diff options
| author | R David Murray <rdmurray@bitdance.com> | 2011-06-18 16:57:28 (GMT) |
|---|---|---|
| committer | R David Murray <rdmurray@bitdance.com> | 2011-06-18 16:57:28 (GMT) |
| commit | e5e366c856b677d568b4ee35194ed9b8c7d4bbb4 (patch) | |
| tree | a3ae5b34dc67dccb52939e23e0f99c03b8aa2690 /Lib/email/header.py | |
| parent | 6bdb1769dcd1a95a7f6fa7d98d05e835be931466 (diff) | |
| download | cpython-e5e366c856b677d568b4ee35194ed9b8c7d4bbb4.zip cpython-e5e366c856b677d568b4ee35194ed9b8c7d4bbb4.tar.gz cpython-e5e366c856b677d568b4ee35194ed9b8c7d4bbb4.tar.bz2 | |
#11584: make Header and make_header handle binary unknown-8bit input
Analogous to the decode_header fix, this fix makes Header.append and
make_header correctly handle the unknown-8bit charset introduced by email5.1,
when the input to them is binary strings. Previous to this fix the
make_header(decode_header(x)) == x invariant was broken in the face of the
unknown-8bit charset.
Diffstat (limited to 'Lib/email/header.py')
| -rw-r--r-- | Lib/email/header.py | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/Lib/email/header.py b/Lib/email/header.py index 0670885..2e687b7 100644 --- a/Lib/email/header.py +++ b/Lib/email/header.py @@ -275,7 +275,10 @@ class Header: charset = Charset(charset) if not isinstance(s, str): input_charset = charset.input_codec or 'us-ascii' - s = s.decode(input_charset, errors) + if input_charset == _charset.UNKNOWN8BIT: + s = s.decode('us-ascii', 'surrogateescape') + else: + s = s.decode(input_charset, errors) # Ensure that the bytes we're storing can be decoded to the output # character set, otherwise an early error is thrown. output_charset = charset.output_codec or 'us-ascii' |