NYCPHP Meetup

[Phillip Powell]

I would think to simply support "https" all you would have to do is 
change "http://" to ((?:https)|(?:http://...))

Then again, it's pretty beastly as it is!  If that's not a call for a 
global included variable, what is?

Phil

James B. Wetterau Jr. wrote:

> Jayesh Sheth says:
> > Hello all,
> >
> > I came up with this Perl-style regular expression to validate URLs.
> ...
> > Any suggestions or corrections?
> ...
>
> A Perl expert of some repute did the hard work of reading all the
> relevant protocol specs, BNF notation, etc., and came up with this
> valid URL parsing regexp.  Anything shorter is likely to miss some
> special case.
>
> This is an article about how to do this:
> http://www.foad.org/~abigail/Perl/url2.html
> (Note that there were some judgement calls involved in interpretation
> of some of the edge cases.)
>
> This is the URL for the actual regexp:
> http://www.foad.org/~abigail/Perl/url3.regex
>
> This is the regexp (note that it is broken up into many lines but 
> actually needs to be
> one long line; note also that it does not support https):
>
> (?:http://(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.
> )*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)
> ){3}))(?::(?:\d+))?)(?:/(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F
> \d]{2}))|[;:@&=])*)(?:/(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{
> 2}))|[;:@&=])*))*)(?:\?(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{
> 2}))|[;:@&=])*))?)?)|(?:ftp://(?:(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?
> :%[a-fA-F\d]{2}))|[;?&=])*)(?::(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-
> fA-F\d]{2}))|[;?&=])*))?@)?(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-
> )*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?
> :\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?))(?:/(?:(?:(?:(?:[a-zA-Z\d$\-_.+!
> *'(),]|(?:%[a-fA-F\d]{2}))|[?:@&=])*)(?:/(?:(?:(?:[a-zA-Z\d$\-_.+!*'()
> ,]|(?:%[a-fA-F\d]{2}))|[?:@&=])*))*)(?:;type=[AIDaid])?)?)|(?:news:(?:
> (?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;/?:&=])+@(?:(?:(
> ?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[
> a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3})))|(?:[a-zA-Z](
> ?:[a-zA-Z\d]|[_.+-])*)|\*))|(?:nntp://(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[
> a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d
> ])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?)/(?:[a-zA-Z](?:[a-zA-Z
> \d]|[_.+-])*)(?:/(?:\d+))?)|(?:telnet://(?:(?:(?:(?:(?:[a-zA-Z\d$\-_.+
> !*'(),]|(?:%[a-fA-F\d]{2}))|[;?&=])*)(?::(?:(?:(?:[a-zA-Z\d$\-_.+!*'()
> ,]|(?:%[a-fA-F\d]{2}))|[;?&=])*))?@)?(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a
> -zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d]
> )?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?))/?)|(?:gopher://(?:(?:
> (?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:
> (?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+
> ))?)(?:/(?:[a-zA-Z\d$\-_.+!*'(),;/?:@&=]|(?:%[a-fA-F\d]{2}))(?:(?:(?:[
> a-zA-Z\d$\-_.+!*'(),;/?:@&=]|(?:%[a-fA-F\d]{2}))*)(?:%09(?:(?:(?:[a-zA
> -Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;:@&=])*)(?:%09(?:(?:[a-zA-Z\d$
> \-_.+!*'(),;/?:@&=]|(?:%[a-fA-F\d]{2}))*))?)?)?)?)|(?:wais://(?:(?:(?:
> (?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:
> [a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?
> )/(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))*)(?:(?:/(?:(?:[a-zA
> -Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))*)/(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(
> ?:%[a-fA-F\d]{2}))*))|\?(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]
> {2}))|[;:@&=])*))?)|(?:mailto:(?:(?:[a-zA-Z\d$\-_.+!*'(),;/?:@&=]|(?:%
> [a-fA-F\d]{2}))+))|(?:file://(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]
> |-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:
> (?:\d+)(?:\.(?:\d+)){3}))|localhost)?/(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'()
> ,]|(?:%[a-fA-F\d]{2}))|[?:@&=])*)(?:/(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(
> ?:%[a-fA-F\d]{2}))|[?:@&=])*))*))|(?:prospero://(?:(?:(?:(?:(?:[a-zA-Z
> \d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)
> *[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?)/(?:(?:(?:(?
> :[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[?:@&=])*)(?:/(?:(?:(?:[a-
> zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[?:@&=])*))*)(?:(?:;(?:(?:(?:[
> a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[?:@&])*)=(?:(?:(?:[a-zA-Z\d
> $\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[?:@&])*)))*)|(?:ldap://(?:(?:(?:(?:
> (?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:
> [a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?
> ))?/(?:(?:(?:(?:(?:(?:(?:[a-zA-Z\d]|%(?:3\d|[46][a-fA-F\d]|[57][Aa\d])
> )|(?:%20))+|(?:OID|oid)\.(?:(?:\d+)(?:\.(?:\d+))*))(?:(?:%0[Aa])?(?:%2
> 0)*)=(?:(?:%0[Aa])?(?:%20)*))?(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F
> \d]{2}))*))(?:(?:(?:%0[Aa])?(?:%20)*)\+(?:(?:%0[Aa])?(?:%20)*)(?:(?:(?
> :(?:(?:[a-zA-Z\d]|%(?:3\d|[46][a-fA-F\d]|[57][Aa\d]))|(?:%20))+|(?:OID
> |oid)\.(?:(?:\d+)(?:\.(?:\d+))*))(?:(?:%0[Aa])?(?:%20)*)=(?:(?:%0[Aa])
> ?(?:%20)*))?(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))*)))*)(?:(
> ?:(?:(?:%0[Aa])?(?:%20)*)(?:[;,])(?:(?:%0[Aa])?(?:%20)*))(?:(?:(?:(?:(
> ?:(?:[a-zA-Z\d]|%(?:3\d|[46][a-fA-F\d]|[57][Aa\d]))|(?:%20))+|(?:OID|o
> id)\.(?:(?:\d+)(?:\.(?:\d+))*))(?:(?:%0[Aa])?(?:%20)*)=(?:(?:%0[Aa])?(
> ?:%20)*))?(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))*))(?:(?:(?:
> %0[Aa])?(?:%20)*)\+(?:(?:%0[Aa])?(?:%20)*)(?:(?:(?:(?:(?:[a-zA-Z\d]|%(
> ?:3\d|[46][a-fA-F\d]|[57][Aa\d]))|(?:%20))+|(?:OID|oid)\.(?:(?:\d+)(?:
> \.(?:\d+))*))(?:(?:%0[Aa])?(?:%20)*)=(?:(?:%0[Aa])?(?:%20)*))?(?:(?:[a
> -zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))*)))*))*(?:(?:(?:%0[Aa])?(?:%2
> 0)*)(?:[;,])(?:(?:%0[Aa])?(?:%20)*))?)(?:\?(?:(?:(?:(?:[a-zA-Z\d$\-_.+
> !*'(),]|(?:%[a-fA-F\d]{2}))+)(?:,(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-f
> A-F\d]{2}))+))*)?)(?:\?(?:base|one|sub)(?:\?(?:((?:[a-zA-Z\d$\-_.+!*'(
> ),;/?:@&=]|(?:%[a-fA-F\d]{2}))+)))?)?)?)|(?:(?:z39\.50[rs])://(?:(?:(?
> :(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?
> :[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))
> ?)(?:/(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))+)(?:\+(?:(?:
> [a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))+))*(?:\?(?:(?:[a-zA-Z\d$\-_
> .+!*'(),]|(?:%[a-fA-F\d]{2}))+))?)?(?:;esn=(?:(?:[a-zA-Z\d$\-_.+!*'(),
> ]|(?:%[a-fA-F\d]{2}))+))?(?:;rs=(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA
> -F\d]{2}))+)(?:\+(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))+))*)
> ?))|(?:cid:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;?:@&=
> ])*))|(?:mid:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;?:@
> &=])*)(?:/(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;?:@&=]
> )*))?)|(?:vemmi://(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z
> \d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\
> .(?:\d+)){3}))(?::(?:\d+))?)(?:/(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a
> -fA-F\d]{2}))|[/?:@&=])*)(?:(?:;(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a
> -fA-F\d]{2}))|[/?:@&])*)=(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d
> ]{2}))|[/?:@&])*))*))?)|(?:imap://(?:(?:(?:(?:(?:(?:(?:[a-zA-Z\d$\-_.+
> !*'(),]|(?:%[a-fA-F\d]{2}))|[&=~])+)(?:(?:;[Aa][Uu][Tt][Hh]=(?:\*|(?:(
> ?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[&=~])+))))?)|(?:(?:;[
> Aa][Uu][Tt][Hh]=(?:\*|(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2
> }))|[&=~])+)))(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[
> &=~])+))?))@)?(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])
> ?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:
> \d+)){3}))(?::(?:\d+))?))/(?:(?:(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:
> %[a-fA-F\d]{2}))|[&=~:@/])+)?;[Tt][Yy][Pp][Ee]=(?:[Ll](?:[Ii][Ss][Tt]|
> [Ss][Uu][Bb])))|(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))
> |[&=~:@/])+)(?:\?(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[
> &=~:@/])+))?(?:(?:;[Uu][Ii][Dd][Vv][Aa][Ll][Ii][Dd][Ii][Tt][Yy]=(?:[1-
> 9]\d*)))?)|(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[&=~
> :@/])+)(?:(?:;[Uu][Ii][Dd][Vv][Aa][Ll][Ii][Dd][Ii][Tt][Yy]=(?:[1-9]\d*
> )))?(?:/;[Uu][Ii][Dd]=(?:[1-9]\d*))(?:(?:/;[Ss][Ee][Cc][Tt][Ii][Oo][Nn
> ]=(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[&=~:@/])+)))?))
> )?)|(?:nfs:(?:(?://(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-
> Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:
> \.(?:\d+)){3}))(?::(?:\d+))?)(?:(?:/(?:(?:(?:(?:(?:[a-zA-Z\d\$\-_.!~*'
> (),])|(?:%[a-fA-F\d]{2})|[:@&=+])*)(?:/(?:(?:(?:[a-zA-Z\d\$\-_.!~*'(),
> ])|(?:%[a-fA-F\d]{2})|[:@&=+])*))*)?)))?)|(?:/(?:(?:(?:(?:(?:[a-zA-Z\d
> \$\-_.!~*'(),])|(?:%[a-fA-F\d]{2})|[:@&=+])*)(?:/(?:(?:(?:[a-zA-Z\d\$\
> -_.!~*'(),])|(?:%[a-fA-F\d]{2})|[:@&=+])*))*)?))|(?:(?:(?:(?:(?:[a-zA-
> Z\d\$\-_.!~*'(),])|(?:%[a-fA-F\d]{2})|[:@&=+])*)(?:/(?:(?:(?:[a-zA-Z\d
> \$\-_.!~*'(),])|(?:%[a-fA-F\d]{2})|[:@&=+])*))*)?)))
>
>
>
>
>
>
>
> _______________________________________________
> talk mailing list
> talk at lists.nyphp.org
> http://lists.nyphp.org/mailman/listinfo/talk
>


-- 
---------------------------------------------------------------------------------
Phil Powell
Multimedia Programmer
ADNET Systems., Inc.
11260 Roger Bacon Drive Suite 403
Reston, VA  20191
#: (703) 709-7218 x107 
Fax: (703) 709-7219