t/import: test for nasty characters

Spammers may send emails with nasty characters which can throw
off git-fast-import.  Users with non-existent or weaker spam
filters may be susceptible to corruption in the fast-import
stream as a result.

This was actually quietly fixed in git on 2020-06-01 by
commit 9ab886546cc89f37819e1ef09cb49fd9325b3a41
("smsg: introduce ->populate method"), but no test case
was created.

Reported-by: Eric W. Biederman <ebiederm@xmission.com>
Link: https://public-inbox.org/meta/87imf4qn87.fsf@x220.int.ebiederm.org/
Link: https://public-inbox.org/meta/20200601100657.14700-6-e@yhbt.net/

diff --git a/t/import.t b/t/import.t
index abbc8229d0e7aaf91099ca9b23462c40660ebce5..9491f337484189418662fd76b3d5f52162c3cd39 100644 (file)
--- a/t/import.t
+++ b/t/import.t
@@ -11,6 +11,7 @@ use PublicInbox::Spawn qw(spawn);
 use Fcntl qw(:DEFAULT SEEK_SET);
 use File::Temp qw/tempfile/;
 use PublicInbox::TestCommon;
+use MIME::Base64 3.05; # Perl 5.10.0 / 5.9.2
 my ($dir, $for_destroy) = tmpdir();
 
 my $git = PublicInbox::Git->new($dir);
@@ -103,4 +104,27 @@ eval {
 };
 ok($@, 'Import->add fails on non-existent dir');
 
+my @cls = qw(PublicInbox::Eml);
+SKIP: {
+       require_mods('PublicInbox::MIME', 1);
+       push @cls, 'PublicInbox::MIME';
+};
+
+$main::badchars = "\n\0\r";
+my $from = '=?UTF-8?B?'. encode_base64("B\ra\nd\0\$main::badchars", ''). '?=';
+for my $cls (@cls) {
+       my $eml = $cls->new(<<EOF);
+From: $from <spammer\@example.com>
+Message-ID: <$cls\@example.com>
+
+EOF
+       ok($im->add($eml), "added $cls message with nasty char in From");
+}
+$im->done;
+my $bref = $git->cat_file('HEAD');
+like($$bref, qr/^author Ba d \$main::badchars <spammer\@example\.com> /sm,
+        'latest commit accepted by spammer');
+$git->qx(qw(fsck --no-progress --strict));
+is($?, 0, 'fsck reported no errors');
+
 done_testing();