X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=t%2Fv1reindex.t;h=f593b3239586e0a013f155451dc9e67138c9b874;hb=ee8746e6db4dbe5a6cdb0d6080f467bc27693b3a;hp=0df36d3fee893f6d2d38eee6c56e013c004b3ad8;hpb=6aa50771d12af52baad214923afd49417f6d8909;p=public-inbox.git
diff --git a/t/v1reindex.t b/t/v1reindex.t
index 0df36d3f..f593b323 100644
--- a/t/v1reindex.t
+++ b/t/v1reindex.t
@@ -1,85 +1,129 @@
-# Copyright (C) 2018 all contributors
+# Copyright (C) 2018-2021 all contributors
# License: AGPL-3.0+
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 $ibx = PublicInbox::Inbox->new($ibx_config);
-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 $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
-foreach my $i (1..10) {
- $mime->header_set('Message-Id', "<$i\@example.com>");
- ok($im->add($mime), "message $i added");
- if ($i == 4) {
+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, $mark4);
+{
+ my %config = %$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 $i added");
+ if ($i == 4) {
+ $mark1 = $im->get_mark($im->{tip});
+ $im->remove($mime);
+ $mark2 = $im->get_mark($im->{tip});
+ }
+ }
+
+ if ('test remove later') {
+ $mark3 = $im->get_mark($im->{tip});
+ $mime->header_set('Message-Id', "<5\@example.com>");
$im->remove($mime);
+ $mark4 = $im->get_mark($im->{tip});
}
-}
-if ('test remove later') {
- $mime->header_set('Message-Id', "<5\@example.com>");
- $im->remove($mime);
+ $im->done;
+ my $rw = PublicInbox::SearchIdx->new($ibx, 1);
+ eval { $rw->index_sync() };
+ is($@, '', 'no error from indexing');
+
+ $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, $max);
+ is_deeply($msgmap, [
+ [1, '1@example.com' ],
+ [2, '2@example.com' ],
+ [3, '3@example.com' ],
+ [6, '6@example.com' ],
+ [7, '7@example.com' ],
+ [8, '8@example.com' ],
+ [9, '9@example.com' ],
+ [10, '10@example.com' ],
+ ], 'msgmap as expected');
}
-$im->done;
-my $rw = PublicInbox::SearchIdx->new($ibx, 1);
-eval { $rw->index_sync() };
-is($@, '', 'no error from indexing');
+{
+ my %config = %$ibx_config;
+ my $ibx = PublicInbox::Inbox->new(\%config);
+ my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
+ my $rw = PublicInbox::SearchIdx->new($ibx, 1);
+ eval { $rw->index_sync({reindex => 1}) };
+ is($@, '', 'no error from reindexing');
+ $im->done;
-my $minmax = [ $ibx->mm->minmax ];
-ok(defined $minmax->[0] && defined $minmax->[1], 'minmax defined');
-is_deeply($minmax, [ 1, 10 ], 'minmax as expected');
+ is($ibx->mm->num_highwater, 10, 'num_highwater as expected');
-$rw = PublicInbox::SearchIdx->new($ibx, 1);
-eval { $rw->index_sync({reindex => 1}) };
-is($@, '', 'no error from reindexing');
-$im->done;
+ my ($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 $xap, 'Xapian directories removed');
-$rw = PublicInbox::SearchIdx->new($ibx, 1);
+{
+ my %config = %$ibx_config;
+ my $ibx = PublicInbox::Inbox->new(\%config);
+ my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
+ my $rw = PublicInbox::SearchIdx->new($ibx, 1);
+
+ eval { $rw->index_sync({reindex => 1}) };
+ is($@, '', 'no error from reindexing');
+ $im->done;
+ ok(-d $xap, 'Xapian directories recreated');
-eval { $rw->index_sync({reindex => 1}) };
-is($@, '', 'no error from reindexing');
-$im->done;
-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');
-delete $ibx->{mm};
-is_deeply([ $ibx->mm->minmax ], $minmax, 'minmax unchanged');
+ my ($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);
-$rw = PublicInbox::SearchIdx->new($ibx, 1);
-
ok(!-d $xap, 'Xapian directories removed again');
{
my @warn;
local $SIG{__WARN__} = sub { push @warn, @_ };
+ my %config = %$ibx_config;
+ my $ibx = PublicInbox::Inbox->new(\%config);
+ my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
+ my $rw = PublicInbox::SearchIdx->new($ibx, 1);
eval { $rw->index_sync({reindex => 1}) };
is($@, '', 'no error from reindexing without msgmap');
is(scalar(@warn), 0, 'no warnings from reindexing');
@@ -87,16 +131,72 @@ 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), $msgmap, 'msgmap unchanged');
+}
+
+ok(unlink "$inboxdir/public-inbox/msgmap.sqlite3", 'remove msgmap');
+remove_tree($xap);
+ok(!-d $xap, 'Xapian directories removed again');
+{
+ my @warn;
+ local $SIG{__WARN__} = sub { push @warn, @_ };
+ my %config = %$ibx_config;
+ my $ibx = PublicInbox::Inbox->new(\%config);
+ my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
+ my $rw = PublicInbox::SearchIdx->new($ibx, 1);
+ eval { $rw->index_sync({reindex => 1}) };
+ is($@, '', 'no error from reindexing without msgmap');
+ is_deeply(\@warn, [], 'no warnings');
+ $im->done;
+ 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);
-$rw = PublicInbox::SearchIdx->new($ibx, 1);
+ok(!-d $xap, 'Xapian directories removed again');
+{
+ my @warn;
+ local $SIG{__WARN__} = sub { push @warn, @_ };
+ my %config = %$ibx_config;
+ $config{indexlevel} = 'medium';
+ my $ibx = PublicInbox::Inbox->new(\%config);
+ my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
+ my $rw = PublicInbox::SearchIdx->new($ibx, 1);
+ eval { $rw->index_sync({reindex => 1}) };
+ is($@, '', 'no error from reindexing without msgmap');
+ is_deeply(\@warn, [], 'no warnings');
+ $im->done;
+ 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 $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), $msgmap, 'msgmap unchanged');
+}
+ok(unlink "$inboxdir/public-inbox/msgmap.sqlite3", 'remove msgmap');
+remove_tree($xap);
ok(!-d $xap, 'Xapian directories removed again');
{
my @warn;
local $SIG{__WARN__} = sub { push @warn, @_ };
+ my %config = %$ibx_config;
+ $config{indexlevel} = 'basic';
+ my $ibx = PublicInbox::Inbox->new(\%config);
+ my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
+ my $rw = PublicInbox::SearchIdx->new($ibx, 1);
eval { $rw->index_sync({reindex => 1}) };
is($@, '', 'no error from reindexing without msgmap');
is_deeply(\@warn, [], 'no warnings');
@@ -104,6 +204,263 @@ 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');
+ isnt($ibx->search, 'no search for basic');
+
+ my ($min, $max) = $ibx->mm->minmax;
+ is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
+}
+
+# upgrade existing basic to medium
+# note: changing indexlevels is not yet supported in v2,
+# and may not be without more effort
+# no removals
+{
+ my @warn;
+ local $SIG{__WARN__} = sub { push @warn, @_ };
+ my %config = %$ibx_config;
+ $config{indexlevel} = 'medium';
+ my $ibx = PublicInbox::Inbox->new(\%config);
+ my $rw = PublicInbox::SearchIdx->new($ibx, 1);
+ eval { $rw->index_sync({reindex => 1}) };
+ is($@, '', 'no error from indexing');
+ is_deeply(\@warn, [], 'no warnings');
+ 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), $msgmap, 'msgmap unchanged');
+}
+
+# An incremental indexing test
+ok(unlink "$inboxdir/public-inbox/msgmap.sqlite3", 'remove msgmap');
+remove_tree($xap);
+ok(!-d $xap, 'Xapian directories removed again');
+{
+ my @warn;
+ local $SIG{__WARN__} = sub { push @warn, @_ };
+ my %config = %$ibx_config;
+ my $ibx = PublicInbox::Inbox->new(\%config);
+ my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
+ my $rw = PublicInbox::SearchIdx->new($ibx, 1);
+ # mark1 4 simple additions in the same index_sync
+ eval { $rw->index_sync({ref => $mark1}) };
+ is($@, '', 'no error from reindexing without msgmap');
+ is_deeply(\@warn, [], 'no warnings');
+ $im->done;
+ my ($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' ],
+ [2, '2@example.com' ],
+ [3, '3@example.com' ],
+ [4, '4@example.com' ],
+ ], 'msgmap as expected' );
+}
+{
+ my @warn;
+ local $SIG{__WARN__} = sub { push @warn, @_ };
+ my %config = %$ibx_config;
+ my $ibx = PublicInbox::Inbox->new(\%config);
+ my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
+ my $rw = PublicInbox::SearchIdx->new($ibx, 1);
+ # mark2 A delete separated form and add in the same index_sync
+ eval { $rw->index_sync({ref => $mark2}) };
+ is($@, '', 'no error from reindexing without msgmap');
+ is_deeply(\@warn, [], 'no warnings');
+ $im->done;
+ my ($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' ],
+ [2, '2@example.com' ],
+ [3, '3@example.com' ],
+ ], 'msgmap as expected' );
+}
+{
+ my @warn;
+ local $SIG{__WARN__} = sub { push @warn, @_ };
+ my %config = %$ibx_config;
+ my $ibx = PublicInbox::Inbox->new(\%config);
+ my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
+ my $rw = PublicInbox::SearchIdx->new($ibx, 1);
+ # mark3 adds following the delete at mark2
+ eval { $rw->index_sync({ref => $mark3}) };
+ is($@, '', 'no error from reindexing without msgmap');
+ is_deeply(\@warn, [], 'no warnings');
+ $im->done;
+ my ($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' ],
+ [2, '2@example.com' ],
+ [3, '3@example.com' ],
+ [5, '5@example.com' ],
+ [6, '6@example.com' ],
+ [7, '7@example.com' ],
+ [8, '8@example.com' ],
+ [9, '9@example.com' ],
+ [10, '10@example.com' ],
+ ], 'msgmap as expected' );
+}
+{
+ my @warn;
+ local $SIG{__WARN__} = sub { push @warn, @_ };
+ my %config = %$ibx_config;
+ my $ibx = PublicInbox::Inbox->new(\%config);
+ my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
+ my $rw = PublicInbox::SearchIdx->new($ibx, 1);
+ # mark4 A delete of an older message
+ eval { $rw->index_sync({ref => $mark4}) };
+ is($@, '', 'no error from reindexing without msgmap');
+ is_deeply(\@warn, [], 'no warnings');
+ $im->done;
+ my ($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, $max),
+ [
+ [1, '1@example.com' ],
+ [2, '2@example.com' ],
+ [3, '3@example.com' ],
+ [6, '6@example.com' ],
+ [7, '7@example.com' ],
+ [8, '8@example.com' ],
+ [9, '9@example.com' ],
+ [10, '10@example.com' ],
+ ], 'msgmap as expected' );
+}
+
+
+# Another incremental indexing test
+ok(unlink "$inboxdir/public-inbox/msgmap.sqlite3", 'remove msgmap');
+remove_tree($xap);
+ok(!-d $xap, 'Xapian directories removed again');
+{
+ my @warn;
+ local $SIG{__WARN__} = sub { push @warn, @_ };
+ my %config = %$ibx_config;
+ my $ibx = PublicInbox::Inbox->new(\%config);
+ my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
+ my $rw = PublicInbox::SearchIdx->new($ibx, 1);
+ # mark2 an add and it's delete in the same index_sync
+ eval { $rw->index_sync({ref => $mark2}) };
+ is($@, '', 'no error from reindexing without msgmap');
+ is_deeply(\@warn, [], 'no warnings');
+ $im->done;
+ my ($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' ],
+ [2, '2@example.com' ],
+ [3, '3@example.com' ],
+ ], 'msgmap as expected' );
+}
+{
+ my @warn;
+ local $SIG{__WARN__} = sub { push @warn, @_ };
+ my %config = %$ibx_config;
+ my $ibx = PublicInbox::Inbox->new(\%config);
+ my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
+ my $rw = PublicInbox::SearchIdx->new($ibx, 1);
+ # mark3 adds following the delete at mark2
+ eval { $rw->index_sync({ref => $mark3}) };
+ is($@, '', 'no error from reindexing without msgmap');
+ is_deeply(\@warn, [], 'no warnings');
+ $im->done;
+ my ($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' ],
+ [2, '2@example.com' ],
+ [3, '3@example.com' ],
+ [5, '5@example.com' ],
+ [6, '6@example.com' ],
+ [7, '7@example.com' ],
+ [8, '8@example.com' ],
+ [9, '9@example.com' ],
+ [10, '10@example.com' ],
+ ], 'msgmap as expected' );
+}
+{
+ my @warn;
+ local $SIG{__WARN__} = sub { push @warn, @_ };
+ my %config = %$ibx_config;
+ my $ibx = PublicInbox::Inbox->new(\%config);
+ my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
+ my $rw = PublicInbox::SearchIdx->new($ibx, 1);
+ # mark4 A delete of an older message
+ eval { $rw->index_sync({ref => $mark4}) };
+ is($@, '', 'no error from reindexing without msgmap');
+ is_deeply(\@warn, [], 'no warnings');
+ $im->done;
+ my ($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' ],
+ [2, '2@example.com' ],
+ [3, '3@example.com' ],
+ [6, '6@example.com' ],
+ [7, '7@example.com' ],
+ [8, '8@example.com' ],
+ [9, '9@example.com' ],
+ [10, '10@example.com' ],
+ ], '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 = $dbh->selectrow_array(<();
+ ok($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();