[ https://issues.apache.org/jira/browse/SPARK-12562?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Reynold Xin updated SPARK-12562: -------------------------------- Assignee: Xiu (Joe) Guo (was: Apache Spark) > DataFrame.write.format("text") requires the column name to be called value > -------------------------------------------------------------------------- > > Key: SPARK-12562 > URL: https://issues.apache.org/jira/browse/SPARK-12562 > Project: Spark > Issue Type: Bug > Components: SQL > Affects Versions: 1.6.0 > Reporter: Michael Armbrust > Assignee: Xiu (Joe) Guo > Fix For: 1.6.1, 2.0.0 > > > We should support writing any DataFrame that has a single string column, > independent of the name. > {code} > wiki.select("text") > .limit(10000) > .write > .format("text") > .mode("overwrite") > .save("/home/michael/wiki.txt") > {code} > {code} > org.apache.spark.sql.AnalysisException: cannot resolve 'value' given input > columns text; > at > org.apache.spark.sql.catalyst.analysis.package$AnalysisErrorAt.failAnalysis(package.scala:42) > at > org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1$$anonfun$apply$2.applyOrElse(CheckAnalysis.scala:60) > at > org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1$$anonfun$apply$2.applyOrElse(CheckAnalysis.scala:57) > at > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:319) > at > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:319) > at > org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:53) > at > org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:318) > at > org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionUp$1(QueryPlan.scala:107) > at > org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$2(QueryPlan.scala:117) > at > org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$2$1.apply(QueryPlan.scala:121) > at > scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) > at > scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) > at scala.collection.immutable.List.foreach(List.scala:318) > at scala.collection.TraversableLike$class.map(TraversableLike.scala:244) > at scala.collection.AbstractTraversable.map(Traversable.scala:105) > at > org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$2(QueryPlan.scala:121) > at > org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$2.apply(QueryPlan.scala:125) > at scala.collection.Iterator$$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:125) > at > org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:57) > at > org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:50) > at > org.apache.spark.sql.catalyst.trees.TreeNode.foreachUp(TreeNode.scala:105) > at > org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.checkAnalysis(CheckAnalysis.scala:50) > at > org.apache.spark.sql.catalyst.analysis.Analyzer.checkAnalysis(Analyzer.scala:44) > at > org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:34) > at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:133) > at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:52) > at > org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation.run(InsertIntoHadoopFsRelation.scala:106) > at > org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:58) > at > org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:56) > at > org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:70) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:132) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:130) > at > org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150) > at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:130) > at > org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:55) > at > org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:55) > at > org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:256) > at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:148) > at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:139) > {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