X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=t%2Fv2reindex.t;h=7bf6bc2f935f7f3ce9923d4a7b249b62dc5cb640;hb=62d1a4da996bd9a664be954f71f78fe052f9df16;hp=3d217aff3c72067f8d57f3c87d7a569efd0a82b1;hpb=1597d1a5fff6c1090cc65f439d1773cb3e98d382;p=public-inbox.git diff --git a/t/v2reindex.t b/t/v2reindex.t index 3d217aff..7bf6bc2f 100644 --- a/t/v2reindex.t +++ b/t/v2reindex.t @@ -1,43 +1,45 @@ -# Copyright (C) 2018 all contributors +# Copyright (C) 2018-2020 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 File::Path qw(remove_tree); - -foreach my $mod (qw(DBD::SQLite Search::Xapian)) { - eval "require $mod"; - plan skip_all => "$mod missing for v2reindex.t" if $@; -} +use PublicInbox::TestCommon; +require_git(2.6); +require_mods(qw(DBD::SQLite Search::Xapian Email::MIME)); use_ok 'PublicInbox::V2Writable'; -my $mainrepo = tempdir('pi-v2reindex-XXXXXX', TMPDIR => 1, CLEANUP => 1); +my ($inboxdir, $for_destroy) = tmpdir(); my $ibx_config = { - mainrepo => $mainrepo, + inboxdir => $inboxdir, name => 'test-v2writable', version => 2, -primary_address => 'test@example.com', indexlevel => 'full', }; -my $mime = PublicInbox::MIME->create( +my $agpl = do { + open my $fh, '<', 'COPYING' or die "can't open COPYING: $!"; + local $/; + <$fh>; +}; +my $phrase = q("defending all users' freedom"); +my $mime = Email::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", + 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>"); @@ -60,6 +62,7 @@ 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, $max); @@ -85,12 +88,13 @@ my ($mark1, $mark2, $mark3, $mark4); 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'); } -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'); { @@ -104,12 +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/msgmap.sqlite3", 'remove msgmap'); +ok(unlink "$inboxdir/msgmap.sqlite3", 'remove msgmap'); remove_tree($xap); ok(!-d $xap, 'Xapian directories removed again'); { @@ -125,13 +130,14 @@ 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), $msgmap, 'msgmap unchanged'); } my %sizes; -ok(unlink "$mainrepo/msgmap.sqlite3", 'remove msgmap'); +ok(unlink "$inboxdir/msgmap.sqlite3", 'remove msgmap'); remove_tree($xap); ok(!-d $xap, 'Xapian directories removed again'); { @@ -147,15 +153,16 @@ 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 = $ibx->search->query($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), $msgmap, 'msgmap unchanged'); } -ok(unlink "$mainrepo/msgmap.sqlite3", 'remove msgmap'); +ok(unlink "$inboxdir/msgmap.sqlite3", 'remove msgmap'); remove_tree($xap); ok(!-d $xap, 'Xapian directories removed again'); { @@ -172,18 +179,21 @@ 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'); if (0) { # not sure why, but Xapian seems to fallback to terms and # phrase searches still work delete $ibx->{search}; - my $mset = $ibx->search->query('"hello world"', {mset=>1}); + my $mset = $ibx->search->query($phrase, {mset=>1}); is($mset->size, 0, 'phrase search does not work on medium'); } - - my $mset = $ibx->search->query('hello world', {mset=>1}); + my $words = $phrase; + $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'); @@ -191,7 +201,7 @@ 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'); { @@ -208,9 +218,11 @@ 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 = $ibx->search->query('hello', {mset=>1}); - is($mset->size, 0, "search fails on indexlevel='basic'"); - for (<"$xap/*/*">) { $sizes{$ibx->{indexlevel}} += -s _ if -f $_ } + is($ibx->mm->num_highwater, 10, 'num_highwater as expected'); + + isnt($ibx->search, 'no search for basic'); + + for (glob("$xap/*/*")) { $sizes{$ibx->{indexlevel}} += -s _ if -f $_ } ok($sizes{medium} > $sizes{basic}, 'basic is smaller than medium'); my ($min, $max) = $ibx->mm->minmax; @@ -219,7 +231,7 @@ 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'); { @@ -329,7 +341,7 @@ 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'); { @@ -413,4 +425,78 @@ 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} = 'medium'; + 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] uno +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] dos +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] tres +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'); + + my %uniq; + for my $s (qw(uno dos tres)) { + my $msgs = $ibx->search->query("s:$s"); + is(scalar(@$msgs), 1, "only one result for `$s'"); + $uniq{$msgs->[0]->{num}}++; + } + is_deeply([values %uniq], [3], 'search on different subjects'); +} + done_testing();