diff options
| author | Neal Norwitz <nnorwitz@gmail.com> | 2005-09-30 04:46:49 (GMT) |
|---|---|---|
| committer | Neal Norwitz <nnorwitz@gmail.com> | 2005-09-30 04:46:49 (GMT) |
| commit | 484d9a409a94e719329b41edaed38c1b16b8de7d (patch) | |
| tree | a95cc808b2ce9df46b41a6ee8b45fb90ef00a68e /Lib/test/test_minidom.py | |
| parent | aa93517de8b5e2b41644a22ae81ddec4f5d72991 (diff) | |
| download | cpython-484d9a409a94e719329b41edaed38c1b16b8de7d.zip cpython-484d9a409a94e719329b41edaed38c1b16b8de7d.tar.gz cpython-484d9a409a94e719329b41edaed38c1b16b8de7d.tar.bz2 | |
Patch #1309009, Fix segfault in pyexpat when the XML document is
in latin_1, but Python incorrectly assumes it is in UTF-8 format
Will backport.
Diffstat (limited to 'Lib/test/test_minidom.py')
| -rw-r--r-- | Lib/test/test_minidom.py | 9 |
1 files changed, 9 insertions, 0 deletions
diff --git a/Lib/test/test_minidom.py b/Lib/test/test_minidom.py index 3154fbf..8b4c715 100644 --- a/Lib/test/test_minidom.py +++ b/Lib/test/test_minidom.py @@ -889,6 +889,15 @@ def testEncodings(): and doc.toxml('utf-8') == '<?xml version="1.0" encoding="utf-8"?><foo>\xe2\x82\xac</foo>' and doc.toxml('iso-8859-15') == '<?xml version="1.0" encoding="iso-8859-15"?><foo>\xa4</foo>', "testEncodings - encoding EURO SIGN") + + # Verify that character decoding errors throw exceptions instead of crashing + try: + doc = parseString('<fran\xe7ais>Comment \xe7a va ? Tr\xe8s bien ?</fran\xe7ais>') + except UnicodeDecodeError: + pass + else: + print 'parsing with bad encoding should raise a UnicodeDecodeError' + doc.unlink() class UserDataHandler: |