peter-toth commented on code in PR #57789: URL: https://github.com/apache/spark/pull/57789#discussion_r3720626848
########## sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/ApplyFunctionExpressionSuite.scala: ########## @@ -0,0 +1,87 @@ +/* + * 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.catalyst.expressions + +import java.util.concurrent.{CountDownLatch, TimeUnit} + +import scala.concurrent.{ExecutionContext, Future} +import scala.concurrent.duration._ + +import org.apache.spark.SparkFunSuite +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.connector.catalog.functions.ScalarFunction +import org.apache.spark.sql.types.{DataType, IntegerType} +import org.apache.spark.util.ThreadUtils + +class ApplyFunctionExpressionSuite extends SparkFunSuite { + + private val intIdentity = new ScalarFunction[Int] { + override def inputTypes(): Array[DataType] = Array(IntegerType) + override def resultType(): DataType = IntegerType + override def name(): String = "int_identity" + override def produceResult(input: InternalRow): Int = input.getInt(0) + } + + test("SPARK-58578: ApplyFunctionExpression is stateful and produces fresh copies") { + val expr = ApplyFunctionExpression( + intIdentity, Seq(BoundReference(0, IntegerType, nullable = false))) + assert(expr.stateful, "ApplyFunctionExpression.stateful should be true") + val copy = expr.freshCopyIfContainsStatefulExpression() + assert(copy ne expr, + "freshCopyIfContainsStatefulExpression should return a new instance " + + "for ApplyFunctionExpression") + assert(copy.eval(InternalRow(7)) === 7) + } + + test("SPARK-58578: concurrent evaluation uses independent input rows") { Review Comment: **Finding 2.** The name reads as "concurrent evaluation of this expression is safe", but the test constructs the two evaluators itself with `freshCopyIfContainsStatefulExpression()`, so what it actually pins is that two fresh copies don't share `reusedRow`. The query-level property needs one more step that isn't exercised here — each concurrent execution building its own projection — so a reader who trusts the name could conclude more than the test shows. Suggest matching the name to the assertion: ```suggestion test("SPARK-58578: fresh copies do not share the reused input row") { ``` Worth keeping the test as it is otherwise — I reverted just the `stateful` override and it fails exactly as intended, with `firstResult` coming back as `2` because both evaluators are then the same instance. -- 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]
