Issue #28992: Use bytes.fromhex().

This commit is contained in:
Serhiy Storchaka 2016-12-21 12:59:28 +02:00
parent 47bdc40352
commit 8cbd3df3ce
4 changed files with 7 additions and 10 deletions

View File

@ -62,7 +62,7 @@ __all__ = ['decode_q',
# regex based decoder. # regex based decoder.
_q_byte_subber = functools.partial(re.compile(br'=([a-fA-F0-9]{2})').sub, _q_byte_subber = functools.partial(re.compile(br'=([a-fA-F0-9]{2})').sub,
lambda m: bytes([int(m.group(1), 16)])) lambda m: bytes.fromhex(m.group(1)))
def decode_q(encoded): def decode_q(encoded):
encoded = encoded.replace(b'_', b' ') encoded = encoded.replace(b'_', b' ')

View File

@ -338,7 +338,7 @@ class TestBase_Mapping(unittest.TestCase):
uc = re.findall('<a u="([A-F0-9]{4})" b="([0-9A-F ]+)"/>', ucmdata) uc = re.findall('<a u="([A-F0-9]{4})" b="([0-9A-F ]+)"/>', ucmdata)
for uni, coded in uc: for uni, coded in uc:
unich = chr(int(uni, 16)) unich = chr(int(uni, 16))
codech = bytes(int(c, 16) for c in coded.split()) codech = bytes.fromhex(coded)
self._testpoint(codech, unich) self._testpoint(codech, unich)
def test_mapping_supplemental(self): def test_mapping_supplemental(self):

View File

@ -1793,9 +1793,6 @@ class UnicodeTest(string_tests.CommonTest,
self.assertEqual(seq.decode('utf-8', 'ignore'), self.assertEqual(seq.decode('utf-8', 'ignore'),
res.replace('\uFFFD', '')) res.replace('\uFFFD', ''))
def to_bytestring(self, seq):
return bytes(int(c, 16) for c in seq.split())
def assertCorrectUTF8Decoding(self, seq, res, err): def assertCorrectUTF8Decoding(self, seq, res, err):
""" """
Check that an invalid UTF-8 sequence raises a UnicodeDecodeError when Check that an invalid UTF-8 sequence raises a UnicodeDecodeError when
@ -1851,7 +1848,7 @@ class UnicodeTest(string_tests.CommonTest,
] ]
FFFD = '\ufffd' FFFD = '\ufffd'
for seq in sequences: for seq in sequences:
self.assertCorrectUTF8Decoding(self.to_bytestring(seq), '\ufffd', self.assertCorrectUTF8Decoding(bytes.fromhex(seq), '\ufffd',
'unexpected end of data') 'unexpected end of data')
def test_invalid_cb_for_2bytes_seq(self): def test_invalid_cb_for_2bytes_seq(self):
@ -1873,7 +1870,7 @@ class UnicodeTest(string_tests.CommonTest,
('DF C0', FFFDx2), ('DF FF', FFFDx2), ('DF C0', FFFDx2), ('DF FF', FFFDx2),
] ]
for seq, res in sequences: for seq, res in sequences:
self.assertCorrectUTF8Decoding(self.to_bytestring(seq), res, self.assertCorrectUTF8Decoding(bytes.fromhex(seq), res,
'invalid continuation byte') 'invalid continuation byte')
def test_invalid_cb_for_3bytes_seq(self): def test_invalid_cb_for_3bytes_seq(self):
@ -1931,7 +1928,7 @@ class UnicodeTest(string_tests.CommonTest,
('EF BF C0', FFFDx2), ('EF BF FF', FFFDx2), ('EF BF C0', FFFDx2), ('EF BF FF', FFFDx2),
] ]
for seq, res in sequences: for seq, res in sequences:
self.assertCorrectUTF8Decoding(self.to_bytestring(seq), res, self.assertCorrectUTF8Decoding(bytes.fromhex(seq), res,
'invalid continuation byte') 'invalid continuation byte')
def test_invalid_cb_for_4bytes_seq(self): def test_invalid_cb_for_4bytes_seq(self):
@ -2010,7 +2007,7 @@ class UnicodeTest(string_tests.CommonTest,
('F4 8F BF C0', FFFDx2), ('F4 8F BF FF', FFFDx2) ('F4 8F BF C0', FFFDx2), ('F4 8F BF FF', FFFDx2)
] ]
for seq, res in sequences: for seq, res in sequences:
self.assertCorrectUTF8Decoding(self.to_bytestring(seq), res, self.assertCorrectUTF8Decoding(bytes.fromhex(seq), res,
'invalid continuation byte') 'invalid continuation byte')
def test_codecs_idna(self): def test_codecs_idna(self):

View File

@ -574,7 +574,7 @@ def unquote_to_bytes(string):
# if the function is never called # if the function is never called
global _hextobyte global _hextobyte
if _hextobyte is None: if _hextobyte is None:
_hextobyte = {(a + b).encode(): bytes([int(a + b, 16)]) _hextobyte = {(a + b).encode(): bytes.fromhex(a + b)
for a in _hexdig for b in _hexdig} for a in _hexdig for b in _hexdig}
for item in bits[1:]: for item in bits[1:]:
try: try: