foreach my $pfx (qw(publicinboxwatch publicinboxlearn)) {
my $k = "$pfx.watchspam";
defined(my $dirs = $config->{$k}) or next;
- $dirs = [ $dirs ] if !ref($dirs);
+ $dirs = PublicInbox::Config::_array($dirs);
for my $dir (@$dirs) {
if (is_maildir($dir)) {
# skip "new", no MUA has seen it, yet.
# need to make all inboxes writable for spam removal:
my $ibx = $_[0] = PublicInbox::InboxWritable->new($_[0]);
- my $watch = $ibx->{watch} or return;
- if (is_maildir($watch)) {
- compile_watchheaders($ibx);
- my ($new, $cur) = ("$watch/new", "$watch/cur");
- return if is_watchspam($cur, $mdmap{$cur}, $ibx);
- push @mdir, $new unless $uniq{$new}++;
- push @mdir, $cur unless $uniq{$cur}++;
- push @{$mdmap{$new} ||= []}, $ibx;
- push @{$mdmap{$cur} ||= []}, $ibx;
- } elsif (my $url = imap_url($watch)) {
- return if is_watchspam($url, $imap{$url}, $ibx);
- compile_watchheaders($ibx);
- push @{$imap{$url} ||= []}, $ibx;
- } else {
- warn "watch unsupported: $k=$watch\n";
+ my $watches = $ibx->{watch} or return;
+ $watches = PublicInbox::Config::_array($watches);
+ for my $watch (@$watches) {
+ if (is_maildir($watch)) {
+ compile_watchheaders($ibx);
+ my ($new, $cur) = ("$watch/new", "$watch/cur");
+ my $cur_dst = $mdmap{$cur} //= [];
+ return if is_watchspam($cur, $cur_dst, $ibx);
+ push @mdir, $new unless $uniq{$new}++;
+ push @mdir, $cur unless $uniq{$cur}++;
+ push @{$mdmap{$new} //= []}, $ibx;
+ push @$cur_dst, $ibx;
+ } elsif (my $url = imap_url($watch)) {
+ return if is_watchspam($url, $imap{$url}, $ibx);
+ compile_watchheaders($ibx);
+ push @{$imap{$url} ||= []}, $ibx;
+ } else {
+ warn "watch unsupported: $k=$watch\n";
+ }
}
});
return unless scalar(@mdir) || scalar(keys %imap);
}
if (my $idle_mic = $self->{idle_mic}) {
eval { $idle_mic->done };
- warn "IDLE DONE error: $@\n" if $@;
- eval { $idle_mic->disconnect };
- warn "IDLE LOGOUT error: $@\n" if $@;
+ if ($@) {
+ warn "IDLE DONE error: $@\n";
+ eval { $idle_mic->disconnect };
+ warn "IDLE LOGOUT error: $@\n" if $@;
+ }
}
}
$self->{imap_opt}->{$sec}->{poll_intvl} = $to if $to;
$to = cfg_intvl($cfg, 'imap', 'IdleInterval', $sec, $url);
$self->{imap_opt}->{$sec}->{idle_intvl} = $to if $to;
+
+ my $key = lc("imap.$sec.fetchBatchSize");
+ my $bs = $cfg->{lc($key)} //
+ $cfg->urlmatch('imap.fetchBatchSize', $url) // next;
+ if ($bs =~ /\A([0-9]+)\z/) {
+ $self->{imap_opt}->{$sec}->{batch_size} = $bs;
+ } else {
+ warn "W: $key=$bs is not an integer\n";
+ }
}
$mic_args;
}
$mic;
}
-sub imap_import_msg ($$$$$) {
- my ($self, $itrk, $r_uidval, $uid, $raw) = @_;
+sub imap_import_msg ($$$$) {
+ my ($self, $url, $uid, $raw) = @_;
# our target audience expects LF-only, save storage
$$raw =~ s/\r\n/\n/sg;
- my $inboxes = $self->{imap}->{$itrk->{url}};
+ my $inboxes = $self->{imap}->{$url};
if (ref($inboxes)) {
for my $ibx (@$inboxes) {
my $eml = PublicInbox::Eml->new($$raw);
}
} elsif ($inboxes eq 'watchspam') {
my $eml = PublicInbox::Eml->new($raw);
- my $arg = [ $self, $eml, "$itrk->{url} UID:$uid" ];
+ my $arg = [ $self, $eml, "$url UID:$uid" ];
$self->{config}->each_inbox(\&remove_eml_i, $arg);
} else {
die "BUG: destination unknown $inboxes";
}
- $itrk->update_last($r_uidval, $uid);
}
sub imap_fetch_all ($$$) {
warn "I: $url fetching UID $l_uid:$r_uid\n";
$mic->Uid(1); # the default, we hope
- my $uids;
+ my $bs = $self->{imap_opt}->{$sec}->{batch_size} // 1;
my $req = $mic->imap4rev1 ? 'BODY.PEEK[]' : 'RFC822.PEEK';
+
+ # TODO: FLAGS may be useful for personal use
my $key = $req;
$key =~ s/\.PEEK//;
- my $uid;
+ my ($uids, $batch);
my $warn_cb = $SIG{__WARN__} || sub { print STDERR @_ };
local $SIG{__WARN__} = sub {
- $uid //= -1;
- $warn_cb->("$url UID:$uid\n");
+ $batch //= '?';
+ $warn_cb->("$url UID:$batch\n");
$warn_cb->(@_);
};
my $err;
do {
+ # I wish "UID FETCH $START:*" could work, but:
+ # 1) servers do not need to return results in any order
+ # 2) Mail::IMAPClient doesn't offer a streaming API
$uids = $mic->search("UID $l_uid:*") or
return "E: $url UID SEARCH $l_uid:* error: $!";
return if scalar(@$uids) == 0;
# RFC 3501 doesn't seem to indicate order of UID SEARCH
- # responses, so sort it ourselves
+ # responses, so sort it ourselves. Order matters so
+ # IMAPTracker can store the newest UID.
@$uids = sort { $a <=> $b } @$uids;
# Did we actually get new messages?
return if $uids->[0] < $l_uid;
$l_uid = $uids->[-1] + 1; # for next search
+ my $last_uid;
- $itrk->{dbh}->begin_work;
- while (defined(($uid = shift(@$uids)))) {
- local $0 = "UID:$uid $mbx $sec";
- my $r = $mic->fetch_hash($uid, $req);
+ while (scalar @$uids) {
+ my @batch = splice(@$uids, 0, $bs);
+ $batch = join(',', @batch);
+ local $0 = "UID:$batch $mbx $sec";
+ my $r = $mic->fetch_hash($batch, $req);
unless ($r) { # network error?
- $err = "E: $url UID FETCH $uid error: $!";
+ $err = "E: $url UID FETCH $batch error: $!";
last;
}
- # messages get deleted, so holes appear
- defined(my $raw = delete $r->{$uid}->{$key}) or next;
- imap_import_msg($self, $itrk, $r_uidval, $uid, \$raw);
+ for my $uid (@batch) {
+ # messages get deleted, so holes appear
+ my $per_uid = delete $r->{$uid} // next;
+ my $raw = delete($per_uid->{$key}) // next;
+ imap_import_msg($self, $url, $uid, \$raw);
+ $last_uid = $uid;
+ last if $self->{quit};
+ }
last if $self->{quit};
}
_done_for_now($self);
- $itrk->{dbh}->commit;
+ $itrk->update_last($r_uidval, $last_uid) if defined $last_uid;
} until ($err || $self->{quit});
$err;
}