-# Copyright (C) 2018-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2020 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::Eml;
+use PublicInbox::ContentHash qw(content_digest);
use File::Path qw(remove_tree);
-require './t/common.perl';
+use PublicInbox::TestCommon;
require_git(2.6);
-
-foreach my $mod (qw(DBD::SQLite Search::Xapian)) {
- eval "require $mod";
- plan skip_all => "$mod missing for v2reindex.t" if $@;
-}
+require_mods(qw(DBD::SQLite Search::Xapian));
use_ok 'PublicInbox::V2Writable';
-my $inboxdir = tempdir('pi-v2reindex-XXXXXX', TMPDIR => 1, CLEANUP => 1);
+use_ok 'PublicInbox::OverIdx';
+my ($inboxdir, $for_destroy) = tmpdir();
my $ibx_config = {
inboxdir => $inboxdir,
name => 'test-v2writable',
-primary_address => 'test@example.com',
indexlevel => 'full',
};
-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, $mark4);
my %config = %$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 $i added");
is($ibx->mm->num_highwater, 10, 'num_highwater as expected');
my $mset = $ibx->search->query($phrase, {mset=>1});
isnt($mset->size, 0, "phrase search succeeds on indexlevel=full");
- for (<"$xap/*/*">) { $sizes{$ibx->{indexlevel}} += -s _ if -f $_ }
+ for (glob("$xap/*/*")) { $sizes{$ibx->{indexlevel}} += -s _ if -f $_ }
my ($min, $max) = $ibx->mm->minmax;
is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
$words =~ tr/"'//d;
my $mset = $ibx->search->query($words, {mset=>1});
isnt($mset->size, 0, "normal search works on indexlevel=medium");
- for (<"$xap/*/*">) { $sizes{$ibx->{indexlevel}} += -s _ if -f $_ }
+ for (glob("$xap/*/*")) { $sizes{$ibx->{indexlevel}} += -s _ if -f $_ }
ok($sizes{full} > $sizes{medium}, 'medium is smaller than full');
isnt($ibx->search, 'no search for basic');
- for (<"$xap/*/*">) { $sizes{$ibx->{indexlevel}} += -s _ if -f $_ }
+ for (glob("$xap/*/*")) { $sizes{$ibx->{indexlevel}} += -s _ if -f $_ }
ok($sizes{medium} > $sizes{basic}, 'basic is smaller than medium');
my ($min, $max) = $ibx->mm->minmax;
], '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->connect;
+ 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
$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
message, could've been something broken on the archiver side.
EOF
- my $m1 = PublicInbox::MIME->new(<<'EOF');
+ my $m1 = PublicInbox::Eml->new(<<'EOF');
From: a@example.com
To: t@example.com
Subject: [PATCH 12/13]
is_deeply([values %uniq], [3], 'search on different subjects');
}
+# XXX: not deterministic when dealing with ambiguous messages, oh well
+$check_rethread->('3-headed-monster once');
+$check_rethread->('3-headed-monster twice');
+
done_testing();