viirya commented on a change in pull request #29828: URL: https://github.com/apache/spark/pull/29828#discussion_r492491314
########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Json.scala ########## @@ -0,0 +1,35 @@ +/* + * 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.{Aggregate, LogicalPlan} +import org.apache.spark.sql.catalyst.rules.Rule + +/** + * Simplify redundant json related expressions. + */ +object OptimizeJsonExprs extends Rule[LogicalPlan] { + override def apply(plan: LogicalPlan): LogicalPlan = plan transform { + case p => p.transformExpressionsUp { + case JsonToStructs(_, options1, StructsToJson(options2, child, timeZoneId2), timeZoneId1) Review comment: Hmm, we already have `SimplifyExtractValueOps`, which is somehow close to you meant. BTW, I will later work on another PR to add column pruning of `JsonToStructs` to `OptimizeJsonExprs`. It sounds not exactly matching `RemoveNoopExpression`, seems to me. ########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Json.scala ########## @@ -0,0 +1,35 @@ +/* + * 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.{Aggregate, LogicalPlan} +import org.apache.spark.sql.catalyst.rules.Rule + +/** + * Simplify redundant json related expressions. + */ +object OptimizeJsonExprs extends Rule[LogicalPlan] { Review comment: Renamed. Thanks. ########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/OptimizeJsonExprs.scala ########## @@ -0,0 +1,35 @@ +/* + * 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.{Aggregate, LogicalPlan} +import org.apache.spark.sql.catalyst.rules.Rule + +/** + * Simplify redundant json related expressions. + */ +object OptimizeJsonExprs extends Rule[LogicalPlan] { + override def apply(plan: LogicalPlan): LogicalPlan = plan transform { + case p => p.transformExpressionsUp { + case JsonToStructs(_, options1, StructsToJson(options2, child, timeZoneId2), timeZoneId1) + if options1.isEmpty && options2.isEmpty && timeZoneId1 == timeZoneId2 => Review comment: Yeah, we may look at that. Currently the safest way is two options both are empty, or they are equal. ########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/OptimizeJsonExprs.scala ########## @@ -0,0 +1,35 @@ +/* + * 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.{Aggregate, LogicalPlan} +import org.apache.spark.sql.catalyst.rules.Rule + +/** + * Simplify redundant json related expressions. + */ +object OptimizeJsonExprs extends Rule[LogicalPlan] { Review comment: Yes, I think so. We could do it in other PR. ########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/OptimizeJsonExprs.scala ########## @@ -0,0 +1,35 @@ +/* + * 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.{Aggregate, LogicalPlan} +import org.apache.spark.sql.catalyst.rules.Rule + +/** + * Simplify redundant json related expressions. + */ +object OptimizeJsonExprs extends Rule[LogicalPlan] { + override def apply(plan: LogicalPlan): LogicalPlan = plan transform { + case p => p.transformExpressionsUp { + case JsonToStructs(_, options1, StructsToJson(options2, child, timeZoneId2), timeZoneId1) + if options1 == options2.isEmpty && timeZoneId1 == timeZoneId2 => Review comment: Oops! thanks. ########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/OptimizeJsonExprs.scala ########## @@ -0,0 +1,35 @@ +/* + * 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.{Aggregate, LogicalPlan} +import org.apache.spark.sql.catalyst.rules.Rule + +/** + * Simplify redundant json related expressions. Review comment: I will work on column pruning of to_from later. It will be in this rule too. ########## File path: sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/JsonSuite.scala ########## @@ -0,0 +1,52 @@ +/* + * 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.dsl.expressions._ +import org.apache.spark.sql.catalyst.dsl.plans._ +import org.apache.spark.sql.catalyst.expressions._ +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 +import org.apache.spark.sql.types._ + +class JsonSuite extends PlanTest with ExpressionEvalHelper { + + object Optimizer extends RuleExecutor[LogicalPlan] { + val batches = Batch("Json optimization", FixedPoint(10), OptimizeJsonExprs) :: Nil + } + + val schema = StructType.fromDDL("a int, b int") + + private val structAtt = 'struct.struct(schema).notNull + + private val testRelation = LocalRelation(structAtt) + + test("SPARK-32948: optimize from_json + to_json") { + val options = Map.empty[String, String] + val schema = StructType.fromDDL("a int, b int") + + val query = testRelation + .select(JsonToStructs(schema, options, StructsToJson(options, 'struct)).as("struct")) + val optimized = Optimizer.execute(query.analyze) + + val expected = testRelation.select('struct.as("struct")).analyze Review comment: ok. added. ########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/OptimizeJsonExprs.scala ########## @@ -0,0 +1,35 @@ +/* + * 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.{Aggregate, LogicalPlan} +import org.apache.spark.sql.catalyst.rules.Rule + +/** + * Simplify redundant json related expressions. + */ +object OptimizeJsonExprs extends Rule[LogicalPlan] { + override def apply(plan: LogicalPlan): LogicalPlan = plan transform { + case p => p.transformExpressionsUp { Review comment: I think no, `transformExpressions` should be fine. ########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/OptimizeJsonExprs.scala ########## @@ -0,0 +1,35 @@ +/* + * 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.{Aggregate, LogicalPlan} +import org.apache.spark.sql.catalyst.rules.Rule + +/** + * Simplify redundant json related expressions. Review comment: sure. will do later when adding other optimization. ---------------------------------------------------------------- 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: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
