diff options
| author | Serhiy Storchaka <storchaka@gmail.com> | 2015-10-02 13:14:03 +0300 |
|---|---|---|
| committer | Serhiy Storchaka <storchaka@gmail.com> | 2015-10-02 13:14:03 +0300 |
| commit | 29e68edbf47b708c1f7082c2235d82f41e747635 (patch) | |
| tree | 554941fc129b51181ea2aa7799a967a3042ebcec /Lib/test/test_unicode.py | |
| parent | 5dbe245ef238762c8e1100885e8671bf2e089157 (diff) | |
| parent | 58c8f2bb6de115b620cec3cf995f04005573765c (diff) | |
| download | cpython-git-29e68edbf47b708c1f7082c2235d82f41e747635.tar.gz | |
Issue #24848: Fixed bugs in UTF-7 decoding of misformed data:
1. Non-ASCII bytes were accepted after shift sequence.
2. A low surrogate could be emitted in case of error in high surrogate.
3. In some circumstances the '\xfd' character was produced instead of the
replacement character '\ufffd' (due to a bug in _PyUnicodeWriter).
Diffstat (limited to 'Lib/test/test_unicode.py')
| -rw-r--r-- | Lib/test/test_unicode.py | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/Lib/test/test_unicode.py b/Lib/test/test_unicode.py index 3fcb590f69..1429a6d545 100644 --- a/Lib/test/test_unicode.py +++ b/Lib/test/test_unicode.py @@ -1553,7 +1553,7 @@ class UnicodeTest(string_tests.CommonTest, self.assertEqual(b'+2AHab9ze-'.decode('utf-7'), '\uD801\U000abcde') # Issue #2242: crash on some Windows/MSVC versions - self.assertEqual(b'+\xc1'.decode('utf-7'), '\xc1') + self.assertEqual(b'+\xc1'.decode('utf-7', 'ignore'), '') # Direct encoded characters set_d = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789'(),-./:?" @@ -1995,6 +1995,7 @@ class UnicodeTest(string_tests.CommonTest, self.assertRaises(UnicodeError, str, b'Andr\202 x', 'ascii', 'strict') self.assertEqual(str(b'Andr\202 x', 'ascii', 'ignore'), "Andr x") self.assertEqual(str(b'Andr\202 x', 'ascii', 'replace'), 'Andr\uFFFD x') + self.assertEqual(str(b'\202 x', 'ascii', 'replace'), '\uFFFD x') # Error handling (unknown character names) self.assertEqual(b"\\N{foo}xx".decode("unicode-escape", "ignore"), "xx") |