Major Description
The following works with spark 1.5.1, but not anymore with spark 1.6.0:
import org.apache.spark.sql.{ DataFrame, Row } import org.apache.spark.sql.types.StructType val rddNoCols = sqlContext.sparkContext.parallelize(1 to 10).map(_ => Row.empty) val dfNoCols = sqlContext.createDataFrame(rddNoCols, StructType(Seq.empty)) dfNoCols.registerTempTable("temp_table_no_cols") sqlContext.sql("select * from temp_table_no_cols").show
spark 1.5.1 result:
++ || ++ || || || || || || || || || || ++
spark 1.6.0 result:
java.lang.IllegalArgumentException: requirement failed
at scala.Predef$.require(Predef.scala:221)
at org.apache.spark.sql.catalyst.analysis.UnresolvedStar.expand(unresolved.scala:199)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$10$$anonfun$applyOrElse$14.apply(Analyzer.scala:354)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$10$$anonfun$applyOrElse$14.apply(Analyzer.scala:353)
at scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:251)
at scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:251)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at scala.collection.TraversableLike$class.flatMap(TraversableLike.scala:251)
at scala.collection.AbstractTraversable.flatMap(Traversable.scala:105)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$10.applyOrElse(Analyzer.scala:353)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$10.applyOrElse(Analyzer.scala:347)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveOperators$1.apply(LogicalPlan.scala:57)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveOperators$1.apply(LogicalPlan.scala:57)
at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:53)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:56)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$.apply(Analyzer.scala:347)
at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$.apply(Analyzer.scala:328)
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:111)
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$1.apply(RuleExecutor.scala:72)
at scala.collection.immutable.List.foreach(List.scala:318)
at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:72)
at org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:36)
at org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:36)
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.SQLContext.sql(SQLContext.scala:817)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:28)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:33)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:35)
at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:37)
at $iwC$$iwC$$iwC$$iwC.<init>(<console>:39)
at $iwC$$iwC$$iwC.<init>(<console>:41)
at $iwC$$iwC.<init>(<console>:43)
at $iwC.<init>(<console>:45)
at <init>(<console>:47)
at .<init>(<console>:51)
at .<clinit>(<console>)
at .<init>(<console>:7)
at .<clinit>(<console>)
at $print(<console>)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1346)
at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871)
at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819)
at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
at scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945)
at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059)
at org.apache.spark.repl.Main$.main(Main.scala:31)
at org.apache.spark.repl.Main.main(Main.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
I can understand why tables with no columns might not be supported in SQL, but in that case I would say that the dfNoCols.registerTempTable() call should fail with a more descriptive error.
