Email is only an image - tag as spam?

[Martin Hepworth]

C. Jon Larsen wrote:
> On Thu, 4 Dec 2003, Martin Hepworth wrote:
>
>
>>I've got one for imap based email systems if you need that (should work
>>with MS-Exchange once you turn on the imap access).
>
>
> Could you post a link to that tool ?

find the script attached. You need to call it with the parameters as below.

the userid will need a spam and ham folder to contain the emails to be
learnt..

/usr/local/bin/learn_spam.pl -uid=spamupdate \ -pwd=passwd

only thing you'll to change is the myserver param at the top of the script.

As I said I got this from a SA email  list archive. Only change I made
was to add in   $imap->delete_message (@msgs);  in the read_email function.

You'll need the Mail::IMAPClient perl module to make it run too (CPAN
will have it).

Seems to work for me, but I use Courier imapd rather than
exchange.....YMMV !!!!

--
Martin Hepworth
Snr Systems Administrator
Solid State Logic
Tel: +44 (0)1865 842300

**********************************************************************

This email and any files transmitted with it are confidential and
intended solely for the use of the individual or entity to whom they
are addressed. If you have received this email in error please notify
the system manager.

This footnote confirms that this email message has been swept
for the presence of computer viruses and is believed to be clean.

**********************************************************************

-------------- next part --------------
#!/usr/bin/perl -w
use strict;
use Mail::IMAPClient;
use Shell;
use Env qw(HOME);
use Getopt::Long;

use File::Temp qw/ tempfile tempdir /;

my $imapserver = "myserver";

# set to 1 to enable imapclient debugging
my $debug = 0;

# set to 1 if running under cron (disables output)
my $cron = 1;

my $filename;
my $fh;

my %options =
(
 uid => undef,
 pwd => undef
);

my $cmdsts = GetOptions ("uid=s" => \$options{uid}, "pwd=s" =>
\$options{pwd});

if (!$options {uid}) { die "[SPAMASSASSIN] uid not set
(-uid=username)\n"; }
if (!$options {pwd}) { die "[SPAMASSASSIN] pwd not set
(-pwd=password)\n"; }

my $uid = $options{uid};
my $pwd = $options{pwd};

# login to imap server
my $imap = Mail::IMAPClient->new (Server=>$imapserver, User=>$uid, Password=>$pwd, Debug=>$debug)
        or die "Can't connect to $uid\@$imapserver: $@ $\n";

if ($imap)
{
  my $count;

  # Deal with spam first
  learn_mail ($HOME."/spam/", ".spam", "INBOX.spam", 0, "--spam --showdots --prefs-file=/opt/MailScanner/etc/spam.assassin.prefs.conf");

  # Now deal with ham
  learn_mail ($HOME."/ham/", ".ham", "INBOX.ham", 0, "--ham --showdots --prefs-file=/opt/MailScanner/etc/spam.assassin.prefs.conf");

}
else
{
  die "[SPAMASSASSIN] Unable to logon to IMAP mail account!
$options{uid}\n";
}

exit;

#
# read and learn mail from imap server
#
# arguments
#  $dir         directory to place retrieved messages in
#  $ext         file extension to use on retrieved messages
#  $folder      imap folder name on server
#  $shared      0 if imap folder is in users mailbox
#               1 if imap folder is in shared name space or
#  $sa_args     additional arguments to specify to sa-learn
#               (e.g. --spam or --ham)
#
sub learn_mail {
  my $dir = shift (@_);
  my $ext = shift (@_);
  my $folder = shift (@_);
  my $shared = shift (@_);
  my $sa_args = shift (@_);

  my $count = 0;

  # tidy up directory before run
  clear_directory ($dir, $ext);

  # read mail from server
  $count = read_mail ($dir, $ext, $folder, $shared);
  if ($count > 0)
  {
    # learn about mail
    sa_learn ($dir, $ext, $sa_args);

    # tidy up files after sa-learn is called
    clear_directory ($dir, $ext);
  }
}


#
# reads mail from an imap folder and saves in a local directory
#
# arguments
#  $dir         directory to place retrieved messages in
#  $ext         file extension to use on retrieved messages
#  $folder      imap folder name on server
#  $shared      0 if imap folder is in users mailbox
#               1 if imap folder is in shared name space or
sub read_mail {
  my $dir = shift (@_);
  my $ext = shift (@_);
  my $folder = shift (@_);
  my $shared = shift (@_);
  my $count = 0;
  my $target = "";

  if ($shared)
  {
    # use a shared public folder instead
    my ($prefix, $sep) = @{$imap->namespace->[2][0]}
       or die "Can't get shared folder namespace or seperator: $@\n";

    $target = $prefix.
       ($prefix =~ /\Q$sep\E$/ || $folder =~ /^\Q$sep/ ? "" : $sep).
       $folder;
  }
  else { $target = $folder; }

  $imap->select ($target) or die "Cannot select $target: $@\n";

  # If a shared public folder is required uncomment the following
  # lines and comment out the previous $imap->select line

  # read through all messages
  my @msgs = $imap->search("ALL");
  foreach my $msg (@msgs)
  {
    ($fh, $filename) = tempfile (SUFFIX => $ext, DIR => $dir);
    $imap->message_to_file ($fh, $msg);
    close $fh;
    $count++;
  }
  $imap->delete_message (@msgs);

  if ($cron == 0) { print "Retrieved $count messages from $target\n"; }

  return $count;
}

#
# Removes files in directory $dir with extension $ext
#
sub clear_directory{
  my $dir = shift (@_);
  my $ext = shift (@_);

  opendir (DIR, $dir) or die "Couldn't open dir: $dir\n";
  my @files = readdir (DIR);
  close (DIR);

  for (my $i = 0; $i <= $#files; $i++ )
  {
    if ($files[$i] =~ /.*?$ext$/) { unlink ($dir.$files[$i]); }
  }
}


#
# execute sa-learn command
#
sub sa_learn {
  my $dir = shift (@_);
  my $ext = shift (@_);
  my $type = shift (@_);
  my $learncmd = "/usr/local/bin/sa-learn ".$type." --dir ".$dir;

  if ($cron == 0) { $learncmd .= " --showdots"; }
  else { $learncmd .= " > /dev/null 2>&1"; }

  #
  # Run sa-learn script on spam directory
  #
  my $sh = Shell->new;
  my @args = ($learncmd);

  system (@args) == 0 or die "system @args failed: $?";
}