From: Eric Wong <e@80x24.org>
Date: Fri, 12 Feb 2021 07:05:52 +0000 (-0700)
Subject: mbox_reader: do not chomp non-blank EOL
X-Git-Tag: v1.7.0~1123
X-Git-Url: http://www.git.stargrave.org/?a=commitdiff_plain;h=376778b910cdf787d6e08cfd11acab26118899f4;p=public-inbox.git

mbox_reader: do not chomp non-blank EOL

It's conceivable some cases won't generate an empty line before
an mboxrd or mboxo From_ line.  Ensure we can handle that case
and don't leave the Eml->{bdy} without a trailing LF character.

And drop an unnecessary alarm import while we're in the area.
---

diff --git a/lib/PublicInbox/MboxReader.pm b/lib/PublicInbox/MboxReader.pm
index 59ce4fb6..df7c78fa 100644
--- a/lib/PublicInbox/MboxReader.pm
+++ b/lib/PublicInbox/MboxReader.pm
@@ -26,7 +26,7 @@ sub _mbox_from {
 		}
 		@raw = grep /[^ \t\r\n]/s, @raw; # skip empty messages
 		while (defined(my $raw = shift @raw)) {
-			$raw =~ s/\r?\n\z//s;
+			$raw =~ s/^\r?\n\z//ms;
 			$raw =~ s/$from_re/$1/gms;
 			my $eml = PublicInbox::Eml->new(\$raw);
 			$eml_cb->($eml, @arg);
diff --git a/t/mbox_reader.t b/t/mbox_reader.t
index 30a5e6e3..18d0fd68 100644
--- a/t/mbox_reader.t
+++ b/t/mbox_reader.t
@@ -74,9 +74,29 @@ for my $fmt (@mbox) { $check_fmt->($fmt) }
 s/\n/\r\n/sg for (values %raw);
 for my $fmt (@mbox) { $check_fmt->($fmt) }
 
+{
+	my $no_blank_eom = <<'EOM';
+From x@y Fri Oct  2 00:00:00 1993
+a: b
+
+body1
+From x@y Fri Oct  2 00:00:00 1993
+c: d
+
+body2
+EOM
+	# chop($no_blank_eom) eq "\n" or BAIL_OUT 'broken LF';
+	for my $variant (qw(mboxrd mboxo)) {
+		my @x;
+		open my $fh, '<', \$no_blank_eom or BAIL_OUT 'PerlIO::scalar';
+		$reader->$variant($fh, sub { push @x, shift });
+		is_deeply($x[0]->{bdy}, \"body1\n", 'LF preserved in 1st');
+		is_deeply($x[1]->{bdy}, \"body2\n", 'no LF added in 2nd');
+	}
+}
+
 SKIP: {
 	use PublicInbox::Spawn qw(popen_rd);
-	use Time::HiRes qw(alarm);
 	my $fh = popen_rd([ $^X, '-E', <<'' ]);
 say "From x@y Fri Oct  2 00:00:00 1993";
 print "a: b\n\n", "x" x 70000, "\n\n";