[PATCH 3/5] clone|--mirror: fix and test against pre-manifest WWW

[Eric Wong <e@80x24.org>]

There may still be pre-manifest.js.gz versions of PublicInbox::WWW.
running and serving v2 inboxes.

Since $INBOX_URL/manifest.js.gz was not understood, it was
assumed to be a Message-ID and 301-ed to
"$INBOX_URL/manifest.js.gz/" with a trailing slash, so our 404
checks were invalid.  Update our fallbacks to deal with 301
by catching JSON decoding errors to trigger HTML scraping.

For HTML parsing, be sure to not be fooled by potential
user-generated content and only scan the part after the last
<hr>.

We also need to avoid propagating $? from curl unnecessarily
when we can continue safely.

Finally, update v2mirror.t with tests to use PublicInbox::WWW
from our "v1.1.0-pre1" tag to ensure these code paths get tested
---
 lib/PublicInbox/LeiMirror.pm  | 13 ++++--
 lib/PublicInbox/TestCommon.pm |  1 +
 t/v2mirror.t                  | 78 +++++++++++++++++++++++++++++++----
 3 files changed, 82 insertions(+), 10 deletions(-)

diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm
index 53f7dd31..fe81b967 100644
--- a/lib/PublicInbox/LeiMirror.pm
+++ b/lib/PublicInbox/LeiMirror.pm
@@ -42,7 +42,8 @@ sub try_scrape {
 
 	# we grep with URL below, we don't want Subject/From headers
 	# making us clone random URLs
-	my @urls = ($html =~ m!\bgit clone --mirror ([a-z\+]+://\S+)!g);
+	my @html = split(/<hr>/, $html);
+	my @urls = ($html[-1] =~ m!\bgit clone --mirror ([a-z\+]+://\S+)!g);
 	my $url = $uri->as_string;
 	chop($url) eq '/' or die "BUG: $uri not canonicalized";
 
@@ -184,7 +185,9 @@ sub run_reap {
 	my $reap = PublicInbox::OnDestroy->new($lei->can('sigint_reap'), $pid);
 	waitpid($pid, 0) == $pid or die "waitpid @$cmd: $!";
 	@$reap = (); # cancel reap
-	$?
+	my $ret = $?;
+	$? = 0; # don't let it influence normal exit
+	$ret;
 }
 
 sub clone_v1 {
@@ -358,7 +361,11 @@ sub try_manifest {
 		return try_scrape($self) if ($cerr >> 8) == 22; # 404 missing
 		return $lei->child_error($cerr, "@$cmd failed");
 	}
-	my $m = decode_manifest($ft, $fn, $uri);
+	my $m = eval { decode_manifest($ft, $fn, $uri) };
+	if ($@) {
+		warn $@;
+		return try_scrape($self);
+	}
 	my ($path_pfx, $v1_path, @v2_epochs) = deduce_epochs($m, $path);
 	if (@v2_epochs) {
 		# It may be possible to have v1 + v2 in parallel someday:
diff --git a/lib/PublicInbox/TestCommon.pm b/lib/PublicInbox/TestCommon.pm
index aff34853..cd706e0e 100644
--- a/lib/PublicInbox/TestCommon.pm
+++ b/lib/PublicInbox/TestCommon.pm
@@ -469,6 +469,7 @@ sub start_script {
 			$ENV{LISTEN_PID} = $$;
 			$ENV{LISTEN_FDS} = $fds;
 		}
+		if ($opt->{-C}) { chdir($opt->{-C}) or die "chdir: $!" }
 		$0 = join(' ', @$cmd);
 		if ($sub) {
 			eval { PublicInbox::DS->Reset };
diff --git a/t/v2mirror.t b/t/v2mirror.t
index 20a8daaa..1231b72d 100644
--- a/t/v2mirror.t
+++ b/t/v2mirror.t
@@ -5,6 +5,7 @@ use v5.10.1;
 use PublicInbox::TestCommon;
 use File::Path qw(remove_tree make_path);
 use Cwd qw(abs_path);
+use PublicInbox::Spawn qw(which);
 require_git(2.6);
 require_cmd('curl');
 local $ENV{HOME} = abs_path('t');
@@ -23,7 +24,8 @@ my $pi_config = "$tmpdir/config";
 	open my $fh, '>', $pi_config or die "open($pi_config): $!";
 	print $fh <<"" or die "print $pi_config: $!";
 [publicinbox "v2"]
-	inboxdir = $tmpdir/in
+; using "mainrepo" rather than "inboxdir" for v1.1.0-pre1 WWW compat below
+	mainrepo = $tmpdir/in
 	address = test\@example.com
 
 	close $fh or die "close($pi_config): $!";
@@ -62,11 +64,11 @@ $v2w->done;
 }
 $ibx->cleanup;
 
-my $sock = tcp_server();
+local $ENV{TEST_IPV4_ONLY} = 1; # plackup (below) doesn't do IPv6
+my $rdr = { 3 => tcp_server() };
 my @cmd = ('-httpd', '-W0', "--stdout=$tmpdir/out", "--stderr=$tmpdir/err");
-my $td = start_script(\@cmd, undef, { 3 => $sock });
-my ($host, $port) = tcp_host_port($sock);
-$sock = undef;
+my $td = start_script(\@cmd, undef, $rdr);
+my ($host, $port) = tcp_host_port(delete $rdr->{3});
 
 @cmd = (qw(-clone -q), "http://$host:$port/v2/", "$tmpdir/m");
 run_script(\@cmd) or xbail '-clone';
@@ -288,7 +290,69 @@ if ('test read-only epoch dirs') {
 		'got one more cloned epoch');
 }
 
-ok($td->kill, 'killed httpd');
-$td->join;
+my $err = '';
+my $v110 = xqx([qw(git rev-parse v1.1.0-pre1)], undef, { 2 => \$err });
+SKIP: {
+	skip("no detected public-inbox GIT_DIR ($err)", 1) if $?;
+	# using plackup to test old PublicInbox::WWW since -httpd from
+	# back then relied on some packages we no longer depend on
+	my $plackup = which('plackup') or skip('no plackup in path', 1);
+	require PublicInbox::Lock;
+	chomp $v110;
+	my ($base) = ($0 =~ m!\b([^/]+)\.[^\.]+\z!);
+	my $wt = "t/data-gen/$base.pre-manifest";
+	my $lk = bless { lock_path => __FILE__ }, 'PublicInbox::Lock';
+	$lk->lock_acquire;
+	my $psgi = "$wt/app.psgi";
+	if (!-f $psgi) { # checkout a pre-manifest.js.gz version
+		my $t = File::Temp->new(TEMPLATE => 'g-XXXX', TMPDIR => 1);
+		my $env = { GIT_INDEX_FILE => $t->filename };
+		xsys([qw(git read-tree), $v110], $env) and xbail 'read-tree';
+		xsys([qw(git checkout-index -a), "--prefix=$wt/"], $env)
+			and xbail 'checkout-index';
+		my $f = "$wt/app.psgi.tmp.$$";
+		open my $fh, '>', $f or xbail $!;
+		print $fh <<'EOM' or xbail $!;
+use Plack::Builder;
+use PublicInbox::WWW;
+my $www = PublicInbox::WWW->new;
+builder { enable 'Head'; sub { $www->call(@_) } }
+EOM
+		close $fh or xbail $!;
+		rename($f, $psgi) or xbail $!;
+	}
+	$lk->lock_release;
+
+	$rdr->{run_mode} = 0;
+	$rdr->{-C} = $wt;
+	my $cmd = [$plackup, qw(-Enone -Ilib), "--host=$host", "--port=$port"];
+	$td->join('TERM');
+	open $rdr->{2}, '>>', "$tmpdir/plackup.err.log" or xbail "open: $!";
+	open $rdr->{1}, '>>&', $rdr->{2} or xbail "open: $!";
+	$td = start_script($cmd, { PERL5LIB => 'lib' }, $rdr);
+	# wait for plackup socket()+bind()+listen()
+	my %opt = ( Proto => 'tcp', Type => Socket::SOCK_STREAM(),
+		PeerAddr => "$host:$port" );
+	for (0..50) {
+		tick();
+		last if IO::Socket::INET->new(%opt);
+	}
+	my $dst = "$tmpdir/scrape";
+	@cmd = (qw(-clone -q), "http://$host:$port/v2", $dst);
+	run_script(\@cmd, undef, { 2 => \(my $err = '') });
+	is($?, 0, 'scraping clone on old PublicInbox::WWW')
+		or diag $err;
+	my @g_all = glob("$dst/git/*.git");
+	ok(scalar(@g_all) > 1, 'cloned multiple epochs');
+
+	remove_tree($dst);
+	@cmd = (qw(-clone -q --epoch=~0), "http://$host:$port/v2", $dst);
+	run_script(\@cmd, undef, { 2 => \($err = '') });
+	is($?, 0, 'partial scraping clone on old PublicInbox::WWW');
+	my @g_last = grep { -w $_ } glob("$dst/git/*.git");
+	is_deeply(\@g_last, [ $g_all[-1] ], 'partial clone of ~0 worked');
+
+	$td->join('TERM');
+}
 
 done_testing;