MailCleaner Anti Spam Community Edition

#!/usr/bin/perl

# Imap Interface to SpamAssassin Learn     v0.03B
# ------------------------------------     -----
#
# Connects to an imap server, and filters the messages from the INBOX
# and SpamTrap (unless otherwise told) through sa-learn
#
#  usage:
#    imap-sa-learn.pl <-hamfolder HAM> <-spamfolder SPAM>
#
#  Other options:
#    -skips nnn      skips over the first nnn messages in the folder(s)
#    -deletespam   after learning from a spam message, delete it
#    -delete-spam   (as above)
#    -dangerous-delete-ham   after learning from a ham (real email),
#                delete it. Most people don't want this...
#    -dangerous-delete-all   after learning from any message, delete
#                it, spam or ham
#
# Uses Mail::IMAPClient and SpamAssassin (sa-learn)
#
# Needs a version of SpamAssassin with the Bayesian filtering support,
# i.e. 2.50 or later
#
#      Nick Burch <nick@tirian.magd.ox.ac.uk>
#           25/06/2003
#
# Changes:
# Added SSL connection to work with Exchange 2007 from Nick's work.
# Added bogofilter to the script so it creates a new bogofilter and spamassassin filter.
# Added a seperate section for spam and ham. (we have seperate e-mail accounts for spam and ham.)
# Restored the debugging feature to IMAPClient. 
# Added several break points that give some debuggin information if there is an error.
#
# Thomas Nelson <tom AT perfectionpc.com>
#        15/04/2009
use Mail::IMAPClient;
use IO::Socket::SSL;

# Define our server and credentials here
# your details go below
my $spamusername = 'spam_account';
my $spampassword = 'spam_password';
my $spamserver = 'spam_server';

my $hamusername = 'ham_account';
my $hampassword = 'ham_password';
my $hamserver = 'ham_server';

# Define where to find messages
my $defspamfolder = 'INBOX';
my $defhamfolder = 'INBOX';
my $deletespam = 1;
my $deleteham = 1;
my $default = 1;

my $skips = 0;

# Output:  Normal (1), Debugging (2), or silent(0)?
my $debug = 0;

my @spams;
my @hams;

while(my $arg = shift) {
   if($arg eq "-spamfolder") {
     my $spam = shift;
     push @spams,$spam;
     print "Using spam folder $spam\n";
     $default = 0;
   }
   if($arg eq "-hamfolder") {
     my $ham = shift;
     push @hams,$ham;
     print "Using normal (ham) folder $ham\n";
     $default = 0;
   }
   if($arg eq "-deletespam" || $arg eq "-deletespams" || $arg eq "-delete-spam" || $arg eq "-delete-spams") {
     $deletespam = 1;
   }
   if($arg eq "-dangerous-delete-ham" || $arg eq "-dangerous-delete-hams") {
     $deleteham = 1;
   }
   if($arg eq "-dangerous-delete-all") {
     $deletespam = 1;
     $deleteham = 1;
   }
   if($arg eq "-skips" || $arg eq "-skip") {
     $skips = shift;
   }
   if($arg eq "-?" || $arg eq "-h") {
     print "Usage:\n";
     print "  imap-sa-learn.pl [-spamfolder f]* [-hamfolder f]*\n\n";
     print "with no argumnets, uses default folders\n";
     print "(a few other options exist, see the header of the program)\n";
     exit;
   }
}

if($default) {
   push @hams,$defhamfolder;
   push @spams,$defspamfolder;
}

my %folders;
$folders{'spam'} = \@spams;
$folders{'ham'} = \@hams;


# Open an SSL session to the IMAP server
# Handles the SSL setup, and gives us back a socket
my $ssl=new IO::Socket::SSL("$spamserver:imaps");
die ("Error connecting - $@") unless defined $ssl;
$ssl->autoflush(1);

# Connect to the IMAP server in peek (i.e. don't set read flag) mode
my $imap = Mail::IMAPClient->new(
             Debug    => $debug,
             Socket   => $ssl,
             Server   => $spamserver,
             User     => $spamusername,
             Password => $spampassword,
             Peek     => 1) or die "Cannot connect to $spamserver as $spamusername: $@";



   $type = 'spam';
   foreach my $folder (@{$folders{$type}}) {
      print "\nLooking in $type folder $folder\n";

      # Pick the folder
      $imap->select($folder) or die "Cannot connect to $folder on $spamserver: $@";

      # Enable peek mode
      $imap->Peek(1);

      # Fetch messages
      my @mails = ($imap->seen(),$imap->unseen);

      my $count = 0;

      foreach my $id (@mails) {
         $count++;
         if($count < $skips) { next; }

         print " Learning on $type message $id\n";
         my $mail = $imap->message_string($id) or die "Cannot fetch $id in $folder: $@";
         open SA, "| sa-learn -p /usr/mailcleaner/etc/mailscanner/spam.assassin.prefs.conf --siteconfigpath /usr/mailcleaner/share/spamassassin --no-sync --$type --single";
         print SA $mail;
         close SA;

     # Bogofilter section
         open BF, "| /usr/bogofilter/bin/bogofilter -s";
         print BF $mail;
         close BF;


         if($type eq "spam" && $deletespam) {
            # If you want to move the message rather than deleting it,
            # uncomment the line below, change the folder, but _don't_
            # remove the delete line!
            #$imap->append('TrashBin', $mail );

            print "Deleting Spam Message $id\n";
            $imap->delete_message($id);
         }
     
      if($deletespam) {
         # Only expunge now, rather than on every message
         $imap->expunge();
      }
   }
}

$imap->close;
$ssl->close;

# Open an SSL session to the IMAP server
# Handles the SSL setup, and gives us back a socket
my $ssl=new IO::Socket::SSL("$hamserver:imaps");
die ("Error connecting - $@") unless defined $ssl;
$ssl->autoflush(1);

# Connect to the IMAP server in peek (i.e. don't set read flag) mode
my $imap = Mail::IMAPClient->new(
             Debug    => $debug,
             Socket   => $ssl,
             Server   => $hamserver,
             User     => $hamusername,
             Password => $hampassword,
             Peek     => 1) or die "Cannot connect to $hamserver as $hamusername: $@";

   $type = 'ham';
   foreach my $folder (@{$folders{$type}}) {
      print "\nLooking in $type folder $folder\n";

      # Pick the folder
      $imap->select($folder) or die "Cannot connect to $folder as $hamusername: $@";

      # Enable peek mode
      $imap->Peek(1);

      # Fetch messages
      my @mails = ($imap->seen(),$imap->unseen);

      my $count = 0;

      foreach my $id (@mails) {
         $count++;
         if($count < $skips) { next; }

         print " Learning on $type message $id\n";
         my $mail = $imap->message_string($id) or die "Cannot fetch $id in $folder: $@";
         open SA, "| sa-learn -p /usr/mailcleaner/etc/mailscanner/spam.assassin.prefs.conf --siteconfigpath /usr/mailcleaner/share/spamassassin --no-sync --$type --single";
         print SA $mail;
         close SA;

     # Bogofilter section
         open BF, "| /usr/bogofilter/bin/bogofilter -n";
         print BF $mail;
         close BF;

         if($deleteham) {
            print "Deleting Ham (normal email) Message $id\n";
            $imap->delete_message($id)  or die "Cannot delete $id in $folder: $@";
         }

      if($deleteham) {
         # Only expunge now, rather than on every message
         $imap->expunge() or die "Cannot empty trash in $hamusername: $@";
      }
   }
}

print "\nNow rebuilding the Bayesian filters\n";
`sa-learn -p /usr/mailcleaner/etc/mailscanner/spam.assassin.prefs.conf --siteconfigpath /usr/mailcleaner/share/spamassassin --sync`;

$imap->close;
$ssl->close;
exit;