Skip to content

[3.12] gh-120380: fix Python implementation of pickle.Pickler for bytes and bytearray objects in protocol version 5. (GH-120422) #120833

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jun 26, 2024
+81 −21
Merged

[3.12] gh-120380: fix Python implementation of pickle.Pickler for bytes and bytearray objects in protocol version 5. (GH-120422) #120833

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
50 changes: 35 additions & 15 deletions Lib/pickle.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -780,14 +780,10 @@ def save_float(self, obj):
self.write(FLOAT + repr(obj).encode("ascii") + b'\n')
dispatch[float] = save_float

def save_bytes(self, obj):
if self.proto < 3:
if not obj: # bytes object is empty
self.save_reduce(bytes, (), obj=obj)
else:
self.save_reduce(codecs.encode,
(str(obj, 'latin1'), 'latin1'), obj=obj)
return
def _save_bytes_no_memo(self, obj):
# helper for writing bytes objects for protocol >= 3
# without memoizing them
assert self.proto >= 3
n = len(obj)
if n <= 0xff:
self.write(SHORT_BINBYTES + pack("<B", n) + obj)
Expand All @@ -797,21 +793,37 @@ def save_bytes(self, obj):
self._write_large_bytes(BINBYTES + pack("<I", n), obj)
else:
self.write(BINBYTES + pack("<I", n) + obj)

def save_bytes(self, obj):
if self.proto < 3:
if not obj: # bytes object is empty
self.save_reduce(bytes, (), obj=obj)
else:
self.save_reduce(codecs.encode,
(str(obj, 'latin1'), 'latin1'), obj=obj)
return
self._save_bytes_no_memo(obj)
self.memoize(obj)
dispatch[bytes] = save_bytes

def _save_bytearray_no_memo(self, obj):
# helper for writing bytearray objects for protocol >= 5
# without memoizing them
assert self.proto >= 5
n = len(obj)
if n >= self.framer._FRAME_SIZE_TARGET:
self._write_large_bytes(BYTEARRAY8 + pack("<Q", n), obj)
else:
self.write(BYTEARRAY8 + pack("<Q", n) + obj)

def save_bytearray(self, obj):
if self.proto < 5:
if not obj: # bytearray is empty
self.save_reduce(bytearray, (), obj=obj)
else:
self.save_reduce(bytearray, (bytes(obj),), obj=obj)
return
n = len(obj)
if n >= self.framer._FRAME_SIZE_TARGET:
self._write_large_bytes(BYTEARRAY8 + pack("<Q", n), obj)
else:
self.write(BYTEARRAY8 + pack("<Q", n) + obj)
self._save_bytearray_no_memo(obj)
self.memoize(obj)
dispatch[bytearray] = save_bytearray

Expand All @@ -830,10 +842,18 @@ def save_picklebuffer(self, obj):
if in_band:
# Write data in-band
# XXX The C implementation avoids a copy here
buf = m.tobytes()
in_memo = id(buf) in self.memo
if m.readonly:
self.save_bytes(m.tobytes())
if in_memo:
self._save_bytes_no_memo(buf)
else:
self.save_bytes(buf)
else:
self.save_bytearray(m.tobytes())
if in_memo:
self._save_bytearray_no_memo(buf)
else:
self.save_bytearray(buf)
else:
# Write data out-of-band
self.write(NEXT_BUFFER)
Expand Down
49 changes: 43 additions & 6 deletions Lib/test/pickletester.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1845,6 +1845,25 @@ def test_bytes(self):
p = self.dumps(s, proto)
self.assert_is_copy(s, self.loads(p))

def test_bytes_memoization(self):
for proto in protocols:
for array_type in [bytes, ZeroCopyBytes]:
for s in b'', b'xyz', b'xyz'*100:
with self.subTest(proto=proto, array_type=array_type, s=s, independent=False):
b = array_type(s)
p = self.dumps((b, b), proto)
x, y = self.loads(p)
self.assertIs(x, y)
self.assert_is_copy((b, b), (x, y))

with self.subTest(proto=proto, array_type=array_type, s=s, independent=True):
b1, b2 = array_type(s), array_type(s)
p = self.dumps((b1, b2), proto)
# Note that (b1, b2) = self.loads(p) might have identical
# components, i.e., b1 is b2, but this is not always the
# case if the content is large (equality still holds).
self.assert_is_copy((b1, b2), self.loads(p))

def test_bytearray(self):
for proto in protocols:
for s in b'', b'xyz', b'xyz'*100:
Expand All @@ -1864,13 +1883,31 @@ def test_bytearray(self):
self.assertNotIn(b'bytearray', p)
self.assertTrue(opcode_in_pickle(pickle.BYTEARRAY8, p))

def test_bytearray_memoization_bug(self):
def test_bytearray_memoization(self):
for proto in protocols:
for s in b'', b'xyz', b'xyz'*100:
b = bytearray(s)
p = self.dumps((b, b), proto)
b1, b2 = self.loads(p)
self.assertIs(b1, b2)
for array_type in [bytearray, ZeroCopyBytearray]:
for s in b'', b'xyz', b'xyz'*100:
with self.subTest(proto=proto, array_type=array_type, s=s, independent=False):
b = array_type(s)
p = self.dumps((b, b), proto)
b1, b2 = self.loads(p)
self.assertIs(b1, b2)

with self.subTest(proto=proto, array_type=array_type, s=s, independent=True):
b1a, b2a = array_type(s), array_type(s)
# Unlike bytes, equal but independent bytearray objects are
# never identical.
self.assertIsNot(b1a, b2a)

p = self.dumps((b1a, b2a), proto)
b1b, b2b = self.loads(p)
self.assertIsNot(b1b, b2b)

self.assertIsNot(b1a, b1b)
self.assert_is_copy(b1a, b1b)

self.assertIsNot(b2a, b2b)
self.assert_is_copy(b2a, b2b)

def test_ints(self):
for proto in protocols:
Expand Down
3 changes: 3 additions & 0 deletions Misc/NEWS.d/next/Core and Builtins/2024-06-12-18-23-15.gh-issue-120380.edtqjq.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
Fix Python implementation of :class:`pickle.Pickler` for :class:`bytes` and
:class:`bytearray` objects when using protocol version 5. Patch by Bénédikt
Tran.
Loading