#!/usr/bin/perl -w
# Copyright (C) 2014-2018 all contributors
# License: AGPL-3.0+
#
# Used for training spam (via SpamAssassin) and removing messages from a
# public-inbox
my $usage = "$0 (spam|ham) < /path/to/message";
use strict;
use warnings;
use PublicInbox::Config;
use PublicInbox::Git;
use PublicInbox::Import;
use PublicInbox::MIME;
use PublicInbox::Address;
use PublicInbox::Spamcheck::Spamc;
my $train = shift or die "usage: $usage\n";
if ($train !~ /\A(?:ham|spam|rm)\z/) {
die "`$train' not recognized.\nusage: $usage\n";
}
my $spamc = PublicInbox::Spamcheck::Spamc->new;
my $pi_config = PublicInbox::Config->new;
my $err;
my $mime = PublicInbox::MIME->new(eval {
local $/;
my $data = scalar ;
$data =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
if ($train ne 'rm') {
eval {
if ($train eq 'ham') {
$spamc->hamlearn(\$data);
} elsif ($train eq 'spam') {
$spamc->spamlearn(\$data);
}
die "spamc failed with: $?\n" if $?;
};
$err = $@;
}
$data
});
# get all recipients
my %dests;
foreach my $h (qw(Cc To)) {
my $val = $mime->header($h) or next;
foreach my $email (PublicInbox::Address::emails($val)) {
$dests{lc($email)} = 1;
}
}
if ($train eq 'spam') {
$pi_config->each_inbox(sub {
my ($ibx) = @_;
my $git = $ibx->git;
my $name = $ibx->{name};
my $addr = $ibx->{-primary_address};
my $im = PublicInbox::Import->new($git, $name, $addr, $ibx);
$im->remove($mime, 'spam');
$im->done;
});
}
require PublicInbox::MDA if $train eq "ham";
# n.b. message may be cross-posted to multiple public-inboxes
foreach my $recipient (keys %dests) {
my $dst = $pi_config->lookup($recipient) or next;
my $git_dir = $dst->{mainrepo} or next;
my $git = PublicInbox::Git->new($git_dir);
# We do not touch GIT_COMMITTER_* env here so we can track
# who trained the message.
my $name = $ENV{GIT_COMMITTER_NAME} || $dst->{name};
my $email = $ENV{GIT_COMMITTER_EMAIL} || $recipient;
my $im = PublicInbox::Import->new($git, $name, $email);
if ($train eq "spam" || $train eq "rm") {
# This needs to be idempotent, as my inotify trainer
# may train for each cross-posted message, and this
# script already learns for every list in
# ~/.public-inbox/config
$im->remove($mime, $train);
} else { # $train eq "ham"
# no checking for spam here, we assume the message has
# been reviewed by a human at this point:
PublicInbox::MDA->set_list_headers($mime, $dst);
# Ham messages are trained when they're marked into
# a SEEN state, so this is idempotent:
$im->add($mime);
}
$im->done;
}
if ($err) {
warn $err;
exit 1;
}