#!/usr/bin/perl -w
# Copyright (C) 2014-2021 all contributors
# License: AGPL-3.0+
#
# Used for training spam (via SpamAssassin) and removing messages from a
# public-inbox
my $help = < 0);
GetOptions(\%opt, qw(all help|h)) or die $help;
my $train = shift or die $help;
if ($train !~ /\A(?:ham|spam|rm)\z/) {
die "`$train' not recognized.\n$help";
}
die "--all only works with `rm'\n" if $opt{all} && $train ne 'rm';
my $spamc = PublicInbox::Spamcheck::Spamc->new;
my $pi_cfg = PublicInbox::Config->new;
my $err;
my $mime = PublicInbox::Eml->new(do{
defined(my $data = do { local $/; }) or die "read STDIN: $!\n";
$data =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
if ($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
});
sub remove_or_add ($$$$) {
my ($ibx, $train, $mime, $addr) = @_;
# We do not touch GIT_COMMITTER_* env here so we can track
# who trained the message.
$ibx->{name} = $ENV{GIT_COMMITTER_NAME} // $ibx->{name};
$ibx->{-primary_address} = $ENV{GIT_COMMITTER_EMAIL} // $addr;
$ibx = PublicInbox::InboxWritable->new($ibx);
my $im = $ibx->importer(0);
if ($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, $train);
} elsif ($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, $ibx);
# Ham messages are trained when they're marked into
# a SEEN state, so this is idempotent:
$im->add($mime);
}
$im->done;
}
# spam is removed from all known inboxes since it is often Bcc:-ed
if ($train eq 'spam' || ($train eq 'rm' && $opt{all})) {
$pi_cfg->each_inbox(sub {
my ($ibx) = @_;
$ibx = PublicInbox::InboxWritable->new($ibx);
my $im = $ibx->importer(0);
$im->remove($mime, $train);
$im->done;
});
} else {
require PublicInbox::MDA;
# get all recipients
my %dests; # address =>
for ($mime->header('Cc'), $mime->header('To')) {
foreach my $addr (PublicInbox::Address::emails($_)) {
$addr = lc($addr);
$dests{$addr} //= $pi_cfg->lookup($addr) // 0;
}
}
# n.b. message may be cross-posted to multiple public-inboxes
my %seen;
while (my ($addr, $ibx) = each %dests) {
next unless ref($ibx); # $ibx may be 0
next if $seen{"$ibx"}++;
remove_or_add($ibx, $train, $mime, $addr);
}
my $dests = PublicInbox::MDA->inboxes_for_list_id($pi_cfg, $mime);
for my $ibx (@$dests) {
next if $seen{"$ibx"}++;
remove_or_add($ibx, $train, $mime, $ibx->{-primary_address});
}
}
if ($err) {
warn $err;
exit 1;
}