Module:Plain text: Difference between revisions

From escforumwiki
Jump to navigation Jump to search
en>Galobtter
strip out more stuff
en>Galobtter
gah fix
Line 14: Line 14:
:gsub('<br ?/?>', ', ') --replace br with commas
:gsub('<br ?/?>', ', ') --replace br with commas
:gsub('<.->.-<.->', '') --strip out tags
:gsub('<.->.-<.->', '') --strip out tags
:gsub('%[%[%s*File%s*:.-%]%]', '') --strip out files
:gsub('%[%[%s*[Ff]ile%s*:.-%]%]', '') --strip out files
:gsub('%[%[%s*Image%s*:.-%]%]', '') --strip out use of image:
:gsub('%[%[%s*[Ii]mage%s*:.-%]%]', '') --strip out use of image:
:gsub('%[%[%sCategory%s:.-%]%]', '') --strip out categories
:gsub('%[%[%s*[Cc]ategory%s*:.-%]%]', '') --strip out categories
:gsub('%[%[[^%]]-|', '') --strip out piped link text
:gsub('%[%[[^%]]-|', '') --strip out piped link text
:gsub('[%[%]]', '') --then strip out remaining [ and ]
:gsub('[%[%]]', '') --then strip out remaining [ and ]

Revision as of 13:30, 24 May 2018

Documentation for this module may be created at Module:Plain text/doc

--converts text with wikilinks to plain text, e.g "[[foo|gah]] is [[bar]]" to "gah is bar"
--removes anything enclosed in tags that isn't nested, mediawiki strip markers (references etc), files, italic and bold markup
local p = {}

function p.main(frame)
	local text = frame.args[1]
	return p._main(text)
end

function p._main(text)
	if not text then return end
	text = mw.text.killMarkers(text)
		:gsub('<span class="nowrap">(.+)</span>', '%1') --remove nowrap while keeping text inside
		:gsub('<br ?/?>', ', ') --replace br with commas
		:gsub('<.->.-<.->', '') --strip out tags
		:gsub('%[%[%s*[Ff]ile%s*:.-%]%]', '') --strip out files
		:gsub('%[%[%s*[Ii]mage%s*:.-%]%]', '') --strip out use of image:
		:gsub('%[%[%s*[Cc]ategory%s*:.-%]%]', '') --strip out categories
		:gsub('%[%[[^%]]-|', '') --strip out piped link text
		:gsub('[%[%]]', '') --then strip out remaining [ and ]
		:gsub("'''''", "") --strip out bold italic markup
		:gsub("'''?", "") --not stripping out '''' gives correct output for bolded text in quotes
	return text
end

return p