From 003829cdaa583d66c5af7564296d266952e0f12f Mon Sep 17 00:00:00 2001
From: Eric Wong <e@80x24.org>
Date: Fri, 8 Mar 2024 21:05:03 +0000
Subject: lei: prevent empty {bytes} field in saved search

Noticed while tracking down fast-import crash bug report.

Link: https://public-inbox.org/meta/CAL_JsqK7P4gjLPyvzxNEcYmxT4j6Ah5f3Pz1RqDHxmysTg3aEg@mail.gmail.com/
---
 lib/PublicInbox/LeiSearch.pm | 2 ++
 lib/PublicInbox/LeiToMail.pm | 1 +
 lib/PublicInbox/OverIdx.pm   | 6 +++++-
 3 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/lib/PublicInbox/LeiSearch.pm b/lib/PublicInbox/LeiSearch.pm
index 29e3213f..684668c5 100644
--- a/lib/PublicInbox/LeiSearch.pm
+++ b/lib/PublicInbox/LeiSearch.pm
@@ -103,6 +103,8 @@ sub xoids_for {
 		for my $o (@overs) {
 			my ($id, $prev);
 			while (my $cur = $o->next_by_mid($mid, \$id, \$prev)) {
+				# {bytes} may be '' from old bug
+				$cur->{bytes} = 1 if $cur->{bytes} eq '';
 				next if $cur->{bytes} == 0 ||
 					$xoids->{$cur->{blob}};
 				$git->cat_async($cur->{blob}, \&_cmp_1st,
diff --git a/lib/PublicInbox/LeiToMail.pm b/lib/PublicInbox/LeiToMail.pm
index a816df6c..dfae29e9 100644
--- a/lib/PublicInbox/LeiToMail.pm
+++ b/lib/PublicInbox/LeiToMail.pm
@@ -149,6 +149,7 @@ sub git_to_mail { # git->cat_async callback
 						"W: $oid is $type (!= blob)");
 		$size or return $self->{lei}->child_error(0,"E: $oid is empty");
 		$smsg->{blob} eq $oid or die "BUG: expected=$smsg->{blob}";
+		$smsg->{bytes} ||= $size;
 		$self->{wcb}->($bref, $smsg);
 	};
 	$self->{lei}->fail("$@ (oid=$oid)") if $@;
diff --git a/lib/PublicInbox/OverIdx.pm b/lib/PublicInbox/OverIdx.pm
index c9c25828..4f8533f7 100644
--- a/lib/PublicInbox/OverIdx.pm
+++ b/lib/PublicInbox/OverIdx.pm
@@ -17,6 +17,7 @@ use PublicInbox::MID qw/id_compress mids_for_index references/;
 use PublicInbox::Smsg qw(subject_normalized);
 use Compress::Zlib qw(compress);
 use Carp qw(croak);
+use bytes (); # length
 
 sub dbh_new {
 	my ($self) = @_;
@@ -263,7 +264,10 @@ sub ddd_for ($) {
 
 sub add_overview {
 	my ($self, $eml, $smsg) = @_;
-	$smsg->{lines} = $eml->body_raw =~ tr!\n!\n!;
+	my $raw = $eml->body_raw;
+	$smsg->{lines} = $raw =~ tr!\n!\n!;
+	$smsg->{bytes} //= bytes::length $raw;
+	undef $raw;
 	my $mids = mids_for_index($eml);
 	my $refs = $smsg->parse_references($eml, $mids);
 	$mids->[0] //= do {
-- 
cgit v1.2.3-24-ge0c7