Aldwin Pollefeyt <aldwinald...@gmail.com> added the comment:
Changing everything to utf-8 breaks a lot of tests, so here a less invasive
solution?
diff --git a/Lib/email/header.py b/Lib/email/header.py
index 4ab0032bc6..1e71eeae7f 100644
--- a/Lib/email/header.py
+++ b/Lib/email/header.py
@@ -136,7 +136,14 @@ def decode_header(header):
last_word = last_charset = None
for word, charset in decoded_words:
if isinstance(word, str):
- word = bytes(word, 'raw-unicode-escape')
+ word_tmp = bytes(word, 'raw-unicode-escape')
+ input_charset = charset or 'us-ascii'
+ try:
+ _ = word_tmp.decode(input_charset, errors='strict')
+ word = word_tmp
+ except UnicodeDecodeError:
+ word = str(word).encode('utf-8')
+ charset = 'utf-8'
if last_word is None:
last_word = word
last_charset = charset
----------
_______________________________________
Python tracker <rep...@bugs.python.org>
<https://bugs.python.org/issue37532>
_______________________________________
_______________________________________________
Python-bugs-list mailing list
Unsubscribe:
https://mail.python.org/mailman/options/python-bugs-list/archive%40mail-archive.com
