code/Filter/liven_urls.filter

   1 # Copyright 2005 Davor Ocelic (docelic@mail.inet.hr)
   2 # Copyright 2005-2007 Interchange Development Group and others
   3 #
   4 # This program is free software; you can redistribute it and/or modify
   5 # it under the terms of the GNU General Public License as published by
   6 # the Free Software Foundation; either version 2 of the License, or
   7 # (at your option) any later version.  See the LICENSE file for details.
   8 #
   9 # $Id: liven_urls.filter,v 1.3 2007-03-30 23:40:44 pajamian Exp $
  10
  11 CodeDef liven_urls Filter
  12 CodeDef liven_urls Description Make URLs clickable
  13 CodeDef liven_urls Routine <<EOR
  14
  15 my %regexps = (
  16
  17 http => <<'ENDR',
  18 (?:https?://(?:(?:(?:(?:(?:[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$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;:@&=])*))?)?)
  19 ENDR
  20
  21
  22 ftp => <<'ENDR',
  23 (?:ftp://(?:(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[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$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[?:@&=])*))*)(?:;type=[AIDaid])?)?)
  24 ENDR
  25
  26
  27 mailto => <<'ENDR',
  28 (?:mailto:(?:(?:[a-zA-Z\d$\-_.+!*'(),;/?:@&=]|(?:%[a-fA-F\d]{2}))+))
  29 ENDR
  30
  31
  32 #news => <<'ENDR',
  33 #(?:news:(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;/?:&=])+@(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3})))|(?:[a-zA-Z](?:[a-zA-Z\d]|[_.+-])*)|\*))
  34 #ENDR
  35
  36
  37 #nntp => <<'ENDR',
  38 #(?:nntp://(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?)/(?:[a-zA-Z](?:[a-zA-Z\d]|[_.+-])*)(?:/(?:\d+))?)
  39 #ENDR
  40
  41
  42 #telnet => <<'ENDR',
  43 #(?:telnet://(?:(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;?&=])*)(?::(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;?&=])*))?@)?(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?))/?)
  44 #ENDR
  45
  46
  47 #gopher => <<'ENDR',
  48 #(?:gopher://(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?)(?:/(?:[a-zA-Z\d$\-_.+!*'(),;/?:@&=]|(?:%[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$\-_.+!*'(),;/?:@&=]|(?:%[a-fA-F\d]{2}))*))?)?)?)?)
  49 #ENDR
  50
  51
  52 #wais => <<'ENDR',
  53 #(?:wais://(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?)/(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[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$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;:@&=])*))?)
  54 #ENDR
  55
  56
  57 #file => <<'ENDR',
  58 #(?:file://(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))|localhost)?/(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[?:@&=])*)(?:/(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[?:@&=])*))*))
  59 #ENDR
  60
  61
  62 #prospero => <<'ENDR',
  63 #(?:prospero://(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?)/(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[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$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[?:@&])*)))*)
  64 #ENDR
  65
  66
  67 #ldap => <<'ENDR',
  68 #(?:ldap://(?:(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?))?/(?:(?:(?:(?:(?:(?:(?:[a-zA-Z\d]|%(?:3\d|[46][a-fA-F\d]|[57][Aa\d]))|(?:%20))+|(?:OID|oid)\.(?:(?:\d+)(?:\.(?:\d+))*))(?:(?:%0[Aa])?(?:%20)*)=(?:(?:%0[Aa])?(?:%20)*))?(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[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}))+)))?)?)?)
  69 #ENDR
  70
  71
  72 #z3950 => <<'ENDR',
  73 #(?:(?: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}))+))*)?))
  74 #ENDR
  75
  76
  77 #cid => <<'ENDR',
  78 #(?:cid:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;?:@&=])*))
  79 #ENDR
  80
  81
  82 #mid => <<'ENDR',
  83 #(?:mid:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;?:@&=])*)(?:/(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;?:@&=])*))?)
  84 #ENDR
  85
  86
  87 #vemmi => <<'ENDR',
  88 #(?:vemmi://(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?)(?:/(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[/?:@&=])*)(?:(?:;(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[/?:@&])*)=(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[/?:@&])*))*))?)
  89 #ENDR
  90
  91
  92 #imap => <<'ENDR',
  93 #(?: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}))|[&=~:@/])+)))?)))?)
  94 #ENDR
  95
  96
  97 #nfs => <<'ENDR',
  98 #(?: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})|[:@&=+])*))*)?)))
  99 #ENDR
 100
 101 ); # my %regexps
 102
 103 chomp $regexps{$_} for keys %regexps;
 104
 105
 106 sub {
 107         my ($val,$tag,@arg) = @_;
 108
 109         @arg or @arg = (qw/http ftp mailto/);
 110         @arg = grep { $regexps{$_} } @arg;
 111         @arg or return $val;
 112         my $match_url = join '|', @regexps{@arg};
 113
 114         $val =~ s/($match_url)/<a href="$1">$1<\/a>/gsi;
 115         $val
 116 }
 117 EOR
 118