skandinavien-wiki.net

Modul:UrlCheck: Unterschied zwischen den Versionen

Modul Diskussion

Modul:UrlCheck (Quelltext anzeigen)

Version vom 11. Februar 2023, 21:58 Uhr

238 Bytes entfernt ,  vor 3 Jahren
K
30 Versionen von wikivoyage:Modul:UrlCheck importiert
KKeine Bearbeitungszusammenfassung
K (30 Versionen von wikivoyage:Modul:UrlCheck importiert)
 
(26 dazwischenliegende Versionen von 3 Benutzern werden nicht angezeigt)
Zeile 1: Zeile 1:
local uc = {}
-- module variable and administration
 
local uc = {
uc.msg = {
moduleInterface = {
[0] = 'No error detected',
suite  = 'UrlCheck',
[1] = 'Host with non-ASCII characters',
serial = '2023-01-17',
[2] = 'Host is IP address',
item  = 40849609
[3] = 'URL is empty',
}
[4] = 'URL has more then 2048 characters',
[5] = 'URL contains control marks or spaces',
[6] = 'Missing or wrong protocol',
[7] = 'Host starts with slash / character',
[8] = 'Host contains invalid character combinations',
[9] = 'More than one commercial ats @ in host detected',
[10] = 'Commercial at @ detected but user or host are missing',
[11] = 'More than one colon : in user detected',
[12] = 'Colon : detected but user or password are missing',
[13] = 'User has more than 64 characters',
[14] = 'Host ist empty',
[15] = 'More than one colon : in host detected',
[16] = 'Colon : detected but host or port are missing',
[17] = 'Port out of range of 0 ... 65535',
[18] = 'Host has more than 253 characters',
[19] = 'Host with missing dot as domain separator',
[20] = 'Host has dot but no top-level domain',
[21] = 'Unknown top-level domain',
[22] = 'Invalid host structure',
}
}


function uc.ip4( address )
function uc.ip4( address )
local parts = { address:match( '(%d+)%.(%d+)%.(%d+)%.(%d+)' ) }
local value
local value
local parts = { address:match("(%d+)%.(%d+)%.(%d+)%.(%d+)") }
if #parts == 4 then
if #parts == 4 then
for _,value in pairs( parts ) do
for _, value in pairs( parts ) do
if tonumber( value ) < 0 or tonumber( value ) > 255
if tonumber( value ) < 0 or tonumber( value ) > 255 then
then return 0 end
return false
end
end
end
return 1 -- ok
return true -- ok
else
return 0
end
end
return false
end
end


function uc.isUrl( url )
function uc.isUrl( url, skipPathCheck )
-- return codes 0 through 2 reserved
-- return codes 0 through 2 reserved
if ( url == nil ) or ( type( url ) ~= 'string' ) then return 3 end
if not url or type( url ) ~= 'string' then
return 3
end


local s = mw.text.trim( url )
local s = mw.text.trim( url )
if s == '' then return 3 end
if s == '' then
if #s > 2048 then return 4 end
return 3
-- limitation because of search engines or IE
elseif #s > 2048 then -- limitation because of search engines or IE
if s:find( '%s' ) or s:find( '%c' ) or s:match( '^%.' ) then return 5 end
return 4
elseif s:find( '%s' ) or s:find( '%c' ) or s:match( '^%.' ) then
return 5
end
-- https://max:muster@www.example.com:8080/index.html?p1=A&p2=B#ressource
-- https://max:muster@www.example.com:8080/index.html?p1=A&p2=B#ressource
Zeile 55: Zeile 41:
-- protocol
-- protocol
local count
local count
s,count = s:gsub( '^http://', '' )
s, count = s:gsub( '^https?://', '' )
if count == 0 then
if count == 0 then
s,count = s:gsub( '^https://', '' )
s, count = s:gsub( '^//', '' )
-- if count == 0 then
end
-- s,count = s:gsub( '^//', '' )
if count == 0 then -- missing or wrong protocol
-- end
return 6
end
end
if count == 0 then return 6 end -- missing or wrong protocol


local user = ''
local user = ''
Zeile 68: Zeile 53:
local host = ''
local host = ''
local port = ''
local port = ''
local path = ''
local aPath = ''
local topLevel = ''
local topLevel = ''
local at


-- split path from host
-- split path from host
at = s:find( '/' )
local at = s:find( '/' )
if at ~= nil then
if at then
path = s:sub( at + 1, #s )
aPath = s:sub( at + 1, #s )
s = s:sub( 1, at - 1 )
s = s:sub( 1, at - 1 )
if not s then return 7 end
if not s then
return 7
end
end
end


-- future: add path check
-- path check
-- split at '/', last part: t == mw.uri.encode( t ) ?
if not skipPathCheck and aPath ~= '' then
if not aPath:match( '^[-A-Za-z0-9_.,~%%%+&:;#*?!=()@/\128-\255]*$' ) then
return 23
end
end


if s:find( '%.%.' ) or s:find( '%.@' ) or s:find( '@[%.%-]' )
if s:find( '%.%.' ) or s:find( '%.@' ) or s:find( '@[%.%-]' ) or s:find( '%-%.' )
or s:find( '%-%.' ) or s:find( '%.%-' ) or s:find( '%./' ) or s:find( '/%.' )
or s:find( '%.%-' ) or s:find( '%./' ) or s:find( '/%.' ) then
then return 8 end
return 8
end


-- user and password
-- user and password
_,count = s:gsub( '@', '@' )
s, count = s:gsub( '@', '@' )
if count > 1 then return 9 end
if count > 1 then
if count == 1 then
return 9
elseif count == 1 then
at = s:find( '@' )
at = s:find( '@' )
user = s:sub( 1, at - 1 )
user = s:sub( 1, at - 1 )
host = s:sub( at + 1, #s )
host = s:sub( at + 1, #s )
if not user or not s then return 10 end
if not user or not s then
return 10
end


_,count = user:gsub( ':', ':' )
user, count = user:gsub( ':', ':' )
if count > 1 then return 11 end
if count > 1 then
if count == 1 then
return 11
elseif count == 1 then
at = user:find( ':' )
at = user:find( ':' )
password = user:sub( at + 1, #user )
password = user:sub( at + 1, #user )
user = user:sub( 1, at - 1 )
user = user:sub( 1, at - 1 )
if not user or not password then return 12 end
if not user or not password then
if #user > 64 then return 13 end
return 12
elseif #user > 64 then
return 13
end
end
end
else
else
host = s
host = s
end
end
if host == '' then return 14 end
if host == '' then
return 14
end


-- host and port
-- host and port
_,count = host:gsub( ':', ':' )
host, count = host:gsub( ':', ':' )
if count > 1 then return 15 end
if count > 1 then
if count == 1 then
return 15
elseif count == 1 then
at = host:find( ':' )
at = host:find( ':' )
port = host:sub( at + 1, #host )
port = host:sub( at + 1, #host )
host = host:sub( 1, at - 1 )
host = host:sub( 1, at - 1 )
if not host or not port then return 16 end
if not host or not port then
if ( port:match( '^[1-9]%d*$' ) == nil ) or
return 16
( tonumber( port ) > 65535 ) then return 17 end
elseif not port:match( '^[1-9]%d*$' ) or tonumber( port ) > 65535 then
return 17
end
end
end


-- handle host part
-- handle host part
if #host > 253 then return 18 end
if #host > 253 then
return 18
end


-- getting top-level domain
-- getting top-level domain
at = host:match( '^.*()%.' ) -- find last dot
at = host:match( '^.*()%.' ) -- find last dot
if at == nil then return 19 end
if not at then
return 19
end
topLevel = host:sub( at + 1, #host )
topLevel = host:sub( at + 1, #host )
if not topLevel then return 20 end
if not topLevel then
return 20
end


-- future: check of top-level domain
-- future: check of top-level domain


if uc.ip4( host ) == 1 then return 2 end -- is ip4 address
if uc.ip4( host ) then -- is ip4 address
if not mw.ustring.match( host, '^[%w%.%-]+%.%a%a+$' ) then return 22 end
return 2
if not host:match( '^[%w%.%-]+%.%a%a+$' ) then
elseif not mw.ustring.match( host, '^[ะ-๏%w%.%-]+%.%a%a+$' ) then
-- Thai diacritical marks ะ (0E30) - ๏ (0E4F)
return 22
elseif not host:match( '^[%w%.%-]+%.%a%a+$' ) then
return 1 -- matches domain only in UTF 8 mode
return 1 -- matches domain only in UTF 8 mode
end
end


return 0
return 0
end
function uc.uriEncodePath( url )
local at, to = url:find( '[^/]/[^/]' )
if at then
local domain = url:sub( 1, at + 1 )
local aPath = url:sub( at + 2, #url )
url = domain .. mw.uri.encode( aPath, 'PATH' )
end
return url
end
end


function uc.checkUrl( frame )
function uc.checkUrl( frame )
local args = frame.args
local args = frame.args
args.url   = args.url or ''
local pArgs = frame:getParent().args
args.show = args.show or ''
args.url   = args.url or pArgs.url or ''
args.show   = args.show or pArgs.show or ''


local result = uc.isUrl( args.url )
local result = uc.isUrl( args.url, false )
if args.show == 'msg' then
if args.show:lower() == 'msg' then
if uc.msg[result] == nil then
local ui = mw.loadData( 'Module:UrlCheck/i18n')
return 'Unknown error'
if ui[ result ] then
return ui[ result ]
else
else
return uc.msg[result]
return ui.unknown
end
end
else
return result
end
end
return result
end
function uc.encodePath( frame )
local args  = frame.args
local pArgs = frame:getParent().args
args.url    = args.url or args[ 1 ] or pArgs.url or pArgs[ 1 ] or ''
return uc.uriEncodePath( args.url )
end
end


return uc
return uc
Abgerufen von „https://skandinavien-wiki.net/wiki/Spezial:Mobiler_Unterschied/22740...22765“