From: Eric Wong <e@80x24.org>
Date: Tue, 27 Oct 2020 07:54:12 +0000 (+0000)
Subject: searchidxshard: allow msgref to be undef
X-Git-Tag: v1.7.0~1689
X-Git-Url: http://www.git.stargrave.org/?a=commitdiff_plain;h=ff760861406b8e6319d0229f743e44283e925296;p=public-inbox.git

searchidxshard: allow msgref to be undef

We don't need to keep it in code paths which are guaranteed to
only see PublicInbox::Eml (and not Email::MIME or PublicInbox::MIME
which did not round-trip properly).  However, we must set
{raw_bytes} since PublicInbox::Eml may add an extra "\n" for
rare messages with no bodies.
---

diff --git a/lib/PublicInbox/SearchIdxShard.pm b/lib/PublicInbox/SearchIdxShard.pm
index 8e24aa1b..8ff9ab8b 100644
--- a/lib/PublicInbox/SearchIdxShard.pm
+++ b/lib/PublicInbox/SearchIdxShard.pm
@@ -107,13 +107,15 @@ sub shard_worker_loop ($$$$$) {
 sub index_raw {
 	my ($self, $msgref, $eml, $smsg) = @_;
 	if (my $w = $self->{w}) {
+		$msgref //= \($eml->as_string);
+		$smsg->{raw_bytes} //= length($$msgref);
 		# mid must be last, it can contain spaces (but not LF)
 		print $w join(' ', @$smsg{qw(raw_bytes bytes
 						num blob ds ts tid mid)}),
 			"\n", $$msgref or die "failed to write shard $!\n";
 	} else {
 		if ($eml) {
-			undef $$msgref;
+			undef($$msgref) if $msgref;
 		} else { # --xapian-only + --sequential-shard:
 			$eml = PublicInbox::Eml->new($msgref);
 		}