From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <e@80x24.org>
X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net
X-Spam-Level: 
X-Spam-ASN:  
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 5065F1FA01
	for <meta@public-inbox.org>; Tue, 26 Oct 2021 10:35:58 +0000 (UTC)
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 3/9] eml: keep body if no headers are found
Date: Tue, 26 Oct 2021 10:35:51 +0000
Message-Id: <20211026103557.2738-4-e@80x24.org>
In-Reply-To: <20211026103557.2738-1-e@80x24.org>
References: <20211026103557.2738-1-e@80x24.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
List-Id: <meta.public-inbox.org>

This easily allows us to treat "git diff" output as header-less
"messages" for commands such as "lei p2q".
---
 lib/PublicInbox/Eml.pm |  7 ++++---
 t/eml.t                | 11 +++++++++++
 t/mbox_reader.t        |  6 +++++-
 3 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/lib/PublicInbox/Eml.pm b/lib/PublicInbox/Eml.pm
index 3c681ba5bc2e..485f637a3e7b 100644
--- a/lib/PublicInbox/Eml.pm
+++ b/lib/PublicInbox/Eml.pm
@@ -122,9 +122,10 @@ sub new {
 		my $hdr = substr($$ref, 0, $header_size_limit + 1);
 		hdr_truncate($hdr) if length($hdr) > $header_size_limit;
 		bless { hdr => \$hdr, crlf => $1 }, __PACKAGE__;
-	} else { # nothing useful
-		my $hdr = $$ref = '';
-		bless { hdr => \$hdr, crlf => "\n" }, __PACKAGE__;
+	} else { # just a body w/o header?
+		my $hdr = '';
+		my $eol = ($$ref =~ /(\r?\n)/) ? $1 : "\n";
+		bless { hdr => \$hdr, crlf => $eol, bdy => $ref }, __PACKAGE__;
 	}
 }
 
diff --git a/t/eml.t b/t/eml.t
index 0cf48f225a45..2d8993a51075 100644
--- a/t/eml.t
+++ b/t/eml.t
@@ -216,6 +216,17 @@ if ('one newline before headers') {
 	is($eml->body, "");
 }
 
+if ('body only') {
+	my $str = <<EOM;
+--- a/lib/PublicInbox/Eml.pm
++++ b/lib/PublicInbox/Eml.pm
+@@ -122,9 +122,10 @@ sub new {
+\x20
+EOM
+	my $eml = PublicInbox::Eml->new($str);
+	is($eml->body, $str, 'body-only accepted');
+}
+
 for my $cls (@classes) { # XXX: matching E::M, but not sure about this
 	my $s = <<EOF;
 Content-Type: multipart/mixed; boundary="b"
diff --git a/t/mbox_reader.t b/t/mbox_reader.t
index e5f57d7bcba3..87e8f397662c 100644
--- a/t/mbox_reader.t
+++ b/t/mbox_reader.t
@@ -138,7 +138,11 @@ EOM
 		PublicInbox::MboxReader->$m($fh, sub {
 			push @x, $_[0]->as_string
 		});
-		is_deeply(\@x, [], "messages in invalid $m");
+		if ($m =~ /\Amboxcl/) {
+			is_deeply(\@x, [], "messages in invalid $m");
+		} else {
+			is_deeply(\@x, [ "\n$html" ], "body-only $m");
+		}
 		is_deeply([grep(!/^W: leftover/, @w)], [],
 			"no extra warnings besides leftover ($m)");
 	}