Jack Hu created SPARK-36672:
-------------------------------
Summary: Using value from map in grouping sets result
org.apache.spark.sql.AnalysisException
Key: SPARK-36672
URL: https://issues.apache.org/jira/browse/SPARK-36672
Project: Spark
Issue Type: Bug
Components: SQL
Affects Versions: 3.1.0
Reporter: Jack Hu
Steps to reproduce：
# create a table with map
{code:java}
create table test (int_value INT, dims MAP<string, string>) using parquet{code}
# Run following query:
{code:java}
select int_value, count(1)
from test
group by int_value, dims.dim_x, dims.dim_y
grouping sets ( (int_value, dims.dim_x), (int_value, dims.dim_y)){code}
The call stack:
{noformat}
org.apache.spark.sql.AnalysisException: dims#34[dim_x] AS dim_x#35 doesn't show
up in the GROUP BY list ArrayBuffer(int_value#33 AS int_value#41,
dims#34[dim_x] AS dim_x#37 AS dim_x#42, dims#34[dim_y] AS dim_y#38 AS dim_y#43);
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.failAnalysis(CheckAnalysis.scala:41)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.failAnalysis(Analyzer.scala:92)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveGroupingAnalytics$$anonfun$19$$anonfun$apply$49$$anonfun$21.apply(Analyzer.scala:387)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveGroupingAnalytics$$anonfun$19$$anonfun$apply$49$$anonfun$21.apply(Analyzer.scala:387)
at scala.Option.getOrElse(Option.scala:121)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveGroupingAnalytics$$anonfun$19$$anonfun$apply$49.apply(Analyzer.scala:386)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveGroupingAnalytics$$anonfun$19$$anonfun$apply$49.apply(Analyzer.scala:385)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveGroupingAnalytics$$anonfun$19.apply(Analyzer.scala:385)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveGroupingAnalytics$$anonfun$19.apply(Analyzer.scala:384)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveGroupingAnalytics$.constructExpand(Analyzer.scala:384)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveGroupingAnalytics$.org$apache$spark$sql$catalyst$analysis$Analyzer$ResolveGroupingAnalytics$$constructAggregate(Analyzer.scala:448)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveGroupingAnalytics$$anonfun$apply$6.applyOrElse(Analyzer.scala:485)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveGroupingAnalytics$$anonfun$apply$6.applyOrElse(Analyzer.scala:473)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:289)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:289)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:288)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveGroupingAnalytics$.apply(Analyzer.scala:473)
at
org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveGroupingAnalytics$.apply(Analyzer.scala:287)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:87)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:84)
at
scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:124)
at scala.collection.immutable.List.foldLeft(List.scala:84)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:84)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:76)
at scala.collection.immutable.List.foreach(List.scala:381)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:76)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.org$apache$spark$sql$catalyst$analysis$Analyzer$$executeSameContext(Analyzer.scala:124)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:118)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.executeAndCheck(Analyzer.scala:103)
at
org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:57)
at
org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:55)
at
org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:47)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:74)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:641)
{noformat}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
