X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=t%2Fv2reindex.t;h=52711f8fd15d34756acbe0ec9c937e057b98affb;hb=f9fc5cf2e8cefda4a56d937ed217e47689fd7e49;hp=2dda80e8c5e5adcf1c2e23a346e53c32165d378c;hpb=0c9092f7075c5bed202b5a71df38765d32da1cf7;p=public-inbox.git
diff --git a/t/v2reindex.t b/t/v2reindex.t
index 2dda80e8..52711f8f 100644
--- a/t/v2reindex.t
+++ b/t/v2reindex.t
@@ -1,4 +1,4 @@
-# Copyright (C) 2018 all contributors
+# Copyright (C) 2018-2019 all contributors
# License: AGPL-3.0+
use strict;
use warnings;
@@ -7,15 +7,17 @@ use PublicInbox::MIME;
use PublicInbox::ContentId qw(content_digest);
use File::Temp qw/tempdir/;
use File::Path qw(remove_tree);
+require './t/common.perl';
+require_git(2.6);
foreach my $mod (qw(DBD::SQLite Search::Xapian)) {
eval "require $mod";
plan skip_all => "$mod missing for v2reindex.t" if $@;
}
use_ok 'PublicInbox::V2Writable';
-my $mainrepo = tempdir('pi-v2reindex-XXXXXX', TMPDIR => 1, CLEANUP => 1);
+my $inboxdir = tempdir('pi-v2reindex-XXXXXX', TMPDIR => 1, CLEANUP => 1);
my $ibx_config = {
- mainrepo => $mainrepo,
+ inboxdir => $inboxdir,
name => 'test-v2writable',
version => 2,
-primary_address => 'test@example.com',
@@ -37,14 +39,13 @@ my $mime = PublicInbox::MIME->create(
],
body => $agpl,
);
-local $ENV{NPROC} = 2;
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, 1);
+ my $im = PublicInbox::V2Writable->new($ibx, {nproc => 1});
my $im0 = $im->importer();
foreach my $i (1..10) {
$mime->header_set('Message-Id', "<$i\@example.com>");
@@ -99,7 +100,7 @@ my ($mark1, $mark2, $mark3, $mark4);
is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
}
-my $xap = "$mainrepo/xap".PublicInbox::Search::SCHEMA_VERSION();
+my $xap = "$inboxdir/xap".PublicInbox::Search::SCHEMA_VERSION();
remove_tree($xap);
ok(!-d $xap, 'Xapian directories removed');
{
@@ -119,7 +120,7 @@ ok(!-d $xap, 'Xapian directories removed');
is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
}
-ok(unlink "$mainrepo/msgmap.sqlite3", 'remove msgmap');
+ok(unlink "$inboxdir/msgmap.sqlite3", 'remove msgmap');
remove_tree($xap);
ok(!-d $xap, 'Xapian directories removed again');
{
@@ -142,7 +143,7 @@ ok(!-d $xap, 'Xapian directories removed again');
}
my %sizes;
-ok(unlink "$mainrepo/msgmap.sqlite3", 'remove msgmap');
+ok(unlink "$inboxdir/msgmap.sqlite3", 'remove msgmap');
remove_tree($xap);
ok(!-d $xap, 'Xapian directories removed again');
{
@@ -167,7 +168,7 @@ ok(!-d $xap, 'Xapian directories removed again');
is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
}
-ok(unlink "$mainrepo/msgmap.sqlite3", 'remove msgmap');
+ok(unlink "$inboxdir/msgmap.sqlite3", 'remove msgmap');
remove_tree($xap);
ok(!-d $xap, 'Xapian directories removed again');
{
@@ -206,7 +207,7 @@ ok(!-d $xap, 'Xapian directories removed again');
is_deeply($ibx->mm->msg_range(\$min, $max), $msgmap, 'msgmap unchanged');
}
-ok(unlink "$mainrepo/msgmap.sqlite3", 'remove msgmap');
+ok(unlink "$inboxdir/msgmap.sqlite3", 'remove msgmap');
remove_tree($xap);
ok(!-d $xap, 'Xapian directories removed again');
{
@@ -224,8 +225,9 @@ 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 = $ibx->search->query('freedom', {mset=>1});
- is($mset->size, 0, "search fails on indexlevel='basic'");
+
+ isnt($ibx->search, 'no search for basic');
+
for (<"$xap/*/*">) { $sizes{$ibx->{indexlevel}} += -s _ if -f $_ }
ok($sizes{medium} > $sizes{basic}, 'basic is smaller than medium');
@@ -235,7 +237,7 @@ ok(!-d $xap, 'Xapian directories removed again');
# An incremental indexing test
-ok(unlink "$mainrepo/msgmap.sqlite3", 'remove msgmap');
+ok(unlink "$inboxdir/msgmap.sqlite3", 'remove msgmap');
remove_tree($xap);
ok(!-d $xap, 'Xapian directories removed again');
{
@@ -345,7 +347,7 @@ ok(!-d $xap, 'Xapian directories removed again');
# Another incremental indexing test
-ok(unlink "$mainrepo/msgmap.sqlite3", 'remove msgmap');
+ok(unlink "$inboxdir/msgmap.sqlite3", 'remove msgmap');
remove_tree($xap);
ok(!-d $xap, 'Xapian directories removed again');
{
@@ -429,4 +431,70 @@ ok(!-d $xap, 'Xapian directories removed again');
], 'msgmap as expected' );
}
+# 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
+# of the Message-IDs in the 3-headed monster.
+{
+ my @warn;
+ local $SIG{__WARN__} = sub { push @warn, @_ };
+ my %config = %$ibx_config;
+ $config{indexlevel} = 'basic';
+ my $ibx = PublicInbox::Inbox->new(\%config);
+ my $im = PublicInbox::V2Writable->new($ibx);
+ my $m3 = PublicInbox::MIME->new(<<'EOF');
+Date: Tue, 24 May 2016 14:34:22 -0700 (PDT)
+Message-Id: <20160524.143422.552507610109476444.d@example.com>
+To: t@example.com
+Cc: c@example.com
+Subject: Re: [PATCH v2 2/2]
+From:
+In-Reply-To: <1463825855-7363-2-git-send-email-y@example.com>
+References: <1463825855-7363-1-git-send-email-y@example.com>
+ <1463825855-7363-2-git-send-email-y@example.com>
+Date: Wed, 25 May 2016 10:01:51 +0900
+From: h@example.com
+To: g@example.com
+Cc: m@example.com
+Subject: Re: [PATCH]
+Message-ID: <20160525010150.GD7292@example.com>
+References: <1463498133-23918-1-git-send-email-g+r@example.com>
+In-Reply-To: <1463498133-23918-1-git-send-email-g+r@example.com>
+From: s@example.com
+To: h@example.com
+Cc: m@example.com
+Subject: [PATCH 12/13]
+Date: Wed, 01 Jun 2016 01:32:35 +0300
+Message-ID: <1923946.Jvi0TDUXFC@wasted.example.com>
+In-Reply-To: <13205049.n7pM8utpHF@wasted.example.com>
+References: <13205049.n7pM8utpHF@wasted.example.com>
+
+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');
+From: a@example.com
+To: t@example.com
+Subject: [PATCH 12/13]
+Date: Wed, 01 Jun 2016 01:32:35 +0300
+Message-ID: <1923946.Jvi0TDUXFC@wasted.example.com>
+In-Reply-To: <13205049.n7pM8utpHF@wasted.example.com>
+References: <13205049.n7pM8utpHF@wasted.example.com>
+
+This is probably one of the original messages
+
+EOF
+ $im->add($m1);
+ $im->add($m3);
+ $im->done;
+ remove_tree($xap);
+ eval { $im->index_sync() };
+ is($@, '', 'no error from initial indexing');
+ is_deeply(\@warn, [], 'no warnings from initial index');
+ eval { $im->index_sync({reindex=>1}) };
+ is($@, '', 'no error from reindexing after reused Message-ID (x3)');
+ is_deeply(\@warn, [], 'no warnings on reindex');
+}
+
done_testing();