cloud-fan commented on code in PR #37994: URL: https://github.com/apache/spark/pull/37994#discussion_r988619447
########## connect/src/test/scala/org/apache/spark/sql/connect/planner/SparkConnectProtoSuite.scala: ########## @@ -0,0 +1,60 @@ +/* + * 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.connect.planner + +import org.apache.spark.connect.proto +import org.apache.spark.sql.catalyst.dsl.expressions._ +import org.apache.spark.sql.catalyst.dsl.plans._ +import org.apache.spark.sql.catalyst.expressions.AttributeReference +import org.apache.spark.sql.catalyst.plans.PlanTest +import org.apache.spark.sql.catalyst.plans.logical.LocalRelation +import org.apache.spark.sql.types.{DataType, IntegerType} + +/** + * This suite is based on connect DSL and test that given same dataframe operations, whether + * connect could construct a proto plan that can be translated back, and after analyzed, be the + * same as Spark dataframe's generated plan. + */ +class SparkConnectProtoSuite extends PlanTest with SparkConnectPlanTest { + + lazy val connectTestRelation = createLocalRelationProto(Map("id" -> IntegerType)) + + lazy val sparkTestRelation: LocalRelation = LocalRelation(AttributeReference("id", IntegerType)()) + + test("Basic select") { + val connectPlan = { + // TODO: Scala only allows one implicit per scope so we keep proto implicit imports in + // this scope. Need to find a better way to make two implicits work in the smae scope. + import org.apache.spark.sql.catalyst.connect.expressions._ + import org.apache.spark.sql.catalyst.connect.plans._ + transform(connectTestRelation.select("id".protoAttr)) + } + val sparkPlan = sparkTestRelation.select("id") + comparePlans(connectPlan.analyze, sparkPlan.analyze, false) + } + + private def createLocalRelationProto(colNameTypeMap: Map[String, DataType]): proto.Relation = { Review Comment: it's weird to pass a `Map` here, as the elements order is not deterministic. We should use `Seq[(String, DataType)]` or simply `Seq[AttributeReference]` -- 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]
