[interchange-cvs] interchange - docelic modified code/Filter/liven_urls.filter

interchange-cvs at icdevgroup.org interchange-cvs at icdevgroup.org
Thu Aug 11 19:21:22 EDT 2005


User:      docelic
Date:      2005-08-11 23:21:22 GMT
Added:     code/Filter liven_urls.filter
Log:
* Add liven_urls filter

  Filter can make all kinds of URLs clickable.

  To save on processing time, only http, ftp and mailto links are
  searched for by default. These three (out of about 15 types
  recognized) are also the default set that the filter looks for.

  You can further refine the search by providing URL type names
  to the filter:

    [filter liven_urls]
    [/filter]

    [filter liven_urls.http]
    [/filter]

    [filter liven_urls.http.mailto]
    [/filter]

Revision  Changes    Path
1.1                  interchange/code/Filter/liven_urls.filter


rev 1.1, prev_rev 1.0
Index: liven_urls.filter
===================================================================
# Copyright 2005 Davor Ocelic (docelic at mail.inet.hr)
# Copyright 2005 Interchange Development Group (http://www.icdevgroup.org/)
# Licensed under the GNU GPL v2. See file LICENSE for details.
# $Id: liven_urls.filter,v 1.1 2005/08/11 23:21:22 docelic Exp $

CodeDef liven_urls Filter
CodeDef liven_urls Description Make URLs clickable
CodeDef liven_urls Routine <<EOR

my %regexps = (

http => <<'ENDR',
(?: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}))|[;:@&=])*))?)?)
ENDR


ftp => <<'ENDR',
(?: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])?)?)
ENDR


mailto => <<'ENDR',
(?:mailto:(?:(?:[a-zA-Z\d$\-_.+!*'(),;/?:@&=]|(?:%[a-fA-F\d]{2}))+))
ENDR


#news => <<'ENDR',
#(?: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]|[_.+-])*)|\*))
#ENDR


#nntp => <<'ENDR',
#(?: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+))?)
#ENDR


#telnet => <<'ENDR',
#(?: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+))?))/?)
#ENDR


#gopher => <<'ENDR',
#(?: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}))*))?)?)?)?)
#ENDR


#wais => <<'ENDR',
#(?: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}))|[;:@&=])*))?)
#ENDR


#file => <<'ENDR',
#(?: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}))|[?:@&=])*))*))
#ENDR


#prospero => <<'ENDR',
#(?: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}))|[?:@&])*)))*)
#ENDR


#ldap => <<'ENDR',
#(?: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])?(?:%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])?(?:%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$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))*))(?:(?:(?:%0[Aa])?(?:%20)*)\+(?:(?:%0[Aa])?(?:%20)*)(?:(?:(?:(?:(?:[a-zA-Z\d]|%(?:3\d|[46][a-fA-F\d]|[57][Aa\d]))|(?:%20))+|(?:OID|oid)\.(?:(?:\d+)(?:\.(?:\d+))*))(?:(?:%0[Aa])?(?:%20)*)=(?:(?:%0[Aa])?(?:%20)*))?(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))*)))*))*(?:(?:(?:%0[Aa])?(?:%20)*)(?:[;,])(?:(?:%0[Aa])?(?:%20)*))?)(?:\?(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))+)(?:,(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))+))*)?)(?:\?(?:base|one|sub)(?:\?(?:((?:[a-zA-Z\d$\-_.+!*'(),;/?:@&=]|(?:%[a-fA-F\d]{2}))+)))?)?)?)
#ENDR


#z3950 => <<'ENDR',
#(?:(?: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}))+))*)?))
#ENDR


#cid => <<'ENDR',
#(?:cid:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;?:@&=])*))
#ENDR


#mid => <<'ENDR',
#(?:mid:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;?:@&=])*)(?:/(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;?:@&=])*))?)
#ENDR


#vemmi => <<'ENDR',
#(?: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}))|[/?:@&])*))*))?)
#ENDR


#imap => <<'ENDR',
#(?: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}))|[&=~:@/])+)))?)))?)
#ENDR


#nfs => <<'ENDR',
#(?: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})|[:@&=+])*))*)?)))
#ENDR

); # my %regexps

chomp $regexps{$_} for keys %regexps;


sub {
	my ($val,$tag, at arg) = @_;

	@arg or @arg = (qw/http ftp mailto/);
	@arg = grep { $regexps{$_} } @arg;
	@arg or return $val;
	my $match_url = join '|', @regexps{@arg};

	$val =~ s/($match_url)/<a href="$1">$1<\/a>/gs;
	$val
}
EOR









More information about the interchange-cvs mailing list