Module:Plain text: Difference between revisions

m
1 revision imported
(implement "encode" option, strip out external link alt text)
m (1 revision imported)
 
(2 intermediate revisions by 2 users not shown)
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