Github user viirya commented on a diff in the pull request:
https://github.com/apache/spark/pull/19349#discussion_r141242553
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonUDFRunner.scala
---
@@ -0,0 +1,103 @@
+/*
+ * 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._
+import java.net._
+import java.util.concurrent.atomic.AtomicBoolean
+
+import org.apache.spark._
+import org.apache.spark.api.python._
+
+/**
+ * A helper class to run Python UDFs in Spark.
+ */
+class PythonUDFRunner(
+ funcs: Seq[ChainedPythonFunctions],
+ bufferSize: Int,
+ reuseWorker: Boolean,
+ evalType: Int,
+ argOffsets: Array[Array[Int]])
+ extends BasePythonRunner[Array[Byte], Array[Byte]](
+ funcs, bufferSize, reuseWorker, evalType, argOffsets) {
+
+ protected override def newWriterThread(
+ env: SparkEnv,
+ worker: Socket,
+ inputIterator: Iterator[Array[Byte]],
+ partitionIndex: Int,
+ context: TaskContext): WriterThread = {
+ new WriterThread(env, worker, inputIterator, partitionIndex, context) {
+
+ override def writeCommand(dataOut: DataOutputStream): Unit = {
--- End diff --
Looks like this implementation is no different than the `writeCommand` in
`ArrowPythonRunner`? If so, I think we don't need to duplicate this.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
