X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=t%2Fsearch.t;h=a75dc9b57b6897af523f4fc2ec487cfac7b7aa38;hb=7eeadcb62729b0efbcb53cd9b7b181897c92cf9a;hp=65539f14c2ca31eb5ae97258360080602a97067b;hpb=73214b02e581ef0a037d85a1ae37ff425654d7b3;p=public-inbox.git

diff --git a/t/search.t b/t/search.t
index 65539f14..a75dc9b5 100644
--- a/t/search.t
+++ b/t/search.t
@@ -1,4 +1,4 @@
-# Copyright (C) 2015, all contributors <meta@public-inbox.org>
+# Copyright (C) 2015 all contributors <meta@public-inbox.org>
 # License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
 use strict;
 use warnings;
@@ -7,8 +7,7 @@ eval { require PublicInbox::SearchIdx; };
 plan skip_all => "Xapian missing for search" if $@;
 use File::Temp qw/tempdir/;
 use Email::MIME;
-use Data::Dumper;
-my $tmpdir = tempdir(CLEANUP => 1);
+my $tmpdir = tempdir('pi-search-XXXXXX', TMPDIR => 1, CLEANUP => 1);
 my $git_dir = "$tmpdir/a.git";
 my ($root_id, $last_id);
 
@@ -16,28 +15,15 @@ is(0, system(qw(git init -q --bare), $git_dir), "git init (main)");
 eval { PublicInbox::Search->new($git_dir) };
 ok($@, "exception raised on non-existent DB");
 
-{
-	my $orig = "FOO " x 30;
-	my $summ = PublicInbox::Search::subject_summary($orig);
-
-	$summ = length($summ);
-	$orig = length($orig);
-	ok($summ < $orig && $summ > 0, "summary shortened ($orig => $summ)");
-
-	$orig = "FOO" x 30;
-	$summ = PublicInbox::Search::subject_summary($orig);
-
-	$summ = length($summ);
-	$orig = length($orig);
-	ok($summ < $orig && $summ > 0,
-	   "summary shortened but not empty: $summ");
-}
-
 my $rw = PublicInbox::SearchIdx->new($git_dir, 1);
+$rw->_xdb_acquire;
+$rw->_xdb_release;
+$rw = undef;
 my $ro = PublicInbox::Search->new($git_dir);
 my $rw_commit = sub {
-	$rw = undef;
+	$rw->{xdb}->commit_transaction if $rw && $rw->{xdb};
 	$rw = PublicInbox::SearchIdx->new($git_dir, 1);
+	$rw->_xdb_acquire->begin_transaction;
 };
 
 {
@@ -83,10 +69,12 @@ my $rw_commit = sub {
 			'Message-ID' => '<last@s>',
 			From => 'John Smith <js@example.com>',
 			To => 'list@example.com',
+			Cc => 'foo@example.com',
 		],
 		body => "goodbye forever :<\n");
 
 	my $rv;
+	$rw_commit->();
 	$root_id = $rw->add_message($root);
 	is($root_id, int($root_id), "root_id is an integer: $root_id");
 	$last_id = $rw->add_message($last);
@@ -104,46 +92,29 @@ sub filter_mids {
 	my $found = $ro->lookup_message('<root@s>');
 	ok($found, "message found");
 	is($root_id, $found->{doc_id}, 'doc_id set correctly');
-	$found->ensure_metadata;
 	is($found->mid, 'root@s', 'mid set correctly');
 	ok(int($found->thread_id) > 0, 'thread_id is an integer');
 
+	my ($res, @res);
 	my @exp = sort qw(root@s last@s);
-	my $res = $ro->query("path:hello_world");
-	my @res = filter_mids($res);
-	is_deeply(\@res, \@exp, 'got expected results for path: match');
-
-	foreach my $p (qw(hello hello_ hello_world2 hello_world_)) {
-		$res = $ro->query("path:$p");
-		is($res->{total}, 0, "path variant `$p' does not match");
-	}
 
-	$res = $ro->query('subject:(Hello world)');
+	$res = $ro->query('s:(Hello world)');
 	@res = filter_mids($res);
-	is_deeply(\@res, \@exp, 'got expected results for subject:() match');
+	is_deeply(\@res, \@exp, 'got expected results for s:() match');
 
-	$res = $ro->query('subject:"Hello world"');
+	$res = $ro->query('s:"Hello world"');
 	@res = filter_mids($res);
-	is_deeply(\@res, \@exp, 'got expected results for subject:"" match');
+	is_deeply(\@res, \@exp, 'got expected results for s:"" match');
 
-	$res = $ro->query('subject:"Hello world"', {limit => 1});
+	$res = $ro->query('s:"Hello world"', {limit => 1});
 	is(scalar @{$res->{msgs}}, 1, "limit works");
 	my $first = $res->{msgs}->[0];
 
-	$res = $ro->query('subject:"Hello world"', {offset => 1});
+	$res = $ro->query('s:"Hello world"', {offset => 1});
 	is(scalar @{$res->{msgs}}, 1, "offset works");
 	my $second = $res->{msgs}->[0];
 
 	isnt($first, $second, "offset returned different result from limit");
-
-	foreach my $f (qw(inreplyto references)) {
-		$res = $ro->query($f . ':root@s');
-		@res = filter_mids($res);
-		is_deeply(\@res, [ 'last@s' ],
-			  "got expected results for $f: match");
-		$res = $ro->query($f . ':root');
-		is($res->{total}, 0, "no partial mid match");
-	}
 }
 
 # ghost vivication
@@ -185,7 +156,7 @@ sub filter_mids {
 	$rw_commit->();
 	$ro->reopen;
 
-	# Subject:
+	# subject
 	my $res = $ro->query('ghost');
 	my @exp = sort qw(ghost-message@s ghost-reply@s);
 	my @res = filter_mids($res);
@@ -201,7 +172,6 @@ sub filter_mids {
 	$rw_commit->();
 	$ro->reopen;
 	my $long_mid = 'last' . ('x' x 60). '@s';
-	my $long_midc = Digest::SHA::sha1_hex($long_mid);
 
 	my $long = Email::MIME->create(
 		header_str => [
@@ -219,14 +189,8 @@ sub filter_mids {
 
 	$rw_commit->();
 	$ro->reopen;
-	my $res = $ro->query('references:root@s');
-	my @res = filter_mids($res);
-	is_deeply(\@res, [ sort('last@s', $long_midc) ],
-		  "got expected results for references: match");
-
-	my $followups = $ro->get_followups('root@s');
-	$followups = [ filter_mids($followups) ];
-	is_deeply($followups, [ filter_mids($res) ], "get_followups matches");
+	my $res;
+	my @res;
 
 	my $long_reply_mid = 'reply-to-long@1';
 	my $long_reply = Email::MIME->create(
@@ -247,7 +211,7 @@ sub filter_mids {
 	$ro->reopen;
 	my $t = $ro->get_thread('root@s');
 	is($t->{total}, 4, "got all 4 mesages in thread");
-	my @exp = sort($long_reply_mid, 'root@s', 'last@s', $long_midc);
+	my @exp = sort($long_reply_mid, 'root@s', 'last@s', $long_mid);
 	@res = filter_mids($t);
 	is_deeply(\@res, \@exp, "get_thread works");
 }
@@ -287,10 +251,11 @@ sub filter_mids {
 
 # circular references
 {
+	my $s = 'foo://'. ('Circle' x 15).'/foo';
 	my $doc_id = $rw->add_message(Email::MIME->create(
+		header => [ Subject => $s ],
 		header_str => [
 			Date => 'Sat, 02 Oct 2010 00:00:01 +0000',
-			Subject => 'Circle',
 			'Message-ID' => '<circle@a>',
 			'References' => '<circle@a>',
 			'In-Reply-To' => '<circle@a>',
@@ -300,8 +265,140 @@ sub filter_mids {
 		body => "LOOP!\n"));
 	ok($doc_id > 0, "doc_id defined with circular reference");
 	my $smsg = $rw->lookup_message('circle@a');
-	$smsg->ensure_metadata;
-	is($smsg->{references}, undef, "no references created");
+	is($smsg->references, '', "no references created");
+	my $msg = PublicInbox::SearchMsg->load_doc($smsg->{doc});
+	is($s, $msg->subject, 'long subject not rewritten');
+}
+
+{
+	my $str = eval {
+		my $mbox = 't/utf8.mbox';
+		open(my $fh, '<', $mbox) or die "failed to open mbox: $mbox\n";
+		local $/;
+		<$fh>
+	};
+	$str =~ s/\AFrom [^\n]+\n//s;
+	my $mime = Email::MIME->new($str);
+	my $doc_id = $rw->add_message($mime);
+	ok($doc_id > 0, 'message indexed doc_id with UTF-8');
+	my $smsg = $rw->lookup_message('testmessage@example.com');
+	my $msg = PublicInbox::SearchMsg->load_doc($smsg->{doc});
+
+	is($mime->header('Subject'), $msg->subject, 'UTF-8 subject preserved');
+}
+
+{
+	my $res = $ro->query('d:19931002..20101002');
+	ok(scalar @{$res->{msgs}} > 0, 'got results within range');
+	$res = $ro->query('d:20101003..');
+	is(scalar @{$res->{msgs}}, 0, 'nothing after 20101003');
+	$res = $ro->query('d:..19931001');
+	is(scalar @{$res->{msgs}}, 0, 'nothing before 19931001');
+}
+
+# names and addresses
+{
+	my $res = $ro->query('t:list@example.com');
+	is(scalar @{$res->{msgs}}, 6, 'searched To: successfully');
+	foreach my $smsg (@{$res->{msgs}}) {
+		like($smsg->to, qr/\blist\@example\.com\b/, 'to appears');
+	}
+
+	$res = $ro->query('tc:list@example.com');
+	is(scalar @{$res->{msgs}}, 6, 'searched To+Cc: successfully');
+	foreach my $smsg (@{$res->{msgs}}) {
+		my $tocc = join("\n", $smsg->to, $smsg->cc);
+		like($tocc, qr/\blist\@example\.com\b/, 'tocc appears');
+	}
+
+	foreach my $pfx ('tcf:', 'c:') {
+		$res = $ro->query($pfx . 'foo@example.com');
+		is(scalar @{$res->{msgs}}, 1,
+			"searched $pfx successfully for Cc:");
+		foreach my $smsg (@{$res->{msgs}}) {
+			like($smsg->cc, qr/\bfoo\@example\.com\b/,
+				'cc appears');
+		}
+	}
+
+	foreach my $pfx ('', 'tcf:', 'f:') {
+		$res = $ro->query($pfx . 'Laggy');
+		is(scalar @{$res->{msgs}}, 1,
+			"searched $pfx successfully for From:");
+		foreach my $smsg (@{$res->{msgs}}) {
+			like($smsg->from, qr/Laggy Sender/,
+				"From appears with $pfx");
+		}
+	}
+}
+
+{
+	$rw_commit->();
+	$ro->reopen;
+	my $res = $ro->query('b:hello');
+	is(scalar @{$res->{msgs}}, 0, 'no match on body search only');
+	$res = $ro->query('bs:smith');
+	is(scalar @{$res->{msgs}}, 0,
+		'no match on body+subject search for From');
+
+	$res = $ro->query('q:theatre');
+	is(scalar @{$res->{msgs}}, 1, 'only one quoted body');
+	like($res->{msgs}->[0]->from, qr/\AQuoter/, 'got quoted body');
+
+	$res = $ro->query('nq:theatre');
+	is(scalar @{$res->{msgs}}, 1, 'only one non-quoted body');
+	like($res->{msgs}->[0]->from, qr/\ANon-Quoter/, 'got non-quoted body');
+
+	foreach my $pfx (qw(b: bs:)) {
+		$res = $ro->query($pfx . 'theatre');
+		is(scalar @{$res->{msgs}}, 2, "searched both bodies for $pfx");
+		like($res->{msgs}->[0]->from, qr/\ANon-Quoter/,
+			"non-quoter first for $pfx");
+	}
+}
+
+{
+	my $part1 = Email::MIME->create(
+                 attributes => {
+                     content_type => 'text/plain',
+                     disposition  => 'attachment',
+                     charset => 'US-ASCII',
+		     encoding => 'quoted-printable',
+		     filename => 'attached_fart.txt',
+                 },
+                 body_str => 'inside the attachment',
+	);
+	my $part2 = Email::MIME->create(
+                 attributes => {
+                     content_type => 'text/plain',
+                     disposition  => 'attachment',
+                     charset => 'US-ASCII',
+		     encoding => 'quoted-printable',
+		     filename => 'part_deux.txt',
+                 },
+                 body_str => 'inside another',
+	);
+	my $amsg = Email::MIME->create(
+		header_str => [
+			Subject => 'see attachment',
+			'Message-ID' => '<file@attached>',
+			From => 'John Smith <js@example.com>',
+			To => 'list@example.com',
+		],
+		parts => [ $part1, $part2 ],
+	);
+	ok($rw->add_message($amsg), 'added attachment');
+	$rw_commit->();
+	$ro->reopen;
+	my $n = $ro->query('n:attached_fart.txt');
+	is(scalar @{$n->{msgs}}, 1, 'got result for n:');
+	my $res = $ro->query('part_deux.txt');
+	is(scalar @{$res->{msgs}}, 1, 'got result without n:');
+	is($n->{msgs}->[0]->mid, $res->{msgs}->[0]->mid,
+		'same result with and without');
+	my $txt = $ro->query('"inside another"');
+	is($txt->{msgs}->[0]->mid, $res->{msgs}->[0]->mid,
+		'search inside text attachments works');
 }
 
 done_testing();