[
https://issues.apache.org/jira/browse/SPARK-2063?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14055193#comment-14055193
]
Yin Huai commented on SPARK-2063:
---------------------------------
Tried two queries.
The following one works
{code}
val query1 = sql("SELECT n.a as aa FROM nestedData GROUP BY n.a ORDER BY aa
LIMIT 10")
query1: org.apache.spark.sql.SchemaRDD =
SchemaRDD[33] at RDD at SchemaRDD.scala:104
== Query Plan ==
TakeOrdered 10, [aa#19:0 ASC]
Aggregate false, [a#20], [a#20 AS aa#19]
Exchange (HashPartitioning [a#20], 200)
Aggregate true, [n#0.a AS a#20], [n#0.a AS a#20]
ExistingRdd [n#0], MapPartitionsRDD[1] at mapPartitions at
basicOperators.scala:176
{code}
But, this one does not work
{code}
val query1 = sql("SELECT n.a FROM nestedData GROUP BY n.a ORDER BY n.a LIMIT
10")
query1: org.apache.spark.sql.SchemaRDD =
SchemaRDD[34] at RDD at SchemaRDD.scala:104
== Query Plan ==
org.apache.spark.sql.catalyst.errors.package$TreeNodeException: Unresolved
attributes: 'n.a ASC, tree:
Sort ['n.a ASC]
Aggregate [n#0.a AS a#22], [n#0.a AS a#23]
Subquery nestedData
SparkLogicalPlan (ExistingRdd [n#0], MapPartitionsRDD[1] at mapPartitions at
basicOperators.scala:176), nestedData
{code}
Seems the issue is that when we resolve a reference to a field of a StructType,
we use the last part of the reference as the alias.
This logic can be found in "LogicalPlan.resolve".
{code}
case StructType(fields) =>
Some(Alias(nestedFields.foldLeft(a: Expression)(GetField),
nestedFields.last)())
{code}
For example, if we have "n.a", we will use "a" as the alias.
> Creating a SchemaRDD via sql() does not correctly resolve nested types
> ----------------------------------------------------------------------
>
> Key: SPARK-2063
> URL: https://issues.apache.org/jira/browse/SPARK-2063
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.0.0
> Reporter: Aaron Davidson
> Assignee: Cheng Lian
>
> For example, from the typical twitter dataset:
> {code}
> scala> val popularTweets = sql("SELECT retweeted_status.text,
> MAX(retweeted_status.retweet_count) AS s FROM tweets WHERE retweeted_status
> is not NULL GROUP BY retweeted_status.text ORDER BY s DESC LIMIT 30")
> scala> popularTweets.toString
> 14/06/06 21:27:48 INFO analysis.Analyzer: Max iterations (2) reached for
> batch MultiInstanceRelations
> 14/06/06 21:27:48 INFO analysis.Analyzer: Max iterations (2) reached for
> batch CaseInsensitiveAttributeReferences
> org.apache.spark.sql.catalyst.analysis.UnresolvedException: Invalid call to
> qualifiers on unresolved object, tree: 'retweeted_status.text
> at
> org.apache.spark.sql.catalyst.analysis.UnresolvedAttribute.qualifiers(unresolved.scala:51)
> at
> org.apache.spark.sql.catalyst.analysis.UnresolvedAttribute.qualifiers(unresolved.scala:47)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$2.apply(LogicalPlan.scala:67)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$2.apply(LogicalPlan.scala:65)
> at
> scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:251)
> at
> scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:251)
> at scala.collection.immutable.List.foreach(List.scala:318)
> at
> scala.collection.TraversableLike$class.flatMap(TraversableLike.scala:251)
> at scala.collection.AbstractTraversable.flatMap(Traversable.scala:105)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolve(LogicalPlan.scala:65)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$3$$anonfun$applyOrElse$2.applyOrElse(Analyzer.scala:100)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$3$$anonfun$applyOrElse$2.applyOrElse(Analyzer.scala:97)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:165)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$transformExpressionDown$1(QueryPlan.scala:51)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$1$$anonfun$apply$1.apply(QueryPlan.scala:65)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at scala.collection.immutable.List.foreach(List.scala:318)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
> at scala.collection.AbstractTraversable.map(Traversable.scala:105)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$1.apply(QueryPlan.scala:64)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at
> scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at
> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at
> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at
> scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> at
> scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionsDown(QueryPlan.scala:69)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressions(QueryPlan.scala:40)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$3.applyOrElse(Analyzer.scala:97)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$3.applyOrElse(Analyzer.scala:94)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:217)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$.apply(Analyzer.scala:94)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$.apply(Analyzer.scala:93)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$apply$1$$anonfun$apply$2.apply(RuleExecutor.scala:62)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$apply$1$$anonfun$apply$2.apply(RuleExecutor.scala:60)
> at
> scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:111)
> at scala.collection.immutable.List.foldLeft(List.scala:84)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$apply$1.apply(RuleExecutor.scala:60)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$apply$1.apply(RuleExecutor.scala:52)
> at scala.collection.immutable.List.foreach(List.scala:318)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor.apply(RuleExecutor.scala:52)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.analyzed$lzycompute(SQLContext.scala:265)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.analyzed(SQLContext.scala:265)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.optimizedPlan$lzycompute(SQLContext.scala:266)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.optimizedPlan(SQLContext.scala:266)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.sparkPlan$lzycompute(SQLContext.scala:268)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.sparkPlan(SQLContext.scala:268)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.executedPlan$lzycompute(SQLContext.scala:269)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.executedPlan(SQLContext.scala:269)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:272)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:272)
> at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:154)
> {code}
--
This message was sent by Atlassian JIRA
(v6.2#6252)
