X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=t%2Fv1reindex.t;h=f593b3239586e0a013f155451dc9e67138c9b874;hb=2f8d15b1170b137a0512a4f3163b236a5dcbf0b8;hp=8e78aa761333942678dc83abcd4af0a5363948bc;hpb=075d15d10333ea9127170b8c7635e4286777c005;p=public-inbox.git

diff --git a/t/v1reindex.t b/t/v1reindex.t
index 8e78aa76..f593b323 100644
--- a/t/v1reindex.t
+++ b/t/v1reindex.t
@@ -1,36 +1,33 @@
-# Copyright (C) 2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 use strict;
 use warnings;
 use Test::More;
-use PublicInbox::MIME;
-use PublicInbox::ContentId qw(content_digest);
-use File::Temp qw/tempdir/;
+use PublicInbox::ContentHash qw(content_digest);
 use File::Path qw(remove_tree);
-
-foreach my $mod (qw(DBD::SQLite Search::Xapian)) {
-	eval "require $mod";
-	plan skip_all => "$mod missing for v1reindex.t" if $@;
-}
+use PublicInbox::TestCommon;
+use PublicInbox::Eml;
+require_git(2.6);
+require_mods(qw(DBD::SQLite Search::Xapian));
 use_ok 'PublicInbox::SearchIdx';
 use_ok 'PublicInbox::Import';
-my $mainrepo = tempdir('pi-v1reindex-XXXXXX', TMPDIR => 1, CLEANUP => 1);
-is(system(qw(git init -q --bare), $mainrepo), 0);
+use_ok 'PublicInbox::OverIdx';
+my ($inboxdir, $for_destroy) = tmpdir();
 my $ibx_config = {
-	mainrepo => $mainrepo,
+	inboxdir => $inboxdir,
 	name => 'test-v1reindex',
 	-primary_address => 'test@example.com',
 	indexlevel => 'full',
+	-no_fsync => 1,
 };
-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 => "hello world\n",
-);
+my $mime = PublicInbox::Eml->new(<<'EOF');
+From: a@example.com
+To: test@example.com
+Subject: this is a subject
+Date: Fri, 02 Oct 1993 00:00:00 +0000
+
+hello world
+EOF
 my $minmax;
 my $msgmap;
 my ($mark1, $mark2, $mark3, $mark4);
@@ -38,6 +35,7 @@ my ($mark1, $mark2, $mark3, $mark4);
 	my %config = %$ibx_config;
 	my $ibx = PublicInbox::Inbox->new(\%config);
 	my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
+	$im->init_bare;
 	foreach my $i (1..10) {
 		$mime->header_set('Message-Id', "<$i\@example.com>");
 		ok($im->add($mime), "message $i added");
@@ -63,6 +61,7 @@ my ($mark1, $mark2, $mark3, $mark4);
 	$minmax = [ $ibx->mm->minmax ];
 	ok(defined $minmax->[0] && defined $minmax->[1], 'minmax defined');
 	is_deeply($minmax, [ 1, 10 ], 'minmax as expected');
+	is($ibx->mm->num_highwater, 10, 'num_highwater as expected');
 
 	my ($min, $max) = @$minmax;
 	$msgmap = $ibx->mm->msg_range(\$min, $max);
@@ -87,11 +86,13 @@ my ($mark1, $mark2, $mark3, $mark4);
 	is($@, '', 'no error from reindexing');
 	$im->done;
 
+	is($ibx->mm->num_highwater, 10, 'num_highwater as expected');
+
 	my ($min, $max) = $ibx->mm->minmax;
 	is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
 }
 
-my $xap = "$mainrepo/public-inbox/xapian".PublicInbox::Search::SCHEMA_VERSION();
+my $xap = "$inboxdir/public-inbox/xapian".PublicInbox::Search::SCHEMA_VERSION();
 remove_tree($xap);
 ok(!-d $xap, 'Xapian directories removed');
 {
@@ -107,12 +108,13 @@ ok(!-d $xap, 'Xapian directories removed');
 
 	delete $ibx->{mm};
 	is_deeply([ $ibx->mm->minmax ], $minmax, 'minmax unchanged');
+	is($ibx->mm->num_highwater, 10, 'num_highwater as expected');
 
 	my ($min, $max) = $ibx->mm->minmax;
 	is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
 }
 
-ok(unlink "$mainrepo/public-inbox/msgmap.sqlite3", 'remove msgmap');
+ok(unlink "$inboxdir/public-inbox/msgmap.sqlite3", 'remove msgmap');
 remove_tree($xap);
 ok(!-d $xap, 'Xapian directories removed again');
 {
@@ -129,12 +131,13 @@ ok(!-d $xap, 'Xapian directories removed again');
 	ok(-d $xap, 'Xapian directories recreated');
 	delete $ibx->{mm};
 	is_deeply([ $ibx->mm->minmax ], $minmax, 'minmax unchanged');
+	is($ibx->mm->num_highwater, 10, 'num_highwater as expected');
 
 	my ($min, $max) = $ibx->mm->minmax;
 	is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
 }
 
-ok(unlink "$mainrepo/public-inbox/msgmap.sqlite3", 'remove msgmap');
+ok(unlink "$inboxdir/public-inbox/msgmap.sqlite3", 'remove msgmap');
 remove_tree($xap);
 ok(!-d $xap, 'Xapian directories removed again');
 {
@@ -151,12 +154,13 @@ ok(!-d $xap, 'Xapian directories removed again');
 	ok(-d $xap, 'Xapian directories recreated');
 	delete $ibx->{mm};
 	is_deeply([ $ibx->mm->minmax ], $minmax, 'minmax unchanged');
+	is($ibx->mm->num_highwater, 10, 'num_highwater as expected');
 
 	my ($min, $max) = @$minmax;
 	is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
 }
 
-ok(unlink "$mainrepo/public-inbox/msgmap.sqlite3", 'remove msgmap');
+ok(unlink "$inboxdir/public-inbox/msgmap.sqlite3", 'remove msgmap');
 remove_tree($xap);
 ok(!-d $xap, 'Xapian directories removed again');
 {
@@ -174,14 +178,15 @@ ok(!-d $xap, 'Xapian directories removed again');
 	ok(-d $xap, 'Xapian directories recreated');
 	delete $ibx->{mm};
 	is_deeply([ $ibx->mm->minmax ], $minmax, 'minmax unchanged');
-	my $mset = $ibx->search->query('hello world', {mset=>1});
+	is($ibx->mm->num_highwater, 10, 'num_highwater as expected');
+	my $mset = $ibx->search->mset('hello world');
 	isnt($mset->size, 0, 'got Xapian search results');
 
 	my ($min, $max) = $ibx->mm->minmax;
 	is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
 }
 
-ok(unlink "$mainrepo/public-inbox/msgmap.sqlite3", 'remove msgmap');
+ok(unlink "$inboxdir/public-inbox/msgmap.sqlite3", 'remove msgmap');
 remove_tree($xap);
 ok(!-d $xap, 'Xapian directories removed again');
 {
@@ -199,8 +204,8 @@ ok(!-d $xap, 'Xapian directories removed again');
 	ok(-d $xap, 'Xapian directories recreated');
 	delete $ibx->{mm};
 	is_deeply([ $ibx->mm->minmax ], $minmax, 'minmax unchanged');
-	my $mset = $ibx->search->reopen->query('hello world', {mset=>1});
-	is($mset->size, 0, "no Xapian search results");
+	is($ibx->mm->num_highwater, 10, 'num_highwater as expected');
+	isnt($ibx->search, 'no search for basic');
 
 	my ($min, $max) = $ibx->mm->minmax;
 	is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
@@ -214,21 +219,23 @@ ok(!-d $xap, 'Xapian directories removed again');
 	my @warn;
 	local $SIG{__WARN__} = sub { push @warn, @_ };
 	my %config = %$ibx_config;
-	$config{indexleve} = 'medium';
+	$config{indexlevel} = 'medium';
 	my $ibx = PublicInbox::Inbox->new(\%config);
 	my $rw = PublicInbox::SearchIdx->new($ibx, 1);
-	eval { $rw->index_sync };
+	eval { $rw->index_sync({reindex => 1}) };
 	is($@, '', 'no error from indexing');
 	is_deeply(\@warn, [], 'no warnings');
-	my $mset = $ibx->search->reopen->query('hello world', {mset=>1});
+	my $mset = $ibx->search->reopen->mset('hello world');
 	isnt($mset->size, 0, 'search OK after basic -> medium');
 
+	is($ibx->mm->num_highwater, 10, 'num_highwater as expected');
+
 	my ($min, $max) = $ibx->mm->minmax;
 	is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
 }
 
 # An incremental indexing test
-ok(unlink "$mainrepo/public-inbox/msgmap.sqlite3", 'remove msgmap');
+ok(unlink "$inboxdir/public-inbox/msgmap.sqlite3", 'remove msgmap');
 remove_tree($xap);
 ok(!-d $xap, 'Xapian directories removed again');
 {
@@ -246,6 +253,7 @@ ok(!-d $xap, 'Xapian directories removed again');
 	my ($min, $max) = $ibx->mm->minmax;
 	is($min, 1, 'min as expected');
 	is($max, 4, 'max as expected');
+	is($ibx->mm->num_highwater, 4, 'num_highwater as expected');
 	is_deeply($ibx->mm->msg_range(\$min, $max),
 		  [
 		   [1, '1@example.com' ],
@@ -269,6 +277,7 @@ ok(!-d $xap, 'Xapian directories removed again');
 	my ($min, $max) = $ibx->mm->minmax;
 	is($min, 1, 'min as expected');
 	is($max, 3, 'max as expected');
+	is($ibx->mm->num_highwater, 4, 'num_highwater as expected');
 	is_deeply($ibx->mm->msg_range(\$min, $max),
 		  [
 		   [1, '1@example.com' ],
@@ -291,6 +300,7 @@ ok(!-d $xap, 'Xapian directories removed again');
 	my ($min, $max) = $ibx->mm->minmax;
 	is($min, 1, 'min as expected');
 	is($max, 10, 'max as expected');
+	is($ibx->mm->num_highwater, 10, 'num_highwater as expected');
 	is_deeply($ibx->mm->msg_range(\$min, $max),
 		  [
 		   [1, '1@example.com' ],
@@ -319,6 +329,7 @@ ok(!-d $xap, 'Xapian directories removed again');
 	my ($min, $max) = $ibx->mm->minmax;
 	is($min, 1, 'min as expected');
 	is($max, 10, 'max as expected');
+	is($ibx->mm->num_highwater, 10, 'num_highwater as expected');
 	is_deeply($ibx->mm->msg_range(\$min, $max),
 		  [
 		   [1, '1@example.com' ],
@@ -334,7 +345,7 @@ ok(!-d $xap, 'Xapian directories removed again');
 
 
 # Another incremental indexing test
-ok(unlink "$mainrepo/public-inbox/msgmap.sqlite3", 'remove msgmap');
+ok(unlink "$inboxdir/public-inbox/msgmap.sqlite3", 'remove msgmap');
 remove_tree($xap);
 ok(!-d $xap, 'Xapian directories removed again');
 {
@@ -352,6 +363,7 @@ ok(!-d $xap, 'Xapian directories removed again');
 	my ($min, $max) = $ibx->mm->minmax;
 	is($min, 1, 'min as expected');
 	is($max, 3, 'max as expected');
+	is($ibx->mm->num_highwater, 4, 'num_highwater as expected');
 	is_deeply($ibx->mm->msg_range(\$min, $max),
 		  [
 		   [1, '1@example.com' ],
@@ -374,6 +386,7 @@ ok(!-d $xap, 'Xapian directories removed again');
 	my ($min, $max) = $ibx->mm->minmax;
 	is($min, 1, 'min as expected');
 	is($max, 10, 'max as expected');
+	is($ibx->mm->num_highwater, 10, 'num_highwater as expected');
 	is_deeply($ibx->mm->msg_range(\$min, $max),
 		  [
 		   [1, '1@example.com' ],
@@ -402,6 +415,7 @@ ok(!-d $xap, 'Xapian directories removed again');
 	my ($min, $max) = $ibx->mm->minmax;
 	is($min, 1, 'min as expected');
 	is($max, 10, 'max as expected');
+	is($ibx->mm->num_highwater, 10, 'num_highwater as expected');
 	is_deeply($ibx->mm->msg_range(\$min, $max),
 		  [
 		   [1, '1@example.com' ],
@@ -415,5 +429,38 @@ ok(!-d $xap, 'Xapian directories removed again');
 		  ], 'msgmap as expected' );
 }
 
+{
+	my @warn;
+	local $SIG{__WARN__} = sub { push @warn, @_ };
+	my $ibx = PublicInbox::Inbox->new({ %$ibx_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);
+
+	my $rw = PublicInbox::SearchIdx->new($ibx, 1);
+	my @pr;
+	my $pr = sub { push @pr, @_ };
+	$rw->index_sync({reindex => 1, rethread => 1, -progress => $pr });
+	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');
+	is_deeply([], \@warn, 'no warnings');
+	# diag "@pr"; # XXX do we care?
+}
 
 done_testing();