drop Message-IDs longer than 244 bytes

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.

diff --git a/lib/PublicInbox/MDA.pm b/lib/PublicInbox/MDA.pm
index 25d6ae556eb7bfc09f33c03e695630bb7c7b08cb..7025fb3c8e054a3a306750cd284655237d9185ed 100644 (file)
--- 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 8184dc719aed6d0ad20835ffbb13864c1b896852..0646cfb38c0f60e90b29e5f0b9b44c3ab04d95bd 100644 (file)
--- 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;