Skip to content

perf: use pre-allocated constant for null sentinel in collection serialization #763

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

Draft
mykaul wants to merge 1 commit into
base: master
Choose a base branch
from
Draft

perf: use pre-allocated constant for null sentinel in collection serialization #763

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
11 changes: 6 additions & 5 deletions cassandra/cqltypes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,6 +52,7 @@
from cassandra import util

_little_endian_flag = 1 # we always serialize LE
_INT32_NULL = int32_pack(-1) # pre-allocated null sentinel for collection serialization
import ipaddress

apache_cassandra_type_prefix = 'org.apache.cassandra.db.marshal.'
Expand Down Expand Up @@ -841,7 +842,7 @@ def serialize_safe(cls, items, protocol_version):
inner_proto = max(3, protocol_version)
for item in items:
if item is None:
buf.write(int32_pack(-1))
buf.write(_INT32_NULL)
else:
itembytes = subtype.to_binary(item, inner_proto)
buf.write(int32_pack(len(itembytes)))
Expand Down Expand Up @@ -912,13 +913,13 @@ def serialize_safe(cls, themap, protocol_version):
buf.write(int32_pack(len(keybytes)))
buf.write(keybytes)
else:
buf.write(int32_pack(-1))
buf.write(_INT32_NULL)
if val is not None:
valbytes = value_type.to_binary(val, inner_proto)
buf.write(int32_pack(len(valbytes)))
buf.write(valbytes)
else:
buf.write(int32_pack(-1))
buf.write(_INT32_NULL)
return buf.getvalue()


Expand Down Expand Up @@ -964,7 +965,7 @@ def serialize_safe(cls, val, protocol_version):
buf.write(int32_pack(len(packed_item)))
buf.write(packed_item)
else:
buf.write(int32_pack(-1))
buf.write(_INT32_NULL)
return buf.getvalue()

@classmethod
Expand Down Expand Up @@ -1041,7 +1042,7 @@ def serialize_safe(cls, val, protocol_version):
buf.write(int32_pack(len(packed_item)))
buf.write(packed_item)
else:
buf.write(int32_pack(-1))
buf.write(_INT32_NULL)
return buf.getvalue()

@classmethod
Expand Down
53 changes: 52 additions & 1 deletion tests/unit/test_types.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@
EmptyValue, LongType, SetType, UTF8Type,
cql_typename, int8_pack, int64_pack, int64_unpack, lookup_casstype,
lookup_casstype_simple, parse_casstype_args,
int32_pack, Int32Type, ListType, MapType, VectorType,
int32_pack, Int32Type, ListType, MapType, TupleType, UserType, VectorType,
FloatType
)
from cassandra.encoder import cql_quote
Expand Down Expand Up @@ -1117,3 +1117,54 @@ def test_token_order(self):
tokens_equal = [Token(1), Token(1)]
check_sequence_consistency(tokens)
check_sequence_consistency(tokens_equal, equal=True)


class CollectionNullSentinelTests(unittest.TestCase):
"""
Tests that collection types correctly round-trip None/null elements
using the pre-allocated _INT32_NULL sentinel.
"""

def test_list_with_none_roundtrip(self):
proto = 4
parameterized = ListType.apply_parameters([Int32Type])
original = [1, None, 3]
serialized = parameterized.serialize(original, proto)
deserialized = parameterized.deserialize(serialized, proto)
self.assertEqual(deserialized, original)

def test_set_with_none_roundtrip(self):
proto = 4
parameterized = SetType.apply_parameters([Int32Type])
original = [1, None, 3]
serialized = parameterized.serialize(original, proto)
deserialized = parameterized.deserialize(serialized, proto)
self.assertEqual(set(deserialized), set(original))

def test_map_with_none_values_roundtrip(self):
proto = 4
parameterized = MapType.apply_parameters([Int32Type, Int32Type])
original = {1: None, 2: 10}
serialized = parameterized.serialize(original, proto)
deserialized = parameterized.deserialize(serialized, proto)
self.assertEqual(dict(deserialized.items()), original)

def test_tuple_with_none_roundtrip(self):
proto = 4
parameterized = TupleType.apply_parameters([Int32Type, UTF8Type, Int32Type])
original = (1, None, 3)
serialized = parameterized.serialize(original, proto)
deserialized = parameterized.deserialize(serialized, proto)
self.assertEqual(deserialized, original)

def test_usertype_with_none_roundtrip(self):
proto = 4
udt_class = UserType.make_udt_class(
'test_ks', 'test_udt',
('field_a', 'field_b', 'field_c'),
(Int32Type, UTF8Type, Int32Type)
)
original = (1, None, 3)
serialized = udt_class.serialize(original, proto)
deserialized = udt_class.deserialize(serialized, proto)
self.assertEqual(deserialized, original)
Loading