ashb commented on code in PR #73783:
URL: https://github.com/apache/airflow/pull/73783#discussion_r4317317251
##########
task-sdk/src/airflow/sdk/execution_time/comms.py:
##########
@@ -176,14 +180,44 @@ def _new_encoder() -> msgspec.msgpack.Encoder:
return msgspec.msgpack.Encoder(enc_hook=_msgpack_enc_hook)
+def _encode_large_ints(value: Any) -> Any:
+ if isinstance(value, int) and not -(2**63) <= value < 2**64:
+ return msgspec.msgpack.Ext(
+ MP_HUGEINT, value.to_bytes((value.bit_length() + 8) // 8, "big",
signed=True)
+ )
+ if isinstance(value, dict):
+ return {key: _encode_large_ints(item) for key, item in value.items()}
+ if isinstance(value, (list, tuple)):
+ return [_encode_large_ints(item) for item in value]
+ if isinstance(value, msgspec.Struct):
+ return msgspec.structs.replace(
+ value, **{name: _encode_large_ints(getattr(value, name)) for name
in value.__struct_fields__}
+ )
+ if isinstance(value, BaseModel):
+ return _encode_large_ints(value.model_dump(exclude_unset=True))
Review Comment:
Ugh, needing to support values in container objects is a bit annoying. Do we
need to do it this way?
##########
task-sdk/src/airflow/sdk/execution_time/comms.py:
##########
@@ -176,14 +180,44 @@ def _new_encoder() -> msgspec.msgpack.Encoder:
return msgspec.msgpack.Encoder(enc_hook=_msgpack_enc_hook)
+def _encode_large_ints(value: Any) -> Any:
+ if isinstance(value, int) and not -(2**63) <= value < 2**64:
+ return msgspec.msgpack.Ext(
+ MP_HUGEINT, value.to_bytes((value.bit_length() + 8) // 8, "big",
signed=True)
+ )
+ if isinstance(value, dict):
+ return {key: _encode_large_ints(item) for key, item in value.items()}
+ if isinstance(value, (list, tuple)):
+ return [_encode_large_ints(item) for item in value]
+ if isinstance(value, msgspec.Struct):
+ return msgspec.structs.replace(
+ value, **{name: _encode_large_ints(getattr(value, name)) for name
in value.__struct_fields__}
+ )
+ if isinstance(value, BaseModel):
+ return _encode_large_ints(value.model_dump(exclude_unset=True))
+ return value
+
+
+def _decode_msgpack_ext(code: int, data: memoryview) -> Any:
+ if code == MP_HUGEINT:
+ return int.from_bytes(data, "big", signed=True)
+ return msgspec.msgpack.Ext(code, data)
+
+
class _FrameMixin:
_encoder: ClassVar[msgspec.msgpack.Encoder] = _new_encoder()
- def as_bytes(self) -> bytearray:
+ def as_bytes(self, *, allow_large_ints: bool = True) -> bytearray:
# https://jcristharif.com/msgspec/perf-tips.html#length-prefix-framing
for inspiration
buffer = bytearray(256)
- self._encoder.encode_into(self, buffer, 4) # type: ignore[arg-type]
+ try:
+ self._encoder.encode_into(self, buffer, 4) # type:
ignore[arg-type]
+ except OverflowError:
+ if not allow_large_ints:
Review Comment:
When would this be set to false?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
