mda, watch: wire up List-ID header support

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

diff --git a/lib/PublicInbox/WatchMaildir.pm b/lib/PublicInbox/WatchMaildir.pm
index 8d8e817ad767d9097b438c84ae336ea503e12a4b..08b1aab43ad1e8a4f6b06e6def310a4ecfb29eb0 100644 (file)
--- a/lib/PublicInbox/WatchMaildir.pm
+++ b/lib/PublicInbox/WatchMaildir.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2016-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2016-2019 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 #
 # ref: https://cr.yp.to/proto/maildir.html
@@ -7,9 +7,6 @@ package PublicInbox::WatchMaildir;
 use strict;
 use warnings;
 use PublicInbox::MIME;
-use PublicInbox::Git;
-use PublicInbox::Import;
-use PublicInbox::MDA;
 use PublicInbox::Spawn qw(spawn);
 use PublicInbox::InboxWritable;
 use File::Temp qw//;
@@ -27,9 +24,10 @@ sub new {
        # indefinitely...
        foreach my $pfx (qw(publicinboxwatch publicinboxlearn)) {
                my $k = "$pfx.watchspam";
-               if (my $dir = $config->{$k}) {
-                       if ($dir =~ s/\Amaildir://) {
-                               $dir =~ s!/+\z!!;
+               defined(my $dirs = $config->{$k}) or next;
+               $dirs = [ $dirs ] if !ref($dirs);
+               for my $dir (@$dirs) {
+                       if (is_maildir($dir)) {
                                # skip "new", no MUA has seen it, yet.
                                my $cur = "$dir/cur";
                                my $old = $mdmap{$cur};
@@ -60,11 +58,20 @@ sub new {
                my $ibx = $_[0] = PublicInbox::InboxWritable->new($_[0]);
 
                my $watch = $ibx->{watch} or return;
-               if ($watch =~ s/\Amaildir://) {
-                       $watch =~ s!/+\z!!;
-                       if (my $wm = $ibx->{watchheader}) {
-                               my ($k, $v) = split(/:/, $wm, 2);
-                               $ibx->{-watchheader} = [ $k, qr/\Q$v\E/ ];
+               if (is_maildir($watch)) {
+                       my $watch_hdrs = [];
+                       if (my $wh = $ibx->{watchheader}) {
+                               my ($k, $v) = split(/:/, $wh, 2);
+                               push @$watch_hdrs, [ $k, qr/\Q$v\E/ ];
+                       }
+                       if (my $list_ids = $ibx->{listid}) {
+                               for (@$list_ids) {
+                                       my $re = qr/<[ \t]*\Q$_\E[ \t]*>/;
+                                       push @$watch_hdrs, ['List-Id', $re ];
+                               }
+                       }
+                       if (scalar @$watch_hdrs) {
+                               $ibx->{-watchheaders} = $watch_hdrs;
                        }
                        my $new = "$watch/new";
                        my $cur = "$watch/cur";
@@ -123,7 +130,7 @@ sub _remove_spam {
                eval {
                        my $im = _importer_for($self, $ibx);
                        $im->remove($mime, 'spam');
-                       if (my $scrub = $ibx->filter) {
+                       if (my $scrub = $ibx->filter($im)) {
                                my $scrubbed = $scrub->scrub($mime, 1);
                                $scrubbed or return;
                                $scrubbed == REJECT() and return;
@@ -152,16 +159,30 @@ sub _try_path {
        if (!ref($inboxes) && $inboxes eq 'watchspam') {
                return _remove_spam($self, $path);
        }
+
+       my $warn_cb = $SIG{__WARN__} || sub { print STDERR @_ };
+       local $SIG{__WARN__} = sub {
+               $warn_cb->("path: $path\n");
+               $warn_cb->(@_);
+       };
        foreach my $ibx (@$inboxes) {
                my $mime = _path_to_mime($path) or next;
                my $im = _importer_for($self, $ibx);
 
-               my $wm = $ibx->{-watchheader};
-               if ($wm) {
-                       my $v = $mime->header_obj->header_raw($wm->[0]);
-                       next unless ($v && $v =~ $wm->[1]);
+               # any header match means it's eligible for the inbox:
+               if (my $watch_hdrs = $ibx->{-watchheaders}) {
+                       my $ok;
+                       my $hdr = $mime->header_obj;
+                       for my $wh (@$watch_hdrs) {
+                               my $v = $hdr->header_raw($wh->[0]);
+                               next unless defined($v) && $v =~ $wh->[1];
+                               $ok = 1;
+                               last;
+                       }
+                       next unless $ok;
                }
-               if (my $scrub = $ibx->filter) {
+
+               if (my $scrub = $ibx->filter($im)) {
                        my $ret = $scrub->scrub($mime) or next;
                        $ret == REJECT() and next;
                        $mime = $ret;
@@ -278,4 +299,11 @@ sub _spamcheck_cb {
        }
 }
 
+sub is_maildir {
+       $_[0] =~ s!\Amaildir:!! or return;
+       $_[0] =~ tr!/!/!s;
+       $_[0] =~ s!/\z!!;
+       $_[0];
+}
+
 1;