Module:Plain text/sandbox - Revision history

Jonesey95: keep contents of sub, sup, and underline

2023-07-23T15:39:29Z

keep contents of sub, sup, and underline

← Previous revision		Revision as of 15:39, 23 July 2023
Line 20:		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

Jonesey95: sync with live module

2023-07-23T15:38:36Z

sync with live module

← Previous revision		Revision as of 15:38, 23 July 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 14:		Line 15:
	:gsub(' ', ' ') --replace nbsp spaces with regular spaces		:gsub(' ', ' ') --replace nbsp spaces with regular spaces
	:gsub('<br ?/?>', ', ') --replace br with commas		:gsub('<br ?/?>', ', ') --replace br with commas
	:gsub('<~~(%a+)[^>]+~~>(.-)</%1>', ~~function(tag, contents~~)		:gsub('<span.->(.-)</span>', '%1') --remove spans while keeping text inside
			:gsub('<i.->(.-)</i>', '%1') --remove italics while keeping text inside
	if tag:lower() == 'span' then
			:gsub('<b.->(.-)</b>', '%1') --remove bold while keeping text inside
	return contents
			:gsub('<em.->(.-)</em>', '%1') --remove emphasis while keeping text inside
	else
			:gsub('<strong.->(.-)</strong>', '%1') --remove strong while keeping text inside
	return ''
		⚫	:gsub('<.->.-<.->', '') --strip out remaining tags and the text inside
	end
			:gsub('<.->', '') --remove any other tag markup
	end)
	:gsub('<i[^>]~~+>(~~[^<]~~+)</i>~~', '%1') --~~remove italics while keeping~~ ~~text~~ ~~inside~~		:gsub('%[%[%s[Ff][Ii][Ll][Ee]%s:.-%]%]', '') --strip out files
	:gsub('<[^>]+>[^<]+<[^>]+>', '') --strip out ~~remaining tags and the~~ ~~text~~ ~~inside~~		:gsub('%[%[%s[Ii][Mm][Aa][Gg][Ee]%s:.-%]%]', '') --strip out use of image:
	:gsub('%~~b<>~~', '') --~~remove any other~~ ~~tag~~ ~~markup~~		:gsub('%[%[%s[Cc][Aa][Tt][Ee][Gg][Oo][Rr][Yy]%s:.-%]%]', '') --strip out categories
	:gsub('__[^_]~~+__~~', '') --~~remove~~ __ ~~markups~~		:gsub('%[%[[^%]]-\|', '') --strip out piped link text
	:gsub('^=+[^=]+=+', ''):gsub('\n=+[^=]+=+', '') --remove section titles
	:gsub('%b[]',
	function(bracketed)
	return bracketed:gsub('^%[%[%s*(%a+):.-%]%]$',
	function(link_prefix)
	link_prefix = link_prefix:lower()
	if link_prefix == 'image' or link_prefix == 'file'
	or link_prefix == 'media' or link_prefix == 'category' then
	return ""
	end -- otherwise leave it alone
	end)
	end)
⚫	:gsub('~~%[%[[^%]\|]+\|~~', '') --strip out ~~piped~~ ~~link~~ text
	:gsub('([^%[])%[[^%[%]][^%]]-%s', '%1') --strip out external link text		:gsub('([^%[])%[[^%[%]][^%]]-%s', '%1') --strip out external link text
	:gsub('^%[[^%[%]][^%]]-%s', '') --strip out external link text		:gsub('^%[[^%[%]][^%]]-%s', '') --strip out external link text
Line 43:		Line 31:
	:gsub("'''''", "") --strip out bold italic markup		:gsub("'''''", "") --strip out bold italic markup
	:gsub("'''?", "") --not stripping out '''' gives correct output for bolded text in quotes		:gsub("'''?", "") --not stripping out '''' gives correct output for bolded text in quotes
	:gsub('----', '') --remove ---- lines		:gsub('----+', '') --remove ---- lines
	:gsub('^%s+', ~~''):gsub('\n%s+', '\n'~~) --strip leading		:gsub("^%s+", "") --strip leading
	:gsub('%s+$', ~~''):gsub('%s+\n', '\n'~~) --and trailing spaces		:gsub("%s+$", "") --and trailing spaces
	:gsub(~~'(%s)~~%s+', ~~'%1'~~) --strip redundant spaces		:gsub("%s+", " ") --strip redundant spaces
	if encode then		if encode then
	return mw.text.encode(text)		return mw.text.encode(text)

Ahecht: fix encode

2021-09-02T14:22:20Z

fix encode

← Previous revision		Revision as of 14:22, 2 September 2021
Line 9:		Line 9:
	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)

Ahecht: Restore User:Guarapiranga's changes

2021-09-02T14:20:47Z

Restore User:Guarapiranga's changes

← Previous revision		Revision as of 14:20, 2 September 2021
Line 9:		Line 9:
	end		end

	function p._main(text~~, encode~~)		function p._main(text)
	if not text then return end		if not text then return end
	text = mw.text.killMarkers(text)		text = mw.text.killMarkers(text)
	:gsub(' ', ' ') --replace nbsp spaces with regular spaces		:gsub(' ', ' ') --replace nbsp spaces with regular spaces
	:gsub('<br ?/?>', ', ') --replace br with commas		:gsub('<br ?/?>', ', ') --replace br with commas
	:gsub('<~~span.-~~>(.-)</~~span~~>', ~~'%1'~~) ~~--remove spans while keeping text inside~~		:gsub('<(%a+)[^>]+>(.-)</%1>', function(tag, contents)
			if tag:lower() == 'span' then
	:gsub('<i.->(.-)</i>', '%1') --remove italics while keeping text inside
			return contents
⚫	:gsub('<.->.-<.->', '') --strip out remaining tags and the text inside
			else
⚫	:gsub('<.->', '') --remove any other tag markup
			return ''
⚫	:gsub('%[%[%s[~~Ff]ile%s:.-~~%]%]', '') --strip out ~~files~~
			end
	:gsub('%[%[%s[Ii]mage%s:.-%]%]', '') --strip out use of image:
			end)
	:gsub('%[%[%s[Cc]ategory%s:.-%]%]', '') --strip out categories
	:gsub('~~%[%~~[[^%]~~]-\|~~', '') --~~strip~~ ~~out~~ ~~piped~~ ~~link~~ text		:gsub('<i[^>]+>([^<]+)</i>', '%1') --remove italics while keeping text inside
		⚫	:gsub('<[^>]+>[^<]+<[^>]+>', '') --strip out remaining tags and the text inside
		⚫	:gsub('%b<>', '') --remove any other tag markup
			:gsub('__[^_]+__', '') --remove __ markups
			:gsub('^=+[^=]+=+', ''):gsub('\n=+[^=]+=+', '') --remove section titles
			:gsub('%b[]',
			function(bracketed)
			return bracketed:gsub('^%[%[%s*(%a+):.-%]%]$',
			function(link_prefix)
			link_prefix = link_prefix:lower()
			if link_prefix == 'image' or link_prefix == 'file'
			or link_prefix == 'media' or link_prefix == 'category' then
			return ""
			end -- otherwise leave it alone
			end)
			end)
		⚫	:gsub('%[%[[^%]\|]+\|', '') --strip out piped link text
	:gsub('([^%[])%[[^%[%]][^%]]-%s', '%1') --strip out external link text		:gsub('([^%[])%[[^%[%]][^%]]-%s', '%1') --strip out external link text
	:gsub('^%[[^%[%]][^%]]-%s', '') --strip out external link text		:gsub('^%[[^%[%]][^%]]-%s', '') --strip out external link text
Line 28:		Line 44:
	:gsub("'''?", "") --not stripping out '''' gives correct output for bolded text in quotes		:gsub("'''?", "") --not stripping out '''' gives correct output for bolded text in quotes
	:gsub('----', '') --remove ---- lines		:gsub('----', '') --remove ---- lines
	:gsub("^%s+", "") --strip leading		:gsub('^%s+', ''):gsub('\n%s+', '\n') --strip leading
	:gsub("%s+$", "") --and trailing spaces		:gsub('%s+$', ''):gsub('%s+\n', '\n') --and trailing spaces
	:gsub("%s+", ~~" "~~) --strip redundant spaces		:gsub('(%s)%s+', '%1') --strip redundant spaces
	if encode then		if encode then
	return mw.text.encode(text)		return mw.text.encode(text)

Ahecht: :gsub('([^%[])%^%[%[^%]]-%s', '%1'):gsub('^%^%[%[^%]]-%s', '')

2021-09-02T14:12:27Z

:gsub('([^%[])%[[^%[%]][^%]]-%s', '%1'):gsub('^%[[^%[%]][^%]]-%s', '')

← Previous revision		Revision as of 14:12, 2 September 2021
Line 22:		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', '%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

Ahecht: strip out external link text

2021-09-02T13:54:46Z

strip out external link text

← Previous revision		Revision as of 13:54, 2 September 2021
Line 22:		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('[%[%]]', '') --then strip out remaining [ and ]		:gsub('[%[%]]', '') --then strip out remaining [ and ]
	:gsub("'''''", "") --strip out bold italic markup		:gsub("'''''", "") --strip out bold italic markup

Ahecht: add encode option

2021-09-02T13:31:00Z

add encode option

← Previous revision		Revision as of 13:31, 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]
			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 28:		Line 29:
	: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

Ahecht: sync

2021-09-02T13:24:03Z

sync

@@ Line 13: / Line 13: @@
 		:gsub('&nbsp;', ' ') --replace nbsp spaces with regular spaces
 		:gsub('<br ?/?>', ', ') --replace br with commas
-		:gsub('<(%a+)[^>]+>(.-)</%1>', function(tag, contents)
+		:gsub('<span.->(.-)</span>', '%1') --remove spans while keeping text inside
-		:gsub('<i[^>]+>([^<]+)</i>', '%1') --remove italics while keeping text inside
+		: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+', ''):gsub('\n%s+', '\n') --strip leading
+		:gsub("^%s+", "") --strip leading
-		:gsub('%s+$', ''):gsub('%s+\n', '\n') --and trailing spaces
+		:gsub("%s+$", "") --and trailing spaces
-		:gsub('(%s)%s+', '%1') --strip redundant spaces
+		:gsub("%s+", " ") --strip redundant spaces
 	return text
 end

Guarapiranga: some performance and results improvements

2021-06-21T13:37:45Z

some performance and results improvements

@@ Line 13: / Line 13: @@
 		:gsub('&nbsp;', ' ') --replace nbsp spaces with regular spaces
 		:gsub('<br ?/?>', ', ') --replace br with commas
-		:gsub('%[%[%s*[Cc]ategory%s*:.-%]%]', '') --strip out categories
+		:gsub('<i[^>]+>([^<]+)</i>', '%1') --remove italics while keeping text inside
-		:gsub('%[%[[^%]]-|', '') --strip out piped link text
+		:gsub('<[^>]+>[^<]+<[^>]+>', '') --strip out remaining tags and the text inside
 		: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+', ''):gsub('\n%s+', '\n') --strip leading
-		:gsub("%s+$", "") --and trailing spaces
+		:gsub('%s+$', ''):gsub('%s+\n', '\n') --and trailing spaces
-		:gsub("%s+", " ") --strip redundant spaces
+		:gsub('(%s)%s+', '%1') --strip redundant spaces
 	return text
 end

DePiep at 07:37, 4 April 2020

2020-04-04T07:37:34Z

← Previous revision		Revision as of 07:37, 4 April 2020
Line 13:		Line 13:
	:gsub(' ', ' ') --replace nbsp spaces with regular spaces		:gsub(' ', ' ') --replace nbsp spaces with regular spaces
	:gsub('<br ?/?>', ', ') --replace br with commas		:gsub('<br ?/?>', ', ') --replace br with commas
	:gsub('^%s<span.->(.-)</span>%s$', '%1'~~, 1~~) --remove outer spans while keeping text inside		:gsub('^%s<span.->(.-)</span>%s$', '%1') --remove outer spans while keeping text inside
	-- :gsub('<span.->(.-)</span>', '%1') --repeat for nested span tags.		:gsub('<span.->(.-)</span>', '%1') --repeat for nested span tags.
	:gsub('<i.->(.-)</i>', '%1') --remove italics while keeping text inside		:gsub('<i.->(.-)</i>', '%1') --remove italics while keeping text inside
	:gsub('<.->.-<.->', '') --strip out remaining tags and the text inside		:gsub('<.->.-<.->', '') --strip out remaining tags and the text inside