From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net X-Spam-Level: X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,BAYES_00 shortcircuit=no autolearn=ham autolearn_force=no version=3.4.2 Received: from localhost (dcvr.yhbt.net [127.0.0.1]) by dcvr.yhbt.net (Postfix) with ESMTP id A63921F9FF for ; Fri, 12 Feb 2021 07:05:52 +0000 (UTC) From: Eric Wong To: meta@public-inbox.org Subject: [PATCH 3/3] mbox_reader: do not chomp non-blank EOL Date: Fri, 12 Feb 2021 00:05:52 -0700 Message-Id: <20210212070552.13901-4-e@80x24.org> In-Reply-To: <20210212070552.13901-1-e@80x24.org> References: <20210212070552.13901-1-e@80x24.org> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit List-Id: 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. --- lib/PublicInbox/MboxReader.pm | 2 +- t/mbox_reader.t | 22 +++++++++++++++++++++- 2 files changed, 22 insertions(+), 2 deletions(-) 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";