Module:Plain text - Revision history

Sanctaria: 1 revision imported

2021-06-25T19:23:51Z

1 revision imported

← Older revision		Revision as of 14:23, 25 June 2021
(No difference)

en>Galobtter: better stripping, strip out more stuff

2019-01-21T08:22:28Z

better stripping, strip out more stuff

← Older revision		Revision as of 03:22, 21 January 2019
Line 11:		Line 11:
	if not text then return end		if not text then return end
	text = mw.text.killMarkers(text)		text = mw.text.killMarkers(text)
	:gsub('~~<span class="nowrap">(.+)</span>~~', '%1') --~~remove nowrap while keeping text inside~~		:gsub(' ', ' ') --replace nbsp spaces with regular spaces
	:gsub('<br ?/?>', ', ') --replace br with commas		:gsub('<br ?/?>', ', ') --replace br with commas
	:gsub('<.->.-<.->', '') --strip out tags		:gsub('<span.->(.-)</span>', '%1') --remove spans while keeping text inside
			:gsub('<i.->(.-)</i>', '%1') --remove italics while keeping text inside
			:gsub('<.->.-<.->', '') --strip out remaining tags and the text inside
			:gsub('<.->', '') --remove any other tag markup
	:gsub('%[%[%s[Ff]ile%s:.-%]%]', '') --strip out files		:gsub('%[%[%s[Ff]ile%s:.-%]%]', '') --strip out files
	:gsub('%[%[%s[Ii]mage%s:.-%]%]', '') --strip out use of image:		:gsub('%[%[%s[Ii]mage%s:.-%]%]', '') --strip out use of image:
Line 21:		Line 24:
	:gsub("'''''", "") --strip out bold italic markup		:gsub("'''''", "") --strip out bold italic markup
	:gsub("'''?", "") --not stripping out '''' gives correct output for bolded text in quotes		:gsub("'''?", "") --not stripping out '''' gives correct output for bolded text in quotes
			:gsub('----', '') --remove ---- lines
			:gsub("^%s+", "") --strip leading
			:gsub("%s+$", "") --and trailing spaces
			:gsub("%s+", " ") --strip redundant spaces
	return text		return text
	end		end

	return p		return p

Sanctaria: 1 revision imported

2018-06-12T10:06:30Z

1 revision imported

New page

--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