#!/usr/bin/perl -w
-# Copyright (C) 2014-2015 all contributors <meta@public-inbox.org>
-# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
+# Copyright (C) 2014-2019 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
#
# Used for training spam (via SpamAssassin) and removing messages from a
# public-inbox
-my $usage = "$0 (spam|ham) < /path/to/message";
+my $usage = "$0 <spam|ham|rm> </path/to/message";
use strict;
use warnings;
use PublicInbox::Config;
-use PublicInbox::Git;
-use PublicInbox::Import;
-use Email::MIME;
-use Email::MIME::ContentType;
-$Email::MIME::ContentType::STRICT_PARAMS = 0; # user input is imperfect
+use PublicInbox::InboxWritable;
+use PublicInbox::MIME;
use PublicInbox::Address;
-use PublicInbox::Spawn qw(spawn);
+use PublicInbox::Spamcheck::Spamc;
my $train = shift or die "usage: $usage\n";
-if ($train !~ /\A(?:ham|spam)\z/) {
+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 = Email::MIME->new(eval {
+my $mime = PublicInbox::MIME->new(eval {
local $/;
my $data = scalar <STDIN>;
- $data =~ s/\AFrom [^\r\n]*\r?\n//s;
- eval {
- my @cmd = (qw(spamc -L), $train);
- my ($r, $w);
- pipe($r, $w) or die "pipe failed: $!";
- open my $null, '>', '/dev/null' or
- die "failed to open /dev/null: $!";
- my $nullfd = fileno($null);
- my %rdr = (0 => fileno($r), 1 => $nullfd, 2 => $nullfd);
- my $pid = spawn(\@cmd, undef, \%rdr);
- close $null;
- close $r or die "close \$r failed: $!";
- print $w $data or die "print \$w failed: $!";
- close $w or die "close \$w failed: $!";
- waitpid($pid, 0);
- die "spamc failed with: $?\n" if $?;
- };
- $err = $@;
+ $data =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
+
+ if ($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;
- }
-}
+# spam is removed from all known inboxes since it is often Bcc:-ed
+if ($train eq 'spam') {
+ $pi_config->each_inbox(sub {
+ my ($ibx) = @_;
+ $ibx = PublicInbox::InboxWritable->new($ibx);
+ my $im = $ibx->importer(0);
+ $im->remove($mime, 'spam');
+ $im->done;
+ });
+} else {
+ require PublicInbox::MDA if $train eq "ham";
-require PublicInbox::MDA if $train eq "ham";
+ # get all recipients
+ my %dests; # address => <PublicInbox::Inbox|0(false)>
+ for ($mime->header('Cc'), $mime->header('To')) {
+ foreach my $addr (PublicInbox::Address::emails($_)) {
+ $addr = lc($addr);
+ $dests{$addr} //= $pi_config->lookup($addr) // 0;
+ }
+ }
-# 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->{inbox};
- my $email = $ENV{GIT_COMMITTER_EMAIL} || $recipient;
- my $im = PublicInbox::Import->new($git, $name, $email);
+ # n.b. message may be cross-posted to multiple public-inboxes
+ while (my ($addr, $dst) = each %dests) {
+ next unless ref($dst);
+ # We do not touch GIT_COMMITTER_* env here so we can track
+ # who trained the message.
+ $dst->{name} = $ENV{GIT_COMMITTER_NAME} || $dst->{name};
+ $dst->{-primary_address} = $ENV{GIT_COMMITTER_EMAIL} || $addr;
+ $dst = PublicInbox::InboxWritable->new($dst);
+ my $im = $dst->importer(0);
- if ($train eq "spam") {
- # 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);
- } 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, $dst);
+ if ($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, $dst);
- # Ham messages are trained when they're marked into
- # a SEEN state, so this is idempotent:
- $im->add($mime);
+ # Ham messages are trained when they're marked into
+ # a SEEN state, so this is idempotent:
+ $im->add($mime);
+ }
+ $im->done;
}
- $im->done;
}
if ($err) {