X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=t%2Fv2reindex.t;h=cafe8648d1e8b0dd1275f6af884585402e5aee70;hb=4452b5ebd8f202d72260325768512230c93ef6f2;hp=7c14117af0514bb1cccff3c3515d17990c776d0f;hpb=95bdac7f09c69036efed537a4d03d5bdd2ae4eb6;p=public-inbox.git
diff --git a/t/v2reindex.t b/t/v2reindex.t
index 7c14117a..cafe8648 100644
--- a/t/v2reindex.t
+++ b/t/v2reindex.t
@@ -1,15 +1,13 @@
-# Copyright (C) 2018-2020 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 strict; use v5.10.1; use PublicInbox::TestCommon;
+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,
@@ -17,23 +15,21 @@ my $ibx_config = {
version => 2,
-primary_address => 'test@example.com',
indexlevel => 'full',
+ -no_fsync => 1,
};
-my $agpl = eval {
+my $agpl = do {
open my $fh, '<', 'COPYING' or die "can't open COPYING: $!";
local $/;
<$fh>;
};
-$agpl or die "AGPL or die :P\n";
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, $mark4);
@@ -41,7 +37,7 @@ my ($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");
@@ -155,7 +151,7 @@ ok(!-d $xap, 'Xapian directories removed again');
delete $ibx->{mm};
is_deeply([ $ibx->mm->minmax ], $minmax, 'minmax unchanged');
is($ibx->mm->num_highwater, 10, 'num_highwater as expected');
- my $mset = $ibx->search->query($phrase, {mset=>1});
+ my $mset = $ibx->search->mset($phrase);
isnt($mset->size, 0, "phrase search succeeds on indexlevel=full");
for (glob("$xap/*/*")) { $sizes{$ibx->{indexlevel}} += -s _ if -f $_ }
@@ -186,12 +182,12 @@ ok(!-d $xap, 'Xapian directories removed again');
# not sure why, but Xapian seems to fallback to terms and
# phrase searches still work
delete $ibx->{search};
- my $mset = $ibx->search->query($phrase, {mset=>1});
+ my $mset = $ibx->search->mset($phrase);
is($mset->size, 0, 'phrase search does not work on medium');
}
my $words = $phrase;
$words =~ tr/"'//d;
- my $mset = $ibx->search->query($words, {mset=>1});
+ my $mset = $ibx->search->mset($words);
isnt($mset->size, 0, "normal search works on indexlevel=medium");
for (glob("$xap/*/*")) { $sizes{$ibx->{indexlevel}} += -s _ if -f $_ }
@@ -426,6 +422,46 @@ 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 = $dbh->selectrow_array(<();
+ ok($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
@@ -437,7 +473,7 @@ 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
@@ -468,7 +504,7 @@ 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]
@@ -493,11 +529,29 @@ EOF
my %uniq;
for my $s (qw(uno dos tres)) {
- my $msgs = $ibx->search->query("s:$s");
+ my $mset = $ibx->search->mset("s:$s");
+ my $msgs = $ibx->search->mset_to_smsg($ibx, $mset);
is(scalar(@$msgs), 1, "only one result for `$s'");
$uniq{$msgs->[0]->{num}}++;
}
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');
+
+my $rdr = { 2 => \(my $err = '') };
+my $env = { PI_CONFIG => '/dev/null' };
+ok(run_script([qw(-index --reindex --xapian-only), $inboxdir], $env, $rdr),
+ '--xapian-only works');
+is($err, '', 'no errors from --xapian-only');
+undef $for_destroy;
+SKIP: {
+ skip 'only testing lsof(8) output on Linux', 1 if $^O ne 'linux';
+ my $lsof = require_cmd('lsof', 1) or skip 'no lsof in PATH', 1;
+ my $rdr = { 2 => \(my $null_err) };
+ my @d = grep(m!/xap[0-9]+/!, xqx([$lsof, '-p', $$], undef, $rdr));
+ is_deeply(\@d, [], 'no deleted index files') or diag explain(\@d);
+}
done_testing();