X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=t%2Fv2reindex.t;h=a2fc20757d2f0a33e4d90918aa1e4fe5d977da36;hb=1814b1a0b78770c8ba9e7a0adef56c4c324d4064;hp=b6164ff810febd2936236e7ac2bd42f0d2e3bdc8;hpb=4bebfa0c80ad7f4596a7dca98b39121470a42af0;p=public-inbox.git

diff --git a/t/v2reindex.t b/t/v2reindex.t
index b6164ff8..a2fc2075 100644
--- a/t/v2reindex.t
+++ b/t/v2reindex.t
@@ -3,13 +3,14 @@
 use strict;
 use warnings;
 use Test::More;
-use PublicInbox::MIME;
-use PublicInbox::ContentId qw(content_digest);
+use PublicInbox::Eml;
+use PublicInbox::ContentHash qw(content_digest);
 use File::Path qw(remove_tree);
 use PublicInbox::TestCommon;
 require_git(2.6);
 require_mods(qw(DBD::SQLite Search::Xapian));
 use_ok 'PublicInbox::V2Writable';
+use_ok 'PublicInbox::OverIdx';
 my ($inboxdir, $for_destroy) = tmpdir();
 my $ibx_config = {
 	inboxdir => $inboxdir,
@@ -24,15 +25,13 @@ my $agpl = do {
 	<$fh>;
 };
 my $phrase = q("defending all users' freedom");
-my $mime = PublicInbox::MIME->create(
-	header => [
-		From => 'a@example.com',
-		To => 'test@example.com',
-		Subject => 'this is a subject',
-		Date => 'Fri, 02 Oct 1993 00:00:00 +0000',
-	],
-	body => $agpl,
-);
+my $mime = PublicInbox::Eml->new(<<'EOF'.$agpl);
+From: a@example.com
+To: test@example.com
+Subject: this is a subject
+Date: Fri, 02 Oct 1993 00:00:00 +0000
+
+EOF
 my $minmax;
 my $msgmap;
 my ($mark1, $mark2, $mark3, $mark4);
@@ -40,7 +39,7 @@ my ($mark1, $mark2, $mark3, $mark4);
 	my %config = %$ibx_config;
 	my $ibx = PublicInbox::Inbox->new(\%config);
 	my $im = PublicInbox::V2Writable->new($ibx, {nproc => 1});
-	my $im0 = $im->importer();
+	my $im0 = $im->importer(0);
 	foreach my $i (1..10) {
 		$mime->header_set('Message-Id', "<$i\@example.com>");
 		ok($im->add($mime), "message $i added");
@@ -425,6 +424,46 @@ ok(!-d $xap, 'Xapian directories removed again');
 		  ], 'msgmap as expected' );
 }
 
+my $check_rethread = sub {
+	my ($desc) = @_;
+	my @warn;
+	local $SIG{__WARN__} = sub { push @warn, @_ };
+	my %config = %$ibx_config;
+	my $ibx = PublicInbox::Inbox->new(\%config);
+	my $f = $ibx->over->{dbh}->sqlite_db_filename;
+	my $over = PublicInbox::OverIdx->new($f);
+	my $dbh = $over->dbh;
+	my $non_ghost_tids = sub {
+		$dbh->selectall_arrayref(<<'');
+SELECT tid FROM over WHERE num > 0 ORDER BY tid ASC
+
+	};
+	my $before = $non_ghost_tids->();
+
+	# mess up threading:
+	my $tid = PublicInbox::OverIdx::get_counter($dbh, 'thread');
+	my $nr = $dbh->do('UPDATE over SET tid = ?', undef, $tid);
+	diag "messing up all threads with tid=$tid";
+
+	my $v2w = PublicInbox::V2Writable->new($ibx);
+	my @pr;
+	my $pr = sub { push @pr, @_ };
+	$v2w->index_sync({reindex => 1, rethread => 1, -progress => $pr});
+	# diag "@pr"; # nobody cares
+	is_deeply(\@warn, [], 'no warnings on reindex + rethread');
+
+	my @n = $dbh->selectrow_array(<<EOS, undef, $tid);
+SELECT COUNT(*) FROM over WHERE tid <= ?
+EOS
+	is_deeply(\@n, [ 0 ], 'rethread dropped old threadids');
+	my $after = $non_ghost_tids->();
+	ok($after->[0]->[0] > $before->[-1]->[0],
+		'all tids greater than before');
+	is(scalar @$after, scalar @$before, 'thread count unchanged');
+};
+
+$check_rethread->('no-monster');
+
 # A real example from linux-renesas-soc on lore where a 3-headed monster
 # of a message has 3 sets of common headers.  Another normal message
 # previously existed with a single Message-ID that conflicts with one
@@ -436,7 +475,7 @@ ok(!-d $xap, 'Xapian directories removed again');
 	$config{indexlevel} = 'medium';
 	my $ibx = PublicInbox::Inbox->new(\%config);
 	my $im = PublicInbox::V2Writable->new($ibx);
-	my $m3 = PublicInbox::MIME->new(<<'EOF');
+	my $m3 = PublicInbox::Eml->new(<<'EOF');
 Date: Tue, 24 May 2016 14:34:22 -0700 (PDT)
 Message-Id: <20160524.143422.552507610109476444.d@example.com>
 To: t@example.com
@@ -467,7 +506,7 @@ Somehow we got a message with 3 sets of headers into one
 message, could've been something broken on the archiver side.
 EOF
 
-	my $m1 = PublicInbox::MIME->new(<<'EOF');
+	my $m1 = PublicInbox::Eml->new(<<'EOF');
 From: a@example.com
 To: t@example.com
 Subject: [PATCH 12/13]
@@ -499,4 +538,8 @@ EOF
 	is_deeply([values %uniq], [3], 'search on different subjects');
 }
 
+# XXX: not deterministic when dealing with ambiguous messages, oh well
+$check_rethread->('3-headed-monster once');
+$check_rethread->('3-headed-monster twice');
+
 done_testing();