panbingkun commented on code in PR #37941: URL: https://github.com/apache/spark/pull/37941#discussion_r979124099
########## sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/PushProjectionThroughLimitSuite.scala: ########## @@ -0,0 +1,62 @@ +/* + * 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.optimizer + +import org.apache.spark.sql.Row +import org.apache.spark.sql.catalyst.dsl.expressions._ +import org.apache.spark.sql.catalyst.dsl.plans._ +import org.apache.spark.sql.catalyst.plans.PlanTest +import org.apache.spark.sql.catalyst.plans.logical.{LocalRelation, LogicalPlan} +import org.apache.spark.sql.catalyst.rules.RuleExecutor + +class PushProjectionThroughLimitSuite extends PlanTest { + object Optimize extends RuleExecutor[LogicalPlan] { + val batches = Batch("Optimizer Batch", + FixedPoint(100), + PushProjectionThroughLimit, + EliminateLimits) :: Nil + } + + test("SPARK-40501: push projection through limit") { + val testRelation = LocalRelation.fromExternalRows( + Seq("a".attr.int, "b".attr.int, "c".attr.int), + 1.to(20).map(_ => Row(1, 2, 3))) + + val query1 = testRelation + .limit(10) + .select('a, 'b, 'c') + .limit(15).analyze + val optimized1 = Optimize.execute(query1) + val expected1 = testRelation + .select('a, 'b, 'c') + .limit(10).analyze Review Comment: > I am curious why expected limit is 10 not 15. `LIMIT 15` should be the top node. > > I guess this is a question of how Spark coalesce adjacent limits. How does Spark choose the value over a, b, c > > LIMIT a --- LIMIT b --------LIMIT c ? EliminateLimits will be performed for optimization. [https://github.com/apache/spark/blob/master/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala#L1977-L1985](url) https://github.com/apache/spark/blob/8ccd41f2f8be0a3db991b7900e928c2988f80a2a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala#L1977-L1985 -- 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]
