[PATCH 3/4] drop Message-IDs longer than 244 bytes

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

Xapian has this limit for terms, and there are likely no
legitimate Message-IDs (or single header lines) this long; so
there's no need to workaround this limit.
---
 lib/PublicInbox/MDA.pm       | 2 ++
 lib/PublicInbox/SearchIdx.pm | 5 +++++
 2 files changed, 7 insertions(+)

diff --git a/lib/PublicInbox/MDA.pm b/lib/PublicInbox/MDA.pm
index 25d6ae5..7025fb3 100644
--- a/lib/PublicInbox/MDA.pm
+++ b/lib/PublicInbox/MDA.pm
@@ -6,6 +6,7 @@ use warnings;
 use Email::Address;
 use Date::Parse qw(strptime);
 use constant MAX_SIZE => 1024 * 500; # same as spamc default, should be tunable
+use constant MAX_MID_SIZE => 244; # max term size - 1 in Xapian
 use constant cmd => qw/ssoma-mda -1/;
 
 # drop plus addressing for matching
@@ -20,6 +21,7 @@ sub precheck {
 	my ($klass, $filter, $address) = @_;
 	my $simple = $filter->simple;
 	my $mid = $simple->header("Message-ID");
+	return 0 if (length($mid) > MAX_MID_SIZE);
 	return 0 unless usable_str(length('<m@h>'), $mid) && $mid =~ /\@/;
 	return 0 unless usable_str(length('u@h'), $filter->from);
 	return 0 unless usable_str(length(':o'), $simple->header("Subject"));
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 8184dc7..0646cfb 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -8,6 +8,7 @@ use base qw(PublicInbox::Search);
 use PublicInbox::MID qw/mid_clean id_compress/;
 *xpfx = *PublicInbox::Search::xpfx;
 
+use constant MAX_MID_SIZE => 244; # max term size - 1 in Xapian
 use constant {
 	PERM_UMASK => 0,
 	OLD_PERM_GROUP => 1,
@@ -52,6 +53,7 @@ sub add_message {
 	my $ct_msg = $mime->header('Content-Type') || 'text/plain';
 
 	eval {
+		die 'Message-ID too long' if length($mid) > MAX_MID_SIZE;
 		my $smsg = $self->lookup_message($mid);
 		my $doc;
 
@@ -230,6 +232,9 @@ sub link_message_to_parents {
 
 		# prevent circular references via References: here:
 		foreach my $ref (@orig_refs) {
+			if (length($ref) > MAX_MID_SIZE) {
+				warn "References: <$ref> too long, ignoring\n";
+			}
 			next if $uniq{$ref};
 			$uniq{$ref} = 1;
 			push @refs, $ref;
-- 
EW