Difference between revisions of "Module:Plain text"

From blackwiki
Jump to navigation Jump to search
blackwiki>Galobtter
(gah fix)
blackwiki>Galobtter
(better stripping, strip out more stuff)
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('&nbsp;', ' ') --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

Revision as of 08:22, 21 January 2019

Implements {{Plain text}}. Developed for producing short descriptions from text that may have markup, or other stuff that needs removing from short descriptions.

Usage

{{#invoke:Plain text|main|'''[[foo|hah]]''' is '''''[[gah]]'''''}} --> hah is gah

See also


--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('&nbsp;', ' ') --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