allisonwang-db commented on code in PR #45023:
URL: https://github.com/apache/spark/pull/45023#discussion_r1480622631
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/PythonScan.scala:
##########
@@ -45,13 +63,50 @@ class PythonScan(
new PythonPartitionReaderFactory(
ds.source, readerFunc, outputSchema, jobArtifactUUID)
}
+}
- override def toBatch: Batch = this
+case class PythonStreamingSourceOffset(json: String) extends Offset
- override def description: String = "(Python)"
+case class PythonStreamingSourcePartition(partition: Array[Byte]) extends
InputPartition
- override def readSchema(): StructType = outputSchema
+class PythonMicroBatchStream(
Review Comment:
should we put this in a different file?
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonStreamingSourceRunner.scala:
##########
@@ -0,0 +1,163 @@
+/*
+ * 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
+import org.apache.spark.sql.internal.SQLConf
+import org.apache.spark.sql.types.StructType
+
+object PythonStreamingSourceRunner {
+ val partitionsFuncId = 886
+ val latestOffsetsFuncId = 887
Review Comment:
what are these hardcoded numbers?
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/python/PythonScan.scala:
##########
@@ -27,9 +30,24 @@ class PythonScan(
ds: PythonDataSourceV2,
shortName: String,
outputSchema: StructType,
- options: CaseInsensitiveStringMap) extends Batch with Scan {
+ options: CaseInsensitiveStringMap) extends Scan {
- private[this] val jobArtifactUUID =
JobArtifactSet.getCurrentJobArtifactState.map(_.uuid)
+ override def toBatch: Batch = new PythonBatch(ds, shortName, outputSchema,
options)
+
+ override def toMicroBatchStream(checkpointLocation: String):
MicroBatchStream =
+ new PythonMicroBatchStream(ds, shortName, outputSchema, options)
+
+ override def description: String = "(Python)"
+
+ override def readSchema(): StructType = outputSchema
+
+ override def supportedCustomMetrics(): Array[CustomMetric] =
+ ds.source.createPythonMetrics()
+}
+
+class PythonBatch(ds: PythonDataSourceV2, shortName: String,
+ outputSchema: StructType, options: CaseInsensitiveStringMap)
extends Batch {
Review Comment:
nit: ident
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonStreamingSourceRunner.scala:
##########
@@ -0,0 +1,163 @@
+/*
+ * 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
+import org.apache.spark.sql.internal.SQLConf
+import org.apache.spark.sql.types.StructType
+
+object PythonStreamingSourceRunner {
+ val partitionsFuncId = 886
+ val latestOffsetsFuncId = 887
+}
+
+class PythonStreamingSourceRunner(
+ func: PythonFunction,
+ outputSchema: StructType) extends Logging {
+ val workerModule = "pyspark.sql.streaming.python_streaming_source_runner"
+
+ private val conf = SparkEnv.get.conf
+ protected val bufferSize: Int = conf.get(BUFFER_SIZE)
+ protected val authSocketTimeout = conf.get(PYTHON_AUTH_SOCKET_TIMEOUT)
+
+ private val envVars: java.util.Map[String, String] = func.envVars
+ private val pythonExec: String = func.pythonExec
+ private var pythonWorker: Option[PythonWorker] = None
+ private var pythonWorkerFactory: Option[PythonWorkerFactory] = None
+ protected val pythonVer: String = func.pythonVer
+
+ private var dataOut: DataOutputStream = null
+ private var dataIn: DataInputStream = null
+
+ import PythonStreamingSourceRunner._
+
+ /**
+ * Initializes the Python worker for streaming functions. Sets up Spark
Connect session
Review Comment:
Where is the Spark Connect session?
--
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
