qpsmtpd/plugins/dspam

#!perl -w

=head1 NAME

dspam - dspam integration for qpsmtpd

=head1 DESCRIPTION

qpsmtpd plugin that uses dspam to classify messages. Can use SpamAssassin to
train dspam.

Adds the X-DSPAM-Result and X-DSPAM-Signature headers to messages. The latter is essential for
training dspam and the former is useful to MDAs, MUAs, and humans.

Adds a transaction note to the qpsmtpd transaction. The notes is a hashref
with at least the 'class' field (Spam,Innocent,Whitelisted). It will normally
contain a probability and confidence ratings as well.

=head1 TRAINING DSPAM

Do not just enable dspam! Its false positive rate when untrained is high. The
good news is; dspam learns very, very fast.

To get dspam into a useful state, it must be trained. The best method way to
train dspam is to feed it two large equal sized corpuses of spam and ham from
your mail server. The dspam authors suggest avoiding public corpuses. I train
dspam as follows:

=over 4

=item learn from SpamAssassin

See the docs on the learn_from_sa feature in the CONFIG section.

=item periodic training

I have a script that searches the contents of every users maildir. Any read
messages that have changed since the last processing run are learned as ham
or spam.

The ham message list consists of read messages in any folder not named like
Spam, Junk, Trash, or Deleted. This catches messages that users have read
and left in their inbox or filed away into subfolders.

=item on-the-fly training

The dovecot IMAP server has an antispam plugin that will train dspam when
messages are moved to/from the Spam folder.

=back

=head1 CONFIG

=head2 dspam_bin

The path to the dspam binary. If yours is installed somewhere other
than /usr/local/bin/dspam, you'll need to set this.

=head2 learn_from_sa

Dspam can be trained by SpamAssassin. This relationship between them requires
attention to several important details:

=over 4

=item 1

dspam must be listed B<after> spamassassin in the config/plugins file.
Because SA runs first, I crank the SA reject_threshold up above 100 so that
all spam messages will be used to train dspam.

Once dspam is trained and errors are rare, I plan to run dspam first and
reduce the SA load.

=item 2

Autolearn must be enabled and configured in SpamAssassin. SA autolearn
preferences will determine whether a message is learned as spam or innocent
by dspam. The settings to pay careful attention to in your SA local.cf file
are bayes_auto_learn_threshold_spam and bayes_auto_learn_threshold_nonspam.
Make sure they are both set to conservative values that are certain to
yield no false positives.

If you are using learn_from_sa and reject, then messages that exceed the SA
threshholds will cause dspam to reject them. Again I say, make sure them SA
autolearn threshholds are set high enough to avoid false positives.

=item 3

dspam must be configured and working properly. I have modified the following
dspam values on my system:

=over 4

=item mysql storage

=item Trust smtpd

=item TrainingMode tum

=item Tokenizer osb

=item Preference "trainingMode=TOE"

=item Preference "spamAction=deliver"

=item Preference "signatureLocation=headers"

=item TrainPristine off

=item ParseToHeaders off

=back

Of those changes, the most important is the signature location. This plugin
only supports storing the signature in the headers. If you want to train dspam
after delivery (ie, users moving messages to/from spam folders), then the
dspam signature must be in the headers.

When using the dspam MySQL backend, use InnoDB tables. Dspam training
is dramatically slowed by MyISAM table locks and dspam requires lots
of training. InnoDB has row level locking and updates are much faster.

=back

=head2 reject

Set to a floating point value between 0 and 1.00 where 0 is no confidence
and 1.0 is 100% confidence.

If dspam's confidence is greater than or equal to this threshold, the
message will be rejected. The default is 1.00.

=head2 reject_type

 reject_type [ temp | perm ]

By default, rejects are permanent (5xx). Set this to temp if you want to
defer mail instead of rejecting it with dspam.

=head1 MULTIPLE RECIPIENT BEHAVIOR

For messages with multiple recipients, the user that dspam is running as will
be the dspam username.

When messages have a single recipient, the recipient address is used as the
dspam username. For dspam to trust qpsmtpd with modifying the username, you
B<must> add the username that qpsmtpd is running to to the dspamd.conf file.

ie, (Trust smtpd).

=head1 CHANGES

=head1 AUTHOR

 Matt Simerson - 2012

=cut

use strict;
use warnings;

use Qpsmtpd::Constants;
use Qpsmtpd::DSN;
use IO::Handle;
use Socket qw(:DEFAULT :crlf);

sub register {
    my ($self, $qp, %args) = @_;

    $self->log(LOGERROR, "Bad parameters for the dspam plugin") if @_ % 2;

    $self->{_args} = { %args };
    $self->{_args}{reject} = defined $args{reject} ? $args{reject} : 1;
    $self->{_args}{reject_type} = $args{reject_type} || 'perm';

    $self->register_hook('data_post', 'dspam_reject');
}

sub hook_data_post {
    my ($self, $transaction) = @_;

    $self->log(LOGDEBUG, "check_dspam");
    if ( $transaction->data_size > 500_000 ) {
        $self->log(LOGINFO, "skip: message too large (" . $transaction->data_size . ")" );
        return (DECLINED);
    };

    my $username = $self->select_username( $transaction );
    my $message  = $self->assemble_message($transaction);
    my $filtercmd = $self->get_filter_cmd( $transaction, $username );
    $self->log(LOGDEBUG, $filtercmd);

    my $response = $self->dspam_process( $filtercmd, $message );
    if ( ! $response ) {
        $self->log(LOGWARN, "skip: no response from dspam. Check logs for errors.");
        return (DECLINED);
    };

    # X-DSPAM-Result: user@example.com; result="Spam"; class="Spam"; probability=1.0000; confidence=1.00; signature=N/A
    # X-DSPAM-Result: smtpd; result="Innocent"; class="Innocent"; probability=0.0023; confidence=1.00; signature=4f8dae6a446008399211546
    my ($result,$prob,$conf,$sig) = $response =~ /result=\"(Spam|Innocent)\";.*?probability=([\d\.]+); confidence=([\d\.]+); signature=(.*)/;
    my $header_str = "$result, probability=$prob, confidence=$conf";
    $self->log(LOGDEBUG, $header_str);
    $transaction->header->replace('X-DSPAM-Result', $header_str, 0);

    # the signature header is required if you intend to train dspam later.
    # In dspam.conf, set: Preference "signatureLocation=headers"
    $transaction->header->add('X-DSPAM-Signature', $sig, 0);

    return (DECLINED);
};

sub select_username {
    my ($self, $transaction) = @_;

    my $recipient_count = scalar $transaction->recipients;
    $self->log(LOGDEBUG, "Message has $recipient_count recipients");

    if ( $recipient_count > 1 ) {
        $self->log(LOGINFO, "skipping user prefs, $recipient_count recipients detected.");
        return getpwuid($>);
    };

# use the recipients email address as username. This enables user prefs
    my $username = ($transaction->recipients)[0]->address;
    return lc($username);
};

sub assemble_message {
    my ($self, $transaction) = @_;

    $transaction->body_resetpos;

    my $message = "X-Envelope-From: "
        . $transaction->sender->format . "\n"
        . $transaction->header->as_string . "\n\n";

    while (my $line = $transaction->body_getline) { $message .= $line; };

    $message = join(CRLF, split/\n/, $message);
    return $message . CRLF;
};

sub dspam_process {
    my ( $self, $filtercmd, $message ) = @_;

    #return $self->dspam_process_open2( $filtercmd, $message );

    my ($in_fh, $out_fh);
    if (! open($in_fh, '-|')) {
        open($out_fh, "|$filtercmd") or die "Can't run $filtercmd: $!\n";
        print $out_fh $message;
        close $out_fh;
        exit(0);
    };
    #my $response = join('', <$in_fh>);
    my $response = <$in_fh>;
    close $in_fh;
    chomp $response;
    $self->log(LOGDEBUG, $response);
    return $response;
};

sub dspam_process_open2 {
    my ( $self, $filtercmd, $message ) = @_;

# not sure why, but this is not as reliable as I'd like. What's a dspam
# error -5 mean anyway?
    use FileHandle;
    use IPC::Open2;
    my ($dspam_in, $dspam_out);
    my $pid = open2($dspam_out, $dspam_in, $filtercmd);
    print $dspam_in $message;
    close $dspam_in;
    #my $response = join('', <$dspam_out>);  # get full response
    my $response = <$dspam_out>;             # get first line only
    waitpid $pid, 0;
    chomp $response;
    $self->log(LOGDEBUG, $response);
    return $response;
};

sub dspam_reject {
    my ($self, $transaction) = @_;

    my $d = $self->get_dspam_results( $transaction ) or return DECLINED;

    if ( ! $d->{class} ) {
        $self->log(LOGWARN, "skip: no dspam class detected");
        return DECLINED;
    };

    my $status = "$d->{class}, $d->{confidence} c.";
    my $reject = $self->{_args}{reject} or do {
        $self->log(LOGINFO, "skip: reject disabled ($status)");
        return DECLINED;
    };

    if ( $reject eq 'agree' ) {
        return $self->dspam_reject_agree( $transaction, $d );
    };
    if ( $d->{class} eq 'Innocent' ) {
        $self->log(LOGINFO, "pass: $status");
        return DECLINED;
    };
    if ( $self->qp->connection->relay_client ) {
        $self->log(LOGINFO, "skip: allowing spam, user authenticated ($status)");
        return DECLINED;
    };
    if ( $d->{probability} <= $reject ) {
        $self->log(LOGINFO, "pass, $d->{class} probability is too low ($d->{probability} < $reject)");
        return DECLINED;
    };
    if ( $d->{confidence} != 1 ) {
        $self->log(LOGINFO, "pass: $d->{class} confidence is too low ($d->{confidence})");
        return DECLINED;
    };

    # dspam is more than $reject percent sure this message is spam
    $self->log(LOGINFO, "fail: $d->{class}, ($d->{confidence} confident)");
    my $deny = $self->{_args}{reject_type} eq 'temp' ? DENYSOFT : DENY;
    return Qpsmtpd::DSN->media_unsupported($deny,'dspam says, no spam please');
}

sub dspam_reject_agree {
    my ($self, $transaction, $d ) = @_;

    my $sa = $transaction->notes('spamassassin' );

    my $status = "$d->{class}, $d->{confidence} c";

    if ( ! $sa->{is_spam} ) {
        $self->log(LOGINFO, "pass: cannot agree, SA results missing ($status)");
        return DECLINED;
    };

    if ( $d->{class} eq 'Spam' && $sa->{is_spam} eq 'Yes' ) {
        $self->log(LOGINFO, "fail: agree, $status");
        return Qpsmtpd::DSN->media_unsupported(DENY,'we agree, no spam please');
    };

    $self->log(LOGINFO, "pass: agree, $status");
    return DECLINED;
};

sub get_dspam_results {
    my ( $self, $transaction ) = @_;

    if ( $transaction->notes('dspam') ) {
        return $transaction->notes('dspam');
    };

    my $string = $transaction->header->get('X-DSPAM-Result') or do {
        $self->log(LOGWARN, "get_dspam_results: failed to find the header");
        return;
    };

    my @bits  = split(/,\s+/, $string); chomp @bits;
    my $class = shift @bits;
    my %d;
    foreach (@bits) {
        my ($key,$val) = split(/=/, $_);
        $d{$key} = $val;
    };
    $d{class} = $class;

    my $message = $d{class};
    if ( defined $d{probability} && defined $d{confidence} ) {
        $message .= ", prob: $d{probability}, conf: $d{confidence}";
    };
    $self->log(LOGDEBUG, $message);
    $transaction->notes('dspam', \%d);
    return \%d;
};

sub get_filter_cmd {
    my ($self, $transaction, $user) = @_;

    my $dspam_bin = $self->{_args}{dspam_bin} || '/usr/local/bin/dspam';
    my $default = "$dspam_bin --user $user --mode=tum --process --deliver=summary --stdout";
    my $min_score = $self->{_args}{learn_from_sa} or return $default;

    #$self->log(LOGDEBUG, "attempting to learn from SA");

    my $sa = $transaction->notes('spamassassin' );
    return $default if ! $sa || ! $sa->{is_spam};

    if ( $sa->{is_spam} eq 'Yes' && $sa->{score} < $min_score ) {
        $self->log(LOGNOTICE, "SA score $sa->{score} < $min_score, skip autolearn");
        return $default;
    };

    return $default if ! $sa->{autolearn};

    if ( $sa->{is_spam} eq 'Yes' && $sa->{autolearn} eq 'spam' ) {
        return "$dspam_bin --user $user --mode=tum --source=corpus --class=spam --deliver=summary --stdout";
    }
    elsif ( $sa->{is_spam} eq 'No' && $sa->{autolearn} eq 'ham' ) {
        return "$dspam_bin --user $user --mode=tum --source=corpus --class=innocent --deliver=summary --stdout";
    };

    return $default;
};