From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <e@80x24.org>
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,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 1B0A120248
	for <meta@public-inbox.org>; Fri, 19 Apr 2019 08:28:27 +0000 (UTC)
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [RFC] index: warn with info about the message as context
Date: Fri, 19 Apr 2019 08:28:26 +0000
Message-Id: <20190419082826.3183-1-e@80x24.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
List-Id: <meta.public-inbox.org>

This can help users track down the source of warnings
when presented with imperfect emails.

While we're at it, make the __WARN__ callback in t/v2writable.t
a no-op since we don't check for warnings, there.
---
 lib/PublicInbox/SearchIdxPart.pm | 7 +++++++
 lib/PublicInbox/V2Writable.pm    | 5 ++++-
 script/public-inbox-index        | 3 +++
 t/v2writable.t                   | 3 +--
 4 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/lib/PublicInbox/SearchIdxPart.pm b/lib/PublicInbox/SearchIdxPart.pm
index 7fe2120..51d81a0 100644
--- a/lib/PublicInbox/SearchIdxPart.pm
+++ b/lib/PublicInbox/SearchIdxPart.pm
@@ -48,8 +48,15 @@ sub spawn_worker {
 sub partition_worker_loop ($$$$) {
 	my ($self, $r, $part, $bnote) = @_;
 	$0 = "pi-v2-partition[$part]";
+	my $current_info = '';
+	my $warn_cb = $SIG{__WARN__} || sub { print STDERR @_ };
+	local $SIG{__WARN__} = sub {
+		chomp $current_info;
+		$warn_cb->("[$part] $current_info: ", @_);
+	};
 	$self->begin_txn_lazy;
 	while (my $line = $r->getline) {
+		$current_info = $line;
 		if ($line eq "commit\n") {
 			$self->commit_txn_lazy;
 		} elsif ($line eq "close\n") {
diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index 6829a34..87e8f3e 100644
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -72,6 +72,7 @@ sub new {
 		im => undef, #  PublicInbox::Import
 		parallel => 1,
 		transact_bytes => 0,
+		current_info => '',
 		xpfx => $xpfx,
 		over => PublicInbox::OverIdx->new("$xpfx/over.sqlite3", 1),
 		lock_path => "$dir/inbox.lock",
@@ -949,8 +950,10 @@ sub index_sync {
 		my $fh = $self->{reindex_pipe} = $git->popen(@cmd, $range);
 		my $cmt;
 		while (<$fh>) {
+			chomp;
+			$self->{current_info} = "$i.git $_";
 			if (/\A$x40$/o && !defined($cmt)) {
-				chomp($cmt = $_);
+				$cmt = $_;
 			} elsif (/\A:\d{6} 100644 $x40 ($x40) [AM]\tm$/o) {
 				$self->reindex_oid($mm_tmp, $D, $git, $1,
 						$regen, $reindex);
diff --git a/script/public-inbox-index b/script/public-inbox-index
index 5adb6e7..2f810a5 100755
--- a/script/public-inbox-index
+++ b/script/public-inbox-index
@@ -85,6 +85,9 @@ sub index_dir {
 				}
 			}
 		}
+		local $SIG{__WARN__} = sub {
+			print STDERR $v2w->{current_info}, ': ', @_;
+		};
 		$v2w->index_sync({ reindex => $reindex, prune => $prune });
 	} else {
 		my $s = PublicInbox::SearchIdx->new($repo, 1);
diff --git a/t/v2writable.t b/t/v2writable.t
index f171417..2826513 100644
--- a/t/v2writable.t
+++ b/t/v2writable.t
@@ -253,10 +253,9 @@ EOF
 }
 
 {
-	my @warn;
 	my $x = 'x'x250;
 	my $y = 'y'x250;
-	local $SIG{__WARN__} = sub { push @warn, @_ };
+	local $SIG{__WARN__} = sub {};
 	$mime->header_set('Subject', 'long mid');
 	$mime->header_set('Message-ID', "<$x>");
 	ok($im->add($mime), 'add excessively long Message-ID');
-- 
EW