Module:Plain text - Revision history

Peppermare: 1 revision imported

2025-01-24T18:29:57Z

1 revision imported

← Older revision	Revision as of 18:29, 24 January 2025
(No difference)

wikipedia>Dpleibovitz: Fixed the stripping of + signs

2024-12-24T01:02:36Z

Fixed the stripping of + signs

← Older revision		Revision as of 01:02, 24 December 2024
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 19:		Line 20:
	:gsub('<em.->(.-)</em>', '%1') --remove emphasis 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('<strong.->(.-)</strong>', '%1') --remove strong while keeping text inside
			:gsub('<sub.->(.-)</sub>', '%1') --remove subscript markup; retain contents
			:gsub('<sup.->(.-)</sup>', '%1') --remove superscript markup; retain contents
			:gsub('<u.->(.-)</u>', '%1') --remove underline markup; retain contents
	: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
Line 30:		Line 34:
	: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

>QuebbingtonBear: 39 revisions imported from :wikipedia:Module:Plain_text

2022-10-28T06:18:11Z

39 revisions imported from wikipedia:Module:Plain_text

← Older revision	Revision as of 06:18, 28 October 2022
(No difference)

>Dinoguy1000: horizontal rules created via ---- can have any number of dashes after the first four

2021-11-08T09:46:54Z

horizontal rules created via ---- can have any number of dashes after the first four

← Older revision		Revision as of 09:46, 8 November 2021
Line 30:		Line 30:
	: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

>Dinoguy1000: namespace names are case-insensitive

2021-10-06T04:15:21Z

namespace names are case-insensitive

← Older revision		Revision as of 04:15, 6 October 2021
Line 21:		Line 21:
	: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

>Dinoguy1000: +// stripping where contained text should also be kept

2021-10-06T03:39:28Z

+// stripping where contained text should also be kept

← Older revision Revision as of 03:39, 6 October 2021
Line 16: Line 16:

:gsub('<span.->(.-)', '%1') --remove spans while keeping text inside
:gsub('<span.->(.-)', '%1') --remove spans while keeping text inside

:gsub('<i.->(.-)', '%1') --remove italics while keeping text inside
:gsub('<i.->(.-)', '%1') --remove italics while keeping text inside

:gsub('<b.->(.-)', '%1') --remove bold while keeping text inside

:gsub('<em.->(.-)', '%1') --remove emphasis while keeping text inside

:gsub('<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

>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, 2 September 2021
Line 5: Line 5:

function p.main(frame)
function p.main(frame)

local text = frame.args[1]
local text = frame.args[1]

return p._main(text)
local encode = require('Module:yesno')(frame.args.encode)

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

return text
if encode then

return mw.text.encode(text)

else

return text

end

end
end

return p
return p

>TheKitKatProject: 1 revision imported

2020-09-21T04:40:51Z

1 revision imported

← Older revision Revision as of 04:40, 21 September 2020
(No difference)

wiki>Galobtter: better stripping, strip out more stuff

2019-01-21T08:22:28Z

better stripping, strip out more stuff

← Older revision Revision as of 08:22, 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('~~(.+)~~', '%1') --~~remove nowrap while keeping text inside~~
:gsub(' ', ' ') --replace nbsp spaces with regular spaces

:gsub(' ', ', ') --replace br with commas
:gsub(' ', ', ') --replace br with commas

:gsub('<.->.-<.->', '') --strip out tags
:gsub('<span.->(.-)', '%1') --remove spans while keeping text inside

:gsub('<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

wikipedia>Galobtter: gah fix

2018-05-24T13:30:49Z

gah fix

← Older revision Revision as of 13:30, 24 May 2018
Line 14: Line 14:

:gsub(' ', ', ') --replace br with commas
:gsub(' ', ', ') --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 ]

← Older revision		Revision as of 03:39, 6 October 2021
Line 16:		Line 16:
	: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

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

	return p		return p

← Older revision	Revision as of 04:40, 21 September 2020
(No difference)

← Older revision		Revision as of 08:22, 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

← Older revision		Revision as of 13:30, 24 May 2018
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 ]