[PATCH 0/2] fixes noticed while tracking down fast-import failures

[PATCH 0/2] fixes noticed while tracking down fast-import failures

[Eric Wong]

I'm still trying to track down the cause of fast-import
failures[1], but this series presents some useful fixes
regardless.

Link: https://public-inbox.org/meta/CAL_JsqK7P4gjLPyvzxNEcYmxT4j6Ah5f3Pz1RqDHxmysTg3aEg@mail.gmail.com/

Eric Wong (2):
  lei: prevent empty {bytes} field in saved search
  import: croak (instead of die) on write failures

 lib/PublicInbox/Import.pm    | 2 +-
 lib/PublicInbox/LeiSearch.pm | 2 ++
 lib/PublicInbox/LeiToMail.pm | 1 +
 lib/PublicInbox/OverIdx.pm   | 6 +++++-
 4 files changed, 9 insertions(+), 2 deletions(-)

[PATCH 1/2] lei: prevent empty {bytes} field in saved search

[Eric Wong]

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 {

[PATCH 2/2] import: croak (instead of die) on write failures

[Eric Wong]

This allows accurate reporting of the error location and can be
made to dump a Perl backtrace via PERL5OPT='-MCarp=verbose'.
Noticed while tracking down fast-import failures.

Link: https://public-inbox.org/meta/CAL_JsqK7P4gjLPyvzxNEcYmxT4j6Ah5f3Pz1RqDHxmysTg3aEg@mail.gmail.com/
---
 lib/PublicInbox/Import.pm | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm
index 51ddfa7f..a951874b 100644
--- a/lib/PublicInbox/Import.pm
+++ b/lib/PublicInbox/Import.pm
@@ -85,7 +85,7 @@ sub gfi_start {
 	$self->{io};
 }
 
-sub wfail () { die "write to fast-import failed: $!" }
+sub wfail () { croak "write to fast-import failed: $!" }
 
 sub now_raw () { time . ' +0000' }