From d79c57846950e31964ffadcd8034c44667c0fbaf Mon Sep 17 00:00:00 2001
From: Simon Ser <contact@emersion.fr>
Date: Tue, 15 Dec 2020 10:37:09 +0000
Subject: [PATCH] dim: fix handling of 8-bit non-UTF-8 messages
Python's open() function will return a file object that decodes input
bytes to an UTF-8 string. Python assumes all files are UTF-8 by default
(unless an explicit encoding param is passed).
This works fine with 7-bit and UTF-8 messages. However, when a message
uses a 8-bit Content-Transfer-Encoding and a non-UTF-8 charset (such as
iso-8859-1), Python will error out.
To prevent this, open the file in binary mode to prevent Python from
doing any charset conversion under-the-hood.
Signed-off-by: Simon Ser <contact@emersion.fr>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
dim | 12 +++++++-----
1 file changed, 7 insertions(+), 5 deletions(-)
diff --git a/dim b/dim
index ac53ade..f4366ea 100755
--- a/dim
+++ b/dim
@@ -443,9 +443,11 @@ function check_dim_config
message_get_id ()
{
$dim_python <<EOF
-from email.parser import Parser
-headers = Parser().parse(open('$1', 'r'))
-message_id = headers['message-id']
+import email
+
+f = open('$1', 'rb')
+msg = email.message_from_binary_file(f)
+message_id = msg['message-id']
if message_id is not None:
print(message_id.strip('<> \n'))
EOF
@@ -457,12 +459,12 @@ message_print_body ()
import email
def print_msg(file):
- msg = email.message_from_file(file)
+ msg = email.message_from_binary_file(file)
for part in msg.walk():
if part.get_content_type() == 'text/plain':
print(part.get_payload(decode=True).decode(part.get_content_charset(failobj='us-ascii'), 'replace'))
-print_msg(open('$1', 'r'))
+print_msg(open('$1', 'rb'))
EOF
}
--
GitLab