mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-09-12 19:57:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

[3.11] gh-96189: Fix test_invalid_utf8 on a number of build bots (GH-96190) (#96218)

Browse source 
Co-authored-by: Michael Droettboom <mdboom@gmail.com>
This commit is contained in:
Miss Islington (bot) 2022-08-23 15:28:44 -07:00 • committed by GitHub
parent d7eea0f1ca
commit c01fc9d30a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 38 additions and 38 deletions
Download patch file Download diff file Expand all files Collapse all files

76
Lib/test/test_source_encoding.py
View file

@ -239,50 +239,50 @@ class UTF8ValidatorTest(unittest.TestCase):
# it's an otherwise valid Python source file. # it's an otherwise valid Python source file.
template = b'"%s"\n' template = b'"%s"\n'
with tempfile.TemporaryDirectory() as tmpd: fn = TESTFN
fn = os.path.join(tmpd, 'test.py') self.addCleanup(unlink, fn)
def check(content): def check(content):
with open(fn, 'wb') as fp: with open(fn, 'wb') as fp:
fp.write(template % content) fp.write(template % content)
script_helper.assert_python_failure(fn) script_helper.assert_python_failure(fn)
# continuation bytes in a sequence of 2, 3, or 4 bytes # continuation bytes in a sequence of 2, 3, or 4 bytes
continuation_bytes = [bytes([x]) for x in range(0x80, 0xC0)] continuation_bytes = [bytes([x]) for x in range(0x80, 0xC0)]
# start bytes of a 2-byte sequence equivalent to code points < 0x7F # start bytes of a 2-byte sequence equivalent to code points < 0x7F
invalid_2B_seq_start_bytes = [bytes([x]) for x in range(0xC0, 0xC2)] invalid_2B_seq_start_bytes = [bytes([x]) for x in range(0xC0, 0xC2)]
# start bytes of a 4-byte sequence equivalent to code points > 0x10FFFF # start bytes of a 4-byte sequence equivalent to code points > 0x10FFFF
invalid_4B_seq_start_bytes = [bytes([x]) for x in range(0xF5, 0xF8)] invalid_4B_seq_start_bytes = [bytes([x]) for x in range(0xF5, 0xF8)]
invalid_start_bytes = ( invalid_start_bytes = (
continuation_bytes + invalid_2B_seq_start_bytes + continuation_bytes + invalid_2B_seq_start_bytes +
invalid_4B_seq_start_bytes + [bytes([x]) for x in range(0xF7, 0x100)] invalid_4B_seq_start_bytes + [bytes([x]) for x in range(0xF7, 0x100)]
) )
for byte in invalid_start_bytes: for byte in invalid_start_bytes:
check(byte) check(byte)
for sb in invalid_2B_seq_start_bytes: for sb in invalid_2B_seq_start_bytes:
for cb in continuation_bytes: for cb in continuation_bytes:
check(sb + cb) check(sb + cb)
for sb in invalid_4B_seq_start_bytes: for sb in invalid_4B_seq_start_bytes:
for cb1 in continuation_bytes[:3]: for cb1 in continuation_bytes[:3]:
for cb3 in continuation_bytes[:3]: for cb3 in continuation_bytes[:3]:
check(sb+cb1+b'\x80'+cb3) check(sb+cb1+b'\x80'+cb3)
for cb in [bytes([x]) for x in range(0x80, 0xA0)]: for cb in [bytes([x]) for x in range(0x80, 0xA0)]:
check(b'\xE0'+cb+b'\x80') check(b'\xE0'+cb+b'\x80')
check(b'\xE0'+cb+b'\xBF') check(b'\xE0'+cb+b'\xBF')
# surrogates # surrogates
for cb in [bytes([x]) for x in range(0xA0, 0xC0)]: for cb in [bytes([x]) for x in range(0xA0, 0xC0)]:
check(b'\xED'+cb+b'\x80') check(b'\xED'+cb+b'\x80')
check(b'\xED'+cb+b'\xBF') check(b'\xED'+cb+b'\xBF')
for cb in [bytes([x]) for x in range(0x80, 0x90)]: for cb in [bytes([x]) for x in range(0x80, 0x90)]:
check(b'\xF0'+cb+b'\x80\x80') check(b'\xF0'+cb+b'\x80\x80')
check(b'\xF0'+cb+b'\xBF\xBF') check(b'\xF0'+cb+b'\xBF\xBF')
for cb in [bytes([x]) for x in range(0x90, 0xC0)]: for cb in [bytes([x]) for x in range(0x90, 0xC0)]:
check(b'\xF4'+cb+b'\x80\x80') check(b'\xF4'+cb+b'\x80\x80')
check(b'\xF4'+cb+b'\xBF\xBF') check(b'\xF4'+cb+b'\xBF\xBF')
class BytesSourceEncodingTest(AbstractSourceEncodingTest, unittest.TestCase): class BytesSourceEncodingTest(AbstractSourceEncodingTest, unittest.TestCase):