mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-30 05:35:08 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

Issue #4874: Most builtin decoders now reject unicode input.

Browse source
This commit is contained in:
Antoine Pitrou 2009-01-22 10:11:36 +00:00
parent dd01f8f37b
commit 81fabdb437
3 changed files with 47 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

31
Lib/test/test_codecs.py
View file

@ -1475,6 +1475,36 @@ class WithStmtTest(unittest.TestCase):
info.streamwriter, 'strict') as srw:
self.assertEquals(srw.read(), "\xfc")
class TypesTest(unittest.TestCase):
def test_decode_unicode(self):
# Most decoders don't accept unicode input
decoders = [
codecs.utf_7_decode,
codecs.utf_8_decode,
codecs.utf_16_le_decode,
codecs.utf_16_be_decode,
codecs.utf_16_ex_decode,
codecs.utf_32_decode,
codecs.utf_32_le_decode,
codecs.utf_32_be_decode,
codecs.utf_32_ex_decode,
codecs.latin_1_decode,
codecs.ascii_decode,
codecs.charmap_decode,
]
if hasattr(codecs, "mbcs_decode"):
decoders.append(codecs.mbcs_decode)
for decoder in decoders:
self.assertRaises(TypeError, decoder, "xxx")
def test_unicode_escape(self):
# Escape-decoding an unicode string is supported ang gives the same
# result as decoding the equivalent ASCII bytes string.
self.assertEquals(codecs.unicode_escape_decode(r"\u1234"), ("\u1234", 6))
self.assertEquals(codecs.unicode_escape_decode(br"\u1234"), ("\u1234", 6))
self.assertEquals(codecs.raw_unicode_escape_decode(r"\u1234"), ("\u1234", 6))
self.assertEquals(codecs.raw_unicode_escape_decode(br"\u1234"), ("\u1234", 6))
def test_main():
support.run_unittest(
@ -1501,6 +1531,7 @@ def test_main():
BasicUnicodeTest,
CharmapTest,
WithStmtTest,
TypesTest,
)