overidx: each_by_mid: account for messages being deleted

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

diff --git a/lib/PublicInbox/OverIdx.pm b/lib/PublicInbox/OverIdx.pm
index 2e3d4534f125d92383f3e05e03fcf0ad10b6e3a1..985abbf4e693de8f01939556abca07504fa21eae 100644 (file)
--- a/lib/PublicInbox/OverIdx.pm
+++ b/lib/PublicInbox/OverIdx.pm
@@ -158,7 +158,8 @@ SELECT $cols FROM over WHERE over.num = ? LIMIT 1
 
                foreach (@$nums) {
                        $sth->execute($_->[0]);
-                       my $smsg = $sth->fetchrow_hashref;
+                       # $cb may delete rows and invalidate nums
+                       my $smsg = $sth->fetchrow_hashref // next;
                        $smsg = PublicInbox::Over::load_from_row($smsg);
                        $cb->($self, $smsg, @arg) or return;
                }
@@ -243,12 +244,13 @@ sub link_refs {
        $tid;
 }
 
-# normalize subjects so they are suitable as pathnames for URLs
-# XXX: consider for removal
+# normalize subjects somewhat, they used to be ASCII-only but now
+# we use \w for UTF-8 support.  We may still drop it entirely and
+# rely on Xapian for subject matches...
 sub subject_path ($) {
        my ($subj) = @_;
        $subj = subject_normalized($subj);
-       $subj =~ s![^a-zA-Z0-9_\.~/\-]+!_!g;
+       $subj =~ s![^\w\.~/\-]+!_!g;
        lc($subj);
 }