[3.11] gh-95782: Fix io.BufferedReader.tell() etc. being able to return offsets < 0 (GH-99709) (GH-115600)

lseek() always returns 0 for character pseudo-devices like
`/dev/urandom` (for other non-regular files, e.g. `/dev/stdin`, it
always returns -1, to which CPython reacts by raising appropriate
exceptions). They are thus technically seekable despite not having seek
semantics.

When calling read() on e.g. an instance of `io.BufferedReader` that
wraps such a file, `BufferedReader` reads ahead, filling its buffer,
creating a discrepancy between the number of bytes read and the internal
`tell()` always returning 0, which previously resulted in e.g.
`BufferedReader.tell()` or `BufferedReader.seek()` being able to return
positions < 0 even though these are supposed to be always >= 0.

Invariably keep the return value non-negative by returning
max(former_return_value, 0) instead, and add some corresponding tests.
(cherry picked from commit 26800cf25a)

Co-authored-by: 6t8k <58048945+6t8k@users.noreply.github.com>
This commit is contained in:
Miss Islington (bot) 2024-02-17 13:55:43 +01:00 committed by GitHub
parent 2c39d00a56
commit a5eaa14584
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 62 additions and 3 deletions

View file

@ -263,6 +263,27 @@ class PyMockUnseekableIO(MockUnseekableIO, pyio.BytesIO):
UnsupportedOperation = pyio.UnsupportedOperation
class MockCharPseudoDevFileIO(MockFileIO):
# GH-95782
# ftruncate() does not work on these special files (and CPython then raises
# appropriate exceptions), so truncate() does not have to be accounted for
# here.
def __init__(self, data):
super().__init__(data)
def seek(self, *args):
return 0
def tell(self, *args):
return 0
class CMockCharPseudoDevFileIO(MockCharPseudoDevFileIO, io.BytesIO):
pass
class PyMockCharPseudoDevFileIO(MockCharPseudoDevFileIO, pyio.BytesIO):
pass
class MockNonBlockWriterIO:
def __init__(self):
@ -1556,6 +1577,30 @@ class BufferedReaderTest(unittest.TestCase, CommonBufferedTests):
self.assertRaises(self.UnsupportedOperation, bufio.truncate)
self.assertRaises(self.UnsupportedOperation, bufio.truncate, 0)
def test_tell_character_device_file(self):
# GH-95782
# For the (former) bug in BufferedIO to manifest, the wrapped IO obj
# must be able to produce at least 2 bytes.
raw = self.MockCharPseudoDevFileIO(b"12")
buf = self.tp(raw)
self.assertEqual(buf.tell(), 0)
self.assertEqual(buf.read(1), b"1")
self.assertEqual(buf.tell(), 0)
def test_seek_character_device_file(self):
raw = self.MockCharPseudoDevFileIO(b"12")
buf = self.tp(raw)
self.assertEqual(buf.seek(0, io.SEEK_CUR), 0)
self.assertEqual(buf.seek(1, io.SEEK_SET), 0)
self.assertEqual(buf.seek(0, io.SEEK_CUR), 0)
self.assertEqual(buf.read(1), b"1")
# In the C implementation, tell() sets the BufferedIO's abs_pos to 0,
# which means that the next seek() could return a negative offset if it
# does not sanity-check:
self.assertEqual(buf.tell(), 0)
self.assertEqual(buf.seek(0, io.SEEK_CUR), 0)
class CBufferedReaderTest(BufferedReaderTest, SizeofTest):
tp = io.BufferedReader
@ -4790,7 +4835,7 @@ def load_tests(loader, tests, pattern):
# classes in the __dict__ of each test.
mocks = (MockRawIO, MisbehavedRawIO, MockFileIO, CloseFailureIO,
MockNonBlockWriterIO, MockUnseekableIO, MockRawIOWithoutRead,
SlowFlushRawIO)
SlowFlushRawIO, MockCharPseudoDevFileIO)
all_members = io.__all__
c_io_ns = {name : getattr(io, name) for name in all_members}
py_io_ns = {name : getattr(pyio, name) for name in all_members}