "Awbono", ["awi"] = "Aekyom", ["awk"] = "Awabakal", ["awm"] = "Arawum", ["awn"] = "Awngi", ["awo"] = "Awak", ["awr"] = "Awera", ["aws"] = "South Awyu", ["awt"] = "Araweté", ["awu"] = "Central Awyu", ["awv"] = "Jair Awyu", ["aww"] = "Awun", ["awx"] = "Awara", ["awy"] = "Edera Awyu", ["axb"] = "Abipón", ["axe"] = "Ayerrerenge", ["axg"] = "Arára (Mato Grosso)", ["axk"] = "Aka (Central Africa)", ["axl"] = "Lower Southern Aranda", ["axm"] = "Middle Armenian", ["axx"] = "Xârâgurè", ["ay"] = "Aymara", ["aya"] = "Awar", ["ayb"] = "Ayizo", ["ayd"] = "Ayabadhu", ["aye"] = "Ayere", ["ayg"] = "Nyanga (Togo)", ["ayi"] = "Leyigha", ["ayk"] = "Akuku", ["ayl"] = "Libyan Arabic", ["ayn"] = "Yemeni Arabic", ["ayo"] = "Ayoreo", ["ayp"] = "North Mesopotamian Arabic", ["ayq"] = "Ayi", ["ays"] = "Sorsogon Ayta", ["ayt"] = "Bataan Ayta", ["ayu"] = "Ayu", ["ayz"] = "Maybrat", ["az"] = "Azerbaijani", ["aza"] = "Azha", ["azc-caz"] = "Cazcan", ["azc-cup-pro"] = "Proto-Cupan", ["azc-ktn"] = "Kitanemuk", ["azc-nah-pro"] = "Proto-Nahuan", ["azc-num-pro"] = "Proto-Numic", ["azc-pro"] = "Proto-Uto-Aztecan", ["azc-tak-pro"] = "Proto-Takic", ["azc-tat"] = "Tataviam", ["azd"] = "Eastern Durango Nahuatl", ["azg"] = "San Pedro Amuzgos Amuzgo", ["azm"] = "Ipalapa Amuzgo", ["azn"] = "Western Durango Nahuatl", ["azo"] = "Awing", ["azt"] = "Faire Atta", ["azz"] = "Highland Puebla Nahuatl", ["ba"] = "Bashkir", ["baa"] = "Babatana", ["bab"] = "Bainouk-Gunyuño", ["bac"] = "Baduy", ["bae"] = "Baré", ["baf"] = "Nubaca", ["bag"] = "Tuki", ["bah"] = "Bahamian Creole", ["baj"] = "Barakai", ["bal"] = "Baluchi", ["ban"] = "Balinese", ["bao"] = "Waimaha", ["bap"] = "Bantawa", ["bar"] = "Bavarian", ["bas"] = "Basaa", ["bau"] = "Badanchi", ["bav"] = "Babungo", ["baw"] = "Bambili-Bambui", ["bax"] = "Bamum", ["bay"] = "Batuley", ["bba"] = "Baatonum", ["bbb"] = "Barai", ["bbc"] = "Toba Batak", ["bbd"] = "Bau", ["bbe"] = "Bangba", ["bbf"] = "Baibai", ["bbg"] = "Barama", ["bbh"] = "Bugan", ["bbi"] = "Barombi", ["bbj"] = "Ghomala'", ["bbk"] = "Babanki", ["bbl"] = "Bats", ["bbm"] = "Babango", ["bbn"] = "Uneapa", ["bbo"] = "Konabéré", ["bbp"] = "West Central Banda", ["bbq"] = "Bamali", ["bbr"] = "Girawa", ["bbs"] = "Bakpinka", ["bbt"] = "Mburku", ["bbu"] = "Bakulung", ["bbv"] = "Karnai", ["bbw"] = "Baba", ["bbx"] = "Bubia", ["bby"] = "Befang", ["bca"] = "Central Bai", ["bcb"] = "Bainouk-Samik", ["bcd"] = "North Babar", ["bce"] = "Bamenyam", ["bcf"] = "Bamu", ["bcg"] = "Baga Pokur", ["bch"] = "Bariai", ["bci"] = "Baoule", ["bcj"] = "Bardi", ["bck"] = "Bunaba", ["bcl"] = "Central Bikol", ["bcm"] = "Banoni", ["bcn"] = "Bibaali", ["bco"] = "Kaluli", ["bcp"] = "Bali", ["bcq"] = "Bench", ["bcr"] = "Babine-Witsuwit'en", ["bcs"] = "Kohumono", ["bct"] = "Bendi", ["bcu"] = "Biliau", ["bcv"] = "Shoo-Minda-Nye", ["bcw"] = "Bana", ["bcy"] = "Bacama", ["bcz"] = "Bainouk-Gunyaamolo", ["bda"] = "Bayot", ["bdb"] = "Basap", ["bdc"] = "Emberá-Baudó", ["bdd"] = "Bunama", ["bde"] = "Bade", ["bdf"] = "Biage", ["bdg"] = "Bonggi", ["bdh"] = "Tara Baka", ["bdi"] = "Burun", ["bdj"] = "Bai (South Sudan)", ["bdk"] = "Budukh", ["bdl"] = "Indonesian Bajau", ["bdm"] = "Buduma", ["bdn"] = "Baldemu", ["bdo"] = "Morom", ["bdp"] = "Bende", ["bdq"] = "Bahnar", ["bdr"] = "West Coast Bajau", ["bds"] = "Burunge", ["bdt"] = "Bokoto", ["bdu"] = "Oroko", ["bdv"] = "Bodo Parja", ["bdw"] = "Baham", ["bdx"] = "Budong-Budong", ["bdy"] = "Bandjalang", ["bdz"] = "Badeshi", ["be"] = "Belarusian", ["bea"] = "Beaver", ["beb"] = "Bebele", ["bec"] = "Iceve-Maci", ["bed"] = "Bedoanas", ["bee"] = "Byangsi", ["bef"] = "Benabena", ["beg"] = "Belait", ["beh"] = "Biali", ["bei"] = "Bekati'", ["bej"] = "Beja", ["bek"] = "Bebeli", ["bem"] = "Bemba", ["beo"] = "Beami", ["bep"] = "Besoa", ["beq"] = "Beembe", ["ber-fog"] = "Fogaha", ["ber-pro"] = "Proto-Berber", ["ber-zuw"] = "Zuwara", ["bes"] = "Besme", ["bet"] = "Guiberoua Bété", ["beu"] = "Blagar", ["bev"] = "Daloa Bété", ["bew"] = "Betawi", ["bex"] = "Jur Modo", ["bey"] = "Beli (New Guinea)", ["bez"] = "Kibena", ["bfa"] = "Bari", ["bfb"] = "Pauri Bareli", ["bfc"] = "Panyi Bai", ["bfd"] = "Bafut", ["bfe"] = "Betaf", ["bff"] = "Bofi", ["bfg"] = "Busang Kayan", ["bfh"] = "Blafe", ["bfi"] = "British Sign Language", ["bfj"] = "Bafanji", ["bfk"] = "Ban Khor Sign Language", ["bfl"] = "Banda-Ndélé", ["bfm"] = "Mmen", ["bfn"] = "Bunak", ["bfo"] = "Malba Birifor", ["bfp"] = "Beba", ["bfq"] = "Badaga", ["bfr"] = "Bazigar", ["bfs"] = "Southern Bai", ["bft"] = "Balti", ["bfu"] = "Gahri", ["bfw"] = "Bondo", ["bfx"] = "Bantayanon", ["bfy"] = "Bagheli", ["bfz"] = "Mahasu Pahari", ["bg"] = "Bulgarian", ["bga"] = "Gwamhi-Wuri", ["bgb"] = "Bobongko", ["bgc"] = "Haryanvi", ["bgd"] = "Rathwi Bareli", ["bge"] = "Bauria", ["bgf"] = "Bangandu", ["bgg"] = "Bugun", ["bgi"] = "Giangan", ["bgj"] = "Bangolan", ["bgk"] = "Bit", ["bgl"] = "Bo", ["bgo"] = "Baga Koga", ["bgq"] = "Bagri", ["bgr"] = "Bawm Chin", ["bgs"] = "Tagabawa", ["bgt"] = "Bughotu", ["bgu"] = "Mbongno", ["bgv"] = "Warkay-Bipim", ["bgw"] = "Bhatri", ["bgx"] = "Balkan Gagauz Turkish", ["bgy"] = "Benggoi", ["bgz"] = "Banggai", ["bh"] = "Bihari", ["bha"] = "Bharia", ["bhb"] = "Bhili", ["bhc"] = "Biga", ["bhd"] = "Bhadrawahi", ["bhe"] = "Bhaya", ["bhf"] = "Odiai", ["bhg"] = "Binandere", ["bhh"] = "Bukhari", ["bhi"] = "Bhilali", ["bhj"] = "Bahing", ["bhl"] = "Bimin", ["bhm"] = "Bathari", ["bhn"] = "Bohtan Neo-Aramaic", ["bho"] = "Bhojpuri", ["bhp"] = "Bima", ["bhq"] = "South Tukang Besi", ["bhs"] = "Buwal", ["bht"] = "Bhattiyali", ["bhu"] = "Bhunjia", ["bhv"] = "Bahau", ["bhw"] = "Biak", ["bhx"] = "Bhalay", ["bhy"] = "Bhele", ["bhz"] = "Bada", ["bi"] = "Bislama", ["bia"] = "Badimaya", ["bib"] = "Bissa", ["bid"] = "Bidiyo", ["bie"] = "Bepour", ["bif"] = "Biafada", ["big"] = "Biangai", ["bij"] = "Kwanka", ["bil"] = "Bile", ["bim"] = "Bimoba", ["bin"] = "Edo", ["bio"] = "Nai", ["bip"] = "Bila", ["biq"] = "Bipi", ["bir"] = "Bisorio", ["bit"] = "Berinomo", ["biu"] = "Biete", ["biv"] = "Southern Birifor", ["biw"] = "Kol (Cameroon)", ["bix"] = "Bijori", ["biy"] = "Birhor", ["biz"] = "Baloi", ["bja"] = "Budza", ["bjb"] = "Barngarla", ["bjc"] = "Bariji", ["bje"] = "Biao-Jiao Mien", ["bjf"] = "Barzani Jewish Neo-Aramaic", ["bjg"] = "Bidyogo", ["bjh"] = "Bahinemo", ["bji"] = "Burji", ["bjj"] = "Kannauji", ["bjk"] = "Barok", ["bjl"] = "Bulu (New Guinea)", ["bjm"] = "Bajelani", ["bjn"] = "Banjarese", ["bjo"] = "Mid-Southern Banda", ["bjp"] = "Fanamaket", ["bjr"] = "Binumarien", ["bjs"] = "Bajan", ["bjt"] = "Balanta-Ganja", ["bju"] = "Busuu", ["bjv"] = "Bedjond", ["bjw"] = "Bakwé", ["bjx"] = "Banao Itneg", ["bjy"] = "Bayali", ["bjz"] = "Baruga", ["bka"] = "Kyak", ["bkc"] = "Baka", ["bkd"] = "Binukid", ["bkf"] = "Beeke", ["bkg"] = "Buraka", ["bkh"] = "Bakoko", ["bki"] = "Baki", ["bkj"] = "Pande", ["bkk"] = "Brokskat", ["bkl"] = "Berik", ["bkm"] = "Kom (Cameroon)", ["bkn"] = "Bukitan", ["bko"] = "Kwa'", ["bkp"] = "Iboko", ["bkq"] = "Bakairí", ["bkr"] = "Bakumpai", ["bks"] = "Masbate Sorsogon", ["bkt"] = "Boloki", ["bku"] = "Buhid", ["bkv"] = "Bekwarra", ["bkw"] = "Bekwel", ["bkx"] = "Baikeno", ["bky"] = "Bokyi", ["bkz"] = "Bungku", ["bla"] = "Blackfoot", ["blb"] = "Bilua", ["blc"] = "Bella Coola", ["bld"] = "Bolango", ["ble"] = "Balanta-Kentohe", ["blf"] = "Buol", ["blg"] = "Balau", ["blh"] = "Kuwaa", ["bli"] = "Bolia", ["blj"] = "Bulungan", ["blk"] = "Pa'o Karen", ["bll"] = "Biloxi", ["blm"] = "Beli (South Sudan)", ["bln"] = "Southern Catanduanes Bikol", ["blo"] = "Anii", ["blp"] = "Blablanga", ["blq"] = "Baluan-Pam", ["blr"] = "Blang", ["bls"] = "Balaesang", ["blt"] = "Tai Dam", ["blv"] = "Kibala", ["blw"] = "Balangao", ["blx"] = "Mag-Indi Ayta", ["bly"] = "Notre", ["blz"] = "Balantak", ["bm"] = "Bambara", ["bma"] = "Lame", ["bmb"] = "Bembe", ["bmc"] = "Biem", ["bmd"] = "Baga Manduri", ["bme"] = "Limassa", ["bmf"] = "Bom", ["bmg"] = "Bamwe", ["bmh"] = "Kein", ["bmi"] = "Bagirmi", ["bmj"] = "Bote-Majhi", ["bmk"] = "Ghayavi", ["bml"] = "Bomboli", ["bmn"] = "Bina", ["bmo"] = "Bambalang", ["bmp"] = "Bulgebi", ["bmq"] = "Bomu", ["bmr"] = "Muinane", ["bmt"] = "Biao Mon", ["bmu"] = "Somba-Siawari", ["bmv"] = "Bum", ["bmw"] = "Bomwali", ["bmx"] = "Baimak", ["bmz"] = "Baramu", ["bn"] = "Bengali", ["bna"] = "Bonerate", ["bnb"] = "Bookan", ["bnd"] = "Banda", ["bne"] = "Bintauna", ["bnf"] = "Masiwang", ["bng"] = "Benga", ["bni"] = "Bangi", ["bnj"] = "Eastern Tawbuid", ["bnk"] = "Bierebo", ["bnl"] = "Boon", ["bnm"] = "Batanga", ["bnn"] = "Bunun", ["bno"] = "Asi", ["bnp"] = "Bola", ["bnq"] = "Bantik", ["bnr"] = "Butmas-Tur", ["bns"] = "Bundeli", ["bnt-bal"] = "Balong", ["bnt-bon"] = "Boma Nkuu", ["bnt-boy"] = "Boma Yumu", ["bnt-bwa"] = "Bwala", ["bnt-cmw"] = "Chimwiini", ["bnt-ind"] = "Indanga", ["bnt-lal"] = "Lala (South Africa)", ["bnt-mpi"] = "Mpiin", ["bnt-mpu"] = "Mpuono", ["bnt-ngu-pro"] = "Proto-Nguni", ["bnt-phu"] = "Phuthi", ["bnt-pro"] = "Proto-Bantu", ["bnt-sab-pro"] = "Proto-Sabaki", ["bnt-sbo"] = "South Boma", ["bnt-sts-pro"] = "Proto-Sotho-Tswana", ["bnu"] = "Bentong", ["bnv"] = "Beneraf", ["bnw"] = "Bisis", ["bnx"] = "Bangubangu", ["bny"] = "Bintulu", ["bnz"] = "Beezen", ["bo"] = "Tibetan", ["boa"] = "Bora", ["bob"] = "Aweer", ["boe"] = "Mundabli", ["bof"] = "Bolon", ["bog"] = "Bamako Sign Language", ["boh"] = "North Boma", ["boi"] = "Barbareño", ["boj"] = "Anjam", ["bok"] = "Bonjo", ["bol"] = "Bole", ["bom"] = "Berom", ["bon"] = "Bine", ["boo"] = "Tiemacèwè Bozo", ["bop"] = "Bonkiman", ["boq"] = "Bogaya", ["bor"] = "Borôro", ["bot"] = "Bongo", ["bou"] = "Bondei", ["bov"] = "Tuwuli", ["bow"] = "Rema", ["box"] = "Buamu", ["boy"] = "Bodo (Central Africa)", ["boz"] = "Tiéyaxo Bozo", ["bpa"] = "Daakaka", ["bpd"] = "Banda-Banda", ["bpe"] = "Bauni", ["bpg"] = "Bonggo", ["bph"] = "Botlikh", ["bpi"] = "Bagupi", ["bpj"] = "Binji", ["bpk"] = "Orowe", ["bpl"] = "Broome Pearling Lugger Pidgin", ["bpm"] = "Biyom", ["bpn"] = "Dzao Min", ["bpo"] = "Anasi", ["bpp"] = "Kaure", ["bpq"] = "Banda Malay", ["bpr"] = "Koronadal Blaan", ["bps"] = "Sarangani Blaan", ["bpt"] = "Barrow Point", ["bpu"] = "Bongu", ["bpv"] = "Bian Marind", ["bpx"] = "Palya Bareli", ["bpy"] = "Bishnupriya Manipuri", ["bpz"] = "Bilba", ["bqa"] = "Tchumbuli", ["bqb"] = "Bagusa", ["bqc"] = "Boko", ["bqd"] = "Bung", ["bqf"] = "Baga Kaloum", ["bqg"] = "Bago-Kusuntu", ["bqh"] = "Baima", ["bqi"] = "Bakhtiari", ["bqj"] = "Bandial", ["bqk"] = "Banda-Mbrès", ["bql"] = "Karian", ["bqm"] = "Wumboko", ["bqn"] = "Bulgarian Sign Language", ["bqo"] = "Balo", ["bqp"] = "Busa", ["bqq"] = "Biritai", ["bqr"] = "Burusu", ["bqs"] = "Bosngun", ["bqt"] = "Bamukumbit", ["bqu"] = "Boguru", ["bqv"] = "Begbere-Ejar", ["bqw"] = "Buru (Nigeria)", ["bqx"] = "Baangi", ["bqy"] = "Bengkala Sign Language", ["bqz"] = "Bakaka", ["br"] = "Breton", ["bra"] = "Braj", ["brb"] = "Lave", ["brc"] = "Berbice Creole Dutch", ["brd"] = "Baraamu", ["brf"] = "Bera", ["brg"] = "Baure", ["brh"] = "Brahui", ["bri"] = "Mokpwe", ["brj"] = "Bieria", ["brk"] = "Birgid", ["brl"] = "Birwa", ["brm"] = "Barambu", ["brn"] = "Boruca", ["bro"] = "Brokkat", ["brp"] = "Barapasi", ["brq"] = "Breri", ["brr"] = "Birao", ["brs"] = "Baras", ["brt"] = "Bitare", ["bru"] = "Eastern Bru", ["brv"] = "Western Bru", ["brw"] = "Bellari", ["brx"] = "Bodo (India)", ["bry"] = "Burui", ["brz"] = "Bilbil", ["bsa"] = "Abinomn", ["bsb"] = "Brunei Bisaya", ["bsc"] = "Bassari", ["bse"] = "Wushi", ["bsf"] = "Bauchi", ["bsg"] = "Bashkardi", ["bsh"] = "Kamkata-viri", ["bsi"] = "Bassossi", ["bsj"] = "Bangwinji", ["bsk"] = "Burushaski", ["bsl"] = "Basa-Gumna", ["bsm"] = "Busami", ["bsn"] = "Barasana", ["bso"] = "Buso", ["bsp"] = "Baga Sitemu", ["bsq"] = "Bassa", ["bsr"] = "Bassa-Kontagora", ["bss"] = "Akoose", ["bst"] = "Basketo", ["bsu"] = "Bahonsuai", ["bsv"] = "Baga Sobané", ["bsw"] = "Baiso", ["bsx"] = "Yangkam", ["bsy"] = "Sabah Bisaya", ["bta"] = "Bata", ["btc"] = "Bati (Cameroon)", ["btd"] = "Dairi Batak", ["bte"] = "Gamo-Ningi", ["btf"] = "Birgit", ["btg"] = "Gagnoa Bété", ["bth"] = "Biatah Bidayuh", ["bti"] = "Burate", ["btj"] = "Bacanese Malay", ["btk-pro"] = "Proto-Batak", ["btm"] = "Mandailing Batak", ["btn"] = "Ratagnon", ["bto"] = "Rinconada Bikol", ["btp"] = "Budibud", ["btq"] = "Batek", ["btr"] = "Baetora", ["bts"] = "Simalungun Batak", ["btt"] = "Bete-Bendi", ["btu"] = "Batu", ["btv"] = "Bateri", ["btw"] = "Butuanon", ["btx"] = "Karo Batak", ["bty"] = "Bobot", ["btz"] = "Alas-Kluet Batak", ["bua"] = "Buryat", ["bub"] = "Bua", ["bud"] = "Ntcham", ["bue"] = "Beothuk", ["buf"] = "Bushoong", ["bug"] = "Buginese", ["buh"] = "Younuo Bunu", ["bui"] = "Bongili", ["buj"] = "Basa-Gurmana", ["buk"] = "Bukawa", ["bum"] = "Bulu (Cameroon)", ["bun"] = "Sherbro", ["buo"] = "Terei", ["bup"] = "Busoa", ["buq"] = "Brem", ["bus"] = "Bokobaru", ["but"] = "Bungain", ["buu"] = "Budu", ["buv"] = "Bun", ["buw"] = "Bubi", ["bux"] = "Boghom", ["buy"] = "Mmani", ["bva"] = "Barein", ["bvb"] = "Bube", ["bvc"] = "Baelelea", ["bvd"] = "Baeggu", ["bve"] = "Berau Malay", ["bvf"] = "Boor", ["bvg"] = "Bonkeng", ["bvh"] = "Bure", ["bvi"] = "Belanda Viri", ["bvj"] = "Baan", ["bvk"] = "Bukat", ["bvl"] = "Bolivian Sign Language", ["bvm"] = "Bamunka", ["bvn"] = "Buna", ["bvo"] = "Bolgo", ["bvp"] = "Bumang", ["bvq"] = "Birri", ["bvr"] = "Burarra", ["bvt"] = "Bati (Indonesia)", ["bvu"] = "Bukit Malay", ["bvv"] = "Baniva", ["bvw"] = "Boga", ["bvx"] = "Babole", ["bvy"] = "Baybayanon", ["bvz"] = "Bauzi", ["bwa"] = "Bwatoo", ["bwb"] = "Namosi-Naitasiri-Serua", ["bwc"] = "Bwile", ["bwd"] = "Bwaidoka", ["bwe"] = "Bwe Karen", ["bwf"] = "Boselewa", ["bwg"] = "Barwe", ["bwh"] = "Bishuo", ["bwi"] = "Baniwa", ["bwj"] = "Láá Láá Bwamu", ["bwk"] = "Bauwaki", ["bwl"] = "Bwela", ["bwm"] = "Biwat", ["bwn"] = "Wunai Bunu", ["bwo"] = "Shinasha", ["bwp"] = "Lower Mandobo", ["bwq"] = "Southern Bobo", ["bwr"] = "Bura", ["bws"] = "Bomboma", ["bwt"] = "Bafaw", ["bwu"] = "Buli (Ghana)", ["bww"] = "Bwa", ["bwx"] = "Bu-Nao Bunu", ["bwy"] = "Cwi Bwamu", ["bwz"] = "Bwisi", ["bxa"] = "Bauro", ["bxb"] = "Belanda Bor", ["bxc"] = "Molengue", ["bxd"] = "Pela", ["bxe"] = "Ongota", ["bxf"] = "Bilur", ["bxg"] = "Bangala", ["bxh"] = "Buhutu", ["bxi"] = "Pirlatapa", ["bxj"] = "Bayungu", ["bxk"] = "Bukusu", ["bxl"] = "Jalkunan", ["bxn"] = "Burduna", ["bxo"] = "Barikanchi", ["bxp"] = "Bebil", ["bxq"] = "Beele", ["bxs"] = "Busam", ["bxv"] = "Berakou", ["bxw"] = "Banka", ["bxz"] = "Binahari", ["bya"] = "Palawan Batak", ["byb"] = "Bikya", ["byc"] = "Ubaghara", ["byd"] = "Benyadu'", ["bye"] = "Pouye", ["byf"] = "Bete", ["byg"] = "Baygo", ["byh"] = "Bujhyal", ["byi"] = "Buyu", ["byj"] = "Binawa", ["byk"] = "Biao", ["byl"] = "Bayono", ["bym"] = "Bidyara", ["byn"] = "Blin", ["byo"] = "Biyo", ["byp"] = "Bumaji", ["byq"] = "Basay", ["byr"] = "Baruya", ["bys"] = "Burak", ["byt"] = "Berti", ["byv"] = "Medumba", ["byw"] = "Belhariya", ["byx"] = "Qaqet", ["byz"] = "Banaro", ["bza"] = "Bandi", ["bzb"] = "Andio", ["bzd"] = "Bribri", ["bze"] = "Jenaama Bozo", ["bzf"] = "Boikin", ["bzg"] = "Babuza", ["bzh"] = "Mapos Buang", ["bzi"] = "Bisu", ["bzj"] = "Belizean Creole", ["bzk"] = "Nicaraguan Creole", ["bzl"] = "Boano (Sulawesi)", ["bzm"] = "Bolondo", ["bzn"] = "Boano (Maluku)", ["bzo"] = "Bozaba", ["bzp"] = "Kemberano", ["bzq"] = "Buli (Indonesia)", ["bzr"] = "Biri", ["bzs"] = "Brazilian Sign Language", ["bzu"] = "Burmeso", ["bzv"] = "Bebe", ["bzw"] = "Basa", ["bzx"] = "Hainyaxo Bozo", ["bzy"] = "Obanliku", ["bzz"] = "Evant", ["ca"] = "Catalan", ["caa"] = "Ch'orti'", ["cab"] = "Garifuna", ["cac"] = "Chuj", ["cad"] = "Caddo", ["cae"] = "Laalaa", ["caf"] = "Southern Carrier", ["cag"] = "Nivaclé", ["cah"] = "Cahuarano", ["caj"] = "Chané", ["cak"] = "Kaqchikel", ["cal"] = "Carolinian", ["cam"] = "Cèmuhî", ["can"] = "Chambri", ["cao"] = "Chácobo", ["cap"] = "Chipaya", ["caq"] = "Car Nicobarese", ["car"] = "Kari'na", ["cas"] = "Tsimané", ["cau-abz-pro"] = "Proto-Abkhaz-Abaza", ["cau-and-pro"] = "Proto-Andian", ["cau-ava-pro"] = "Proto-Avaro-Andian", ["cau-cir-pro"] = "Proto-Circassian", ["cau-drg-pro"] = "Proto-Dargwa", ["cau-lzg-pro"] = "Proto-Lezghian", ["cau-nec-pro"] = "Proto-Northeast Caucasian", ["cau-nkh-pro"] = "Proto-Nakh", ["cau-nwc-pro"] = "Proto-Northwest Caucasian", ["cau-tsz-pro"] = "Proto-Tsezian", ["cav"] = "Cavineña", ["caw"] = "Kallawaya", ["cax"] = "Chiquitano", ["cay"] = "Cayuga", ["caz"] = "Canichana", ["cba-ata"] = "Atanques", ["cba-cat"] = "Catío Chibcha", ["cba-dor"] = "Dorasque", ["cba-dui"] = "Duit", ["cba-hue"] = "Huetar", ["cba-nut"] = "Nutabe", ["cba-pro"] = "Proto-Chibchan", ["cbb"] = "Cabiyarí", ["cbc"] = "Carapana", ["cbd"] = "Carijona", ["cbg"] = "Chimila", ["cbi"] = "Chachi", ["cbj"] = "Ede Cabe", ["cbk"] = "Chavacano", ["cbl"] = "Bualkhaw Chin", ["cbn"] = "Nyah Kur", ["cbo"] = "Izora", ["cbq"] = "Tsucuba", ["cbr"] = "Cashibo-Cacataibo", ["cbs"] = "Cashinahua", ["cbt"] = "Chayahuita", ["cbu"] = "Candoshi-Shapra", ["cbv"] = "Cacua", ["cbw"] = "Kinabalian", ["cby"] = "Carabayo", ["ccc"] = "Chamicuro", ["ccd"] = "Cafundó", ["cce"] = "Chopi", ["ccg"] = "Chamba Daka", ["cch"] = "Atsam", ["ccj"] = "Kasanga", ["ccl"] = "Cutchi-Swahili", ["ccm"] = "Malaccan Creole Malay", ["cco"] = "Comaltepec Chinantec", ["ccp"] = "Chakma", ["ccr"] = "Cacaopera", ["ccs-gzn-pro"] = "Proto-Georgian-Zan", ["ccs-pro"] = "Proto-Kartvelian", ["cda"] = "Choni", ["cdc-cbm-pro"] = "Proto-Central Chadic", ["cdc-mas-pro"] = "Proto-Masa", ["cdc-pro"] = "Proto-Chadic", ["cdd-pro"] = "Proto-Caddoan", ["cde"] = "Chenchu", ["cdf"] = "Chiru", ["cdh"] = "Chambeali", ["cdi"] = "Chodri", ["cdj"] = "Churahi", ["cdm"] = "Chepang", ["cdn"] = "Chaudangsi", ["cdo"] = "Eastern Min", ["cdr"] = "Cinda-Regi-Tiyal", ["cds"] = "Chadian Sign Language", ["cdy"] = "Chadong", ["cdz"] = "Koda", ["ce"] = "Chechen", ["cea"] = "Lower Chehalis", ["ceb"] = "Cebuano", ["ceg"] = "Chamacoco", ["cel-bry-pro"] = "Proto-Brythonic", ["cel-gal"] = "Gallaecian", ["cel-gau"] = "Gaulish", ["cel-pro"] = "Proto-Celtic", ["cen"] = "Cen", ["cet"] = "Centúúm", ["cfa"] = "Dijim-Bwilim", ["cfd"] = "Cara", ["cfg"] = "Como Karim", ["cfm"] = "Falam Chin", ["cga"] = "Changriwa", ["cgc"] = "Kagayanen", ["cgg"] = "Rukiga", ["cgk"] = "Chocangaca", ["ch"] = "Chamorro", ["chb"] = "Chibcha", ["chc"] = "Catawba", ["chd"] = "Highland Oaxaca Chontal", ["chf"] = "Chontal Maya", ["chg"] = "Chagatai", ["chh"] = "Chinook", ["chi-pro"] = "Proto-Chimakuan", ["chj"] = "Ojitlán Chinantec", ["chk"] = "Chuukese", ["chl"] = "Cahuilla", ["chm-pro"] = "Proto-Mari", ["chn"] = "Chinook Jargon", ["cho"] = "Choctaw", ["chp"] = "Chipewyan", ["chq"] = "Quiotepec Chinantec", ["chr"] = "Cherokee", ["cht"] = "Cholón", ["chw"] = "Chuabo", ["chx"] = "Chantyal", ["chy"] = "Cheyenne", ["chz"] = "Ozumacín Chinantec", ["cia"] = "Cia-Cia", ["cib"] = "Ci Gbe", ["cic"] = "Chickasaw", ["cid"] = "Chimariko", ["cie"] = "Cineni", ["cih"] = "Chinali", ["cik"] = "Chitkuli Kinnauri", ["cim"] = "Cimbrian", ["cin"] = "Cinta Larga", ["cip"] = "Chiapanec", ["cir"] = "Tinrin", ["ciy"] = "Chaima", ["cja"] = "Western Cham", ["cje"] = "Chru", ["cjh"] = "Upper Chehalis", ["cji"] = "Chamalal", ["cjk"] = "Chokwe", ["cjm"] = "Eastern Cham", ["cjn"] = "Chenapian", ["cjo"] = "Pajonal Ashéninka", ["cjp"] = "Cabécar", ["cjs"] = "Shor", ["cjv"] = "Chuave", ["cjy"] = "Jin", ["ckb"] = "Central Kurdish", ["ckh"] = "Chak", ["ckl"] = "Cibak", ["ckn"] = "Kaang Chin", ["cko"] = "Anufo", ["ckq"] = "Kajakse", ["ckr"] = "Kairak", ["cks"] = "Tayo", ["ckt"] = "Chukchi", ["cku"] = "Koasati", ["ckv"] = "Kavalan", ["ckx"] = "Caka", ["cky"] = "Cakfem-Mushere", ["ckz"] = "Kaqchikel-K'iche' Mixed Language", ["cla"] = "Ron", ["clc"] = "Chilcotin", ["cld"] = "Chaldean Neo-Aramaic", ["cle"] = "Lealao Chinantec", ["clh"] = "Chilisso", ["cli"] = "Chakali", ["clj"] = "Laitu Chin", ["clk"] = "Idu", ["cll"] = "Chala", ["clm"] = "Klallam", ["clo"] = "Lowland Oaxaca Chontal", ["clt"] = "Lutuv", ["clu"] = "Caluyanun", ["clw"] = "Chulym", ["cly"] = "Eastern Highland Chatino", ["cma"] = "Mạ", ["cmc-pro"] = "Proto-Chamic", ["cme"] = "Cerma", ["cmg"] = "Classical Mongolian", ["cmi"] = "Emberá-Chamí", ["cml"] = "Campalagian", ["cmm"] = "Michigamea", ["cmn"] = "Mandarin", ["cmo"] = "Central Mnong", ["cmr"] = "Mro Chin", ["cms"] = "Messapic", ["cmt"] = "Camtho", ["cna"] = "Changthang", ["cnb"] = "Chinbon Chin", ["cnc"] = "Cốông", ["cng"] = "Northern Qiang", ["cnh"] = "Lai", ["cni"] = "Asháninka", ["cnk"] = "Khumi Chin", ["cnl"] = "Lalana Chinantec", ["cno"] = "Con", ["cnp"] = "Northern Pinghua", ["cns"] = "Central Asmat", ["cnt"] = "Tepetotutla Chinantec", ["cnu"] = "Chenoua", ["cnw"] = "Ngawn Chin", ["cnx"] = "Middle Cornish", ["co"] = "Corsican", ["coa"] = "Cocos Islands Malay", ["cob"] = "Chicomuceltec", ["coc"] = "Cocopa", ["cod"] = "Cocama", ["coe"] = "Koreguaje", ["cof"] = "Tsafiki", ["cog"] = "Chong", ["coh"] = "Chichonyi-Chidzihana-Chikauma", ["coj"] = "Cochimi", ["cok"] = "Santa Teresa Cora", ["col"] = "Columbia-Wenatchi", ["com"] = "Comanche", ["con"] = "Cofán", ["coo"] = "Comox", ["cop"] = "Coptic", ["coq"] = "Coquille", ["cot"] = "Caquinte", ["cou"] = "Wamey", ["cov"] = "Cao Miao", ["cow"] = "Cowlitz", ["cox"] = "Nanti", ["coy"] = "Coyaima", ["coz"] = "Chochotec", ["cpa"] = "Palantla Chinantec", ["cpb"] = "Ucayali-Yurúa Ashéninka", ["cpc"] = "Apurucayali Ashéninka", ["cpg"] = "Cappadocian Greek", ["cpi"] = "Chinese Pidgin English", ["cpn"] = "Cherepon", ["cpo"] = "Kpee", ["cps"] = "Capiznon", ["cpu"] = "Pichis Ashéninka", ["cpx"] = "Puxian Min", ["cpy"] = "South Ucayali Ashéninka", ["cqd"] = "Chuanqiandian Cluster Miao", ["cr"] = "Cree", ["cra"] = "Chara", ["crb"] = "Kalinago", ["crc"] = "Lonwolwol", ["crd"] = "Coeur d'Alene", ["crf"] = "Caramanta", ["crg"] = "Michif", ["crh"] = "Crimean Tatar", ["cri"] = "Sãotomense", ["crj"] = "Southern East Cree", ["crk"] = "Plains Cree", ["crl"] = "Northern East Cree", ["crm"] = "Moose Cree", ["crn"] = "Cora", ["cro"] = "Crow", ["crp-bip"] = "Basque-Icelandic Pidgin", ["crp-cpr"] = "Chinese Pidgin Russian", ["crp-gep"] = "West Greenlandic Pidgin", ["crp-kia"] = "Kiautschou German Pidgin", ["crp-mar"] = "Maroon Spirit Language", ["crp-mpp"] = "Macau Pidgin Portuguese", ["crp-rsn"] = "Russenorsk", ["crp-slb"] = "Solombala English", ["crp-spp"] = "Samoan Plantation Pidgin", ["crp-tpr"] = "Taimyr Pidgin Russian", ["crq"] = "Iyo'wujwa Chorote", ["crr"] = "Carolina Algonquian", ["crs"] = "Seychellois Creole", ["crt"] = "Iyojwa'ja Chorote", ["crv"] = "Chaura", ["crw"] = "Chrau", ["crx"] = "Carrier", ["cry"] = "Cori", ["crz"] = "Cruzeño", ["cs"] = "Czech", ["csa"] = "Chiltepec Chinantec", ["csb"] = "Kashubian", ["csc"] = "Catalan Sign Language", ["csd"] = "Chiangmai Sign Language", ["cse"] = "Czech Sign Language", ["csf"] = "Cuban Sign Language", ["csg"] = "Chilean Sign Language", ["csh"] = "Asho Chin", ["csi"] = "Coast Miwok", ["csj"] = "Songlai Chin", ["csk"] = "Jola-Kasa", ["csl"] = "Chinese Sign Language", ["csm"] = "Central Sierra Miwok", ["csn"] = "Colombian Sign Language", ["cso"] = "Sochiapam Chinantec", ["csp"] = "Southern Pinghua", ["csq"] = "Croatian Sign Language", ["csr"] = "Costa Rican Sign Language", ["css"] = "Southern Ohlone", ["cst"] = "Northern Ohlone", ["csu-bba-pro"] = "Proto-Bongo-Bagirmi", ["csu-maa-pro"] = "Proto-Mangbetu", ["csu-pro"] = "Proto-Central Sudanic", ["csu-sar-pro"] = "Proto-Sara", ["csv"] = "Sumtu Chin", ["csw"] = "Swampy Cree", ["csx"] = "Cambodian Sign Language", ["csy"] = "Siyin Chin", ["csz"] = "Coos", ["cta"] = "Tataltepec Chatino", ["ctc"] = "Chetco-Tolowa", ["ctd"] = "Tedim Chin", ["cte"] = "Tepinapa Chinantec", ["ctg"] = "Chittagonian", ["cth"] = "Thaiphum Chin", ["ctl"] = "Tlacoatzintepec Chinantec", ["ctm"] = "Chitimacha", ["ctn"] = "Chhintange", ["cto"] = "Emberá-Catío", ["ctp"] = "Western Highland Chatino", ["cts"] = "Northern Catanduanes Bikol", ["ctt"] = "Wayanad Chetti", ["ctu"] = "Chol", ["ctz"] = "Zacatepec Chatino", ["cu"] = "Old Church Slavonic", ["cua"] = "Cua", ["cub"] = "Cubeo", ["cuc"] = "Usila Chinantec", ["cug"] = "Cung", ["cuh"] = "Chuka", ["cui"] = "Cuiba", ["cuj"] = "Mashco Piro", ["cuk"] = "Kuna", ["cul"] = "Culina", ["cuo"] = "Cumanagoto", ["cup"] = "Cupeño", ["cuq"] = "Cun", ["cur"] = "Chhulung", ["cus-ash"] = "Ashraaf", ["cus-hec-pro"] = "Proto-Highland East Cushitic", ["cus-pro"] = "Proto-Cushitic", ["cus-som-pro"] = "Proto-Somaloid", ["cus-sou-pro"] = "Proto-South Cushitic", ["cut"] = "Teutila Cuicatec", ["cuu"] = "Tai Ya", ["cuv"] = "Cuvok", ["cuw"] = "Chukwa", ["cux"] = "Tepeuxila Cuicatec", ["cuy"] = "Cuitlatec", ["cv"] = "Chuvash", ["cvg"] = "Chug", ["cvn"] = "Valle Nacional Chinantec", ["cwa"] = "Kabwa", ["cwb"] = "Maindo", ["cwd"] = "Woods Cree", ["cwe"] = "Kwere", ["cwg"] = "Chewong", ["cwt"] = "Kuwaataay", ["cy"] = "Welsh", ["cya"] = "Nopala Chatino", ["cyb"] = "Cayubaba", ["cyo"] = "Cuyunon", ["czh"] = "Huizhou", ["czk"] = "Knaanic", ["czn"] = "Zenzontepec Chatino", ["czo"] = "Central Min", ["czt"] = "Zotung Chin", ["da"] = "Danish", ["daa"] = "Dangaléat", ["dac"] = "Dambi", ["dad"] = "Marik", ["dae"] = "Duupa", ["dag"] = "Dagbani", ["dah"] = "Gwahatike", ["dai"] = "Day", ["daj"] = "Dar Fur Daju", ["dak"] = "Dakota", ["dal"] = "Dahalo", ["dam"] = "Damakawa", ["dao"] = "Daai Chin", ["daq"] = "Dandami Maria", ["dar"] = "Dargwa", ["das"] = "Daho-Doo", ["dau"] = "Dar Sila Daju", ["dav"] = "Taita", ["daw"] = "Davawenyo", ["dax"] = "Dayi", ["daz"] = "Dao", ["dba"] = "Bangime", ["dbb"] = "Deno", ["dbd"] = "Dadiya", ["dbe"] = "Dabe", ["dbf"] = "Edopi", ["dbg"] = "Dogul Dom", ["dbi"] = "Doka", ["dbj"] = "Ida'an", ["dbl"] = "Dyirbal", ["dbm"] = "Duguri", ["dbn"] = "Duriankere", ["dbo"] = "Dulbu", ["dbp"] = "Duwai", ["dbq"] = "Daba", ["dbr"] = "Dabarre", ["dbt"] = "Ben Tey", ["dbu"] = "Bondum Dom Dogon", ["dbv"] = "Dungu", ["dbw"] = "Bankan Tey Dogon", ["dby"] = "Dibiyaso", ["dcc"] = "Deccani", ["dcr"] = "Negerhollands", ["dda"] = "Dadi Dadi", ["ddd"] = "Dongotono", ["dde"] = "Doondo", ["ddg"] = "Fataluku", ["ddi"] = "Diodio", ["ddj"] = "Jaru", ["ddn"] = "Dendi", ["ddo"] = "Tsez", ["ddr"] = "Dhudhuroa", ["dds"] = "Donno So Dogon", ["ddw"] = "Dawera-Daweloor", ["de"] = "German", ["dec"] = "Dagik", ["ded"] = "Dedua", ["dee"] = "Dewoin", ["def"] = "Dezfuli", ["deg"] = "Degema", ["deh"] = "Dehwari", ["dei"] = "Demisa", ["dem"] = "Dem", ["dep"] = "Pidgin Delaware", ["der"] = "Deori", ["des"] = "Desano", ["dev"] = "Domung", ["dez"] = "Dengese", ["dga"] = "Southern Dagaare", ["dgb"] = "Bunoge", ["dgc"] = "Casiguran Dumagat Agta", ["dgd"] = "Dagaari Dioula", ["dge"] = "Degenan", ["dgg"] = "Doga", ["dgh"] = "Dghwede", ["dgi"] = "Northern Dagara", ["dgk"] = "Dagba", ["dgn"] = "Dagoman", ["dgo"] = "Hindi Dogri", ["dgr"] = "Dogrib", ["dgs"] = "Dogoso", ["dgt"] = "Ntra'ngith", ["dgw"] = "Daungwurrung", ["dgx"] = "Doghoro", ["dgz"] = "Daga", ["dhd"] = "Dhundhari", ["dhg"] = "Dhangu", ["dhi"] = "Dhimal", ["dhl"] = "Dhalandji", ["dhm"] = "Zemba", ["dhn"] = "Dhanki", ["dho"] = "Dhodia", ["dhr"] = "Tharrgari", ["dhs"] = "Dhaiso", ["dhu"] = "Dhurga", ["dhv"] = "Drehu", ["dhw"] = "Danuwar", ["dhx"] = "Dhungaloo", ["dia"] = "Dia", ["dib"] = "South Central Dinka", ["dic"] = "Lakota Dida", ["did"] = "Didinga", ["dif"] = "Dieri", ["dig"] = "Digo", ["dii"] = "Dimbong", ["dij"] = "Dai", ["dik"] = "Southwestern Dinka", ["dil"] = "Dilling", ["dim"] = "Dime", ["din"] = "Dinka", ["dio"] = "Dibo", ["dip"] = "Northeastern Dinka", ["dir"] = "Dirim", ["dis"] = "Dimasa", ["diu"] = "Gciriku", ["diw"] = "Northwestern Dinka", ["dix"] = "Dixon Reef", ["diy"] = "Diuwe", ["diz"] = "Ding", ["dja"] = "Djadjawurrung", ["djb"] = "Djinba", ["djc"] = "Dar Daju Daju", ["djd"] = "Jaminjung", ["dje"] = "Zarma", ["djf"] = "Djangun", ["dji"] = "Djinang", ["djj"] = "Ndjébbana", ["djk"] = "Aukan", ["djl"] = "Djiwarli", ["djm"] = "Jamsay", ["djn"] = "Djauan", ["djo"] = "Jangkang", ["djr"] = "Djambarrpuyngu", ["dju"] = "Kapriman", ["djw"] = "Djawi", ["dka"] = "Dakpa", ["dkk"] = "Dakka", ["dkr"] = "Kuijau", ["dks"] = "Southeastern Dinka", ["dkx"] = "Mazagway", ["dlg"] = "Dolgan", ["dlk"] = "Dahalik", ["dlm"] = "Dalmatian", ["dln"] = "Darlong", ["dma"] = "Duma", ["dmb"] = "Mombo Dogon", ["dmc"] = "Gavak", ["dmd"] = "Madhi Madhi", ["dme"] = "Dugwor", ["dmf"] = "Medefaidrin", ["dmg"] = "Upper Kinabatangan", ["dmk"] = "Domaaki", ["dml"] = "Dameli", ["dmm"] = "Dama (Nigeria)", ["dmn-dam"] = "Dama (Sierra Leone)", ["dmn-mdw-pro"] = "Proto-Western Mande", ["dmn-pro"] = "Proto-Mande", ["dmo"] = "Kemezung", ["dmr"] = "East Damar", ["dms"] = "Dampelas", ["dmu"] = "Dubu", ["dmv"] = "Dumpas", ["dmw"] = "Mudburra", ["dmx"] = "Dema", ["dmy"] = "Demta", ["dna"] = "Upper Grand Valley Dani", ["dnd"] = "Daonda", ["dne"] = "Ndendeule", ["dng"] = "Dungan", ["dni"] = "Lower Grand Valley Dani", ["dnj"] = "Dan", ["dnk"] = "Dengka", ["dnn"] = "Dzuun", ["dno"] = "Ndrulo", ["dnr"] = "Danaru", ["dnt"] = "Mid Grand Valley Dani", ["dnu"] = "Danau", ["dnv"] = "Danu", ["dnw"] = "Western Dani", ["dny"] = "Dení", ["doa"] = "Dom", ["dob"] = "Dobu", ["doc"] = "Northern Kam", ["doe"] = "Doe", ["dof"] = "Domu", ["doh"] = "Dong", ["doi"] = "Dogri", ["dok"] = "Dondo", ["dol"] = "Doso", ["don"] = "Doura", ["doo"] = "Dongo", ["dop"] = "Lukpa", ["doq"] = "Dominican Sign Language", ["dor"] = "Dori'o", ["dos"] = "Dogosé", ["dot"] = "Dass", ["dov"] = "Toka-Leya", ["dow"] = "Doyayo", ["dox"] = "Bussa", ["doy"] = "Dompo", ["doz"] = "Dorze", ["dpp"] = "Papar", ["dra-bry"] = "Beary", ["dra-cen-pro"] = "Proto-Central Dravidian", ["dra-mkn"] = "Middle Kannada", ["dra-nor-pro"] = "Proto-North Dravidian", ["dra-okn"] = "Old Kannada", ["dra-ote"] = "Old Telugu", ["dra-pro"] = "Proto-Dravidian", ["dra-sdo-pro"] = "Proto-South Dravidian I", ["dra-sdt-pro"] = "Proto-South Dravidian II", ["dra-sou-pro"] = "Proto-South Dravidian", ["drb"] = "Dair", ["drc"] = "Minderico", ["drd"] = "Darmiya", ["drg"] = "Rungus", ["dri"] = "Lela", ["drl"] = "Baagandji", ["drn"] = "West Damar", ["dro"] = "Daro-Matu Melanau", ["drq"] = "Dura", ["drs"] = "Gedeo", ["dru"] = "Rukai", ["dru-pro"] = "Proto-Rukai", ["dry"] = "Darai", ["dsb"] = "Lower Sorbian", ["dse"] = "Dutch Sign Language", ["dsh"] = "Daasanach", ["dsi"] = "Disa", ["dsl"] = "Danish Sign Language", ["dsn"] = "Dusner", ["dso"] = "Desiya", ["dsq"] = "Tadaksahak", ["dta"] = "Daur", ["dtb"] = "Labuk-Kinabatangan Kadazan", ["dtd"] = "Ditidaht", ["dth"] = "Adithinngithigh", ["dti"] = "Ana Tinga Dogon", ["dtk"] = "Tene Kan Dogon", ["dtm"] = "Tomo Kan Dogon", ["dto"] = "Tommo So", ["dtp"] = "Central Dusun", ["dtr"] = "Lotud", ["dts"] = "Toro So Dogon", ["dtt"] = "Toro Tegu Dogon", ["dtu"] = "Tebul Ure Dogon", ["dty"] = "Doteli", ["dua"] = "Duala", ["dub"] = "Dubli", ["duc"] = "Duna", ["due"] = "Umiray Dumaget Agta", ["duf"] = "Dumbea", ["dug"] = "Chiduruma", ["duh"] = "Dungra Bhil", ["dui"] = "Dumun", ["duk"] = "Uyajitaya", ["dul"] = "Alabat Island Agta", ["dum"] = "Middle Dutch", ["dun"] = "Dusun Deyah", ["duo"] = "Dupaningan Agta", ["dup"] = "Duano", ["duq"] = "Dusun Malang", ["dur"] = "Dii", ["dus"] = "Dumi", ["duu"] = "Drung", ["duv"] = "Duvle", ["duw"] = "Dusun Witu", ["dux"] = "Duun", ["duy"] = "Dicamay Agta", ["duz"] = "Duli", ["dv"] = "Dhivehi", ["dva"] = "Duau", ["dwa"] = "Diri", ["dwr"] = "Dawro", ["dwu"] = "Dhuwal", ["dww"] = "Dawawa", ["dwy"] = "Dhuwaya", ["dwz"] = "Dewas Rai", ["dya"] = "Dyan", ["dyb"] = "Dyaberdyaber", ["dyd"] = "Dyugun", ["dyi"] = "Djimini", ["dym"] = "Yanda Dogon", ["dyn"] = "Dyangadi", ["dyo"] = "Jola-Fonyi", ["dyu"] = "Dyula", ["dyy"] = "Dyaabugay", ["dz"] = "Dzongkha", ["dza"] = "Tunzu", ["dzg"] = "Dazaga", ["dzl"] = "Dzala", ["dzn"] = "Dzando", ["ebg"] = "Ebughu", ["ebk"] = "Eastern Bontoc", ["ebr"] = "Ebrié", ["ebu"] = "Embu", ["ecr"] = "Eteocretan", ["ecs"] = "Ecuadorian Sign Language", ["ecy"] = "Eteocypriot", ["ee"] = "Ewe", ["eee"] = "E", ["efa"] = "Efai", ["efe"] = "Efe", ["efi"] = "Efik", ["ega"] = "Ega", ["egl"] = "Emilian", ["ego"] = "Eggon", ["egx-dem"] = "Demotic Egyptian", ["egy"] = "Egyptian", ["ehu"] = "Ehueun", ["eip"] = "Eipomek", ["eit"] = "Eitiep", ["eiv"] = "Askopan", ["eja"] = "Ejamat", ["eka"] = "Ekajuk", ["eke"] = "Ekit", ["ekg"] = "Ekari", ["eki"] = "Eki", ["ekl"] = "Kolhe", ["ekm"] = "Elip", ["eko"] = "Koti", ["ekp"] = "Ekpeye", ["ekr"] = "Yace", ["eky"] = "Eastern Kayah", ["el"] = "Greek", ["ele"] = "Elepi", ["elh"] = "El Hugeirat", ["eli"] = "Nding", ["elk"] = "Elkei", ["elm"] = "Eleme", ["elo"] = "El Molo", ["elu"] = "Elu", ["elx"] = "Elamite", ["ema"] = "Emai", ["emb"] = "Embaloh", ["eme"] = "Emerillon", ["emg"] = "Eastern Meohang", ["emi"] = "Mussau-Emira", ["emk"] = "Eastern Maninkakan", ["emm"] = "Mamulique", ["emn"] = "Eman", ["emp"] = "Northern Emberá", ["ems"] = "Alutiiq", ["emu"] = "Eastern Muria", ["emw"] = "Emplawas", ["emx"] = "Erromintxela", ["emy"] = "Epigraphic Mayan", ["en"] = "English", ["ena"] = "Apali", ["enb"] = "Markweeta", ["enc"] = "En", ["end"] = "Ende", ["enf"] = "Forest Enets", ["enh"] = "Tundra Enets", ["enl"] = "Enlhet", ["enm"] = "Middle English", ["enn"] = "Engenni", ["eno"] = "Enggano", ["enq"] = "Enga", ["enr"] = "Emem", ["enu"] = "Enu", ["env"] = "Enwan", ["enw"] = "Enwang", ["enx"] = "Enxet", ["eo"] = "Esperanto", ["eot"] = "Eotile", ["epi"] = "Epie", ["era"] = "Eravallan", ["erg"] = "Sie", ["erh"] = "Eruwa", ["eri"] = "Ogea", ["erk"] = "South Efate", ["ero-gsz"] = "Geshiza", ["ero-nya"] = "Nyagrong Minyag", ["ero-tau"] = "Stau", ["err"] = "Erre", ["ers"] = "Ersu", ["ert"] = "Eritai", ["erw"] = "Erokwanas", ["es"] = "Spanish", ["ese"] = "Ese Ejja", ["esh"] = "Eshtehardi", ["esl"] = "Egyptian Sign Language", ["esm"] = "Esuma", ["esn"] = "Salvadoran Sign Language", ["eso"] = "Estonian Sign Language", ["esq"] = "Esselen", ["ess"] = "Central Siberian Yupik", ["esu"] = "Yup'ik", ["esx-esk-pro"] = "Proto-Eskimo", ["esx-ink"] = "Inuktun", ["esx-inq"] = "Inuinnaqtun", ["esx-inu-pro"] = "Proto-Inuit", ["esx-pro"] = "Proto-Eskimo-Aleut", ["esx-tut"] = "Tunumiisut", ["esy"] = "Eskayan", ["et"] = "Estonian", ["etb"] = "Etebi", ["etc"] = "Etchemin", ["eth"] = "Ethiopian Sign Language", ["etn"] = "Eton (Vanuatu)", ["eto"] = "Eton (Cameroon)", ["etr"] = "Edolo", ["ets"] = "Yekhee", ["ett"] = "Etruscan", ["etu"] = "Ejagham", ["etx"] = "Eten", ["etz"] = "Semimi", ["eu"] = "Basque", ["euq-pro"] = "Proto-Basque", ["eve"] = "Even", ["evh"] = "Uvbie", ["evn"] = "Evenki", ["ewo"] = "Ewondo", ["ext"] = "Extremaduran", ["eya"] = "Eyak", ["eyo"] = "Keiyo", ["eza"] = "Ezaa", ["eze"] = "Uzekwe", ["fa"] = "Persian", ["faa"] = "Fasu", ["fab"] = "Annobonese", ["fad"] = "Wagi", ["faf"] = "Fagani", ["fag"] = "Finongan", ["fah"] = "Baissa Fali", ["fai"] = "Faiwol", ["faj"] = "Kursav", ["fak"] = "Fang (Beboid)", ["fal"] = "South Fali", ["fam"] = "Fam", ["fan"] = "Fang (Bantu)", ["fap"] = "Palor", ["far"] = "Fataleka", ["fau"] = "Fayu", ["fax"] = "Fala", ["fay"] = "Southwestern Fars", ["faz"] = "Northwestern Fars", ["fbl"] = "West Miraya Bikol", ["fcs"] = "Quebec Sign Language", ["fer"] = "Feroge", ["ff"] = "Fula", ["ffi"] = "Foia Foia", ["fgr"] = "Fongoro", ["fi"] = "Finnish", ["fia"] = "Nobiin", ["fie"] = "Fyer", ["fif"] = "Faifi", ["fip"] = "Fipa", ["fir"] = "Firan", ["fit"] = "Meänkieli", ["fiw"] = "Fiwaga", ["fj"] = "Fijian", ["fkk"] = "Kirya-Konzel", ["fkv"] = "Kven", ["fla"] = "Montana Salish", ["flh"] = "Foau", ["fli"] = "Fali", ["fll"] = "North Fali", ["fln"] = "Flinders Island", ["flr"] = "Fuliiru", ["fly"] = "Tsotsitaal", ["fmp"] = "Fe'fe'", ["fmu"] = "Far Western Muria", ["fng"] = "Fanagalo", ["fni"] = "Fania", ["fo"] = "Faroese", ["fod"] = "Foodo", ["foi"] = "Foi", ["fom"] = "Foma", ["fon"] = "Fon", ["for"] = "Fore", ["fos"] = "Siraya", ["fpe"] = "Pichinglis", ["fqs"] = "Fas", ["fr"] = "French", ["frd"] = "Fordata", ["frm"] = "Middle French", ["fro"] = "Old French", ["frp"] = "Franco-Provençal", ["frq"] = "Forak", ["frr"] = "North Frisian", ["frt"] = "Fortsenal", ["fse"] = "Finnish Sign Language", ["fsl"] = "French Sign Language", ["fss"] = "Finnish-Swedish Sign Language", ["fud"] = "East Futuna", ["fuj"] = "Ko", ["fum"] = "Fum", ["fun"] = "Fulniô", ["fur"] = "Friulian", ["fut"] = "Futuna-Aniwa", ["fuu"] = "Furu", ["fuy"] = "Fuyug", ["fvr"] = "Fur", ["fwa"] = "Fwâi", ["fwe"] = "Fwe", ["fy"] = "West Frisian", ["ga"] = "Irish", ["gaa"] = "Ga", ["gab"] = "Gabri", ["gac"] = "Mixed Great Andamanese", ["gad"] = "Gaddang", ["gae"] = "Warekena", ["gaf"] = "Gende", ["gag"] = "Gagauz", ["gah"] = "Alekano", ["gai"] = "Borei", ["gaj"] = "Gadsup", ["gak"] = "Gamkonora", ["gal"] = "Galoli", ["gam"] = "Kandawo", ["gan"] = "Gan", ["gao"] = "Gants", ["gap"] = "Gal", ["gaq"] = "Gata'", ["gar"] = "Galeya", ["gas"] = "Adiwasi Garasia", ["gat"] = "Kenati", ["gau"] = "Kondekor", ["gaw"] = "Nobonob", ["gay"] = "Gayo", ["gba-pro"] = "Proto-Gbaya", ["gbb"] = "Kaytetye", ["gbd"] = "Karadjeri", ["gbe"] = "Niksek", ["gbf"] = "Gaikundi", ["gbg"] = "Gbanziri", ["gbh"] = "Defi Gbe", ["gbi"] = "Galela", ["gbj"] = "Bodo Gadaba", ["gbk"] = "Gaddi", ["gbl"] = "Gamit", ["gbm"] = "Garhwali", ["gbn"] = "Mo'da", ["gbo"] = "Northern Grebo", ["gbp"] = "Gbaya-Bossangoa", ["gbq"] = "Gbaya-Bozoum", ["gbr"] = "Gbagyi", ["gbs"] = "Gbesi Gbe", ["gbu"] = "Gagadu", ["gbv"] = "Gbanu", ["gbw"] = "Gabi", ["gbx"] = "Eastern Xwla Gbe", ["gby"] = "Gbari", ["gcc"] = "Mali", ["gcd"] = "Ganggalida", ["gce"] = "Galice", ["gcf"] = "Antillean Creole", ["gcl"] = "Grenadian Creole English", ["gcn"] = "Gaina", ["gcr"] = "Guianese Creole", ["gct"] = "Colonia Tovar German", ["gd"] = "Scottish Gaelic", ["gdb"] = "Ollari", ["gdc"] = "Gugu Badhun", ["gdd"] = "Gedaged", ["gde"] = "Gude", ["gdf"] = "Guduf-Gava", ["gdg"] = "Ga'dang", ["gdh"] = "Gadjerawang", ["gdi"] = "Gundi", ["gdj"] = "Kurtjar", ["gdk"] = "Gadang", ["gdl"] = "Dirasha", ["gdm"] = "Laal", ["gdn"] = "Umanakaina", ["gdo"] = "Godoberi", ["gdq"] = "Mehri", ["gdr"] = "Wipi", ["gds"] = "Ghandruk Sign Language", ["gdt"] = "Kungardutyi", ["gdu"] = "Gudu", ["gdx"] = "Godwari", ["gea"] = "Geruma", ["geb"] = "Kire", ["gec"] = "Gboloo Grebo", ["ged"] = "Gade", ["geg"] = "Gengle", ["geh"] = "Hutterisch", ["gei"] = "Gebe", ["gej"] = "Gen", ["gek"] = "Gerka", ["gel"] = "Fakkanci", ["gem-pro"] = "Proto-Germanic", ["geq"] = "Geme", ["ges"] = "Geser-Gorom", ["gev"] = "Viya", ["gew"] = "Gera", ["gex"] = "Garre", ["gey"] = "Enya", ["gez"] = "Ge'ez", ["gfk"] = "Patpatar", ["gft"] = "Gafat", ["gga"] = "Gao", ["ggb"] = "Gbii", ["ggd"] = "Gugadj", ["gge"] = "Guragone", ["ggg"] = "Gurgula", ["ggk"] = "Kungarakany", ["ggl"] = "Ganglau", ["ggt"] = "Gitua", ["ggu"] = "Gban", ["ggw"] = "Gogodala", ["gha"] = "Ghadames", ["ghc"] = "Classical Gaelic", ["ghe"] = "Southern Ghale", ["ghh"] = "Northern Ghale", ["ghk"] = "Geko Karen", ["ghl"] = "Ghulfan", ["ghn"] = "Ghanongga", ["gho"] = "Ghomara", ["ghr"] = "Ghera", ["ghs"] = "Guhu-Samane", ["ght"] = "Kutang Ghale", ["gia"] = "Kitja", ["gib"] = "Gibanawa", ["gid"] = "Gidar", ["gie"] = "Guébie", ["gig"] = "Goaria", ["gih"] = "Githabul", ["gii"] = "Girirra", ["gil"] = "Gilbertese", ["gim"] = "Gimi (Papuan)", ["gin"] = "Hinukh", ["gip"] = "Gimi (Austronesian)", ["giq"] = "Green Gelao", ["gir"] = "Red Gelao", ["gis"] = "North Giziga", ["git"] = "Gitxsan", ["giu"] = "Mulao", ["giw"] = "White Gelao", ["gix"] = "Gilima", ["giy"] = "Giyug", ["giz"] = "South Giziga", ["gji"] = "Geji", ["gjk"] = "Kachi Koli", ["gjm"] = "Gunditjmara", ["gjn"] = "Gonja", ["gjr"] = "Gurindji Kriol", ["gju"] = "Gojri", ["gka"] = "Guya", ["gkd"] = "Magi", ["gke"] = "Ndai", ["gkn"] = "Gokana", ["gko"] = "Kok-Nar", ["gkp"] = "Guinea Kpelle", ["gl"] = "Galician", ["glc"] = "Bon Gula", ["gld"] = "Nanai", ["glh"] = "Northwest Pashayi", ["glj"] = "Kulaal", ["glk"] = "Gilaki", ["glo"] = "Galambu", ["glr"] = "Glaro-Twabo", ["glu"] = "Gula", ["glw"] = "Glavda", ["gly"] = "Gule", ["gma"] = "Gambera", ["gmb"] = "Gula'alaa", ["gmd"] = "Mághdì", ["gme-bur"] = "Burgundian", ["gme-cgo"] = "Crimean Gothic", ["gmg"] = "Magiyi", ["gmh"] = "Middle High German", ["gml"] = "Middle Low German", ["gmm"] = "Gbaya-Mbodomo", ["gmn"] = "Gimnime", ["gmq-gut"] = "Gutnish", ["gmq-jmk"] = "Jamtish", ["gmq-mno"] = "Middle Norwegian", ["gmq-oda"] = "Old Danish", ["gmq-ogt"] = "Old Gutnish", ["gmq-osw"] = "Old Swedish", ["gmq-pro"] = "Proto-Norse", ["gmq-scy"] = "Scanian", ["gmr"] = "Mirning", ["gmu"] = "Gumalu", ["gmv"] = "Gamo", ["gmw-bgh"] = "Bergish", ["gmw-cfr"] = "Central Franconian", ["gmw-ecg"] = "East Central German", ["gmw-fin"] = "Fingallian", ["gmw-gts"] = "Gottscheerish", ["gmw-jdt"] = "Jersey Dutch", ["gmw-msc"] = "Middle Scots", ["gmw-pro"] = "Proto-West Germanic", ["gmw-rfr"] = "Rhine Franconian", ["gmw-stm"] = "Sathmar Swabian", ["gmw-tsx"] = "Transylvanian Saxon", ["gmw-vog"] = "Volga German", ["gmw-zps"] = "Zipser German", ["gmx"] = "Magoma", ["gmy"] = "Mycenaean Greek", ["gmz"] = "Mgbo", ["gn-cls"] = "Classical Guarani", ["gna"] = "Kaansa", ["gnb"] = "Gangte", ["gnc"] = "Guanche", ["gnd"] = "Zulgo-Gemzek", ["gne"] = "Ganang", ["gng"] = "Ngangam", ["gnh"] = "Lere", ["gni"] = "Gooniyandi", ["gnj"] = "Ngen of Djonkro", ["gnk"] = "ǁGana", ["gnl"] = "Gangulu", ["gnm"] = "Ginuman", ["gnn"] = "Gumatj", ["gnq"] = "Gana", ["gnr"] = "Gureng Gureng", ["gnt"] = "Guntai", ["gnu"] = "Gnau", ["gnw"] = "Western Bolivian Guarani", ["gnz"] = "Ganzi", ["goa"] = "Guro", ["gob"] = "Playero", ["goc"] = "Gorakor", ["god"] = "Godié", ["goe"] = "Gongduk", ["gof"] = "Gofa", ["gog"] = "Gogo", ["goh"] = "Old High German", ["goi"] = "Gobasi", ["goj"] = "Gowlan", ["gol"] = "Gola", ["gon"] = "Gondi", ["goo"] = "Gone Dau", ["gop"] = "Yeretuar", ["goq"] = "Gorap", ["gor"] = "Gorontalo", ["got"] = "Gothic", ["gou"] = "Gavar", ["gov"] = "Goo", ["gow"] = "Gorwaa", ["gox"] = "Gobu", ["goy"] = "Goundo", ["goz"] = "Gozarkhani", ["gpa"] = "Gupa-Abawa", ["gpn"] = "Taiap", ["gqa"] = "Ga'anda", ["gqi"] = "Guiqiong", ["gqn"] = "Kinikinao", ["gqr"] = "Gor", ["gqu"] = "Qau", ["gra"] = "Rajput Garasia", ["grc"] = "Ancient Greek", ["grd"] = "Guruntum", ["grg"] = "Madi", ["grh"] = "Gbiri-Niragu", ["gri"] = "Ghari", ["grj"] = "Southern Grebo", ["grk-cal"] = "Calabrian Greek", ["grk-ita"] = "Italiot Greek", ["grk-mar"] = "Mariupol Greek", ["grk-pro"] = "Proto-Hellenic", ["grm"] = "Kota Marudu Talantang", ["gro"] = "Groma", ["grq"] = "Gorovu", ["grs"] = "Gresi", ["grt"] = "Garo", ["gru"] = "Kistane", ["grv"] = "Central Grebo", ["grw"] = "Gweda", ["grx"] = "Guriaso", ["gry"] = "Barclayville Grebo", ["grz"] = "Guramalum", ["gse"] = "Ghanaian Sign Language", ["gsg"] = "German Sign Language", ["gsl"] = "Gusilay", ["gsm"] = "Guatemalan Sign Language", ["gsn"] = "Gusan", ["gso"] = "Southwest Gbaya", ["gsp"] = "Wasembo", ["gss"] = "Greek Sign Language", ["gsw"] = "Alemannic German", ["gta"] = "Guató", ["gtu"] = "Aghu Tharrnggala", ["gu"] = "Gujarati", ["gua"] = "Shiki", ["gub"] = "Guajajára", ["guc"] = "Wayuu", ["gud"] = "Yocoboué Dida", ["gue"] = "Gurindji", ["guf"] = "Gupapuyngu", ["gug"] = "Paraguayan Guarani", ["guh"] = "Guahibo", ["gui"] = "Eastern Bolivian Guarani", ["guk"] = "Gumuz", ["gul"] = "Gullah", ["gum"] = "Guambiano", ["gun"] = "Mbya Guarani", ["guo"] = "Guayabero", ["gup"] = "Gunwinggu", ["guq"] = "Aché", ["gur"] = "Farefare", ["gus"] = "Guinean Sign Language", ["gut"] = "Maléku Jaíka", ["guu"] = "Yanomamö", ["guv"] = "Gey", ["guw"] = "Gun", ["gux"] = "Gourmanchéma", ["guz"] = "Gusii", ["gv"] = "Manx", ["gva"] = "Kaskihá", ["gvc"] = "Guanano", ["gve"] = "Duwet", ["gvf"] = "Golin", ["gvj"] = "Guajá", ["gvl"] = "Gulay", ["gvm"] = "Gurmana", ["gvn"] = "Kuku-Yalanji", ["gvo"] = "Gavião do Jiparaná", ["gvp"] = "Pará Gavião", ["gvr"] = "Gurung", ["gvs"] = "Gumawana", ["gvy"] = "Guyani", ["gwa"] = "Mbato", ["gwb"] = "Gwa", ["gwc"] = "Kalami", ["gwd"] = "Gawwada", ["gwe"] = "Gweno", ["gwf"] = "Gowro", ["gwg"] = "Moo", ["gwi"] = "Gwich'in", ["gwj"] = "Gcwi", ["gwm"] = "Awngthim", ["gwn"] = "Gwandara", ["gwr"] = "Gwere", ["gwt"] = "Gawar-Bati", ["gwu"] = "Guwamu", ["gww"] = "Kwini", ["gwx"] = "Gua", ["gxx"] = "Wè Southern", ["gya"] = "Northwest Gbaya", ["gyb"] = "Garus", ["gyd"] = "Kayardild", ["gye"] = "Gyem", ["gyf"] = "Gungabula", ["gyg"] = "Gbayi", ["gyi"] = "Gyele", ["gyl"] = "Gayil", ["gym"] = "Ngäbere", ["gyn"] = "Guyanese Creole English", ["gyo"] = "Gyalsumdo", ["gyr"] = "Guarayu", ["gyy"] = "Gunya", ["gza"] = "Ganza", ["gzn"] = "Gane", ["ha"] = "Hausa", ["haa"] = "Hän", ["hab"] = "Hanoi Sign Language", ["hac"] = "Gurani", ["had"] = "Hatam", ["haf"] = "Haiphong Sign Language", ["hag"] = "Hanga", ["hah"] = "Hahon", ["hai"] = "Haida", ["haj"] = "Hajong", ["hak"] = "Hakka", ["hal"] = "Halang", ["ham"] = "Hewa", ["hao"] = "Hakö", ["hap"] = "Hupla", ["har"] = "Harari", ["has"] = "Haisla", ["hav"] = "Havu", ["haw"] = "Hawaiian", ["hax"] = "Southern Haida", ["hay"] = "Haya", ["hba"] = "Hamba", ["hbb"] = "Huba", ["hbn"] = "Heiban", ["hbu"] = "Habu", ["hca"] = "Andaman Creole Hindi", ["hch"] = "Huichol", ["hdn"] = "Northern Haida", ["hds"] = "Honduras Sign Language", ["hdy"] = "Hadiyya", ["he"] = "Hebrew", ["hea"] = "Northern Qiandong Miao", ["hed"] = "Herdé", ["heg"] = "Helong", ["heh"] = "Hehe", ["hei"] = "Heiltsuk", ["hem"] = "Hemba", ["hgm"] = "Haiǁom", ["hgw"] = "Haigwai", ["hhi"] = "Hoia Hoia", ["hhr"] = "Kerak", ["hhy"] = "Hoyahoya", ["hi"] = "Hindi", ["hia"] = "Lamang", ["hib"] = "Hibito", ["hid"] = "Hidatsa", ["hif"] = "Fiji Hindi", ["hig"] = "Kamwe", ["hih"] = "Pamosu", ["hii"] = "Hinduri", ["hij"] = "Hijuk", ["hik"] = "Seit-Kaitetu", ["hil"] = "Hiligaynon", ["hio"] = "Tshwa", ["hir"] = "Himarimã", ["hit"] = "Hittite", ["hiw"] = "Hiw", ["hix"] = "Hixkaryana", ["hji"] = "Haji", ["hka"] = "Kahe", ["hke"] = "Hunde", ["hkh"] = "Pogali", ["hkk"] = "Hunjara-Kaina Ke", ["hkn"] = "Mel-Khaonh", ["hks"] = "Hong Kong Sign Language", ["hla"] = "Halia", ["hlb"] = "Halbi", ["hld"] = "Halang Doan", ["hle"] = "Hlersu", ["hlt"] = "Nga La", ["hma"] = "Southern Mashan Hmong", ["hmb"] = "Humburi Senni", ["hmc"] = "Central Huishui Hmong", ["hmd"] = "A-Hmao", ["hme"] = "Eastern Huishui Hmong", ["hmf"] = "Hmong Don", ["hmg"] = "Southwestern Guiyang Hmong", ["hmh"] = "Southwestern Huishui Hmong", ["hmi"] = "Northern Huishui Hmong", ["hmj"] = "Ge", ["hmk"] = "Yemaek", ["hml"] = "Luopohe Hmong", ["hmm"] = "Central Mashan Hmong", ["hmn-pro"] = "Proto-Hmongic", ["hmp"] = "Northern Mashan Hmong", ["hmq"] = "Eastern Qiandong Miao", ["hmr"] = "Hmar", ["hms"] = "Southern Qiandong Miao", ["hmt"] = "Hamtai", ["hmu"] = "Hamap", ["hmv"] = "Hmong Dô", ["hmw"] = "Western Mashan Hmong", ["hmx-mie-pro"] = "Proto-Mienic", ["hmx-pro"] = "Proto-Hmong-Mien", ["hmy"] = "Southern Guiyang Hmong", ["hmz"] = "Hmong Shua", ["hna"] = "Mina", ["hnd"] = "Southern Hindko", ["hne"] = "Chhattisgarhi", ["hnh"] = "ǁAni", ["hni"] = "Hani", ["hnj"] = "Green Hmong", ["hnm"] = "Hainanese", ["hnn"] = "Hanunoo", ["hno"] = "Northern Hindko", ["hns"] = "Caribbean Hindustani", ["hnu"] = "Hung", ["ho"] = "Hiri Motu", ["hoa"] = "Hoava", ["hob"] = "Mari (Austronesian)", ["hoc"] = "Ho", ["hod"] = "Holma", ["hoe"] = "Horom", ["hoh"] = "Hobyót", ["hoi"] = "Holikachuk", ["hoj"] = "Hadoti", ["hol"] = "Holu", ["hom"] = "Homa", ["hoo"] = "Holoholo", ["hop"] = "Hopi", ["hor"] = "Horo", ["hos"] = "Ho Chi Minh City Sign Language", ["hot"] = "Hote", ["hov"] = "Hovongan", ["how"] = "Honi", ["hoy"] = "Holiya", ["hoz"] = "Hozo", ["hpo"] = "Hpon", ["hps"] = "Hawai'i Pidgin Sign Language", ["hra"] = "Hrangkhol", ["hrc"] = "Niwer Mil", ["hre"] = "Hrê", ["hrk"] = "Haruku", ["hrm"] = "Horned Miao", ["hro"] = "Haroi", ["hrp"] = "Nhirrpi", ["hrt"] = "Hértevin", ["hru"] = "Hruso", ["hrw"] = "Warwar Feni", ["hrx"] = "Hunsrik", ["hrz"] = "Harzani", ["hsb"] = "Upper Sorbian", ["hsh"] = "Hungarian Sign Language", ["hsl"] = "Hausa Sign Language", ["hsn"] = "Xiang", ["hss"] = "Harsusi", ["ht"] = "Haitian Creole", ["hti"] = "Hoti", ["hto"] = "Minica Huitoto", ["hts"] = "Hadza", ["htu"] = "Hitu", ["hu"] = "Hungarian", ["hub"] = "Huambisa", ["huc"] = "ǂHoan", ["hud"] = "Huaulu", ["huf"] = "Humene", ["hug"] = "Huachipaeri", ["huh"] = "Huilliche", ["hui"] = "Huli", ["huj"] = "Northern Guiyang Hmong", ["huk"] = "Hulung", ["hul"] = "Hula", ["hum"] = "Hungana", ["huo"] = "Hu", ["hup"] = "Hupa", ["huq"] = "Tsat", ["hur"] = "Halkomelem", ["hus"] = "Wastek", ["huu"] = "Murui Huitoto", ["huv"] = "Huave", ["huw"] = "Hukumina", ["hux"] = "Nüpode Huitoto", ["huy"] = "Hulaulá", ["huz"] = "Hunzib", ["hvc"] = "Haitian Vodoun Culture Language", ["hvk"] = "Haveke", ["hvn"] = "Sabu", ["hwa"] = "Wané", ["hwc"] = "Hawaiian Creole", ["hwo"] = "Hwana", ["hy"] = "Armenian", ["hya"] = "Hya", ["hyx-pro"] = "Proto-Armenian", ["hz"] = "Herero", ["ia"] = "Interlingua", ["iai"] = "Iaai", ["ian"] = "Iatmul", ["iar"] = "Purari", ["iba"] = "Iban", ["ibb"] = "Ibibio", ["ibd"] = "Iwaidja", ["ibe"] = "Akpes", ["ibg"] = "Ibanag", ["ibh"] = "Bih", ["ibl"] = "Ibaloi", ["ibm"] = "Agoi", ["ibn"] = "Ibino", ["ibr"] = "Ibuoro", ["ibu"] = "Ibu", ["iby"] = "Ibani", ["ica"] = "Ede Ica", ["ich"] = "Etkywan", ["icl"] = "Icelandic Sign Language", ["icr"] = "Islander Creole English", ["id"] = "Indonesian", ["ida"] = "Idakho-Isukha-Tiriki", ["idb"] = "Indo-Portuguese", ["idc"] = "Idon", ["idd"] = "Ede Idaca", ["ide"] = "Idere", ["idi"] = "Idi", ["idr"] = "Indri", ["ids"] = "Idesa", ["idt"] = "Idaté", ["idu"] = "Idoma", ["ie"] = "Interlingue", ["ifa"] = "Amganad Ifugao", ["ifb"] = "Batad Ifugao", ["ife"] = "Ifè", ["iff"] = "Ifo", ["ifk"] = "Tuwali Ifugao", ["ifm"] = "Teke-Fuumu", ["ifu"] = "Mayoyao Ifugao", ["ify"] = "Keley-I Kallahan", ["ig"] = "Igbo", ["igb"] = "Ebira", ["ige"] = "Igede", ["igg"] = "Igana", ["igl"] = "Igala", ["igm"] = "Kanggape", ["ign"] = "Ignaciano", ["igo"] = "Isebe", ["igs"] = "Glosa", ["igw"] = "Igwe", ["ihb"] = "Pidgin Iha", ["ihi"] = "Ihievbe", ["ihp"] = "Iha", ["ii"] = "Nuosu", ["iir-nur-pro"] = "Proto-Nuristani", ["iir-pro"] = "Proto-Indo-Iranian", ["ijc"] = "Izon", ["ije"] = "Biseni", ["ijj"] = "Ede Ije", ["ijn"] = "Kalabari", ["ijo-pro"] = "Proto-Ijoid", ["ijs"] = "Southeast Ijo", ["ik"] = "Inupiaq", ["ike"] = "Eastern Canadian Inuktitut", ["iki"] = "Iko", ["ikk"] = "Ika", ["ikl"] = "Ikulu", ["iko"] = "Olulumo-Ikom", ["ikp"] = "Ikpeshi", ["ikr"] = "Ikaranggal", ["iks"] = "Inuit Sign Language", ["ikt"] = "Inuvialuktun", ["ikv"] = "Iku-Gora-Ankwa", ["ikw"] = "Ikwere", ["ikx"] = "Ik", ["ikz"] = "Ikizu", ["ila"] = "Ile Ape", ["ilb"] = "Ila", ["ilg"] = "Ilgar", ["ili"] = "Ili Turki", ["ilk"] = "Ilongot", ["ill"] = "Iranun", ["ilo"] = "Ilocano", ["ils"] = "International Sign", ["ilu"] = "Ili'uun", ["ilv"] = "Ilue", ["ima"] = "Mala Malasar", ["imi"] = "Anamgura", ["iml"] = "Miluk", ["imn"] = "Imonda", ["imo"] = "Imbongu", ["imr"] = "Imroing", ["ims"] = "Marsian", ["imy"] = "Milyan", ["inb"] = "Inga", ["inc-apa"] = "Apabhramsa", ["inc-ash"] = "Ashokan Prakrit", ["inc-dng-pro"] = "Proto-Dangari", ["inc-kam"] = "Kamarupi Prakrit", ["inc-kho"] = "Kholosi", ["inc-krd-pro"] = "Proto-Kamta", ["inc-mas"] = "Middle Assamese", ["inc-mbn"] = "Middle Bengali", ["inc-mgu"] = "Middle Gujarati", ["inc-mor"] = "Middle Odia", ["inc-oas"] = "Early Assamese", ["inc-oaw"] = "Old Awadhi", ["inc-obn"] = "Old Bengali", ["inc-ogu"] = "Old Gujarati", ["inc-ohi"] = "Old Hindi", ["inc-oor"] = "Old Odia", ["inc-opa"] = "Old Punjabi", ["inc-pro"] = "Proto-Indo-Aryan", ["ine-ana-pro"] = "Proto-Anatolian", ["ine-bsl-pro"] = "Proto-Balto-Slavic", ["ine-grp-pro"] = "Proto-Graeco-Phrygian", ["ine-kal"] = "Kalašma", ["ine-pae"] = "Paeonian", ["ine-pro"] = "Proto-Indo-European", ["ine-toc-pro"] = "Proto-Tocharian", ["ing"] = "Deg Xinag", ["inh"] = "Ingush", ["inj"] = "Jungle Inga", ["inl"] = "Indonesian Sign Language", ["inm"] = "Minaean", ["inn"] = "Isinai", ["ino"] = "Inoke-Yate", ["inp"] = "Iñapari", ["ins"] = "Indian Sign Language", ["int"] = "Intha", ["inz"] = "Ineseño", ["io"] = "Ido", ["ior"] = "Inor", ["iou"] = "Tuma-Irumu", ["iow"] = "Chiwere", ["ipi"] = "Ipili", ["ipo"] = "Ipiko", ["iqu"] = "Iquito", ["iqw"] = "Ikwo", ["ira-kms-pro"] = "Proto-Komisenian", ["ira-mny-pro"] = "Proto-Munji-Yidgha", ["ira-mpr-pro"] = "Proto-Medo-Parthian", ["ira-pat-pro"] = "Proto-Pathan", ["ira-pro"] = "Proto-Iranian", ["ira-sgc-pro"] = "Proto-Sogdic", ["ira-sgi-pro"] = "Proto-Sanglechi-Ishkashimi", ["ira-shr-pro"] = "Proto-Shughni-Roshani", ["ira-shy-pro"] = "Proto-Shughni-Yazghulami", ["ira-sym-pro"] = "Proto-Shughni-Yazghulami-Munji", ["ira-wnj"] = "Vanji", ["ira-zgr-pro"] = "Proto-Zaza-Gorani", ["ire"] = "Iresim", ["irh"] = "Irarutu", ["iri"] = "Rigwe", ["irk"] = "Iraqw", ["irn"] = "Irantxe", ["iro-ere"] = "Erie", ["iro-min"] = "Mingo", ["iro-nor-pro"] = "Proto-North Iroquoian", ["iro-pro"] = "Proto-Iroquoian", ["irr"] = "Ir", ["iru"] = "Irula", ["irx"] = "Kamberau", ["iry"] = "Iraya", ["is"] = "Icelandic", ["isa"] = "Isabi", ["isc"] = "Isconahua", ["isd"] = "Isnag", ["ise"] = "Italian Sign Language", ["isg"] = "Irish Sign Language", ["ish"] = "Esan", ["isi"] = "Nkem-Nkum", ["isk"] = "Ishkashimi", ["ism"] = "Masimasi", ["isn"] = "Isanzu", ["iso"] = "Isoko", ["isr"] = "Israeli Sign Language", ["ist"] = "Istriot", ["isu"] = "Isu", ["isv"] = "Interslavic", ["it"] = "Italian", ["itb"] = "Binongan Itneg", ["itc-pro"] = "Proto-Italic", ["itc-psa"] = "Pre-Samnite", ["itd"] = "Southern Tidung", ["ite"] = "Itene", ["iti"] = "Inlaod Itneg", ["itk"] = "Judeo-Italian", ["itl"] = "Itelmen", ["itm"] = "Itu Mbon Uzo", ["ito"] = "Itonama", ["itr"] = "Iteri", ["its"] = "Itsekiri", ["itt"] = "Maeng Itneg", ["itv"] = "Itawit", ["itw"] = "Ito", ["itx"] = "Itik", ["ity"] = "Moyadan Itneg", ["itz"] = "Itza'", ["iu"] = "Inuktitut", ["ium"] = "Iu Mien", ["ivb"] = "Ibatan", ["ivv"] = "Ivatan", ["iwk"] = "I-Wak", ["iwm"] = "Iwam", ["iwo"] = "Iwur", ["iws"] = "Sepik Iwam", ["ixc"] = "Ixcatec", ["ixl"] = "Ixil", ["iya"] = "Iyayu", ["iyo"] = "Mesaka", ["iyx"] = "Yaa", ["izh"] = "Ingrian", ["izi"] = "Izi-Ezaa-Ikwo-Mgbo", ["izr"] = "Izere", ["izz"] = "Izi", ["ja"] = "Japanese", ["jaa"] = "Jamamadí", ["jab"] = "Hyam", ["jac"] = "Jakaltek", ["jad"] = "Jahanka", ["jae"] = "Jabem", ["jaf"] = "Jara", ["jah"] = "Jah Hut", ["jaj"] = "Zazao", ["jal"] = "Yalahatan", ["jam"] = "Jamaican Creole", ["jan"] = "Janday", ["jao"] = "Yanyuwa", ["jaq"] = "Yaqay", ["jas"] = "New Caledonian Javanese", ["jat"] = "Jakati", ["jau"] = "Yaur", ["jax"] = "Jambi Malay", ["jay"] = "Yan-nhangu", ["jaz"] = "Jawe", ["jbi"] = "Badjiri", ["jbj"] = "Arandai", ["jbk"] = "Barikewa", ["jbn"] = "Nefusa", ["jbo"] = "Lojban", ["jbr"] = "Jofotek-Bromnya", ["jbt"] = "Jabutí", ["jbu"] = "Jukun Takum", ["jbw"] = "Yawijibaya", ["jcs"] = "Jamaican Country Sign Language", ["jct"] = "Krymchak", ["jda"] = "Jad", ["jdg"] = "Jadgali", ["jdt"] = "Judeo-Tat", ["jeb"] = "Jebero", ["jee"] = "Jerung", ["jeg"] = "Jeng", ["jeh"] = "Jeh", ["jei"] = "Yei", ["jek"] = "Jeri Kuo", ["jel"] = "Yelmek", ["jen"] = "Dza", ["jer"] = "Jere", ["jet"] = "Manem", ["jeu"] = "Jonkor Bourmataguil", ["jgb"] = "Ngbee", ["jgk"] = "Gwak", ["jgo"] = "Ngomba", ["jhi"] = "Jehai", ["jhs"] = "Jhankot Sign Language", ["jia"] = "Jina", ["jib"] = "Jibu", ["jic"] = "Tol", ["jid"] = "Bu", ["jie"] = "Jilbe", ["jig"] = "Jingulu", ["jih"] = "Shangzhai", ["jii"] = "Jiiddu", ["jil"] = "Jilim", ["jim"] = "Jimjimen", ["jio"] = "Jiamao", ["jiq"] = "Khroskyabs", ["jit"] = "Jita", ["jiu"] = "Youle Jino", ["jiv"] = "Shuar", ["jiy"] = "Buyuan Jino", ["jje"] = "Jeju", ["jjr"] = "Zhár", ["jka"] = "Kaera", ["jko"] = "Kubo", ["jkp"] = "Paku Karen", ["jkr"] = "Koro (India)", ["jku"] = "Labir", ["jle"] = "Ngile", ["jls"] = "Jamaican Sign Language", ["jma"] = "Dima", ["jmb"] = "Zumbun", ["jmc"] = "Machame", ["jmd"] = "Yamdena", ["jmi"] = "Jimi", ["jml"] = "Jumli", ["jmn"] = "Makuri Naga", ["jmr"] = "Kamara", ["jmw"] = "Mouwase", ["jmx"] = "Western Juxtlahuaca Mixtec", ["jna"] = "Jangshung", ["jnd"] = "Jandavra", ["jng"] = "Yangman", ["jni"] = "Janji", ["jnj"] = "Yemsa", ["jnl"] = "Rawat", ["jns"] = "Jaunsari", ["job"] = "Joba", ["jod"] = "Wojenaka", ["jor"] = "Jorá", ["jos"] = "Jordanian Sign Language", ["jow"] = "Jowulu", ["jpr"] = "Judeo-Persian", ["jpx-hcj"] = "Hachijō", ["jpx-pro"] = "Proto-Japonic", ["jpx-ryu-pro"] = "Proto-Ryukyuan", ["jqr"] = "Jaqaru", ["jra"] = "Jarai", ["jrr"] = "Jiru", ["jru"] = "Japrería", ["jsl"] = "Japanese Sign Language", ["jua"] = "Júma", ["jub"] = "Wannu", ["juc"] = "Jurchen", ["jud"] = "Worodougou", ["juh"] = "Hone", ["jui"] = "Ngadjuri", ["juk"] = "Wapan", ["jul"] = "Jirel", ["jum"] = "Jumjum", ["jun"] = "Juang", ["juo"] = "Jiba", ["jup"] = "Hupdë", ["jur"] = "Jurúna", ["jus"] = "Jumla Sign Language", ["jut"] = "Jutish", ["juu"] = "Ju", ["juw"] = "Wãpha", ["juy"] = "Juray", ["jv"] = "Javanese", ["jvd"] = "Javindo", ["jvn"] = "Caribbean Javanese", ["jwi"] = "Jwira-Pepesa", ["jyy"] = "Jaya", ["ka"] = "Georgian", ["kaa"] = "Karakalpak", ["kab"] = "Kabyle", ["kac"] = "Jingpho", ["kad"] = "Kadara", ["kae"] = "Ketangalan", ["kaf"] = "Katso", ["kag"] = "Kajaman", ["kah"] = "Fer", ["kai"] = "Karekare", ["kaj"] = "Jju", ["kak"] = "Kayapa Kallahan", ["kam"] = "Kamba", ["kao"] = "Kassonke", ["kap"] = "Bezhta", ["kaq"] = "Capanahua", ["kar-pro"] = "Proto-Karen", ["kaw"] = "Old Javanese", ["kax"] = "Kao", ["kay"] = "Kamayurá", ["kba"] = "Kalarko", ["kbb"] = "Kaxuyana", ["kbc"] = "Kadiwéu", ["kbd"] = "East Circassian", ["kbe"] = "Kanju", ["kbh"] = "Camsá", ["kbi"] = "Kaptiau", ["kbj"] = "Kari", ["kbk"] = "Grass Koiari", ["kbm"] = "Iwal", ["kbn"] = "Kare (Central Africa)", ["kbo"] = "Keliko", ["kbp"] = "Kabiye", ["kbq"] = "Kamano", ["kbr"] = "Kafa", ["kbs"] = "Kande", ["kbt"] = "Gabadi", ["kbu"] = "Kabutra", ["kbv"] = "Kamberataro", ["kbw"] = "Kaiep", ["kbx"] = "Ap Ma", ["kbz"] = "Duhwa", ["kca-eas"] = "Eastern Khanty", ["kca-nor"] = "Northern Khanty", ["kca-pro"] = "Proto-Khanty", ["kca-sou"] = "Southern Khanty", ["kcb"] = "Kawacha", ["kcc"] = "Lubila", ["kcd"] = "Ngkâlmpw Kanum", ["kce"] = "Kaivi", ["kcf"] = "Ukaan", ["kcg"] = "Tyap", ["kch"] = "Vono", ["kci"] = "Kamantan", ["kcj"] = "Kobiana", ["kck"] = "Kalanga", ["kcl"] = "Kala", ["kcm"] = "Tar Gula", ["kcn"] = "Nubi", ["kco"] = "Kinalakna", ["kcp"] = "Kanga", ["kcq"] = "Kamo", ["kcr"] = "Katla", ["kcs"] = "Koenoem", ["kct"] = "Kaian", ["kcu"] = "Kikami", ["kcv"] = "Kete", ["kcw"] = "Kabwari", ["kcx"] = "Kachama-Ganjule", ["kcy"] = "Korandje", ["kcz"] = "Konongo", ["kda"] = "Worimi", ["kdc"] = "Kutu", ["kdd"] = "Yankunytjatjara", ["kde"] = "Makonde", ["kdf"] = "Mamusi", ["kdg"] = "Seba", ["kdh"] = "Tem", ["kdi"] = "Kumam", ["kdj"] = "Karamojong", ["kdk"] = "Numèè", ["kdl"] = "Tsikimba", ["kdm"] = "Kagoma", ["kdn"] = "Kunda", ["kdp"] = "Kaningdon-Nindem", ["kdq"] = "Koch", ["kdr"] = "Karaim", ["kdt"] = "Kuy", ["kdu"] = "Kadaru", ["kdv"] = "Kado", ["kdw"] = "Koneraw", ["kdx"] = "Kam", ["kdy"] = "Keder", ["kdz"] = "Kwaja", ["kea"] = "Kabuverdianu", ["keb"] = "Kélé", ["kec"] = "Keiga", ["ked"] = "Kerewe", ["kee"] = "Eastern Keres", ["kef"] = "Kpessi", ["keg"] = "Tese", ["keh"] = "Keak", ["kei"] = "Kei", ["kej"] = "Kadar", ["kek"] = "Q'eqchi", ["kel"] = "Kela-Yela", ["kem"] = "Kemak", ["ken"] = "Kenyang", ["keo"] = "Kakwa", ["kep"] = "Kaikadi", ["keq"] = "Kamar", ["ker"] = "Kera", ["kes"] = "Kugbo", ["ket"] = "Ket", ["keu"] = "Akebu", ["kev"] = "Kanikkaran", ["kew"] = "Kewa", ["kex"] = "Kukna", ["key"] = "Kupia", ["kez"] = "Kukele", ["kfa"] = "Kodava", ["kfb"] = "Kolami", ["kfc"] = "Konda-Dora", ["kfd"] = "Korra Koraga", ["kfe"] = "Kota (India)", ["kff"] = "Koya", ["kfg"] = "Kudiya", ["kfh"] = "Kurichiya", ["kfi"] = "Kannada Kurumba", ["kfj"] = "Kemiehua", ["kfk"] = "Kinnauri", ["kfl"] = "Kung", ["kfn"] = "Kuk", ["kfo"] = "Koro (West Africa)", ["kfp"] = "Korwa", ["kfq"] = "Korku", ["kfr"] = "Kachchi", ["kfs"] = "Bilaspuri", ["kft"] = "Kanjari", ["kfu"] = "Katkari", ["kfv"] = "Kurmukar", ["kfw"] = "Kharam Naga", ["kfx"] = "Kullu Pahari", ["kfy"] = "Kumaoni", ["kfz"] = "Koromfé", ["kg"] = "Kongo", ["kga"] = "Koyaga", ["kgb"] = "Kawe", ["kgd"] = "Kataang", ["kge"] = "Komering", ["kgf"] = "Kube", ["kgg"] = "Kusunda", ["kgi"] = "Selangor Sign Language", ["kgj"] = "Gamale Kham", ["kgk"] = "Kaiwá", ["kgl"] = "Kunggari", ["kgn"] = "Karingani", ["kgo"] = "Krongo", ["kgp"] = "Kaingang", ["kgq"] = "Kamoro", ["kgr"] = "Abun", ["kgs"] = "Kumbainggar", ["kgt"] = "Somyev", ["kgu"] = "Kobol", ["kgv"] = "Karas", ["kgw"] = "Karon Dori", ["kgx"] = "Kamaru", ["kgy"] = "Kyerung", ["kha"] = "Khasi", ["khb"] = "Lü", ["khc"] = "North Tukang Besi", ["khd"] = "Bädi Kanum", ["khe"] = "Korowai", ["khf"] = "Khuen", ["khh"] = "Kehu", ["khi-kho-pro"] = "Proto-Khoe", ["khi-kun"] = "ǃKung", ["khj"] = "Kuturmi", ["khl"] = "Lusi", ["khn"] = "Khandeshi", ["kho"] = "Khotanese", ["khp"] = "Kapauri", ["khq"] = "Koyra Chiini", ["khr"] = "Kharia", ["khs"] = "Kasua", ["kht"] = "Khamti", ["khu"] = "Nkhumbi", ["khv"] = "Khvarshi", ["khw"] = "Khowar", ["khx"] = "Kanu", ["khy"] = "Ekele", ["khz"] = "Keapara", ["ki"] = "Kikuyu", ["kia"] = "Kim", ["kib"] = "Koalib", ["kic"] = "Kickapoo", ["kid"] = "Koshin", ["kie"] = "Kibet", ["kif"] = "Eastern Parbate Kham", ["kig"] = "Kimaama", ["kih"] = "Kilmeri", ["kii"] = "Kitsai", ["kij"] = "Kilivila", ["kil"] = "Kariya", ["kim"] = "Tofa", ["kio"] = "Kiowa", ["kip"] = "Sheshi Kham", ["kiq"] = "Kosadle", ["kis"] = "Kis", ["kit"] = "Agob", ["kiv"] = "Kimbu", ["kiw"] = "Northeast Kiwai", ["kix"] = "Khiamniungan Naga", ["kiy"] = "Kirikiri", ["kiz"] = "Kisi", ["kj"] = "Kwanyama", ["kja"] = "Mlap", ["kjb"] = "Q'anjob'al", ["kjc"] = "Coastal Konjo", ["kjd"] = "Southern Kiwai", ["kje"] = "Kisar", ["kjg"] = "Khmu", ["kjh"] = "Khakas", ["kji"] = "Zabana", ["kjj"] = "Khinalug", ["kjk"] = "Highland Konjo", ["kjl"] = "Western Parbate Kham", ["kjm"] = "Kháng", ["kjn"] = "Kunjen", ["kjo"] = "Harijan Kinnauri", ["kjp"] = "Eastern Pwo", ["kjq"] = "Western Keres", ["kjr"] = "Kurudu", ["kjs"] = "East Kewa", ["kjt"] = "Phrae Pwo", ["kju"] = "Kashaya", ["kjx"] = "Ramopa", ["kjy"] = "Erave", ["kjz"] = "Bumthangkha", ["kk"] = "Kazakh", ["kka"] = "Kakanda", ["kkb"] = "Kwerisa", ["kkc"] = "Odoodee", ["kkd"] = "Kinuku", ["kke"] = "Kakabe", ["kkf"] = "Kalaktang Monpa", ["kkg"] = "Mabaka Valley Kalinga", ["kkh"] = "Khün", ["kki"] = "Kagulu", ["kkj"] = "Kako", ["kkk"] = "Kokota", ["kkl"] = "Kosarek Yale", ["kkm"] = "Kiong", ["kkn"] = "Kon Keu", ["kko"] = "Karko", ["kkp"] = "Koko-Bera", ["kkq"] = "Kaiku", ["kkr"] = "Kir-Balar", ["kks"] = "Kirfi", ["kkt"] = "Koi", ["kku"] = "Tumi", ["kkv"] = "Kangean", ["kkw"] = "Teke-Kukuya", ["kkx"] = "Kohin", ["kky"] = "Guugu Yimidhirr", ["kkz"] = "Kaska", ["kl"] = "Greenlandic", ["kla"] = "Klamath-Modoc", ["klb"] = "Kiliwa", ["klc"] = "Kolbila", ["kld"] = "Gamilaraay", ["kle"] = "Kulung", ["klf"] = "Kendeje", ["klg"] = "Tagakaulu Kalagan", ["klh"] = "Weliki", ["kli"] = "Kalumpang", ["klj"] = "Khalaj", ["klk"] = "Kono (Nigeria)", ["kll"] = "Kagan Kalagan", ["klm"] = "Kolom", ["kln"] = "Kalenjin", ["klo"] = "Kapya", ["klp"] = "Kamasa", ["klq"] = "Rumu", ["klr"] = "Khaling", ["kls"] = "Kalasha", ["klt"] = "Nukna", ["klu"] = "Klao", ["klv"] = "Maskelynes", ["klw"] = "Lindu", ["klx"] = "Koluwawa", ["kly"] = "Kalao", ["klz"] = "Kabola", ["km"] = "Khmer", ["kma"] = "Konni", ["kmb"] = "Kimbundu", ["kmc"] = "Southern Kam", ["kmd"] = "Madukayang Kalinga", ["kme"] = "Bakole", ["kmf"] = "Kare (New Guinea)", ["kmg"] = "Kâte", ["kmh"] = "Kalam", ["kmi"] = "Kami", ["kmj"] = "Kumarbhag Paharia", ["kmk"] = "Limos Kalinga", ["kml"] = "Tanudan Kalinga", ["kmm"] = "Kom (India)", ["kmn"] = "Awtuw", ["kmo"] = "Kwoma", ["kmp"] = "Gimme", ["kmq"] = "Kwama", ["kmr"] = "Northern Kurdish", ["kms"] = "Kamasau", ["kmt"] = "Kemtuik", ["kmu"] = "Kanite", ["kmv"] = "Karipúna Creole French", ["kmw"] = "Kumu", ["kmx"] = "Waboda", ["kmy"] = "Koma", ["kmz"] = "Khorasani Turkish", ["kn"] = "Kannada", ["kna"] = "Kanakuru", ["knb"] = "Lubuagan Kalinga", ["knd"] = "Konda", ["kne"] = "Kankanaey", ["knf"] = "Mankanya", ["kni"] = "Kanufi", ["knj"] = "Akatek", ["knk"] = "Kuranko", ["knl"] = "Keninjal", ["knm"] = "Kanamari", ["kno"] = "Kono (Sierra Leone)", ["knp"] = "Kwanja", ["knq"] = "Kintaq", ["knr"] = "Kaningra", ["kns"] = "Kensiu", ["knt"] = "Katukina", ["knu"] = "Kono (Guinea)", ["knv"] = "Tabo", ["knx"] = "Kendayan", ["kny"] = "Kanyok", ["knz"] = "Kalamsé", ["ko"] = "Korean", ["ko-ear"] = "Early Modern Korean", ["koa"] = "Konomala", ["koc"] = "Kpati", ["kod"] = "Kodi", ["koe"] = "Kacipo-Balesi", ["kof"] = "Kubi", ["kog"] = "Cogui", ["koh"] = "Koyo", ["koi"] = "Komi-Permyak", ["kok"] = "Konkani", ["kol"] = "Kol (New Guinea)", ["koo"] = "Konzo", ["kop"] = "Waube", ["koq"] = "Kota (Gabon)", ["kos"] = "Kosraean", ["kot"] = "Lagwan", ["kou"] = "Koke", ["kov"] = "Kudu-Camo", ["kow"] = "Kugama", ["koy"] = "Koyukon", ["koz"] = "Korak", ["kpa"] = "Kutto", ["kpb"] = "Mullu Kurumba", ["kpc"] = "Curripaco", ["kpd"] = "Koba", ["kpe"] = "Kpelle", ["kpf"] = "Komba", ["kpg"] = "Kapingamarangi", ["kph"] = "Kplang", ["kpi"] = "Kofei", ["kpj"] = "Karajá", ["kpk"] = "Kpan", ["kpl"] = "Kpala", ["kpm"] = "Koho", ["kpn"] = "Kepkiriwát", ["kpo"] = "Ikposo", ["kpq"] = "Korupun-Sela", ["kpr"] = "Korafe-Yegha", ["kps"] = "Tehit", ["kpt"] = "Karata", ["kpu"] = "Kafoa", ["kpv"] = "Komi-Zyrian", ["kpw"] = "Kobon", ["kpx"] = "Mountain Koiari", ["kpy"] = "Koryak", ["kpz"] = "Kupsabiny", ["kqa"] = "Mum", ["kqb"] = "Kovai", ["kqc"] = "Doromu-Koki", ["kqd"] = "Koy Sanjaq Surat", ["kqe"] = "Kalagan", ["kqf"] = "Kakabai", ["kqg"] = "Khe", ["kqh"] = "Kisankasa", ["kqi"] = "Koitabu", ["kqj"] = "Koromira", ["kqk"] = "Kotafon Gbe", ["kql"] = "Kyenele", ["kqm"] = "Khisa", ["kqn"] = "Kaonde", ["kqo"] = "Eastern Krahn", ["kqp"] = "Kimré", ["kqq"] = "Krenak", ["kqr"] = "Kimaragang", ["kqs"] = "Northern Kissi", ["kqt"] = "Klias River Kadazan", ["kqu"] = "Seroa", ["kqv"] = "Okolod", ["kqw"] = "Kandas", ["kqx"] = "Mser", ["kqy"] = "Koorete", ["kqz"] = "Korana", ["kr"] = "Kanuri", ["kra"] = "Kumhali", ["krb"] = "Karkin", ["krc"] = "Karachay-Balkar", ["krd"] = "Kairui-Midiki", ["kre"] = "Panará", ["krf"] = "Koro (Vanuatu)", ["krh"] = "Kurama", ["kri"] = "Krio", ["krj"] = "Kinaray-a", ["krk"] = "Kerek", ["krl"] = "Karelian", ["krm"] = "Krim", ["krn"] = "Sapo", ["kro-pro"] = "Proto-Kru", ["krp"] = "Korop", ["krr"] = "Kru'ng", ["krs"] = "Kresh", ["kru"] = "Kurux", ["krv"] = "Kavet", ["krw"] = "Western Krahn", ["krx"] = "Karon", ["kry"] = "Kryts", ["krz"] = "Sota Kanum", ["ks"] = "Kashmiri", ["ksa"] = "Shuwa-Zamani", ["ksb"] = "Shambala", ["ksc"] = "Southern Kalinga", ["ksd"] = "Tolai", ["kse"] = "Kuni", ["ksf"] = "Bafia", ["ksg"] = "Kusaghe", ["ksi"] = "Krisa", ["ksj"] = "Uare", ["ksk"] = "Kansa", ["ksl"] = "Kumalu", ["ksm"] = "Kumba", ["ksn"] = "Kasiguranin", ["kso"] = "Kofa", ["ksp"] = "Kaba", ["ksq"] = "Kwaami", ["ksr"] = "Borong", ["kss"] = "Southern Kissi", ["kst"] = "Winyé", ["ksu"] = "Khamyang", ["ksv"] = "Kusu", ["ksw"] = "S'gaw Karen", ["ksx"] = "Kedang", ["ksy"] = "Kharia Thar", ["ksz"] = "Kodaku", ["kta"] = "Katua", ["ktb"] = "Kambaata", ["ktc"] = "Kholok", ["ktd"] = "Kokata", ["ktf"] = "Kwami", ["ktg"] = "Kalkatungu", ["kth"] = "Karanga", ["kti"] = "North Muyu", ["ktj"] = "Plapo Krumen", ["ktk"] = "Kaniet", ["ktl"] = "Koroshi", ["ktm"] = "Kurti", ["ktn"] = "Karitiâna", ["kto"] = "Kuot", ["ktp"] = "Kaduo", ["ktq"] = "Katabaga", ["kts"] = "South Muyu", ["ktt"] = "Ketum", ["ktu"] = "Kituba", ["ktv"] = "Eastern Katu", ["ktw"] = "Kato", ["ktx"] = "Kaxararí", ["kty"] = "Kango", ["ktz"] = "Juǀ'hoan", ["ku-pro"] = "Proto-Kurdish", ["kub"] = "Kutep", ["kuc"] = "Kwinsu", ["kud"] = "Auhelawa", ["kue"] = "Kuman", ["kuf"] = "Western Katu", ["kug"] = "Kupa", ["kuh"] = "Kushi", ["kui"] = "Kuikúro", ["kuj"] = "Kuria", ["kuk"] = "Kepo'", ["kul"] = "Kulere", ["kum"] = "Kumyk", ["kun"] = "Kunama", ["kuo"] = "Kumukio", ["kup"] = "Kunimaipa", ["kuq"] = "Karipuna", ["kus"] = "Kusaal", ["kut"] = "Ktunaxa", ["kuu"] = "Upper Kuskokwim", ["kuv"] = "Kur", ["kuw"] = "Kpagua", ["kux"] = "Kukatja", ["kuy"] = "Kuuku-Ya'u", ["kuz"] = "Kunza", ["kva"] = "Bagvalal", ["kvb"] = "Kubu", ["kvc"] = "Kove", ["kvd"] = "Kui (Indonesia)", ["kve"] = "Kalabakan", ["kvf"] = "Kabalai", ["kvg"] = "Kuni-Boazi", ["kvh"] = "Komodo", ["kvi"] = "Kwang", ["kvj"] = "Psikye", ["kvk"] = "Korean Sign Language", ["kvl"] = "Brek Karen", ["kvm"] = "Kendem", ["kvn"] = "Border Kuna", ["kvo"] = "Dobel", ["kvp"] = "Kompane", ["kvq"] = "Geba Karen", ["kvr"] = "Kerinci", ["kvt"] = "Lahta Karen", ["kvu"] = "Yinbaw Karen", ["kvv"] = "Kola", ["kvw"] = "Wersing", ["kvx"] = "Parkari Koli", ["kvy"] = "Yintale Karen", ["kvz"] = "Tsakwambo", ["kw"] = "Cornish", ["kwa"] = "Dâw", ["kwb"] = "Baa", ["kwc"] = "Likwala", ["kwd"] = "Kwaio", ["kwe"] = "Kwerba", ["kwf"] = "Kwara'ae", ["kwg"] = "Sara Kaba Deme", ["kwh"] = "Kowiai", ["kwi"] = "Awa-Cuaiquer", ["kwj"] = "Kwanga", ["kwk"] = "Kwak'wala", ["kwl"] = "Kofyar", ["kwm"] = "Kwambi", ["kwn"] = "Kwangali", ["kwo"] = "Kwomtari", ["kwp"] = "Kodia", ["kwq"] = "Kwak", ["kwr"] = "Kwer", ["kws"] = "Kwese", ["kwt"] = "Kwesten", ["kwu"] = "Kwakum", ["kwv"] = "Sara Kaba Náà", ["kww"] = "Kwinti", ["kwx"] = "Khirwar", ["kwz"] = "Kwadi", ["kxa"] = "Kairiru", ["kxb"] = "Krobu", ["kxc"] = "Konso", ["kxd"] = "Brunei Malay", ["kxe"] = "Kakihum", ["kxf"] = "Manumanaw Karen", ["kxh"] = "Karo", ["kxi"] = "Keningau Murut", ["kxj"] = "Kulfa", ["kxk"] = "Zayein Karen", ["kxm"] = "Northern Khmer", ["kxn"] = "Kanowit", ["kxo"] = "Kanoé", ["kxp"] = "Wadiyara Koli", ["kxq"] = "Smärky Kanum", ["kxr"] = "Manus Koro", ["kxs"] = "Kangjia", ["kxt"] = "Koiwat", ["kxu"] = "Kui (India)", ["kxv"] = "Kuvi", ["kxw"] = "Konai", ["kxx"] = "Likuba", ["kxy"] = "Kayong", ["kxz"] = "Kerewo", ["ky"] = "Kyrgyz", ["kya"] = "Kwaya", ["kyb"] = "Butbut Kalinga", ["kyc"] = "Kyaka", ["kyd"] = "Karey", ["kye"] = "Krache", ["kyf"] = "Kouya", ["kyg"] = "Keyagana", ["kyh"] = "Karok", ["kyi"] = "Kiput", ["kyj"] = "Karao", ["kyk"] = "Kamayo", ["kyl"] = "Kalapuya", ["kym"] = "Kpatili", ["kyn"] = "Karolanos", ["kyo"] = "Kelon", ["kyp"] = "Kang", ["kyq"] = "Kenga", ["kyr"] = "Kuruáya", ["kys"] = "Baram Kayan", ["kyt"] = "Kayagar", ["kyu"] = "Western Kayah", ["kyv"] = "Kayort", ["kyw"] = "Kudmali", ["kyx"] = "Rapoisi", ["kyy"] = "Kambaira", ["kyz"] = "Kayabí", ["kza"] = "Western Karaboro", ["kzb"] = "Kaibobo", ["kzc"] = "Bondoukou Kulango", ["kzd"] = "Kadai", ["kzf"] = "Da'a Kaili", ["kzg"] = "Kikai", ["kzh"] = "Dongolawi", ["kzi"] = "Kelabit", ["kzj"] = "Coastal Kadazan", ["kzk"] = "Kazukuru", ["kzl"] = "Kayeli", ["kzm"] = "Kais", ["kzn"] = "Kokola", ["kzo"] = "Kaningi", ["kzp"] = "Kaidipang", ["kzq"] = "Kaike", ["kzr"] = "Karang", ["kzs"] = "Sugut Dusun", ["kzu"] = "Kayupulau", ["kzv"] = "Komyandaret", ["kzw"] = "Kariri", ["kzx"] = "Kamarian", ["kzy"] = "Kango-Sua", ["kzz"] = "Kalabra", ["la"] = "Latin", ["laa"] = "Lapuyan Subanun", ["lab"] = "Linear A", ["lac"] = "Lacandon", ["lad"] = "Ladino", ["lae"] = "Pattani", ["laf"] = "Lafofa", ["lag"] = "Langi", ["lah"] = "Lahnda", ["lai"] = "Lambya", ["laj"] = "Lango (Uganda)", ["lak"] = "Laka", ["lam"] = "Lamba", ["lan"] = "Laru", ["lap"] = "Kabba-Laka", ["laq"] = "Qabiao", ["lar"] = "Larteh", ["las"] = "Gur Lama", ["lau"] = "Laba", ["law"] = "Lauje", ["lax"] = "Tiwa", ["lay"] = "Lama Bai", ["laz"] = "Aribwatsa", ["lb"] = "Luxembourgish", ["lbb"] = "Label", ["lbc"] = "Lakkia", ["lbe"] = "Lak", ["lbf"] = "Tinani", ["lbg"] = "Laopang", ["lbi"] = "La'bi", ["lbj"] = "Ladakhi", ["lbk"] = "Central Bontoc", ["lbl"] = "Libon Bikol", ["lbm"] = "Lodhi", ["lbn"] = "Lamet", ["lbo"] = "Laven", ["lbq"] = "Wampar", ["lbr"] = "Northern Lorung", ["lbs"] = "Libyan Sign Language", ["lbt"] = "Lachi", ["lbu"] = "Labu", ["lbv"] = "Lavatbura-Lamusong", ["lbw"] = "Tolaki", ["lbx"] = "Lawangan", ["lby"] = "Lamu-Lamu", ["lbz"] = "Lardil", ["lcc"] = "Legenyem", ["lcd"] = "Lola", ["lce"] = "Loncong", ["lcf"] = "Lubu", ["lch"] = "Luchazi", ["lcl"] = "Lisela", ["lcm"] = "Tungag", ["lcp"] = "Western Lawa", ["lcq"] = "Luhu", ["lcs"] = "Lisabata-Nuniali", ["lda"] = "Kla", ["ldb"] = "Idun", ["ldd"] = "Luri (Nigeria)", ["ldg"] = "Lenyima", ["ldh"] = "Lamja-Dengsa-Tola", ["ldj"] = "Lemoro", ["ldk"] = "Leelau", ["ldl"] = "Kaan", ["ldm"] = "Landoma", ["ldn"] = "Láadan", ["ldo"] = "Loo", ["ldp"] = "Tso", ["ldq"] = "Lufu", ["lea"] = "Lega-Shabunda", ["leb"] = "Lala-Bisa", ["lec"] = "Leco", ["led"] = "Lendu", ["lee"] = "Lyélé", ["lef"] = "Lelemi", ["leh"] = "Lenje", ["lei"] = "Lemio", ["lej"] = "Lengola", ["lek"] = "Leipon", ["lel"] = "Lele (Congo)", ["lem"] = "Nomaande", ["len"] = "Honduran Lenca", ["leo"] = "Mengisa", ["lep"] = "Lepcha", ["leq"] = "Lembena", ["ler"] = "Lenkau", ["les"] = "Lese", ["let"] = "Lesing-Gelimi", ["leu"] = "Kara (New Guinea)", ["lev"] = "Lamma", ["lew"] = "Ledo Kaili", ["lex"] = "Luang", ["ley"] = "Lemolang", ["lez"] = "Lezgi", ["lfa"] = "Lefa", ["lfn"] = "Lingua Franca Nova", ["lg"] = "Luganda", ["lga"] = "Lungga", ["lgb"] = "Laghu", ["lgg"] = "Lugbara", ["lgh"] = "Laghuu", ["lgi"] = "Lengilu", ["lgk"] = "Neverver", ["lgl"] = "Wala", ["lgm"] = "Lega-Mwenga", ["lgn"] = "Opuuo", ["lgq"] = "Logba", ["lgr"] = "Lengo", ["lgs"] = "Guinea-Bissau Sign Language", ["lgt"] = "Pahi", ["lgu"] = "Longgu", ["lgz"] = "Ligenza", ["lha"] = "Laha (Vietnam)", ["lhh"] = "Laha (Indonesia)", ["lhi"] = "Lahu Shi", ["lhl"] = "Lahul Lohar", ["lhn"] = "Lahanan", ["lhp"] = "Lhokpu", ["lhs"] = "Mlahsö", ["lht"] = "Lo-Toga", ["lhu"] = "Lahu", ["li"] = "Limburgish", ["lia"] = "West-Central Limba", ["lib"] = "Likum", ["lic"] = "Hlai", ["lid"] = "Nyindrou", ["lie"] = "Likila", ["lif"] = "Limbu", ["lig"] = "Ligbi", ["lih"] = "Lihir", ["lii"] = "Lingkhim", ["lij"] = "Ligurian", ["lik"] = "Lika", ["lil"] = "Lillooet", ["lio"] = "Liki", ["lip"] = "Sekpele", ["liq"] = "Libido", ["lir"] = "Liberian Kreyol", ["lis"] = "Lisu", ["liu"] = "Logorik", ["liv"] = "Livonian", ["liw"] = "Col", ["lix"] = "Liabuku", ["liy"] = "Banda-Bambari", ["liz"] = "Libinza", ["lja"] = "Golpa", ["lje"] = "Rampi", ["lji"] = "Laiyolo", ["ljl"] = "Li'o", ["ljp"] = "Lampung Api", ["ljw"] = "Yirandali", ["ljx"] = "Yuru", ["lka"] = "Lakalei", ["lkb"] = "Kabras", ["lkc"] = "Kucong", ["lkd"] = "Lakondê", ["lke"] = "Kenyi", ["lkh"] = "Lakha", ["lki"] = "Laki", ["lkj"] = "Remun", ["lkl"] = "Laeko-Libuat", ["lkm"] = "Kalaamaya", ["lkn"] = "Lakon", ["lko"] = "Khayo", ["lkr"] = "Päri", ["lks"] = "Kisa", ["lkt"] = "Lakota", ["lku"] = "Kungkari", ["lky"] = "Lokoya", ["lla"] = "Lala-Roba", ["llb"] = "Lolo", ["llc"] = "Lele (Guinea)", ["lld"] = "Ladin", ["lle"] = "Lele (New Guinea)", ["llf"] = "Hermit", ["llg"] = "Lole", ["llh"] = "Lamu", ["lli"] = "Teke-Laali", ["llj"] = "Ladji-Ladji", ["llk"] = "Lelak", ["lll"] = "Lilau", ["llm"] = "Lasalimu", ["lln"] = "Lele (Chad)", ["llp"] = "North Efate", ["llq"] = "Lolak", ["lls"] = "Lithuanian Sign Language", ["llu"] = "Lau", ["llx"] = "Lauan", ["lma"] = "East Limba", ["lmb"] = "Merei", ["lmc"] = "Limilngan", ["lmd"] = "Lumun", ["lme"] = "Pévé", ["lmf"] = "South Lembata", ["lmg"] = "Lamogai", ["lmh"] = "Lambichhong", ["lmi"] = "Lombi", ["lmj"] = "West Lembata", ["lmk"] = "Lamkang", ["lml"] = "Raga", ["lmn"] = "Lambadi", ["lmo"] = "Lombard", ["lmp"] = "Limbum", ["lmq"] = "Lamatuka", ["lmr"] = "Lamalera", ["lmu"] = "Lamenu", ["lmv"] = "Lomaiviti", ["lmw"] = "Lake Miwok", ["lmx"] = "Laimbue", ["lmy"] = "Laboya", ["ln"] = "Lingala", ["lna"] = "Langbashe", ["lnb"] = "Mbalanhu", ["lnd"] = "Lun Bawang", ["lnh"] = "Lanoh", ["lni"] = "Daantanai'", ["lnj"] = "Linngithigh", ["lnl"] = "South Central Banda", ["lnm"] = "Pondi", ["lnn"] = "Lorediakarkar", ["lno"] = "Lango (Sudan)", ["lns"] = "Lamnso'", ["lnu"] = "Longuda", ["lnw"] = "Lanima", ["lo"] = "Lao", ["loa"] = "Loloda", ["lob"] = "Lobi", ["loc"] = "Inonhan", ["lod"] = "Berawan", ["loe"] = "Saluan", ["lof"] = "Logol", ["log"] = "Logo", ["loh"] = "Narim", ["loi"] = "Lomakka", ["loj"] = "Lou", ["lok"] = "Loko", ["lol"] = "Mongo", ["lom"] = "Loma", ["lon"] = "Malawi Lomwe", ["loo"] = "Lombo", ["lop"] = "Lopa", ["loq"] = "Lobala", ["lor"] = "Téén", ["los"] = "Loniu", ["lot"] = "Lotuko", ["lou"] = "Louisiana Creole", ["lov"] = "Lopi", ["low"] = "Tampias Lobu", ["lox"] = "Loun", ["loz"] = "Lozi", ["lpa"] = "Lelepa", ["lpe"] = "Lepki", ["lpn"] = "Long Phuri Naga", ["lpo"] = "Lipo", ["lpx"] = "Lopit", ["lra"] = "Rara Bakati'", ["lrc"] = "Northern Luri", ["lre"] = "Laurentian", ["lrg"] = "Laragia", ["lri"] = "Marachi", ["lrk"] = "Loarki", ["lrl"] = "Larestani", ["lrm"] = "Marama", ["lrn"] = "Lorang", ["lro"] = "Laro", ["lrr"] = "Southern Lorung", ["lrt"] = "Larantuka Malay", ["lrv"] = "Larëvat", ["lrz"] = "Lemerig", ["lsa"] = "Lasgerdi", ["lsb"] = "Burundian Sign Language", ["lsd"] = "Lishana Deni", ["lse"] = "Lusengo", ["lsh"] = "Lish", ["lsi"] = "Lashi", ["lsl"] = "Latvian Sign Language", ["lsm"] = "Saamia", ["lsn"] = "Tibetan Sign Language", ["lso"] = "Laos Sign Language", ["lsp"] = "Panamanian Sign Language", ["lsr"] = "Aruop", ["lss"] = "Lasi", ["lst"] = "Trinidad and Tobago Sign Language", ["lsv"] = "Sivia Sign Language", ["lsw"] = "Seychelles Sign Language", ["lsy"] = "Mauritian Sign Language", ["lt"] = "Lithuanian", ["ltc"] = "Middle Chinese", ["ltg"] = "Latgalian", ["lti"] = "Leti", ["ltn"] = "Latundê", ["lto"] = "Olutsotso", ["lts"] = "Lutachoni", ["ltu"] = "Latu", ["lu"] = "Luba-Katanga", ["lua"] = "Luba-Kasai", ["luc"] = "Aringa", ["lud"] = "Ludian", ["lue"] = "Luvale", ["luf"] = "Laua", ["luh"] = "Leizhou Min", ["lui"] = "Luiseño", ["luj"] = "Luna", ["luk"] = "Lunanakha", ["lul"] = "Olu'bo", ["lum"] = "Luimbi", ["lun"] = "Lunda", ["luo"] = "Luo", ["lup"] = "Lumbu", ["luq"] = "Lucumí", ["lur"] = "Laura", ["lus"] = "Mizo", ["lut"] = "Lushootseed", ["luu"] = "Lumba-Yakkha", ["luv"] = "Luwati", ["luy"] = "Luhya", ["luz"] = "Southern Luri", ["lv"] = "Latvian", ["lva"] = "Maku'a", ["lvi"] = "Lawi", ["lvk"] = "Lavukaleve", ["lvl"] = "Lwel", ["lvu"] = "Levuka", ["lwa"] = "Lwalu", ["lwe"] = "Lewo Eleng", ["lwg"] = "Wanga", ["lwh"] = "White Lachi", ["lwl"] = "Eastern Lawa", ["lwm"] = "Laomian", ["lwo"] = "Luwo", ["lws"] = "Malawian Sign Language", ["lwt"] = "Lewotobi", ["lwu"] = "Lawu", ["lww"] = "Lewo", ["lya"] = "Layakha", ["lyg"] = "Lyngngam", ["lyn"] = "Luyana", ["lzh"] = "Classical Chinese", ["lzl"] = "Litzlitz", ["lzn"] = "Leinong Naga", ["lzz"] = "Laz", ["maa"] = "San Jerónimo Tecóatl Mazatec", ["mab"] = "Yutanduchi Mixtec", ["mad"] = "Madurese", ["mae"] = "Bo-Rukul", ["maf"] = "Mafa", ["mag"] = "Magahi", ["mai"] = "Maithili", ["maj"] = "Jalapa de Díaz Mazatec", ["mak"] = "Makasar", ["mam"] = "Mam", ["man"] = "Mandingo", ["map-ata-pro"] = "Proto-Atayalic", ["map-bms"] = "Banyumasan", ["map-pro"] = "Proto-Austronesian", ["maq"] = "Chiquihuitlán Mazatec", ["mas"] = "Maasai", ["mat"] = "Matlatzinca", ["mau"] = "Huautla Mazatec", ["mav"] = "Sateré-Mawé", ["maw"] = "Mampruli", ["max"] = "North Moluccan Malay", ["maz"] = "Central Mazahua", ["mba"] = "Higaonon", ["mbb"] = "Western Bukidnon Manobo", ["mbc"] = "Macushi", ["mbd"] = "Dibabawon Manobo", ["mbe"] = "Molale", ["mbf"] = "Baba Malay", ["mbh"] = "Mangseng", ["mbi"] = "Ilianen Manobo", ["mbj"] = "Nadëb", ["mbk"] = "Malol", ["mbl"] = "Maxakalí", ["mbm"] = "Ombamba", ["mbn"] = "Macaguán", ["mbo"] = "Mbo (Cameroon)", ["mbp"] = "Wiwa", ["mbq"] = "Maisin", ["mbr"] = "Nukak Makú", ["mbs"] = "Sarangani Manobo", ["mbt"] = "Matigsalug Manobo", ["mbu"] = "Mbula-Bwazza", ["mbv"] = "Mbulungish", ["mbw"] = "Maring", ["mbx"] = "Mari (Sepik)", ["mby"] = "Memoni", ["mbz"] = "Amoltepec Mixtec", ["mca"] = "Maca", ["mcb"] = "Machiguenga", ["mcc"] = "Bitur", ["mcd"] = "Sharanahua", ["mce"] = "Itundujia Mixtec", ["mcf"] = "Matsés", ["mcg"] = "Mapoyo", ["mch"] = "Ye'kwana", ["mci"] = "Mese", ["mcj"] = "Mvanip", ["mck"] = "Mbunda", ["mcl"] = "Macaguaje", ["mcm"] = "Kristang", ["mcn"] = "Masana", ["mco"] = "Coatlán Mixe", ["mcp"] = "Makaa", ["mcq"] = "Ese", ["mcr"] = "Menya", ["mcs"] = "Mambai", ["mcu"] = "Cameroon Mambila", ["mcw"] = "Mawa", ["mcx"] = "Mpiemo", ["mcy"] = "South Watut", ["mcz"] = "Mawan", ["mda"] = "Mada (Nigeria)", ["mdb"] = "Morigi", ["mdc"] = "Male", ["mdd"] = "Mbum", ["mde"] = "Bura Mabang", ["mdf"] = "Moksha", ["mdg"] = "Massalat", ["mdh"] = "Maguindanao", ["mdi"] = "Mamvu", ["mdj"] = "Mangbetu", ["mdk"] = "Mangbutu", ["mdl"] = "Maltese Sign Language", ["mdm"] = "Mayogo", ["mdn"] = "Mbati", ["mdp"] = "Mbala", ["mdq"] = "Mbole", ["mdr"] = "Mandar", ["mds"] = "Maria", ["mdt"] = "Mbere", ["mdu"] = "Mboko", ["mdv"] = "Santa Lucía Monteverde Mixtec", ["mdw"] = "Mbosi", ["mdx"] = "Dizin", ["mdy"] = "Maale", ["mdz"] = "Suruí Do Pará", ["mea"] = "Menka", ["meb"] = "Ikobi-Mena", ["mec"] = "Mara", ["med"] = "Melpa", ["mee"] = "Mengen", ["mef"] = "Megam", ["meh"] = "Southwestern Tlaxiaco Mixtec", ["mei"] = "Midob", ["mej"] = "Meyah", ["mek"] = "Mekeo", ["mel"] = "Central Melanau", ["mem"] = "Mangala", ["men"] = "Mende (Sierra Leone)", ["meo"] = "Kedah Malay", ["mep"] = "Miriwoong", ["meq"] = "Merey", ["mer"] = "Meru", ["mes"] = "Masmaje", ["met"] = "Mato", ["meu"] = "Motu", ["mev"] = "Mano", ["mew"] = "Maaka", ["mey"] = "Hassaniya Arabic", ["mez"] = "Menominee", ["mfa"] = "Pattani Malay", ["mfb"] = "Bangka", ["mfc"] = "Mba", ["mfd"] = "Mendankwe-Nkwen", ["mfe"] = "Mauritian Creole", ["mff"] = "Naki", ["mfg"] = "Mixifore", ["mfh"] = "Matal", ["mfi"] = "Wandala", ["mfj"] = "Mefele", ["mfk"] = "North Mofu", ["mfl"] = "Putai", ["mfm"] = "Marghi South", ["mfn"] = "Cross River Mbembe", ["mfo"] = "Mbe", ["mfp"] = "Makassar Malay", ["mfq"] = "Moba", ["mfr"] = "Marrithiyel", ["mfs"] = "Mexican Sign Language", ["mft"] = "Mokerang", ["mfu"] = "Mbwela", ["mfv"] = "Mandjak", ["mfw"] = "Mulaha", ["mfx"] = "Melo", ["mfy"] = "Mayo", ["mfz"] = "Mabaan", ["mg"] = "Malagasy", ["mga"] = "Middle Irish", ["mgb"] = "Mararit", ["mgc"] = "Morokodo", ["mgd"] = "Moru", ["mge"] = "Mango", ["mgf"] = "Maklew", ["mgg"] = "Mpongmpong", ["mgh"] = "Makhuwa-Meetto", ["mgi"] = "Jili", ["mgj"] = "Abureni", ["mgk"] = "Mawes", ["mgl"] = "Maleu-Kilenge", ["mgm"] = "Mambae", ["mgn"] = "Mbangi", ["mgo"] = "Meta'", ["mgp"] = "Eastern Magar", ["mgq"] = "Malila", ["mgr"] = "Mambwe-Lungu", ["mgs"] = "Manda (Tanzania)", ["mgt"] = "Mwakai", ["mgu"] = "Mailu", ["mgv"] = "Matengo", ["mgw"] = "Matumbi", ["mgy"] = "Mbunga", ["mgz"] = "Mbugwe", ["mh"] = "Marshallese", ["mha"] = "Manda (India)", ["mhb"] = "Mahongwe", ["mhc"] = "Mocho", ["mhd"] = "Mbugu", ["mhe"] = "Besisi", ["mhf"] = "Mamaa", ["mhg"] = "Marrgu", ["mhi"] = "Ma'di", ["mhj"] = "Mogholi", ["mhk"] = "Mungaka", ["mhl"] = "Mauwake", ["mhm"] = "Makhuwa-Moniga", ["mhn"] = "Mòcheno", ["mho"] = "Mashi", ["mhp"] = "Balinese Malay", ["mhq"] = "Mandan", ["mhr"] = "Eastern Mari", ["mhs"] = "Buru (Indonesia)", ["mht"] = "Mandahuaca", ["mhu"] = "Taraon", ["mhw"] = "Mbukushu", ["mhx"] = "Lhao Vo", ["mhy"] = "Ma'anyan", ["mhz"] = "Mor (Austronesian)", ["mi"] = "Māori", ["mia"] = "Miami", ["mib"] = "Atatláhuca Mixtec", ["mic"] = "Mi'kmaq", ["mid"] = "Mandaic", ["mie"] = "Ocotepec Mixtec", ["mif"] = "Mofu-Gudur", ["mig"] = "San Miguel el Grande Mixtec", ["mih"] = "Chayuco Mixtec", ["mii"] = "Chigmecatitlán Mixtec", ["mij"] = "Mungbam", ["mik"] = "Mikasuki", ["mil"] = "Peñoles Mixtec", ["mim"] = "Alacatlatzala Mixtec", ["min"] = "Minangkabau", ["mio"] = "Pinotepa Nacional Mixtec", ["mip"] = "Apasco-Apoala Mixtec", ["miq"] = "Miskito", ["mir"] = "Isthmus Mixe", ["mis-hkl"] = "Kelantan Peranakan Hokkien", ["mis-idn"] = "Idiom Neutral", ["mis-isa"] = "Isaurian", ["mis-jie"] = "Jie", ["mis-jzh"] = "Jizhao", ["mis-kas"] = "Kassite", ["mis-mmd"] = "Mimi of Decorse", ["mis-mmn"] = "Mimi of Nachtigal", ["mis-phi"] = "Philistine", ["mis-rou"] = "Rouran", ["mis-tdl"] = "Turdulian", ["mis-tdt"] = "Turdetanian", ["mis-tnw"] = "Tangwang", ["mis-tuh"] = "Tuyuhun", ["mis-tuo"] = "Tuoba", ["mis-wuh"] = "Wuhuan", ["mis-xbi"] = "Xianbei", ["mis-xnu"] = "Xiongnu", ["mit"] = "Southern Puebla Mixtec", ["miu"] = "Cacaloxtepec Mixtec", ["miw"] = "Akoye", ["mix"] = "Mixtepec Mixtec", ["miy"] = "Ayutla Mixtec", ["miz"] = "Coatzospan Mixtec", ["mjb"] = "Makalero", ["mjc"] = "San Juan Colorado Mixtec", ["mjd"] = "Northwest Maidu", ["mje"] = "Muskum", ["mjg-mgl"] = "Mongghul", ["mjg-mgr"] = "Mangghuer", ["mji"] = "Kim Mun", ["mjj"] = "Mawak", ["mjk"] = "Matukar", ["mjl"] = "Mandeali", ["mjm"] = "Medebur", ["mjn"] = "Mebu", ["mjo"] = "Malankuravan", ["mjp"] = "Malapandaram", ["mjq"] = "Malaryan", ["mjr"] = "Malavedan", ["mjs"] = "Miship", ["mjt"] = "Sawriya Paharia", ["mju"] = "Manna-Dora", ["mjv"] = "Mannan", ["mjw"] = "Karbi", ["mjx"] = "Mahali", ["mjy"] = "Mahican", ["mjz"] = "Majhi", ["mk"] = "Macedonian", ["mka"] = "Mbre", ["mkb"] = "Mal Paharia", ["mkc"] = "Siliput", ["mke"] = "Mawchi", ["mkf"] = "Miya", ["mkg"] = "Mak (China)", ["mkh-asl-pro"] = "Proto-Aslian", ["mkh-ban-pro"] = "Proto-Bahnaric", ["mkh-kat-pro"] = "Proto-Katuic", ["mkh-khm-pro"] = "Proto-Khmuic", ["mkh-kmr-pro"] = "Proto-Khmeric", ["mkh-mmn"] = "Middle Mon", ["mkh-mnc-pro"] = "Proto-Monic", ["mkh-mvi"] = "Middle Vietnamese", ["mkh-pal-pro"] = "Proto-Palaungic", ["mkh-pea-pro"] = "Proto-Pearic", ["mkh-pkn-pro"] = "Proto-Pakanic", ["mkh-pro"] = "Proto-Mon-Khmer", ["mkh-vie-pro"] = "Proto-Vietic", ["mki"] = "Dhatki", ["mkj"] = "Mokilese", ["mkk"] = "Byep", ["mkl"] = "Mokole", ["mkm"] = "Moklen", ["mkn"] = "Kupang Malay", ["mko"] = "Mingang Doso", ["mkp"] = "Moikodi", ["mkq"] = "Bay Miwok", ["mkr"] = "Malas", ["mks"] = "Silacayoapan Mixtec", ["mkt"] = "Vamale", ["mku"] = "Konyanka Maninka", ["mkv"] = "Mav̋ea", ["mkx"] = "Cinamiguin Manobo", ["mky"] = "Taba", ["mkz"] = "Makasae", ["ml"] = "Malayalam", ["mla"] = "Tamambo", ["mlb"] = "Mbule", ["mlc"] = "Caolan", ["mle"] = "Manambu", ["mlf"] = "Mal", ["mlh"] = "Mape", ["mli"] = "Malimpung", ["mlj"] = "Miltu", ["mlk"] = "Ilwana", ["mll"] = "Malua Bay", ["mlm"] = "Mulam", ["mln"] = "Malango", ["mlo"] = "Mlomp", ["mlp"] = "Bargam", ["mlq"] = "Western Maninkakan", ["mlr"] = "Vame", ["mls"] = "Masalit", ["mlu"] = "To'abaita", ["mlv"] = "Mwotlap", ["mlw"] = "Moloko", ["mlx"] = "Malfaxal", ["mlz"] = "Malaynon", ["mma"] = "Mama", ["mmb"] = "Momina", ["mmc"] = "Michoacán Mazahua", ["mmd"] = "Maonan", ["mme"] = "Tirax", ["mmf"] = "Mundat", ["mmg"] = "North Ambrym", ["mmh"] = "Mehináku", ["mmi"] = "Hember Avu", ["mmj"] = "Majhwar", ["mmk"] = "Mukha-Dora", ["mml"] = "Man Met", ["mmm"] = "Maii", ["mmn"] = "Mamanwa", ["mmo"] = "Mangga Buang", ["mmp"] = "Musan", ["mmq"] = "Aisi", ["mmr"] = "Western Xiangxi Miao", ["mmt"] = "Malalamai", ["mmu"] = "Mmaala", ["mmv"] = "Miriti", ["mmw"] = "Emae", ["mmx"] = "Madak", ["mmy"] = "Migaama", ["mmz"] = "Mabaale", ["mn"] = "Mongolian", ["mna"] = "Mbula", ["mnb"] = "Muna", ["mnc"] = "Manchu", ["mnd"] = "Mondé", ["mne"] = "Naba", ["mnf"] = "Mundani", ["mng"] = "Eastern Mnong", ["mnh"] = "Mono (Congo)", ["mni"] = "Manipuri", ["mnj"] = "Munji", ["mnk"] = "Mandinka", ["mnl"] = "Tiale", ["mnm"] = "Mapena", ["mnn"] = "Southern Mnong", ["mnp"] = "Northern Min", ["mnq"] = "Minriq", ["mnr"] = "Mono (California)", ["mns-cen"] = "Central Mansi", ["mns-nor"] = "Northern Mansi", ["mns-pro"] = "Proto-Mansi", ["mns-sou"] = "Southern Mansi", ["mnt"] = "Maykulan", ["mnu"] = "Mer", ["mnv"] = "Rennellese", ["mnw"] = "Mon", ["mnw-tha"] = "Thai Mon", ["mnx"] = "Sougb", ["mny"] = "Manyawa", ["mnz"] = "Moni", ["moa"] = "Mwan", ["moc"] = "Mocoví", ["mod"] = "Mobilian", ["moe"] = "Montagnais", ["mog"] = "Mongondow", ["moh"] = "Mohawk", ["moi"] = "Mboi", ["moj"] = "Monzombo", ["mok"] = "Morori", ["mom"] = "Monimbo", ["moo"] = "Monom", ["mop"] = "Mopan Maya", ["moq"] = "Mor (Papuan)", ["mor"] = "Moro", ["mos"] = "Moore", ["mot"] = "Barí", ["mou"] = "Mogum", ["mov"] = "Mojave", ["mow"] = "Moi (Congo)", ["mox"] = "Molima", ["moy"] = "Shekkacho", ["moz"] = "Mukulu", ["mpa"] = "Mpoto", ["mpb"] = "Mullukmulluk", ["mpc"] = "Mangarayi", ["mpd"] = "Machinere", ["mpe"] = "Majang", ["mpg"] = "Marba", ["mph"] = "Maung", ["mpi"] = "Mpade", ["mpj"] = "Martu Wangka", ["mpk"] = "Mbara (Chad)", ["mpl"] = "Middle Watut", ["mpm"] = "Yosondúa Mixtec", ["mpn"] = "Mindiri", ["mpo"] = "Miu", ["mpp"] = "Migabac", ["mpq"] = "Matís", ["mpr"] = "Vangunu", ["mps"] = "Dadibi", ["mpt"] = "Mian", ["mpu"] = "Makuráp", ["mpv"] = "Mungkip", ["mpw"] = "Mapidian", ["mpx"] = "Misima-Paneati", ["mpy"] = "Mapia", ["mpz"] = "Mpi", ["mqa"] = "Maba", ["mqb"] = "Mbuko", ["mqc"] = "Mangole", ["mqe"] = "Matepi", ["mqf"] = "Momuna", ["mqg"] = "Kota Bangun Kutai Malay", ["mqh"] = "Tlazoyaltepec Mixtec", ["mqi"] = "Mariri", ["mqj"] = "Mamasa", ["mqk"] = "Rajah Kabunsuwan Manobo", ["mql"] = "Mbelime", ["mqm"] = "South Marquesan", ["mqn"] = "Moronene", ["mqo"] = "Modole", ["mqp"] = "Manipa", ["mqq"] = "Minokok", ["mqr"] = "Mander", ["mqs"] = "West Makian", ["mqt"] = "Mok", ["mqu"] = "Mandari", ["mqv"] = "Mosimo", ["mqw"] = "Murupi", ["mqx"] = "Mamuju", ["mqy"] = "Manggarai", ["mqz"] = "Malasanga", ["mr"] = "Marathi", ["mra"] = "Mlabri", ["mrb"] = "Sungwadia", ["mrc"] = "Maricopa", ["mrd"] = "Western Magar", ["mre"] = "Martha's Vineyard Sign Language", ["mrf"] = "Elseng", ["mrg"] = "Mising", ["mrh"] = "Mara Chin", ["mrj"] = "Western Mari", ["mrk"] = "Hmwaveke", ["mrl"] = "Mortlockese", ["mrm"] = "Mwerlap", ["mrn"] = "Cheke Holo", ["mro"] = "Mru", ["mrp"] = "Morouas", ["mrq"] = "North Marquesan", ["mrr"] = "Hill Maria", ["mrs"] = "Maragus", ["mrt"] = "Margi", ["mru"] = "Mono (Cameroon)", ["mrv"] = "Mangarevan", ["mrw"] = "Maranao", ["mrx"] = "Dineor", ["mry"] = "Karaga Mandaya", ["mrz"] = "Marind", ["ms"] = "Malay", ["msb"] = "Masbatenyo", ["msc"] = "Sankaran Maninka", ["msd"] = "Yucatec Maya Sign Language", ["mse"] = "Musey", ["msf"] = "Mekwei", ["msg"] = "Moraid", ["msi"] = "Sabah Malay", ["msj"] = "Ma", ["msk"] = "Mansaka", ["msl"] = "Molof", ["msm"] = "Agusan Manobo", ["msn"] = "Vurës", ["mso"] = "Mombum", ["msp"] = "Maritsauá", ["msq"] = "Caac", ["msr"] = "Mongolian Sign Language", ["mss"] = "West Masela", ["msu"] = "Musom", ["msv"] = "Maslam", ["msw"] = "Mansoanka", ["msx"] = "Moresada", ["msy"] = "Aruamu", ["msz"] = "Momare", ["mt"] = "Maltese", ["mta"] = "Cotabato Manobo", ["mtb"] = "Anyin Morofo", ["mtc"] = "Munit", ["mtd"] = "Mualang", ["mte"] = "Alu", ["mtf"] = "Murik (New Guinea)", ["mtg"] = "Una", ["mth"] = "Munggui", ["mti"] = "Maiwa (New Guinea)", ["mtj"] = "Moskona", ["mtk"] = "Mbe'", ["mtl"] = "Montol", ["mtm"] = "Mator", ["mtn"] = "Matagalpa", ["mto"] = "Totontepec Mixe", ["mtp"] = "Wichí Lhamtés Nocten", ["mtq"] = "Muong", ["mtr"] = "Mewari", ["mts"] = "Yora", ["mtt"] = "Mota", ["mtu"] = "Tututepec Mixtec", ["mtv"] = "Asaro'o", ["mtw"] = "Magahat", ["mtx"] = "Tidaá Mixtec", ["mty"] = "Nabi", ["mua"] = "Mundang", ["mub"] = "Mubi", ["muc"] = "Mbu'", ["mud"] = "Mednyj Aleut", ["mue"] = "Media Lengua", ["mug"] = "Musgu", ["muh"] = "Mündü", ["mui"] = "Musi", ["muj"] = "Mabire", ["mul"] = "Translingual", ["mum"] = "Maiwala", ["mun-pro"] = "Proto-Munda", ["muo"] = "Nyong", ["mup"] = "Malvi", ["muq"] = "Eastern Xiangxi Miao", ["mur"] = "Murle", ["mus"] = "Creek", ["mut"] = "Western Muria", ["muu"] = "Yaaku", ["muv"] = "Muthuvan", ["mux"] = "Bo-Ung", ["muy"] = "Muyang", ["muz"] = "Mursi", ["mva"] = "Manam", ["mvb"] = "Mattole", ["mvd"] = "Mamboru", ["mvg"] = "Yucuañe Mixtec", ["mvh"] = "Mire", ["mvi"] = "Miyako", ["mvk"] = "Mekmek", ["mvl"] = "Mbara (Australia)", ["mvm"] = "Muya", ["mvn"] = "Minaveha", ["mvo"] = "Marovo", ["mvp"] = "Duri", ["mvq"] = "Moere", ["mvr"] = "Marau", ["mvs"] = "Massep", ["mvt"] = "Mpotovoro", ["mvu"] = "Marfa", ["mvv"] = "Tagal Murut", ["mvw"] = "Machinga", ["mvx"] = "Meoswar", ["mvy"] = "Indus Kohistani", ["mvz"] = "Mesqan", ["mwa"] = "Mwatebu", ["mwb"] = "Juwal", ["mwc"] = "Are", ["mwe"] = "Mwera", ["mwf"] = "Murrinh-Patha", ["mwg"] = "Aiklep", ["mwh"] = "Mouk-Aria", ["mwi"] = "Labo", ["mwk"] = "Kita Maninkakan", ["mwl"] = "Mirandese", ["mwm"] = "Sar", ["mwn"] = "Nyamwanga", ["mwo"] = "Sungwadaga", ["mwp"] = "Kala Lagaw Ya", ["mwq"] = "Mün Chin", ["mwr"] = "Marwari", ["mws"] = "Mwimbi-Muthambi", ["mwt"] = "Moken", ["mwu"] = "Mittu", ["mwv"] = "Mentawai", ["mww"] = "White Hmong", ["mwz"] = "Moingi", ["mxa"] = "Northwest Oaxaca Mixtec", ["mxb"] = "Tezoatlán Mixtec", ["mxd"] = "Modang", ["mxe"] = "Mele-Fila", ["mxf"] = "Malgbe", ["mxg"] = "Mbangala", ["mxh"] = "Mvuba", ["mxi"] = "Mozarabic", ["mxj"] = "Miju", ["mxk"] = "Monumbo", ["mxl"] = "Maxi Gbe", ["mxm"] = "Meramera", ["mxn"] = "Moi (Indonesia)", ["mxo"] = "Mbowe", ["mxp"] = "Tlahuitoltepec Mixe", ["mxq"] = "Juquila Mixe", ["mxr"] = "Murik (Malaysia)", ["mxs"] = "Huitepec Mixtec", ["mxt"] = "Jamiltepec Mixtec", ["mxu"] = "Mada (Cameroon)", ["mxv"] = "Metlatónoc Mixtec", ["mxw"] = "Namo", ["mxx"] = "Mahou", ["mxy"] = "Southeastern Nochixtlán Mixtec", ["mxz"] = "Central Masela", ["my"] = "Burmese", ["myb"] = "Mbay", ["myc"] = "Mayeka", ["mye"] = "Myene", ["myf"] = "Bambassi", ["myg"] = "Manta", ["myh"] = "Makah", ["myj"] = "Mangayat", ["myk"] = "Mamara", ["myl"] = "Moma", ["mym"] = "Me'en", ["myn-chl"] = "Ch'olti'", ["myn-pro"] = "Proto-Mayan", ["myo"] = "Anfillo", ["myp"] = "Pirahã", ["myr"] = "Muniche", ["mys"] = "Mesmes", ["myu"] = "Mundurukú", ["myv"] = "Erzya", ["myw"] = "Muyuw", ["myx"] = "Masaba", ["myy"] = "Macuna", ["myz"] = "Classical Mandaic", ["mza"] = "Santa María Zacatepec Mixtec", ["mzb"] = "Northern Saharan Berber", ["mzc"] = "Madagascar Sign Language", ["mzd"] = "Malimba", ["mze"] = "Morawa", ["mzg"] = "Monastic Sign Language", ["mzh"] = "Wichí Lhamtés Güisnay", ["mzi"] = "Ixcatlán Mazatec", ["mzj"] = "Manya", ["mzk"] = "Nigeria Mambila", ["mzl"] = "Mazatlán Mixe", ["mzm"] = "Mumuye", ["mzn"] = "Mazanderani", ["mzo"] = "Matipuhy", ["mzp"] = "Movima", ["mzq"] = "Mori Atas", ["mzr"] = "Marúbo", ["mzs"] = "Macanese", ["mzt"] = "Mintil", ["mzu"] = "Inapang", ["mzv"] = "Manza", ["mzw"] = "Deg", ["mzx"] = "Mawayana", ["mzy"] = "Mozambican Sign Language", ["mzz"] = "Maiadomu", ["na"] = "Nauruan", ["naa"] = "Namla", ["nab"] = "Nambikwara", ["nac"] = "Narak", ["nae"] = "Naka'ela", ["naf"] = "Nabak", ["nag"] = "Naga Pidgin", ["nah"] = "Nahuatl", ["nai-ala"] = "Alazapa", ["nai-bay"] = "Bayogoula", ["nai-cal"] = "Calusa", ["nai-chi"] = "Chiquimulilla", ["nai-chu-pro"] = "Proto-Chumash", ["nai-cig"] = "Ciguayo", ["nai-ckn-pro"] = "Proto-Chinookan", ["nai-guz"] = "Guazacapán", ["nai-hit"] = "Hitchiti", ["nai-ipa"] = "Ipai", ["nai-jtp"] = "Jutiapa", ["nai-jum"] = "Jumaytepeque", ["nai-kat"] = "Kathlamet", ["nai-klp-pro"] = "Proto-Kalapuyan", ["nai-knm"] = "Konomihu", ["nai-kum"] = "Kumeyaay", ["nai-mac"] = "Macoris", ["nai-mdu-pro"] = "Proto-Maidun", ["nai-miz-pro"] = "Proto-Mixe-Zoque", ["nai-mus-pro"] = "Proto-Muskogean", ["nai-nao"] = "Naolan", ["nai-nrs"] = "New River Shasta", ["nai-okw"] = "Okwanuchu", ["nai-per"] = "Pericú", ["nai-pic"] = "Picuris", ["nai-plp-pro"] = "Proto-Plateau Penutian", ["nai-pom-pro"] = "Proto-Pomo", ["nai-qng"] = "Quinigua", ["nai-sca-pro"] = "Proto-Siouan-Catawban", ["nai-sin"] = "Sinacantán", ["nai-sln"] = "Salvadoran Lenca", ["nai-spt"] = "Sahaptin", ["nai-tap"] = "Tapachultec", ["nai-taw"] = "Tawasa", ["nai-teq"] = "Tequistlatec", ["nai-tip"] = "Tipai", ["nai-tot-pro"] = "Proto-Totozoquean", ["nai-tsi-pro"] = "Proto-Tsimshianic", ["nai-utn-pro"] = "Proto-Utian", ["nai-wai"] = "Waikuri", ["nai-wji"] = "Western Jicaque", ["nai-yup"] = "Yupiltepeque", ["naj"] = "Nalu", ["nak"] = "Nakanai", ["nal"] = "Nalik", ["nam"] = "Ngan'gityemerri", ["nan"] = "Min Nan", ["nan-dat"] = "Datian Min", ["nan-hbl"] = "Hokkien", ["nan-hlh"] = "Hailufeng Min", ["nan-lnx"] = "Longyan Min", ["nan-tws"] = "Teochew", ["nan-zhe"] = "Zhenan Min", ["nan-zsh"] = "Sanxiang Min", ["nao"] = "Naaba", ["nap"] = "Neapolitan", ["naq"] = "Khoekhoe", ["nar"] = "Iguta", ["nas"] = "Nasioi", ["nat"] = "Hungworo", ["naw"] = "Nawuri", ["nax"] = "Nakwi", ["nay"] = "Ngarrindjeri", ["naz"] = "Coatepec Nahuatl", ["nb"] = "Norwegian Bokmål", ["nba"] = "Nyemba", ["nbb"] = "Ndoe", ["nbc"] = "Chang", ["nbd"] = "Ngbinda", ["nbe"] = "Konyak Naga", ["nbg"] = "Nagarchal", ["nbh"] = "Ngamo", ["nbi"] = "Mao Naga", ["nbj"] = "Ngarinman", ["nbk"] = "Nake", ["nbm"] = "Ngbaka Ma'bo", ["nbn"] = "Kuri", ["nbo"] = "Nkukoli", ["nbp"] = "Nnam", ["nbq"] = "Nggem", ["nbr"] = "Numana", ["nbs"] = "Namibian Sign Language", ["nbt"] = "Na", ["nbu"] = "Rongmei Naga", ["nbv"] = "Ngamambo", ["nbw"] = "Southern Ngbandi", ["nby"] = "Ningera", ["nca"] = "Iyo", ["ncb"] = "Central Nicobarese", ["ncc"] = "Ponam", ["ncd"] = "Nachering", ["nce"] = "Yale", ["ncf"] = "Notsi", ["ncg"] = "Nisga'a", ["nch"] = "Central Huasteca Nahuatl", ["nci"] = "Classical Nahuatl", ["ncj"] = "Northern Puebla Nahuatl", ["nck"] = "Nakara", ["ncl"] = "Michoacán Nahuatl", ["ncm"] = "Nambo", ["ncn"] = "Nauna", ["nco"] = "Sibe", ["ncr"] = "Ncane", ["ncs"] = "Nicaraguan Sign Language", ["nct"] = "Chothe Naga", ["ncu"] = "Chumburung", ["ncx"] = "Central Puebla Nahuatl", ["ncz"] = "Natchez", ["nd"] = "Northern Ndebele", ["nda"] = "Ndasa", ["ndb"] = "Kenswei Nsei", ["ndc"] = "Ndau", ["ndd"] = "Nde-Nsele-Nta", ["ndf"] = "Nadruvian", ["ndg"] = "Ndengereko", ["ndh"] = "Ndali", ["ndi"] = "Chamba Leko", ["ndj"] = "Ndamba", ["ndk"] = "Ndaka", ["ndl"] = "Ndolo", ["ndm"] = "Ndam", ["ndn"] = "Ngundi", ["ndp"] = "Ndo", ["ndq"] = "Ndombe", ["ndr"] = "Ndoola", ["nds"] = "Low German", ["ndt"] = "Ndunga", ["ndu"] = "Dugun", ["ndv"] = "Ndut", ["ndw"] = "Ndobo", ["ndx"] = "Nduga", ["ndy"] = "Lutos", ["ndz"] = "Ndogo", ["ne"] = "Nepali", ["nea"] = "Eastern Ngad'a", ["neb"] = "Toura", ["nec"] = "Nedebang", ["ned"] = "Nde-Gbite", ["nee"] = "Kumak", ["nef"] = "Nefamese", ["neg"] = "Negidal", ["neh"] = "Nyenkha", ["nej"] = "Neko", ["nek"] = "Neku", ["nem"] = "Nemi", ["nen"] = "Nengone", ["neo"] = "Ná-Meo", ["neq"] = "North Central Mixe", ["ner"] = "Yahadian", ["nes"] = "Bhoti Kinnauri", ["net"] = "Nete", ["neu"] = "Neo", ["nev"] = "Nyaheun", ["new"] = "Newar", ["nex"] = "Neme", ["ney"] = "Neyo", ["nez"] = "Nez Perce", ["nfa"] = "Dhao", ["nfd"] = "Ahwai", ["nfl"] = "Äiwoo", ["nfr"] = "Nafaanra", ["nfu"] = "Mfumte", ["ng"] = "Ndonga", ["nga"] = "Ngbaka", ["ngb"] = "Northern Ngbandi", ["ngc"] = "Ngombe (Congo)", ["ngd"] = "Ngando (Central African Republic)", ["nge"] = "Ngemba", ["ngf-bin-pro"] = "Proto-Binanderean", ["ngf-pro"] = "Proto-Trans-New Guinea", ["ngg"] = "Ngbaka Manza", ["ngh"] = "Nǀuu", ["ngi"] = "Ngizim", ["ngj"] = "Ngie", ["ngk"] = "Ngalkbun", ["ngl"] = "Lomwe", ["ngm"] = "Ngatik Men's Creole", ["ngn"] = "Ngwo", ["ngo"] = "Ngoni", ["ngp"] = "Ngulu", ["ngq"] = "Ngoreme", ["ngr"] = "Nagu", ["ngs"] = "Gvoko", ["ngt"] = "Ngeq", ["ngu"] = "Guerrero Nahuatl", ["ngv"] = "Nagumi", ["ngw"] = "Ngwaba", ["ngx"] = "Nggwahyi", ["ngy"] = "Tibea", ["ngz"] = "Ngungwel", ["nha"] = "Nhanda", ["nhb"] = "Beng", ["nhc"] = "Tabasco Nahuatl", ["nhd"] = "Chiripá", ["nhe"] = "Eastern Huasteca Nahuatl", ["nhf"] = "Nhuwala", ["nhg"] = "Tetelcingo Nahuatl", ["nhh"] = "Nahari", ["nhi"] = "Zacatlán-Ahuacatlán-Tepetzintla Nahuatl", ["nhk"] = "Cosoleacaque Nahuatl", ["nhm"] = "Morelos Nahuatl", ["nhn"] = "Central Nahuatl", ["nho"] = "Takuu", ["nhp"] = "Pajapan Nahuatl", ["nhq"] = "Huaxcaleca Nahuatl", ["nhr"] = "Naro", ["nht"] = "Ometepec Nahuatl", ["nhu"] = "Noone", ["nhv"] = "Temascaltepec Nahuatl", ["nhw"] = "Western Huasteca Nahuatl", ["nhx"] = "Mecayapan Nahuatl", ["nhy"] = "Northern Oaxaca Nahuatl", ["nhz"] = "Santa María La Alta Nahuatl", ["nia"] = "Nias", ["nib"] = "Nakame", ["nic-bco-pro"] = "Proto-Benue-Congo", ["nic-bod-pro"] = "Proto-Bantoid", ["nic-eov-pro"] = "Proto-Eastern Oti-Volta", ["nic-gns-pro"] = "Proto-Gurunsi", ["nic-grf-pro"] = "Proto-Grassfields", ["nic-gur-pro"] = "Proto-Gur", ["nic-jkn-pro"] = "Proto-Jukunoid", ["nic-lcr-pro"] = "Proto-Lower Cross River", ["nic-ogo-pro"] = "Proto-Ogoni", ["nic-ovo-pro"] = "Proto-Oti-Volta", ["nic-plt-pro"] = "Proto-Plateau", ["nic-pro"] = "Proto-Niger-Congo", ["nic-ubg-pro"] = "Proto-Ubangian", ["nic-ucr-pro"] = "Proto-Upper Cross River", ["nic-vco-pro"] = "Proto-Volta-Congo", ["nid"] = "Ngandi", ["nie"] = "Niellim", ["nif"] = "Nek", ["nig"] = "Ngalakan", ["nih"] = "Nyiha", ["nii"] = "Nii", ["nij"] = "Ngaju", ["nik"] = "Southern Nicobarese", ["nil"] = "Nila", ["nim"] = "Nilamba", ["nin"] = "Ninzo", ["nio"] = "Nganasan", ["niq"] = "Nandi", ["nir"] = "Nimboran", ["nis"] = "Nimi", ["nit"] = "Southeastern Kolami", ["niu"] = "Niuean", ["niv"] = "Nivkh", ["niw"] = "Nimo", ["nix"] = "Hema", ["niy"] = "Ngiti", ["niz"] = "Ningil", ["nja"] = "Nzanyi", ["njb"] = "Nocte", ["njh"] = "Lotha Naga", ["nji"] = "Gudanji", ["njj"] = "Njen", ["njl"] = "Njalgulgule", ["njm"] = "Angami", ["njn"] = "Liangmai Naga", ["njo-jgl"] = "Chungli Ao", ["njo-mng"] = "Mongsen Ao", ["njr"] = "Njerep", ["njs"] = "Nisa", ["njt"] = "Ndyuka-Trio Pidgin", ["nju"] = "Ngadjunmaya", ["njx"] = "Kunyi", ["njy"] = "Njyem", ["njz"] = "Nyishi", ["nka"] = "Nkoya", ["nkb"] = "Khoibu Naga", ["nkc"] = "Nkongho", ["nkd"] = "Koireng", ["nke"] = "Duke", ["nkf"] = "Inpui Naga", ["nkg"] = "Nekgini", ["nkh"] = "Khezha Naga", ["nki"] = "Thangal Naga", ["nkj"] = "Nakai", ["nkk"] = "Nokuku", ["nkm"] = "Namat", ["nkn"] = "Nkangala", ["nko"] = "Nkonya", ["nkp"] = "Niuatoputapu", ["nkq"] = "Nkami", ["nkr"] = "Nukuoro", ["nks"] = "North Asmat", ["nkt"] = "Nyika", ["nku"] = "Bouna Kulango", ["nkw"] = "Nkutu", ["nkx"] = "Nkoroo", ["nkz"] = "Nkari", ["nl"] = "Dutch", ["nla"] = "Ngombale", ["nlc"] = "Nalca", ["nle"] = "East Nyala", ["nlg"] = "Gela", ["nli"] = "Grangali", ["nlj"] = "Nyali", ["nlk"] = "Ninia Yali", ["nll"] = "Nihali", ["nlm"] = "Mankiyali", ["nlo"] = "Ngul", ["nlq"] = "Lao Naga", ["nlu"] = "Nchumbulu", ["nlv"] = "Orizaba Nahuatl", ["nlw"] = "Walangama", ["nlx"] = "Nahali", ["nly"] = "Nyamal", ["nlz"] = "Nalögo", ["nma"] = "Maram Naga", ["nmb"] = "Big Nambas", ["nmc"] = "Ngam", ["nmd"] = "Ndumu", ["nme"] = "Mzieme Naga", ["nmf"] = "Tangkhul Naga", ["nmg"] = "Kwasio", ["nmh"] = "Monsang Naga", ["nmi"] = "Nyam", ["nmj"] = "Ngombe (Central African Republic)", ["nmk"] = "Namakura", ["nml"] = "Ndemli", ["nmm"] = "Manangba", ["nmn"] = "ǃXóõ", ["nmo"] = "Moyon Naga", ["nmp"] = "Nimanbur", ["nmq"] = "Nambya", ["nmr"] = "Nimbari", ["nms"] = "Letemboi", ["nmt"] = "Namonuito", ["nmu"] = "Northeast Maidu", ["nmv"] = "Ngamini", ["nmw"] = "Nimoa", ["nmx"] = "Nama", ["nmy"] = "Namuyi", ["nmz"] = "Nawdm", ["nn"] = "Norwegian Nynorsk", ["nna"] = "Nyangumarta", ["nnb"] = "Nande", ["nnc"] = "Nancere", ["nnd"] = "West Ambae", ["nne"] = "Ngandyera", ["nnf"] = "Ngaing", ["nng"] = "Maring Naga", ["nnh"] = "Ngiemboon", ["nni"] = "North Nuaulu", ["nnj"] = "Nyangatom", ["nnk"] = "Nankina", ["nnl"] = "Northern Rengma Naga", ["nnm"] = "Namia", ["nnn"] = "Ngete", ["nnp"] = "Wancho", ["nnq"] = "Ngindo", ["nnr"] = "Narungga", ["nnt"] = "Nanticoke", ["nnu"] = "Dwang", ["nnv"] = "Nukunu", ["nnw"] = "Southern Nuni", ["nnx"] = "Ngong", ["nny"] = "Nyangga", ["nnz"] = "Nda'nda'", ["no"] = "Norwegian", ["noa"] = "Woun Meu", ["noc"] = "Nuk", ["nod"] = "Northern Thai", ["noe"] = "Nimadi", ["nof"] = "Nomane", ["nog"] = "Nogai", ["noh"] = "Nomu", ["noi"] = "Noiri", ["noj"] = "Nonuya", ["nok"] = "Nooksack", ["nol"] = "Nomlaki", ["nom"] = "Nocamán", ["non"] = "Old Norse", ["nop"] = "Numanggang", ["noq"] = "Ngongo", ["nos"] = "Eastern Nisu", ["not"] = "Nomatsiguenga", ["nou"] = "Ewage-Notu", ["nov"] = "Novial", ["now"] = "Nyambo", ["noy"] = "Noy", ["noz"] = "Nayi", ["npa"] = "Nar Phu", ["npb"] = "Nupbikha", ["npg"] = "Ponyo", ["nph"] = "Phom", ["npl"] = "Southeastern Puebla Nahuatl", ["npn"] = "Mondropolon", ["npo"] = "Pochuri Naga", ["nps"] = "Nipsan", ["npu"] = "Puimei Naga", ["npx"] = "Noipä", ["npy"] = "Napu", ["nqg"] = "Ede Nago", ["nqk"] = "Kura Ede Nago", ["nql"] = "Ngendelengo", ["nqm"] = "Ndom", ["nqn"] = "Nen", ["nqo"] = "N'Ko", ["nqq"] = "Kyan-Karyaw Naga", ["nqy"] = "Akyaung Ari", ["nr"] = "Southern Ndebele", ["nra"] = "Ngom", ["nrb"] = "Nara", ["nrc"] = "Noric", ["nre"] = "Southern Rengma Naga", ["nrf"] = "Norman", ["nrg"] = "Narango", ["nri"] = "Chokri Naga", ["nrk"] = "Ngarla", ["nrl"] = "Ngarluma", ["nrm"] = "Narom", ["nrn"] = "Norn", ["nrp"] = "North Picene", ["nrr"] = "Norra", ["nrt"] = "Northern Kalapuya", ["nru"] = "Narua", ["nrx"] = "Ngurmbur", ["nrz"] = "Lala (New Guinea)", ["nsa"] = "Sangtam Naga", ["nsb"] = "Lower Nossob", ["nsc"] = "Nshi", ["nsd"] = "Southern Nisu", ["nse"] = "Nsenga", ["nsg"] = "Ngasa", ["nsh"] = "Ngoshie", ["nsi"] = "Nigerian Sign Language", ["nsk"] = "Naskapi", ["nsl"] = "Norwegian Sign Language", ["nsm"] = "Sema", ["nsn"] = "Nehan", ["nso"] = "Northern Sotho", ["nsp"] = "Nepalese Sign Language", ["nsq"] = "Northern Sierra Miwok", ["nsr"] = "Maritime Sign Language", ["nss"] = "Nali", ["nst"] = "Tangsa", ["nsu"] = "Sierra Negra Nahuatl", ["nsv"] = "Southwestern Nisu", ["nsw"] = "Navut", ["nsx"] = "Nsongo", ["nsy"] = "Nasal", ["nsz"] = "Nisenan", ["ntd"] = "Northern Tidung", ["ntg"] = "Ngantangarra", ["nti"] = "Natioro", ["ntj"] = "Ngaanyatjarra", ["ntk"] = "Ikoma", ["ntm"] = "Nateni", ["nto"] = "Ntomba", ["ntp"] = "Northern Tepehuan", ["ntr"] = "Delo", ["nts"] = "Natagaimas", ["ntu"] = "Natügu", ["ntw"] = "Nottoway", ["ntx"] = "Somra", ["nty"] = "Mantsi", ["nua"] = "Yuanga", ["nub-har"] = "Haraza", ["nub-pro"] = "Proto-Nubian", ["nuc"] = "Nukuini", ["nud"] = "Ngala", ["nue"] = "Ngundu", ["nuf"] = "Nusu", ["nug"] = "Nungali", ["nuh"] = "Ndunda", ["nui"] = "Ngumbi", ["nuj"] = "Nyole (Uganda)", ["nuk"] = "Nootka", ["nul"] = "Nusa Laut", ["num"] = "Niuafo'ou", ["nun"] = "Anong", ["nuo"] = "Nguôn", ["nup"] = "Nupe", ["nuq"] = "Nukumanu", ["nur"] = "Nuguria", ["nus"] = "Nuer", ["nut"] = "Nùng", ["nuu"] = "Ngbundu", ["nuv"] = "Northern Nuni", ["nuw"] = "Nguluwan", ["nux"] = "Mehek", ["nuy"] = "Nunggubuyu", ["nuz"] = "Tlamacazapa Nahuatl", ["nv"] = "Navajo", ["nvh"] = "Nasarian", ["nvm"] = "Namiae", ["nvo"] = "Nyokon", ["nwa"] = "Nawathinehena", ["nwb"] = "Nyabwa", ["nwc"] = "Classical Newar", ["nwe"] = "Ngwe", ["nwg"] = "Ngaiawang", ["nwi"] = "Southwest Tanna", ["nwm"] = "Nyamusa-Molo", ["nwo"] = "Nauo", ["nwr"] = "Nawaru", ["nwx"] = "Middle Newar", ["nwy"] = "Nottoway-Meherrin", ["nxa"] = "Nauete", ["nxd"] = "Ngando (Congo)", ["nxe"] = "Nage", ["nxg"] = "Ngadha", ["nxi"] = "Nindi", ["nxl"] = "South Nuaulu", ["nxm"] = "Numidian", ["nxn"] = "Ngawun", ["nxo"] = "Ndambomo", ["nxq"] = "Naxi", ["nxr"] = "Ninggerum", ["nxx"] = "Nafri", ["ny"] = "Chichewa", ["nyb"] = "Nyangbo", ["nyc"] = "Nyanga-li", ["nyd"] = "Nyole (Kenya)", ["nye"] = "Nyengo", ["nyf"] = "Giryama", ["nyg"] = "Nyindu", ["nyh"] = "Nyigina", ["nyi"] = "Nyimang", ["nyj"] = "Nyanga (Congo)", ["nyk"] = "Nyaneka", ["nyl"] = "Nyeu", ["nym"] = "Nyamwezi", ["nyn"] = "Nyankole", ["nyo"] = "Nyoro", ["nyp"] = "Nyang'i", ["nys"] = "Nyunga", ["nyt"] = "Nyawaygi", ["nyu"] = "Nyungwe", ["nyv"] = "Nyulnyul", ["nyw"] = "Nyaw", ["nyx"] = "Nganyaywana", ["nyy"] = "Nyakyusa", ["nza"] = "Tigon Mbembe", ["nzb"] = "Njebi", ["nzd"] = "Nzadi", ["nzi"] = "Nzima", ["nzk"] = "Nzakara", ["nzm"] = "Zeme Naga", ["nzs"] = "New Zealand Sign Language", ["nzu"] = "Central Teke", ["nzy"] = "Nzakambay", ["nzz"] = "Nanga Dama Dogon", ["oaa"] = "Orok", ["oac"] = "Oroch", ["oak"] = "Noakhali", ["oav"] = "Old Avar", ["obi"] = "Obispeño", ["obk"] = "Southern Bontoc", ["obl"] = "Oblo", ["obm"] = "Moabite", ["obo"] = "Obo Manobo", ["obr"] = "Old Burmese", ["obt"] = "Old Breton", ["obu"] = "Obulom", ["oc"] = "Occitan", ["oca"] = "Ocaina", ["och"] = "Old Chinese", ["ocm"] = "Old Cham", ["oco"] = "Old Cornish", ["ocu"] = "Tlahuica", ["oda"] = "Odut", ["odk"] = "Od", ["odt"] = "Old Dutch", ["odu"] = "Odual", ["ofo"] = "Ofo", ["ofs"] = "Old Frisian", ["ofu"] = "Efutop", ["ogb"] = "Ogbia", ["ogc"] = "Ogbah", ["oge"] = "Old Georgian", ["ogg"] = "Ogbogolo", ["ogo"] = "Khana", ["ogu"] = "Ogbronuagum", ["ohu"] = "Old Hungarian", ["oia"] = "Oirata", ["oin"] = "Inebu One", ["oj"] = "Ojibwe", ["ojb"] = "Northwestern Ojibwa", ["ojc"] = "Central Ojibwa", ["ojg"] = "Eastern Ojibwa", ["ojp"] = "Old Japanese", ["ojs"] = "Severn Ojibwa", ["ojv"] = "Ontong Java", ["ojw"] = "Western Ojibwa", ["oka"] = "Okanagan", ["okb"] = "Okobo", ["okd"] = "Okodia", ["oke"] = "Okpe (Southwestern Edo)", ["okg"] = "Kok-Paponk", ["okh"] = "Koresh-e Rostam", ["oki"] = "Okiek", ["okj"] = "Oko-Juwoi", ["okk"] = "Kwamtim One", ["okl"] = "Old Kentish Sign Language", ["okm"] = "Middle Korean", ["okn"] = "Okinoerabu", ["oko"] = "Old Korean", ["okr"] = "Kirike", ["oks"] = "Oko-Eni-Osayen", ["oku"] = "Oku", ["okv"] = "Orokaiva", ["okx"] = "Okpe (Northwestern Edo)", ["okz"] = "Old Khmer", ["old"] = "Mochi", ["ole"] = "Olekha", ["olm"] = "Oloma", ["olo"] = "Livvi", ["olr"] = "Olrat", ["olt"] = "Old Lithuanian", ["olu"] = "Kuvale", ["om"] = "Oromo", ["oma"] = "Omaha-Ponca", ["omb"] = "Omba", ["omc"] = "Mochica", ["omg"] = "Omagua", ["omi"] = "Omi", ["omk"] = "Omok", ["oml"] = "Ombo", ["omn"] = "Minoan", ["omo"] = "Utarmbung", ["omp"] = "Old Manipuri", ["omq-cha-pro"] = "Proto-Chatino", ["omq-maz-pro"] = "Proto-Mazatec", ["omq-mix-pro"] = "Proto-Mixtecan", ["omq-mxt-pro"] = "Proto-Mixtec", ["omq-otp-pro"] = "Proto-Oto-Pamean", ["omq-pro"] = "Proto-Oto-Manguean", ["omq-sjq"] = "San Juan Quiahije Chatino", ["omq-tel"] = "Teposcolula Mixtec", ["omq-teo"] = "Teojomulco Chatino", ["omq-tri-pro"] = "Proto-Triqui", ["omq-zap-pro"] = "Proto-Zapotecan", ["omq-zpc-pro"] = "Proto-Zapotec", ["omr"] = "Old Marathi", ["omt"] = "Omotik", ["omu"] = "Omurano", ["omv-aro-pro"] = "Proto-Aroid", ["omv-diz-pro"] = "Proto-Dizoid", ["omv-pro"] = "Proto-Omotic", ["omw"] = "South Tairora", ["omx"] = "Old Mon", ["ona"] = "Selk'nam", ["onb"] = "Lingao", ["one"] = "Oneida", ["ong"] = "Olo", ["oni"] = "Onin", ["onj"] = "Onjob", ["onk"] = "Kabore One", ["onn"] = "Onobasulu", ["ono"] = "Onondaga", ["onp"] = "Sartang", ["onr"] = "Northern One", ["ons"] = "Ono", ["onu"] = "Unua", ["onw"] = "Old Nubian", ["onx"] = "Pidgin Onin", ["ood"] = "O'odham", ["oog"] = "Ong", ["oon"] = "Önge", ["oor"] = "Oorlams", ["opa"] = "Okpamheri", ["opk"] = "Kopkaka", ["opm"] = "Oksapmin", ["opo"] = "Opao", ["opt"] = "Opata", ["opy"] = "Ofayé", ["or"] = "Odia", ["ora"] = "Oroha", ["ore"] = "Orejón", ["org"] = "Oring", ["orh"] = "Oroqen", ["oro"] = "Orokolo", ["orr"] = "Oruma", ["ort"] = "Adivasi Odia", ["oru"] = "Ormuri", ["orv"] = "Old East Slavic", ["orw"] = "Oro Win", ["orx"] = "Oro", ["orz"] = "Ormu", ["os"] = "Ossetian", ["osa"] = "Osage", ["osc"] = "Oscan", ["osi"] = "Osing", ["osn"] = "Old Sundanese", ["oso"] = "Ososo", ["osp"] = "Old Spanish", ["ost"] = "Osatu", ["osu"] = "Southern One", ["osx"] = "Old Saxon", ["ota"] = "Ottoman Turkish", ["otb"] = "Old Tibetan", ["otd"] = "Ot Danum", ["ote"] = "Mezquital Otomi", ["oti"] = "Oti", ["otk"] = "Old Turkic", ["otl"] = "Tilapa Otomi", ["otm"] = "Eastern Highland Otomi", ["otn"] = "Tenango Otomi", ["oto-otm-pro"] = "Proto-Otomi", ["oto-pro"] = "Proto-Otomian", ["otq"] = "Querétaro Otomi", ["otr"] = "Otoro", ["ots"] = "Estado de México Otomi", ["ott"] = "Temoaya Otomi", ["otu"] = "Otuke", ["otw"] = "Ottawa", ["otx"] = "Texcatepec Otomi", ["oty"] = "Old Tamil", ["otz"] = "Ixtenco Otomi", ["oub"] = "Glio-Oubi", ["oue"] = "Oune", ["oui"] = "Old Uyghur", ["oum"] = "Ouma", ["ovd"] = "Elfdalian", ["owi"] = "Owiniga", ["owl"] = "Old Welsh", ["oyb"] = "Oy", ["oyd"] = "Oyda", ["oym"] = "Wayampi", ["oyy"] = "Oya'oya", ["ozm"] = "Koonzime", ["pa"] = "Punjabi", ["paa-kmn"] = "Kómnzo", ["paa-kwn"] = "Kuwani", ["paa-lei"] = "Leitre", ["paa-nha-pro"] = "Proto-North Halmahera", ["paa-nun"] = "Nungon", ["pab"] = "Pareci", ["pac"] = "Pacoh", ["pad"] = "Paumarí", ["pae"] = "Pagibete", ["paf"] = "Paranawát", ["pag"] = "Pangasinan", ["pah"] = "Tenharim", ["pai"] = "Pe", ["pak"] = "Parakanã", ["pal"] = "Middle Persian", ["pam"] = "Kapampangan", ["pao"] = "Northern Paiute", ["pap"] = "Papiamentu", ["paq"] = "Parya", ["par"] = "Panamint", ["pas"] = "Papasena", ["pau"] = "Palauan", ["pav"] = "Wari'", ["paw"] = "Pawnee", ["pax"] = "Pankararé", ["pay"] = "Pech", ["paz"] = "Pankararú", ["pbb"] = "Páez", ["pbc"] = "Patamona", ["pbe"] = "Mezontla Popoloca", ["pbf"] = "Coyotepec Popoloca", ["pbg"] = "Paraujano", ["pbh"] = "Panare", ["pbi"] = "Podoko", ["pbl"] = "Mak (Nigeria)", ["pbm"] = "Puebla Mazatec", ["pbn"] = "Kpasam", ["pbo"] = "Papel", ["pbp"] = "Badyara", ["pbr"] = "Pangwa", ["pbs"] = "Central Pame", ["pbv"] = "Pnar", ["pby"] = "Pyu (New Guinea)", ["pca"] = "Santa Inés Ahuatempan Popoloca", ["pcb"] = "Pear", ["pcc"] = "Bouyei", ["pcd"] = "Picard", ["pce"] = "Ruching Palaung", ["pcf"] = "Paliyan", ["pcg"] = "Paniya", ["pch"] = "Pardhan", ["pci"] = "Duruwa", ["pcj"] = "Parenga", ["pck"] = "Paite", ["pcl"] = "Pardhi", ["pcm"] = "Nigerian Pidgin", ["pcn"] = "Piti", ["pcp"] = "Pacahuara", ["pcw"] = "Pyapun", ["pda"] = "Anam", ["pdc"] = "Pennsylvania German", ["pdi"] = "Pa Di", ["pdn"] = "Fedan", ["pdo"] = "Padoe", ["pdt"] = "Plautdietsch", ["pdu"] = "Kayan", ["pea"] = "Peranakan Indonesian", ["peb"] = "Eastern Pomo", ["ped"] = "Mala (New Guinea)", ["pee"] = "Taje", ["pef"] = "Northeastern Pomo", ["peg"] = "Pengo", ["peh"] = "Bonan", ["pei"] = "Chichimeca-Jonaz", ["pej"] = "Northern Pomo", ["pek"] = "Penchal", ["pel"] = "Pekal", ["pem"] = "Phende", ["peo"] = "Old Persian", ["pep"] = "Kunja", ["peq"] = "Southern Pomo", ["pev"] = "Pémono", ["pex"] = "Petats", ["pey"] = "Petjo", ["pez"] = "Eastern Penan", ["pfa"] = "Pááfang", ["pfe"] = "Peere", ["pga"] = "Juba Arabic", ["pgd"] = "Gandhari", ["pgg"] = "Pangwali", ["pgi"] = "Pagi", ["pgk"] = "Rerep", ["pgl"] = "Primitive Irish", ["pgn"] = "Paelignian", ["pgs"] = "Pangseng", ["pgu"] = "Pagu", ["pgz"] = "Papua New Guinean Sign Language", ["pha"] = "Pa-Hng", ["phd"] = "Phudagi", ["phg"] = "Phuong", ["phh"] = "Phukha", ["phi-din"] = "Dinapigue Agta", ["phi-kal-pro"] = "Proto-Kalamian", ["phi-nag"] = "Nagtipunan Agta", ["phi-pro"] = "Proto-Philippine", ["phk"] = "Phake", ["phl"] = "Palula", ["phm"] = "Phimbi", ["phn"] = "Phoenician", ["pho"] = "Phunoi", ["phq"] = "Phana'", ["phr"] = "Pahari-Potwari", ["pht"] = "Phu Thai", ["phu"] = "Phuan", ["phv"] = "Pahlavani", ["phw"] = "Phangduwali", ["pi"] = "Pali", ["pia"] = "Pima Bajo", ["pib"] = "Yine", ["pic"] = "Pinji", ["pid"] = "Piaroa", ["pie"] = "Piro", ["pif"] = "Pingelapese", ["pig"] = "Pisabo", ["pih"] = "Pitcairn-Norfolk", ["pii"] = "Pini", ["pij"] = "Pijao", ["pil"] = "Yom", ["pim"] = "Powhatan", ["pin"] = "Piame", ["pio"] = "Piapoco", ["pip"] = "Pero", ["pir"] = "Piratapuyo", ["pis"] = "Pijin", ["pit"] = "Pitta-Pitta", ["piu"] = "Pintupi-Luritja", ["piv"] = "Pileni", ["piw"] = "Pimbwe", ["pix"] = "Piu", ["piy"] = "Piya-Kwonci", ["piz"] = "Pije", ["pjt"] = "Pitjantjatjara", ["pkb"] = "Kipfokomo", ["pkc"] = "Baekje", ["pkg"] = "Pak-Tong", ["pkh"] = "Pankhu", ["pkn"] = "Pakanha", ["pko"] = "Pökoot", ["pkp"] = "Pukapukan", ["pkr"] = "Attapady Kurumba", ["pks"] = "Pakistan Sign Language", ["pkt"] = "Maleng", ["pku"] = "Paku", ["pl"] = "Polish", ["pla"] = "Miani", ["plb"] = "Polonombauk", ["plc"] = "Central Palawano", ["ple"] = "Palu'e", ["plg"] = "Pilagá", ["plh"] = "Paulohi", ["plj"] = "Polci", ["plk"] = "Kohistani Shina", ["pll"] = "Shwe Palaung", ["pln"] = "Palenquero", ["plo"] = "Oluta Popoluca", ["plq"] = "Palaic", ["plr"] = "Palaka", ["pls"] = "San Marcos Tlalcoyalco Popoloca", ["plu"] = "Palikur", ["plv"] = "Southwest Palawano", ["plw"] = "Brooke's Point Palawano", ["ply"] = "Bolyu", ["plz"] = "Paluan", ["pma"] = "Paamese", ["pmb"] = "Pambia", ["pmd"] = "Pallanganmiddang", ["pme"] = "Pwaamèi", ["pmf"] = "Pamona", ["pmi"] = "Northern Pumi", ["pmj"] = "Southern Pumi", ["pmk"] = "Pamlico", ["pml"] = "Sabir", ["pmm"] = "Pol", ["pmn"] = "Pam", ["pmo"] = "Pom", ["pmq"] = "Northern Pame", ["pmr"] = "Manat", ["pms"] = "Piedmontese", ["pmt"] = "Tuamotuan", ["pmu"] = "Mirpur Panjabi", ["pmw"] = "Plains Miwok", ["pmx"] = "Poumei Naga", ["pmy"] = "Papuan Malay", ["pmz"] = "Southern Pame", ["pna"] = "Punan Bah-Biau", ["pnc"] = "Pannei", ["pnd"] = "Mpinda", ["pne"] = "Western Penan", ["png"] = "Pongu", ["pnh"] = "Penrhyn", ["pni"] = "Aoheng", ["pnj"] = "Pinjarup", ["pnk"] = "Paunaka", ["pnl"] = "Paleni", ["pnm"] = "Punan Batu", ["pnn"] = "Pinai-Hagahai", ["pno"] = "Panobo", ["pnp"] = "Pancana", ["pnq"] = "Pana (West Africa)", ["pnr"] = "Panim", ["pns"] = "Ponosakan", ["pnt"] = "Pontic Greek", ["pnu"] = "Jiongnai Bunu", ["pnv"] = "Pinigura", ["pnw"] = "Panyjima", ["pnx"] = "Phong-Kniang", ["pny"] = "Pinyin", ["pnz"] = "Pana (Central Africa)", ["poc"] = "Poqomam", ["poe"] = "San Juan Atzingo Popoloca", ["pof"] = "Poke", ["pog"] = "Potiguára", ["poh"] = "Poqomchi'", ["poi"] = "Highland Popoluca", ["pok"] = "Pokangá", ["pom"] = "Southeastern Pomo", ["pon"] = "Pohnpeian", ["poo"] = "Central Pomo", ["pop"] = "Pwapwâ", ["poq"] = "Texistepec Popoluca", ["pos"] = "Sayula Popoluca", ["pot"] = "Potawatomi", ["pov"] = "Guinea-Bissau Creole", ["pow"] = "San Felipe Otlaltepec Popoloca", ["pox"] = "Polabian", ["poy"] = "Pogolo", ["poz-abi"] = "Abai", ["poz-bal"] = "Baliledo", ["poz-btk-pro"] = "Proto-Bungku-Tolaki", ["poz-cet-pro"] = "Proto-Central-Eastern Malayo-Polynesian", ["poz-hce-pro"] = "Proto-Halmahera-Cenderawasih", ["poz-lgx-pro"] = "Proto-Lampungic", ["poz-mcm-pro"] = "Proto-Malayo-Chamic", ["poz-mic-pro"] = "Proto-Micronesian", ["poz-mly-pro"] = "Proto-Malayic", ["poz-msa-pro"] = "Proto-Malayo-Sumbawan", ["poz-oce-pro"] = "Proto-Oceanic", ["poz-pep-pro"] = "Proto-Eastern Polynesian", ["poz-pnp-pro"] = "Proto-Nuclear Polynesian", ["poz-pol-pro"] = "Proto-Polynesian", ["poz-pro"] = "Proto-Malayo-Polynesian", ["poz-sml"] = "Sarawak Malay", ["poz-ssw-pro"] = "Proto-South Sulawesi", ["poz-swa-pro"] = "Proto-North Sarawak", ["poz-ter"] = "Terengganu Malay", ["ppa"] = "Pao", ["ppe"] = "Papi", ["ppi"] = "Paipai", ["ppk"] = "Uma", ["ppl"] = "Pipil", ["ppm"] = "Papuma", ["ppn"] = "Papapana", ["ppo"] = "Folopa", ["ppq"] = "Pei", ["pps"] = "San Luís Temalacayuca Popoloca", ["ppt"] = "Pa", ["ppu"] = "Papora", ["pqa"] = "Pa'a", ["pqe-pro"] = "Proto-Eastern Malayo-Polynesian", ["pqm"] = "Malecite-Passamaquoddy", ["pra"] = "Prakrit", ["pra-niy"] = "Niya Prakrit", ["prc"] = "Parachi", ["pre"] = "Principense", ["prf"] = "Paranan", ["prg"] = "Old Prussian", ["prh"] = "Porohanon", ["pri"] = "Paicî", ["prk"] = "Parauk", ["prl"] = "Peruvian Sign Language", ["prm"] = "Kibiri", ["prn"] = "Prasuni", ["pro"] = "Old Occitan", ["prq"] = "Perené Ashéninka", ["prr"] = "Puri", ["prt"] = "Phai", ["pru"] = "Puragi", ["prw"] = "Parawen", ["prx"] = "Purik", ["prz"] = "Providencia Sign Language", ["ps"] = "Pashto", ["psa"] = "Asue Awyu", ["psc"] = "Persian Sign Language", ["psd"] = "Plains Indian Sign Language", ["pse"] = "Central Malay", ["psg"] = "Penang Sign Language", ["psh"] = "Southwest Pashayi", ["psi"] = "Southeast Pashayi", ["psl"] = "Puerto Rican Sign Language", ["psm"] = "Pauserna", ["psn"] = "Panasuan", ["pso"] = "Polish Sign Language", ["psp"] = "Philippine Sign Language", ["psq"] = "Pasi", ["psr"] = "Portuguese Sign Language", ["pss"] = "Kaulong", ["psw"] = "Port Sandwich", ["psy"] = "Piscataway", ["pt"] = "Portuguese", ["pta"] = "Pai Tavytera", ["pth"] = "Pataxó Hã-Ha-Hãe", ["pti"] = "Pintiini", ["ptn"] = "Patani", ["pto"] = "Zo'é", ["ptp"] = "Patep", ["ptq"] = "Pattapu", ["ptr"] = "Piamatsina", ["ptt"] = "Enrekang", ["ptu"] = "Bambam", ["ptv"] = "Port Vato", ["ptw"] = "Pentlatch", ["pty"] = "Pathiya", ["pua"] = "Purepecha", ["pub"] = "Purum", ["puc"] = "Punan Merap", ["pud"] = "Punan Aput", ["pue"] = "Puelche", ["puf"] = "Punan Merah", ["pug"] = "Phuie", ["pui"] = "Puinave", ["puj"] = "Punan Tubu", ["pum"] = "Puma", ["puo"] = "Puoc", ["pup"] = "Pulabu", ["puq"] = "Puquina", ["pur"] = "Puruborá", ["put"] = "Putoh", ["puu"] = "Punu", ["puw"] = "Puluwat", ["pux"] = "Puare", ["puy"] = "Purisimeño", ["pwa"] = "Pawaia", ["pwb"] = "Panawa", ["pwg"] = "Gapapaiwa", ["pwi"] = "Patwin", ["pwm"] = "Molbog", ["pwn"] = "Paiwan", ["pwo"] = "Western Pwo", ["pwr"] = "Powari", ["pww"] = "Northern Pwo", ["pxm"] = "Quetzaltepec Mixe", ["pye"] = "Pye Krumen", ["pym"] = "Fyam", ["pyn"] = "Poyanáwa", ["pys"] = "Paraguayan Sign Language", ["pyu"] = "Puyuma", ["pyx"] = "Pyu (Myanmar)", ["pyy"] = "Pyen", ["pzh"] = "Pazeh", ["pzn"] = "Para Naga", ["qfa-adm-pro"] = "Proto-Great Andamanese", ["qfa-bet-pro"] = "Proto-Be-Tai", ["qfa-cka-pro"] = "Proto-Chukotko-Kamchatkan", ["qfa-hur-pro"] = "Proto-Hurro-Urartian", ["qfa-kad-pro"] = "Proto-Kadu", ["qfa-kms-pro"] = "Proto-Kam-Sui", ["qfa-kor-pro"] = "Proto-Koreanic", ["qfa-kra-pro"] = "Proto-Kra", ["qfa-lic-pro"] = "Proto-Hlai", ["qfa-onb-pro"] = "Proto-Be", ["qfa-ong-pro"] = "Proto-Ongan", ["qfa-tak-pro"] = "Proto-Kra-Dai", ["qfa-yen-pro"] = "Proto-Yeniseian", ["qfa-yuk-pro"] = "Proto-Yukaghir", ["qu"] = "Quechua", ["qua"] = "Quapaw", ["quc"] = "K'iche'", ["qui"] = "Quileute", ["qum"] = "Sipakapense", ["qun"] = "Quinault", ["quq"] = "Quinqui", ["quv"] = "Sacapulteco", ["qvy"] = "Queyu", ["qwc"] = "Classical Quechua", ["qwe-kch"] = "Kichwa", ["qwe-pro"] = "Proto-Quechuan", ["qwm"] = "Kipchak", ["qwt"] = "Kwalhioqua-Tlatskanai", ["qxs"] = "Southern Qiang", ["qya"] = "Quenya", ["qyp"] = "Quiripi", ["raa"] = "Dungmali", ["rab"] = "Chamling", ["rac"] = "Rasawa", ["rad"] = "Rade", ["raf"] = "Western Meohang", ["rag"] = "Logooli", ["rah"] = "Rabha", ["rai"] = "Ramoaaina", ["rak"] = "Tulu-Bohuai", ["ral"] = "Ralte", ["ram"] = "Canela", ["ran"] = "Riantana", ["rao"] = "Rao", ["rap"] = "Rapa Nui", ["raq"] = "Saam", ["rar"] = "Rarotongan", ["ras"] = "Tegali", ["rat"] = "Razajerdi", ["rau"] = "Raute", ["rav"] = "Sampang", ["raw"] = "Rawang", ["rax"] = "Rang", ["ray"] = "Rapa", ["raz"] = "Rahambuu", ["rbb"] = "Rumai Palaung", ["rbk"] = "Northern Bontoc", ["rbl"] = "East Miraya Bikol", ["rcf"] = "Réunion Creole French", ["rdb"] = "Rudbari", ["rea"] = "Rerau", ["reb"] = "Rembong", ["ree"] = "Rejang Kayan", ["reg"] = "Kara (Tanzania)", ["rei"] = "Reli", ["rej"] = "Rejang", ["rel"] = "Rendille", ["rem"] = "Remo", ["ren"] = "Rengao", ["rer"] = "Rer Bare", ["res"] = "Reshe", ["ret"] = "Retta", ["rey"] = "Reyesano", ["rga"] = "Roria", ["rge"] = "Romano-Greek", ["rgk"] = "Rangkas", ["rgn"] = "Romagnol", ["rgr"] = "Resígaro", ["rgs"] = "Southern Roglai", ["rgu"] = "Ringgou", ["rhg"] = "Rohingya", ["rhp"] = "Yahang", ["ria"] = "Reang", ["rif"] = "Tarifit", ["ril"] = "Riang", ["rim"] = "Nyaturu", ["rin"] = "Nungu", ["rir"] = "Ribun", ["rit"] = "Ritarungo", ["riu"] = "Riung", ["rjg"] = "Rajong", ["rji"] = "Raji", ["rjs"] = "Rajbanshi", ["rka"] = "Kraol", ["rkb"] = "Rikbaktsa", ["rkh"] = "Rakahanga-Manihiki", ["rki"] = "Rakhine", ["rkm"] = "Marka", ["rkt"] = "Kamta", ["rkw"] = "Arakwal", ["rm"] = "Romansh", ["rma"] = "Rama", ["rmb"] = "Rembarunga", ["rmc"] = "Carpathian Romani", ["rmd"] = "Traveller Danish", ["rme"] = "Angloromani", ["rmf"] = "Kalo Finnish Romani", ["rmg"] = "Traveller Norwegian", ["rmh"] = "Murkim", ["rmi"] = "Lomavren", ["rmk"] = "Romkun", ["rml"] = "Baltic Romani", ["rmm"] = "Roma", ["rmn"] = "Balkan Romani", ["rmo"] = "Sinte Romani", ["rmp"] = "Rempi", ["rmq"] = "Caló", ["rms"] = "Romanian Sign Language", ["rmt"] = "Domari", ["rmu"] = "Tavringer Romani", ["rmv"] = "Romanova", ["rmw"] = "Welsh Romani", ["rmx"] = "Romam", ["rmy"] = "Vlax Romani", ["rmz"] = "Marma", ["rnd"] = "Ruwund", ["rng"] = "Ronga", ["rnl"] = "Ranglong", ["rnn"] = "Roon", ["rnp"] = "Rongpo", ["rnw"] = "Rungwa", ["ro"] = "Romanian", ["roa-ang"] = "Angevin", ["roa-bbn"] = "Bourbonnais-Berrichon", ["roa-brg"] = "Bourguignon", ["roa-can"] = "Cantabrian", ["roa-cha"] = "Champenois", ["roa-fcm"] = "Franc-Comtois", ["roa-gal"] = "Gallo", ["roa-gib"] = "Gallo-Italic of Basilicata", ["roa-gis"] = "Gallo-Italic of Sicily", ["roa-leo"] = "Leonese", ["roa-lor"] = "Lorrain", ["roa-oca"] = "Old Catalan", ["roa-ole"] = "Old Leonese", ["roa-ona"] = "Old Navarro-Aragonese", ["roa-opt"] = "Old Galician-Portuguese", ["roa-orl"] = "Orléanais", ["roa-poi"] = "Poitevin-Saintongeais", ["roa-tar"] = "Tarantino", ["rob"] = "Tae'", ["roc"] = "Cacgia Roglai", ["rod"] = "Rogo", ["roe"] = "Ronji", ["rof"] = "Rombo", ["rog"] = "Northern Roglai", ["rol"] = "Romblomanon", ["rom"] = "Romani", ["roo"] = "Rotokas", ["rop"] = "Australian Kriol", ["ror"] = "Rongga", ["rou"] = "Runga", ["row"] = "Dela-Oenale", ["rpn"] = "Repanbitip", ["rpt"] = "Rapting", ["rri"] = "Ririo", ["rrm"] = "Moriori", ["rro"] = "Roro", ["rrt"] = "Arritinngithigh", ["rsb"] = "Romano-Serbian", ["rsk"] = "Pannonian Rusyn", ["rsl"] = "Russian Sign Language", ["rsm"] = "Miriwoong Sign Language", ["rsn"] = "Rwandan Sign Language", ["rtc"] = "Rungtu", ["rth"] = "Ratahan", ["rtm"] = "Rotuman", ["rtw"] = "Rathawi", ["ru"] = "Russian", ["rub"] = "Gungu", ["ruc"] = "Ruuli", ["rue"] = "Carpathian Rusyn", ["ruf"] = "Luguru", ["rug"] = "Roviana", ["ruh"] = "Ruga", ["rui"] = "Rufiji", ["ruk"] = "Che", ["ruo"] = "Istro-Romanian", ["rup"] = "Aromanian", ["ruq"] = "Megleno-Romanian", ["rut"] = "Rutul", ["ruu"] = "Lanas Lobu", ["ruy"] = "Mala (Nigeria)", ["ruz"] = "Ruma", ["rw"] = "Rwanda-Rundi", ["rwa"] = "Rawo", ["rwk"] = "Rwa", ["rwm"] = "Amba", ["rwo"] = "Rawa", ["rxd"] = "Ngardi", ["rxw"] = "Karuwali", ["ryn"] = "Northern Amami Ōshima", ["rys"] = "Yaeyama", ["ryu"] = "Okinawan", ["rzh"] = "Razihi", ["sa"] = "Sanskrit", ["saa"] = "Saba", ["sab"] = "Buglere", ["sac"] = "Fox", ["sad"] = "Sandawe", ["sae"] = "Sabanê", ["saf"] = "Safaliba", ["sah"] = "Yakut", ["sai-all"] = "Allentiac", ["sai-and"] = "Andoquero", ["sai-ayo"] = "Ayomán", ["sai-bae"] = "Baenan", ["sai-bag"] = "Bagua", ["sai-bet"] = "Betoi", ["sai-bor-pro"] = "Proto-Boran", ["sai-cac"] = "Cacán", ["sai-caq"] = "Caranqui", ["sai-car-pro"] = "Proto-Cariban", ["sai-cat"] = "Catacao", ["sai-cer-pro"] = "Proto-Cerrado", ["sai-chi"] = "Chirino", ["sai-chn"] = "Chaná", ["sai-chp"] = "Chapacura", ["sai-chr"] = "Charrua", ["sai-chu"] = "Churuya", ["sai-cje-pro"] = "Proto-Central Jê", ["sai-cmg"] = "Comechingon", ["sai-cno"] = "Chono", ["sai-cnr"] = "Cañari", ["sai-coe"] = "Coeruna", ["sai-col"] = "Colán", ["sai-cop"] = "Copallén", ["sai-crd"] = "Coroado Puri", ["sai-ctq"] = "Catuquinaru", ["sai-cul"] = "Culli", ["sai-cva"] = "Cueva", ["sai-esm"] = "Esmeralda", ["sai-ewa"] = "Ewarhuyana", ["sai-gam"] = "Gamela", ["sai-gay"] = "Gayón", ["sai-gmo"] = "Guamo", ["sai-gua"] = "Guachí", ["sai-gue"] = "Güenoa", ["sai-hau"] = "Haush", ["sai-jee-pro"] = "Proto-Jê", ["sai-jko"] = "Jeikó", ["sai-jrj"] = "Jirajara", ["sai-kat"] = "Katembri", ["sai-mal"] = "Malalí", ["sai-mar"] = "Maratino", ["sai-mat"] = "Matanawi", ["sai-mcn"] = "Mocana", ["sai-men"] = "Menien", ["sai-mil"] = "Millcayac", ["sai-mlb"] = "Malibu", ["sai-msk"] = "Masakará", ["sai-muc"] = "Mucuchí", ["sai-mue"] = "Muellama", ["sai-muz"] = "Muzo", ["sai-mys"] = "Maynas", ["sai-nat"] = "Natú", ["sai-nje-pro"] = "Proto-Northern Jê", ["sai-opo"] = "Opón", ["sai-oto"] = "Otomaco", ["sai-pal"] = "Palta", ["sai-pam"] = "Pamigua", ["sai-par"] = "Paratió", ["sai-peb"] = "Peba", ["sai-pnz"] = "Panzaleo", ["sai-prh"] = "Puruhá", ["sai-ptg"] = "Patagón", ["sai-pur"] = "Purukotó", ["sai-pyg"] = "Payaguá", ["sai-pyk"] = "Pykobjê", ["sai-qmb"] = "Quimbaya", ["sai-qtm"] = "Quitemo", ["sai-rab"] = "Rabona", ["sai-ram"] = "Ramanos", ["sai-sac"] = "Sácata", ["sai-san"] = "Sanaviron", ["sai-sap"] = "Sapará", ["sai-sec"] = "Sechura", ["sai-sin"] = "Sinúfana", ["sai-sje-pro"] = "Proto-Southern Jê", ["sai-tab"] = "Tabancale", ["sai-tal"] = "Tallán", ["sai-tap"] = "Tapayuna", ["sai-tar-pro"] = "Proto-Taranoan", ["sai-teu"] = "Teushen", ["sai-tim"] = "Timote", ["sai-tpr"] = "Taparita", ["sai-trr"] = "Tarairiú", ["sai-wai"] = "Waitaká", ["sai-way"] = "Wayumara", ["sai-wit-pro"] = "Proto-Witotoan", ["sai-wnm"] = "Wanham", ["sai-xoc"] = "Xocó", ["sai-yao"] = "Yao (South America)", ["sai-yar"] = "Yarumá", ["sai-yri"] = "Yuri", ["sai-yup"] = "Yupua", ["sai-yur"] = "Yurumanguí", ["saj"] = "Sahu", ["sak"] = "Sake", ["sal-pro"] = "Proto-Salish", ["sam"] = "Samaritan Aramaic", ["sao"] = "Sause", ["saq"] = "Samburu", ["sar"] = "Saraveca", ["sas"] = "Sasak", ["sat"] = "Santali", ["sau"] = "Saleman", ["sav"] = "Saafi-Saafi", ["saw"] = "Sawi", ["sax"] = "Sa", ["say"] = "Saya", ["saz"] = "Saurashtra", ["sba"] = "Ngambay", ["sbb"] = "Simbo", ["sbc"] = "Gele'", ["sbd"] = "Southern Samo", ["sbe"] = "Saliba (New Guinea)", ["sbf"] = "Shabo", ["sbg"] = "Seget", ["sbh"] = "Sori-Harengan", ["sbi"] = "Seti", ["sbj"] = "Surbakhal", ["sbk"] = "Safwa", ["sbl"] = "Botolan Sambal", ["sbm"] = "Sagala", ["sbn"] = "Sindhi Bhil", ["sbo"] = "Sabüm", ["sbp"] = "Sangu (Tanzania)", ["sbq"] = "Sirva", ["sbr"] = "Sembakung Murut", ["sbs"] = "Subiya", ["sbt"] = "Kimki", ["sbu"] = "Stod Bhoti", ["sbv"] = "Sabine", ["sbw"] = "Simba", ["sbx"] = "Seberuang", ["sby"] = "Soli", ["sbz"] = "Sara Kaba", ["sc"] = "Sardinian", ["scb"] = "Chut", ["sce"] = "Dongxiang", ["scf"] = "San Miguel Creole French", ["scg"] = "Sanggau", ["sch"] = "Sakachep", ["sci"] = "Sri Lankan Creole Malay", ["sck"] = "Sadri", ["scl"] = "Shina", ["scn"] = "Sicilian", ["sco"] = "Scots", ["scp"] = "Yolmo", ["scq"] = "Sa'och", ["scs"] = "North Slavey", ["scu"] = "Shumcho", ["scv"] = "Sheni", ["scw"] = "Sha", ["scx"] = "Sicel", ["scz"] = "Shetland", ["sd"] = "Sindhi", ["sda"] = "Toraja-Sa'dan", ["sdb"] = "Shabak", ["sdc"] = "Sassarese", ["sde"] = "Surubu", ["sdf"] = "Sarli", ["sdg"] = "Savi", ["sdh"] = "Southern Kurdish", ["sdj"] = "Suundi", ["sdk"] = "Sos Kundi", ["sdl"] = "Saudi Arabian Sign Language", ["sdm"] = "Semandang", ["sdn"] = "Gallurese", ["sdo"] = "Bukar-Sadung Bidayuh", ["sdp"] = "Sherdukpen", ["sdr"] = "Oraon Sadri", ["sds"] = "Tunisian Berber", ["sdu"] = "Sarudu", ["sdv-daj-pro"] = "Proto-Daju", ["sdv-eje-pro"] = "Proto-Eastern Jebel", ["sdv-nil-pro"] = "Proto-Nilotic", ["sdv-nyi-pro"] = "Proto-Nyima", ["sdv-tmn-pro"] = "Proto-Taman", ["sdx"] = "Sibu Melanau", ["se"] = "Northern Sami", ["sea"] = "Semai", ["sec"] = "Sechelt", ["sed"] = "Sedang", ["see"] = "Seneca", ["sef"] = "Cebaara", ["seg"] = "Segeju", ["seh"] = "Sena", ["sei"] = "Seri", ["sej"] = "Sene", ["sek"] = "Sekani", ["sel-nor"] = "Northern Selkup", ["sel-pro"] = "Proto-Selkup", ["sel-sou"] = "Southern Selkup", ["sem-amm"] = "Ammonite", ["sem-amo"] = "Amorite", ["sem-cha"] = "Chaha", ["sem-dad"] = "Dadanitic", ["sem-dum"] = "Dumaitic", ["sem-has"] = "Hasaitic", ["sem-his"] = "Hismaic", ["sem-mhr"] = "Muher", ["sem-pro"] = "Proto-Semitic", ["sem-saf"] = "Safaitic", ["sem-sam"] = "Samalian", ["sem-srb"] = "Old South Arabian", ["sem-tay"] = "Taymanitic", ["sem-tha"] = "Thamudic", ["sem-wes-pro"] = "Proto-West Semitic", ["sen"] = "Nanerige", ["seo"] = "Asaba", ["sep"] = "Sicite", ["seq"] = "Senara", ["ser"] = "Serrano", ["ses"] = "Koyraboro Senni", ["set"] = "Sentani", ["seu"] = "Serui-Laut", ["sev"] = "Nyarafolo", ["sew"] = "Sewa Bay", ["sey"] = "Secoya", ["sez"] = "Senthang Chin", ["sfb"] = "French Belgian Sign Language", ["sfe"] = "Eastern Subanun", ["sfm"] = "Small Flowery Miao", ["sfs"] = "South African Sign Language", ["sfw"] = "Sehwi", ["sg"] = "Sango", ["sga"] = "Old Irish", ["sgb"] = "Mag-Anchi Ayta", ["sgc"] = "Kipsigis", ["sgd"] = "Surigaonon", ["sge"] = "Segai", ["sgg"] = "Swiss-German Sign Language", ["sgh"] = "Shughni", ["sgi"] = "Suga", ["sgk"] = "Sangkong", ["sgm"] = "Singa", ["sgp"] = "Singpho", ["sgr"] = "Sangisari", ["sgs"] = "Samogitian", ["sgt"] = "Brokpake", ["sgu"] = "Salas", ["sgw"] = "Sebat Bet Gurage", ["sgx"] = "Sierra Leone Sign Language", ["sgy"] = "Sanglechi", ["sgz"] = "Sursurunga", ["sh"] = "Serbo-Croatian", ["sha"] = "Shall-Zwall", ["shb"] = "Ninam", ["shc"] = "Sonde", ["shd"] = "Kundal Shahi", ["she"] = "Sheko", ["shg"] = "Shua", ["shh"] = "Shoshone", ["shi"] = "Tashelhit", ["shj"] = "Shatt", ["shk"] = "Shilluk", ["shl"] = "Shendu", ["shm"] = "Shahrudi", ["shn"] = "Shan", ["sho"] = "Shanga", ["shp"] = "Shipibo-Conibo", ["shq"] = "Sala", ["shr"] = "Shi", ["shs"] = "Shuswap", ["sht"] = "Shasta", ["shu"] = "Chadian Arabic", ["shv"] = "Shehri", ["shw"] = "Shwai", ["shx"] = "She", ["shy"] = "Tachawit", ["shz"] = "Syenara", ["si"] = "Sinhalese", ["sia"] = "Akkala Sami", ["sib"] = "Sebop", ["sid"] = "Sidamo", ["sie"] = "Simaa", ["sif"] = "Siamou", ["sig"] = "Paasaal", ["sih"] = "Sîshëë", ["sii"] = "Shom Peng", ["sij"] = "Numbami", ["sik"] = "Sikiana", ["sil"] = "Tumulung Sisaala", ["sim"] = "Mende (New Guinea)", ["sio-pro"] = "Proto-Siouan", ["sip"] = "Sikkimese", ["siq"] = "Sonia", ["sir"] = "Siri", ["sis"] = "Siuslaw", ["sit-aao-pro"] = "Proto-Central Naga", ["sit-bai-pro"] = "Proto-Bai", ["sit-ban"] = "Bangru", ["sit-bdi-pro"] = "Proto-Bodish", ["sit-bok"] = "Bokar", ["sit-cai"] = "Caijia", ["sit-cha"] = "Chairel", ["sit-ers-pro"] = "Proto-Ersuic", ["sit-hrs-pro"] = "Proto-Hrusish", ["sit-jap"] = "Japhug", ["sit-kha-pro"] = "Proto-Kham", ["sit-khb-pro"] = "Proto-Kho-Bwa", ["sit-khp-pro"] = "Proto-Puroik", ["sit-khw-pro"] = "Proto-Western Kho-Bwa", ["sit-kon-pro"] = "Proto-Northern Naga", ["sit-liz"] = "Lizu", ["sit-lnj"] = "Longjia", ["sit-lrn"] = "Luren", ["sit-luu-pro"] = "Proto-Luish", ["sit-nas-pro"] = "Proto-Naish", ["sit-prn"] = "Puiron", ["sit-pro"] = "Proto-Sino-Tibetan", ["sit-sit"] = "Situ", ["sit-tam-pro"] = "Proto-Tamangic", ["sit-tan-pro"] = "Proto-Tani", ["sit-tgm"] = "Tangam", ["sit-tng-pro"] = "Proto-Tangkhulic", ["sit-tos"] = "Tosu", ["sit-tsh"] = "Tshobdun", ["sit-zbu"] = "Zbu", ["siu"] = "Sinagen", ["siv"] = "Sumariup", ["siw"] = "Siwai", ["six"] = "Sumau", ["siy"] = "Sivandi", ["siz"] = "Siwi", ["sja"] = "Epena", ["sjb"] = "Sajau Basap", ["sjc"] = "Shaojiang Min", ["sjd"] = "Kildin Sami", ["sje"] = "Pite Sami", ["sjg"] = "Assangori", ["sjk"] = "Kemi Sami", ["sjl"] = "Miji", ["sjm"] = "Mapun", ["sjn"] = "Sindarin", ["sjo"] = "Xibe", ["sjp"] = "Surjapuri", ["sjr"] = "Siar-Lak", ["sjs"] = "Senhaja de Srair", ["sjt"] = "Ter Sami", ["sju"] = "Ume Sami", ["sjw"] = "Shawnee", ["sk"] = "Slovak", ["skb"] = "Saek", ["skc"] = "Ma Manda", ["skd"] = "Southern Sierra Miwok", ["ske"] = "Ske", ["skf"] = "Mekéns", ["skh"] = "Sikule", ["ski"] = "Sika", ["skj"] = "Seke", ["skk"] = "Sok", ["skm"] = "Sakam", ["skn"] = "Kolibugan Subanon", ["sko"] = "Seko Tengah", ["skp"] = "Sekapan", ["skq"] = "Sininkere", ["skr"] = "Saraiki", ["sks"] = "Maia", ["skt"] = "Sakata", ["sku"] = "Sakao", ["skv"] = "Skou", ["skw"] = "Skepi Creole Dutch", ["skx"] = "Seko Padang", ["sky"] = "Sikaiana", ["skz"] = "Sekar", ["sl"] = "Slovene", ["sla-pro"] = "Proto-Slavic", ["slc"] = "Saliba (Colombia)", ["sld"] = "Sisaala", ["sle"] = "Sholaga", ["slf"] = "Swiss-Italian Sign Language", ["slg"] = "Selungai Murut", ["slj"] = "Salumá", ["sll"] = "Salt-Yui", ["slm"] = "Pangutaran Sama", ["sln"] = "Salinan", ["slp"] = "Lamaholot", ["slr"] = "Salar", ["sls"] = "Singapore Sign Language", ["slt"] = "Sila", ["slu"] = "Selaru", ["slw"] = "Sialum", ["slx"] = "Salampasu", ["sly"] = "Selayar", ["slz"] = "Ma'ya", ["sm"] = "Samoan", ["sma"] = "Southern Sami", ["smb"] = "Simbari", ["smc"] = "Som", ["smd"] = "Sama", ["smf"] = "Auwe", ["smg"] = "Simbali", ["smh"] = "Samei", ["smi-pro"] = "Proto-Samic", ["smj"] = "Lule Sami", ["smk"] = "Bolinao", ["sml"] = "Central Sama", ["smm"] = "Musasa", ["smn"] = "Inari Sami", ["smp"] = "Samaritan Hebrew", ["smq"] = "Samo", ["smr"] = "Simeulue", ["sms"] = "Skolt Sami", ["smt"] = "Simte", ["smu"] = "Somray", ["smv"] = "Samvedi", ["smw"] = "Sumbawa", ["smx"] = "Samba", ["smy"] = "Semnani", ["smz"] = "Simeku", ["sn"] = "Shona", ["snb"] = "Sebuyau", ["snc"] = "Sinaugoro", ["sne"] = "Bau Bidayuh", ["snf"] = "Noon", ["sng"] = "Sanga (Congo)", ["sni"] = "Sensi", ["snj"] = "Riverain Sango", ["snk"] = "Soninke", ["snl"] = "Sangil", ["snm"] = "Southern Ma'di", ["snn"] = "Siona", ["snp"] = "Siane", ["snq"] = "Sangu (Gabon)", ["snr"] = "Sihan", ["sns"] = "Nahavaq", ["snu"] = "Senggi", ["snv"] = "Sa'ban", ["snw"] = "Selee", ["snx"] = "Sam", ["sny"] = "Saniyo-Hiyewe", ["snz"] = "Kou", ["so"] = "Somali", ["soa"] = "Thai Song", ["sob"] = "Sobei", ["soc"] = "Soko", ["sod"] = "Songoora", ["soe"] = "Songomeno", ["sog"] = "Sogdian", ["soh"] = "Aka (Sudan)", ["soi"] = "Sonha", ["sok"] = "Sokoro", ["sol"] = "Solos", ["son-pro"] = "Proto-Songhay", ["soo"] = "Nsong", ["sop"] = "Songe", ["soq"] = "Kanasi", ["sor"] = "Somrai", ["sos"] = "Seenku", ["sou"] = "Southern Thai", ["sov"] = "Sonsorolese", ["sow"] = "Sowanda", ["sox"] = "Swo", ["soy"] = "Miyobe", ["soz"] = "Temi", ["spb"] = "Sepa (Indonesia)", ["spc"] = "Sapé", ["spd"] = "Saep", ["spe"] = "Sepa (New Guinea)", ["spg"] = "Sian", ["spi"] = "Saponi", ["spk"] = "Sengo", ["spl"] = "Selepet", ["spm"] = "Sepen", ["spn"] = "Sanapaná", ["spo"] = "Spokane", ["spp"] = "Supyire", ["spr"] = "Saparua", ["sps"] = "Saposa", ["spt"] = "Spiti Bhoti", ["spu"] = "Sapuan", ["spv"] = "Sambalpuri", ["spx"] = "South Picene", ["spy"] = "Sabaot", ["sq"] = "Albanian", ["sqa"] = "Shama-Sambuga", ["sqh"] = "Shau", ["sqj-pro"] = "Proto-Albanian", ["sqk"] = "Albanian Sign Language", ["sqm"] = "Suma", ["sqn"] = "Susquehannock", ["sqo"] = "Sorkhei", ["sqq"] = "Sou", ["sqr"] = "Siculo-Arabic", ["sqs"] = "Sri Lankan Sign Language", ["sqt"] = "Soqotri", ["squ"] = "Squamish", ["sra"] = "Saruga", ["srb"] = "Sora", ["sre"] = "Sara", ["srf"] = "Nafi", ["srg"] = "Sulod", ["srh"] = "Sarikoli", ["sri"] = "Siriano", ["srk"] = "Serudung Murut", ["srl"] = "Isirawa", ["srm"] = "Saramaccan", ["srn"] = "Sranan Tongo", ["srq"] = "Sirionó", ["srr"] = "Serer", ["srs"] = "Tsuut'ina", ["srt"] = "Sauri", ["sru"] = "Suruí", ["srv"] = "Waray Sorsogon", ["srw"] = "Serua", ["srx"] = "Sirmauri", ["sry"] = "Sera", ["srz"] = "Shahmirzadi", ["ss"] = "Swazi", ["ssa-klk-pro"] = "Proto-Kuliak", ["ssa-kom-pro"] = "Proto-Koman", ["ssa-pro"] = "Proto-Nilo-Saharan", ["ssb"] = "Southern Sama", ["ssc"] = "Suba-Simbiti", ["ssd"] = "Siroi", ["sse"] = "Balangingi", ["ssf"] = "Thao", ["ssg"] = "Seimat", ["ssh"] = "Shihhi Arabic", ["ssi"] = "Sansi", ["ssj"] = "Sausi", ["ssk"] = "Sunam", ["ssl"] = "Western Sisaala", ["ssm"] = "Semnam", ["sso"] = "Sissano", ["ssp"] = "Spanish Sign Language", ["ssq"] = "So'a", ["ssr"] = "Swiss-French Sign Language", ["sss"] = "Sô", ["sst"] = "Sinasina", ["ssu"] = "Susuami", ["ssv"] = "Shark Bay", ["ssx"] = "Samberigi", ["ssy"] = "Saho", ["ssz"] = "Sengseng", ["st"] = "Sotho", ["stb"] = "Northern Subanen", ["std"] = "Sentinelese", ["ste"] = "Liana-Seti", ["stf"] = "Seta", ["stg"] = "Trieng", ["sth"] = "Shelta", ["sti"] = "Bulo Stieng", ["stj"] = "Matya Samo", ["stk"] = "Arammba", ["stm"] = "Setaman", ["stn"] = "Owa", ["sto"] = "Stoney", ["stp"] = "Southeastern Tepehuan", ["stq"] = "Saterland Frisian", ["str"] = "Saanich", ["sts"] = "Shumashti", ["stt"] = "Budeh Stieng", ["stu"] = "Samtao", ["stv"] = "Silt'e", ["stw"] = "Satawalese", ["sty"] = "Siberian Tatar", ["su"] = "Sundanese", ["sua"] = "Sulka", ["sub"] = "Suku", ["suc"] = "Western Subanon", ["sue"] = "Suena", ["sug"] = "Suganga", ["sui"] = "Suki", ["suk"] = "Sukuma", ["suo"] = "Bouni", ["suq"] = "Suri", ["sur"] = "Mwaghavul", ["sus"] = "Susu", ["sut"] = "Subtiaba", ["suv"] = "Puroik", ["suw"] = "Sumbwa", ["sux"] = "Sumerian", ["suy"] = "Suyá", ["suz"] = "Sunwar", ["sv"] = "Swedish", ["sva"] = "Svan", ["svb"] = "Ulau-Suain", ["svc"] = "Vincentian Creole English", ["sve"] = "Serili", ["svk"] = "Slovakian Sign Language", ["svm"] = "Slavomolisano", ["svs"] = "Savosavo", ["svx"] = "Skalvian", ["sw"] = "Swahili", ["swb"] = "Maore Comorian", ["swf"] = "Sere", ["swg"] = "Swabian", ["swi"] = "Sui", ["swj"] = "Sira", ["swl"] = "Swedish Sign Language", ["swm"] = "Samosa", ["swn"] = "Sokna", ["swo"] = "Shanenawa", ["swp"] = "Suau", ["swq"] = "Sharwa", ["swr"] = "Saweru", ["sws"] = "Seluwasan", ["swt"] = "Sawila", ["swu"] = "Suwawa", ["sww"] = "Sowa", ["swx"] = "Suruahá", ["swy"] = "Sarua", ["sxb"] = "Suba", ["sxc"] = "Sicanian", ["sxe"] = "Sighu", ["sxg"] = "Shixing", ["sxk"] = "Southern Kalapuya", ["sxl"] = "Selonian", ["sxm"] = "Samre", ["sxn"] = "Sangir", ["sxo"] = "Sorothaptic", ["sxr"] = "Saaroa", ["sxs"] = "Sasaru", ["sxw"] = "Saxwe Gbe", ["sya"] = "Siang", ["syb"] = "Central Subanen", ["syc"] = "Classical Syriac", ["syd-pro"] = "Proto-Samoyedic", ["syi"] = "Seki", ["syk"] = "Sukur", ["syl"] = "Sylheti", ["sym"] = "Maya Samo", ["syn"] = "Senaya", ["syo"] = "Suoy", ["sys"] = "Sinyar", ["syw"] = "Kagate", ["syx"] = "Osamayi", ["syy"] = "Al-Sayyid Bedouin Sign Language", ["sza"] = "Semelai", ["szb"] = "Ngalum", ["szc"] = "Semaq Beri", ["szd"] = "Seru", ["sze"] = "Seze", ["szg"] = "Sengele", ["szl"] = "Silesian", ["szn"] = "Sula", ["szp"] = "Suabo", ["szs"] = "Solomon Islands Sign Language", ["szv"] = "Isubu", ["szw"] = "Sawai", ["szy"] = "Sakizaya", ["ta"] = "Tamil", ["taa"] = "Lower Tanana", ["tab"] = "Tabasaran", ["tac"] = "Lowland Tarahumara", ["tad"] = "Tause", ["tae"] = "Tariana", ["taf"] = "Tapirapé", ["tag"] = "Tagoi", ["tai-pro"] = "Proto-Tai", ["tai-swe-pro"] = "Proto-Southwestern Tai", ["taj"] = "Eastern Tamang", ["tak"] = "Tala", ["tal"] = "Tal", ["tan"] = "Tangale", ["tao"] = "Yami", ["tap"] = "Taabwa", ["tar"] = "Central Tarahumara", ["tas"] = "Tây Bồi", ["tau"] = "Upper Tanana", ["tav"] = "Tatuyo", ["taw"] = "Tai", ["tax"] = "Tamki", ["tay"] = "Atayal", ["taz"] = "Tocho", ["tba"] = "Aikanã", ["tbc"] = "Takia", ["tbd"] = "Kaki Ae", ["tbe"] = "Tanimbili", ["tbf"] = "Mandara", ["tbg"] = "North Tairora", ["tbh"] = "Thurawal", ["tbi"] = "Gaam", ["tbj"] = "Tiang", ["tbk"] = "Calamian Tagbanwa", ["tbl"] = "Tboli", ["tbm"] = "Tagbu", ["tbn"] = "Barro Negro Tunebo", ["tbo"] = "Tawala", ["tbp"] = "Taworta", ["tbq-bdg-pro"] = "Proto-Bodo-Garo", ["tbq-blg"] = "Bailang", ["tbq-brm-pro"] = "Proto-Burmish", ["tbq-gkh"] = "Gokhy", ["tbq-kuk-pro"] = "Proto-Kuki-Chin", ["tbq-lal-pro"] = "Proto-Lalo", ["tbq-laz"] = "Laze", ["tbq-lob-pro"] = "Proto-Lolo-Burmese", ["tbq-lol-pro"] = "Proto-Loloish", ["tbq-mil"] = "Milang", ["tbq-mor"] = "Moran", ["tbq-ngo"] = "Ngochang", ["tbr"] = "Tumtum", ["tbs"] = "Tanguat", ["tbt"] = "Kitembo", ["tbu"] = "Tubar", ["tbv"] = "Tobo", ["tbw"] = "Aborlan Tagbanwa", ["tbx"] = "Kapin", ["tby"] = "Tabaru", ["tbz"] = "Ditammari", ["tca"] = "Ticuna", ["tcb"] = "Tanacross", ["tcc"] = "Datooga", ["tcd"] = "Tafi", ["tce"] = "Southern Tutchone", ["tcf"] = "Malinaltepec Tlapanec", ["tcg"] = "Tamagario", ["tch"] = "Turks and Caicos Creole English", ["tci"] = "Wára", ["tck"] = "Tchitchege", ["tcl"] = "Taman (Myanmar)", ["tcm"] = "Tanahmerah", ["tco"] = "Taungyo", ["tcp"] = "Tawr Chin", ["tcq"] = "Kaiy", ["tcs"] = "Torres Strait Creole", ["tct"] = "T'en", ["tcu"] = "Southeastern Tarahumara", ["tcw"] = "Tecpatlán Totonac", ["tcx"] = "Toda", ["tcy"] = "Tulu", ["tcz"] = "Thado Chin", ["tda"] = "Tagdal", ["tdb"] = "Panchpargania", ["tdc"] = "Emberá-Tadó", ["tdd"] = "Tai Nüa", ["tde"] = "Tiranige Diga Dogon", ["tdf"] = "Talieng", ["tdg"] = "Western Tamang", ["tdh"] = "Thulung", ["tdi"] = "Tomadino", ["tdj"] = "Tajio", ["tdk"] = "Tambas", ["tdl"] = "Sur", ["tdm"] = "Taruma", ["tdn"] = "Tondano", ["tdo"] = "Teme", ["tdq"] = "Tita", ["tdr"] = "Todrah", ["tds"] = "Doutai", ["tdt"] = "Tetun Dili", ["tdu"] = "Tempasuk Dusun", ["tdv"] = "Toro", ["tdy"] = "Tadyawan", ["te"] = "Telugu", ["tea"] = "Temiar", ["teb"] = "Tetete", ["tec"] = "Terik", ["ted"] = "Tepo Krumen", ["tee"] = "Huehuetla Tepehua", ["tef"] = "Teressa", ["teg"] = "Teke-Tege", ["teh"] = "Tehuelche", ["tei"] = "Torricelli", ["tek"] = "Ibali Teke", ["tem"] = "Temne", ["ten"] = "Tama (Colombia)", ["teo"] = "Ateso", ["tep"] = "Tepecano", ["teq"] = "Temein", ["ter"] = "Tereno", ["tes"] = "Tengger", ["tet"] = "Tetum", ["teu"] = "Soo", ["tev"] = "Teor", ["tew"] = "Tewa", ["tex"] = "Tennet", ["tey"] = "Tulishi", ["tez"] = "Tetserret", ["tfi"] = "Tofin Gbe", ["tfn"] = "Dena'ina", ["tfo"] = "Tefaro", ["tfr"] = "Teribe", ["tft"] = "Ternate", ["tg"] = "Tajik", ["tga"] = "Sagalla", ["tgb"] = "Tobilung", ["tgc"] = "Tigak", ["tgd"] = "Ciwogai", ["tge"] = "Eastern Gorkha Tamang", ["tgf"] = "Chali", ["tgh"] = "Tobagonian Creole English", ["tgi"] = "Lawunuia", ["tgn"] = "Tandaganon", ["tgo"] = "Sudest", ["tgp"] = "Tangoa", ["tgq"] = "Tring", ["tgr"] = "Tareng", ["tgs"] = "Nume", ["tgt"] = "Central Tagbanwa", ["tgu"] = "Tanggu", ["tgv"] = "Tingui-Boto", ["tgw"] = "Tagwana", ["tgx"] = "Tagish", ["tgy"] = "Togoyo", ["th"] = "Thai", ["thc"] = "Tai Hang Tong", ["thd"] = "Kuuk Thaayorre", ["the"] = "Chitwania Tharu", ["thf"] = "Thangmi", ["thh"] = "Northern Tarahumara", ["thi"] = "Tai Long", ["thk"] = "Tharaka", ["thl"] = "Dangaura Tharu", ["thm"] = "Thavung", ["thn"] = "Thachanadan", ["thp"] = "Thompson", ["thq"] = "Kochila Tharu", ["thr"] = "Rana Tharu", ["ths"] = "Thakali", ["tht"] = "Tahltan", ["thu"] = "Thuri", ["thy"] = "Tha", ["ti"] = "Tigrinya", ["tic"] = "Tira", ["tif"] = "Tifal", ["tig"] = "Tigre", ["tih"] = "Timugon Murut", ["tii"] = "Tiene", ["tij"] = "Tilung", ["tik"] = "Tikar", ["til"] = "Tillamook", ["tim"] = "Timbe", ["tin"] = "Tindi", ["tio"] = "Teop", ["tip"] = "Trimuris", ["tiq"] = "Tiéfo", ["tis"] = "Masadiit Itneg", ["tit"] = "Tinigua", ["tiu"] = "Adasen", ["tiv"] = "Tiv", ["tiw"] = "Tiwi", ["tix"] = "Southern Tiwa", ["tiy"] = "Tiruray", ["tiz"] = "Tai Hongjin", ["tja"] = "Tajuasohn", ["tjg"] = "Tunjung", ["tji"] = "Northern Tujia", ["tjl"] = "Tai Laing", ["tjm"] = "Timucua", ["tjn"] = "Tonjon", ["tjs"] = "Southern Tujia", ["tju"] = "Tjurruru", ["tjw"] = "Chaap Wuurong", ["tk"] = "Turkmen", ["tka"] = "Truká", ["tkb"] = "Buksa", ["tkd"] = "Tukudede", ["tke"] = "Takwane", ["tkf"] = "Tukumanféd", ["tkl"] = "Tokelauan", ["tkm"] = "Takelma", ["tkn"] = "Tokunoshima", ["tkp"] = "Tikopia", ["tkq"] = "Tee", ["tkr"] = "Tsakhur", ["tks"] = "Ramandi", ["tkt"] = "Kathoriya Tharu", ["tku"] = "Upper Necaxa Totonac", ["tkv"] = "Mur Pano", ["tkw"] = "Teanu", ["tkx"] = "Tangko", ["tkz"] = "Takua", ["tl"] = "Tagalog", ["tla"] = "Southwestern Tepehuan", ["tlb"] = "Tobelo", ["tlc"] = "Misantla Totonac", ["tld"] = "Talaud", ["tlf"] = "Telefol", ["tlg"] = "Tofanma", ["tlh"] = "Klingon", ["tli"] = "Tlingit", ["tlj"] = "Talinga-Bwisi", ["tlk"] = "Taloki", ["tll"] = "Tetela", ["tlm"] = "Tolomako", ["tln"] = "Talondo'", ["tlo"] = "Talodi", ["tlp"] = "Filomena Mata-Coahuitlán Totonac", ["tlq"] = "Tai Loi", ["tlr"] = "Talise", ["tls"] = "Tambotalo", ["tlt"] = "Teluti", ["tlu"] = "Tulehu", ["tlv"] = "Taliabu", ["tlx"] = "Khehek", ["tly"] = "Talysh", ["tma"] = "Tama (Chad)", ["tmb"] = "Avava", ["tmc"] = "Tumak", ["tmd"] = "Haruai", ["tme"] = "Tremembé", ["tmf"] = "Toba-Maskoy", ["tmg"] = "Ternateño", ["tmh"] = "Tuareg", ["tmi"] = "Tutuba", ["tmj"] = "Samarokena", ["tml"] = "Tamnim Citak", ["tmm"] = "Tai Thanh", ["tmn"] = "Taman (Indonesia)", ["tmo"] = "Temoq", ["tmq"] = "Tumleo", ["tms"] = "Tima", ["tmt"] = "Tasmate", ["tmu"] = "Iau", ["tmv"] = "Motembo", ["tmy"] = "Tami", ["tmz"] = "Tamanaku", ["tn"] = "Tswana", ["tna"] = "Tacana", ["tnb"] = "Western Tunebo", ["tnc"] = "Tanimuca-Retuarã", ["tnd"] = "Angosturas Tunebo", ["tne"] = "Tinoc Kallahan", ["tng"] = "Tobanga", ["tnh"] = "Maiani", ["tni"] = "Tandia", ["tnk"] = "Kwamera", ["tnl"] = "Lenakel", ["tnm"] = "Tabla", ["tnn"] = "North Tanna", ["tno"] = "Toromono", ["tnp"] = "Whitesands", ["tnq"] = "Taíno", ["tnr"] = "Bedik", ["tns"] = "Tenis", ["tnt"] = "Tontemboan", ["tnu"] = "Tay Khang", ["tnv"] = "Tanchangya", ["tnw"] = "Tonsawang", ["tnx"] = "Tanema", ["tny"] = "Tongwe", ["tnz"] = "Ten'edn", ["to"] = "Tongan", ["tob"] = "Toba", ["toc"] = "Coyutla Totonac", ["tod"] = "Toma", ["tof"] = "Gizrra", ["tog"] = "Tonga (Malawi)", ["toh"] = "Tonga (Mozambique)", ["toi"] = "Tonga (Zambia)", ["toj"] = "Tojolabal", ["tok"] = "Toki Pona", ["tol"] = "Tolowa", ["tom"] = "Tombulu", ["too"] = "Xicotepec de Juárez Totonac", ["top"] = "Papantla Totonac", ["toq"] = "Toposa", ["tor"] = "Togbo-Vara Banda", ["tos"] = "Highland Totonac", ["tou"] = "Tho", ["tov"] = "Upper Taromi", ["tow"] = "Jemez", ["tox"] = "Tobian", ["toy"] = "Topoiyo", ["toz"] = "To", ["tpa"] = "Taupota", ["tpc"] = "Azoyú Me'phaa", ["tpe"] = "Tippera", ["tpf"] = "Tarpia", ["tpg"] = "Kula", ["tpi"] = "Tok Pisin", ["tpj"] = "Tapieté", ["tpk"] = "Tupinikin", ["tpl"] = "Tlacoapa Me'phaa", ["tpm"] = "Tampulma", ["tpn"] = "Tupinambá", ["tpo"] = "Tai Pao", ["tpp"] = "Pisaflores Tepehua", ["tpq"] = "Tukpa", ["tpr"] = "Tuparí", ["tpt"] = "Tlachichilco Tepehua", ["tpu"] = "Tampuan", ["tpv"] = "Tanapag", ["tpw"] = "Old Tupi", ["tpx"] = "Acatepec Me'phaa", ["tpy"] = "Trumai", ["tpz"] = "Tinputz", ["tqb"] = "Tembé", ["tql"] = "Lehali", ["tqm"] = "Turumsa", ["tqn"] = "Tenino", ["tqo"] = "Toaripi", ["tqp"] = "Tomoip", ["tqq"] = "Tunni", ["tqr"] = "Torona", ["tqt"] = "Western Totonac", ["tqu"] = "Touo", ["tqw"] = "Tonkawa", ["tr"] = "Turkish", ["tra"] = "Tirahi", ["trb"] = "Terebu", ["trc"] = "Copala Triqui", ["trd"] = "Turi", ["tre"] = "East Tarangan", ["trf"] = "Trinidadian Creole English", ["trg"] = "Lishán Didán", ["trh"] = "Turaka", ["tri"] = "Trió", ["trj"] = "Toram", ["trk-dkh"] = "Dukhan", ["trk-eog"] = "Early Old Oghuz", ["trk-oat"] = "Old Anatolian Turkish", ["trk-pro"] = "Proto-Turkic", ["trl"] = "Traveller Scottish", ["trm"] = "Tregami", ["trn"] = "Trinitario", ["tro"] = "Tarao", ["trp"] = "Kokborok", ["trq"] = "San Martín Itunyoso Triqui", ["trr"] = "Taushiro", ["trs"] = "Chicahuaxtla Triqui", ["trt"] = "Tunggare", ["tru"] = "Turoyo", ["trv"] = "Taroko", ["trw"] = "Torwali", ["trx"] = "Tringgus", ["try"] = "Turung", ["trz"] = "Torá", ["ts"] = "Tsonga", ["tsa"] = "Tsaangi", ["tsb"] = "Tsamai", ["tsc"] = "Tswa", ["tsd"] = "Tsakonian", ["tse"] = "Tunisian Sign Language", ["tsg"] = "Tausug", ["tsh"] = "Tsuvan", ["tsi"] = "Tsimshian", ["tsj"] = "Tshangla", ["tsl"] = "Ts'ün-Lao", ["tsm"] = "Turkish Sign Language", ["tsp"] = "Northern Toussian", ["tsq"] = "Thai Sign Language", ["tsr"] = "Akei", ["tss"] = "Taiwan Sign Language", ["tsu"] = "Tsou", ["tsv"] = "Tsogo", ["tsw"] = "Tsishingini", ["tsx"] = "Mubami", ["tsy"] = "Tebul Sign Language", ["tt"] = "Tatar", ["tta"] = "Tutelo", ["ttb"] = "Gaa", ["ttc"] = "Tektiteko", ["ttd"] = "Tauade", ["tte"] = "Bwanabwana", ["ttf"] = "Tuotomb", ["ttg"] = "Tutong", ["tth"] = "Upper Ta'oih", ["tti"] = "Tobati", ["ttj"] = "Tooro", ["ttk"] = "Totoro", ["ttl"] = "Totela", ["ttm"] = "Northern Tutchone", ["ttn"] = "Towei", ["tto"] = "Lower Ta'oih", ["ttp"] = "Tombelala", ["ttr"] = "Tera", ["tts"] = "Isan", ["ttt"] = "Tat", ["ttu"] = "Torau", ["ttv"] = "Titan", ["ttw"] = "Long Wat", ["tty"] = "Sikaritai", ["ttz"] = "Tsum", ["tua"] = "Wiarumus", ["tub"] = "Tübatulabal", ["tuc"] = "Mutu", ["tud"] = "Tuxá", ["tue"] = "Tuyuca", ["tuf"] = "Central Tunebo", ["tug"] = "Tunia", ["tuh"] = "Taulil", ["tui"] = "Tupuri", ["tuj"] = "Tugutil", ["tul"] = "Tula", ["tum"] = "Tumbuka", ["tun"] = "Tunica", ["tuo"] = "Tucano", ["tup-gua-pro"] = "Proto-Tupi-Guarani", ["tup-kab"] = "Kabishiana", ["tup-pro"] = "Proto-Tupian", ["tuq"] = "Tedaga", ["tus"] = "Tuscarora", ["tuu"] = "Tututni", ["tuv"] = "Turkana", ["tuw-alk"] = "Alchuka", ["tuw-bal"] = "Bala", ["tuw-kkl"] = "Kyakala", ["tuw-kli"] = "Kili", ["tuw-pro"] = "Proto-Tungusic", ["tuw-sol"] = "Solon", ["tux"] = "Tuxináwa", ["tuy"] = "Tugen", ["tuz"] = "Turka", ["tva"] = "Vaghua", ["tvd"] = "Tsuvadi", ["tve"] = "Te'un", ["tvk"] = "Southeast Ambrym", ["tvl"] = "Tuvaluan", ["tvm"] = "Tela-Masbuar", ["tvn"] = "Tavoyan", ["tvo"] = "Tidore", ["tvs"] = "Taveta", ["tvt"] = "Tutsa Naga", ["tvu"] = "Tunen", ["tvw"] = "Sedoa", ["tvx"] = "Taivoan", ["tvy"] = "Timor Pidgin", ["twa"] = "Twana", ["twb"] = "Western Tawbuid", ["twc"] = "Teshenawa", ["twe"] = "Teiwa", ["twf"] = "Taos", ["twg"] = "Tereweng", ["twh"] = "Tai Dón", ["twm"] = "Tawang Monpa", ["twn"] = "Twendi", ["two"] = "Tswapong", ["twp"] = "Ere", ["twq"] = "Tasawaq", ["twr"] = "Southwestern Tarahumara", ["twt"] = "Turiwára", ["twu"] = "Termanu", ["tww"] = "Tuwari", ["twy"] = "Tawoyan", ["txa"] = "Tombonuo", ["txb"] = "Tocharian B", ["txc"] = "Tsetsaut", ["txe"] = "Totoli", ["txg"] = "Tangut", ["txh"] = "Thracian", ["txi"] = "Ikpeng", ["txj"] = "Tarjumo", ["txm"] = "Tomini", ["txn"] = "West Tarangan", ["txo"] = "Toto", ["txq"] = "Tii", ["txr"] = "Tartessian", ["txs"] = "Tonsea", ["txt"] = "Citak", ["txu"] = "Kayapó", ["txx"] = "Tatana", ["ty"] = "Tahitian", ["tya"] = "Tauya", ["tye"] = "Kyenga", ["tyh"] = "O'du", ["tyi"] = "Teke-Tsaayi", ["tyj"] = "Tai Do", ["tyl"] = "Thu Lao", ["tyn"] = "Kombai", ["typ"] = "Kuku-Thaypan", ["tyr"] = "Tai Daeng", ["tys"] = "Sapa", ["tyt"] = "Tày Tac", ["tyu"] = "Kua", ["tyv"] = "Tuvan", ["tyx"] = "Teke-Tyee", ["tyz"] = "Tày", ["tza"] = "Tanzanian Sign Language", ["tzh"] = "Tzeltal", ["tzj"] = "Tz'utujil", ["tzl"] = "Talossan", ["tzm"] = "Central Atlas Tamazight", ["tzn"] = "Tugun", ["tzo"] = "Tzotzil", ["tzx"] = "Tabriak", ["uam"] = "Uamué", ["uan"] = "Kuan", ["uar"] = "Tairuma", ["uba"] = "Ubang", ["ubi"] = "Ubi", ["ubl"] = "Buhi'non Bikol", ["ubr"] = "Ubir", ["ubu"] = "Umbu-Ungu", ["uby"] = "Ubykh", ["uda"] = "Uda", ["ude"] = "Udihe", ["udg"] = "Muduga", ["udi"] = "Udi", ["udj"] = "Ujir", ["udl"] = "Uldeme", ["udm"] = "Udmurt", ["udu"] = "Uduk", ["ues"] = "Kioko", ["ufi"] = "Ufim", ["ug"] = "Uyghur", ["uga"] = "Ugaritic", ["ugb"] = "Kuku-Ugbanh", ["uge"] = "Ughele", ["ugn"] = "Ugandan Sign Language", ["ugo"] = "Gong", ["ugy"] = "Uruguayan Sign Language", ["uha"] = "Uhami", ["uhn"] = "Damal", ["uis"] = "Uisai", ["uiv"] = "Iyive", ["uji"] = "Tanjijili", ["uk"] = "Ukrainian", ["uka"] = "Kaburi", ["ukg"] = "Ukuriguma", ["ukh"] = "Ukhwejo", ["ukk"] = "Muak Sa-aak", ["ukl"] = "Ukrainian Sign Language", ["ukp"] = "Ukpe-Bayobiri", ["ukq"] = "Ukwa", ["uks"] = "Kaapor Sign Language", ["uku"] = "Ukue", ["ukw"] = "Ukwuani-Aboh-Ndoni", ["uky"] = "Kuuk Yak", ["ula"] = "Fungwa", ["ulb"] = "Olukumi", ["ulc"] = "Ulch", ["ule"] = "Lule", ["ulf"] = "Afra", ["uli"] = "Ulithian", ["ulk"] = "Meriam", ["ull"] = "Ullatan", ["ulm"] = "Ulumanda'", ["uln"] = "Unserdeutsch", ["ulu"] = "Uma' Lung", ["ulw"] = "Ulwa (Nicaragua)", ["uma"] = "Umatilla", ["umb"] = "Umbundu", ["umc"] = "Marrucinian", ["umd"] = "Umbindhamu", ["umg"] = "Umbuygamu", ["umi"] = "Ukit", ["umm"] = "Umon", ["umn"] = "Makyan Naga", ["umo"] = "Umotína", ["ump"] = "Umpila", ["umr"] = "Umbugarla", ["ums"] = "Pendau", ["umu"] = "Munsee", ["una"] = "North Watut", ["und"] = "Undetermined", ["une"] = "Uneme", ["ung"] = "Ngarinyin", ["uni"] = "Uni", ["unk"] = "Enawené-Nawé", ["unm"] = "Unami", ["unn"] = "Kurnai", ["unr"] = "Mundari", ["unu"] = "Unubahe", ["unx"] = "Munda", ["unz"] = "Unde Kaili", ["uok"] = "Uokha", ["uon"] = "Kulon", ["upi"] = "Umeda", ["upv"] = "Northeast Malakula", ["ur"] = "Urdu", ["ura"] = "Urarina", ["urb"] = "Urubú-Kaapor", ["urc"] = "Urningangg", ["ure"] = "Uru", ["urf"] = "Uradhi", ["urg"] = "Urigina", ["urh"] = "Urhobo", ["uri"] = "Urim", ["urj-fin-pro"] = "Proto-Finnic", ["urj-koo"] = "Old Komi", ["urj-kuk"] = "Kukkuzi", ["urj-kya"] = "Komi-Yazva", ["urj-mdv-pro"] = "Proto-Mordvinic", ["urj-prm-pro"] = "Proto-Permic", ["urj-pro"] = "Proto-Uralic", ["urj-ugr-pro"] = "Proto-Ugric", ["urk"] = "Urak Lawoi'", ["url"] = "Urali", ["urm"] = "Urapmin", ["urn"] = "Uruangnirin", ["uro"] = "Ura (New Guinea)", ["urp"] = "Uru-Pa-In", ["urr"] = "Löyöp", ["urt"] = "Urat", ["uru"] = "Urumi", ["urv"] = "Uruava", ["urw"] = "Sop", ["urx"] = "Urimo", ["ury"] = "Orya", ["urz"] = "Uru-Eu-Wau-Wau", ["usa"] = "Usarufa", ["ush"] = "Ushojo", ["usi"] = "Usui", ["usk"] = "Usaghade", ["usp"] = "Uspanteco", ["uss"] = "Saare", ["usu"] = "Uya", ["uta"] = "Otank", ["ute"] = "Ute", ["uth"] = "Hun", ["utp"] = "Aba", ["utr"] = "Etulo", ["utu"] = "Utu", ["uum"] = "Urum", ["uur"] = "Ura (Vanuatu)", ["uuu"] = "U", ["uve"] = "West Uvean", ["uvh"] = "Uri", ["uvl"] = "Lote", ["uwa"] = "Kuku-Uwanh", ["uya"] = "Doko-Uyanga", ["uz"] = "Uzbek", ["vaa"] = "Vaagri Booli", ["vae"] = "Vale", ["vag"] = "Vagla", ["vah"] = "Varhadi", ["vai"] = "Vai", ["vaj"] = "Sekele", ["val"] = "Vehes", ["vam"] = "Vanimo", ["van"] = "Valman", ["vao"] = "Vao", ["vap"] = "Vaiphei", ["var"] = "Huarijio", ["vas"] = "Vasavi", ["vau"] = "Vanuma", ["vav"] = "Varli", ["vay"] = "Vayu", ["vbb"] = "Southeast Babar", ["vbk"] = "Southwestern Bontoc", ["ve"] = "Venda", ["vec"] = "Venetan", ["ved"] = "Veddah", ["vem"] = "Vemgo-Mabas", ["veo"] = "Ventureño", ["vep"] = "Veps", ["ver"] = "Mom Jango", ["vgr"] = "Vaghri", ["vgt"] = "Flemish Sign Language", ["vi"] = "Vietnamese", ["vic"] = "Virgin Islands Creole", ["vid"] = "Vidunda", ["vif"] = "Vili", ["vig"] = "Viemo", ["vil"] = "Vilela", ["vis"] = "Vishavan", ["vit"] = "Viti", ["viv"] = "Iduna", ["vjk"] = "Bajjika", ["vka"] = "Kariyarra", ["vki"] = "Ija-Zuba", ["vkj"] = "Kujarge", ["vkk"] = "Kaur", ["vkl"] = "Kulisusu", ["vkm"] = "Kamakan", ["vko"] = "Kodeoha", ["vkp"] = "Korlai Creole Portuguese", ["vkt"] = "Tenggarong Kutai Malay", ["vku"] = "Kurrama", ["vlp"] = "Valpei", ["vls"] = "West Flemish", ["vma"] = "Martuthunira", ["vmb"] = "Mbabaram", ["vmc"] = "Juxtlahuaca Mixtec", ["vmd"] = "Mudu Koraga", ["vme"] = "East Masela", ["vmf"] = "East Franconian", ["vmg"] = "Vinitiri", ["vmh"] = "Maraghei", ["vmi"] = "Miwa", ["vmj"] = "Ixtayutla Mixtec", ["vmk"] = "Makhuwa-Shirima", ["vml"] = "Malgana", ["vmm"] = "Mitlatongo Mixtec", ["vmp"] = "Soyaltepec Mazatec", ["vmq"] = "Soyaltepec Mixtec", ["vmr"] = "Marenje", ["vmu"] = "Muluridyi", ["vmv"] = "Valley Maidu", ["vmw"] = "Makhuwa", ["vmx"] = "Tamazola Mixtec", ["vmy"] = "Ayautla Mazatec", ["vmz"] = "Mazatlán Mazatec", ["vnk"] = "Lovono", ["vnm"] = "Neve'ei", ["vnp"] = "Vunapu", ["vo"] = "Volapük", ["vor"] = "Voro", ["vot"] = "Votic", ["vra"] = "Vera'a", ["vro"] = "Võro", ["vrs"] = "Varisi", ["vrt"] = "Burmbar", ["vsi"] = "Moldova Sign Language", ["vsl"] = "Venezuelan Sign Language", ["vsv"] = "Valencian Sign Language", ["vto"] = "Vitou", ["vum"] = "Vumbu", ["vun"] = "Vunjo", ["vut"] = "Vute", ["vwa"] = "Awa (China)", ["wa"] = "Walloon", ["waa"] = "Walla Walla", ["wab"] = "Wab", ["wac"] = "Wasco-Wishram", ["wad"] = "Wandamen", ["waf"] = "Wakoná", ["wag"] = "Wa'ema", ["wah"] = "Watubela", ["waj"] = "Waffa", ["wal"] = "Wolaytta", ["wam"] = "Massachusett", ["wan"] = "Wan", ["wao"] = "Wappo", ["wap"] = "Wapishana", ["waq"] = "Wageman", ["war"] = "Waray-Waray", ["was"] = "Washo", ["wat"] = "Kaninuwa", ["wau"] = "Wauja", ["wav"] = "Waka", ["waw"] = "Waiwai", ["wax"] = "Watam", ["way"] = "Wayana", ["waz"] = "Wampur", ["wba"] = "Warao", ["wbb"] = "Wabo", ["wbe"] = "Waritai", ["wbf"] = "Wara", ["wbh"] = "Wanda", ["wbi"] = "Wanji", ["wbj"] = "Alagwa", ["wbk"] = "Waigali", ["wbl"] = "Wakhi", ["wbm"] = "Wa", ["wbp"] = "Warlpiri", ["wbq"] = "Waddar", ["wbr"] = "Wagdi", ["wbt"] = "Wanman", ["wbv"] = "Wajarri", ["wbw"] = "Woi", ["wca"] = "Yanomam", ["wci"] = "Waci Gbe", ["wdd"] = "Wandji", ["wdg"] = "Wadaginam", ["wdj"] = "Wadjiginy", ["wdt"] = "Wendat", ["wdu"] = "Wadjigu", ["wdy"] = "Wadjabangayi", ["wea"] = "Wewaw", ["wec"] = "Wè Western", ["wed"] = "Wedau", ["weh"] = "Weh", ["wei"] = "Kiunum", ["wem"] = "Weme Gbe", ["weo"] = "Wemale", ["wer"] = "Weri", ["wes"] = "Cameroon Pidgin", ["wet"] = "Perai", ["weu"] = "Welaung", ["wew"] = "Weyewa", ["wfg"] = "Yafi", ["wga"] = "Wagaya", ["wgb"] = "Wagawaga", ["wgg"] = "Wangganguru", ["wgi"] = "Wahgi", ["wgo"] = "Waigeo", ["wgu"] = "Wirangu", ["wgy"] = "Warrgamay", ["wha"] = "Manusela", ["whg"] = "North Wahgi", ["whk"] = "Wahau Kenyah", ["whu"] = "Wahau Kayan", ["wib"] = "Southern Toussian", ["wic"] = "Wichita", ["wie"] = "Wik-Epa", ["wif"] = "Wik-Keyangan", ["wig"] = "Wik-Ngathana", ["wih"] = "Wik-Me'anha", ["wii"] = "Minidien", ["wij"] = "Wik-Iiyanh", ["wik"] = "Wikalkan", ["wil"] = "Wilawila", ["wim"] = "Wik-Mungkan", ["win"] = "Winnebago", ["wir"] = "Wiraféd", ["wiu"] = "Wiru", ["wiv"] = "Muduapa", ["wiy"] = "Wiyot", ["wja"] = "Waja", ["wji"] = "Warji", ["wka"] = "Kw'adza", ["wkb"] = "Kumbaran", ["wkd"] = "Mo", ["wkl"] = "Kalanadi", ["wku"] = "Kunduvadi", ["wkw"] = "Wakawaka", ["wky"] = "Wangkayutyuru", ["wla"] = "Walio", ["wlc"] = "Mwali Comorian", ["wle"] = "Wolane", ["wlg"] = "Kunbarlang", ["wli"] = "Waioli", ["wlk"] = "Wailaki", ["wll"] = "Wali (Sudan)", ["wlm"] = "Middle Welsh", ["wlo"] = "Wolio", ["wlr"] = "Wailapa", ["wls"] = "Wallisian", ["wlu"] = "Wuliwuli", ["wlv"] = "Wichí Lhamtés Vejoz", ["wlw"] = "Walak", ["wlx"] = "Wali (Ghana)", ["wly"] = "Waling", ["wmb"] = "Wambaya", ["wmc"] = "Wamas", ["wmd"] = "Mamaindé", ["wme"] = "Wambule", ["wmh"] = "Waima'a", ["wmi"] = "Wamin", ["wmm"] = "Maiwa (Indonesia)", ["wmn"] = "Waamwang", ["wmo"] = "Wam", ["wms"] = "Wambon", ["wmt"] = "Walmajarri", ["wmw"] = "Mwani", ["wmx"] = "Womo", ["wnb"] = "Mokati", ["wnc"] = "Wantoat", ["wnd"] = "Wandarang", ["wne"] = "Waneci", ["wng"] = "Wanggom", ["wni"] = "Ndzwani Comorian", ["wnk"] = "Wanukaka", ["wnm"] = "Wanggamala", ["wno"] = "Wano", ["wnp"] = "Wanap", ["wnu"] = "Usan", ["wnw"] = "Wintu", ["wny"] = "Wanyi", ["wo"] = "Wolof", ["woa"] = "Tyaraity", ["wob"] = "Wobé", ["woc"] = "Wogeo", ["wod"] = "Wolani", ["woe"] = "Woleaian", ["wog"] = "Wogamusin", ["woi"] = "Kamang", ["wok"] = "Longto", ["wom"] = "Perema", ["won"] = "Wongo", ["woo"] = "Manombai", ["wor"] = "Woria", ["wos"] = "Hanga Hundi", ["wow"] = "Wawonii", ["woy"] = "Weyto", ["wpc"] = "Wirö", ["wra"] = "Warapu", ["wrb"] = "Warluwara", ["wrg"] = "Warungu", ["wrh"] = "Wiradjuri", ["wri"] = "Wariyangga", ["wrk"] = "Garawa", ["wrl"] = "Warlmanpa", ["wrm"] = "Warumungu", ["wrn"] = "Warnang", ["wro"] = "Worora", ["wrp"] = "Waropen", ["wrr"] = "Wardaman", ["wrs"] = "Waris", ["wru"] = "Waru", ["wrv"] = "Waruna", ["wrw"] = "Gugu Warra", ["wrx"] = "Wae Rana", ["wrz"] = "Warray", ["wsa"] = "Warembori", ["wsi"] = "Wusi", ["wsk"] = "Waskia", ["wsr"] = "Owenia", ["wsu"] = "Wasu", ["wsv"] = "Wotapuri-Katarqalai", ["wtf"] = "Watiwa", ["wth"] = "Wathaurong", ["wti"] = "Berta", ["wtk"] = "Watakataui", ["wtm"] = "Mewati", ["wtw"] = "Wotu", ["wua"] = "Wikngenchera", ["wub"] = "Wunambal", ["wud"] = "Wudu", ["wuh"] = "Wutunhua", ["wul"] = "Silimo", ["wum"] = "Wumbvu", ["wun"] = "Bungu", ["wur"] = "Wurrugu", ["wut"] = "Wutung", ["wuu"] = "Wu", ["wuv"] = "Wuvulu-Aua", ["wux"] = "Wulna", ["wuy"] = "Wauyai", ["wwa"] = "Waama", ["wwo"] = "Dorig", ["wwr"] = "Warrwa", ["www"] = "Wawa", ["wxa"] = "Waxiang", ["wxw"] = "Wardandi", ["wya"] = "Wyandot", ["wyb"] = "Ngiyambaa", ["wyi"] = "Woiwurrung", ["wym"] = "Vilamovian", ["wyr"] = "Wayoró", ["wyy"] = "Western Fijian", ["xaa"] = "Andalusian Arabic", ["xab"] = "Sambe", ["xac"] = "Kachari", ["xad"] = "Adai", ["xae"] = "Aequian", ["xag"] = "Aghwan", ["xai"] = "Kaimbé", ["xaj"] = "Ararandewára", ["xak"] = "Maku", ["xal"] = "Kalmyk", ["xam"] = "ǀXam", ["xan"] = "Xamtanga", ["xao"] = "Khao", ["xap"] = "Apalachee", ["xar"] = "Karami", ["xas"] = "Kamassian", ["xat"] = "Katawixi", ["xau"] = "Kauwera", ["xav"] = "Xavante", ["xaw"] = "Kawaiisu", ["xay"] = "Kayan Mahakam", ["xbb"] = "Lower Burdekin", ["xbc"] = "Bactrian", ["xbd"] = "Bindal", ["xbe"] = "Bigambal", ["xbg"] = "Bunganditj", ["xbi"] = "Kombio", ["xbj"] = "Birrpayi", ["xbm"] = "Middle Breton", ["xbn"] = "Kenaboi", ["xbo"] = "Bulgar", ["xbp"] = "Bibbulman", ["xbr"] = "Kambera", ["xbw"] = "Kambiwá", ["xby"] = "Butchulla", ["xcb"] = "Cumbric", ["xcc"] = "Camunic", ["xce"] = "Celtiberian", ["xch"] = "Chemakum", ["xcl"] = "Old Armenian", ["xcm"] = "Comecrudo", ["xcn"] = "Cotoname", ["xco"] = "Khwarezmian", ["xcr"] = "Carian", ["xct"] = "Classical Tibetan", ["xcu"] = "Curonian", ["xcv"] = "Chuvan", ["xcw"] = "Coahuilteco", ["xcy"] = "Cayuse", ["xda"] = "Darkinjung", ["xdc"] = "Dacian", ["xdk"] = "Dharug", ["xdm"] = "Edomite", ["xdq"] = "Kaitag", ["xdy"] = "Malayic Dayak", ["xeb"] = "Eblaite", ["xed"] = "Hdi", ["xeg"] = "ǁXegwi", ["xel"] = "Kelo", ["xem"] = "Kembayan", ["xep"] = "Epi-Olmec", ["xer"] = "Xerénte", ["xes"] = "Koromu", ["xet"] = "Xetá", ["xeu"] = "Keoru-Ahia", ["xfa"] = "Faliscan", ["xga"] = "Galatian", ["xgb"] = "Gbin", ["xgd"] = "Gudang", ["xgf"] = "Gabrielino-Fernandeño", ["xgg"] = "Goreng", ["xgi"] = "Garingbal", ["xgl"] = "Galindian", ["xgm"] = "Darumbal", ["xgn-pro"] = "Proto-Mongolic", ["xgr"] = "Garza", ["xgu"] = "Unggumi", ["xgw"] = "Guwa", ["xh"] = "Xhosa", ["xha"] = "Harami", ["xhc"] = "Hunnic", ["xhd"] = "Hadrami", ["xhe"] = "Khetrani", ["xhm"] = "Middle Khmer", ["xhr"] = "Hernican", ["xht"] = "Hattic", ["xhu"] = "Hurrian", ["xhv"] = "Khua", ["xib"] = "Iberian", ["xii"] = "Xiri", ["xil"] = "Illyrian", ["xin"] = "Xinca", ["xir"] = "Xiriâna", ["xis"] = "Kisan", ["xiv"] = "Harappan", ["xiy"] = "Xipaya", ["xjb"] = "Minjungbal", ["xka"] = "Kalkoti", ["xkb"] = "Manigri-Kambolé Ede Nago", ["xkc"] = "Khoini", ["xkd"] = "Mendalam Kayan", ["xke"] = "Kereho", ["xkf"] = "Khengkha", ["xkg"] = "Kagoro", ["xki"] = "Kenyan Sign Language", ["xkj"] = "Kajali", ["xkk"] = "Kaco'", ["xkl"] = "Bakung", ["xkn"] = "Kayan River Kayan", ["xko"] = "Kiorr", ["xkp"] = "Kabatei", ["xkq"] = "Koroni", ["xkr"] = "Xakriabá", ["xks"] = "Kumbewaha", ["xkt"] = "Kantosi", ["xku"] = "Kaamba", ["xkv"] = "Kgalagadi", ["xkw"] = "Kembra", ["xkx"] = "Karore", ["xky"] = "Uma' Lasan", ["xkz"] = "Kurtöp", ["xla"] = "Kamula", ["xlb"] = "Loup B", ["xlc"] = "Lycian", ["xld"] = "Lydian", ["xle"] = "Lemnian", ["xlg"] = "Ancient Ligurian", ["xli"] = "Liburnian", ["xln"] = "Alanic", ["xlo"] = "Loup A", ["xlp"] = "Lepontic", ["xls"] = "Lusitanian", ["xlu"] = "Luwian", ["xly"] = "Elymian", ["xmb"] = "Mbonga", ["xmc"] = "Makhuwa-Marrevone", ["xmd"] = "Mbudum", ["xme-ker"] = "Kermanic", ["xme-kls"] = "Kalasuri", ["xme-klt"] = "Kilit", ["xme-mid"] = "Middle Median", ["xme-old"] = "Old Median", ["xme-ott"] = "Old Tati", ["xme-taf"] = "Tafreshi", ["xme-ttc-pro"] = "Proto-Tatic", ["xmf"] = "Mingrelian", ["xmg"] = "Mengaka", ["xmh"] = "Kugu-Muminh", ["xmj"] = "Majera", ["xmk"] = "Ancient Macedonian", ["xml"] = "Malaysian Sign Language", ["xmm"] = "Manado Malay", ["xmo"] = "Morerebi", ["xmp"] = "Kuku-Mu'inh", ["xmq"] = "Kuku-Mangk", ["xmr"] = "Meroitic", ["xms"] = "Moroccan Sign Language", ["xmt"] = "Matbat", ["xmu"] = "Kamu", ["xmx"] = "Maden", ["xmy"] = "Mayaguduna", ["xmz"] = "Mori Bawah", ["xna"] = "Ancient North Arabian", ["xnb"] = "Kanakanabu", ["xnd-pro"] = "Proto-Na-Dene", ["xng"] = "Middle Mongol", ["xnh"] = "Kuanhua", ["xni"] = "Ngarigu", ["xnk"] = "Nganakarti", ["xnr"] = "Kangri", ["xns"] = "Kanashi", ["xnt"] = "Narragansett", ["xnu"] = "Nukunul", ["xny"] = "Nyiyaparli", ["xoc"] = "O'chi'chi'", ["xod"] = "Kokoda", ["xog"] = "Soga", ["xoi"] = "Kominimung", ["xok"] = "Xokleng", ["xom"] = "Komo", ["xon"] = "Konkomba", ["xoo"] = "Xukurú", ["xop"] = "Kopar", ["xor"] = "Korubo", ["xow"] = "Kowaki", ["xpa"] = "Pirriya", ["xpb"] = "Pyemmairre", ["xpc"] = "Pecheneg", ["xpd"] = "Paredarerme", ["xpe"] = "Liberia Kpelle", ["xpf"] = "Southeast Tasmanian", ["xpg"] = "Phrygian", ["xph"] = "Tyerrernotepanner", ["xpi"] = "Pictish", ["xpj"] = "Mpalitjanh", ["xpk"] = "Kulina", ["xpl"] = "Port Sorell", ["xpm"] = "Pumpokol", ["xpn"] = "Kapinawá", ["xpo"] = "Pochutec", ["xpp"] = "Puyo-Paekche", ["xpq"] = "Mohegan-Pequot", ["xpr"] = "Parthian", ["xps"] = "Pisidian", ["xpu"] = "Punic", ["xpv"] = "Tommeginne", ["xpw"] = "Peerapper", ["xpx"] = "Toogee", ["xpy"] = "Buyeo", ["xpz"] = "Bruny Island", ["xqa"] = "Karakhanid", ["xqt"] = "Qatabanian", ["xra"] = "Krahô", ["xrb"] = "Eastern Karaboro", ["xrd"] = "Gundungurra", ["xre"] = "Kreye", ["xrg"] = "Minang", ["xri"] = "Krikati-Timbira", ["xrm"] = "Armazic", ["xrn"] = "Arin", ["xrq"] = "Karranga", ["xrr"] = "Raetic", ["xrt"] = "Aranama-Tamique", ["xru"] = "Marriammu", ["xrw"] = "Karawa", ["xsa"] = "Sabaean", ["xsb"] = "Sambali", ["xsc-pro"] = "Proto-Scythian", ["xsc-sak-pro"] = "Proto-Saka", ["xsc-sar-pro"] = "Proto-Sarmatian", ["xsc-skw-pro"] = "Proto-Saka-Wakhi", ["xsd"] = "Sidetic", ["xse"] = "Sempan", ["xsh"] = "Shamang", ["xsi"] = "Sio", ["xsj"] = "Subi", ["xsl"] = "South Slavey", ["xsm"] = "Kasem", ["xsn"] = "Sanga (Nigeria)", ["xso"] = "Solano", ["xsp"] = "Silopi", ["xsq"] = "Makhuwa-Saka", ["xsr"] = "Sherpa", ["xss"] = "Assan", ["xsu"] = "Sanumá", ["xsv"] = "Sudovian", ["xsy"] = "Saisiyat", ["xta"] = "Alcozauca Mixtec", ["xtb"] = "Chazumba Mixtec", ["xtc"] = "Kadugli", ["xtd"] = "Diuxi-Tilantongo Mixtec", ["xte"] = "Ketengban", ["xth"] = "Yitha Yitha", ["xti"] = "Sinicahua Mixtec", ["xtj"] = "San Juan Teita Mixtec", ["xtl"] = "Tijaltepec Mixtec", ["xtm"] = "Magdalena Peñasco Mixtec", ["xtn"] = "Northern Tlaxiaco Mixtec", ["xto"] = "Tocharian A", ["xtp"] = "San Miguel Piedras Mixtec", ["xtq"] = "Tumshuqese", ["xtr"] = "Early Tripuri", ["xts"] = "Sindihui Mixtec", ["xtt"] = "Tacahua Mixtec", ["xtu"] = "Cuyamecalco Mixtec", ["xtv"] = "Thawa", ["xtw"] = "Tawandê", ["xty"] = "Yoloxochitl Mixtec", ["xua"] = "Alu Kurumba", ["xub"] = "Betta Kurumba", ["xud"] = "Umiida", ["xug"] = "Kunigami", ["xuj"] = "Jennu Kurumba", ["xul"] = "Ngunawal", ["xum"] = "Umbrian", ["xun"] = "Unggaranggu", ["xuo"] = "Kuo", ["xup"] = "Upper Umpqua", ["xur"] = "Urartian", ["xut"] = "Kuthant", ["xuu"] = "Khwe", ["xve"] = "Venetic", ["xvn"] = "Vandalic", ["xvo"] = "Volscian", ["xvs"] = "Vestinian", ["xwa"] = "Kwaza", ["xwc"] = "Woccon", ["xwd"] = "Wadi Wadi", ["xwe"] = "Xwela Gbe", ["xwg"] = "Kwegu", ["xwj"] = "Wajuk", ["xwk"] = "Wangkumara", ["xwl"] = "Western Xwla Gbe", ["xwo"] = "Written Oirat", ["xwr"] = "Kwerba Mamberamo", ["xww"] = "Wemba-Wemba", ["xxb"] = "Boro", ["xxk"] = "Ke'o", ["xxm"] = "Minkin", ["xxr"] = "Koropó", ["xxt"] = "Tambora", ["xya"] = "Yaygir", ["xyb"] = "Yandjibara", ["xyl"] = "Yalakalore", ["xyt"] = "Mayi-Thakurti", ["xyy"] = "Yorta Yorta", ["xzh"] = "Zhang-Zhung", ["xzm"] = "Semigallian", ["xzp"] = "Ancient Zapotec", ["yaa"] = "Yaminahua", ["yab"] = "Yuhup", ["yac"] = "Pass Valley Yali", ["yad"] = "Yagua", ["yae"] = "Pumé", ["yaf"] = "Yaka", ["yag"] = "Yámana", ["yah"] = "Yazghulami", ["yai"] = "Yaghnobi", ["yaj"] = "Banda-Yangere", ["yak"] = "Yakima", ["yal"] = "Yalunka", ["yam"] = "Yamba", ["yan"] = "Mayangna", ["yao"] = "Yao (Africa)", ["yap"] = "Yapese", ["yaq"] = "Yaqui", ["yar"] = "Yabarana", ["yas"] = "Gunu", ["yat"] = "Yambeta", ["yau"] = "Yuwana", ["yav"] = "Yangben", ["yaw"] = "Yawalapití", ["yay"] = "Agwagwune", ["yaz"] = "Lokaa", ["yba"] = "Yala", ["ybb"] = "Yemba", ["ybe"] = "Western Yugur", ["ybh"] = "Yakkha", ["ybi"] = "Yamphu", ["ybj"] = "Hasha", ["ybk"] = "Bokha", ["ybl"] = "Yukuben", ["ybm"] = "Yaben", ["ybn"] = "Yabaâna", ["ybo"] = "Yabong", ["ybx"] = "Yawiyo", ["yby"] = "Yaweyuha", ["ych"] = "Chesu", ["ycl"] = "Lolopo", ["ycn"] = "Yucuna", ["ycp"] = "Chepya", ["ycr"] = "Yilan Creole", ["yda"] = "Yanda", ["yde"] = "Yangum Dey", ["ydg"] = "Yidgha", ["ydk"] = "Yoidik", ["yea"] = "Ravula", ["yec"] = "Yenish", ["yee"] = "Yimas", ["yei"] = "Yeni", ["yej"] = "Yevanic", ["yen"] = "Yendang", ["yer"] = "Tarok", ["yes"] = "Yeskwa", ["yet"] = "Yetfa", ["yeu"] = "Yerukula", ["yev"] = "Yeri", ["yey"] = "Yeyi", ["ygi"] = "Yiningayi", ["ygl"] = "Yangum Gel", ["ygm"] = "Yagomi", ["ygp"] = "Gepo", ["ygr"] = "Yagaria", ["ygs"] = "Yolngu Sign Language", ["ygu"] = "Yugul", ["ygw"] = "Yagwoia", ["yha"] = "Baha", ["yhl"] = "Hlepho Phowa", ["yi"] = "Yiddish", ["yia"] = "Yinggarda", ["yif"] = "Ache", ["yig"] = "Wusa", ["yii"] = "Yidiny", ["yij"] = "Yindjibarndi", ["yik"] = "Dongshanba Lalo", ["yil"] = "Yindjilandji", ["yim"] = "Yimchungru Naga", ["yin"] = "Yinchia", ["yip"] = "Pholo", ["yiq"] = "Micha", ["yir"] = "North Awyu", ["yis"] = "Yis", ["yit"] = "Eastern Lalu", ["yiu"] = "Lope", ["yiv"] = "Northern Nisu", ["yix"] = "Axi", ["yiy"] = "Yir-Yoront", ["yiz"] = "Azhe", ["yka"] = "Yakan", ["ykg"] = "Northern Yukaghir", ["ykh"] = "Khamnigan Mongol", ["yki"] = "Yoke", ["ykk"] = "Yakaikeke", ["ykl"] = "Khlula", ["ykm"] = "Kap", ["ykn"] = "Kua-nsi", ["yko"] = "Yasa", ["ykr"] = "Yekora", ["ykt"] = "Kathu", ["yku"] = "Kuamasi", ["yky"] = "Yakoma", ["yla"] = "Ulwa (New Guinea)", ["ylb"] = "Yaleba", ["yle"] = "Yele", ["ylg"] = "Yelogu", ["yli"] = "Angguruk Yali", ["yll"] = "Yil", ["ylm"] = "Limi", ["yln"] = "Langnian Buyang", ["ylo"] = "Naruo", ["ylr"] = "Yalarnnga", ["ylu"] = "Aribwaung", ["yly"] = "Nyelâyu", ["ymb"] = "Yambes", ["ymc"] = "Southern Muji", ["ymd"] = "Muda", ["yme"] = "Yameo", ["ymg"] = "Yamongeri", ["ymh"] = "Mili", ["ymi"] = "Moji", ["ymk"] = "Makwe", ["yml"] = "Iamalele", ["ymm"] = "Maay", ["ymn"] = "Sunum", ["ymo"] = "Yangum Mon", ["ymp"] = "Yamap", ["ymq"] = "Qila Muji", ["ymr"] = "Malasar", ["yms"] = "Mysian", ["ymx"] = "Northern Muji", ["ymz"] = "Muzi", ["yna"] = "Aluo", ["ynb"] = "Yamben", ["ynd"] = "Yandruwandha", ["yne"] = "Lang'e", ["yng"] = "Yango", ["ynk"] = "Naukanski", ["ynl"] = "Yangulam", ["ynn"] = "Yana", ["yno"] = "Yong", ["yns"] = "Yansi", ["ynu"] = "Yahuna", ["yo"] = "Yoruba", ["yob"] = "Yoba", ["yog"] = "Yogad", ["yoi"] = "Yonaguni", ["yok-bvy"] = "Buena Vista Yokuts", ["yok-dly"] = "Delta Yokuts", ["yok-gsy"] = "Gashowu Yokuts", ["yok-kry"] = "Kings River Yokuts", ["yok-nvy"] = "Northern Valley Yokuts", ["yok-ply"] = "Palewyami Yokuts", ["yok-svy"] = "Southern Valley Yokuts", ["yok-tky"] = "Tule-Kaweah Yokuts", ["yol"] = "Yola", ["yom"] = "Yombe", ["yon"] = "Yongkom", ["yox"] = "Yoron", ["yoy"] = "Yoy", ["ypa"] = "Phala", ["ypb"] = "Labo Phowa", ["ypg"] = "Phola", ["yph"] = "Phupha", ["ypk-pro"] = "Proto-Yupik", ["ypm"] = "Phuma", ["ypn"] = "Ani Phowa", ["ypo"] = "Alo Phola", ["ypp"] = "Phupa", ["ypz"] = "Phuza", ["yra"] = "Yerakai", ["yrb"] = "Yareba", ["yre"] = "Yaouré", ["yri"] = "Yarí", ["yrk-for"] = "Forest Nenets", ["yrk-tun"] = "Tundra Nenets", ["yrl"] = "Nheengatu", ["yrn"] = "Yerong", ["yro"] = "Ỹaroamë", ["yrw"] = "Yarawata", ["yry"] = "Yarluyandi", ["ysc"] = "Jassic", ["ysd"] = "Samatao", ["ysg"] = "Sonaga", ["ysl"] = "Yugoslavian Sign Language", ["ysn"] = "Sani", ["yso"] = "Nisi", ["ysp"] = "Southern Lolopo", ["ysr"] = "Sirenik", ["yss"] = "Yessan-Mayo", ["ysy"] = "Sanie", ["yta"] = "Talu", ["ytl"] = "Toloza", ["ytp"] = "Thopho", ["ytw"] = "Yout Wam", ["yty"] = "Yatay", ["yua"] = "Yucatec Maya", ["yub"] = "Yugambal", ["yuc"] = "Yuchi", ["yue"] = "Cantonese", ["yuf"] = "Havasupai-Walapai-Yavapai", ["yug"] = "Yug", ["yui"] = "Yurutí", ["yuj"] = "Karkar-Yuri", ["yuk"] = "Yuki", ["yul"] = "Yulu", ["yum"] = "Yuma", ["yun"] = "Bena", ["yup"] = "Yukpa", ["yuq"] = "Yuqui", ["yur"] = "Yurok", ["yut"] = "Yopno", ["yuw"] = "Yau (Finisterre)", ["yux"] = "Southern Yukaghir", ["yuy"] = "East Yugur", ["yuz"] = "Yuracare", ["yva"] = "Yawa", ["yvt"] = "Yavitero", ["ywa"] = "Kalou", ["ywg"] = "Yinhawangka", ["ywl"] = "Western Lalu", ["ywn"] = "Yawanawa", ["ywq"] = "Nasu", ["ywr"] = "Yawuru", ["ywt"] = "Xishanba Lalo", ["ywu"] = "Wumeng", ["yww"] = "Yawarawarga", ["yxa"] = "Mayawali", ["yxg"] = "Yagara", ["yxl"] = "Yarli", ["yxm"] = "Yinwum", ["yxu"] = "Yuyu", ["yxy"] = "Yabula Yabula", ["yyu"] = "Yau (Torricelli)", ["yyz"] = "Ayizi", ["yzg"] = "E'ma Buyang", ["yzk"] = "Zokhuo", ["za"] = "Zhuang", ["zaa"] = "Sierra de Juárez Zapotec", ["zab"] = "San Juan Guelavía Zapotec", ["zac"] = "Ocotlán Zapotec", ["zad"] = "Cajonos Zapotec", ["zae"] = "Yareni Zapotec", ["zaf"] = "Ayoquesco Zapotec", ["zag"] = "Zaghawa", ["zah"] = "Zangwal", ["zai"] = "Isthmus Zapotec", ["zaj"] = "Zaramo", ["zak"] = "Zanaki", ["zal"] = "Zauzou", ["zam"] = "Central Mahuatlán Zapotec", ["zao"] = "Ozolotepec Zapotec", ["zap"] = "Zapotec", ["zaq"] = "Aloápam Zapotec", ["zar"] = "Rincón Zapotec", ["zas"] = "Santo Domingo Albarradas Zapotec", ["zat"] = "Tabaa Zapotec", ["zau"] = "Zangskari", ["zav"] = "Yatzachi Zapotec", ["zaw"] = "Mitla Zapotec", ["zax"] = "Xadani Zapotec", ["zay"] = "Zayse-Zergulla", ["zaz"] = "Zari", ["zbt"] = "Batui", ["zca"] = "Coatecas Altas Zapotec", ["zdj"] = "Ngazidja Comorian", ["zea"] = "Zealandic", ["zeg"] = "Zenag", ["zen"] = "Zenaga", ["zga"] = "Kinga", ["zgh"] = "Moroccan Amazigh", ["zgr"] = "Magori", ["zh"] = "Chinese", ["zhb"] = "Zhaba", ["zhi"] = "Zhire", ["zhn"] = "Nong Zhuang", ["zhw"] = "Zhoa", ["zhx-min-pro"] = "Proto-Min", ["zhx-sht"] = "Shaozhou Tuhua", ["zhx-sic"] = "Sichuanese", ["zhx-tai"] = "Taishanese", ["zia"] = "Zia", ["zib"] = "Zimbabwe Sign Language", ["zik"] = "Zimakani", ["zil"] = "Zialo", ["zim"] = "Mesme", ["zin"] = "Zinza", ["zir"] = "Ziriya", ["ziw"] = "Zigula", ["ziz"] = "Zizilivakan", ["zka"] = "Kaimbulawa", ["zkb"] = "Koibal", ["zkd"] = "Kadu (Myanmar)", ["zkg"] = "Goguryeo", ["zkh"] = "Khorezmian Turkic", ["zkk"] = "Karankawa", ["zko"] = "Kott", ["zkp"] = "São Paulo Kaingáng", ["zkr"] = "Zakhring", ["zkt"] = "Khitan", ["zku"] = "Kaurna", ["zkv"] = "Krevinian", ["zkz"] = "Khazar", ["zle-ono"] = "Old Novgorodian", ["zle-ort"] = "Old Ruthenian", ["zls-chs"] = "Church Slavonic", ["zlw-ocs"] = "Old Czech", ["zlw-opl"] = "Old Polish", ["zlw-osk"] = "Old Slovak", ["zlw-slv"] = "Slovincian", ["zma"] = "Manda (Australia)", ["zmb"] = "Zimba", ["zmc"] = "Margany", ["zmd"] = "Maridan", ["zme"] = "Mangerr", ["zmf"] = "Mfinu", ["zmg"] = "Marti Ke", ["zmh"] = "Makolkol", ["zmi"] = "Negeri Sembilan Malay", ["zmj"] = "Maridjabin", ["zmk"] = "Mandandanyi", ["zml"] = "Madngele", ["zmm"] = "Marimanindji", ["zmn"] = "Mbangwe", ["zmo"] = "Molo", ["zmp"] = "Mbuun", ["zmq"] = "Mituku", ["zmr"] = "Maranungku", ["zms"] = "Mbesa", ["zmt"] = "Maringarr", ["zmu"] = "Muruwari", ["zmv"] = "Mbariman-Gudhinma", ["zmw"] = "Mbo (Congo)", ["zmx"] = "Bomitaba", ["zmy"] = "Mariyedi", ["zmz"] = "Mbandja", ["zna"] = "Zan Gula", ["zne"] = "Zande", ["zng"] = "Mang", ["znk"] = "Manangkari", ["zns"] = "Mangas", ["zoc"] = "Copainalá Zoque", ["zoh"] = "Chimalapa Zoque", ["zom"] = "Zou", ["zoo"] = "Asunción Mixtepec Zapotec", ["zoq"] = "Tabasco Zoque", ["zor"] = "Rayón Zoque", ["zos"] = "Francisco León Zoque", ["zpa"] = "Lachiguiri Zapotec", ["zpb"] = "Yautepec Zapotec", ["zpc"] = "Choapan Zapotec", ["zpd"] = "Southeastern Ixtlán Zapotec", ["zpe"] = "Petapa Zapotec", ["zpf"] = "San Pedro Quiatoni Zapotec", ["zpg"] = "Guevea de Humboldt Zapotec", ["zph"] = "Totomachapan Zapotec", ["zpi"] = "Santa María Quiegolani Zapotec", ["zpj"] = "Quiavicuzas Zapotec", ["zpk"] = "Tlacolulita Zapotec", ["zpl"] = "Lachixío Zapotec", ["zpm"] = "Mixtepec Zapotec", ["zpn"] = "Santa Inés Yatzechi Zapotec", ["zpo"] = "Amatlán Zapotec", ["zpp"] = "El Alto Zapotec", ["zpq"] = "Zoogocho Zapotec", ["zpr"] = "Santiago Xanica Zapotec", ["zps"] = "Coatlán Zapotec", ["zpt"] = "San Vicente Coatlán Zapotec", ["zpu"] = "Yalálag Zapotec", ["zpv"] = "Chichicapan Zapotec", ["zpw"] = "Zaniza Zapotec", ["zpx"] = "San Baltazar Loxicha Zapotec", ["zpy"] = "Mazaltepec Zapotec", ["zpz"] = "Texmelucan Zapotec", ["zra"] = "Gaya", ["zrg"] = "Mirgan", ["zrn"] = "Zirenkel", ["zro"] = "Záparo", ["zrs"] = "Mairasi", ["zsa"] = "Sarasira", ["zsk"] = "Kaskean", ["zsl"] = "Zambian Sign Language", ["zsr"] = "Southern Rincon Zapotec", ["zsu"] = "Sukurum", ["zte"] = "Elotepec Zapotec", ["ztg"] = "Xanaguía Zapotec", ["ztl"] = "Lapaguía-Guivini Zapotec", ["ztm"] = "San Agustín Mixtepec Zapotec", ["ztn"] = "Santa Catarina Albarradas Zapotec", ["ztp"] = "Loxicha Zapotec", ["ztq"] = "Quioquitani-Quierí Zapotec", ["zts"] = "Tilquiapan Zapotec", ["ztt"] = "Tejalapan Zapotec", ["ztu"] = "San Pablo Güilá Zapotec", ["ztx"] = "Zaachila Zapotec", ["zty"] = "Yatee Zapotec", ["zu"] = "Zulu", ["zua"] = "Zeem", ["zuh"] = "Tokano", ["zum"] = "Kumzari", ["zun"] = "Zuni", ["zuy"] = "Zumaya", ["zwa"] = "Zay", ["zyp"] = "Zyphe", ["zza"] = "Zazaki", ["zzj"] = "Zuojiang Zhuang", } 2d72j95294gd1u2gzv1hbvvpo0q61oy 828 5994 17431 2026-07-13T08:41:51Z Hiyuune 6766 + 17431 Scribunto text/plain return { ["aae"] = "Arbëresh Albanian", ["aat"] = "Arvanitika Albanian", ["abr"] = "Abron", ["acm-khu"] = "Khuzestani Arabic", ["act"] = "Achterhoeks", ["adx"] = "Amdo Tibetan", ["ae-old"] = "Old Avestan", ["ae-yng"] = "Younger Avestan", ["ain-hok"] = "Hokkaido Ainu", ["ain-kur"] = "Kuril Ainu", ["ain-sak"] = "Sakhalin Ainu", ["akk-lbb"] = "Late Babylonian", ["akk-mas"] = "Middle Assyrian", ["akk-mbb"] = "Middle Babylonian", ["akk-nas"] = "Neo-Assyrian", ["akk-nbb"] = "Neo-Babylonian", ["akk-oas"] = "Old Assyrian", ["akk-obb"] = "Old Babylonian", ["akk-old"] = "Old Akkadian", ["akk-stb"] = "Standard Babylonian", ["aln"] = "Gheg Albanian", ["als"] = "Tosk Albanian", ["alv-kro"] = "Kromanti", ["ang-ang"] = "Anglian Old English", ["ang-ken"] = "Kentish Old English", ["ang-mer"] = "Mercian Old English", ["ang-nor"] = "Northumbrian Old English", ["ang-wsx"] = "West Saxon Old English", ["apc-ale"] = "Aleppine North Levantine Arabic", ["apc-dam"] = "Damascene North Levantine Arabic", ["apc-leb"] = "Lebanese North Levantine Arabic", ["apc-nle"] = "North Lebanese North Levantine Arabic", ["apc-sle"] = "South Lebanese North Levantine Arabic", ["apc-syr"] = "Syrian North Levantine Arabic", ["arc-bib"] = "Biblical Aramaic", ["arc-cpa"] = "Christian Palestinian Aramaic", ["arc-hat"] = "Hatran Aramaic", ["arc-imp"] = "Imperial Aramaic", ["arc-jla"] = "Jewish Literary Aramaic", ["arc-nab"] = "Nabataean Aramaic", ["arc-old"] = "Old Aramaic", ["arc-pal"] = "Palmyrene Aramaic", ["as-bkm"] = "Barpetia Kamrupi Assamese", ["as-nkm"] = "Nalbaria Kamrupi Assamese", ["as-pkm"] = "Palasbaria Kamrupi Assamese", ["atn"] = "Ashtiani", ["az-cls"] = "Classical Azerbaijani", ["bat-dni"] = "Dnieper Baltic", ["bat-gol"] = "Golyad", ["bat-pro"] = "Proto-Baltic", ["bcc"] = "Southern Balochi", ["bew-kot"] = "Betawi Kota", ["bgn"] = "Western Balochi", ["bgp"] = "Eastern Balochi", ["bn-dvn"] = "Dhakaiya Vaṅga Bengali", ["bn-nvn"] = "Noakhailla Vaṅga Bengali", ["bnt-cmn"] = "Common Bantu", ["bra-old"] = "Old Braj", ["bry-ear"] = "Early Brythonic", ["bry-lat"] = "Late Brythonic", ["bsg-ban"] = "Bandari", ["bsg-hor"] = "Hormozi", ["bsg-min"] = "Minabi", ["bsh-kat"] = "Kativiri", ["bsh-mum"] = "Mumviri", ["ca-val"] = "Valencian", ["ckm"] = "Chakavian Serbo-Croatian", ["cls"] = "Classical Sanskrit", ["cmn-MY"] = "Malaysian Mandarin", ["cmn-PH"] = "Philippine Mandarin", ["cmn-SG"] = "Singapore Mandarin", ["cmn-TW"] = "Taiwanese Mandarin", ["cmn-bec"] = "Beijingic Mandarin", ["cmn-bei"] = "Beijing Mandarin", ["cmn-cep"] = "Central Plains Mandarin", ["cmn-ear"] = "Early Mandarin", ["cmn-gua"] = "Guanzhong Mandarin", ["cmn-gui"] = "Guilin Mandarin", ["cmn-jhu"] = "Jianghuai Mandarin", ["cmn-lan"] = "Lanyin Mandarin", ["cmn-nan"] = "Nanjing Mandarin", ["cmn-noe"] = "Northeastern Mandarin", ["cmn-palladius"] = "Palladius", ["cmn-pinyin"] = "Hanyu Pinyin", ["cmn-sow"] = "Southwestern Mandarin", ["cmn-tia"] = "Tianjin Mandarin", ["cmn-tongyong"] = "Tongyong Pinyin", ["cmn-wadegiles"] = "Wade–Giles", ["cmn-wuh"] = "Wuhan Mandarin", ["cmn-wvc"] = "Written vernacular Mandarin", ["cmn-xin"] = "Xining Mandarin", ["cmn-yan"] = "Yangzhou Mandarin", ["cop-akh"] = "Akhmimic Coptic", ["cop-boh"] = "Bohairic Coptic", ["cop-fay"] = "Fayyumic Coptic", ["cop-ggg"] = "Coptic Dialect G", ["cop-her"] = "Hermopolitan Coptic", ["cop-jjj"] = "Coptic Dialect J", ["cop-kkk"] = "Coptic Dialect K", ["cop-lyc"] = "Lycopolitan Coptic", ["cop-old"] = "Old Coptic", ["cop-oxy"] = "Oxyrhynchite Coptic", ["cop-ply"] = "Proto-Lycopolitan Coptic", ["cop-ppp"] = "Coptic Dialect P", ["cop-sah"] = "Sahidic Coptic", ["crh-dbj"] = "Dobrujan Tatar", ["crp-cpr-kya"] = "Kyakhta Chinese Pidgin Russian", ["cs-ear"] = "Early Modern Czech", ["cu-bgm"] = "Middle Bulgarian", ["cv-ana"] = "Anatri Chuvash", ["cv-mid"] = "Middle Chuvash", ["cv-old"] = "Old Chuvash", ["cv-vir"] = "Viryal Chuvash", ["cy-nor"] = "North Wales Welsh", ["cy-sou"] = "South Wales Welsh", ["de-AT"] = "Austrian German", ["de-AT-vie"] = "Viennese German", ["de-CH"] = "Switzerland German", ["de-bal"] = "Baltic German", ["de-ear"] = "Early New High German", ["drt"] = "Drents", ["dv-add"] = "Addu Dhivehi", ["dv-huv"] = "Huvadhu Dhivehi", ["dv-mul"] = "Mulaku Dhivehi", ["dv-old"] = "Old Dhivehi", ["egl-old"] = "Old Emilian", ["egy-lat"] = "Late Egyptian", ["egy-mid"] = "Middle Egyptian", ["egy-nmi"] = "Neo-Middle Egyptian", ["egy-old"] = "Old Egyptian", ["el-crt"] = "Cretan Greek", ["el-cyp"] = "Cypriot Greek", ["el-kal"] = "Kaliarda", ["el-kth"] = "Katharevousa", ["el-pap"] = "Paphian Greek", ["elx-ach"] = "Achaemenid Elamite", ["elx-mid"] = "Middle Elamite", ["elx-neo"] = "Neo-Elamite", ["elx-old"] = "Old Elamite", ["en-AU"] = "Australian English", ["en-CA"] = "Canadian English", ["en-GB"] = "British English", ["en-GB-NIR"] = "Northern Irish English", ["en-GB-SCT"] = "Scottish English", ["en-GB-WLS"] = "Welsh English", ["en-HK"] = "Hong Kong English", ["en-IE"] = "Irish English", ["en-IM"] = "Manx English", ["en-IN"] = "Indian English", ["en-NNN"] = "North American English", ["en-NZ"] = "New Zealand English", ["en-US"] = "American English", ["en-US-CA"] = "California English", ["en-ZA"] = "South African English", ["en-aae"] = "Australian Aboriginal English", ["en-ear"] = "Early Modern English", ["en-geo"] = "Geordie", ["en-uls"] = "Ulster English", ["enm-emi"] = "East Midland Middle English", ["enm-esc"] = "Early Scots", ["enm-ken"] = "Kentish Middle English", ["enm-nor"] = "Northern Middle English", ["enm-sou"] = "Southern Middle English", ["enm-wmi"] = "West Midland Middle English", ["es-AR"] = "Rioplatense Spanish", ["es-BO"] = "Bolivian Spanish", ["es-CL"] = "Chilean Spanish", ["es-CO"] = "Colombian Spanish", ["es-CU"] = "Cuban Spanish", ["es-MX"] = "Mexican Spanish", ["es-PE"] = "Peruvian Spanish", ["es-PH"] = "Philippine Spanish", ["es-PR"] = "Puerto Rican Spanish", ["es-US"] = "United States Spanish", ["es-VE"] = "Venezuelan Spanish", ["es-ear"] = "Early Modern Spanish", ["es-lun"] = "Lunfardo", ["esi"] = "North Alaskan Inupiatun", ["esk"] = "Northwest Alaskan Inupiatun", ["fa-cls"] = "Classical Persian", ["fa-ear"] = "Early New Persian", ["fa-ira"] = "Iranian Persian", ["fat"] = "Fante Akan", ["fay-bsh"] = "Bushehri", ["fay-bur"] = "Burenjani", ["fay-dav"] = "Davani", ["fay-dsh"] = "Dashtaki", ["fay-eze"] = "Emamzada Esmaili", ["fay-gav"] = "Gavkoshaki", ["fay-kar"] = "Khargi", ["fay-kho"] = "Khollari", ["fay-kon"] = "Kondazi", ["fay-kzo"] = "Old Kazeruni", ["fay-mas"] = "Masarami", ["fay-pap"] = "Papuni", ["fay-sam"] = "Samghani", ["fay-sho"] = "Old Shirazi", ["fay-shr"] = "Shirazi", ["fay-sor"] = "Sorkhi", ["ffm"] = "Maasina Fulfulde", ["fiu-pro"] = "Proto-Finno-Ugric", ["fr-CA"] = "Canadian French", ["fr-CH"] = "Swiss French", ["fr-aca"] = "Acadian French", ["fr-lou"] = "Louisiana French", ["fr-mis"] = "Missouri French", ["frc"] = "Cajun French", ["frk"] = "Frankish", ["fro-nor"] = "Old Northern French", ["fro-pic"] = "Picard Old French", ["frp-old"] = "Old Franco-Provençal", ["frr-amr"] = "Amrum North Frisian", ["frr-fam"] = "Föhr-Amrum North Frisian", ["frr-foh"] = "Föhr North Frisian", ["frr-goe"] = "Goesharde North Frisian", ["frr-hal"] = "Halligen North Frisian", ["frr-hel"] = "Heligoland North Frisian", ["frr-ins"] = "Insular North Frisian", ["frr-kar"] = "Karrharde North Frisian", ["frr-mai"] = "Mainland North Frisian", ["frr-moo"] = "Mooring North Frisian", ["frr-syl"] = "Sylt North Frisian", ["frr-wie"] = "Wiedingharde North Frisian", ["frs"] = "East Frisian Low German", ["fub"] = "Adamawa Fulfulde", ["fuc"] = "Pulaar", ["fue"] = "Borgu Fulfulde", ["fuf"] = "Pular", ["fuh"] = "Western Niger Fulfulde", ["fui"] = "Bagirmi Fulfulde", ["fuq"] = "Central-Eastern Niger Fulfulde", ["fur-old"] = "Old Friulian", ["fuv"] = "Nigerian Fulfulde", ["gax"] = "Borana", ["gbz"] = "Zoroastrian Dari", ["gem-sue"] = "Suevic", ["gkm"] = "Byzantine Greek", ["gmq-osw-lat"] = "Late Old Swedish", ["gmw-afr-pro"] = "Proto-Anglo-Frisian", ["gmw-nsg-pro"] = "Proto-North Sea Germanic", ["gos"] = "Gronings", ["grc-aeo"] = "Aeolic Greek", ["grc-arc"] = "Arcadian Greek", ["grc-arp"] = "Arcadocypriot Greek", ["grc-att"] = "Attic Greek", ["grc-boi"] = "Boeotian Greek", ["grc-cyp"] = "Cypriot Ancient Greek", ["grc-dor"] = "Doric Greek", ["grc-ela"] = "Elean Greek", ["grc-epi"] = "Epic Greek", ["grc-ion"] = "Ionic Greek", ["grc-koi"] = "Koine Greek", ["grc-kre"] = "Cretan Ancient Greek", ["grc-opl"] = "Opuntian Locrian", ["grc-ozl"] = "Ozolian Locrian", ["grc-pam"] = "Pamphylian Greek", ["grc-ths"] = "Thessalian Greek", ["gsw-FR-als"] = "Alsatian Alemannic German", ["gsw-hig"] = "High Alemannic German", ["gsw-hst"] = "Highest Alemannic German", ["gsw-low"] = "Low Alemannic German", ["gu-kat"] = "Kathiyawadi", ["gu-lda"] = "Lisan ud-Dawat Gujarati", ["gzi"] = "Gazi", ["hae"] = "Harar Oromo", ["hak-HK"] = "Hong Kong Hakka", ["hak-TW"] = "Taiwanese Hakka", ["hak-dab"] = "Dabu Hakka", ["hak-eam"] = "Early Modern Hakka", ["hak-hai"] = "Hailu Hakka", ["hak-hui"] = "Huiyang Hakka", ["hak-hui-MY"] = "Malaysian Huiyang Hakka", ["hak-mei"] = "Meixian Hakka", ["hak-six"] = "Sixian Hakka", ["hak-zha"] = "Zhao'an Hakka", ["haz"] = "Hazaragi", ["hbo"] = "Biblical Hebrew", ["he-IL"] = "Israeli Hebrew", ["he-med"] = "Medieval Hebrew", ["he-mis"] = "Mishnaic Hebrew", ["hi-mid"] = "Middle Hindi", ["hi-mum"] = "Bombay Hindi", ["hsn-hya"] = "Hengyang Xiang", ["hsn-hzh"] = "Hengzhou Xiang", ["hsn-lou"] = "Loudi Xiang", ["hsn-new"] = "New Xiang", ["hsn-old"] = "Old Xiang", ["ht-sdm"] = "Saint Dominican Creole French", ["hye"] = "Eastern Armenian", ["hyw"] = "Western Armenian", ["inc-aav"] = "Avahattha", ["inc-agu"] = "Gurjara Apabhramsa", ["inc-aka"] = "Kasmiri Apabhramsa", ["inc-ama"] = "Maharastri Apabhramsa", ["inc-asa"] = "Sauraseni Apabhramsa", ["inc-ash-pro"] = "Proto-Middle Indo-Aryan", ["inc-ata"] = "Takka Apabhramsa", ["inc-avr"] = "Vracada Apabhramsa", ["inc-mit"] = "Mitanni", ["iro-ohu"] = "Old Wendat", ["iro-omo"] = "Old Mohawk", ["iro-oon"] = "Old Onondaga", ["it-CH"] = "Switzerland Italian", ["itc-lan"] = "Lanuvian", ["itc-ola"] = "Old Latin", ["itc-pra"] = "Praenestine", ["ja-cla"] = "Classical Japanese", ["ja-ear"] = "Early Modern Japanese", ["ja-mid"] = "Middle Japanese", ["ja-mid-ear"] = "Early Middle Japanese", ["ja-mid-lat"] = "Late Middle Japanese", ["jpa"] = "Jewish Palestinian Aramaic", ["jrb"] = "Judeo-Arabic", ["ka-mid"] = "Middle Georgian", ["kbg"] = "Khamba", ["kea-alu"] = "ALUPEC Kabuverdianu", ["kea-bar"] = "Barlavento Kabuverdianu", ["kea-bra"] = "Brava Kabuverdianu", ["kea-bvi"] = "Boa Vista Kabuverdianu", ["kea-fog"] = "Fogo Kabuverdianu", ["kea-mai"] = "Maio Kabuverdianu", ["kea-saa"] = "Santo Antão Kabuverdianu", ["kea-sal"] = "Sal Kabuverdianu", ["kea-san"] = "Santiago Kabuverdianu", ["kea-sni"] = "São Nicolau Kabuverdianu", ["kea-sot"] = "Sotavento Kabuverdianu", ["kea-svi"] = "São Vicente Kabuverdianu", ["kfm"] = "Khunsari", ["khg"] = "Khams Tibetan", ["kho-lat"] = "Late Khotanese", ["kho-old"] = "Old Khotanese", ["kjh-fyu"] = "Fuyu Kyrgyz", ["kjv"] = "Kajkavian Serbo-Croatian", ["klj-arg"] = "Arghu", ["kn-hav"] = "Havigannada", ["kn-kun"] = "Kundagannada", ["ko-cen"] = "Central Korean", ["ko-chu"] = "Chungcheong Korean", ["ko-gan"] = "Gangwon Korean", ["ko-gyg"] = "Gyeonggi Korean", ["ko-gys"] = "Gyeongsang Korean", ["ko-ham"] = "Hamgyong Korean", ["ko-hwa"] = "Hwanghae Korean", ["ko-jeo"] = "Jeolla Korean", ["ko-pyo"] = "Pyongan Korean", ["ko-yuk"] = "Yukjin Korean", ["kok-mid"] = "Middle Konkani", ["kok-old"] = "Old Konkani", ["krl-nor"] = "North Karelian", ["krl-sou"] = "South Karelian", ["ksh"] = "Kölsch", ["kze"] = "Kosena", ["la-afr"] = "African Romance", ["la-cla"] = "Classical Latin", ["la-con"] = "Contemporary Latin", ["la-ecc"] = "Ecclesiastical Latin", ["la-eme"] = "Early Medieval Latin", ["la-lat"] = "Late Latin", ["la-med"] = "Medieval Latin", ["la-new"] = "New Latin", ["la-ren"] = "Renaissance Latin", ["la-vul"] = "Vulgar Latin", ["lij-old"] = "Old Ligurian", ["lld-amp"] = "Ampezan Ladin", ["lld-bad"] = "Badiot Ladin", ["lld-cad"] = "Cadorino Ladin", ["lld-fas"] = "Fascian Ladin", ["lld-fod"] = "Fodom Ladin", ["lld-for"] = "Fornes Ladin", ["lld-ghe"] = "Gherdëina Ladin", ["lld-non"] = "Nones Ladin", ["lmo-old"] = "Old Lombard", ["lng"] = "Lombardic", ["ltc-ear"] = "Early Middle Chinese", ["ltc-lat"] = "Late Middle Chinese", ["lut-nor"] = "Northern Lushootseed", ["lzh-KO"] = "Korean Classical Chinese", ["lzh-VI"] = "Vietnamese Classical Chinese", ["lzh-cii"] = "Ci", ["lzh-cmn"] = "Classical Mandarin", ["lzh-cmn-TW"] = "Classical Taiwanese Mandarin", ["lzh-lit"] = "Literary Chinese", ["lzh-pre"] = "Pre-Classical Chinese", ["lzh-shi"] = "Traditional Chinese poetry", ["lzh-tai"] = "Classical Taishanese", ["lzh-yue"] = "Classical Cantonese", ["mn-cha"] = "Chakhar Mongolian", ["mn-kha"] = "Khalkha Mongolian", ["mn-khr"] = "Khorchin Mongolian", ["mn-ord"] = "Ordos Mongolian", ["mns-eas"] = "Eastern Mansi", ["mns-wes"] = "Western Mansi", ["ms-cla"] = "Classical Malay", ["ms-old"] = "Old Malay", ["mul-tax"] = "taxonomic name", ["nan-anx"] = "Anxi Hokkien", ["nan-cha"] = "Changtai Hokkien", ["nan-hbl-PH"] = "Philippine Hokkien", ["nan-hbl-SG"] = "Singapore Hokkien", ["nan-hbl-TW"] = "Taiwanese Hokkien", ["nan-hou"] = "Houlu Min", ["nan-hui"] = "Hui'an Hokkien", ["nan-jin"] = "Jinjiang Hokkien", ["nan-kin"] = "Kinmenese Hokkien", ["nan-med"] = "Medan Hokkien", ["nan-pen"] = "Penang Hokkien", ["nan-qia"] = "Qianlu Min", ["nan-qua"] = "Quanzhou Hokkien", ["nan-spm"] = "Southern Malaysian Hokkien", ["nan-ton"] = "Tong'an Hokkien", ["nan-xia"] = "Xiamen Hokkien", ["nan-yon"] = "Yongchun Hokkien", ["nan-zha"] = "Zhangzhou Hokkien", ["nan-zho"] = "Zhao'an Hokkien", ["nan-zhp"] = "Zhangping Hokkien", ["nap-old"] = "Old Neapolitan", ["ncb-cam"] = "Camorta", ["ncb-kat"] = "Katchal", ["ncb-nan"] = "Nancowry", ["nds-de"] = "German Low German", ["nds-lpr"] = "Low Prussian", ["nds-nl"] = "Dutch Low Saxon", ["nl-BE"] = "Belgian Dutch", ["non-grn"] = "Greenlandic Norse", ["non-oen"] = "Old East Norse", ["non-own"] = "Old West Norse", ["nrf-grn"] = "Guernsey Norman", ["nrf-jer"] = "Jersey Norman", ["ntz"] = "Natanzi", ["nyq"] = "Nayini", ["oc-ara"] = "Aranese", ["oc-auv"] = "Auvergnat", ["oc-gas"] = "Gascon", ["oc-jud"] = "Shuadit", ["oc-lan"] = "Languedocien", ["oc-lim"] = "Limousin", ["oc-pro"] = "Provençal", ["oc-pro-old"] = "Old Provençal", ["oc-viv"] = "Vivaro-Alpine", ["och-ear"] = "Early Old Chinese", ["och-lat"] = "Late Old Chinese", ["ojp-eas"] = "Eastern Old Japanese", ["okm-ear"] = "Early Middle Korean", ["oko-lat"] = "Late Old Korean", ["okz-ang"] = "Angkorian Old Khmer", ["okz-pre"] = "Pre-Angkorian Old Khmer", ["ont"] = "Ontenu", ["oos"] = "Old Ossetic", ["oos-ear"] = "Early Old Ossetic", ["oos-lat"] = "Late Old Ossetic", ["orc"] = "Orma", ["oru-kan"] = "Kaniguram", ["oru-log"] = "Logar", ["os-dig"] = "Digor Ossetian", ["os-iro"] = "Iron Ossetian", ["osc-luc"] = "Lucanian", ["osc-sam"] = "Samnite", ["otk-kir"] = "Old Kirghiz", ["otk-ork"] = "Orkhon Turkic", ["pal-ear"] = "Early Middle Persian", ["pal-lat"] = "Late Middle Persian", ["peo-ear"] = "Early Old Persian", ["peo-lat"] = "Late Old Persian", ["pfl"] = "Palatine German", ["pl-gor"] = "Goral", ["pl-gre"] = "Greater Polish", ["pl-les"] = "Lesser Polish", ["pl-mas"] = "Masovian Polish", ["pld"] = "Polari", ["pms-old"] = "Old Piedmontese", ["pnb"] = "Western Punjabi", ["pra-abh"] = "Abhiri", ["pra-ard"] = "Ardhamagadhi Prakrit", ["pra-ava"] = "Avanti", ["pra-bah"] = "Bahliki", ["pra-can"] = "Candali", ["pra-dak"] = "Daksinatya", ["pra-dra"] = "Dramili", ["pra-hel"] = "Helu Prakrit", ["pra-kha"] = "Khasa Prakrit", ["pra-mag"] = "Magadhi Prakrit", ["pra-mah"] = "Maharastri Prakrit", ["pra-odr"] = "Odri", ["pra-pai"] = "Paisaci Prakrit", ["pra-pra"] = "Pracya", ["pra-pro"] = "Proto-New Indo-Aryan", ["pra-sab"] = "Sabari", ["pra-sak"] = "Sakari", ["pra-sau"] = "Sauraseni Prakrit", ["prs"] = "Dari", ["ps-afr"] = "Afridi", ["ps-ban"] = "Bannu", ["ps-bng"] = "Bangash", ["ps-cgi"] = "Central Ghilzay", ["ps-jad"] = "Jadrani", ["ps-kak"] = "Kakari", ["ps-kan"] = "Kandahari", ["ps-mah"] = "Mahsudi", ["ps-nea"] = "Northeastern Pashto", ["ps-nwe"] = "Northwestern Pashto", ["ps-pes"] = "Peshawari", ["ps-sea"] = "Southeastern Pashto", ["ps-ser"] = "Sher", ["ps-swe"] = "Southwestern Pashto", ["ps-waz"] = "Waziri", ["ps-xat"] = "Khatak", ["pse-bsm"] = "Besemah", ["pt-BR"] = "Brazilian Portuguese", ["pt-PT"] = "European Portuguese", ["qfa-yke-pro"] = "Proto-Ketic", ["qfa-yko-pro"] = "Proto-Kottic", ["qfa-ypm-pro"] = "Proto-Pumpokolic", ["qfa-yrn-pro"] = "Proto-Arinic", ["qsb-bal"] = "Paleo-Balkan", ["qsb-bma"] = "the BMAC substrate", ["qsb-grc"] = "Pre-Greek", ["qsb-ibe"] = "Paleo-Hispanic", ["qwm-arm"] = "Armeno-Kipchak", ["qwm-cum"] = "Cuman", ["qwm-mam"] = "Mamluk-Kipchak", ["qxq"] = "Qashqai", ["rdb-jir"] = "Jirofti", ["rdb-kah"] = "Kahnuji", ["rgn-old"] = "Old Romagnol", ["rm-gri"] = "Rumantsch Grischun", ["rm-old"] = "Old Romansh", ["rm-put"] = "Puter Romansh", ["rm-srm"] = "Surmiran Romansh", ["rm-srs"] = "Sursilvan Romansh", ["rm-sut"] = "Sutsilvan Romansh", ["rm-val"] = "Vallader Romansh", ["ro-MD"] = "Moldovan", ["roa-oit"] = "Old Italian", ["roa-pro"] = "Proto-Romance", ["rw-kin"] = "Kinyarwanda", ["rw-run"] = "Kirundi", ["sa-bhs"] = "Buddhist Hybrid Sanskrit", ["sa-bra"] = "Brahmanic Sanskrit", ["sa-epi"] = "Epic Sanskrit", ["sa-neo"] = "New Sanskrit", ["sa-rig"] = "Rigvedic Sanskrit", ["sc-nuo"] = "Nuorese", ["sc-old"] = "Old Sardinian", ["sc-src"] = "Logudorese", ["sc-sro"] = "Campidanese", ["scn-old"] = "Old Sicilian", ["sco-ins"] = "Insular Scots", ["sco-nor"] = "Northern Scots", ["sco-sou"] = "Southern Scots", ["sco-uls"] = "Ulster Scots", ["sdz"] = "Sallands", ["sgh-baj"] = "Bajui", ["sgh-bar"] = "Bartangi", ["sgh-bro"] = "Bartangi-Oroshori", ["sgh-oro"] = "Oroshori", ["sgh-ros"] = "Roshani", ["sgh-rsx"] = "Roshani-Khufi", ["sgh-xgb"] = "Khughni-Bajui", ["sgh-xuf"] = "Khufi", ["sgh-xug"] = "Khughni", ["sh-tor"] = "Torlakian Serbo-Croatian", ["shi-med"] = "Medieval Tashelhit", ["si-med"] = "Medieval Sinhalese", ["ska"] = "Skagit", ["slh"] = "Southern Lushootseed", ["sli"] = "Silesian East Central German", ["sno"] = "Snohomish", ["sog-ear"] = "Early Sogdian", ["sog-lat"] = "Late Sogdian", ["soj"] = "Soi", ["ssn"] = "Waata", ["stl"] = "Stellingwerfs", ["sxu"] = "Upper Saxon German", ["ta-mid"] = "Middle Tamil", ["tai-shz"] = "Shangsi Zhuang", ["taq"] = "Tamasheq", ["tbq-pro"] = "Proto-Tibeto-Burman", ["th-ayu"] = "Ayutthaya Old Thai", ["th-old"] = "Old Thai", ["th-suk"] = "Sukhothai Old Thai", ["thv"] = "Tamahaq", ["thv-ght"] = "Ghat", ["thz"] = "Tayert", ["tks-cal"] = "Chali Tati", ["tks-dan"] = "Danesfani", ["tks-ebr"] = "Ebrahimabadi", ["tks-esf"] = "Esfarvarini", ["tks-sag"] = "Sagzabadi", ["tks-tak"] = "Takestani", ["tks-xia"] = "Khiaraji", ["tks-xoz"] = "Khoznini", ["tl-cls"] = "Classical Tagalog", ["tl-old"] = "Old Tagalog", ["tly-anb"] = "Anbarani", ["tly-asa"] = "Asalemi", ["tly-aze"] = "Azerbaijani Talysh", ["tly-cen"] = "Central Talysh", ["tly-fum"] = "Fumani", ["tly-kar"] = "Karganrudi", ["tly-msa"] = "Masali", ["tly-msu"] = "Masulei", ["tly-nor"] = "Northern Talysh", ["tly-san"] = "Shandarmani", ["tly-sou"] = "Southern Talysh", ["tly-tal"] = "Taleshdulabi", ["tly-tul"] = "Tularudi", ["tmr"] = "Jewish Babylonian Aramaic", ["tpw-lga"] = "Língua Geral Amazônica", ["tpw-lgp"] = "Língua Geral Paulista", ["tr-CY"] = "Cypriot Turkish", ["trk-bul-pro"] = "Proto-Bulgar", ["trk-cmn-pro"] = "Proto-Common Turkic", ["trk-ogr-pro"] = "Proto-Oghur", ["trk-ogz-pro"] = "Proto-Oghuz", ["tsk"] = "Tseku", ["ttq"] = "Tawellemmet", ["tw"] = "Twi Akan", ["tw-aku"] = "Akuapem Twi", ["tw-asa"] = "Asante Twi", ["twd"] = "Twents", ["uk-CA"] = "Canadian Ukrainian", ["urj-fpr-pro"] = "Proto-Finno-Permic", ["uz-afg"] = "Afghan Uzbek", ["vaf"] = "Vafsi", ["vec-old"] = "Old Venetan", ["vel"] = "Veluws", ["vsn"] = "Vedic Sanskrit", ["wae"] = "Walser German", ["wep"] = "Westphalian", ["wss"] = "Wasa", ["wuu-chm"] = "Shadi Wu", ["wuu-han"] = "Hangzhounese", ["wuu-nin"] = "Ningbonese", ["wuu-nor"] = "Northern Wu", ["wuu-sha"] = "Shanghainese", ["wuu-suz"] = "Suzhounese", ["wuu-wen"] = "Wenzhounese", ["xaq"] = "Aquitanian", ["xbo-dan"] = "Danube Bulgar", ["xbo-vol"] = "Volga Bulgar", ["xcg"] = "Cisalpine Gaulish", ["xfa-cap"] = "Capenate", ["xh-bha"] = "Bhaca", ["xme-aby"] = "Abyanehi", ["xme-abz"] = "Abuzeydabadi", ["xme-amo"] = "Amorehi", ["xme-ana"] = "Anaraki", ["xme-ard"] = "Ardestani", ["xme-azr"] = "Old Azari", ["xme-bdr"] = "Badrudi", ["xme-bid"] = "Bidhandi", ["xme-bij"] = "Bijagani", ["xme-bor"] = "Borujerdi", ["xme-cim"] = "Chimehi", ["xme-del"] = "Delijani", ["xme-far"] = "Farizandi", ["xme-ham"] = "Hamadani", ["xme-han"] = "Hanjani", ["xme-isf"] = "Isfahani", ["xme-jow"] = "Jowshaqani", ["xme-kaf"] = "Kafroni", ["xme-kah"] = "Kahaki", ["xme-kas"] = "Kashani", ["xme-kes"] = "Kesehi", ["xme-kom"] = "Komjani", ["xme-krm"] = "Kermani", ["xme-mah"] = "Mahallati", ["xme-mey"] = "Meymehi", ["xme-nar"] = "Naraqi", ["xme-nas"] = "Nashalji", ["xme-nus"] = "Nushabadi", ["xme-qal"] = "Qalhari", ["xme-qoh"] = "Qohrudi", ["xme-sed"] = "Sedehi", ["xme-tar"] = "Tari", ["xme-trh"] = "Tarehi", ["xme-ttc-cen"] = "Central Tati", ["xme-ttc-eas"] = "Eastern Tati", ["xme-ttc-nor"] = "Northern Tati", ["xme-ttc-sou"] = "Southern Tati", ["xme-ttc-wes"] = "Western Tati", ["xme-val"] = "Valujerdi", ["xme-var"] = "Varani", ["xme-von"] = "Vonishuni", ["xme-vrz"] = "Varzenehi", ["xme-xur"] = "Khuri", ["xme-yar"] = "Yarandi", ["xme-yaz"] = "Yazdi", ["xme-zef"] = "Zefrehi", ["xme-zor"] = "Zori", ["xmn"] = "Manichaean Middle Persian", ["xng-ear"] = "Early Middle Mongol", ["xng-lat"] = "Late Middle Mongol", ["xnn"] = "Northern Kankanaey", ["xno"] = "Anglo-Norman", ["xno-law"] = "Law French", ["xtg"] = "Transalpine Gaulish", ["xvi"] = "Kamviri", ["yue-HK"] = "Hong Kong Cantonese", ["yue-gua"] = "Guangzhou Cantonese", ["yue-lit"] = "Literary Cantonese", ["yue-wvc"] = "Written vernacular Cantonese", ["zh-postal"] = "Postal Romanization", ["zhx-dan"] = "Danzhou Chinese", ["zhx-tai-wvc"] = "Written vernacular Taishanese", ["zhx-zho"] = "Zhongshan Min", ["zle-mbe"] = "Middle Belarusian", ["zle-mru"] = "Middle Russian", ["zle-muk"] = "Middle Ukrainian", ["zle-ops"] = "Old Pskovian", ["zls-chs-ru"] = "Russian Church Slavonic", ["zls-chs-uk"] = "Ukrainian Church Slavonic", ["zlw-mpl"] = "Middle Polish", ["zrp"] = "Zarphatic", } 4t4gtnxf23weh7kgdqpi5fqs2q9ymmw 828 5995 17432 2026-07-13T08:42:15Z Hiyuune 6766 + 17432 Scribunto text/plain return { ["aav"] = "Austroasiatic", ["aav-khs"] = "Khasian", ["aav-nic"] = "Nicobarese", ["aav-pkl"] = "Pnar-Khasi-Lyngngam", ["afa"] = "Afroasiatic", ["alg"] = "Algonquian", ["alg-abp"] = "Abenaki-Penobscot", ["alg-ara"] = "Arapahoan", ["alg-eas"] = "Eastern Algonquian", ["alg-sfk"] = "Sac-Fox-Kickapoo", ["alv"] = "Atlantic-Congo", ["alv-aah"] = "Ayere-Ahan", ["alv-ada"] = "Adamawa", ["alv-bag"] = "Baga", ["alv-bak"] = "Bak", ["alv-bam"] = "Bambukic", ["alv-bny"] = "Banyum", ["alv-bua"] = "Bua", ["alv-bwj"] = "Bikwin-Jen", ["alv-cng"] = "Cangin", ["alv-ctn"] = "Central Tano", ["alv-dlt"] = "Delta Edoid", ["alv-dur"] = "Duru", ["alv-ede"] = "Ede", ["alv-edk"] = "Edekiri", ["alv-edo"] = "Edoid", ["alv-eeo"] = "Edo-Esan-Ora", ["alv-fli"] = "Fali", ["alv-fwo"] = "Fula-Wolof", ["alv-gbe"] = "Gbe", ["alv-gda"] = "Ga-Dangme", ["alv-gng"] = "Guang", ["alv-gtm"] = "Ghana-Togo Mountain", ["alv-hei"] = "Heiban", ["alv-ido"] = "Idomoid", ["alv-igb"] = "Igboid", ["alv-jfe"] = "Jola-Felupe", ["alv-jol"] = "Jola", ["alv-kim"] = "Kim", ["alv-kis"] = "Kissi", ["alv-krb"] = "Karaboro", ["alv-ktg"] = "Ka-Togo", ["alv-kul"] = "Kulango", ["alv-kwa"] = "Kwa", ["alv-lag"] = "Lagoon", ["alv-lek"] = "Leko", ["alv-lim"] = "Limba", ["alv-lni"] = "Leko-Nimbari", ["alv-mbd"] = "Mbum-Day", ["alv-mbm"] = "Mbum", ["alv-mel"] = "Mel", ["alv-mum"] = "Mumuye", ["alv-mye"] = "Mumuye-Yendang", ["alv-nal"] = "Nalu", ["alv-nce"] = "North-Central Edoid", ["alv-ngb"] = "Nupe-Gbagyi", ["alv-ntg"] = "Na-Togo", ["alv-nup"] = "Nupoid", ["alv-nwd"] = "Northwestern Edoid", ["alv-nyn"] = "Nyun", ["alv-pap"] = "Papel", ["alv-pph"] = "Phla-Pherá", ["alv-ptn"] = "Potou-Tano", ["alv-sav"] = "Savanna", ["alv-sma"] = "Supyire-Mamara", ["alv-snf"] = "Senufo", ["alv-sng"] = "Senegambian", ["alv-snr"] = "Senari", ["alv-swd"] = "Southwestern Edoid", ["alv-tal"] = "Talodi", ["alv-tdj"] = "Tagwana-Djimini", ["alv-ten"] = "Tenda", ["alv-the"] = "Talodi-Heiban", ["alv-von"] = "Volta-Niger", ["alv-wan"] = "Wara-Natyoro", ["alv-wjk"] = "Waja-Kam", ["alv-yek"] = "Yekhee", ["alv-yor"] = "Yoruba", ["alv-yrd"] = "Yoruboid", ["alv-yun"] = "Yungur", ["apa"] = "Apachean", ["aqa"] = "Alacalufan", ["aql"] = "Algic", ["art"] = "constructed", ["ath"] = "Athabaskan", ["ath-nor"] = "North Athabaskan", ["ath-pco"] = "Pacific Coast Athabaskan", ["auf"] = "Arauan", ["aus-arn"] = "Arnhem", ["aus-bub"] = "Bunuban", ["aus-cww"] = "Central New South Wales", ["aus-dal"] = "Daly", ["aus-dyb"] = "Dyirbalic", ["aus-gar"] = "Garawan", ["aus-gun"] = "Gunwinyguan", ["aus-jar"] = "Jarrakan", ["aus-kar"] = "Karnic", ["aus-mir"] = "Mirndi", ["aus-nga"] = "Ngayarda", ["aus-nyu"] = "Nyulnyulan", ["aus-pam"] = "Pama-Nyungan", ["aus-pmn"] = "Paman", ["aus-psw"] = "Southwest Pama-Nyungan", ["aus-rnd"] = "Arandic", ["aus-tnk"] = "Tangkic", ["aus-wdj"] = "Iwaidjan", ["aus-wor"] = "Worrorran", ["aus-yid"] = "Yidinyic", ["aus-yng"] = "Yangmanic", ["aus-yol"] = "Yolngu", ["aus-yuk"] = "Yuin-Kuric", ["awd"] = "Arawak", ["awd-nwk"] = "Nawiki", ["awd-taa"] = "Ta-Arawak", ["azc"] = "Uto-Aztecan", ["azc-cup"] = "Cupan", ["azc-dur"] = "Durango Nahuatl", ["azc-hua"] = "Huasteca Nahuatl", ["azc-nah"] = "Nahuan", ["azc-num"] = "Numic", ["azc-pim"] = "Piman", ["azc-tak"] = "Takic", ["azc-trc"] = "Taracahitic", ["bad"] = "Banda", ["bad-cnt"] = "Central Banda", ["bai"] = "Bamileke", ["bat"] = "Baltic", ["bat-eas"] = "East Baltic", ["bat-wes"] = "West Baltic", ["ber"] = "Berber", ["bnt"] = "Bantu", ["bnt-baf"] = "Bafia", ["bnt-bbo"] = "Bafo-Bonkeng", ["bnt-bdz"] = "Boma-Dzing", ["bnt-bek"] = "Bekwilic", ["bnt-bki"] = "Bena-Kinga", ["bnt-bmo"] = "Bangi-Moi", ["bnt-bne"] = "Northeast Bantu", ["bnt-bnm"] = "Bangi-Ntomba", ["bnt-boa"] = "Boan", ["bnt-bot"] = "Botatwe", ["bnt-bsa"] = "Basaa", ["bnt-bsh"] = "Bushoong", ["bnt-bso"] = "Southern Bantu", ["bnt-bta"] = "Bati-Angba", ["bnt-btb"] = "Beti", ["bnt-bte"] = "Bangi-Tetela", ["bnt-bun"] = "Buja-Ngombe", ["bnt-chg"] = "Chaga", ["bnt-cht"] = "Chaga-Taita", ["bnt-clu"] = "Chokwe-Luchazi", ["bnt-com"] = "Comorian", ["bnt-glb"] = "Great Lakes Bantu", ["bnt-haj"] = "Haya-Jita", ["bnt-kak"] = "Kako", ["bnt-kav"] = "Kavango", ["bnt-kbi"] = "Komo-Bira", ["bnt-kel"] = "Kele", ["bnt-kil"] = "Kilombero", ["bnt-kka"] = "Kikuyu-Kamba", ["bnt-kmb"] = "Kimbundu", ["bnt-kng"] = "Kongo", ["bnt-kpw"] = "Kpwe", ["bnt-ksb"] = "Kavango-Southwest Bantu", ["bnt-kts"] = "Kele-Tsogo", ["bnt-lbn"] = "Luban", ["bnt-leb"] = "Lebonya", ["bnt-lgb"] = "Lega-Binja", ["bnt-lok"] = "Logooli-Kuria", ["bnt-lub"] = "Luba", ["bnt-lun"] = "Lunda", ["bnt-mak"] = "Makua", ["bnt-mbb"] = "Mboshi-Buja", ["bnt-mbe"] = "Mbole-Enya", ["bnt-mbi"] = "Mbinga", ["bnt-mbo"] = "Mboshi", ["bnt-mbt"] = "Mbete", ["bnt-mby"] = "Mbeya", ["bnt-mij"] = "Mijikenda", ["bnt-mka"] = "Makaa", ["bnt-mne"] = "Manenguba", ["bnt-mnj"] = "Makaa-Njem", ["bnt-mon"] = "Mongo", ["bnt-mra"] = "Mbugwe-Rangi", ["bnt-msl"] = "Masaba-Luhya", ["bnt-mwi"] = "Mwika", ["bnt-ncb"] = "Northeast Coast Bantu", ["bnt-ndb"] = "Ndzem-Bomwali", ["bnt-ngn"] = "Ngondi-Ngiri", ["bnt-ngu"] = "Nguni", ["bnt-nya"] = "Nyali", ["bnt-nyb"] = "Nyanga-Buyi", ["bnt-nyg"] = "Nyoro-Ganda", ["bnt-nys"] = "Nyasa", ["bnt-nze"] = "Nzebi", ["bnt-ova"] = "Ovambo", ["bnt-par"] = "Pare", ["bnt-pen"] = "Pende", ["bnt-pob"] = "Pomo-Bomwali", ["bnt-ruk"] = "Rukwa", ["bnt-run"] = "Rungwe", ["bnt-rur"] = "Rufiji-Ruvuma", ["bnt-ruv"] = "Ruvu", ["bnt-rvm"] = "Ruvuma", ["bnt-sab"] = "Sabaki", ["bnt-saw"] = "Sawabantu", ["bnt-sbi"] = "Sabi", ["bnt-seu"] = "Seuta", ["bnt-shh"] = "Shi-Havu", ["bnt-sho"] = "Shona", ["bnt-sir"] = "Sira", ["bnt-ske"] = "Soko-Kele", ["bnt-sna"] = "Sena", ["bnt-sts"] = "Sotho-Tswana", ["bnt-swb"] = "Southwest Bantu", ["bnt-swh"] = "Swahili", ["bnt-tek"] = "Teke", ["bnt-tet"] = "Tetela", ["bnt-tkc"] = "Central Teke", ["bnt-tkm"] = "Takama", ["bnt-tmb"] = "Teke-Mbede", ["bnt-tso"] = "Tsogo", ["bnt-tsr"] = "Tswa-Ronga", ["bnt-yak"] = "Yaka", ["bnt-yko"] = "Yasa-Kombe", ["bnt-zbi"] = "Zamba-Binza", ["btk"] = "Batak", ["cau-abz"] = "Abkhaz-Abaza", ["cau-and"] = "Andian", ["cau-ava"] = "Avaro-Andian", ["cau-cir"] = "Circassian", ["cau-drg"] = "Dargwa", ["cau-esm"] = "Eastern Samur", ["cau-ets"] = "East Tsezian", ["cau-lzg"] = "Lezghian", ["cau-nec"] = "Northeast Caucasian", ["cau-nkh"] = "Nakh", ["cau-nwc"] = "Northwest Caucasian", ["cau-sam"] = "Samur", ["cau-ssm"] = "Southern Samur", ["cau-tsz"] = "Tsezian", ["cau-vay"] = "Vainakh", ["cau-wsm"] = "Western Samur", ["cau-wts"] = "West Tsezian", ["cba"] = "Chibchan", ["ccs"] = "Kartvelian", ["ccs-gzn"] = "Georgian-Zan", ["ccs-zan"] = "Zan", ["cdc"] = "Chadic", ["cdc-cbm"] = "Central Chadic", ["cdc-est"] = "East Chadic", ["cdc-mas"] = "Masa", ["cdc-wst"] = "West Chadic", ["cdd"] = "Caddoan", ["cel"] = "Celtic", ["cel-brs"] = "Southwestern Brythonic", ["cel-brw"] = "Western Brythonic", ["cel-bry"] = "Brythonic", ["cel-gae"] = "Goidelic", ["cel-his"] = "Hispano-Celtic", ["cel-ins"] = "Insular Celtic", ["chi"] = "Chimakuan", ["chm"] = "Mari", ["cmc"] = "Chamic", ["crp"] = "creole or pidgin", ["csu"] = "Central Sudanic", ["csu-bba"] = "Bongo-Bagirmi", ["csu-bbk"] = "Bongo-Baka", ["csu-bgr"] = "Bagirmi", ["csu-bkr"] = "Birri-Kresh", ["csu-ecs"] = "Eastern Central Sudanic", ["csu-kab"] = "Kaba", ["csu-lnd"] = "Lendu", ["csu-maa"] = "Mangbetu", ["csu-mle"] = "Mangbutu-Lese", ["csu-mma"] = "Moru-Madi", ["csu-sar"] = "Sara", ["csu-val"] = "Vale", ["cus"] = "Cushitic", ["cus-cen"] = "Central Cushitic", ["cus-eas"] = "East Cushitic", ["cus-hec"] = "Highland East Cushitic", ["cus-som"] = "Somaloid", ["cus-sou"] = "South Cushitic", ["day"] = "Land Dayak", ["del"] = "Lenape", ["den"] = "Slavey", ["dmn"] = "Mande", ["dmn-bbu"] = "Bisa-Busa", ["dmn-emn"] = "East Manding", ["dmn-jje"] = "Jogo-Jeri", ["dmn-man"] = "Manding", ["dmn-mda"] = "Mano-Dan", ["dmn-mdc"] = "Central Mande", ["dmn-mde"] = "Eastern Mande", ["dmn-mdw"] = "Western Mande", ["dmn-mjo"] = "Manding-Jogo", ["dmn-mmo"] = "Manding-Mokole", ["dmn-mnk"] = "Maninka", ["dmn-mnw"] = "Northwestern Mande", ["dmn-mok"] = "Mokole", ["dmn-mse"] = "Southeastern Mande", ["dmn-msw"] = "Southwestern Mande", ["dmn-mva"] = "Manding-Vai", ["dmn-nbe"] = "Nwa-Beng", ["dmn-sam"] = "Samo", ["dmn-smg"] = "Samogo", ["dmn-snb"] = "Soninke-Bobo", ["dmn-sya"] = "Susu-Yalunka", ["dmn-vak"] = "Vai-Kono", ["dmn-wmn"] = "West Manding", ["dra"] = "Dravidian", ["dra-cen"] = "Central Dravidian", ["dra-gki"] = "Gondi-Kui", ["dra-gon"] = "Gondi", ["dra-imd"] = "Irula-Muduga", ["dra-kan"] = "Kannadoid", ["dra-kki"] = "Konda-Kui", ["dra-kml"] = "Kurux-Malto", ["dra-knk"] = "Kolami-Naiki", ["dra-kod"] = "Kodagu", ["dra-kor"] = "Koraga", ["dra-mal"] = "Malayalamoid", ["dra-mdy"] = "Madiya", ["dra-mlo"] = "Malto", ["dra-mur"] = "Muria", ["dra-nor"] = "North Dravidian", ["dra-pgd"] = "Parji-Gadaba", ["dra-sdo"] = "South Dravidian I", ["dra-sdt"] = "South Dravidian II", ["dra-sou"] = "South Dravidian", ["dra-tam"] = "Tamiloid", ["dra-tel"] = "Teluguic", ["dra-tkd"] = "Tamil-Kodagu", ["dra-tkn"] = "Tamil-Kannada", ["dra-tkt"] = "Toda-Kota", ["dra-tlk"] = "Tulu-Koraga", ["dra-tml"] = "Tamil-Malayalam", ["egx"] = "Egyptian", ["ero"] = "Horpa", ["esx"] = "Eskimo-Aleut", ["esx-esk"] = "Eskimo", ["esx-inu"] = "Inuit", ["euq"] = "Vasconic", ["gba"] = "Gbaya", ["gba-eas"] = "Eastern Gbaya", ["gba-sou"] = "Southern Gbaya", ["gba-wes"] = "Western Gbaya", ["gem"] = "Germanic", ["gio"] = "Gelao", ["gme"] = "East Germanic", ["gmq"] = "North Germanic", ["gmq-eas"] = "East Scandinavian", ["gmq-ins"] = "Insular Scandinavian", ["gmq-wes"] = "West Scandinavian", ["gmw"] = "West Germanic", ["gmw-afr"] = "Anglo-Frisian", ["gmw-ang"] = "Anglic", ["gmw-fri"] = "Frisian", ["gmw-frk"] = "Low Franconian", ["gmw-hgm"] = "High German", ["gmw-ian"] = "Irish Anglo-Norman", ["gmw-lgm"] = "Low German", ["gmw-nsg"] = "North Sea Germanic", ["gn"] = "Guarani", ["grb"] = "Grebo proper", ["grk"] = "Hellenic", ["him"] = "Western Pahari", ["hmn"] = "Hmongic", ["hmx"] = "Hmong-Mien", ["hmx-mie"] = "Mienic", ["hok"] = "Hokan", ["hyx"] = "Armenian", ["iir"] = "Indo-Iranian", ["iir-nur"] = "Nuristani", ["ijo"] = "Ijoid", ["inc"] = "Indo-Aryan", ["inc-bas"] = "Bengali-Assamese", ["inc-bhi"] = "Bhil", ["inc-bih"] = "Bihari", ["inc-cen"] = "Central Indo-Aryan", ["inc-chi"] = "Chitrali", ["inc-dar"] = "Dardic", ["inc-dng"] = "Dangari", ["inc-dre"] = "Eastern Dardic", ["inc-eas"] = "Eastern Indo-Aryan", ["inc-hal"] = "Halbic", ["inc-hie"] = "Eastern Hindi", ["inc-hiw"] = "Western Hindi", ["inc-hnd"] = "Hindustani", ["inc-ins"] = "Insular Indo-Aryan", ["inc-kas"] = "Kashmiric", ["inc-koh"] = "Kohistani", ["inc-krd"] = "KRDS languages", ["inc-kun"] = "Kunar", ["inc-mid"] = "Middle Indo-Aryan", ["inc-nor"] = "Northern Indo-Aryan", ["inc-nwe"] = "Northwestern Indo-Aryan", ["inc-old"] = "Old Indo-Aryan", ["inc-pah"] = "Pahari", ["inc-pan"] = "Punjabic", ["inc-pas"] = "Pashayi", ["inc-rom"] = "Romani", ["inc-shn"] = "Shinaic", ["inc-snd"] = "Sindhic", ["inc-sou"] = "Southern Indo-Aryan", ["inc-tha"] = "Tharu", ["inc-wes"] = "Western Indo-Aryan", ["ine"] = "Indo-European", ["ine-ana"] = "Anatolian", ["ine-bsl"] = "Balto-Slavic", ["ine-grp"] = "Graeco-Phrygian", ["ine-luw"] = "Luwic", ["ine-toc"] = "Tocharian", ["ira"] = "Iranian", ["ira-cen"] = "Central Iranian", ["ira-csp"] = "Caspian", ["ira-kms"] = "Komisenian", ["ira-mid"] = "Middle Iranian", ["ira-mny"] = "Munji-Yidgha", ["ira-mpr"] = "Medo-Parthian", ["ira-msh"] = "Mazanderani-Shahmirzadi", ["ira-nei"] = "Northeastern Iranian", ["ira-nwi"] = "Northwestern Iranian", ["ira-old"] = "Old Iranian", ["ira-orp"] = "Ormuri-Parachi", ["ira-pat"] = "Pathan", ["ira-sbc"] = "Sogdo-Bactrian", ["ira-sei"] = "Southeastern Iranian", ["ira-sgc"] = "Sogdic", ["ira-sgi"] = "Sanglechi-Ishkashimi", ["ira-shr"] = "Shughni-Roshani", ["ira-shy"] = "Shughni-Yazghulami", ["ira-swi"] = "Southwestern Iranian", ["ira-sym"] = "Shughni-Yazghulami-Munji", ["ira-wes"] = "Western Iranian", ["ira-zgr"] = "Zaza-Gorani", ["iro"] = "Iroquoian", ["iro-nor"] = "North Iroquoian", ["itc"] = "Italic", ["itc-laf"] = "Latino-Faliscan", ["itc-sbl"] = "Osco-Umbrian", ["jpx"] = "Japonic", ["jpx-nry"] = "Northern Ryukyuan", ["jpx-ryu"] = "Ryukyuan", ["jpx-sry"] = "Southern Ryukyuan", ["kar"] = "Karen", ["kca"] = "Khanty", ["khi-kal"] = "Kalahari Khoe", ["khi-khk"] = "Khoekhoe", ["khi-kho"] = "Khoe", ["khi-kkw"] = "Khoe-Kwadi", ["khi-kxa"] = "Kx'a", ["khi-tuu"] = "Tuu", ["kro"] = "Kru", ["kro-aiz"] = "Aizi", ["kro-bet"] = "Bété", ["kro-did"] = "Dida", ["kro-ekr"] = "Eastern Kru", ["kro-grb"] = "Grebo", ["kro-wee"] = "Wee", ["kro-wkr"] = "Western Kru", ["ku"] = "Kurdish", ["kv"] = "Komi", ["map"] = "Austronesian", ["map-ata"] = "Atayalic", ["mjg"] = "Monguor", ["mkh"] = "Mon-Khmer", ["mkh-asl"] = "Aslian", ["mkh-ban"] = "Bahnaric", ["mkh-kat"] = "Katuic", ["mkh-khm"] = "Khmuic", ["mkh-kmr"] = "Khmeric", ["mkh-mnc"] = "Monic", ["mkh-mng"] = "Mangic", ["mkh-nbn"] = "North Bahnaric", ["mkh-pal"] = "Palaungic", ["mkh-pea"] = "Pearic", ["mkh-pkn"] = "Pakanic", ["mkh-vie"] = "Vietic", ["mno"] = "Manobo", ["mns"] = "Mansi", ["mun"] = "Munda", ["myn"] = "Mayan", ["nai-cat"] = "Catawban", ["nai-chu"] = "Chumashan", ["nai-ckn"] = "Chinookan", ["nai-coo"] = "Coosan", ["nai-jcq"] = "Jicaquean", ["nai-ker"] = "Keresan", ["nai-klp"] = "Kalapuyan", ["nai-kta"] = "Kiowa-Tanoan", ["nai-len"] = "Lencan", ["nai-mdu"] = "Maiduan", ["nai-min"] = "Misumalpan", ["nai-miz"] = "Mixe-Zoquean", ["nai-mus"] = "Muskogean", ["nai-pak"] = "Pakawan", ["nai-pal"] = "Palaihnihan", ["nai-plp"] = "Plateau Penutian", ["nai-pom"] = "Pomoan", ["nai-sca"] = "Siouan-Catawban", ["nai-shp"] = "Sahaptian", ["nai-shs"] = "Shastan", ["nai-tot"] = "Totozoquean", ["nai-tqn"] = "Tequistlatecan", ["nai-tsi"] = "Tsimshianic", ["nai-ttn"] = "Totonacan", ["nai-utn"] = "Utian", ["nai-wtq"] = "Wintuan", ["nai-xin"] = "Xincan", ["nai-ykn"] = "Yukian", ["nai-you"] = "Yok-Utian", ["nai-yuc"] = "Yuman-Cochimí", ["ngf"] = "Trans-New Guinea", ["ngf-ais"] = "Aisian", ["ngf-ang"] = "Angan", ["ngf-ank"] = "Angal-Kewa", ["ngf-ask"] = "Asmat-Kamoro", ["ngf-asm"] = "Asmat", ["ngf-ata"] = "Ankave-Tainae-Akoye", ["ngf-awd"] = "Awyu-Dumut", ["ngf-awy"] = "Awyu", ["ngf-bda"] = "Becking-Dawi", ["ngf-bin"] = "Binanderean", ["ngf-boa"] = "Boane", ["ngf-bos"] = "Bosavi", ["ngf-bsi"] = "Baruya-Simbari", ["ngf-cda"] = "Central Dani", ["ngf-chw"] = "Chimbu-Wahgi", ["ngf-dag"] = "Dagan", ["ngf-dal"] = "Dallman", ["ngf-dan"] = "Dani", ["ngf-dum"] = "Dumut", ["ngf-ehu"] = "Eastern Huon", ["ngf-eku"] = "East Kutubuan", ["ngf-enc"] = "Engic", ["ngf-eng"] = "Engan", ["ngf-era"] = "Erap", ["ngf-eso"] = "East Sogeram", ["ngf-est"] = "East Strickland", ["ngf-eva"] = "Evapia", ["ngf-fgi"] = "Fore-Gimi", ["ngf-fhu"] = "Finisterre-Huon", ["ngf-fin"] = "Finisterre", ["ngf-gah"] = "Gahuku", ["ngf-gau"] = "Gauwa", ["ngf-gaw"] = "Greater Awyu", ["ngf-gbi"] = "Greater Binanderean", ["ngf-gko"] = "Gaena-Korafe", ["ngf-gmo"] = "Gusap-Mot", ["ngf-gor"] = "Goroka", ["ngf-gsu"] = "Gogodala-Suki", ["ngf-gum"] = "Gum", ["ngf-gvd"] = "Grand Valley Dani", ["ngf-hag"] = "Hagen", ["ngf-han"] = "Hanseman", ["ngf-huo"] = "Huon", ["ngf-jim"] = "Jimi", ["ngf-kab"] = "Kabwum", ["ngf-kai"] = "Kainantu", ["ngf-kak"] = "Kalam-Kobon", ["ngf-kau"] = "Kaukombar", ["ngf-kbm"] = "Kosorong-Burum-Mindik", ["ngf-kgo"] = "Kainantu-Goroka", ["ngf-khu"] = "Kewa-Huli", ["ngf-kma"] = "Kâte-Mape", ["ngf-kme"] = "Kapau-Menya", ["ngf-koi"] = "Koiarian", ["ngf-kok"] = "Kokon", ["ngf-kow"] = "Kowan", ["ngf-ksa"] = "Kalam-Southern Adelbert", ["ngf-kto"] = "Kube-Tobo", ["ngf-kts"] = "Komyandaret-Tsaukambo", ["ngf-kum"] = "Kumil", ["ngf-kya"] = "Kamano-Yagaria", ["ngf-lok"] = "Lowland Ok", ["ngf-mab"] = "Mabuso", ["ngf-mad"] = "Madang", ["ngf-mek"] = "Mek", ["ngf-min"] = "Mindjim", ["ngf-mok"] = "Mountain Ok", ["ngf-mom"] = "Mombum", ["ngf-msu"] = "Mian-Suganga", ["ngf-nad"] = "Northern Adelbert", ["ngf-nbi"] = "North Binanderean", ["ngf-nde"] = "Ndeiram", ["ngf-ngn"] = "Ngalik-Nduga", ["ngf-nso"] = "North Sogeram", ["ngf-num"] = "Numugen", ["ngf-nur"] = "Nuru", ["ngf-nwh"] = "Northwest Hanseman", ["ngf-oen"] = "Outer Engan", ["ngf-okk"] = "Ok", ["ngf-omo"] = "Omosan", ["ngf-oro"] = "Orokaivic", ["ngf-pan"] = "Paniai Lakes", ["ngf-pek"] = "Peka", ["ngf-pom"] = "Pomoikan", ["ngf-rai"] = "Rai Coast", ["ngf-sab"] = "Sabakor", ["ngf-sad"] = "Southern Adelbert", ["ngf-sak"] = "Sau-Angal-Kewa", ["ngf-san"] = "Sankwep", ["ngf-sbh"] = "South Bird's Head", ["ngf-sim"] = "Simbu", ["ngf-sog"] = "Sogeram", ["ngf-sop"] = "Sopac", ["ngf-taa"] = "Tainae-Akoye", ["ngf-tai"] = "Tairora", ["ngf-tib"] = "Tiboran", ["ngf-tna"] = "Tangko-Nakai", ["ngf-uru"] = "Uruwa", ["ngf-usi"] = "Utu-Silopi", ["ngf-waa"] = "Wantoat-Awara", ["ngf-wah"] = "Wahgi", ["ngf-wan"] = "Wantoatic", ["ngf-war"] = "Warup", ["ngf-woj"] = "Wojokesic", ["ngf-wok"] = "West Ok", ["ngf-wso"] = "West Sogeram", ["ngf-yag"] = "Yaganon", ["ngf-yal"] = "Yali", ["ngf-yar"] = "Yareban", ["ngf-ynu"] = "Yau-Nungon", ["ngf-yup"] = "Yupna", ["nic"] = "Niger-Congo", ["nic-alu"] = "Alumic", ["nic-bas"] = "Basa", ["nic-bbe"] = "Eastern Beboid", ["nic-bco"] = "Benue-Congo", ["nic-bcr"] = "Bantoid-Cross", ["nic-bdn"] = "Northern Bantoid", ["nic-bds"] = "Southern Bantoid", ["nic-beb"] = "Beboid", ["nic-ben"] = "Bendi", ["nic-beo"] = "Beromic", ["nic-bod"] = "Bantoid", ["nic-buk"] = "Buli-Koma", ["nic-bwa"] = "Bwa", ["nic-cde"] = "Central Delta", ["nic-cri"] = "Cross River", ["nic-dag"] = "Dagbani", ["nic-dak"] = "Dakoid", ["nic-dge"] = "Escarpment Dogon", ["nic-dgw"] = "West Dogon", ["nic-eko"] = "Ekoid", ["nic-eov"] = "Eastern Oti-Volta", ["nic-fru"] = "Furu", ["nic-gne"] = "Eastern Gurunsi", ["nic-gnn"] = "Northern Gurunsi", ["nic-gns"] = "Gurunsi", ["nic-gnw"] = "Western Gurunsi", ["nic-gre"] = "Eastern Grassfields", ["nic-grf"] = "Grassfields", ["nic-grm"] = "Gurma", ["nic-grs"] = "Southwest Grassfields", ["nic-gur"] = "Gur", ["nic-ief"] = "Ibibio-Efik", ["nic-jer"] = "Jera", ["nic-jkn"] = "Jukunoid", ["nic-jrn"] = "Jarawan", ["nic-jrw"] = "Jarawa", ["nic-kam"] = "Kambari", ["nic-kau"] = "Kauru", ["nic-kmk"] = "Kamuku", ["nic-kne"] = "East Kainji", ["nic-knj"] = "Kainji", ["nic-knn"] = "Northwest Kainji", ["nic-ktl"] = "Katloid", ["nic-lcr"] = "Lower Cross River", ["nic-mam"] = "Mamfe", ["nic-mba"] = "Mbam", ["nic-mbc"] = "Mba", ["nic-mbw"] = "West Mbam", ["nic-mmb"] = "Mambiloid", ["nic-mom"] = "Momo", ["nic-mre"] = "Moré", ["nic-ngd"] = "Ngbandi", ["nic-nge"] = "Ngemba", ["nic-ngk"] = "Ngbaka", ["nic-nin"] = "Ninzic", ["nic-nka"] = "Nkambe", ["nic-nkb"] = "Baka", ["nic-nke"] = "Eastern Ngbaka", ["nic-nkg"] = "Gbanziri", ["nic-nkk"] = "Kpala", ["nic-nkm"] = "Mbaka", ["nic-nkw"] = "Western Ngbaka", ["nic-npd"] = "North Plateau Dogon", ["nic-nun"] = "Nun", ["nic-nwa"] = "Nanga-Walo", ["nic-ogo"] = "Ogoni", ["nic-ovo"] = "Oti-Volta", ["nic-pla"] = "Platoid", ["nic-plc"] = "Central Plateau", ["nic-pld"] = "Plains Dogon", ["nic-ple"] = "East Plateau", ["nic-pls"] = "South Plateau", ["nic-plt"] = "Plateau", ["nic-ras"] = "Rashad", ["nic-rnc"] = "Central Ring", ["nic-rng"] = "Ring", ["nic-rnn"] = "Northern Ring", ["nic-rnw"] = "Western Ring", ["nic-ser"] = "Sere", ["nic-shi"] = "Shiroro", ["nic-sis"] = "Sisaala", ["nic-tar"] = "Tarokoid", ["nic-tiv"] = "Tivoid", ["nic-tvc"] = "Central Tivoid", ["nic-tvn"] = "Northern Tivoid", ["nic-ubg"] = "Ubangian", ["nic-uce"] = "East-West Upper Cross River", ["nic-ucn"] = "North-South Upper Cross River", ["nic-ucr"] = "Upper Cross River", ["nic-vco"] = "Volta-Congo", ["nic-wov"] = "Western Oti-Volta", ["nic-ykb"] = "Yukubenic", ["nic-ymb"] = "Yambasa", ["nic-yon"] = "Yom-Nawdm", ["njo"] = "Ao", ["nub"] = "Nubian", ["nub-hil"] = "Hill Nubian", ["nur-nor"] = "Northern Nuristani", ["nur-sou"] = "Southern Nuristani", ["omq"] = "Oto-Manguean", ["omq-cha"] = "Chatino", ["omq-chi"] = "Chinantecan", ["omq-cui"] = "Cuicatec", ["omq-maz"] = "Mazatecan", ["omq-mix"] = "Mixtecan", ["omq-mxt"] = "Mixtec", ["omq-otp"] = "Oto-Pamean", ["omq-pop"] = "Popolocan", ["omq-tri"] = "Triqui", ["omq-zap"] = "Zapotecan", ["omq-zpc"] = "Zapotec", ["omv"] = "Omotic", ["omv-aro"] = "Aroid", ["omv-diz"] = "Dizoid", ["omv-eom"] = "East Ometo", ["omv-gon"] = "Gonga", ["omv-mao"] = "Mao", ["omv-nom"] = "North Ometo", ["omv-ome"] = "Ometo", ["oto"] = "Otomian", ["oto-otm"] = "Otomi", ["paa"] = "Papuan", ["paa-aia"] = "Aian", ["paa-alp"] = "Alor-Pantar", ["paa-amu"] = "Amto-Musan", ["paa-ani"] = "Anim", ["paa-ara"] = "Arapesh", ["paa-arf"] = "Arafundi", ["paa-ata"] = "Ataitan", ["paa-baa"] = "Bayono-Awbono", ["paa-bai"] = "Baining", ["paa-baw"] = "Bosngun-Awar", ["paa-bew"] = "Bewani", ["paa-boa"] = "Boazi", ["paa-bor"] = "Border", ["paa-bul"] = "Bulaka River", ["paa-bvi"] = "Betaf-Vitou", ["paa-clp"] = "Central Lakes Plain", ["paa-dtu"] = "Doso-Turumsa", ["paa-ebh"] = "East Bird's Head", ["paa-eel"] = "Eastern Eleman", ["paa-egb"] = "East Geelvink Bay", ["paa-eke"] = "East Keram", ["paa-ele"] = "Eleman", ["paa-elp"] = "East Lakes Plain", ["paa-epw"] = "Eastern Pauwasi", ["paa-etf"] = "Eastern Trans-Fly", ["paa-eti"] = "East Timor", ["paa-fas"] = "Fas", ["paa-flp"] = "Far West Lakes Plain", ["paa-gkw"] = "Greater Kwerba", ["paa-gto"] = "Galela-Tobelo", ["paa-hya"] = "Heyo-Yahang", ["paa-ing"] = "Inland Gulf", ["paa-isk"] = "Inner Sko", ["paa-iwa"] = "Iwam", ["paa-kae"] = "Kamula-Elevala", ["paa-kan"] = "Kanum", ["paa-kay"] = "Kayagaric", ["paa-ker"] = "Keram", ["paa-kiw"] = "Kiwaian", ["paa-kko"] = "Kaure-Kosare", ["paa-koa"] = "Kombio-Arapesh", ["paa-kol"] = "Kolopom", ["paa-kom"] = "Kombio", ["paa-kun"] = "Kunimaipan", ["paa-kwa"] = "Kwalean", ["paa-kwe"] = "Kwerba proper", ["paa-kwo"] = "Kwomtari", ["paa-lla"] = "Loloda-Laba", ["paa-lma"] = "Left May", ["paa-lmu"] = "Lepki-Murkim", ["paa-lpl"] = "Lakes Plain", ["paa-lra"] = "Lower Ramu", ["paa-lse"] = "Lower Sepik", ["paa-mai"] = "Mairasi", ["paa-mal"] = "Mailuan", ["paa-mam"] = "Maimai", ["paa-man"] = "Manubaran", ["paa-mar"] = "Marienberg", ["paa-may"] = "Maybratic", ["paa-mbi"] = "Mbaham-Iha", ["paa-mby"] = "Marind-Boazi-Yaqay", ["paa-mmu"] = "Mandi-Muniwara", ["paa-mon"] = "Monumbo", ["paa-mri"] = "Marindic", ["paa-nam"] = "Nambu", ["paa-nbo"] = "North Bougainville", ["paa-ndu"] = "Ndu", ["paa-ngk"] = "Ngkolmpu", ["paa-nha"] = "North Halmahera", ["paa-nim"] = "Nimboran", ["paa-nnd"] = "Nuclear Ndu", ["paa-nnh"] = "Northern North Halmahera", ["paa-nto"] = "Namla-Tofanma", ["paa-ott"] = "Ottilien", ["paa-pah"] = "Pahoturi River", ["paa-pal"] = "Palei", ["paa-pia"] = "Piawi", ["paa-pio"] = "Piore River", ["paa-por"] = "Porapora", ["paa-ram"] = "Ramu", ["paa-rsa"] = "Rasawa-Saponi", ["paa-rub"] = "Ruboni", ["paa-saa"] = "Samarokena-Airoran", ["paa-sah"] = "Sahu", ["paa-sbo"] = "South Bougainville", ["paa-sen"] = "Sentani", ["paa-sep"] = "Sepik", ["paa-shi"] = "Serra Hills", ["paa-sko"] = "Sko", ["paa-sng"] = "Senagi", ["paa-taa"] = "Taikat-Awyi", ["paa-tam"] = "Tamolan", ["paa-tap"] = "Timor-Alor-Pantar", ["paa-teb"] = "Teberan", ["paa-tir"] = "Tirio", ["paa-tki"] = "Turama-Kikori", ["paa-ton"] = "Tonda", ["paa-too"] = "Tor-Orya", ["paa-tor"] = "Tor", ["paa-trr"] = "Torricelli", ["paa-tti"] = "Ternate-Tidore", ["paa-wal"] = "Walio", ["paa-wap"] = "Wapei", ["paa-war"] = "Waris", ["paa-wbh"] = "West Bird's Head", ["paa-wel"] = "Western Eleman", ["paa-wig"] = "West Inland Gulf", ["paa-wke"] = "West Keram", ["paa-wko"] = "Wára-Kómnzo", ["paa-wlp"] = "West Lakes Plain", ["paa-wpa"] = "Wapei-Palei", ["paa-wpw"] = "Western Pauwasi", ["paa-yam"] = "Yam", ["paa-yaq"] = "Yaqayic", ["paa-ysa"] = "Yawa-Saweru", ["paa-yua"] = "Yuat", ["phi"] = "Philippine", ["phi-kal"] = "Kalamian", ["poz"] = "Malayo-Polynesian", ["poz-aay"] = "Admiralty Islands", ["poz-bnn"] = "North Bornean", ["poz-bre"] = "East Barito", ["poz-brw"] = "West Barito", ["poz-bss"] = "Bali-Sasak-Sumbawa", ["poz-btk"] = "Bungku-Tolaki", ["poz-cet"] = "Central-Eastern Malayo-Polynesian", ["poz-clb"] = "Celebic", ["poz-cln"] = "New Caledonian", ["poz-cma"] = "Central Maluku", ["poz-hce"] = "Halmahera-Cenderawasih", ["poz-kal"] = "Kaili-Pamona", ["poz-lgx"] = "Lampungic", ["poz-mcm"] = "Malayo-Chamic", ["poz-mic"] = "Micronesian", ["poz-mly"] = "Malayic", ["poz-msa"] = "Malayo-Sumbawan", ["poz-mun"] = "Muna-Buton", ["poz-nws"] = "Northwest Sumatran", ["poz-occ"] = "Central-Eastern Oceanic", ["poz-oce"] = "Oceanic", ["poz-ocs"] = "Southern Oceanic", ["poz-ocw"] = "Western Oceanic", ["poz-pcc"] = "Central Pacific", ["poz-pep"] = "Eastern Polynesian", ["poz-pnp"] = "Nuclear Polynesian", ["poz-pol"] = "Polynesian", ["poz-san"] = "Sabahan", ["poz-sbj"] = "Sama-Bajaw", ["poz-slb"] = "Saluan-Banggai", ["poz-sls"] = "Southeast Solomonic", ["poz-ssw"] = "South Sulawesi", ["poz-stm"] = "St. Matthias", ["poz-swa"] = "North Sarawakan", ["poz-tem"] = "Temotu", ["poz-tim"] = "Timoric", ["poz-ton"] = "Tongic", ["poz-tot"] = "Tomini-Tolitoli", ["poz-vnc"] = "Central Vanuatu", ["poz-vnn"] = "North Vanuatu", ["poz-vns"] = "South Vanuatu", ["poz-wot"] = "Wotu-Wolio", ["pqe"] = "Eastern Malayo-Polynesian", ["qfa-adc"] = "Central Great Andamanese", ["qfa-adm"] = "Great Andamanese", ["qfa-adn"] = "Northern Great Andamanese", ["qfa-ads"] = "Southern Great Andamanese", ["qfa-ain"] = "Ainuic", ["qfa-bej"] = "Be-Jizhao", ["qfa-bet"] = "Be-Tai", ["qfa-buy"] = "Buyang", ["qfa-cka"] = "Chukotko-Kamchatkan", ["qfa-ckn"] = "Chukotkan", ["qfa-cnt"] = "contact", ["qfa-cre"] = "creole", ["qfa-dgn"] = "Dogon", ["qfa-dis"] = "disputed affiliation", ["qfa-dny"] = "Dene-Yeniseian", ["qfa-hur"] = "Hurro-Urartian", ["qfa-iso"] = "isolate", ["qfa-kad"] = "Kadu", ["qfa-kms"] = "Kam-Sui", ["qfa-kor"] = "Koreanic", ["qfa-kra"] = "Kra", ["qfa-lic"] = "Hlai", ["qfa-mch"] = "Macro-Chibchan", ["qfa-mix"] = "mixed", ["qfa-not"] = "not a family", ["qfa-onb"] = "Be", ["qfa-ong"] = "Ongan", ["qfa-pid"] = "pidgin", ["qfa-sub"] = "substrate", ["qfa-tak"] = "Kra-Dai", ["qfa-tyn"] = "Tyrsenian", ["qfa-unc"] = "unclassifiable", ["qfa-xgs"] = "Serbi-Mongolic", ["qfa-xgx"] = "Para-Mongolic", ["qfa-yen"] = "Yeniseian", ["qfa-yke"] = "Ketic", ["qfa-yko"] = "Kottic", ["qfa-ypm"] = "Pumpokolic", ["qfa-yrn"] = "Arinic", ["qfa-yuk"] = "Yukaghir", ["qwe"] = "Quechuan", ["raj"] = "Rajasthani", ["roa"] = "Romance", ["roa-asl"] = "Asturleonese", ["roa-cas"] = "Castilian", ["roa-dal"] = "Dalmatian Romance", ["roa-eas"] = "Eastern Romance", ["roa-emr"] = "Emilian-Romagnol", ["roa-gap"] = "Galician-Portuguese", ["roa-gar"] = "Gallo-Romance", ["roa-git"] = "Gallo-Italic", ["roa-grh"] = "Gallo-Rhaetian", ["roa-ibe"] = "Ibero-Romance", ["roa-itd"] = "Italo-Dalmatian", ["roa-itr"] = "Italo-Romance", ["roa-iwr"] = "Italo-Western Romance", ["roa-nar"] = "Navarro-Aragonese", ["roa-ocr"] = "Occitano-Romance", ["roa-oil"] = "Oïl", ["roa-rhe"] = "Rhaeto-Romance", ["roa-sou"] = "Southern Romance", ["roa-wes"] = "Western Romance", ["sai-ara"] = "Araucanian", ["sai-aym"] = "Aymaran", ["sai-bar"] = "Barbacoan", ["sai-bor"] = "Boran", ["sai-cah"] = "Cahuapanan", ["sai-car"] = "Cariban", ["sai-cer"] = "Cerrado", ["sai-chc"] = "Chocoan", ["sai-cho"] = "Chonan", ["sai-cje"] = "Central Jê", ["sai-cpc"] = "Chapacuran", ["sai-crn"] = "Charruan", ["sai-ctc"] = "Catacaoan", ["sai-guc"] = "Guaicuruan", ["sai-guh"] = "Guahiban", ["sai-gui"] = "Guianan", ["sai-har"] = "Harákmbut", ["sai-hkt"] = "Harákmbut-Katukinan", ["sai-hrp"] = "Huarpean", ["sai-jee"] = "Jê", ["sai-jir"] = "Jirajaran", ["sai-jiv"] = "Jivaroan", ["sai-ktk"] = "Katukinan", ["sai-kui"] = "Kuikuroan", ["sai-map"] = "Mapoyan", ["sai-mas"] = "Mascoian", ["sai-mgc"] = "Mataco-Guaicuru", ["sai-mje"] = "Macro-Jê", ["sai-mtc"] = "Matacoan", ["sai-mur"] = "Muran", ["sai-nad"] = "Nadahup", ["sai-nje"] = "Northern Jê", ["sai-nmk"] = "Nambikwaran", ["sai-otm"] = "Otomacoan", ["sai-pan"] = "Panoan", ["sai-pat"] = "Pano-Tacanan", ["sai-pek"] = "Pekodian", ["sai-pem"] = "Pemongan", ["sai-pey"] = "Peba-Yaguan", ["sai-prk"] = "Parukotoan", ["sai-sje"] = "Southern Jê", ["sai-tac"] = "Tacanan", ["sai-tar"] = "Taranoan", ["sai-tin"] = "Tiniguan", ["sai-tuc"] = "Tucanoan", ["sai-tyu"] = "Ticuna-Yuri", ["sai-ucp"] = "Uru-Chipaya", ["sai-ven"] = "Venezuelan Cariban", ["sai-wic"] = "Wichí", ["sai-wit"] = "Witotoan", ["sai-ynm"] = "Yanomami", ["sai-yuk"] = "Yukpan", ["sai-zam"] = "Zamucoan", ["sai-zap"] = "Zaparoan", ["sal"] = "Salish", ["sdv"] = "Eastern Sudanic", ["sdv-bri"] = "Bari", ["sdv-daj"] = "Daju", ["sdv-dnu"] = "Dinka-Nuer", ["sdv-eje"] = "Eastern Jebel", ["sdv-kln"] = "Kalenjin", ["sdv-lma"] = "Lotuko-Maa", ["sdv-lon"] = "Northern Luo", ["sdv-los"] = "Southern Luo", ["sdv-luo"] = "Luo", ["sdv-nes"] = "Northern Eastern Sudanic", ["sdv-nie"] = "Eastern Nilotic", ["sdv-nil"] = "Nilotic", ["sdv-nis"] = "Southern Nilotic", ["sdv-niw"] = "Western Nilotic", ["sdv-nma"] = "Nandi-Markweta", ["sdv-nyi"] = "Nyima", ["sdv-tmn"] = "Taman", ["sdv-ttu"] = "Teso-Turkana", ["sel"] = "Selkup", ["sem"] = "Semitic", ["sem-ara"] = "Aramaic", ["sem-arb"] = "Arabic", ["sem-are"] = "Eastern Aramaic", ["sem-arw"] = "Western Aramaic", ["sem-ase"] = "Southeastern Aramaic", ["sem-can"] = "Canaanite", ["sem-cen"] = "Central Semitic", ["sem-cna"] = "Central Neo-Aramaic", ["sem-eas"] = "East Semitic", ["sem-eth"] = "Ethiopian Semitic", ["sem-nna"] = "Northeastern Neo-Aramaic", ["sem-nwe"] = "Northwest Semitic", ["sem-osa"] = "Old South Arabian", ["sem-sar"] = "Modern South Arabian", ["sem-wes"] = "West Semitic", ["sgn"] = "sign", ["sgn-asl"] = "American Sign Languages", ["sgn-fsl"] = "French Sign Languages", ["sgn-gsl"] = "German Sign Languages", ["sgn-jsl"] = "Japanese Sign Languages", ["sio"] = "Siouan", ["sio-dhe"] = "Dhegihan", ["sio-dkt"] = "Dakotan", ["sio-mor"] = "Missouri River Siouan", ["sio-msv"] = "Mississippi Valley Siouan", ["sio-ohv"] = "Ohio Valley Siouan", ["sit"] = "Sino-Tibetan", ["sit-aao"] = "Central Naga", ["sit-alm"] = "Almora", ["sit-bai"] = "Bai", ["sit-bdi"] = "Bodish", ["sit-cln"] = "Cai-Long", ["sit-dhi"] = "Dhimalish", ["sit-ebo"] = "East Bodish", ["sit-egy"] = "East rGyalrongic", ["sit-ers"] = "Ersuic", ["sit-gma"] = "Greater Magaric", ["sit-gsi"] = "Greater Siangic", ["sit-hrs"] = "Hrusish", ["sit-jnp"] = "Jingphoic", ["sit-jpl"] = "Kachin-Luic", ["sit-kch"] = "Konyak-Chang", ["sit-kha"] = "Kham", ["sit-khb"] = "Kho-Bwa", ["sit-khc"] = "Chug-Lish", ["sit-khm"] = "Mey-Sartang", ["sit-khw"] = "Western Kho-Bwa", ["sit-kic"] = "Central Kiranti", ["sit-kie"] = "Eastern Kiranti", ["sit-kin"] = "Kinnauric", ["sit-kir"] = "Kiranti", ["sit-kiw"] = "Western Kiranti", ["sit-kon"] = "Northern Naga", ["sit-kyk"] = "Kyirong-Kagate", ["sit-lab"] = "Ladakhi-Balti", ["sit-las"] = "Lahuli-Spiti", ["sit-luu"] = "Luish", ["sit-mar"] = "Maringic", ["sit-mba"] = "Macro-Bai", ["sit-mdz"] = "Midzu", ["sit-mnz"] = "Mondzish", ["sit-mru"] = "Mruic", ["sit-nas"] = "Naish", ["sit-nax"] = "Naic", ["sit-nba"] = "Northern Bai", ["sit-new"] = "Newaric", ["sit-nng"] = "Nungish", ["sit-qia"] = "Qiangic", ["sit-rgy"] = "Rgyalrongic", ["sit-sba"] = "Sino-Bai", ["sit-tam"] = "Tamangic", ["sit-tan"] = "Tani", ["sit-tib"] = "Tibetic", ["sit-tja"] = "Tujia", ["sit-tma"] = "Tangkhul-Maring", ["sit-tng"] = "Tangkhulic", ["sit-tno"] = "Tangsa-Nocte", ["sit-tsk"] = "Tshangla", ["sit-wgy"] = "West rGyalrongic", ["sit-whm"] = "West Himalayish", ["sit-zem"] = "Zeme", ["sla"] = "Slavic", ["smi"] = "Sami", ["son"] = "Songhay", ["sqj"] = "Albanian", ["ssa"] = "Nilo-Saharan", ["ssa-fur"] = "Fur", ["ssa-klk"] = "Kuliak", ["ssa-kom"] = "Koman", ["ssa-sah"] = "Saharan", ["syd"] = "Samoyedic", ["syd-ene"] = "Enets", ["tai"] = "Tai", ["tai-cen"] = "Central Tai", ["tai-cho"] = "Chongzuo Tai", ["tai-nor"] = "Northern Tai", ["tai-sap"] = "Sapa-Southwestern Tai", ["tai-swe"] = "Southwestern Tai", ["tai-tay"] = "Tày", ["tai-wen"] = "Wenma-Southwestern Tai", ["tbq"] = "Tibeto-Burman", ["tbq-anp"] = "Angami-Pochuri", ["tbq-axi"] = "Axioid", ["tbq-bdg"] = "Bodo-Garo", ["tbq-bis"] = "Bisoid", ["tbq-bka"] = "Bi-Ka", ["tbq-bkj"] = "Sal", ["tbq-brm"] = "Burmish", ["tbq-buq"] = "Burmo-Qiangic", ["tbq-drp"] = "Downriver Phula", ["tbq-han"] = "Hanoid", ["tbq-hph"] = "Highland Phula", ["tbq-jin"] = "Jino", ["tbq-kuk"] = "Kuki-Chin", ["tbq-kzh"] = "Kazhuoish", ["tbq-lal"] = "Lalo", ["tbq-lho"] = "Lahoish", ["tbq-llo"] = "Lipo-Lolopo", ["tbq-lob"] = "Lolo-Burmese", ["tbq-lol"] = "Loloish", ["tbq-lso"] = "Lisoish", ["tbq-lwo"] = "Lawoish", ["tbq-muj"] = "Muji", ["tbq-nas"] = "Nasoid", ["tbq-nis"] = "Nisu", ["tbq-nlo"] = "Northern Loloish", ["tbq-nso"] = "Nisoish", ["tbq-nus"] = "Nusoish", ["tbq-phw"] = "Phowa", ["tbq-rph"] = "Riverine Phula", ["tbq-sel"] = "Southeastern Loloish", ["tbq-sil"] = "Siloid", ["tbq-slo"] = "Southern Loloish", ["tbq-tal"] = "Taloid", ["tbq-urp"] = "Upriver Phula", ["trk"] = "Turkic", ["trk-cmn"] = "Common Turkic", ["trk-kar"] = "Karluk", ["trk-kbu"] = "Kipchak-Bulgar", ["trk-kcu"] = "Kipchak-Cuman", ["trk-kip"] = "Kipchak", ["trk-kkp"] = "Kyrgyz-Kipchak", ["trk-kno"] = "Kipchak-Nogai", ["trk-nsb"] = "North Siberian Turkic", ["trk-ogr"] = "Oghur", ["trk-ogz"] = "Oghuz", ["trk-sib"] = "Siberian Turkic", ["trk-ssb"] = "South Siberian Turkic", ["tup"] = "Tupian", ["tup-gua"] = "Tupi-Guarani", ["tuw"] = "Tungusic", ["tuw-ewe"] = "Ewenic", ["tuw-jrc"] = "Jurchenic", ["tuw-nan"] = "Nanaic", ["tuw-udg"] = "Udegheic", ["urj"] = "Uralic", ["urj-fin"] = "Finnic", ["urj-mdv"] = "Mordvinic", ["urj-prm"] = "Permic", ["urj-ugr"] = "Ugric", ["wak"] = "Wakashan", ["wen"] = "Sorbian", ["xgn"] = "Mongolic", ["xgn-cen"] = "Central Mongolic", ["xgn-shr"] = "Shirongolic", ["xgn-sou"] = "Southern Mongolic", ["xme"] = "Median", ["xme-ttc"] = "Tatic", ["xnd"] = "Na-Dene", ["xsc"] = "Scythian", ["xsc-sak"] = "Saka", ["xsc-sar"] = "Sarmatian", ["xsc-skw"] = "Saka-Wakhi", ["yok"] = "Yokuts", ["ypk"] = "Yupik", ["yrk"] = "Nenets", ["zhx"] = "Sinitic", ["zhx-com"] = "Coastal Min", ["zhx-inm"] = "Inland Min", ["zhx-man"] = "Mandarinic", ["zhx-min"] = "Min", ["zhx-nan"] = "Southern Min", ["zhx-pin"] = "Pinghua", ["zhx-yue"] = "Yue", ["zle"] = "East Slavic", ["zls"] = "South Slavic", ["zlw"] = "West Slavic", ["zlw-lch"] = "Lechitic", ["zlw-pom"] = "Pomeranian", ["znd"] = "Zande", } at1n1wg69b612bxe19wg6xq47edegaw 828 5996 17433 2026-07-13T08:42:37Z Hiyuune 6766 + 17433 Scribunto text/plain local html_create = mw.html.create local tostring = tostring local export = {} local function make_box(tag, rows, image, header, text) tag = tag:addClass("noprint") :tag("table") :tag("tr") :tag("td") if rows > 1 then tag:attr("rowspan", rows) end tag = tag:wikitext(image) :done() if header then tag = tag:node(header) :done() :tag("tr") end return tostring(tag:tag("td") :wikitext(text) :allDone()) .. require("Module:TemplateStyles")("Module:message box/styles.css") end function export.maintenance(color, image, title, text) local div = html_create("div") :addClass("maintenance-box") :addClass("maintenance-box-" .. color) local header = html_create("th") :css("text-align", "left") :wikitext(title) return make_box(div, 2, image, header, text) end function export.request(image, text) local div = html_create("div") :addClass("request-box") return make_box(div, 1, image, nil, text) end return export 0njvtu4cuuvz98uci9fdhcz9qzscuod 828 5997 17434 2026-07-13T08:43:00Z Hiyuune 6766 + 17434 sanitized-css text/css .maintenance-box { width: 90%; margin: 0.75em auto; border-width: 1px; border-style: dashed; padding: 0.25em; } body.skin-vector-2022 .maintenance-box > table td p:last-of-type { /* remove extraneous bottom margin from bottom edge of maintenance box if it has multiple lines/paragraphs */ margin-bottom: 0.25em; } .maintenance-box-image-cell { padding: 0 0.5em; } .request-box { /* width: fit-content added as inline style */ margin: 0.75em 1em 0.75em 1em; border: 1px dashed var(--border-color-base, #999999); padding: 0.25em; background: var(--background-color-base, #FFFFFF); } body.skin-minerva .request-box table { margin-top: 0.25em; margin-bottom: 0.25em; } /* Colors */ .maintenance-box-blue { background-color: var(--wikt-palette-indigo-2, #E6E6FF); border: 1px dashed var(--wikt-palette-indigo-9, #000061); } .maintenance-box-red { background-color: var(--wikt-palette-red-2, #FFE6E6); border: 1px dashed var(--wikt-palette-red-9, #610000); } .maintenance-box-yellow { background-color: var(--wikt-palette-yellow-2, #FFFFE6); border: 1px dashed var(--wikt-palette-yellow-9, #616100); } .maintenance-box-grey { background-color: var(--wikt-palette-grey-2, #F2F2F2); border: 1px dashed var(--wikt-palette-grey-9, #303030); } .maintenance-box-orange { background-color: var(--wikt-palette-orange-2, #FFF2E6); border: 1px dashed var(--wikt-palette-orange-9, #612F00); } 94apw72wdbw2yvw3hygvo1l8sbdhyi8 828 5998 17435 2026-07-13T08:43:26Z Hiyuune 6766 + 17435 Scribunto text/plain local string = string local case_insensitive_pattern = require("Module:string utilities").case_insensitive_pattern local gsub = string.gsub local upper = string.upper local data = {} do local tags = mw.loadData("Module:data/parser extension tags") local data_end_tags = {} -- Generates the string pattern for the end tag. -- The preprocessor uses the regex "/<\/TAG\s*>/i", so only ASCII characters -- are case-insensitive. local function end_tag_pattern(tag) data_end_tags[tag] = "</" .. case_insensitive_pattern(tag, nil, true) .. "%s*>" end for tag in pairs(tags) do end_tag_pattern(tag) end end_tag_pattern("includeonly") end_tag_pattern("noinclude") data_end_tags["onlyinclude"] = true -- Pattern is not required, but a key is needed for tag validity checks. data.end_tags = data_end_tags end -- The parser's HTML sanitizer validates tag attributes with the regex -- "/^([:_\p{L}\p{N}][:_\.\-\p{L}\p{N}]*)$/sxu". Ustring's "%w" is defined as -- "[\p{L}\p{Nd}]", so any characters in \p{N} but not \p{Nd} must be added -- manually. -- NOTE: \p{N} *MUST* be defined according to the same version of Unicode that -- the sanitizer uses in order to remain in sync. As of September 2024, this is -- version 11.0. local N_not_Nd = "\194\178" .. -- U+00B2 "\194\179" .. -- U+00B3 "\194\185" .. -- U+00B9 "\194\188-\194\190" .. -- U+00BC-U+00BE "\224\167\180-\224\167\185" .. -- U+09F4-U+09F9 "\224\173\178-\224\173\183" .. -- U+0B72-U+0B77 "\224\175\176-\224\175\178" .. -- U+0BF0-U+0BF2 "\224\177\184-\224\177\190" .. -- U+0C78-U+0C7E "\224\181\152-\224\181\158" .. -- U+0D58-U+0D5E "\224\181\176-\224\181\184" .. -- U+0D70-U+0D78 "\224\188\170-\224\188\179" .. -- U+0F2A-U+0F33 "\225\141\169-\225\141\188" .. -- U+1369-U+137C "\225\155\174-\225\155\176" .. -- U+16EE-U+16F0 "\225\159\176-\225\159\185" .. -- U+17F0-U+17F9 "\225\167\154" .. -- U+19DA "\226\129\176" .. -- U+2070 "\226\129\180-\226\129\185" .. -- U+2074-U+2079 "\226\130\128-\226\130\137" .. -- U+2080-U+2089 "\226\133\144-\226\134\130" .. -- U+2150-U+2182 "\226\134\133-\226\134\137" .. -- U+2185-U+2189 "\226\145\160-\226\146\155" .. -- U+2460-U+249B "\226\147\170-\226\147\191" .. -- U+24EA-U+24FF "\226\157\182-\226\158\147" .. -- U+2776-U+2793 "\226\179\189" .. -- U+2CFD "\227\128\135" .. -- U+3007 "\227\128\161-\227\128\169" .. -- U+3021-U+3029 "\227\128\184-\227\128\186" .. -- U+3038-U+303A "\227\134\146-\227\134\149" .. -- U+3192-U+3195 "\227\136\160-\227\136\169" .. -- U+3220-U+3229 "\227\137\136-\227\137\143" .. -- U+3248-U+324F "\227\137\145-\227\137\159" .. -- U+3251-U+325F "\227\138\128-\227\138\137" .. -- U+3280-U+3289 "\227\138\177-\227\138\191" .. -- U+32B1-U+32BF "\234\155\166-\234\155\175" .. -- U+A6E6-U+A6EF "\234\160\176-\234\160\181" .. -- U+A830-U+A835 "\240\144\132\135-\240\144\132\179" .. -- U+10107-U+10133 "\240\144\133\128-\240\144\133\184" .. -- U+10140-U+10178 "\240\144\134\138" .. -- U+1018A "\240\144\134\139" .. -- U+1018B "\240\144\139\161-\240\144\139\187" .. -- U+102E1-U+102FB "\240\144\140\160-\240\144\140\163" .. -- U+10320-U+10323 "\240\144\141\129" .. -- U+10341 "\240\144\141\138" .. -- U+1034A "\240\144\143\145-\240\144\143\149" .. -- U+103D1-U+103D5 "\240\144\161\152-\240\144\161\159" .. -- U+10858-U+1085F "\240\144\161\185-\240\144\161\191" .. -- U+10879-U+1087F "\240\144\162\167-\240\144\162\175" .. -- U+108A7-U+108AF "\240\144\163\187-\240\144\163\191" .. -- U+108FB-U+108FF "\240\144\164\150-\240\144\164\155" .. -- U+10916-U+1091B "\240\144\166\188" .. -- U+109BC "\240\144\166\189" .. -- U+109BD "\240\144\167\128-\240\144\167\143" .. -- U+109C0-U+109CF "\240\144\167\146-\240\144\167\191" .. -- U+109D2-U+109FF "\240\144\169\128-\240\144\169\136" .. -- U+10A40-U+10A48 "\240\144\169\189" .. -- U+10A7D "\240\144\169\190" .. -- U+10A7E "\240\144\170\157-\240\144\170\159" .. -- U+10A9D-U+10A9F "\240\144\171\171-\240\144\171\175" .. -- U+10AEB-U+10AEF "\240\144\173\152-\240\144\173\159" .. -- U+10B58-U+10B5F "\240\144\173\184-\240\144\173\191" .. -- U+10B78-U+10B7F "\240\144\174\169-\240\144\174\175" .. -- U+10BA9-U+10BAF "\240\144\179\186-\240\144\179\191" .. -- U+10CFA-U+10CFF "\240\144\185\160-\240\144\185\190" .. -- U+10E60-U+10E7E "\240\144\188\157-\240\144\188\166" .. -- U+10F1D-U+10F26 "\240\144\189\145-\240\144\189\148" .. -- U+10F51-U+10F54 "\240\145\129\146-\240\145\129\165" .. -- U+11052-U+11065 "\240\145\135\161-\240\145\135\180" .. -- U+111E1-U+111F4 "\240\145\156\186" .. -- U+1173A "\240\145\156\187" .. -- U+1173B "\240\145\163\170-\240\145\163\178" .. -- U+118EA-U+118F2 "\240\145\177\154-\240\145\177\172" .. -- U+11C5A-U+11C6C "\240\146\144\128-\240\146\145\174" .. -- U+12400-U+1246E "\240\150\173\155-\240\150\173\161" .. -- U+16B5B-U+16B61 "\240\150\186\128-\240\150\186\150" .. -- U+16E80-U+16E96 "\240\157\139\160-\240\157\139\179" .. -- U+1D2E0-U+1D2F3 "\240\157\141\160-\240\157\141\184" .. -- U+1D360-U+1D378 "\240\158\163\135-\240\158\163\143" .. -- U+1E8C7-U+1E8CF "\240\158\177\177-\240\158\178\171" .. -- U+1EC71-U+1ECAB "\240\158\178\173-\240\158\178\175" .. -- U+1ECAD-U+1ECAF "\240\158\178\177-\240\158\178\180" .. -- U+1ECB1-U+1ECB4 "\240\159\132\128-\240\159\132\140" -- U+1F100-U+1F10C data.valid_attribute_name = "^[:_%w" .. N_not_Nd .."][:_.%-%w" .. N_not_Nd .. "]*$" -- Value is the namespace number of the linked page at parameter 0, where 0 is mainspace. -- If the namespace is the mainspace, it can be overridden by an explicitly specified category (e.g. {{PAGENAME:Category:Foo}} refers to "Category:Foo"). This does not apply to any other namespace (e.g. {{#SPECIAL:Category:Foo}} refers to "Special:Category:Foo"). data.template_link_param_1 = { ["#CATEGORYTREE:"] = 14, -- Category: ["#IFEXIST:"] = 0, ["#INVOKE:"] = 828, -- Module: ["#LST:"] = 0, ["#LSTH:"] = 0, ["#LSTX:"] = 0, ["#SPECIAL:"] = -1, -- Special: ["#SPECIALE:"] = -1, -- Special: ["#TITLEPARTS:"] = 0, ["BASEPAGENAME:"] = 0, ["BASEPAGENAMEE:"] = 0, ["CANONICALURL:"] = 0, ["CANONICALURLE:"] = 0, ["CASCADINGSOURCES:"] = 0, ["FILEPATH:"] = 6, -- File: ["FULLPAGENAME:"] = 0, ["FULLPAGENAMEE:"] = 0, ["FULLURL:"] = 0, ["FULLURLE:"] = 0, ["INT:"] = 8, -- MediaWiki: ["LOCALURL:"] = 0, ["LOCALURLE:"] = 0, ["NAMESPACE:"] = 0, ["NAMESPACEE:"] = 0, ["NAMESPACENUMBER:"] = 0, ["PAGEID:"] = 0, ["PAGENAME:"] = 0, ["PAGENAMEE:"] = 0, ["PAGESINCATEGORY:"] = 14, -- Category: ["PAGESIZE:"] = 0, ["REVISIONDAY:"] = 0, ["REVISIONDAY2:"] = 0, ["REVISIONID:"] = 0, ["REVISIONMONTH:"] = 0, ["REVISIONMONTH1:"] = 0, ["REVISIONTIMESTAMP:"] = 0, ["REVISIONUSER:"] = 0, ["REVISIONYEAR:"] = 0, ["ROOTPAGENAME:"] = 0, ["ROOTPAGENAMEE:"] = 0, ["SUBJECTPAGENAME:"] = 0, ["SUBJECTPAGENAMEE:"] = 0, ["SUBJECTSPACE:"] = 0, ["SUBJECTSPACEE:"] = 0, ["SUBPAGENAME:"] = 0, ["SUBPAGENAMEE:"] = 0, ["TALKPAGENAME:"] = 0, ["TALKPAGENAMEE:"] = 0, ["TALKSPACE:"] = 0, ["TALKSPACEE:"] = 0, } -- Value is the namespace number of the linked page at parameter 1. data.template_link_param_2 = { ["PROTECTIONEXPIRY:"] = 0, ["PROTECTIONLEVEL:"] = 0, } return data t4rorng7wydircsbpm0pxhr9wjhuh7e 828 5999 17436 2026-07-13T08:43:49Z Hiyuune 6766 + 17436 Scribunto text/plain --Note: noinclude, includeonly and onlyinclude are not parser extension tags, as they are handled in a special way by the preprocessor. Among other things, they cannot be used with {{#TAG:}}, for example. return { ["categorytree"] = "mw:Extension:CategoryTree", ["ce"] = "mw:Extension:Math", ["charinsert"] = "mw:Extension:CharInsert", ["chem"] = "mw:Extension:Math", ["dynamicpagelist"] = "mw:Extension:DynamicPageList (Wikimedia)", ["gallery"] = "mw:Help:Images#Rendering a gallery of images", ["graph"] = "mw:Extension:Graph", ["hiero"] = "mw:Extension:WikiHiero", ["imagemap"] = "mw:Extension:ImageMap", ["indicator"] = "mw:Help:Page status indicators#Adding page status indicators", ["inputbox"] = "mw:Extension:InputBox", ["langconvert"] = "mw:Parser extension tags", -- undocumented ["mapframe"] = "mw:Extension:Kartographer", ["maplink"] = "mw:Extension:Kartographer", ["math"] = "mw:Extension:Math", ["nowiki"] = "mw:Help:Formatting", ["phonos"] = "mw:Extension:Phonos", ["poem"] = "mw:Extension:Poem", ["pre"] = "mw:Help:Formatting", ["ref"] = "mw:Extension:Cite", ["references"] = "mw:Extension:Cite", ["score"] = "mw:Extension:Score", ["section"] = "mw:Extension:Labeled Section Transclusion", ["source"] = "mw:Extension:SyntaxHighlight", ["syntaxhighlight"] = "mw:Extension:SyntaxHighlight", ["talkpage"] = "mw:Extension:LiquidThreads", -- undocumented ["templatedata"] = "mw:Extension:TemplateData", ["templatestyles"] = "mw:Extension:TemplateStyles", ["thread"] = "mw:Extension:LiquidThreads", -- undocumented ["timeline"] = "mw:Extension:EasyTimeline", } ofvfawk3x15dsa9oos9tt1283gyzpwv 828 6000 17437 2026-07-13T08:44:11Z Hiyuune 6766 + 17437 Scribunto text/plain local error = error local select = select --[==[ Given a table, value and an arbitrary number of keys, will successively access subtables using each key in turn, and sets the value at the final key. For example, if {t} is { {} }, {export.setNested(t, "foo", 1, 2, 3)} will modify {t} to { {[1] = {[2] = {[3] = "foo"} } } }. If no subtable exists for a given key value, one will be created, but the function will throw an error if a non-table value is found at an intermediary key. Note: the parameter order (table, value, keys) differs from functions like rawset, because the number of keys can be arbitrary. This is to avoid situations where an additional argument must be appended to arbitrary lists of variables, which can be awkward and error-prone: for example, when handling variable arguments ({...}) or function return values.]==] return function(...) local n = select("#", ...) if n < 3 then error("Must provide a table, value and at least one key.") end local t, v, k = ... for i = 4, n do local next_t = t[k] if next_t == nil then -- If there's no next table while setting nil, there's nothing more -- to do. if v == nil then return end next_t = {} t[k] = next_t end t, k = next_t, select(i, ...) end t[k] = v end 1jxfjipchypy8qfjkmtb9b9sal1bcc1 828 6001 17438 2026-07-13T08:44:37Z Hiyuune 6766 new module using category tree 17438 Scribunto text/plain local error = error local select = select --[==[ Given a table and an arbitrary number of keys, will successively access subtables using each key in turn, returning the value at the final key. For example, if {t} is { {[1] = {[2] = {[3] = "foo"}}}}, {export.getNested(t, 1, 2, 3)} will return {"foo"}. If no subtable exists for a given key value, returns nil, but will throw an error if a non-table is found at an intermediary key.]==] return function(...) local n = select("#", ...) if n < 2 then error("Must provide a table and at least one key.") end local t, k = ... for i = 3, n do local v = t[k] if v == nil then return nil end t, k = v, select(i, ...) end return t[k] end tm1q0pycz7xr0ute9n4h4yhpf1jzo33 828 6002 17439 2026-07-13T08:45:50Z Hiyuune 6766 + 17439 Scribunto text/plain local labels = {} labels["Cape Afrikaans"] = { aliases = {"Kaapse Afrikaans"}, Wikipedia = "Kaapse Afrikaans", plain_categories = true, } labels["Namīpia"] = { aliases = {"Namibia","Namibian"}, Wikipedia = true, regional_categories = "Namīpia", } return require("Module:labels").finalize_data(labels) tn27pnndhcilnuo4mt2qoitwsuu3iqy 828 6003 17440 2026-07-13T08:46:38Z Hiyuune 6766 + 17440 Scribunto text/plain -- This module contains a list of languages with lang-specific modules. local langs_with_modules = { ["acm"] = true, } return langs_with_modules 7yr271x5lpmsf41wcc36xc3lw3z5zgt 828 6004 17443 2026-07-13T08:48:42Z Hiyuune 6766 + 17443 Scribunto text/plain local data = {} -- Namespaces which format_categories will allow: (main), Appendix, Thesaurus, Citations, Reconstruction data.category_namespaces = require("Module:table").listToSet{0, 100, 110, 114, 118} -- Script that should be applied to links in categories. data.catfix_scripts = { ["ab"] = "Cyrl", ["ae"] = "Avst", ["ar"] = "Arab", ["ary"] = "Arab", ["be"] = "Cyrl", ["cmn"] = "Hani", ["cu"] = "Cyrs", ["de"] = "Latn", ["el"] = "Grek", ["en"] = "Latn", ["fa"] = "fa-Arab", ["grc"] = "Polyt", ["he"] = "Hebr", ["hi"] = "Deva", ["hu"] = "Latn", ["ja"] = "Jpan", ["ka"] = "Geor", ["ko"] = "Kore", ["mr"] = "Deva", ["nan-hbl"] = "Hani", ["orv"] = "Cyrs", ["ro"] = "Latn", ["ru"] = "Cyrl", ["sa"] = "Deva", ["sq"] = "Latn", ["syl"] = "Sylo", ["xfa"] = "Ital", ["yue"] = "Hani", ["zh"] = "Hani", ["zle-ono"] = "Cyrs", ["zle-ort"] = "Cyrs", --[[ [""] = "", ]] } return data 4x56htm3m5cvzeaw1vqlu3qn70xkp8k 828 6005 17444 2026-07-13T08:49:07Z Hiyuune 6766 + 17444 Scribunto text/plain local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared local m = {} m["uam"] = { "Uamué", 3441418, } m["uan"] = { "Kuan", 6441085, } m["uar"] = { "Tairuma", 7676386, "paa-eel", "Latn", } m["uba"] = { "Ubang", 3914467, "nic-ben", "Latn", } m["ubi"] = { "Ubi", 56264, } m["ubl"] = { "Buhi'non Bikol", 18664494, "phi", "Latn", } m["ubr"] = { "Ubir", 3547642, "poz-ocw", "Latn", } m["ubu"] = { "Umbu-Ungu", 12953245, "ngf-hag", "Latn", } m["uby"] = { "Ubykh", 36931, "cau-nwc", "Cyrl, Latn", translit = "uby-translit", override_translit = true, display_text = {Cyrl = s["cau-Cyrl-displaytext"]}, strip_diacritics = { Cyrl = s["cau-Cyrl-stripdiacritics"], Latn = s["cau-Latn-stripdiacritics"], }, sort_key = "uby-sortkey", } m["uda"] = { "Uda", 11011951, "nic-lcr", } m["ude"] = { "Udihe", 13235, "tuw-udg", "Cyrl", } m["udg"] = { "Muduga", 16886762, "dra-imd", "Mlym", -- Mlym translit in [[Module:scripts/data]] } m["udi"] = { "Udi", 36867, "cau-esm", "Cyrl, Latn, Armn, Geor", ancestors = "xag", translit = { Cyrl = "udi-translit", -- Geor, Armn translit in [[Module:scripts/data]] }, override_translit = true, display_text = {Cyrl = s["cau-Cyrl-displaytext"]}, strip_diacritics = { Cyrl = s["cau-Cyrl-stripdiacritics"], Latn = s["cau-Latn-stripdiacritics"], }, } m["udj"] = { "Ujir", 14916906, "poz-cet", "Latn", } m["udl"] = { "Uldeme", 3515078, "cdc-cbm", "Latn", } m["udm"] = { "Udmurt", 13238, "urj-prm", "Cyrl", translit = "udm-translit", override_translit = true, sort_key = "udm-sortkey", } m["udu"] = { "Uduk", 3182573, "ssa-kom", } m["ues"] = { "Kioko", 18343036, } m["ufi"] = { "Ufim", 7877531, "ngf-gmo", "Latn", } m["uga"] = { "Ugaritic", 36928, "sem-nwe", "Ugar", translit = { Ugar = "uga-translit", } } m["ugb"] = { "Kuku-Ugbanh", 10549854, } m["uge"] = { "Ughele", 966303, "poz-ocw", } m["ugn"] = { "Ugandan Sign Language", 7877677, "sgn-asl", } m["ugo"] = { "Gong", 3448919, "tbq-lob", "Thai", sort_key = "Thai-sortkey", } m["ugy"] = { "Uruguayan Sign Language", 7901470, "sgn", } m["uha"] = { "Uhami", 3913328, "alv-nwd", "Latn", } m["uhn"] = { "Damal", 4748974, "qfa-dis", -- ngf? or uncertain "Latn", } m["uis"] = { "Uisai", 7878123, "paa-sbo", "Latn", } m["uiv"] = { "Iyive", 11128658, "nic-tvc", "Latn", } m["uji"] = { "Tanjijili", 3914939, "nic-pls", "Latn", } m["uka"] = { "Kaburi", 6344482, "ngf-sbh", "Latn", } m["ukg"] = { "Ukuriguma", 7878623, "ngf-num", "Latn", } m["ukh"] = { "Ukhwejo", 36623, "bnt-bek", "Latn", } m["ukk"] = { "Muak Sa-aak", 23807993, "mkh-pal", "Latn", } m["ukl"] = { "Ukrainian Sign Language", 10322106, "sgn", } m["ukp"] = { "Ukpe-Bayobiri", 3914470, "nic-ben", "Latn", } m["ukq"] = { "Ukwa", 7878635, "nic-ief", "Latn", } m["uks"] = { "Kaapor Sign Language", 3322101, "sgn", } m["uku"] = { "Ukue", 3913387, "alv-nwd", "Latn", } m["ukw"] = { "Ukwuani-Aboh-Ndoni", 36636, "alv", "Latn", } m["uky"] = { "Kuuk Yak", 6448719, "aus-psw", "Latn", } m["ula"] = { "Fungwa", 5509187, "nic-shi", "Latn", } m["ulb"] = { "Olukumi", 36722, "alv-yor", "Latn", strip_diacritics = {Latn = {remove_diacritics = c.grave .. c.acute .. c.macron}}, sort_key = { from = {"ch", "ẹ", "gb", "gh", "gw", "kp", "kw", "ọ", "ṣ"}, to = {"c" .. p[1], "e" .. p[1], "g" .. p[1], "g" .. p[2], "g" .. p[3], "k" .. p[1], "k" .. p[2], "o" .. p[1], "s" .. p[1]} }, } m["ulc"] = { "Ulch", 13239, "tuw-nan", "Cyrl, Latn", strip_diacritics = { from = {"['’]"}, to = {"ʼ"} }, sort_key = "ulc-sortkey", } m["ule"] = { "Lule", 12635889, nil, "Latn", } m["ulf"] = { "Afra", 4477735, "qfa-dis", -- Papuan; extinct and poorly documented; per Wurm (1975), an independent branch of TNG; per Ross (2005), -- unclassifiable; per Usher (2020), West Pauwasi, though divergent; per Foley (2018), isolate. "Latn", } m["uli"] = { "Ulithian", 36842, "poz-mic", "Latn", } m["ulk"] = { "Meriam", 788174, "paa-etf", "Latn", } m["ull"] = { "Ullatan", 8761579, "dra-mal", } m["ulm"] = { "Ulumanda'", 3501892, "poz-ssw", "Latn", } m["uln"] = { "Unserdeutsch", 13244, "crp", "Latn", ancestors = "de", } m["ulu"] = { "Uma' Lung", 3548186, "poz-swa", } m["ulw"] = { "Ulwa (Nicaragua)", 2405552, "nai-min", "Latn", } m["uma"] = { "Umatilla", 12953952, "nai-shp", "Latn", ancestors = "nai-spt", } m["umb"] = { "Umbundu", 36983, "bnt", "Latn", } m["umc"] = { "Marrucinian", 36110, "itc-sbl", "Ital, Latn", -- Ital translit in [[Module:scripts/data]] display_text = { Latn = s["itc-Latn-displaytext"] }, strip_diacritics = { Latn = s["itc-Latn-stripdiacritics"] }, sort_key = { Latn = s["itc-Latn-sortkey"] }, } m["umd"] = { "Umbindhamu", 7881346, "aus-pmn", "Latn", } m["umg"] = { "Umbuygamu", 3915677, "aus-pmn", "Latn", } m["umi"] = { "Ukit", 7878321, nil, "Latn", } m["umm"] = { "Umon", 3915448, "nic-ucn", "Latn", } m["umn"] = { "Makyan Naga", 6740516, "sit-kch", } m["umo"] = { "Umotína", 7881740, "sai-mje", } m["ump"] = { "Umpila", 12953954, "aus-pmn", "Latn", } m["umr"] = { "Umbugarla", 2980392, } m["ums"] = { "Pendau", 7162371, "poz-tot", "Latn", } m["umu"] = { "Munsee", 56547, "del", "Latn", strip_diacritics = {remove_diacritics = c.acute .. c.breve}, } m["una"] = { "North Watut", 15887898, "poz-ocw", "Latn", } m["und"] = { "Undetermined", 22282914, "qfa-not", "All", } m["une"] = { "Uneme", 3913357, "alv-yek", "Latn", } m["ung"] = { "Ngarinyin", 1284885, "aus-wor", "Latn", } m["uni"] = { "Uni", 65043886, "paa-pio", "Latn", } m["unk"] = { "Enawené-Nawé", 3307184, "awd", "Latn", } m["unm"] = { "Unami", 3549180, "del", "Latn", --[===[Don't strip diacritics from display text, per [[WT:Grease pit/2020/May]]. strip_diacritics = {remove_diacritics = c.grave .. c.diaer},]===] } m["unn"] = { "Kurnai", 61676882, "aus-pam", "Latn", } m["unr"] = { "Mundari", 3327828, "mun", "Nagm, Deva, Onao", -- Onao is used by Bhumij, which may be a separate language; remove if it gets split out translit = "hi-translit", -- for now } m["unu"] = { "Unubahe", 7897776, } m["unx"] = { "Munda", 36264959, "mun", "Latn", } m["unz"] = { "Unde Kaili", 12953596, "poz-kal", "Latn", } m["uok"] = { "Uokha", 3441216, "alv-edo", "Latn", } m["uon"] = { "Kulon", 11182000, "map", "Latn", } m["upi"] = { "Umeda", 7881465, "paa-war", "Latn", } m["upv"] = { "Northeast Malakula", 13249, "poz-vnc", "Latn", } m["ura"] = { "Urarina", 1579560, } m["urb"] = { "Urubú-Kaapor", 13893353, "tup-gua", "Latn", } m["urc"] = { "Urningangg", 10710522, } m["ure"] = { "Uru", 2992892, } m["urf"] = { "Uradhi", 3915680, "aus-pam", "Latn", } m["urg"] = { "Urigina", 7900603, "ngf-pek", "Latn", } m["urh"] = { "Urhobo", 36663, "alv-swd", "Latn", } m["uri"] = { "Urim", 7900609, "paa-trr", "Latn", } m["urk"] = { "Urak Lawoi'", 7899573, "poz-mly", "Thai", sort_key = "Thai-sortkey", } m["url"] = { "Urali", 7899602, "dra-kod", "Knda", -- Knda translit in [[Module:scripts/data]] (NOTE: not present before, presumably an accidental omission) } m["urm"] = { "Urapmin", 7899769, "ngf-mok", "Latn", } m["urn"] = { "Uruangnirin", 7901389, "poz-cet", "Latn", } m["uro"] = { "Ura (New Guinea)", 3121049, "paa-bai", "Latn", } m["urp"] = { "Uru-Pa-In", 7901376, "tup-gua", "Latn", } m["urr"] = { "Löyöp", 3272124, "poz-vnn", "Latn", } m["urt"] = { "Urat", 3502084, "paa-trr", "Latn", } m["uru"] = { "Urumi", 7901530, "tup", "Latn", } m["urv"] = { "Uruava", 36875, "poz-ocw", "Latn", } m["urw"] = { "Sop", 7562808, "ngf-pek", "Latn", } m["urx"] = { "Urimo", 7900611, "paa-mar", "Latn", } m["ury"] = { "Orya", 7105295, "paa-too", "Latn", } m["urz"] = { "Uru-Eu-Wau-Wau", 10266012, "tup-gua", "Latn", } m["usa"] = { "Usarufa", 7901714, "ngf-gau", "Latn", } m["ush"] = { "Ushojo", 3540446, "inc-shn", "ur-Arab", } m["usi"] = { "Usui", 12644231, } m["usk"] = { "Usaghade", 3914048, "nic-lcr", "Latn", } m["usp"] = { "Uspanteco", 36728, "myn", "Latn", } m["uss"] = { "Saare", 63313662, "nic-knn", "Latn", } m["usu"] = { "Uya", 7904082, "ngf-nur", "Latn", } m["uta"] = { "Otank", 3913990, "nic-tvc", "Latn", } m["ute"] = { "Ute", 13260, "azc-num", "Latn", } m["uth"] = { "Hun", 63313668, "nic-knn", "Latn", } m["utp"] = { "Aba", 2841465, "poz-tem", "Latn", } m["utr"] = { "Etulo", 35262, "alv-ido", "Latn", } m["utu"] = { "Utu", 7903469, "ngf-usi", "Latn", } m["uum"] = { "Urum", 13257, "trk-kcu", "Cyrl", translit = "uum-translit", } m["uur"] = { "Ura (Vanuatu)", 7899531, "poz-vns", "Latn", } m["uuu"] = { "U", 953082, "mkh-pal", } m["uve"] = { "West Uvean", 36837, "poz-pnp", "Latn", } m["uvh"] = { "Uri", 7900540, "ngf-era", "Latn", } m["uvl"] = { "Lote", 3259972, "poz-ocw", "Latn", } m["uwa"] = { "Kuku-Uwanh", 3915687, "aus-pmn", "Latn", } m["uya"] = { "Doko-Uyanga", 7904095, "nic-ucr", "Latn", } return require("Module:languages").finalizeData(m, "language") 3oda5x9aa99bfo2zgt1m3fng4tu86ux 828 6006 17445 2026-07-13T08:49:29Z Hiyuune 6766 + 17445 Scribunto text/plain local headword_page_module = "Module:headword/page" local list_to_set = require("Module:table").listToSet local data = {} ------ 1. Lists which are converted into sets. ------ --[==[ var: Large pages where we disable label tracking, red link checking and similar. ]==] data.large_pages = list_to_set { -- pages that consistently hit timeouts "a", -- pages that sometimes hit timeouts "A", "baba", "de", "e", "i", "lima", "o", "u", "и", "山", "子", "月", "一", "人", } --[==[ var: Map from singular to plural, and from plural to itself, for recognized parts of speech with irregular plurals. Most of these are invariable plurals, e.g. `kanji` is its own plural; but we also have `mora` plural `morae`. ]==] data.irregular_plurals = list_to_set({ "cmavo", "cmene", "fu'ivla", "gismu", "Han tu", "hanja", "hanzi", "jyutping", "kana", "kanji", "lujvo", "phrasebook", "pinyin", "rafsi", }, function(_, item) return item end) local irregular_plurals = data.irregular_plurals -- Irregular non-zero plurals AND any regular plurals where the singular ends in "s", -- because the module assumes that inputs ending in "s" are plurals. The singular and -- plural both need to be added, as the module will generate a default plural if -- the input doesn't match a key in this table. for sg, pl in next, { mora = "morae" } do irregular_plurals[sg], irregular_plurals[pl] = pl, pl end --[==[ var: Recognized lemmas. If the part of speech in {{tl|head}} is set to one of these or its singular equivalent, the category 'LANG lemmas' will automatically be added. If the part of speech is not a singular or plural lemma or non-lemma form and is not an abbreviation that expands to a recognized lemma or non-lemma form, the page will be added to various tracking categories: * [[Special:WhatLinksHere/Wiktionary:Tracking/headword/unrecognized pos]] * [[Special:WhatLinksHere/Wiktionary:Tracking/headword/unrecognized pos/LANG]] * [[Special:WhatLinksHere/Wiktionary:Tracking/headword/unrecognized pos/pos/POS]] * [[Special:WhatLinksHere/Wiktionary:Tracking/headword/unrecognized pos/pos/POS/LANG]] ]==] data.lemmas = list_to_set{ "abbreviations", "acronyms", "adjectives", "adnominals", "adpositions", "adverbs", "affixes", "ambipositions", "articles", "circumfixes", "circumpositions", "classifiers", "cmavo", "cmavo clusters", "cmene", "combining forms", "conjunctions", "counters", "determiners", "diacritical marks", "digraphs", "equative adjectives", "fu'ivla", "gismu", "Han characters", "Han tu", "hanja", "hanzi", "ideophones", "idioms", "infixes", "initialisms", "iteration marks", "interfixes", "interjections", "kana", "kanji", "letters", "ligatures", "logograms", "lujvo", "morae", "morphemes", "non-constituents", "nouns", "numbers", "numeral symbols", "numerals", "particles", "phrases", "postpositions", "postpositional phrases", "predicatives", "prefixes", "prepositional phrases", "prepositions", "preverbs", "pronominal adverbs", "pronouns", "proper nouns", "proverbs", "punctuation marks", "relatives", "roots", "stems", "suffixes", "syllables", "symbols", "verbs", } --[==[ var: Recognized non-lemma forms. If the part of speech in {{tl|head}} is set to one of these or its singular equivalent, the category 'LANG non-lemma forms' will automatically be added. If the part of speech is not a singular or plural lemma or non-lemma form and is not an abbreviation that expands to a recognized lemma or non-lemma form, the page will be added to various tracking categories; see the documentation of `data.lemmas`. ]==] data.nonlemmas = list_to_set{ "active participle forms", "active participles", "adjectival participles", "adjective case forms", "adjective forms", "adjective feminine forms", "adjective plural forms", "adverb forms", "adverbial participles", "agent participles", "article forms", "circumfix forms", "combined forms", "comparative adjective forms", "comparative adjectives", "comparative adverb forms", "comparative adverbs", "conjunction forms", "contractions", "converbs", "determiner comparative forms", "determiner forms", "determiner superlative forms", "diminutive nouns", "elative adjectives", "equative adjective forms", "equative adjectives", "future participles", "gerunds", "infinitive forms", "infinitives", "interjection forms", "jyutping", "misspellings", "negative participles", "nominal participles", "noun case forms", "noun construct forms", "noun dual forms", "noun forms", "noun paucal forms", "noun plural forms", "noun possessive forms", "noun singulative forms", "numeral forms", "participles", "participle forms", "particle forms", "passive participles", "past active participles", "past adverbial participles", "past participles", "past participle forms", "past passive participles", "perfect active participles", "perfect participles", "perfect passive participles", "pinyin", "plurals", "postposition forms", "prefix forms", "preposition contractions", "preposition forms", "prepositional pronouns", "present active participles", "present adverbial participles", "present participles", "present passive participles", "preverb forms", "pronoun forms", "pronoun possessive forms", "proper noun forms", "proper noun plural forms", "rafsi", "romanizations", "root forms", "singulatives", "suffix forms", "superlative adjective forms", "superlative adjectives", "superlative adverb forms", "superlative adverbs", "verb forms", "verbal nouns", } --[==[ var: List of languages that will not have links to separate parts of the headword. ]==] data.no_multiword_links = list_to_set{ "zh", } --[==[ var: List of languages that will not have `LANG multiword terms` categories added. There are various reasons why languages are in this list: (a) words are written without spaces between them; (b) syllables are written with spaces between them; (c) variant reconstructions are notated with a tilde surrounded by spaces; (d) the language is a sign language, where pagenames are multiword descriptions of the gesture(s) required to make an individual sign; (e) some other weirdnesses. ]==] data.no_multiword_cat = list_to_set{ -------- Languages without spaces between words (sometimes spaces between phrases) -------- "blt", -- Tai Dam "ja", -- Japanese "khb", -- Lü "km", -- Khmer "lo", -- Lao "mnw", -- Mon "my", -- Burmese "nan", -- Min Nan (some words in Latin script; hyphens between syllables) "nan-hbl", -- Hokkien (some words in Latin script; hyphens between syllables) "nod", -- Northern Thai "ojp", -- Old Japanese "shn", -- Shan "sou", -- Southern Thai "tdd", -- Tai Nüa "th", -- Thai "tts", -- Isan "twh", -- Tai Dón "txg", -- Tangut "zh", -- Chinese (all varieties with Chinese characters) "zkt", -- Khitan -------- Languages with spaces between syllables -------- "ahk", -- Akha "aou", -- A'ou "atb", -- Zaiwa "byk", -- Biao "cdy", -- Chadong --"duu", -- Drung; not sure --"hmx-pro", -- Proto-Hmong-Mien --"hnj", -- Green Hmong; not sure "huq", -- Tsat "ium", -- Iu Mien --"lis", -- Lisu; not sure "mtq", -- Muong --"mww", -- White Hmong; not sure "onb", -- Lingao --"sit-gkh", -- Gokhy; not sure --"swi", -- Sui; not sure "tbq-lol-pro", -- Proto-Loloish "tdh", -- Thulung "ukk", -- Muak Sa-aak "vi", -- Vietnamese "yig", -- Wusa Nasu "zng", -- Mang -------- Languages with ~ with surrounding spaces used to separate variants -------- "mkh-ban-pro", -- Proto-Bahnaric "sit-pro", -- Proto-Sino-Tibetan; listed above -------- Other weirdnesses -------- "mul", -- Translingual; gestures, Morse code, etc. "aot", -- Atong (India); bullet is a letter -------- All sign languages -------- "ads", "aed", "aen", "afg", "ase", "asf", "asp", "asq", "asw", "bfi", "bfk", "bog", "bqn", "bqy", "bvl", "bzs", "cds", "csc", "csd", "cse", "csf", "csg", "csl", "csn", "csq", "csr", "doq", "dse", "dsl", "ecs", "esl", "esn", "eso", "eth", "fcs", "fse", "fsl", "fss", "gds", "gse", "gsg", "gsm", "gss", "gus", "hab", "haf", "hds", "hks", "hos", "hps", "hsh", "hsl", "icl", "iks", "ils", "inl", "ins", "ise", "isg", "isr", "jcs", "jhs", "jls", "jos", "jsl", "jus", "kgi", "kvk", "lbs", "lls", "lsl", "lso", "lsp", "lst", "lsy", "lws", "mdl", "mfs", "mre", "msd", "msr", "mzc", "mzg", "mzy", "nbs", "ncs", "nsi", "nsl", "nsp", "nsr", "nzs", "okl", "pgz", "pks", "prl", "prz", "psc", "psd", "psg", "psl", "pso", "psp", "psr", "pys", "rms", "rsl", "rsm", "sdl", "sfb", "sfs", "sgg", "sgx", "slf", "sls", "sqk", "sqs", "ssp", "ssr", "svk", "swl", "syy", "tse", "tsm", "tsq", "tss", "tsy", "tza", "ugn", "ugy", "ukl", "uks", "vgt", "vsi", "vsl", "vsv", "xki", "xml", "xms", "ygs", "ysl", "zib", "zsl", } --[==[ var: List of languages where a hyphen is not considered a word separator for the `LANG multiword terms` category. There are numerous reasons why languages are in this list; by each language should be listed the reason for inclusion. ]==] data.hyphen_not_multiword_sep = list_to_set{ "akk", -- Akkadian; hyphens between syllables "akl", -- Aklanon; hyphens for mid-word glottal stops "ber-pro", -- Proto-Berber; morphemes separated by hyphens "ceb", -- Cebuano; hyphens for mid-word glottal stops "cnk", -- Khumi Chin; hyphens used in single words "cpi", -- Chinese Pidgin English; Chinese-derived words with hyphens between syllables "de", -- German; too many false positives "esx-esk-pro", -- hyphen used to separate morphemes "fi", -- Finnish; hyphen used to separate components in compound words if the final and initial vowels match, respectively "gd", -- Scottish Gaelic; too many false positives like [[a-chianaibh]], [[a-nìos]], [[an-dè]] and other adverbs in a- and an- "hil", -- Hiligaynon; hyphens for mid-word glottal stops "hnn", -- Hanunoo; too many false positives "ilo", -- Ilocano; hyphens for mid-word glottal stops "kne", -- Kankanaey; hyphens for mid-word glottal stops "lcp", -- Western Lawa; dash as syllable joiner "lwl", -- Eastern Lawa; dash as syllable joiner "mfa", -- Pattani Malay in Thai script; dash as syllable joiner "mkh-vie-pro", -- Proto-Vietic; morphemes separated by hyphens "msb", -- Masbatenyo; too many false positives "tl", -- Tagalog; too many false positives "war", -- Waray-Waray; too many false positives "yo", -- Yoruba; hyphens used to show lengthened nasal vowels } --[==[ var: List of languages that will not have `LANG masculine nouns` and similar categories added. Generally, these languages are lacking gender but use the gender field for other purposes. (This is a massive hack and should be changed.) ]==] data.no_gender_cat = list_to_set{ -- Languages without gender but which use the gender field for other purposes "ja", "th", } --[==[ var: List of languages where [[Module:headword]] should not attempt to generate a transliteration even if the term is written in a non-Latin script. FIXME: Notate reasons why each language is in this list. ]==] data.notranslit = list_to_set{ "ams", "az", "bbc", "bug", "cdo", "cia", "cjm", "cjy", "cmn", "cnp", "cpi", "cpx", "csp", "czh", "czo", "gan", "hak", "hnm", "hsn", "ja", "kzg", "lad", "ltc", "luh", "lzh", "mnp", "ms", "mul", "mvi", "nan", "nan-dat", "nan-hbl", "nan-hlh", "nan-lnx", "nan-tws", "nan-zhe", "nan-zsh", "och", "oj", "okn", "ryn", "rys", "ryu", "sh", "sjc", "tgt", "th", "tkn", "tly", "txg", "und", "vi", "wuu", "xug", "yoi", "yox", "yue", "za", "zh", "zhx-sic", "zhx-tai", } --[==[ var: List of languages that will default to `sccat` being true, i.e. categories like `LANG POS in SCRIPT script` will automatically be generated. This can be overridden using {{para|sccat|0}} in {{tl|head}} or setting `sccat` to `false` in Lua. ]==] data.default_sccat = list_to_set{ "inc-apa", "inc-ash", "kfr", "ks", "mr", "mwr", "inc-oaw", "inc-ohi", "omr", "inc-opa", "phr", "pi", "pra", "sa", "skr", "sd", } --[==[ var: List of script codes for which a script-tagged display title will be added. ]==] data.toBeTagged = list_to_set{ "Ahom", "Arab", "fa-Arab", "glk-Arab", "kk-Arab", "ks-Arab", "ku-Arab", "mzn-Arab", "ms-Arab", "ota-Arab", "pa-Arab", "ps-Arab", "sd-Arab", "tt-Arab", "ug-Arab", "ur-Arab", "Armi", "Armn", "Avst", "Bali", "Bamu", "Batk", "Beng", "as-Beng", "Bopo", "Brah", "Brai", "Bugi", "Buhd", "Cakm", "Cans", "Cari", "Cham", "Cher", "Copt", "Cprt", "Cyrl", "Cyrs", "Deva", "Dsrt", "Egyd", "Egyp", "Ethi", "Geok", "Geor", "Glag", "Goth", "Grek", "Polyt", "polytonic", "Gujr", "Guru", "Hang", "Hani", "Hano", "Hebr", "Hira", "Hluw", "Ital", "Java", "Kali", "Kana", "Khar", "Khmr", "Knda", "Kthi", "Lana", "Laoo", "Latn", "Latf", "Latg", "Latnx", "Latinx", "pjt-Latn", "Lepc", "Limb", "Linb", "Lisu", "Lyci", "Lydi", "Mand", "Mani", "Marc", "Merc", "Mero", "Mlym", "Mong", "mnc-Mong", "sjo-Mong", "xwo-Mong", "Mtei", "Mymr", "Narb", "Nkoo", "Nshu", "Ogam", "Olck", "Orkh", "Orya", "Osma", "Ougr", "Palm", "Phag", "Phli", "Phlv", "Phnx", "Plrd", "Prti", "Rjng", "Runr", "Samr", "Sarb", "Saur", "Sgnw", "Shaw", "Shrd", "Sinh", "Sora", "Sund", "Sylo", "Syrc", "Tagb", "Tale", "Talu", "Taml", "Tang", "Tavt", "Telu", "Tfng", "Tglg", "Thaa", "Thai", "Tibt", "Ugar", "Vaii", "Xpeo", "Xsux", "Yiii", "Zmth", "Zsym", "Ipach", "Music", "Rumin", } --[==[ var: Parts of speech which will not be categorised in categories like `English terms spelled with É` if the term is the character in question (e.g. the letter entry for English [[é]]). This contrasts with entries like the French adjective [[m̂]], which is a one-letter word spelled with the letter. ]==] data.pos_not_spelled_with_self = list_to_set{ "diacritical marks", "Han characters", "Han tu", "hanja", "hanzi", "iteration marks", "kana", "kanji", "letters", "ligatures", "logograms", "morae", "numeral symbols", "numerals", "punctuation marks", "syllables", "symbols", } ------ 2. Lists not converted into sets. ------ --[==[ var: Recognized aliases for parts of speech (param 2=). Key is the short form and value is the canonical singular (not pluralized) form. It is singular so the same table can be used in [[Module:form of]] for the {{para|p}}/{{para|POS}} param and [[Module:links]] for the pos= param. Note that any part of speech, abbreviated or not, can be suffixed with `f` to generate the corresponding non-lemma form part of speech, such as `adjf`, `af` or `adjectivef` for `adjective form`, and `nounf` or `nf` for `noun form`. This expansion happens even when it does not make sense for the given part of speech (e.g. `pclf` expands to `particle form` and `symf` expands to `symbol form`), and currently also, at least in [[Module:headword]] (but not [[Module:links]]), even if the part before the `f` is not a recognized part of speech or abbreviation (hence `nerf` expands to `ner form`). ]==] data.pos_aliases = { a = "adjective", adj = "adjective", adv = "adverb", art = "article", aug = "augmentative", cls = "classifier", compadj = "comparative adjective", compadv = "comparative adverb", compdet = "comparative determiner", comppron = "comparative pronoun", conj = "conjunction", contr = "contraction", conv = "converb", det = "determiner", dim = "diminutive", int = "interjection", interj = "interjection", intj = "interjection", n = "noun", -- the next two support Algonquian languages; see also vii/vai/vti/vta below na = "animate noun", ni = "inanimate noun", num = "numeral", part = "participle", pastpart = "past participle", pastptcp = "past participle", pcl = "particle", phr = "phrase", pn = "proper noun", postp = "postposition", pref = "prefix", prep = "preposition", prepphr = "prepositional phrase", prespart = "present participle", presptcp = "present participle", pron = "pronoun", prop = "proper noun", proper = "proper noun", propn = "proper noun", ptcp = "participle", rom = "romanization", roman = "romanization", romanisation = "romanization", romanisations = "romanization", suf = "suffix", supadj = "superlative adjective", supadv = "superlative adverb", supdet = "superlative determiner", suppron = "superlative pronoun", sym = "symbol", v = "verb", vb = "verb", vi = "intransitive verb", vm = "modal verb", vt = "transitive verb", -- the next four support Algonquian languages vii = "inanimate intransitive verb", vai = "animate intransitive verb", vti = "transitive inanimate verb", vta = "transitive animate verb", } --[==[ var: Map of parts of speech for which categories like `German masculine nouns` or `Russian imperfective verbs` will be generated if the headword is of the appropriate gender/number. The map is used to canonicalize parts of speech for categorization purposes; specifically, proper nouns categorizes like nouns. ]==] data.pos_for_gender_number_cat = { ["nouns"] = "nouns", ["proper nouns"] = "nouns", ["suffixes"] = "suffixes", -- We include verbs because impf and pf are valid "genders". ["verbs"] = "verbs", } --[==[ var: Lower limit for a "long" word in a particular language. Used to categorize terms into e.g. [[:Category:Long English words]] automatically. Languages with no mapping here do not get categorized. ]==] data.long_word_thresholds = { ["af"] = 20, ["bg"] = 20, ["cy"] = 25, ["de"] = 20, ["en"] = 25, ["es"] = 20, ["fr"] = 20, ["ka"] = 20, ["sv"] = 20, ["tl"] = 25, } ------ 3. Page-wide processing (so that it only needs to be done once per page). ------ data.page = require(headword_page_module).process_page() -- Set some page properties directly on `data` for ease of use. data.pagename = data.page.pagename data.encoded_pagename = data.page.encoded_pagename return data 81blund1lug5e3dv927kffaobiikgrc 828 6007 17446 2026-07-13T08:49:50Z Hiyuune 6766 + 17446 Scribunto text/plain local debug_track_module = "Module:debug/track" local table_get_metamethod_module = "Module:table/getMetamethod" local require = require local type = type local function debug_track(...) debug_track = require(debug_track_module) return debug_track(...) end local function get_metamethod(...) get_metamethod = require(table_get_metamethod_module) return get_metamethod(...) end --[==[ Return {true} if the input is a function or functor (an object which can be called like a function, because it has a {__call} metamethod). Note: if the input is an object with a {__call} metamethod, but this function is not able to find it because the object's metatable is protected with {__metatable}, then it will return {false} by default, or {nil} if the {allow_maybe} flag is set.]==] return function(obj, allow_maybe) if type(obj) == "function" then return true end -- An object is callable if it has a __call metamethod, so try to get it -- with get_metamethod(). local success, __call = get_metamethod(obj, "__call") -- If this succeeds, `obj` will only be callable if the __call metamethod is -- a function (i.e. it can't itself be a callable table), so don't recurse -- to check it. if __call and type(__call) == "function" then return true -- If not, then the metatable is protected, so it's not possible to know if -- `obj` is callable without actually calling it. elseif not success then debug_track("fun/isCallable/protected metatable") if allow_maybe then return nil end end return false end nr6fmojt64uvmsick8bst0i74ec4d2z 828 6008 17447 2026-07-13T08:50:11Z Hiyuune 6766 + 17447 Scribunto text/plain local export = {} local languages_module = "Module:languages" local maintenance_category_module = "Module:maintenance category" local pages_module = "Module:pages" local string_compare_module = "Module:string/compare" local string_decode_entities_module = "Module:string/decodeEntities" local string_remove_comments_module = "Module:string/removeComments" local string_utilities_module = "Module:string utilities" local table_module = "Module:table" local template_parser_module = "Module:template parser" local mw = mw local string = string local table = table local ustring = mw.ustring local concat = table.concat local find = string.find local format = string.format local gsub = string.gsub local insert = table.insert local load_data = mw.loadData local match = string.match local new_title = mw.title.new local pairs = pairs local require = require local sub = string.sub local toNFC = ustring.toNFC local toNFD = ustring.toNFD local ugsub = ustring.gsub local function class_else_type(...) class_else_type = require(template_parser_module).class_else_type return class_else_type(...) end local function decode_entities(...) decode_entities = require(string_decode_entities_module) return decode_entities(...) end local function encode_entities(...) encode_entities = require(string_utilities_module).encode_entities return encode_entities(...) end local function get_category(...) get_category = require(maintenance_category_module).get_category return get_category(...) end local function get_lang(...) get_lang = require(languages_module).getByCode return get_lang(...) end local function list_to_set(...) list_to_set = require(table_module).listToSet return list_to_set(...) end local function parse(...) parse = require(template_parser_module).parse return parse(...) end local function remove_comments(...) remove_comments = require(string_remove_comments_module) return remove_comments(...) end local function physical_to_logical_pagename_if_mammoth(...) physical_to_logical_pagename_if_mammoth = require(pages_module).physical_to_logical_pagename_if_mammoth return physical_to_logical_pagename_if_mammoth(...) end local function split(...) split = require(string_utilities_module).split return split(...) end local function string_compare(...) string_compare = require(string_compare_module) return string_compare(...) end local function uupper(...) uupper = require(string_utilities_module).upper return uupper(...) end --[==[ Loaders for objects, which load data (or some other object) into some variable, which can then be accessed as "foo or get_foo()", where the function get_foo sets the object to "foo" and then returns it. This ensures they are only loaded when needed, and avoids the need to check for the existence of the object each time, since once "foo" has been set, "get_foo" will not be called again.]==] local langnames local function get_langnames() langnames, get_langnames = load_data("Module:languages/canonical names"), nil return langnames end -- Combining character data used when categorising unusual characters. These resolve into two patterns, used to find -- single combining characters (i.e. character + diacritic(s)) or double combining characters (i.e. character + -- diacritic(s) + character). -- Charsets are in the format used by Unicode's UnicodeSet tool: https://util.unicode.org/UnicodeJsps/list-unicodeset.jsp. -- Single combining characters. -- Charset: [[:M:]&[:^Canonical_Combining_Class=/^Double_/:]&[:^subhead=Grapheme joiner:]&[:^Variation_Selector=Yes:]] -- Note: concatenating hundreds of lines at once gives an error, so () are used every 150 lines to break it up into chunks. local comb_chars_single = ("\204\128-\205\142" .. -- U+0300-U+034E "\205\144-\205\155" .. -- U+0350-U+035B "\205\163-\205\175" .. -- U+0363-U+036F "\210\131-\210\137" .. -- U+0483-U+0489 "\214\145-\214\189" .. -- U+0591-U+05BD "\214\191" .. -- U+05BF "\215\129" .. -- U+05C1 "\215\130" .. -- U+05C2 "\215\132" .. -- U+05C4 "\215\133" .. -- U+05C5 "\215\135" .. -- U+05C7 "\216\144-\216\154" .. -- U+0610-U+061A "\217\139-\217\159" .. -- U+064B-U+065F "\217\176" .. -- U+0670 "\219\150-\219\156" .. -- U+06D6-U+06DC "\219\159-\219\164" .. -- U+06DF-U+06E4 "\219\167" .. -- U+06E7 "\219\168" .. -- U+06E8 "\219\170-\219\173" .. -- U+06EA-U+06ED "\220\145" .. -- U+0711 "\220\176-\221\138" .. -- U+0730-U+074A "\222\166-\222\176" .. -- U+07A6-U+07B0 "\223\171-\223\179" .. -- U+07EB-U+07F3 "\223\189" .. -- U+07FD "\224\160\150-\224\160\153" .. -- U+0816-U+0819 "\224\160\155-\224\160\163" .. -- U+081B-U+0823 "\224\160\165-\224\160\167" .. -- U+0825-U+0827 "\224\160\169-\224\160\173" .. -- U+0829-U+082D "\224\161\153-\224\161\155" .. -- U+0859-U+085B "\224\162\151-\224\162\159" .. -- U+0897-U+089F "\224\163\138-\224\163\161" .. -- U+08CA-U+08E1 "\224\163\163-\224\164\131" .. -- U+08E3-U+0903 "\224\164\186-\224\164\188" .. -- U+093A-U+093C "\224\164\190-\224\165\143" .. -- U+093E-U+094F "\224\165\145-\224\165\151" .. -- U+0951-U+0957 "\224\165\162" .. -- U+0962 "\224\165\163" .. -- U+0963 "\224\166\129-\224\166\131" .. -- U+0981-U+0983 "\224\166\188" .. -- U+09BC "\224\166\190-\224\167\132" .. -- U+09BE-U+09C4 "\224\167\135" .. -- U+09C7 "\224\167\136" .. -- U+09C8 "\224\167\139-\224\167\141" .. -- U+09CB-U+09CD "\224\167\151" .. -- U+09D7 "\224\167\162" .. -- U+09E2 "\224\167\163" .. -- U+09E3 "\224\167\190" .. -- U+09FE "\224\168\129-\224\168\131" .. -- U+0A01-U+0A03 "\224\168\188" .. -- U+0A3C "\224\168\190-\224\169\130" .. -- U+0A3E-U+0A42 "\224\169\135" .. -- U+0A47 "\224\169\136" .. -- U+0A48 "\224\169\139-\224\169\141" .. -- U+0A4B-U+0A4D "\224\169\145" .. -- U+0A51 "\224\169\176" .. -- U+0A70 "\224\169\177" .. -- U+0A71 "\224\169\181" .. -- U+0A75 "\224\170\129-\224\170\131" .. -- U+0A81-U+0A83 "\224\170\188" .. -- U+0ABC "\224\170\190-\224\171\133" .. -- U+0ABE-U+0AC5 "\224\171\135-\224\171\137" .. -- U+0AC7-U+0AC9 "\224\171\139-\224\171\141" .. -- U+0ACB-U+0ACD "\224\171\162" .. -- U+0AE2 "\224\171\163" .. -- U+0AE3 "\224\171\186-\224\171\191" .. -- U+0AFA-U+0AFF "\224\172\129-\224\172\131" .. -- U+0B01-U+0B03 "\224\172\188" .. -- U+0B3C "\224\172\190-\224\173\132" .. -- U+0B3E-U+0B44 "\224\173\135" .. -- U+0B47 "\224\173\136" .. -- U+0B48 "\224\173\139-\224\173\141" .. -- U+0B4B-U+0B4D "\224\173\149-\224\173\151" .. -- U+0B55-U+0B57 "\224\173\162" .. -- U+0B62 "\224\173\163" .. -- U+0B63 "\224\174\130" .. -- U+0B82 "\224\174\190-\224\175\130" .. -- U+0BBE-U+0BC2 "\224\175\134-\224\175\136" .. -- U+0BC6-U+0BC8 "\224\175\138-\224\175\141" .. -- U+0BCA-U+0BCD "\224\175\151" .. -- U+0BD7 "\224\176\128-\224\176\132" .. -- U+0C00-U+0C04 "\224\176\188" .. -- U+0C3C "\224\176\190-\224\177\132" .. -- U+0C3E-U+0C44 "\224\177\134-\224\177\136" .. -- U+0C46-U+0C48 "\224\177\138-\224\177\141" .. -- U+0C4A-U+0C4D "\224\177\149" .. -- U+0C55 "\224\177\150" .. -- U+0C56 "\224\177\162" .. -- U+0C62 "\224\177\163" .. -- U+0C63 "\224\178\129-\224\178\131" .. -- U+0C81-U+0C83 "\224\178\188" .. -- U+0CBC "\224\178\190-\224\179\132" .. -- U+0CBE-U+0CC4 "\224\179\134-\224\179\136" .. -- U+0CC6-U+0CC8 "\224\179\138-\224\179\141" .. -- U+0CCA-U+0CCD "\224\179\149" .. -- U+0CD5 "\224\179\150" .. -- U+0CD6 "\224\179\162" .. -- U+0CE2 "\224\179\163" .. -- U+0CE3 "\224\179\179" .. -- U+0CF3 "\224\180\128-\224\180\131" .. -- U+0D00-U+0D03 "\224\180\187" .. -- U+0D3B "\224\180\188" .. -- U+0D3C "\224\180\190-\224\181\132" .. -- U+0D3E-U+0D44 "\224\181\134-\224\181\136" .. -- U+0D46-U+0D48 "\224\181\138-\224\181\141" .. -- U+0D4A-U+0D4D "\224\181\151" .. -- U+0D57 "\224\181\162" .. -- U+0D62 "\224\181\163" .. -- U+0D63 "\224\182\129-\224\182\131" .. -- U+0D81-U+0D83 "\224\183\138" .. -- U+0DCA "\224\183\143-\224\183\148" .. -- U+0DCF-U+0DD4 "\224\183\150" .. -- U+0DD6 "\224\183\152-\224\183\159" .. -- U+0DD8-U+0DDF "\224\183\178" .. -- U+0DF2 "\224\183\179" .. -- U+0DF3 "\224\184\177" .. -- U+0E31 "\224\184\180-\224\184\186" .. -- U+0E34-U+0E3A "\224\185\135-\224\185\142" .. -- U+0E47-U+0E4E "\224\186\177" .. -- U+0EB1 "\224\186\180-\224\186\188" .. -- U+0EB4-U+0EBC "\224\187\136-\224\187\142" .. -- U+0EC8-U+0ECE "\224\188\152" .. -- U+0F18 "\224\188\153" .. -- U+0F19 "\224\188\181" .. -- U+0F35 "\224\188\183" .. -- U+0F37 "\224\188\185" .. -- U+0F39 "\224\188\190" .. -- U+0F3E "\224\188\191" .. -- U+0F3F "\224\189\177-\224\190\132" .. -- U+0F71-U+0F84 "\224\190\134" .. -- U+0F86 "\224\190\135" .. -- U+0F87 "\224\190\141-\224\190\151" .. -- U+0F8D-U+0F97 "\224\190\153-\224\190\188" .. -- U+0F99-U+0FBC "\224\191\134" .. -- U+0FC6 "\225\128\171-\225\128\190" .. -- U+102B-U+103E "\225\129\150-\225\129\153" .. -- U+1056-U+1059 "\225\129\158-\225\129\160" .. -- U+105E-U+1060 "\225\129\162-\225\129\164" .. -- U+1062-U+1064 "\225\129\167-\225\129\173" .. -- U+1067-U+106D "\225\129\177-\225\129\180" .. -- U+1071-U+1074 "\225\130\130-\225\130\141" .. -- U+1082-U+108D "\225\130\143" .. -- U+108F "\225\130\154-\225\130\157" .. -- U+109A-U+109D "\225\141\157-\225\141\159" .. -- U+135D-U+135F "\225\156\146-\225\156\149" .. -- U+1712-U+1715 "\225\156\178-\225\156\180" .. -- U+1732-U+1734 "\225\157\146" .. -- U+1752 "\225\157\147" .. -- U+1753 "\225\157\178" .. -- U+1772 "\225\157\179" .. -- U+1773 "\225\158\180-\225\159\147") .. -- U+17B4-U+17D3 ("\225\159\157" .. -- U+17DD "\225\162\133" .. -- U+1885 "\225\162\134" .. -- U+1886 "\225\162\169" .. -- U+18A9 "\225\164\160-\225\164\171" .. -- U+1920-U+192B "\225\164\176-\225\164\187" .. -- U+1930-U+193B "\225\168\151-\225\168\155" .. -- U+1A17-U+1A1B "\225\169\149-\225\169\158" .. -- U+1A55-U+1A5E "\225\169\160-\225\169\188" .. -- U+1A60-U+1A7C "\225\169\191" .. -- U+1A7F "\225\170\176-\225\171\142" .. -- U+1AB0-U+1ACE "\225\172\128-\225\172\132" .. -- U+1B00-U+1B04 "\225\172\180-\225\173\132" .. -- U+1B34-U+1B44 "\225\173\171-\225\173\179" .. -- U+1B6B-U+1B73 "\225\174\128-\225\174\130" .. -- U+1B80-U+1B82 "\225\174\161-\225\174\173" .. -- U+1BA1-U+1BAD "\225\175\166-\225\175\179" .. -- U+1BE6-U+1BF3 "\225\176\164-\225\176\183" .. -- U+1C24-U+1C37 "\225\179\144-\225\179\146" .. -- U+1CD0-U+1CD2 "\225\179\148-\225\179\168" .. -- U+1CD4-U+1CE8 "\225\179\173" .. -- U+1CED "\225\179\180" .. -- U+1CF4 "\225\179\183-\225\179\185" .. -- U+1CF7-U+1CF9 "\225\183\128-\225\183\140" .. -- U+1DC0-U+1DCC "\225\183\142-\225\183\187" .. -- U+1DCE-U+1DFB "\225\183\189-\225\183\191" .. -- U+1DFD-U+1DFF "\226\131\144-\226\131\176" .. -- U+20D0-U+20F0 "\226\179\175-\226\179\177" .. -- U+2CEF-U+2CF1 "\226\181\191" .. -- U+2D7F "\226\183\160-\226\183\191" .. -- U+2DE0-U+2DFF "\227\128\170-\227\128\175" .. -- U+302A-U+302F "\227\130\153" .. -- U+3099 "\227\130\154" .. -- U+309A "\234\153\175-\234\153\178" .. -- U+A66F-U+A672 "\234\153\180-\234\153\189" .. -- U+A674-U+A67D "\234\154\158" .. -- U+A69E "\234\154\159" .. -- U+A69F "\234\155\176" .. -- U+A6F0 "\234\155\177" .. -- U+A6F1 "\234\160\130" .. -- U+A802 "\234\160\134" .. -- U+A806 "\234\160\139" .. -- U+A80B "\234\160\163-\234\160\167" .. -- U+A823-U+A827 "\234\160\172" .. -- U+A82C "\234\162\128" .. -- U+A880 "\234\162\129" .. -- U+A881 "\234\162\180-\234\163\133" .. -- U+A8B4-U+A8C5 "\234\163\160-\234\163\177" .. -- U+A8E0-U+A8F1 "\234\163\191" .. -- U+A8FF "\234\164\166-\234\164\173" .. -- U+A926-U+A92D "\234\165\135-\234\165\147" .. -- U+A947-U+A953 "\234\166\128-\234\166\131" .. -- U+A980-U+A983 "\234\166\179-\234\167\128" .. -- U+A9B3-U+A9C0 "\234\167\165" .. -- U+A9E5 "\234\168\169-\234\168\182" .. -- U+AA29-U+AA36 "\234\169\131" .. -- U+AA43 "\234\169\140" .. -- U+AA4C "\234\169\141" .. -- U+AA4D "\234\169\187-\234\169\189" .. -- U+AA7B-U+AA7D "\234\170\176" .. -- U+AAB0 "\234\170\178-\234\170\180" .. -- U+AAB2-U+AAB4 "\234\170\183" .. -- U+AAB7 "\234\170\184" .. -- U+AAB8 "\234\170\190" .. -- U+AABE "\234\170\191" .. -- U+AABF "\234\171\129" .. -- U+AAC1 "\234\171\171-\234\171\175" .. -- U+AAEB-U+AAEF "\234\171\181" .. -- U+AAF5 "\234\171\182" .. -- U+AAF6 "\234\175\163-\234\175\170" .. -- U+ABE3-U+ABEA "\234\175\172" .. -- U+ABEC "\234\175\173" .. -- U+ABED "\239\172\158" .. -- U+FB1E "\239\184\160-\239\184\175" .. -- U+FE20-U+FE2F "\240\144\135\189" .. -- U+101FD "\240\144\139\160" .. -- U+102E0 "\240\144\141\182-\240\144\141\186" .. -- U+10376-U+1037A "\240\144\168\129-\240\144\168\131" .. -- U+10A01-U+10A03 "\240\144\168\133" .. -- U+10A05 "\240\144\168\134" .. -- U+10A06 "\240\144\168\140-\240\144\168\143" .. -- U+10A0C-U+10A0F "\240\144\168\184-\240\144\168\186" .. -- U+10A38-U+10A3A "\240\144\168\191" .. -- U+10A3F "\240\144\171\165" .. -- U+10AE5 "\240\144\171\166" .. -- U+10AE6 "\240\144\180\164-\240\144\180\167" .. -- U+10D24-U+10D27 "\240\144\181\169-\240\144\181\173" .. -- U+10D69-U+10D6D "\240\144\186\171" .. -- U+10EAB "\240\144\186\172" .. -- U+10EAC "\240\144\187\188-\240\144\187\191" .. -- U+10EFC-U+10EFF "\240\144\189\134-\240\144\189\144" .. -- U+10F46-U+10F50 "\240\144\190\130-\240\144\190\133" .. -- U+10F82-U+10F85 "\240\145\128\128-\240\145\128\130" .. -- U+11000-U+11002 "\240\145\128\184-\240\145\129\134" .. -- U+11038-U+11046 "\240\145\129\176" .. -- U+11070 "\240\145\129\179" .. -- U+11073 "\240\145\129\180" .. -- U+11074 "\240\145\129\191-\240\145\130\130" .. -- U+1107F-U+11082 "\240\145\130\176-\240\145\130\186" .. -- U+110B0-U+110BA "\240\145\131\130" .. -- U+110C2 "\240\145\132\128-\240\145\132\130" .. -- U+11100-U+11102 "\240\145\132\167-\240\145\132\180" .. -- U+11127-U+11134 "\240\145\133\133" .. -- U+11145 "\240\145\133\134" .. -- U+11146 "\240\145\133\179" .. -- U+11173 "\240\145\134\128-\240\145\134\130" .. -- U+11180-U+11182 "\240\145\134\179-\240\145\135\128" .. -- U+111B3-U+111C0 "\240\145\135\137-\240\145\135\140" .. -- U+111C9-U+111CC "\240\145\135\142" .. -- U+111CE "\240\145\135\143" .. -- U+111CF "\240\145\136\172-\240\145\136\183" .. -- U+1122C-U+11237 "\240\145\136\190" .. -- U+1123E "\240\145\137\129" .. -- U+11241 "\240\145\139\159-\240\145\139\170" .. -- U+112DF-U+112EA "\240\145\140\128-\240\145\140\131" .. -- U+11300-U+11303 "\240\145\140\187" .. -- U+1133B "\240\145\140\188" .. -- U+1133C "\240\145\140\190-\240\145\141\132" .. -- U+1133E-U+11344 "\240\145\141\135" .. -- U+11347 "\240\145\141\136" .. -- U+11348 "\240\145\141\139-\240\145\141\141" .. -- U+1134B-U+1134D "\240\145\141\151" .. -- U+11357 "\240\145\141\162" .. -- U+11362 "\240\145\141\163" .. -- U+11363 "\240\145\141\166-\240\145\141\172" .. -- U+11366-U+1136C "\240\145\141\176-\240\145\141\180" .. -- U+11370-U+11374 "\240\145\142\184-\240\145\143\128" .. -- U+113B8-U+113C0 "\240\145\143\130" .. -- U+113C2 "\240\145\143\133" .. -- U+113C5 "\240\145\143\135-\240\145\143\138" .. -- U+113C7-U+113CA "\240\145\143\140-\240\145\143\144" .. -- U+113CC-U+113D0 "\240\145\143\146" .. -- U+113D2 "\240\145\143\161" .. -- U+113E1 "\240\145\143\162" .. -- U+113E2 "\240\145\144\181-\240\145\145\134" .. -- U+11435-U+11446 "\240\145\145\158" .. -- U+1145E "\240\145\146\176-\240\145\147\131" .. -- U+114B0-U+114C3 "\240\145\150\175-\240\145\150\181" .. -- U+115AF-U+115B5 "\240\145\150\184-\240\145\151\128" .. -- U+115B8-U+115C0 "\240\145\151\156" .. -- U+115DC "\240\145\151\157" .. -- U+115DD "\240\145\152\176-\240\145\153\128" .. -- U+11630-U+11640 "\240\145\154\171-\240\145\154\183" .. -- U+116AB-U+116B7 "\240\145\156\157-\240\145\156\171" .. -- U+1171D-U+1172B "\240\145\160\172-\240\145\160\186" .. -- U+1182C-U+1183A "\240\145\164\176-\240\145\164\181" .. -- U+11930-U+11935 "\240\145\164\183" .. -- U+11937 "\240\145\164\184" .. -- U+11938 "\240\145\164\187-\240\145\164\190" .. -- U+1193B-U+1193E "\240\145\165\128") .. -- U+11940 ("\240\145\165\130" .. -- U+11942 "\240\145\165\131" .. -- U+11943 "\240\145\167\145-\240\145\167\151" .. -- U+119D1-U+119D7 "\240\145\167\154-\240\145\167\160" .. -- U+119DA-U+119E0 "\240\145\167\164" .. -- U+119E4 "\240\145\168\129-\240\145\168\138" .. -- U+11A01-U+11A0A "\240\145\168\179-\240\145\168\185" .. -- U+11A33-U+11A39 "\240\145\168\187-\240\145\168\190" .. -- U+11A3B-U+11A3E "\240\145\169\135" .. -- U+11A47 "\240\145\169\145-\240\145\169\155" .. -- U+11A51-U+11A5B "\240\145\170\138-\240\145\170\153" .. -- U+11A8A-U+11A99 "\240\145\176\175-\240\145\176\182" .. -- U+11C2F-U+11C36 "\240\145\176\184-\240\145\176\191" .. -- U+11C38-U+11C3F "\240\145\178\146-\240\145\178\167" .. -- U+11C92-U+11CA7 "\240\145\178\169-\240\145\178\182" .. -- U+11CA9-U+11CB6 "\240\145\180\177-\240\145\180\182" .. -- U+11D31-U+11D36 "\240\145\180\186" .. -- U+11D3A "\240\145\180\188" .. -- U+11D3C "\240\145\180\189" .. -- U+11D3D "\240\145\180\191-\240\145\181\133" .. -- U+11D3F-U+11D45 "\240\145\181\135" .. -- U+11D47 "\240\145\182\138-\240\145\182\142" .. -- U+11D8A-U+11D8E "\240\145\182\144" .. -- U+11D90 "\240\145\182\145" .. -- U+11D91 "\240\145\182\147-\240\145\182\151" .. -- U+11D93-U+11D97 "\240\145\187\179-\240\145\187\182" .. -- U+11EF3-U+11EF6 "\240\145\188\128" .. -- U+11F00 "\240\145\188\129" .. -- U+11F01 "\240\145\188\131" .. -- U+11F03 "\240\145\188\180-\240\145\188\186" .. -- U+11F34-U+11F3A "\240\145\188\190-\240\145\189\130" .. -- U+11F3E-U+11F42 "\240\145\189\154" .. -- U+11F5A "\240\147\145\128" .. -- U+13440 "\240\147\145\135-\240\147\145\149" .. -- U+13447-U+13455 "\240\150\132\158-\240\150\132\175" .. -- U+1611E-U+1612F "\240\150\171\176-\240\150\171\180" .. -- U+16AF0-U+16AF4 "\240\150\172\176-\240\150\172\182" .. -- U+16B30-U+16B36 "\240\150\189\143" .. -- U+16F4F "\240\150\189\145-\240\150\190\135" .. -- U+16F51-U+16F87 "\240\150\190\143-\240\150\190\146" .. -- U+16F8F-U+16F92 "\240\150\191\164" .. -- U+16FE4 "\240\150\191\176" .. -- U+16FF0 "\240\150\191\177" .. -- U+16FF1 "\240\155\178\157" .. -- U+1BC9D "\240\155\178\158" .. -- U+1BC9E "\240\156\188\128-\240\156\188\173" .. -- U+1CF00-U+1CF2D "\240\156\188\176-\240\156\189\134" .. -- U+1CF30-U+1CF46 "\240\157\133\165-\240\157\133\169" .. -- U+1D165-U+1D169 "\240\157\133\173-\240\157\133\178" .. -- U+1D16D-U+1D172 "\240\157\133\187-\240\157\134\130" .. -- U+1D17B-U+1D182 "\240\157\134\133-\240\157\134\139" .. -- U+1D185-U+1D18B "\240\157\134\170-\240\157\134\173" .. -- U+1D1AA-U+1D1AD "\240\157\137\130-\240\157\137\132" .. -- U+1D242-U+1D244 "\240\157\168\128-\240\157\168\182" .. -- U+1DA00-U+1DA36 "\240\157\168\187-\240\157\169\172" .. -- U+1DA3B-U+1DA6C "\240\157\169\181" .. -- U+1DA75 "\240\157\170\132" .. -- U+1DA84 "\240\157\170\155-\240\157\170\159" .. -- U+1DA9B-U+1DA9F "\240\157\170\161-\240\157\170\175" .. -- U+1DAA1-U+1DAAF "\240\158\128\128-\240\158\128\134" .. -- U+1E000-U+1E006 "\240\158\128\136-\240\158\128\152" .. -- U+1E008-U+1E018 "\240\158\128\155-\240\158\128\161" .. -- U+1E01B-U+1E021 "\240\158\128\163" .. -- U+1E023 "\240\158\128\164" .. -- U+1E024 "\240\158\128\166-\240\158\128\170" .. -- U+1E026-U+1E02A "\240\158\130\143" .. -- U+1E08F "\240\158\132\176-\240\158\132\182" .. -- U+1E130-U+1E136 "\240\158\138\174" .. -- U+1E2AE "\240\158\139\172-\240\158\139\175" .. -- U+1E2EC-U+1E2EF "\240\158\147\172-\240\158\147\175" .. -- U+1E4EC-U+1E4EF "\240\158\151\174" .. -- U+1E5EE "\240\158\151\175" .. -- U+1E5EF "\240\158\163\144-\240\158\163\150" .. -- U+1E8D0-U+1E8D6 "\240\158\165\132-\240\158\165\138") -- U+1E944-U+1E94A -- Double combining characters. -- Charset: [[:M:]&[:Canonical_Combining_Class=/^Double_/:]&[:^subhead=Grapheme joiner:]&[:^Variation_Selector=Yes:]] local comb_chars_double = "\205\156-\205\162" .. -- U+035C-U+0362 "\225\183\141" .. -- U+1DCD "\225\183\188" -- U+1DFC -- Variation selectors etc.; separated out so that we don't get categories for them. -- Charset: [[:M:]&[[:subhead=Grapheme joiner:][:Variation_Selector=Yes:]]]. local comb_chars_other = "\205\143" .. -- U+034F "\225\160\139-\225\160\141" .. -- U+180B-U+180D "\225\160\143" .. -- U+180F "\239\184\128-\239\184\143" .. -- U+FE00-U+FE0F "\243\160\132\128-\243\160\135\175" -- U+E0100-U+E01EF local comb_chars_all = comb_chars_single .. comb_chars_double .. comb_chars_other local comb_chars = { combined_single = "[^" .. comb_chars_all .. "][" .. comb_chars_single .. comb_chars_other .. "]+%f[^" .. comb_chars_all .. "]", combined_double = "[^" .. comb_chars_all .. "][" .. comb_chars_single .. comb_chars_other .. "]*[" .. comb_chars_double .. "]+[" .. comb_chars_all .. "]*.[" .. comb_chars_single .. comb_chars_other .. "]*", diacritics_single = "[" .. comb_chars_single .. "]", diacritics_double = "[" .. comb_chars_double .. "]", diacritics_all = "[" .. comb_chars_all .. "]" } -- Somewhat curated list from https://unicode.org/Public/emoji/16.0/emoji-sequences.txt. -- NOTE: There are lots more emoji sequences involving non-emoji Plane 0 symbols followed by 0xFE0F, which we don't -- (yet?) handle. local emoji_chars = "\226\140\154" .. -- U+231A (⌚) "\226\140\155" .. -- U+231B (⌛) "\226\140\168" .. -- U+2328 (⌨) "\226\143\143" .. -- U+23CF (⏏) "\226\143\169-\226\143\179" .. -- U+23E9-U+23F3 (⏩-⏳) "\226\143\184-\226\143\186" .. -- U+23F8-U+23FA (⏸-⏺) "\226\150\170" .. -- U+25AA (▪) "\226\150\171" .. -- U+25AB (▫) "\226\150\182" .. -- U+25B6 (▶) "\226\151\128" .. -- U+25C0 (◀) "\226\151\187-\226\151\190" .. -- U+25FB-U+25FE (◻-◾) "\226\152\128-\226\152\132" .. -- U+2600-U+2604 (☀-☄) "\226\152\142" .. -- U+260E (☎) "\226\152\145" .. -- U+2611 (☑) "\226\152\148" .. -- U+2614 (☔) "\226\152\149" .. -- U+2615 (☕) "\226\152\152" .. -- U+2618 (☘) "\226\152\157" .. -- U+261D (☝) "\226\152\160" .. -- U+2620 (☠) "\226\152\162" .. -- U+2622 (☢) "\226\152\163" .. -- U+2623 (☣) "\226\152\166" .. -- U+2626 (☦) "\226\152\170" .. -- U+262A (☪) "\226\152\174" .. -- U+262E (☮) "\226\152\175" .. -- U+262F (☯) "\226\152\184-\226\152\186" .. -- U+2638-U+263A (☸-☺) "\226\153\136-\226\153\147" .. -- U+2648-U+2653 (♈-♓) "\226\153\159" .. -- U+265F (♟) "\226\153\160" .. -- U+2660 (♠) "\226\153\163" .. -- U+2663 (♣) "\226\153\165" .. -- U+2665 (♥) "\226\153\166" .. -- U+2666 (♦) "\226\153\168" .. -- U+2668 (♨) "\226\153\187" .. -- U+267B (♻) "\226\153\190" .. -- U+267E (♾) "\226\153\191" .. -- U+267F (♿) "\226\154\146-\226\154\151" .. -- U+2692-U+2697 (⚒-⚗) "\226\154\153" .. -- U+2699 (⚙) "\226\154\155" .. -- U+269B (⚛) "\226\154\156" .. -- U+269C (⚜) "\226\154\160" .. -- U+26A0 (⚠) "\226\154\161" .. -- U+26A1 (⚡) "\226\154\170" .. -- U+26AA (⚪) "\226\154\171" .. -- U+26AB (⚫) "\226\154\176" .. -- U+26B0 (⚰) "\226\154\177" .. -- U+26B1 (⚱) "\226\154\189" .. -- U+26BD (⚽) "\226\154\190" .. -- U+26BE (⚾) "\226\155\132" .. -- U+26C4 (⛄) "\226\155\133" .. -- U+26C5 (⛅) "\226\155\136" .. -- U+26C8 (⛈) "\226\155\142" .. -- U+26CE (⛎) "\226\155\143" .. -- U+26CF (⛏) "\226\155\145" .. -- U+26D1 (⛑) "\226\155\147" .. -- U+26D3 (⛓) "\226\155\148" .. -- U+26D4 (⛔) "\226\155\169" .. -- U+26E9 (⛩) "\226\155\170" .. -- U+26EA (⛪) "\226\155\176-\226\155\181" .. -- U+26F0-U+26F5 (⛰-⛵) "\226\155\183-\226\155\186" .. -- U+26F7-U+26FA (⛷-⛺) "\226\155\189" .. -- U+26FD (⛽) "\226\156\130" .. -- U+2702 (✂) "\226\156\133" .. -- U+2705 (✅) "\226\156\136-\226\156\141" .. -- U+2708-U+270D (✈-✍) "\226\156\143" .. -- U+270F (✏) "\226\156\146" .. -- U+2712 (✒) "\226\156\148" .. -- U+2714 (✔) "\226\156\150" .. -- U+2716 (✖) "\226\156\157" .. -- U+271D (✝) "\226\156\161" .. -- U+2721 (✡) "\226\156\168" .. -- U+2728 (✨) "\226\156\179" .. -- U+2733 (✳) "\226\156\180" .. -- U+2734 (✴) "\226\157\132" .. -- U+2744 (❄) "\226\157\135" .. -- U+2747 (❇) "\226\157\140" .. -- U+274C (❌) "\226\157\142" .. -- U+274E (❎) "\226\157\147-\226\157\149" .. -- U+2753-U+2755 (❓-❕) "\226\157\151" .. -- U+2757 (❗) "\226\157\163" .. -- U+2763 (❣) "\226\157\164" .. -- U+2764 (❤) "\226\158\149-\226\158\151" .. -- U+2795-U+2797 (➕-➗) "\226\158\161" .. -- U+27A1 (➡) "\226\158\176" .. -- U+27B0 (➰) "\226\158\191" .. -- U+27BF (➿) "\226\164\180" .. -- U+2934 (⤴) "\226\164\181" .. -- U+2935 (⤵) "\226\172\133-\226\172\135" .. -- U+2B05-U+2B07 (⬅-⬇) "\226\172\155" .. -- U+2B1B (⬛) "\226\172\156" .. -- U+2B1C (⬜) "\226\173\144" .. -- U+2B50 (⭐) "\226\173\149" .. -- U+2B55 (⭕) "\227\128\176" .. -- U+3030 (〰) "\227\128\189" .. -- U+303D (〽) "\227\138\151" .. -- U+3297 (㊗) "\227\138\153" .. -- U+3299 (㊙) "\240\159\128\132" .. -- U+1F004 (🀄) "\240\159\131\143" .. -- U+1F0CF (🃏) "\240\159\133\176" .. -- U+1F170 (🅰) "\240\159\133\177" .. -- U+1F171 (🅱) "\240\159\133\190" .. -- U+1F17E (🅾) "\240\159\133\191" .. -- U+1F17F (🅿) "\240\159\134\142" .. -- U+1F18E (🆎) "\240\159\134\145-\240\159\134\154" .. -- U+1F191-U+1F19A (🆑-🆚) "\240\159\136\129" .. -- U+1F201 (🈁) "\240\159\136\130" .. -- U+1F202 (🈂) "\240\159\136\154" .. -- U+1F21A (🈚) "\240\159\136\175" .. -- U+1F22F (🈯) "\240\159\136\178-\240\159\136\186" .. -- U+1F232-U+1F23A (🈲-🈺) "\240\159\137\144" .. -- U+1F250 (🉐) "\240\159\137\145" .. -- U+1F251 (🉑) "\240\159\140\128-\240\159\153\143" .. -- U+1F300-U+1F64F (🌀-🙏) "\240\159\154\128-\240\159\155\151" .. -- U+1F680-U+1F6D7 (🚀-🛗) "\240\159\155\156-\240\159\155\172" .. -- U+1F6DC-U+1F6EC (🛜-🛬) "\240\159\155\176-\240\159\155\188" .. -- U+1F6F0-U+1F6FC (🛰-🛼) "\240\159\159\160-\240\159\159\171" .. -- U+1F7E0-U+1F7EB (🟠-🟫) "\240\159\159\176" .. -- U+1F7F0 (🟰) "\240\159\164\140-\240\159\169\147" .. -- U+1F90C-U+1FA53 (🤌-🩓) "\240\159\169\160-\240\159\169\173" .. -- U+1FA60-U+1FA6D (🩠-🩭) "\240\159\169\176-\240\159\169\188" .. -- U+1FA70-U+1FA7C (🩰-🩼) "\240\159\170\128-\240\159\170\137" .. -- U+1FA80-U+1FA89 (🪀-🪉) "\240\159\170\143-\240\159\171\134" .. -- U+1FA8F-U+1FAC6 (🪏-🫆) "\240\159\171\142-\240\159\171\156" .. -- U+1FACE-U+1FADC (🫎-🫜) "\240\159\171\159-\240\159\171\169" .. -- U+1FADF-U+1FAE9 (🫟-🫩) "\240\159\171\176-\240\159\171\184" -- U+1FAF0-U+1FAF8 (🫰-🫸) local unsupported_characters local function get_unsupported_characters() unsupported_characters, get_unsupported_characters = {}, nil for k, v in pairs(load_data("Module:links/data").unsupported_characters) do unsupported_characters[v] = k end return unsupported_characters end -- The list of unsupported titles and invert it (so the keys are pagenames and values are canonical titles). local unsupported_titles local function get_unsupported_titles() unsupported_titles, get_unsupported_titles = {}, nil for k, v in pairs(load_data("Module:links/data").unsupported_titles) do unsupported_titles[v] = k end return unsupported_titles end -- To save on memory, we only cache names with either non-ASCII characters in them or ASCII characters to be removed or -- transformed (apostrophe, double quote, hyphen). local L2_sort_key_cache = {} function export.get_L2_sort_key(L2) if L2 == "Translingual" then return "\1" elseif L2 == "English" then return "\2" elseif match(L2, "^[%z\1-\b\14-!#-&(-,.-\127]+$") then return L2 end local sort_key = L2_sort_key_cache[L2] if sort_key then return sort_key end sort_key = toNFC(ugsub(ugsub(toNFD(L2), "[" .. comb_chars_all .. "'\"ʻʼ]+", ""), "[%s%-]+", " ")) L2_sort_key_cache[L2] = sort_key return sort_key end --[==[ Given a pagename (or {nil} for the current page), create and return a data structure describing the page. The returned object includes the following fields: * `comb_chars`: A table containing various Lua character class patterns for different types of combined characters (those that decompose into multiple characters in the NFD decomposition). The patterns are meant to be used with {mw.ustring.find()}. The keys are: ** `single`: Single combining characters (character + diacritic), without surrounding brackets; ** `double`: Double combining characters (character + diacritic + character), without surrounding brackets; ** `vs`: Variation selectors, without surrounding brackets; ** `all`: Concatenation of `single` + `double` + `vs`, without surrounding brackets; ** `diacritics_single`: Like `single` but with surrounding brackets; ** `diacritics_double`: Like `double` but with surrounding brackets; ** `diacritics_all`: Like `all` but with surrounding brackets; ** `combined_single`: Lua pattern for matching a spacing character followed by one or more single combining characters; ** `combined_double`: Lua pattern for matching a combination of two spacing characters separated by one or more double combining characters, possibly also with single combining characters; * `emoji_pattern`: A Lua character class pattern (including surrounding brackets) that matches emojis. Meant to be used with {mw.ustring.find()}. * `L2_list`: Ordered list of L2 headings on the page, with the extra key `n` that gives the length of the list. * `L2_sections`: Lookup table of L2 headings on the page, where the key is the section number assigned by the preprocessor, and the value is the L2 heading name. Once an invocation has got its actual section number from get_current_L2 in [[Module:pages]], it can use this table to determine its parent L2. TODO: We could expand this to include subsections, to check POS headings are correct etc. * `unsupported_titles`: Map from pagenames to canonical titles for unsupported-title pages. * `namespace`: Namespace of the pagename. * `ns`: Namespace table for the page from mw.site.namespaces (TODO: merge with `namespace` above). * `full_raw_pagename`: Full version of the '''RAW''' pagename (i.e. unsupported-title pages aren't canonicalized); including the namespace and the base (portion before the slash). * `pagename`: Canonicalized subpage portion of the pagename (unsupported-title pages are canonicalized). * `pagename_with_base`: Same as `pagename` in the main namespace; otherwise, the whole pagename without the namespace. * `decompose_pagename`: Equivalent of `pagename` in NFD decomposition. * `pagename_len`: Length of `pagename` in Unicode chars, where combinations of spacing character + decomposed diacritic are treated as single characters. * `explode_pagename`: Set of characters found in `pagename`. The keys are characters (where combinations of spacing character + decomposed diacritic are treated as single characters). * `encoded_pagename`: FIXME: Document me. * `pagename_defaultsort`: FIXME: Document me. * `raw_defaultsort`: FIXME: Document me. * `wikitext_topic_cat`: FIXME: Document me. * `wikitext_langname_cat`: FIXME: Document me. `no_fetch_content` says to not fetch and parse the content or set a DEFAULTSORT sort key, in order to save time on test and documentation pages that have lots of template invocations that set `|pagename=`. It turns out nearly all the time of this function is contained in the line `frame:callParserFunction("DEFAULTSORT", data.pagename_defaultsort)`, so we skip it on test and documentation pages where it accomplishes nothing in any case. ]==] function export.process_page(pagename, no_fetch_content) local data = { comb_chars = comb_chars, emoji_pattern = "[" .. emoji_chars .. "]", unsupported_titles = unsupported_titles or get_unsupported_titles() } local cats = {} data.cats = cats -- We cannot store `raw_title` in `data` because it contains a metatable. local raw_title local function bad_pagename() if not pagename then error("Internal error: Something wrong, `data.pagename` not specified but current title contains illegal characters") else error(format("Bad value for `data.pagename`: '%s', which must not contain illegal characters", pagename)) end end if pagename then -- for testing, doc pages, etc. raw_title = new_title(pagename) if not raw_title then bad_pagename() end else raw_title = mw.title.getCurrentTitle() end local nsText = raw_title.nsText local namespace_is_reconstruction = nsText == "Reconstruction" data.namespace = nsText data.ns = mw.site.namespaces[raw_title.namespace] local full_raw_pagename = raw_title.fullText data.full_raw_pagename = full_raw_pagename local frame = mw.getCurrentFrame() -- WARNING: `content` may be nil, e.g. if we're substing a template like {{ja-new}} on a not-yet-created page -- or if the module specifies the subpage as `data.pagename` (which many modules do) and we're in an Appendix -- or other non-mainspace page. We used to make the latter an error but there are too many modules that do it, -- and substing on a nonexistent page is totally legit, and we don't actually need to be able to access the -- content of the page. local content = not no_fetch_content and raw_title:getContent() or nil -- Get the pagename. pagename = physical_to_logical_pagename_if_mammoth(raw_title) pagename = gsub(pagename, "^Unsupported titles/(.+)", function(m) insert(cats, "Unsupported titles") local title = (unsupported_titles or get_unsupported_titles())[m] if title then return title end -- Substitute pairs of "`". Those not used for escaping should be escaped as "`grave`", but might not be, -- so if a pair don't form a match, the closing "`" should become the opening "`" of the next match attempt. -- This has to be done manually, instead of using gsub. local open_pos = find(m, "`") if not open_pos then return m end title = {sub(m, 1, open_pos - 1)} while true do local close_pos = find(m, "`", open_pos + 1) if not close_pos then -- Add "`" plus any remaining characters. insert(title, sub(m, open_pos)) break end local escape = sub(m, open_pos, close_pos) local ch = (unsupported_characters or get_unsupported_characters())[escape] -- Match found, so substitute the character and move to the first "`" after the match if found, or -- otherwise return. if ch then insert(title, ch) local nxt_pos = close_pos + 1 open_pos = find(m, "`", nxt_pos) -- Add any characters between the match and the next "`" or end. if open_pos then insert(title, sub(m, nxt_pos, open_pos - 1)) else insert(title, sub(m, nxt_pos)) break end -- Match not found, so make the closing "`" the opening "`" of the next attempt. else -- Add the failed match, except for the closing "`". insert(title, sub(m, open_pos, close_pos - 1)) open_pos = close_pos end end return concat(title) end) -- Save pagename, as the local variable will be destructively modified. data.pagename = pagename if nsText == "" then data.pagename_with_base = pagename else data.pagename_with_base = raw_title.text end -- Decompose the pagename in Unicode normalization form D. data.decompose_pagename = toNFD(pagename) -- Explode the current page name into a character table, taking decomposed combining characters into account. local explode_pagename = {} local pagename_len = 0 local function explode(char) explode_pagename[char] = true pagename_len = pagename_len + 1 return "" end pagename = ugsub(pagename, comb_chars.combined_double, explode) pagename = gsub(ugsub(pagename, comb_chars.combined_single, explode), ".[\128-\191]*", explode) data.explode_pagename = explode_pagename data.pagename_len = pagename_len -- Generate DEFAULTSORT. data.encoded_pagename = encode_entities(data.pagename) data.pagename_defaultsort = get_lang("mul"):makeSortKey(data.encoded_pagename) if not no_fetch_content then frame:callParserFunction("DEFAULTSORT", data.pagename_defaultsort) end data.raw_defaultsort = uupper(raw_title.text) -- Make `L2_list` and `L2_sections`, note raw wikitext use of {{DEFAULTSORT:}} and {{DISPLAYTITLE:}}, then add categories if any unwanted L1 headings are found, the L2 headings are in the wrong order, or they don't match a canonical language name. -- Note: HTML comments shouldn't be removed from `content` until after this step, as they can affect the result. do local L2_list, L2_list_len, L2_sections = {}, 0, {} local prev, rc local new_cats, L2_wrong_order = {} local function handle_heading(heading) local level = heading.level if level > 2 then return end local name = heading:get_name() -- heading:get_name() will return nil if there are any newline characters in the preprocessed heading name (e.g. from an expanded template). In such cases, the preprocessor section count still increments (since it's calculated pre-expansion), but the heading will fail, so the L2 count shouldn't be incremented. if name == nil then return end L2_list_len = L2_list_len + 1 L2_list[L2_list_len] = name L2_sections[heading.section] = name -- Also add any L1s, since they terminate the preceding L2, but add a maintenance category since it's probably a mistake. if level == 1 then new_cats["Pages with unwanted L1 headings"] = true end -- Check the heading is in the right order. -- FIXME: we need a more sophisticated sorting method which handles non-diacritic special characters (e.g. Magɨ). if prev and not ( L2_wrong_order or string_compare(export.get_L2_sort_key(prev), export.get_L2_sort_key(name)) ) then new_cats["Pages with language headings in the wrong order"] = true L2_wrong_order = true end -- Check it's a canonical language name. if not (langnames or get_langnames())[name] then new_cats["Pages with nonstandard language headings"] = true end prev = name end local function handle_template(template) -- Turn off redirect checking except in the Reconstruction namespace because the rc flag is only -- used in the Reconstruction namespace and the other names are parser functions, which AFAIK can't -- be redirected to. local name = template:get_name(nil, not namespace_is_reconstruction and "no_redirect" or nil) if name == "DEFAULTSORT:" then new_cats["Pages with DEFAULTSORT conflicts"] = true elseif name == "DISPLAYTITLE:" then new_cats["Pages with DISPLAYTITLE conflicts"] = true elseif name == "reconstructed" then rc = true end end if content then for node in parse(content):iterate_nodes() do local node_class = class_else_type(node) if node_class == "heading" then handle_heading(node) elseif node_class == "template" then handle_template(node) elseif node_class == "parameter" then new_cats["Pages with raw triple-brace template parameters"] = true end end end L2_list.n = L2_list_len data.L2_list = L2_list data.L2_sections = L2_sections insert(cats, get_category("Pages with entries")) insert(cats, get_category(format("Pages with %s entr%s", L2_list_len, L2_list_len == 1 and "y" or "ies"))) for cat in pairs(new_cats) do insert(cats, get_category(cat)) end if namespace_is_reconstruction and not rc then local langname = match(full_raw_pagename, "^Reconstruction:([^/]+)/.") if langname then insert(cats, get_category(langname .. " entries missing Template:reconstructed")) end end end ------ 4. Parse page for maintenance categories. ------ -- Use of tab characters. if content and find(content, "\t", 1, true) then insert(cats, get_category("Pages with tab characters")) end -- Unencoded character(s) in title. local IDS = list_to_set{"⿰", "⿱", "⿲", "⿳", "⿴", "⿵", "⿶", "⿷", "⿸", "⿹", "⿺", "⿻", "⿼", "⿽", "⿾", "⿿", "㇯"} for char in pairs(explode_pagename) do if IDS[char] and char ~= data.pagename then insert(cats, "Terms containing unencoded characters") break end end -- Raw wikitext use of a topic or langname category. Also check if any raw sortkeys have been used. do local wikitext_topic_cat = {} local wikitext_langname_cat = {} local raw_sortkey -- If a raw sortkey has been found, add it to the relevant table. -- If there's no table (or the index is just `true`), create one first. local function add_cat_table(t, lang, sortkey) local t_lang = t[lang] if not sortkey then if not t_lang then t[lang] = true end return elseif t_lang == true or not t_lang then t_lang = {} t[lang] = t_lang end t_lang[uupper(decode_entities(sortkey))] = true end local function process_category(content, cat, colon, nxt) local pipe = find(cat, "|", colon + 1, true) -- Categories cannot end "|]]". if pipe == #cat then return end local title = new_title(pipe and sub(cat, 1, pipe - 1) or cat) if not (title and title.namespace == 14) then return end -- Get the sortkey (if any), then canonicalize category title. local sortkey = pipe and sub(cat, pipe + 1) or nil cat = title.text if sortkey then raw_sortkey = true -- If the sortkey contains "[", the first "]" of a final "]]]" is treated as part of the sortkey. if find(sortkey, "[", 1, true) and sub(content, nxt, nxt) == "]" then sortkey = sortkey .. "]" end end local code = match(cat, "^([%w%-.]+):") if code then add_cat_table(wikitext_topic_cat, code, sortkey) return end -- Split by word. cat = split(cat, " ", true, true) -- Formerly we looked for the language name anywhere in the category. This is simply wrong -- because there are no categories like 'Alsatian French lemmas' (only L2 languages -- have langname categories), but doing it this way wrongly catches things like [[Category:Shapsug Adyghe]] -- in [[Category:Adyghe entries with language name categories using raw markup]]. local n = #cat - 1 if n <= 0 then return end -- Go from longest to shortest and stop once we've found a language name. Going from shortest -- to longest or not stopping after a match risks falsely matching (e.g.) German Low German -- categories as German. repeat local name = concat(cat, " ", 1, n) if (langnames or get_langnames())[name] then add_cat_table(wikitext_langname_cat, name, sortkey) return end n = n - 1 until n == 0 end if content then -- Remove comments, then iterate over category links. content = remove_comments(content, "BOTH") local head = find(content, "[[", 1, true) while head do local close = find(content, "]]", head + 2, true) if not close then break end -- Make sure there are no intervening "[[" between head and close. local open = find(content, "[[", head + 2, true) while open and open < close do head = open open = find(content, "[[", head + 2, true) end local cat = sub(content, head + 2, close - 1) -- Locate the colon, and weed out most unwanted links. "[ _\128-\244]*" catches valid whitespace, and ensures any category links using the colon trick are ignored. We match all non-ASCII characters, as there could be multibyte spaces, and mw.title.new will filter out any remaining false-positives; this is a lot faster than running mw.title.new on every link. local colon = match(cat, "^[ _\128-\244]*[Cc][Aa][Tt][EeGgOoRrYy _\128-\244]*():") if colon then process_category(content, cat, colon, close + 2) end head = open end end data.wikitext_topic_cat = wikitext_topic_cat data.wikitext_langname_cat = wikitext_langname_cat if raw_sortkey then insert(cats, get_category("Pages with raw sortkeys")) end end return data end return export 0esb0zcz2sjpy8aqh1uv1deoe3q625h 828 6009 17448 2026-07-13T08:50:48Z Hiyuune 6766 + 17448 Scribunto text/plain local export = {} local m_links_data = mw.loadData("Module:links/data") local m_parameters = require("Module:parameters") local m_template_parser = require("Module:template parser") local m_utilities = require("Module:utilities") local insert = table.insert local concat = table.concat local unpack = unpack or table.unpack -- Lua 5.2 compatibility function export.show_template(frame) local parent_args = frame:getParent().args local args = m_parameters.process(parent_args, { pagename = true }) local this_title if args.pagename then this_title = mw.title.new(args.pagename) if not this_title then error(("Bad pagename: '%s'"):format(args.pagename)) end else this_title = mw.title.getCurrentTitle() end -- Are we on a subpage? local root_mammoth_page_title = this_title -- Formerly we checked for the specific known subpages of a given mammoth split page, e.g. we would convert -- [[a/languages M to Z]] to [[a]] assuming that [[a/languages M to Z]] was one of the splits, but not -- [[a/languages N to Z]]. To simplify this, we just convert anything with the right mammoth split page format -- on the assumption that it's unlikely we will ever have a legitimate non-mammoth-split pagename of this sort. local prefixed_base, subpage = this_title.prefixedText:match("^(.+)/(languages [A-Z] to [A-Z])$") if subpage then root_mammoth_page_title = mw.title.new(prefixed_base) if not root_mammoth_page_title then error(("Internal error: Something wrong, prefixed base '%s' of mammoth page has bad character even though prefixedText '%s' does not seem to"):format( prefixed_base, this_title.prefixedText)) end end -- Translingual and English are assumed to always be present on the root page local toc_links = { "[[" .. root_mammoth_page_title.prefixedText .. "#Translingual|Translingual]] •&nbsp;" .. "[[" .. root_mammoth_page_title.prefixedText .. "#English|English]]" } local L2_count = 2 -- compile a list of L2 headers on each subpage for _, subpage_spec in ipairs(m_links_data.mammoth_page_subpage_types[m_links_data.mammoth_pages[root_mammoth_page_title.subpageText]]) do local subpage_name = subpage_spec[1] local subpage_title = root_mammoth_page_title:subPageTitle(subpage_name) local subpage_content = subpage_title and subpage_title:getContent() if subpage_content then local subpage_links = {} for heading in m_template_parser.find_headings(subpage_content, 2, 2) do local name = heading:get_name() if name then -- malformed L2 headings (e.g. with newlines in them due to template expansion) don't have names local link = "[[" .. root_mammoth_page_title.prefixedText .. "/" .. subpage_name .. "#" .. name .. "|" .. name .. "]]" insert(subpage_links, link) L2_count = L2_count + 1 end end insert(toc_links, concat(subpage_links, " •&nbsp;")) end end return frame:extensionTag("templatestyles", nil, {src="Module:minitoc/styles.css"}) .. "<div class=\"NavFrame no-collapse minitoc mammoth-minitoc\">" .. "<div class=\"NavHead\">Languages (" .. L2_count .. ")</div>" .. "<div class=\"NavContent\">" .. (toc_links and concat(toc_links, "<hr>") or "") .. "<hr>" .. "<div>''The entries for '''" .. root_mammoth_page_title.text .. "''' are spread across multiple pages due to their length.''</div></div></div>" .. m_utilities.format_categories("Mammoth pages") end return export oyq8xohsusjfjndqkkkxqvrhbv19ich 828 6010 17450 2026-07-13T08:52:15Z Hiyuune 6766 + 17450 Scribunto text/plain local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared local m = {} m["maa"] = { "San Jerónimo Tecóatl Mazatec", 7692927, "omq-maz", "Latn", } m["mab"] = { "Yutanduchi Mixtec", 12645448, "omq-mxt", "Latn", } m["mad"] = { "Madurese", 36213, "poz-msa", "Latn, Java", } m["mae"] = { "Bo-Rukul", 34967, "nic-ple", "Latn", } m["maf"] = { "Mafa", 35819, "cdc-cbm", "Latn", } m["mag"] = { "Magahi", -- Not to be confused with Magadhi Prakrit (pra-mag) 33728, "inc-bih", "Deva, Kthi", translit = { Deva = "bho-translit", Kthi = "bho-Kthi-translit", }, } m["mai"] = { "Maithili", 36109, "inc-bih", "Deva, Tirh, Kthi, Newa", translit = { Deva = "mai-translit", Tirh = "mai-Tirh-translit", Kthi = "bho-Kthi-translit", }, } m["maj"] = { "Jalapa de Díaz Mazatec", 3915999, "omq-maz", "Latn", } m["mak"] = { "Makasar", 33643, "poz-ssw", "Latn, Bugi, Maka", } m["mam"] = { "Mam", 33467, "myn", "Latn", } m["man"] = { "Mandingo", 35772, "dmn-man", "Latn", } m["maq"] = { "Chiquihuitlán Mazatec", 5101757, "omq-maz", "Latn", } m["mas"] = { "Maasai", 35787, "sdv-lma", "Latn", } m["mat"] = { "Matlatzinca", 12953704, "omq", "Latn", } m["mau"] = { "Huautla Mazatec", 36230, "omq-maz", "Latn", } m["mav"] = { "Sateré-Mawé", 6794475, "tup", "Latn", } m["maw"] = { "Mampruli", 35804, "nic-wov", "Latn", } m["max"] = { "North Moluccan Malay", 7056136, "crp", "Latn", ancestors = "ms", } m["maz"] = { "Central Mazahua", 36228, "oto", "Latn", } m["mba"] = { "Higaonon", 5753411, "mno", "Latn", } m["mbb"] = { "Western Bukidnon Manobo", 7987643, "mno", "Latn", } m["mbc"] = { "Macushi", 56633, "sai-pem", "Latn", } m["mbd"] = { "Dibabawon Manobo", 18755523, "mno", "Latn", } m["mbe"] = { "Molale", 3319444, "nai-plp", "Latn", } m["mbf"] = { "Baba Malay", 18642798, "crp", "Latn", ancestors = "ms", } m["mbh"] = { "Mangseng", 6749147, "poz-ocw", "Latn", } m["mbi"] = { "Ilianen Manobo", 14916911, "mno", "Latn", } m["mbj"] = { "Nadëb", 3335011, "sai-nad", "Latn", } m["mbk"] = { "Malol", 6744477, "poz-ocw", "Latn", } m["mbl"] = { "Maxakalí", 3029682, "sai-mje", "Latn", } m["mbm"] = { "Ombamba", 36407, "bnt-mbt", "Latn", } m["mbn"] = { "Macaguán", 3273980, "sai-guh", "Latn", } m["mbo"] = { -- is, like 'bqz', 'bsi' and 'bss', a dialect of Manenguba "Mbo (Cameroon)", 36011, "bnt-mne", "Latn", } m["mbp"] = { "Wiwa", 3012604, "cba", "Latn", } m["mbq"] = { "Maisin", 3448149, nil, "Latn", } m["mbr"] = { "Nukak Makú", 3346228, "sai-nad", "Latn", } m["mbs"] = { "Sarangani Manobo", 7423093, "mno", "Latn", } m["mbt"] = { "Matigsalug Manobo", 6787447, "mno", "Latn", } m["mbu"] = { "Mbula-Bwazza", 3913324, "nic-jrn", "Latn", } m["mbv"] = { "Mbulungish", 36003, "alv-nal", "Latn", } m["mbw"] = { "Maring", 3293280, "ngf-jim", "Latn", } m["mbx"] = { "Mari (Sepik)", 6760942, "paa-sep", "Latn", } m["mby"] = { "Memoni", 4180871, "inc-snd", "Gujr, ur-Arab", } m["mbz"] = { "Amoltepec Mixtec", 13583504, "omq-mxt", "Latn", } m["mca"] = { "Maca", 3281043, "sai-mtc", "Latn", } m["mcb"] = { "Machiguenga", 3915441, "awd", "Latn", } m["mcc"] = { "Bitur", 4919173, "paa-tir", "Latn", } m["mcd"] = { "Sharanahua", 12953881, "sai-pan", "Latn", } m["mce"] = { "Itundujia Mixtec", 12953727, "omq-mxt", "Latn", } m["mcf"] = { "Matsés", 2981620, "sai-pan", "Latn", } m["mcg"] = { "Mapoyo", 56946, "sai-map", "Latn", } m["mch"] = { "Ye'kwana", 3082027, "sai-car", "Latn", sort_key = { remove_diacritics = "%-%s", from = {"'", "ñ", "ö", "sh", "ü"}, to = {"’", "n" .. p[1], "o" .. p[1], "s" .. p[1], "u" .. p[1]} } } m["mci"] = { "Mese", 6821190, "ngf-san", "Latn", } m["mcj"] = { "Mvanip", 3913281, "nic-mmb", "Latn", } m["mck"] = { "Mbunda", 34170, "bnt-clu", "Latn", } m["mcl"] = { "Macaguaje", 6722435, "sai-tuc", "Latn", } m["mcm"] = { "Kristang", 2669169, "crp", "Latn", ancestors = "pt", } m["mcn"] = { "Masana", 56668, "cdc-mas", } m["mco"] = { "Coatlán Mixe", 25559716, "nai-miz", "Latn", } m["mcp"] = { "Makaa", 35803, "bnt-mka", } m["mcq"] = { "Ese", 5397551, "ngf-koi", "Latn", } m["mcr"] = { "Menya", 11732444, "ngf-kme", "Latn", } m["mcs"] = { "Mambai", 6748872, "alv-mbm", } m["mcu"] = { "Cameroon Mambila", 19359039, "nic-mmb", "Latn", } -- mcv (Minanibai) merged into ffi (Foia Foia) per Glottolog m["mcw"] = { "Mawa", 3441333, "cdc-est", "Latn", } m["mcx"] = { "Mpiemo", 35908, "bnt-bek", } m["mcy"] = { "South Watut", 12953293, "poz-ocw", "Latn", } m["mcz"] = { "Mawan", 11732429, "ngf-han", "Latn", } m["mda"] = { "Mada (Nigeria)", 3915843, "nic-nin", "Latn", } m["mdb"] = { "Morigi", 6912195, "paa-kiw", "Latn", } m["mdc"] = { "Male", 6742927, "ngf-min", "Latn", } m["mdd"] = { "Mbum", 36170, "alv-mbm", } m["mde"] = { "Bura Mabang", 35860, "ssa", "Arab, Latn", } m["mdf"] = { "Moksha", 13343, "urj-mdv", "Cyrl", translit = "mdf-translit", strip_diacritics = {remove_diacritics = c.acute}, override_translit = true, sort_key = "mdf-sortkey", } m["mdg"] = { "Massalat", 759984, nil, "Latn", } m["mdh"] = { "Maguindanao", 33717, "phi", "Latn, Arab", } m["mdi"] = { "Mamvu", 3033594, "csu-mle", } m["mdj"] = { "Mangbetu", 56327, "csu-maa", "Latn", } m["mdk"] = { "Mangbutu", 6748877, "csu-mle", } m["mdl"] = { "Maltese Sign Language", 6744816, "sgn", } m["mdm"] = { "Mayogo", 6797580, "nic-nke", "Latn", } m["mdn"] = { "Mbati", 36165, "bnt-ngn", } m["mdp"] = { "Mbala", 6799583, "bnt-pen", } m["mdq"] = { "Mbole", 6799727, "bnt-mbe", } m["mdr"] = { "Mandar", 35995, "poz-ssw", "Bugi, Latn", } m["mds"] = { "Maria", 3448673, "paa-man", "Latn", } m["mdt"] = { "Mbere", 36062, "bnt-mbt", } m["mdu"] = { "Mboko", 36058, "bnt-mbo", } m["mdv"] = { "Santa Lucía Monteverde Mixtec", 12953722, "omq-mxt", "Latn", } m["mdw"] = { "Mbosi", 36035, "bnt-mbo", } m["mdx"] = { "Dizin", 35313, "omv-diz", "Ethi, Latn", } m["mdy"] = { "Maale", 795327, "omv-ome", } m["mdz"] = { "Suruí Do Pará", 10322149, "tup-gua", "Latn", } m["mea"] = { "Menka", 36078, "nic-grs", "Latn", } m["meb"] = { "Ikobi-Mena", 11732241, "paa-tki", "Latn", } m["mec"] = { "Mara", 6772774, } m["med"] = { "Melpa", 36166, "ngf-hag", "Latn", } m["mee"] = { "Mengen", 3305831, "poz-ocw", "Latn", } m["mef"] = { "Megam", 6808589, } m["meh"] = { "Southwestern Tlaxiaco Mixtec", 7070686, "omq-mxt", "Latn", } m["mei"] = { "Midob", 36007, "nub", "Latn", } m["mej"] = { "Meyah", 11732436, "paa-ebh", "Latn", } m["mek"] = { "Mekeo", 3304803, "poz-ocw", "Latn", } m["mel"] = { "Central Melanau", 18638319, "poz-swa", "Latn", } m["mem"] = { "Mangala", 6748664, } m["men"] = { "Mende (Sierra Leone)", 1478672, "dmn-msw", "Latn, Mend", } m["meo"] = { "Kedah Malay", 4925684, "poz-mly", "Latn, ms-Arab, Thai", strip_diacritics = { from = {u(0xF70F)}, to = {"ญ"} }, sort_key = {Thai = "Thai-sortkey"}, } m["mep"] = { "Miriwoong", 3111847, "aus-jar", "Latn", } m["meq"] = { "Merey", 3502314, "cdc-cbm", "Latn", } m["mer"] = { "Meru", 13313, "bnt-kka", "Latn", } m["mes"] = { "Masmaje", 3440448, } m["met"] = { "Mato", 3299190, "poz-ocw", "Latn", } m["meu"] = { "Motu", 33516, "poz-ocw", "Latn", } m["mev"] = { "Mano", 3913286, "dmn-mda", "Latn", } m["mew"] = { "Maaka", 3438764, "cdc-wst", "Latn", } m["mey"] = { "Hassaniya Arabic", 56231, "sem-arb", "Arab", } m["mez"] = { "Menominee", 13363, "alg", "Latn", sort_key = {remove_diacritics = "·"}, } m["mfa"] = { "Pattani Malay", 1199751, "poz-mly", "Latn, ms-Arab, Thai", strip_diacritics = { from = {u(0xF70F)}, to = {"ญ"} }, sort_key = {Thai = "Thai-sortkey"}, } m["mfb"] = { "Bangka", 3258818, "poz-mly", "Latn, Arab", } m["mfc"] = { "Mba", 4286464, "nic-mbc", "Latn", } m["mfd"] = { "Mendankwe-Nkwen", 11129537, "nic-nge", "Latn", } m["mfe"] = { "Mauritian Creole", 33661, "crp", "Latn", ancestors = "fr", sort_key = s["roa-oil-sortkey"], } m["mff"] = { "Naki", 36083, "nic-bbe", "Latn", } m["mfg"] = { "Mixifore", 3914478, "dmn-mok", } m["mfh"] = { "Matal", 3501751, "cdc-cbm", "Latn", } m["mfi"] = { "Wandala", 3441249, "cdc-cbm", "Latn", } m["mfj"] = { "Mefele", 3501871, "cdc-cbm", } m["mfk"] = { "North Mofu", 56303, "cdc-cbm", "Latn", } m["mfl"] = { "Putai", 56291, } m["mfm"] = { "Marghi South", 56248, } m["mfn"] = { "Cross River Mbembe", 3915395, "nic-uce", "Latn", } m["mfo"] = { "Mbe", 36075, "nic-eko", "Latn", } m["mfp"] = { "Makassar Malay", 12952776, "qfa-mix", "Latn", ancestors = "ms, mak" } m["mfq"] = { "Moba", 19921578, "nic-grm", "Latn", } m["mfr"] = { "Marrithiyel", 6773014, "aus-dal", "Latn", } m["mfs"] = { "Mexican Sign Language", 3915511, "sgn", "Latn", -- when documented } m["mft"] = { "Mokerang", 3319387, "poz-aay", "Latn", } m["mfu"] = { "Mbwela", 11004988, "bnt-clu", ancestors = "lch", } m["mfv"] = { "Mandjak", 35822, "alv-pap", } m["mfw"] = { "Mulaha", 6933720, "paa-kwa", "Latn", } m["mfx"] = { "Melo", 6813268, "omv-nom", } m["mfy"] = { "Mayo", 56729, "azc-trc", "Latn", sort_key = {remove_diacritics = c.acute}, } m["mfz"] = { "Mabaan", 20526385, "sdv", "Latn", } m["mga"] = { "Middle Irish", 36116, "cel-gae", "Latn", ancestors = "sga", strip_diacritics = {remove_diacritics = c.dotabove .. c.diaer .. "·"}, sort_key = "mga-sortkey", } m["mgb"] = { "Mararit", 56359, "sdv-tmn", } m["mgc"] = { "Morokodo", 6913216, "csu-bbk", "Latn", } m["mgd"] = { "Moru", 6915014, "csu-mma", "Latn, Arab", } m["mge"] = { "Mango", 713659, "csu-sar", "Latn", } m["mgf"] = { "Maklew", 6739816, "paa-bul", "Latn", } m["mgg"] = { "Mpongmpong", 35924, "bnt-bek", } m["mgh"] = { "Makhuwa-Meetto", 33604, "bnt-mak", "Latn", ancestors = "vmw", } m["mgi"] = { "Jili", 3914497, "nic-pls", } m["mgj"] = { "Abureni", 3441256, "nic-cde", "Latn", } m["mgk"] = { "Mawes", 6794395, "qfa-dis", -- Papuan; isolate in Glottolog, Foley (2018) and Hammarström (2010); in the Tor-Kwerba languages per -- Usher (2020) "Latn", } m["mgl"] = { "Maleu-Kilenge", 3281884, } m["mgm"] = { "Mambae", 35774, "poz-tim", "Latn", } m["mgn"] = { "Mbangi", 11017443, "nic-ngd", "Latn", } m["mgo"] = { "Meta'", 36054, "nic-mom", "Latn", } m["mgp"] = { "Eastern Magar", 12952758, "sit-gma", "Deva, Latn", } m["mgq"] = { "Malila", 6743679, "bnt-mby", "Latn", } m["mgr"] = { "Mambwe-Lungu", 626210, "bnt-mwi", "Latn", } m["mgs"] = { "Manda (Tanzania)", 16939267, "bnt-bki", } m["mgt"] = { "Mwakai", 11260674, "paa-wke", "Latn", } m["mgu"] = { "Mailu", 3278246, "paa-mal", "Latn", } m["mgv"] = { "Matengo", 6786446, "bnt-mbi", "Latn", } m["mgw"] = { "Matumbi", 6791974, "bnt-mbi", "Latn", } m["mgy"] = { "Mbunga", 6799817, "bnt-kil", } m["mgz"] = { "Mbugwe", 3426367, "bnt-mra", } m["mha"] = { "Manda (India)", 56760, "dra-kki", "Orya", translit = "kxv-translit", } m["mhb"] = { "Mahongwe", 35816, "bnt-kel", } m["mhc"] = { "Mocho", 1941682, "myn", } m["mhd"] = { "Mbugu", 36152, "qfa-mix", "Latn", ancestors = "asa", } m["mhe"] = { "Besisi", 2742262, "mkh-asl", "Latn", } m["mhf"] = { "Mamaa", 6745346, "ngf-era", "Latn", } m["mhg"] = { "Marrgu", 6772812, } m["mhi"] = { "Ma'di", 56670, "csu-mma", "Latn", strip_diacritics = {remove_diacritics = c.acute .. c.grave .. c.tilde .. c.dotbelow}, } m["mhj"] = { "Mogholi", 13336, "xgn", "fa-Arab, Latn", translit = "fa-cls-translit", strip_diacritics = { ["fa-Arab"] = "ar-stripdiacritics", }, } m["mhk"] = { "Mungaka", 36068, "nic-nun", } m["mhl"] = { "Mauwake", 6794095, "ngf-kum", "Latn", } m["mhm"] = { "Makhuwa-Moniga", 6900145, "bnt-mak", } m["mhn"] = { "Mòcheno", 268130, "gmw-hgm", "Latn", ancestors = "bar", sort_key = {remove_diacritics = c.grave}, } m["mho"] = { "Mashi", 10962737, "bnt-kav", "Latn", } m["mhp"] = { "Balinese Malay", 12473441, "crp", "Latn, Bali, ms-Arab", } m["mhq"] = { "Mandan", 1957120, "sio", "Latn", } m["mhr"] = { "Eastern Mari", 3906614, "chm", "Cyrl", translit = "chm-translit", override_translit = true, strip_diacritics = {remove_diacritics = c.grave .. c.acute}, sort_key = { from = {"ё", "ҥ", "ӧ", "ӱ"}, to = {"е" .. p[1], "н" .. p[1], "о" .. p[1], "у" .. p[1]} } } m["mhs"] = { "Buru (Indonesia)", 2928650, "poz-cma", "Latn", } m["mht"] = { "Mandahuaca", 6747924, "awd-nwk", } m["mhu"] = { "Taraon", 56400, "sit-gsi", "Latn", } m["mhw"] = { "Mbukushu", 2691548, "bnt", "Latn", } m["mhx"] = { "Lhao Vo", 11149315, "tbq-brm", "Latn", } m["mhy"] = { "Ma'anyan", 2328761, "poz-bre", "Latn", } m["mhz"] = { "Mor (Austronesian)", 2122792, "poz-hce", "Latn", } m["mia"] = { "Miami", 56523, "alg", "Latn", } m["mib"] = { "Atatláhuca Mixtec", 32093046, "omq-mxt", "Latn", } m["mic"] = { "Mi'kmaq", 13321, "alg-eas", "Latn", } m["mid"] = { "Mandaic", 6991742, "sem-ase", "Mand", ancestors = "myz", translit = { Mand = "Mand-translit", }, strip_diacritics = { Mand = "Mand-stripdiacritics", } } m["mie"] = { "Ocotepec Mixtec", 25559575, "omq-mxt", "Latn", } m["mif"] = { "Mofu-Gudur", 1365132, "cdc-cbm", "Latn", } m["mig"] = { "San Miguel el Grande Mixtec", 12953719, "omq-mxt", "Latn", } m["mih"] = { "Chayuco Mixtec", 13583510, "omq-mxt", "Latn", } m["mii"] = { "Chigmecatitlán Mixtec", 12953724, "omq-mxt", "Latn", } m["mij"] = { "Mungbam", 34725, "nic-beb", "Latn", } m["mik"] = { "Mikasuki", 13316, "nai-mus", "Latn", } m["mil"] = { "Peñoles Mixtec", 42411307, "omq-mxt", "Latn", } m["mim"] = { "Alacatlatzala Mixtec", 14697894, "omq-mxt", "Latn", } m["min"] = { "Minangkabau", 13324, "poz-mly", "Latn, Arab", } m["mio"] = { "Pinotepa Nacional Mixtec", 7196415, "omq-mxt", "Latn", } m["mip"] = { "Apasco-Apoala Mixtec", 13583505, "omq-mxt", "Latn", } m["miq"] = { "Miskito", 1516803, "nai-min", "Latn", strip_diacritics = {remove_diacritics = c.circ}, } m["mir"] = { "Isthmus Mixe", 6088873, "nai-miz", "Latn", } m["mit"] = { "Southern Puebla Mixtec", 7570345, "omq-mxt", "Latn", } m["miu"] = { "Cacaloxtepec Mixtec", 12953723, "omq-mxt", "Latn", } m["miw"] = { "Akoye", 3327462, "ngf-taa", "Latn", } m["mix"] = { "Mixtepec Mixtec", 6884125, "omq-mxt", "Latn", } m["miy"] = { "Ayutla Mixtec", 13583508, "omq-mxt", "Latn", } m["miz"] = { "Coatzospan Mixtec", 3317290, "omq-mxt", "Latn", } m["mjb"] = { "Makalero", 35729, "paa-alp", "Latn", } m["mjc"] = { "San Juan Colorado Mixtec", 12953718, "omq-mxt", "Latn", } m["mjd"] = { "Northwest Maidu", 3198700, "nai-mdu", "Latn", } m["mje"] = { "Muskum", 3913334, } -- mjg "Monguor" is not recognized as a language, but it is a family code m["mji"] = { "Kim Mun", 1115317, "hmx-mie", "Latn", } m["mjj"] = { "Mawak", 11732427, "ngf-tib", "Latn", } m["mjk"] = { "Matukar", 6791963, "poz-ocw", "Latn", } m["mjl"] = { "Mandeali", 6747931, "him", "Deva, Takr", translit = "hi-translit", } m["mjm"] = { "Medebur", 6805227, "poz-ocw", "Latn", } m["mjn"] = { "Mebu", 6804364, "ngf-yup", "Latn", } m["mjo"] = { "Malankuravan", 14916887, "dra-mal", } m["mjp"] = { "Malapandaram", 10575729, "dra-tam", } m["mjq"] = { "Malaryan", 12952773, "dra-mal", } m["mjr"] = { "Malavedan", 12952775, "dra-mal", "Mlym", -- Mlym translit in [[Module:scripts/data]] } m["mjs"] = { "Miship", 3441264, "cdc-wst", "Latn", } m["mjt"] = { "Sawriya Paharia", 33907, "dra-mlo", "Beng, Deva", } m["mju"] = { "Manna-Dora", 10576453, "dra-tel", } m["mjv"] = { "Mannan", 3286037, "dra-tam", "Mlym, Taml", translit = { Taml = "ta-translit", }, -- Mlym translit in [[Module:scripts/data]] } m["mjw"] = { "Karbi", 56591, "tbq-kuk", "Latn", } m["mjx"] = { "Mahali", 12953686, "mun", } m["mjy"] = { "Mahican", 3182562, "alg-eas", "Latn", } m["mjz"] = { "Majhi", 6737786, "inc-bih", } m["mka"] = { "Mbre", 3450154, "nic", --unclassified within niger-congo tho } m["mkb"] = { "Mal Paharia", 6583595, "inc-eas", "Deva", } m["mkc"] = { "Siliput", 7515090, "paa-mam", "Latn", } m["mke"] = { "Mawchi", 21403317, } m["mkf"] = { "Miya", 43328, "cdc-wst", "Latn", } m["mkg"] = { "Mak (China)", 3280623, "qfa-kms", } m["mki"] = { "Dhatki", 32480, "raj", "Deva, Mahj, Arab", } m["mkj"] = { "Mokilese", 2335528, "poz-mic", "Latn", } m["mkk"] = { "Byep", 35052, "bnt-mka", } m["mkl"] = { "Mokole", 36047, "alv-yor", "Latn", } m["mkm"] = { "Moklen", 3319380, } m["mkn"] = { "Kupang Malay", 18458203, "crp", "Latn", } m["mko"] = { "Mingang Doso", 3915382, "alv-bwj", } m["mkp"] = { "Moikodi", 6894594, "ngf-yar", "Latn", } m["mkq"] = { "Bay Miwok", 3460957, "nai-utn", "Latn", } m["mkr"] = { "Malas", 11732402, "ngf-nad", "Latn", } m["mks"] = { "Silacayoapan Mixtec", 7514027, "omq-mxt", "Latn", } m["mkt"] = { "Vamale", 14916907, "poz-cln", "Latn", } m["mku"] = { "Konyanka Maninka", 11163298, "dmn-mnk", } m["mkv"] = { "Mav̋ea", 3073532, "poz-vnn", "Latn", } m["mkx"] = { "Cinamiguin Manobo", 12953697, "mno", "Latn", } m["mky"] = { "Taba", 3512690, "poz-hce", "Latn", } m["mkz"] = { "Makasae", 35782, "paa-eti", "Latn", } m["mla"] = { "Tamambo", 1153276, "poz-vnn", "Latn", } m["mlb"] = { "Mbule", 35843, "nic-ymb", "Latn", } m["mlc"] = { "Caolan", 3446682, "tai-cho", "Latn, Hani", sort_key = {Hani = "Hani-sortkey"}, } m["mle"] = { "Manambu", 11732406, "paa-nnd", "Latn", } m["mlf"] = { "Mal", 3281057, "mkh-khm", } m["mlh"] = { "Mape", 6753787, "ngf-kma", "Latn", } m["mli"] = { "Malimpung", 12473435, } m["mlj"] = { "Miltu", 3441310, } m["mlk"] = { "Ilwana", 6001357, "bnt-sab", } m["mll"] = { "Malua Bay", 6744946, "poz-vnc", "Latn", } m["mlm"] = { "Mulam", 3092284, "qfa-kms", "Latn", } m["mln"] = { "Malango", 3281522, "poz-sls", "Latn", } m["mlo"] = { "Mlomp", 36009, "alv-bak", } m["mlp"] = { "Bargam", 4860543, "ngf-mad", "Latn", } m["mlq"] = { "Western Maninkakan", 11028033, "dmn-wmn", } m["mlr"] = { "Vame", 3515088, "cdc-cbm", "Latn", } m["mls"] = { "Masalit", 56557, "ssa", } m["mlu"] = { "To'abaita", 36645, "poz-sls", "Latn", } m["mlv"] = { "Mwotlap", 2475538, "poz-vnn", "Latn", } m["mlw"] = { "Moloko", 1965222, "cdc-cbm", "Latn", } m["mlx"] = { "Malfaxal", 2157421, "poz-vnc", "Latn", } m["mlz"] = { "Malaynon", 18755512, "phi", } m["mma"] = { "Mama", 3913963, "nic-jrn", } m["mmb"] = { "Momina", 6897297, } m["mmc"] = { "Michoacán Mazahua", 12953705, "oto", "Latn", } m["mmd"] = { "Maonan", 3092293, "qfa-kms", "Latn", } m["mme"] = { "Tirax", 3276286, "poz-vnc", "Latn", } m["mmf"] = { "Mundat", 56263, "cdc-wst", "Latn", } m["mmg"] = { "North Ambrym", 2842468, "poz-vnc", "Latn", } m["mmh"] = { "Mehináku", 3501838, "awd", "Latn", } m["mmi"] = { "Hember Avu", 6940113, "ngf-tib", "Latn", } m["mmj"] = { "Majhwar", 6737795, } m["mmk"] = { "Mukha-Dora", 6933447, } m["mml"] = { "Man Met", 3194984, "mkh-pal", } m["mmm"] = { "Maii", 6735599, "poz-vnc", "Latn", } m["mmn"] = { "Mamanwa", 3206623, "phi", "Latn", } m["mmo"] = { "Mangga Buang", 12952294, "poz-ocw", "Latn", } m["mmp"] = { "Musan", 2605703, "paa-amu", "Latn", } m["mmq"] = { "Aisi", 6940074, "ngf-ais", "Latn", } m["mmr"] = { "Western Xiangxi Miao", 3307901, "hmn", "Latn", } m["mmt"] = { "Malalamai", 3281496, "poz-ocw", "Latn", } m["mmu"] = { "Mmaala", 13123461, "nic-ymb", "Latn", } m["mmv"] = { "Miriti", 6873567, "sai-tuc", "Latn", } m["mmw"] = { "Emae", 3051961, "poz-pnp", "Latn", } m["mmx"] = { "Madak", 3275205, "poz-ocw", "Latn", } m["mmy"] = { "Migaama", 56259, "cdc-est", "Latn", } m["mmz"] = { "Mabaale", 11003249, "bnt-ngn", } m["mna"] = { "Mbula", 3303572, "poz-ocw", "Latn", } m["mnb"] = { "Muna", 6935584, "poz-mun", "Latn", } m["mnc"] = { "Manchu", 33638, "tuw-jrc", "mnc-Mong, Latn", ancestors = "juc", -- mnc-Mong translit in [[Module:scripts/data]] } m["mnd"] = { "Mondé", 6898840, "tup", "Latn", } m["mne"] = { "Naba", 760732, "csu-bgr", } m["mnf"] = { "Mundani", 35839, "nic-mom", "Latn", } m["mng"] = { "Eastern Mnong", 12953747, "mkh-ban", "Latn, Khmr", } m["mnh"] = { "Mono (Congo)", 33501, "bad-cnt", "Latn", } m["mni"] = { "Manipuri", 33868, "sit", "Mtei, Beng", ancestors = "omp", translit = {Mtei = "Mtei-translit"}, } m["mnj"] = { "Munji", 33639, "ira-mny", "Arab", } m["mnk"] = { "Mandinka", 33678, "dmn-wmn", "Latn, Arab, Nkoo", } m["mnl"] = { "Tiale", 6744350, "poz-vnn", "Latn", } m["mnm"] = { "Mapena", 11732415, "ngf-dag", "Latn", } m["mnn"] = { "Southern Mnong", 23857582, "mkh-ban", } m["mnp"] = { "Northern Min", 36457, "zhx-inm", "Hants", generate_forms = "zh-generateforms", translit = "zh-translit", sort_key = "Hani-sortkey", } m["mnq"] = { "Minriq", 2742268, "mkh-asl", "Latn", } m["mnr"] = { "Mono (California)", 33591, "azc-num", "Latn", } m["mnt"] = { "Maykulan", 3915696, "aus-pam", "Latn", } m["mnu"] = { "Mer", 6817854, "paa-mai", "Latn", } m["mnv"] = { "Rennellese", 3397346, "poz-pnp", "Latn", } m["mnw"] = { "Mon", 13349, "mkh-mnc", "Mymr", ancestors = "mkh-mmn", sort_key = { from = {"ျ", "ြ", "ွ", "ှ", "ၞ", "ၟ", "ၠ", "ၚ", "ဿ"}, to = {"္ယ", "္ရ", "္ဝ", "္ဟ", "္န", "္မ", "္လ", "င", "သ္သ"} }, } m["mnx"] = { "Sougb", 3507964, "paa-ebh", "Latn", } m["mny"] = { "Manyawa", 11002622, "bnt-mak", ancestors = "vmw", } m["mnz"] = { "Moni", 6899857, "ngf-pan", "Latn", } m["moa"] = { "Mwan", 3320111, "dmn-nbe", "Latn", } m["moc"] = { "Mocoví", 3027906, "sai-guc", "Latn", } m["mod"] = { "Mobilian", 13333, "crp", "Latn", ancestors = "cho, cic", } m["moe"] = { "Montagnais", 13351, "alg", "Latn", ancestors = "cr", strip_diacritics = {remove_diacritics = c.macron}, } m["mog"] = { "Mongondow", 3058458, "phi", "Latn", } m["moh"] = { "Mohawk", 13339, "iro-nor", "Latn", ancestors = "iro-omo", } m["moi"] = { "Mboi", 3914417, "alv-yun", } m["moj"] = { "Monzombo", 11154772, "nic-nkk", "Latn", } m["mok"] = { "Morori", 6913275, } m["mom"] = { "Monimbo", 56542, } m["moo"] = { "Monom", 6901726, "mkh-ban", } m["mop"] = { "Mopan Maya", 36183, "myn", "Latn", } m["moq"] = { "Mor (Papuan)", 11732468, "qfa-dis", -- Papuan; isolate in Glottolog and Palmer (2018); top-level TNG in Ross (2005), in Berau Gulf (under -- TNG) in Usher (2020) } m["mor"] = { "Moro", 36172, "alv-hei", "Latn", } m["mos"] = { "Moore", 36096, "nic-mre", "Latn", } m["mot"] = { "Barí", 2886281, "cba", "Latn", } m["mou"] = { "Mogum", 3440473, "cdc-est", "Latn", } m["mov"] = { "Mojave", 56510, "nai-yuc", "Latn", } m["mow"] = { "Moi (Congo)", 11124792, "bnt-bmo", "Latn", } m["mox"] = { "Molima", 3319495, "poz-ocw", "Latn", } m["moy"] = { "Shekkacho", 56827, "omv-gon", } m["moz"] = { "Mukulu", 3440403, "cdc-est", } m["mpa"] = { "Mpoto", 6928303, "bnt-mbi", "Latn", } m["mpb"] = { "Mullukmulluk", 6741120, } m["mpc"] = { "Mangarayi", 6748829, } m["mpd"] = { "Machinere", 12953681, "awd", "Latn", } m["mpe"] = { "Majang", 56724, "sdv", } m["mpg"] = { "Marba", 56614, "cdc-mas", } m["mph"] = { "Maung", 6792550, "aus-wdj", "Latn", } m["mpi"] = { "Mpade", 3280670, "cdc-cbm", "Latn", } m["mpj"] = { "Martu Wangka", 3295916, "aus-pam", "Latn", } m["mpk"] = { "Mbara (Chad)", 3912770, "cdc-cbm", } m["mpl"] = { "Middle Watut", 15887910, "poz-ocw", "Latn", } m["mpm"] = { "Yosondúa Mixtec", 12953741, "omq-mxt", "Latn", } m["mpn"] = { "Mindiri", 6863842, "poz-ocw", "Latn", } m["mpo"] = { "Miu", 6883668, "poz-ocw", "Latn", } m["mpp"] = { "Migabac", 11732448, "ngf-sop", "Latn", } m["mpq"] = { "Matís", 3299145, "sai-pan", "Latn", } m["mpr"] = { "Vangunu", 3554582, "poz-ocw", "Latn", } m["mps"] = { "Dadibi", 5208077, "paa-teb", "Latn", } m["mpt"] = { "Mian", 12952846, "ngf-msu", "Latn", } m["mpu"] = { "Makuráp", 3281037, "tup", "Latn", } m["mpv"] = { "Mungkip", 11732485, "ngf-boa", "Latn", } m["mpw"] = { "Mapidian", 6753812, "awd", "Latn", } m["mpx"] = { "Misima-Paneati", 6875666, "poz-ocw", "Latn", } m["mpy"] = { "Mapia", 3287224, "poz-mic", "Latn", } m["mpz"] = { "Mpi", 6928276, "tbq-bka", } m["mqa"] = { "Maba", 3273750, } m["mqb"] = { "Mbuko", 3502213, "cdc-cbm", "Latn", } m["mqc"] = { "Mangole", 6749097, "poz-cma", "Latn", } m["mqe"] = { "Matepi", 11732426, "ngf-han", "Latn", } m["mqf"] = { "Momuna", 6897518, } m["mqg"] = { "Kota Bangun Kutai Malay", 12952778, } m["mqh"] = { "Tlazoyaltepec Mixtec", 12953740, "omq-mxt", "Latn", } m["mqi"] = { "Mariri", 6765544, } m["mqj"] = { "Mamasa", 6745452, "poz-ssw", "Latn", } m["mqk"] = { "Rajah Kabunsuwan Manobo", 12953700, "mno", } m["mql"] = { "Mbelime", 4286473, "nic-eov", "Latn", } m["mqm"] = { "South Marquesan", 19694214, "poz-pep", "Latn", } m["mqn"] = { "Moronene", 642581, "poz-btk", "Latn", } m["mqo"] = { "Modole", 11732457, "paa-gto", "Latn", } m["mqp"] = { "Manipa", 6749799, "poz-cma", "Latn", } m["mqq"] = { "Minokok", 18642293, "poz-san", "Latn", } m["mqr"] = { "Mander", 6747979, "paa-tor", "Latn", } m["mqs"] = { "West Makian", 3033575, "paa-nha", "Latn", } m["mqt"] = { "Mok", 13018559, "mkh-pal", } m["mqu"] = { "Mandari", 3285426, "sdv-bri", } m["mqv"] = { "Mosimo", 11732478, "ngf-nwh", "Latn", } m["mqw"] = { "Murupi", 11732486, "ngf-nwh", "Latn", } m["mqx"] = { "Mamuju", 6746004, "poz-ssw", "Latn", } m["mqy"] = { "Manggarai", 3285748, "poz-cet", "Latn", } m["mqz"] = { "Malasanga", 14916889, "poz-ocw", "Latn", } m["mra"] = { "Mlabri", 3073465, "mkh", } m["mrb"] = { "Sungwadia", 3293299, "poz-vnn", "Latn", } m["mrc"] = { "Maricopa", 56386, "nai-yuc", "Latn", } m["mrd"] = { "Western Magar", 22303263, "sit-gma", "Deva", } m["mre"] = { "Martha's Vineyard Sign Language", 33494, "sgn", "Latn, Sgnw", } m["mrf"] = { "Elseng", 3915667, "qfa-unc", -- "Border or language isolate"; unclassifiable due to paucity of data "Latn", } m["mrg"] = { "Mising", 3316328, "sit-tan", "Latn, Beng, Deva", ancestors = "adi", } m["mrh"] = { "Mara Chin", 4175893, "tbq-kuk", "Latn", } m["mrj"] = { "Western Mari", 1776032, "chm", "Cyrl", translit = "chm-translit", sort_key = "mrj-sortkey", } m["mrk"] = { "Hmwaveke", 5873712, "poz-cln", "Latn", } m["mrl"] = { "Mortlockese", 3324598, "poz-mic", "Latn", } m["mrm"] = { "Mwerlap", 3331115, "poz-vnn", "Latn", } m["mrn"] = { "Cheke Holo", 2962165, "poz-ocw", "Latn", } m["mro"] = { "Mru", 1951521, "sit-mru", "Latn, Mroo", } m["mrp"] = { "Morouas", 6913299, "poz-vnn", "Latn", } m["mrq"] = { "North Marquesan", 2603808, "poz-pep", "Latn", } m["mrr"] = { "Hill Maria", 27602, "dra-mdy", "Deva", } m["mrs"] = { "Maragus", 6754640, "poz-vnc", "Latn", } m["mrt"] = { "Margi", 56241, "cdc-cbm", "Latn", } m["mru"] = { "Mono (Cameroon)", 11031964, "alv-mbm", "Latn", } m["mrv"] = { "Mangarevan", 36237, "poz-pep", "Latn", } m["mrw"] = { "Maranao", 33800, "phi", "Latn, Arab", } m["mrx"] = { "Dineor", 5278044, "paa-tor", "Latn", } m["mry"] = { "Karaga Mandaya", 6747925, "phi", } m["mrz"] = { "Marind", 6763970, "paa-mri", "Latn", } m["msb"] = { "Masbatenyo", 33948, "phi", "Latn", } m["msc"] = { "Sankaran Maninka", 11155812, "dmn-mnk", } m["msd"] = { "Yucatec Maya Sign Language", 34281, "sgn", "Latn", -- when documented } m["mse"] = { "Musey", 56328, "cdc-mas", } m["msf"] = { "Mekwei", 4544752, "paa-nim", "Latn", } m["msg"] = { "Moraid", 6909020, "paa-wbh", "Latn", } m["msi"] = { "Sabah Malay", 10867404, "crp", "Latn, Arab", } m["msj"] = { "Ma", 6720909, "nic-mbc", "Latn", } m["msk"] = { "Mansaka", 12952800, "phi", "Latn", } m["msl"] = { "Molof", 4300950, } m["msm"] = { "Agusan Manobo", 12953696, "mno", "Latn", } m["msn"] = { "Vurës", 3563857, "poz-vnn", "Latn", } m["mso"] = { "Mombum", 6897079, "ngf-mom", "Latn", } m["msp"] = { "Maritsauá", 6765915, "tup", "Latn", } m["msq"] = { "Caac", 2932212, "poz-cln", "Latn", } m["msr"] = { "Mongolian Sign Language", 3915499, "sgn", } m["mss"] = { "West Masela", 12952816, "poz-tim", } m["msu"] = { "Musom", 6943041, "poz-ocw", "Latn", } m["msv"] = { "Maslam", 3502273, } m["msw"] = { "Mansoanka", 35814, } m["msx"] = { "Moresada", 11732475, "ngf-pom", "Latn", } m["msy"] = { "Aruamu", 3501809, "paa-rub", "Latn", } m["msz"] = { "Momare", 6897030, "ngf-sop", "Latn", } m["mta"] = { "Cotabato Manobo", 12953698, "mno", "Latn", } m["mtb"] = { "Anyin Morofo", 3502338, "alv-ctn", "Latn", ancestors = "any", } m["mtc"] = { "Munit", 11732482, "ngf-kok", "Latn", } m["mtd"] = { "Mualang", 3073458, "poz-mly", "Latn", } m["mte"] = { "Alu", 33503, "poz-ocw", "Latn", } m["mtf"] = { "Murik (New Guinea)", 7050035, "paa-lse", "Latn", } m["mtg"] = { "Una", 5580728, "ngf-mek", "Latn", } m["mth"] = { "Munggui", 6936018, "poz-hce", "Latn", } m["mti"] = { "Maiwa (New Guinea)", 6737223, "ngf-dag", "Latn", } m["mtj"] = { "Moskona", 11288953, "paa-ebh", "Latn", } m["mtk"] = { "Mbe'", 10964025, "nic-nka", "Latn", } m["mtl"] = { "Montol", 3440457, "cdc-wst", "Latn", } m["mtm"] = { "Mator", 20669419, "syd", "Cyrl", } m["mtn"] = { "Matagalpa", 3490756, "nai-min", } m["mto"] = { "Totontepec Mixe", 7828400, "nai-miz", "Latn", } m["mtp"] = { "Wichí Lhamtés Nocten", 5908756, "sai-wic", "Latn", } m["mtq"] = { "Muong", 3236789, "mkh-vie", "Latn", sort_key = "vi-sortkey", } m["mtr"] = { "Mewari", 2992857, "raj", "Deva", translit = "hi-translit", -- for now } m["mts"] = { "Yora", 3572572, "sai-pan", "Latn", } m["mtt"] = { "Mota", 3325052, "poz-vnn", "Latn", } m["mtu"] = { "Tututepec Mixtec", 7857069, "omq-mxt", "Latn", } m["mtv"] = { "Asaro'o", 3503684, "ngf-war", -- ngf-moa if we split out Molet from Asaro'o "Latn", } m["mtw"] = { "Magahat", 6729600, "phi", } m["mtx"] = { "Tidaá Mixtec", 7800805, "omq-mxt", "Latn", } m["mty"] = { "Nabi", 6956858, "paa-wpa", "Latn", } m["mua"] = { "Mundang", 36032, "alv-mbm", } m["mub"] = { "Mubi", 3440518, "cdc-est", "Latn", } m["muc"] = { "Mbu'", 35868, "nic-beb", "Latn", } m["mud"] = { "Mednyj Aleut", 1977419, "qfa-mix", ancestors = "ale, ru" } m["mue"] = { "Media Lengua", 36066, "qfa-mix", "Latn", ancestors = "es, qu", } m["mug"] = { "Musgu", 3123545, "cdc-cbm", "Latn", } m["muh"] = { "Mündü", 35981, "nic-nke", "Latn", } m["mui"] = { "Musi", 615660, "poz-mly", "Latn", } m["muj"] = { "Mabire", 3440437, } m["mul"] = { "Translingual", 7834564, "qfa-not", "All", -- NOTE: The following sort keys are used in process_page() in [[Module:headword/page]], which generates -- the default sort key for the page (corresponding to {{DEFAULTSORT:...}}) by generating a sort key for -- the pagename using `makeSortKey()` called on language object "mul". Currently this just handles -- Japanese sort keys. -- -- FIXME: This should be smarter and use the language of the page if there's only one. sort_key = { Hani = "Hani-sortkey", Jpan = "Jpan-sortkey", Hrkt = "Hira-sortkey", -- Sort all kana as Hira. Hira = "Hira-sortkey", Kana = "Hira-sortkey", }, standard_chars = "AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz" .. c.punc, } m["mum"] = { "Maiwala", 12952764, "poz-ocw", "Latn", } m["muo"] = { "Nyong", 36373, "alv-lek", } m["mup"] = { "Malvi", 33413, "raj", "Deva", translit = "hi-translit" } m["muq"] = { "Eastern Xiangxi Miao", 27431376, "hmn", } m["mur"] = { "Murle", 56727, "sdv", } m["mus"] = { "Creek", 523014, "nai-mus", "Latn", } m["mut"] = { "Western Muria", 12952886, "dra-mur", } m["muu"] = { "Yaaku", 34222, "cus-eas", } m["muv"] = { "Muthuvan", 3327420, "dra-tam", } m["mux"] = { "Bo-Ung", 15831607, "ngf-hag", "Latn", } m["muy"] = { "Muyang", 3502301, "cdc-cbm", "Latn", } m["muz"] = { "Mursi", 36013, "sdv", } m["mva"] = { "Manam", 6746851, "poz-ocw", "Latn", } m["mvb"] = { "Mattole", 20824, "ath-pco", "Latn", } m["mvd"] = { "Mamboru", 578815, "poz", "Latn", } m["mvg"] = { "Yucuañe Mixtec", 25562736, "omq-mxt", "Latn", } m["mvh"] = { "Mire", 3441359, } m["mvi"] = { "Miyako", 36218, "jpx-sry", "Jpan", translit = s["jpx-translit"], display_text = s["jpx-displaytext"], strip_diacritics = s["jpx-stripdiacritics"], sort_key = s["jpx-sortkey"], } m["mvk"] = { "Mekmek", 6810592, "paa-yua", "Latn", } m["mvl"] = { "Mbara (Australia)", 6799620, "aus-pam", "Latn", } m["mvm"] = { "Muya", 2422759, "sit-qia", } m["mvn"] = { "Minaveha", 6863278, "poz-ocw", "Latn", } m["mvo"] = { "Marovo", 3294683, "poz-ocw", "Latn", } m["mvp"] = { "Duri", 3915414, "poz-ssw", "Latn", } m["mvq"] = { "Moere", 11732458, "ngf-kum", "Latn", } m["mvr"] = { "Marau", 6755069, "poz-hce", "Latn", } m["mvs"] = { "Massep", 3502895, "qfa-dis", -- poorly documented (but in vigorous use); isolate per Ethnologue, Glottolog, and Foley (2018); Greater -- Kwerba per Usher "Latn", } m["mvt"] = { "Mpotovoro", 6928305, "poz-vnc", "Latn", } m["mvu"] = { "Marfa", 713633, } m["mvv"] = { "Tagal Murut", 7675300, "poz-san", "Latn", } m["mvw"] = { "Machinga", 12952754, "bnt-rvm", } m["mvx"] = { "Meoswar", 6817777, "poz-hce", "Latn", } m["mvy"] = { "Indus Kohistani", 33399, "inc-koh", "Arab", } m["mvz"] = { "Mesqan", 6821677, "sem-eth", } m["mwa"] = { "Mwatebu", 14916896, "poz-ocw", "Latn", } m["mwb"] = { "Juwal", 6319103, "paa-mmu", "Latn", } m["mwc"] = { "Are", 29277, "poz-ocw", "Latn", } m["mwe"] = { "Mwera", 6944725, "bnt-rvm", "Latn", } m["mwf"] = { "Murrinh-Patha", 2980398, "aus-dal", "Latn", } m["mwg"] = { "Aiklep", 3399652, "poz-ocw", "Latn", } m["mwh"] = { "Mouk-Aria", 3325498, "poz-ocw", "Latn", } m["mwi"] = { "Labo", 2157452, "poz-vnc", "Latn", } m["mwk"] = { "Kita Maninkakan", 3015523, "dmn-wmn", } m["mwl"] = { "Mirandese", 13330, "roa-asl", "Latn", } m["mwm"] = { "Sar", 56850, "csu-sar", "Latn", } m["mwn"] = { "Nyamwanga", 6944666, "bnt-mwi", "Latn", } m["mwo"] = { "Sungwadaga", 3276435, "poz-vnn", "Latn", } m["mwp"] = { "Kala Lagaw Ya", 2591262, "aus-pam", "Latn", } m["mwq"] = { "Mün Chin", 331340, "tbq-kuk", } m["mwr"] = { "Marwari", 56312, "raj", "Deva, Mahj", translit = { Deva = "hi-translit", -- for now Mahj = "Mahj-translit", }, } m["mws"] = { "Mwimbi-Muthambi", 15632357, "bnt-kka", "Latn", } m["mwt"] = { "Moken", 18648701, "poz", } m["mwu"] = { "Mittu", 6883573, "csu-bbk", "Latn", } m["mwv"] = { "Mentawai", 13365, "poz-nws", "Latn", } m["mww"] = { "White Hmong", 3138829, "hmn", "Latn, Hmng, Hmnp", } m["mwz"] = { "Moingi", 11011905, } m["mxa"] = { "Northwest Oaxaca Mixtec", 12953739, "omq-mxt", "Latn", } m["mxb"] = { "Tezoatlán Mixtec", 3317286, "omq-mxt", "Latn", } m["mxd"] = { "Modang", 6888037, "poz", "Latn", } m["mxe"] = { "Mele-Fila", 3305008, "poz-pnp", "Latn", } m["mxf"] = { "Malgbe", 3502224, } m["mxg"] = { "Mbangala", 6799612, "bnt-yak", } m["mxh"] = { "Mvuba", 6944591, "csu-mle", "Latn", } m["mxi"] = { "Mozarabic", 317044, "roa-ibe", "Arab, Hebr, Latn", translit = "mxi-translit", strip_diacritics = { Arab = "ar-stripdiacritics", }, -- Hebr display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["mxj"] = { "Miju", 56332, "sit-mdz", "Latn, Deva", } m["mxk"] = { "Monumbo", 6906792, "paa-mon", "Latn", } m["mxl"] = { "Maxi Gbe", 35770, "alv-gbe", } m["mxm"] = { "Meramera", 6817936, "poz-ocw", "Latn", } m["mxn"] = { "Moi (Indonesia)", 11732459, "paa-wbh", "Latn", } m["mxo"] = { "Mbowe", 10962309, "bnt-kav", } m["mxp"] = { "Tlahuitoltepec Mixe", 7810697, } m["mxq"] = { "Juquila Mixe", 25559721, } m["mxr"] = { "Murik (Malaysia)", 3328150, nil, "Latn", } m["mxs"] = { "Huitepec Mixtec", 12953729, "omq-mxt", "Latn", } m["mxt"] = { "Jamiltepec Mixtec", 12953730, "omq-mxt", "Latn", } m["mxu"] = { "Mada (Cameroon)", 3441206, "cdc-cbm", "Latn", } m["mxv"] = { "Metlatónoc Mixtec", 36363, "omq-mxt", "Latn", } m["mxw"] = { "Namo", 12952923, "paa-nam", "Latn", } m["mxx"] = { "Mahou", 11004334, "dmn-mnk", "Latn, Nkoo", } m["mxy"] = { "Southeastern Nochixtlán Mixtec", 7070684, "omq-mxt", "Latn", } m["mxz"] = { "Central Masela", 42575433, "poz-tim", "Latn", } m["myb"] = { "Mbay", 3033565, "csu-sar", "Latn", } m["myc"] = { "Mayeka", 11129517, "bnt-boa", } m["mye"] = { "Myene", 35832, "bnt-tso", "Latn", } m["myf"] = { "Bambassi", 56540, "omv-mao", "Latn", } m["myg"] = { "Manta", 35799, "nic-mom", "Latn", } m["myh"] = { "Makah", 3280640, "wak", "Latn", } m["myj"] = { "Mangayat", 35988, "nic-ser", } m["myk"] = { "Mamara", 36187, "alv-sma", "Latn", } m["myl"] = { "Moma", 6897018, "poz", "Latn", } m["mym"] = { "Me'en", 3408516, "sdv", } m["myo"] = { "Anfillo", 34928, "omv-gon", } m["myp"] = { "Pirahã", 33825, "sai-mur", "Latn", } m["myr"] = { "Muniche", 3915654, } m["mys"] = { "Mesmes", 3508617, "sem-eth", } m["myu"] = { "Mundurukú", 746723, "tup", "Latn", } m["myv"] = { "Erzya", 29952, "urj-mdv", "Cyrl", translit = "myv-translit", override_translit = true, } m["myw"] = { "Muyuw", 3502878, "poz-ocw", "Latn", } m["myx"] = { "Masaba", 12952814, "bnt-msl", "Latn", } m["myy"] = { "Macuna", 3275059, "sai-tuc", "Latn", } m["myz"] = { "Classical Mandaic", 25559314, "sem-ase", "Mand", translit = { Mand = "Mand-translit", }, strip_diacritics = { Mand = "Mand-stripdiacritics", } } m["mza"] = { "Santa María Zacatepec Mixtec", 8063756, "omq-mxt", "Latn", } m["mzb"] = { "Northern Saharan Berber", 11156769, "ber", "Arab, Latn, Tfng", } m["mzc"] = { "Madagascar Sign Language", 12715020, "sgn", } m["mzd"] = { "Malimba", 35806, "bnt-saw", } m["mze"] = { "Morawa", 6909384, "paa-mal", "Latn", } m["mzg"] = { "Monastic Sign Language", 3217333, "sgn", } m["mzh"] = { "Wichí Lhamtés Güisnay", 7998197, "sai-wic", "Latn", } m["mzi"] = { "Ixcatlán Mazatec", 6101049, "omq-maz", "Latn", } m["mzj"] = { "Manya", 11006832, "dmn-mnk", } m["mzk"] = { "Nigeria Mambila", 11004163, "nic-mmb", "Latn", } m["mzl"] = { "Mazatlán Mixe", 25559728, } m["mzm"] = { "Mumuye", 36021, "alv-mum", "Latn", } m["mzn"] = { "Mazanderani", 13356, "ira-msh", "mzn-Arab", } m["mzo"] = { "Matipuhy", 6787588, "sai-kui", "Latn", } m["mzp"] = { "Movima", 1659701, "qfa-iso", "Latn", } m["mzq"] = { "Mori Atas", 3324070, "poz-btk", "Latn", } m["mzr"] = { "Marúbo", 3296011, "sai-pan", "Latn", } m["mzs"] = { "Macanese", 35785, "crp", "Latn", ancestors = "pt", sort_key = {Latn = {remove_diacritics = c.grave .. c.acute .. c.circ .. c.tilde .. c.diaer .. c.cedilla}}, } m["mzt"] = { "Mintil", 6869641, "mkh-asl", } m["mzu"] = { "Inapang", 6013569, "paa-tam", "Latn", } m["mzv"] = { "Manza", 36038, "gba-eas", } m["mzw"] = { "Deg", 35183, "nic-gnw", "Latn", } m["mzx"] = { "Mawayana", 6794377, "awd", } m["mzy"] = { "Mozambican Sign Language", 6927809, "sgn", } m["mzz"] = { "Maiadomu", 6735234, "poz-ocw", "Latn", } return require("Module:languages").finalizeData(m, "language") pz15eb7017x1b323qrdyp4glpwckqz2 828 6011 17451 2026-07-13T08:52:37Z Hiyuune 6766 + 17451 Scribunto text/plain local subexport = {} local require_when_needed = require("Module:require when needed") local cp = require_when_needed("Module:string utilities", "codepoint") local floor = math.floor local get_plaintext = require_when_needed("Module:utilities", "get_plaintext") local get_script = require_when_needed("Module:scripts", "getByCode") local insert = table.insert local ipairs = ipairs local min = math.min local pairs = pairs local setmetatable = setmetatable local sort = table.sort local split = require_when_needed("Module:string utilities", "split") local table_len = require_when_needed("Module:table", "length") local type = type -- Copied from [[Module:Unicode data]]. local function binaryRangeSearch(codepoint, ranges) local low, mid, high low, high = 1, ranges.length or table_len(ranges) while low <= high do mid = floor((low + high) / 2) local range = ranges[mid] if codepoint < range[1] then high = mid - 1 elseif codepoint <= range[2] then return range, mid else low = mid + 1 end end return nil, mid end -- Copied from [[Module:Unicode data]]. local function linearRangeSearch(codepoint, ranges) for i, range in ipairs(ranges) do if codepoint < range[1] then break elseif codepoint <= range[2] then return range end end end local function compareRanges(range1, range2) return range1[1] < range2[1] end -- Save previously used codepoint ranges in case another character is in the -- same range. local rangesCache = {} --[=[ Takes a codepoint or a character and finds the script code(s) (if any) that are appropriate for it based on the codepoint, using the data module [[Module:scripts/recognition data]]. The data module was generated from the patterns in [[Module:scripts/data]] using [[Module:User:Erutuon/script recognition]]. By default, it returns only the first script code if there are multiple matches (i.e. the code we take to be the default). If `all_scripts` is set, then a table of all matching codes is returned. ]=] local charToScriptData function subexport.charToScript(char, all_scripts) charToScriptData = charToScriptData or mw.loadData("Module:scripts/recognition data") local t = type(char) local codepoint if t == "string" then local etc codepoint, etc = cp(char, 1, 2) if etc then error("bad argument #1 to 'charToScript' (expected a single character)") end elseif t == "number" then codepoint = char else error(("bad argument #1 to 'charToScript' (expected string or a number, got %s)") :format(t)) end local ret = {} local individualMatch = charToScriptData.individual[codepoint] if individualMatch then ret = split(individualMatch, "%s*,%s*", true) else local range if rangesCache[1] then range = linearRangeSearch(codepoint, rangesCache) if range then for i, script in ipairs(range) do if i > 2 then insert(ret, script) if not all_scripts then break end end end end end if not ret[1] then local index = floor(codepoint / 0x1000) range = linearRangeSearch(index, charToScriptData.blocks) if not range and charToScriptData[index] then range = binaryRangeSearch(codepoint, charToScriptData[index]) if range then insert(rangesCache, range) sort(rangesCache, compareRanges) end end if range then for i, script in ipairs(range) do if i > 2 then insert(ret, script) if not all_scripts then break end end end end end end if not ret[1] then insert(ret, "None") end if all_scripts then return ret else return ret[1] end end --[=[ Finds the best script for a string in a language-agnostic way. Converts each character to a codepoint. Iterates the counter for the script code if the codepoint is in the list of individual characters, or if it is in one of the defined ranges in the 4096-character block that it belongs to. Each script has a two-part counter, for primary and secondary matches. Primary matches are when the script is the first one listed; otherwise, it's a secondary match. When comparing scripts, first the total of both are compared (i.e. the overall number of matches). If these are the same, the number of primary and then secondary matches are used as tiebreakers. For example, this is used to ensure that `Grek` takes priority over `Polyt` if no characters which exclusively match `Polyt` are found, as `Grek` is a subset of `Polyt`. If `none_is_last_resort_only` is specified, this will never return None if any characters in `text` belong to a script. Otherwise, it will return None if there are more characters that don't belong to a script than belong to any individual script. (FIXME: This behavior is probably wrong, and `none_is_last_resort_only` should probably become the default.) ]=] function subexport.findBestScriptWithoutLang(text, none_is_last_resort_only) -- `scripts` contains counters for any scripts detected so far. Jpan and Kore are handled as special-cases, as they are combinations of other scripts. local scripts_mt = {Jpan = true, Kore = true} local weights_mt = { __lt = function(a, b) if a[1] + a[2] ~= b[1] + b[2] then return a[1] + a[2] < b[1] + b[2] elseif a[1] ~= b[1] then return a[1] < b[1] elseif a[2] ~= b[2] then return a[2] < b[2] else return false end end } scripts_mt.__index = function(t, k) local ret = {} if k == "Jpan" and scripts_mt.Jpan then for i = 1, 2 do ret[i] = t["Hani"][i] + t["Hira"][i] + t["Kana"][i] end elseif k == "Kore" and scripts_mt.Kore then for i = 1, 2 do ret[i] = t["Hani"][i] + t["Hang"][i] end else for i = 1, 2 do insert(ret, 0) end end return setmetatable(ret, weights_mt) end local scripts = setmetatable({}, scripts_mt) text = get_plaintext(text) local combined_scripts = { Jpan = {["Hani"] = true, ["Hira"] = true, ["Kana"] = true}, Kore = {["Hani"] = true, ["Hang"] = true} } for character in text:gmatch(".[\128-\191]*") do for i, script in ipairs(subexport.charToScript(character, true)) do if not none_is_last_resort_only or script ~= "None" then scripts[script] = scripts[script] local weight = min(i, 2) scripts[script][weight] = scripts[script][weight] + 1 end end end -- Check the combined script counts. If a single constituent has the same count (i.e. it's the only one), discard the combined script. for combined_script, set in pairs(combined_scripts) do for script in pairs(set) do scripts[combined_script] = scripts[combined_script] if (scripts[script][1] + scripts[script][2]) == (scripts[combined_script][1] + scripts[combined_script][2]) then scripts[combined_script] = nil break end end end local bestScript local greatestCount for script, count in pairs(scripts) do if (not greatestCount) or greatestCount < count then bestScript = script greatestCount = count end end bestScript = bestScript or "None" return get_script(bestScript) end return subexport cs19bg8d41yuv7ovit6o3v0kd4ou9kq 828 6012 17452 2026-07-13T08:52:58Z Hiyuune 6766 + 17452 Scribunto text/plain local data = { [0x00] = { { 0x00041, 0x0005A, "Latn"}, { 0x00061, 0x0007A, "Latn"}, { 0x000C0, 0x000D6, "Latn"}, { 0x000D8, 0x000F6, "Latn"}, { 0x000F8, 0x0024F, "Latn"}, { 0x00370, 0x003E1, "Grek", "Polyt" }, { 0x003E2, 0x003EF, "Copt" }, { 0x003F0, 0x003FF, "Grek", "Polyt" }, { 0x00400, 0x0045F, "Cyrl" }, { 0x00460, 0x00469, "Cyrs" }, { 0x0046A, 0x0046D, "Cyrl" }, { 0x0046E, 0x00471, "Cyrs" }, { 0x00472, 0x00475, "Cyrl" }, { 0x00476, 0x00489, "Cyrs" }, { 0x0048A, 0x00527, "Cyrl" }, { 0x00531, 0x0058F, "Armn" }, { 0x00590, 0x005FF, "Hebr" }, { 0x00600, 0x006FF, "Arab" }, { 0x00700, 0x0074F, "Syrc" }, { 0x00750, 0x0077F, "Arab" }, { 0x00780, 0x007B1, "Thaa" }, { 0x007C0, 0x007FF, "Nkoo" }, { 0x00800, 0x0083E, "Samr" }, { 0x00840, 0x0085E, "Mand" }, { 0x00860, 0x0086A, "Syrc" }, { 0x008A0, 0x008FF, "Arab" }, { 0x00900, 0x0097F, "Deva" }, { 0x00980, 0x00983, "Beng" }, { 0x00985, 0x0098C, "Beng" }, { 0x00993, 0x009A8, "Beng" }, { 0x009AA, 0x009B0, "Beng" }, { 0x009B6, 0x009B9, "Beng" }, { 0x009BC, 0x009C4, "Beng" }, { 0x009CB, 0x009CE, "Beng" }, { 0x009E0, 0x009E3, "Beng" }, { 0x009E6, 0x009EF, "Beng" }, { 0x009F0, 0x009F1, "as-Beng" }, { 0x00A01, 0x00A76, "Guru" }, { 0x00A81, 0x00AF1, "Gujr" }, { 0x00B01, 0x00B77, "Orya" }, { 0x00B82, 0x00BFA, "Taml" }, { 0x00C00, 0x00C7F, "Telu" }, { 0x00C80, 0x00CF2, "Knda" }, { 0x00D02, 0x00D7F, "Mlym" }, { 0x00D82, 0x00DF4, "Sinh" }, { 0x00E01, 0x00E5B, "Thai" }, { 0x00E81, 0x00EDF, "Laoo" }, { 0x00F00, 0x00FDA, "Tibt" }, }, [0x01] = { { 0x01000, 0x0109F, "Mymr" }, { 0x010A0, 0x010CD, "Geok" }, { 0x010D0, 0x010FF, "Geor" }, { 0x01100, 0x011FF, "Hang" }, { 0x01200, 0x01399, "Ethi" }, { 0x013A0, 0x013F4, "Cher" }, { 0x01400, 0x0167F, "Cans" }, { 0x01680, 0x0169C, "Ogam" }, { 0x016A0, 0x016F0, "Runr" }, { 0x01700, 0x01714, "Tglg" }, { 0x01720, 0x01734, "Hano" }, { 0x01740, 0x01753, "Buhd" }, { 0x01760, 0x01773, "Tagb" }, { 0x01780, 0x017F9, "Khmr" }, { 0x01800, 0x018AA, "Mong" }, { 0x01900, 0x0194F, "Limb" }, { 0x01950, 0x01974, "Tale" }, { 0x01980, 0x019DF, "Talu" }, { 0x019E0, 0x019FF, "Khmr" }, { 0x01A00, 0x01A1F, "Bugi" }, { 0x01A20, 0x01AAD, "Lana" }, { 0x01B00, 0x01B7C, "Bali" }, { 0x01B80, 0x01BBF, "Sund" }, { 0x01BC0, 0x01BFF, "Batk" }, { 0x01C00, 0x01C4F, "Lepc" }, { 0x01C50, 0x01C7F, "Olck" }, { 0x01C90, 0x01CBF, "Geor" }, { 0x01E00, 0x01EFF, "Latn" }, { 0x01F00, 0x01FFE, "Polyt" }, }, [0x02] = { { 0x02190, 0x021FF, "Zsym" }, { 0x02200, 0x022FF, "Zmth" }, { 0x02300, 0x023FF, "Zsym" }, { 0x02500, 0x027BF, "Zsym" }, { 0x027C0, 0x027EF, "Zmth" }, { 0x02800, 0x028FF, "Brai" }, { 0x02980, 0x02AFF, "Zmth" }, { 0x02B00, 0x02BFE, "Zsym" }, { 0x02C00, 0x02C5E, "Glag" }, { 0x02C60, 0x02C7F, "Latn" }, { 0x02C80, 0x02CFF, "Copt" }, { 0x02D00, 0x02D2D, "Geok" }, { 0x02D30, 0x02D7F, "Tfng" }, { 0x02D80, 0x02DDE, "Ethi" }, { 0x02E80, 0x02FDF, "Hani" }, }, [0x03] = { { 0x03001, 0x03002, "Hani", "Bopo", "Hang", "Hira", "Kana", "Yiii" }, { 0x03003, 0x03007, "Hani" }, { 0x03008, 0x03011, "Hani", "Bopo", "Hang", "Hira", "Kana", "Yiii" }, { 0x03012, 0x03013, "Hani" }, { 0x03014, 0x0301B, "Hani", "Bopo", "Hang", "Hira", "Kana", "Yiii" }, { 0x0301C, 0x0301F, "Hani", "Bopo", "Hang", "Hira", "Kana" }, { 0x03020, 0x0303F, "Hani" }, { 0x03041, 0x0309F, "Hira" }, { 0x030A0, 0x030FF, "Kana" }, { 0x03105, 0x0312F, "Bopo" }, { 0x03131, 0x0318E, "Hang" }, { 0x031A0, 0x031BA, "Bopo" }, { 0x031C0, 0x031E3, "Hani" }, { 0x031F0, 0x031FF, "Kana" }, { 0x03220, 0x03247, "Hani" }, { 0x03280, 0x032B0, "Hani" }, { 0x032C0, 0x032CB, "Hani" }, { 0x03300, 0x03357, "Kana" }, { 0x03358, 0x03370, "Hani" }, { 0x0337B, 0x0337F, "Hani" }, { 0x033E0, 0x033FE, "Hani" }, { 0x03400, 0x03FFF, "Hani" }, }, [0x04] = { { 0x04000, 0x04DB5, "Hani" }, { 0x04E00, 0x04FFF, "Hani" }, }, [0x05] = { { 0x05000, 0x05FFF, "Hani" }, }, [0x06] = { { 0x06000, 0x06FFF, "Hani" }, }, [0x07] = { { 0x07000, 0x07FFF, "Hani" }, }, [0x08] = { { 0x08000, 0x08FFF, "Hani" }, }, [0x09] = { { 0x09000, 0x09FFF, "Hani" }, }, [0x0A] = { { 0x0A000, 0x0A4C6, "Yiii" }, { 0x0A4D0, 0x0A4FF, "Lisu" }, { 0x0A500, 0x0A62B, "Vaii" }, { 0x0A640, 0x0A67F, "Cyrs" }, { 0x0A680, 0x0A697, "Cyrl" }, { 0x0A6A0, 0x0A6F7, "Bamu" }, { 0x0A720, 0x0A7FF, "Latn" }, { 0x0A800, 0x0A82B, "Sylo" }, { 0x0A830, 0x0A832, "Deva", "Dogr", "Gujr", "Guru", "Khoj", "Knda", "Kthi", "Mahj", "Modi", "Nand", "Sind", "Takr", "Tirh"}, { 0x0A833, 0x0A835, "Deva", "Dogr", "Gujr", "Guru", "Khoj", "Knda", "Kthi", "Mahj", "Mlym", "Modi", "Nand", "Sind", "Takr", "Tirh"}, { 0x0A836, 0x0A839, "Deva", "Dogr", "Gujr", "Guru", "Khoj", "Kthi", "Mahj", "Modi", "Sind", "Takr", "Tirh"}, { 0x0A840, 0x0A877, "Phag" }, { 0x0A880, 0x0A8D9, "Saur" }, { 0x0A8E0, 0x0A8FF, "Deva" }, { 0x0A900, 0x0A92F, "Kali" }, { 0x0A930, 0x0A95F, "Rjng" }, { 0x0A980, 0x0A9DF, "Java" }, { 0x0A9E0, 0x0A9FE, "Mymr" }, { 0x0AA00, 0x0AA5F, "Cham" }, { 0x0AA60, 0x0AA7F, "Mymr" }, { 0x0AA80, 0x0AADF, "Tavt" }, { 0x0AAE0, 0x0AAFF, "Mtei" }, { 0x0AB01, 0x0AB2E, "Ethi" }, { 0x0AB30, 0x0AB65, "Latn" }, { 0x0AB70, 0x0ABBF, "Cher" }, { 0x0ABC0, 0x0ABFF, "Mtei" }, { 0x0AC00, 0x0AFFF, "Hang" }, }, [0x0B] = { { 0x0B000, 0x0BFFF, "Hang" }, }, [0x0C] = { { 0x0C000, 0x0CFFF, "Hang" }, }, [0x0D] = { { 0x0D000, 0x0D7A3, "Hang" }, }, [0x0F] = { { 0x0FA27, 0x0FA29, "Hani" }, { 0x0FB13, 0x0FB17, "Armn" }, { 0x0FB1D, 0x0FB4F, "Hebr" }, { 0x0FB50, 0x0FDFD, "Arab" }, { 0x0FE45, 0x0FE46, "Hani", "Bopo", "Hang", "Hira", "Kana" }, { 0x0FE70, 0x0FEFC, "Arab" }, { 0x0FF61, 0x0FF65, "Hani", "Bopo", "Hang", "Hira", "Kana", "Yiii" }, }, [0x10] = { { 0x10000, 0x100FA, "Linb" }, { 0x10280, 0x1029C, "Lyci" }, { 0x102A0, 0x102D0, "Cari" }, { 0x102E1, 0x102FB, "Copt" }, { 0x10300, 0x10323, "Ital" }, { 0x10330, 0x1034A, "Goth" }, { 0x10350, 0x1037A, "Perm" }, { 0x10380, 0x1039F, "Ugar" }, { 0x103A0, 0x103D5, "Xpeo" }, { 0x10400, 0x1044F, "Dsrt" }, { 0x10450, 0x1047F, "Shaw" }, { 0x10480, 0x104A9, "Osma" }, { 0x104B0, 0x104FB, "Osge" }, { 0x10500, 0x10527, "Elba" }, { 0x10530, 0x10563, "Aghb" }, { 0x10600, 0x10767, "Lina" }, { 0x10800, 0x1083F, "Cprt" }, { 0x10840, 0x1085F, "Armi" }, { 0x10860, 0x1087F, "Palm" }, { 0x10880, 0x108AF, "Nbat" }, { 0x108E0, 0x108FF, "Hatr" }, { 0x10900, 0x1091F, "Phnx" }, { 0x10920, 0x1093F, "Lydi" }, { 0x10980, 0x1099F, "Mero" }, { 0x109A0, 0x109BF, "Merc" }, { 0x10A00, 0x10A58, "Khar" }, { 0x10A60, 0x10A7F, "Sarb" }, { 0x10A80, 0x10A9F, "Narb" }, { 0x10AC0, 0x10AF6, "Mani" }, { 0x10B00, 0x10B3F, "Avst" }, { 0x10B40, 0x10B5F, "Prti" }, { 0x10B60, 0x10B7F, "Phli" }, { 0x10B80, 0x10BAF, "Phlp" }, { 0x10C00, 0x10C48, "Orkh" }, { 0x10C80, 0x10CB2, "Hung" }, { 0x10D00, 0x10D39, "Rohg" }, { 0x10E60, 0x10E7E, "Rumin" }, { 0x10F00, 0x10F27, "Sogo" }, { 0x10F30, 0x10F59, "Sogd" }, { 0x10F70, 0x10FAF, "Ougr" }, { 0x10FE0, 0x10FFF, "Elym" }, }, [0x11] = { { 0x11000, 0x1107F, "Brah" }, { 0x11080, 0x110CD, "Kthi" }, { 0x110D0, 0x110F9, "Sora" }, { 0x11100, 0x11146, "Cakm" }, { 0x11150, 0x11176, "Mahj" }, { 0x11180, 0x111D9, "Shrd" }, { 0x11200, 0x1123D, "Khoj" }, { 0x11280, 0x112A9, "Mult" }, { 0x112B0, 0x112F9, "Sind" }, { 0x11301, 0x11374, "Gran" }, { 0x11400, 0x1145E, "Newa" }, { 0x11480, 0x114D9, "Tirh" }, { 0x11580, 0x115DD, "Sidd" }, { 0x11600, 0x11659, "Modi" }, { 0x11680, 0x116C9, "Takr" }, { 0x11700, 0x1173F, "Ahom" }, { 0x11800, 0x1183B, "Dogr" }, { 0x118A0, 0x118FF, "Wara" }, { 0x119A0, 0x119FF, "Nand" }, { 0x11A00, 0x11A47, "Zanb" }, { 0x11A50, 0x11AA2, "Soyo" }, { 0x11AC0, 0x11AF8, "Pauc" }, { 0x11C00, 0x11C6C, "Bhks" }, { 0x11C70, 0x11CB6, "Marc" }, { 0x11D00, 0x11D59, "Gonm" }, { 0x11D60, 0x11DA9, "Gong" }, { 0x11EE0, 0x11EF8, "Maka" }, }, [0x12] = { { 0x12000, 0x1236E, "Xsux" }, { 0x12400, 0x12473, "Xsux" }, { 0x12F90, 0x12FFF, "Cpmn" }, }, [0x13] = { { 0x13000, 0x1342E, "Egyp" }, }, [0x14] = { { 0x14400, 0x14646, "Hluw" }, }, [0x16] = { { 0x16800, 0x16A38, "Bamu" }, { 0x16A40, 0x16A6F, "Mroo" }, { 0x16AD0, 0x16AF5, "Bass" }, { 0x16B00, 0x16B8F, "Hmng" }, { 0x16E40, 0x16E9A, "Medf" }, { 0x16F00, 0x16F9F, "Plrd" }, }, [0x17] = { { 0x17000, 0x17FFF, "Tang" }, }, [0x18] = { { 0x18000, 0x18AF2, "Tang" }, }, [0x1B] = { { 0x1B001, 0x1B11E, "Hira" }, { 0x1B170, 0x1B2FB, "Nshu" }, { 0x1BC00, 0x1BC9F, "Dupl" }, }, [0x1C] = { { 0x1CF00, 0x1CFCF, "Zname" }, }, [0x1D] = { { 0x1D100, 0x1D1DD, "Music" }, { 0x1D2E0, 0x1D2F3, "Maya" }, { 0x1D400, 0x1D7FF, "Zmth" }, { 0x1D800, 0x1DAAF, "Sgnw" }, }, [0x1E] = { { 0x1E000, 0x1E02A, "Glag" }, { 0x1E800, 0x1E8D6, "Mend" }, { 0x1E900, 0x1E95F, "Adlm" }, }, [0x1F] = { { 0x1F000, 0x1F0F5, "Zsym" }, { 0x1F300, 0x1FA6D, "Zsym" }, }, [0x20] = { { 0x20000, 0x20FFF, "Hani" }, }, [0x21] = { { 0x21000, 0x21FFF, "Hani" }, }, [0x22] = { { 0x22000, 0x22FFF, "Hani" }, }, [0x23] = { { 0x23000, 0x23FFF, "Hani" }, }, [0x24] = { { 0x24000, 0x24FFF, "Hani" }, }, [0x25] = { { 0x25000, 0x25FFF, "Hani" }, }, [0x26] = { { 0x26000, 0x26FFF, "Hani" }, }, [0x27] = { { 0x27000, 0x27FFF, "Hani" }, }, [0x28] = { { 0x28000, 0x28FFF, "Hani" }, }, [0x29] = { { 0x29000, 0x29FFF, "Hani" }, }, [0x2A] = { { 0x2A000, 0x2AFFF, "Hani" }, }, [0x2B] = { { 0x2B000, 0x2BFFF, "Hani" }, }, [0x2C] = { { 0x2C000, 0x2CFFF, "Hani" }, }, [0x2D] = { { 0x2D000, 0x2DFFF, "Hani" }, }, [0x2E] = { { 0x2E000, 0x2EBE0, "Hani" }, }, [0x30] = { { 0x30000, 0x30FFF, "Hani" }, }, [0x31] = { { 0x31000, 0x31FFF, "Hani" }, }, [0x32] = { { 0x32000, 0x32FFF, "Hani" }, }, [0x33] = { { 0x33000, 0x33FFF, "Hani" }, }, } for _, v in next, data do v.length = #v end data.individual = { [0x00462] = "Cyrl", [0x00463] = "Cyrl", [0x0060C] = "Arab, Nkoo, Rohg, Syrc, Thaa, Yezi", [0x0061B] = "Arab, Nkoo, Rohg, Syrc, Thaa, Yezi", [0x0061F] = "Arab, Adlm, Nkoo, Rohg, Syrc, Thaa, Yezi", [0x00640] = "Arab, Adlm, Mand, Mani, Ougr, Phlp, Rohg, Sogd, Syrc", [0x00951] = "Deva, Beng, Gran, Gujr, Guru, Knda, Latn, Mlym, Orya, Shrd, Taml, Telu, Tirh", [0x00952] = "Deva, Beng, Gran, Gujr, Guru, Knda, Latn, Mlym, Orya, Taml, Telu, Tirh", [0x00964] = "Deva, Beng, Dogr, Gong, Gonm, Gran, Gujr, Guru, Knda, Mahj, Mlym, Nand, Orya, Sind, Sinh, Sylo, Takr, Taml, Telu, Tirh", [0x00965] = "Deva, Beng, Dogr, Gong, Gonm, Gran, Gujr, Guru, Knda, Limb, Mahj, Mlym, Nand, Orya, Sind, Sinh, Sylo, Takr, Taml, Telu, Tirh", [0x0098F] = "Beng", [0x00990] = "Beng", [0x009A1] = "Beng", [0x009A2] = "Beng", [0x009AF] = "Beng", [0x009B2] = "Beng", [0x009BC] = "Beng", [0x009C7] = "Beng", [0x009C8] = "Beng", [0x009D7] = "Beng", [0x01CDA] = "Deva, Knda, Mlym, Orya, Taml, Telu", [0x01CF2] = "Deva, Beng, Gran, Knda, Nand, Orya, Telu, Tirh", [0x02135] = "Zmth", [0x03000] = "Hani", [0x03003] = "Hani, Bopo, Hang, Hira, Kana", [0x03013] = "Hani, Bopo, Hang, Hira, Kana", [0x03030] = "Hani, Bopo, Hang, Hira, Kana", [0x03037] = "Hani, Bopo, Hang, Hira, Kana", [0x030FB] = "Kana, Hani, Bopo, Hang, Hira, Yiii", [0x032FF] = "Hani", [0x0FA0E] = "Hani", [0x0FA0F] = "Hani", [0x0FA11] = "Hani", [0x0FA13] = "Hani", [0x0FA14] = "Hani", [0x0FA1F] = "Hani", [0x0FA21] = "Hani", [0x0FA23] = "Hani", [0x0FA24] = "Hani", [0x1056F] = "Aghb", [0x16FE0] = "Tang", [0x16FE1] = "Nshu", [0x1B000] = "Kana", } data.blocks = { { 0x04, 0x09, "Hani" }, { 0x0B, 0x0D, "Hang" }, { 0x17, 0x18, "Tang" }, { 0x20, 0x2E, "Hani" }, } return data 4m69qs8gnq8knzros5qbkff3yz21cb5 828 6013 17458 2026-07-13T08:57:01Z Hiyuune 6766 + 17458 Scribunto text/plain local auto_subtable_mt = { __index = function(self, key) local val = {} self[key] = val return val end } local function un_auto_subtable(t) t.un_auto_subtable = nil return setmetatable(t, nil) end return function(t) t = t or {} t.un_auto_subtable = un_auto_subtable return setmetatable(t, auto_subtable_mt) end 651lcbfe9p7obaexp4i0jesds6puc4f 828 6014 17459 2026-07-13T08:57:50Z Hiyuune 6766 + 17459 Scribunto text/plain local m_langdata = require("Module:languages/data") -- Loaded on demand, as it may not be needed (depending on the data). local function u(...) u = require("Module:string utilities").char return u(...) end local c = m_langdata.chars local p = m_langdata.puaChars local s = m_langdata.shared local m = {} m["taa"] = { "Lower Tanana", 28565, "ath-nor", "Latn", } m["tab"] = { "Tabasaran", 34079, "cau-esm", "Cyrl, Latn, Arab", translit = { Cyrl = "tab-translit", }, override_translit = true, display_text = { Cyrl = s["cau-Cyrl-displaytext"] }, strip_diacritics = { Cyrl = s["cau-Cyrl-stripdiacritics"], Latn = s["cau-Latn-stripdiacritics"], }, sort_key = { Cyrl = "tab-sortkey", } } m["tac"] = { "Lowland Tarahumara", 15616384, "azc-trc", "Latn", } m["tad"] = { "Tause", 2356440, "paa-wlp", "Latn", } m["tae"] = { "Tariana", 732726, "awd-nwk", "Latn", } m["taf"] = { "Tapirapé", 7684673, "tup-gua", "Latn", } m["tag"] = { "Tagoi", 36537, "nic-ras", "Latn", } m["taj"] = { "Eastern Tamang", 12953177, "sit-tam", "sit-tam-Tibt, Deva", -- sit-tam-Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] -- NOTE: Formerly there was no sort_key or translit specified; I assume that's a mistake. } m["tak"] = { "Tala", 3914494, "cdc-wst", "Latn", } m["tal"] = { "Tal", 3440387, "cdc-wst", "Latn", } m["tan"] = { "Tangale", 529921, "cdc-wst", "Latn", } m["tao"] = { "Yami", 715760, "phi", "Latn", } m["tap"] = { "Taabwa", 7673650, "bnt-sbi", "Latn", } m["tar"] = { "Central Tarahumara", 20090009, "azc-trc", "Latn", sort_key = {remove_diacritics = c.acute .. "ꞌ"}, } m["tas"] = { "Tây Bồi", 2233794, "crp", "Latn", ancestors = "fr", sort_key = s["roa-oil-sortkey"], } m["tau"] = { "Upper Tanana", 28281, "ath-nor", "Latn", } m["tav"] = { "Tatuyo", 2524007, "sai-tuc", "Latn", } m["taw"] = { "Tai", 7675861, "ngf-kak", "Latn", } m["tax"] = { "Tamki", 3449082, "cdc-est", "Latn", } m["tay"] = { "Atayal", 715766, "map-ata", "Latn", } m["taz"] = { "Tocho", 36680, "alv-tal", "Latn", } m["tba"] = { "Aikanã", 3409307, "qfa-iso", "Latn", } -- Tapeba [tbb] is spurious m["tbc"] = { "Takia", 3514336, "poz-oce", "Latn", } m["tbd"] = { "Kaki Ae", 6349417, "qfa-iso", -- isolate in Glottolog and Pawley and Hammarström (2018); tentatively in Eleman family by Ross (2005) -- (and Usher?), but they don't address counterarguments of Clifton 1997 "Latn", } m["tbe"] = { "Tanimbili", 3515188, "poz-tem", "Latn", } m["tbf"] = { "Mandara", 3285424, "poz-ocw", "Latn", } m["tbg"] = { "North Tairora", 20210398, "ngf-tai", "Latn", } m["tbh"] = { "Thurawal", 3537135, "aus-yuk", "Latn", } m["tbi"] = { "Gaam", 35338, "sdv-eje", "Latn", } m["tbj"] = { "Tiang", 3528020, "poz-ocw", "Latn", } m["tbk"] = { "Calamian Tagbanwa", 3915487, "phi-kal", "Tagb, Latn", } m["tbl"] = { "Tboli", 7690594, "phi", "Latn", } m["tbm"] = { "Tagbu", 7675188, "nic-ser", } m["tbn"] = { "Barro Negro Tunebo", 12953943, "cba", } m["tbo"] = { "Tawala", 7689206, "poz-ocw", "Latn", } m["tbp"] = { "Taworta", 7689337, "paa-elp", "Latn", } m["tbr"] = { "Tumtum", 3407029, "qfa-kad", } m["tbs"] = { "Tanguat", 7683166, "paa-ata", "Latn", } m["tbt"] = { "Kitembo", 13123561, "bnt-shh", "Latn", } m["tbu"] = { "Tubar", 56730, "azc-trc", "Latn", } m["tbv"] = { -- considered a dialect of Kulungtfu-Yuanggeng-Tobo [kgf] by Glottolog "Tobo", 7811712, "ngf-kto", "Latn", } m["tbw"] = { "Aborlan Tagbanwa", 3915475, "phi", "Latn", } m["tbx"] = { "Kapin", 6366665, "poz-ocw", "Latn", } m["tby"] = { "Tabaru", 11732670, "paa-gto", "Latn", } m["tbz"] = { "Ditammari", 35186, "nic-eov", "Latn", } m["tca"] = { "Ticuna", 1815205, "sai-tyu", "Latn", } m["tcb"] = { "Tanacross", 28268, "ath-nor", "Latn", } m["tcc"] = { "Datooga", 35327, "sdv-nis", "Latn", } m["tcd"] = { "Tafi", 36545, "alv-ktg", } m["tce"] = { "Southern Tutchone", 31091048, "ath-nor", "Latn", } m["tcf"] = { "Malinaltepec Tlapanec", 25559732, "omq", "Latn", } m["tcg"] = { "Tamagario", 7680531, "paa-kay", "Latn", } m["tch"] = { "Turks and Caicos Creole English", 7855478, "crp", "Latn", ancestors = "en", } m["tci"] = { "Wára", 20825638, "paa-wko", "Latn", } m["tck"] = { "Tchitchege", 36595, "bnt-tek", } m["tcl"] = { "Taman (Myanmar)", 15616518, "sit-jnp", "Latn", } m["tcm"] = { "Tanahmerah", 3514927, "qfa-dis", -- Papuan; isolate per Glottolog and Palmer (2018), considered an independent branch of TNG by Usher -- (2020); seems based only on some pronoun correspondences "Latn", } m["tco"] = { "Taungyo", 12953186, "tbq-brm", ancestors = "obr", } m["tcp"] = { "Tawr Chin", 7689338, "tbq-kuk", } m["tcq"] = { "Kaiy", 6348709, "paa-clp", "Latn", } m["tcs"] = { "Torres Strait Creole", 36648, "crp", "Latn", ancestors = "en", } m["tct"] = { "T'en", 3442330, "qfa-kms", } m["tcu"] = { "Southeastern Tarahumara", 36807, "azc-trc", "Latn", } m["tcw"] = { "Tecpatlán Totonac", 7692795, "nai-ttn", "Latn", } m["tcx"] = { "Toda", 34042, "dra-tkt", "Taml", --translit = {Taml = "Taml-translit"}, } m["tcy"] = { "Tulu", 34251, "dra-tlk", "Tutg, Mlym, Knda", -- Mlym is nearer than Knda but both lack ɛ/ɛː. translit = { Tutg = "tcy-Tutg-translit", }, -- Knda translit in [[Module:scripts/data]] -- Mlym translit in [[Module:scripts/data]] } m["tcz"] = { "Thado Chin", 6583558, "tbq-kuk", } m["tda"] = { "Tagdal", 36570, "son", } m["tdb"] = { "Panchpargania", 21946879, "inc-bih", "Deva, as-Beng, Orya, Chis", } m["tdc"] = { "Emberá-Tadó", 3052041, "sai-chc", "Latn", } m["tdd"] = { "Tai Nüa", 36556, "tai-swe", "Tale", translit = "Tale-translit", strip_diacritics = {remove_diacritics = c.ZWNJ .. c.ZWJ}, } m["tde"] = { "Tiranige Diga Dogon", 5313387, "nic-dgw", } m["tdf"] = { "Talieng", 37525108, "mkh-ban", } m["tdg"] = { "Western Tamang", 12953178, "sit-tam", "sit-tam-Tibt, Deva", -- sit-tam-Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] -- NOTE: Formerly there was no sort_key or translit specified; I assume that's a mistake. } m["tdh"] = { "Thulung", 56553, "sit-kiw", } m["tdi"] = { "Tomadino", 7818197, "poz-btk", "Latn", } m["tdj"] = { "Tajio", 7676870, "poz", "Latn", } m["tdk"] = { "Tambas", 3440392, "cdc-wst", } m["tdl"] = { "Sur", 3914453, "nic-tar", } m["tdm"] = { "Taruma", 5559094, } m["tdn"] = { "Tondano", 3531514, "phi", "Latn", } m["tdo"] = { "Teme", 3913994, "alv-mye", } m["tdq"] = { "Tita", 3914899, "nic-bco", } m["tdr"] = { "Todrah", 7812881, "mkh", } m["tds"] = { "Doutai", 5302331, "paa-clp", "Latn", } m["tdt"] = { "Tetun Dili", 12643484, "poz-tim", "Latn", } m["tdu"] = { "Tempasuk Dusun", 3529155, "poz-san", } m["tdv"] = { "Toro", 3438367, "nic-alu", "Latn", } m["tdy"] = { "Tadyawan", 7674700, "phi", "Latn", } m["tea"] = { "Temiar", 3914693, "mkh-asl", "Latn", } m["teb"] = { "Tetete", 7706087, "sai-tuc", "Latn", } m["tec"] = { "Terik", 3518379, "sdv-nma", } m["ted"] = { "Tepo Krumen", 11152243, "kro-grb", } m["tee"] = { "Huehuetla Tepehua", 56455, "nai-ttn", "Latn", } m["tef"] = { "Teressa", 3518362, "aav-nic", } m["teg"] = { "Teke-Tege", 36478, "bnt-tek", } m["teh"] = { "Tehuelche", 33930, "sai-cho", "Latn", } m["tei"] = { "Torricelli", 3450788, "paa-kom", "Latn", } m["tek"] = { "Ibali Teke", 2802914, "bnt-tek", } m["tem"] = { "Temne", 36613, "alv-mel", "Latn", } m["ten"] = { "Tama (Colombia)", 3832969, "sai-tuc", "Latn", } m["teo"] = { "Ateso", 29474, "sdv-ttu", "Latn", } m["tep"] = { "Tepecano", 3915525, "azc-pim", "Latn", } m["teq"] = { "Temein", 7698064, "sdv", } m["ter"] = { "Tereno", 3314742, "awd", "Latn", } m["tes"] = { "Tengger", 12473479, "poz", "Latn, Java", } m["tet"] = { "Tetum", 34125, "poz-tim", "Latn", } m["teu"] = { "Soo", 3437607, "ssa-klk", } m["tev"] = { "Teor", 12953198, "poz-cma", } m["tew"] = { "Tewa", 56492, "nai-kta", "Latn", } m["tex"] = { "Tennet", 56346, "sdv", } m["tey"] = { "Tulishi", 12911106, "qfa-kad", "Latn", } m["tez"] = { "Tetserret", 7706841, "ber", "Latn", } m["tfi"] = { "Tofin Gbe", 3530330, "alv-pph", } m["tfn"] = { "Dena'ina", 27785, "ath-nor", "Latn", } m["tfo"] = { "Tefaro", 7694618, "paa-egb", "Latn", } m["tfr"] = { "Teribe", 36533, "cba", "Latn", } m["tft"] = { "Ternate", 3518492, "paa-tti", "Latn, Arab", } m["tga"] = { "Sagalla", 12953082, "bnt-cht", } m["tgb"] = { "Tobilung", 12953913, "poz-san", "Latn", } m["tgc"] = { "Tigak", 3528276, "poz-ocw", "Latn", } m["tgd"] = { "Ciwogai", 3438799, "cdc-wst", "Latn", } m["tge"] = { "Eastern Gorkha Tamang", 12953175, "sit-tam", "sit-tam-Tibt, Deva", -- sit-tam-Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] -- NOTE: Formerly there was no sort_key or translit specified; I assume that's a mistake. } m["tgf"] = { "Chali", 3695197, "sit-ebo", "Tibt, Latn", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["tgh"] = { "Tobagonian Creole English", 7811541, "crp", ancestors = "en", } m["tgi"] = { "Lawunuia", 3219937, "poz-ocw", } m["tgn"] = { "Tandaganon", 63311769, "phi", "Latn", } m["tgo"] = { "Sudest", 7675351, "poz-ocw", } m["tgp"] = { "Tangoa", 2410276, "poz-vnn", "Latn", } m["tgq"] = { "Tring", 7842360, "poz-swa", } m["tgr"] = { "Tareng", 25559541, "mkh", } m["tgs"] = { "Nume", 3346290, "poz-vnn", "Latn", } m["tgt"] = { "Central Tagbanwa", 3915515, "phi", "Tagb", } m["tgu"] = { "Tanggu", 7682930, "paa-ata", "Latn", } m["tgv"] = { "Tingui-Boto", 7808195, "sai-mje", "Latn", } m["tgw"] = { "Tagwana", 36514, "alv-tdj", } m["tgx"] = { "Tagish", 28064, "ath-nor", "Latn", } m["tgy"] = { "Togoyo", 36825, "nic-ser", } m["thc"] = { "Tai Hang Tong", 7675753, "tai-nor", } m["thd"] = { "Kuuk Thaayorre", 6448718, "aus-pmn", "Latn", } m["the"] = { "Chitwania Tharu", 22083804, "inc-tha", "Deva", } m["thf"] = { "Thangmi", 7710314, "sit-new", } m["thh"] = { "Northern Tarahumara", 15616395, "azc-trc", "Latn", } m["thi"] = { "Tai Long", 25559562, "tai-swe", } m["thk"] = { "Tharaka", 15407179, "bnt-kka", } m["thl"] = { "Dangaura Tharu", 22083815, "inc-tha", "Deva", } m["thm"] = { "Thavung", 34780, "mkh-vie", "Thai", --Laoo is feasible but no evidence yet. sort_key = "Thai-sortkey", } m["thn"] = { "Thachanadan", 7708880, "dra-mal", } m["thp"] = { "Thompson", 1755054, "sal", "Latn, Dupl", } m["thq"] = { "Kochila Tharu", 22083826, "inc-tha", } m["thr"] = { "Rana Tharu", 12953920, "inc-tha", "Deva", } m["ths"] = { "Thakali", 7709348, "sit-tam", } m["tht"] = { "Tahltan", 30125, "ath-nor", "Latn", } m["thu"] = { "Thuri", 7799291, "sdv-lon", } m["thy"] = { "Tha", 3915849, "alv-bwj", } m["tic"] = { "Tira", 36677, "alv-hei", } m["tif"] = { "Tifal", 11732691, "ngf-mok", "Latn", } m["tig"] = { "Tigre", 34129, "sem-eth", "Ethi", translit = "Ethi-translit", } m["tih"] = { "Timugon Murut", 7807680, "poz-san", "Latn", } m["tii"] = { "Tiene", 36469, "bnt-tek", } m["tij"] = { "Tilung", 7803037, "sit-kiw", } m["tik"] = { "Tikar", 36483, "nic-bdn", "Latn", } m["til"] = { "Tillamook", 2109432, "sal", "Latn", } m["tim"] = { "Timbe", 7804599, "ngf-kab", "Latn", } m["tin"] = { "Tindi", 36860, "cau-and", "Cyrl", display_text = s["cau-Cyrl-displaytext"], strip_diacritics = s["cau-Cyrl-stripdiacritics"], } m["tio"] = { "Teop", 3518239, "poz-ocw", "Latn", } m["tip"] = { "Trimuris", 7842270, "paa-kwe", "Latn", } m["tiq"] = { "Tiéfo", 3914874, "alv-sav", } m["tis"] = { "Masadiit Itneg", 18748769, "phi", } m["tit"] = { "Tinigua", 3029805, "sai-tin", "Latn", } m["tiu"] = { "Adasen", 11214797, "phi", "Latn", } m["tiv"] = { "Tiv", 34131, "nic-tvc", "Latn", } m["tiw"] = { "Tiwi", 1656014, "qfa-iso", "Latn", } m["tix"] = { "Southern Tiwa", 7570552, "nai-kta", "Latn", } m["tiy"] = { "Tiruray", 7809425, "phi", "Latn", } m["tiz"] = { "Tai Hongjin", 3915716, "tai-swe", } m["tja"] = { "Tajuasohn", 3915326, "kro-wkr", } m["tjg"] = { "Tunjung", 3542117, "poz", "Latn", } m["tji"] = { "Northern Tujia", 12953229, "sit-tja", "Latn", } m["tjl"] = { "Tai Laing", 7675773, "tai-swe", "Mymr", } m["tjm"] = { "Timucua", 638300, "qfa-iso", "Latn", } m["tjn"] = { "Tonjon", 3913372, "dmn-jje", } m["tjs"] = { "Southern Tujia", 12633994, "sit-tja", "Latn", } m["tju"] = { "Tjurruru", 3913834, "aus-nga", "Latn", } m["tjw"] = { "Chaap Wuurong", 5285187, "aus-pam", "Latn", } m["tka"] = { "Truká", 7847648, } m["tkb"] = { "Buksa", 20983638, "inc-eas", "Deva", } m["tkd"] = { "Tukudede", 36863, "poz-tim", "Latn", } m["tke"] = { "Takwane", 11030092, "bnt-mak", "Latn", ancestors = "vmw", } m["tkf"] = { "Tukumanféd", 42330115, "tup-gua", "Latn", } m["tkl"] = { "Tokelauan", 34097, "poz-pnp", "Latn", } m["tkm"] = { "Takelma", 56710, } m["tkn"] = { "Tokunoshima", 3530484, "jpx-nry", "Jpan", translit = s["jpx-translit"], display_text = s["jpx-displaytext"], strip_diacritics = s["jpx-stripdiacritics"], sort_key = s["jpx-sortkey"], } m["tkp"] = { "Tikopia", 36682, "poz-pnp", "Latn", } m["tkq"] = { "Tee", 3075144, "nic-ogo", "Latn", } m["tkr"] = { "Tsakhur", 36853, "cau-wsm", "Cyrl, Latn, Arab", translit = "tkr-translit", override_translit = true, display_text = { Cyrl = s["cau-Cyrl-displaytext"] }, strip_diacritics = { Cyrl = s["cau-Cyrl-stripdiacritics"], Latn = s["cau-Latn-stripdiacritics"], }, } m["tks"] = { "Ramandi", 25261947, "xme-ttc", "Arab", ancestors = "xme-ttc-sou", } m["tkt"] = { "Kathoriya Tharu", 22083822, "inc-tha", } m["tku"] = { "Upper Necaxa Totonac", 56343, "nai-ttn", "Latn", } m["tkv"] = { "Mur Pano", 16939373, "poz-ocw", "Latn", } m["tkw"] = { "Teanu", 3516731, "poz-tem", "Latn", } m["tkx"] = { "Tangko", 7682993, "ngf-tna", "Latn", } m["tkz"] = { "Takua", 7678544, "mkh", } m["tla"] = { "Southwestern Tepehuan", 3518245, "azc-pim", "Latn", } m["tlb"] = { "Tobelo", 1142333, "paa-gto", "Latn", } m["tlc"] = { "Misantla Totonac", 56460, "nai-ttn", "Latn", } m["tld"] = { "Talaud", 7678964, "phi", "Latn", } m["tlf"] = { "Telefol", 7696150, "ngf-mok", "Latn", } m["tlg"] = { "Tofanma", 4461493, "paa-nto", "Latn", } m["tlh"] = { "Klingon", 10134, "art", "Latn", type = "appendix-constructed", } m["tli"] = { "Tlingit", 27792, "xnd", "Latn, Cyrl", } m["tlj"] = { "Talinga-Bwisi", 7679530, "bnt-haj", } m["tlk"] = { "Taloki", 3514563, "poz-btk", } m["tll"] = { "Tetela", 2613465, "bnt-tet", } m["tlm"] = { "Tolomako", 3130514, "poz-vnn", "Latn", } m["tln"] = { "Talondo'", 7680293, "poz-ssw", } m["tlo"] = { "Talodi", 36525, "alv-tal", } m["tlp"] = { "Filomena Mata-Coahuitlán Totonac", 5449202, "nai-ttn", "Latn", } m["tlq"] = { "Tai Loi", 7675784, "mkh-pal", } m["tlr"] = { "Talise", 3514510, "poz-sls", "Latn", } m["tls"] = { "Tambotalo", 7681065, "poz-vnn", "Latn", } m["tlt"] = { "Teluti", 12953194, "poz-cma", } m["tlu"] = { "Tulehu", 7852006, "poz-cma", } m["tlv"] = { "Taliabu", 3514498, "poz-cma", "Latn", } m["tlx"] = { "Khehek", 3196124, "poz-aay", } m["tly"] = { "Talysh", 34318, "xme-ttc", "Latn, Cyrl, fa-Arab", } m["tma"] = { "Tama (Chad)", 57001, "sdv-tmn", } m["tmb"] = { "Avava", 2157461, "poz-vnc", "Latn", } m["tmc"] = { "Tumak", 3121045, "cdc-est", } m["tmd"] = { "Haruai", 12632146, "paa-pia", "Latn", } m["tme"] = { "Tremembé", 5246937, } m["tmf"] = { "Toba-Maskoy", 3033544, "sai-mas", "Latn", } m["tmg"] = { "Ternateño", 7232597, } m["tmh"] = { "Tuareg", 34065, "ber", "Latn, Tfng, Arab", strip_diacritics = { Latn = {remove_diacritics = c.grave .. c.acute .. c.circ}, }, } m["tmi"] = { "Tutuba", 7857052, "poz-vnn", "Latn", } m["tmj"] = { "Samarokena", 7408865, "paa-saa", "Latn", } m["tml"] = { "Tamnim Citak", 12643315, "ngf-asm", "Latn", } m["tmm"] = { "Tai Thanh", 7675842, "tai-swe", } m["tmn"] = { "Taman (Indonesia)", 7680671, "poz", "Latn", } m["tmo"] = { "Temoq", 7698205, "mkh-asl", } m["tmq"] = { "Tumleo", 7852641, "poz-ocw", } m["tms"] = { "Tima", 36684, "nic-ktl", } m["tmt"] = { "Tasmate", 7687571, "poz-vnn", "Latn", } m["tmu"] = { "Iau", 56867, "paa-lpl", "Latn", } m["tmv"] = { "Motembo", 11013108, "bnt-bun", } m["tmy"] = { "Tami", 3514812, "poz-oce", } m["tmz"] = { "Tamanaku", 3441435, "sai-ven", "Latn", } m["tna"] = { "Tacana", 3182551, "sai-tac", "Latn", } m["tnb"] = { "Western Tunebo", 3181238, "cba", } m["tnc"] = { "Tanimuca-Retuarã", 36535, "sai-tuc", "Latn", } m["tnd"] = { "Angosturas Tunebo", 25559604, "cba", } m["tne"] = { "Tinoc Kallahan", 3192219, } m["tng"] = { "Tobanga", 3440501, "cdc-est", } m["tnh"] = { "Maiani", 6735243, "ngf-kau", "Latn", } m["tni"] = { "Tandia", 7682454, "poz-hce", "Latn", } m["tnk"] = { "Kwamera", 3200806, "poz-vns", "Latn", } m["tnl"] = { "Lenakel", 3229429, "poz-vns", "Latn", } m["tnm"] = { "Tabla", 7673105, "paa-sen", "Latn", } m["tnn"] = { "North Tanna", 957945, "poz-vns", "Latn", } m["tno"] = { "Toromono", 510544, "sai-tac", "Latn", } m["tnp"] = { "Whitesands", 3063761, "poz-vns", "Latn", } m["tnq"] = { "Taíno", 5232952, "awd-taa", "Latn", } m["tnr"] = { "Bedik", 35096, "alv-ten", "Latn", } m["tns"] = { "Tenis", 7699870, "poz-stm", "Latn", } m["tnt"] = { "Tontemboan", 3531666, "phi", "Latn", } m["tnu"] = { "Tay Khang", 6362363, "tai", } m["tnv"] = { "Tanchangya", 7682361, "inc-bas", "Cakm", ancestors = "inc-obn", } m["tnw"] = { "Tonsawang", 3531660, "phi", "Latn", } m["tnx"] = { "Tanema", 2106984, "poz-tem", "Latn", } m["tny"] = { "Tongwe", 7821200, "bnt", } m["tnz"] = { "Ten'edn", 3073453, "mkh-asl", "Latn", } m["tob"] = { "Toba", 3113756, "sai-guc", "Latn", } m["toc"] = { "Coyutla Totonac", 15615591, "nai-ttn", "Latn", } m["tod"] = { "Toma", 11055484, "dmn-msw", "Latn, Loma" } m["tof"] = { "Gizrra", 5565941, "paa-etf", "Latn", } m["tog"] = { "Tonga (Malawi)", 3847648, "bnt-nys", "Latn", } m["toh"] = { "Tonga (Mozambique)", 7820988, "bnt-bso", } m["toi"] = { "Tonga (Zambia)", 34101, "bnt-bot", "Latn", } m["toj"] = { "Tojolabal", 36762, "myn", "Latn", } m["tok"] = { "Toki Pona", 36846, "art", "Latn", type = "appendix-constructed", } m["tol"] = { "Tolowa", 20827, "ath-pco", "Latn", } m["tom"] = { "Tombulu", 3531199, "phi", "Latn", } m["too"] = { "Xicotepec de Juárez Totonac", 8044353, "nai-ttn", "Latn", } m["top"] = { "Papantla Totonac", 56329, "nai-ttn", "Latn", } m["toq"] = { "Toposa", 3033588, "sdv-ttu", } m["tor"] = { "Togbo-Vara Banda", 11002922, "bad-cnt", } m["tos"] = { "Highland Totonac", 13154149, "nai-ttn", "Latn", } m["tou"] = { "Tho", 22694631, "mkh-vie", "Latn", } m["tov"] = { "Upper Taromi", 12953183, "xme-ttc", ancestors = "xme-ttc-cen", } m["tow"] = { "Jemez", 3912876, "nai-kta", "Latn", } m["tox"] = { "Tobian", 34022, "poz-mic", } m["toy"] = { "Topoiyo", 7824977, "poz-kal", } m["toz"] = { "To", 7811216, "alv-mbm", } m["tpa"] = { "Taupota", 7688832, "poz-ocw", } m["tpc"] = { "Azoyú Me'phaa", 25559730, "omq", "Latn", } m["tpe"] = { "Tippera", 16115423, "tbq-bdg", } m["tpf"] = { "Tarpia", 12953185, "poz-ocw", "Latn", } m["tpg"] = { "Kula", 6442714, "paa-alp", "Latn", } m["tpi"] = { "Tok Pisin", 34159, "crp", "Latn", ancestors = "en", } m["tpj"] = { "Tapieté", 3121063, "gn", "Latn", } m["tpk"] = { "Tupinikin", 33924, "tup-gua", } m["tpl"] = { "Tlacoapa Me'phaa", 16115511, "omq", } m["tpm"] = { "Tampulma", 36590, "nic-gnw", } m["tpn"] = { "Tupinambá", 31528147, "tup-gua", "Latn", } m["tpo"] = { "Tai Pao", 7675795, "tai-nor", } m["tpp"] = { "Pisaflores Tepehua", 56349, "nai-ttn", } m["tpq"] = { "Tukpa", 12953230, "sit-las", } m["tpr"] = { "Tuparí", 3542217, "tup", "Latn", } m["tpt"] = { "Tlachichilco Tepehua", 56330, "nai-ttn", } m["tpu"] = { "Tampuan", 3514882, "mkh-ban", "Khmr", } m["tpv"] = { "Tanapag", 3397371, "poz-mic", } m["tpw"] = { "Old Tupi", 56944, "tup-gua", "Latn", } m["tpx"] = { "Acatepec Me'phaa", 31157882, "omq", "Latn", } m["tpy"] = { "Trumai", 12294279, "qfa-iso", } m["tpz"] = { "Tinputz", 3529205, "poz-ocw", } m["tqb"] = { "Tembé", 10322157, "tup-gua", "Latn", } m["tql"] = { "Lehali", 3229119, "poz-vnn", "Latn", } m["tqm"] = { "Turumsa", 7856508, "paa-dtu", "Latn", } m["tqn"] = { "Tenino", 15699255, "nai-shp", "Latn", ancestors = "nai-spt", } m["tqo"] = { "Toaripi", 7811403, "paa-eel", "Latn", } m["tqp"] = { "Tomoip", 3531388, "poz-ocw", } m["tqq"] = { "Tunni", 3514343, "cus-som", } m["tqr"] = { "Torona", 36679, "alv-tal", } m["tqt"] = { "Western Totonac", 7116691, "nai-ttn", "Latn", } m["tqu"] = { "Touo", 56750, } m["tqw"] = { "Tonkawa", 2454881, "qfa-iso", "Latn", } m["tra"] = { "Tirahi", 3812406, "inc-koh", } m["trb"] = { "Terebu", 7701797, "poz-ocw", } m["trc"] = { "Copala Triqui", 12953935, "omq-tri", "Latn", } m["trd"] = { "Turi", 7854914, "mun", } m["tre"] = { "East Tarangan", 18609750, "poz", } m["trf"] = { "Trinidadian Creole English", 7842493, "crp", "Latn", ancestors = "en", } m["trg"] = { "Lishán Didán", 56473, "sem-nna", "Hebr", } m["trh"] = { "Turaka", 12953237, "ngf-dag", "Latn", } m["tri"] = { "Trió", 56885, "sai-tar", "Latn", } m["trj"] = { "Toram", 3441225, "cdc-est", } m["trl"] = { "Traveller Scottish", 3915671, "qfa-mix", "Latn", ancestors = "rom, sco", } m["trm"] = { "Tregami", 34081, "nur-sou", } m["trn"] = { "Trinitario", 3539279, "awd", } m["tro"] = { "Tarao", 3515603, "tbq-kuk", "Latn", } m["trp"] = { "Kokborok", 35947, "tbq-bdg", "Beng, Latn" -- WP lists 2 more } m["trq"] = { "San Martín Itunyoso Triqui", 12953934, "omq-tri", "Latn", } m["trr"] = { "Taushiro", 1957508, nil, "Latn", } m["trs"] = { "Chicahuaxtla Triqui", 3539587, "omq-tri", "Latn", } m["trt"] = { "Tunggare", 615071, "paa-egb", "Latn", } m["tru"] = { "Turoyo", 34040, "sem-cna", "Syrc, Latn", translit = { Syrc = "tru-translit", }, strip_diacritics = { Syrc = "Syrc-stripdiacritics", }, } m["trv"] = { "Taroko", 716686, "map-ata", "Latn", } m["trw"] = { "Torwali", 2665246, "inc-koh", "ur-Arab", } m["trx"] = { "Tringgus", 7842365, "day", } m["try"] = { "Turung", 7856514, "tai-swe", "as-Beng", } m["trz"] = { "Torá", 7827518, "sai-cpc", } m["tsa"] = { "Tsaangi", 36675, "bnt-nze", } m["tsb"] = { "Tsamai", 2371358, "cus-eas", } m["tsc"] = { "Tswa", 2085051, "bnt-tsr", } m["tsd"] = { "Tsakonian", 220607, "grk", "Grek", ancestors = "grc-dor", translit = "el-translit", -- Grek display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["tse"] = { "Tunisian Sign Language", 7853191, "sgn", } m["tsg"] = { "Tausug", 34142, "phi", "Latn, Arab", } m["tsh"] = { "Tsuvan", 3502326, "cdc-cbm", "Latn", } m["tsi"] = { "Tsimshian", 20085721, "nai-tsi", "Latn", } m["tsj"] = { "Tshangla", 36840, "sit-tsk", "Tibt, Latn, Deva", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["tsl"] = { "Ts'ün-Lao", 3446675, "tai", } m["tsm"] = { "Turkish Sign Language", 36885, "sgn", } m["tsp"] = { "Northern Toussian", 11155635, "alv-sav", } m["tsq"] = { "Thai Sign Language", 7709156, "sgn-asl", "Sgnw", } m["tsr"] = { "Akei", 2828964, "poz-vnn", "Latn", } m["tss"] = { "Taiwan Sign Language", 34019, "sgn-jsl", } m["tsu"] = { "Tsou", 716681, "map", "Latn", } m["tsv"] = { "Tsogo", 36674, "bnt-tso", } m["tsw"] = { "Tsishingini", 13123571, "nic-kam", } m["tsx"] = { "Mubami", 6930815, "paa-wig", "Latn", } m["tsy"] = { "Tebul Sign Language", 7692090, "sgn", } m["tta"] = { "Tutelo", 2311602, "sio-ohv", "Latn", } m["ttb"] = { "Gaa", 3438361, "nic-dak", "Latn", } m["ttc"] = { "Tektiteko", 36686, "myn", "Latn", } m["ttd"] = { "Tauade", 7688634, "qfa-dis", -- Papuan; isolate per Glottolog; Glottolog says "A Goilalan family uniting Kunimaipan, Tauade and Fuyug -- is often posited based on the lexicostatistical figures reported in Tom E. Dutton 1975: 631-632" but -- goes on to say the data "is clearly insufficient, as the lexical links so far proposed are few and -- show irregular one-consonant correspondences". "Latn", } m["tte"] = { "Bwanabwana", 5003667, "poz-ocw", "Latn", } m["ttf"] = { "Tuotomb", 7853459, "nic-mbw", "Latn", } m["ttg"] = { "Tutong", 3507990, "poz-swa", "Latn", } m["tth"] = { "Upper Ta'oih", 3512660, "mkh-kat", } m["tti"] = { "Tobati", 7811556, "poz-ocw", "Latn", } m["ttj"] = { "Tooro", 7824218, "bnt-nyg", "Latn", } m["ttk"] = { "Totoro", 3532756, "sai-bar", "Latn", } m["ttl"] = { "Totela", 10962316, "bnt-bot", "Latn", } m["ttm"] = { "Northern Tutchone", 20822, "ath-nor", "Latn", } m["ttn"] = { "Towei", 7829606, "paa-wpw", "Latn", } m["tto"] = { "Lower Ta'oih", 25559539, "mkh-kat", } m["ttp"] = { "Tombelala", 6799663, "poz-kal", } m["ttr"] = { "Tera", 56267, "cdc-cbm", } m["tts"] = { "Isan", 33417, "tai-swe", "Thai", -- also Tai Noi/Lao Buhan script sort_key = "Thai-sortkey", } m["ttt"] = { "Tat", 56489, "ira-swi", "Cyrl, Latn, Armn, fa-Arab", -- Armn translit in [[Module:scripts/data]] (NOTE: formerly not present, probably an accidental omission) ancestors = "fa", } m["ttu"] = { "Torau", 3532208, "poz-ocw", } m["ttv"] = { "Titan", 3445811, "poz-aay", "Latn", } m["ttw"] = { "Long Wat", 7856961, "poz-swa", } m["tty"] = { "Sikaritai", 7513600, "paa-clp", "Latn", } m["ttz"] = { "Tsum", 12953223, "sit-kyk", } m["tua"] = { "Wiarumus", 7998045, "paa-mmu", "Latn", } m["tub"] = { "Tübatulabal", 56704, "azc", "Latn", } m["tuc"] = { "Mutu", 3331003, "poz-ocw", "Latn", } m["tud"] = { "Tuxá", 7857217, } m["tue"] = { "Tuyuca", 2520538, "sai-tuc", "Latn", } m["tuf"] = { "Central Tunebo", 12953942, "cba", "Latn", } m["tug"] = { "Tunia", 863721, "alv-bua", } m["tuh"] = { "Taulil", 3516141, } m["tui"] = { "Tupuri", 36646, "alv-mbm", "Latn", } m["tuj"] = { "Tugutil", 12953228, "paa-gto", "Latn", } m["tul"] = { "Tula", 3914907, "alv-wjk", } m["tum"] = { "Tumbuka", 34138, "bnt-nys", "Latn", } m["tun"] = { "Tunica", 56619, "qfa-iso", "Latn", } m["tuo"] = { "Tucano", 3541834, "sai-tuc", "Latn", } m["tuq"] = { "Tedaga", 36639, "ssa-sah", "Latn", } m["tus"] = { "Tuscarora", 36944, "iro-nor", "Latn", } m["tuu"] = { "Tututni", 20627, "ath-pco", "Latn", } m["tuv"] = { "Turkana", 36958, "sdv-ttu", "Latn", } m["tux"] = { "Tuxináwa", 7857204, "sai-pan", "Latn", } m["tuy"] = { "Tugen", 3541935, "sdv-nma", } m["tuz"] = { "Turka", 36643, "nic-gur", "Latn", } m["tva"] = { "Vaghua", 3553248, "poz-ocw", "Latn", } m["tvd"] = { "Tsuvadi", 3914936, "nic-kam", } m["tve"] = { "Te'un", 7690709, "poz-cet", "Latn", } m["tvk"] = { "Southeast Ambrym", 252411, "poz-vnc", "Latn", } m["tvl"] = { "Tuvaluan", 34055, "poz-pnp", "Latn", } m["tvm"] = { "Tela-Masbuar", 7695666, "poz-tim", } m["tvn"] = { "Tavoyan", 7689158, "tbq-brm", "Mymr", ancestors = "obr", } m["tvo"] = { "Tidore", 3528199, "paa-tti", "Latn, Arab", } m["tvs"] = { "Taveta", 15632387, "bnt-par", "Latn", } m["tvt"] = { "Tutsa Naga", 7856987, "sit-tno", } m["tvu"] = { "Tunen", 36632, "nic-mbw", } m["tvw"] = { "Sedoa", 7445362, "poz-kal", } m["tvx"] = { "Taivoan", 1975271, "map", "Latn", } m["tvy"] = { "Timor Pidgin", 4904029, "crp", ancestors = "pt", } m["twa"] = { "Twana", 7857412, "sal", "Latn", } m["twb"] = { "Western Tawbuid", 12953912, "phi", } m["twc"] = { "Teshenawa", 3436597, "phi", } m["twe"] = { "Teiwa", 3519302, "paa-alp", "Latn", } m["twf"] = { "Taos", 7684320, "nai-kta", "Latn", } m["twg"] = { "Tereweng", 12953200, "paa-alp", "Latn", } m["twh"] = { "Tai Dón", 7675751, "tai-swe", "Tavt", --translit = "Tavt-translit", sort_key = { from = {"[꪿ꫀ꫁ꫂ]", "([ꪵꪶꪹꪻꪼ])([ꪀ-ꪯ])"}, to = {"", "%2%1"} }, } m["twm"] = { "Tawang Monpa", 36586, "sit-ebo", "Tibt", override_translit = true, -- Tibt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["twn"] = { "Twendi", 7857682, "nic-mmb", } m["two"] = { "Tswapong", 3446241, "bnt-sts", } m["twp"] = { "Ere", 3056045, "poz-aay", "Latn", } m["twq"] = { "Tasawaq", 36564, "son", } m["twr"] = { "Southwestern Tarahumara", 12953909, "azc-trc", "Latn", } m["twt"] = { "Turiwára", 3542307, "tup-gua", "Latn", } m["twu"] = { "Termanu", 7702572, "poz-tim", "Latn", } m["tww"] = { "Tuwari", 7857159, "paa-wal", "Latn", } m["twy"] = { "Tawoyan", 3513542, "poz-bre", "Latn", } m["txa"] = { "Tombonuo", 7818692, "poz-san", "Latn", } m["txb"] = { "Tocharian B", 3199353, "ine-toc", "Latn", standard_chars = "AaÄäĀāCcEeIiKkLlMmṂṃNnṄṅÑñOoPpRrSsŚśṢṣTtUuWwYy" .. c.punc, } m["txc"] = { "Tsetsaut", 20829, "ath-nor", "Latn", } m["txe"] = { "Totoli", 7828387, "poz-tot", "Latn", } m["txg"] = { "Tangut", 2727930, "ero", "Tang", -- Tang translit in [[Module:scripts/data]] } m["txh"] = { "Thracian", 36793, "ine", "Latn, Polyt", -- Polyt translit, display_text, strip_diacritics, sort_key in [[Module:scripts/data]] } m["txi"] = { "Ikpeng", 9344891, "sai-pek", "Latn", } m["txj"] = { "Tarjumo", 24906088, "ssa-sah", "Latn, Arab", } m["txm"] = { "Tomini", 7818911, "poz", "Latn", } m["txn"] = { "West Tarangan", 3515594, "poz", "Latn", } m["txo"] = { "Toto", 36709, "sit-dhi", "Beng, Toto" } m["txq"] = { "Tii", 7801784, "poz-tim", } m["txr"] = { "Tartessian", 36795, "qfa-unc", -- extinct, no consensus on classification } m["txs"] = { "Tonsea", 3531659, "phi", "Latn", } m["txt"] = { "Citak", 3447279, "ngf-asm", "Latn", } m["txu"] = { "Kayapó", 3101212, "sai-nje", "Latn", } m["txx"] = { "Tatana", 18643518, "poz-san", "Latn", } m["tya"] = { "Tauya", 7688978, "ngf-rai", "Latn", } m["tye"] = { "Kyenga", 3913304, "dmn-bbu", "Latn", } m["tyh"] = { "O'du", 3347428, "mkh", } m["tyi"] = { "Teke-Tsaayi", 33123613, "bnt-nze", } m["tyj"] = { "Tai Do", 7675746, "tai-nor", -- Chamberlain (1991), but Pittayaporn (2009) suggests tai-swe "Latn, Tayo", -- Vietnam } m["tyl"] = { "Thu Lao", 12953921, "tai-cen", } m["tyn"] = { "Kombai", 6428241, "ngf-nde", "Latn", } m["typ"] = { "Kuku-Thaypan", 3915693, "aus-pmn", "Latn", } m["tyr"] = { "Tai Daeng", 3915207, "tai-swe", "Tavt", } m["tys"] = { "Sapa", 3446668, "tai-sap", "Latn", } m["tyt"] = { "Tày Tac", 7862029, "tai-swe", } m["tyu"] = { "Kua", 3832933, "khi-kal", "Latn", } m["tyv"] = { "Tuvan", 34119, "trk-ssb", "Cyrl", translit = "tyv-translit", override_translit = true, sort_key = "tyv-sortkey", } m["tyx"] = { "Teke-Tyee", 36634, "bnt-nze", "Latn", } m["tyz"] = { "Tày", -- This does not mean its family "Tai" languages. 2511476, "tai-tay", "Latn, Hani", sort_key = { Hani = "Hani-sortkey" }, } m["tza"] = { "Tanzanian Sign Language", 7684177, "sgn", } m["tzh"] = { "Tzeltal", 36808, "myn", "Latn", } m["tzj"] = { "Tz'utujil", 36941, "myn", "Latn", } m["tzl"] = { "Talossan", 1063911, "art", "Latn", type = "appendix-constructed", sort_key = "tzl-sortkey", } m["tzm"] = { "Central Atlas Tamazight", 49741, "ber", "Tfng, Arab, Latn", translit = { Tfng = "Tfng-translit", }, } m["tzn"] = { "Tugun", 12953225, "poz-tim", "Latn", } m["tzo"] = { "Tzotzil", 36809, "myn", "Latn", } m["tzx"] = { "Tabriak", 56872, "paa-lse", "Latn", } return require("Module:languages").finalizeData(m, "language") iv1un0e66t5lah4fo1uaq0ipxx9ulbl