viirya commented on a change in pull request #29828: URL: https://github.com/apache/spark/pull/29828#discussion_r494011718
########## File path: sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/JsonSuite.scala ########## @@ -0,0 +1,85 @@ +/* + * 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 query1 = testRelation + .select(JsonToStructs(schema, options, StructsToJson(options, 'struct)).as("struct")) + val optimized1 = Optimizer.execute(query1.analyze) + + val expected = testRelation.select('struct.as("struct")).analyze + comparePlans(optimized1, expected) + + val query2 = testRelation + .select( + JsonToStructs(schema, options, + StructsToJson(options, + JsonToStructs(schema, options, + StructsToJson(options, 'struct)))).as("struct")) + val optimized2 = Optimizer.execute(query2.analyze) + + comparePlans(optimized2, expected) + } + + test("SPARK-32948: not optimize from_json + to_json if schema is different") { + val options = Map.empty[String, String] + val schema = StructType.fromDDL("a int") + + val query = testRelation + .select(JsonToStructs(schema, options, StructsToJson(options, 'struct)).as("struct")) + val optimized = Optimizer.execute(query.analyze) + + val expected = testRelation.select( + JsonToStructs(schema, options, StructsToJson(options, 'struct)).as("struct")).analyze + comparePlans(optimized, expected) + } + + test("SPARK-32948: not optimize from_json + to_json if option is not empty") { Review comment: ok. ########## File path: sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/JsonSuite.scala ########## @@ -0,0 +1,85 @@ +/* + * 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 query1 = testRelation + .select(JsonToStructs(schema, options, StructsToJson(options, 'struct)).as("struct")) + val optimized1 = Optimizer.execute(query1.analyze) + + val expected = testRelation.select('struct.as("struct")).analyze + comparePlans(optimized1, expected) + + val query2 = testRelation + .select( + JsonToStructs(schema, options, + StructsToJson(options, + JsonToStructs(schema, options, + StructsToJson(options, 'struct)))).as("struct")) + val optimized2 = Optimizer.execute(query2.analyze) + + comparePlans(optimized2, expected) + } + + test("SPARK-32948: not optimize from_json + to_json if schema is different") { + val options = Map.empty[String, String] + val schema = StructType.fromDDL("a int") + + val query = testRelation + .select(JsonToStructs(schema, options, StructsToJson(options, 'struct)).as("struct")) + val optimized = Optimizer.execute(query.analyze) + + val expected = testRelation.select( + JsonToStructs(schema, options, StructsToJson(options, 'struct)).as("struct")).analyze + comparePlans(optimized, expected) + } + + test("SPARK-32948: not optimize from_json + to_json if option is not empty") { Review comment: added. ########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/OptimizeJsonExprs.scala ########## @@ -0,0 +1,38 @@ +/* + * 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.types.DataType + +/** + * Simplify redundant json related expressions. + */ +object OptimizeJsonExprs extends Rule[LogicalPlan] { + override def apply(plan: LogicalPlan): LogicalPlan = plan transform { + case p => p.transformExpressions { + case JsonToStructs(schema, options1, + t @ StructsToJson(options2, child, timeZoneId2), timeZoneId1) + if options1.isEmpty && options2.isEmpty && timeZoneId1 == timeZoneId2 && + schema.sameType(child.dataType) => Review comment: Good suggestion. ########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/OptimizeJsonExprs.scala ########## @@ -0,0 +1,38 @@ +/* + * 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.types.DataType + +/** + * Simplify redundant json related expressions. + */ +object OptimizeJsonExprs extends Rule[LogicalPlan] { + override def apply(plan: LogicalPlan): LogicalPlan = plan transform { + case p => p.transformExpressions { + case JsonToStructs(schema, options1, + StructsToJson(options2, child, timeZoneId2), timeZoneId1) + if options1.isEmpty && options2.isEmpty && timeZoneId1 == timeZoneId2 && + schema == child.dataType => Review comment: Ok, the safest is like currently, only optimize the exprs when schema is exactly matched. Technically, under case-insensitive, two schema is considered the same if letter case is the only difference. I am thinking if user gives explicitly a schema, we should respect it, right? I can add one test case for the case. ########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/OptimizeJsonExprs.scala ########## @@ -0,0 +1,38 @@ +/* + * 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.types.DataType + +/** + * Simplify redundant json related expressions. + */ +object OptimizeJsonExprs extends Rule[LogicalPlan] { + override def apply(plan: LogicalPlan): LogicalPlan = plan transform { + case p => p.transformExpressions { + case JsonToStructs(schema, options1, + StructsToJson(options2, child, timeZoneId2), timeZoneId1) + if options1.isEmpty && options2.isEmpty && timeZoneId1 == timeZoneId2 && + schema == child.dataType => Review comment: Ok, the safest is like currently, only optimize the exprs when schema is exactly matched. Technically, under case-insensitive, two schema is considered the same if letter case is the only difference. But I am thinking if user gives explicitly a schema, we should respect it, right? I can add one test case for the case. ########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/OptimizeJsonExprs.scala ########## @@ -0,0 +1,38 @@ +/* + * 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.types.DataType + +/** + * Simplify redundant json related expressions. + */ +object OptimizeJsonExprs extends Rule[LogicalPlan] { + override def apply(plan: LogicalPlan): LogicalPlan = plan transform { + case p => p.transformExpressions { + case JsonToStructs(schema, options1, + StructsToJson(options2, child, timeZoneId2), timeZoneId1) + if options1.isEmpty && options2.isEmpty && timeZoneId1 == timeZoneId2 && Review comment: thanks. ########## File path: sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/JsonSuite.scala ########## @@ -0,0 +1,128 @@ +/* + * 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.catalyst.util.DateTimeUtils.getZoneId +import org.apache.spark.sql.types._ + +class JsonSuite extends PlanTest with ExpressionEvalHelper { Review comment: ok. ########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/OptimizeJsonExprs.scala ########## @@ -0,0 +1,38 @@ +/* + * 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.types.DataType + +/** + * Simplify redundant json related expressions. + */ +object OptimizeJsonExprs extends Rule[LogicalPlan] { + override def apply(plan: LogicalPlan): LogicalPlan = plan transform { + case p => p.transformExpressions { + case JsonToStructs(schema, options1, + StructsToJson(options2, child, timeZoneId2), timeZoneId1) + if options1.isEmpty && options2.isEmpty && timeZoneId1 == timeZoneId2 && + schema == child.dataType => Review comment: Added test. ---------------------------------------------------------------- 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
