Skip to content

[3.15] gh-150771: Fix email serialization for shift_jis and euc-jp (GH-151120) #151541

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
serhiy-storchaka merged 1 commit into from
Jun 16, 2026
+46 −1
Merged

[3.15] gh-150771: Fix email serialization for shift_jis and euc-jp (GH-151120) #151541

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion Lib/email/contentmanager.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -174,7 +174,8 @@ def set_text_content(msg, string, subtype="plain", charset='utf-8', cte=None,
params=None, headers=None):
_prepare_set(msg, 'text', subtype, headers)

charset = email.charset.Charset(charset).input_charset
cs = email.charset.Charset(charset)
charset = cs.output_charset
cte, payload = _encode_text(string, charset, cte, msg.policy)
msg.set_payload(payload)
msg.set_param('charset', charset, replace=True)
Expand Down
40 changes: 40 additions & 0 deletions Lib/test/test_email/test_contentmanager.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -362,6 +362,46 @@ def test_set_text_charset_cp949(self):
self.assertEqual(m.get_payload(decode=True), content.encode('ks_c_5601-1987'))
self.assertEqual(m.get_content(), content)

def test_set_text_charset_shift_jis(self):
m = self._make_message()
content = "\u65e5\u672c\u8a9e\n"
raw_data_manager.set_content(m, content, charset='shift_jis')
self.assertEqual(m['Content-Type'], 'text/plain; charset="iso-2022-jp"')
self.assertEqual(m.get_payload(decode=True), content.encode('iso-2022-jp'))
self.assertEqual(m.get_content(), content)
self.assertEqual(str(m), textwrap.dedent("""\
Content-Type: text/plain; charset="iso-2022-jp"
Content-Transfer-Encoding: 7bit

\x1b$BF|K\\8l\x1b(B
"""))
self.assertEqual(bytes(m), textwrap.dedent("""\
Content-Type: text/plain; charset="iso-2022-jp"
Content-Transfer-Encoding: 7bit

\u65e5\u672c\u8a9e
""").encode('iso-2022-jp'))

def test_set_text_charset_euc_jp(self):
m = self._make_message()
content = "\u65e5\u672c\u8a9e\n"
raw_data_manager.set_content(m, content, charset='euc-jp')
self.assertEqual(m['Content-Type'], 'text/plain; charset="iso-2022-jp"')
self.assertEqual(m.get_payload(decode=True), content.encode('iso-2022-jp'))
self.assertEqual(m.get_content(), content)
self.assertEqual(str(m), textwrap.dedent("""\
Content-Type: text/plain; charset="iso-2022-jp"
Content-Transfer-Encoding: 7bit

\x1b$BF|K\\8l\x1b(B
"""))
self.assertEqual(bytes(m), textwrap.dedent("""\
Content-Type: text/plain; charset="iso-2022-jp"
Content-Transfer-Encoding: 7bit

\u65e5\u672c\u8a9e
""").encode('iso-2022-jp'))

def test_set_text_plain_long_line_heuristics(self):
m = self._make_message()
content = ("Simple but long message that is over 78 characters"
Expand Down
4 changes: 4 additions & 0 deletions Misc/NEWS.d/next/Library/2026-06-09-12-00-00.gh-issue-150771.K7mNx2.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
Fix :mod:`email` messages created with ``shift_jis`` or ``euc-jp`` charsets.
``set_content()`` now stores the payload using the output charset
(``iso-2022-jp``) so printing the message no longer raises
:exc:`UnicodeEncodeError`.
Loading