Module:Excerpt/sandbox: Difference between revisions

Revision as of 18:56, 22 March 2025

Latest revision as of 21:21, 26 May 2025

(25 intermediate revisions by 2 users not shown)

Line 7:

local yesno = require( 'Module:Yesno' )

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

if not ok then config = {} end

Line 15:

function Excerpt.main( frame )

-- Make sure the requested page exists and get the wikitext

local page = Excerpt.getArg( 1 )

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

local title = mw.title.new( page )

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

local fragment = title.fragment -- save for later

if title.isRedirect then title = title.redirectTarget end

if title.isRedirect then

title = title.redirectTarget

if fragment == "" then

fragment = title.fragment -- page merge potential

end

end

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

page = title.prefixedText

-- Set variables from the template parameters

local hash = string.match( Excerpt.getArg( 1 ), '[^#]+#(.+)' )

local section = Excerpt.getArg( 2, hash )

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

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

local editIntro = Excerpt.getArg( 'editintro' )

local this = Excerpt.getArg( 'this' )

local only = Excerpt.getArg( 'only' )

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

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

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

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

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

local references = yesno( Excerpt.getArg( 'references', true ) )

local subsections = yesno( Excerpt.getArg( 'subsections', false ) )

local links = yesno( Excerpt.getArg( 'links', true ) )

local bold = yesno( Excerpt.getArg( 'bold', false ) )

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

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

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

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

local class = Excerpt.getArg( 'class' )

local displayTitle = Excerpt.getArg( 'displaytitle', page )

-- Get the full wikitext

local wikitext = title:getContent()

-- Reduce toGet the sectiontemplate params we'reand interestedprocess inthem

local params = {

hat = yesno( Excerpt.getArg( 'hat', true ) ),

this = Excerpt.getArg( 'this' ),

only = Excerpt.getArg( 'only' ),

files = Excerpt.getArg( 'files', Excerpt.getArg( 'file' ) ),

lists = Excerpt.getArg( 'lists', Excerpt.getArg( 'list' ) ),

tables = Excerpt.getArg( 'tables', Excerpt.getArg( 'table' ) ),

templates = Excerpt.getArg( 'templates', Excerpt.getArg( 'template' ) ),

paragraphs = Excerpt.getArg( 'paragraphs', Excerpt.getArg( 'paragraph' ) ),

references = yesno( Excerpt.getArg( 'references', true ) ),

subsections = yesno( Excerpt.getArg( 'subsections', false ) ),

links = yesno( Excerpt.getArg( 'links', true ) ),

bold = yesno( Excerpt.getArg( 'bold', false ) ),

briefDates = yesno( Excerpt.getArg( 'briefdates', false ) ),

inline = yesno( Excerpt.getArg( 'inline' ) ),

quote = yesno( Excerpt.getArg( 'quote' ) ),

more = yesno( Excerpt.getArg( 'more' ) ),

class = Excerpt.getArg( 'class' ),

displayTitle = Excerpt.getArg( 'displaytitle', page ),

}

-- Make sure the requested section exists and get the excerpt

local excerpt

local section = Excerpt.getArg( 2, fragment )

section = mw.text.trim( section )

if section == '' then section = nil end

if section then

excerpt = parser.getSectionTag( wikitext, section )

if not excerpt then

if params.subsections then

excerpt = parser.getSection( wikitext, section )

else

Line 63 ⟶ 69:

end

if not excerpt then return Excerpt.getError( 'section-not-found', section ) end

if excerpt == '' and not only then return Excerpt.getError( 'section-empty', section ) end

else

excerpt = parser.getLead( wikitext )

if excerpt == '' and not only then return Excerpt.getError( 'lead-empty' ) end

end

-- Remove noinclude bits

-- Leave only the requested elements

excerpt = excerpt:gsub( '<[Nn][Oo][Ii][Nn][Cc][Ll][Uu][Dd][Ee]>.-</[Nn][Oo][Ii][Nn][Cc][Ll][Uu][Dd][Ee]>', '' )

if only then

if only == 'table' then

local tables = parser.getTables( excerpt )

excerpt = tables[1]

end

if only == 'tables' then

local tables = parser.getTables( excerpt )

excerpt = table.concat( tables, '\n' )

end

end

-- Filter various elements from the excerpt

if briefDates then

excerpt = Excerpt.fixDatesfilterFiles( excerpt, params.files )

excerpt = Excerpt.filterLists( excerpt, params.lists )

end

excerpt = Excerpt.filterTables( excerpt, params.tables )

excerpt = Excerpt.filterParagraphs( excerpt, params.paragraphs )

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

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

and not section -- and we're in the lead section

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

and #parser.getFiles( excerpt ) == 0 -- and there are're no files in the excerpt

then

excerpt = Excerpt.addInfoboxFile( excerpt )

end

-- Filter the templates by appending the templates blacklist to the templates filter

if config.blacklist then

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

if params.templates then

if string.sub( params.templates, 1, 1 ) == '-' then

params.templates = params.templates .. ',' .. blacklist

end

else

params.templates = '-' .. blacklist

end

end

excerpt = Excerpt.filterTemplates( excerpt, params.templates )

-- Leave only the requested elements

if params.only == 'file' or params.only == 'files' then

local files = parser.getFiles( excerpt )

excerpt = params.only == 'file' and files[1] or table.concat( files, '\n\n' )

end

if params.only == 'list' or params.only == 'lists' then

local lists = parser.getLists( excerpt )

excerpt = params.only == 'list' and lists[1] or table.concat( lists, '\n\n' )

end

if params.only == 'table' or params.only == 'tables' then

local tables = parser.getTables( excerpt )

excerpt = params.only == 'table' and tables[1] or table.concat( tables, '\n\n' )

end

if params.only == 'paragraph' or params.only == 'paragraphs' then

local paragraphs = parser.getParagraphs( excerpt )

excerpt = params.only == 'paragraph' and paragraphs[1] or table.concat( paragraphs, '\n\n' )

end

if params.only == 'template' or params.only == 'templates' then

local templates = parser.getTemplates( excerpt )

excerpt = params.only == 'template' and templates[1] or table.concat( templates, '\n\n' )

end

-- @todo Make more robust and move downwards

if params.briefDates then

excerpt = Excerpt.fixDates( excerpt )

end

-- Remove unwanted elements

excerpt = Excerpt.removeComments( excerpt )

excerpt = Excerpt.removeBlacklist( excerpt )

excerpt = Excerpt.removeSelfLinks( excerpt )

excerpt = Excerpt.removeNonFreeFiles( excerpt )

excerpt = Excerpt.removeBehaviorSwitches( excerpt )

-- Fix or remove the references

if params.references then

excerpt = Excerpt.fixReferences( excerpt, page, wikitext )

else

excerpt = Excerpt.removeReferences( excerpt )

end

-- Remove wikilinks

if not params.links then

excerpt = Excerpt.removeLinks( excerpt )

end

-- Link the bold text near the start of most leads and then remove it

if not section then

excerpt = Excerpt.linkBold( excerpt, page )

excerpt = Excerpt.linkBold( excerpt, page )

if not bold then

end

if not params.bold then

excerpt = Excerpt.removeBold( excerpt )

end

if references then

excerpt = Excerpt.fixReferences( excerpt, page, wikitext )

else

excerpt = Excerpt.removeReferences( excerpt )

end

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

excerpt = excerpt:gsub( '\n\n\n+', '\n\n' )

excerpt = mw.text.trim( excerpt )

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

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

Line 128 ⟶ 170:

-- Add tracking categories

if config.categories then

excerpt = Excerpt.addTrackingCategories( excerpt )

local currentTitle = mw.title.getCurrentTitle()

local contentCategory = config.categories.content

if contentCategory and currentTitle.isContentPage then

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

end

local namespaceCategory = config.categories[ currentTitle.namespace ]

if namespaceCategory then

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

end

end

-- LoadBuild the stylesfinal output

if params.inline then

local styles

return mw.text.trim( excerpt )

end

local tag = params.quote and 'blockquote' or 'div'

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

if config.styles then

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

block:node( styles )

end

if params.hat then

-- Combine and return the elements

local hat = Excerpt.getHat( page, section, params )

if inline then

block:node( hat )

return mw.text.trim( excerpt )

end

local tag = 'div'

if quote then

tag = 'blockquote'

end

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

block:node( excerpt )

if hat and not inlineparams.more then

hatlocal more = Excerpt.getHatgetReadMore( page, section, displayTitle, this, quote, only, edit, editIntro )

block:node( more )

end

return block

if more and not inline then

end

more = Excerpt.getReadMore( page, section, more )

-- Filter the files in the given wikitext against the given filter

function Excerpt.filterFiles( wikitext, filter )

if not filter then return wikitext end

local filters, isBlacklist = Excerpt.parseFilter( filter )

local files = parser.getFiles( wikitext )

for index, file in pairs( files ) do

local name = parser.getFileName( file )

if isBlacklist and ( Excerpt.matchFilter( index, filters ) or Excerpt.matchFilter( name, filters ) )

or not isBlacklist and ( not Excerpt.matchFilter( index, filters ) and not Excerpt.matchFilter( name, filters ) ) then

wikitext = Excerpt.removeString( wikitext, file )

end

end

return wikitext

end

-- Filter the lists in the given wikitext against the given filter

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

function Excerpt.filterLists( wikitext, filter )

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

if not filter then return wikitext end

local filters, isBlacklist = Excerpt.parseFilter( filter )

local lists = parser.getLists( wikitext )

for index, list in pairs( lists ) do

if isBlacklist and Excerpt.matchFilter( index, filters )

or not isBlacklist and not Excerpt.matchFilter( index, filters ) then

wikitext = Excerpt.removeString( wikitext, list )

end

end

return wikitext

end

-- Filter the tables in the given wikitext against the given filter

function Excerpt.filterTables( wikitext, filter )

if not filter then return wikitext end

local filters, isBlacklist = Excerpt.parseFilter( filter )

local tables = parser.getTables( wikitext )

for index, t in pairs( tables ) do

local id = string.match( t, '{|[^\n]-id%s*=%s*["\']?([^"\'\n]+)["\']?[^\n]*\n' )

if isBlacklist and ( Excerpt.matchFilter( index, filters ) or Excerpt.matchFilter( id, filters ) )

or not isBlacklist and ( not Excerpt.matchFilter( index, filters ) and not Excerpt.matchFilter( id, filters ) ) then

wikitext = Excerpt.removeString( wikitext, t )

end

end

return wikitext

end

-- Filter the paragraphs in the given wikitext against the given filter

function Excerpt.filterParagraphs( wikitext, filter )

if not filter then return wikitext end

local filters, isBlacklist = Excerpt.parseFilter( filter )

local paragraphs = parser.getParagraphs( wikitext )

for index, paragraph in pairs( paragraphs ) do

if isBlacklist and Excerpt.matchFilter( index, filters )

or not isBlacklist and not Excerpt.matchFilter( index, filters ) then

wikitext = Excerpt.removeString( wikitext, paragraph )

end

end

return wikitext

end

-- Filter the templates in the given wikitext against the given filter

function Excerpt.filterTemplates( wikitext, filter )

if not filter then return wikitext end

local filters, isBlacklist = Excerpt.parseFilter( filter )

local templates = parser.getTemplates( wikitext )

for index, template in pairs( templates ) do

local name = parser.getTemplateName( template )

if isBlacklist and ( Excerpt.matchFilter( index, filters ) or Excerpt.matchFilter( name, filters ) )

or not isBlacklist and ( not Excerpt.matchFilter( index, filters ) and not Excerpt.matchFilter( name, filters ) ) then

wikitext = Excerpt.removeString( wikitext, template )

end

end

return wikitext

end

Line 177 ⟶ 285:

file = parameters[file]

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

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

captions = pair[2]

for _, p in pairs( captions ) do

Line 207 ⟶ 315:

local fileName = 'File:' .. parser.getFileName( file )

local fileTitle = mw.title.new( fileName )

if fileTitle then

local fileDescription = fileTitle:getContent()

if not fileDescription or local fileDescription == '' thenfileTitle:getContent()

if not fileDescription or fileDescription == '' then

local frame = mw.getCurrentFrame()

local frame = mw.getCurrentFrame()
fileDescription = frame:preprocess( '{{' .. fileName .. '}}' ) -- try Commons

end

if fileDescription and string.match( fileDescription, '[Nn]on%-free' ) then

wikitext = Excerpt.removeString( wikitext, file )

end

end

end

Line 219 ⟶ 329:

end

function Excerpt.getHat( page, section, displayTitle, this, quote, only, edit, editIntroparams )

local hat

-- Build the main part of the hatnotetext

if params.this then

hat = params.this

elseif params.quote then

hat = Excerpt.getMessage( 'this' )

elseif params.only then

hat = Excerpt.getMessage( params.only )

else

hat = Excerpt.getMessage( 'section' )

Line 234 ⟶ 344:

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

-- Build the section link

if section then

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

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

else

hat = hat .. ' [[:' .. page .. '|' .. params.displayTitle .. ']].'

end

-- Build the edit link

local title = mw.title.new( page )

if edit then

local titleeditUrl = mw.title.new:fullUrl( page'action=edit' )

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

local editUrl = title:fullUrl( 'action=edit' )

hat = hat .. editUrl .. ' ' .. mw.message.new( 'editsection' ):plain()

if editIntro then

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

editUrl = title:fullUrl( 'action=edit&editintro=' .. editIntro )

end

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

hat = hat .. editUrl .. ' ' .. mw.message.new( 'editsection' ):plain()

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

end

if config.hat then

Line 265 ⟶ 370:

end

function Excerpt.getReadMore( page, section, more )

local link = "'''[[" .. page

if section then

link = link .. '#' .. section

end

linklocal text = '|' .Excerpt.getMessage( 'more' .. "]]'''")

link = link .. '|' .. text .. "]]'''"

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

return link

Line 278 ⟶ 384:

-- @todo Use parser.getParagraphs() to get the first paragraph

function Excerpt.fixDates( excerpt )

local startposstart = 1 -- skip initial templates

local s

local e = 0

repeat

startposstart = e + 1

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

until not s or s > startposstart

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

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

local year1, conjunction, year2excerptStart = mw.ustring.match( mw.ustring.sub( excerpt, s, e ), '(%d%d%d+)(.-)(%d%d%d+)' )

iflocal year1, andconjunction, year2 and= ( mw.ustringstring.match( conjunctionexcerptStart, '[(%d%d%d+)(.-–—]' ) or mw.ustring.match( conjunction, '{{%s*[sS]ndd%d%s*}}d+)' ) ) then

if year1 and year2 and ( string.match( conjunction, '[%-–—]' ) or string.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

end

Line 299 ⟶ 406:

end

-- Replace the first call to each reference defined outside of the textexcerpt for the full reference, to prevent undefined references

-- Then prefix the page title to the reference names to prevent conflicts

-- that is, replace <ref name="Foo"> for <ref name="Title of the article Foo">

Line 307 ⟶ 414:

-- @todo The current regex may fail in cases with both kinds of quotes, like <ref name="Darwin's book">

function Excerpt.fixReferences( excerpt, page, wikitext )

local references = parser.getReferences( excerpt )

local refNames = {}

local refNamefixed = {}

for _, reference in pairs( references ) do

local refBody

local name = parser.getTagAttribute( reference, 'name' )

local position = 1

if not fixed[ name ] then -- fix each reference only once

while position < mw.ustring.len( excerpt ) do

local content = parser.getTagContent( reference )

refName, position = mw.ustring.match( excerpt, '<%s*[Rr][Ee][Ff][^>]*name%s*=%s*["\']?([^"\'>]+)["\']?[^>]*/%s*>()', position )

if not content then -- reference is self-closing

if refName then

refName local full = mwparser.text.trimgetReference( refNameexcerpt, name )

if not refNames[ refName ]full then -- makethe surereference weis process eachnot refdefined namein onlythe onceexcerpt

table full = parser.insertgetReference( refNameswikitext, refNamename )

if full then

refName = Excerpt.escapeString( refName )

excerpt = excerpt:gsub( Excerpt.escapeString( reference ), Excerpt.escapeString( full ), 1 )

refBody = mw.ustring.match( excerpt, '<%s*[Rr][Ee][Ff][^>]*name%s*=%s*["\']?%s*' .. refName .. '%s*["\']?[^>/]*>.-<%s*/%s*[Rr][Ee][Ff]%s*>' )

if not refBody then -- the ref body is not in the excerpt

refBody = mw.ustring.match( wikitext, '<%s*[Rr][Ee][Ff][^>]*name%s*=%s*["\']?%s*' .. refName .. '%s*["\']?[^/>]*>.-<%s*/%s*[Rr][Ee][Ff]%s*>' )

if refBody then -- the ref body was found elsewhere

excerpt = mw.ustring.gsub( excerpt, '<%s*[Rr][Ee][Ff][^>]*name%s*=%s*["\']?%s*' .. refName .. '%s*["\']?[^>]*/?%s*>', mw.ustring.gsub( refBody, '%%', '%%%%' ), 1 )

end

table.insert( fixed, name )

end

end

else

position = mw.ustring.len( excerpt )

end

end

page = string.gsub( page, '"', '' ) -- remove any quotation marks from the page title

excerpt = mw.ustring.gsub( excerpt, '<%s*[Rr][Ee][Ff][^>]*name%s*=%s*["\']?([^"\'>/]+)["\']?[^>/]*(/?)%s*>', '<ref name="' .. page .. ' %1"%2>' )

excerpt = mw.ustring.gsub( excerpt, '<%s*[Rr][Ee][Ff]%s*group%s*=%s*["\']?[^"\'>/]+["\']%s*>', '<ref>' )

return excerpt

end

-- Remove blacklisted templates

function Excerpt.removeBlacklist( excerpt )

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

local filters = Excerpt.parseFilter( blacklist )

for _, template in pairs( parser.getTemplates( excerpt ) ) do

local templateName = parser.getTemplateName( template )

if Excerpt.matchFilter( templateName, filters ) then

excerpt = Excerpt.removeString( excerpt, template )

end

end

-- Prepend the page title to the reference names to prevent conflicts with other references in the transcluding page

excerpt = excerpt:gsub( '< *[Rr][Ee][Ff][^>]*name *= *["\']?([^"\'>/]+)["\']?[^>/]*(/?) *>', '<ref name="' .. page:gsub( '"', '' ) .. ' %1"%2>' )

-- Remove reference groups because they don't apply to the transcluding page

excerpt = excerpt:gsub( '< *[Rr][Ee][Ff] *group *= *["\']?[^"\'>/]+["\'] *>', '<ref>' )

return excerpt

end

Line 363 ⟶ 453:

end

return excerpt

end

function Excerpt.removeBold( excerpt )

return string.gsub( excerpt, "'''", '' )

end

function Excerpt.removeBehaviorSwitches( excerpt )

return string.excerpt:gsub( excerpt, '__[A-Z]+__', '' )

end

function Excerpt.removeComments( excerpt )

return string.excerpt:gsub( excerpt, '<!%-%-.-%-%->', '' )

end

function Excerpt.removeBold( excerpt )

return string.excerpt:gsub( excerpt, "'''", '' )

end

Line 418 ⟶ 504:

return nil -- instruct gsub to make no change

end

end, 1 ) -- "end" here terminates the anonymous replacement function(a, b) passed to gsub

end

return excerpt

end

function Excerpt.addTrackingCategories( excerpt )

-- Helper method to get the local name of a namespace and all its aliases

local currentTitle = mw.title.getCurrentTitle()

-- @param name Canonical name of the namespace, for example 'File'

local contentCategory = config.categories.content

-- @return Local name of the namespace and all aliases, for example {'File','Image','Archivo','Imagen'}

if contentCategory and currentTitle.isContentPage then

function Excerpt.getNamespaces( name )

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

local namespaces = mw.clone( mw.site.namespaces[ name ].aliases ) -- Clone because https://en.wikipedia.org/w/index.php?diff=1056921358

end

table.insert( namespaces, mw.site.namespaces[ name ].name )

local namespaceCategory = config.categories[ currentTitle.namespace ]

table.insert( namespaces, mw.site.namespaces[ name ].canonicalName )

if namespaceCategory then

return namespaces

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

end

return excerpt

end

Line 489 ⟶ 578:

-- Helper method to remove a string from a text

-- @param text Text from where to search forremove the string to remove

-- @param str String to remove

-- @return The given text with the string removed

Line 495 ⟶ 584:

local pattern = Excerpt.escapeString( str )

if #pattern > 9999 then -- strings longer than 10000 bytes can't be put into regexes

pattern = Excerpt.escapeString( mw.ustring.sub( str, 1, 999 ) ) .. '.-' .. Excerpt.escapeString( mw.ustring.sub( str, -999 ) )

end

return string.text:gsub( text, pattern, '' )

end

-- Helper method to convert a comma-separated list of numbers or min-max ranges into a list of booleans

-- @param filter Required. Comma-separated list of numbers or min-max ranges, for example '1,3-5'

-- @return Map from integers to booleans, for example {1=true,2=false,3=true,4=true,5=true}

-- @return Boolean indicating whether the flagsfilters should be treated as a blacklist or not

-- @todonote MergeMerging withthis into matchFilter is possible, but way too inefficient

function Excerpt.parseFilter( valuefilter )

local flagsfilters = {}

local blacklistisBlacklist = false

if string.sub( filter, 1, 1 ) == '-' then

if not value then return nil, false end

isBlacklist = true

if string.sub( value, 1, 1 ) == '-' then

filter = string.sub( filter, 2 )

blacklist = true

value = string.sub( value, 2 )

end

local rangesvalues = mw.text.split( valuefilter, ',' ) -- split rangesvalues: '1,3-5' to {'1','3-5'}

for _, rangevalue in pairs( rangesvalues ) do

rangevalue = mw.text.trim( rangevalue )

local min, max = mw.ustring.match( rangevalue, '^(%d+)%s*[-–—]%s*(%d+)$' ) -- '3-5' to min=3 max=5

if not max then min, max = string.match( rangevalue, '^((%d+))$' ) end -- '1' to min=1 max=1

if max then

for i = min, max do flagsfilters[ i ] = true end

else

flagsfilters[ rangevalue ] = true -- if we reach this point, the string had the form 'a,b,c' rather than '1,2,3'

end

end

local filter = {cache = {}, terms = filters}

return flags, blacklist

return filter, isBlacklist

end

-- Helper function to see if a value matches any of the given filters

function Excerpt.matchFilter( value, filtersfilter )

if not type(value) then== return"number" false endthen

return filter.terms[value]

value = tostring( value )

else

local lang = mw.language.getContentLanguage()

local lcvaluecached = lang:lcfirst( filter.cache[value )]

if cached ~= nil then

local ucvalue = lang:ucfirst( value )

return cached

for filter in pairs( filters ) do

if value == tostring( filter )

or lcvalue == filter

or ucvalue == filter

or ( not tonumber( filter ) and mw.ustring.match( value, filter ) ) then

return true

end

local lang = mw.language.getContentLanguage()

local lcvalue = lang:lcfirst(value)

local ucvalue = lang:ucfirst(value)

for term in pairs( filter.terms ) do

if value == tostring(term)

or type(term) == "string" and (

lcvalue == term

or ucvalue == term

or mw.ustring.match( value, term )

) then

filter.cache[value] = true

return true

end

end

filter.cache[value] = false

end

end

-- Entry points for backwards compatibility

-- @todo Verify that no one uses them and remove them

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

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

return Excerpt