watch: limit batch size of NNTP and IMAP workers, too

[public-inbox.git] / lib / PublicInbox / WatchMaildir.pm

diff --git a/lib/PublicInbox/WatchMaildir.pm b/lib/PublicInbox/WatchMaildir.pm
index 2ba10a9eaf4295762f352936a3612291c849fcf4..5176ef69db9e9d698ceb4a33efadc019739b80f9 100644 (file)
--- a/lib/PublicInbox/WatchMaildir.pm
+++ b/lib/PublicInbox/WatchMaildir.pm
@@ -108,6 +108,7 @@ sub new {
        return unless $mdre || scalar(keys %imap) || scalar(keys %nntp);
 
        bless {
+               max_batch => 10, # avoid hogging locks for too long
                spamcheck => $spamcheck,
                mdmap => \%mdmap,
                mdre => $mdre,
@@ -198,7 +199,10 @@ sub _try_path {
                return;
        }
        my $warn_cb = $SIG{__WARN__} || sub { print STDERR @_ };
-       local $SIG{__WARN__} = sub { $warn_cb->("path: $path\n", @_) };
+       local $SIG{__WARN__} = sub {
+               my $pfx = ($_[0] // '') =~ /^([A-Z]: )/g ? $1 : '';
+               $warn_cb->($pfx, "path: $path\n", @_);
+       };
        if (!ref($inboxes) && $inboxes eq 'watchspam') {
                return _remove_spam($self, $path);
        }
@@ -379,8 +383,8 @@ sub mic_for ($$$) { # mic = Mail::IMAPClient
        $mic;
 }
 
-sub imap_import_msg ($$$$) {
-       my ($self, $url, $uid, $raw) = @_;
+sub imap_import_msg ($$$$$) {
+       my ($self, $url, $uid, $raw, $flags) = @_;
        # our target audience expects LF-only, save storage
        $$raw =~ s/\r\n/\n/sg;
 
@@ -391,10 +395,13 @@ sub imap_import_msg ($$$$) {
                        my $x = import_eml($self, $ibx, $eml);
                }
        } elsif ($inboxes eq 'watchspam') {
-               local $SIG{__WARN__} = warn_ignore_cb();
-               my $eml = PublicInbox::Eml->new($raw);
-               my $arg = [ $self, $eml, "$url UID:$uid" ];
-               $self->{config}->each_inbox(\&remove_eml_i, $arg);
+               # we don't remove unseen messages
+               if ($flags =~ /\\Seen\b/) {
+                       local $SIG{__WARN__} = warn_ignore_cb();
+                       my $eml = PublicInbox::Eml->new($raw);
+                       my $arg = [ $self, $eml, "$url UID:$uid" ];
+                       $self->{config}->each_inbox(\&remove_eml_i, $arg);
+               }
        } else {
                die "BUG: destination unknown $inboxes";
        }
@@ -443,8 +450,9 @@ sub imap_fetch_all ($$$) {
        my ($uids, $batch);
        my $warn_cb = $SIG{__WARN__} || sub { print STDERR @_ };
        local $SIG{__WARN__} = sub {
+               my $pfx = ($_[0] // '') =~ /^([A-Z]: )/g ? $1 : '';
                $batch //= '?';
-               $warn_cb->("$url UID:$batch\n", @_);
+               $warn_cb->("$pfx$url UID:$batch\n", @_);
        };
        my $err;
        do {
@@ -465,12 +473,18 @@ sub imap_fetch_all ($$$) {
 
                $l_uid = $uids->[-1] + 1; # for next search
                my $last_uid;
+               my $n = $self->{max_batch};
 
                while (scalar @$uids) {
+                       if (--$n < 0) {
+                               _done_for_now($self);
+                               $itrk->update_last($r_uidval, $last_uid);
+                               $n = $self->{max_batch};
+                       }
                        my @batch = splice(@$uids, 0, $bs);
                        $batch = join(',', @batch);
                        local $0 = "UID:$batch $mbx $sec";
-                       my $r = $mic->fetch_hash($batch, $req);
+                       my $r = $mic->fetch_hash($batch, $req, 'FLAGS');
                        unless ($r) { # network error?
                                $err = "E: $url UID FETCH $batch error: $!";
                                last;
@@ -479,14 +493,15 @@ sub imap_fetch_all ($$$) {
                                # messages get deleted, so holes appear
                                my $per_uid = delete $r->{$uid} // next;
                                my $raw = delete($per_uid->{$key}) // next;
-                               imap_import_msg($self, $url, $uid, \$raw);
+                               my $fl = $per_uid->{FLAGS} // '';
+                               imap_import_msg($self, $url, $uid, \$raw, $fl);
                                $last_uid = $uid;
                                last if $self->{quit};
                        }
                        last if $self->{quit};
                }
                _done_for_now($self);
-               $itrk->update_last($r_uidval, $last_uid) if defined $last_uid;
+               $itrk->update_last($r_uidval, $last_uid);
        } until ($err || $self->{quit});
        $err;
 }
@@ -875,13 +890,20 @@ sub nntp_fetch_all ($$$) {
        my $warn_cb = $SIG{__WARN__} || sub { print STDERR @_ };
        my ($err, $art);
        local $SIG{__WARN__} = sub {
-               $warn_cb->("$url ", $art ? ("ARTICLE $art") : (), "\n", @_);
+               my $pfx = ($_[0] // '') =~ /^([A-Z]: )/g ? $1 : '';
+               $warn_cb->("$pfx$url ", $art ? ("ARTICLE $art") : (), "\n", @_);
        };
        my $inboxes = $self->{nntp}->{$url};
        my $last_art;
+       my $n = $self->{max_batch};
        for ($beg..$end) {
                last if $self->{quit};
                $art = $_;
+               if (--$n < 0) {
+                       _done_for_now($self);
+                       $itrk->update_last(0, $last_art);
+                       $n = $self->{max_batch};
+               }
                my $raw = $nn->article($art);
                unless (defined($raw)) {
                        my $msg = $nn->message;
@@ -909,8 +931,8 @@ sub nntp_fetch_all ($$$) {
                }
                $last_art = $art;
        }
-       $itrk->update_last(0, $last_art) if defined $last_art;
        _done_for_now($self);
+       $itrk->update_last(0, $last_art);
        $err;
 }
 
@@ -967,12 +989,11 @@ sub fs_scan_step {
        local $PublicInbox::DS::in_loop = 0; # waitpid() synchronously
 
        # continue existing scan
-       my $max = 10;
        my $opendirs = $self->{opendirs};
        my @dirnames = keys %$opendirs;
        foreach my $dir (@dirnames) {
                my $dh = delete $opendirs->{$dir};
-               my $n = $max;
+               my $n = $self->{max_batch};
                while (my $fn = readdir($dh)) {
                        _try_path($self, "$dir/$fn");
                        last if --$n < 0;
@@ -987,7 +1008,7 @@ sub fs_scan_step {
                                warn "failed to open $dir: $!\n";
                                next;
                        }
-                       my $n = $max;
+                       my $n = $self->{max_batch};
                        while (my $fn = readdir($dh)) {
                                _try_path($self, "$dir/$fn");
                                last if --$n < 0;