Module:Utilities

The following documentation is located at Module:Utilities/documentation. ^[edit]

Useful links: subpage list • transclusions • testcases • sandbox

This module exports various general utility functions, which can be used by other modules.

pattern_escape

pattern_escape(text)

Escapes the magic characters used in patterns (Lua's version of regular expressions). For example, "^$()%.[]*+-?" becomes "%^%$%(%)%%%.%[%]%*%+%-%?".

format_categories

format_categories(categories, lang, sort_key, sort_base, force_output)

Formats a list (table) of category names. The output is a string consisting of all categories with [[Category:...]] applied to each one, and the given sort key added. If the namespace is not the main, Appendix or Reconstruction namespaces, the output will be an empty string unless force_output is given. If no sort key is given:

1. A default one is generated by using sort_base (if given) or the current subpage name, and by removing hyphens from the beginning (so that suffixes can be sorted without a key).
2. If a sort key is available for the given language, it is then used to create a sort key that follows the rules for that language.
3. If the final sort key ends up being identical to the page name (which is the default sort key used by the software), then it is omitted entirely, so that it can be used in combination with DEFAULTSORT.

template_categorize

{{#invoke:utilities|template_categorize}}

This function is used by the {{categorize}}, {{catlangname}} and {{catlangcode}} templates.

catfix

This function adds a "catfix", which is used on language-specific category pages to add language attributes and often script classes to all entry names. The addition of language attributes and script classes makes the entry names display better (using the language- or script-specific styles specified in MediaWiki:Common.css), which is particularly important for non-English languages that do not have consistent font support in browsers.

Language attributes are added for all languages, but script classes are only added for languages with one script listed in their data file, or for languages that have a default script listed in the catfix_script list in Module:utilities/data. Some languages clearly have a default script, but still have other scripts listed in their data file and therefore need their default script to be specified. Others do not have a default script.

• Serbo-Croatian is regularly written in both the Latin and Cyrillic scripts. Because it uses two scripts, Serbo-Croation cannot have a script class applied to entries in its category pages, as only one script class can be specified at a time.

• Russian is usually written in the Cyrillic script (Cyrl), but Braille (Brai) is also listed in its data file. So Russian needs an entry in the catfix_script list, so that the Cyrl (Cyrillic) script class will be applied to entries in its category pages.

To find the scripts listed for a language, go to Module:languages and use the search box to find the data file for the language. To find out what a script code means, search the script code in Module:scripts/data

---

local decode = mw.text.decode
local u = mw.ustring.char

local data = mw.loadData("Module:utilities/data")
local notneeded = data.notneeded
local neededhassubpage = data.neededhassubpage

local export = {}

function export.require_when_needed(text)
	return setmetatable({}, {
		__index = function(t, k)
			t = require(text)
			return t[k]
		end,
		__call = function(t, ...)
			t = require(text)
			return t(...)
		end
	})
end

-- A helper function to escape magic characters in a string.
-- Magic characters: ^$()%.[]*+-?
function export.pattern_escape(text)
	if type(text) == "table" then
		text = text.args[1]
	end
	return (text:gsub("[%^$()%%.[%]*+%-?]", "%%%0"))
end

-- A helper function to resolve HTML entities into plaintext.
-- Iterates over entities in a string, and decodes them into plaintext. We use iteration (instead of decoding the whole string in one go) because it means we can avoid loading the lookup string unnecessarily, as it uses more memory.
local entities
function export.get_entities(text)
	return (text:gsub("&(#?[%w]-);", function(entity)
		-- Check if mw.text.decode is able to decode the entity.
		if (
			entity == "lt" or
			entity == "gt" or
			entity == "amp" or
			entity == "quot" or
			entity == "nbsp"
		) then
			return decode("&" .. entity .. ";")
		-- Catch hex entities beginning with &#X, which are valid but unsupported by mw.text.decode.
		elseif entity:sub(1, 1) == "#" then
			entity = entity:lower()
			return decode("&" .. entity .. ";")
		-- [[Module:utilities/data/entities]] is a lookup string of every named HTML entity (except the ones listed above), as they aren't covered by mw.text.decode.
		-- mw.text.decode can decode lots of named entities if the second parameter is true, but around 600 are still not covered, and it's less efficient than doing it this way anyway.
		else
			entities = entities or require("Module:utilities/data/entities")
			return entities:match("%f[%Z]" .. entity .. "(%Z+)")
		end
	end))
end

-- A helper function to convert plaintext into HTML entities where these match the characters given in set.
-- By default, this resolves any pre-existing entities into plaintext first, to allow mixed input and to avoid accidental double-conversion. This can be turned off with the raw parameter.
function export.make_entities(text, set, raw)
	text = not raw and export.get_entities(text) or text
	return mw.text.encode(text, set)
end

-- A helper function to strip wiki markup, giving the plaintext of what is displayed on the page.
function export.get_plaintext(text)
	text = text
		:gsub("%[%[", "\1")
		:gsub("%]%]", "\2")
	
	-- Remove strip markers and HTML tags.
	text = mw.text.unstrip(text)
		:gsub("<[^<>\1\2]+>", "")
		
	-- Parse internal links for the display text, and remove categories.
	text = require("Module:links").remove_links(text)
	
	-- Remove files.
	for _, falsePositive in ipairs({"File", "Image"}) do
		text = text:gsub("\1" .. falsePositive .. ":[^\1\2]+\2", "")
	end

	-- Parse external links for the display text.
	text = text:gsub("%[(https?://[^%[%]]+)%]",
		function(capture)
			return capture:match("https?://[^%s%]]+%s([^%]]+)") or ""
		end)
	
	text = text
		:gsub("\1", "[[")
		:gsub("\2", "]]")
	
	-- Any remaining square brackets aren't involved in links, but must be escaped to avoid creating new links.
	text = text:gsub("[%[%]]", mw.text.nowiki)
		
	-- Strip bold, italics and soft hyphens.
	text = text
		:gsub("('*)'''(.-'*)'''", "%1%2")
		:gsub("('*)''(.-'*)''", "%1%2")
		:gsub("­", "")
	
	-- Get any HTML entities.
	-- Note: don't decode URL percent encoding, as it shouldn't be used in display text and may cause problems if % is used.
	text = export.get_entities(text)
	
	return mw.text.trim(text)
end

function export.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, nil, "utilities", "plain_gsub")
			
			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 = export.pattern_escape(pattern)
	
	local gsub = require("Module:string utilities").gsub
	if invoked then
		return (gsub(text, pattern, replacement))
	else
		return gsub(text, pattern, replacement)
	end
end

--[[
Format the categories with the appropriate sort key. CATEGORIES is a list of
categories.
	-- LANG is an object encapsulating a language; if nil, the object for
	   language code 'und' (undetermined) will be used.
	-- SORT_KEY is placed in the category invocation, and indicates how the
	   page will sort in the respective category. Normally this should be nil,
	   and a default sort key based on the subpage name (the part after the
	   colon) will be used.
	-- SORT_BASE lets you override the default sort key used when SORT_KEY is
	   nil. Normally, this should be nil, and a language-specific default sort
	   key is computed from the subpage name (e.g. for Russian this converts
	   Cyrillic ё to a string consisting of Cyrillic е followed by U+10FFFF,
	   so that effectively ё sorts after е instead of the default Wikimedia
	   sort, which (I think) is based on Unicode sort order and puts ё after я,
	   the last letter of the Cyrillic alphabet.
	-- FORCE_OUTPUT forces normal output in all namespaces. Normally, nothing
	   is output if the page isn't in the main, Appendix:, Reconstruction: or
	   Citations: namespaces.
	-- SC is a script object; if nil, the default will be used from the sort
	   base.
]]
function export.format_categories(categories, lang, sort_key, sort_base, force_output, sc)
	if type(lang) == "table" and not lang.getCode then
		error("The second argument to format_categories should be a language object.")
	end

	local title_obj = mw.title.getCurrentTitle()	
	local allowedNamespaces = {
		[0] = true, [100] = true, [114] = true, [118] = true -- (main), Appendix, Citations, Reconstruction
	}

	if force_output or allowedNamespaces[title_obj.namespace] or title_obj.prefixedText == "Wiktionary:Sandbox" then
		local headword_data = mw.loadData("Module:headword/data")
		local pagename = headword_data.pagename
		local pagename_defaultsort = headword_data.pagename_defaultsort
		
		-- Generate a default sort key.
		if sort_key ~= "-" then
			if not lang then
				lang = require("Module:languages").getByCode("und")
			end
			sort_base = (lang:makeSortKey(sort_base or pagename, sc))
			if sort_key and sort_key ~= "" then
				-- Gather some statistics regarding sort keys
				if not no_track and sort_key:uupper() == sort_base then
					table.insert(categories, "Sort key tracking/redundant")
				end
			else
				sort_key = sort_base
			end
			-- If the sort key is empty, remove it.
			if sort_key == "" then
				sort_key = nil
			end
		-- If the sort key is "-", bypass the process of generating a sort key altogether. This is desirable when categorising (e.g.) translation requests, as the pages to be categorised are always in English/Translingual.
		else
			sort_key = sort_base and sort_base:uupper() or pagename_defaultsort
		end
		
		local out_categories = {}
		for key, cat in ipairs(categories) do
			out_categories[key] = "[[Category:" .. cat .. (sort_key and "|" .. sort_key or "") .. "]]"
		end
		
		return table.concat(out_categories, "")
	else
		return ""
	end
end

function export.catfix(lang, sc)
	if not lang then
		require("Module:debug").track("catfix/no lang")
		return nil
	elseif type(lang) ~= "table" then
		require("Module:debug").track("catfix/lang not table")
		return nil
	end
	local canonicalName = lang:getCanonicalName() or error('The first argument to the function "catfix" should be a language object from Module:languages.')
	
	if sc and not sc.getCode then
		error('The second argument to the function "catfix" should be a script object from Module:scripts.')
	end
	
	-- To add script classes to links on pages created by category boilerplate templates.
	if not sc then
		sc = data.catfix_scripts[lang:getCode()]
		if sc then
			sc = require("Module:scripts").getByCode(sc)
		end
	end
	
	return "<span id=\"catfix\" style=\"display:none;\" class=\"CATFIX-" .. mw.uri.anchorEncode(canonicalName) .. "\">" ..
		require("Module:script utilities").tag_text("&nbsp;", lang, sc, nil) ..
		"</span>"
end

function export.catfix_template(frame)
	local params = {
		[1] = {},
		[2] = { alias_of = "sc" },
		["sc"] = {},
	}
	
	local args = require("Module:parameters").process(frame:getParent().args, params, nil, "utilities", "catfix_template")
	
	local lang = require("Module:languages").getByCode(args[1]) or require("Module:languages").err(args[1], 1)
	
	local sc = args.sc
	if sc then
		sc = require("Module:scripts").getByCode(sc) or error('The script code "' .. sc .. '", provided in the second parameter, is not valid.')
	end
	
	return export.catfix(lang, sc)
end

-- Not exporting because it is not used yet.
local function getDateTense(frame) 
	local name_num_mapping = {["January"] = 1, ["February"] = 2, ["March"] = 3, ["April"] = 4, ["May"] = 5, ["June"] = 6, 
		["July"] = 7, ["August"] = 8, ["September"] = 9, ["October"] = 10, ["November"] = 11, ["December"] = 12, 
		[1] = 1, [2] = 2, [3] = 3, [4] = 4, [5] = 5, [6] = 6, [7] = 7, [8] = 8, [9] = 9, [10] = 10, [11] = 11, [12] = 12}
	local month = name_num_mapping[frame.args[2]]
	local date = os.time({year = frame.args[1], day = frame.args[3], month = month})
	local today = os.time() -- 12 AM/PM
	local diff = os.difftime(date, today)
	local daylength = 24 * 3600
	
	if diff < -daylength / 2 then return "past"
	else 
		if diff > daylength / 2  then return "future"
		else return "present" end
	end
end

function export.make_id(lang, str)
	--[[	If called with invoke, first argument is a frame object.
			If called by a module, first argument is a language object. ]]
	local invoked = false
	
	if type(lang) == "table" then
		if lang.args then
			invoked = true
			
			local frame = lang
			
			local params = {
				[1] = {},
				[2] = {},
			}
			
			local args = require("Module:parameters").process(frame:getParent().args, params, nil, "utilities", "make_id")
			
			local langCode = args[1]
			str = args[2]
			
			local m_languages = require("Module:languages")
			
			lang = m_languages.getByCode(langCode) or m_languages.err(langCode, 1)
		elseif not lang.getCanonicalName then
			error("The first argument to make_id should be a language object.")
		end
	end

	if not ( type(str) == "string" or type(str) == "number" ) then
		error("The second argument to make_id should be a string or a number.")
	end
	
	local id = require("Module:senseid").anchor(lang, str)
	
	if invoked then
		return '<li class="senseid" id="' .. id .. '">'
	else
		return id
	end
end

-- Given a type (as a string) and an arbitrary number of entities, checks whether all of those entities are language, family, script, writing system or Wikimedia language objects. Useful for error handling in functions that require one of these kinds of object.
-- If noErr is set, the function returns false instead of throwing an error, which allows customised error handling to be done in the calling function.
function export.check_object(typ, noErr, ...)
	local function fail(message)
		if noErr then
			return false
		else
			error(message, 3)
		end
	end
	
	local objs = {...}
	if #objs == 0 then
		return fail("Must provide at least one object to check.")
	end
	for _, obj in ipairs{...} do
		if type(obj) ~= "table" or type(obj.hasType) ~= "function" then
			return fail("Function expected a " .. typ .. " object, but received a " .. type(obj) .. " instead.")
		elseif not (typ == "object" or obj:hasType(typ)) then
			for _, wrong_type in ipairs{"family", "language", "script", "Wikimedia language", "writing system"} do
				if obj:hasType(wrong_type) then
					return fail("Function expected a " .. typ .. " object, but received a " .. wrong_type .. " object instead.")
				end
			end
			return fail("Function expected a " .. typ .. " object, but received another type of object instead.")
		end
	end
	return true
end

return export