[PATCH] process_io: fix binmode and use it in lei_xsearch for curl

[PATCH] process_io: fix binmode and use it in lei_xsearch for curl

[Eric Wong]

The `binmode' perlop can only take two scalars, so passing
`@_' blindly won't work since prototypes are checked.  This
means we can get IO::Uncompress::Gunzip working properly
with ProcessIO.
---
 lib/PublicInbox/LeiXSearch.pm | 25 +++++++++++--------------
 lib/PublicInbox/ProcessIO.pm  |  4 ++--
 t/lei-q-remote-import.t       | 33 ++++++++++++++++++++-------------
 3 files changed, 33 insertions(+), 29 deletions(-)

diff --git a/lib/PublicInbox/LeiXSearch.pm b/lib/PublicInbox/LeiXSearch.pm
index 4077191f..ef66aaea 100644
--- a/lib/PublicInbox/LeiXSearch.pm
+++ b/lib/PublicInbox/LeiXSearch.pm
@@ -21,6 +21,7 @@ use PublicInbox::LEI;
 use Fcntl qw(SEEK_SET F_SETFL O_APPEND O_RDWR);
 use PublicInbox::ContentHash qw(git_sha);
 use POSIX qw(strftime);
+use autodie qw(seek truncate);
 
 sub new {
 	my ($class) = @_;
@@ -353,29 +354,25 @@ sub query_remote_mboxrd {
 		$uri->query_form(@qform, q => $q);
 		my $cmd = $curl->for_uri($lei, $uri);
 		$lei->qerr("# $cmd");
-		my ($fh, $pid) = popen_rd($cmd, undef, $rdr);
-		my $reap_curl = PublicInbox::AutoReap->new($pid);
-		$fh = IO::Uncompress::Gunzip->new($fh, MultiStream => 1);
+		my $cfh = popen_rd($cmd, undef, $rdr);
+		my $fh = IO::Uncompress::Gunzip->new($cfh, MultiStream => 1);
 		PublicInbox::MboxReader->mboxrd($fh, \&each_remote_eml, $self,
 						$lei, $each_smsg);
 		$lei->sto_done_request if delete($self->{-sto_imported});
-		$reap_curl->join;
 		my $nr = delete $lei->{-nr_remote_eml} // 0;
-		if ($? == 0) {
-			# don't update if no results, maybe MTA is down
+		close $cfh;
+		if ($? == 0) { # don't update if no results, maybe MTA is down
 			$lei->{lss}->cfg_set($key, $start) if $key && $nr;
 			mset_progress($lei, $lei->{-current_url}, $nr, $nr);
 			next;
 		}
 		my $err;
-		if (-s $cerr) {
-			seek($cerr, 0, SEEK_SET) //
-					warn "seek($cmd stderr): $!";
-			$err = do { local $/; <$cerr> } //
-					warn "read($cmd stderr): $!";
-			truncate($cerr, 0) // warn "truncate($cmd stderr): $!";
-		}
-		$err //= '';
+		eval {
+			seek($cerr, 0, SEEK_SET);
+			read($cerr, $err, -s $cerr);
+			truncate($cerr, 0);
+		};
+		warn "E: $@ ($cmd stderr)" if $@;
 		next if (($? >> 8) == 22 && $err =~ /\b404\b/);
 		$uri->query_form(q => $qstr);
 		$lei->child_error($?, "E: <$uri> $err");
diff --git a/lib/PublicInbox/ProcessIO.pm b/lib/PublicInbox/ProcessIO.pm
index 5a81e3a6..f120edd0 100644
--- a/lib/PublicInbox/ProcessIO.pm
+++ b/lib/PublicInbox/ProcessIO.pm
@@ -33,8 +33,8 @@ sub TIEHANDLE {
 
 # for IO::Uncompress::Gunzip
 sub BINMODE {
-	my $self = shift;
-	binmode($self->{fh}, @_);
+	return binmode($_[0]->{fh}) if @_ == 1;
+	binmode $_[0]->{fh}, $_[1];
 }
 
 sub READ { read($_[0]->{fh}, $_[1], $_[2], $_[3] || 0) }
diff --git a/t/lei-q-remote-import.t b/t/lei-q-remote-import.t
index 92d8c9b6..885fa3e1 100644
--- a/t/lei-q-remote-import.t
+++ b/t/lei-q-remote-import.t
@@ -1,7 +1,8 @@
 #!perl -w
-# Copyright (C) 2021 all contributors <meta@public-inbox.org>
+# Copyright (C) all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
-use strict; use v5.10.1; use PublicInbox::TestCommon;
+use v5.12; use PublicInbox::TestCommon;
+use autodie qw(open close unlink);
 require_mods(qw(lei -httpd));
 require_cmd 'curl';
 use PublicInbox::MboxReader;
@@ -16,7 +17,7 @@ my $url = "http://$host_port/t2/";
 my $exp1 = [ eml_load('t/plack-qp.eml') ];
 my $exp2 = [ eml_load('t/iso-2202-jp.eml') ];
 my $slurp_emls = sub {
-	open my $fh, '<', $_[0] or BAIL_OUT "open: $!";
+	open my $fh, '<', $_[0];
 	my @eml;
 	PublicInbox::MboxReader->mboxrd($fh, sub {
 		my $eml = shift;
@@ -31,33 +32,33 @@ test_lei({ tmpdir => $tmpdir }, sub {
 	my @cmd = ('q', '-o', "mboxrd:$o", 'm:qp@example.com');
 	lei_ok(@cmd);
 	ok(-f $o && !-s _, 'output exists but is empty');
-	unlink $o or BAIL_OUT $!;
+	unlink $o;
 	lei_ok(@cmd, '-I', $url);
 	is_deeply($slurp_emls->($o), $exp1, 'got results after remote search');
-	unlink $o or BAIL_OUT $!;
+	unlink $o;
 	lei_ok(@cmd);
 	ok(-f $o && -s _, 'output exists after import but is not empty') or
 		diag $lei_err;
 	is_deeply($slurp_emls->($o), $exp1, 'got results w/o remote search');
-	unlink $o or BAIL_OUT $!;
+	unlink $o;
 
 	$cmd[-1] = 'm:199707281508.AAA24167@hoyogw.example';
 	lei_ok(@cmd, '-I', $url, '--no-import-remote');
 	is_deeply($slurp_emls->($o), $exp2, 'got another after remote search');
-	unlink $o or BAIL_OUT $!;
+	unlink $o;
 	lei_ok(@cmd);
 	ok(-f $o && !-s _, '--no-import-remote did not memoize');
 
 	open my $fh, '>', "$o.lock";
 	$cmd[-1] = 'm:qp@example.com';
-	unlink $o or xbail("unlink $o $! cwd=".Cwd::getcwd());
+	unlink $o;
 	lei_ok(@cmd, '--lock=none');
 	ok(-f $o && -s _, '--lock=none respected') or diag $lei_err;
-	unlink $o or xbail("unlink $o $! cwd=".Cwd::getcwd());
+	unlink $o;
 	ok(!lei(@cmd, '--lock=dotlock,timeout=0.000001'), 'dotlock fails');
 	like($lei_err, qr/dotlock timeout/, 'timeout noted');
 	ok(-f $o && !-s _, 'nothing output on lock failure');
-	unlink "$o.lock" or BAIL_OUT $!;
+	unlink "$o.lock";
 	lei_ok(@cmd, '--lock=dotlock,timeout=0.000001',
 		\'succeeds after lock removal');
 
@@ -76,8 +77,8 @@ test_lei({ tmpdir => $tmpdir }, sub {
 			'm:testmessage@example.com');
 	is($lei_out, '', 'message not imported when in local external');
 
-	open $fh, '>', $o or BAIL_OUT;
-	print $fh <<'EOF' or BAIL_OUT;
+	open $fh, '>', $o;
+	print $fh <<'EOF';
 From a@z Mon Sep 17 00:00:00 2001
 From: nobody@localhost
 Date: Sat, 13 Mar 2021 18:23:01 +0600
@@ -86,7 +87,7 @@ Status: OR
 
 whatever
 EOF
-	close $fh or BAIL_OUT;
+	close $fh;
 	lei_ok(qw(q -o), "mboxrd:$o", 'm:testmessage@example.com');
 	is_deeply($slurp_emls->($o), [$exp],
 		'got expected result after clobber') or diag $lei_err;
@@ -103,5 +104,11 @@ EOF
 	lei_ok([qw(edit-search), "$ENV{HOME}/md"], $edit_env);
 	like($lei_out, qr/^\Q[external "$url"]\E\n\s*lastresult = \d+/sm,
 		'lastresult set');
+
+	unlink $o;
+	lei_ok qw(q --no-save -q m:never2exist@example.com -o), "mboxrd:$o",
+		'--only', $url,
+		\'404 curl exit (22) does not influence lei(1)';
+	is(-s $o, 0, 'empty result');
 });
 done_testing;