[PATCH 12/14] mda: support multiple List-ID matches

[Eric Wong <e@80x24.org>]

While it's not RFC2919-conformant, mail software can
theoretically set multiple List-ID headers.  Deliver to all
inboxes which match a given List-ID since that's likely the
intended.

Cc: Eric W. Biederman <ebiederm@xmission.com>
Link: https://public-inbox.org/meta/87pniltscf.fsf@x220.int.ebiederm.org/
---
 lib/PublicInbox/MDA.pm    | 19 +++++++++++++------
 script/public-inbox-learn |  5 +++--
 script/public-inbox-mda   |  7 +++----
 t/mda.t                   | 19 +++++++++++++++++++
 4 files changed, 38 insertions(+), 12 deletions(-)

diff --git a/lib/PublicInbox/MDA.pm b/lib/PublicInbox/MDA.pm
index ce2c870f..933d82a8 100644
--- a/lib/PublicInbox/MDA.pm
+++ b/lib/PublicInbox/MDA.pm
@@ -84,18 +84,25 @@ sub set_list_headers {
 }
 
 # TODO: deal with multiple List-ID headers?
-sub inbox_for_list_id ($$) {
+sub inboxes_for_list_id ($$) {
 	my ($klass, $config, $simple) = @_;
 
 	# newer Email::Simple allows header_raw, as does Email::MIME:
-	my $list_id = $simple->can('header_raw') ?
+	my @list_ids = $simple->can('header_raw') ?
 			$simple->header_raw('List-Id') :
 			$simple->header('List-Id');
-	my $ibx;
-	if (defined $list_id && $list_id =~ /<[ \t]*(.+)?[ \t]*>/) {
-		$ibx = $config->lookup_list_id($1);
+	my @dests;
+	for my $list_id (@list_ids) {
+		$list_id =~ /<[ \t]*(.+)?[ \t]*>/ or next;
+		if (my $ibx = $config->lookup_list_id($1)) {
+			push @dests, $ibx;
+		}
+	}
+	if (scalar(@list_ids) > 1) {
+		warn "W: multiple List-IDs in message:\n";
+		warn "W: List-ID: $_\n" for @list_ids
 	}
-	$ibx;
+	\@dests;
 }
 
 1;
diff --git a/script/public-inbox-learn b/script/public-inbox-learn
index 79f3ead5..3073294a 100644
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -95,8 +95,9 @@ if ($train eq 'spam') {
 		next if $seen{"$ibx"}++;
 		remove_or_add($ibx, $train, $addr);
 	}
-	my $ibx = PublicInbox::MDA->inbox_for_list_id($pi_config, $mime);
-	if ($ibx && !$seen{"$ibx"}) {
+	my $dests = PublicInbox::MDA->inboxes_for_list_id($pi_config, $mime);
+	for my $ibx (@$dests) {
+		next if !$seen{"$ibx"}++;
 		remove_or_add($ibx, $train, $ibx->{-primary_address});
 	}
 }
diff --git a/script/public-inbox-mda b/script/public-inbox-mda
index 821bd9cc..dca8a0ea 100755
--- a/script/public-inbox-mda
+++ b/script/public-inbox-mda
@@ -44,12 +44,11 @@ if (defined $recipient) {
 	push @$dests, $ibx if $ibx;
 }
 if (!scalar(@$dests)) {
-	my $ibx = PublicInbox::MDA->inbox_for_list_id($config, $simple);
-	if (!defined($ibx) && !defined($recipient)) {
+	$dests = PublicInbox::MDA->inboxes_for_list_id($config, $simple);
+	if (!scalar(@$dests) && !defined($recipient)) {
 		die "ORIGINAL_RECIPIENT not defined in ENV\n";
 	}
-	defined($ibx) or do_exit(67); # EX_NOUSER 5.1.1 user unknown
-	push @$dests, $ibx;
+	scalar(@$dests) or do_exit(67); # EX_NOUSER 5.1.1 user unknown
 }
 
 my $err;
diff --git a/t/mda.t b/t/mda.t
index 99592b2d..35811ac6 100644
--- a/t/mda.t
+++ b/t/mda.t
@@ -308,6 +308,25 @@ EOF
 	my $cur = `git --git-dir=$maindir diff HEAD~1..HEAD`;
 	like($cur, qr/this message would not be accepted without --no-precheck/,
 		'--no-precheck delivered message anyways');
+
+	# try a message with multiple List-ID headers
+	$in = <<EOF;
+List-ID: <foo.bar>
+List-ID: <$list_id>
+Message-ID: <2lids\@example>
+Subject: two List-IDs
+From: user <user\@example.com>
+To: $addr
+Date: Fri, 02 Oct 1993 00:00:00 +0000
+
+EOF
+	($out, $err) = ('', '');
+	IPC::Run::run([$mda], \$in, \$out, \$err);
+	is($?, 0, 'mda OK with multiple List-Id matches');
+	$cur = `git --git-dir=$maindir diff HEAD~1..HEAD`;
+	like($cur, qr/Message-ID: <2lids\@example>/,
+		'multi List-ID match delivered');
+	like($err, qr/multiple List-ID/, 'warned about multiple List-ID');
 }
 
 done_testing();