Github user ueshin commented on a diff in the pull request: https://github.com/apache/spark/pull/19147#discussion_r138005735 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/python/VectorizedPythonRunner.scala --- @@ -0,0 +1,329 @@ +/* + * 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 java.net.Socket +import java.nio.charset.StandardCharsets + +import scala.collection.JavaConverters._ + +import org.apache.arrow.vector.VectorSchemaRoot +import org.apache.arrow.vector.stream.{ArrowStreamReader, ArrowStreamWriter} + +import org.apache.spark.{SparkEnv, SparkFiles, TaskContext} +import org.apache.spark.api.python.{ChainedPythonFunctions, PythonEvalType, PythonException, PythonRDD, SpecialLengths} +import org.apache.spark.internal.Logging +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.execution.arrow.{ArrowUtils, ArrowWriter} +import org.apache.spark.sql.execution.vectorized.{ArrowColumnVector, ColumnarBatch, ColumnVector} +import org.apache.spark.sql.types._ +import org.apache.spark.util.Utils + +/** + * Similar to `PythonRunner`, but exchange data with Python worker via columnar format. + */ +class VectorizedPythonRunner( + funcs: Seq[ChainedPythonFunctions], + batchSize: Int, + bufferSize: Int, + reuse_worker: Boolean, + argOffsets: Array[Array[Int]]) extends Logging { + + require(funcs.length == argOffsets.length, "argOffsets should have the same length as funcs") + + // All the Python functions should have the same exec, version and envvars. + private val envVars = funcs.head.funcs.head.envVars + private val pythonExec = funcs.head.funcs.head.pythonExec + private val pythonVer = funcs.head.funcs.head.pythonVer + + // TODO: support accumulator in multiple UDF + private val accumulator = funcs.head.funcs.head.accumulator + + // todo: return column batch? + def compute( --- End diff -- @icexelloss Ah, I see, thanks! I still agree with refactoring `PythonRunner`. @BryanCutler As for the error, do you mean the case like [test_vectorized_udf_exception](https://github.com/apache/spark/pull/19147/files#diff-7c2fe8530271c0635fb99f7b49e0c4a4R3250)? If not, could you please let me know the case and think about it?
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org