From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net X-Spam-Level: X-Spam-ASN: X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,AWL,BAYES_00 shortcircuit=no autolearn=ham autolearn_force=no version=3.4.2 Received: from localhost (dcvr.yhbt.net [127.0.0.1]) by dcvr.yhbt.net (Postfix) with ESMTP id 033EA1FA04 for ; Sat, 18 Apr 2020 03:38:54 +0000 (UTC) From: Eric Wong To: meta@public-inbox.org Subject: [PATCH 2/8] searchidx: die on cat-file failures Date: Sat, 18 Apr 2020 03:38:47 +0000 Message-Id: <20200418033853.9798-3-e@yhbt.net> In-Reply-To: <20200418033853.9798-1-e@yhbt.net> References: <20200418033853.9798-1-e@yhbt.net> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit List-Id: We always use the object ID from "git " for retrieving blobs, so fail loudly if the git repository is corrupt instead of silently continuing. --- lib/PublicInbox/SearchIdx.pm | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm index 05689941..d1290dc2 100644 --- a/lib/PublicInbox/SearchIdx.pm +++ b/lib/PublicInbox/SearchIdx.pm @@ -551,13 +551,11 @@ sub unindex_both { sub do_cat_mail { my ($git, $blob, $sizeref) = @_; - my $mime = eval { - my $str = $git->cat_file($blob, $sizeref); - # fixup bugs from import: - $$str =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s; - PublicInbox::MIME->new($str); - }; - $@ ? undef : $mime; + my $str = $git->cat_file($blob, $sizeref) or + die "BUG: $blob not found in $git->{git_dir}"; + # fixup bugs from import: + $$str =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s; + PublicInbox::MIME->new($str); } # called by public-inbox-index @@ -602,7 +600,7 @@ sub read_log { } next; } - my $mime = do_cat_mail($git, $blob, \$bytes) or next; + my $mime = do_cat_mail($git, $blob, \$bytes); my $smsg = bless {}, 'PublicInbox::Smsg'; batch_adjust(\$max, $bytes, $batch_cb, $latest, ++$nr); $smsg->{blob} = $blob; @@ -623,7 +621,7 @@ sub read_log { close($log) or die "git log failed: \$?=$?"; # get the leftovers foreach my $blob (keys %D) { - my $mime = do_cat_mail($git, $blob, \$bytes) or next; + my $mime = do_cat_mail($git, $blob, \$bytes); $del_cb->($self, $mime); } $batch_cb->($nr, $latest, $newest);