Module:Wikidata label: Difference between revisions

From DataLib
Jump to navigation Jump to search
d>Ameisenigel
m (Reverted edits by Ameisenigel (talk) to last revision by Matěj Suchánek)
 
m (1 revision imported)
(No difference)

Revision as of 20:05, 24 May 2024

Documentation for this module may be created at Module:Wikidata label/doc

--[[
  __  __           _       _      __        ___ _    _     _       _          _       _          _
 |  \/  | ___   __| |_   _| | ___ \ \      / (_) | _(_) __| | __ _| |_ __ _  | | __ _| |__   ___| |
 | |\/| |/ _ \ / _` | | | | |/ _ (_) \ /\ / /| | |/ / |/ _` |/ _` | __/ _` | | |/ _` | '_ \ / _ \ |
 | |  | | (_) | (_| | |_| | |  __/_ \ V  V / | |   <| | (_| | (_| | || (_| | | | (_| | |_) |  __/ |
 |_|  |_|\___/ \__,_|\__,_|_|\___(_) \_/\_/  |_|_|\_\_|\__,_|\__,_|\__\__,_| |_|\__,_|_.__/ \___|_|

This module is intended to be the engine behind "Template:Label".
This module was copied from Commons please ask for changes there.

Please do not modify this code without applying the changes first at "Module:Wikidata label/sandbox" and testing
at "Module:Wikidata label/testcases".

Authors and maintainers:
* User:Jarekt - original version

]]

require('strict') -- used for debugging purposes as it detects cases of unintended global variables

--=============================================
--=== Internal functions ======================
--=============================================

---------------------------------------------------------------------------
-- Normalize input arguments by converting them all to lower case and
-- replacing space with "_" in the argument name. Also empty strings are
-- converted to nils. Arguments are collected from arguments passed to the
-- module and if missing from the template that calls the module
local function getArgs(frame)
	local function normalize_input_args(input_args, output_args)
		for name, value in pairs( input_args ) do
			value = mw.text.trim(value) -- trim whitespaces from the beggining and the end of the string
			if value ~= '' then -- nuke empty strings
				if type(name)=='string' then
					name = string.gsub( string.lower(name), ' ', '_')
				end
				output_args[name] = value
			end
		end
		return output_args
	end
	local args = {}
	args = normalize_input_args(frame:getParent().args, args)
	args = normalize_input_args(frame.args, args)
	return args
end

---------------------------------------------------------------------------
-- Function allowing for consistent treatment of boolean-like wikitext input.
-- It works similarly to Module:Yesno but does not assume val is a string
local function yesno(val, default)
	if type(val) == 'boolean' then
		return val
	elseif type(val) == 'number' then
		if val == 1 then
			return true
		elseif val == 0 then
			return false
		end
	elseif type(val) == 'string' then
		val = mw.ustring.lower(val)  -- put in lower case
		if val == 'no'  or val == 'n' or val == 'false' or val == '0' then
			return false
		elseif val == 'yes' or val == 'y' or val == 'true' or val == '1' then
			return true
		end
	end
	return default
end

-------------------------------------------------------------------------
-- get message in a given language
-- INPUTS:
-- * msg  - name of a message. For it to work [[MediaWiki:msg]] page need to be set up
-- * lang - translate message to language "lang"
-- * default - string to return in case this module is moved to a project where this message is not set
-- OUTPUT:
--  * translated message
local function getMessage(msg, lang, default)
	msg = mw.message.new(msg):inLanguage(lang):plain()
	return (msg == nil and default) or msg
end

---------------------------------------------------------------------------
-- use different sitelink call depending if you already have an entity or not
-- INPUTS:
--  * item and entity - entity id and entity: if full entity already uploded than use that
--                      otherwise use entity id to look up sitelink
--  * lang - language of the project
-- OUTPUT:
--  * sitelink
local function getSitelink(item, entity, lang)
	if entity and entity.getSitelink then -- if we have entity then use it
		return entity:getSitelink(lang .. 'wiki')
	else -- if no entity then use different function
		return mw.wikibase.getSitelink(item, lang .. 'wiki')
	end
end

---------------------------------------------------------------------------
-- use different sitelink call depending if you already have an entity or not
-- INPUTS:
--  * item and entity - entity id and entity: if full entity already uploded than use that
--                      otherwise use entity id to look up sitelink
--  * prop - property for which to return the best statment
-- OUTPUT:
--  * value of the best statment (only from the first one)
local function getBestStatementsValue(item, entity, prop)
	local statments
	if entity then
		statments = entity:getBestStatements(prop)
	else
		statments = mw.wikibase.getBestStatements(item, prop)
	end
	for _, statment in ipairs(statments) do
		if statment and statment.mainsnak.datavalue.value then
			return statment.mainsnak.datavalue.value
		end
	end
end

---------------------------------------------------------------------------
-- change capitalization of the label
-- INPUTS:
--  * label - label string
--  * capitalization - capitalization to be applied: allowed values are "lc",
--      "uc", "lcfirst", and "ucfirst". Any other value will return original string
--  * lang - language of the label
-- OUTPUT:
--  * value of the best statment (only from the first one)
local function apply_capitalization(label, capitalization, lang)
	capitalization = string.lower(capitalization or 'none')
	if capitalization == 'none' then
		return label
	elseif capitalization == 'uc' then
		return mw.ustring.upper(label)
	elseif capitalization == 'ucfirst' then
		return mw.language.new(lang):ucfirst(label)
	elseif capitalization == 'lc' then
		return mw.ustring.lower(label)
	elseif capitalization == 'lcfirst' then
		return mw.language.new(lang):lcfirst(label)
	end
	return label
end

--[[-------------------------------------------------------------------------
get link based on user preference
INPUTS:
* link_type - can be :
   * "wikidata" - link to wikidata
   * "wikipedia" - link to wikipedia (language dependent)
   * "wikidata talk" - link to wikidata talk page
   * "commons" - link to commons (try sitelink then commons category then commons gallery)
   * "commonscat" - link to commons (try commons category then commons gallery)
   * "-" - means no link
* item   - entity ID (always provided)
* entity - whole entity. It can be nil if whole entity is not loaded
* langList - language fallback list for preferred language (required)
OUTPUT:
* link - link to the wikimedia page
]]
local function getLink(link_type, item, entity, langList)
	local link, eLink
	link_type = mw.ustring.lower(link_type or '')
	local item_type = mw.ustring.sub(item, 1, 1) -- first letter prefix of item entity ID: 'Q', 'P' or 'M'
	if item_type == 'M' then
		eLink='c:Special:EntityPage/'..item
	elseif item_type == 'Q' then
		eLink='d:'..item -- wikibase entity page link
	elseif item_type == 'P' then
		eLink='d:Property:'..item -- wikibase entity page link
	else
		eLink='d:Special:EntityPage/'..item
	end
	if link_type == '-' then -- allow different link formats
		link = ''            -- no link
	elseif link_type == 'wikidata' or item_type == 'M' then
		link = eLink        -- link to wikibase entity page
	elseif link_type == 'wikidata talk' and item_type == 'P' then
		link = 'd:Property talk:'.. item        -- link to wikidata property talk page
	elseif link_type == 'wikidata talk' then
		link = 'd:Talk:'..item   -- link to wikidata talk page
	elseif link_type == 'commons' or link_type == 'commonscat' then
		--[[
		When link_type == 'commons' we try the following links (in specified order):
		  1) commons sitelink
		  2) P373 "Commons Category" claims
		  3) P935 "Commons Gallery"  claims
		Since most items have a commons sitelink we never have to look for claims
		When link_type == 'commonscat' we try to maximize chances of commons link being a category, so we
		      try the following links (in specified order):
		  1) commons sitelink, which is kept if it points to a category
		  2) P373 "Commons Category" claims
		  3) commons sitelink (which does not point to a category)
		  4) P935 "Commons Gallery"  claims
		Since most pages have a commons sitelink we never have to look for claims
		]]
		local sLink = getSitelink(item, entity, 'commons')  -- look for sitelink to commons
		if sLink then
			sLink = 'c:'..sLink
			if (link_type == 'commons') or (link_type == 'commonscat' and mw.ustring.find(sLink, 'Category:')) then
				link = sLink
			end
		end
		if not link then -- try linking to P373 "Commons Category"
			local cat = getBestStatementsValue(item, entity, 'P373')
			link = (cat ~= nil and 'c:Category:' .. cat) or nil
		end
		link = link or sLink
		if not link then -- try linking to P935 "Commons Gallery"
			link = getBestStatementsValue(item, entity, 'P935')
		end
	end
	if not link then -- apply default "Wikipedia" link type
		for _, language in ipairs(langList) do
			local sitelink = getSitelink(item, entity, language)
			if sitelink then
				link = 'w:'.. language ..':'.. sitelink
				break
			end
		end
	end
	return link or eLink  -- no wiki sitelink, so link to wikidata
end

--=============================================
--=== External functions ======================
--=============================================
local p = {}

--======================================================================
--=== API functions for use from other Scribunto modules ===============
--======================================================================

--[[
_getLabel

This function returns a label translated to desired language, created based on wikidata

Inputs:
	1: item - wikidata's item's q-id or entity class
	2: lang - desired language of the label
	3: link_type - link style. Possible values (case-insensitive): "wikipedia", "wikidata", "Commons", or "-" (no link)
	4: capitalization - can be "uc" (upper case), "lc" (lower case), "ucfirst" (upper case for the first letter),
			"lcfirst" (lower case for the first letter), or 'none' (default)

Error Handling:
	Bad q-id will result in displayed error
]]
function p._getLabel(item, lang, link_type, capitalization, show_id)
	local entity, s, link, label, language

	-- clean up the input parameters
	if type(item) ~= 'string' then -- "item" is not a q-id
		entity = item            -- "item" must be the entity
		item   = entity.id       -- look-up q-id
	elseif tonumber(item) then   -- if it is just the number then add "Q" in front
		item = 'Q'..item
	end
	item = mw.ustring.gsub(mw.ustring.upper(item), 'PROPERTY:P', 'P') -- make all the properties the same and capitalize

	if not lang then
		label, lang = mw.wikibase.getLabelWithLang(item)
	end
	if not lang then -- if still no language
		lang  = mw.getCurrentFrame():callParserFunction("int","lang")  -- get user's chosen language
		label = nil
	end

	-- build language fallback list
	lang = mw.ustring.lower(lang)
	local langList = mw.language.getFallbacksFor(lang)
	table.insert(langList, 1, lang)

	-- get label (visible part of the link)
	if not label then
		for _, language in ipairs(langList) do  -- loop over language fallback list looking for label in the specific language
			if entity then
				label = entity:getLabel(language)
			else
				label = mw.wikibase.getLabelByLang(item, language)
			end
			if label then break end                    -- label found and we are done
		end
	end
	if label then  -- wikitext-escape the label if we have one
		label = mw.text.nowiki(label)
	end
	if not label then                              -- no labels found, so just show the q-id
		label = item
	elseif show_id then           -- add id
		show_id = yesno(show_id,false)
		if show_id then
			local wordsep = getMessage('Word-separator', lang, ' ')
			local id = mw.message.new('parentheses', item):inLanguage(lang):plain()
			id = (id~=nil and id) or ('('..item..')') -- in case this module is moved to a project where {{int:parenthesis}} is not set
			label = label .. wordsep .. "<small>" .. id .. "</small>"
		end
	end
	label = apply_capitalization(label, capitalization, lang)

	-- return the results
	if link_type == '-' then
		return label -- return just the label
	else
		link = getLink(link_type, item, entity, langList)
		return '[[' .. link .. '|' .. label .. ']]' -- return link
	end
end

--[[-------------------------------------------------------------------------------
_sitelinks

This function returns a table of sitelinks for a single project organized by language

Inputs:
	1: item - wikidata's item's q-id or entity class
	2: project - (case-insensitive) one of: "wikipedia", "wikisource", "wikiquote", "wikibooks", "wikinews",
			"wikiversity", "wikivoyage", "wiktionary", "commons", "mediawiki", "wikispecies", "wikidata", etc.

Output:
	Table of sitelinks with language fields

Output:
	Table of sitelinks with language fields
See also
* [https://foundation.wikimedia.org/wiki/Special:SiteMatrix] for the full list of supported interwikis.
* [https://dumps.wikimedia.org/backup-index.html] for the full list of sitecodes (used in database dumps).
]]
function p._sitelinks(item, project)
	local entity, sitelink
	-- get entity
	if type(item) == 'string' then -- "item" is a q-id
		entity = mw.wikibase.getEntity(item)
	else
		entity = item              -- "item" is the entity
	end

	-- convert from english project name  to proproject code
	local projLUT = {
		wikipedia   = 'wiki',           commons   = 'commonswiki',
		foundation  = 'foundationwiki', mediawiki = 'mediawikiwiki',
		wikispecies = 'specieswiki',    wikidata  = 'wikidatawiki',
		incubator   = 'incubatorwiki',	oldwikisource = 'sourceswiki',
	}
	local langLUT = {
		-- These are not language codes before the 'wiki' or 'wikiversity' suffix in a sitecode:
		foundation = '~', commons = '~',	-- they will be skipped
		incubator  = '~', meta    = '~',
		mediawiki  = '~', sources = '~',
		species    = '~', beta    = '~',
		-- Legacy language codes used in sitecodes, remapped to standard Wikimedia language codes:
		-- See https://meta.wikimedia.org/wiki/Special_language_codes for details
		als     = 'gsw', bat_smg      = 'sgs',
		fiu_vro = 'vro', be_x_old     = 'be-tarask',
		roa_rup = 'rup', zh_classical = 'lzh',
		zh_yue  = 'yue', zh_min_nan   = 'nan',
		zh_wuu  = 'wuu', no           = 'nb',
	}
	project = project:lower()
	project = projLUT[project] or project -- correct the project name
	local n = project:len()
	local linkTable = {}
	if entity and entity.sitelinks then  -- See if entity exists, and that it has sitelinks
		for _, sitelink in pairs(entity.sitelinks) do -- loop over all sitelinks
			local site = sitelink.site
			local m    = site:len() - n
			local proj = site:sub(m +1)  -- project part of the siteID
			if proj == project  then -- proj matches desired "project"
				local lang = site:sub(1, m)  -- language part of the siteID
				lang = langLUT[lang] or lang:gsub('_','-')
				if lang ~= '~' then -- proj matches desired "project"
					linkTable[lang] = sitelink.title
				end
			end
		end
	end
	return linkTable
end

--[[----------------------------------------------------------------
_aliases

This function returns a table of aliases for a single language

Inputs:
	1: item - wikidata's item's q-id or entity class
	2: lang - language code, like 'en' or 'de'

Output:
	Table of aliases with language fields
]]
function p._aliases(item, lang)
	local entity
	if type(item) == 'string' then -- "item" is a q-id
		entity = mw.wikibase.getEntity(item)
	else
		entity = item            -- "item" is the entity
	end
	local aliasTable = {}
	if entity and entity.aliases then						-- See if there is an entity and that is has aliases
		if entity.aliases[lang] then						-- See if it has English Aliases
			for _, alias in pairs(entity.aliases[lang]) do  -- Make a loop around the English aliases
				table.insert(aliasTable, alias.value)				-- Create a table of English aliases
			end
		end
	end
	return aliasTable
end

--======================================================================
--=== Invoke functions for use from wikitext, e.g., templates ==========
---=====================================================================

--[[
getLabel

This function returns a label translated to desired language, created based on wikidata

Usage:
{{#invoke:Wikidata label|getLabel|item=Q...|lang=..|link_style=..|capitalization=..}}

Parameters
	1: wikidata's item's q-id (required)
	2: language (optional; default {{int:lang}})
	3: link_style: "wikipedia" (default), "Wikidata", "Commons", or "-" (no link)
	4: capitalization - can be "uc", "lc", "ucfirst", "lcfirst"

Error Handling:
	Bad q-id will result in displayed error
]]
function p.getLabel(frame)
	local args = getArgs(frame)
	return p._getLabel(args.item, args.lang, args.link, args.capitalization, args.show_id)
end

--[[-------------------------------------------------------------------------------
sitelinks

This function returns a comma separated list of sitelinks for a single project organized by language
Its main purpose is to help with testing of _sitelinks function.

Usage:
{{#invoke:Wikidata label|sitelinks|item=Q...|project=..}}

Inputs:
	1: item - wikidata's item's q-id or entity class
	2: project - "wikipedia" (or "wiki"), "wikisource", "wikiquote", "wikibooks",
	             "wikinews", "wikiversity", "wikivoyage", "wiktionary", etc.

Output:
	comma separated list
]]
function p.sitelinks(frame)
	local args = getArgs(frame)
	local sitelinks = p._sitelinks(args.item, args.project)
	local sitelinkList = {}
	for lang, sitelink in pairs(sitelinks) do
		table.insert(sitelinkList, (lang=='' and sitelink) or (lang .. ':' .. sitelink))
	end
	return table.concat(sitelinkList, ', ')
end

--[[----------------------------------------------------------------------------
aliases

This function returns a comma separated list of aliases for a single language
Its main purpose is to help with testing of _aliases function.

Usage:
{{#invoke:Wikidata label|aliases|item=Q...|lang=..}}

Inputs:
	1: item - wikidata's item's q-id or entity class
	2: lang - language code, like 'en' or 'de'

Output:
	Comma separated list of aliases
]]
function p.aliases(frame)
	local args = getArgs(frame)
	return table.concat(p._aliases(args.item, args.lang), ', ')
end

return p