searchidx: deal with empty In-Reply-To and References headers

In some messages, these headers exist, but have empty values.
Do not let empty values throw off our search indexer to tie
threads together, as it can make non-sensical threads grouped
to a Message-Id of "" (empty string).

See
<https://public-inbox.org/git/11340844841342-git-send-email-mailing-lists.git@rawuncut.elitemail.org/raw>
for an example of such a message.

Thanks-to: Johannes Schindelin <Johannes.Schindelin@gmx.de>
  <https://public-inbox.org/git/alpine.DEB.2.20.1702041206130.3496@virtualbox/>

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index d63dd7c742b4c21ef9420d810954df3e8332f45e..1142ca7a0f4c83a6aa4103edc79d91bd04944e5a 100644 (file)
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -292,11 +292,15 @@ sub link_message {
        my $mime = $smsg->{mime};
        my $hdr = $mime->header_obj;
        my $refs = $hdr->header_raw('References');
        my $mime = $smsg->{mime};
        my $hdr = $mime->header_obj;
        my $refs = $hdr->header_raw('References');

-       my @refs = $refs ? ($refs =~ /<([^>]+)>/g) : ();
+       my @refs = defined $refs ? ($refs =~ /<([^>]+)>/g) : ();

        my $irt = $hdr->header_raw('In-Reply-To');
        if (defined $irt) {
        my $irt = $hdr->header_raw('In-Reply-To');
        if (defined $irt) {

-               $irt = mid_clean($irt);
-               $irt = undef if $mid eq $irt;
+               if ($irt eq '') {
+                       $irt = undef;
+               } else {
+                       $irt = mid_clean($irt);
+                       $irt = undef if $mid eq $irt;
+               }

        }
 
        my $tid;
        }
 
        my $tid;