allisonwang-db commented on code in PR #45023: URL: https://github.com/apache/spark/pull/45023#discussion_r1492090151
########## python/pyspark/sql/streaming/python_streaming_source_runner.py: ########## @@ -0,0 +1,160 @@ +# +# 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 sys +import json +from typing import IO + +from pyspark.accumulators import _accumulatorRegistry +from pyspark.errors import PySparkAssertionError, PySparkRuntimeError +from pyspark.java_gateway import local_connect_and_auth +from pyspark.serializers import ( + read_int, + write_int, + write_with_length, + SpecialLengths, +) +from pyspark.sql.datasource import DataSource, DataSourceStreamReader +from pyspark.sql.types import ( + _parse_datatype_json_string, + StructType, +) +from pyspark.util import handle_worker_exception +from pyspark.worker_util import ( + check_python_version, + read_command, + pickleSer, + send_accumulator_updates, + setup_memory_limits, + setup_spark_files, + utf8_deserializer, +) + +initial_offset_func_id = 884 +latest_offset_func_id = 885 +partitions_func_id = 886 +commit_func_id = 887 + + +def initial_offset_func(reader: DataSourceStreamReader, outfile: IO) -> None: + offset = reader.initialOffset() + write_with_length(json.dumps(offset).encode("utf-8"), outfile) + + +def latest_offset_func(reader: DataSourceStreamReader, outfile: IO) -> None: + offset = reader.latestOffset() + write_with_length(json.dumps(offset).encode("utf-8"), outfile) + + +def partitions_func(reader: DataSourceStreamReader, infile: IO, outfile: IO) -> None: + start_offset = json.loads(utf8_deserializer.loads(infile)) + end_offset = json.loads(utf8_deserializer.loads(infile)) + partitions = reader.partitions(start_offset, end_offset) + # Return the serialized partition values. + write_int(len(partitions), outfile) + for partition in partitions: + pickleSer._write_with_length(partition, outfile) + + +def commit_func(reader: DataSourceStreamReader, infile: IO, outfile: IO) -> None: + end_offset = json.loads(utf8_deserializer.loads(infile)) + reader.commit(end_offset) + write_int(0, outfile) + + +def main(infile: IO, outfile: IO) -> None: + try: + check_python_version(infile) + setup_spark_files(infile) + + memory_limit_mb = int(os.environ.get("PYSPARK_PLANNER_MEMORY_MB", "-1")) + setup_memory_limits(memory_limit_mb) + + _accumulatorRegistry.clear() + + # Receive the data source instance. + data_source = read_command(pickleSer, infile) + + if not isinstance(data_source, DataSource): + raise PySparkAssertionError( + error_class="PYTHON_DATA_SOURCE_TYPE_MISMATCH", + message_parameters={ + "expected": "a Python data source instance of type 'DataSource'", + "actual": f"'{type(data_source).__name__}'", + }, + ) + + # Receive the data source output schema. + schema_json = utf8_deserializer.loads(infile) + schema = _parse_datatype_json_string(schema_json) + if not isinstance(schema, StructType): + raise PySparkAssertionError( + error_class="PYTHON_DATA_SOURCE_TYPE_MISMATCH", + message_parameters={ + "expected": "an output schema of type 'StructType'", + "actual": f"'{type(schema).__name__}'", + }, + ) + + # Instantiate data source reader. + try: + reader = data_source.streamReader(schema=schema) + # Initialization succeed. + write_int(0, outfile) + outfile.flush() + + # handle method call from socket + while True: + func_id = read_int(infile) + if func_id == initial_offset_func_id: + initial_offset_func(reader, outfile) + elif func_id == latest_offset_func_id: + latest_offset_func(reader, outfile) + elif func_id == partitions_func_id: + partitions_func(reader, infile, outfile) + elif func_id == commit_func_id: + commit_func(reader, infile, outfile) + outfile.flush() + except Exception as e: + error_msg = 'data source {} throw exception: {}'.format(data_source.name, e) + raise PySparkRuntimeError( + error_class="PYTHON_STREAMING_DATA_SOURCE_RUNTIME_ERROR", + message_parameters={"type": "reader", "error": error_msg}, Review Comment: Could you add a test case for this? I don't think the PYTHON_STREAMING_DATA_SOURCE_RUNTIME_ERROR has a parameter called `type`. ########## sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonStreamingSourceRunner.scala: ########## @@ -0,0 +1,206 @@ +/* + * 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. + */ + + +package org.apache.spark.sql.execution.python + +import java.io.{BufferedInputStream, BufferedOutputStream, DataInputStream, DataOutputStream} + +import scala.collection.mutable.ArrayBuffer +import scala.jdk.CollectionConverters._ + +import org.apache.spark.SparkEnv +import org.apache.spark.api.python.{PythonFunction, PythonWorker, PythonWorkerFactory, PythonWorkerUtils, SpecialLengths} +import org.apache.spark.internal.Logging +import org.apache.spark.internal.config.BUFFER_SIZE +import org.apache.spark.internal.config.Python.{PYTHON_AUTH_SOCKET_TIMEOUT, PYTHON_USE_DAEMON} +import org.apache.spark.sql.errors.{QueryCompilationErrors, QueryExecutionErrors} +import org.apache.spark.sql.types.StructType + +object PythonStreamingSourceRunner { + val initialOffsetFuncId = 884 Review Comment: Could you also add some comments on what are these IDs? Also, use ```suggestion val INITIAL_OFFSET_FUNC_ID = 884 ``` -- 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: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
