t/msg_iter: test for X-UNKNOWN charset from Alpine

A long overdue test for behavior established in 2016.

Fixes: 1b28cc7f00a866cb ("view: try assuming UTF-8 for bogus charsets")

diff --git a/MANIFEST b/MANIFEST
index 5acd8531b938fdf80ced8f6cda49c31785e4066e..48df274ea6b7880a967d89cde47e59e081886a64 100644 (file)
--- a/MANIFEST
+++ b/MANIFEST
@@ -299,6 +299,7 @@ t/watch_maildir.t
 t/watch_maildir_v2.t
 t/www_listing.t
 t/www_static.t
+t/x-unknown-alpine.eml
 t/xcpdb-reshard.t
 xt/git-http-backend.t
 xt/git_async_cmp.t

diff --git a/t/msg_iter.t b/t/msg_iter.t
index de9c39fa6742d9b7dff39029be556ca0e3fad55d..e33bfc69df1bcc2d0b00d16424e3f70993d9d419 100644 (file)
--- a/t/msg_iter.t
+++ b/t/msg_iter.t
@@ -4,6 +4,7 @@ use strict;
 use warnings;
 use Test::More;
 use Email::MIME;
+use PublicInbox::Hval qw(ascii_html);
 use_ok('PublicInbox::MsgIter');
 
 {
@@ -58,5 +59,24 @@ use_ok('PublicInbox::MsgIter');
        is(index($raw, '$$$'), -1, 'no unescaped $$$');
 }
 
+{
+       my $f = 't/x-unknown-alpine.eml';
+       my $mime = Email::MIME->new(do {
+               open my $fh, '<', $f or die "open($f): $!";
+               local $/;
+               binmode $fh;
+               <$fh>;
+       });
+       my $raw = '';
+       msg_iter($mime, sub {
+               my ($part, $level, @ex) = @{$_[0]};
+               my ($s, $err) = msg_part_text($part, 'text/plain');
+               $raw .= $s;
+       });
+       like($raw, qr!^\thttps://!ms, 'tab expanded with X-UNKNOWN');
+       like(ascii_html($raw), qr/&#8226; bullet point/s,
+               'got bullet point when X-UNKNOWN assumes UTF-8');
+}
+
 done_testing();
 1;

diff --git a/t/x-unknown-alpine.eml b/t/x-unknown-alpine.eml
new file mode 100644 (file)
index 0000000..75b0bc5
--- /dev/null
+++ b/t/x-unknown-alpine.eml
@@ -0,0 +1,21 @@
+Date:  Sat, 13 Aug 2016 12:14:15 +0200 (CEST)
+From:  Alpine User <a@example.com>
+To: <list@example.com>
+Subject: charset=X-UNKNOWN test
+Message-ID: <alpine.DEB.2.20.1608131214070.4924@example>
+User-Agent: Alpine 2.20 (DEB 67 2015-01-07)
+MIME-Version: 1.0
+Content-Type: multipart/mixed; BOUNDARY="8323329-703494712-1471083256=:4924"
+
+  This message is in MIME format.  The first part should be readable text,
+  while the remaining parts are likely unreadable without MIME-aware tools.
+
+--8323329-703494712-1471083256=:4924
+Content-Type: text/plain; charset=X-UNKNOWN
+Content-Transfer-Encoding: QUOTED-PRINTABLE
+
+=09https://example.com/
+
+  =E2=80=A2 bullet point
+
+--8323329-703494712-1471083256=:4924--