gh-111089: PyUnicode_AsUTF8() now raises on embedded NUL (#111091)

* PyUnicode_AsUTF8() now raises an exception if the string contains
  embedded null characters.
* Update related C API tests (test_capi.test_unicode).
* type_new_set_doc() uses PyUnicode_AsUTF8AndSize() to silently
  truncate doc containing null bytes.

Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
This commit is contained in:
Victor Stinner 2023-10-20 17:59:29 +02:00 committed by GitHub
parent 59ea0f523e
commit d731579bfb
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
8 changed files with 49 additions and 25 deletions

View file

@ -882,7 +882,10 @@ class CAPITest(unittest.TestCase):
self.assertEqual(unicode_asutf8('abc', 4), b'abc\0')
self.assertEqual(unicode_asutf8('абв', 7), b'\xd0\xb0\xd0\xb1\xd0\xb2\0')
self.assertEqual(unicode_asutf8('\U0001f600', 5), b'\xf0\x9f\x98\x80\0')
self.assertEqual(unicode_asutf8('abc\0def', 8), b'abc\0def\0')
# disallow embedded null characters
self.assertRaises(ValueError, unicode_asutf8, 'abc\0', 0)
self.assertRaises(ValueError, unicode_asutf8, 'abc\0def', 0)
self.assertRaises(UnicodeEncodeError, unicode_asutf8, '\ud8ff', 0)
self.assertRaises(TypeError, unicode_asutf8, b'abc', 0)