Module:Excerpt: Difference between revisions

Revision as of 18:46, 27 April 2018

Latest revision as of 01:57, 28 January 2025

(169 intermediate revisions by 10 users not shown)

Line 1:

-- Module:Excerpt implements the Excerpt template

-- Documentation and master version: https://en.wikipedia.org/wiki/Module:Excerpt

-- Authors: User:Sophivorus, User:Certes, User:Aidan9382 & others

-- License: CC-BY-SA-3.0

local Transcluder = require( 'Module:Transcluder' )

local yesno = require( 'Module:Yesno' )

local ok, config = pcall( require, 'Module:Excerpt/config' )

if not ok then config = {} end

local p = {}

local mRedirect = require('Module:Redirect')

-- Helper function to get arguments

-- Entry point for Lua callers

local args

-- Returns a string value: text of the lead of a page

local function p._leadgetArg(pagename key, optionsdefault )

local value = args[ key ]

if not pagename then return "" end -- Return blank text rather than an error splurge

if value and mw.text.trim( value ) ~= '' then

local title = mw.title.new(pagename) -- Find the lead section of the named page

if not title then return "" endvalue

end

local redir = mRedirect.getTarget(title)

return default

if redir then title = mw.title.new(redir) end

end

-- Helper function to handle errors

local text = title:getContent() or ""

local function getError( message, value )

text = mw.ustring.gsub(text, "%c%s*==.*","") -- remove first heading and everything after it

if type( message ) == 'string' then

text = mw.ustring.gsub(text, "<noinclude>.-</noinclude>", "") -- remove noinclude bits

message = Transcluder.getError( message, value )

text = mw.ustring.gsub(text, "<%s*ref[^>]-/%s*>", "") -- remove refs cited elsewhere

text = mw.ustring.gsub(text, "<%s*ref.->.-<%s*/%s*ref%s*>", "") -- remove refs

for _, t in pairs {"[Ee]fn", "[Ee]fn-la", "[Ee]l[mn]", "[Rr]", "[Ss]fn[bp]", "[Ss]f[bn]", "NoteTag"} do

text = mw.ustring.gsub(text, "{{%s*" .. t .. "%s*|.-}}", "") -- remove ref and footnote templates

end

if config.categories and config.categories.errors and mw.title.getCurrentTitle().isContentPage then

text = mw.ustring.gsub(text, "\n%s*{{%s*[Tt][Oo][Cc].-}}", "\n") -- remove most common tables of contents

message:node( '[[Category:' .. config.categories.errors .. ']]' )

end

return message

end

-- Helper function to get localized messages

local allparas = true -- keep all paragraphs?

local function getMessage( key )

if options.paraflags then

local ok, TNT = pcall( require, 'Module:TNT' )

for _, v in pairs(options.paraflags) do

if not ok then return key end

if v then allparas = false end -- if any para specifically requested, don't keep all

return TNT.format( 'I18n/Module:Excerpt.tab', key )

end

-- Main entry point for templates

function p.main( frame )

args = Transcluder.parseArgs( frame )

-- Make sure the requested page exists

local page = getArg( 1 )

if not page or page == '{{{1}}}' then return getError( 'no-page' ) end

local title = mw.title.new(page)

if not title then return getError( 'invalid-title', page ) end

if title.isRedirect then title = title.redirectTarget end

if not title.exists then return getError( 'page-not-found', page ) end

page = title.prefixedText

-- Set variables from the template parameters

local section = getArg( 2, mw.ustring.match( getArg( 1 ), '[^#]+#(.+)' ) )

local hat = yesno( getArg( 'hat', true ) )

local edit = yesno( getArg( 'edit', true ) )

local this = getArg( 'this' )

local only = getArg( 'only' )

local files = getArg( 'files', getArg( 'file', ( only == 'file' and 1 ) ) )

local lists = getArg( 'lists', getArg( 'list', ( only == 'list' and 1 ) ) )

local tables = getArg( 'tables', getArg( 'table', ( only == 'table' and 1 ) ) )

local templates = getArg( 'templates', getArg( 'template', ( only == 'template' and 1 ) ) )

local paragraphs = getArg( 'paragraphs', getArg( 'paragraph', ( only == 'paragraph' and 1 ) ) )

local references = getArg( 'references' )

local subsections = not yesno( getArg( 'subsections' ) )

local noLinks = not yesno( getArg( 'links', true ) )

local noBold = not yesno( getArg( 'bold' ) )

local onlyFreeFiles = yesno( getArg( 'onlyfreefiles', true ) )

local briefDates = yesno( getArg( 'briefdates', false ) )

local inline = yesno( getArg( 'inline' ) )

local quote = yesno( getArg( 'quote' ) )

local more = yesno( getArg( 'more' ) )

local class = getArg( 'class' )

local displaytitle = getArg( 'displaytitle' ) or page

-- Build the hatnote

if hat and not inline then

if this then

hat = this

elseif quote then

hat = getMessage( 'this' )

elseif only then

hat = getMessage( only )

else

hat = getMessage( 'section' )

end

hat = hat .. ' ' .. getMessage( 'excerpt' ) .. ' '

if section then

hat = hat .. '[[:' .. page .. '#' .. mw.uri.anchorEncode( section ) .. '|' .. displaytitle

.. ' § ' .. mw.ustring.gsub( section, '%[%[([^]|]+)|?[^]]*%]%]', '%1' ) .. ']].' -- remove nested links

else

hat = hat .. '[[:' .. page .. '|' .. displaytitle .. ']].'

end

if edit then

hat = hat .. '<span class="mw-editsection-like plainlinks"><span class="mw-editsection-bracket">[</span>['

hat = hat .. title:fullUrl( 'action=edit' ) .. ' ' .. mw.message.new( 'editsection' ):plain()

hat = hat .. ']<span class="mw-editsection-bracket">]</span></span>'

end

if config.hat then

hat = config.hat .. hat .. '}}'

hat = frame:preprocess( hat )

else

hat = mw.html.create( 'div' ):addClass( 'dablink excerpt-hat' ):wikitext( hat )

end

else

hat = nil

end

-- Build the "Read more" link

-- a basic parser to trim down the lead

if more and not inline then

local inlead = false -- have we found some text yet?

more = "'''[[" .. page .. '#' .. ( section or '' ) .. "|" .. getMessage( 'more' ) .. "]]'''"

local t = "" -- the stripped down output text

more = mw.html.create( 'div' ):addClass( 'noprint excerpt-more' ):wikitext( more )

local files = 0 -- how many [[Image: or [[File: so far

else

local paras = 0 -- how many paragraphs so far

more = nil

end

-- Build the options for Module:Transcluder out of the template parameters and the desired defaults

text = mw.ustring.gsub(text,"^%s*","") -- remove initial white space

local options = {

repeat -- loop around parsing a comment, template, image or paragraph

files = files,

local token = mw.ustring.match(text, "^%s*<!%-%-.-%-%->%s*") -- <!--HTML comment-->

lists = lists,

or mw.ustring.match(text, "^%b{}%s*") or false -- or {{Template}}

tables = tables,

if token then

paragraphs = paragraphs,

if inlead then t = t .. token end -- keep comments and templates only within text body

sections = subsections,

else

categories = 0,

token = mw.ustring.match(text, "^%[%[%s*[Ff]ile%s*:%C*%]%]%s*") -- [[File: ... ]]

references = references,

or mw.ustring.match(text, "^%[%[%s*[Ii]mage%s*:%C*%]%]%s*") -- or [[Image: ... ]]

only = only and mw.text.trim( only, 's' ) .. 's',

if token then

filesnoLinks = files + 1noLinks,

noBold = noBold,

if options.fileflags and options.fileflags[files] then t = t .. token end

noSelfLinks = true,

else -- got a paragraph, which ends at a file, image, blank line or end of text

noNonFreeFiles = onlyFreeFiles,

local afterend = mw.ustring.len(text) + 1

noBehaviorSwitches = true,

local blankpos = mw.ustring.find(text, "\n%s*\n") or afterend

fixReferences = true,

local endpos = math.min(

linkBold = true,

mw.ustring.find(text, "%[%[%s*[Ff]ile%s*:") or afterend,

}

mw.ustring.find(text, "%[%[%s*[Ff]ile%s*:") or afterend,

blankpos)

-- Get the excerpt itself

token = mw.ustring.sub(text, 1, endpos-1)

local title = page .. '#' .. ( section or '' )

if blankpos < afterend and blankpos == endpos then -- paragraph ends with a blank line

local ok, excerpt = pcall( Transcluder.get, title, options )

token = token .. mw.ustring.match(text, "\n%s*\n", blankpos)

if not ok then return getError( excerpt ) end

if mw.text.trim( excerpt ) == '' and not only then

if section then return getError( 'section-empty', section ) else return getError( 'lead-empty' ) end

end

-- Fix birth and death dates, but only in the first paragraph

if briefDates then

local startpos = 1 -- skip initial templates

local s

local e = 0

repeat

startpos = e + 1

s, e = mw.ustring.find( excerpt, "%s*%b{}%s*", startpos )

until not s or s > startpos

s, e = mw.ustring.find( excerpt, "%b()", startpos ) -- get (...), which may be (year–year)

if s and s < startpos + 100 then -- look only near the start

local year1, conjunction, year2 = mw.ustring.match( mw.ustring.sub( excerpt, s, e ), '(%d%d%d+)(.-)(%d%d%d+)' )

if year1 and year2 and (mw.ustring.match( conjunction, '[%-–—]' ) or mw.ustring.match( conjunction, '{{%s*[sS]nd%s*}}' )) then

local y1 = tonumber(year1)

local y2 = tonumber(year2)

if y2 > y1 and y2 < y1 + 125 and y1 <= tonumber( os.date( "%Y" )) then

excerpt = mw.ustring.sub( excerpt, 1, s ) .. year1 .. "–" .. year2 .. mw.ustring.sub( excerpt, e )

end

inlead = true

paras = paras + 1

if allparas or (options.paraflags and options.paraflags[paras]) then t = t .. token end

end

end

end

-- If no file was found, try to get one from the infobox

if token then text = mw.ustring.sub(text, mw.ustring.len(token)+1) end

local fileNamespaces = Transcluder.getNamespaces( 'File' )

until not text or text == "" or not token or token == ""

if ( ( only == 'file' or only == 'files' ) or ( not only and ( files ~= '0' or not files ) ) ) and -- caller asked for files

not Transcluder.matchAny( excerpt, '%[%[', fileNamespaces, ':' ) and -- and there are no files in Transcluder's output

config.captions -- and we have the config option required to try finding files in templates

then

-- We cannot distinguish the infobox from the other templates so we search them all

local infobox = Transcluder.getTemplates( excerpt );

infobox = table.concat( infobox )

local parameters = Transcluder.getParameters( infobox )

local file, captions, caption, cssclasses, cssclass

for _, pair in pairs( config.captions ) do

file = pair[1]

file = parameters[file]

if file and Transcluder.matchAny( file, '^.*%.', { '[Jj][Pp][Ee]?[Gg]', '[Pp][Nn][Gg]', '[Gg][Ii][Ff]', '[Ss][Vv][Gg]' }, '.*' ) then

file = mw.ustring.match( file, '%[?%[?.-:([^{|]+)%]?%]?' ) or file -- [[File:Example.jpg{{!}}upright=1.5]] to Example.jpg

captions = pair[2]

for _, p in pairs( captions ) do

if parameters[ p ] then caption = parameters[ p ] break end

end

-- Check for CSS classes

-- We opt to use skin-invert-image instead of skin-invert

-- in all other cases, the CSS provided in the infobox is used

if pair[3] then

cssclasses = pair[3]

for _, p in pairs(cssclasses) do

if parameters[p] then

cssclass = ((parameters[p] == 'skin-invert') and 'skin-invert-image' or parameters[p])

break

end

end

end

excerpt = '[[File:' .. file ..

(cssclass and ('|class=' .. cssclass) or '') ..

'|thumb|' .. (caption or '') .. ']]' .. excerpt

if ( onlyFreeFiles ) then

excerpt = Transcluder.removeNonFreeFiles( excerpt )

end

break

end

end

end

-- Unlike other elements, templates are filtered here

text = mw.ustring.gsub(t, "\n+$", "") -- remove trailing line feeds, so "{{Transclude text excerpt|Foo}} more" flows on one line

-- because we had to search the infoboxes for files

local trash

if options.more then text = text .. " '''[[" .. pagename .. "|" .. options.more .. "]]'''" end

if only and ( only == 'template' or only == 'templates' ) then

return text

trash, excerpt = Transcluder.getTemplates( excerpt, templates );

end

else -- Remove blacklisted templates

local blacklist = config.blacklist and table.concat( config.blacklist, ',' ) or ''

-- Convert a comma-separated list of numbers or min-max ranges into a list of booleans, e.g. "1,3-5" → {1=true,2=false,3=true,4=true,5=true}

if templates then

function p.numberflags(str)

if string.sub( templates, 1, 1 ) == '-' then --Unwanted templates. Append to blacklist

local ranges = mw.text.split(str, ",") -- parse ranges, e.g. "1,3-5" → {"1","3-5"}

blacklist = templates .. ',' .. blacklist

local flags = {}

else --Wanted templates. Replaces blacklist and acts as whitelist

for _, r in pairs(ranges) do

blacklist = templates

local min, max = mw.ustring.match(r, "^%s*(%d+)%s*%-%s*(%d+)%s*$") -- "3-5" → min=3 max=5

end

if not max then min, max = mw.ustring.match(r, "^%s*((%d+))%s*$") end -- "1" → min=1 max=1

else

if max then

blacklist = '-' .. blacklist

for p = min, max do flags[p] = true end

end

trash, excerpt = Transcluder.getTemplates( excerpt, blacklist );

end

return flags

end

-- Remove extra line breaks but leave one before and after so the parser interprets lists, tables, etc. correctly

-- Entry point for template callers using #invoke:

excerpt = mw.text.trim( excerpt )

function p.lead(frame)

excerpt = string.gsub( excerpt, '\n\n\n+', '\n\n' )

-- args = { 1 = page name, paragraphs = list e.g. "1,3-5", files = list, more = text}

excerpt = '\n' .. excerpt .. '\n'

local args = frame.args -- from calling module

local pargs = frame:getParent().args -- from template

-- Remove nested categories

local pagename = args[1] or pargs[1] or ""

excerpt = frame:preprocess( excerpt )

pagename = mw.ustring.match(pagename, "%[%[%s*(.-)[]|#]") or pagename -- "[[Foo|Bar]]" → "Foo"

local categories, excerpt = Transcluder.getCategories( excerpt, options.categories )

-- Add tracking categories

local options = {}

if config.categories then

options.paraflags = p.numberflags(args["paragraphs"] or pargs["paragraphs"] or "") -- parse paragraphs, e.g. "1,3-5" → {"1","3-5"}

local contentCategory = config.categories.content

options.fileflags = p.numberflags(args["files"] or pargs["files"] or "") -- parse file numbers

if contentCategory and mw.title.getCurrentTitle().isContentPage then

options.more = args["more"] or pargs["more"]

excerpt = excerpt .. '[[Category:' .. contentCategory .. ']]'

if options.more and options.more == "" then options.more = "Read more..." end -- more= is short for this default text

end

local namespaceCategory = config.categories[ mw.title.getCurrentTitle().namespace ]

if namespaceCategory then

excerpt = excerpt .. '[[Category:' .. namespaceCategory .. ']]'

end

end

-- Load the styles

local text = p._lead(pagename, options)

local styles

return frame:preprocess(text)

if config.styles then

styles = frame:extensionTag( 'templatestyles', '', { src = config.styles } )

end

-- Combine and return the elements

if inline then

return mw.text.trim( excerpt )

end

local tag = 'div'

if quote then

tag = 'blockquote'

end

excerpt = mw.html.create( 'div' ):addClass( 'excerpt' ):wikitext( excerpt )

local block = mw.html.create( tag ):addClass( 'excerpt-block' ):addClass( class )

return block:node( styles ):node( hat ):node( excerpt ):node( more )

end

-- Entry points for backwards compatibility

function p.lead( frame ) return p.main( frame ) end

function p.excerpt( frame ) return p.main( frame ) end

return p