X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FWatch.pm;h=0bb92d0a9055703233b7af5cafe53bdfa0232e2f;hb=94ae705673cb03045a109041eec9a6704b8a735b;hp=5f78613961db1058506b8193c4ea7bd55c0522f3;hpb=3bfbaacac15a14a379e360dc2d6c5989f49c3769;p=public-inbox.git diff --git a/lib/PublicInbox/Watch.pm b/lib/PublicInbox/Watch.pm index 5f786139..0bb92d0a 100644 --- a/lib/PublicInbox/Watch.pm +++ b/lib/PublicInbox/Watch.pm @@ -134,15 +134,34 @@ sub _done_for_now { sub remove_eml_i { # each_inbox callback my ($ibx, $arg) = @_; my ($self, $eml, $loc) = @$arg; + eval { - my $im = _importer_for($self, $ibx); - $im->remove($eml, 'spam'); - if (my $scrub = $ibx->filter($im)) { - my $scrubbed = $scrub->scrub($eml, 1); - if ($scrubbed && $scrubbed != REJECT) { - $im->remove($scrubbed, 'spam'); + # try to avoid taking a lock or unnecessary spawning + my $im = $self->{importers}->{"$ibx"}; + my $scrubbed; + if ((!$im || !$im->active) && $ibx->over) { + if (content_exists($ibx, $eml)) { + # continue + } elsif (my $scrub = $ibx->filter($im)) { + $scrubbed = $scrub->scrub($eml, 1); + if ($scrubbed && $scrubbed != REJECT && + !content_exists($ibx, $scrubbed)) { + return; + } + } else { + return; } } + + $im //= _importer_for($self, $ibx); # may spawn fast-import + $im->remove($eml, 'spam'); + $scrubbed //= do { + my $scrub = $ibx->filter($im); + $scrub ? $scrub->scrub($eml, 1) : undef; + }; + if ($scrubbed && $scrubbed != REJECT) { + $im->remove($scrubbed, 'spam'); + } }; if ($@) { warn "error removing spam at: $loc from $ibx->{name}: $@\n";