Import: Don't copy nulls from emails into git

Recently I ran git --git-dir=lkml/git/1.git fsck
and it reported:
> warning in commit 299dbd50b6995c6debe2275f0df984ce697fb4cc: nulInCommit: NULL byte inthe commit object body

Which I found quite scary.  Nulls in the wrong place have a bad tendency
to make programs misbehave.

It turns out someone had placed "=?iso-8859-1?q?=00?=" at the end of
their subject line.  Which is the mime encoding for NULL.  Email::Mime
had correctly decoded the header, and then public-inbox had simply
copied the contents of the header into the subject line of the git
commit.

To prevent that from causing problems replace nulls in such subject
lines with spaces.

Signed-off-by: Eric Biederman <ebiederm@xmission.com>

3 files changed, 36 insertions, 0 deletions

diff --git a/MANIFEST b/MANIFEST
index 6d2aecee..a2fcae9f 100644
--- a/MANIFEST
+++ b/MANIFEST
@@ -177,6 +177,7 @@ t/msgmap.t
 t/msgtime.t
 t/nntp.t
 t/nntpd.t
+t/nulsubject.t
 t/over.t
 t/perf-nntpd.t
 t/perf-threading.t
diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm
index 250a2db3..f320c58c 100644
--- a/lib/PublicInbox/Import.pm
+++ b/lib/PublicInbox/Import.pm
@@ -405,6 +405,8 @@ sub add {
                 print $w "reset $ref\n" or wfail;
         }
 
+        # Mime decoding can create nulls replace them with spaces to protect git
+        $subject =~ tr/\0/ /;
         utf8::encode($subject);
         print $w "commit $ref\nmark :$commit\n",
                 "author $name <$email> $author_time_raw\n",
diff --git a/t/nulsubject.t b/t/nulsubject.t
new file mode 100644
index 00000000..bb05be85
--- /dev/null
+++ b/t/nulsubject.t
@@ -0,0 +1,33 @@
+# Copyright (C) 2016-2018 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+use strict;
+use warnings;
+use Test::More;
+use File::Temp qw/tempdir/;
+
+use_ok 'PublicInbox::Import';
+use_ok 'PublicInbox::Git';
+my $tmpdir = tempdir('pi-nulsubject-XXXXXX', TMPDIR => 1, CLEANUP => 1);
+my $git_dir = "$tmpdir/a.git";
+
+{
+        is(system(qw(git init -q --bare), $git_dir), 0, 'git init ok');
+        my $git = PublicInbox::Git->new($git_dir);
+        my $im = PublicInbox::Import->new($git, 'testbox', 'test@example');
+        $im->add(Email::MIME->create(
+                header => [
+                        From => 'a@example.com',
+                        To => 'b@example.com',
+                        'Content-Type' => 'text/plain',
+                        Subject => ' A subject line with a null =?iso-8859-1?q?=00?= see!',
+                        'Message-ID' => '<null-test.a@example.com>',
+                ],
+                body => "hello world\n",
+        ));
+        $im->done;
+        is(system(qw(git --git-dir), $git_dir, 'fsck', '--strict'), 0, 'git fsck ok');
+}
+
+done_testing();
+
+1;