Module:links

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

Useful links: subpage list • links • transclusions • testcases • sandbox

This module provides many useful utility functions for creating and processing wikilinks within Wiktionary. It is used by the linking templates {{m}} and {{l}} through the functions in Module:links/templates.

Functions

export.getLinkPage

function export.getLinkPage(target, lang)

export.language_link

function export.language_link(data, allowSelfLink, dontLinkRecons)

export.format_link_annotations

function export.format_link_annotations(data, face)

export.full_link

function export.full_link(data, face, allowSelfLink, dontLinkRecons)

export.remove_links

function export.remove_links(text)

export.english_links

function export.english_links(text)

export.light_link

function export.light_link(data)

Changes

• 2013-09-13: Category:Terms with manual transliterations different from the automated ones and Category:Terms with redundant transliterations or their subcategories begin to be added
• 2018-03-08: ts (transcription) annotation added; accepted as field of table in first parameter of full_link and as field of table in second parameter of format_link_annotations, and as second parameter (itemType) of mark

Contents of data module

---

local export = {}

local ignore_cap = {
	["ko"] = true,
}

local phonetic_extraction = {
	["th"] = "Module:th"
}

local 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",
}

local unsupported_titles = mw.loadData("Module:links/unsupported titles")

function export.getLinkPage(target, lang)
	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("{{{", nil, true) then
		return nil
	end
	
	if target:find("^:") or target:find("^w:") or target:find("^wikipedia:") then
		return target
	end
	
	-- Remove diacritics from the page name
	target = lang:makeEntryName(target)
	
	-- Link to appendix for reconstructed terms and terms in appendix-only languages
	if target:find("^*.") then
		if lang:getCode() == "und" then
			return nil
		end
		
		target = "Reconstruction:" .. lang:getCanonicalName() .. "/" .. mw.ustring.sub(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, allowSelfLink)
	-- 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:find("^:") and not unsupported_titles[link.display] then
			link.display = link.display:gsub("^:", "")
		elseif link.display:find("^w:") then
			link.display = link.display:gsub("^w:", "")
		elseif link.display:find("^wikipedia:") then
			link.display = link.display:gsub("^wikipedia:", "")
		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, then return a "self-link" like the software does
	if not allowSelfLink and not id and (link.target == mw.title.getCurrentTitle().prefixedText or link.target == ":" .. 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.
	if not (link.target:find("^w:") or link.target:find("^wikipedia:")) then
		if link.fragment or mw.ustring.find(link.target, "#$") then
			require("Module:debug").track("links/fragment")
			require("Module:debug").track("links/fragment/" .. lang:getCode())
		end
		
		if not link.fragment and lang:getCode() ~= "und" then
			if id then
				link.fragment = lang:getCanonicalName() .. "-" .. id
			elseif not link.target:find("^Appendix:") and not link.target:find("^Reconstruction:") then
				link.fragment = lang:getCanonicalName()
			end
		end
	end
	
	-- This allows linking to pages like [[sms:a]] without it being treated weirdly.
	link.target = mw.ustring.gsub(link.target, ":", "&#x3a;")
	
	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 found, _, first, second
	
	found, _, first, second = mw.ustring.find(link.target, "^([^|]+)|(.+)$")
	
	if found then
		link.target = first
		link.display = second
	else
		link.display = link.target
	end
	
	found, _, first, second = mw.ustring.find(link.target, "^(.+)#(.+)$")
	
	if found then
		link.target = first
		link.fragment = second
	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, allowSelfLink, dontLinkRecons)
	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
	
	if ignore_cap[data.lang:getCode()] and text then
		text = mw.ustring.gsub(text, "%^", "")
	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")
		end
		
		if data.id then
			require("Module:debug").track("links/id-ignored")
		end
		
		-- Begins and ends with a wikilink tag
		if mw.ustring.find(text, "^%[%[(.+)%]%]$") then
			-- There are no [ ] in between.
			-- This makes the wikilink tag redundant.
			if mw.ustring.find(text, "^%[%[[^%[%]]+%]%]$") then
				require("Module:debug").track("links/redundant wikilink")
			else
				local temp = mw.ustring.gsub(text, "^%[%[(.+)%]%]$", "%1")
				temp = mw.ustring.gsub(temp, "%]%], %[%[", "|")
				
				if not mw.ustring.find(temp, "[%[%]]") then
					require("Module:debug").track("links/list")
				end
			end
		end
		
		text = mw.ustring.gsub(text, "%[%[([^%]]+)%]%]",
			function(linktext)
				local link = parseLink(linktext)
				
				if allReconstructed then
					link.target = "*" .. link.target
				end
				
				return makeLangLink(link, data.lang, data.id, allowSelfLink, dontLinkRecons)
			end
			)
		
		-- Remove the extra * at the beginning if it's immediately followed
		-- by a link whose display begins with * too
		if allReconstructed then
			text = mw.ustring.gsub(text, "^%*%[%[([^|%]]+)|%*", "[[%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, allowSelfLink, dontLinkRecons)
	end
	
	return text
end
	
local function mark(text, itemType, face)
	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="" class="tr mention-tr">', '</span>' }
		else
			tag = { '<span lang="" class="tr">', '</span>' }
		end
	elseif itemType == "annotations" then
		tag = { '<span class="mention-gloss-paren">(</span>', '<span class="mention-gloss-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 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
	if data.tr then
		table.insert(annotations, mark(data.tr, "tr", face))
	end
	
	-- Gloss/translation
	if data.gloss then
		table.insert(annotations, mark(data.gloss, "gloss"))
	end
	
	-- Part of speech
	if data.pos then
		table.insert(annotations, pos_tags[data.pos] or data.pos)
	end
	
	-- Literal/sum-of-parts meaning
	if data.lit then
		table.insert(annotations, "literally " .. mark(data.lit, "gloss"))
	end
	
	if #annotations > 0 then
		table.insert(output, " " .. 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, allowSelfLink, dontLinkRecons)
	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
	
	local m_utilities = require("Module:utilities")
	local m_scriptutils = require("Module:script utilities")
	
	-- 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)
		end
		
		-- Only make a link if the term has been given, otherwise just show the alt text without a link
		link = m_scriptutils.tag_text(data.term and export.language_link(data, allowSelfLink, dontLinkRecons) or data.alt, data.lang, data.sc, face)
		
		-- Replace space characters with newlines in Mongolian text, which is written top-to-bottom.
		if data.sc and data.sc:getDirection() == "down" then
			link = mw.ustring.gsub(
				link,
				"(|)([^%]]+)(%]%])",
				function(a, b, c)
					b = mw.ustring.gsub(b, "%s+", "<br>")
					return a .. b .. c
				end
			)
		end
	else
		--[[	No term to show.
				Is there at least a transliteration we can work from?	]]
		link = m_scriptutils.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("Latn", nil, true)) or data.sc:getCode() == "Latinx") then
		
		-- Try to generate a transliteration if necessary
		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
					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
		
			if (not manual_tr) or data.lang:overrideManualTranslit() then
				data.tr = automated_tr
			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
	
	annotations = export.format_link_annotations(data, face)
	
	table.insert(output, annotations)
	
	return table.concat(output) .. table.concat(categories)
end


-- Strips all square brackets out or replaces them.
function export.remove_links(text)
	if type(text) == "table" then text = text.args[1] end; if not text then text = "" end
	
	text = text:gsub("%[%[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")
	
	text = mw.ustring.gsub(text, "%[%[([^%]]+)%]%]",
		function(linktext)
			local link = parseLink(linktext)
			return makeLangLink(link, lang, nil, true, false)
		end
	)
	
	return text
end

function export.light_link(data)
	local language_names = mw.loadData("Module:languages/code to canonical name")
	local script_codes = mw.loadData("Module:scripts/codes")
	
	if data.langCode then
		data.langName = language_names[data.langCode] or error('The language code "' .. data.langCode .. '" is not recognized.')
	else
		error('Language code is required.')
	end
	
	if not data.term then
		error('Term to link to is required.')
	end
	
	if data.sc then
		if not script_codes[data.sc] then
			error('The script code "' .. data.sc .. '" is not recognized.')
		end
	end
	
	return '<span class="' .. data.sc .. '" lang="' .. data.langCode .. '">[[' .. data.term .. "#" .. data.langName .. "|" .. data.alt or data.term .. "]]</span>"
end

return export