anishshri-db commented on code in PR #49156: URL: https://github.com/apache/spark/pull/49156#discussion_r1887542845
########## python/pyspark/sql/streaming/transform_with_state_driver_worker.py: ########## @@ -0,0 +1,89 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +import os +import json + +from pyspark.util import local_connect_and_auth +from pyspark.serializers import ( + write_int, + read_int, + UTF8Deserializer, + CPickleSerializer, +) +from pyspark import worker +from pyspark.util import handle_worker_exception +from typing import IO +from pyspark.worker_util import check_python_version +from pyspark.sql.streaming.stateful_processor_api_client import StatefulProcessorApiClient +from pyspark.sql.streaming.stateful_processor_util import TransformWithStateInPandasFuncMode +from pyspark.sql.types import StructType + +pickle_ser = CPickleSerializer() +utf8_deserializer = UTF8Deserializer() + + +def main(infile: IO, outfile: IO) -> None: Review Comment: Could we add some file level comment here ? ########## python/pyspark/sql/streaming/proto/StateMessage_pb2.py: ########## @@ -51,7 +51,7 @@ if not _descriptor._USE_C_DESCRIPTORS: DESCRIPTOR._loaded_options = None _globals["_HANDLESTATE"]._serialized_start = 6408 - _globals["_HANDLESTATE"]._serialized_end = 6504 + _globals["_HANDLESTATE"]._serialized_end = 6518 Review Comment: this is auto-generated ? ########## python/pyspark/sql/streaming/stateful_processor_util.py: ########## @@ -25,3 +25,4 @@ class TransformWithStateInPandasFuncMode(Enum): PROCESS_DATA = 1 PROCESS_TIMER = 2 COMPLETE = 3 + PRE_INIT = 4 Review Comment: What does this mean ? ########## python/pyspark/sql/pandas/group_ops.py: ########## @@ -504,6 +504,20 @@ def transformWithStateInPandas( if isinstance(outputStructType, str): outputStructType = cast(StructType, _parse_datatype_string(outputStructType)) + def handle_pre_init( + statefulProcessorApiClient: StatefulProcessorApiClient, + ) -> Iterator["PandasDataFrameLike"]: + # driver handle is different from the handle used on executors + driver_handle = StatefulProcessorHandle(statefulProcessorApiClient) + statefulProcessorApiClient.set_handle_state(StatefulProcessorHandleState.PRE_INIT) + statefulProcessor.init(driver_handle) + + # TODO figure out why we need to call close here in Scala side Review Comment: mostly just to reset the internal state right ? ########## python/pyspark/sql/pandas/group_ops.py: ########## @@ -504,6 +504,20 @@ def transformWithStateInPandas( if isinstance(outputStructType, str): outputStructType = cast(StructType, _parse_datatype_string(outputStructType)) + def handle_pre_init( + statefulProcessorApiClient: StatefulProcessorApiClient, + ) -> Iterator["PandasDataFrameLike"]: + # driver handle is different from the handle used on executors Review Comment: lets also briefly say why its different ? -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
