[
https://issues.apache.org/jira/browse/SPARK-6472?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Yin Huai resolved SPARK-6472.
-----------------------------
Resolution: Not a Problem
It is not a problem. For select, we support column name string. I need to use
selectExpr to access an array element.
> Elements of an array of structs cannot be accessed.
> ---------------------------------------------------
>
> Key: SPARK-6472
> URL: https://issues.apache.org/jira/browse/SPARK-6472
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Reporter: Yin Huai
> Priority: Blocker
>
> I tried the following snippet with HiveContext.
> {code}
> import sqlContext._
> val rdd = sc.parallelize("""{"a":[{"b":1}, {"b":2}]}""" :: Nil)
> val df = jsonRDD(rdd)
> df.registerTempTable("jt")
> // This one does not work.
> df.select("a[0]").collect
> // This one is fine.
> sql("select a[0] from jt").collect
> {code}
> The exception is
> {code}
> df.select("a[0]").collect
> org.apache.spark.sql.AnalysisException: cannot resolve 'a[0]' given input
> columns a;
> at
> org.apache.spark.sql.catalyst.analysis.package$AnalysisErrorAt.failAnalysis(package.scala:42)
> at
> org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$apply$3$$anonfun$apply$1.applyOrElse(CheckAnalysis.scala:48)
> at
> org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$apply$3$$anonfun$apply$1.applyOrElse(CheckAnalysis.scala:45)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:250)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:250)
> at
> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:50)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:249)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$transformExpressionUp$1(QueryPlan.scala:104)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$2$$anonfun$apply$2.apply(QueryPlan.scala:118)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at
> scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
> at scala.collection.AbstractTraversable.map(Traversable.scala:105)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$2.apply(QueryPlan.scala:117)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at
> scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at
> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at
> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at
> scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> at
> scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionsUp(QueryPlan.scala:122)
> at
> org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$apply$3.apply(CheckAnalysis.scala:45)
> at
> org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$apply$3.apply(CheckAnalysis.scala:43)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.foreachUp(TreeNode.scala:88)
> at
> org.apache.spark.sql.catalyst.analysis.CheckAnalysis.apply(CheckAnalysis.scala:43)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.assertAnalyzed(SQLContext.scala:1108)
> at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:133)
> at
> org.apache.spark.sql.DataFrame.logicalPlanToDataFrame(DataFrame.scala:157)
> at org.apache.spark.sql.DataFrame.select(DataFrame.scala:465)
> at org.apache.spark.sql.DataFrame.select(DataFrame.scala:480)
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
