https://github.com/python/cpython/commit/68098110367bf23fc03cd4a5813c266bd234e6f7 commit: 68098110367bf23fc03cd4a5813c266bd234e6f7 branch: 3.14 author: Miss Islington (bot) <[email protected]> committer: bitdancer <[email protected]> date: 2025-12-24T13:20:05-05:00 summary:
[3.14] Correctly fold unknown-8bit originating from encoded words. (GH-142517) (#143146) The unknown-8bit trick was designed to deal with unknown bytes in an ASCII message, and it works fine for that. However, I also tried to extend it to handle bytes that can't be decoded using the charset specified in an encoded word, and there it fails because there can be other non-ASCII characters that were *successfully* decoded. The fix is simple: do the unknown-8bit encoding using the utf-8 codec. This is especially appropriate since anyone trying to do recovery on an unknown byte string will probably attempt utf-8 first. (cherry picked from commit 1e17ccd030a2285ad53db5952360fffa33a8a877) Co-authored-by: R. David Murray <[email protected]> Co-authored-by: Stan Ulbrych <[email protected]> files: A Misc/NEWS.d/next/Library/2025-12-10-10-00-06.gh-issue-142517.fG4hbe.rst M Lib/email/_encoded_words.py M Lib/test/test_email/test__header_value_parser.py diff --git a/Lib/email/_encoded_words.py b/Lib/email/_encoded_words.py index 6795a606de037e..05a34a4c105233 100644 --- a/Lib/email/_encoded_words.py +++ b/Lib/email/_encoded_words.py @@ -219,7 +219,7 @@ def encode(string, charset='utf-8', encoding=None, lang=''): """ if charset == 'unknown-8bit': - bstring = string.encode('ascii', 'surrogateescape') + bstring = string.encode('utf-8', 'surrogateescape') else: bstring = string.encode(charset) if encoding is None: diff --git a/Lib/test/test_email/test__header_value_parser.py b/Lib/test/test_email/test__header_value_parser.py index f33844910beee4..426ec4644e3096 100644 --- a/Lib/test/test_email/test__header_value_parser.py +++ b/Lib/test/test_email/test__header_value_parser.py @@ -3340,5 +3340,13 @@ def test_fold_unfoldable_element_stealing_whitespace(self): token = parser.get_address_list(text)[0] self._test(token, expected, policy=policy) + def test_encoded_word_with_undecodable_bytes(self): + self._test(parser.get_address_list( + ' =?utf-8?Q?=E5=AE=A2=E6=88=B6=E6=AD=A3=E8=A6=8F=E4=BA=A4=E7?=' + )[0], + ' =?unknown-8bit?b?5a6i5oi25q2j6KaP5Lqk5w==?=\n', + ) + + if __name__ == '__main__': unittest.main() diff --git a/Misc/NEWS.d/next/Library/2025-12-10-10-00-06.gh-issue-142517.fG4hbe.rst b/Misc/NEWS.d/next/Library/2025-12-10-10-00-06.gh-issue-142517.fG4hbe.rst new file mode 100644 index 00000000000000..d58e532ac43ebe --- /dev/null +++ b/Misc/NEWS.d/next/Library/2025-12-10-10-00-06.gh-issue-142517.fG4hbe.rst @@ -0,0 +1,4 @@ +The non-``compat32`` :mod:`email` policies now correctly handle refolding +encoded words that contain bytes that can not be decoded in their specified +character set. Previously this resulted in an encoding exception during +folding. _______________________________________________ Python-checkins mailing list -- [email protected] To unsubscribe send an email to [email protected] https://mail.python.org/mailman3//lists/python-checkins.python.org Member address: [email protected]
