HyukjinKwon commented on a change in pull request #30912: URL: https://github.com/apache/spark/pull/30912#discussion_r548355759
########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/OptimizeCsvJsonExprs.scala ########## @@ -0,0 +1,116 @@ +/* + * 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.catalyst.expressions._ +import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan +import org.apache.spark.sql.catalyst.rules.Rule +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.types.{ArrayType, StructType} + +/** + * Simplify redundant csv/json related expressions. + * + * The optimization includes: + * 1. JsonToStructs(StructsToJson(child)) => child. + * 2. Prune unnecessary columns from GetStructField/GetArrayStructFields + JsonToStructs. + * 3. CreateNamedStruct(JsonToStructs(json).col1, JsonToStructs(json).col2, ...) => + * If(IsNull(json), nullStruct, KnownNotNull(JsonToStructs(prunedSchema, ..., json))) + * if JsonToStructs(json) is shared among all fields of CreateNamedStruct. `prunedSchema` + * contains all accessed fields in original CreateNamedStruct. + * 4. Prune unnecessary columns from GetStructField + CsvToStructs. + */ +object OptimizeCsvJsonExprs extends Rule[LogicalPlan] { + override def apply(plan: LogicalPlan): LogicalPlan = plan transform { + case p => + val optimized = if (SQLConf.get.jsonExpressionOptimization) { + p.transformExpressions(jsonOptimization) + } else { + p + } + + if (SQLConf.get.csvExpressionOptimization) { + optimized.transformExpressions(csvOptimization) + } else { + optimized + } + } Review comment: What about: ```scala case p if SQLConf.get.jsonExpressionOptimization => p.transformExpressions(jsonOptimization) case p if SQLConf.get.csvExpressionOptimization => p.transformExpressions(csvOptimization) case p => p ``` ? Or is the optimization dependent on each other? ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
