Module:Plain text: Difference between revisions
Jump to navigation
Jump to search
Content added Content deleted
(better stripping, strip out more stuff) |
Antoniokf5 (talk | contribs) m (1 revision imported from templatewiki:Module:Plain_text) |
||
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(' |
:gsub('<span class="nowrap">(.+)</span>', '%1') --remove nowrap while keeping text inside |
||
:gsub('<br ?/?>', ', ') --replace br with commas |
:gsub('<br ?/?>', ', ') --replace br with commas |
||
:gsub('< |
:gsub('<.->.-<.->', '') --strip out tags |
||
: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 24: | Line 21: | ||
: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 |
Revision as of 17:09, 16 August 2021
Documentation for this module may be created at Module:Plain text/doc
--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