Maria Rebelka created SPARK-19308:
-------------------------------------
Summary: Unable to write to Hive table where column names contains
period (.)
Key: SPARK-19308
URL: https://issues.apache.org/jira/browse/SPARK-19308
Project: Spark
Issue Type: Bug
Components: SQL
Affects Versions: 2.0.2
Reporter: Maria Rebelka
When saving DataFrame which contains columns with dots to Hive in append mode,
it only succeeds when the table doesn't exists yet.
{noformat}
scala> spark.sql("drop table test")
res0: org.apache.spark.sql.DataFrame = []
scala> val test = sc.parallelize(Array("{\"a\":1,\"b.b\":2}"))
test: org.apache.spark.rdd.RDD[String] = ParallelCollectionRDD[1] at
parallelize at <console>:24
scala> val j = spark.read.json(test)
j: org.apache.spark.sql.DataFrame = [a: bigint, b.b: bigint]
scala> j.write.mode("append").saveAsTable("test")
// succeeds
scala> j.write.mode("append").saveAsTable("test")
org.apache.spark.sql.AnalysisException: cannot resolve '`b.b`' given input
columns: [a, b.b]; line 1 pos 0;
'Project [a#6L, 'b.b]
+- LogicalRDD [a#6L, b.b#7L]
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:77)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1$$anonfun$apply$2.applyOrElse(CheckAnalysis.scala:74)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:308)
at
org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:308)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:69)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:307)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionUp$1(QueryPlan.scala:269)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$2(QueryPlan.scala:279)
at
org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$2$1.apply(QueryPlan.scala:283)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$2(QueryPlan.scala:283)
at
org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$8.apply(QueryPlan.scala:288)
at
org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:186)
at
org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionsUp(QueryPlan.scala:288)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:74)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:67)
at org.apache.spark.sql.catalyst.trees.TreeNode.foreachUp(TreeNode.scala:126)
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.checkAnalysis(CheckAnalysis.scala:67)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.checkAnalysis(Analyzer.scala:58)
at
org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:49)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:64)
at
org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$withPlan(Dataset.scala:2603)
at org.apache.spark.sql.Dataset.select(Dataset.scala:969)
at org.apache.spark.sql.Dataset.selectExpr(Dataset.scala:1004)
at
org.apache.spark.sql.execution.command.CreateDataSourceTableAsSelectCommand.run(createDataSourceTables.scala:236)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114)
at
org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:86)
at
org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:86)
at org.apache.spark.sql.DataFrameWriter.saveAsTable(DataFrameWriter.scala:378)
at org.apache.spark.sql.DataFrameWriter.saveAsTable(DataFrameWriter.scala:354)
... 48 elided
scala> spark.sql("drop table test")
res3: org.apache.spark.sql.DataFrame = []
scala> j.write.mode("append").saveAsTable("test")
// succeeds again
{noformat}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
