Module:Plain text - Revision history

Johnrdorazio: 1 revision imported

2023-05-04T16:23:26Z

1 revision imported

← Older revision	Revision as of 16:23, May 4, 2023
(No difference)

en>Uzume: strict

2023-02-10T20:22:05Z

strict

← Older revision		Revision as of 20:22, February 10, 2023
Line 1:		Line 1:
	--converts text with wikilinks to plain text, e.g "[[foo\|gah]] is [[bar]]" to "gah is bar"		--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		--removes anything enclosed in tags that isn't nested, mediawiki strip markers (references etc), files, italic and bold markup
			require[[strict]]
	local p = {}		local p = {}

Line 16:		Line 17:
	:gsub('<span.->(.-)</span>', '%1') --remove spans while keeping text inside		:gsub('<span.->(.-)</span>', '%1') --remove spans while keeping text inside
	:gsub('<i.->(.-)</i>', '%1') --remove italics while keeping text inside		:gsub('<i.->(.-)</i>', '%1') --remove italics while keeping text inside
			:gsub('<b.->(.-)</b>', '%1') --remove bold while keeping text inside
			:gsub('<em.->(.-)</em>', '%1') --remove emphasis while keeping text inside
			:gsub('<strong.->(.-)</strong>', '%1') --remove strong while keeping text inside
	:gsub('<.->.-<.->', '') --strip out remaining tags and the text inside		:gsub('<.->.-<.->', '') --strip out remaining tags and the text inside
	:gsub('<.->', '') --remove any other tag markup		:gsub('<.->', '') --remove any other tag markup
	:gsub('%[%[%s[Ff]~~ile~~%s:.-%]%]', '') --strip out files		:gsub('%[%[%s[Ff][Ii][Ll][Ee]%s:.-%]%]', '') --strip out files
	:gsub('%[%[%s[Ii]~~mage~~%s:.-%]%]', '') --strip out use of image:		:gsub('%[%[%s[Ii][Mm][Aa][Gg][Ee]%s:.-%]%]', '') --strip out use of image:
	:gsub('%[%[%s[Cc]~~ategory~~%s:.-%]%]', '') --strip out categories		:gsub('%[%[%s[Cc][Aa][Tt][Ee][Gg][Oo][Rr][Yy]%s:.-%]%]', '') --strip out categories
	:gsub('%[%[[^%]]-\|', '') --strip out piped link text		:gsub('%[%[[^%]]-\|', '') --strip out piped link text
	:gsub('([^%[])%[[^%[%]][^%]]-%s', '%1') --strip out external link text		:gsub('([^%[])%[[^%[%]][^%]]-%s', '%1') --strip out external link text
Line 27:		Line 31:
	: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('----+', '') --remove ---- lines
	:gsub("^%s+", "") --strip leading		:gsub("^%s+", "") --strip leading
	:gsub("%s+$", "") --and trailing spaces		:gsub("%s+$", "") --and trailing spaces

Johnrdorazio: 1 revision imported

2021-09-11T22:15:23Z

1 revision imported

← Older revision	Revision as of 22:15, September 11, 2021
(No difference)

en>Ahecht: implement "encode" option, strip out external link alt text

2021-09-02T14:19:07Z

implement "encode" option, strip out external link alt text

← Older revision		Revision as of 14:19, September 2, 2021
Line 5:		Line 5:
	function p.main(frame)		function p.main(frame)
	local text = frame.args[1]		local text = frame.args[1]
			local encode = require('Module:yesno')(frame.args.encode)
	return p._main(text)		return p._main(text, encode)
	end		end

	function p._main(text)		function p._main(text, encode)
	if not text then return end		if not text then return end
	text = mw.text.killMarkers(text)		text = mw.text.killMarkers(text)
Line 21:		Line 22:
	:gsub('%[%[%s[Cc]ategory%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('([^%[])%[[^%[%]][^%]]-%s', '%1') --strip out external link text
			:gsub('^%[[^%[%]][^%]]-%s', '') --strip out external link text
	:gsub('[%[%]]', '') --then strip out remaining [ and ]		:gsub('[%[%]]', '') --then strip out remaining [ and ]
	:gsub("'''''", "") --strip out bold italic markup		:gsub("'''''", "") --strip out bold italic markup
Line 28:		Line 31:
	:gsub("%s+$", "") --and trailing spaces		:gsub("%s+$", "") --and trailing spaces
	:gsub("%s+", " ") --strip redundant spaces		:gsub("%s+", " ") --strip redundant spaces
			if encode then
⚫	return text
			return mw.text.encode(text)
			else
		⚫	return text
			end
	end		end

Johnrdorazio: 1 revision imported

2020-08-21T10:39:20Z

1 revision imported

← Older revision		Revision as of 10:39, August 21, 2020
(No difference)

en>Galobtter: better stripping, strip out more stuff

2019-01-21T08:22:28Z

better stripping, strip out more stuff

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(' ', ' ') --replace nbsp spaces with regular spaces
:gsub('<br ?/?>', ', ') --replace br with commas
: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*[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
:gsub('----', '') --remove ---- lines
:gsub("^%s+", "") --strip leading
:gsub("%s+$", "") --and trailing spaces
:gsub("%s+", " ") --strip redundant spaces
return text
end

return p