Module:WikitextParser - Revision history

Aidan9382: Slightly improve getXYZAttribute when getting string-wrapped content (this should allow cases like to capture name, though other cases like \-escaped quotes will still break)

2025-05-09T18:28:23Z

Slightly improve getXYZAttribute when getting string-wrapped content (this should allow cases like <ref name="xyz's abc"> to capture name, though other cases like \-escaped quotes will still break)

← Previous revision		Revision as of 18:28, 9 May 2025
Line 245:		Line 245:
	-- @return Value of the attribute or nil if not found		-- @return Value of the attribute or nil if not found
	function WikitextParser.getTagAttribute( tagWikitext, attribute )		function WikitextParser.getTagAttribute( tagWikitext, attribute )
	~~return~~ string.match( tagWikitext, '^<[^/>]' .. attribute .. ' = *["\']?([^~~"\'~~/>]+)~~["\']?~~[ />]' )		local _quote, value = string.match( tagWikitext, '^<[^/>]' .. attribute .. ' = *(["\']?)([^/>]-)%1[ />]' )
			return value
	end		end

Line 319:		Line 320:
	-- @param tableWikitext Required. Wikitext of the table to parse.		-- @param tableWikitext Required. Wikitext of the table to parse.
	-- @param attribute Required. Name of the attribute.		-- @param attribute Required. Name of the attribute.
	-- @return Value of the attribute or nil is not found		-- @return Value of the attribute or nil if not found
	function WikitextParser.getTableAttribute( tableWikitext, attribute )		function WikitextParser.getTableAttribute( tableWikitext, attribute )
	~~return~~ string.match( tableWikitext, '^{\|[^\n]' .. attribute .. ' = ["\']?([^~~"\'~~\n]+)~~["\']?~~[^\n]\n' )		local _quote, value = string.match( tableWikitext, '^{\|[^\n]' .. attribute .. ' = (["\']?)([^\n]-)%1[^\n]\n' )
			return value
	end		end

Aidan9382: singificantly improve the performance of getTagAttribute (prevent the .- from trying to scan everything after the opening tag when the attribute isn't present) (also just simplified it in general to avoid repeated ambiguous captures)

2025-05-09T18:18:14Z

singificantly improve the performance of getTagAttribute (prevent the .- from trying to scan everything after the opening tag when the attribute isn't present) (also just simplified it in general to avoid repeated ambiguous captures)

← Previous revision		Revision as of 18:18, 9 May 2025
Line 245:		Line 245:
	-- @return Value of the attribute or nil if not found		-- @return Value of the attribute or nil if not found
	function WikitextParser.getTagAttribute( tagWikitext, attribute )		function WikitextParser.getTagAttribute( tagWikitext, attribute )
	return string.match( tagWikitext, '^< ~~.- ~~[^/>]' .. attribute .. ' = *["\']?([^"\'/>]+)["\']?[ />]' )		return string.match( tagWikitext, '^<[^/>]' .. attribute .. ' = *["\']?([^"\'/>]+)["\']?[ />]' )
	end		end

Sophivorus at 14:16, 9 May 2025

2025-05-09T14:16:51Z

← Previous revision		Revision as of 14:16, 9 May 2025
Line 307:		Line 307:
	local tables = {}		local tables = {}
	wikitext = '\n' .. wikitext		wikitext = '\n' .. wikitext
	for t in string.gmatch( ~~gmatch~~, '\n%b{}' ) do		for t in string.gmatch( wikitext, '\n%b{}' ) do
	if string.sub( t, 1, 3 ) == '\n{\|' then		if string.sub( t, 1, 3 ) == '\n{\|' then
	t = mw.text.trim( t ) -- exclude the leading newline		t = mw.text.trim( t ) -- exclude the leading newline

Sophivorus: Make string calls explicit for easier debugging

2025-05-09T14:15:50Z

Make string calls explicit for easier debugging

Show changes

Sophivorus: Refine paragraph matching

2025-05-08T13:55:56Z

Refine paragraph matching

← Previous revision		Revision as of 13:55, 8 May 2025
Line 88:		Line 88:
	-- Remove non-paragraphs		-- Remove non-paragraphs
	wikitext = '\n' .. wikitext .. '\n'		wikitext = '\n' .. wikitext .. '\n'
	wikitext = wikitext:gsub( '\n[#][^\n]', '' ) -- remove lists		wikitext = wikitext:gsub( '\n[#][^\n]', '\n' ) -- remove lists
	wikitext = wikitext:gsub( '\n%[%b[]%]\n', '' ) -- remove files and categories		wikitext = wikitext:gsub( '\n%[%b[]%]\n', '\n' ) -- remove files and categories
	wikitext = wikitext:gsub( '\n%b{} *\n', '\n%0\n' ) -- add spacing between tables and block templates		wikitext = wikitext:gsub( '\n%b{} *\n', '\n%0\n' ) -- add spacing between tables and block templates
	wikitext = wikitext:gsub( '\n%b{} *\n', '\n' ) -- remove tables and block templates		wikitext = wikitext:gsub( '\n%b{} *\n', '\n' ) -- remove tables and block templates

Sophivorus: Fix getTagAttribute

2025-05-08T12:35:28Z

Fix getTagAttribute

← Previous revision		Revision as of 12:35, 8 May 2025
Line 245:		Line 245:
	-- @return Value of the attribute or nil if not found		-- @return Value of the attribute or nil if not found
	function WikitextParser.getTagAttribute( tagWikitext, attribute )		function WikitextParser.getTagAttribute( tagWikitext, attribute )
	return tagWikitext:match( '^< .- [^/>]' .. attribute .. ' = *["\']?([^"\'>]+)["\']?[ />]' )		return tagWikitext:match( '^< .- [^/>]' .. attribute .. ' = *["\']?([^"\'/>]+)["\']?[ />]' )
	end		end

Sophivorus: Code style

2025-03-25T15:27:22Z

Code style

← Previous revision		Revision as of 15:27, 25 March 2025
Line 344:		Line 344:
	local tableData = {}		local tableData = {}
	tableWikitext = mw.text.trim( tableWikitext );		tableWikitext = mw.text.trim( tableWikitext );
	tableWikitext = ~~string.~~gsub( ~~tableWikitext,~~ '^{\|.-\n', '' ) -- remove the header		tableWikitext = tableWikitext:gsub( '^{\|.-\n', '' ) -- remove the header
	tableWikitext = ~~string.~~gsub( ~~tableWikitext,~~ '\n\|}$', '' ) -- remove the footer		tableWikitext = tableWikitext:gsub( '\n\|}$', '' ) -- remove the footer
	tableWikitext = ~~string.~~gsub( ~~tableWikitext,~~ '^\|%+.-\n', '' ) -- remove any caption		tableWikitext = tableWikitext:gsub( '^\|%+.-\n', '' ) -- remove any caption
	tableWikitext = ~~string.~~gsub( ~~tableWikitext,~~ '\|%-.-\n', '\|-\n' ) -- remove any row attributes		tableWikitext = tableWikitext:gsub( '\|%-.-\n', '\|-\n' ) -- remove any row attributes
	tableWikitext = ~~string.~~gsub( ~~tableWikitext,~~ '^\|%-\n', '' ) -- remove any leading empty row		tableWikitext = tableWikitext:gsub( '^\|%-\n', '' ) -- remove any leading empty row
	tableWikitext = ~~string.~~gsub( ~~tableWikitext,~~ '\n\|%-$', '' ) -- remove any trailing empty row		tableWikitext = tableWikitext:gsub( '\n\|%-$', '' ) -- remove any trailing empty row
	for rowWikitext in mw.text.gsplit( ~~tableWikitext,~~ '\|-', true ) do		for rowWikitext in mw.text.gsplit( '\|-', true ) do
	local rowData = {}		local rowData = {}
	rowWikitext = ~~string.~~gsub( ~~rowWikitext,~~ '\|\|', '\n\|' )		rowWikitext = rowWikitext:gsub( '\|\|', '\n\|' )
	rowWikitext = ~~string.~~gsub( ~~rowWikitext,~~ '!!', '\n\|' )		rowWikitext = rowWikitext:gsub( '!!', '\n\|' )
	rowWikitext = ~~string.~~gsub( ~~rowWikitext,~~ '\n!', '\n\|' )		rowWikitext = rowWikitext:gsub( '\n!', '\n\|' )
	rowWikitext = ~~string.~~gsub( ~~rowWikitext,~~ '^!', '\n\|' )		rowWikitext = rowWikitext:gsub( '^!', '\n\|' )
	rowWikitext = ~~string.~~gsub( ~~rowWikitext,~~ '^\n\|', '' )		rowWikitext = rowWikitext:gsub( '^\n\|', '' )
	for cellWikitext in mw.text.gsplit( rowWikitext, '\n\|' ) do		for cellWikitext in mw.text.gsplit( rowWikitext, '\n\|' ) do
	cellWikitext = mw.text.trim( cellWikitext )		cellWikitext = mw.text.trim( cellWikitext )

Sophivorus: Refine getTags

2025-03-25T15:20:33Z

Refine getTags

← Previous revision		Revision as of 15:20, 25 March 2025
Line 215:		Line 215:
	tag = wikitext:sub( tagStart, tagEnd )		tag = wikitext:sub( tagStart, tagEnd )

	-- Else we're in tag that shouldn't contain others like it, like <math> or <strong>		-- Else we're probably in tag that shouldn't contain others like it, like <math> or <strong>
	else		else
	tagEnd = wikitext:match( '</ ?' .. tagName .. ' ?>()', tagStart ) ~~- 1~~		tagEnd = wikitext:match( '</ ?' .. tagName .. ' ?>()', tagStart )
	tag = wikitext:sub( tagStart, tagEnd )		if tagEnd then
			tag = wikitext:sub( tagStart, tagEnd - 1 )

			-- If no end tag is found, assume we matched something that wasn't a tag, like <no. 1>
			else
			tag = nil
			end
	end		end
	table.insert( tags, tag )		table.insert( tags, tag )

Sophivorus: Refine getTags

2025-03-25T14:56:20Z

Refine getTags

← Previous revision		Revision as of 14:56, 25 March 2025
Line 184:		Line 184:
	local tags = {}		local tags = {}
	local tag, tagName, tagEnd		local tag, tagName, tagEnd
			-- Don't match closing tags like </div>, comments like <!--foo-->, comparisons like 1<2 or things like <3
	for tagStart, tagOpen in wikitext:gmatch( '()(<[^/!].->)' ) do		for tagStart, tagOpen in wikitext:gmatch( '()(<[^/!%d].->)' ) do
	tagName = WikitextParser.getTagName( tagOpen )		tagName = WikitextParser.getTagName( tagOpen )

Line 226:		Line 227:
	-- Get the name of the tag in the given wikitext		-- Get the name of the tag in the given wikitext
	-- @param tag Required. Tag to parse.		-- @param tag Required. Tag to parse.
	-- @return Name of the tag ~~(in lowercase)~~ or nil if not found		-- @return Name of the tag or nil if not found
	function WikitextParser.getTagName( tagWikitext )		function WikitextParser.getTagName( tagWikitext )
	local tagName = tagWikitext:match( '^< *(.-)[ />]' )		local tagName = tagWikitext:match( '^< *(.-)[ />]' )

Sophivorus at 14:35, 25 March 2025

2025-03-25T14:35:41Z

← Previous revision		Revision as of 14:35, 25 March 2025
Line 184:		Line 184:
	local tags = {}		local tags = {}
	local tag, tagName, tagEnd		local tag, tagName, tagEnd
	for tagStart, tagOpen in wikitext:gmatch( '()(<[^/].->)' ) do		for tagStart, tagOpen in wikitext:gmatch( '()(<[^/!].->)' ) do
	tagName = WikitextParser.getTagName( tagOpen )		tagName = WikitextParser.getTagName( tagOpen )

Line 226:		Line 226:
	-- Get the name of the tag in the given wikitext		-- Get the name of the tag in the given wikitext
	-- @param tag Required. Tag to parse.		-- @param tag Required. Tag to parse.
	-- @return Name of the tag or nil if not found		-- @return Name of the tag (in lowercase) or nil if not found
	function WikitextParser.getTagName( tagWikitext )		function WikitextParser.getTagName( tagWikitext )
	~~return~~ tagWikitext:match( '^< *(.-)[ />]' )		local tagName = tagWikitext:match( '^< *(.-)[ />]' )
			if tagName then tagName = tagName:lower() end
			return tagName
	end		end

Line 237:		Line 239:
	function WikitextParser.getTagAttribute( tagWikitext, attribute )		function WikitextParser.getTagAttribute( tagWikitext, attribute )
	return tagWikitext:match( '^< .- [^/>]' .. attribute .. ' = *["\']?([^"\'>]+)["\']?[ />]' )		return tagWikitext:match( '^< .- [^/>]' .. attribute .. ' = *["\']?([^"\'>]+)["\']?[ />]' )
			end

			-- Get the content of the given tag.
			-- @param tagWikitext Required. Wikitext of the tag to parse.
			-- @return Content of the tag. May be empty if the tag is empty. Will be nil if the tag is self-closing.
			-- @todo May fail with nested tags
			function WikitextParser.getTagContent( tagWikitext, attribute )
			return tagWikitext:match( '^<.->.-</.->' )
	end		end

Line 267:		Line 277:
	end		end
	return references		return references
			end

			-- Get the reference with the given name from the given wikitext.
			-- @param wikitext Required. Wikitext to parse.
			-- @param referenceName Required. Name of the reference.
			-- @return Wikitext of the reference
			function WikitextParser.getReference( wikitext, referenceName )
			local references = WikitextParser.getReferences( wikitext )
			for _, reference in pairs( references ) do
			local content = WikitextParser.getTagContent( reference )
			local name = WikitextParser.getTagAttribute( reference, 'name' )
			if content and name == referenceName then
			return reference
			end
			end
	end		end

← Previous revision		Revision as of 15:27, 25 March 2025
Line 344:		Line 344:
	local tableData = {}		local tableData = {}
	tableWikitext = mw.text.trim( tableWikitext );		tableWikitext = mw.text.trim( tableWikitext );
	tableWikitext = ~~string.~~gsub( ~~tableWikitext,~~ '^{\|.-\n', '' ) -- remove the header		tableWikitext = tableWikitext:gsub( '^{\|.-\n', '' ) -- remove the header
	tableWikitext = ~~string.~~gsub( ~~tableWikitext,~~ '\n\|}$', '' ) -- remove the footer		tableWikitext = tableWikitext:gsub( '\n\|}$', '' ) -- remove the footer
	tableWikitext = ~~string.~~gsub( ~~tableWikitext,~~ '^\|%+.-\n', '' ) -- remove any caption		tableWikitext = tableWikitext:gsub( '^\|%+.-\n', '' ) -- remove any caption
	tableWikitext = ~~string.~~gsub( ~~tableWikitext,~~ '\|%-.-\n', '\|-\n' ) -- remove any row attributes		tableWikitext = tableWikitext:gsub( '\|%-.-\n', '\|-\n' ) -- remove any row attributes
	tableWikitext = ~~string.~~gsub( ~~tableWikitext,~~ '^\|%-\n', '' ) -- remove any leading empty row		tableWikitext = tableWikitext:gsub( '^\|%-\n', '' ) -- remove any leading empty row
	tableWikitext = ~~string.~~gsub( ~~tableWikitext,~~ '\n\|%-$', '' ) -- remove any trailing empty row		tableWikitext = tableWikitext:gsub( '\n\|%-$', '' ) -- remove any trailing empty row
	for rowWikitext in mw.text.gsplit( ~~tableWikitext,~~ '\|-', true ) do		for rowWikitext in mw.text.gsplit( '\|-', true ) do
	local rowData = {}		local rowData = {}
	rowWikitext = ~~string.~~gsub( ~~rowWikitext,~~ '\|\|', '\n\|' )		rowWikitext = rowWikitext:gsub( '\|\|', '\n\|' )
	rowWikitext = ~~string.~~gsub( ~~rowWikitext,~~ '!!', '\n\|' )		rowWikitext = rowWikitext:gsub( '!!', '\n\|' )
	rowWikitext = ~~string.~~gsub( ~~rowWikitext,~~ '\n!', '\n\|' )		rowWikitext = rowWikitext:gsub( '\n!', '\n\|' )
	rowWikitext = ~~string.~~gsub( ~~rowWikitext,~~ '^!', '\n\|' )		rowWikitext = rowWikitext:gsub( '^!', '\n\|' )
	rowWikitext = ~~string.~~gsub( ~~rowWikitext,~~ '^\n\|', '' )		rowWikitext = rowWikitext:gsub( '^\n\|', '' )
	for cellWikitext in mw.text.gsplit( rowWikitext, '\n\|' ) do		for cellWikitext in mw.text.gsplit( rowWikitext, '\n\|' ) do
	cellWikitext = mw.text.trim( cellWikitext )		cellWikitext = mw.text.trim( cellWikitext )