Wiktionary tnwiktionary https://tn.wiktionary.org/wiki/Tsebe_ya_konokono MediaWiki 1.39.0-wmf.21 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 Gadget Gadget talk Gadget definition Gadget definition talk 0 2921 8243 8233 2022-07-21T16:12:04Z Rebel Agent 2678 /* Setswana */Added content wikitext text/x-wiki ==Setswana== * Setswana * Setswana ke teme ===Sekai=== * Ke bua Setswana * Setswana ke teme e e buiwang ko lefatsheng la [[Botswana]] ===Le buiwa jaana=== {{audio|en|en-uk-setswana.ogg|Lentswe}} {{wikipedia}} 515ptqblljery4i0no408bl0chy8kke 8256 8243 2022-07-21T17:55:34Z Rebel Agent 2678 /* Setswana */Added content wikitext text/x-wiki ==Setswana== * Setswana * Setswana ke teme ===Sekai=== * Ke bua Setswana * Setswana ke teme e e buiwang ko lefatsheng la [[Botswana]] ===Le buiwa jaana=== {{audio|en|en-uk-setswana.ogg|Lentswe}} {{wikipedia}} ==Sekgoa== on42abrh2e7zz1ng96kak2uroq5i1e7 8257 8256 2022-07-21T17:56:13Z Rebel Agent 2678 /* Setswana */Removed content wikitext text/x-wiki ==Setswana== * Setswana * Setswana ke teme ===Sekai=== * Ke bua Setswana * Setswana ke teme e e buiwang ko lefatsheng la [[Botswana]] ===Le buiwa jaana=== {{audio|en|en-uk-setswana.ogg|Lentswe}} ==Sekgoa== kn6rrwjb35hg4swgp3d4v0u14tcz4nz 8258 8257 2022-07-21T17:56:41Z Rebel Agent 2678 /* Sekgoa */Added content wikitext text/x-wiki ==Setswana== * Setswana * Setswana ke teme ===Sekai=== * Ke bua Setswana * Setswana ke teme e e buiwang ko lefatsheng la [[Botswana]] ===Le buiwa jaana=== {{audio|en|en-uk-setswana.ogg|Lentswe}} ==Sekgoa== {{wikipedia}} ae1h8trqumiil1yi6sxq3qherp2q7t0 8259 8258 2022-07-21T17:58:59Z Rebel Agent 2678 /* Sekgoa */Added content wikitext text/x-wiki ==Setswana== * Setswana * Setswana ke teme ===Sekai=== * Ke bua Setswana * Setswana ke teme e e buiwang ko lefatsheng la [[Botswana]] ===Le buiwa jaana=== {{audio|en|en-uk-setswana.ogg|Lentswe}} ==Sekgoa== {{wikipedia}} ===Etymology=== Borrowed from {{bor|en|tn|Setswana}}. ===Pronunciation=== * {{a|UK}} {{IPA|en|/sɛtˈswɑːnə/}} * {{a|US}} {{enPR|sĕt-swäʹnə}}, {{IPA|en|/sɛtˈswɑnə/}} * {{rhymes|en|ɑːnə|s=3}} * {{audio|en|en-uk-setswana.ogg|Audio (UK)}} {{rfap|en|US|US}} ===Proper noun=== {{en-proper noun}} # A language spoken widely in Southern Africa, mainly in [[Botswana]] and [[South Africa]] in the [[w:Northern Cape|Northern Cape]], the central and western [[w:Free State|Free State]] and in the [[w:North West (South African province)|North West province]], and also, to a lesser extent, in [[Namibia]], also known as [[Tswana]]. ====Synonyms==== * {{l|en|Tswana}} ====Translations==== {{trans-see|Tswana}} ====See also==== * {{l|en|Sekgalagadi}} * {{l|en|Shilozi}} * {{ethnologue|code=tsn}} ====References==== September 2000 UNESCO. World Languages Survey Report - Prepared by the Department of Arts, Culture, Science and Technology (South Africa). ===Anagrams=== * {{anagrams|en|a=aaensstw|seawants}} o891cmpezobml4959ddk8cg8bkawsjq 0 2935 8242 2022-07-21T16:09:36Z Rebel Agent 2678 Ke dirile tsebe wikitext text/x-wiki == Setswana == * Buka * Buka ke sedirisiwa se se dirisiwang go kwalelwa mafoko '''bontsi''' ke “dibuka" j8csach96ro74jq6ydhqacfz72prqyq 828 2936 8244 2022-07-21T16:15:45Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local export = {} local function track(page) require("Module:debug/track")("interproject/" .. page) return true end local function process_links(linkdata, prefix, name, wmlang, sc) prefix = prefix .. ":" .. (wmlang:getCode() == "en" and "" or wmlang:getCode() .. ":") local links = {} local iplinks = {} local m_links = require("Module:links") local lang = wmlang:getWiktionaryLanguage() local ipalt = name .. " " .. (wmlang:getCode() == "en" and "" or "^{" .. wmlang:getCode() .. "}") for i, link in ipairs(linkdata) do link.lang = lang link.sc = sc link.term = prefix .. link.term link.tr = "-" table.insert(iplinks, "<span class=\"interProject\">[[" .. link.term .. "|" .. ipalt .. "]]</span>") table.insert(links, m_links.full_link(link, "bold")) end return links, iplinks end function export.wikipedia_box(frame) local params = { [1] = {}, [2] = {}, ["cat"] = {}, ["category"] = {alias_of = "cat"}, ["i"] = {type = "boolean"}, ["lang"] = {default = "en"}, ["mul"] = {}, ["mullabel"] = {}, ["mulcat"] = {}, ["mulcatlabel"] = {}, ["portal"] = {}, ["sc"] = {}, } local args = require("Module:parameters").process(frame:getParent().args, params) if args.mul or args.mullabel or args.mulcat or args.mulcatlabel then track("wikipedia-box-mul") end local wmlang = require("Module:wikimedia languages").getByCodeWithFallback(args["lang"]) or error("The Wikimedia language code \"" .. args["lang"] .. "\" is not valid.") local sc = args["sc"] and require("Module:scripts").getByCode(args["sc"], "sc") or nil local linkdata = {} if args["cat"] then table.insert(linkdata, {term = "Category:" .. args["cat"], alt = args[1] or args["cat"]}) elseif args["portal"] then table.insert(linkdata, {term = "Portal:" .. args["portal"], alt = args[1] or args["portal"]}) else local term = args[1] or mw.title.getCurrentTitle().text table.insert(linkdata, {term = term, alt = args[2] or term}) end if args["mul"] or args["mulcat"] then if args["mulcat"] then table.insert(linkdata, {term = "Category:" .. args["mulcat"], alt = args["mulcatlabel"] or args["mulcat"]}) else table.insert(linkdata, {term = args["mul"], alt = args["mullabel"] or args["mul"]}) end end local links, iplinks = process_links(linkdata, "w", "Wikipedia", wmlang, sc) if frame.args["slim"] then return "<div class=\"sister-wikipedia sister-project noprint floatright\" style=\"border: solid #aaa 1px; font-size: 90%; background: #f9f9f9; width: 250px; padding: 4px; text-align: left;\">" .. "<div style=\"float: left;\">[[File:Wikipedia-logo.png|14px|none| ]]</div>" .. "<div style=\"margin-left: 15px;\">" .. " &nbsp;" .. table.concat(links, " and ") .. " on " .. (wmlang:getCode() == "en" and "" or wmlang:getCanonicalName() .. "&nbsp;") .. "Wikipedia" .. "</div>" .. "</div>" else local linktype if args["cat"] then linktype = "a category" elseif args["mul"] then linktype = "articles" elseif args["mulcat"] then linktype = "categories" elseif args["portal"] then linktype = "a portal" else linktype = "an article" end return "<div class=\"sister-wikipedia sister-project noprint floatright\" style=\"border: 1px solid #aaa; font-size: 90%; background: #f9f9f9; width: 250px; padding: 4px; text-align: left;\">" .. "<div style=\"float: left;\">[[File:Wikipedia-logo-v2.svg|44px|none|link=|alt=]]</div>" .. "<div style=\"margin-left: 60px;\">" .. wmlang:getCanonicalName() .. " [[Wikipedia]] has " .. linktype .. " on:" .. "<div style=\"margin-left: 10px;\">" .. table.concat(links, " and ") .. "</div>" .. "</div>" .. table.concat(iplinks) .. ((args[1] == mw.title.getCurrentTitle().text and not args[2]) and "[[Category:wikipedia with redundant first parameter]]" or "") .. "</div>" end end function export.projectlink(frame, compat) local m_params = require("Module:parameters") local iparams = { ["prefix"] = {required = true}, ["name"] = {required = true}, ["image"] = {required = true}, ["compat"] = {type = "boolean"}, } iargs = m_params.process(frame.args, iparams) compat = compat or iargs.compat local lang_param = compat and "lang" or 1 local term_param = compat and 1 or 2 local alt_param = compat and 2 or 3 local params = { [lang_param] = {}, [term_param] = {}, [alt_param] = {}, ["i"] = {type = "boolean"}, ["nodot"] = {}, ["sc"] = {}, } local args = m_params.process(frame:getParent().args, params) local wmlang = args[lang_param] or "en" wmlang = require("Module:wikimedia languages").getByCodeWithFallback(wmlang) or error("The Wikimedia language code \"" .. wmlang .. "\" is not valid.") local sc = args["sc"] and require("Module:scripts").getByCode(args["sc"], "sc") or nil local term = args[term_param] or mw.title.getCurrentTitle().text local linkdata = {term = term, alt = args[alt_param] or term} if args["i"] then linkdata.alt = "''" .. linkdata.alt .. "''" end local links, iplinks = process_links({linkdata}, iargs["prefix"], iargs["name"], wmlang, sc) return "[[Image:" .. iargs["image"] .. "|15px|link=" .. linkdata.term .. "]] " .. table.concat(links, " and ") .. " on " .. (wmlang:getCode() == "en" and "" or "the " .. wmlang:getCanonicalName() .. " ") .. " " .. iargs["name"] .. (args["nodot"] and "" or ".") .. table.concat(iplinks) end return export iqfi2fi38bam1z1ski9ljdunohbs1v9 828 2937 8245 2022-07-21T16:17:30Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local export = {} -- A helper function to escape magic characters in a string -- Magic characters: ^$()%.[]*+-? local plain = require("Module:string/pattern_escape") -- A helper function that removes empty numeric indexes in a table, -- so that the values are tightly packed like in a normal Lua table. -- equivalent to require("Module:table").compressSparseArray local function remove_holes(t) local ret = {} local index = 1 local highest = 0 for num, _ in pairs(t) do if type(num) == "number" and num > 0 and num < math.huge and math.floor(num) == num then highest = math.max(highest, num) end end for i = 1, highest do if t[i] then ret[index] = t[i] index = index + 1 end end return ret end function export.process(args, params, return_unknown) local args_new = {} -- Process parameters for specific properties local required = {} local patterns = {} local names_with_equal_sign = {} local list_from_index = nil for name, param in pairs(params) do if param.required then if param.alias_of then require("Module:debug/track")("parameters/required alias") end required[name] = true end if param.list then local key = name if type(name) == "string" then key = string.gsub(name, "=", "") end if param.default ~= nil then args_new[key] = {param.default, maxindex = 1} else args_new[key] = {maxindex = 0} end if type(param.list) == "string" then -- If the list property is a string, then it represents the name -- to be used as the prefix for list items. This is for use with lists -- where the first item is a numbered parameter and the -- subsequent ones are named, such as 1, pl2, pl3. if string.find(param.list, "=") then patterns["^" .. string.gsub(plain(param.list), "=", "(%%d+)") .. "$"] = name else patterns["^" .. plain(param.list) .. "(%d+)$"] = name end elseif type(name) == "number" then -- If the name is a number, then all indexed parameters from -- this number onwards go in the list. list_from_index = name else if string.find(name, "=") then patterns["^" .. string.gsub(plain(name), "=", "(%%d+)") .. "$"] = string.gsub(name, "=", "") else patterns["^" .. plain(name) .. "(%d+)$"] = name end end if string.find(name, "=") then -- DO NOT SIDE-EFFECT A TABLE WHILE ITERATING OVER IT. -- Some elements may be skipped or processed twice if you do. -- Instead, track the changes we want to make to `params`, and -- do them after the iteration over `params` is done. table.insert(names_with_equal_sign, name) end elseif param.default ~= nil then args_new[name] = param.default end end --Process required changes to `params` for _, name in ipairs(names_with_equal_sign) do require("Module:debug/track")("parameters/name with equals") params[string.gsub(name, "=", "")] = params[name] params[name] = nil end -- Process the arguments local args_unknown = {} for name, val in pairs(args) do local index = nil if type(name) == "number" then if list_from_index ~= nil and name >= list_from_index then index = name - list_from_index + 1 name = list_from_index end else -- Does this argument name match a pattern? for pattern, pname in pairs(patterns) do index = mw.ustring.match(name, pattern) -- It matches, so store the parameter name and the -- numeric index extracted from the argument name. if index then index = tonumber(index) name = pname break end end end local param = params[name] -- If a parameter without the trailing index was found, and -- require_index is set on the param, set the param to nil to treat it -- as if it isn't recognized. if not index and param and param.require_index then param = nil end -- If no index was found, use 1 as the default index. -- This makes list parameters like g, g2, g3 put g at index 1. index = index or 1 -- If the argument is not in the list of parameters, trigger an error. -- return_unknown suppresses the error, and stores it in a separate list instead. if not param then if return_unknown then args_unknown[name] = val else error("The parameter \"" .. name .. "\" is not used by this template.", 2) end else -- Remove leading and trailing whitespace unless allow_whitespace is true. if not param.allow_whitespace then val = mw.text.trim(val) end -- Empty string is equivalent to nil unless allow_empty is true. if val == "" and not param.allow_empty then val = nil end -- Convert to proper type if necessary. if param.type == "boolean" then val = not (not val or val == "" or val == "0" or val == "no" or val == "n" or val == "false") elseif param.type == "number" then val = tonumber(val) elseif param.type then require("Module:debug/track") { "parameters/unrecognized type", "parameters/unrecognized type/" .. tostring(param.type) } end -- Can't use "if val" alone, because val may be a boolean false. if val ~= nil then -- Mark it as no longer required, as it is present. required[param.alias_of or name] = nil -- Store the argument value. if param.list then -- If the parameter is an alias of another, store it as the original, -- but avoid overwriting it; the original takes precedence. if not param.alias_of then args_new[name][index] = val -- Store the highest index we find. args_new[name].maxindex = math.max(index, args_new[name].maxindex) elseif args[param.alias_of] == nil then if params[param.alias_of] and params[param.alias_of].list then args_new[param.alias_of][index] = val -- Store the highest index we find. args_new[param.alias_of].maxindex = math.max(index, args_new[param.alias_of].maxindex) else args_new[param.alias_of] = val end end else -- If the parameter is an alias of another, store it as the original, -- but avoid overwriting it; the original takes precedence. if not param.alias_of then args_new[name] = val elseif args[param.alias_of] == nil then if params[param.alias_of] and params[param.alias_of].list then args_new[param.alias_of][1] = val -- Store the highest index we find. args_new[param.alias_of].maxindex = math.max(1, args_new[param.alias_of].maxindex) else args_new[param.alias_of] = val end end end end end end -- The required table should now be empty. -- If any entry remains, trigger an error, unless we're in the template namespace. if mw.title.getCurrentTitle().nsText ~= "Template" then local list = {} for name, param in pairs(required) do table.insert(list, name) end local count = #list if count == 1 then error('The parameter "' .. list[1] .. '" is required.', 2) elseif count == 2 then error('The parameters "' .. table.concat(list, '" and "') .. '" are required.', 2) elseif count > 2 then error('The parameters "' .. mw.text.listToText(list, '", "', '", and "') .. '" are required.', 2) end end -- Remove holes in any list parameters if needed. for name, val in pairs(args_new) do if type(val) == "table" and not params[name].allow_holes then args_new[name] = remove_holes(val) end end if return_unknown then return args_new, args_unknown else return args_new end end return export 0nt3o8rxqgvpf7q9r5ol60nr1atmz12 828 2938 8246 2022-07-21T16:24:41Z Rebel Agent 2678 Ke dirile module Scribunto text/plain return function (str) return mw.ustring.gsub(str, "([%(%)%.%%%+%-%*%?%[%^%$%]])", "%%%1") end b97lzgihya1ilvmrqr6a3ng2jjomdnw 828 2939 8247 2022-07-21T16:29:00Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local export = {} local WikimediaLanguage = {} function WikimediaLanguage:getCode() return self._code end function WikimediaLanguage:getCanonicalName() return self._rawData.canonicalName end --function WikimediaLanguage:getAllNames() -- return self._rawData.names --end function WikimediaLanguage:getType() return "Wikimedia" end function WikimediaLanguage:getWiktionaryLanguage() if not self._wiktionaryLanguageObject then self._wiktionaryLanguageObject = require("Module:languages").getByCode(self._rawData.wiktionary_code) end return self._wiktionaryLanguageObject end -- Do NOT use this method! -- All uses should be pre-approved on the talk page! function WikimediaLanguage:getRawData() return self._rawData end WikimediaLanguage.__index = WikimediaLanguage function export.getByCode(code) -- Only accept codes the software recognises if not mw.language.isKnownLanguageTag(code) then return nil end local rawData = mw.loadData("Module:wikimedia languages/data")[code] -- If there is no specific Wikimedia code, then "borrow" the information -- from the general Wiktionary language code if not rawData then local lang = require("Module:languages").getByCode(code) if not lang then return nil end rawData = {canonicalName = lang:getCanonicalName(), wiktionary_code = code} elseif not rawData.canonicalName then rawData = {canonicalName = require("Module:languages").getByCode(rawData.wiktionary_code):getCanonicalName(), wiktionary_code = rawData.wiktionary_code} end return setmetatable({ _rawData = rawData, _code = code }, WikimediaLanguage) end function export.getByCodeWithFallback(code) local object = export.getByCode(code) if object then return object end local lang = require("Module:languages").getByCode(code) if not lang then return nil end return lang:getWikimediaLanguages()[1] end return export 8aqgh0h89a1ndi0gs8h7gojtvnwa8lb 828 2940 8248 2022-07-21T16:44:19Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local m = {} m["als"] = { wiktionary_code = "gsw", } m["bat-smg"] = { wiktionary_code = "sgs", } m["bs"] = { canonicalName = "Bosnian", wiktionary_code = "sh", } m["bxr"] = { wiktionary_code = "bua", } m["diq"] = { wiktionary_code = "zza", } m["eml"] = { canonicalName = "Emiliano-Romagnolo", wiktionary_code = "egl", } m["fiu-vro"] = { wiktionary_code = "vro", } m["hr"] = { canonicalName = "Croatian", wiktionary_code = "sh", } m["ksh"] = { wiktionary_code = "gmw-cfr", } m["ku"] = { canonicalName = "Kurdish", wiktionary_code = "kmr", } m["kv"] = { canonicalName = "Komi", wiktionary_code = "kpv", } m["mhr"] = { wiktionary_code = "chm", } m["nrm"] = { wiktionary_code = "nrf", } m["roa-rup"] = { wiktionary_code = "rup", } m["roa-tara"] = { wiktionary_code = "roa-tar", } m["simple"] = { canonicalName = "Simple English", wiktionary_code = "en", } m["sr"] = { canonicalName = "Serbian", wiktionary_code = "sh", } m["zh-classical"] = { wiktionary_code = "ltc", } m["zh-min-nan"] = { wiktionary_code = "nan", } m["zh-yue"] = { wiktionary_code = "yue", } return m 9iotoc6wxyrnnh9zao3h6hxl2p4qe6j 828 2941 8249 2022-07-21T16:47:28Z Rebel Agent 2678 Ke dirile module 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]] ]=] -- These are prefixed with u to avoid confusion with the default string methods -- of the same name. local usub = mw.ustring.sub local table_insert = table.insert local table_concat = table.concat local ignore_cap local phonetic_extraction local pos_tags local unsupported_titles function export.getLinkPage(target, lang) unsupported_titles = unsupported_titles or mw.loadData("Module:links/data").unsupported_titles if unsupported_titles[target] then return "Unsupported titles/" .. unsupported_titles[target] end -- If the link contains unexpanded template parameters, then don't create a link. if target:find("{{{") then return nil end if target:sub(1, 1) == ":" or target:sub(1, 2) == "w:" or target:sub(1, 10) == "wikipedia:" then return target end -- Remove diacritics from the page name target = lang:makeEntryName(target) if target:sub(1, 1) == "/" then return ":" .. target -- Link to appendix for reconstructed terms and terms in appendix-only languages elseif target:sub(1, 1) == "*" and #target > 1 then if lang:getCode() == "und" then return nil end target = "Reconstruction:" .. lang:getCanonicalName() .. "/" .. usub(target, 2) elseif lang:getType() == "reconstructed" then error("The specified language " .. lang:getCanonicalName() .. " is unattested, while the given word is not marked with '*' to indicate that it is reconstructed") elseif lang:getType() == "appendix-constructed" then target = "Appendix:" .. lang:getCanonicalName() .. "/" .. target end return target end -- Make a language-specific link from given link's parts local function makeLangLink(link, lang, id, allow_self_link) -- Temporary tracking code local langCode = lang:getCode() if langCode == "se" or langCode == "sia" or langCode:find("^sm[ajns]$") or langCode:find("^sj[dektu]$") then if link.display and link.display:find("'") then require("Module:debug/track")("links/Sami apostrophe display") elseif link.target and link.target:find("'") then require("Module:debug/track")("links/Sami apostrophe target") end end -- Find fragments (when link didn't come from parseLink). -- Prevents {{l|en|word#Etymology 2|word}} from linking to [[word#Etymology 2#English]]. if link.fragment == nil then -- Replace numeric character references with the corresponding character (&#29; → '), -- as they contain #, which causes the numeric character reference to be -- misparsed (wa'a → wa&#29;a → pagename wa&, fragment 29;a). link.target = link.target:gsub("&#(%d+);", function(number) return mw.ustring.char(tonumber(number)) end) local first, second = link.target:match("^([^#]+)#(.+)$") if first then link.target, link.fragment = first, second end end -- If there is no display form, then create a default one if not link.display then link.display = link.target -- Strip the prefix from the displayed form -- TODO: other interwiki links? if link.display:sub(1, 1) == ":" and not mw.loadData("Module:links/data").unsupported_titles[link.display] then link.display = link.display:sub(2) -- remove colon from beginning else local prefix = link.display:match("^([^:]+):") local prefixes = { w = true, wikipedia = true, } if prefixes[prefix] then link.display = link.display:sub(#prefix + 2) -- remove prefix plus colon end end end -- Process the target link.target = export.getLinkPage(link.target, lang) if not link.target then return link.display end -- If the target is the same as the current page and there is no sense id -- and linking to the same page hasn't been turned on, then return a "self-link" -- like the software does. if not (allow_self_link or id) and link.target:gsub("^:", "") == mw.title.getCurrentTitle().prefixedText then return "<strong class=\"selflink\">" .. link.display .. "</strong>" end --[[ Add fragment Do not add a section link to "Undetermined", as such sections do not exist and are invalid. TabbedLanguages handles links without a section by linking to the "last visited" section, but adding "Undetermined" would break that feature. For localized prefixes that make syntax error, please use the format: ["xyz"] = true, ]] local prefix = link.target:match("^:?([^:]+):") local prefixes = { w = true, wikipedia = true, Category = true, } if not prefixes[prefix] then if link.fragment or link.target:find("#$") then require("Module:debug/track") { "links/fragment", "links/fragment/" .. lang:getCode() } end if not link.fragment and lang:getCode() ~= "und" then if id then link.fragment = require("Module:senseid").anchor(lang, id) elseif not mw.ustring.find(link.target, "^Appendix:") and not mw.ustring.find(link.target, "^Reconstruction:") then link.fragment = lang:getCanonicalName() end end -- This allows linking to pages like [[sms:a]] without it being treated weirdly. link.target = link.target:gsub(":", "&#x3a;") end return "[[" .. link.target .. (link.fragment and "#" .. link.fragment or "") .. "|" .. link.display .. "]]" end -- Split a link into its parts local function parseLink(linktext) local link = { target = linktext } local first, second = link.target:match("^([^|]+)|(.+)$") if first then link.target = first link.display = second else link.display = link.target end first, second = link.target:match("^(.+)#(.+)$") if first then link.target = first link.fragment = second else -- So that makeLangLink does not look for a fragment again link.fragment = false end return link end -- Creates a basic wikilink to the given term. If the text already contains -- links, these are replaced with links to the correct section. function export.language_link(data, allow_self_link) 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.") end local text = data.term ignore_cap = ignore_cap or mw.loadData("Module:links/data").ignore_cap if ignore_cap[data.lang:getCode()] and text then text = text:gsub("%^", "") end -- If the text begins with * and another character, -- then act as if each link begins with * local allReconstructed = false if text:find("^*.") then allReconstructed = true end -- Do we have embedded wikilinks? if text:find("[[", nil, true) then --[=[ [[Special:WhatLinksHere/Template:tracking/links/alt-ignored]] [[Special:WhatLinksHere/Template:tracking/links/id-ignored]] ]=] if data.alt then require("Module:debug/track")("links/alt-ignored") mw.log("(from Module:links)", "text with embedded wikilinks:", text, "ignored alt:", data.alt, "lang:", data.lang:getCode()) end if data.id then require("Module:debug/track")("links/id-ignored") mw.log("(from Module:links)", "text with embedded wikilinks:", text, "ignored id:", data.id, "lang:", data.lang:getCode()) end -- Begins and ends with a wikilink tag if text:find("^%[%[(.+)%]%]$") then -- There are no [ ] in between. -- This makes the wikilink tag redundant. if text:find("^%[%[[^%[%]]+%]%]$") then require("Module:debug/track")("links/redundant wikilink") else local temp = text:gsub("^%[%[(.+)%]%]$", "%1") temp = temp:gsub("%]%], %[%[", "|") if not temp:find("[%[%]]") then require("Module:debug/track")("links/list") end end end text = text:gsub("%[%[([^%]]+)%]%]", function(linktext) local link = parseLink(linktext) if allReconstructed then link.target = "*" .. link.target end return makeLangLink(link, data.lang, data.id, allow_self_link) end) -- Remove the extra * at the beginning if it's immediately followed -- by a link whose display begins with * too if allReconstructed then text = text:gsub("^%*%[%[([^|%]]+)|%*", "[[%1|*") end else -- There is no embedded wikilink, make a link using the parameters. text = makeLangLink({ target = text, display = data.alt }, data.lang, data.id, allow_self_link) end return text end function export.mark(text, itemType, face, lang) local tag = { "", "" } if itemType == "gloss" then tag = { '<span class="mention-gloss-double-quote">“</span><span class="mention-gloss">', '</span><span class="mention-gloss-double-quote">”</span>' } elseif itemType == "tr" then if face == "term" then tag = { '<span lang="' .. lang:getCode() .. '" class="tr mention-tr Latn">', '</span>' } else tag = { '<span lang="' .. lang:getCode() .. '" class="tr Latn">', '</span>' } end elseif itemType == "ts" then tag = { '<span class="ts mention-ts Latn">/', '/</span>' } elseif itemType == "pos" then tag = { '<span class="ann-pos">', '</span>' } elseif itemType == "annotations" then tag = { '<span class="mention-gloss-paren annotation-paren">(</span>', '<span class="mention-gloss-paren annotation-paren">)</span>' } end if type(text) == "string" then return tag[1] .. text .. tag[2] else return "" end end -- Format the annotations (things following the linked term) function export.format_link_annotations(data, face) local output = {} -- Interwiki link if data.interwiki then table_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 m_gen = require("Module:gender and number") table_insert(output, "&nbsp;" .. m_gen.format_list(data.genders, data.lang)) end local annotations = {} -- Transliteration and transcription if data.tr or data.ts then local kind if face == "term" then kind = face else kind = "default" end if data.tr and data.ts then table_insert(annotations, require("Module:script utilities").tag_translit(data.tr, data.lang, kind) .. " " .. export.mark(data.ts, "ts")) elseif data.ts then table_insert(annotations, export.mark(data.ts, "ts")) else table_insert(annotations, require("Module:script utilities").tag_translit(data.tr, data.lang, kind)) end end -- Gloss/translation if data.gloss then table_insert(annotations, export.mark(data.gloss, "gloss")) end -- Part of speech if data.pos then -- debug category for pos= containing transcriptions if data.pos:find("/[^><]*/") then data.pos = data.pos .. "[[Category:links likely containing transcriptions in pos]]" end pos_tags = pos_tags or mw.loadData("Module:links/data").pos_tags table_insert(annotations, export.mark(pos_tags[data.pos] or data.pos, "pos")) end -- Literal/sum-of-parts meaning if data.lit then table_insert(annotations, "literally " .. export.mark(data.lit, "gloss")) end if #annotations > 0 then table_insert(output, " " .. export.mark(table_concat(annotations, ", "), "annotations")) end return table_concat(output) end -- A version of {{l}} or {{m}} that can be called from other modules too function export.full_link(data, face, allow_self_link, no_check_redundant_translit) 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.") end -- Create the link local output = {} local categories = {} local link = "" local annotations phonetic_extraction = phonetic_extraction or mw.loadData("Module:links/data").phonetic_extraction -- Is there any text to show? if (data.term or data.alt) then -- Try to detect the script if it was not provided if not data.sc then data.sc = require("Module:scripts").findBestScript(data.alt or data.term, data.lang) else -- Track uses of sc parameter local best = require("Module:scripts").findBestScript(data.alt or data.term, data.lang) require("Module:debug/track")("links/sc") if data.sc:getCode() == best:getCode() then require("Module:debug/track")("links/sc/redundant") require("Module:debug/track")("links/sc/redundant/" .. data.sc:getCode()) else require("Module:debug/track")("links/sc/needed") require("Module:debug/track")("links/sc/needed/" .. data.sc:getCode()) end end local class = "" local function encode_accel_param_chars(param) local retval = param:gsub("%%", "."):gsub(" ", "_") -- discard second return v laue return retval 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, v 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 = table.concat(filled_params, "*~!") end -- This is decoded again by [[WT:ACCEL]]. return prefix .. encode_accel_param_chars(param) end if data.accel then local form = data.accel.form and encode_accel_param_chars(data.accel.form) .. "-form-of" or "" local gender = encode_accel_param("gender-", data.accel.gender) local pos = encode_accel_param("pos-", data.accel.pos) local translit = encode_accel_param("transliteration-", data.accel.translit or (data.tr ~= "-" and data.tr or nil)) local target = encode_accel_param("target-", data.accel.target) local lemma = encode_accel_param("origin-", data.accel.lemma) local lemma_translit = encode_accel_param("origin_transliteration-", data.accel.lemma_translit) local no_store = data.accel.no_store and "form-of-nostore" or "" local accel = form .. " " .. gender .. " " .. pos .. " " .. translit .. " " .. target .. " " .. lemma .. " " .. lemma_translit .. " " .. no_store .. " " class = "form-of lang-" .. data.lang:getCode() .. " " .. accel end -- Only make a link if the term has been given, otherwise just show the alt text without a link link = require("Module:script utilities").tag_text( data.term and export.language_link(data, allow_self_link) or data.alt, data.lang, data.sc, face, class) else --[[ No term to show. Is there at least a transliteration we can work from? ]] link = require("Module:script utilities").request_script(data.lang, data.sc) if link == "" or not data.tr or data.tr == "-" then -- No link to show, and no transliteration either. Show a term request. local category = "" if mw.title.getCurrentTitle().nsText ~= "Template" then table_insert(categories, "[[Category:" .. data.lang:getCanonicalName() .. " term requests]]") end link = "<small>[Term?]</small>" end end table_insert(output, link) if data.tr == "" or data.tr == "-" then data.tr = nil elseif phonetic_extraction[data.lang:getCode()] then local m_phonetic = require(phonetic_extraction[data.lang:getCode()]) data.tr = data.tr or m_phonetic.getTranslit(export.remove_links(data.term)) elseif (data.term or data.alt) and not data.sc:getCode():find("Lati?n") then -- Try to generate a transliteration, unless transliteration has been supplied and either -- no_check_redundant_translit is given or we are in a high-memory entry. (Checking for redundant -- transliteration can use up significant amounts of memory so we don't want to do it if memory -- is tight. `no_check_redundant_translit` is currently set when called ultimately from -- {{multitrans|...|no-check-redundant-translit=1}}.) if not (data.tr and ( no_check_redundant_translit or mw.loadData("Module:links/data").high_memory_entries[mw.title.getCurrentTitle().text] )) then local automated_tr = data.lang:transliterate(export.remove_links(data.alt or data.term), data.sc) if automated_tr then local manual_tr = data.tr if manual_tr then if manual_tr == automated_tr then table_insert(categories, "[[Category:Terms with redundant transliterations]]" .. "[[Category:Terms with redundant transliterations/" .. data.lang:getCode() .. "]]") else -- Prevents Arabic root categories from flooding the tracking categories. if mw.title.getCurrentTitle().nsText ~= "Category" then table_insert(categories, "[[Category:Terms with manual transliterations different from the automated ones]]" .. "[[Category:Terms with manual transliterations different from the automated ones/" .. data.lang:getCode() .. "]]") end end end if (not manual_tr) or data.lang:overrideManualTranslit() then data.tr = automated_tr end end end end -- Link to the transliteration entry for languages that require this if data.tr and data.lang:link_tr() then data.tr = export.language_link { lang = data.lang, term = data.tr } end table_insert(output, export.format_link_annotations(data, face)) return table_concat(output) .. table_concat(categories) end --[[ Strips links: deletes category links, the targets of piped links, and all double square brackets. ]] function export.remove_links(text) if type(text) == "table" then text = text.args[1] end if not text or text == "" then return "" end text = mw.ustring.gsub(text, "%[%[Category:[^|%]]-|?[^|%]]-%]%]", "") text = text:gsub("%[%[[^|%]]-|", "") text = text:gsub("%[%[", "") text = text:gsub("%]%]", "") return text end function export.english_links(text) local lang = require("Module:languages").getByCode("en") -- Parentheses around function call to remove second return value, the -- number of replacements. return (text:gsub("%[%[([^%]]+)%]%]", function(linktext) local link = parseLink(linktext) return makeLangLink(link, lang, nil, true, false) end)) end --[=[ This decodes old section encodings. For example, Norwegian_Bokm.C3.A5l → Norwegian_Bokmål. It isn't picky about whether the section encodings represent the UTF-8 encoding of a real Unicode character, so it will mangle section names that contain a period followed by two uppercase hex characters. At least such section names are probably pretty rare. Wiktionary adds an additional id="" attribute for sections using a legacy encoding, if it is different from the modern minimally modified attribute. It is like percent encoding (URI or URL encoding) except with "." instead of "%". See [[mw:Manual:$wgFragmentMode]] and the code that does the encoding at https://gerrit.wikimedia.org/r/plugins/gitiles/mediawiki/core/+/7bf779524ab1fd8e1d74f79ea4840564d48eea4d/includes/parser/Sanitizer.php#893 ]=] -- The character class %x should not be used, as it includes the characters a-f, -- which do not occur in these anchor encodings. local capitalHex = "[0-9A-F]" local function decodeAnchor(anchor) return (anchor:gsub("%.(" .. capitalHex .. capitalHex .. ")", function(hexByte) return string.char(tonumber(hexByte, 16)) end)) 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.") end link = link:gsub("_", " ") local numberSigns = select(2, mw.ustring.gsub(link, "#", "")) if numberSigns > 1 then error("The section link should only contain one number sign (#).") end link = mw.uri.decode(link, "WIKI") local page, section = link:match("^([^#]*)#(.+)$") if page == "" then page = nil end if section then section = decodeAnchor(section) -- URI-encode (percent-encode) section to allow square brackets and -- other dodgy characters in section name. -- If not percent-encoded, they prevent the parser from creating a link. -- Decode percent-encoding in the displayed text if page then return "[[" .. page .. "#" .. mw.uri.encode(section, "WIKI") .. "|" .. page .. " §&nbsp;" .. section .. "]]" else return "[[#" .. mw.uri.encode(section, "WIKI") .. "|§&nbsp;" .. section .. "]]" end else error("The function “section_link” could not find a number sign marking a section name.") end end return export qlkvbve4fbcj7vwfswne2sccn4a95uq 828 2942 8250 2022-07-21T16:49:47Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local data = {} data.ignore_cap = { ["ko"] = true, } data.phonetic_extraction = { ["th"] = "Module:th", ["km"] = "Module:km", } data.pos_tags = { ["a"] = "adjective", ["adv"] = "adverb", ["int"] = "interjection", ["n"] = "noun", ["pron"] = "pronoun", ["v"] = "verb", ["vi"] = "intransitive verb", ["vt"] = "transitive verb", ["vti"] = "transitive and intransitive verb", } data.high_memory_entries = { "a", "animal", "book", "coffee", "do", "e", "language", "night", "o", "smoke", "son", "sun", "water", "wind", } local U = mw.ustring.char local soft_hyphen = U(0xAD) --[[ The "actual title" is the page name with the prefix "Unsupported titles/" removed. ["displayed_title"] = "actual title" ]] data.unsupported_titles = { [" "] = "Space", ["{"] = "Left curly bracket", ["}"] = "Right curly bracket", ["["] = "Left square bracket", ["]"] = "Right square bracket", ["<"] = "Less than", [">"] = "Greater than", ["=<"] = "Equal less than", ["=>"] = "Equal greater than", [">="] = "Greater than equal", ["<="] = "Less than equal", ["->"] = "Hyphen greater than", ["<-"] = "Less than hyphen", [">_<"] = "Greater than low line less than", ["::"] = "Double colon", [": :"] = "Enclosing colons", [":/"] = "Colon slash", [":="] = "Colon equals", [":Þ"] = "Colon capital thorn", [":þ"] = "Colon lowercase thorn", [":("] = "Colon left paren", [":)"] = "Colon right paren", [":3"] = "Colon three", ["<>"] = "Less than greater than", ["<3"] = "Less than three", ["</3"] = "Less than slash three", ["< >"] = "Enclosing less than greater than", ["< />"] = "Less than trailing slash greater than", ["< > </ >"] = "HTML start tag end tag", ["<!-- -->"] = "HTML comment", ["<g>"] = "g tag", [":-("] = "Colon hyphen left paren", [":-)"] = "Colon hyphen right paren", ["|"] = "Vertical line", ["||"] = "Vertical line vertical line", ["| |"] = "Enclosing vertical lines", ["C#"] = "C sharp", ["#"] = "Number sign", ["# #"] = "Enclosing number signs", ["&amp;"] = "Amp", [":"] = "Colon", [".."] = "Double period", ["."] = "Full stop", ["_"] = "Low line", ["-_-"] = "Low line interfix", [U(0xFFFD)] = "Replacement character", [U(0x1680)] = "Ogham space", ["[ ]"] = "Square brackets", ["{ }"] = "Curly brackets", ["[…]"] = "Square bracketed ellipsis", ["_ _"] = "Enclosing low lines", ["C|N>K"] = "C through N to K", ["#MeToo"] = "MeToo", ["о/."] = "о slash dot", ["กรุงเทพมหานคร อมรรัตนโกสินทร์ มหินทรายุธยา มหาดิลกภพ นพรัตนราชธานีบูรีรมย์ อุดมราชนิเวศน์มหาสถาน อมรพิมานอวตารสถิต สักกะทัตติยวิษณุกรรมประสิทธิ์"] = "Thai name of Bangkok", ["λοπαδοτεμαχοσελαχογαλεοκρανιολειψανοδριμυποτριμματοσιλφιοκαραβομελιτοκατακεχυμενοκιχλ" .. soft_hyphen .. "επικοσσυφοφαττοπεριστεραλεκτρυονοπτοκεφαλλιοκιγκλοπελειολαγῳοσιραιοβαφητραγανοπτερύγων"] = "Ancient Greek dish", [":≠"] = ":≠", ["S:t"] = "S:t", ["S:ta"] = "S:ta", ["c:a"] = "c:a", ["eq #"] = "eq number sign", ["hr #"] = "hr number sign", ["n:a"] = "n:a", ["n:o"] = "n:o", ["n:r"] = "n:r", ["s:a"] = "s:a", ["st:a"] = "st:a", ["v:a"] = "v:a", } for i, item in ipairs(data.high_memory_entries) do data.high_memory_entries[i] = nil data.high_memory_entries[item] = true end return data g64o5nvanq972b581i1wf6a1ntbxmt4 828 2943 8251 2022-07-21T16:52:46Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local export = {} local Script = {} function Script:getCode() return self._code end function Script:getCanonicalName() return self._rawData.canonicalName end function Script:getDisplayForm() return self:getCategoryName("nocap") end function Script:getOtherNames(onlyOtherNames) return require("Module:language-like").getOtherNames(self, onlyOtherNames) end function Script:getAliases() return self._rawData.aliases or {} end function Script:getVarieties(flatten) return require("Module:language-like").getVarieties(self, flatten) end function Script:getParent() return self._rawData.parent end function Script:getSystems() if not self._systemObjects then local m_systems = require("Module:writing systems") self._systemObjects = {} for _, sys in ipairs(self._rawData.systems or {}) do table.insert(self._systemObjects, m_systems.getByCode(sys)) end end return self._systemObjects end --function Script:getAllNames() -- return self._rawData.names --end function Script:getType() return "script" end function Script:getCategoryName(nocap) local name = self._rawData.canonicalName -- If the name already has "code" or "semaphore" in it, don't add it. -- No names contain "script". if not name:find("[Cc]ode$") and not name:find("[Ss]emaphore$") then name = name .. " script" end if not nocap then name = mw.getContentLanguage():ucfirst(name) end return name end function Script:makeCategoryLink() return "[[:Category:" .. self:getCategoryName() .. "|" .. self:getDisplayForm() .. "]]" end function Script:getWikipediaArticle() return self._rawData.wikipedia_article or self:getCategoryName() end function Script:getCharacters() if self._rawData.characters then return self._rawData.characters else return nil end end function Script:countCharacters(text) if not self._rawData.characters then return 0 else local _, num = mw.ustring.gsub(text, "[" .. self._rawData.characters .. "]", "") return num end end function Script:getDirection() local direction = self._rawData.direction if not direction then return nil else return direction end end function Script:getRawData() return self._rawData end function Script:toJSON() local ret = { canonicalName = self:getCanonicalName(), categoryName = self:getCategoryName("nocap"), code = self._code, otherNames = self:getOtherNames(true), aliases = self:getAliases(), varieties = self:getVarieties(), type = self:getType(), direction = self:getDirection(), characters = self:getCharacters(), parent = self:getParent(), systems = self._rawData.systems or {}, wikipediaArticle = self._rawData.wikipedia_article, } return require("Module:JSON").toJSON(ret) end Script.__index = Script function export.makeObject(code, data) return data and setmetatable({ _rawData = data, _code = code }, Script) or nil end function export.getByCode(code, paramForError, disallowNil) if code == nil and not disallowNil then return nil end if code == "IPAchar" then require("Module:debug/track")("IPAchar") end local retval = export.makeObject(code, mw.loadData("Module:scripts/data")[code]) if not retval and paramForError then require("Module:languages").err(code, paramForError, "script code", nil, "not real lang") end return retval end function export.getByCanonicalName(name) local code = mw.loadData("Module:scripts/by name")[name] if not code then return nil end return export.makeObject(code, mw.loadData("Module:scripts/data")[code]) end -- Find the best script to use, based on the characters of a string. -- If forceDetect is set, run the detection algorithm even if there's only one -- possible script; in that case, if the text isn't in the script, the return -- value will be None. function export.findBestScript(text, lang, forceDetect) if not text or not lang or not lang.getScripts then return export.getByCode("None") end local scripts = lang:getScripts() if not scripts[2] and not forceDetect then return scripts[1] end return require("Module:scripts/findBestScript")(export, text, lang, scripts, forceDetect) end --[=[ Takes a codepoint or a character and finds the script code (if any) that is 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]]. Converts the character to a codepoint. Returns a 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, else returns "None". ]=] function export.charToScript(char) return require("Module:scripts/charToScript").charToScript(char) end function export.findBestScriptWithoutLang(text) return require("Module:scripts/charToScript").findBestScriptWithoutLang(text) end return export 2hz8vrw8h1kwohcji8xdwyxty49ftzr 828 2944 8252 2022-07-21T16:55:19Z Rebel Agent 2678 Ke dirile module Scribunto text/plain --[=[ When adding new scripts to this file, please don't forget to add style definitons for the script in [[MediaWiki:Common.css]]. ]=] local u = mw.ustring.char local m = {} m["Adlm"] = { canonicalName = "Adlam", characters = "𞤀-𞥟", direction = "rtl", } m["Afak"] = { canonicalName = "Afaka", } m["Aghb"] = { canonicalName = "Caucasian Albanian", characters = "𐔰-𐕣𐕯", } m["Ahom"] = { canonicalName = "Ahom", characters = "𑜀-𑝆", systems = {"abugida"}, } m["Arab"] = { canonicalName = "Arabic", varieties = {"Jawi", {"Nastaliq", "Nastaleeq"}}, characters = "؀-ۿݐ-ݿࢠ-ࣿﭐ-﷽ﹰ-ﻼ", direction = "rtl", systems = {"abjad"}, -- more precisely, impure abjad } m["fa-Arab"] = { canonicalName = "Arabic", otherNames = {"Perso-Arabic"}, characters = m["Arab"].characters, direction = "rtl", parent = "Arab", } m["kk-Arab"] = { canonicalName = "Arabic", characters = m["Arab"].characters, direction = "rtl", parent = "Arab", } m["ks-Arab"] = { canonicalName = "Arabic", characters = m["Arab"].characters, direction = "rtl", parent = "Arab", } m["ku-Arab"] = { canonicalName = "Arabic", characters = m["Arab"].characters, direction = "rtl", parent = "Arab", } m["ms-Arab"] = { canonicalName = "Arabic", characters = m["Arab"].characters, direction = "rtl", parent = "Arab", } m["mzn-Arab"] = { canonicalName = "Arabic", characters = m["Arab"].characters, direction = "rtl", parent = "Arab", } m["ota-Arab"] = { canonicalName = "Arabic", characters = m["Arab"].characters, direction = "rtl", parent = "Arab", } m["pa-Arab"] = { canonicalName = "Shahmukhi", otherNames = {"Arabic"}, characters = m["Arab"].characters, direction = "rtl", parent = "Arab", } m["ps-Arab"] = { canonicalName = "Arabic", characters = m["Arab"].characters, direction = "rtl", parent = "Arab", } m["sd-Arab"] = { canonicalName = "Arabic", characters = m["Arab"].characters, direction = "rtl", parent = "Arab", } m["tt-Arab"] = { canonicalName = "Arabic", characters = m["Arab"].characters, direction = "rtl", parent = "Arab", } m["ug-Arab"] = { canonicalName = "Arabic", characters = m["Arab"].characters, direction = "rtl", parent = "Arab", } m["ur-Arab"] = { canonicalName = "Arabic", characters = m["Arab"].characters, direction = "rtl", parent = "Arab", } m["xka-Arab"] = { canonicalName = "Arabic", characters = m["Arab"].characters, direction = "rtl", parent = "Arab", } -- Aran (Nastaliq) is subsumed into Arab m["Armi"] = { canonicalName = "Imperial Aramaic", characters = "𐡀-𐡟", direction = "rtl", systems = {"abjad"}, } m["Armn"] = { canonicalName = "Armenian", characters = "Ա-֏ﬓ-ﬗ", } m["Avst"] = { canonicalName = "Avestan", characters = "𐬀-𐬿", direction = "rtl", } m["pal-Avst"] = { canonicalName = "Pazend", characters = m["Avst"].characters, direction = "rtl", parent = "Avst", } m["Bali"] = { canonicalName = "Balinese", characters = "ᬀ-᭼", systems = {"abugida"}, } m["Bamu"] = { canonicalName = "Bamum", characters = "ꚠ-꛷𖠀-𖨸", } m["Bass"] = { canonicalName = "Bassa", aliases = {"Bassa Vah", "Vah"}, characters = "𖫐-𖫵", } m["Batk"] = { canonicalName = "Batak", characters = "ᯀ-᯿", systems = {"abugida"}, } m["Beng"] = { canonicalName = "Bengali", characters = "ঀ-ঃঅ-ঌএঐও-নপ-রললশ-হ়-ৄেৈো-ৎৗড়ঢ়য়়ৠ-ৣ০-৯", systems = {"abugida"}, } m["as-Beng"] = { canonicalName = "Assamese", otherNames = {"Bengali-Assamese", "Eastern Nagari"}, characters = "ঁ-ঃঅ-ঌএঐও-নপ-যশ-হ়-ৄেৈো-ৎৗড়ঢ়য়়ৠ-ৣ০-ৱ", systems = {"abugida"}, } m["Bhks"] = { canonicalName = "Bhaiksuki", characters = "𑰀-𑱬", systems = {"abugida"}, } m["Bopo"] = { canonicalName = "Zhuyin", aliases = {"Zhuyin Fuhao", "Bopomofo"}, characters = "ㄅ-ㄯㆠ-ㆿ", } m["Brah"] = { canonicalName = "Brahmi", characters = "𑀀-𑁿", systems = {"abugida"}, } m["Brai"] = { canonicalName = "Braille", characters = "⠀-⣿", } m["Bugi"] = { canonicalName = "Buginese", aliases = {"Lontara"}, characters = "ᨀ-᨟", systems = {"abugida"}, } m["Buhd"] = { canonicalName = "Buhid", characters = "ᝀ-ᝓ", systems = {"abugida"}, } m["Cakm"] = { canonicalName = "Chakma", characters = "𑄀-𑅇", systems = {"abugida"}, } m["Cans"] = { canonicalName = "Canadian syllabics", characters = "᐀-ᙿᢰ-ᣵ", systems = {"abugida"}, } m["Cari"] = { canonicalName = "Carian", characters = "𐊠-𐋐", systems = {"alphabet"}, } m["Cham"] = { canonicalName = "Cham", characters = "ꨀ-꩟", systems = {"abugida"}, } m["Chrs"] = { canonicalName = "Chorasmian", characters = "𐾰-𐿋", direction = "rtl", systems = {"abjad"}, } m["Cher"] = { canonicalName = "Cherokee", characters = "Ꭰ-ᏽꭰ-ꮿ", systems = {"syllabary"}, } m["Copt"] = { canonicalName = "Coptic", characters = "Ϣ-ϯⲀ-⳿𐋠-𐋻", -- this is mostly "Coptic", not unified "Greek and Coptic" systems = {"alphabet"}, } m["Cpmn"] = { canonicalName = "Cypro-Minoan", aliases = {"Cypro Minoan"}, characters = "𒾐-𒿲", systems = {"syllabary"}, } m["Cprt"] = { canonicalName = "Cypriot", characters = "𐠀-𐠿", direction = "rtl", systems = {"syllabary"}, } m["Cyrl"] = { canonicalName = "Cyrillic", characters = "Ѐ-џѢѣѪѫѬѭѲѳѴѵҊ-ԧꚀ-ꚗ", systems = {"alphabet"}, } m["Cyrs"] = { canonicalName = "Old Cyrillic", aliases = {"Early Cyrillic"}, characters = "Ѐ-ԧꙀ-ꚗ", wikipedia_article = "Early Cyrillic alphabet", systems = {"alphabet"}, } m["Deva"] = { canonicalName = "Devanagari", characters = "ऀ-ॿ꣠-ꣿ", systems = {"abugida"}, } m["Diak"] = { canonicalName = "Dhives Akuru", characters = "𑤀-𑥙", systems = {"abugida"}, } m["Dogr"] = { canonicalName = "Dogra", characters = "𑠀-𑠻", systems = {"abugida"}, } m["Dsrt"] = { canonicalName = "Deseret", characters = "𐐀-𐑏", systems = {"alphabet"}, } m["Dupl"] = { canonicalName = "Duployan", characters = "𛰀-𛲟", } m["Egyd"] = { canonicalName = "Demotic", systems = {"abjad", "logography"}, } m["Egyh"] = { canonicalName = "Hieratic", systems = {"abjad", "logography"}, } m["Egyp"] = { canonicalName = "Egyptian hieroglyphic", varieties = {"Hieratic"}, characters = "𓀀-𓐮"..u(0x13430).."-"..u(0x13438), wikipedia_article = "Egyptian hieroglyphs", systems = {"abjad", "logography"}, } m["Elba"] = { canonicalName = "Elbasan", characters = "𐔀-𐔧", systems = {"alphabet"}, } m["Ethi"] = { canonicalName = "Ethiopic", aliases = {"Ge'ez"}, characters = "ሀ-᎙ⶀ-ⷞꬁ-ꬮ", systems = {"abugida"}, } m["Geok"] = { canonicalName = "Khutsuri", varieties = {"Nuskhuri", "Asomtavruli"}, characters = "Ⴀ-Ⴭⴀ-ⴭ", -- Ⴀ-Ⴭ is Asomtavruli, ⴀ-ⴭ is Nuskhuri systems = {"alphabet"}, } m["Geor"] = { canonicalName = "Georgian", varieties = {"Mkhedruli", "Mtavruli"}, characters = "ა-ჿᲐ-Ჿ", -- ა-ჿ is lowercase Mkhedruli; Ა-Ჿ is uppercase Mkhedruli (Mtavruli) systems = {"alphabet"}, } m["Glag"] = { canonicalName = "Glagolitic", characters = "Ⰰ-ⱞ𞀀-𞀪", systems = {"alphabet"}, } m["Gong"] = { canonicalName = "Gunjala Gondi", characters = "𑵠-𑶩", systems = {"abugida"}, } m["Gonm"] = { canonicalName = "Masaram Gondi", characters = "𑴀-𑵙", systems = {"abugida"}, } m["Goth"] = { canonicalName = "Gothic", characters = "𐌰-𐍊", systems = {"alphabet"}, } m["Gran"] = { canonicalName = "Grantha", characters = "𑌀-𑍴", systems = {"abugida"}, } m["Grek"] = { canonicalName = "Greek", characters = "Ͱ-ϡϰ-Ͽ", systems = {"alphabet"}, } m["polytonic"] = { canonicalName = "Greek", characters = "ἀ-῾" .. m["Grek"].characters, parent = "Grek", systems = {"alphabet"}, } m["Gujr"] = { canonicalName = "Gujarati", characters = "ઁ-૿", systems = {"abugida"}, } m["Guru"] = { canonicalName = "Gurmukhi", characters = "ਁ-੶", systems = {"abugida"}, } m["Hang"] = { canonicalName = "Hangul", aliases = {"Hangeul"}, characters = ( "가-힣".. -- Syllables "ᄀ-ᇿ".. -- Jamo "ꥠ-ꥼ".. -- Jamo Ext-A "ힰ-ퟻ".. -- Jamo Ext-B "ㄱ-ㆎ".. -- Compat Jamo "ﾠ-ￜ" -- Halfwidth ), systems = {"syllabary"}, } m["Hani"] = { canonicalName = "Han", varieties = {"Hanzi", "Kanji", "Hanja", "Chu Nom"}, characters = ( "一-鿿".. "㐀-䶿".. -- ExtA "𠀀-𮯯".. -- SIP "𰀀-𱍏".. -- ExtG "﨎﨏﨑﨓﨔﨟﨡﨣﨤﨧﨨﨩".. "⺀-⻿".. -- Radicals Supplement "　-〿".. -- CJK Symbols and Punctuation "𖿢𖿣𖿰𖿱".. -- Ideographic Symbols and Punctuation "㇀-㇯".. -- Strokes "㍻-㍿㋿" -- 組文字 ), systems = {"logography"}, } m["Hans"] = { canonicalName = "Simplified Han", characters = m["Hani"].characters, systems = {"logography"}, } m["Hant"] = { canonicalName = "Traditional Han", characters = m["Hani"].characters, systems = {"logography"}, } m["Hatr"] = { canonicalName = "Hatran", characters = "𐣠-𐣿", direction = "rtl", systems = {"abjad"}, } m["Hira"] = { canonicalName = "Hiragana", varieties = {"Hentaigana"}, characters = "ぁ-ゟ𛀁-𛄞𛅐𛅑𛅒🈀", systems = {"syllabary"}, } m["Hluw"] = { canonicalName = "Anatolian Hieroglyphs", characters = "𔐀-𔙆", wikipedia_article = "Anatolian hieroglyphs", } m["Hung"] = { canonicalName = "Old Hungarian", aliases = {"Hungarian runic"}, characters = "𐲀-𐲲", direction = "rtl", } m["Kana"] = { canonicalName = "Katakana", characters = "゠-ヿㇰ-ㇿ㌀-㍗ｦ-ﾟ𛀀𛅤𛅥𛅦𛅧", systems = {"syllabary"}, } -- These should be defined after the scripts they are composed of m["Kore"] = { canonicalName = "Korean", characters = m["Hang"].characters .. m["Hani"].characters, systems = {"syllabary", "logography"}, } m["Hano"] = { canonicalName = "Hanunoo", characters = "ᜠ-᜴", systems = {"abugida"}, } m["Hebr"] = { canonicalName = "Hebrew", characters = u(0x0590) .. "-" .. u(0x05FF) .. u(0xFB1D) .. "-" .. u(0xFB4F), direction = "rtl", systems = {"abjad"}, -- more precisely, impure abjad } m["Hmng"] = { canonicalName = "Hmong", aliases = {"Pahawh Hmong"}, characters = "𖬀-𖮏", } m["Ibrn"] = { canonicalName = "Iberian", } m["Imag"] = { -- To be used to avoid any formatting or link processing canonicalName = "Image-rendered", -- This should not have any characters listed character_category = false, } m["Inds"] = { canonicalName = "Indus", aliases = {"Harappan", "Indus Valley"}, } m["IPAchar"] = { canonicalName = "International Phonetic Alphabet", aliases = {"IPA"}, } m["Ital"] = { canonicalName = "Old Italic", characters = "𐌀-𐌯", systems = {"alphabet"}, } m["Java"] = { canonicalName = "Javanese", characters = "ꦀ-꧟", systems = {"abugida"}, } m["Jurc"] = { canonicalName = "Jurchen", } m["Kali"] = { canonicalName = "Kayah Li", characters = "꤀-꤯", systems = {"abugida"}, } m["Khar"] = { canonicalName = "Kharoshthi", characters = "𐨀-𐩘", systems = {"abugida"}, direction = "rtl", } m["Khmr"] = { canonicalName = "Khmer", characters = "ក-៹᧠-᧿", systems = {"abugida"}, } m["Khoj"] = { canonicalName = "Khojki", characters = "𑈀-𑈾", systems = {"abugida"}, } m["Kitl"] = { canonicalName = "Khitan Large", systems = {"logography", "syllabary"}, } m["Kits"] = { canonicalName = "Khitan Small", characters = "𘬀-𘳕"..u(0x16FE4), systems = {"logography", "syllabary"}, } m["Knda"] = { canonicalName = "Kannada", characters = "ಀ-ೲ", systems = {"abugida"}, } m["Kthi"] = { canonicalName = "Kaithi", characters = "𑂀-𑃍", systems = {"abugida"}, } m["Lana"] = { canonicalName = "Tai Tham", aliases = {"Tham", "Tua Mueang", "Lanna"}, characters = "ᨠ-᪭", systems = {"abugida"}, } m["Laoo"] = { canonicalName = "Lao", characters = "ກ-ໟ", systems = {"abugida"}, } m["Latn"] = { canonicalName = "Latin", aliases = {"Roman"}, varieties = {"Rumi", "Romaji", "Rōmaji", "Romaja"}, characters = "A-Za-zÀ-ÖØ-öø-ɏḀ-ỿ", systems = {"alphabet"}, } m["Latf"] = { canonicalName = "Fraktur", otherNames = {"Blackletter"}, -- Blackletter is actually the parent "script" characters = m["Latn"].characters, } m["Latinx"] = { canonicalName = "Latin", characters = m["Latn"].characters .. "Ⱡ-Ɀ꜠-ꟿꬰ-ꭥ", parent = "Latn", } m["pjt-Latn"] = { canonicalName = "Latin", characters = m["Latn"].characters, parent = "Latn", } m["Jpan"] = { canonicalName = "Japanese", characters = m["Hira"].characters .. m["Kana"].characters .. m["Hani"].characters .. m["Latn"].characters, systems = {"syllabary", "logography"}, } m["Leke"] = { canonicalName = "Leke", systems = {"abugida"}, } m["Lepc"] = { canonicalName = "Lepcha", characters = "ᰀ-ᱏ", systems = {"abugida"}, } m["Limb"] = { canonicalName = "Limbu", characters = "ᤀ-᥏", systems = {"abugida"}, } m["Lina"] = { canonicalName = "Linear A", characters = "𐘀-𐝧", } m["Linb"] = { canonicalName = "Linear B", characters = "𐀀-𐃺", } m["Lisu"] = { canonicalName = "Lisu", aliases = {"Fraser"}, characters = "ꓐ-꓿𑾰", systems = {"alphabet"}, } m["Lyci"] = { canonicalName = "Lycian", characters = "𐊀-𐊜", systems = {"alphabet"}, } m["Lydi"] = { canonicalName = "Lydian", characters = "𐤠-𐤿", direction = "rtl", systems = {"alphabet"}, } m["Mahj"] = { canonicalName = "Mahajani", characters = "𑅐-𑅶", systems = {"abugida"}, } m["Maka"] = { canonicalName = "Lontara", aliases = {"Makasar"}, characters = "𑻠-𑻸", systems = {"abugida"}, } m["Mand"] = { canonicalName = "Mandaic", aliases = {"Mandaean"}, characters = "ࡀ-࡞", direction = "rtl", } m["Mani"] = { canonicalName = "Manichaean", characters = "𐫀-𐫶", direction = "rtl", systems = {"abjad"}, } m["Maya"] = { canonicalName = "Maya", aliases = {"Maya hieroglyphic", "Mayan", "Mayan hieroglyphic"}, characters = "𝋠-𝋳", } m["Medf"] = { canonicalName = "Medefaidrin", aliases = {"Oberi Okaime", "Oberi Ɔkaimɛ"}, characters = "𖹀-𖺚", } m["Mend"] = { canonicalName = "Mende", aliases = {"Mende Kikakui"}, characters = "𞠀-𞣖", direction = "rtl", } m["Merc"] = { canonicalName = "Meroitic cursive", characters = "𐦠-𐦿", direction = "rtl", systems = {"abugida"}, } m["Mero"] = { canonicalName = "Meroitic hieroglyphic", characters = "𐦀-𐦟", direction = "rtl", systems = {"abugida"}, } m["Mlym"] = { canonicalName = "Malayalam", characters = "ഀ-ൿ", systems = {"abugida"}, } m["Modi"] = { canonicalName = "Modi", characters = "𑘀-𑙙", systems = {"abugida"}, } m["Mong"] = { canonicalName = "Mongolian", aliases = {"Uyghurjin"}, characters = "᠀-ᢪ𑙠-𑙬", direction = "down", } m["Morse"] = { canonicalName = "Morse code", } m["Mroo"] = { canonicalName = "Mro", characters = "𖩀-𖩯", } m["Mtei"] = { canonicalName = "Meitei Mayek", aliases = {"Meetei Mayek", "Manipuri"}, characters = "ꯀ-꯹ꫠ-꫶", systems = {"abugida"}, } m["Mult"] = { canonicalName = "Multani", characters = "𑊀-𑊩", systems = {"abugida"}, } m["musical"] = { canonicalName = "Musical notation", characters = "𝄀-𝇨", systems = {"pictography"}, } m["Mymr"] = { canonicalName = "Burmese", aliases = {"Myanmar"}, characters = "က-႟ꩠ-ꩿꧠ-ꧾ", systems = {"abugida"}, } m["Nand"] = { canonicalName = "Nandinagari", characters = "𑦠-𑧤", systems = {"abugida"}, } m["Narb"] = { canonicalName = "Old North Arabian", characters = "𐪀-𐪟", direction = "rtl", systems = {"abjad"}, } m["Nbat"] = { canonicalName = "Nabataean", aliases = {"Nabatean"}, characters = "𐢀-𐢯", direction = "rtl", systems = {"abjad"}, } m["Newa"] = { canonicalName = "Newa", aliases = {"Newar", "Newari", "Prachalit Nepal"}, -- and Ranjana? characters = "𑐀-𑑡", systems = {"abugida"}, } m["Nkoo"] = { canonicalName = "N'Ko", characters = "߀-߿", direction = "rtl", systems = {"alphabet"}, } m["None"] = { canonicalName = "Unspecified", -- renders as 'unspecified script' -- This should not have any characters listed character_category = false, -- none } m["Nshu"] = { canonicalName = "Nushu", aliases = {"Nüshu"}, characters = "𖿡𛅰-𛋻", systems = {"syllabary"}, } m["Ogam"] = { canonicalName = "Ogham", characters = " -᚜", } m["Olck"] = { canonicalName = "Ol Chiki", characters = "᱐-᱿", } m["Orkh"] = { canonicalName = "Orkhon runes", characters = "𐰀-𐱈", direction = "rtl", } m["Orya"] = { canonicalName = "Oriya", aliases = {"Odia"}, characters = "ଁ-୷", systems = {"abugida"}, } m["Osge"] = { canonicalName = "Osage", characters = "𐒰-𐓻", } m["Osma"] = { canonicalName = "Osmanya", characters = "𐒀-𐒩", } m["Ougr"] = { canonicalName = "Old Uyghur", characters = "𐽰-𐾉", direction = "down", systems = {"abjad", "alphabet"}, } m["Palm"] = { canonicalName = "Palmyrene", characters = "𐡠-𐡿", direction = "rtl", } m["Pauc"] = { canonicalName = "Pau Cin Hau", characters = "𑫀-𑫸", } m["Perm"] = { canonicalName = "Old Permic", characters = "𐍐-𐍺", } m["Phag"] = { canonicalName = "Phags-pa", characters = "ꡀ-꡷", direction = "down", systems = {"abugida"}, } m["Marc"] = { canonicalName = "Marchen", characters = "𑱰-𑲶", systems = {"abugida"}, } m["Phli"] = { canonicalName = "Inscriptional Pahlavi", characters = "𐭠-𐭿", direction = "rtl", systems = {"abjad"}, } m["Phlp"] = { canonicalName = "Psalter Pahlavi", characters = "𐮀-𐮯", direction = "rtl", systems = {"abjad"}, } m["Phlv"] = { canonicalName = "Book Pahlavi", direction = "rtl", systems = {"abjad"}, -- Not in Unicode } m["Phnx"] = { canonicalName = "Phoenician", characters = "𐤀-𐤟", direction = "rtl", systems = {"abjad"}, } m["Plrd"] = { canonicalName = "Pollard", characters = "𖼀-𖾟", systems = {"abugida"}, } m["Prti"] = { canonicalName = "Inscriptional Parthian", characters = "𐭀-𐭟", direction = "rtl", } m["Rjng"] = { canonicalName = "Rejang", characters = "ꤰ-꥟", systems = {"abugida"}, } m["Rohg"] = { canonicalName = "Hanifi Rohingya", characters = "𐴀-𐴹", direction = "rtl", systems = {"alphabet"}, } m["Ruminumerals"] = { canonicalName = "Rumi numerals", characters = "𐹠-𐹾", character_category = "Rumi numerals", } m["Runr"] = { canonicalName = "Runic", characters = "ᚠ-ᛰ", systems = {"alphabet"}, } m["Samr"] = { canonicalName = "Samaritan", characters = "ࠀ-࠾", direction = "rtl", systems = {"abjad"}, } m["Sarb"] = { canonicalName = "Old South Arabian", characters = "𐩠-𐩿", direction = "rtl", systems = {"abjad"}, } m["Saur"] = { canonicalName = "Saurashtra", characters = "ꢀ-꣙", systems = {"abugida"}, } m["Semap"] = { canonicalName = "flag semaphore", systems = {"pictography"}, } m["Sgnw"] = { canonicalName = "SignWriting", characters = "𝠀-𝪯", systems = {"pictography"}, } m["Shaw"] = { canonicalName = "Shavian", characters = "𐑐-𐑿", } m["Shrd"] = { canonicalName = "Sharada", characters = "𑆀-𑇙", systems = {"abugida"}, } m["Sidd"] = { canonicalName = "Siddham", characters = "𑖀-𑗝", systems = {"abugida"}, } m["Sind"] = { canonicalName = "Khudawadi", characters = "𑊰-𑋹", systems = {"abugida"}, } m["Sinh"] = { canonicalName = "Sinhalese", characters = "ං-෴", systems = {"abugida"}, } m["Sogd"] = { canonicalName = "Sogdian", characters = "𐼰-𐽙", direction = "rtl", systems = {"abjad"}, } m["Sogo"] = { canonicalName = "Old Sogdian", characters = "𐼀-𐼧", direction = "rtl", systems = {"abjad"}, } m["Sora"] = { canonicalName = "Sorang Sompeng", aliases = {"Sora Sompeng"}, characters = "𑃐-𑃹", } m["Soyo"] = { canonicalName = "Soyombo", characters = "𑩐-𑪢", systems = {"abugida"}, } m["Sund"] = { canonicalName = "Sundanese", characters = "ᮀ-ᮿ", systems = {"abugida"}, } m["Sylo"] = { canonicalName = "Syloti Nagri", aliases = {"Sylheti Nagari"}, characters = "ꠀ-꠫", systems = {"abugida"}, } m["Syrc"] = { canonicalName = "Syriac", characters = "܀-ݏ"..u(0x0860).."-"..u(0x086A), direction = "rtl", systems = {"abjad"}, -- more precisely, impure abjad } -- Syre, Syrj, Syrn are apparently subsumed into Syrc; discuss if this causes issues m["Tagb"] = { canonicalName = "Tagbanwa", characters = "ᝠ-ᝳ", systems = {"abugida"}, } m["Takr"] = { canonicalName = "Takri", characters = "𑚀-𑛉", systems = {"abugida"}, } m["Tale"] = { canonicalName = "Tai Nüa", aliases = {"Tai Nuea", "New Tai Nüa", "New Tai Nuea", "Dehong Dai", "Tai Dehong", "Tai Le"}, characters = "ᥐ-ᥴ", systems = {"abugida"}, } m["Talu"] = { canonicalName = "New Tai Lue", characters = "ᦀ-᧟", systems = {"abugida"}, } m["Taml"] = { canonicalName = "Tamil", characters = "ஂ-௺𑿀-𑿿", systems = {"abugida"}, } m["Tang"] = { canonicalName = "Tangut", characters = "𖿠𗀀-𘫿𘴀-𘴈", systems = {"logography", "syllabary"}, } m["Tavt"] = { canonicalName = "Tai Viet", characters = "ꪀ-꫟", systems = {"abugida"}, } m["Telu"] = { canonicalName = "Telugu", characters = "ఀ-౿", systems = {"abugida"}, } m["Teng"] = { canonicalName = "Tengwar", } m["Tfng"] = { canonicalName = "Tifinagh", otherNames = {"Libyco-Berber", "Berber"}, -- per Wikipedia, Libyco-Berber is the parent characters = "ⴰ-⵿", systems = {"abjad", "alphabet"}, } m["Tglg"] = { canonicalName = "Baybayin", aliases = {"Tagalog"}, characters = "ᜀ-᜔", systems = {"abugida"}, } m["Thaa"] = { canonicalName = "Thaana", characters = "ހ-ޱ", systems = {"abugida"}, direction = "rtl", } m["Thai"] = { canonicalName = "Thai", characters = "ก-๛", systems = {"abugida"}, } m["Tibt"] = { canonicalName = "Tibetan", characters = "ༀ-࿚", systems = {"abugida"}, } m["Tirh"] = { canonicalName = "Tirhuta", characters = "𑒀-𑓙", systems = {"abugida"}, } m["xzh-Tibt"] = { canonicalName = "Zhang-Zhung", systems = {"abugida"}, } m["Tnsa"] = { canonicalName = "Tangsa", characters = "𖩰-𖫉", systems = {"alphabet"}, } m["Toto"] = { canonicalName = "Toto", characters = "𞊐-𞊮", systems = {"abugida"}, } m["Ugar"] = { canonicalName = "Ugaritic", characters = "𐎀-𐎟", systems = {"abjad"}, } m["Vaii"] = { canonicalName = "Vai", characters = "ꔀ-ꘫ", systems = {"syllabary"}, } m["Vith"] = { canonicalName = "Vithkuqi", characters = "𐕰-𐖼", systems = {"alphabet"}, } m["Wara"] = { canonicalName = "Varang Kshiti", characters = "𑢠-𑣿", } m["Xpeo"] = { canonicalName = "Old Persian", characters = "𐎠-𐏕", } m["Xsux"] = { canonicalName = "Cuneiform", aliases = {"Sumero-Akkadian Cuneiform"}, characters = "𒀀-𒎙𒐀-𒑳", } m["Yiii"] = { canonicalName = "Yi", characters = "ꀀ-꓆", systems = {"syllabary"}, } m["Zanb"] = { canonicalName = "Zanabazar Square", characters = u(0x11A00).."-"..u(0x11A47), } m["Zmth"] = { canonicalName = "mathematical notation", characters = "ℵ∀-⋿⟀-⟯⦀-⫿𝐀-𝟿", character_category = "Mathematical notation symbols", -- ? } m["Zsym"] = { canonicalName = "symbol", characters = "─-➿←-⇿⌀-⏿⬀-⯾🀀-🃵🌀-🩭", character_category = false, -- none systems = {"pictography"}, } m["Zyyy"] = { canonicalName = "undetermined", -- This should not have any characters listed, probably character_category = false, -- none characters = m["Latn"].characters, } m["Zzzz"] = { canonicalName = "uncoded", -- This should not have any characters listed character_category = false, -- none } return m tm69ywxw1p65kbf625cw3xds4jrp1uq 828 2945 8253 2022-07-21T16:58:14Z Rebel Agent 2678 Ke dirile module Scribunto text/plain return function (export, text, lang, scripts, forceDetect) --[=[ Remove any HTML entities; catfix function in [[Module:utilities]] adds tagging to a no-break space (&nbsp;), which contains Latin characters; hence Latin was returned as the script if "Latn" is one of the language's scripts. ]=] text = string.gsub(text, "&[a-zA-Z0-9]+;", "") -- Try to match every script against the text, -- and return the one with the most matching characters. local bestcount = 0 local bestscript = nil -- Get length of text minus any spacing or punctuation characters. -- Counting instances of UTF-8 character pattern is faster than mw.ustring.len. local _, length = string.gsub(mw.ustring.gsub(text, "[%s%p]+", ""), "[\1-\127\194-\244][\128-\191]*", "") if length == 0 then return export.getByCode("None") end for i, script in ipairs(scripts) do local count = script:countCharacters(text) if count >= length then return script end if count > bestcount then bestcount = count bestscript = script end end if bestscript then return bestscript end -- No matching script was found. Return "None". return export.getByCode("None") end 2k718fyv9gb6qdxf079j9elt4xfrl9m 828 2946 8254 2022-07-21T17:11:02Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local export = {} --[=[ Modules used: [[Module:script utilities/data]] [[Module:scripts]] [[Module:senseid]] (only when id's present) [[Module:string utilities]] (only when hyphens in Korean text or spaces in vertical text) [[Module:languages]] [[Module:parameters]] [[Module:utilities/format_categories]] [[Module:debug/track]] ]=] function export.is_Latin_script(sc) -- Latn, Latf, Latinx, pjt-Latn return sc:getCode():find("Lat") and true or false end -- Used by [[Template:lang]] function export.lang_t(frame) params = { [1] = {}, [2] = { allow_empty = true, default = "" }, ["sc"] = {}, ["face"] = {}, ["class"] = {}, } local args = require("Module:parameters").process(frame:getParent().args, params) local NAMESPACE = mw.title.getCurrentTitle().nsText local lang = args[1] or (NAMESPACE == "Template" and "und") or error("Language code has not been specified. Please pass parameter 1 to the template.") lang = require("Module:languages").getByCode(lang) or require("Module:languages").err(lang, 1) local text = args[2] local sc = args["sc"] sc = (sc and (require("Module:scripts").getByCode(sc) or error("The script code \"" .. sc .. "\" is not valid.")) or nil) local face = args["face"] return export.tag_text(text, lang, sc, face, class) 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, ustring) local find = ustring and mw.ustring.find or string.find if pattern and find(text, pattern) then require("Module:debug/track")("script/" .. tracking) end end local function track(text, lang, sc) local U = mw.ustring.char if lang and text then local langCode = lang:getCode() -- [[Special:WhatLinksHere/Template:tracking/script/ang/acute]] if langCode == "ang" then local decomposed = mw.ustring.toNFD(text) local acute = U(0x301) trackPattern(decomposed, acute, "ang/acute") --[=[ [[Special:WhatLinksHere/Template:tracking/script/Greek/wrong-phi]] [[Special:WhatLinksHere/Template:tracking/script/Greek/wrong-theta]] [[Special:WhatLinksHere/Template:tracking/script/Greek/wrong-kappa]] [[Special:WhatLinksHere/Template: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/Template:tracking/script/Ancient Greek/spacing-coronis]] [[Special:WhatLinksHere/Template:tracking/script/Ancient Greek/spacing-smooth-breathing]] [[Special:WhatLinksHere/Template: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/Template:tracking/script/Russian/grave-accent]] elseif langCode == "ru" then local decomposed = mw.ustring.toNFD(text) trackPattern(decomposed, U(0x300), "Russian/grave-accent") -- [[Special:WhatLinksHere/Template:tracking/script/Tibetan/trailing-punctuation]] elseif langCode == "bo" then trackPattern(text, "[་།]$", "Tibetan/trailing-punctuation", true) trackPattern(text, "[་།]%]%]$", "Tibetan/trailing-punctuation", true) --[=[ [[Special:WhatLinksHere/Template:tracking/script/Thai/broken-ae]] [[Special:WhatLinksHere/Template:tracking/script/Thai/broken-am]] [[Special:WhatLinksHere/Template:tracking/script/Thai/wrong-rue-lue]] ]=] elseif langCode == "th" then trackPattern(text, "เ".."เ", "Thai/broken-ae") trackPattern(text, "ํ[่้๊๋]?า", "Thai/broken-am", true) trackPattern(text, "[ฤฦ]า", "Thai/wrong-rue-lue", true) --[=[ [[Special:WhatLinksHere/Template:tracking/script/Lao/broken-ae]] [[Special:WhatLinksHere/Template:tracking/script/Lao/broken-am]] [[Special:WhatLinksHere/Template:tracking/script/Lao/possible-broken-ho-no]] [[Special:WhatLinksHere/Template:tracking/script/Lao/possible-broken-ho-mo]] [[Special:WhatLinksHere/Template:tracking/script/Lao/possible-broken-ho-lo]] ]=] elseif langCode == "lo" then trackPattern(text, "ເ".."ເ", "Lao/broken-ae") trackPattern(text, "ໍ[່້໊໋]?າ", "Lao/broken-am", true) 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/Template:tracking/script/Lü/broken-ae]] [[Special:WhatLinksHere/Template: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", true) end end end -- Wrap text in the appropriate HTML tags with language and script class. function export.tag_text(text, lang, sc, face, class, id) if not sc then sc = require("Module:scripts").findBestScript(text, lang) end track(text, lang, sc) -- Replace space characters with newlines in Mongolian-script text, which is written top-to-bottom. if sc:getDirection() == "down" and text:find(" ") then text = require("Module: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. -- XXX: 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:find("%-") or text:find("[()]")) then text = require("Module:munge_text")(text, function(txt) -- Hani/Hang regex is a reasonable subset of Hani/Hang from [[Module:scripts/data]], -- last checked on 20220221 txt = txt:gsub("%-", "") txt = mw.ustring.gsub(txt, "([一-鿿㐀-䶿𠀀-𮯯𰀀-𱍏]+)%(([가-힣ᄀ-ᇿꥠ-ꥼힰ-ퟻ]+)%)", "<ruby>%1<rp>(</rp><rt>%2</rt><rp>)</rp></ruby>") return txt end) end if sc:getCode() == "Imag" then face = nil end local function class_attr(classes) table.insert(classes, 1, sc:getCode()) if class and class ~= '' then table.insert(classes, class) end return 'class="' .. table.concat(classes, ' ') .. '"' end local function tag_attr(...) local output = {} if id then table.insert(output, 'id="' .. require("Module:senseid").anchor(lang, id) .. '"') end table.insert(output, class_attr({...}) ) if lang then table.insert(output, 'lang="' .. lang:getCode() .. '"') end return table.concat(output, " ") end if face == "hypothetical" then -- [[Special:WhatLinksHere/Template:tracking/script-utilities/face/hypothetical]] require("Module:debug/track")("script-utilities/face/hypothetical") end local data = mw.loadData("Module:script utilities/data").faces[face or "nil"] local post = "" if sc:getDirection() == "rtl" and (face == "translation" or mw.ustring.find(text, "%p$")) then post = "&lrm;" end -- Add a script wrapper if data then return ( data.prefix or "" ) .. '<' .. data.tag .. ' ' .. tag_attr(data.class) .. '>' .. text .. '</' .. data.tag .. '>' .. post else error('Invalid script face "' .. face .. '".') end end function export.tag_translit(translit, lang, kind, attributes, is_manual) if type(lang) == "table" then lang = lang.getCode and lang:getCode() or error("Second argument to tag_translit should be a language code or language object.") end local data = mw.loadData("Module:script utilities/data").translit[kind or "default"] local opening_tag = {} table.insert(opening_tag, data.tag) if lang == "ja" then table.insert(opening_tag, 'class="' .. (data.classes and data.classes .. " " or "") .. (is_manual and "manual-tr " or "") .. 'tr"') else table.insert(opening_tag, 'lang="' .. lang .. '-Latn"') table.insert(opening_tag, 'class="' .. (data.classes and data.classes .. " " or "") .. (is_manual and "manual-tr " or "") .. 'tr Latn"') end if data.dir then table.insert(opening_tag, 'dir="' .. data.dir .. '"') end table.insert(opening_tag, attributes) return "<" .. table.concat(opening_tag, " ") .. ">" .. translit .. "</" .. data.tag .. ">" end function export.tag_transcription(transcription, lang, kind, attributes) if type(lang) == "table" then lang = lang.getCode and lang:getCode() or error("Third argument to tag_translit should be a language code or language object.") end local data = mw.loadData("Module:script utilities/data").transcription[kind or "default"] local opening_tag = {} table.insert(opening_tag, data.tag) if lang == "ja" then table.insert(opening_tag, 'class="' .. (data.classes and data.classes .. " " or "") .. 'ts"') else table.insert(opening_tag, 'lang="' .. lang .. '-Latn"') table.insert(opening_tag, 'class="' .. (data.classes and data.classes .. " " or "") .. 'ts Latn"') end if data.dir then table.insert(opening_tag, 'dir="' .. data.dir .. '"') end table.insert(opening_tag, attributes) return "<" .. table.concat(opening_tag, " ") .. ">" .. transcription .. "</" .. data.tag .. ">" end -- Add a notice to request the native script of a word 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 then -- If the script is Latin, return nothing. if export.is_Latin_script(sc) then return "" end if 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 lang=und, or when the language has -- multiple scripts. if lang:getCode() == "und" 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 i, 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 then return "" end end local category if usex then category = "Requests for " .. cat_script .. " script in " .. lang:getCanonicalName() .. " usage examples" else category = "Requests for " .. cat_script .. " script for " .. lang:getCanonicalName() .. " terms" end return "<small>[" .. disp_script .. " needed]</small>" .. (nocat and "" or require("Module:utilities/format_categories")({category}, lang, sort_key)) end function export.template_rfscript(frame) params = { [1] = { required = true, default = "und" }, ["sc"] = {}, ["usex"] = { type = "boolean" }, ["nocat"] = { type = "boolean" }, ["sort"] = {}, } local args = require("Module:parameters").process(frame:getParent().args, params) local lang = require("Module:languages").getByCode(args[1], 1) local sc = args.sc and require("Module:scripts").getByCode(args.sc, true) local ret = export.request_script(lang, sc, 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.") else return ret end end function export.checkScript(text, scriptCode, result) local scriptObject = require("Module:scripts").getByCode(scriptCode) if not scriptObject then error('The script code "' .. scriptCode .. '" is not recognized.') end local originalText = text -- Remove non-letter characters. text = mw.ustring.gsub(text, "[%A]", "") -- Remove all characters of the script in question. text = mw.ustring.gsub(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 9ngfwzgm248m0tf7f4w21s67ibt0yyw 828 2947 8255 2022-07-21T17:13:11Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local data = {} data.translit = { ["term"] = { --[=[ can't be done until Kana transliterations are correctly parsed by [[Module:links]] ["tag"] = "i", ]=] ["classes"] = "mention-tr", }, ["usex"] = { ["tag"] = "i", ["classes"] = "e-transliteration", }, ["head"] = { ["classes"] = "headword-tr", ["dir"] = "ltr", }, ["default"] = {}, } data.transcription = { ["head"] = { ["tag"] = "span", ["classes"] = "headword-ts", ["dir"] = "ltr", }, ["usex"] = { tag = "span", ["classes"] = "e-transcription", }, ["default"] = {}, } for key, value in pairs(data.translit) do if not value.tag then value.tag = "span" end end data.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", }, ["translation"] = { tag = "span", }, ["nil"] = { tag = "span", }, } return data fm6qqnko32z2ecx0x8dstbowpirn5sa 10 2948 8260 2022-07-21T18:01:00Z Rebel Agent 2678 Ke dirile tempolete wikitext text/x-wiki {{#invoke:etymology/templates/borrowed|borrowed}}<noinclude>{{documentation}}</noinclude> ck2uicyt84ro88jfftayvgmjj8u9dbl 828 2949 8261 2022-07-21T18:02:43Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local export = {} function export.borrowed(frame) local args, lang, term, sources = require("Module:etymology/templates/internal").parse_2_lang_args(frame) if sources then return require("Module:etymology/multi").format_multi_borrowed(lang, sources, term, args.sort, args.nocat, args.conj) else return require("Module:etymology").format_borrowed(lang, term, args.sort, args.nocat) end end return export 2wenvc67iugvzhxiwy5qv5hywo2wzz9 828 2950 8262 2022-07-21T18:04:14Z Rebel Agent 2678 Ke dirile module Scribunto text/plain -- For internal use only with [[Module:etymology/templates]] and its submodules. local export = {} function export.fetch_lang(lang, param) return require("Module:languages").getByCode(lang, param) end function export.fetch_source(code, param, disallow_family) return require("Module:languages").getByCode(code, param, true, not disallow_family) end local function fetch_sources(codes, param, disallow_family) local m_languages = require("Module:languages") codes = mw.text.split(codes, "%s*,%s*") for i, code in ipairs(codes) do codes[i] = m_languages.getByCode(code, param, true, not disallow_family) end return codes end function export.fetch_source_or_sources(source, param, disallow_family) local sources if source:find(",") then sources = fetch_sources(source, param, no_family) source = sources[#sources] else source = export.fetch_source(source, param, no_family) end return source, sources end function export.fetch_script(sc, param) return require("Module:scripts").getByCode(sc, param) end function export.parse_2_lang_args(frame, has_text, no_family) local params = { [1] = {required = true, default = "und"}, [2] = {required = true, default = "und"}, [3] = {}, [4] = {alias_of = "alt"}, [5] = {alias_of = "t"}, ["alt"] = {}, ["cat"] = {}, ["g"] = {list = true}, ["gloss"] = {alias_of = "t"}, ["id"] = {}, ["lit"] = {}, ["pos"] = {}, ["t"] = {}, ["tr"] = {}, ["ts"] = {}, ["sc"] = {}, ["nocat"] = {type = "boolean"}, ["sort"] = {}, ["conj"] = {}, } if has_text then params["notext"] = {type = "boolean"} params["nocap"] = {type = "boolean"} end local args = require("Module:parameters").process(frame:getParent().args, params) local lang = export.fetch_lang(args[1], 1) local source, sources = export.fetch_source_or_sources(args[2], 2, no_family) local sc = export.fetch_script(args["sc"], "sc") return args, lang, { lang = source, sc = sc, term = args[3], alt = args["alt"], id = args["id"], genders = args["g"], tr = args["tr"], ts = args["ts"], gloss = args["t"], pos = args["pos"], lit = args["lit"] }, sources end return export 9duq6puisyqx6d59rmi3rsi7e0116q0 828 2951 8263 2022-07-21T18:07:17Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local u = mw.ustring.char -- UTF-8 encoded strings for some commonly used diacritics local GRAVE = u(0x0300) local ACUTE = u(0x0301) local CIRC = u(0x0302) local TILDE = u(0x0303) local MACRON = u(0x0304) local BREVE = u(0x0306) local DOTABOVE = u(0x0307) local DIAER = u(0x0308) local CARON = u(0x030C) local DGRAVE = u(0x030F) local INVBREVE = u(0x0311) local DOTBELOW = u(0x0323) local RINGBELOW = u(0x0325) local CEDILLA = u(0x0327) local Latn = {"Latn"} local m = {} m["uam"] = { "Uamué", 3441418, } m["uan"] = { "Kuan", 6441085, } m["uar"] = { "Tairuma", 7676386, "ngf", } m["uba"] = { "Ubang", 3914467, "nic-ben", Latn, } m["ubi"] = { "Ubi", 56264, } m["ubl"] = { "Buhi'non Bikol", 18664494, "phi", } m["ubr"] = { "Ubir", 3547642, "poz-ocw", Latn, } m["ubu"] = { "Umbu-Ungu", 12953245, "ngf", } m["uby"] = { "Ubykh", 36931, "cau-nwc", {"Latn", "Cyrl"}, } m["uda"] = { "Uda", 11011951, "nic-lcr", } m["ude"] = { "Udihe", 13235, "tuw", {"Cyrl"}, } m["udg"] = { "Muduga", 16886762, "dra", } m["udi"] = { "Udi", 36867, "cau-nec", {"Cyrl", "Latn", "Armn", "Geor"}, ancestors = {"xag"}, translit_module = "translit-redirect", override_translit = true, } m["udj"] = { "Ujir", 14916906, "poz-cet", } m["udl"] = { "Uldeme", 3515078, "cdc-cbm", } m["udm"] = { "Udmurt", 13238, "urj-prm", {"Cyrl"}, translit_module = "udm-translit", override_translit = true, } m["udu"] = { "Uduk", 3182573, "ssa-kom", } m["ues"] = { "Kioko", 18343036, } m["ufi"] = { "Ufim", 7877531, "ngf-fin", Latn, } m["uga"] = { "Ugaritic", 36928, "sem-nwe", {"Ugar"}, translit_module = "uga-translit", } m["ugb"] = { "Kuku-Ugbanh", 10549854, } m["uge"] = { "Ughele", 966303, "poz-ocw", } m["ugn"] = { "Ugandan Sign Language", 7877677, "sgn", } m["ugo"] = { "Gong", 3448919, "tbq-lob", {"Thai"}, sort_key = { from = {"[%pๆ]", "[็-๎]", "([เแโใไ])([ก-ฮ])"}, to = {"", "", "%2%1"}}, } m["ugy"] = { "Uruguayan Sign Language", 7901470, "sgn", } m["uha"] = { "Uhami", 3913328, "alv-nwd", Latn, } m["uhn"] = { "Damal", 4748974, } m["uis"] = { "Uisai", 7878123, "paa-sbo", } m["uiv"] = { "Iyive", 11128658, "nic-tvc", Latn, } m["uji"] = { "Tanjijili", 3914939, "nic-pls", } m["uka"] = { "Kaburi", 6344482, } m["ukg"] = { "Ukuriguma", 7878623, "ngf-mad", } m["ukh"] = { "Ukhwejo", 36623, "bnt-bek", } m["ukk"] = { "Muak Sa-aak", nil, "mkh-pal", } m["ukl"] = { "Ukrainian Sign Language", 10322106, "sgn", } m["ukp"] = { "Ukpe-Bayobiri", 3914470, "nic-ben", Latn, } m["ukq"] = { "Ukwa", 7878635, "nic-ief", } 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", } m["ulb"] = { "Ulukwumi", 36722, "alv-yor", } m["ulc"] = { "Ulch", 13239, "tuw", {"Cyrl", "Latn"}, } m["ule"] = { "Lule", 12635889, nil, Latn, } m["ulf"] = { "Afra", 4477735, "paa-pau", } m["uli"] = { "Ulithian", 36842, "poz-mic", } m["ulk"] = { "Meriam", 788174, "ngf", Latn, } m["ull"] = { "Ullatan", 8761579, "dra", } m["ulm"] = { "Ulumanda'", 3501892, } m["uln"] = { "Unserdeutsch", 13244, "crp", Latn, ancestors = {"de"}, } m["ulu"] = { "Uma' Lung", 3548186, "poz-swa", } m["ulw"] = { "Ulwa", 2405552, } m["uma"] = { "Umatilla", 12953952, "nai-shp", Latn, ancestors = {"nai-spt"}, } m["umb"] = { "Umbundu", 36983, "bnt", Latn, } m["umc"] = { "Marrucinian", 36110, "itc", {"Latn", "Ital"}, } m["umd"] = { "Umbindhamu", 7881346, "aus-pmn", } m["umg"] = { "Umbuygamu", 3915677, "aus-pmn", } m["umi"] = { "Ukit", 7878321, } 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", } m["umu"] = { "Munsee", 56547, "del", Latn, entry_name = { from = {"Á", "Ă", "É", "Í", "Ó", "Ú", "Ŭ", "á", "á", "ă", "é", "í", "ó", "ú", "ŭ"}, to = {"A", "A", "E", "I", "O", "U", "U", "a", "á", "a", "e", "i", "o", "u", "u"}} , } m["una"] = { "North Watut", 15887898, "poz-ocw", Latn, } m["und"] = { "Undetermined", nil, "qfa-not", {"Zyyy"}, } m["une"] = { "Uneme", 3913357, "alv-yek", Latn, } m["ung"] = { "Ngarinyin", 1284885, "aus-wor", Latn, } m["unk"] = { "Enawené-Nawé", 3307184, "awd", Latn, } m["unm"] = { "Unami", 3549180, "del", Latn, --Don't strip diacritics from entry names, per [[WT:Grease pit/2020/May]]. --entry_name = { -- from = {"À", "Ä", "È", "Ë", "Ì", "Ò", "Ù", "à", "ä", "è", "ë", "ì", "ò", "ù"}, -- to = {"A", "A", "E", "E", "I", "O", "U", "a", "a", "e", "e", "i", "o", "u"}} , } m["unn"] = { "Kurnai", nil, "aus-pam", Latn, } m["unr"] = { "Mundari", 3327828, "mun", {"Deva"}, translit_module = "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", Q11182000, "map", Latn, } m["upi"] = { "Umeda", 7881465, "paa-brd", } m["upv"] = { "Uripiv-Wala-Rano-Atchin", 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", Latn, } m["urh"] = { "Urhobo", 36663, "alv-swd", Latn, } m["uri"] = { "Urim", 7900609, "qfa-tor", Latn, } m["urk"] = { "Urak Lawoi'", 7899573, "poz-mly", {"Thai"}, sort_key = { from = {"[%pๆ]", "[็-๎]", "([เแโใไ])([ก-ฮ])"}, to = {"", "", "%2%1"}}, } m["url"] = { "Urali", 7899602, "dra", {"Knda"}, } m["urm"] = { "Urapmin", 7899769, "ngf-okk", } m["urn"] = { "Uruangnirin", 7901389, "poz-cet", Latn, } m["uro"] = { "Ura (New Guinea)", 3121049, "paa-bng", Latn, } m["urp"] = { "Uru-Pa-In", 7901376, "tup-gua", Latn, } m["urr"] = { "Lehalurup", 3272124, } m["urt"] = { "Urat", 3502084, "qfa-tor", Latn, } m["uru"] = { "Urumi", 7901530, "tup", Latn, } m["urv"] = { "Uruava", 36875, "poz-ocw", Latn, } m["urw"] = { "Sop", 7562808, "ngf-mad", Latn, } m["urx"] = { "Urimo", 7900611, "qfa-tor", Latn, } m["ury"] = { "Orya", 7105295, "paa-tkw", Latn, } m["urz"] = { "Uru-Eu-Wau-Wau", 10266012, "tup-gua", Latn, } m["usa"] = { "Usarufa", 7901714, "paa-kag", Latn, } m["ush"] = { "Ushojo", 3540446, "inc-dar", } m["usi"] = { "Usui", 12644231, } m["usk"] = { "Usaghade", 3914048, "nic-lcr", Latn, } m["usp"] = { "Uspanteco", 36728, "myn", Latn, } m["uss"] = { "Saare", nil, "nic-knn", Latn, } m["usu"] = { "Uya", 7904082, } m["uta"] = { "Otank", 3913990, "nic-tvc", Latn, } m["ute"] = { "Ute", 13260, "azc-num", Latn, } m["uth"] = { "Hun", nil, "nic-knn", Latn, } m["utp"] = { "Aba", 2841465, "poz-oce", Latn, } m["utr"] = { "Etulo", 35262, "alv-ido", Latn, } m["utu"] = { "Utu", 7903469, "ngf-mad", } m["uum"] = { "Urum", 13257, "trk-kcu", {"Cyrl"}, } m["uun"] = { "Kulon-Pazeh", 36435, "map", Latn, } m["uur"] = { "Ura (Vanuatu)", 7899531, "poz-oce", Latn, } m["uuu"] = { "U", 953082, "mkh-pal", } m["uve"] = { "West Uvean", 36837, "poz-pnp", Latn, } m["uvh"] = { "Uri", 7900540, "ngf-fin", Latn, } m["uvl"] = { "Lote", 3259972, "poz-ocw", Latn, } m["uwa"] = { "Kuku-Uwanh", 3915687, "aus-pmn", } m["uya"] = { "Doko-Uyanga", 7904095, "nic-ucr", Latn, } return m 1n8pmgbzhtsl63yklmxrfc7pm2y2y8f 828 2952 8264 2022-07-21T18:08:53Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local export = {} -- For testing local force_cat = false --[[ If language is an etymology language, iterates through parent languages until it finds a non-etymology language. ]] --FIXME: Callers of this should use [[Module:languages]] directly. function export.getNonEtymological(lang) if lang:getType() == "etymology language" then return require("Module:languages").getNonEtymological(lang) end return lang end local function term_error(terminfo) if terminfo.lang:getType() == "family" then if terminfo.term and terminfo.term ~= "-" then require("Module:debug/track")("etymology/family/has-term") end terminfo.term = "-" end return terminfo end local function create_link(terminfo, template_name) local link = "" if terminfo.term == "-" then --[=[ [[Special:WhatLinksHere/Template:tracking/cognate/no-term]] [[Special:WhatLinksHere/Template:tracking/derived/no-term]] [[Special:WhatLinksHere/Template:tracking/borrowed/no-term]] [[Special:WhatLinksHere/Template:tracking/calque/no-term]] ]=] require("Module:debug/track")(template_name .. "/no-term") else -- mw.log(terminfo.term) link = " " .. require("Module:links").full_link(terminfo, "term", true) end return link end function export.process_and_create_link(terminfo, template_name) terminfo.lang = export.getNonEtymological(terminfo.lang) terminfo = term_error(terminfo) return create_link(terminfo, template_name or "derived") end function export.get_display_and_cat_name(source, raw) local display, cat_name if source:getCode() == "und" then display = "undetermined" cat_name = "other languages" elseif source:getCode() == "mul" then display = "[[w:Translingualism|translingual]]" cat_name = "Translingual" elseif source:getCode() == "mul-tax" then display = "[[w:taxonomic name|taxonomic name]]" cat_name = "taxonomic names" else display = raw and source:getCanonicalName() or source:makeWikipediaLink() cat_name = source:getDisplayForm() end return display, cat_name end function export.insert_source_cat_get_display(categories, lang, source, raw, nocat) local display, cat_name = export.get_display_and_cat_name(source, raw) if lang and not nocat then -- Add the category, but only if there is a current language if not categories then categories = {} end if lang:getCode() == source:getCode() then table.insert(categories, lang:getCanonicalName() .. " twice-borrowed terms") else table.insert(categories, lang:getCanonicalName() .. " terms derived from " .. cat_name) end end return display, categories end -- FIXME: rename to format_source() function export.format_etyl(lang, source, sort_key, categories, nocat) -- [[Special:WhatLinksHere/Template:tracking/etymology/sortkey]] if sort_key then require("Module:debug/track")("etymology/sortkey") end local display display, categories = export.insert_source_cat_get_display(categories, lang, source, false, nocat) if lang and not nocat then -- Format categories, but only if there is a current language; {{cog}} currently gets no categories categories = require("Module:utilities").format_categories(categories, lang, sort_key, nil, force_cat) else categories = "" end return "<span class=\"etyl\">" .. display .. categories .. "</span>" end -- Internal implementation of {{cognate|...}} template function export.format_cognate(terminfo, sort_key) return export.format_derived(nil, terminfo, sort_key, nil, "cognate") end -- Internal implementation of {{derived|...}} template function export.format_derived(lang, terminfo, sort_key, nocat, template_name) local source = terminfo.lang return export.format_etyl(lang, source, sort_key, nil, nocat) .. export.process_and_create_link(terminfo, template_name) end -- Return true if `lang` has `otherlang` (which may be an etymology-only language) as an ancestor. This includes -- cases such as Italian -> Old Italian, which is an etymology-only language whose "parent" is Italian but which is -- marked as "ancestral to parent". `non_etym_otherlang` is the non-etymology-language equivalent of `otherlang`. -- If `otherlang` is not an etymology-only language, the two will be the same. local function has_ancestor(lang, otherlang, non_etym_otherlang) -- First check if `lang` has (the non-etymology-language parent of) `otherlang` as its ancestor. If `lang` is e.g. -- Italian and `otherlang` is Latin, this will be caught here. If `lang` is Italian and `otherlang` is Vulgar Latin -- (an etymology-only language whose parent is Latin), this will also be caught here, as we use the -- non-etymology-language parent, in this case Latin, when checking the ancestor hierarchy. if lang:hasAncestor(non_etym_otherlang) then return true end -- Second check for the Italian -> Old Italian case. This happens when (a) `otherlang` is etymology-only, -- (b) `otherlang` is marked as "ancestral to parent", (c) `otherlang`'s parent is the same as `lang`. This is not -- caught above because Italian is not ancestral to Italian. if otherlang:getType() == "etymology language" and otherlang:isAncestralToParent() then local otherlang_parent = export.getNonEtymological(otherlang) if otherlang_parent and otherlang_parent:getCode() == lang:getCode() then return true end end return false end -- Check that `lang` has `otherlang` (which may be an etymology-only language) as an ancestor. Throw an error if not. local function check_ancestor(lang, otherlang, non_etym_otherlang) if not has_ancestor(lang, otherlang, non_etym_otherlang) and mw.title.getCurrentTitle().nsText ~= "Template" then -- Generate the non-ancestor error message. local function showLanguage(lang) local retval = ("%s (%s)"):format(lang:makeCategoryLink(), lang:getCode()) if lang:getType() == "etymology language" then retval = retval .. (" (an etymology-only language whose regular parent is %s)"):format( showLanguage(export.getNonEtymological(lang))) end return retval end local postscript local ancestors = lang:getAncestors() local moduleLink = "[[Module:" .. require("Module:languages").getDataModuleName(lang:getCode()) .. "]]" if not ancestors[1] then postscript = showLanguage(lang) .. " has no ancestors." else local ancestorList = table.concat( require("Module:fun").map( showLanguage, ancestors), " and ") postscript = ("The ancestor%s of %s %s %s."):format( ancestors[2] and "s" or "", lang:getCanonicalName(), ancestors[2] and "are" or "is", ancestorList) end error(("%s is not set as an ancestor of %s in %s. %s") :format(showLanguage(otherlang), showLanguage(lang), moduleLink, postscript)) end end -- Internal implementation of {{inherited|...}} template function export.format_inherited(lang, terminfo, sort_key, nocat) local source = terminfo.lang local categories = {} if not nocat then table.insert(categories, lang:getCanonicalName() .. " terms inherited from " .. source:getCanonicalName()) end local link = export.process_and_create_link(terminfo, "inherited") check_ancestor(lang, source, terminfo.lang) return export.format_etyl(lang, source, sort_key, categories, nocat) .. link end function export.insert_borrowed_cat(categories, lang, source) local category if lang:getCode() == source:getCode() then category = " twice-borrowed terms" else category = " terms borrowed from " .. source:getDisplayForm() end table.insert(categories, lang:getCanonicalName() .. category) end -- Internal implementation of {{borrowed|...}} template. function export.format_borrowed(lang, terminfo, sort_key, nocat) local source = terminfo.lang local categories = {} if not nocat then export.insert_borrowed_cat(categories, lang, source) end return export.format_etyl(lang, source, sort_key, categories, nocat) .. export.process_and_create_link(terminfo, "borrowed") end return export itco1l2s6lw2a800rf0grfrj9it14yt 10 2953 8265 2022-07-21T18:28:47Z Rebel Agent 2678 Ke dirile tempolete wikitext text/x-wiki {{#invoke:accent qualifier|show}}<noinclude>{{documentation}}</noinclude> rkp8073yt7s9fcxmgfve8gzuy1sj8us 828 2954 8266 2022-07-21T18:34:42Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local export = {} local m_qualifier = require("Module:qualifier") function export.format_qualifiers(qualifiers) local m_data = mw.loadData("Module:accent qualifier/data") if type(qualifiers) ~= "table" then qualifiers = { qualifiers } end local accents = {} local categories = {} for _, accent in ipairs(qualifiers) do local data -- Replace an alias with the label that has a data table. if m_data.aliases[accent] then accent = m_data.aliases[accent] end -- Retrieve the label's data table. if m_data.labels[accent] then data = m_data.labels[accent] end -- Use the link and displayed text in the data table, if they exist. if data then if data.link then table.insert(accents, "[[w:" .. data.link .. "|" .. (data.display or data.link) .. "]]") elseif data.display then table.insert(accents, data.display) end --[[ if data[accent] then if data[accent].type == "sound change" then table.insert(categories, lang:getCanonicalName() .. " terms with pronunciations exhibiting " .. accent) end end ]] else table.insert(accents, accent) end end return m_qualifier.format_qualifier(accents) end -- Called by {{accent}} or {{a}}. function export.show(frame) local args = frame.getParent and frame:getParent().args or frame if (not args[1] or args[1] == "") and mw.title.getCurrentTitle().nsText == "Template" then return m_qualifier.format_qualifier{ '{{{1}}}' } end local params = { [1] = {required = true, list = true} } args = require("Module:parameters").process(args, params) return export.format_qualifiers(args[1]) end return export lz0w34ceclze1jy7yv9znoh9d75vz1c 828 2955 8267 2022-07-21T18:36:10Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local export = {} function export.format_qualifier(list) -- keep in sync with [[Template:qualifier]] if type(list) ~= "table" then list = { list } end if #list == 0 then return '' end return '<span class="ib-brac qualifier-brac">(</span>' .. '<span class="ib-content qualifier-content">' .. table.concat(list, '<span class="ib-comma qualifier-comma">,</span> ') .. '</span><span class="ib-brac qualifier-brac">)</span>' end function export.sense(list) -- keep in sync with [[Template:sense]] return export.format_qualifier(list) .. '<span class="ib-colon sense-qualifier-colon">:</span>' end return export c9hl0r9z9t1dp3atblkfi1gopwa55p1 10 2956 8268 2022-07-21T18:38:42Z Rebel Agent 2678 Ke dirile tempolete wikitext text/x-wiki {{check deprecated lang param usage|lang={{{lang|}}}|<!-- -->{{#invoke:IPA/templates|IPA}}<!-- -->}}<!-- --><noinclude>{{documentation}}</noinclude> k9mhfq9a7nf5suoyiwknfuk0p4ozvdo 828 2957 8269 2022-07-21T18:40:14Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local export = {} local m_IPA = require("Module:IPA") local U = mw.ustring.char local syllabic = U(0x0329) -- Used for [[Template:IPA]]. function export.IPA(frame) local parent_args = frame.getParent and frame:getParent().args or frame local compat = parent_args["lang"] local offset = compat and 0 or 1 local params = { [compat and "lang" or 1] = {required = true, default = "en"}, [1 + offset] = {list = true, allow_holes = true}, ["ref"] = {list = true, allow_holes = true}, -- Came before 'ref' but too obscure ["n"] = {list = true, allow_holes = true, alias_of = "ref"}, ["qual"] = {list = true, allow_holes = true}, ["nocount"] = {type = "boolean"}, ["sort"] = {}, } local args = require("Module:parameters").process(parent_args, params) local lang = args[compat and "lang" or 1] lang = require("Module:languages").getByCode(lang) or require("Module:languages").err(lang, compat and "lang" or 1) -- [[Special:WhatLinksHere/Template:tracking/IPA/grc]] if lang and lang:getCode() == "grc" then require("Module:debug").track("IPA/grc") end local items = {} for i = 1, math.max(args[1 + offset].maxindex, args["ref"].maxindex, args["qual"].maxindex) do local pron = args[1 + offset][i] local refs = args["ref"][i] if refs then refs = require("Module:references").parse_references(refs) end local qual = args["qual"][i] if not pron then if refs or qual then local param = i == 1 and "" or "" .. i error("Specified qual" .. param .. "= or ref" .. param .. "= without corresponding pronunciation") end else if lang then require("Module:IPA/tracking").run_tracking(pron, lang) end if pron or refs or qual then table.insert(items, {pron = pron, refs = refs, qualifiers = {qual}}) end end end return m_IPA.format_IPA_full(lang, items, nil, nil, args.sort, args.nocount) end -- Used for [[Template:IPAchar]]. function export.IPAchar(frame) local params = { [1] = {list = true, allow_holes = true}, ["ref"] = {list = true, allow_holes = true}, -- Came before 'ref' but too obscure ["n"] = {list = true, allow_holes = true, alias_of = "ref"}, ["qual"] = {list = true, allow_holes = true}, -- FIXME, remove this. ["lang"] = {}, -- This parameter is not used and does nothing, but is allowed for futureproofing. } local args = require("Module:parameters").process(frame.getParent and frame:getParent().args or frame, params) -- [[Special:WhatLinksHere/Template:tracking/IPAchar/lang]] if args.lang then require("Module:debug").track("IPAchar/lang") end local items = {} for i = 1, math.max(args[1].maxindex, args["ref"].maxindex, args["qual"].maxindex) do local pron = args[1][i] local refs = args["ref"][i] if refs then refs = require("Module:references").parse_references(refs) end local qual = args["qual"][i] if pron or refs or qual then table.insert(items, {pron = pron, refs = refs, qualifiers = {qual}}) end end -- Format return m_IPA.format_IPA_multiple(nil, items) end function export.XSAMPA(frame) local params = { [1] = { required = true }, } local args = require("Module:parameters").process(frame:getParent().args, params) return m_IPA.XSAMPA_to_IPA(args[1] or "[Eg'zA:mp5=]") end -- Used by [[Template:X2IPA]] function export.X2IPAtemplate(frame) local parent_args = frame.getParent and frame:getParent().args or frame local compat = parent_args["lang"] local offset = compat and 0 or 1 local params = { [compat and "lang" or 1] = {required = true, default = "und"}, [1 + offset] = {list = true, allow_holes = true}, ["ref"] = {list = true, allow_holes = true}, -- Came before 'ref' but too obscure ["n"] = {list = true, allow_holes = true, alias_of = "ref"}, ["qual"] = { list = true, allow_holes = true }, } local args = require("Module:parameters").process(parent_args, params) local m_XSAMPA = require("Module:IPA/X-SAMPA") local pronunciations, refs, qualifiers, lang = args[1 + offset], args["ref"], args["qual"], args[compat and "lang" or 1] local output = {} table.insert(output, "{{IPA") table.insert(output, "|" .. lang) for i = 1, math.max(pronunciations.maxindex, refs.maxindex, qualifiers.maxindex) do if pronunciations[i] then table.insert(output, "|" .. m_XSAMPA.XSAMPA_to_IPA(pronunciations[i])) end if refs[i] then table.insert(output, "|ref" .. i .. "=" .. refs[i]) end if qualifiers[i] then table.insert(output, "|qual" .. i .. "=" .. qualifiers[i]) end end table.insert(output, "}}") return table.concat(output) end -- Used by [[Template:X2IPAchar]] function export.X2IPAchar(frame) local params = { [1] = { list = true, allow_holes = true }, ["ref"] = {list = true, allow_holes = true}, -- Came before 'ref' but too obscure ["n"] = {list = true, allow_holes = true, alias_of = "ref"}, ["qual"] = { list = true, allow_holes = true }, -- FIXME, remove this. ["lang"] = {}, } local args = require("Module:parameters").process(frame:getParent().args, params) -- [[Special:WhatLinksHere/Template:tracking/X2IPAchar/lang]] if args.lang then require("Module:debug").track("X2IPAchar/lang") end local m_XSAMPA = require("Module:IPA/X-SAMPA") local pronunciations, refs, qualifiers, lang = args[1], args["ref"], args["qual"], args["lang"] local output = {} table.insert(output, "{{IPAchar") for i = 1, math.max(pronunciations.maxindex, refs.maxindex, qualifiers.maxindex) do if pronunciations[i] then table.insert(output, "|" .. m_XSAMPA.XSAMPA_to_IPA(pronunciations[i])) end if refs[i] then table.insert(output, "|ref" .. i .. "=" .. refs[i]) end if qualifiers[i] then table.insert(output, "|qual" .. i .. "=" .. qualifiers[i]) end end if lang then table.insert(output, "|lang=" .. lang) end table.insert(output, "}}") return table.concat(output) end -- Used by [[Template:x2rhymes]] function export.X2rhymes(frame) local parent_args = frame.getParent and frame:getParent().args or frame local compat = parent_args["lang"] local offset = compat and 0 or 1 local params = { [compat and "lang" or 1] = {required = true, default = "und"}, [1 + offset] = {required = true, list = true, allow_holes = true}, } local args = require("Module:parameters").process(parent_args, params) local m_XSAMPA = require("Module:IPA/X-SAMPA") pronunciations, lang = args[1 + offset], args[compat and "lang" or 1] local output = {} table.insert(output, "{{rhymes") table.insert(output, "|" .. lang) for i = 1, pronunciations.maxindex do if pronunciations[i] then table.insert(output, "|" .. m_XSAMPA.XSAMPA_to_IPA(pronunciations[i])) end end table.insert(output, "}}") return table.concat(output) end return export fertbyhcrc4gw6c99oyklgsx627amxy 828 2958 8270 2022-07-21T18:41:38Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local export = {} -- [[Module:IPA/data]] local m_data = mw.loadData('Module:IPA/data') -- [[Module:IPA/data]] local m_symbols = mw.loadData('Module:IPA/data/symbols') -- [[Module:IPA/data/symbols]] local m_syllables -- [[Module:syllables]]; loaded below if needed local sub = mw.ustring.sub local find = mw.ustring.find local gsub = mw.ustring.gsub local match = mw.ustring.match local gmatch = mw.ustring.gmatch local U = mw.ustring.char function export.format_IPA_full(lang, items, err, separator, sortKey, no_count) local IPA_key, key_link, err_text, prefix, IPAs, category local hasKey = m_data.langs_with_infopages local namespace = mw.title.getCurrentTitle().nsText if err then err_text = '<span class="error">' .. err .. '</span>' else if hasKey[lang:getCode()] then IPA_key = "Appendix:" .. lang:getCanonicalName() .. " pronunciation" else IPA_key = "wikipedia:" .. lang:getCanonicalName() .. " phonology" end key_link = "[[" .. IPA_key .. "|key]]" end local prefix = "[[Wiktionary:International Phonetic Alphabet|IPA]]^{(" .. ( key_link or err_text ) .. ")}:&#32;" IPAs = export.format_IPA_multiple(lang, items, separator, no_count) if lang and (namespace == "" or namespace == "Reconstruction") then sortKey = sortKey or lang:makeSortKey(mw.title.getCurrentTitle().text) sortKey = sortKey and ("|" .. sortKey) or "" category = "[[Category:" .. lang:getCanonicalName() .. " terms with IPA pronunciation" .. sortKey .. "]]" else category = "" end return prefix .. IPAs .. category end local function determine_repr(pron) local repr_mark = {} local repr, reconstructed -- remove initial asterisk before representation marks, used on some Reconstruction pages if find(pron, "^%*") then reconstructed = true pron = sub(pron, 2) end local representation_types = { ['/'] = { right = '/', type = 'phonemic', }, ['['] = { right = ']', type = 'phonetic', }, ['⟨'] = { right = '⟩', type = 'orthographic', }, ['-'] = { type = 'rhyme' }, } repr_mark.i, repr_mark.f, repr_mark.left, repr_mark.right = find(pron, '^(.).-(.)$') local representation_type = representation_types[repr_mark.left] if representation_type then if representation_type.right then if repr_mark.right == representation_type.right then repr = representation_type.type end else repr = representation_type.type end else repr = nil end return repr, reconstructed end local function hasInvalidSeparators(transcription) if find(transcription, "%.[ˈˌ]") then return true else return false end end function export.format_IPA_multiple(lang, items, separator, no_count) local categories = {} separator = separator or ', ' -- Format if not items[1] then if mw.title.getCurrentTitle().nsText == "Template" then table.insert(items, {pron = "/aɪ piː ˈeɪ/"}) else table.insert(categories, "[[Category:Pronunciation templates without a pronunciation]]") end end local bits = {} for _, item in ipairs(items) do local bit = export.format_IPA(lang, item.pron) if item.pretext then bit = item.pretext .. bit end if item.posttext then bit = bit .. item.posttext end if item.qualifiers and item.qualifiers[1] then bit = require("Module:qualifier").format_qualifier(item.qualifiers) .. " " .. bit end if item.refs or item.note then local refspecs if item.note then -- FIXME: eliminate item.note in favor of item.refs. Use tracking to find places -- that use item.note. refspecs = {item.note} require("Module:debug").track("IPA/note") else refspecs = item.refs end local refs = {} if #refspecs > 0 then for _, refspec in ipairs(refspecs) do if type(refspec) ~= "table" then refspec = {text = refspec} end local refargs if refspec.name or refspec.group then refargs = {name = refspec.name, group = refspec.group} end table.insert(refs, mw.getCurrentFrame():extensionTag("ref", refspec.text, refargs)) end bit = bit .. table.concat(refs) end end table.insert(bits, bit) --[=[ [[Special:WhatLinksHere/Template:tracking/IPA/syntax-error]] The length or gemination symbol should not appear after a syllable break or stress symbol. ]=] if find(item.pron, "[ˈˌ%.][ːˑ]") then require("Module:debug").track("IPA/syntax-error") end if lang then -- Add syllable count if the language's diphthongs are listed in [[Module:syllables]]. -- Don't do this if the term has spaces or a liaison mark (‿). if not no_count and mw.title.getCurrentTitle().namespace == 0 then m_syllables = m_syllables or require('Module:syllables') local langcode = lang:getCode() if m_data.langs_to_generate_syllable_count_categories[langcode] then local repr = determine_repr(item.pron) local use_it if m_data.langs_to_use_phonetic_notation[langcode] then use_it = repr == "phonetic" else use_it = repr == "phonemic" end if use_it and not find(item.pron, "[ ‿]") then local syllable_count = m_syllables.getVowels(item.pron, lang) if syllable_count then table.insert(categories, "[[Category:" .. lang:getCanonicalName() .. " " .. syllable_count .. "-syllable words]]") end end end end if lang:getCode() == "en" and hasInvalidSeparators(item.pron) then table.insert(categories, "[[Category:IPA for English using .ˈ or .ˌ]]") end end end return table.concat(bits, separator) .. table.concat(categories) end -- Takes an IPA pronunciation and formats it and adds cleanup categories. function export.format_IPA(lang, pron, split_output) local err = {} local categories = {} -- Remove wikilinks, so that wikilink brackets are not misinterpreted as -- indicating phonemic transcription local str_gsub = string.gsub local without_links = str_gsub(pron, '%[%[[^|%]]+|([^%]]+)%]%]', '%1') without_links = str_gsub(without_links, '%[%[[^%]]+%]%]', '%1') -- Detect whether this is a phonemic or phonetic transcription local repr, reconstructed = determine_repr(without_links) if reconstructed then pron = sub(pron, 2) end -- If valid, strip the representation marks if repr == "phonemic" then pron = sub(pron, 2, -2) without_links = sub(without_links, 2, -2) elseif repr == "phonetic" then pron = sub(pron, 2, -2) without_links = sub(without_links, 2, -2) elseif repr == "orthographic" then pron = sub(pron, 2, -2) without_links = sub(without_links, 2, -2) elseif repr == "rhyme" then pron = sub(pron, 2) without_links = sub(without_links, 2) else table.insert(categories, "[[Category:IPA pronunciations with invalid representation marks]]") -- table.insert(err, "invalid representation marks") -- Removed because it's annoying when previewing pronunciation pages. end if pron == "" then table.insert(categories, "[[Category:IPA pronunciations with no pronunciation present]]") end -- Check for obsolete and nonstandard symbols for i, symbol in ipairs(m_data.nonstandard) do local result for nonstandard in gmatch(pron, symbol) do if not result then result = {} end table.insert(result, nonstandard) table.insert(categories, "[[Category:IPA pronunciations with obsolete or nonstandard characters|" .. nonstandard .. "]]") end if result then table.insert(err, "obsolete or nonstandard characters (" .. table.concat(result) .. ")") break end end --[[ Check for invalid symbols after removing the following: 1. wikilinks (handled above) 2. paired HTML tags 3. bolding 4. italics 5. HTML entity for space 6. asterisk at beginning of transcription 7. comma followed by spacing characters 8. superscripts enclosed in superscript parentheses ]] local found_HTML local result = str_gsub(without_links, "<(%a+)[^>]*>([^<]+)</%1>", function(tagName, content) found_HTML = true return content end) result = str_gsub(result, "'''([^']*)'''", "%1") result = str_gsub(result, "''([^']*)''", "%1") result = str_gsub(result, "&[^;]+;", "") -- This may catch things that are not valid character entities. result = str_gsub(result, "^%*", "") result = gsub(result, ",%s+", "") result = gsub(result, "⁽[".. m_symbols.superscripts .. "]+⁾", "") result = gsub(result, '[' .. m_symbols.valid .. ']', '') -- VS15 local vs15_class = "[" .. m_symbols.add_vs15 .. "]" if mw.ustring.find(pron, vs15_class) then local vs15 = U(0xFE0E) if mw.ustring.find(result, vs15) then result = gsub(result, vs15, "") pron = mw.ustring.gsub(pron, vs15, "") end pron = mw.ustring.gsub(pron, "(" .. vs15_class .. ")", "%1" .. vs15) end if result ~= '' then local suggestions = {} mw.log(pron, result) local namespace = mw.title.getCurrentTitle().namespace local category if namespace == 0 then -- main namespace category = "IPA pronunciations with invalid IPA characters" elseif namespace == 118 then -- reconstruction namespace category = "IPA pronunciations with invalid IPA characters/reconstruction" else category = "IPA pronunciations with invalid IPA characters/non_mainspace" end for character in gmatch(result, ".") do local suggestion = m_symbols.suggestions[character] if suggestion then table.insert(suggestions, character .. " with " .. suggestion) end table.insert(categories, "[[Category:" .. category .. "|" .. character .. "]]") end table.insert(err, "invalid IPA characters (" .. result .. ")") if suggestions[1] then table.insert(err, "replace " .. table.concat(suggestions, ", ")) end end if found_HTML then table.insert(categories, "[[Category:IPA pronunciations with paired HTML tags]]") end -- Reference inside IPA template usage -- FIXME: Doesn't work; you can't put HTML in module output. --if mw.ustring.find(pron, '</ref>') then -- table.insert(categories, "[[Category:IPA pronunciations with reference]]") --end if repr == "phonemic" or repr == "rhyme" then if lang and m_data.phonemes[lang:getCode()] then local valid_phonemes = m_data.phonemes[lang:getCode()] local rest = pron local phonemes = {} while mw.ustring.len(rest) > 0 do local longestmatch = "" if sub(rest, 1, 1) == "(" or sub(rest, 1, 1) == ")" then longestmatch = sub(rest, 1, 1) else for _, phoneme in ipairs(valid_phonemes) do if mw.ustring.len(phoneme) > mw.ustring.len(longestmatch) and sub(rest, 1, mw.ustring.len(phoneme)) == phoneme then longestmatch = phoneme end end end if mw.ustring.len(longestmatch) > 0 then table.insert(phonemes, longestmatch) rest = sub(rest, mw.ustring.len(longestmatch) + 1) else local phoneme = sub(rest, 1, 1) table.insert(phonemes, "<span style=\"color: red\">" .. phoneme .. "</span>") rest = sub(rest, 2) table.insert(categories, "[[Category:IPA pronunciations with invalid phonemes/" .. lang:getCode() .. "]]") require("Module:debug").track("IPA/invalid phonemes/" .. phoneme) end end pron = table.concat(phonemes) end if repr == "phonemic" then pron = "/" .. pron .. "/" else pron = "-" .. pron end elseif repr == "phonetic" then pron = "[" .. pron .. "]" elseif repr == "orthographic" then pron = "⟨" .. pron .. "⟩" end if reconstructed then pron = "*" .. pron end if err[1] then err = '<span class="previewonly error" style="font-size: small;>&#32;' .. table.concat(err, ', ') .. '</span>' else err = "" end if split_output then -- for use of IPA in links return '<span class="IPA">' .. pron .. '</span>', table.concat(categories), err else return '<span class="IPA">' .. pron .. '</span>' .. err .. table.concat(categories) end end function export.example(frame) local output = {} local m_links = require('Module:links') local m_languages = require('Module:languages') table.insert( output, [[ {| class="wikitable" ! Term !! IPA !! Generated X-SAMPA !! Regenerated IPA !! Matched? ]] ) local row = [[ |- | link || IPA || XSAMPA || regenerated_IPA || matched ]] local examples = mw.text.split(frame.args[1], ",%s*") local m_XSAMPA = require("Module:IPA/X-SAMPA") for _, example in pairs(examples) do local lang, word = match(example, "(%l%l%l?):(.+) [/%[]") if lang then lang = m_languages.getByCode(lang) or error('"' .. lang .. '" is not a valid language code.') end local IPA = match(example, "/[^/]+/") or match(example, "%[[^%]]+%]") or error('No IPA transcription found in "' .. example .. '".') local XSAMPA = m_XSAMPA.IPA_to_XSAMPA(IPA) local regenerated_IPA = m_XSAMPA.XSAMPA_to_IPA(XSAMPA) content = { link = lang and word and m_links.full_link{ term = word, lang = lang }, matched = IPA == regenerated_IPA and '<span style="color: green;">yes</span>' or '<span style="color: red;">no</span>', IPA = '<span class="IPA">' .. IPA .. '</span>', XSAMPA = '<code>' .. XSAMPA .. '</code>', regenerated_IPA = '<span class="IPA">' .. regenerated_IPA .. '</span>' } local function add_content(item) return content[item] or "" end local row = gsub(row, "[%a_]+", add_content) table.insert(output, row) end table.insert(output, "|}") return table.concat(output) end return export f9zzr4y7bt605p4pj2dovcyvlp77hw4 828 2959 8271 2022-07-21T18:43:06Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local data = {} --[=[ This should list the language codes of all languages that have a pronunciation page in the appendix of the form ''Appendix:LANG pronunciation'', e.g. [[Appendix:Russian pronunciation]]. For these languages, the text "key" next to the generated pronunciation links to such pages; for other languages, it links to the "LANG phonology" page in Wikipedia (which may or may not exist). [[Module:IPA]] is responsible for this linking; see format_IPA_full(). ]=] local langs_with_infopages = { "acw", "ady", "ang", "arc", "ba", "bg", "bo", "ca", "cho", "cmn", "cs", "cv", "cy", "da", "de", "dsb", "dz", "egl", "egy", "el", "en", "enm", "eo", "es", "fa", "fi", "fo", "fr", "fy", "ga", "gd", "gem-pro", "got", "he", "hi", "hu", "hy", "ii", "is", "it", "iu", "ja", "jbo", "ka", "kls", "ko", "kw", "la", "lb", "liv", "lt", "lv", "mdf", "mfe", "mic", "mk", "ms", "mt", "mul", "my", "nan", "nci", "nl", "nn", "no", "nov", "nv", "pjt", "pl", "ps", "pt", "ro", "ru", "scn", "sco", "sga", "sh", "sl", "sq", "sv", "sw", "syc", "th", "tl", "tr", "tyv", "ug", "uk", "vi", "vo", "wlm", "yi", "yue", } data.langs_with_infopages = {} -- Convert the list in `langs_with_infopages` to a set. for _, langcode in ipairs(langs_with_infopages) do data.langs_with_infopages[langcode] = true end --[=[ This should list the diphthongs of a language (in the form of Lua patterns), provided they do *NOT* contain semivowel symbols such as /j w ɰ ɥ/ or vowels with nonsyllabic diacritics such as /i̯ u̯/. For example, list /au/ or /aʊ/, but do not list /aw/ or /au̯/. The data in this table is used to count the number of syllables in a word. [[Module:syllables]] automatically knows how to correctly handle semivowel symbols and nonsyllabic diacritics. Any language listed here will automatically have categories of the form "LANG #-syllable words" generated. In addition, any language listed below under `langs_to_generate_syllable_count_categories` will also have such categories generated. NOTE: There are some additional languages that have these categories. For example: * Thai words have these categories added by [[Module:th-pron]]. ]=] data.diphthongs = { ["cs"] = { -- [[w:Czech phonology#Diphthongs]] "[aeo]u", }, ["de"] = { "a[ɪʊ]", "ɔ[ʏɪ]", }, ["en"] = { -- from [[Appendix:English pronunciation]] mostly, but /ʌɪ/ is from the OED "[aɑeɛoɔʌ][ɪi]", "[ɑɒæo]e", "[əɐ]ʉ", "[aɒəoɔʌ]ʊ", "æo", "[ɛeɪiɔʊʉ]ə", -- /iə/ is a diphthong in NZE, but a disyllabic sequence in GA. -- /ɪə/ is both a disyllabic sequence and a diphthong in old-fashioned RP. "[aʌ][ʊɪ]ə", -- May be a disyllabic sequence in some or all dialects? }, ["grc"] = { "[aeyo]i", "[ae]u", "[ɛɔa]ː[iu]", }, ["is"] = { -- [[w:Icelandic phonology#Vowels]] "[aeø][iɪy]", -- Wikipedia is oddly specific about the second element: ei and ai, but øɪ. "[ao]u", }, ["it"] = { "[aeɛoɔu]i", "[aeɛioɔ]u", }, ["la"] = { "[eaou]i", "[eao]u", "[ao]e", }, ["lb"] = { "[iu]ə", "[ɜoæɑ]ɪ", "[əæɑ]ʊ", }, } --[=[ This should list any languages for which categories of the form "LANG #-syllable words", e.g. [[:Category:Russian 3-syllable words]], should be generated. Do not list languages here if they have an entry above under `data.diphthongs`; such languages are automatically added to this list. ]=] local langs_to_generate_syllable_count_categories = { "ar", -- Arabic has diphthongs, but they are transcribed -- with semivowel symbols. "ary", -- Moroccan Arabic has diphthongs, but they are transcribed -- with semivowel symbols. "ca", -- Catalan has diphthongs, but they are generally transcribed using -- /w/ and /j/, so do not need to be listed (see [[w:Catalan language#Diphthongs and triphthongs]]. "es", -- Spanish has diphthongs, but they are transcribed with i̯ etc. "fi", -- Finnish has diphthongs, but they are now automatically transcribed with -- the nonsyllabic diacritic "fr", -- French has diphthongs, but they are transcribed -- with semivowel symbols: [[w:French phonology#Glides and diphthongs]]. "ka", "kmr", "ku", "mk", "mt", -- Maltese has diphthongs, but they are transcribed -- with semivowel symbols. "pl", -- No diphthongs, properly speaking; sequences of a vowel and /w/ or /j/ though. "ru", -- No diphthongs, properly speaking; sequences of a vowel and /j/ though. "sk", -- Slovak has rising diphthongs, /i̯e, i̯a, i̯u, u̯o/, which are probably always spelled with the nonsyllabic diacritic, so do not need to be listed. "sl", -- No diphthongs, properly speaking; sequences of a vowel, /j/ and /w/ though "sq", -- [[w:Albanian language#Vowels]] doesn't mention anything about diphthongs. "ug", -- No diphthongs. } data.langs_to_generate_syllable_count_categories = {} -- Convert the list in `langs_to_generate_syllable_count_categories` to a set. for _, langcode in ipairs(langs_to_generate_syllable_count_categories) do data.langs_to_generate_syllable_count_categories[langcode] = true end -- Also add languages listed under `data.diphthongs`. for langcode, _ in pairs(data.diphthongs) do data.langs_to_generate_syllable_count_categories[langcode] = true end -- Languages to use the phonetic not phonemic notation to compute syllables counts. local langs_to_use_phonetic_notation = { "es", "mk", "ru", } data.langs_to_use_phonetic_notation = {} -- Convert the list in `langs_to_use_phonetic_notation` to a set. for _, langcode in ipairs(langs_to_use_phonetic_notation) do data.langs_to_use_phonetic_notation[langcode] = true end -- Non-standard or obsolete IPA symbols. data.nonstandard = { --[[ The following symbols consist of more than one character, so we can't put them in the line below. ]] "ɑ̢", "d̂", "t̂", "n̂", "l̂", "k̫", "ɔ̗", "ɔ̖", "[ʦʣʧʤʨʥ?ƍσƺƪƻƾƞᶀᶁᶂᶃᶄᶅᶆᶈᶇᶉᶊᶋƫᶌᶍᶎʓʆλƛłščžǰǧǯẋᵻᵿⱻʚ" .. "ɷωıȹȸ∅ØƥƭƈƙʠʇʗʖʞɩɼȣяɿʅʮʯᴀᴀᴇGRŒQȡȶȵȴKPT]" } -- See valid IPA characters at [[Module:IPA/data/symbols]]. data.phonemes = {} data.phonemes["dz"] = { "m", "n", "ŋ", "p", "t", "ʈ", "k", "pʰ", "tʰ", "ʈʰ", "kʰ", "t͡s", "t͡ɕ", "t͡sʰ", "t͡ɕʰ", "w", "s", "z", "ɬ", "l", "r", "ɕ", "ʑ", "j", "h", "ɑ", "e", "i", "o", "u", "ɑː", "eː", "ɛː", "iː", "oː", "øː", "uː", "yː", "ɑ˥", "e˥", "i˥", "o˥", "u˥", "ɑː˥", "eː˥", "ɛː˥", "iː˥", "oː˥", "øː˥", "uː˥", "yː˥", "m˥", "n˥", "ŋ˥", "p˥", "k˥", "k̚˥", "w˥", "l˥", "r˥", "ɕ˥", "j˥", ")˥", "ɑ˩", "e˩", "i˩", "o˩", "u˩", "ɑː˩", "eː˩", "ɛː˩", "iː˩", "oː˩", "øː˩", "uː˩", "yː˩", "m˩", "n˩", "ŋ˩", "p˩", "k˩", "k̚˩", "w˩", "l˩", "r˩", "ɕ˩", "j˩", ")˩", ".", ",", "-", } data.phonemes["eo"] = { "a", "b", "d", "d͡ʒ", "e", "f", "h", "i", "j", "k", "l", "m", "n", "o", "p", "r", "s", "t", "t͡s", "t͡ʃ", "u", "v", "w", "x", "z", "ɡ", "ʃ", "ʒ", "ˈ", ".", " ", "-", } data.phonemes["hy"] = { "ɑ", "b", "ɡ", "d", "ɛ", "z", "ɛ", "ə", "tʰ", "ʒ", "i", "l", "χ", "t͡s", "k", "h", "d͡z", "ʁ", "t͡ʃ", "m", "j", "n", "ʃ", "ɔ", "t͡ʃʰ", "p", "d͡ʒ", "r", "s", "v", "t", "ɾ", "t͡sʰ", "v", "pʰ", "kʰ", "ɔ", "f", "ŋɡ", "ŋk", "ŋχ", "u", "ˈ", "ˌ", ".", " ", "ː", } data.phonemes["nl"] = { "m", "n", "ŋ", "p", "b", "t", "d", "k", "ɡ", "f", "v", "s", "z", "ʃ", "ʒ", "x", "ɣ", "ɦ", "ʋ", "l", "j", "r", "ɪ", "ʏ", "ɛ", "ə", "ɔ", "ɑ", "i", "iː", "y", "yː", "u", "uː", "eː", "øː", "oː", "ɛː", "œː", "ɔː", "aː", "ɛi̯", "œy̯", "ɔi̯", "ɑu̯", "ɑi̯", "iu̯", "yu̯", "ui̯", "eːu̯", "oːi̯", "aːi̯", "ˈ", "ˌ", ".", " ", } return data 84jgjvqkd6f56yaicj1wroxsm0makkb 828 2960 8272 2022-07-21T18:45:11Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local data = {} --[=[ Valid IPA symbols. Currently almost all values of "title" and "link" keys are just the comments that were used in [[Module:IPA]]. The "link" fields should be checked (those that start with an uppercase letter are checked). ]=] local U = mw.ustring.char data[1] = { -- PULMONIC CONSONANTS -- nasal ["m"] = { title = "bilabial nasal", link = "w:Bilabial nasal", }, ["ɱ"] = { title = "labiodental nasal", link = "w:Labiodental nasal", }, ["n"] = { title = "alveolar nasal", link = "w:Alveolar nasal", }, ["ɳ"] = { title = "retroflex nasal", link = "w:Retroflex nasal", }, ["ɲ"] = { title = "palatal nasal", link = "w:Palatal nasal", }, ["ŋ"] = { title = "velar nasal", link = "w:Velar nasal", }, ["ɴ"] = { title = "uvular nasal", link = "w:Uvular nasal", }, -- plosive ["p"] = { title = "voiceless bilabial plosive", link = "w:Voiceless bilabial stop", }, ["b"] = { title = "voiced bilabial plosive", link = "w:Voiced bilabial stop", }, ["t"] = { title = "voiceless alveolar plosive", link = "w:Voiceless alveolar stop", }, ["d"] = { title = "voiced alveolar plosive", link = "w:Voiced alveolar stop", }, ["ʈ"] = { title = "voiceless retroflex plosive", link = "w:Voiceless retroflex stop", }, ["ɖ"] = { title = "voiced retroflex plosive", link = "w:Voiced retroflex stop", }, ["c"] = { title = "voiceless palatal plosive", link = "w:Voiceless palatal stop", }, ["ɟ"] = { title = "voiced palatal plosive", link = "w:Voiced palatal stop", }, ["k"] = { title = "voiceless velar plosive", link = "w:Voiceless velar stop", }, ["ɡ"] = { title = "voiced velar plosive", link = "w:Voiced velar stop", }, ["q"] = { title = "voiceless uvular plosive", link = "w:Voiceless uvular stop", }, ["ɢ"] = { title = "voiced uvular plosive", link = "w:Voiced uvular stop", }, ["ʡ"] = { title = "epiglottal plosive", link = "w:Epiglottal stop", }, ["ʔ"] = { title = "glottal stop", link = "w:Glottal stop", }, -- fricative ["ɸ"] = { title = "voiceless bilabial fricative", link = "w:Voiceless bilabial fricative", }, ["β"] = { title = "voiced bilabial fricative", link = "w:Voiced bilabial fricative", }, ["f"] = { title = "voiceless labiodental fricative", link = "w:Voiceless labiodental fricative", }, ["v"] = { title = "voiced labiodental fricative", link = "w:Voiced labiodental fricative", }, ["θ"] = { title = "voiceless dental fricative", link = "w:Voiceless dental fricative", }, ["ð"] = { title = "voiced dental fricative", link = "w:Voiced dental fricative", }, ["s"] = { title = "voiceless alveolar fricative", link = "w:Voiceless alveolar fricative", }, ["z"] = { title = "voiced alveolar fricative", link = "w:Voiced alveolar fricative", }, ["ʃ"] = { title = "voiceless postalveolar fricative", link = "w:Voiceless palato-alveolar sibilant", }, ["ʒ"] = { title = "voiced postalveolar fricative", link = "w:Voiced palato-alveolar sibilant", }, ["ʂ"] = { title = "voiceless retroflex fricative", link = "w:Voiceless retroflex sibilant", }, ["ʐ"] = { title = "voiced retroflex fricative", link = "w:Voiced retroflex sibilant", }, ["ɕ"] = { title = "voiceless alveolo-palatal fricative", link = "w:Voiceless alveolo-palatal sibilant", }, ["ʑ"] = { title = "voiced alveolo-palatal fricative", link = "w:Voiced alveolo-palatal sibilant", }, ["ç"] = { title = "voiceless palatal fricative", link = "w:Voiceless palatal fricative", }, ["ʝ"] = { title = "voiced palatal fricative", link = "w:Voiced palatal fricative", }, ["x"] = { title = "voiceless velar fricative", link = "w:Voiceless velar fricative", }, ["ɣ"] = { title = "voiced velar fricative", link = "w:Voiced velar fricative", }, ["χ"] = { title = "voiceless uvular fricative", link = "w:Voiceless uvular fricative", }, ["ʁ"] = { title = "voiced uvular fricative", link = "w:Voiced uvular fricative", }, ["ħ"] = { title = "voiceless pharyngeal fricative", link = "w:Voiceless pharyngeal fricative", }, ["ʕ"] = { title = "voiced pharyngeal fricative", link = "w:Voiced pharyngeal fricative", }, ["ʜ"] = { title = "voiceless epiglottal fricative", link = "w:Voiceless epiglottal fricative", }, ["ʢ"] = { title = "voiced epiglottal fricative", link = "w:Voiced epiglottal fricative", }, ["h"] = { title = "voiceless glottal fricative", link = "w:Voiceless glottal fricative", }, ["ɦ"] = { title = "voiced glottal fricative", link = "w:Voiced glottal fricative", }, -- approximant ["ʋ"] = { title = "labiodental approximant", link = "w:Labiodental approximant", }, ["ɹ"] = { title = "alveolar approximant", link = "w:Alveolar approximant", }, ["ɻ"] = { title = "retroflex approximant", link = "w:Retroflex approximant", }, ["j"] = { title = "palatal approximant", link = "w:Palatal approximant", }, ["ɰ"] = { title = "velar approximant", link = "w:Velar approximant", }, -- tap, flap ["ⱱ"] = { title = "labiodental tap", link = "w:Labiodental flap", }, ["ɾ"] = { title = "alveolar flap", link = "w:Alveolar flap", }, ["ɽ"] = { title = "retroflex flap", link = "w:Retroflex flap", }, -- trill ["ʙ"] = { title = "bilabial trill", link = "w:Bilabial trill", }, ["r"] = { title = "alveolar trill", link = "w:Alveolar trill", }, ["ʀ"] = { title = "uvular trill", link = "w:Uvular trill", }, ["ᴙ"] = { title = "epiglottal trill", link = "w:Epiglottal trill", }, -- lateral fricative ["ɬ"] = { title = "voiceless alveolar lateral fricative", link = "w:Voiceless alveolar lateral fricative", }, ["ɮ"] = { title = "voiced alveolar lateral fricative", link = "w:Voiced alveolar lateral fricative", }, -- no precomposed Unicode character --TOMOVE --["ɬ̢"] = {title = "voiceless retroflex lateral fricative", link = "w:voiceless retroflex lateral fricative"}, -- no precomposed Unicode character --TOMOVE:3 --["ʎ̝̊"] = {title = "voiceless palatal lateral fricative", link = "w:voiceless palatal lateral fricative"}, -- no precomposed Unicode character --TOMOVE:3 --["ʟ̝̊"] = {title = "voiceless velar lateral fricative", link = "w:voiceless velar lateral fricative"}, -- no precomposed Unicode character --TOMOVE --["ʟ̝"] = {title = "voiced velar lateral fricative", link = "w:voiced velar lateral fricative"}, -- lateral approximant ["l"] = { title = "alveolar lateral approximant", link = "w:Alveolar lateral approximant", }, ["ɭ"] = { title = "retroflex lateral approximant", link = "w:Retroflex lateral approximant", }, ["ʎ"] = { title = "palatal lateral approximant", link = "w:Palatal lateral approximant", }, ["ʟ"] = { title = "velar lateral approximant", link = "w:Velar lateral approximant", }, -- lateral flap ["ɺ"] = { title = "alveolar lateral flap", link = "w:Alveolar lateral flap", }, --["ɭ̆"] = {title = "retroflex lateral flap", link = "w:retroflex lateral flap"}, -- no precomposed Unicode character --TOMOVE --["ɺ˞"] = {title = "retroflex lateral flap", link = "w:retroflex lateral flap"}, -- no precomposed Unicode character --TOMOVE -- NON-PULMONIC CONSONANTS -- clicks ["ʘ"] = { title = "bilabial click", link = "w:Bilabial clicks", }, ["ǀ"] = { title = "dental click", link = "w:Dental clicks", }, ["ǃ"] = { title = "postalveolar click", link = "w:Alveolar clicks", }, ["‼"] = { title = "subapical retroflex", link = "w:Retroflex clicks", }, -- NOT IN X-SAMPA ["ǂ"] = { title = "palatal click", link = "w:Palatal clicks", }, ["ǁ"] = { title = "alveolar lateral click", link = "w:Lateral clicks", }, -- implosives ["ɓ"] = { title = "voiced bilabial implosive", link = "w:Voiced bilabial implosive", }, ["ɗ"] = { title = "voiced alveolar implosive", link = "w:Voiced alveolar implosive", }, -- NOT IN X-SAMPA ["ᶑ"] = { title = "retroflex implosive", link = "w:Voiced retroflex implosive", }, ["ʄ"] = { title = "voiced palatal implosive", link = "w:Voiced palatal implosive", }, ["ɠ"] = { title = "voiced velar implosive", link = "w:Voiced velar implosive", }, ["ʛ"] = { title = "voiced uvular implosive", link = "w:Voiced uvular implosive", }, -- ejectives ["ʼ"] = { title = "ejective", link = "w:Ejective consonant", }, -- CO-ARTICULATED CONSONANTS ["ʍ"] = { title = "voiceless labial-velar fricative", link = "w:Voiceless labio-velar approximant", }, ["w"] = { title = "labial-velar approximant", link = "w:Labio-velar approximant", }, ["ɥ"] = { title = "labial-palatal approximant", link = "w:Labialized palatal approximant", }, ["ɧ"] = { title = "voiceless palatal-velar fricative", link = "w:Sj-sound", }, -- should be handled in [[Module:IPA]] and not through this table -- BRACKETS --[[ -- ["//"] = { title = "morphophonemic", link = "w:morphophonemic", }, ["/"] = { title = "phonemic", link = "w:phonemic", }, ["["] = { title = "phonetic", link = "w:phonetic", }, ["["] = { title = "phonetic", link = "w:phonetic", }, ["〈"] = { title = "orthographic", link = "w:orthographic", }, ["〉"] = { title = "orthographic", link = "w:orthographic", }, ["⟨"] = { title = "orthographic", link = "w:orthographic", }, ["⟩"] = { title = "orthographic", link = "w:orthographic", }, ]] -- VOWELS -- close ["i"] = { title = "close front unrounded vowel", link = "w:Close front unrounded vowel", }, ["y"] = { title = "close front rounded vowel", link = "w:Close front rounded vowel", }, ["ɨ"] = { title = "close central unrounded vowel", link = "w:Close central unrounded vowel", }, ["ʉ"] = { title = "close central rounded vowel", link = "w:Close central rounded vowel", }, ["ɯ"] = { title = "close back unrounded vowel", link = "w:Close back unrounded vowel", }, ["u"] = { title = "close back rounded vowel", link = "w:Close back rounded vowel", }, -- near close ["ɪ"] = { title = "near-close near-front unrounded vowel", link = "w:Near-close near-front unrounded vowel", }, ["ʏ"] = { title = "near-close near-front rounded vowel", link = "w:Near-close near-front rounded vowel", }, ["ᵻ"] = { title = "near-close central unrounded vowel", link = "w:Near-close central unrounded vowel", }, -- (alternative) --TOMOVE --[[ ["ɪ̈"] = { title = "near-close central unrounded vowel", link = "w:near-close central unrounded vowel", }, ]] ["ᵿ"] = { title = "near-close central rounded vowel", link = "w:Near-close central rounded vowel", }, --[[ (alternative) TOMOVE ["ʊ̈"] = { title = "near-close central rounded vowel", link = "w:near-close central rounded vowel", }, ]] ["ʊ"] = { title = "near-close near-back rounded vowel", link = "w:Near-close near-back rounded vowel", }, --close mid ["e"] = { title = "close-mid front unrounded vowel", link = "w:Close-mid front unrounded vowel", }, ["ø"] = { title = "close-mid front rounded vowel", link = "w:Close-mid front rounded vowel", }, ["ɘ"] = { title = "close-mid central unrounded vowel", link = "w:Close-mid central unrounded vowel", }, ["ɵ"] = { title = "close-mid central rounded vowel", link = "w:Close-mid central rounded vowel", }, ["ɤ"] = { title = "close-mid back unrounded vowel", link = "w:Close-mid back unrounded vowel", }, ["o"] = { title = "close-mid back rounded vowel", link = "w:Close-mid back rounded vowel", }, -- mid ["ə"] = { title = "schwa", link = "w:Schwa", }, ["ɚ"] = { title = "schwa+r", link = "w:R-colored vowel", }, -- open mid ["ɛ"] = { title = "open-mid front unrounded vowel", link = "w:Open-mid front unrounded vowel", }, ["œ"] = { title = "open-mid front rounded vowel", link = "w:Open-mid front rounded vowel", }, ["ɜ"] = { title = "open-mid central unrounded vowel", link = "w:Open-mid central unrounded vowel", }, ["ɝ"] = { title = "open-mid central unrounded vowel+r", link = "w:R-colored vowel", }, ["ɞ"] = { title = "open-mid central rounded vowel", link = "w:Open-mid central rounded vowel", }, ["ʌ"] = { title = "open-mid back unrounded vowel", link = "w:Open-mid back unrounded vowel", }, ["ɔ"] = { title = "open-mid back rounded vowel", link = "w:Open-mid back rounded vowel", }, -- near open ["æ"] = { title = "near-open front unrounded vowel", link = "w:Near-open front unrounded vowel", }, ["ɐ"] = { title = "near-open central vowel", link = "w:Near-open central vowel", }, -- open ["a"] = { title = "open front unrounded vowel", link = "w:Open front unrounded vowel", }, ["ɶ"] = { title = "open front rounded vowel", link = "w:Open front rounded vowel", }, ["ɑ"] = { title = "open back unrounded vowel", link = "w:Open back unrounded vowel", }, ["ɒ"] = { title = "open back rounded vowel", link = "w:Open back rounded vowel", }, -- SUPRASEGMENTALS ["ˈ"] = {title = "primary stress", link = "w:Stress (linguistics)", XSAMPA = "\""}, --[[ ["???"] = { title = "extra stress: no Unicode char; double primary stress instead", link = "w:extra stress: no Unicode char; double primary stress instead", XSAMPA = "" }, --TOMOVE:3 ]] ["ˌ"] = { title = "secondary stress", link = "w:Secondary stress", }, ["ː"] = { title = "long", link = "w:Length (phonetics)", }, ["ˑ"] = { title = "half long", link = "w:Length (phonetics)", }, ["̆"] = { title = "extra-short", link = "w:Length (phonetics)", }, --[[ ["%."] = { title = "syllable break", link = "w:syllable break", }, ]] --TOMOVE ["‿"] = { title = "linking mark (absence of a break)", link = "w:Tie (typography)#International_Phonetic_Alphabet", }, [" "] = { title = "separator", link = "w:separator", }, -- TONE -- level tones ["˥"] = { title = "top", link = "w:Tone letter", }, ["˦"] = { title = "high", link = "w:Tone letter", }, ["˧"] = { title = "mid", link = "w:Tone letter", }, ["˨"] = { title = "low", link = "w:Tone letter", }, ["˩"] = { title = "bottom", link = "w:Tone letter", }, ["̋"] = { title = "extra high tone", link = "w:Tone letter", }, ["́"] = { title = "high tone", link = "w:Tone letter", }, ["̄"] = { title = "mid tone", link = "w:Tone letter", }, ["̀"] = { title = "low tone", link = "w:Tone letter", }, ["̏"] = { title = "extra low tone", link = "w:Tone letter", }, -- tone terracing ["ꜛ"] = { title = "upstep", link = "w:Upstep", }, ["ꜜ"] = { title = "downstep", link = "w:Downstep", }, -- contour tones ["̌"] = { title = "rising tone", link = "w:Tone (linguistics)", }, ["̂"] = { title = "falling tone", link = "w:Tone (linguistics)", }, ["᷄"] = { title = "high rising tone", link = "w:Tone (linguistics)", }, ["᷅"] = { title = "low rising tone", link = "w:Tone (linguistics)", }, ["᷇"] = { title = "high falling tone", link = "w:Tone (linguistics)", }, ["᷆"] = { title = "low falling tone", link = "w:Tone (linguistics)", }, ["᷈"] = { title = "rising falling tone (peaking)", link = "w:Tone (linguistics)", }, ["᷉"] = { title = "dipping", link = "w:Tone (linguistics)", }, -- [extrapolated from the chart -- please confirm] -- intonation ["|"] = { title = "minor (foot) group", link = "w:Prosodic unit", }, ["‖"] = { title = "major (intonation) group", link = "w:Prosodic unit", }, ["↗"] = { title = "global rise", link = "w:Intonation (linguistics)", }, ["↘"] = { title = "global fall", link = "w:Intonation (linguistics)", }, -- DIACRITICS -- syllabicity & releases ["̩"] = { title = "syllabi ", link = "w:Syllabic consonant", withdescender = "̍" }, -- (or "_=" ["̯"] = { title = "non-syllabic", link = "w:Semivowel", withdescender = "̑" }, ["ʰ"] = { title = "aspirated", link = "w:Aspirated consonant", }, ["ⁿ"] = { title = "nasal release", link = "w:Nasal release", }, ["ˡ"] = { title = "lateral release", link = "w:Lateral release (phonetics)", }, ["̚"] = { title = "no audible release", link = "w:No audible release", }, -- phonation ["̥"] = { title = "voiceless", link = "w:Voicelessness", withdescender = "̊" }, ["̬"] = { title = "voiced", link = "w:Voice (phonetics)", }, ["̤"] = { title = "breathy voice", link = "w:Breathy voice", }, ["̰"] = { title = "creaky voice", link = "w:Creaky voice", }, ["᷽"] = { title = "strident", link = "w:Strident vowel", }, -- primary articulation ["̪"] = { title = "dental", link = "w:Dental consonant", }, ["̺"] = { title = "apical", link = "w:Apical consonant", }, ["̻"] = { title = "laminal", link = "w:Laminal consonant", }, ["̟"] = { title = "advanced", link = "w:Relative articulation#Advanced_and_retracted", withdescender = "˖" }, ["̠"] = { title = "retracted", link = "w:Relative articulation#Retracted", withdescender = "˗" }, ["̼"] = { title = "linguolabial", link = "w:Linguolabial consonant", }, ["̈"] = { title = "centralized", link = "w:Relative articulation#Centralized_vowels", XSAMPA = "_\"" }, ["̽"] = { title = "mid-centralized", link = "Relative articulation#Mid-centralized_vowel", }, ["̞"] = { title = "lowered", link = "w:Relative articulation#Raised_and_lowered", withdescender = "˕" }, ["̝"] = { title = "raised", link = "w:Relative articulation#Raised_and_lowered", withdescender = "˔" }, ["͡"] = { title = "coarticulated", link = "w:Co-articulated consonant", }, ["͈"] = { title = "strong articulation", link = "w:Fortis and lenis", }, -- secondary articulation ["ʷ"] = { title = "labialized", link = "w:Labialization", }, ["ʲ"] = { title = "palatalized", link = "w:Palatalization (phonetics)", }, ["ˠ"] = { title = "velarized", link = "w:Velarization", }, ["ˤ"] = { title = "pharyngealized", link = "w:Pharyngealization", }, -- also see _e ["ɫ"] = { title = "velarized alveolar lateral approximant", link = "w:Alveolar lateral approximant", }, ["̴"] = { title = "velarized or pharyngealized; also see 5", link = "w:Velarization", }, ["̹"] = { title = "more rounded", link = "w:Roundedness", }, ["̜"] = { title = "less rounded", link = "w:Roundedness", }, ["̃"] = { title = "nasalization", link = "w:Nasalization", }, ["˞"] = { title = "rhotacization in vowels, retroflexion in consonants", link = "w:R-colored vowel", }, ["̘"] = { title = "advanced tongue root", link = "w:Advanced and retracted tongue root", }, ["̙"] = { title = "retracted tongue root", link = "w:Advanced and retracted tongue root", }, } data[2] = { -- TODO --["%("] = {}, --["%)"] = {}, ["ːː"] = { title = "extra long", link = "w:Length (phonetics)", }, ["r̥"] = {title = "voiceless alveolar trill", link = "w:Voiceless alveolar trill"}, ["ɬ’"] = {title = "alveolar lateral ejective fricative", link = "w:Alveolar lateral ejective fricative"}, } data[3] = { ["t͡s"] = {title = "voiceless alveolar sibilant affricate", link = "w:Voiceless alveolar affricate"}, ["d͡z"] = {title = "voiced alveolar sibilant affricate", link = "w:Voiced alveolar affricate"}, ["t͡ʃ"] = {title = "voiceless palato-alveolar affricate", link = "w:Voiceless palato-alveolar affricate", descender = true}, ["d͡ʒ"] = {title = "voiced palato-alveolar affricate", link = "w:Voiced palato-alveolar affricate"}, ["ʈ͡ʂ"] = {title = "voiceless retroflex affricate", link = "w:Voiceless retroflex affricate", descender = true}, ["ɖ͡ʐ"] = {title = "voiced retroflex affricate", link = "w:Voiced retroflex affricate, descender = true"}, ["t͡ɕ"] = {title = "voiceless alveolo-palatal affricate", link = "w:Voiceless alveolo-palatal affricate"}, ["d͡ʑ"] = {title = "voiced alveolo-palatal affricate", link = "w:Voiced alveolo-palatal affricate"}, ["c͡ç"] = {title = "voiceless palatal affricate", link = "w:Voiceless palatal affricate, descender = true"}, ["ɟ͡ʝ"] = {title = "voiced palatal affricate", link = "w:Voiced palatal affricate, descender = true"}, ["k͡x"] = {title = "voiceless velar affricate", link = "w:Voiceless velar affricate"}, ["ɡ͡ɣ"] = {title = "voiced velar affricate", link = "w:Voiced velar affricate, descender = true"}, } data[4] = { ["ǃ͡qʼ"] = {title = "alveolar linguo-glottalic stop", link = "w:Ejective-contour clicks, descender = true"}, ["ǁ͡χʼ"] = {title = "lateral linguo-glottalic affricate (homorganic)", link = "w:Ejective-contour clicks", descender = true}, } data[5] = { ["k͡ʟ̝̊"] = {title = "voiceless velar lateral affricate", link = "w:Voiceless velar lateral affricate"}, ["ᶢǀ͡qʼ"] = {title = "voiced dental linguo-glottalic stop", link = "w:Ejective-contour clicks"}, ["ǂ͡kxʼ"] = {title = "palatal linguo-glottalic affricate (heterorganic)", link = "w:Ejective-contour clicks"}, } data[6] = { ["k͡ʟ̝̊ʼ"] = {title = "velar lateral ejective affricate", link = "w:Velar lateral ejective affricate"}, ["ᶢʘ͡kxʼ"] = {title = "voiced labial linguo-glottalic affricate", link = "w:Ejective-contour clicks"}, } -- acute and grave tone marks data["diacritics"] = -- grave, acute, circumflex, tilde, macron, breve U(0x300) .. U(0x301) .. U(0x302) .. U(0x303) .. U(0x304) .. U(0x306) -- diaeresis, ring above, double acute, caron, vertical line above, double grave, left tack .. U(0x308) .. U(0x30A) .. U(0x30B) .. U(0x30C) .. U(0x30D) .. U(0x30F) .. U(0x318) -- right tack, left angle, left half ring below, up tack below, down tack below, plus sign below .. U(0x319) .. U(0x31A) .. U(0x31C) .. U(0x31D) .. U(0x31E) .. U(0x31F) -- minus sign below, rhotic hook below, dot below, diaeresis below, ring below, vertical line below, bridge below .. U(0x320) .. U(0x322) .. U(0x323) .. U(0x324) .. U(0x325) .. U(0x329) .. U(0x32A) -- caron below, inverted breve below .. U(0x32C) .. U(0x32F) -- tilde below, right half ring below, inverted bridge below, square below, seagull below, x above .. U(0x330) .. U(0x339) .. U(0x33A) .. U(0x33B) .. U(0x33C) .. U(0x33D) -- grave tone mark, acute tone mark, bridge above, equals sign below, double vertical line below .. U(0x340) .. U(0x341) .. U(0x346) .. U(0x347) .. U(0x348) -- left angle below, not tilde above, homothetic above, almost equal above, left right arrow below .. U(0x349) .. U(0x34A) .. U(0x34B) .. U(0x34C) .. U(0x34D) -- upwards arrow below, left arrowhead below, right arrowhead below .. U(0x34E) .. U(0x354) .. U(0x355) -- double rightwards arrow below, combining Latin small letter a .. U(0x362) .. U(0x361) -- macron–acute, grave–macron, macron–grave, acute–macron, grave–acute–grave, acute–grave–acute .. U(0x1DC4) .. U(0x1DC5) .. U(0x1DC6) .. U(0x1DC7) .. U(0x1DC8) .. U(0x1DC9) data["tones"] = '˥˦˧˨˩꜒꜓꜔꜕꜖꜈꜉꜊꜋꜌꜍꜎꜏꜐꜑¹²³⁴⁵⁶⁷⁸⁹⁰' data["vowels"] = 'iyɨʉɯuɪʏʊeøɘɵɤoəɚɛœɜɝɞʌɔæɐaɶɑɒäëïöüÿ' data["superscripts"] = '¹²³⁴⁵⁶⁷⁸⁹⁰ᵝʰʱʲʳʴʵʶʷʸ˞ˠˡˢꟹᶣᶬᶮᶯᶰᶹˀˤⁿᵇᵈᶢ' data["valid"] = U(0xA0) .. ' %(%)%%{%|%}%-~⁓.◌abcdefhijklmnopqrstuvwxyz¡àáâãāăēäæçèéêëĕěħìíîïĩīĭĺḿǹńňðòóôõöōŏőœøŕùúûüũūŭűýÿŷŋ' .. 'ǀǁǂǃǎǐǒǔřǖǘǚǜǟǣǽǿȁȅȉȍȕȫȭȳɐɑɒɓɔɕɖɗɘəɚɛɜɝɞɟɠɡɢɣɤɥɦɧɨɪɫɬɭɮɯɰɱɲɳɴɵɶɸɹɺɻɽɾʀʁʂʃʄʈʉʊʋṽʌʍʎʏʐʑʒʔʕʘʙʛʜʝʟʡʢʬʭ⁻' .. 'ʼˈˌːˑˣ˔˕ˬ͗˭ˇ˖β͜θχᴙᵄᵊᵏᵐᵑᶑ᷽ḁḛḭḯṍṏṳṵṹṻạẹẽịọụỳỵỹ‖․‥…‼‿↑↓↗↘ⱱꜛꜜꟸ𝆏𝆑˗' .. data.diacritics .. data.tones .. data.superscripts -- Characters to add VARIATION SELECTOR-15 (U+FE0E) after. -- These are characters with emoji variants that are used by default by some clients. -- Adding VS15 after them instructs them to draw the characters as text instead. data["add_vs15"] = "‼↗↘" data["suggestions"] = { ["g"] = "ɡ", ["'"] = "ˈ", [""] = "", [":"] = "ː", ["ˁ"] = "ˤ", ["ǝ"] = "ə", ["ә"] = "ə", -- Syllabic fricatives ["ɿ"] = "z̩", ["ʅ"] = "ʐ̩", ["ʮ"] = "z̩ʷ", ["ʯ"] = "ʐ̩ʷ", ["Ɂ"] = "ʔ", -- Deprecated symbols ["ɩ"] = "ɪ", ["ɷ"] = "ʊ", ["ᴜ"] = "ʊ", ["ʣ"] = "d͡z", ["ʤ"] = "d͡ʒ", ["ʥ"] = "d͡ʑ", ["ʦ"] = "t͡s", ["ʧ"] = "t͡ʃ", ["ʨ"] = "t͡ɕ", ["ʪ"] = "ɬ͡s", ["ʫ"] = "ɮ͡z", -- Greek letters ["α"] = "ɑ", ["γ"] = "ɣ", ["δ"] = "ð", ["ε"] = "ɛ", ["η"] = "ŋ", ["ι"] = "ɪ", ["λ"] = "ʎ", ["υ"] = "ʋ", ["ϕ"] = "ɸ", } return data l6c8uo6m5gekbgfrnfm2rgm0oimzcpv 10 2961 8273 2022-07-21T18:47:47Z Rebel Agent 2678 Ke dirile tempolete wikitext text/x-wiki {{#invoke:anagrams|show}}<noinclude>{{documentation}}</noinclude> kg1a16fgo89h5sdb2yvhvikoic4a4nt 828 2962 8274 2022-07-21T18:50:10Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local m_languages = require("Module:languages") local m_links = require("Module:links") local export = {} function export.show(frame) local params = { [1] = {required = true, default = "und"}, [2] = {required = true, default = "anagram", list = true}, ["a"] = {required = false}, } local args = require("Module:parameters").process(frame:getParent().args, params) local lang = m_languages.getByCode(args[1], 1) for i, val in ipairs(args[2]) do args[2][i] = m_links.full_link({lang = lang, term = val}) end local result = table.concat(args[2], ", ") return result end return export 4pvv0g03a2puivhmifj4zefgo5v2cny 10 2963 8275 2022-07-21T18:53:23Z Rebel Agent 2678 Ke dirile tempolete wikitext text/x-wiki {{#invoke:en-headword|show|proper nouns}}<!-- -->{{#ifeq:{{{given}}}|yes<!-- -->|<!-- -->{{catlangname|en|given names}}<!-- -->|<!-- -->{{#ifeq:{{{surname}}}|yes<!-- -->|<!-- -->{{catlangname|en|surnames}}<!-- -->}}<!-- -->}}<!-- --><noinclude>{{documentation}}</noinclude> nz68p4h0poh457bydz0cteiv3orvkgd 828 2964 8276 2022-07-21T18:57:05Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local export = {} local pos_functions = {} local lang = require("Module:languages").getByCode("en") local PAGENAME = mw.title.getCurrentTitle().text local function glossary_link(entry, text) text = text or entry return "[[Appendix:Glossary#" .. entry .. "|" .. text .. "]]" end local function track(page) require("Module:debug").track("en-headword/" .. page) return true end -- The main entry point. -- This is the only function that can be invoked from a template. function export.show(frame) local poscat = frame.args[1] or error("Part of speech has not been specified. Please pass parameter 1 to the module invocation.") local params = { ["head"] = {list = true}, ["suff"] = {type = "boolean"}, ["sort"] = {}, } local pos_data = pos_functions[poscat] if pos_data then for key, val in pairs(pos_data.params) do params[key] = val end end local args, unknown_args = require("Module:parameters").process(frame:getParent().args, params, pos_data.return_unknown) if unknown_args and next(unknown_args) then track("unknown args") track("unknown args/POS/" .. tostring(poscat)) for parameter, value in pairs(unknown_args) do track("unknown args/param/" .. tostring(parameter)) mw.log("unknown parameter in [[Module:headword]]: |" .. tostring(parameter) .. "=" .. tostring(value)) end end local data = {lang = lang, pos_category = poscat, categories = {}, heads = args["head"], inflections = {}} if #data.heads == 0 and args.pagename then table.insert(data.heads, args.pagename) end if args["suff"] then data.pos_category = "suffixes" if poscat == "adjectives" or poscat == "adverbs" or poscat == "nouns" or poscat == "verbs" then table.insert(data.categories, ("%s %s-forming suffixes") :format(lang:getCanonicalName(), poscat:gsub("s$", ""))) else error("No category exists for suffixes forming " .. poscat .. ".") end end if pos_data then pos_data.func(args, data) end local extra_categories = {} if PAGENAME:find("[Qq][^Uu]") or PAGENAME:find("[Qq]$") then table.insert(data.categories, lang:getCanonicalName() .. " words containing Q not followed by U") end if PAGENAME:find("([A-Za-z])%1%1") then table.insert(data.categories, lang:getCanonicalName() .. " words containing three consecutive instances of the same letter") end if PAGENAME:find("([A-Za-z])%1%1%1") then table.insert(data.categories, lang:getCanonicalName() .. " words containing four consecutive instances of the same letter") end -- mw.ustring.toNFD performs decomposition, so letters that decompose -- to an ASCII vowel and a diacritic, such as é, are counted as vowels and -- do not need to be included in the pattern. if not mw.ustring.find(mw.ustring.lower(mw.ustring.toNFD(PAGENAME)), "[aeiouyæœø]") then table.insert(data.categories, lang:getCanonicalName() .. " words without vowels") end if PAGENAME:find("yre$") then table.insert(data.categories, lang:getCanonicalName() .. ' words ending in "-yre"') end if not PAGENAME:find(" ") and mw.ustring.len(PAGENAME) >= 25 then table.insert(extra_categories, "Long " .. lang:getCanonicalName() .. ' words') end if PAGENAME:find("^[^aeiou ]*a[^aeiou ]*e[^aeiou ]*i[^aeiou ]*o[^aeiou ]*u[^aeiou ]*$") then table.insert(data.categories, lang:getCanonicalName() .. ' words that use all vowels in alphabetical order') end data.sort_key = args.sort return require("Module:headword").full_headword(data) .. (#extra_categories > 0 and require("Module:utilities").format_categories(extra_categories, lang, args.sort) or "") end -- This function does the common work between adjectives and adverbs function make_comparatives(params, data) local comp_parts = {label = glossary_link("comparative"), accel = {form = "comparative"}} local sup_parts = {label = glossary_link("superlative"), accel = {form = "superlative"}} if #params == 0 then table.insert(params, {"more"}) end -- To form the stem, replace -(e)y with -i and remove a final -e. local stem = PAGENAME:gsub("([^aeiou])e?y$", "%1i"):gsub("e$", "") -- Go over each parameter given and create a comparative and superlative form for i, val in ipairs(params) do local comp = val[1] local comp_qual = val[2] local sup = val[3] local sup_qual = val[4] local comp_part, sup_part if comp == "more" and PAGENAME ~= "many" and PAGENAME ~= "much" then comp_part = "[[more]] " .. PAGENAME sup_part = "[[most]] " .. PAGENAME elseif comp == "further" and PAGENAME ~= "far" then comp_part = "[[further]] " .. PAGENAME sup_part = "[[furthest]] " .. PAGENAME elseif comp == "er" then comp_part = stem .. "er" sup_part = stem .. "est" elseif comp == "-" or sup == "-" then -- Allowing '-' makes it more flexible to not have some forms if comp ~= "-" then comp_part = comp end if sup ~= "-" then sup_part = sup end else -- If the full comparative was given, but no superlative, then -- create it by replacing the ending -er with -est. if not sup then if comp:find("er$") then sup = comp:gsub("er$", "est") else error("The superlative of \"" .. comp .. "\" cannot be generated automatically. Please provide it with the \"sup" .. (i == 1 and "" or i) .. "=\" parameter.") end end comp_part = comp sup_part = sup end if comp_part then table.insert(comp_parts, {term = comp_part, qualifiers = {comp_qual}}) end if sup_part then table.insert(sup_parts, {term = sup_part, qualifiers = {sup_qual}}) end end table.insert(data.inflections, comp_parts) table.insert(data.inflections, sup_parts) end pos_functions["adjectives"] = { params = { [1] = {list = true, allow_holes = true}, ["comp_qual"] = {list = "comp=_qual", allow_holes = true}, ["sup"] = {list = true, allow_holes = true}, ["sup_qual"] = {list = "sup=_qual", allow_holes = true}, }, func = function(args, data) local shift = 0 local is_not_comparable = false local is_comparative_only = false -- If the first parameter is ?, then don't show anything, just return. if args[1][1] == "?" then return -- If the first parameter is -, then move all parameters up one position. elseif args[1][1] == "-" then shift = 1 is_not_comparable = true -- If the only argument is +, then remember this and clear parameters elseif args[1][1] == "+" and args[1].maxindex == 1 then shift = 1 is_comparative_only = true end -- Gather all the comparative and superlative parameters. local params = {} for i = 1, args[1].maxindex - shift do local comp = args[1][i + shift] local comp_qual = args["comp_qual"][i + shift] local sup = args["sup"][i] local sup_qual = args["sup_qual"][i + shift] if comp or sup then table.insert(params, {comp, comp_qual, sup, sup_qual}) end end if shift == 1 then -- If the first parameter is "-" but there are no parameters, -- then show "not comparable" only and return. -- If there are parameters, then show "not generally comparable" -- before the forms. if #params == 0 then if is_not_comparable then table.insert(data.inflections, {label = "not " .. glossary_link("comparable")}) table.insert(data.categories, lang:getCanonicalName() .. " uncomparable adjectives") return end if is_comparative_only then table.insert(data.inflections, {label = glossary_link("comparative") .. " form only"}) table.insert(data.categories, lang:getCanonicalName() .. " comparative-only adjectives") return end else table.insert(data.inflections, {label = "not generally " .. glossary_link("comparable")}) end end -- Process the parameters make_comparatives(params, data) end } pos_functions["adverbs"] = { params = { [1] = {list = true, allow_holes = true}, ["comp_qual"] = {list = "comp=_qual", allow_holes = true}, ["sup"] = {list = true, allow_holes = true}, ["sup_qual"] = {list = "sup=_qual", allow_holes = true}, }, func = function(args, data) local shift = 0 -- If the first parameter is ?, then don't show anything, just return. if args[1][1] == "?" then return -- If the first parameter is -, then move all parameters up one position. elseif args[1][1] == "-" then shift = 1 end -- Gather all the comparative and superlative parameters. local params = {} for i = 1, args[1].maxindex - shift do local comp = args[1][i + shift] local comp_qual = args["comp_qual"][i + shift] local sup = args["sup"][i] local sup_qual = args["sup_qual"][i + shift] if comp or sup then table.insert(params, {comp, comp_qual, sup, sup_qual}) end end if shift == 1 then -- If the first parameter is "-" but there are no parameters, -- then show "not comparable" only and return. If there are parameters, -- then show "not generally comparable" before the forms. if #params == 0 then table.insert(data.inflections, {label = "not " .. glossary_link("comparable")}) table.insert(data.categories, lang:getCanonicalName() .. " uncomparable adverbs") return else table.insert(data.inflections, {label = "not generally " .. glossary_link("comparable")}) end end -- Process the parameters make_comparatives(params, data) end } pos_functions["conjunctions"] = { params = { [1] = { alias_of = "head" }, }, return_unknown = true, func = function (args, data) end, } pos_functions["interjections"] = { params = { [1] = { alias_of = "head" }, }, return_unknown = true, func = function (args, data) end, } local function default_plural(noun) local new_pl if noun:find("[sxz]$") or noun:find("[cs]h$") then new_pl = noun .. "es" elseif noun:find("[^aeiou]y$") then new_pl = noun:gsub("y$", "i") .. "es" else new_pl = noun .. "s" end return new_pl end local function canonicalize_plural(pl, stem) if pl == "s" then return stem .. "s" elseif pl == "es" then return stem .. "es" elseif pl == "+" then return default_plural(PAGENAME) else return nil end end pos_functions["nouns"] = { params = { [1] = {list = true, allow_holes = true}, ["pl=qual"] = { list = true, allow_holes = true }, }, func = function(args, data) -- Gather all the plural parameters from the numbered parameters. local plurals = {} for i = 1, args[1].maxindex do local pl = args[1][i] if pl then local qual = args["plqual"][i] if qual then table.insert(plurals, {term = pl, qualifiers = {qual}}) else table.insert(plurals, pl) end end end -- Decide what to do next... local mode = nil if plurals[1] == "?" or plurals[1] == "!" or plurals[1] == "-" or plurals[1] == "~" then mode = plurals[1] table.remove(plurals, 1) -- Remove the mode parameter end -- Plural is unknown if mode == "?" then table.insert(data.categories, lang:getCanonicalName() .. " nouns with unknown or uncertain plurals") return -- Plural is not attested elseif mode == "!" then table.insert(data.inflections, {label = "plural not attested"}) table.insert(data.categories, lang:getCanonicalName() .. " nouns with unattested plurals") return -- Uncountable noun; may occasionally have a plural elseif mode == "-" then table.insert(data.categories, lang:getCanonicalName() .. " uncountable nouns") -- If plural forms were given explicitly, then show "usually" if #plurals > 0 then table.insert(data.inflections, {label = "usually " .. glossary_link("uncountable")}) table.insert(data.categories, lang:getCanonicalName() .. " countable nouns") else table.insert(data.inflections, {label = glossary_link("uncountable")}) end -- Mixed countable/uncountable noun, always has a plural elseif mode == "~" then table.insert(data.inflections, {label = glossary_link("countable") .. " and " .. glossary_link("uncountable")}) table.insert(data.categories, lang:getCanonicalName() .. " uncountable nouns") table.insert(data.categories, lang:getCanonicalName() .. " countable nouns") -- If no plural was given, add a default one now if #plurals == 0 then plurals = {default_plural(PAGENAME)} end -- The default, always has a plural else table.insert(data.categories, lang:getCanonicalName() .. " countable nouns") -- If no plural was given, add a default one now if #plurals == 0 then plurals = {default_plural(PAGENAME)} end end -- If there are no plurals to show, return now if #plurals == 0 then return end -- There are plural forms to show, so show them local pl_parts = {label = "plural", accel = {form = "p"}} local function check_ies(pl, stem) local newplural, nummatches = stem:gsub("([^aeiou])y$","%1ies") return nummatches > 0 and pl == newplural end local stem = PAGENAME local irregular = false for i, pl in ipairs(plurals) do local canon_pl = canonicalize_plural(pl, stem) if canon_pl then table.insert(pl_parts, canon_pl) elseif type(pl) == "table" then canon_pl = canonicalize_plural(pl.term, stem) if canon_pl then table.insert(pl_parts, {term=canon_pl, qualifiers=pl.qualifiers}) end end if not canon_pl then table.insert(pl_parts, pl) if type(pl) == "table" then pl = pl.term end if not stem:find(" ") and not (pl == stem .. "s" or pl == stem .. "es" or check_ies(pl, stem)) then irregular = true if pl == stem then table.insert(data.categories, lang:getCanonicalName() .. " indeclinable nouns") end end end end if irregular then table.insert(data.categories, lang:getCanonicalName() .. " nouns with irregular plurals") end table.insert(data.inflections, pl_parts) end } pos_functions["proper nouns"] = { params = { [1] = {list = true}, }, func = function(args, data) local plurals = args[1] -- Decide what to do next... local mode = nil if plurals[1] == "?" or plurals[1] == "!" or plurals[1] == "-" or plurals[1] == "~" then mode = plurals[1] table.remove(plurals, 1) -- Remove the mode parameter end -- Plural is unknown if mode == "?" then table.insert(data.categories, lang:getCanonicalName() .. " proper nouns with unknown or uncertain plurals") return -- Plural is not attested elseif mode == "!" then table.insert(data.inflections, {label = "plural not attested"}) table.insert(data.categories, lang:getCanonicalName() .. " proper nouns with unattested plurals") return -- Uncountable noun; may occasionally have a plural elseif mode == "-" then -- If plural forms were given explicitly, then show "usually" if #plurals > 0 then table.insert(data.inflections, {label = "usually " .. glossary_link("uncountable")}) table.insert(data.categories, lang:getCanonicalName() .. " countable proper nouns") else table.insert(data.inflections, {label = glossary_link("uncountable")}) end -- Mixed countable/uncountable noun, always has a plural elseif mode == "~" then table.insert(data.inflections, {label = glossary_link("countable") .. " and " .. glossary_link("uncountable")}) table.insert(data.categories, lang:getCanonicalName() .. " countable proper nouns") -- If no plural was given, add a default one now if #plurals == 0 then plurals = {"s"} end elseif #plurals > 0 then table.insert(data.categories, lang:getCanonicalName() .. " countable proper nouns") end -- If there are no plurals to show, return now if #plurals == 0 then return end -- There are plural forms to show, so show them local pl_parts = {label = "plural", accel = {form = "p"}} local stem = PAGENAME for i, pl in ipairs(plurals) do if pl == "s" then table.insert(pl_parts, stem .. "s") elseif pl == "es" then table.insert(pl_parts, stem .. "es") else table.insert(pl_parts, pl) end end table.insert(data.inflections, pl_parts) end } local function base_default_verb_forms(verb) local s_form = default_plural(verb) local ing_form, ed_form local vowel = "aeiouáéíóúàèìòùâêîôûäëïöüæœø" local ulvowel = vowel .. "AEIOUÁÉÍÓÚÀÈÌÒÙÂÊÎÔÛÄËÏÖÜÆŒØ" -- (1) Check for C*VC verbs. -- -- flip -> flipping/flipped, strum -> strumming/strummed, nag -> nagging/nagged, etc. -- Do not include words with final -y, e.g. 'stay' (staying/stayed), 'toy' (toying/toyed), -- or with final -w, e.g. 'flow' (flowing/flowed), or with final -h, e.g. 'ah' (ahing/ahed), -- or with final -x, e.g. 'box' (boxing/boxed), or ending in an uppercase consonant, -- e.g. 'XOR' (XORing/XORed), 'OK' (OKing/OKed). Check specially for initial y- as a consonant, -- e.g. 'yip' (yipping/yipped), otherwise treat y as a vowel, so we don't trigger on 'hyphen' -- but do trigger on 'gyp'. local last_cons = mw.ustring.match(verb, "^[Yy][" .. vowel .. "y]([^A-Z" .. vowel .. "ywxh])$") if not last_cons then last_cons = mw.ustring.match(verb, "^[^" .. ulvowel .. "yY]*[" .. ulvowel .. "yY]([^A-Z" .. vowel .. "ywxh])$") end if last_cons then ing_form = verb .. last_cons .. "ing" ed_form = verb .. last_cons .. "ed" else -- (2) Generate -ing form. -- (2a) lie -> lying, untie -> untying, etc. local stem = verb:match("^(.*)ie$") if stem then ing_form = stem .. "ying" else -- (2b) argue -> arguing, sprue -> spruing, dialogue -> dialoguing, etc. stem = verb:match("^(.*)ue$") if stem then ing_form = stem .. "uing" else stem = mw.ustring.match(verb, "^(.*[" .. ulvowel .. "yY][^" .. vowel .. "y]+)e$") if stem then -- (2c) baptize -> baptizing, rake -> raking, type -> typing, parse -> parsing, etc. -- (ending in vowel + consonant(s) + -e); but not referee -> refereeing, -- backhoe -> backhoeing, redye -> redyeing (ending in some other vowel + -e or in -ye); -- and not be -> being (no vowel before the consonant preceding the -e) ing_form = stem .. "ing" else -- (2d) regular verbs ing_form = verb .. "ing" end end end -- (3) Generate -ed form. if verb:find("e$") then -- (3a) baptize -> baptized, rake -> raked, parse -> parsed, free -> freed, hoe -> hoed ed_form = verb .. "d" else stem = mw.ustring.match(verb, "^(.*[^" .. ulvowel .. "yY])y$") if stem then -- (3b) marry -> married, levy -> levied, try -> tried, etc.; but not toy -> toyed ed_form = stem .. "ied" else -- (3c) regular verbs ed_form = verb .. "ed" end end end return s_form, ing_form, ed_form end local function default_verb_forms(verb) local full_s_form, full_ing_form, full_ed_form = base_default_verb_forms(verb) if verb:find(" ") then local first, rest = verb:match("^(.-)( .*)$") local first_s_form, first_ing_form, first_ed_form = base_default_verb_forms(first) return full_s_form, full_ing_form, full_ed_form, first_s_form .. rest, first_ing_form .. rest, first_ed_form .. rest else return full_s_form, full_ing_form, full_ed_form, nil, nil, nil end end pos_functions["verbs"] = { params = { [1] = {list = "pres_3sg", allow_holes = true}, ["pres_3sg_qual"] = {list = "pres_3sg=_qual", allow_holes = true}, [2] = {list = "pres_ptc", allow_holes = true}, ["pres_ptc_qual"] = {list = "pres_ptc=_qual", allow_holes = true}, [3] = {list = "past", allow_holes = true}, ["past_qual"] = {list = "past=_qual", allow_holes = true}, [4] = {list = "past_ptc", allow_holes = true}, ["past_ptc_qual"] = {list = "past_ptc=_qual", allow_holes = true}, ["pagename"] = {}, -- for testing }, func = function(args, data) -- Get parameters local par1 = args[1][1] local par2 = args[2][1] local par3 = args[3][1] local par4 = args[4][1] local pres_3sgs, pres_ptcs, pasts, past_ptcs local pagename = args.pagename or PAGENAME ------------------------------------------- UTILITY FUNCTIONS #1 ------------------------------------------ -- These functions are used directly in the <> format as well as in the utility functions #2 below. local function compute_double_last_cons_stem(verb) local last_cons = verb:match("([bcdfghjklmnpqrstvwxyzBCDFGHJKLMNPQRSTVWXYZ])$") if not last_cons then error("Verb stem '" .. verb .. "' must end in a consonant to use ++") end return verb .. last_cons end local function compute_plusplus_s_form(verb, default_s_form) if verb:find("[sz]$") then -- regas -> regasses, derez -> derezzes return compute_double_last_cons_stem(verb) .. "es" else return default_s_form end end ------------------------------------------- UTILITY FUNCTIONS #2 ------------------------------------------ -- These functions are used in both in the separate-parameter format and in the override params such as past_ptc2=. local new_default_s, new_default_ing, new_default_ed, split_default_s, split_default_ing, split_default_ed = default_verb_forms(pagename) local function compute_double_last_cons_stem_of_split_verb(verb, ending) local first, rest = verb:match("^(.-)( .*)$") if not first then error("Verb '" .. verb .. "' must have a space in it to use ++*") end local last_cons = first:match("([bcdfghjklmnpqrstvwxyzBCDFGHJKLMNPQRSTVWXYZ])$") if not last_cons then error("First word '" .. first .. "' must end in a consonant to use ++*") end return first .. last_cons .. ending .. rest end local function check_non_nil_star_form(form) if form == nil then error("Verb '" .. pagename .. "' must have a space in it to use * or ++*") end return form end local function sub_tilde(form) if not form then return nil end local retval = form:gsub("~", pagename) -- discard second return value return retval end local function canonicalize_s_form(form) if form == "+" then return new_default_s elseif form == "*" then return check_non_nil_star_form(split_default_s) elseif form == "++" then return compute_plusplus_s_form(pagename, new_default_s) elseif form == "++*" then if pagename:find("^[^ ]*[sz] ") then return compute_double_last_cons_stem_of_split_verb(pagename, "es") else return check_non_nil_star_form(split_default_s) end else return sub_tilde(form) end end local function canonicalize_ing_form(form) if form == "+" then return new_default_ing elseif form == "*" then return check_non_nil_star_form(split_default_ing) elseif form == "++" then return compute_double_last_cons_stem(pagename) .. "ing" elseif form == "++*" then return compute_double_last_cons_stem_of_split_verb(pagename, "ing") else return sub_tilde(form) end end local function canonicalize_ed_form(form) if form == "+" then return new_default_ed elseif form == "*" then return check_non_nil_star_form(split_default_ed) elseif form == "++" then return compute_double_last_cons_stem(pagename) .. "ed" elseif form == "++*" then return compute_double_last_cons_stem_of_split_verb(pagename, "ed") else return sub_tilde(form) end end --------------------------------- MAIN PARSING/CONJUGATING CODE -------------------------------- local past_ptcs_given if par1 and par1:find("<") then -------------------------- ANGLE-BRACKET FORMAT -------------------------- if par2 or par3 or par4 then error("Can't specify 2=, 3= or 4= when 1= contains angle brackets: " .. par1) end -- In the angle bracket format, we always copy the full past tense specs to the past participle -- specs if none of the latter are given, so act as if the past participle is always given. -- There is a separate check to see if the past tense and past participle are identical, in any case. past_ptcs_given = true local iut = require("Module:inflection utilities") -- (1) Parse the indicator specs inside of angle brackets. local function parse_indicator_spec(angle_bracket_spec) local inside = angle_bracket_spec:match("^<(.*)>$") assert(inside) local segments = iut.parse_balanced_segment_run(inside, "[", "]") local comma_separated_groups = iut.split_alternating_runs(segments, ",") if #comma_separated_groups > 4 then error("Too many comma-separated parts in indicator spec: " .. angle_bracket_spec) end local function fetch_qualifiers(separated_group) local qualifiers for j = 2, #separated_group - 1, 2 do if separated_group[j + 1] ~= "" then error("Extraneous text after bracketed qualifiers: '" .. table.concat(separated_group) .. "'") end if not qualifiers then qualifiers = {} end table.insert(qualifiers, separated_group[j]) end return qualifiers end local function fetch_specs(comma_separated_group) if not comma_separated_group then return {{}} end local specs = {} local colon_separated_groups = iut.split_alternating_runs(comma_separated_group, ":") for _, colon_separated_group in ipairs(colon_separated_groups) do local form = colon_separated_group[1] if form == "*" or form == "++*" then error("* and ++* not allowed inside of indicator specs: " .. angle_bracket_spec) end if form == "" then form = nil end table.insert(specs, {form = form, qualifiers = fetch_qualifiers(colon_separated_group)}) end return specs end local s_specs = fetch_specs(comma_separated_groups[1]) local ing_specs = fetch_specs(comma_separated_groups[2]) local ed_specs = fetch_specs(comma_separated_groups[3]) local en_specs = fetch_specs(comma_separated_groups[4]) for _, spec in ipairs(s_specs) do if spec.form == "++" and #ing_specs == 1 and not ing_specs[1].form and not ing_specs[1].qualifiers and #ed_specs == 1 and not ed_specs[1].form and not ed_specs[1].qualifiers then ing_specs[1].form = "++" ed_specs[1].form = "++" break end end return { forms = {}, s_specs = s_specs, ing_specs = ing_specs, ed_specs = ed_specs, en_specs = en_specs, } end local parse_props = { parse_indicator_spec = parse_indicator_spec, } local alternant_multiword_spec = iut.parse_inflected_text(par1, parse_props) -- (2) Remove any links from the lemma, but remember the original form -- so we can use it below in the 'lemma_linked' form. iut.map_word_specs(alternant_multiword_spec, function(base) if base.lemma == "" then base.lemma = pagename end base.orig_lemma = base.lemma base.lemma = require("Module:links").remove_links(base.lemma) end) -- (3) Conjugate the verbs according to the indicator specs parsed above. local all_verb_slots = { lemma = "infinitive", lemma_linked = "infinitive", s_form = "3|s|pres", ing_form = "pres|ptcp", ed_form = "past", en_form = "past|ptcp", } local function conjugate_verb(base) local def_s_form, def_ing_form, def_ed_form = base_default_verb_forms(base.lemma) local function process_specs(slot, specs, default_form, canonicalize_plusplus) for _, spec in ipairs(specs) do local form = spec.form if not form or form == "+" then form = default_form elseif form == "++" then form = canonicalize_plusplus() end -- If there's a ~ in the form, substitute it with the lemma, -- but make sure to first replace % in the lemma with %% so that -- it doesn't get interpreted as a capture replace expression. if form:find("~") then -- Assign to a var because gsub returns multiple values. local subbed_lemma = base.lemma:gsub("%%", "%%%%") form = form:gsub("~", subbed_lemma) end -- If the form is -, don't insert any forms, which will result -- in there being no overall forms (in fact it will be nil). -- We check for that down below and substitute a single "-" as -- the form, which in turn gets turned into special labels like -- "no present participle". if form ~= "-" then iut.insert_form(base.forms, slot, {form = form, footnotes = spec.qualifiers}) end end end process_specs("s_form", base.s_specs, def_s_form, function() return compute_plusplus_s_form(base.lemma, def_s_form) end) process_specs("ing_form", base.ing_specs, def_ing_form, function() return compute_double_last_cons_stem(base.lemma) .. "ing" end) process_specs("ed_form", base.ed_specs, def_ed_form, function() return compute_double_last_cons_stem(base.lemma) .. "ed" end) -- If the -en spec is completely missing, substitute the -ed spec in its entirely. -- Otherwise, if individual -en forms are missing or use +, we will substitute the -- default -ed form, as with the -ed spec. local en_specs = base.en_specs if #en_specs == 1 and not en_specs[1].form and not en_specs[1].qualifiers then en_specs = base.ed_specs end process_specs("en_form", en_specs, def_ed_form, function() return compute_double_last_cons_stem(base.lemma) .. "ed" end) iut.insert_form(base.forms, "lemma", {form = base.lemma}) -- Add linked version of lemma for use in head=. We write this in a general fashion in case -- there are multiple lemma forms (which isn't possible currently at this level, although it's -- possible overall using the ((...,...)) notation). iut.insert_forms(base.forms, "lemma_linked", iut.map_forms(base.forms.lemma, function(form) if form == base.lemma and base.orig_lemma:find("%[%[") then return base.orig_lemma else return form end end)) end local inflect_props = { slot_table = all_verb_slots, inflect_word_spec = conjugate_verb, } iut.inflect_multiword_or_alternant_multiword_spec(alternant_multiword_spec, inflect_props) -- (4) Fetch the forms and put the conjugated lemmas in data.heads if not explicitly given. local function fetch_forms(slot) local forms = alternant_multiword_spec.forms[slot] -- See above. This should only occur if the user explicitly used - -- for a spec. if not forms or #forms == 0 then forms = {{form = "-"}} end return forms end pres_3sgs = fetch_forms("s_form") pres_ptcs = fetch_forms("ing_form") pasts = fetch_forms("ed_form") past_ptcs = fetch_forms("en_form") -- Use the "linked" form of the lemma as the head if no head= explicitly given. -- If no links in this form and it has multiple words, autolink the individual words. -- The user can override this using head=. if #data.heads == 0 then for _, lemma_obj in ipairs(alternant_multiword_spec.forms.lemma_linked) do local lemma = lemma_obj.form if not lemma:find("%[%[") then local m_headword = require("Module:headword") if m_headword.head_is_multiword(lemma) then lemma = m_headword.add_multiword_links(lemma) end end table.insert(data.heads, lemma) end end else -------------------------- SEPARATE-PARAM FORMAT -------------------------- local pres_3sg, pres_ptc, past if par1 and not par2 and not par3 then -- Use of a single parameter other than "++", "*" or "++*" is now the "legacy" format, -- and no longer supported. if par1 == "es" or par1 == "ies" or par1 == "d" then error("Legacy parameter 1=es/ies/d no longer supported, just use 'en-verb' without params") elseif par1 == "++" or par1 == "*" or par1 == "++*" then pres_3sg = canonicalize_s_form(par1) pres_ptc = canonicalize_ing_form(par1) past = canonicalize_ed_form(par1) else error("Legacy parameter 1=STEM no longer supported, just use 'en-verb' without params") end else if par3 then track("xxx3") elseif par2 then track("xxx2") end end if not pres_3sg or not pres_ptc or not past then -- Either all three should be set above, or none of them. assert(not pres_3sg and not pres_ptc and not past) if par1 then pres_3sg = canonicalize_s_form(par1) else pres_3sg = new_default_s end if par2 then pres_ptc = canonicalize_ing_form(par2) else pres_ptc = new_default_ing end if par3 then past = canonicalize_ed_form(par3) else past = new_default_ed end end if par4 then past_ptcs_given = true past_ptc = canonicalize_ed_form(par4) else past_ptc = past end pres_3sgs = {{form = pres_3sg}} pres_ptcs = {{form = pres_ptc}} pasts = {{form = past}} past_ptcs = {{form = past_ptc}} end ------------------------------------------- HANDLE OVERRIDES ------------------------------------------ local pres_3sg_infls, pres_ptc_infls, past_infls, past_ptc_infls local function strip_brackets(qualifiers) if not qualifiers then return nil end local stripped_qualifiers = {} for _, qualifier in ipairs(qualifiers) do local stripped_qualifier = qualifier:match("^%[(.*)%]$") if not stripped_qualifier then error("Internal error: Qualifier should be surrounded by brackets at this stage: " .. qualifier) end table.insert(stripped_qualifiers, stripped_qualifier) end return stripped_qualifiers end local function collect_forms(label, accel_form, defaults, overrides, override_qualifiers, canonicalize) if defaults[1].form == "-" then return {label = "no " .. label} else local into_table = {label = label, accel = {form = accel_form}} local maxindex = math.max(#defaults, overrides.maxindex) local qualifiers = override_qualifiers[1] and {override_qualifiers[1]} or strip_brackets(defaults[1].footnotes) table.insert(into_table, {term = defaults[1].form, qualifiers = qualifiers}) -- Present 3rd singular for i = 2, maxindex do local override_form = canonicalize(overrides[i]) if override_form then -- If there is an override such as past_ptc2=..., only use the qualifier specified -- using an override (past_ptc2_qual=...), if any; it doesn't make sense to combine -- an override form with a qualifier specified inside of angle brackets. table.insert(into_table, {term = override_form, qualifiers = {override_qualifiers[i]}}) elseif defaults[i] then -- If the form comes from inside angle brackets, allow any override qualifier -- (past_ptc2_qual=...) to override any qualifier specified inside of angle brackets. -- FIXME: Maybe we should throw an error here if both exist. local qualifiers = override_qualifiers[i] and {override_qualifiers[i]} or strip_brackets(defaults[i].footnotes) table.insert(into_table, {term = defaults[i].form, qualifiers = qualifiers}) end end return into_table end end local pres_3sg_infls = collect_forms("third-person singular simple present", "3|s|pres", pres_3sgs, args[1], args.pres_3sg_qual, canonicalize_s_form) local pres_ptc_infls = collect_forms("present participle", "pres|ptcp", pres_ptcs, args[2], args.pres_ptc_qual, canonicalize_ing_form) local past_infls = collect_forms("simple past", "past", pasts, args[3], args.past_qual, canonicalize_ed_form) local past_ptc_infls = collect_forms("past participle", "past|ptcp", past_ptcs, args[4], args.past_ptc_qual, canonicalize_ed_form) -- Are the past forms identical to the past participle forms? If so, we use a single -- combined "simple past and past participle" label on the past tense forms. -- We check for two conditions: Either no past participle forms were given at all, or -- they were given but are identical in every way (all forms and qualifiers) to the past -- tense forms. The former "no explicit past participle forms" check is important in the -- "separate-parameter" format; if past tense overrides are given and no past participle -- forms given, the past tense overrides should apply to the past participle as well. -- In the angle-bracket format, it's expected that all forms and qualifiers are specified -- using that format, and we explicitly copy past tense forms and qualifiers to past -- participle ones if the latter are omitted, so we disable to "no explicit past participle -- forms" check. if args[4].maxindex > 0 or args.past_ptc_qual.maxindex > 0 then past_ptcs_given = true end local identical = true -- For the past and past participle to be identical, there must be -- the same number of inflections, and each inflection must match -- in term and qualifiers. if #past_infls ~= #past_ptc_infls then identical = false else for key, val in ipairs(past_infls) do if past_ptc_infls[key].term ~= val.term then identical = false break else local quals1 = past_ptc_infls[key].qualifiers local quals2 = val.qualifiers if (not not quals1) ~= (not not quals2) then -- one is nil, the other is not identical = false elseif quals1 and quals2 then -- qualifiers present in both; each qualifier must match if #quals1 ~= #quals2 then identical = false else for k, v in ipairs(quals1) do if v ~= quals2[k] then identical = false break end end end end if not identical then break end end end end -- Insert the forms table.insert(data.inflections, pres_3sg_infls) table.insert(data.inflections, pres_ptc_infls) if not past_ptcs_given or identical then if past_ptcs[1].form == "-" then past_infls.label = "no simple past or past participle" else past_infls.label = "simple past and past participle" past_infls.accel = {form = "past|and|past|ptcp"} end table.insert(data.inflections, past_infls) else table.insert(data.inflections, past_infls) table.insert(data.inflections, past_ptc_infls) end end } return export 6dsxm87ymuyut1g18bydur83dkkd2ec 828 2965 8277 2022-07-21T19:00:34Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local export = {} local m_data = mw.loadData("Module:headword/data") local title = mw.title.getCurrentTitle() local isLemma = m_data.lemmas local isNonLemma = m_data.nonlemmas local notranslit = m_data.notranslit local toBeTagged = m_data.toBeTagged -- If set to true, categories always appear, even in non-mainspace pages local test_force_categories = false local function test_script(text, script_code) if type(text) == "string" and type(script_code) == "string" then local sc = require("Module:scripts").getByCode(script_code) local characters if sc then characters = sc:getCharacters() end local out if characters then text = mw.ustring.gsub(text, "%W", "") out = mw.ustring.find(text, "[" .. characters .. "]") end if out then return true else return false end else mw.log("Parameters to test_script were incorrect.") return nil end end local spacingPunctuation = "[%s%p]+" --[[ List of punctuation or spacing characters that are found inside of words. Used to exclude characters from the regex above. ]] local wordPunc = "-־׳״'.·*’་•" local notWordPunc = "[^" .. wordPunc .. "]+" -- Return true if the given head is multiword according to the algorithm used -- in full_headword(). function export.head_is_multiword(head) for possibleWordBreak in mw.ustring.gmatch(head, spacingPunctuation) do if mw.ustring.find(possibleWordBreak, notWordPunc) then return true end end return false end -- Add links to a multiword head. function export.add_multiword_links(head) local function workaround_to_exclude_chars(s) return mw.ustring.gsub(s, notWordPunc, "]]%1[[") end head = "[[" .. mw.ustring.gsub( head, spacingPunctuation, workaround_to_exclude_chars ) .. "]]" --[=[ use this when workaround is no longer needed: head = "[[" .. mw.ustring.gsub(head, WORDBREAKCHARS, "]]%1[[") .. "]]" Remove any empty links, which could have been created above at the beginning or end of the string. ]=] head = mw.ustring.gsub(head, "%[%[%]%]", "") return head end local function non_categorizable() return (title:inNamespace("") and title.text:find("^Unsupported titles/")) or (title:inNamespace("Appendix") and title.text:find("^Gestures/")) end local function preprocess(data, postype) --[=[ [[Special:WhatLinksHere/Template:tracking/headword/heads-not-table]] [[Special:WhatLinksHere/Template:tracking/headword/translits-not-table]] ]=] if type(data.heads) ~= "table" then if data.heads then require("Module:debug/track")("headword/heads-not-table") end data.heads = { data.heads } end if type(data.translits) ~= "table" then if data.translits then require("Module:debug/track")("headword/translits-not-table") end data.translits = { data.translits } end if type(data.transcriptions) ~= "table" then if data.transcriptions then require("Module:debug/track")("headword/transcriptions-not-table") end data.transcriptions = { data.transcriptions } end if not data.heads or #data.heads == 0 then data.heads = {""} end -- Determine if term is reconstructed local is_reconstructed = data.lang:getType() == "reconstructed" or title.nsText == "Reconstruction" -- Create a default headword. local subpagename = title.subpageText local pagename = title.text local default_head if is_reconstructed then default_head = require("Module:utilities").plain_gsub(pagename, data.lang:getCanonicalName() .. "/", "") else default_head = subpagename end local unmodified_default_head = default_head -- Add links to multi-word page names when appropriate if data.lang:getCode() ~= "zh" and (not is_reconstructed) and export.head_is_multiword(default_head) then default_head = export.add_multiword_links(default_head) end if is_reconstructed then default_head = "*" .. default_head end -- If a head is the empty string "", then replace it with the default for i, head in ipairs(data.heads) do if head == "" then head = default_head else if head == default_head and data.lang:getCanonicalName() == "English" then table.insert(data.categories, data.lang:getCanonicalName() .. " terms with redundant head parameter") end end data.heads[i] = head end -- If the first head is multiword (after removing links), maybe insert into "LANG multiword terms" if not data.nomultiwordcat and postype == "lemma" and not m_data.no_multiword_cat[data.lang:getCode()] then -- Check for spaces or hyphens, but exclude prefixes and suffixes. -- Use the pagename, not the head= value, because the latter may have extra -- junk in it, e.g. superscripted text that throws off the algorithm. local checkpattern = ".[%s%-፡]." if m_data.hyphen_not_multiword_sep[data.lang:getCode()] then -- Exclude hyphens if the data module states that they should for this language checkpattern = ".[%s፡]." end if mw.ustring.find(unmodified_default_head, checkpattern) and not non_categorizable() then table.insert(data.categories, data.lang:getCanonicalName() .. " multiword terms") end end --[[ Try to detect the script if it was not provided We use the first headword for this, and assume that all of them have the same script This *should* always be true, right? ]] if not data.sc then data.sc = require("Module:scripts").findBestScript(data.heads[1], data.lang) end for i, val in pairs(data.translits) do data.translits[i] = {display = val, is_manual = true} end -- Make transliterations for i, head in ipairs(data.heads) do local translit = data.translits[i] -- Try to generate a transliteration if necessary -- Generate it if the script is not Latn or similar, and if no transliteration was provided if translit and translit.display == "-" then translit = nil elseif not translit and not (data.sc:getCode():find("Latn", nil, true) or data.sc:getCode() == "Latinx" or data.sc:getCode() == "None") and (not data.sc or data.sc:getCode() ~= "Imag") then translit = data.lang:transliterate(require("Module:links").remove_links(head), data.sc) -- There is still no transliteration? -- Add the entry to a cleanup category. if not translit and not notranslit[data.lang:getCode()] then translit = "<small>transliteration needed</small>" table.insert(data.categories, "Requests for transliteration of " .. data.lang:getCanonicalName() .. " terms") end if translit then translit = {display = translit, is_manual = false} end end -- Link to the transliteration entry for languages that require this if translit and data.lang:link_tr() then translit.display = require("Module:links").full_link{ term = translit.display, lang = data.lang, sc = require("Module:scripts").getByCode("Latn"), tr = "-" } end data.translits[i] = translit end if data.id and type(data.id) ~= "string" then error("The id in the data table should be a string.") end end -- Format a headword with transliterations local function format_headword(data) local m_scriptutils = require("Module:script utilities") -- Are there non-empty transliterations? -- Need to do it this way because translit[1] might be nil while translit[2] is not local has_translits = false local has_manual_translits = false -- Format the headwords for i, head in ipairs(data.heads) do if data.translits[i] or data.transcriptions[i] then has_translits = true end if data.translits[i] and data.translits[i].is_manual or data.transcriptions[i] then has_manual_translits = true end -- Apply processing to the headword, for formatting links and such if head:find("[[", nil, true) and (not data.sc or data.sc:getCode() ~= "Imag") then head = require("Module:links").language_link({term = head, lang = data.lang}, false) end -- Add language and script wrapper if i == 1 then head = m_scriptutils.tag_text(head, data.lang, data.sc, "head", nil, data.id) else head = m_scriptutils.tag_text(head, data.lang, data.sc, "head", nil) end data.heads[i] = head end local translits_formatted = "" if has_manual_translits then -- [[Special:WhatLinksHere/Template:tracking/headword/has-manual-translit/LANG]] require("Module:debug/track")("headword/has-manual-translit/" .. data.lang:getCode()) end if has_translits then -- Format the transliterations local translits = data.translits local transcriptions = data.transcriptions if translits then -- using pairs() instead of ipairs() in case there is a gap for i, _ in pairs(translits) do if type(i) == "number" then translits[i] = m_scriptutils.tag_translit(translits[i].display, data.lang:getCode(), "head", nil, translits[i].is_manual) end end end if transcriptions then for i, _ in pairs(transcriptions) do if type(i) == "number" then transcriptions[i] = m_scriptutils.tag_transcription(transcriptions[i], data.lang:getCode(), "head") end end end for i = 1, math.max(#translits, #transcriptions) do local translits_formatted = {} table.insert(translits_formatted, translits[i] and translits[i] or "") table.insert(translits_formatted, (translits[i] and transcriptions[i]) and " " or "") table.insert(translits_formatted, transcriptions[i] and "/" .. transcriptions[i] .. "/" or "") data.translits[i] = table.concat(translits_formatted) end translits_formatted = " (" .. table.concat(data.translits, " <i>or</i> ") .. ")" local transliteration_page = mw.title.new(data.lang:getCanonicalName() .. " transliteration", "Wiktionary") if transliteration_page then local success, exists = pcall(function () return transliteration_page.exists end) if success and exists then translits_formatted = " [[Wiktionary:" .. data.lang:getCanonicalName() .. " transliteration|•]]" .. translits_formatted end end end return table.concat(data.heads, " <i>or</i> ") .. translits_formatted end local function format_genders(data) if data.genders and #data.genders > 0 then local pos_for_cat if not data.nogendercat and not m_data.no_gender_cat[data.lang:getCode()] then local pos_category = data.pos_category:gsub("^reconstructed ", "") pos_for_cat = m_data.pos_for_gender_number_cat[pos_category] end local text, cats = require("Module:gender and number").format_genders(data.genders, data.lang, pos_for_cat) for _, cat in ipairs(cats) do table.insert(data.categories, cat) end return "&nbsp;" .. text else return "" end end local function format_inflection_parts(data, parts) for key, part in ipairs(parts) do if type(part) ~= "table" then part = {term = part} end local qualifiers local reftext if part.qualifiers and #part.qualifiers > 0 then qualifiers = require("Module:qualifier").format_qualifier(part.qualifiers) .. " " -- [[Special:WhatLinksHere/Template:tracking/headword/qualifier]] require("Module:debug/track")("headword/qualifier") end if part.refs and #part.refs > 0 then local refs = {} for _, ref in ipairs(part.refs) do if type(ref) ~= "table" then ref = {text = ref} end local refargs if ref.name or ref.group then refargs = {name = ref.name, group = ref.group} end table.insert(refs, mw.getCurrentFrame():extensionTag("ref", ref.text, refargs)) end reftext = table.concat(refs) end local partaccel = part.accel local face = part.hypothetical and "hypothetical" or "bold" local nolink = part.hypothetical or part.nolink if part.label then -- There should be a better way of italicizing a label. As is, this isn't customizable. part = "<i>" .. part.label .. "</i>" else -- Convert the term into a full link -- Don't show a transliteration here, the consensus seems to be not to -- show them in headword lines to avoid clutter. part = require("Module:links").full_link( { term = not nolink and part.term or nil, alt = part.alt or (nolink and part.term or nil), lang = part.lang or data.lang, sc = part.sc or parts.sc or (not part.lang and data.sc), id = part.id, genders = part.genders, tr = part.translit or (not (parts.enable_auto_translit or data.inflections.enable_auto_translit) and "-" or nil), ts = part.transcription, accel = parts.accel or partaccel, }, face, false ) end if qualifiers then part = qualifiers .. part end if reftext then part = part .. reftext end parts[key] = part end local parts_output = "" if #parts > 0 then parts_output = " " .. table.concat(parts, " <i>or</i> ") elseif parts.request then parts_output = " <small>[please provide]</small>" .. require("Module:utilities/format_categories")( {"Requests for inflections in " .. data.lang:getCanonicalName() .. " entries"}, lang, nil, nil, data.force_cat_output or test_force_categories, data.sc ) end return "<i>" .. parts.label .. "</i>" .. parts_output end -- Format the inflections following the headword local function format_inflections(data) if data.inflections and #data.inflections > 0 then -- Format each inflection individually for key, infl in ipairs(data.inflections) do data.inflections[key] = format_inflection_parts(data, infl) end return " (" .. table.concat(data.inflections, ", ") .. ")" else return "" end end -- Return "lemma" if the given POS is a lemma, "non-lemma form" if a non-lemma form, or nil -- if unknown. The POS passed in must be in its plural form ("nouns", "prefixes", etc.). -- If you have a POS in its singular form, call pluralize() in [[Module:string utilities]] to -- pluralize it in a smart fashion that knows when to add '-s' and when to add '-es'. -- -- If `best_guess` is given and the POS is in neither the lemma nor non-lemma list, guess -- based on whether it ends in " forms"; otherwise, return nil. function export.pos_lemma_or_nonlemma(plpos, best_guess) -- Is it a lemma category? if isLemma[plpos] or isLemma[plpos:gsub("^reconstructed ", "")] then return "lemma" -- Is it a nonlemma category? elseif isNonLemma[plpos] or isNonLemma[plpos:gsub("^reconstructed ", "")] or isLemma[plpos:gsub("^mutated ", "")] or isNonLemma[plpos:gsub("^mutated ", "")] then return "non-lemma form" elseif best_guess then return plpos:find(" forms$") and "non-lemma form" or "lemma" else return nil end end local function show_headword_line(data) local namespace = title.nsText -- Check the namespace against the language type if namespace == "" then if data.lang:getType() == "reconstructed" then error("Entries for this language must be placed in the Reconstruction: namespace.") elseif data.lang:getType() == "appendix-constructed" then error("Entries for this language must be placed in the Appendix: namespace.") end end local tracking_categories = {} if not data.noposcat then local pos_category = data.lang:getCanonicalName() .. " " .. data.pos_category if pos_category ~= "Translingual Han characters" then table.insert(data.categories, 1, pos_category) end end if data.sccat and data.sc then table.insert(data.categories, data.lang:getCanonicalName() .. " " .. data.pos_category .. " in " .. data.sc:getDisplayForm()) end -- Is it a lemma category? local postype = export.pos_lemma_or_nonlemma(data.pos_category) if not postype then -- We don't know what this category is, so tag it with a tracking category. --[=[ [[Special:WhatLinksHere/Template:tracking/headword/unrecognized pos]] ]=] table.insert(tracking_categories, "head tracking/unrecognized pos") require("Module:debug/track"){ "headword/unrecognized pos", "headword/unrecognized pos/lang/" .. data.lang:getCode(), "headword/unrecognized pos/pos/" .. data.pos_category } elseif not data.noposcat then table.insert(data.categories, 1, data.lang:getCanonicalName() .. " " .. postype .. "s") end -- Preprocess preprocess(data, postype) if namespace == "" and data.lang:getType() ~= "reconstructed" then local m_links = require("Module:links") for _, head in ipairs(data.heads) do if title.prefixedText ~= m_links.getLinkPage(m_links.remove_links(head), data.lang) then --[=[ [[Special:WhatLinksHere/Template:tracking/headword/pagename spelling mismatch]] ]=] require("Module:debug/track"){ "headword/pagename spelling mismatch", "headword/pagename spelling mismatch/" .. data.lang:getCode() } break end end end -- Format and return all the gathered information return format_headword(data) .. format_genders(data) .. format_inflections(data) .. require("Module:utilities/format_categories")( tracking_categories, data.lang, data.sort_key, nil, data.force_cat_output or test_force_categories, data.sc ) end function export.full_headword(data) local tracking_categories = {} -- Script-tags the topmost header. local pagename = title.text local fullPagename = title.fullText local namespace = title.nsText if not data.lang or type(data.lang) ~= "table" or not data.lang.getCode then error("In data, the first argument to full_headword, data.lang should be a language object.") end if not data.sc then data.sc = require("Module:scripts").findBestScript(data.heads and data.heads[1] ~= "" and data.heads[1] or pagename, data.lang) else -- Track uses of sc parameter local best = require("Module:scripts").findBestScript(pagename, data.lang) require("Module:debug/track")("headword/sc") if data.sc:getCode() == best:getCode() then require("Module:debug/track")("headword/sc/redundant") require("Module:debug/track")("headword/sc/redundant/" .. data.sc:getCode()) else require("Module:debug/track")("headword/sc/needed") require("Module:debug/track")("headword/sc/needed/" .. data.sc:getCode()) end end local displayTitle -- Assumes that the scripts in "toBeTagged" will never occur in the Reconstruction namespace. -- Avoid tagging ASCII as Hani even when it is tagged as Hani in the -- headword, as in [[check]]. The check for ASCII might need to be expanded -- to a check for any Latin characters and whitespace or punctuation. if (namespace == "" and data.sc and toBeTagged[data.sc:getCode()] and not pagename:find "^[%z\1-\127]+$") or (data.sc:getCode() == "Jpan" and (test_script(pagename, "Hira") or test_script(pagename, "Kana"))) then displayTitle = '<span class="' .. data.sc:getCode() .. '">' .. pagename .. '</span>' elseif namespace == "Reconstruction" then displayTitle, matched = mw.ustring.gsub( fullPagename, "^(Reconstruction:[^/]+/)(.+)$", function(before, term) return before .. require("Module:script utilities").tag_text( term, data.lang, data.sc ) end ) if matched == 0 then displayTitle = nil end end if displayTitle then local frame = mw.getCurrentFrame() frame:callParserFunction( "DISPLAYTITLE", displayTitle ) end if data.force_cat_output then --[=[ [[Special:WhatLinksHere/Template:tracking/headword/force cat output]] ]=] require("Module:debug/track")("headword/force cat output") end if data.getCanonicalName then error('The "data" variable supplied to "full_headword" should not be a language object.') end -- Were any categories specified? if data.categories and #data.categories > 0 then local lang_name = require("Module:string/pattern_escape")(data.lang:getCanonicalName()) for _, cat in ipairs(data.categories) do -- Does the category begin with the language name? If not, tag it with a tracking category. if not mw.ustring.find(cat, "^" .. lang_name) then mw.log(cat, data.lang:getCanonicalName()) table.insert(tracking_categories, "head tracking/no lang category") --[=[ [[Special:WhatLinksHere/Template:tracking/head tracking/no lang category]] ]=] require("Module:debug/track"){ "headword/no lang category", "headword/no lang category/lang/" .. data.lang:getCode() } end end if not data.pos_category and mw.ustring.find(data.categories[1], "^" .. data.lang:getCanonicalName()) then data.pos_category = mw.ustring.gsub(data.categories[1], "^" .. data.lang:getCanonicalName() .. " ", "") table.remove(data.categories, 1) end end if not data.pos_category then error( 'No valid part-of-speech categories were found in the list ' .. 'of categories passed to the function "full_headword". ' .. 'The part-of-speech category should consist of a language\'s ' .. 'canonical name plus a part of speech.' ) end -- Categorise for unusual characters local standard = data.lang:getStandardCharacters() if standard then if mw.ustring.len(title.subpageText) ~= 1 and not non_categorizable() then for character in mw.ustring.gmatch(title.subpageText, "([^" .. standard .. "])") do local upper = mw.ustring.upper(character) if not mw.ustring.find(upper, "[" .. standard .. "]") then character = upper end table.insert( data.categories, data.lang:getCanonicalName() .. " terms spelled with " .. character ) end end end -- Categorise for palindromes if title.nsText ~= "Reconstruction" and mw.ustring.len(title.subpageText)>2 and require('Module:palindromes').is_palindrome( title.subpageText, data.lang, data.sc ) then table.insert(data.categories, data.lang:getCanonicalName() .. " palindromes") end -- This may add more categories (e.g. gender categories), so make sure it gets -- evaluated first. local text = show_headword_line(data) return text .. require("Module:utilities/format_categories")( data.categories, data.lang, data.sort_key, nil, data.force_cat_output or test_force_categories, data.sc ) .. require("Module:utilities/format_categories")( tracking_categories, data.lang, data.sort_key, nil, data.force_cat_output or test_force_categories, data.sc ) end return export 8l8q643q8t9ku2yjo8k2eyfr2scxjw0 828 2966 8278 2022-07-21T19:03:33Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local data = {} data.invariable = { "cmavo", "cmene", "fu'ivla", "gismu", "Han tu", "hanzi", "hanja", "jyutping", "kanji", "lujvo", "phrasebook", "pinyin", "rafsi", "romaji", } data.lemmas = { "abbreviations", "acronyms", "adjectives", "adnominals", "adpositions", "adverbs", "affixes", "ambipositions", "articles", "circumfixes", "circumpositions", "classifiers", "cmavo", "cmavo clusters", "cmene", "combining forms", "conjunctions", "counters", "determiners", "diacritical marks", "equative adjectives", "fu'ivla", "gismu", "Han characters", "Han tu", "hanzi", "hanja", "ideophones", "idioms", "infixes", "interfixes", "initialisms", "interjections", "kanji", "letters", "ligatures", "lujvo", "morphemes", "non-constituents", "nouns", "numbers", "numeral symbols", "numerals", "particles", "phrases", "postpositions", "postpositional phrases", "predicatives", "prefixes", "prepositions", "prepositional phrases", "preverbs", "pronominal adverbs", "pronouns", "proverbs", "proper nouns", "punctuation marks", "relatives", "roots", "stems", "suffixes", "syllables", "symbols", "verbs", } data.nonlemmas = { "active participles", "adjectival participles", "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", "contractions", "converbs", "determiner comparative forms", "determiner forms", "determiner superlative forms", "diminutive nouns", "equative adjective forms", "equative adjectives", "future participles", "gerunds", "infinitive forms", "infinitives", "interjection forms", "jyutping", "kanji readings", "misspellings", "negative participles", "nominal participles", "noun case 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 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 participles", "present passive participles", "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", } -- These languages will not have "LANG multiword terms" categories added. data.no_multiword_cat = { -------- Languages without spaces between words (sometimes spaces between phrases) -------- "aho", -- Ahom "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) "nod", -- Northern Thai "ojp", -- Old Japanese "tdd", -- Tai Nüa "th", -- Thai "tts", -- Isan "twh", -- Tai Dón "shn", -- Shan "sou", -- Southern Thai "zh", -- Chinese (all varieties with Chinese characters) -------- 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", } -- In these languages, the hyphen is not considered a word separator for the "multiword terms" category. data.hyphen_not_multiword_sep = { "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", -- 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 "hil", -- Hiligaynon; hyphens for mid-word glottal stops "ilo", -- Ilocano; hyphens for mid-word glottal stops "lcp", -- Western Lawa; dash as syllable joiner "lwl", -- Eastern Lawa; 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 } -- These languages will not have "LANG masculine nouns" and similar categories added. data.no_gender_cat = { -- Languages without gender but which use the gender field for other purposes "ja", "th", } data.notranslit = { "ams", "az", "bbc", "bug", "cia", "cjm", "cmn", "hak", "ja", "kzg", "lad", "lzh", "ms", "mul", "mvi", "nan", "oj", "okn", "pi", "ro", "ryn", "rys", "ryu", "sh", "tgt", "th", "tkn", "tly", "txg", "und", "vi", "xug", "yue", "yoi", "yox", "za", "zh", } -- Script codes for which a script-tagged display title will be added. data.toBeTagged = { "Ahom", "Arab", "Avst", "Bali", "Cham", "Copt", "Deva", "Kali", "Hani", "Hebr", "Lana", "Linb", "Mand", "Mong", "polytonic", "Rjng", "Samr", "Sund", "Sylo", "Syrc", "Tang", "Tavt", "Ugar", "Xsux", } for key, list in pairs(data) do data[key] = {} for _, item in ipairs(list) do data[key][item] = true end end -- 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. We put this at the bottom -- because it's a map, not a list. 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", } return data 6pn90w8n5vs655s5g93y40jsgu2oe3b 10 2967 8279 2022-07-21T19:07:33Z Rebel Agent 2678 Ke dile tsebe wikitext text/x-wiki [[Appendix:English pronunciation|enPR]]: {{enPRchar|{{{1}}}|{{{2|}}}|{{{3|}}}|{{{4|}}}|{{{5|}}}|{{{6|}}}}}<!-- --><noinclude>{{documentation}}</noinclude> 0okn96a7wutprh259r9mis6yqfn86op 10 2968 8280 2022-07-21T19:08:37Z Rebel Agent 2678 Ke dirile tempolete wikitext text/x-wiki <!-- --><span class="AHD enPR">{{{1}}}</span><!-- -->{{#if:{{{2|}}}|, <span class="AHD enPR">{{{2}}}</span>}}<!-- -->{{#if:{{{3|}}}|, <span class="AHD enPR">{{{3}}}</span>}}<!-- -->{{#if:{{{4|}}}|, <span class="AHD enPR">{{{4}}}</span>}}<!-- -->{{#if:{{{5|}}}|, <span class="AHD enPR">{{{5}}}</span>}}<!-- -->{{#if:{{{6|}}}|, <span class="AHD enPR">{{{6}}}</span>}}<!-- --><includeonly>{{#if:{{{1|}}}||[[Category:Pronunciation templates without a pronunciation]]}}</includeonly><!-- --><noinclude>{{documentation}}</noinclude> es26i6n2ayh3jwns222l7799p7yavd5 10 2969 8281 2022-07-21T19:16:19Z Rebel Agent 2678 Ke dirile tempolete wikitext text/x-wiki [[ethnologue:{{{code|{{{1}}}}}}|Ethnologue entry for {{{lang|{{{2|{{PAGENAME}}}}}}}}]], '''{{{code|{{{1}}}}}}'''<noinclude> {{documentation}} {{rfd}} </noinclude> s50qg4rd4fgn2kj8znszszun1u63ve0 10 2970 8282 2022-07-21T19:18:06Z Rebel Agent 2678 Ke dirile tempolete wikitext text/x-wiki {{check deprecated lang param usage|lang={{{lang|}}}|<!-- -->{{maintenance box|red<!-- -->|image={{#if:{{{fail|}}}|[[File:Icon delete.svg|50px]]|[[Image:Crystal Clear filesystem trashcan full.png|60px]]}}<!-- -->|title=<!-- --><span id="rfd-notice-{{{1|}}}-{{{topic|}}}"></span><!-- -->{{#if:{{{fail|}}}<!-- -->|A user has marked this {{<noinclude>temp|</noinclude>pagetype}} as having failed a<!-- -->|A user has added this {{<noinclude>temp|</noinclude>pagetype}} to<!-- -->}} [[{{#invoke:request-forum|rfd|{{{1|}}}|{{NAMESPACE}}}}#{{{fragment|{{{section|{{#invoke:string|gsub|{{FULLPAGENAME}}|/documentation|}}}}}}}}|{{#if:{{{fail|}}}|request|requests}} for deletion]]<!-- -->{{#if:{{{fail|}}}||<sup class="plainlinks" style="font-weight:normal" title="Start discussion">(<!-- -->[{{fullurl:{{#invoke:request-forum|rfd|{{{1|}}}|{{NAMESPACE}}}}|action=edit&section=new{{#switch:{{#if:{{{lang|}}}|{{{lang|}}}|{{{1|}}}}}|=|en=|#default=&preload=Template:rfd/preload$1&preloadparams%5B%5D={{urlencode:{{langname|{{{lang|{{{1|<noinclude>und</noinclude>}}}}}}}}}}.%20}}&preloadtitle={{urlencode:[[:{{FULLPAGENAME}}#rfd-notice-{{{1|}}}-{{{topic|}}}|{{FULLPAGENAME}}]]}}}} +]<!-- -->)</sup>}}.<!-- -->|text=<!-- -->Please see that page for discussion and {{#if:{{{fail|}}}|consensus|justifications}}{{#if:{{{2|}}}|&#32;beyond the initial comment of: '''“{{{2|}}}”'''}}<!-- -->. <!-- -->{{#if:{{{fail|}}}<!-- -->|The discussion is closed now, and this page is awaiting speedy-deletion by an administrator. If you object, please remove {{p|fail|1}} from the template and reopen the discussion.<!-- -->|You may continue to edit this {{<noinclude>temp|</noinclude>pagetype}} while the discussion proceeds, but please mention significant edits at the RFD discussion and ensure that the intention of votes already cast is not left unclear. Do not remove the {{temp|rfd}} until the debate has finished.<!-- -->}}<!-- -->}}<!--(end of {{maintenance box}}) -->}}<!-- (end of {{check deprecated lang param usage}}) --><includeonly><!-- -->{{#if:{{{nocat|}}}||<!-- -->{{#if:{{{fail|}}}<!-- -->|[[Category:Candidates for speedy deletion]]<!-- -->|{{#switch:{{NAMESPACE}}<!-- -->||Citations|Transwiki|Reconstruction=<!-- -->{{categorize<!-- -->|{{{1|}}}<!-- -->|Requests for deletion in {{langname|{{{1|}}}}} entries<!-- -->|{{#if:{{{topic|}}}|Entries needing topical attention}}<!-- -->|sort={{{sort|}}}<!-- -->}}<!-- -->|#default=[[Category:Requests for deletion/Others]]<!-- -->}}<!-- -->}}<!-- -->{{#if:{{{topic|}}}|[[Category:rfd with topic]]}}<!-- -->}}<!-- --></includeonly><!-- --><noinclude>{{documentation}}</noinclude> qjbm4pfvb7fkn7ao7nl869ax67zuehg 10 2971 8283 2022-07-21T19:19:30Z Rebel Agent 2678 Ke dirile tempolete wikitext text/x-wiki <div class="noprint maintenance-box maintenance-box-{{{1|blue}}}" style="background:#{{#switch:{{{1|blue}}}||blue=EEEEFF|red=FFE7DD|yellow=FFFFDD|grey=F0F0F0|orange=FFDD44}}; width:90%; margin: 0.75em auto; border:1px dashed #{{#switch:{{{1|blue}}}||blue=4444AA|red=884444|yellow=888822|grey=444444|orange=DDAA00}}; padding: 0.25em; "> {| | rowspan="2" | {{{image}}} ! style="text-align: left;" | {{{title}}} |- | {{{text}}} |}</div><noinclude>{{documentation}}</noinclude> n8lldvtjper0ph2s663yda8kyuifv9z 828 2972 8284 2022-07-21T19:21:24Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local str = {} -- Cannot include null byte. local UTF8_char = "[\1-\127\194-\244][\128-\191]*" --[[ ulen Counts UTF-8 characters. Faster than mw.ustring.len. Assumes that the encoding is correct. Unlike mw.ustring.len, does not return nil if encoding is invalid. Does not count the bytes 192, 193, and 245-255. They are not used in UTF-8 and will not occur if the string is valid. They are replaced with the replacement character (U+FFFD) on MediaWiki pages. --]] function str.ulen(text) local _, length = string.gsub(text, UTF8_char, "") return length end --[[ len This function returns the length of the target string. Usage: {{#invoke:string|len|target_string|}} OR {{#invoke:string|len|s=target_string}} Parameters s: The string whose length to report If invoked using named parameters, Mediawiki will automatically remove any leading or trailing whitespace from the target string. ]] function str.len(frame) local new_args = str._getParameters(frame.args, { 's' }); local s = new_args['s'] or ''; return mw.ustring.len(s) end --[[ sub This function returns a substring of the target string at specified indices. Usage: {{#invoke:string|sub|target_string|start_index|end_index}} OR {{#invoke:string|sub|s=target_string|i=start_index|j=end_index}} Parameters s: The string to return a subset of i: The fist index of the substring to return, defaults to 1. j: The last index of the string to return, defaults to the last character. The first character of the string is assigned an index of 1. If either i or j is a negative value, it is interpreted the same as selecting a character by counting from the end of the string. Hence, a value of -1 is the same as selecting the last character of the string. If the requested indices are out of range for the given string, an error is reported. ]] function str.sub(frame) local new_args = str._getParameters(frame.args, { 's', 'i', 'j' }); local s = new_args['s'] or ''; local i = tonumber(new_args['i']) or 1; local j = tonumber(new_args['j']) or -1; local len = mw.ustring.len(s); -- Convert negatives for range checking if i < 0 then i = len + i + 1; end if j < 0 then j = len + j + 1; end if i > len or j > len or i < 1 or j < 1 then return str._error('String subset index out of range'); end if j < i then return str._error('String subset indices out of order'); end return mw.ustring.sub(s, i, j) end --[[ This function implements that features of {{str sub old}} and is kept in order to maintain these older templates. ]] function str.sublength(frame) local i = tonumber(frame.args.i) or 0 local len = tonumber(frame.args.len) return mw.ustring.sub(frame.args.s, i + 1, len and (i + len)) end --[[ match This function returns a substring from the source string that matches a specified pattern. Usage: {{#invoke:string|match|source_string|pattern_string|start_index|match_number|plain_flag|nomatch_output}} OR {{#invoke:string|pos|s=source_string|pattern=pattern_string|start=start_index |match=match_number|plain=plain_flag|nomatch=nomatch_output}} Parameters s: The string to search pattern: The pattern or string to find within the string start: The index within the source string to start the search. The first character of the string has index 1. Defaults to 1. match: In some cases it may be possible to make multiple matches on a single string. This specifies which match to return, where the first match is match= 1. If a negative number is specified then a match is returned counting from the last match. Hence match = -1 is the same as requesting the last match. Defaults to 1. plain: A flag indicating that the pattern should be understood as plain text. Defaults to false. nomatch: If no match is found, output the "nomatch" value rather than an error. If invoked using named parameters, Mediawiki will automatically remove any leading or trailing whitespace from each string. In some circumstances this is desirable, in other cases one may want to preserve the whitespace. If the match_number or start_index are out of range for the string being queried, then this function generates an error. An error is also generated if no match is found. If one adds the parameter ignore_errors=true, then the error will be suppressed and an empty string will be returned on any failure. For information on constructing Lua patterns, a form of [regular expression], see: * http://www.lua.org/manual/5.1/manual.html#5.4.1 * http://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#Patterns * http://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#Ustring_patterns ]] function str.match(frame) local new_args = str._getParameters(frame.args, { 's', 'pattern', 'start', 'match', 'plain', 'nomatch' }); local s = new_args['s'] or ''; local start = tonumber(new_args['start']) or 1; local plain_flag = str._getBoolean(new_args['plain'] or false); local pattern = new_args['pattern'] or ''; local match_index = math.floor(tonumber(new_args['match']) or 1); local nomatch = new_args['nomatch']; if s == '' then return str._error('Target string is empty'); end if pattern == '' then return str._error('Pattern string is empty'); end if math.abs(start) < 1 or math.abs(start) > mw.ustring.len(s) then return str._error('Requested start is out of range'); end if match_index == 0 then return str._error('Match index is out of range'); end if plain_flag then pattern = str.pattern_escape(pattern); end local result if match_index == 1 then -- Find first match is simple case result = mw.ustring.match(s, pattern, start) else if start > 1 then s = mw.ustring.sub(s, start); end local iterator = mw.ustring.gmatch(s, pattern); if match_index > 0 then -- Forward search for w in iterator do match_index = match_index - 1; if match_index == 0 then result = w; break; end end else -- Reverse search local result_table = {}; local count = 1; for w in iterator do result_table[count] = w; count = count + 1; end result = result_table[count + match_index]; end end if result == nil then if nomatch == nil then return str._error('Match not found'); else return nomatch; end else return result; end end --[[ pos This function returns a single character from the target string at position pos. Usage: {{#invoke:string|pos|target_string|index_value}} OR {{#invoke:string|pos|target=target_string|pos=index_value}} Parameters target: The string to search pos: The index for the character to return If invoked using named parameters, Mediawiki will automatically remove any leading or trailing whitespace from the target string. In some circumstances this is desirable, in other cases one may want to preserve the whitespace. The first character has an index value of 1. If one requests a negative value, this function will select a character by counting backwards from the end of the string. In other words pos = -1 is the same as asking for the last character. A requested value of zero, or a value greater than the length of the string returns an error. ]] function str.pos(frame) local new_args = str._getParameters(frame.args, { 'target', 'pos' }); local target_str = new_args['target'] or ''; local pos = tonumber(new_args['pos']) or 0; if pos == 0 or math.abs(pos) > mw.ustring.len(target_str) then return str._error('String index out of range'); end return mw.ustring.sub(target_str, pos, pos); end --[[ str_find This function duplicates the behavior of {{str_find}}, including all of its quirks. This is provided in order to support existing templates, but is NOT RECOMMENDED for new code and templates. New code is recommended to use the "find" function instead. Returns the first index in "source" that is a match to "target". Indexing is 1-based, and the function returns -1 if the "target" string is not present in "source". Important Note: If the "target" string is empty / missing, this function returns a value of "1", which is generally unexpected behavior, and must be accounted for separatetly. ]] function str.str_find(frame) local new_args = str._getParameters(frame.args, { 'source', 'target' }); local source_str = new_args['source'] or ''; local target_str = new_args['target'] or ''; if target_str == '' then return 1; end local start = mw.ustring.find(source_str, target_str, 1, true) if start == nil then start = -1 end return start end --[[ find This function allows one to search for a target string or pattern within another string. Usage: {{#invoke:string|find|source_str|target_string|start_index|plain_flag}} OR {{#invoke:string|find|source=source_str|target=target_str|start=start_index|plain=plain_flag}} Parameters source: The string to search target: The string or pattern to find within source start: The index within the source string to start the search, defaults to 1 plain: Boolean flag indicating that target should be understood as plain text and not as a Lua style regular expression, defaults to true If invoked using named parameters, Mediawiki will automatically remove any leading or trailing whitespace from the parameter. In some circumstances this is desirable, in other cases one may want to preserve the whitespace. This function returns the first index >= "start" where "target" can be found within "source". Indices are 1-based. If "target" is not found, then this function returns an empty string. If either "source" or "target" are missing / empty, this function also returns an empty string. This function should be safe for UTF-8 strings. ]] function str.find(frame) local params = { [1] = { required = true, allow_empty = true }, [2] = { required = true, allow_empty = true }, [3] = { type = "number" }, [4] = { type = "boolean" }, } local args = require("Module:parameters").process(frame.args, params) return mw.ustring.find(args[1], args[2], args[3], args[4]) end --[[ replace This function allows one to replace a target string or pattern within another string. Usage: {{#invoke:string|replace|source_str|pattern_string|replace_string|replacement_count|plain_flag}} OR {{#invoke:string|replace|source=source_string|pattern=pattern_string|replace=replace_string| count=replacement_count|plain=plain_flag}} Parameters source: The string to search pattern: The string or pattern to find within source replace: The replacement text count: The number of occurences to replace, defaults to all. plain: Boolean flag indicating that pattern should be understood as plain text and not as a Lua style regular expression, defaults to true ]] function str.replace(frame) local new_args = str._getParameters(frame.args, { 'source', 'pattern', 'replace', 'count', 'plain' }); local source_str = new_args['source'] or ''; local pattern = new_args['pattern'] or ''; local replace = new_args['replace'] or ''; local count = tonumber(new_args['count']); local plain = new_args['plain'] or true; if source_str == '' or pattern == '' then return source_str; end plain = str._getBoolean(plain); if plain then pattern = str.pattern_escape(pattern); replace = mw.ustring.gsub(replace, "%%", "%%%%"); --Only need to escape replacement sequences. end local result; result = mw.ustring.gsub(source_str, pattern, replace, count); return result; end function str.gsub(frame) local params = { [1] = { required = true, allow_empty = true, allow_whitespace = true}, [2] = { required = true, allow_empty = true, allow_whitespace = true}, [3] = { required = true, allow_empty = true, allow_whitespace = true}, [4] = { type = "number" }, } local args = require("Module:parameters").process(frame.args, params) return (mw.ustring.gsub(args[1], args[2], args[3], args[4])) end --[[ simple function to pipe string.rep to templates. ]] function str.rep(frame) local repetitions = tonumber(frame.args[2]) if not repetitions then return str._error('function rep expects a number as second parameter, received "' .. (frame.args[2] or '') .. '"') end return string.rep(frame.args[1] or '', repetitions) end function str.lower(frame) local text = frame.args[1] or '' return mw.ustring.lower(text) end str.lc = str.lower --[[ format This function allows one to format strings according to a template. This is a direct interface onto str.format() in Lua, and works like the C printf() function. For example: {{#invoke:string|format|page_%04d.html|65}} will produce the result page_0065.html Parameters 1: The format template. See https://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#string.format 2, 3, ...: Arguments to be inserted into the template. Note that leading and trailing whitespace is not removed from the arguments. ]] function str.format(frame) local fmt = frame.args[1] -- You can't call unpack() directly on frame.args because it isn't really a -- table, and doesn't support the # operator. local args = {} local i = 2 while true do local val = frame.args[i] if not val then break end table.insert(args, val) i = i + 1 end return fmt:format(unpack(args)) end --[[ Helper function that populates the argument list given that user may need to use a mix of named and unnamed parameters. This is relevant because named parameters are not identical to unnamed parameters due to string trimming, and when dealing with strings we sometimes want to either preserve or remove that whitespace depending on the application. ]] function str._getParameters(frame_args, arg_list) local new_args = {}; local index = 1; local value; for _, arg in ipairs(arg_list) do value = frame_args[arg] if value == nil then value = frame_args[index]; index = index + 1; end new_args[arg] = value; end return new_args; end --[[ Helper function to handle error messages. ]] function str._error(error_str) local frame = mw.getCurrentFrame(); local error_category = frame.args.error_category or 'Errors reported by Module String'; local ignore_errors = frame.args.ignore_errors or false; local no_category = frame.args.no_category or false; if str._getBoolean(ignore_errors) then return ''; end local error_str = '<strong class="error">String Module Error: ' .. error_str .. '</strong>'; if error_category ~= '' and not str._getBoolean(no_category) then error_str = '[[Category:' .. error_category .. ']]' .. error_str; end return error_str; end --[[ Helper Function to interpret boolean strings ]] function str._getBoolean(boolean_str) local boolean_value; if type(boolean_str) == 'string' then boolean_str = boolean_str:lower(); if boolean_str == 'false' or boolean_str == 'no' or boolean_str == '0' or boolean_str == '' then boolean_value = false; else boolean_value = true; end elseif type(boolean_str) == 'boolean' then boolean_value = boolean_str; else error('No boolean value found'); end return boolean_value end --[[ Helper function that escapes all pattern characters – ().%+-*?[^$] – so that they will be treated as plain text. ]] function str.pattern_escape(pattern_str) local invoked = false local escape = require("Module:string/pattern_escape") if type(pattern_str) == "table" then if pattern_str.args then local frame = pattern_str invoked = true if frame.args[1] then pattern_str = frame.args[1] else pattern_str = frame:getParent().args[1] end else error("First argument to pattern_escape should be a string, a number, or a frame object.") end elseif not (type(pattern_str) == "string" or type(pattern_str) == "number") then error("First argument to pattern_escape should be a string or a number.") end if invoked then return (escape(pattern_str)) -- only the first value else return escape(pattern_str) end end function str.count(text, pattern, plain) if not (type(text) == "string" or type(text) == "number") then error('The first argument to the function "count" must be a string or a number, not a ' .. type(text) .. '.') end if not (type(pattern) == "string" or type(pattern) == "number") then error('The first argument to the function "count" must be a string or a number, not a ' .. type(text) .. '.') end if plain then pattern = str.pattern_escape(pattern) end local _, count = mw.ustring.gsub(text, pattern, "") return count end function str.plain_gsub(text, pattern, replacement) local invoked = false if type(text) == "table" then invoked = true if text.args then local frame = text local params = { [1] = {}, [2] = {}, [3] = { allow_empty = true }, } local args = require("Module:parameters").process(frame.args, params) text = args[1] pattern = args[2] replacement = args[3] else error("If the first argument to plain_gsub is a table, it should be a frame object.") end else if not (type(pattern) == "string" or type(pattern) == "number") then error("The second argument to plain_gsub should be a string or a number.") end if not (type(replacement) == "string" or type(replacement) == "number") then error("The third argument to plain_gsub should be a string or a number.") end end pattern = str.pattern_escape(pattern) if invoked then text = mw.ustring.gsub(text, pattern, replacement) return text else return mw.ustring.gsub(text, pattern, replacement) end end function str.matchToArray(text, pattern) local invoked = false if type(text) == "table" then invoked = true if text.args then local frame = text local params = { [1] = { required = true }, [2] = { required = true }, } local args = require("Module:parameters").process(frame.args, params) text = args[1] pattern = args[2] else error("If the first argument to matchToArray is a table, it should be a frame object.") end else if not (type(pattern) == "string" or type(pattern) == "number") then error("The second argument to matchToArray should be a string or a number.") end end local matches = {} local i = 0 for match in mw.ustring.gmatch(text, pattern) do i = i + 1 matches[i] = match end if i > 0 then if invoked then return table.concat(matches, ", ") else return matches end else if invoked then return "" else return nil end end end --[=[ Similar to gmatch, but it returns the count of the match in addition to the list of captures, something like ipairs(). If the pattern doesn't contain any captures, the whole match is returned. Invoke thus: for i, whole_match in require("Module:string").imatch(text, pattern) do [ do something with i and whole_match ] end or for i, capture1[, capture2[, capture3[, ...]]] in require("Module:string").imatch(text, pattern) do [ do something with i and capture1 ] end For example, this code for i, whole_match in require("Module:string").imatch("a b c", "[a-z]") do mw.log(i, whole_match) end will log 1 a 2 b 3 c ]=] function str.imatch(text, pattern, pos, plain, use_basic_Lua_function) local i = 0 pos = pos or 0 if not string.find(pattern, "%b()") then pattern = "(" .. pattern .. ")" end local find = use_basic_Lua_function and string.find or mw.ustring.find return function() i = i + 1 local return_values = { find(text, pattern, pos, plain) } local j = return_values[2] if return_values[3] then pos = j + 1 -- Skip the first two returned values, which are the indices of the -- whole match. return i, unpack(return_values, 3) end end end function str.escapebytes(s) return (string.gsub(s, '.', function(char) return ('\\%03d'):format(string.byte(char)) end)) end function str.URIdecode(frame) return mw.uri.decode(frame.args[1], frame.args[2] or "PATH") end return str oeq6i4dx2v1wn2dviuppuuuutmkonbn 10 2973 8285 2022-07-21T19:22:54Z Rebel Agent 2678 Ke dirile tempolete wikitext text/x-wiki {{#invoke:documentation|show|hr={{{hr|above}}}}} 3mqq1e6fru8l8n97ptwphb1qc1b72m7 828 2974 8286 2022-07-21T19:24:52Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local export = {} -- it is either here, or in [[Module:ugly hacks]], and it is not in ugly hacks. function export.CONTENTMODEL() return mw.title.getCurrentTitle().contentModel end local skins = { ["common" ] = ""; ["vector" ] = "Vector"; ["monobook" ] = "Monobook"; ["cologneblue"] = "Cologne Blue"; ["modern" ] = "Modern"; } local Array = require "Module:array" local function compare_pages(page1, page2, text) return "[" .. tostring( mw.uri.fullUrl("Special:ComparePages", { page1 = page1, page2 = page2 })) .. " " .. text .. "]" end local function page_exists(title) local success, title_obj = pcall(mw.title.new, title) return success and title_obj.exists end -- Avoid transcluding [[Module:languages/cache]] everywhere. local lang_cache = setmetatable({}, { __index = function (self, k) return require "Module:languages/cache"[k] end }) local function zh_link(word) return require("Module:links").full_link{ lang = lang_cache.zh, term = word } end local function make_Unicode_data_documentation(title, cats) local subpage, first_three_of_code_point = title.fullText:match("^Module:Unicode data/([^/]+)/(%x%x%x)$") if subpage == "names" or subpage == "images" then local low, high = tonumber(first_three_of_code_point .. "000", 16), tonumber(first_three_of_code_point .. "FFF", 16) return string.format( "This data module contains the %s of " .. "[[Appendix:Unicode|Unicode]] code points within the range U+%04X to U+%04X.", subpage == "images" and "titles of images" or "names", low, high) end end -- This provides categories and documentation for various data modules, so that -- [[Category:Uncategorized modules]] isn’t unnecessarily cluttered. -- It is a list of tables, each of which have the following possible fields: -- `regex` (required): A Lua pattern to match the module's title. If it matches, the data in this entry will be used. -- Any captures in the pattern can by referenced in the `cat` field using %1 for the first capture, %2 for the -- second, etc. (often used for creating the sortkey for the category). In addition, the captures are passed to the -- `process` function as the third and subsequent parameters. -- `process` (optional): This may be a function or a string. If it is a function, it is called as follows: -- process(TITLE, CATS, CAPTURE1, CAPTURE2, ...) -- where: -- * TITLE is a title object describing the module's title; see [https://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#Title_objects]. -- * CATS is an array object (see [[Module:array]]) of categories that the module will be added to. -- * CAPTURE1, CAPTURE2, ... contain any captures in the `regex` field. -- The return value of `process` should be a string and will be used as the module's documentation. -- If `process` is a string, it is the name of a submodule under 'Module:documentation/functions/' which returns a -- function, of the same type as described above. If `process` is omitted entirely, the module will have no -- documentation. -- `cat` (optional): A string naming the category into which the module should be placed. Captures specified in `regex` -- may be referenced in this string using %1 for the first capture, %2 for the second, etc. Currently, in order to put -- the module into multiple categories, you need to write a `process` function that adds categories to the CATS -- parameter passed in. local module_regex = { { regex = "^Module:languages/.+$", cat = "Language and script modules", }, { regex = "^Module:scripts/.+$", cat = "Language and script modules", }, { regex = "^Module:data tables/data..?.?.?$", cat = "Reference module sharded data tables", }, { regex = "^Module:Quotations/...?.?.?.?.?.?$", cat = "Quotation data modules", }, { regex = "^Module:zh/data/dial%-pron/.+$", cat = "Chinese dialectal pronunciation data modules", process = "zh dial or syn", }, { regex = "^Module:zh/data/dial%-syn/.+$", cat = "Chinese dialectal synonyms data modules", process = "zh dial or syn", }, { regex = "^Module:zh/data/glyph%-data/.+$", cat = "Chinese historical character forms data modules", process = function(title, cats) local character = title.fullText:match("^Module:zh/data/glyph%-data/(.+)") if character then return ("This module contains data on historical forms of the Chinese character %s.") :format(zh_link(character)) end end, }, { regex = "^Module:zh/data/ltc%-pron/(.+)$", cat = "Middle Chinese pronunciation data modules|%1", process = "zh data", }, { regex = "^Module:zh/data/och%-pron%-BS/(.+)$", cat = "Old Chinese (Baxter-Sagart) pronunciation data modules|%1", process = "zh data", }, { regex = "^Module:zh/data/och%-pron%-ZS/(.+)$", cat = "Old Chinese (Zhengzhang) pronunciation data modules|%1", process = "zh data", }, { -- capture rest of zh/data submodules regex = "^Module:zh/data/(.+)$", cat = "Chinese data modules|%1", }, { regex = "^Module:mul/guoxue%-data/cjk%-?(.*)$", process = "guoxue-data", }, { regex = "^Module:Unicode data/(.+)$", cat = "Unicode data modules|%1", process = make_Unicode_data_documentation, }, { regex = "^Module:number list/data/(.+)$", process = "number list", }, { regex = "^Module:accel/(.+)$", process = function(title, cats) local lang_code = title.subpageText local lang = lang_cache[lang_code] if lang then cats:insert(lang:getCanonicalName() .. " modules|accel") cats:insert(("Accel submodules|%s"):format(lang:getCanonicalName())) return ("This module contains new entry creation rules for %s; see [[WT:ACCEL]] for an overview, and [[Module:accel]] for information on creating new rules.") :format(lang:makeCategoryLink()) end end, }, { regex = "^Module:inc%-ash/dial/data/(.+)$", cat = "Ashokan Prakrit modules|%1", process = function(title, cats) local word = title.fullText:match("^Module:inc%-ash/dial/data/(.+)$") if word then local lang = lang_cache["inc-ash"] return ("This module contains data on the pronunciation of %s in dialects of %s.") :format(require("Module:links").full_link({ term = word, lang = lang }, "term"), lang:makeCategoryLink()) end end, }, { regex = "^Module:[%l-]+:Dialects$", process = function(title, cats) local content = title:getContent() local has_aliases = content:find("aliases") ~= nil return mw.getCurrentFrame():expandTemplate { title = "dialectal data module", args = { ["labels-aliases"] = has_aliases }, } end, }, { regex = "^.+%-translit$", process = "translit", }, { regex = "^Module:category tree/poscatboiler/data/lang%-specific/(.+)$", process = function(title, cats, lang_code) local lang = lang_cache[lang_code] if lang then local langname = lang:getCanonicalName() cats:insert("Category tree data modules/poscatboiler|" .. langname) cats:insert(langname .. " modules") cats:insert(langname .. " data modules") return "This module handles generating the descriptions and categorization for " .. langname .. " category pages " .. "of the format \"" .. langname .. " LABEL\" where LABEL can be any text. Examples are " .. "[[:Category:Bulgarian conjugation 2.1 verbs]] and [[:Category:Russian velar-stem neuter-form nouns]]. " .. "This module is part of the poscatboiler system, which is a general framework for generating the " .. "descriptions and categorization of category pages.\n\n" .. "For more information, see [[Module:category tree/poscatboiler/data/lang-specific/documentation]]." end end }, { regex = "^Module:category tree/poscatboiler/data/(.+)$", cat = "Category tree data modules/poscatboiler|%1", }, { regex = "^Module:ja/data/(.+)$", cat = "Japanese data modules|%1", }, { regex = "^Module:Swadesh/data/(.+)$", cat = "Swadesh modules|%1", }, { regex = "^Module:typing%-aids", process = function(title, cats) local data_suffix = title.fullText:match("^Module:typing%-aids/data/(.+)$") if data_suffix then cats:insert("Data modules") if data_suffix:find "^[%l-]+$" then local lang = require "Module:languages".getByCode(data_suffix) if lang then cats:insert(lang:getCanonicalName() .. " modules") end elseif data_suffix:find "^%u%l%l%l$" then local script = require "Module:scripts".getByCode(data_suffix) if script then cats:insert(script:getCategoryName()) end end end end, }, { regex = "^Module:R:([a-z%-]+):(.+)$", process = function(title, cats, lang_code, refname) local lang = lang_cache[lang_code] if lang then cats:insert(lang:getCanonicalName() .. " modules|" .. refname) cats:insert(("Reference modules|%s"):format(lang:getCanonicalName())) return mw.getCurrentFrame():preprocess("This module implements the reference template {{temp|R:" .. lang_code .. ":" .. refname .. "}}.") end end, }, } function export.show(frame) local params = { ["hr"] = {}, ["for"] = {}, ["from"] = {}, ["notsubpage"] = { type = "boolean", default = false }, ["nodoc"] = { type = "boolean", default = false }, } local args = require("Module:parameters").process(frame.args, params) local output = Array('\n<div class="documentation" style="display:block; clear:both">\n') local cats = Array() local nodoc = args.nodoc if (not args.hr) or (args.hr == "above") then output:insert("----\n") end local title = ((args['for'] ~= "") and args['for']) and mw.title.new(args['for']) or mw.title.getCurrentTitle() local doc_title = mw.title.new((args['from'] ~= "") and args['from'] or (title.fullText .. '/documentation')) local contentModel = title.contentModel local pagetype = mw.getContentLanguage():lcfirst(title.nsText) .. " page" local preload, fallback_docs, doc_content, doc_content_module, old_doc_title, user_name, skin_name, needs_doc if contentModel == "javascript" then pagetype = "script" if title.nsText == 'MediaWiki' then if title.text:find('Gadget-') then preload = 'Template:documentation/preloadGadget' else preload = 'Template:documentation/preloadMediaWikiJavaScript' end else preload = 'Template:documentation/preloadTemplate' -- XXX end if title.nsText == 'User' then user_name = title.rootText end elseif contentModel == "css" then pagetype = "style sheet" preload = 'Template:documentation/preloadTemplate' -- XXX if title.nsText == 'User' then user_name = title.rootText end elseif contentModel == "Scribunto" then pagetype = "module" user_name = title.rootText:match("^[Uu]ser:(.+)") if user_name then preload = 'Template:documentation/preloadModuleSandbox' else preload = 'Template:documentation/preloadModule' end elseif title.nsText == "Template" then pagetype = "template" preload = 'Template:documentation/preloadTemplate' elseif title.nsText == "Wiktionary" then pagetype = "project page" preload = 'Template:documentation/preloadTemplate' -- XXX end if doc_title.isRedirect then old_doc_title = doc_title doc_title = mw.title.new(string.match(doc_title:getContent(), "^#[Rr][Ee][Dd][Ii][Rr][Ee][Cc][Tt]%s*:?%s*%[%[([^%[%]]-)%]%]")) end output:insert("<dl class=\"plainlinks\" style=\"font-size: smaller;\">") if doc_title.exists then output:insert( "<dd><i style=\"font-size: larger;\">The following " .. "[[Help:Documenting templates and modules|documentation]] is located at [[" .. doc_title.fullText .. "]]. " .. "^{[[" .. doc_title:fullUrl { action = 'edit' } .. " edit]]} </i></dd>") else if contentModel == "Scribunto" then local automatic_cats = nil if user_name then fallback_docs = "documentation/fallback/user module" automatic_cats = {"User sandbox modules"} else for _, data in ipairs(module_regex) do local captures = {mw.ustring.match(title.fullText, data.regex)} if #captures > 0 then local cat local process_function if type(data.process) == "function" then process_function = data.process elseif type(data.process) == "string" then doc_content_module = "Module:documentation/functions/" .. data.process process_function = require(doc_content_module) end if process_function then doc_content = process_function(title, cats, unpack(captures)) end cat = data.cat if cat then if type(cat) == "string" then cat = {cat} end for _, c in ipairs(cat) do -- gsub() and Lua :gsub() return two arguments, which causes all sorts of problems. -- Terrible design, there should have been a separate two-argument function. local gsub_sucks = mw.ustring.gsub(title.fullText, data.regex, c) table.insert(cats, gsub_sucks) end end break end end end if not automatic_cats then local success, auto_cats = pcall(require("Module:module categorization").categorize, frame, true) if success then for _, category in ipairs(auto_cats) do cats:insert(category) end end end if title.subpageText == "templates" then cats:insert("Template interface modules") end if automatic_cats then for _, c in ipairs(automatic_cats) do cats:insert(c) end end -- meaning module is not in user’s sandbox or one of many datamodule boring series needs_doc = not (automatic_cats or doc_content or fallback_docs) elseif title.nsText == "Template" then --cats:insert("Uncategorized templates") needs_doc = not (fallback_docs or nodoc) elseif (contentModel == "css") or (contentModel == "javascript") then if user_name then skin_name = skins[title.text:sub(#title.rootText + 1):match("^/([a-z]+)%.[jc]ss?$")] if skin_name then fallback_docs = 'documentation/fallback/user ' .. contentModel end end end if doc_content then output:insert( "<dd><i style=\"font-size: larger;\">The following " .. "[[Help:Documenting templates and modules|documentation]] is " .. "generated by [[" .. (doc_content_module or "Module:documentation") .. "]]. ^{[[" .. mw.title.new("Module:documentation"):fullUrl { action = 'edit' } .. " edit]]} </i></dd>") elseif not nodoc then output:insert( "<dd><i style=\"font-size: larger;\">This " .. pagetype .. " lacks a [[Help:Documenting templates and modules|documentation subpage]]. " .. (fallback_docs and "You may " or "Please ") .. "[" .. doc_title:fullUrl { action = 'edit', preload = preload } .. " create it].</i></dd>\n") end end if title.fullText:match("^MediaWiki:Gadget%-") then local is_gadget = false local gadget_list = mw.title.new("MediaWiki:Gadgets-definition"):getContent() for line in mw.text.gsplit(gadget_list, "\n") do local gadget, opts, items = line:match("^%*%s*([A-Za-z][A-Za-z0-9_%-]*)%[(.-)%]|(.+)$") -- opts is unused if not gadget then gadget, items = line:match("^%*%s*([A-Za-z][A-Za-z0-9_%-]*)|(.+)$") end if gadget then items = Array(mw.text.split(items, "|")) for i, item in ipairs(items) do if title.fullText == ("MediaWiki:Gadget-" .. item) then is_gadget = true output:insert("<dd> ''This script is a part of the <code>") output:insert(gadget) output:insert("</code> gadget ([") output:insert(tostring(mw.uri.fullUrl('MediaWiki:Gadgets-definition', 'action=edit'))) output:insert(" edit definitions])'' <dl>") output:insert("<dd> ''Description ([") output:insert(tostring(mw.uri.fullUrl('MediaWiki:Gadget-' .. gadget, 'action=edit'))) output:insert(" edit])'': ") local gadget_description = mw.message.new('Gadget-' .. gadget):plain() gadget_description = frame:preprocess(gadget_description) output:insert(gadget_description) output:insert(" </dd>") items:remove(i) if #items > 0 then for j, item in ipairs(items) do items[j] = '[[MediaWiki:Gadget-' .. item .. '|' .. item .. ']]' end output:insert("<dd> ''Other parts'': ") output:insert(mw.text.listToText(items)) output:insert("</dd>") end output:insert("</dl></dd>") break end end end end if not is_gadget then output:insert("<dd> ''This script is not a part of any [") output:insert(tostring(mw.uri.fullUrl('Special:Gadgets', 'uselang=en'))) output:insert(' gadget] ([') output:insert(tostring(mw.uri.fullUrl('MediaWiki:Gadgets-definition', 'action=edit'))) output:insert(' edit definitions]).</dd>') -- else -- cats:insert("Wiktionary gadgets") end end if old_doc_title then output:insert("<dd> ''Redirected from'' [") output:insert(old_doc_title:fullUrl { redirect = 'no' }) output:insert(" ") output:insert(old_doc_title.fullText) output:insert("] ([") output:insert(old_doc_title:fullUrl { action = 'edit' }) output:insert(" edit]).</dd>\n") end local links = Array() if title.isSubpage and not args.notsubpage then links:insert("[[:" .. title.nsText .. ":" .. title.rootText .. "|root page]]") links:insert("[[Special:PrefixIndex/" .. title.nsText .. ":" .. title.rootText .. "/|root page’s subpages]]") else links:insert("[[Special:PrefixIndex/" .. title.fullText .. "/|subpage list]]") end links:insert( '[' .. tostring(mw.uri.fullUrl('Special:WhatLinksHere/' .. title.fullText, 'hidetrans=1&hideredirs=1')) .. ' links]') if contentModel ~= "Scribunto" then links:insert( '[' .. tostring(mw.uri.fullUrl('Special:WhatLinksHere/' .. title.fullText, 'hidelinks=1&hidetrans=1')) .. ' redirects]') end if (contentModel == "javascript") or (contentModel == "css") then if user_name then links:insert("[[Special:MyPage" .. title.text:sub(#title.rootText + 1) .. "|your own]]") end else links:insert( '[' .. tostring(mw.uri.fullUrl('Special:WhatLinksHere/' .. title.fullText, 'hidelinks=1&hideredirs=1')) .. ' transclusions]') end if contentModel == "Scribunto" then local is_testcases = title.isSubpage and title.subpageText == "testcases" local without_subpage = title.nsText .. ":" .. title.baseText if is_testcases then links:insert("[[:" .. without_subpage .. "|tested module]]") else links:insert("[[" .. title.fullText .. "/testcases|testcases]]") end if user_name then links:insert("[[User:" .. user_name .. "|user page]]") links:insert("[[User talk:" .. user_name .. "|user talk page]]") links:insert("[[Special:PrefixIndex/User:" .. user_name .. "/|userspace]]") else -- If sandbox module, add a link to the module that this is a sandbox of. -- Exclude user sandbox modules like [[User:Dine2016/sandbox]]. if title.text:find("/sandbox%d*%f[/%z]") then cats:insert("Sandbox modules") -- Sandbox modules don’t really need documentation. needs_doc = false -- Will behave badly if “/sandbox” occurs twice in title! local sandbox_of = title.fullText:gsub("/sandbox%d*%f[/%z]", "") local diff if page_exists(sandbox_of) then diff = " (" .. compare_pages(title.fullText, sandbox_of, "diff") .. ")" else require("Module:debug").track("documentation/no sandbox of") end links:insert("[[:" .. sandbox_of .. "|sandbox of]]" .. (diff or "")) -- If not a sandbox module, add link to sandbox module. -- Sometimes there are multiple sandboxes for a single module: -- [[Module:sa-pronunc/sandbox]], [[Module:sa-pronunc/sandbox2]]. -- Occasionally sandbox modules have their own subpages that are also -- sandboxes: [[Module:grc-decl/sandbox/decl]]. else local sandbox_title if title.fullText:find("^Module:grc%-decl/") then sandbox_title = title.fullText:gsub("^Module:grc%-decl/", "Module:grc-decl/sandbox/") elseif is_testcases then sandbox_title = title.fullText:gsub("/testcases", "/sandbox/testcases") else sandbox_title = title.fullText .. "/sandbox" end local sandbox_link = "[[:" .. sandbox_title .. "|sandbox]]" local diff if page_exists(sandbox_title) then diff = " (" .. compare_pages(title.fullText, sandbox_title, "diff") .. ")" end links:insert(sandbox_link .. (diff or "")) end end end if title.nsText == "Template" then -- Error search: all(any namespace), hastemplate (show pages using the template), insource (show source code), incategory (any/specific error) -- [[mw:Help:CirrusSearch]], [[w:Help:Searching/Regex]] -- apparently same with/without: &profile=advanced&fulltext=1 local errorq = 'searchengineselect=mediawiki&search=all: hastemplate:\"'..title.rootText..'\" insource:\"'..title.rootText..'\" incategory:' local eincategory = "Pages_with_module_errors|ParserFunction_errors|DisplayTitle_errors|Pages_with_ISBN_errors|Pages_with_ISSN_errors|Pages_with_reference_errors|Pages_with_syntax_highlighting_errors|Pages_with_TemplateStyles_errors" links:insert( '[' .. tostring(mw.uri.fullUrl('Special:Search', errorq..eincategory )) .. ' errors]' .. ' (' .. '[' .. tostring(mw.uri.fullUrl('Special:Search', errorq..'ParserFunction_errors' )) .. ' parser]' .. '/' .. '[' .. tostring(mw.uri.fullUrl('Special:Search', errorq..'Pages_with_module_errors' )) .. ' module]' .. ')' ) if title.isSubpage and title.text:find("/sandbox%d*%f[/%z]") then -- This is a sandbox template. -- At the moment there are no user sandbox templates with subpage -- “/sandbox”. cats:insert("Sandbox templates") -- Sandbox templates don’t really need documentation. needs_doc = false -- Will behave badly if “/sandbox” occurs twice in title! local sandbox_of = title.fullText:gsub("/sandbox%d*%f[/%z]", "") local diff if page_exists(sandbox_of) then diff = " (" .. compare_pages(title.fullText, sandbox_of, "diff") .. ")" else require("Module:debug").track("documentation/no sandbox of") end links:insert("[[:" .. sandbox_of .. "|sandbox of]]" .. (diff or "")) else -- This is a template that can have a sandbox. local sandbox_title = title.fullText .. "/sandbox" local diff if page_exists(sandbox_title) then diff = " (" .. compare_pages(title.fullText, sandbox_title, "diff") .. ")" end links:insert("[[:" .. sandbox_title .. "|sandbox]]" .. (diff or "")) end end if #links > 0 then output:insert("<dd> ''Useful links'': " .. links:concat(" • ") .. "</dd>") end output:insert("</dl>\n") -- Show error from [[Module:category tree/topic cat/data]] on its submodules' -- documentation to, for instance, warn about duplicate labels. if title.fullText:find("Module:category tree/topic cat/data", 1, true) == 1 then local ok, err = pcall(require, "Module:category tree/topic cat/data") if not ok then output:insert('<span class="error">' .. err .. '</span>\n\n') end end if doc_title.exists then -- Override automatic documentation, if present. doc_content = frame:expandTemplate { title = doc_title.fullText } elseif not doc_content and fallback_docs then doc_content = frame:expandTemplate { title = fallback_docs; args = { ['user'] = user_name; ['page'] = title.fullText; ['skin name'] = skin_name; } } end if doc_content then output:insert(doc_content) end output:insert(('\n<%s style="clear: both;" />'):format(args.hr == "below" and "hr" or "br")) if not cats[1] and not doc_content then if contentModel == "Scribunto" then cats:insert("Uncategorized modules") -- elseif title.nsText == "Template" then -- cats:insert("Uncategorized templates") end end if needs_doc then cats:insert("Templates and modules needing documentation") end for _, cat in ipairs(cats) do output:insert("[[Category:" .. cat .. "]]") end output:insert("</div>\n") return output:concat() end -- Used by {{translit module documentation}}. function export.translitModuleLangList(frame) local pagename, subpage if frame.args[1] then pagename = frame.args[1] else local title = mw.title.getCurrentTitle() subpage = title.subpageText pagename = title.text if subpage ~= pagename then pagename = title.rootText end end local translitModule = pagename local languageObjects = require("Module:languages/byTranslitModule")(translitModule) local codeInPagename = pagename:match("^([%l-]+)%-.*translit$") local categories = Array() local codeInPagenameInList = false if codeInPagename then if languageObjects[1] and subpage ~= "documentation" then local agreement = languageObjects[2] and "s" or "" categories:insert("[[Category:Transliteration modules used by " .. #languageObjects .. " language" .. agreement .. "]]") end languageObjects = Array(languageObjects) :filter( function (lang) local result = lang:getCode() ~= codeInPagename codeInPagenameInList = codeInPagenameInList or result return result end) end if subpage ~= "documentation" then for script_code in pagename:gmatch("%f[^-%z]%u%l%l%l%f[-]") do local script = require "Module:scripts".getByCode(script_code) if script then categories:insert("[[Category:" .. script:getCategoryName() .. "]]") end end end if subpage ~= "documentation" and not page_exists("Module:" .. pagename .. "/testcases") then categories:insert("[[Category:Transliteration modules without a testcases subpage]]") end if not languageObjects[1] then return categories:concat() end local langs = Array(languageObjects) :sort( function(lang1, lang2) return lang1:getCode() < lang2:getCode() end) -- This will not error because languageObjects is not empty. :map(languageObjects[1].makeCategoryLink) :serial_comma_join() return "It is " .. ( codeInPagenameInList and "also" or "" ) .. " used to transliterate " .. langs .. "." .. categories:concat() end return export 336j4iird08ev5f8xj0ywmbvtt1ssdt 828 2975 8287 2022-07-21T19:26:28Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local Array = {} local array_constructor -- Copy table library so as not to unexpectedly change the behavior of code that -- uses it. local array_methods = mw.clone(table) -- Create version of table.sort that returns the table. array_methods.sort = function (t, comp) table.sort(t, comp) return t end -- ipairs and unpack operate on arrays. array_methods.ipairs = ipairs array_methods.unpack = unpack function array_methods:type() local mt = getmetatable(self) return type(mt) == "table" and mt.__type or nil end function array_methods:adjustIndex(index) index = math.floor(index) if index < 0 then index = #self + index + 1 end return index end -- string.sub-style slicing. function array_methods:slice(i, j) if i == nil then i = 1 elseif type(i) == "number" then i = self:adjust_index(i) else error("Expected number, got " .. type(i)) end if j == nil or type(j) == "number" then j = self:adjust_index(j or -1) else error("Expected number, got " .. type(j)) end local new_arr = array_constructor() local k = 0 for index = i, j do k = k + 1 new_arr[k] = self[index] end return new_arr end -- A function to convert string key-table modules such -- as [[Module:languages/data2]] into arrays. -- "from" is a bad name. -- field_for_key supplies the field name in which the -- key will be stored. local function to_array(map, field_for_key) m_table = m_table or require "Module:table" local arr = {} local i = 0 for key, val in pairs(map) do i = i + 1 local new_val = m_table.shallowcopy(val) if field_for_key then new_val[field_for_key] = key end arr[i] = new_val end return array_constructor(arr) end -- Functions from [[Module:table]] that operate on arrays or sparse arrays. -- List copied from [[Module:table/documentation]]. local operate_on_array = { -- non-sparse "removeDuplicates", "length", "contains", "serialCommaJoin", "reverseIpairs", "reverse", "invert", "listToSet", "isArray", -- sparse "numKeys", "maxIndex", "compressSparseArray", "sparseIpairs", -- tables in general "shallowcopy", "deepcopy", } -- Not all of these operate on arrays. local create_new_array = { -- Functions from [[Module:table]] that create an array. -- List copied from [[Module:table/documentation]]. "removeDuplicates", "numKeys", "affixNums", "compressSparseArray", "keysToList", "reverse", -- Functions from [[Module:table]] that create an table. "shallowcopy", "deepcopy", -- Functions from [[Module:fun]] that create an array. "map", "filter", } -- Functions from [[Module:fun]] that take an array in the second argument. -- They just have to have the argument order reversed to work as methods of the -- array object. local second_argument_is_array = { "map", "some", "all", "filter" } -- Add aliases for the functions from [[Module:table]] whose names -- contain "array" or "list", which is redundant, and whose names don't conform -- to the usual camel case. -- The key redirects to the value. local alias_of = { compress = "compressSparseArray", keys = "keysToList", toSet = "listToSet", deepCopy = "deepcopy", shallowCopy = "shallowcopy", } local function get_module_function(key, module, module_name) return module[key] or error("No function named " .. tostring(key) .. " in Module:" .. module_name) end local function wrap_in_array_constructor(func) return function (...) return array_constructor(func(...)) end end local function create_array_generating_func(key, module, module_name) return wrap_in_array_constructor(get_module_function(key, module, module_name)) end local function reverse_arguments(func) return function (a, b) return func(b, a, true) end end local function underscore_to_camel_case(str) if type(str) ~= "string" then return str end str = str:gsub("_(.)", string.upper) return str end local m_table, m_fun local Array = {} Array.__type = "array" function Array:__index(key) if type(key) ~= "string" then return nil end -- Convert underscores to camel case: num_keys -> numKeys. key = underscore_to_camel_case(key) local val = array_methods[key] if val then return val end key = alias_of[key] or key local func m_table = m_table or require "Module:table" if m_table.contains(operate_on_array, key) then if m_table.contains(create_new_array, key) then func = create_array_generating_func(key, m_table, "table") else func = m_table[key] end elseif m_table.contains(second_argument_is_array, key) then m_fun = m_fun or require "Module:fun" local raw_func = reverse_arguments(get_module_function(key, m_fun, "fun")) if m_table.contains(create_new_array, key) then func = wrap_in_array_constructor(raw_func) else func = raw_func end elseif key == "fold" then m_fun = m_fun or require "Module:fun" local raw_func = get_module_function(key, m_fun, "fun") func = function(t, func, accum) return raw_func(func, t, accum) end end if func then array_methods[key] = func return func end end function Array.__add(a, b) if type(a) == 'table' and type(b) == 'table' then m_table = m_table or require "Module:table" local new_arr = array_constructor(m_table.shallowcopy(a)) for _, val in ipairs(b) do new_arr:insert(val) end return new_arr end end function Array:new(...) local arr if select("#", ...) == 1 and type((...)) == "table" then arr = ... local mt = getmetatable(arr) -- If table has been loaded with mw.loadData, copy it to avoid the -- limitations of it being a virtual table. if mt and mt.mw_loadData then m_table = m_table or require "Module:table" arr = m_table.shallowcopy(arr) end else arr = { ... } end return setmetatable(arr, self) end -- Declared as local above. function array_constructor(...) return Array:new(...) end local array_generating_funcs = { from = to_array } local Array_library_mt = { __call = Array.new, __index = array_generating_funcs } setmetatable(Array, Array_library_mt) function Array_library_mt:__index(key) key = underscore_to_camel_case(key) key = alias_of[key] or key if array_generating_funcs[key] then return array_generating_funcs[key] end m_table = m_table or require "Module:table" if m_table.contains(create_new_array, key) then local func = create_array_generating_func(key, m_table, "table") array_generating_funcs[key] = func return func end end return Array 0xqegsnmoi0ytt538j00om4leq9onzn 10 2976 8288 2022-07-22T03:00:08Z Rebel Agent 2678 Ke dirile tempolete wikitext text/x-wiki {{safesubst:<noinclude></noinclude>#invoke:template link|format_link}}<noinclude>{{documentation}}</noinclude> hxjpg9dwvwj7zi4ktw8vqtcsxfwdnh0 828 2977 8289 2022-07-22T03:03:10Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local export = {} local date_and_time = "mw:Help:Magic words#Date and time" local technical_metadata = "mw:Help:Magic words#Technical metadata" local tech_meta_another_page = "mw:Help:Magic words#Technical metadata of another page" local page_names = "mw:Help:Magic words#Page names" local namespaces = "mw:Help:Magic words#Namespaces" local formatting = "mw:Help:Magic words#Formatting" local URL_data = "mw:Help:Magic words#URL data" local localization = "mw:Help:Magic words#Localization" local miscellaneous = "mw:Help:Magic words#Miscellaneous" local parser_functions_link = "mw:Help:Extension:ParserFunctions" local LST = "mw:Extension:Labeled Section Transclusion" local variables_nullary = { ["CURRENTYEAR" ] = date_and_time; ["CURRENTMONTH" ] = date_and_time; ["CURRENTMONTH1" ] = date_and_time; -- undocumented ["CURRENTMONTH2" ] = date_and_time; -- undocumented ["CURRENTMONTHNAME" ] = date_and_time; ["CURRENTMONTHNAMEGEN"] = date_and_time; ["CURRENTMONTHABBREV" ] = date_and_time; ["CURRENTDAY" ] = date_and_time; ["CURRENTDAY2" ] = date_and_time; ["CURRENTDOW" ] = date_and_time; ["CURRENTDAYNAME" ] = date_and_time; ["CURRENTTIME" ] = date_and_time; ["CURRENTHOUR" ] = date_and_time; ["CURRENTWEEK" ] = date_and_time; ["CURRENTTIMESTAMP" ] = date_and_time; ["LOCALYEAR" ] = date_and_time; ["LOCALMONTH" ] = date_and_time; ["LOCALMONTH1" ] = date_and_time; -- undocumented ["LOCALMONTH2" ] = date_and_time; -- undocumented ["LOCALMONTHNAME" ] = date_and_time; ["LOCALMONTHNAMEGEN" ] = date_and_time; ["LOCALMONTHABBREV" ] = date_and_time; ["LOCALDAY" ] = date_and_time; ["LOCALDAY2" ] = date_and_time; ["LOCALDOW" ] = date_and_time; ["LOCALDAYNAME" ] = date_and_time; ["LOCALTIME" ] = date_and_time; ["LOCALHOUR" ] = date_and_time; ["LOCALWEEK" ] = date_and_time; ["LOCALTIMESTAMP" ] = date_and_time; ["SITENAME" ] = technical_metadata; ["SERVER" ] = technical_metadata; ["SERVERNAME" ] = technical_metadata; ["DIRMARK" ] = technical_metadata; ["DIRECTIONMARK" ] = technical_metadata; ["ARTICLEPATH" ] = technical_metadata; -- undocumented ["SCRIPTPATH" ] = technical_metadata; ["STYLEPATH" ] = technical_metadata; ["CURRENTVERSION" ] = technical_metadata; ["CONTENTLANGUAGE" ] = technical_metadata; ["CONTENTLANG" ] = technical_metadata; ["PAGEID" ] = technical_metadata; ["CASCADINGSOURCES" ] = technical_metadata; ["REVISIONID" ] = technical_metadata; ["REVISIONDAY" ] = technical_metadata; ["REVISIONDAY2" ] = technical_metadata; ["REVISIONMONTH" ] = technical_metadata; ["REVISIONMONTH1" ] = technical_metadata; ["REVISIONYEAR" ] = technical_metadata; ["REVISIONTIMESTAMP" ] = technical_metadata; ["REVISIONUSER" ] = technical_metadata; ["REVISIONSIZE" ] = technical_metadata; ["NUMBEROFPAGES" ] = technical_metadata; ["NUMBEROFARTICLES" ] = technical_metadata; ["NUMBEROFFILES" ] = technical_metadata; ["NUMBEROFEDITS" ] = technical_metadata; ["NUMBEROFVIEWS" ] = technical_metadata; ["NUMBEROFUSERS" ] = technical_metadata; ["NUMBEROFADMINS" ] = technical_metadata; ["NUMBEROFACTIVEUSERS"] = technical_metadata; ["FULLPAGENAME" ] = page_names; ["PAGENAME" ] = page_names; ["BASEPAGENAME" ] = page_names; ["SUBPAGENAME" ] = page_names; ["SUBJECTPAGENAME" ] = page_names; ["ARTICLEPAGENAME" ] = page_names; ["TALKPAGENAME" ] = page_names; ["ROOTPAGENAME" ] = page_names; -- undocumented ["FULLPAGENAMEE" ] = page_names; ["PAGENAMEE" ] = page_names; ["BASEPAGENAMEE" ] = page_names; ["SUBPAGENAMEE" ] = page_names; ["SUBJECTPAGENAMEE" ] = page_names; ["ARTICLEPAGENAMEE" ] = page_names; ["TALKPAGENAMEE" ] = page_names; ["ROOTPAGENAMEE" ] = page_names; -- undocumented ["NAMESPACE" ] = namespaces; ["NAMESPACENUMBER" ] = namespaces; ["SUBJECTSPACE" ] = namespaces; ["ARTICLESPACE" ] = namespaces; ["TALKSPACE" ] = namespaces; ["NAMESPACEE" ] = namespaces; ["SUBJECTSPACEE" ] = namespaces; ["TALKSPACEE" ] = namespaces; ["!" ] = "mw:Help:Magic words#Other"; } local variables_nonnullary = { ["PROTECTIONLEVEL" ] = technical_metadata; ["DISPLAYTITLE" ] = technical_metadata; ["DEFAULTSORT" ] = technical_metadata; ["PAGESINCATEGORY" ] = technical_metadata; ["PAGESINCAT" ] = technical_metadata; ["NUMBERINGROUP" ] = technical_metadata; ["PAGESINNS" ] = technical_metadata; ["PAGESINNAMESPACE" ] = technical_metadata; ["FULLPAGENAME" ] = page_names; ["PAGENAME" ] = page_names; ["BASEPAGENAME" ] = page_names; ["SUBPAGENAME" ] = page_names; ["SUBJECTPAGENAME" ] = page_names; ["ARTICLEPAGENAME" ] = page_names; ["TALKPAGENAME" ] = page_names; ["ROOTPAGENAME" ] = page_names; -- undocumented ["FULLPAGENAMEE" ] = page_names; ["PAGENAMEE" ] = page_names; ["BASEPAGENAMEE" ] = page_names; ["SUBPAGENAMEE" ] = page_names; ["SUBJECTPAGENAMEE" ] = page_names; ["ARTICLEPAGENAMEE" ] = page_names; ["TALKPAGENAMEE" ] = page_names; ["ROOTPAGENAMEE" ] = page_names; -- undocumented ["NAMESPACE" ] = namespaces; ["NAMESPACENUMBER" ] = namespaces; ["SUBJECTSPACE" ] = namespaces; ["ARTICLESPACE" ] = namespaces; ["TALKSPACE" ] = namespaces; ["NAMESPACEE" ] = namespaces; ["SUBJECTSPACEE" ] = namespaces; ["TALKSPACEE" ] = namespaces; ["PAGEID" ] = tech_meta_another_page; ["PAGESIZE" ] = tech_meta_another_page; ["PROTECTIONLEVEL" ] = tech_meta_another_page; ["CASCADINGSOURCES" ] = tech_meta_another_page; ["REVISIONID" ] = tech_meta_another_page; ["REVISIONDAY" ] = tech_meta_another_page; ["REVISIONDAY2" ] = tech_meta_another_page; ["REVISIONMONTH" ] = tech_meta_another_page; ["REVISIONMONTH1" ] = tech_meta_another_page; ["REVISIONYEAR" ] = tech_meta_another_page; ["REVISIONTIMESTAMP" ] = tech_meta_another_page; ["REVISIONUSER" ] = tech_meta_another_page; } local parser_functions = { -- built-ins ["localurl" ] = URL_data; ["localurle" ] = URL_data; ["fullurl" ] = URL_data; ["fullurle" ] = URL_data; ["canonicalurl" ] = URL_data; ["canonicalurle"] = URL_data; ["filepath" ] = URL_data; ["urlencode" ] = URL_data; ["urldecode" ] = URL_data; ["anchorencode" ] = URL_data; ["ns" ] = namespaces; ["nse" ] = namespaces; ["formatnum" ] = formatting; ["#dateformat" ] = formatting; ["#formatdate" ] = formatting; ["lc" ] = formatting; ["lcfirst" ] = formatting; ["uc" ] = formatting; ["ucfirst" ] = formatting; ["padleft" ] = formatting; ["padright" ] = formatting; ["plural" ] = localization; ["grammar" ] = localization; ["gender" ] = localization; ["int" ] = localization; ["#language" ] = miscellaneous; ["#special" ] = miscellaneous; ["#speciale" ] = miscellaneous; ["#tag" ] = miscellaneous; -- [[mw:Extension:ParserFunctions]] ["#expr" ] = parser_functions_link .. "##expr"; ["#if" ] = parser_functions_link .. "##if"; ["#ifeq" ] = parser_functions_link .. "##ifeq"; ["#iferror" ] = parser_functions_link .. "##iferror"; ["#ifexpr" ] = parser_functions_link .. "##ifexpr"; ["#ifexist" ] = parser_functions_link .. "##ifexist"; ["#rel2abs" ] = parser_functions_link .. "##rel2abs"; ["#switch" ] = parser_functions_link .. "##switch"; ["#time" ] = parser_functions_link .. "##time"; ["#timel" ] = parser_functions_link .. "##timel"; ["#titleparts" ] = parser_functions_link .. "##titleparts"; -- other extensions ["#invoke" ] = "mw:Extension:Scribunto"; ["#babel" ] = "mw:Extension:Babel"; ["#categorytree" ] = "mw:Extension:CategoryTree#The {{#categorytree}} parser function"; ["#lst" ] = LST; ["#lstx" ] = LST; ["#lsth" ] = LST; -- not available, it seems ["#lqtpagelimit" ] = "mw:Extension:LiquidThreads"; ["#useliquidthreads"] = "mw:Extension:LiquidThreads"; ["#target" ] = "mw:Extension:MassMessage"; -- not documented yet } -- rudimentary local function is_valid_pagename(pagename) if (pagename == "") or pagename:match("[%[%]%|%{%}#\127<>]") then return false end return true end local function hook_special(page) if is_valid_pagename(page) then return "[[Special:" .. page .. "|" .. page .. "]]" else return page end end local parser_function_hooks = { ["#special" ] = hook_special; ["#speciale"] = hook_special; ["int"] = function (mesg) if is_valid_pagename(mesg) then return ("[[:MediaWiki:" .. mesg .. "|" .. mesg .. "]]") else return mesg end end; ["#categorytree"] = function (cat) if is_valid_pagename(cat) and not (mw.title.getCurrentTitle().fullText == ("Category:" .. cat)) then return ("[[:Category:" .. cat .. "|" .. cat .. "]]") else return cat end end; ["#invoke"] = function (mod) if is_valid_pagename(mod) and not (mw.title.getCurrentTitle().fullText == ("Module:" .. mod)) then return ("[[Module:%s|%s]]"):format(mod, mod) else return mod end end; ["#tag"] = function (tag) local doc_table = require('Module:wikitag link').doc_table if doc_table[tag] then return ("[[%s|%s]]"):format(doc_table[tag], tag) else return tag end end; } function export.format_link(frame) if mw.isSubsting() then return require('Module:unsubst').unsubst_template("format_link") end local args = (frame.getParent and frame:getParent().args) or frame -- Allows function to be called from other modules. local output = { (frame.args and frame.args.nested) and "&#123;&#123;" or "<code>&#123;&#123;" } local templ = (frame.args and frame.args.annotate) or args[1] local noargs = (frame.args and not frame.args.annotate) and next(args) == nil if not templ then if mw.title.getCurrentTitle().fullText == frame:getParent():getTitle() then -- demo mode return "<code>{{<var>{{{1}}}</var>|<var>{{{2}}}</var>|...}}</code>" else error("The template name must be given.") end end local function render_title(templ) local marker, rest marker, rest = templ:match("^([Ss][Uu][Bb][Ss][Tt]):(.*)") if not marker then marker, rest = templ:match("^([Ss][Aa][Ff][Ee][Ss][Uu][Bb][Ss][Tt]):(.*)") end if marker then templ = rest table.insert(output, ("[[mw:Manual:Substitution|%s]]:"):format(marker)) end if noargs and variables_nullary[templ] then table.insert(output, ("[[%s|%s]]"):format(variables_nullary[templ], templ)) return end marker, rest = templ:match("^([Mm][Ss][Gg][Nn][Ww]):(.*)") if marker then templ = rest -- not the most accurate documentation ever table.insert(output, ("[[m:Help:Magic words#Template modifiers|%s]]:"):format(marker)) else marker, rest = templ:match("^([Mm][Ss][Gg]):(.*)") if marker then templ = rest table.insert(output, ("[[m:Help:Magic words#Template modifiers|%s]]:"):format(marker)) -- ditto end end marker, rest = templ:match("^([Rr][Aa][Ww]):(.*)") if marker then table.insert(output, ("[[m:Help:Magic words#Template modifiers|%s]]:"):format(marker)) -- missingno. templ = rest end if templ:match("^%s*/") then table.insert(output, ("[[%s]]"):format(templ)) return end marker, rest = templ:match("^(.-):(.*)") if marker then local lcmarker = marker:lower() if parser_functions[lcmarker] then if parser_function_hooks[lcmarker] then rest = parser_function_hooks[lcmarker](rest) end table.insert(output, ("[[%s|%s]]:%s"):format(mw.uri.encode(parser_functions[lcmarker], "WIKI"), marker, rest)) return elseif variables_nonnullary[marker] then table.insert(output, ("[[%s|%s]]:%s"):format(variables_nonnullary[marker], marker, rest)) return end end if not is_valid_pagename(templ) then table.insert(output, templ) return end if marker then if mw.site.namespaces[marker] then if (title == "") or (mw.title.getCurrentTitle().fullText == templ) then -- ?? no such variable "title" table.insert(output, templ) elseif marker == "" and templ:find("^:") then -- for cases such as {{temp|:entry}}; MediaWiki displays [[:entry]] without a colon, like [[entry]], but colon should be shown table.insert(output, ("[[%s|%s]]"):format(templ, templ)) else table.insert(output, ("[[:%s|%s]]"):format(templ, templ)) end return elseif mw.site.interwikiMap()[marker:lower()] then -- XXX: not sure what to do now… table.insert(output, ("[[:%s:|%s]]:%s"):format(marker, marker, rest)) return end end if (templ == "") or (mw.title.getCurrentTitle().fullText == ("Template:" .. templ)) then table.insert(output, templ) else table.insert(output, ("[[Template:%s|%s]]"):format(templ, templ)) end end render_title(templ) local i = (frame.args and frame.args.annotate) and 1 or 2 while args[i] do table.insert(output, "&#124;" .. args[i]) i = i + 1 end for key, value in require("Module:table").sortedPairs(args) do if type(key) == "string" then table.insert(output, "&#124;" .. key .. "=" .. value) end end table.insert(output, (frame.args and frame.args.nested) and "&#125;&#125;" or "&#125;&#125;</code>") return table.concat(output) end return export cy6xa1x3igx8v32yt0p1sxatf4d38ex 10 2978 8290 2022-07-22T08:45:00Z Rebel Agent 2678 Ke dirile template wikitext text/x-wiki {{#invoke:links/templates|l_term_t<noinclude>|demo=term</noinclude>}}<!-- -->{{#ifeq:{{PAGENAME}}|RecentChanges||<!-- -->{{#ifeq:{{{1|}}}|und|[[Category:Undetermined language links]]}}<!-- -->}}<!-- -->{{redlink category|{{{1|}}}|{{{2|}}}|template=l}}<!-- --><noinclude>{{documentation}}</noinclude> 99mqntzbd62dvi0u0aty63zyqj6joo9 828 2979 8291 2022-07-22T08:47:32Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local export = {} --[=[ Modules used: [[Module:links]] [[Module:languages]] [[Module:scripts]] [[Module:parameters]] [[Module:debug]] ]=] -- Used in [[Template:l]] and [[Template:m]]. function export.l_term_t(frame) local face = frame.args["face"] local allowSelfLink = frame.args["notself"]; allowSelfLink = not allowSelfLink or allowSelfLink == "" local params = { [1] = {required = true}, [2] = {}, [3] = {}, [4] = {alias_of = "gloss"}, ["accel-form"] = {}, ["accel-translit"] = {}, ["accel-lemma"] = {}, ["accel-lemma-translit"] = {}, ["accel-gender"] = {}, ["accel-nostore"] = {type = "boolean"}, ["g"] = {list = true}, ["gloss"] = {}, ["id"] = {}, ["lit"] = {}, ["pos"] = {}, ["t"] = {alias_of = "gloss"}, ["tr"] = {}, ["ts"] = {}, ["sc"] = {}, } -- Compatibility mode for {{term}}. -- If given a nonempty value, the function uses lang= to specify the -- language, and all the positional parameters shift one number lower. local compat = (frame.args["compat"] or "") ~= "" if compat then params["lang"] = {}, table.remove(params, 1) end local args = require("Module:parameters").process(frame:getParent().args, params) local lang = args[compat and "lang" or 1] -- Tracking for missing language or und if not lang then require("Module:debug").track("link/no lang") elseif lang == "und" then require("Module:debug").track("link/und") end lang = lang or "und" local sc = args["sc"] local term = args[(compat and 1 or 2)] local alt = args[(compat and 2 or 3)] -- Check parameters lang = require("Module:languages").getByCode(lang, 1, "allow etym") lang = require("Module:languages").getNonEtymological(lang) if sc then sc = require("Module:scripts").getByCode(sc, "sc") end if not term and not alt and frame.args["demo"] then term = frame.args["demo"] end -- Forward the information to full_link return require("Module:links").full_link( { lang = lang, sc = sc, term = term, alt = alt, id = args["id"], tr = args["tr"], ts = args["ts"], genders = args["g"], gloss = args["gloss"], pos = args["pos"], lit = args["lit"], accel = args["accel-form"] and { form = args["accel-form"], translit = args["accel-translit"], lemma = args["accel-lemma"], lemma_translit = args["accel-lemma-translit"], gender = args["accel-gender"], nostore = args["accel-nostore"], } or nil, }, face, allowSelfLink ) end -- Used in [[Template:ll]]. function export.ll(frame) local params = { [1] = { required = true }, [2] = { allow_empty = true }, [3] = {}, ["notself"] = { type = "boolean", default = false }, ["id"] = {}, } local args = require("Module:parameters").process(frame:getParent().args, params) local allowSelfLink = not args["notself"] local lang = args[1] lang = require("Module:languages").getByCode(lang, 1, "allow etym") lang = require("Module:languages").getNonEtymological(lang) local text = args[2] local alt = args[3] if text == "" then return alt or "" end local id = args["id"] return require("Module:links").language_link( { term = text, alt = alt, lang = lang, id = id }, allowSelfLink ) end function export.def_t(frame) local params = { [1] = {required = true, default = ""}, } local args = require("Module:parameters").process(frame:getParent().args, params) return require("Module:links").english_links(args[1]) end function export.linkify_t(frame) local params = { [1] = {required = true, default = ""}, } local args = require("Module:parameters").process(frame:getParent().args, params) args[1] = mw.text.trim(args[1]) if args[1] == "" or args[1]:find("[[", nil, true) then return args[1] else return "[[" .. args[1] .. "]]" end end function export.section_link_t(frame) local params = { [1] = {}, } local args = require("Module:parameters").process(frame:getParent().args, params) return require("Module:links").section_link(args[1]) end function export.language_name_link_t(frame) local face = frame.args["face"] local allowSelfLink = frame.args["notself"]; allowSelfLink = not allowSelfLink or allowSelfLink == "" local params = { [1] = {required = true}, [2] = {}, [3] = {}, [4] = {alias_of = "gloss"}, ["g"] = {list = true}, ["gloss"] = {}, ["id"] = {}, ["lit"] = {}, ["pos"] = {}, ["t"] = {alias_of = "gloss"}, ["tr"] = {}, ["ts"] = {}, ["sc"] = {}, ["w"] = { type = "boolean", default = false }, } -- Compatibility mode for {{term}}. -- If given a nonempty value, the function uses lang= to specify the -- language, and all the positional parameters shift one number lower. local compat = (frame.args["compat"] or "") ~= "" if compat then params["lang"] = {}, table.remove(params, 1) end local args = require("Module:parameters").process(frame:getParent().args, params) local lang = args[compat and "lang" or 1] -- Tracking for missing language or und if not lang then require("Module:debug").track("link/no lang") elseif lang == "und" then require("Module:debug").track("link/und") end lang = lang or "und" local sc = args["sc"] local term = args[(compat and 1 or 2)] local alt = args[(compat and 2 or 3)] -- Check parameters lang = require("Module:languages").getByCode(lang, 1, "allow etym") local non_etym_lang = require("Module:languages").getNonEtymological(lang) if sc then sc = require("Module:scripts").getByCode(sc, "sc") end if not term and not alt and frame.args["demo"] then term = frame.args["demo"] end --[[ Add a language name, linked to Wikipedia if the Wikipedia parameter is set to true. Forward the information to full_link. ]] local language_name = args.w and lang:makeWikipediaLink() or lang:getCanonicalName() if term == "-" then return language_name else return language_name .. " " .. require("Module:links").full_link( { lang = non_etym_lang, sc = sc, term = term, alt = alt, id = args["id"], tr = args["tr"], ts = args["ts"], genders = args["g"], gloss = args["gloss"], pos = args["pos"], lit = args["lit"] }, face, allowSelfLink ) end end return export c74idvbcjv5qumy4nemez9113m0f9co 828 2980 8292 2022-07-22T08:51:17Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local export = {} local escape do local escapes = { ["\a"] = "a", ["\b"] = "b", ["\f"] = "f", ["\n"] = "n", ["\r"] = "r", ["\t"] = "t", ["\v"] = "v", ["\\"] = "\\", ["\""] = '"', ["'"] = "'", } local function helper(char) return escapes[char] and "\\" .. escapes[char] or ("\\%03d"):format(char:byte()) end -- Escape control characters, backslash, double quote, and bytes that aren't -- used in UTF-8. -- Escape stuff that can't be saved in a MediaWiki page, like invalid UTF-8 -- and NFD character sequences? Hard. -- Similar to string.format("%q", str), which does not use C-like simple -- escapes and does not escape bytes that are not used in UTF-8. escape = function (str) return (str:gsub("[%z\1-\31\\\"\127\192\193\245-\255]", helper)) end end export.escape = escape -- Convert a value to a string function export.dump(value, prefix, tsort) local t = type(value) prefix = prefix or "" if t == "string" then return '"' .. escape(value) .. '"' elseif t == "table" then local str_table = {} table.insert(str_table, " {") for key, val in require("Module:table").sortedPairs(value, tsort) do table.insert(str_table, " " .. prefix .. "\t[" .. export.dump(key, prefix .. "\t") .. "] = " .. export.dump(val, prefix .. "\t"):gsub("^ ", "") .. ",") end table.insert(str_table, " " .. prefix .. "}") return table.concat(str_table, "\n") else return tostring(value) end end function export.highlight_dump(value, prefix, tsort, options) options = options or {} local func = options.modified and "modified_dump" or "dump" local dump = export[func](value, prefix, tsort) -- Remove spaces at beginnings of lines (which are simply to force a <pre></pre> tag). dump = dump:gsub("%f[^%z\n] ", "") return export.highlight(dump) end -- Returns true if table contains a table as one of its values local function containsTable(t) for key, value in pairs(t) do if type(value) == "table" then return true end end return false end local function containsTablesWithSize(t, size) for key, value in pairs(t) do if type(value) == "table" and require("Module:table").size(value) ~= size then return false end end return true end --[=[ Convert a value to a string. Like dump below, but if a table has consecutive numbered keys and does not have a table as one of its values, it will be placed on a single line. Used by [[Module:User:Erutuon/script recognition]]. ]=] function export.modified_dump(value, prefix, tsort) local t = type(value) prefix = prefix or "" if t == "string" then return '"' .. value .. '"' elseif t == "table" then local str_table = {} local containsTable = containsTable(value) local consecutive = require("Module:table").isArray(value) if consecutive and not containsTable or containsTable and containsTablesWithSize(value, 3) then table.insert(str_table, "{") for key, val in require("Module:table").sortedPairs(value, tsort) do if containsTable then table.insert(str_table, "\n\t" .. prefix) else table.insert(str_table, " ") end if type(key) == "string" then table.insert(str_table, "[" .. export.modified_dump(key) .. "] = ") end table.insert(str_table, type(key) == "number" and type(val) == "number" and string.format("0x%05X", val) or export.modified_dump(val)) if not (consecutive and #value == 3) or type(key) == "number" and value[key + 1] then table.insert(str_table, ",") end end if containsTable then table.insert(str_table, "\n" .. prefix) else table.insert(str_table, " ") end table.insert(str_table, "}") return table.concat(str_table) end table.insert(str_table, " {") for key, val in require("Module:table").sortedPairs(value, tsort) do table.insert(str_table, " " .. prefix .. "\t[" .. export.modified_dump(key, prefix .. "\t") .. "] = " .. export.modified_dump(val, prefix .. "\t"):gsub("^ ", "") .. ",") end table.insert(str_table, " " .. prefix .. "}") return table.concat(str_table, "\n") elseif t == "number" and value > 46 then return string.format("0x%05X", value) else return tostring(value) end end export.track = require("Module:debug/track") -- Trigger a script error from a template function export.error(frame) error(frame.args[1] or "(no message specified)") end --[[ Convenience function for generating syntaxhighlight tags. Display defaults to block. Options is a table. To display inline text with HTML highlighting: { inline = true, lang = "html" } ]] function export.highlight(content, options) if type(content) == "table" then options = content options = { lang = options.lang or "lua", inline = options.inline and true } return function(content) return mw.getCurrentFrame():extensionTag{ name = "syntaxhighlight", content = content, args = options } end else return mw.getCurrentFrame():extensionTag{ name = "syntaxhighlight", content = content, args = { lang = options and options.lang or "lua", inline = options and options.inline and true or nil } } end end function export.track_unrecognized_args(args, template_name) local function track(code) export.track(template_name .. "/" .. code) end track("unrecognized arg") local arg_list = {} for arg, value in pairs(args) do track("unrecognized arg/" .. arg) table.insert(arg_list, ("|%s=%s"):format(arg, value)) end mw.log( ("Unrecognized parameter%s in {{%s}}: %s."):format( arg_list[2] and "s" or "", template_name, table.concat(arg_list, ", "))) end return export lh9pml9xbqqss9zincq7y36za820tt6 828 2981 8293 2022-07-22T08:53:19Z Rebel Agent 2678 Ke dirile module Scribunto text/plain return function (key) local frame = mw.getCurrentFrame() if key then if type(key) ~= "table" then key = { key } end for i, value in pairs(key) do pcall(frame.expandTemplate, frame, { title = 'tracking/' .. value }) end else error('No tracking key supplied to the function "' .. track .. '".') end end 332d44anbo5v9lwub0vhfkjrof53szz 828 2982 8294 2022-07-22T08:56:33Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local labels = {} local aliases = {} local CE = '<small class="ce-date2">CE</small>' local BCE = '<small class="ce-date2">BCE</small>' -- A labels["AAVE"] = { link = "African American Vernacular English", display = "AAVE" } aliases["African American Vernacular English"] = "AAVE" aliases["African American Vernacular"] = "AAVE" aliases["African-American Vernacular English"] = "AAVE" aliases["African-American Vernacular"] = "AAVE" labels["æ-tensing"] = { link = "æ-tensing", type = "sound change" } aliases["ae-tensing"] = "æ-tensing" labels["afb"] = { link = "Gulf Arabic", display = "Gulf Arabic" } aliases["Gulf"] = "afb" aliases["Khaleeji"] = "afb" aliases["Gulfie"] = "afb" labels["Ala-Laukaa"] = { link = "Ingrian phonology#Ala-Laukaa dialect", display = "Ala-Laukaa" } labels["Anglicised"] = { link = "Anglicisation#Anglicisation of non-English-language vocabulary and names", display = "Anglicised" } aliases["Anglicized"] = "Anglicised" labels["Aran"] = { link = "Aran Islands", display = "Aran" } labels["ar-Cairene"] = { link = "Egyptian Arabic", display = "Cairene" } aliases["Cairene"] = "ar-Cairene" labels["Arvanite"] = { link = "Arvanitika", display = "Arvanite" } labels["Ashkenazi Hebrew"] = { link = "Ashkenazi Hebrew", display = "Ashkenazi Hebrew" } aliases["Ashkenazi"] = "Ashkenazi Hebrew" labels["Australia"] = { link = "Australian English phonology", display = "General Australian" } aliases["AU"] = "Australia" aliases["AuE"] = "Australia" aliases["Aus"] = "Australia" aliases["AusE"] = "Australia" aliases["GenAus"] = "Australia" aliases["General Australian"] = "Australia" -- B labels["Balearic Catalan"] = { link = "Balearic dialect", display = "Balearic", } aliases["Balearic"] = "Balearic Catalan" labels["Batangas"] = { link = "Batangas Tagalog", display = "Batangas" } aliases["Batangas Tagalog"] = "Batangas" aliases["Batangueño"] = "Batangas" labels["BE-nl"] = { link = "Belgian Dutch", display = "Belgium" } aliases["BE"] = "BE-nl" labels["Beijing"] = { link = "Beijing dialect", display = "Beijing" } labels["Bohol"] = { link = "Boholano dialect", display = "Bohol" } aliases["Binol-anon"] = "Bohol" aliases["Boholano"] = "Bohol" aliases["Bohol Island"] = "Bohol" aliases["Bohol Province"] = "Bohol" labels["Bosnia"] = { link = "Comparison of standard Bosnian, Croatian, Montenegrin and Serbian#Accentuation", display = "Bosnia" } aliases["Bosnian"] = "Bosnia" labels["Boston"] = { link = "Boston English", display = "Boston" } aliases["Bos"] = "Boston" labels["Brazil"] = { link = "Brazilian Portuguese", display = "Brazil" } aliases["BP"] = "Brazil" aliases["BR"] = "Brazil" aliases["Brazilian Portuguese"] = "Brazil" labels["Burträsk"] = { link = "Burträsk", } labels["Bygdeå"] = { link = "Bygdeå", } -- C labels["Canada"] = { link = "Canadian English", display = "Canada" } aliases["CA"] = "Canada" aliases["Canadian"] = "Canada" labels["Canadian Shift"] = { link = "Canadian Shift", display = "Canadian Vowel Shift", type = "sound change" } aliases["Canadian shift"] = "Canadian Shift" aliases["Canadian Vowel Shift"] = "Canadian Shift" aliases["Canadian vowel shift"] = "Canadian Shift" labels["Rio de Janeiro"] = { link = "Carioca#Sociolect", display = "Rio de Janeiro" } aliases["RJ"] = "Rio de Janeiro" aliases["Carioca"] = "Rio de Janeiro" labels["Castilian"] = { link = "Castilian Spanish", display = "Castilian" } aliases["Spain"] = "Castilian" labels["Central Catalan"] = { link = "Central Catalan", display = "Central", } labels["central Germany"] = { display = "central Germany" } aliases["central German"] = "central Germany" aliases["Central German"] = "central Germany" aliases["Central Germany"] = "central Germany" labels["central Italy"] = { link = "Central Italian", display = "central Italy" } aliases["central Italian"] = "central Italy" aliases["Central Italian"] = "central Italy" aliases["Central Italy"] = "central Italy" labels["Central Scotland"] = { link = "Central Scots", display = "Central Scotland" } labels["Central Sweden"] = { link = "Central Swedish", display = "Central Sweden" } aliases["Central Swedish"] = "Central Sweden" labels["ceceo"] = { link = "ceceo", display = "''ceceo'' merger", type = "sound change" } labels["Clay"] = { link = "Clay Frisian", display = "Clay", } labels["Classical"] = { link = "Classical Latin", display = "Classical" } labels["Classical Persian"] = { link = "Persian_language#Classical_Persian", display = "Classical Persian" } labels["Classical Sanskrit"] = { link = "Sanskrit#Classical Sanskrit", display = "Classical" } labels["Cois Fharraige"] = { link = "Gaeltacht Cois Fharraige", display = "Cois Fharraige" } aliases["CF"] = "Cois Fharraige" labels["Connacht"] = { link = "Connacht Irish", display = "Connacht" } labels["Connemara"] = { link = "Connemara", display = "Connemara" } aliases["Conamara"] = "Connemara" labels["Cork"] = { link = "Gaeltacht#Cork Gaeltacht", display = "Cork" } aliases["West Cork"] = "Cork" aliases["West Muskerry"] = "Cork" labels["cot-caught"] = { link = "Cot–caught merger", display = "''cot''–''caught'' merger", type = "sound change" } aliases["caught-cot"] = "cot-caught" labels["Croatia"] = { link = "Comparison of standard Bosnian, Croatian, Montenegrin and Serbian#Accentuation", display = "Croatia" } aliases["Croatian"] = "Croatia" labels["cure-force"] = { link = "Cure–force merger", display = "''cure''–''force'' merger", type = "sound change" } aliases["pour-poor"] = "cure-force" labels["cure-nurse"] = { link = "Cure-nurse merger", display = "''cure''–''nurse'' merger", type = "sound change" } aliases["cure-fir"] = "cure-nurse" labels["cy-N"] = { link = "Welsh language#Dialects", display = "North Wales" } aliases["cy-g"] = "cy-N" aliases["North Wales"] = "cy-N" labels["cy-S"] = { link = "Welsh language#Dialects", display = "South Wales" } aliases["cy-h"] = "cy-S" aliases["South Wales"] = "cy-S" -- D labels["Dhakaiya"] = { link = "Dhakaiya Urdu", display = "Dhakaiya" } aliases["Khoshbas"] = "Dhakaiya" aliases["Sobbasi"] = "Dhakaiya" labels["Dari"] = { link = "Dari Persian", display = "Dari" } aliases["Dari Persian"] = "Dari" labels["Deccani"] = { link = "Deccani language", display = "Deccani" } aliases["Hyderabadi"] = "Deccani" aliases["Telangana"] = "Deccani" aliases["Dakhni"] = "Deccani" aliases["Dakhini"] = "Deccani" labels["Delhi"] = { display = "Delhi Hindi" } labels["Delhi"] = { display = "Delhi Hindi" } labels["distinción"] = { link = "distinción", display = "''z''-''s'' distinction", type = "sound change" } aliases["distincion"] = "distinción" labels["DE"] = { link = "Dublin English", display = "Dublin English" } aliases["Dublin English"] = "DE" labels["Doabi"] = { link = "Doabi dialect", display = "Doabi" } -- E labels["Ecclesiastical"] = { link = "Ecclesiastical Latin", display = "Ecclesiastical" } labels["Egyptological"] = { link = "Egyptian language#Egyptological pronunciation", display = "modern Egyptological" } aliases["modern Egyptological"] = "Egyptological" labels["Estuary English"] = { link = "Estuary English" } -- F labels["father-bother"] = { link = "Father–bother merger", display = "''father''-''bother'' merger", type = "sound change" } labels["Finland"] = { link = "Finland Swedish#Phonology", display = "Finland" } aliases["Finland Swedish"] = "Finland" aliases["Fenno-Swedish"] = "Finland" labels["FS"] = { link = "Standard French", display = "FS" } labels["FV"] = { link = "French Flemish", display = "French Flanders" } -- G labels["Galway"] = { link = "Gaeltacht#Galway Gaeltacht", display = "Galway" } labels["GenAm"] = { link = "General American" } aliases["GA"] = "GenAm" aliases["General American"] = "GenAm" labels["General Cebuano"] = { link = "Cebuano language#Dialects", display = "General Cebuano" } aliases["Carcar-Dalaguete"] = "General Cebuano" aliases["GCeb"] = "General Cebuano" aliases["Sialo"] = "General Cebuano" aliases["Standard Cebuano"] = "General Cebuano" labels["Geordie"] = { link = "Geordie" } labels["Ghawa"] = { display = "[[Ghawa syndrome]]" } labels["Gheg"] = { link = "Gheg Albanian", display = "Gheg" } labels["Givi"] = { link = "Giv, South Khorasan", display = "Givi" } labels["Glenties"] = { link = "Glenties", display = "The Glenties" } labels["grc-byz1"] = { link = "Medieval Greek", display = '10^th ' .. CE .. ' Byzantine' } labels["grc-byz2"] = { link = "Medieval Greek", display = '15^th ' .. CE .. ' Constantinopolitan' } labels["grc-cla"] = { link = "Ancient Greek phonology", display = '5^th ' .. BCE .. ' Attic' } labels["grc-koi1"] = { link = "Koine Greek phonology", display = '1^st ' .. CE .. ' Egyptian' } labels["grc-koi2"] = { link = "Koine Greek phonology", display = '4^th ' .. CE .. ' Koine' } labels["Gwenedeg"] = { link = "Gwenedeg", display = "Gwened" } -- H labels["hbo"] = { link = "Biblical Hebrew#Phonology", display = "Biblical Hebrew" } aliases["Biblical Hebrew"] = "hbo" labels["Hevaha"] = { link = "Ingrian language#Dialects", display = "Hevaha" } labels["Hong Kong"] = { link = "Hong Kong English", display = "Hong Kong" } aliases["HK"] = "Hong Kong" labels["horse-hoarse"] = { link = "horse–hoarse merger", display = "without the ''horse''–''hoarse'' merger", type = "sound change" } labels["Hössjö"] = { link = "sv:Hössjö", } labels["Hure"] = { link = "Hure Banner", } labels["hy-E"] = { link = "Eastern Armenian", display = "Eastern Armenian, standard" } labels["hy-IR"] = { link = "Armenian Iranians#Culture and language", display = "Eastern Armenian, Iran" } labels["hy-W"] = { link = "Western Armenian", display = "Western Armenian, standard" } labels["hy-Y"] = { link = "Yerevan dialect", display = "Eastern Armenian, Yerevan" } -- I labels["IL"] = { link = "Modern Hebrew phonology", display = "Modern Israeli Hebrew" } aliases["Israeli Hebrew"] = "IL" aliases["Modern Hebrew"] = "IL" aliases["Modern Israeli"] = "IL" aliases["Modern Israeli Hebrew"] = "IL" aliases["Modern/Israeli Hebrew"] = "IL" labels["InE"] = { link = "Indian English", display = "Indian English" } labels["Inland North"] = { link = "Inland Northern American English", display = "Inland Northern American" } aliases["US Inland North"] = "Inland North" aliases["Inland Northern"] = "Inland North" aliases["Inland Northern American"] = "Inland North" aliases["Inland Northern English"] = "Inland North" aliases["Inland Northern American English"] = "Inland North" aliases["Great Lakes"] = "Inland North" aliases["Northern Cities Vowel Shift"] = "Inland North" aliases["northern cities vowel shift"] = "Inland North" labels["intrusive r"] = { link = "Intrusive r", display = "intrusive r", type = "sound change" } labels["Iranian Persian"] = { link = "Western Persian", display = "Iranian Persian" } aliases["IR"] = "Iranian Persian" aliases["Western Persian"] = "Iranian Persian" labels["Ireland"] = { link = "Hiberno-English", display = "Ireland" } aliases["HE"] = "Ireland" aliases["IE"] = "Ireland" labels["Italian Hebrew"] = { link = "Italian Hebrew", display = "Italian Hebrew" } -- J labels["Johor-Selangor"] = { link = "Malayan languages", display = "Johor-Selangor" } -- K labels["Kabul, Peshawar"] = { link = "Pashto dialects", display = "Kabul, Peshawar" } labels["Kalix"] = { link = "Kalix dialect", display = "Kalix" } labels["Kandahar"] = { link = "Kandahari Pashto", display = "Kandahar" } aliases["ps-Kandahar"] = "Kandahar" labels["Karachi"] = { display = "Karachi Urdu" } labels["Kerry"] = { link = "Gaeltacht#Kerry Gaeltacht", display = "Kerry" } aliases["West Kerry"] = "Kerry" labels["khk"] = { link = "Khalkha Mongolian", display = "Mongolia Khalkha", } labels["kw"] = { link = "Kuwaiti Arabic", display = "Kuwaiti Gulf Arabic" } aliases["Q8"] = "kw" aliases["KW"] = "kw" aliases["Kuwait"] = "kw" aliases["Kuwaiti"] = "kw" aliases["Kuwaiti Gulf Arabic"] = "kw" labels["xme-ham"] = { display = "Hamadani", link = "Kermanic languages", } labels["xme-mah"] = { display = "Mahallati", link = "Kermanic languages", } labels["xme-von"] = { display = "Vonishuni", link = "Kermanic languages", } labels["xme-del"] = { display = "Delijani", link = "Kermanic languages", } labels["xme-kas"] = { display = "Kashani", link = "Kermanic languages", } labels["xme-kes"] = { display = "Kese'i", link = "Kermanic languages", } labels["xme-mey"] = { display = "Meyme'i", link = "Kermanic languages", } labels["xme-abz"] = { display = "Abuzeydabadi", link = "Kermanic languages", } labels["xme-aby"] = { display = "Abyanehi", link = "Kermanic languages", } labels["xme-far"] = { display = "Farizandi", link = "Kermanic languages", } labels["xme-jow"] = { display = "Jowshaqani", link = "Kermanic languages", } labels["xme-qoh"] = { display = "Qohrudi", link = "Kermanic languages", } labels["xme-yar"] = { display = "Yarandi", link = "Kermanic languages", } labels["xme-tar"] = { display = "Tari", link = "Kermanic languages", } labels["xme-sed"] = { display = "Sedehi", link = "Kermanic languages", } labels["xme-ard"] = { display = "Ardestani", link = "Kermanic languages", } labels["xme-zef"] = { display = "Zefre'i", link = "Kermanic languages", } labels["xme-isf"] = { display = "Isfahani", link = "Kermanic languages", } labels["xme-kaf"] = { display = "Kafroni", link = "Kermanic languages", } labels["xme-var"] = { display = "Varzenei", link = "Kermanic languages", } labels["xme-nay"] = { display = "Nayini", link = "Nayini language", } labels["xme-vaf"] = { display = "Vafsi", link = "Vafsi dialect", } labels["xme-ast"] = { display = "Ashtiani language", link = "nyq", } labels["xme-xun"] = { display = "Khunsari", link = "Khunsari language", } labels["xme-nat"] = { display = "Natanzi", link = "Natanzi language", } labels["xme-soi"] = { display = "Soi", link = "Soi language", } labels["xme-gaz"] = { display = "Gazi", link = "Gazi language", } labels["xme-ana"] = { display = "Anaraki", link = "Nayini language", } labels["xme-ker"] = { display = "Kermani", link = "Zoroastrian Dari language", } labels["xme-yaz"] = { display = "Yazdi", link = "Zoroastrian Dari language", } -- L labels["Lyallpuri"] = { link = "Faisalabad", display = "Lyallpuri" } aliases["Faisalabad"] = "Lyallpuri" labels["LAm"] = { link = "Spanish language in the Americas", display = "Latin American" } labels["Late Egyptian"] = { link = "Late Egyptian language", display = "reconstructed Late Egyptian" } labels["Latinate"] = { link = "Latin#Phonology", display = "Latinate" } labels["lleísmo"] = { link = "Yeísmo", display = "''ll''-''y'' distinction", type = "sound change" } labels["Lövånger"] = { link = "Lövånger", } labels["Luleå"] = { link = "Luleå", } -- M labels["Malwai"] = { link = "Malwai dialect", display = "Malwai" } labels["Majha"] = { link = "Punjabi dialects and languages#Standard_Punjabi", display = "Standard Punjabi" } aliases["pa"] = "Majha" aliases["Majhi"] = "Majha" labels["Mary-marry-merry"] = { link = "Mary–marry–merry merger", display = "''Mary''–''marry''–''merry'' merger", type = "sound change" } aliases["Mmmm"] = "Mary-marry-merry" labels["Mayo"] = { link = "Gaeltacht Iorrais agus Acaill", display = "Mayo" } labels["Medio-Late Egyptian"] = { link = "Late Egyptian language", display = "reconstructed Medio-Late Egyptian" } labels["Metro Cebu"] = { link = "Metro Cebu" } aliases["Cebu City"] = "Metro Cebu" aliases["Urban Cebuano"] = "Metro Cebu" labels["Middle Egyptian"] = { link = "Egyptian language#Middle Egyptian", display = "reconstructed Middle Egyptian" } labels["Midwestern US"] = { link = "Midwestern United States#Linguistic characteristics", display = "Midwestern US" } aliases["Midwest US"] = "Midwestern US" aliases["Midwest US English"] = "Midwestern US" aliases["Midwestern US English"] = "Midwestern US" labels["Mizrahi Hebrew"] = { link = "Mizrahi Hebrew", display = "Mizrahi Hebrew" } aliases["Mizrahi"] = "Mizrahi Hebrew" aliases["Mizrakhi"] = "Mizrahi Hebrew" aliases["Mizrachi"] = "Mizrahi Hebrew" aliases["Mizrakhi Hebrew"] = "Mizrahi Hebrew" aliases["Mizrachi Hebrew"] = "Mizrahi Hebrew" labels["MLE"] = { link = "Multicultural London English", display = "MLE" } aliases["Multicultural London English"] = "MLE" labels["MTE"] = { link = "Multicultural Toronto English", display = "MTE" } aliases["Multicultural Toronto English"] = "MTE" aliases["Greater Toronto English"] = "MTE" aliases["GTE"] = "MTE" labels["Montenegro"] = { link = "Comparison of standard Bosnian, Croatian, Montenegrin and Serbian#Accentuation", display = "Montenegro" } aliases["Montenegrin"] = "Montenegro" labels["Munster"] = { link = "Munster Irish", display = "Munster" } -- N labels["near-square"] = { link = "near-square merger", display = "''near''–''square'' merger", type = "sound change" } labels["Netherlands"] = { link = "Dutch phonology", display = "Netherlands" } aliases["NL"] = "Netherlands" labels["New Latin"] = { link = "New Latin" } labels["New York"] = { link = "New York accent", display = "NYC" } aliases["NY"] = "New York" aliases["NYC"] = "New York" aliases["New York City"] = "New York" labels["New Zealand"] = { link = "New Zealand English phonology", display = "New Zealand" } aliases["NZ"] = "New Zealand" aliases["GNZ"] = "New Zealand" aliases["General New Zealand"] = "New Zealand" labels["non-cure-force"] = { link = "Cure–force merger", display = "''cure''–''force'' distinction", type = "sound change" } aliases["non-pour-poor"] = "non-cure-force" labels["non-Mary-marry-merry"] = { link = "Mary–marry–merry merger", display = "''Mary''–''marry''–''merry'' distinction", type = "sound change" } aliases["nMmmm"] = "non-Mary-marry-merry" labels["non-rhotic"] = { link = "Rhoticity in English", display = "non-rhotic" } aliases["nonrhotic"] = "non-rhotic" labels["non-weak vowel"] = { link = "Weak vowel merger", display = "weak vowel distinction", type = "sound change" } labels["northern and central Germany"] = { display = "northern Germany, central Germany" } aliases["north and central German"] = "northern and central Germany" aliases["North and Central German"] = "northern and central Germany" aliases["north and central Germany"] = "northern and central Germany" aliases["North and Central Germany"] = "northern and central Germany" aliases["northern and central German"] = "northern and central Germany" aliases["Northern and Central German"] = "northern and central Germany" aliases["Northern and Central Germany"] = "northern and central Germany" labels["Northern England"] = { link = "English language in Northern England", display = "Northern England" } aliases["North England"] = "Northern England" labels["northern Germany"] = { display = "northern Germany" } aliases["north German"] = "northern Germany" aliases["North German"] = "northern Germany" aliases["north Germany"] = "northern Germany" aliases["North Germany"] = "northern Germany" aliases["northern German"] = "northern Germany" aliases["Northern German"] = "northern Germany" aliases["Northern Germany"] = "northern Germany" labels["Northern Scotland"] = { link = "Northern Scots", display = "Northern Scotland" } -- O labels["Old Egyptian"] = { link = "Egyptian language#Old Egyptian", display = "reconstructed Old Egyptian" } labels["Osaka"] = { link = "Kansai dialect", display = "Osaka" } -- P labels["pa-IN"] = { link = "Punjabi dialects and languages", display = "India" } aliases["pan"] = "pa-IN" aliases["East Punjab"] = "pa-PK" labels["pa-PK"] = { link = "Punjabi dialects and languages", display = "Pakistan" } aliases["pnb"] = "pa-PK" aliases["Lahnda"] = "pa-PK" aliases["West Punjab"] = "pa-PK" labels["Palestinian Hebrew"] = { link = "Palestinian vocalization", display = "Palestinian Hebrew" } labels["pin-pen"] = { link = "pin–pen merger", display = "''pin''–''pen'' merger", type = "sound change" } aliases["pen-pin"] = "pin-pen" labels["Philippine"] = { link = "Philippine English", display = "Philippine" } aliases["Philippines"] = "Philippine" labels["Portugal"] = { link = "European Portuguese", display = "Portugal" } aliases["EP"] = "Portugal" aliases["PT"] = "Portugal" labels["ps-Kabul"] = { link = "Pashto dialects", display = "Kabuli" } -- Q labels["Quanzhou"] = { link = "Quanzhou" } labels["Quebec"] = { link = "Quebec French phonology", display = "Quebec" } aliases["Québec"] = "Quebec" aliases["Joual"] = "Quebec" labels["Quetta"] = { link = "Pashto dialects", display = "Quetta" } -- R labels["r-dissimilation"] = { link = "Dissimilation", display = "''r''-dissimilation", type = "sound change" } labels["Rālik"] = { link = "Rālik Chain", display = "Rālik" } aliases["Ralik"] = "Rālik"; labels["Ratak"] = { link = "Ratak Chain", display = "Ratak" } labels["rhotic"] = { link = "Rhotic and non-rhotic accents", display = "rhotic", type = "sound change" } labels["Riau-Lingga"] = { link = "Riau-Lingga Sultanate", display = "Riau-Lingga" } labels["Rioplatense"] = { link = "Rioplatense Spanish", display = "Rioplatense" } labels["RP"] = { link = "Received Pronunciation" } aliases["Received Pronunciation"] = "RP" aliases["Received Standard"] = "RP" aliases["RS"] = "RP" labels["Rosmuc"] = { link = "Rosmuc", display = "Rosmuc" } aliases["Ros Muc"] = "Rosmuc" -- S labels["São Paulo"] = { link = "Brazilian Portuguese", display = "São Paulo" } labels["Scania"] = { link = "Scanian dialect", display = "Scania" } labels["Scotland"] = { link = "Scottish English", display = "Scotland" } labels["Sephardi Hebrew"] = { link = "Sephardi Hebrew", display = "Sephardi Hebrew" } aliases["Sephardi"] = "Sephardi Hebrew" labels["Serbia"] = { link = "Comparison of standard Bosnian, Croatian, Montenegrin and Serbian#Accentuation", display = "Serbia" } aliases["Serbian"] = "Serbia" labels["seseo"] = { link = "seseo", display = "''seseo'' merger", type = "sound change" } labels["Sistani"] = { link = "Sistani dialect", display = "Sistani" } labels["Skellefteå"] = { link = "Skellefteå" } labels["Soikkola"] = { link = "Ingrian phonology#Soikkola dialect", display = "Soikkola" } labels["South Africa"] = { link = "South African English phonology", display = "General South African" } aliases["SAE"] = "South Africa" aliases["GSAE"] = "South Africa" aliases["GenSAE"] = "South Africa" aliases["General South African"] = "South Africa" labels["Southern American English"] = { link = "Southern American English" } aliases["Southern US"] = "Southern American English" aliases["Southern US English"] = "Southern American English" aliases["Southern U.S. English"] = "Southern American English" aliases["US South"] = "Southern American English" labels["South Brazil"] = { link = "Brazilian Portuguese", display = "South Brazil" } labels["southern Germany"] = { display = "southern Germany" } aliases["south German"] = "southern Germany" aliases["South German"] = "southern Germany" aliases["south Germany"] = "southern Germany" aliases["South Germany"] = "southern Germany" aliases["southern German"] = "southern Germany" aliases["Southern German"] = "southern Germany" aliases["Southern Germany"] = "southern Germany" labels["Southern Leyte"] = { link = "Southern Leyte" } aliases["Kana Habagatan"] = "Southern Leyte" labels["Southern Scotland"] = { link = "Southern Scots", display = "Southern Scotland" } aliases["Southern Scots"] = "Southern Scotland" labels["St. Louis"] = { link = "North American regional phonology#St. Louis and vicinity", display = "St. Louis (Missouri)" } aliases["STL"] = "St. Louis" labels["standard"] = { display = "standard" } aliases["Standard"] = "standard" labels["Standard Basque"] = { link = "Standard Basque", display = "standard" } labels["Standard Southern British English"] = { link = "Standard Southern British English", display = "Standard Southern British English" } aliases["SSBE"] = "Standard Southern British English" labels["Standard Zhuang"] = { link = "Standard Zhuang", display = "Standard Zhuang" } labels["Stockholm e"] = { link = "Swedish phonology", display = "with Stockholm ''e''", type = "sound change" } labels["Sweden"] = { link = "Swedish phonology", display = "Sweden" } aliases["Swedish"] = "Sweden" labels["Syrian Hebrew"] = { link = "Syrian Jews#Pronunciation of Hebrew", display = "Syrian Hebrew" } -- T labels["t-glottalization"] = { link = "T-glottalization", display = "''t''-glottalization", type = "sound change" } aliases["t-glottaling"] = "t-glottalization" labels["Tajik"] = { link = "Tajik language", display = "Tajik" } aliases["Tajiki"] = "Tajik" labels["Tehrani"] = { link = "Tehrani accent", display = "Tehrani" } labels["th-fronting"] = { link = "th-fronting", type = "sound change" } labels["Tiberian Hebrew"] = { link = "Tiberian Hebrew", display = "Tiberian Hebrew" } aliases["Tiberian"] = "Tiberian Hebrew" labels["Tosk"] = { link = "Tosk Albanian", display = "Tosk" } -- U labels["UK"] = { link = "British English", display = "UK" } aliases["British"] = "UK" aliases["U.K."] = "UK" labels["Ulaanbaatar"] = { link = "Ulaanbaatar" } aliases["UlaanBaatar"] = "Ulaanbaatar" labels["Ulster"] = { link = "Ulster Irish", display = "Ulster" } aliases["Donegal"] = "Ulster" labels["Umeå"] = { link = "Umeå", } labels["ur"] = { link = "Urdu#Phonology", display = "Standard Urdu" } aliases["urd"] = "ur" labels["ur-KPK"] = { link = "Khyber Pakhtunkhwa", display = "Khyber Pakhtunkhwa" } labels["US"] = { link = "American English", display = "US" } aliases["U.S."] = "US" -- V labels["Valencia"] = { link = "Valencian" } aliases["Valencian"] = "Valencia" aliases["Vannetais"] = "Gwenedeg" labels["Vedic Sanskrit"] = { link = "Vedic Sanskrit", display = "Vedic" } aliases["Vedic"] = "Vedic Sanskrit" labels["Rigvedic Sanskrit"] = { link = "wikt:Rigvedic", display = "Rigvedic" } aliases["Rigvedic"] = "Rigvedic Sanskrit" labels["Samavedic"] = { link = "wikt:Samavedic", display = "Samavedic" } labels["Yajurvedic"] = { link = "wikt:Yajurvedic", display = "Yajurvedic" } labels["Atharvavedic"] = { link = "wikt:Atharvavedic", display = "Atharvavedic" } labels["Vulgar"] = { link = "Vulgar Latin", display = "Vulgar" } -- W labels["Wales"] = { link = "Welsh English", display = "Wales" } aliases["Welsh"] = "Wales" labels["Wardak"] = { link = "Pashto dialects", display = "Wardak" } labels["Waterford"] = { link = "Gaeltacht na nDéise", display = "Waterford" } aliases["Ring"] = "Waterford" labels["Wazirwola"] = { link = "Wazirwola dialect", display = "Wazirwola" } labels["weak vowel"] = { link = "Weak vowel merger", display = "weak vowel merger", type = "sound change" } labels["wine/whine"] = { link = "wine–whine merger", display = "without the ''wine''–''whine'' merger", type = "sound change" } aliases["wine-whine"] = "wine/whine" labels["Wood"] = { link = "Wood Frisian", display = "Wood", } -- X labels["Xiamen"] = { link = "Xiamen" } -- Y labels["yeísmo"] = { link = "Yeísmo", display = "''ll''-''y'' neutralization", type = "sound change" } labels["Yemenite Hebrew"] = { link = "Yemenite Hebrew", display = "Yemenite Hebrew" } labels["YIVO"] = { link = "YIVO" } labels["Ylä-Laukaa"] = { link = "Ingrian language#Dialects", display = "Ylä-Laukaa" } labels["yod-coalescence"] = { link = "yod-coalescence", display = "yod-coalescence", type = "sound change" } -- Z labels["Zhangzhou"] = { link = "Zhangzhou" } labels["Zurich"] = { link = "Zürich German", display = "Zurich" } aliases["Zürich"] = "Zurich" return { labels = labels, aliases = aliases } akyh5yejwy5y2vphcwixg8kjecyo9iq 828 2983 8295 2022-07-22T08:58:14Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local export = {} --[[ symb is what is tracked. It can be a literal symbol or a Lua pattern. If it is a table, tracking is added for any of the symbols in the list. cat is the subtemplate that is added to the default path "IPA/" + language code + "/". ]] local U = mw.ustring.char local syllabic = U(0x329) -- The validity of this table is checked by documentation function -- in [[Module:User:Erutuon/sandbox]]. export.tracking = { en = { { symb = "iə", cat = "ambig", }, { symb = { "ɪi", "ʊu", "ɪj", "ʊw" }, cat = "eeoo", }, { symb = { "r" }, cat = "plain r", }, }, cs = { { symb = "[mnrl]" .. syllabic, cat = "syllabic-consonant", }, }, ps = { { symb = "ɤ", cat = "Pashto", }, }, fa = { { symb = "ʔ", cat = "glottal-stop", }, }, { { symb = "", cat = "", }, }, } function export.run_tracking(IPA, lang) if not IPA or IPA == "" then return end lang = lang:getCode() if not export.tracking[lang] then return end for i, arguments in ipairs(export.tracking[lang]) do local symbols = arguments.symb local category = arguments.cat if type(symbols) == "string" then symbols = { symbols } end for _, symbol in pairs(symbols) do if mw.ustring.find(IPA, symbol) then require("Module:debug/track")("IPA/" .. lang .. "/" .. category) end end end end return export ioeemmyd720mxl78g3poo7owgj72fqh 10 2984 8296 2022-07-22T09:17:21Z Rebel Agent 2678 Ke dirile tsebe wikitext text/x-wiki <div class="pseudo NavFrame"><div class="NavHead" style="text-align: left;" {{#if:{{{id|}}}|id{{=}}"Translations-{{anchorencode:{{{id}}}}}"}}>{{{1}}} <!-- --><span style="font-weight: normal" >— <i>see</i></span> <!-- -->{{#if:{{{id|}}}|[[{{{2|{{{1}}}}}}#Translations-{{{id}}}|{{{2|{{{1}}}}}}]]|[[{{{2|{{{1}}}}}}]]}}<!-- -->{{#if:{{{3|}}}|,&lrm; {{#if:{{{id|}}}|[[{{{3}}}#Translations-{{{id}}}|{{{3}}}]]|[[{{{3}}}]]}}}}<!-- -->{{#if:{{{4|}}}|,&lrm; {{#if:{{{id|}}}|[[{{{4}}}#Translations-{{{id}}}|{{{4}}}]]|[[{{{4}}}]]}}}}<!-- -->{{#if:{{{5|}}}|,&lrm; {{#if:{{{id|}}}|[[{{{5}}}#Translations-{{{id}}}|{{{5}}}]]|[[{{{5}}}]]}}}}<!-- -->{{#if:{{{6|}}}|,&lrm; {{#if:{{{id|}}}|[[{{{6}}}#Translations-{{{id}}}|{{{6}}}]]|[[{{{6}}}]]}}}}<!-- -->{{#if:{{{7|}}}|,&lrm; {{#if:{{{id|}}}|[[{{{7}}}#Translations-{{{id}}}|{{{7}}}]]|[[{{{7}}}]]}}}}<!-- -->{{#if:{{{8|}}}|,&lrm; {{#if:{{{id|}}}|[[{{{8}}}#Translations-{{{id}}}|{{{8}}}]]|[[{{{8}}}]]}}}}<!-- -->{{#if:{{{9|}}}|,&lrm; {{#if:{{{id|}}}|[[{{{9}}}#Translations-{{{id}}}|{{{9}}}]]|[[{{{9}}}]]}}}}<!-- -->{{#if:{{{10|}}}|,&lrm; {{#if:{{{id|}}}|[[{{{10}}}#Translations-{{{id}}}|{{{10}}}]]|[[{{{10}}}]]}}[[Category:Limit of template reached]]}}<!-- --></div></div><!-- --><noinclude>{{documentation}}</noinclude> 8mzmeasmjynwfxu7zgdnheawzi9ko23 10 2985 8297 2022-07-22T09:46:24Z Rebel Agent 2678 Ke dirile template wikitext text/x-wiki {{check deprecated lang param usage|lang={{{lang|}}}|<!-- -->{{#invoke:rhymes|show}}<!-- -->}}<!-- --><noinclude>{{documentation}}</noinclude> cylhiuhtttqu3tsw64glng6vzvai220 828 2986 8298 2022-07-22T09:47:56Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local export = {} local force_cat = false -- for testing local function tag_rhyme(rhyme, lang) local formatted_rhyme, cat -- FIXME, should not be here. Telugu should use IPA as well. if lang:getCode() == "te" then formatted_rhyme = require("Module:script utilities").tag_text(rhyme, lang) cat = "" else formatted_rhyme, cat = require("Module:IPA").format_IPA(lang, rhyme, true) end return formatted_rhyme, cat end local function make_rhyme_link(lang, link_rhyme, display_rhyme, qualifiers) local retval if not link_rhyme then retval = table.concat{"[[Rhymes:", lang:getCanonicalName(), "|", lang:getCanonicalName(), "]]"} else local formatted_rhyme, cat = tag_rhyme(display_rhyme or link_rhyme, lang) retval = table.concat{"[[Rhymes:", lang:getCanonicalName(), "/", link_rhyme, "|", formatted_rhyme, "]]", cat} end if qualifiers and #qualifiers > 0 then return require("Module:qualifier").format_qualifier(qualifiers) .. " " .. retval else return retval end end function export.show_row(frame) local params = { [1] = {required = true}, [2] = {required = true}, [3] = {}, } local args = frame.getParent and frame:getParent().args or frame if (not args[1] or args[1] == "") and mw.title.getCurrentTitle().nsText == "Template" then return '[[Rhymes:English/aɪmz|<span class="IPA">-aɪmz</span>]]' end local args = require("Module:parameters").process(args, params) local lang = require("Module:languages").getByCode(args[1], 1) return make_rhyme_link(lang, args[2], "-" .. args[2]) .. (args[3] and (" (''" .. args[3] .. "'')") or "") end local function add_syllable_categories(categories, lang, rhyme, num_syl) local prefix = "Rhymes:" .. lang .. "/" .. rhyme table.insert(categories, prefix) if num_syl then for _, n in ipairs(num_syl) do local c if n > 1 then c = prefix .. "/" .. n .. " syllables" else c = prefix .. "/1 syllable" end table.insert(categories, c) end end end --[=[ Meant to be called from a module. `data` is a table in the following format: { lang = LANGUAGE_OBJECT, rhymes = {{rhyme = "RHYME", qualifiers = nil or {"QUALIFIER", "QUALIFIER", ...}, num_syl = nil or {#SYL, #SYL, ...}}, ...}, qualifiers = nil or {"QUALIFIER", "QUALIFIER", ...}, num_syl = nil or {#SYL, #SYL, ...}, caption = nil or "CAPTION", nocaption = BOOLEAN, sort = nil or "SORTKEY", force_cat = BOOLEAN, } Here: * `lang` is a language object. * `rhymes` is the list of rhymes to display. RHYME is the IPA rhyme, without initial hyphen. QUALIFIER is a qualifier string to display before the specific rhyme in question, formatted using format_qualifier() in [[Module:qualifier]]. #SYL is the number of syllables of the word or words containing this rhyme, for categorization purposes (see below). * `qualifiers` (at top level), if non-nil, is a list of qualifier strings to display after the caption "Rhymes:" and before the formatted rhymes, formatted using format_qualifier() in [[Module:qualifier]]. * `num_syl` (at top level), if non-nil, a list of the number(s) of syllables of the word or words with each rhyme specified in `rhymes`. This applies to all rhymes specified in `rhymes`, while the corresponding `num_syl` attached to an individual rhyme applies only to that rhyme (and overrides the global `num_syl`, if both are given). * `caption`, if specified, overrides the default caption "Rhymes". A colon and space is automatically added after the caption. * `nocaption`, if specified, suppresses the caption entirely. * `sort`, if specified, is the sort key for categories. * `force_cat`, if specified, forces categories even on non-mainspace pages (for testing). Note that the number of syllables is currently used only for categorization; if present, an extra category will be added such as [[Category:Rhymes:Italian/ino/3 syllables]] in addition to [[Category:Rhymes:Italian/ino]]. ]=] function export.format_rhymes(data) local langname = data.lang:getCanonicalName() local links = {} local categories = {} for i, r in ipairs(data.rhymes) do local rhyme = r.rhyme table.insert(links, make_rhyme_link(data.lang, rhyme, "-" .. rhyme, r.qualifiers)) add_syllable_categories(categories, langname, rhyme, r.num_syl or data.num_syl) end local ret = data.nocaption and "" or (data.caption or "Rhymes") .. ": " if data.qualifiers and data.qualifiers[1] then ret = require("Module:qualifier").format_qualifier(data.qualifiers) .. " " .. ret end return ret .. table.concat(links, ", ") .. require("Module:utilities").format_categories(categories, data.lang, data.sort, nil, force_cat or data.force_cat) end function export.show(frame) local args = frame.getParent and frame:getParent().args or frame local compat = args["lang"] local offset = compat and 0 or 1 local params = { [1 + offset] = {required = true, list = true, default = "aɪmz"}, [compat and "lang" or 1] = {required = true, default = "en"}, ["s"] = {}, ["srhymes"] = {list = "s", allow_holes = true, require_index = true}, ["q"] = {}, ["qrhymes"] = {list = "q", allow_holes = true, require_index = true}, ["caption"] = {}, ["nocaption"] = {type = "boolean"}, ["sort"] = {}, } local args = require("Module:parameters").process(args, params) local lang = args[compat and "lang" or 1] lang = require("Module:languages").getByCode(lang, compat and "lang" or 1) -- temporary tracking code to find usage of {{rhymes}} in various languages -- [[Special:WhatLinksHere/Template:tracking/rhymes/LANGCODE]] local code = lang:getCode() if code == "it" or code == "es" then require("Module:debug").track("rhymes/" .. code) end local function parse_num_syl(val) val = mw.text.split(val, "%s*,%s*") local ret = {} for _, v in ipairs(val) do local n = tonumber(v) or error("Unrecognized #syllables '" .. v .. "', should be a number") table.insert(ret, n) end return ret end local rhymes = {} for i, rhyme in ipairs(args[1 + offset]) do local rhymeobj = {rhyme = rhyme} if args.srhymes[i] then rhymeobj.num_syl = parse_num_syl(args.srhymes[i]) end if args.qrhymes[i] then rhymeobj.qualifiers = {args.qrhymes[i]} end table.insert(rhymes, rhymeobj) end return export.format_rhymes { lang = lang, rhymes = rhymes, num_syl = args.s and parse_num_syl(args.s) or nil, qualifiers = args.q and {args.q} or nil, caption = args.caption, nocaption = args.nocaption, sort = args.sort, } end -- {{rhymes nav}} function export.show_nav(frame) -- Gather parameters local args = frame:getParent().args local lang = args[1] or (mw.title.getCurrentTitle().nsText == "Template" and "und") or error("Language code has not been specified. Please pass parameter 1 to the template.") lang = require("Module:languages").getByCode(lang, 1) local parts = {} local i = 2 while args[i] do local part = args[i]; if part == "" then part = nil end table.insert(parts, part) i = i + 1 end -- Create steps local steps = {"» [[Wiktionary:Rhymes|Rhymes]]", "» " .. make_rhyme_link(lang)} local categories = {} if #parts > 0 then local last = parts[#parts] parts[#parts] = nil local prefix = "" for i, part in ipairs(parts) do prefix = prefix .. part parts[i] = prefix end for _, part in ipairs(parts) do table.insert(steps, "» " .. make_rhyme_link(lang, part .. "-", "-" .. part .. "-")) end if last == "-" then table.insert(steps, "» " .. make_rhyme_link(lang, prefix, "-" .. prefix)) table.insert(categories, "[[Category:" .. lang:getCanonicalName() .. " rhymes" .. (prefix == "" and "" or "/" .. prefix .. "-") .. "| ]]") elseif mw.title.getCurrentTitle().text == lang:getCanonicalName() .. "/" .. prefix .. last .. "-" then table.insert(steps, "» " .. make_rhyme_link(lang, prefix .. last .. "-", "-" .. prefix .. last .. "-")) table.insert(categories, "[[Category:" .. lang:getCanonicalName() .. " rhymes/" .. prefix .. last .. "-|-]]") else table.insert(steps, "» " .. make_rhyme_link(lang, prefix .. last, "-" .. prefix .. last)) table.insert(categories, "[[Category:" .. lang:getCanonicalName() .. " rhymes" .. (prefix == "" and "" or "/" .. prefix .. "-") .. "|" .. last .. "]]") end elseif lang:getCode() ~= "und" then table.insert(categories, "[[Category:" .. lang:getCanonicalName() .. " rhymes| ]]") end frame:callParserFunction("DISPLAYTITLE", mw.title.getCurrentTitle().fullText:gsub( "/(.+)$", function (rhyme) return "/" .. tag_rhyme(rhyme, lang) end)) return table.concat(steps, " ") .. table.concat(categories) end return export kwa1fseql6qtl47csps6mlpm917dvni 828 2987 8299 2022-07-22T09:50:12Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local export = {} local diphthongs = mw.loadData("Module:IPA/data").diphthongs local vowels = mw.loadData("Module:IPA/data/symbols").vowels .. "ᵻ" .. "ᵿ" local U = mw.ustring.char --[[ No use for this at the moment, though it is an interesting catalogue. It might be usable for phonetic transcriptions. Diacritics added to vowels: inverted breve above, inverted breve below, up tack, down tack, left tack, right tack, diaeresis (above), diaeresis below, right half ring, left half ring, plus sign below, minus sign below, combining x above, rhotic hook, tilde (above), tilde below ligature tie (combining double breve), ligature tie below ]] local diacritics = U(0x311)..U(0x32F) ..U(0x31D)..U(0x31E) ..U(0x318)..U(0x319) ..U(0x308)..U(0x324) ..U(0x339)..U(0x31C) ..U(0x31F)..U(0x320) ..U(0x33D)..U(0x2DE) ..U(0x303)..U(0x330) ..U(0x361)..U(0x35C) --[[ combining acute and grave tone marks, circumflex ]]-- local tone = "[" .. U(0x341) .. U(0x340) ..U (0x302) .. "]" local nonsyllabicDiacritics = U(0x311) .. U(0x32F) local syllabicDiacritics = U(0x0329) .. U(0x030D) local ties = U(0x361) .. U(0x35C) -- long, half-long, extra short local lengthDiacritics = U(0x2D0) .. U(0x2D1) .. U(0x306) local vowel = "[" .. vowels .. "]" .. tone .. "?" local tie = "[" .. ties .. "]" local nonsyllabicDiacritic = "[" .. nonsyllabicDiacritics .. "]" local syllabicDiacritic = "[" .. syllabicDiacritics .. "]" local UTF8Char = "[\1-\127\194-\244][\128-\191]*" function export.getVowels(remainder, lang) if string.find(remainder, "^[%\[/]?%-") or string.find(remainder, "%-[%\[/]?$") then return nil end -- If a hyphen is at the beginning or end of the transcription, do not count syllables. local count = 0 local diphs = diphthongs[lang:getCode()] or {} remainder = mw.ustring.toNFD(remainder) remainder = string.gsub(remainder, "%((.*)%)", "%1") -- Remove parentheses. while remainder ~= "" do -- Ignore nonsyllabic vowels remainder = mw.ustring.gsub(remainder, "^" .. vowel .. nonsyllabicDiacritic, "") local m = mw.ustring.match(remainder, "^." .. syllabicDiacritic) or -- Syllabic consonant mw.ustring.match(remainder, "^" .. vowel .. tie .. vowel) -- Tie bar -- Starts with a recognised diphthong? for _, diph in ipairs(diphs) do if m then break end m = m or mw.ustring.match(remainder, "^" .. diph) end -- If we haven't found anything yet, just match on a single vowel m = m or mw.ustring.match(remainder, "^" .. vowel) if m then -- Found a vowel, add it count = count + 1 remainder = string.sub(remainder, #m + 1) else -- Found a non-vowel, skip it remainder = string.gsub(remainder, "^" .. UTF8Char, "") end end if count ~= 0 then return count end return nil end function export.countVowels2Test(frame) local params = { [1] = {required = true}, [2] = {default = ""}, } local args = require("Module:parameters").process(frame.args, params) local lang = require("Module:languages").getByCode(args[1]) or require("Module:languages").err(args[1], 1) local count = export.getVowels(args[2], lang) return 'The text "' .. args[2] .. '" contains ' .. count .. ' vowels.' end local function countVowels(text) text = mw.ustring.toNFD(text) or error("Invalid UTF-8") local _, count = mw.ustring.gsub(text, vowel, "") local _, sequenceCount = mw.ustring.gsub(text, vowel.."+", "") local _, nonsyllabicCount = mw.ustring.gsub(text, vowel .. nonsyllabicDiacritic, "") local _, tieCount = mw.ustring.gsub(text, vowel .. tie .. vowel, "") local diphthongCount = count - (nonsyllabicCount + tieCount) return count, sequenceCount, diphthongCount end local function countDiphthongs(text, lang) text = mw.ustring.toNFD(text) or error("Invalid UTF-8") local diphthongs = diphthongs[lang:getCode()] or {} local _, count local total = 0 if diphthongs then for i, diphthong in pairs(diphthongs) do _, count = mw.ustring.gsub(text, diphthong, "") total = total + count end end return total end function export.countVowels(frame) local params = { [1] = {default = ""}, } local args = require("Module:parameters").process(frame.args, params) local count, sequenceCount, diphthongCount = countVowels(args[1]) local outputs = {} table.insert(outputs, (count or 'an unknown number of') .. ' vowels') table.insert(outputs, (sequenceCount or 'an unknown number of') .. ' vowel sequences') table.insert(outputs, (diphthongCount or 'an unknown number of') .. ' vowels or vowels and diphthongs') return 'The text "' .. args[1] .. '" contains ' .. mw.text.listToText(outputs) .. "." end function export.countVowelsDiphthongs(frame) local params = { [1] = {required = true}, [2] = {default = ""}, } local args = require("Module:parameters").process(frame.args, params) local lang = require("Module:languages").getByCode(args[1]) or require("Module:languages").err(args[1], 1) local vowels = countVowels(args[2]) local count = vowels - countDiphthongs(args[2], lang) or 0 local out = 'The text "' .. args[2] .. '" contains ' .. (count or 'an unknown number of') if count == 1 then out = out .. ' vowel or diphthong.' else out = out .. ' vowels or diphthongs.' end return out end return export 89qaat609gtr1wjnqtjv2m5kljpokku 10 2988 8300 2022-07-22T09:52:45Z Rebel Agent 2678 Ke dirile template wikitext text/x-wiki {{check deprecated lang param usage|lang={{{lang|}}}|<!-- -->{{request box<!-- -->|1=[[Image:Headset_icon.svg|20px]]<!-- -->|2=This {{<noinclude>temp|</noinclude>pagetype}} needs [[:Category:Requests for audio pronunciation in {{langname|{{#if:{{{lang|}}}|{{{lang|}}}|{{{1<noinclude>|und</noinclude>}}}}}}} entries|audio files]]. If you are a native speaker with a microphone, please [[Help:Audio pronunciations|record some]] and [[commons:Special:Upload|upload]] them. <small>(For audio required quickly, visit [[WT:APR]].)</small> {{#if:{{#if:{{{lang|}}}|{{{1|}}}|{{{2|}}}}}| <br />Particularly: "{{#if:{{{lang|}}}|{{{1|}}}|{{{2|}}}}}"}}<!-- -->|inline={{{inline|no}}}}}<!-- -->}}<!-- (end of {{check deprecated lang param usage}}) --><includeonly><!-- -->{{#if:{{{nocat|}}}||<!-- -->{{categorize<!-- -->|{{#if:{{{lang|}}}|{{{lang|}}}|{{{1|}}}}}<!-- -->|Requests for audio pronunciation in {{langname|{{#if:{{{lang|}}}|{{{lang|}}}|{{{1|}}}}}}} entries<!-- -->|{{#if:{{{variety|}}}|Requests for audio pronunciation from {{{variety}}} in {{langname|{{#if:{{{lang|}}}|{{{lang|}}}|{{{1|}}}}}}} entries}}<!-- -->|sort={{{sort|}}}<!-- -->}}<!-- -->{{#if:{{{variety|}}}|[[Category:rfap with variety]]}}<!-- -->}}<!-- --></includeonly><!-- --><noinclude>{{documentation}}</noinclude> s98sn3zc10ecovsdrusc5cfx863d9xq 10 2989 8301 2022-07-22T09:54:05Z Rebel Agent 2678 Ke dirile template wikitext text/x-wiki {{#ifeq:{{yesno|{{{inline|}}}}}|yes|{{maintenance line|{{{2}}}}} |<div class="noprint request-box" style="width: auto; margin: 0; padding: 0.5em; border-collapse: collapse;overflow: hidden;"> {{{!}} style="background:#FFFFFF; width:90%; margin: auto; border:1px dashed #999999; text-align:left" {{!}}{{{1}}} {{!}}{{{2}}} {{!}}}</div>}}<noinclude>{{documentation}}[[Category:Template boxes]]</noinclude> m65gyylguoazwtajli7p8owsxngezm7 828 2990 8302 2022-07-22T09:56:23Z Rebel Agent 2678 Ke dirile module Scribunto text/plain --[[ ------------------------------------------------------------------------------------ -- table (formerly TableTools) -- -- -- -- This module includes a number of functions for dealing with Lua tables. -- -- It is a meta-module, meant to be called from other Lua modules, and should -- -- not be called directly from #invoke. -- ------------------------------------------------------------------------------------ --]] --[[ Inserting new values into a table using a local "index" variable, which is incremented each time, is faster than using "table.insert(t, x)" or "t[#t + 1] = x". See the talk page. ]] local libraryUtil = require('libraryUtil') local export = {} -- Define often-used variables and functions. local floor = math.floor local infinity = math.huge local checkType = libraryUtil.checkType local checkTypeMulti = libraryUtil.checkTypeMulti local function _check(funcName, expectType) if type(expectType) == "string" then return function(argIndex, arg, nilOk) checkType(funcName, argIndex, arg, expectType, nilOk) end else return function(argIndex, arg, expectType, nilOk) if type(expectType) == "table" then checkTypeMulti(funcName, argIndex, arg, expectType, nilOk) else checkType(funcName, argIndex, arg, expectType, nilOk) end end end end --[[ ------------------------------------------------------------------------------------ -- isPositiveInteger -- -- This function returns true if the given value is a positive integer, and false -- if not. Although it doesn't operate on tables, it is included here as it is -- useful for determining whether a given table key is in the array part or the -- hash part of a table. ------------------------------------------------------------------------------------ --]] function export.isPositiveInteger(v) return type(v) == 'number' and v >= 1 and floor(v) == v and v < infinity end --[[ ------------------------------------------------------------------------------------ -- isNan -- -- This function returns true if the given number is a NaN value, and false -- if not. Although it doesn't operate on tables, it is included here as it is -- useful for determining whether a value can be a valid table key. Lua will -- generate an error if a NaN is used as a table key. ------------------------------------------------------------------------------------ --]] function export.isNan(v) if type(v) == 'number' and tostring(v) == '-nan' then return true else return false end end --[[ ------------------------------------------------------------------------------------ -- shallowcopy -- -- This 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, but the returned table will have no metatable of -- its own. ------------------------------------------------------------------------------------ --]] function export.shallowcopy(orig) local orig_type = type(orig) local copy if orig_type == 'table' then copy = {} for orig_key, orig_value in pairs(orig) do copy[orig_key] = orig_value end else -- number, string, boolean, etc copy = orig end return copy end -- An alias for shallowcopy(); prefer shallowcopy(). function export.shallowClone(t) return export.shallowcopy(t) end --[[ Recursive deep copy function Equivalent to mw.clone? ]] local function deepcopy(orig, includeMetatable, already_seen) -- Stores copies of tables indexed by the original table. already_seen = already_seen or {} local copy = already_seen[orig] if copy ~= nil then return copy end if type(orig) == 'table' then copy = {} for orig_key, orig_value in pairs(orig) do copy[deepcopy(orig_key, includeMetatable, already_seen)] = deepcopy(orig_value, includeMetatable, already_seen) end already_seen[orig] = copy if includeMetatable then local mt = getmetatable(orig) if mt ~= nil then local mt_copy = deepcopy(mt, includeMetatable, already_seen) setmetatable(copy, mt_copy) end end else -- number, string, boolean, etc copy = orig end return copy end function export.deepcopy(orig, noMetatable, already_seen) checkType("deepcopy", 3, already_seen, "table", true) return deepcopy(orig, not noMetatable, already_seen) end --[[ ------------------------------------------------------------------------------------ -- append -- -- This appends any number of tables together and returns the result. Compare the Lisp -- expression (append list1 list2 ...). ------------------------------------------------------------------------------------ --]] function export.append(...) local ret = {} for i=1,select('#', ...) do local argt = select(i, ...) checkType('append', i, argt, 'table') for _, v in ipairs(argt) do table.insert(ret, v) end end return ret end --[[ ------------------------------------------------------------------------------------ -- removeDuplicates -- -- This removes duplicate values from an array. Non-positive-integer keys are -- ignored. The earliest value is kept, and all subsequent duplicate values are -- removed, but otherwise the array order is unchanged. ------------------------------------------------------------------------------------ --]] function export.removeDuplicates(t) checkType('removeDuplicates', 1, t, 'table') local isNan = export.isNan local ret, exists = {}, {} local index = 1 for _, v in ipairs(t) do if isNan(v) then -- NaNs can't be table keys, and they are also unique, so we don't need to check existence. ret[index] = v index = index + 1 else if not exists[v] then ret[index] = v index = index + 1 exists[v] = true end end end return ret end --[[ ------------------------------------------------------------------------------------ -- numKeys -- -- This takes a table and returns an array containing the numbers of any numerical -- keys that have non-nil values, sorted in numerical order. ------------------------------------------------------------------------------------ --]] function export.numKeys(t, checked) if not checked then checkType('numKeys', 1, t, 'table') end local isPositiveInteger = export.isPositiveInteger local nums = {} local index = 1 for k, _ in pairs(t) do if isPositiveInteger(k) then nums[index] = k index = index + 1 end end table.sort(nums) return nums end function export.maxIndex(t) checkType('maxIndex', 1, t, 'table') local positiveIntegerKeys = export.numKeys(t) if positiveIntegerKeys[1] then return math.max(unpack(positiveIntegerKeys)) else return 0 -- ??? end end --[[ ------------------------------------------------------------------------------------ -- affixNums -- -- This takes a table and returns an array containing the numbers of keys with the -- specified prefix and suffix. -- affixNums({a1 = 'foo', a3 = 'bar', a6 = 'baz'}, "a") -- ↓ -- {1, 3, 6}. ------------------------------------------------------------------------------------ --]] function export.affixNums(t, prefix, suffix) local check = _check('affixNums') check(1, t, 'table') check(2, prefix, 'string', true) check(3, suffix, 'string', true) local function cleanPattern(s) -- Cleans a pattern so that the magic characters ()%.[]*+-?^$ are interpreted literally. s = s:gsub('([%(%)%%%.%[%]%*%+%-%?%^%$])', '%%%1') return s end prefix = prefix or '' suffix = suffix or '' prefix = cleanPattern(prefix) suffix = cleanPattern(suffix) local pattern = '^' .. prefix .. '([1-9]%d*)' .. suffix .. '$' local nums = {} local index = 1 for k, _ in pairs(t) do if type(k) == 'string' then local num = mw.ustring.match(k, pattern) if num then nums[index] = tonumber(num) index = index + 1 end end end table.sort(nums) return nums end --[[ ------------------------------------------------------------------------------------ -- numData -- -- Given a table with keys like ("foo1", "bar1", "foo2", "baz2"), returns a table -- of subtables in the format -- { [1] = {foo = 'text', bar = 'text'}, [2] = {foo = 'text', baz = 'text'} } -- Keys that don't end with an integer are stored in a subtable named "other". -- The compress option compresses the table so that it can be iterated over with -- ipairs. ------------------------------------------------------------------------------------ --]] function export.numData(t, compress) local check = _check('numData') check(1, t, 'table') check(2, compress, 'boolean', true) local ret = {} for k, v in pairs(t) do local prefix, num = tostring(k):match('^([^0-9]*)([1-9][0-9]*)$') if num then num = tonumber(num) local subtable = ret[num] or {} if prefix == '' then -- Positional parameters match the blank string; put them at the start of the subtable instead. prefix = 1 end subtable[prefix] = v ret[num] = subtable else local subtable = ret.other or {} subtable[k] = v ret.other = subtable end end if compress then local other = ret.other ret = export.compressSparseArray(ret) ret.other = other end return ret end --[[ ------------------------------------------------------------------------------------ -- compressSparseArray -- -- This takes an array with one or more nil values, and removes the nil values -- while preserving the order, so that the array can be safely traversed with -- ipairs. ------------------------------------------------------------------------------------ --]] function export.compressSparseArray(t) checkType('compressSparseArray', 1, t, 'table') local ret = {} local index = 1 local nums = export.numKeys(t) for _, num in ipairs(nums) do ret[index] = t[num] index = index + 1 end return ret end --[[ ------------------------------------------------------------------------------------ -- sparseIpairs -- -- This is an iterator for sparse arrays. It can be used like ipairs, but can -- handle nil values. ------------------------------------------------------------------------------------ --]] function export.sparseIpairs(t) checkType('sparseIpairs', 1, t, 'table') local nums = export.numKeys(t) local i = 0 return function() i = i + 1 local key = nums[i] if key then return key, t[key] else return nil, nil end end end --[[ ------------------------------------------------------------------------------------ -- size -- -- This returns the size of a key/value pair table. It will also work on arrays, -- but for arrays it is more efficient to use the # operator. ------------------------------------------------------------------------------------ --]] function export.size(t) checkType('size', 1, t, 'table') local i = 0 for _ in pairs(t) do i = i + 1 end return i end --[[ -- This returns the length of a table, or the first integer key n counting from -- 1 such that t[n + 1] is nil. It is similar to the operator #, but may return -- a different value when there are gaps in the array portion of the table. -- Intended to be used on data loaded with mw.loadData. For other tables, use #. --]] function export.length(t) local i = 0 repeat i = i + 1 until t[i] == nil return i - 1 end --[[ Recursively compare two values that may be tables, including tables with nested tables as values. Return true if both values are structurally equal. Note that this handles arbitary levels of nesting. If all tables are known to be lists (with only integral keys), use export.deepEqualsList, which will be more efficient. NOTE: This is *NOT* smart enough to properly handle cycles; in such a case, it will get into an infinite loop. ]] function export.deepEquals(x, y) if type(x) == "table" and type(y) == "table" then -- Two tables are the same if they have the same number of elements -- and all keys that are present in one of the tables compare equal -- to the corresponding keys in the other table, using structural -- comparison. local sizex = 0 for key, value in pairs(x) do if not export.deepEquals(value, y[key]) then return false end sizex = sizex + 1 end local sizey = export.size(y) if sizex ~= sizey then return false end return true end return x == y end --[[ Recursively compare two values that may be lists (i.e. tables with integral keys), including lists with nested lists as values. Return true if both values are structurally equal. Note that this handles arbitary levels of nesting. Results are undefined if tables with non-integral keys are present anywhere in either structure; if that may be the case, use export.deepEquals, which will handle such tables correctly but be less efficient on lists than export.deepEqualsList. NOTE: This is *NOT* smart enough to properly handle cycles; in such a case, it will get into an infinite loop. ]] function export.deepEqualsList(x, y) if type(x) == "table" and type(y) == "table" then if #x ~= #y then return false end for key, value in ipairs(x) do if not export.deepEqualsList(value, y[key]) then return false end end return true end return x == y end --[[ Given a list and a value to be found, return true if the value is in the array portion of the list. Comparison is by value, using `deepEquals`. NOTE: This used to do shallow comparison by default and accepted a third 'deepCompare' param to do deep comparison. This param is still accepted but now ignored. ]] function export.contains(list, x) checkType('contains', 1, list, 'table') for _, v in ipairs(list) do if export.deepEquals(v, x) then return true end end return false end --[[ Given a general table and a value to be found, return true if the value is in either the array or hashmap portion of the table. Comparison is by value, using `deepEquals`. NOTE: This used to do shallow comparison by default and accepted a third 'deepCompare' param to do deep comparison. This param is still accepted but now ignored. ]] function export.tableContains(tbl, x) checkType('tableContains', 1, tbl, 'table') for _, v in pairs(tbl) do if export.deepEquals(v, x) then return true end end return false end --[[ Given a list and a value to be inserted, append or insert the value if not already present in the list. Comparison is by value, using `deepEquals`. Appends to the end, like the default behavior of table.insert(), unless `pos` is given, in which case insertion happens at position `pos` (i.e. before the existing item at position `pos`). NOTE: The order of `item` and `pos` is reversed in comparison to table.insert(), which uses `table.insert(list, item)` to insert at the end but `table.insert(list, pos, item)` to insert at position POS. NOTE: This used to do shallow comparison by default and accepted a fourth 'deepCompare' param to do deep comparison. This param is still accepted but now ignored. ]] function export.insertIfNot(list, item, pos) if not export.contains(list, item) then if pos then table.insert(list, pos, item) else table.insert(list, item) end end end --[[ Finds key for specified value in a given table. Roughly equivalent to reversing the key-value pairs in the table – reversed_table = { [value1] = key1, [value2] = key2, ... } – and then returning reversed_table[valueToFind]. The value can only be a string or a number (not nil, a boolean, a table, or a function). Only reliable if there is just one key with the specified value. Otherwise, the function returns the first key found, and the output is unpredictable. ]] function export.keyFor(t, valueToFind) local check = _check('keyFor') check(1, t, 'table') check(2, valueToFind, { 'string', 'number' }) for key, value in pairs(t) do if value == valueToFind then return key end end return nil end --[[ The default sorting function used in export.keysToList if no keySort is defined. ]] local function defaultKeySort(key1, key2) -- "number" < "string", so numbers will be sorted before strings. local type1, type2 = type(key1), type(key2) if type1 ~= type2 then return type1 < type2 else return key1 < key2 end end --[[ Returns a list of the keys in a table, sorted using either the default table.sort function or a custom keySort function. If there are only numerical keys, numKeys is probably more efficient. ]] function export.keysToList(t, keySort, checked) if not checked then local check = _check('keysToList') check(1, t, 'table') check(2, keySort, 'function', true) end local list = {} local index = 1 for key, _ in pairs(t) do list[index] = key index = index + 1 end -- Place numbers before strings, otherwise sort using <. if not keySort then keySort = defaultKeySort end table.sort(list, keySort) return list end --[[ Iterates through a table, with the keys sorted using the keysToList function. If there are only numerical keys, sparseIpairs is probably more efficient. ]] function export.sortedPairs(t, keySort) local check = _check('keysToList') check(1, t, 'table') check(2, keySort, 'function', true) local list = export.keysToList(t, keySort, true) local i = 0 return function() i = i + 1 local key = list[i] if key ~= nil then return key, t[key] else return nil, nil end end end function export.reverseIpairs(list) checkType('reverse_ipairs', 1, list, 'table') local i = #list + 1 return function() i = i - 1 if list[i] ~= nil then return i, list[i] else return nil, nil end end end --[=[ Joins an array with serial comma and serial conjunction, normally "and". An improvement on mw.text.listToText, which doesn't properly handle serial commas. Options: - conj Conjunction to use; defaults to "and". - italicizeConj Italicize conjunction: for [[Module:Template:also]] - dontTag Don't tag the serial comma and serial "and". For error messages, in which HTML cannot be used. ]=] function export.serialCommaJoin(seq, options) local check = _check("serialCommaJoin", "table") check(1, seq) check(2, options, true) local length = #seq if not options then options = {} end local conj if length > 1 then conj = options.conj or "and" if options.italicizeConj then conj = "''" .. conj .. "''" end end if length == 0 then return "" elseif length == 1 then return seq[1] -- nothing to join elseif length == 2 then return seq[1] .. " " .. conj .. " " .. seq[2] else local comma = options.dontTag and "," or '<span class="serial-comma">,</span>' conj = options.dontTag and ' ' .. conj .. " " or '<span class="serial-and"> ' .. conj .. '</span> ' return table.concat(seq, ", ", 1, length - 1) .. comma .. conj .. seq[length] end end --[[ Concatenates all values in the table that are indexed by a number, in order. sparseConcat{ a, nil, c, d } => "acd" sparseConcat{ nil, b, c, d } => "bcd" ]] function export.sparseConcat(t, sep, i, j) local list = {} local list_i = 0 for _, v in export.sparseIpairs(t) do list_i = list_i + 1 list[list_i] = v end return table.concat(list, sep, i, j) end --[[ Values of numberic keys in array portion of table are reversed: { "a", "b", "c" } -> { "c", "b", "a" } --]] function export.reverse(t) checkType("reverse", 1, t, "table") local new_t = {} local new_t_i = 1 for i = #t, 1, -1 do new_t[new_t_i] = t[i] new_t_i = new_t_i + 1 end return new_t end function export.reverseConcat(t, sep, i, j) return table.concat(export.reverse(t), sep, i, j) end -- { "a", "b", "c" } -> { a = 1, b = 2, c = 3 } function export.invert(array) checkType("invert", 1, array, "table") local map = {} for i, v in ipairs(array) do map[v] = i end return map end --[[ { "a", "b", "c" } -> { ["a"] = true, ["b"] = true, ["c"] = true } --]] function export.listToSet(t) checkType("listToSet", 1, t, "table") local set = {} for _, item in ipairs(t) do set[item] = true end return set end --[[ Returns true if all keys in the table are consecutive integers starting at 1. --]] function export.isArray(t) checkType("isArray", 1, t, "table") local i = 0 for _ in pairs(t) do i = i + 1 if t[i] == nil then return false end end return true end return export qngdifkzhm48c4ao05cne39capwc0ti 10 2991 8303 2022-07-22T10:01:53Z Rebel Agent 2678 Ke dirile template wikitext text/x-wiki <includeonly>{{safesubst:#invoke:languages/templates|getByCode|{{{1}}}|getCanonicalName}}</includeonly><noinclude> {{documentation}} </noinclude> ie1odf96p0hd3cw3do2bii2qoengusl 828 2992 8304 2022-07-22T10:04:18Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local export = {} function export.exists(frame) local args = frame.args local lang = args[1] or error("Language code has not been specified. Please pass parameter 1 to the module invocation.") lang = require("Module:languages").getByCode(lang) if lang then return "1" else return "" end end -- Used by the following JS: -- * [[WT:ACCEL]] -- * [[WT:EDIT]] -- * [[WT:NEC]] function export.getByCode(frame) local iparams = { [1] = {required = true}, [2] = {required = true}, [3] = {}, [4] = {}, [5] = {}, } local iargs = require("Module:parameters").process(frame.args, iparams) local langcode = iargs[1] local lang = require("Module:languages").getByCode(langcode, true) return require("Module:language-like").templateGetByCode(lang, iargs, function(itemname) local list if itemname == "getWikimediaLanguages" then list = lang:getWikimediaLanguages() elseif itemname == "getScripts" then list = lang:getScriptCodes() elseif itemname == "getAncestors" then list = lang:getAncestors() end if list then local index = iargs[3] index = tonumber(index) or error("Please specify the numeric index of the desired item.") local retval = list[index] if retval then if type(retval) == "string" then return retval else return retval:getCode() end else return "" end end if itemname == "transliterate" then local text = iargs[3] local sc = iargs[4] local module_override = iargs[5] sc = require("Module:scripts").getByCode(sc, 4) return lang:transliterate(text, sc, module_override) or "" elseif itemname == "makeEntryName" then local text = iargs[3] return lang:makeEntryName(text) or "" elseif itemname == "makeSortKey" then local text = iargs[3] return lang:makeSortKey(text) or "" elseif itemname == "countCharacters" then local text = args[3] or "" local sc = require("Module:scripts").getByCode(iargs[4], 4, "disallow nil") return sc:countCharacters(text) end end ) end function export.getByCanonicalName(frame) local args = frame.args local langname = args[1] or error("Language name has not been specified. Please pass parameter 1 to the module invocation.") local lang = require("Module:languages").getByCanonicalName(langname) if lang then return lang:getCode() else return "" end end function export.getByName(frame) local args = frame.args local langname = args[1] or error("Language name has not been specified. Please pass parameter 1 to the module invocation.") local lang = require("Module:languages").getByName(langname) if lang then return lang:getCode() else return "" end end function export.makeEntryName(frame) local args = frame.args local langname = args[1] or error("Language name has not been specified. Please pass parameter 1 to the module invocation.") local lang = require("Module:languages").getByCode(langname) if lang then return lang:makeEntryName(args[2]) else return "" end end function export.getCanonicalName(frame) local langCode, args if require("Module:yesno")(frame.args.parent) then args = frame:getParent().args else args = frame.args end langCode = args[1] if not langCode or langCode == "" then error("Supply a language code in parameter 1.") end return mw.loadData("Module:languages/code to canonical name")[langCode] or not args.return_if_invalid and "" or langCode end return export lw6ouppnon2ycbze4i1ulntb02ss8qf 828 2993 8305 2022-07-22T10:07:15Z Rebel Agent 2678 Ke dirile module Scribunto text/plain local export = {} -- Implementation of getOtherNames() for languages, etymology languages, -- families and scripts. If `onlyOtherNames` is passed in, only return -- the names in the `otherNames` field, otherwise combine `otherNames`, -- `aliases` and `varieties`. function export.getOtherNames(self, onlyOtherNames) local data if self._extraData then data = self._extraData else data = self._rawData end if onlyOtherNames then return data.otherNames or {} end -- Combine otherNames, aliases and varieties. First try to optimize and not create any -- new memory. This is possible if exactly one of the three exist, and if it's `varieties`, -- there are no nested lists in `varieties`. if data.otherNames and not data.aliases and not data.varieties then return data.otherNames elseif data.aliases and not data.otherNames and not data.varieties then return data.aliases elseif data.varieties and not data.otherNames and not data.aliases then local saw_table = false for _, name in ipairs(data.varieties) do if type(name) == "table" then saw_table = true break end end if not saw_table then return data.varieties end end -- Have to do it the "hard way". local ret = {} if data.otherNames then for _, name in ipairs(data.otherNames) do table.insert(ret, name) end end if data.aliases then for _, name in ipairs(data.aliases) do table.insert(ret, name) end end if data.varieties then for _, name in ipairs(data.varieties) do if type(name) == "table" then for _, n in ipairs(name) do table.insert(ret, n) end else table.insert(ret, name) end end end return ret end -- Implementation of getVarieties() for languages, etymology languages, -- families and scripts. If `flatten` is passed in, flatten down to a -- list of stings; otherwise, keep the structure. function export.getVarieties(self, flatten) local data if self._extraData then data = self._extraData else data = self._rawData end if data.varieties then -- If flattening not requested, just return them. if not flatten then return data.varieties end -- Check if no nested table; if so, just return the result. local saw_table = false for _, name in ipairs(data.varieties) do if type(name) == "table" then saw_table = true break end end if not saw_table then return data.varieties end -- At this point, we need to flatten the varieties. local ret = {} for _, name in ipairs(data.varieties) do if type(name) == "table" then for _, n in ipairs(name) do table.insert(ret, n) end else table.insert(ret, name) end end return ret else return {} end 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(item, args, extra_processing) -- The item that the caller wanted to look up local itemname = args[2] or error("Function to call (parameter 2) has not been specified.") local list if itemname == "getOtherNames" then list = item:getOtherNames() elseif itemname == "getOnlyOtherNames" then list = item:getOtherNames(true) 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 else error("The function \"" .. itemname .. "\" did not return a string value.") end end error("Requested invalid item name \"" .. itemname .. "\".") end return export 3jgkiy44irau7thwbogjol2d5vqovih