We may be handling invalid mboxes, so just return no objects in
that case. While "lei q" on HTTP(S) externals expects a gzipped
mboxrd, there's always a chance something else gzipped can be
sent to us.
There's also changes to lei_to_mail to better handle emails
which lack a body and/or headers (e.g. t/solve/bare.patch)
Link: https://public-inbox.org/meta/20210903151500.h72mzcpqixgtytjs@meerkat.local/
sub crlf { $_[0]->{crlf} // "\n" }
+sub raw_size {
+ my ($self) = @_;
+ my $len = length(${$self->{hdr}});
+ defined($self->{bdy}) and
+ $len += length(${$self->{bdy}}) + length($self->{crlf});
+ $len;
+}
+
# warnings to ignore when handling spam mailboxes and maybe other places
sub warn_ignore {
my $s = "@_";
$$buf .= 'Content-Length: '.length($$bdy).$crlf.
'Lines: '.$lines.$crlf.$crlf;
substr($$bdy, 0, 0, $$buf); # prepend header
- $_[0] = $bdy;
+ $$bdy .= $crlf;
+ $bdy;
}
# mboxcl still escapes "From " lines
sub eml2mboxcl {
my ($eml, $smsg) = @_;
my $buf = _mbox_hdr_buf($eml, 'mboxcl', $smsg);
- my $crlf = $eml->{crlf};
- if (my $bdy = delete $eml->{bdy}) {
- $$bdy =~ s/^From />From /gm;
- _mboxcl_common($buf, $bdy, $crlf);
- }
- $$buf .= $crlf;
- $buf;
+ my $bdy = delete($eml->{bdy}) // \(my $empty = '');
+ $$bdy =~ s/^From />From /gm;
+ _mboxcl_common($buf, $bdy, $eml->{crlf});
}
# mboxcl2 has no "From " escaping
sub eml2mboxcl2 {
my ($eml, $smsg) = @_;
my $buf = _mbox_hdr_buf($eml, 'mboxcl2', $smsg);
- my $crlf = $eml->{crlf};
- if (my $bdy = delete $eml->{bdy}) {
- _mboxcl_common($buf, $bdy, $crlf);
- }
- $$buf .= $crlf;
- $buf;
+ my $bdy = delete($eml->{bdy}) // \(my $empty = '');
+ _mboxcl_common($buf, $bdy, $eml->{crlf});
}
sub git_to_mail { # git->cat_async callback
$raw =~ s/^\r?\n\z//ms;
$raw =~ s/$from_re/$1/gms;
my $eml = PublicInbox::Eml->new(\$raw);
- $eml_cb->($eml, @arg);
+ $eml_cb->($eml, @arg) if $eml->raw_size;
}
return if $r == 0; # EOF
}
$$hdr =~ s/\A[\r\n]*From [^\n]*\n//s or
die "E: no 'From ' line in:\n", Dumper($hdr);
my $eml = PublicInbox::Eml->new($hdr);
+ next unless $eml->raw_size;
my @cl = $eml->header_raw('Content-Length');
my $n = scalar(@cl);
$n == 0 and die "E: Content-Length missing in:\n",
"Content-Length is correct $fmt $cur");
# clobber for ->as_string comparison below
$eml->header_set('Content-Length');
+
+ # special case for t/solve/bare.patch, not sure if we
+ # should even handle it...
+ if ($cl[0] eq '0' && ${$eml->{hdr}} eq '') {
+ delete $eml->{bdy};
+ }
} else {
is(scalar(@cl), 0, "Content-Length unset $fmt $cur");
}
is(scalar(grep(/Final/, @x)), 0, 'no incomplete bit');
}
+{
+ my $html = <<EOM;
+<html><head><title>hi,</title></head><body>how are you</body></html>
+EOM
+ for my $m (qw(mboxrd mboxcl mboxcl2 mboxo)) {
+ my (@w, @x);
+ local $SIG{__WARN__} = sub { push @w, @_ };
+ open my $fh, '<', \$html or xbail 'PerlIO::scalar';
+ PublicInbox::MboxReader->$m($fh, sub {
+ push @x, $_[0]->as_string
+ });
+ is_deeply(\@x, [], "messages in invalid $m");
+ is_deeply([grep(!/^W: leftover/, @w)], [],
+ "no extra warnings besides leftover ($m)");
+ }
+}
+
done_testing;