t/psgi_search.t

#!perl -w
# Copyright (C) all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
use v5.12;
use PublicInbox::TestCommon;
use IO::Uncompress::Gunzip qw(gunzip);
use PublicInbox::Eml;
use PublicInbox::Inbox;
require_mods qw(DBD::SQLite Xapian psgi);
use_ok 'PublicInbox::WWW';
use_ok 'PublicInbox::SearchIdx';
my ($tmpdir, $for_destroy) = tmpdir();
local $ENV{TZ} = 'UTC';

my $digits = '10010260936330';
my $ua = 'Pine.LNX.4.10';
my $mid = "$ua.$digits.2460-100000\@penguin.transmeta.com";
my $ibx = create_inbox '26-git', indexlevel => 'full', tmpdir => "$tmpdir/1",
sub {
	my ($im) = @_;
	# n.b. these headers are not properly RFC2047-encoded
	$im->add(PublicInbox::Eml->new(<<EOF)) or BAIL_OUT;
Subject: test Ævar
Message-ID: <$mid>
From: Ævar Arnfjörð Bjarmason <avarab\@example>
To: git\@vger.kernel.org

EOF

	$im->add(PublicInbox::Eml->new(<<"")) or BAIL_OUT;
Message-ID: <reply\@asdf>
From: replier <r\@example.com>
In-Reply-To: <$mid>
Subject: mismatch

	$im->add(PublicInbox::Eml->new(<<'EOF')) or BAIL_OUT;
Subject:
Message-ID: <blank-subject@example.com>
From: blank subject <blank-subject@example.com>
To: git@vger.kernel.org

EOF

	$im->add(PublicInbox::Eml->new(<<'EOF')) or BAIL_OUT;
Message-ID: <no-subject-at-all@example.com>
From: no subject at all <no-subject-at-all@example.com>
To: git@vger.kernel.org

EOF
	$im->add(PublicInbox::Eml->new(<<'EOF')) or BAIL_OUT;
Message-ID: <ampersand@example.com>
From: <e@example.com>
To: git@vger.kernel.org
Subject: git & ampersand

hi +++ b/foo
x=y
s'more

EOF
};

my $cfg = cfg_new $tmpdir, <<EOF;
[publicinbox "test"]
	address = git\@vger.kernel.org
	inboxdir = $ibx->{inboxdir}
EOF
my $www = PublicInbox::WWW->new($cfg);
test_psgi(sub { $www->call(@_) }, sub {
	my ($cb) = @_;
	my ($html, $res);
	my $approxidate = 'now';
	for my $req ('/test/?q=%C3%86var', '/test/?q=%25C3%2586var') {
		$res = $cb->(GET($req."+d:..$approxidate"));
		$html = $res->content;
		like($html, qr/<title>&#198;var d:\.\.\Q$approxidate\E/,
			'HTML escaped in title, "d:..$APPROXIDATE" preserved');
		my @res = ($html =~ m/\?q=(.+var)\+d:\.\.\Q$approxidate\E/g);
		ok(scalar(@res), 'saw query strings');
		my %uniq = map { $_ => 1 } @res;
		is(1, scalar keys %uniq, 'all query values identical in HTML');
		is('%C3%86var', (keys %uniq)[0], 'matches original query');
		ok(index($html, 'by &#198;var Arnfj&#246;r&#240; Bjarmason')
			>= 0, "displayed Ævar's name properly in HTML");
		like($html, qr/download mbox\.gz: .*?"full threads"/s,
			'"full threads" download option shown');
	}
	like($html, qr/Initial query\b.*?returned no.results, used:.*instead/s,
		'noted retry on double-escaped query {-uxs_retried}');

	my $warn = [];
	local $SIG{__WARN__} = sub { push @$warn, @_ };
	$res = $cb->(GET('/test/?q=s:test&l=5e'));
	is($res->code, 200, 'successful search result');
	is_deeply([], $warn, 'no warnings from non-numeric comparison');

	$res = $cb->(GET('/test/?&q=s:test'));
	is($res->code, 200, 'successful search result');
	is_deeply([], $warn, 'no warnings from black parameter');

	$res = $cb->(POST('/test/?q=s:bogus&x=m'));
	is($res->code, 404, 'failed search result gives 404');
	like($res->content, qr/No results found/, "`No results' shown");
	is_deeply([], $warn, 'no warnings');

	my $mid_re = qr/\Q$mid\E/o;
	while (length($digits) > 8) {
		$res = $cb->(GET("/test/$ua.$digits/"));
		is($res->code, 300, 'partial match found while truncated');
		like($res->content, qr/\b1 partial match found\b/);
		like($res->content, $mid_re, 'found mid in response');
		chop($digits);
	}
	$res = $cb->(GET("/test/$mid/"));
	$html = $res->content;
	like($html, qr/\bFrom: &#198;var /,
		"displayed Ævar's name properly in permalink From:");
	unlike($html, qr/&#195;/, 'no raw octets in permalink HTML');

	$res = $cb->(GET('/test/'));
	$html = $res->content;
	like($html, qr/\bhref="no-subject-at-all[^>]+>\(no subject\)</,
		'subject-less message linked from "/$INBOX/"');
	like($html, qr/\bhref="blank-subject[^>]+>\(no subject\)</,
		'blank subject message linked from "/$INBOX/"');
	like($html, qr/test &#198;var/,
		"displayed Ævar's name properly in topic view");

	$res = $cb->(GET('/test/?q=tc:git'));
	like($html, qr/\bhref="no-subject-at-all[^>]+>\(no subject\)</,
		'subject-less message linked from "/$INBOX/?q=..."');
	like($html, qr/\bhref="blank-subject[^>]+>\(no subject\)</,
		'blank subject message linked from "/$INBOX/?q=..."');
	$res = $cb->(GET('/test/no-subject-at-all@example.com/raw'));
	like($res->header('Content-Disposition'),
		qr/filename=no-subject\.txt/);
	$res = $cb->(GET('/test/no-subject-at-all@example.com/t.mbox.gz'));
	like($res->header('Content-Disposition'),
		qr/filename=no-subject\.mbox\.gz/);

	# "full threads" mbox.gz download
	$res = $cb->(POST("/test/?q=s:test+d:..$approxidate&x=m&t"));
	is($res->code, 200, 'successful mbox download with threads');
	gunzip(\($res->content) => \(my $before));
	is_deeply([ "Message-ID: <$mid>\n", "Message-ID: <reply\@asdf>\n" ],
		[ grep(/^Message-ID:/m, split(/^/m, $before)) ],
		'got full thread');

	# clobber has_threadid to emulate old versions:
	{
		my $sidx = PublicInbox::SearchIdx->new($ibx, 0);
		my $xdb = $sidx->idx_acquire;
		$xdb->set_metadata('has_threadid', '0');
		$sidx->idx_release;
	}
	$cfg->each_inbox(sub { delete $_[0]->{search} });
	$res = $cb->(GET('/test/?q=s:test'));
	is($res->code, 200, 'successful search w/o has_threadid');
	unlike($html, qr/download mbox\.gz: .*?"full threads"/s,
		'"full threads" download option not shown w/o has_threadid');

	# in case somebody uses curl to bypass <form>
	$res = $cb->(POST("/test/?q=s:test+d:..$approxidate&x=m&t"));
	is($res->code, 200, 'successful mbox download w/ threads');
	gunzip(\($res->content) => \(my $after));
	isnt($before, $after);

	$res = $cb->(GET('/test/?q=git+%26+ampersand&x=A'));
	is $res->code, 200, 'Atom hit with ampersand';
	unlike $res->content, qr/git\+&\+ampersand/, '& is HTML-escaped';

	$res = $cb->(GET('/test/?q=%22hi+%2b%2b%2b+b/foo%22&x=A'));
	is $res->code, 200, 'slashes and plusses search hit';
	like $res->content, qr!q=%22hi\+(?:%2[bB]){3}\+b/foo%22!,
		'+ and " escaped, but slash not escaped in query';

	$res = $cb->(GET(q{/test/?q=%22s'more%22&x=A}));
	is $res->code, 200, 'single quote inside phrase';

	$res = $cb->(GET("/test/<$mid>/"));
	is $res->code, 301, "redirect for raw `<' and `>' in msgid";
	like $res->header('location'), qr!/test/\Q$mid\E/\z!,
		"redirected to URL without raw `<' and `>'";

	$res = $cb->(GET("/test/%3c$mid%3e/"));
	is $res->code, 301, "redirect for escaped `<' and `>' in msgid";
	like $res->header('location'), qr!/test/\Q$mid\E/\z!,
		"redirected to URL without escaped `<' and `>'";

	# TODO: more tests and odd cases
});

done_testing();