X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=t%2Fsearch.t;h=f026e5093c9176d00f7bd39487d919caff6baa27;hb=d73d783ab2cf14ba28ca63723223d8c85a68cdd5;hp=40264345985477bc0609381d5dbdd4c606c317ac;hpb=e39585ee2bdcbeaab7b6bd33b3568021042d0879;p=public-inbox.git diff --git a/t/search.t b/t/search.t index 40264345..f026e509 100644 --- a/t/search.t +++ b/t/search.t @@ -8,7 +8,7 @@ require_mods(qw(DBD::SQLite Search::Xapian)); require PublicInbox::SearchIdx; require PublicInbox::Inbox; require PublicInbox::InboxWritable; -use PublicInbox::MIME; +use PublicInbox::Eml; my ($tmpdir, $for_destroy) = tmpdir(); my $git_dir = "$tmpdir/a.git"; my $ibx = PublicInbox::Inbox->new({ inboxdir => $git_dir }); @@ -21,8 +21,8 @@ ok($@, "exception raised on non-existent DB"); my $rw = PublicInbox::SearchIdx->new($ibx, 1); $ibx->with_umask(sub { - $rw->_xdb_acquire; - $rw->_xdb_release; + $rw->idx_acquire; + $rw->idx_release; }); $rw = undef; my $ro = PublicInbox::Search->new($ibx); @@ -59,17 +59,26 @@ sub oct_is ($$$) { } } +{ + my $crlf_adjust = \&PublicInbox::SearchIdx::crlf_adjust; + is($crlf_adjust->("hi\r\nworld\r\n"), 0, 'no adjustment needed'); + is($crlf_adjust->("hi\nworld\n"), 2, 'LF-only counts two CR'); + is($crlf_adjust->("hi\r\nworld\n"), 1, 'CRLF/LF-mix 1 counts 1 CR'); + is($crlf_adjust->("hi\nworld\r\n"), 1, 'CRLF/LF-mix 2 counts 1 CR'); +} + $ibx->with_umask(sub { - my $root = PublicInbox::MIME->new(<<'EOF'); + my $root = PublicInbox::Eml->new(<<'EOF'); Date: Fri, 02 Oct 1993 00:00:00 +0000 Subject: Hello world Message-ID: From: John Smith To: list@example.com +List-Id: I'm not mad \m/ EOF - my $last = PublicInbox::MIME->new(<<'EOF'); + my $last = PublicInbox::Eml->new(<<'EOF'); Date: Sat, 02 Oct 2010 00:00:00 +0000 Subject: Re: Hello world In-Reply-To: @@ -77,6 +86,7 @@ Message-ID: From: John Smith To: list@example.com Cc: foo@example.com +List-Id: there's nothing goodbye forever :< EOF @@ -90,7 +100,7 @@ EOF sub filter_mids { my ($msgs) = @_; - sort(map { $_->mid } @$msgs); + sort(map { $_->{mid} } @$msgs); } { @@ -98,7 +108,7 @@ sub filter_mids { $ro->reopen; my $found = $ro->query('m:root@s'); is(scalar(@$found), 1, "message found"); - is($found->[0]->mid, 'root@s', 'mid set correctly') if scalar(@$found); + is($found->[0]->{mid}, 'root@s', 'mid set correctly') if @$found; my ($res, @res); my @exp = sort qw(root@s last@s); @@ -126,7 +136,7 @@ sub filter_mids { $ibx->with_umask(sub { $rw_commit->(); my $rmid = ''; - my $reply_to_ghost = PublicInbox::MIME->new(<<"EOF"); + my $reply_to_ghost = PublicInbox::Eml->new(<<"EOF"); Date: Sat, 02 Oct 2010 00:00:00 +0000 Subject: Re: ghosts Message-ID: @@ -140,7 +150,7 @@ EOF my $reply_id = $rw->add_message($reply_to_ghost); is($reply_id, int($reply_id), "reply_id is an integer: $reply_id"); - my $was_ghost = PublicInbox::MIME->new(<<"EOF"); + my $was_ghost = PublicInbox::Eml->new(<<"EOF"); Date: Sat, 02 Oct 2010 00:00:01 +0000 Subject: ghosts Message-ID: $rmid @@ -151,7 +161,7 @@ are real EOF my $ghost_id = $rw->add_message($was_ghost); is($ghost_id, int($ghost_id), "ghost_id is an integer: $ghost_id"); - my $msgs = $rw->{over}->get_thread('ghost-message@s'); + my $msgs = $rw->{oidx}->get_thread('ghost-message@s'); is(scalar(@$msgs), 2, 'got both messages in ghost thread'); foreach (qw(sid tid)) { is($msgs->[0]->{$_}, $msgs->[1]->{$_}, "{$_} match"); @@ -174,7 +184,7 @@ EOF # body $res = $ro->query('goodbye'); is(scalar(@$res), 1, "goodbye message found"); - is($res->[0]->mid, 'last@s', 'got goodbye message body') if scalar(@$res); + is($res->[0]->{mid}, 'last@s', 'got goodbye message body') if @$res; # datestamp $res = $ro->query('dt:20101002000001..20101002000001'); @@ -189,7 +199,7 @@ $ibx->with_umask(sub { $rw_commit->(); $ro->reopen; my $long_mid = 'last' . ('x' x 60). '@s'; - my $long = PublicInbox::MIME->new(<new(< @@ -209,7 +219,7 @@ EOF my @res; my $long_reply_mid = 'reply-to-long@1'; - my $long_reply = PublicInbox::MIME->new(<new(< @@ -233,7 +243,7 @@ EOF # quote prioritization $ibx->with_umask(sub { $rw_commit->(); - $rw->add_message(PublicInbox::MIME->new(<<'EOF')); + $rw->add_message(PublicInbox::Eml->new(<<'EOF')); Date: Sat, 02 Oct 2010 00:00:01 +0000 Subject: Hello Message-ID: @@ -243,7 +253,7 @@ To: list@example.com > theatre illusions fade EOF - $rw->add_message(PublicInbox::MIME->new(<<'EOF')); + $rw->add_message(PublicInbox::Eml->new(<<'EOF')); Date: Sat, 02 Oct 2010 00:00:02 +0000 Subject: Hello Message-ID: @@ -253,21 +263,23 @@ To: list@example.com theatre fade EOF - my $res = $rw->query("theatre"); + $rw_commit->(); + my $res = $ro->reopen->query("theatre"); is(scalar(@$res), 2, "got both matches"); - is($res->[0]->mid, 'nquote@a', "non-quoted scores higher") if scalar(@$res); - is($res->[1]->mid, 'quote@a', "quoted result still returned") if scalar(@$res); - - $res = $rw->query("illusions"); + if (@$res == 2) { + is($res->[0]->{mid}, 'nquote@a', 'non-quoted scores higher'); + is($res->[1]->{mid}, 'quote@a', 'quoted result still returned'); + } + $res = $ro->query("illusions"); is(scalar(@$res), 1, "got a match for quoted text"); - is($res->[0]->mid, 'quote@a', + is($res->[0]->{mid}, 'quote@a', "quoted result returned if nothing else") if scalar(@$res); }); # circular references $ibx->with_umask(sub { my $s = 'foo://'. ('Circle' x 15).'/foo'; - my $doc_id = $rw->add_message(PublicInbox::MIME->new(<add_message(PublicInbox::Eml->new(< @@ -279,21 +291,13 @@ To: list\@example.com LOOP! EOF ok($doc_id > 0, "doc_id defined with circular reference"); - my $smsg = $rw->query('m:circle@a', {limit=>1})->[0]; + $rw_commit->(); + my $smsg = $ro->reopen->query('m:circle@a', {limit=>1})->[0]; is(defined($smsg), 1, 'found m:circl@a'); - is($smsg->references, '', "no references created") if defined($smsg); - is($smsg->subject, $s, 'long subject not rewritten') if defined($smsg); -}); - -$ibx->with_umask(sub { - my $eml = 't/utf8.eml'; - my $mime = PublicInbox::InboxWritable::mime_from_path($eml) or - die "open $eml: $!"; - my $doc_id = $rw->add_message($mime); - ok($doc_id > 0, 'message indexed doc_id with UTF-8'); - my $msg = $rw->query('m:testmessage@example.com', {limit => 1})->[0]; - is(defined($msg), 1, 'found testmessage@example.com'); - is($mime->header('Subject'), $msg->subject, 'UTF-8 subject preserved') if defined($msg); + if (defined $smsg) { + is($smsg->{references}, '', "no references created"); + is($smsg->{subject}, $s, 'long subject not rewritten'); + } }); { @@ -305,20 +309,45 @@ $ibx->with_umask(sub { is(scalar(@$msgs), 0, 'nothing before 19931001'); } +$ibx->with_umask(sub { + my $mime = eml_load 't/utf8.eml'; + my $doc_id = $rw->add_message($mime); + ok($doc_id > 0, 'message indexed doc_id with UTF-8'); + $rw_commit->(); + my $msg = $ro->reopen-> + query('m:testmessage@example.com', {limit => 1})->[0]; + is(defined($msg), 1, 'found testmessage@example.com'); + if (defined $msg) { + is($mime->header('Subject'), $msg->{subject}, + 'UTF-8 subject preserved'); + } +}); + # names and addresses { my $mset = $ro->query('t:list@example.com', {mset => 1}); - is($mset->size, 6, 'searched To: successfully'); + is($mset->size, 9, 'searched To: successfully'); foreach my $m ($mset->items) { my $smsg = $ro->{over_ro}->get_art($m->get_docid); - like($smsg->to, qr/\blist\@example\.com\b/, 'to appears'); + like($smsg->{to}, qr/\blist\@example\.com\b/, 'to appears'); + my $doc = $m->get_document; + my $col = PublicInbox::Search::BYTES(); + my $bytes = PublicInbox::Smsg::get_val($doc, $col); + like($bytes, qr/\A[0-9]+\z/, '$bytes stored as digit'); + ok($bytes > 0, '$bytes is > 0'); + is($bytes, $smsg->{bytes}, 'bytes Xapian value matches Over'); + + $col = PublicInbox::Search::UID(); + my $uid = PublicInbox::Smsg::get_val($doc, $col); + is($uid, $smsg->{num}, 'UID column matches {num}'); + is($uid, $m->get_docid, 'UID column matches docid'); } $mset = $ro->query('tc:list@example.com', {mset => 1}); - is($mset->size, 6, 'searched To+Cc: successfully'); + is($mset->size, 9, 'searched To+Cc: successfully'); foreach my $m ($mset->items) { my $smsg = $ro->{over_ro}->get_art($m->get_docid); - my $tocc = join("\n", $smsg->to, $smsg->cc); + my $tocc = join("\n", $smsg->{to}, $smsg->{cc}); like($tocc, qr/\blist\@example\.com\b/, 'tocc appears'); } @@ -327,7 +356,7 @@ $ibx->with_umask(sub { is($mset->items, 1, "searched $pfx successfully for Cc:"); foreach my $m ($mset->items) { my $smsg = $ro->{over_ro}->get_art($m->get_docid); - like($smsg->cc, qr/\bfoo\@example\.com\b/, + like($smsg->{cc}, qr/\bfoo\@example\.com\b/, 'cc appears'); } } @@ -337,7 +366,7 @@ $ibx->with_umask(sub { is(scalar(@$res), 1, "searched $pfx successfully for From:"); foreach my $smsg (@$res) { - like($smsg->from_name, qr/Laggy Sender/, + like($smsg->{from_name}, qr/Laggy Sender/, "From appears with $pfx"); } } @@ -354,46 +383,49 @@ $ibx->with_umask(sub { $res = $ro->query('q:theatre'); is(scalar(@$res), 1, 'only one quoted body'); - like($res->[0]->from_name, qr/\AQuoter/, + like($res->[0]->{from_name}, qr/\AQuoter/, 'got quoted body') if (scalar(@$res)); $res = $ro->query('nq:theatre'); is(scalar @$res, 1, 'only one non-quoted body'); - like($res->[0]->from_name, qr/\ANon-Quoter/, + like($res->[0]->{from_name}, qr/\ANon-Quoter/, 'got non-quoted body') if (scalar(@$res)); foreach my $pfx (qw(b: bs:)) { $res = $ro->query($pfx . 'theatre'); is(scalar @$res, 2, "searched both bodies for $pfx"); - like($res->[0]->from_name, qr/\ANon-Quoter/, + like($res->[0]->{from_name}, qr/\ANon-Quoter/, "non-quoter first for $pfx") if scalar(@$res); } } $ibx->with_umask(sub { - my $amsg = mime_load 't/search-amsg.eml'; - ok($rw->add_message($amsg), 'added attachment'); + my $amsg = eml_load 't/search-amsg.eml'; + my $oid = ('0'x40); + my $smsg = bless { blob => $oid }, 'PublicInbox::Smsg'; + ok($rw->add_message($amsg, $smsg), 'added attachment'); $rw_commit->(); $ro->reopen; my $n = $ro->query('n:attached_fart.txt'); is(scalar @$n, 1, 'got result for n:'); my $res = $ro->query('part_deux.txt'); is(scalar @$res, 1, 'got result without n:'); - is($n->[0]->mid, $res->[0]->mid, + is($n->[0]->{mid}, $res->[0]->{mid}, 'same result with and without') if scalar(@$res); my $txt = $ro->query('"inside another"'); is(scalar @$txt, 1, 'found inside another'); - is($txt->[0]->mid, $res->[0]->mid, + is($txt->[0]->{mid}, $res->[0]->{mid}, 'search inside text attachments works') if scalar(@$txt); my $art; if (scalar(@$n) >= 1) { - my $mid = $n->[0]->mid; + my $mid = $n->[0]->{mid}; my ($id, $prev); $art = $ro->{over_ro}->next_by_mid($mid, \$id, \$prev); ok($art, 'article exists in OVER DB'); } - $rw->unindex_blob($amsg); + $rw->_msgmap_init; + $rw->unindex_eml($oid, $amsg); $rw->commit_txn_lazy; SKIP: { skip('$art not defined', 1) unless defined $art; @@ -429,7 +461,7 @@ $ibx->with_umask(sub { my $mid = "$ua.$digits.2460-100000\@penguin.transmeta.com"; is($ro->reopen->query("m:$digits", { mset => 1})->size, 0, 'no results yet'); - my $pine = PublicInbox::MIME->new(<new(< From: torvalds\@transmeta @@ -450,6 +482,60 @@ EOF is($ro->query("m:Pine m:LNX m:10010260936330", {mset=>1})->size, 1); }); +{ # List-Id searching + my $found = $ro->query('lid:i.m.just.bored'); + is_deeply([ filter_mids($found) ], [ 'root@s' ], + 'got expected mid on exact lid: search'); + + $found = $ro->query('lid:just.bored'); + is_deeply($found, [], 'got nothing on lid: search'); + + $found = $ro->query('lid:*.just.bored'); + is_deeply($found, [], 'got nothing on lid: search'); + + $found = $ro->query('l:i.m.just.bored'); + is_deeply([ filter_mids($found) ], [ 'root@s' ], + 'probabilistic search works on full List-Id contents'); + + $found = $ro->query('l:just.bored'); + is_deeply([ filter_mids($found) ], [ 'root@s' ], + 'probabilistic search works on partial List-Id contents'); + + $found = $ro->query('lid:mad'); + is_deeply($found, [], 'no match on phrase with lid:'); + + $found = $ro->query('lid:bored'); + is_deeply($found, [], 'no match on partial List-Id with lid:'); + + $found = $ro->query('l:nothing'); + is_deeply($found, [], 'matched on phrase with l:'); +} + +$ibx->with_umask(sub { + $rw_commit->(); + my $doc_id = $rw->add_message(eml_load('t/data/message_embed.eml')); + ok($doc_id > 0, 'messages within messages'); + $rw->commit_txn_lazy; + $ro->reopen; + my $n_test_eml = $ro->query('n:test.eml'); + is(scalar(@$n_test_eml), 1, 'got a result'); + my $n_embed2x_eml = $ro->query('n:embed2x.eml'); + is_deeply($n_test_eml, $n_embed2x_eml, '.eml filenames searchable'); + for my $m (qw(20200418222508.GA13918@dcvr 20200418222020.GA2745@dcvr + 20200418214114.7575-1-e@yhbt.net)) { + is($ro->query("m:$m")->[0]->{mid}, + '20200418222508.GA13918@dcvr', 'probabilistic m:'.$m); + is($ro->query("mid:$m")->[0]->{mid}, + '20200418222508.GA13918@dcvr', 'boolean mid:'.$m); + } + is($ro->query('dfpost:4dc62c50')->[0]->{mid}, + '20200418222508.GA13918@dcvr', + 'diff search reaches inside message/rfc822'); + is($ro->query('s:"mail header experiments"')->[0]->{mid}, + '20200418222508.GA13918@dcvr', + 'Subject search reaches inside message/rfc822'); +}); + done_testing(); 1;