[ https://issues.apache.org/jira/browse/SPARK-14165?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Sean Owen updated SPARK-14165: ------------------------------ Issue Type: Bug (was: Improvement) Hm yeah this is a problem then. I'm not 100% sure which case sensitivity rules apply but seems like it's case-insensitive here. In that case whatever went to get column "abc" in the second table should succeed above. > NoSuchElementException: None.get when joining DataFrames with Seq of fields > of different case > --------------------------------------------------------------------------------------------- > > Key: SPARK-14165 > URL: https://issues.apache.org/jira/browse/SPARK-14165 > Project: Spark > Issue Type: Bug > Components: SQL > Affects Versions: 2.0.0 > Reporter: Jacek Laskowski > Priority: Minor > > {code} > scala> val left = Seq((1,"a")).toDF("id", "abc") > left: org.apache.spark.sql.DataFrame = [id: int, abc: string] > scala> val right = Seq((1,"a")).toDF("id", "ABC") > right: org.apache.spark.sql.DataFrame = [id: int, ABC: string] > scala> left.join(right, Seq("abc")) > java.util.NoSuchElementException: None.get > at scala.None$.get(Option.scala:347) > at scala.None$.get(Option.scala:345) > at > org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$62.apply(Analyzer.scala:1444) > at > org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$62.apply(Analyzer.scala:1444) > at > scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245) > at > scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245) > at scala.collection.immutable.List.foreach(List.scala:381) > at scala.collection.TraversableLike$class.map(TraversableLike.scala:245) > at scala.collection.immutable.List.map(List.scala:285) > at > org.apache.spark.sql.catalyst.analysis.Analyzer.org$apache$spark$sql$catalyst$analysis$Analyzer$$commonNaturalJoinProcessing(Analyzer.scala:1444) > at > org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveNaturalAndUsingJoin$$anonfun$apply$29.applyOrElse(Analyzer.scala:1426) > at > org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveNaturalAndUsingJoin$$anonfun$apply$29.applyOrElse(Analyzer.scala:1418) > at > org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveOperators$1.apply(LogicalPlan.scala:58) > at > org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveOperators$1.apply(LogicalPlan.scala:58) > at > org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:67) > at > org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:57) > at > org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveNaturalAndUsingJoin$.apply(Analyzer.scala:1418) > at > org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveNaturalAndUsingJoin$.apply(Analyzer.scala:1417) > at > org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:83) > at > org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:80) > at > scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:124) > at scala.collection.immutable.List.foldLeft(List.scala:84) > at > org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:80) > at > org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:72) > at scala.collection.immutable.List.foreach(List.scala:381) > at > org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:72) > at > org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:41) > at > org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:41) > at > org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:34) > at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:58) > at > org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$withPlan(Dataset.scala:2299) > at org.apache.spark.sql.Dataset.join(Dataset.scala:553) > at org.apache.spark.sql.Dataset.join(Dataset.scala:526) > ... 51 elided > {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