forked from apache/spark
-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Rework group by map type to fix bind reference exception
- Loading branch information
1 parent
aca0d24
commit 2935bdb
Showing
5 changed files
with
185 additions
and
119 deletions.
There are no files selected for viewing
121 changes: 121 additions & 0 deletions
121
...talyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/AddMapSortInAggregate.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,121 @@ | ||
| /* | ||
| * 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 scala.collection.mutable | ||
|
|
||
| import org.apache.spark.sql.catalyst.expressions.{Alias, ArrayTransform, CreateNamedStruct, Expression, GetStructField, If, IsNull, LambdaFunction, Literal, MapFromArrays, MapKeys, MapSort, MapValues, NamedExpression, NamedLambdaVariable} | ||
| import org.apache.spark.sql.catalyst.plans.logical.{Aggregate, LogicalPlan} | ||
| import org.apache.spark.sql.catalyst.rules.Rule | ||
| import org.apache.spark.sql.types.{ArrayType, MapType, StructType} | ||
| import org.apache.spark.util.ArrayImplicits.SparkArrayOps | ||
|
|
||
| /** | ||
| * Adds [[MapSort]] to group expressions containing map columns, as the key/value paris need to be | ||
| * in the correct order before grouping: | ||
| * | ||
| * SELECT COUNT(*) FROM TABLE GROUP BY map_column => | ||
| * SELECT COUNT(*) FROM TABLE GROUP BY map_sort(map_column) | ||
| * | ||
| * SELECT map_column, COUNT(*) FROM TABLE GROUP BY map_column => | ||
| * SELECT map_sort(map_column) as map_column, COUNT(*) FROM TABLE GROUP BY map_sort(map_column) | ||
| * | ||
| * SELECT map_expr as c, COUNT(*) FROM TABLE GROUP BY map_expr => | ||
| * SELECT map_sort(map_expr) as c, COUNT(*) FROM TABLE GROUP BY map_sort(map_expr) | ||
| */ | ||
| object AddMapSortInAggregate extends Rule[LogicalPlan] { | ||
| private def shouldAddMapSort(expr: Expression): Boolean = { | ||
| expr.dataType.existsRecursively(_.isInstanceOf[MapType]) && !expr.isInstanceOf[MapSort] | ||
| } | ||
|
|
||
| override def apply(plan: LogicalPlan): LogicalPlan = { | ||
| val shouldRewrite = plan.exists { | ||
| case agg: Aggregate if agg.groupingExpressions.exists(shouldAddMapSort) => true | ||
| case _ => false | ||
| } | ||
| if (!shouldRewrite) { | ||
| return plan | ||
| } | ||
|
|
||
| plan transformUpWithNewOutput { | ||
| case agg @ Aggregate(groupingExpr, aggregateExpressions, child) => | ||
| val exprToMapSort = new mutable.HashMap[Expression, Expression] | ||
| val newGroupingKeys = groupingExpr.map(insertMapSortRecursively(_, exprToMapSort)) | ||
| if (exprToMapSort.isEmpty) { | ||
| agg -> agg.output.zip(agg.output) | ||
| } else { | ||
| val newAggregateExprs = aggregateExpressions.map { namedExpr => | ||
| val rewritten = namedExpr.transformUp { | ||
| case e => exprToMapSort.getOrElse(e.canonicalized, e) | ||
| } | ||
| if (namedExpr.eq(rewritten)) { | ||
| namedExpr | ||
| } else { | ||
| rewritten match { | ||
| case e @ MapSort(named: NamedExpression) => Alias(e, named.name)() | ||
| case other => other.asInstanceOf[NamedExpression] | ||
| } | ||
| } | ||
| } | ||
| val newAgg = Aggregate(newGroupingKeys, newAggregateExprs, child) | ||
| newAgg -> agg.output.zip(newAgg.output) | ||
| } | ||
| } | ||
| } | ||
|
|
||
| /** | ||
| * Inserts MapSort recursively taking into account when it is nested inside a struct or array. | ||
| */ | ||
| private def insertMapSortRecursively( | ||
| e: Expression, | ||
| exprToMapSort: mutable.HashMap[Expression, Expression]): Expression = { | ||
| e.dataType match { | ||
| case m: MapType => | ||
| // Check if value type of MapType contains MapType (possibly nested) | ||
| // and special handle this case. | ||
| val mapSortExpr = if (m.valueType.existsRecursively(_.isInstanceOf[MapType])) { | ||
| MapFromArrays(MapKeys(e), insertMapSortRecursively(MapValues(e), exprToMapSort)) | ||
| } else { | ||
| e | ||
| } | ||
| exprToMapSort.getOrElseUpdate(e.canonicalized, MapSort(mapSortExpr)) | ||
|
|
||
| case StructType(fields) | ||
| if fields.exists(_.dataType.existsRecursively(_.isInstanceOf[MapType])) => | ||
| val struct = CreateNamedStruct(fields.zipWithIndex.flatMap { case (f, i) => | ||
| Seq(Literal(f.name), insertMapSortRecursively( | ||
| GetStructField(e, i, Some(f.name)), exprToMapSort)) | ||
| }.toImmutableArraySeq) | ||
| if (struct.valExprs.forall(_.isInstanceOf[GetStructField])) { | ||
| // No field needs MapSort processing, just return the original expression. | ||
| e | ||
| } else if (e.nullable) { | ||
| If(IsNull(e), Literal(null, struct.dataType), struct) | ||
| } else { | ||
| struct | ||
| } | ||
|
|
||
| case ArrayType(et, containsNull) if et.existsRecursively(_.isInstanceOf[MapType]) => | ||
| val param = NamedLambdaVariable("x", et, containsNull) | ||
| val funcBody = insertMapSortRecursively(param, exprToMapSort) | ||
| ArrayTransform(e, LambdaFunction(funcBody, Seq(param))) | ||
|
|
||
| case _ => e | ||
| } | ||
| } | ||
| } |
90 changes: 0 additions & 90 deletions
90
...in/scala/org/apache/spark/sql/catalyst/optimizer/InsertMapSortInGroupingExpressions.scala
This file was deleted.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters