mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-07-19 01:05:26 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

Issue #24848: Fixed bugs in UTF-7 decoding of misformed data:

Browse source 
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).
This commit is contained in:
Serhiy Storchaka 2015-10-02 13:13:14 +03:00
commit 58c8f2bb6d
4 changed files with 75 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

3
Lib/test/test_unicode.py
View file

@ -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")