[SPARK-10709] When loading a json dataset as a data frame, if the input path is wrong, the error message is very confusing

• Type: Improvement
• Status: Resolved
• Priority: Minor
• Resolution: Duplicate
• Component/s: SQL
• Assignee: Unassigned
• Reporter: Yin Huai
• Created: 18/Sep/15 21:20
• Updated: 24/Oct/15 18:05
• Resolved: 24/Oct/15 18:05

Description

If you do something like sqlContext.read.json("a wrong path"), when we actually read data, the error message is

java.io.IOException: No input paths specified in job
	at org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:198)
	at org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:270)
	at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:207)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
	at org.apache.spark.ShuffleDependency.<init>(Dependency.scala:91)
	at org.apache.spark.sql.execution.ShuffledRowRDD.getDependencies(ShuffledRowRDD.scala:59)
	at org.apache.spark.rdd.RDD$$anonfun$dependencies$2.apply(RDD.scala:226)
	at org.apache.spark.rdd.RDD$$anonfun$dependencies$2.apply(RDD.scala:224)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.dependencies(RDD.scala:224)
	at org.apache.spark.scheduler.DAGScheduler.visit$2(DAGScheduler.scala:427)
	at org.apache.spark.scheduler.DAGScheduler.getAncestorShuffleDependencies(DAGScheduler.scala:442)
	at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$getShuffleMapStage(DAGScheduler.scala:301)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$visit$1$1.apply(DAGScheduler.scala:403)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$visit$1$1.apply(DAGScheduler.scala:400)
	at scala.collection.immutable.List.foreach(List.scala:318)
	at org.apache.spark.scheduler.DAGScheduler.visit$1(DAGScheduler.scala:400)
	at org.apache.spark.scheduler.DAGScheduler.getParentStages(DAGScheduler.scala:412)
	at org.apache.spark.scheduler.DAGScheduler.getParentStagesAndId(DAGScheduler.scala:315)
	at org.apache.spark.scheduler.DAGScheduler.newResultStage(DAGScheduler.scala:350)
	at org.apache.spark.scheduler.DAGScheduler.handleJobSubmitted(DAGScheduler.scala:846)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1637)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1629)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1618)
	at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
java.io.IOException: No input paths specified in job
	at org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:198)
	at org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:270)
	at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:207)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
	at org.apache.spark.ShuffleDependency.<init>(Dependency.scala:91)
	at org.apache.spark.sql.execution.ShuffledRowRDD.getDependencies(ShuffledRowRDD.scala:59)
	at org.apache.spark.rdd.RDD$$anonfun$dependencies$2.apply(RDD.scala:226)
	at org.apache.spark.rdd.RDD$$anonfun$dependencies$2.apply(RDD.scala:224)
	at scala.Option.getOrElse(Option.scala:120)
	at org.apache.spark.rdd.RDD.dependencies(RDD.scala:224)
	at org.apache.spark.scheduler.DAGScheduler.visit$2(DAGScheduler.scala:427)
	at org.apache.spark.scheduler.DAGScheduler.getAncestorShuffleDependencies(DAGScheduler.scala:442)
	at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$getShuffleMapStage(DAGScheduler.scala:301)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$visit$1$1.apply(DAGScheduler.scala:403)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$visit$1$1.apply(DAGScheduler.scala:400)
	at scala.collection.immutable.List.foreach(List.scala:318)
	at org.apache.spark.scheduler.DAGScheduler.visit$1(DAGScheduler.scala:400)
	at org.apache.spark.scheduler.DAGScheduler.getParentStages(DAGScheduler.scala:412)
	at org.apache.spark.scheduler.DAGScheduler.getParentStagesAndId(DAGScheduler.scala:315)
	at org.apache.spark.scheduler.DAGScheduler.newResultStage(DAGScheduler.scala:350)
	at org.apache.spark.scheduler.DAGScheduler.handleJobSubmitted(DAGScheduler.scala:846)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1637)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1629)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1618)
	at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
	at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:630)
	at org.apache.spark.SparkContext.runJob(SparkContext.scala:1823)
	at org.apache.spark.SparkContext.runJob(SparkContext.scala:1943)
	at org.apache.spark.rdd.RDD$$anonfun$reduce$1.apply(RDD.scala:997)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
	at org.apache.spark.rdd.RDD.withScope(RDD.scala:306)
	at org.apache.spark.rdd.RDD.reduce(RDD.scala:979)
	at org.apache.spark.rdd.RDD$$anonfun$takeOrdered$1.apply(RDD.scala:1360)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
	at org.apache.spark.rdd.RDD.withScope(RDD.scala:306)
	at org.apache.spark.rdd.RDD.takeOrdered(RDD.scala:1347)
	at org.apache.spark.sql.execution.TakeOrderedAndProject.collectData(basicOperators.scala:257)
	at org.apache.spark.sql.execution.TakeOrderedAndProject.executeCollect(basicOperators.scala:263)
	at org.apache.spark.sql.DataFrame$$anonfun$collect$1.apply(DataFrame.scala:1399)
	at org.apache.spark.sql.DataFrame$$anonfun$collect$1.apply(DataFrame.scala:1399)
	at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)
	at org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:1917)
	at org.apache.spark.sql.DataFrame.collect(DataFrame.scala:1398)
	at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1328)
	at org.apache.spark.sql.DataFrame.take(DataFrame.scala:1391)
	at org.apache.spark.sql.DataFrame.showString(DataFrame.scala:178)
	at org.apache.spark.sql.DataFrame.show(DataFrame.scala:402)
	at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:37)
	at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:42)
	at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:44)
	at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:46)
	at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:48)
	at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:50)
	at $iwC$$iwC$$iwC$$iwC.<init>(<console>:52)
	at $iwC$$iwC$$iwC.<init>(<console>:54)
	at $iwC$$iwC.<init>(<console>:56)
	at $iwC.<init>(<console>:58)
	at <init>(<console>:60)
	at .<init>(<console>:64)
	at .<clinit>(<console>)
	at .<init>(<console>:7)
	at .<clinit>(<console>)
	at $print(<console>)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:606)
	at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
	at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1340)
	at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840)
	at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871)
	at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819)
	at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
	at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
	at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
	at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
	at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
	at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$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)

This message is very confusing.

Issue Links

• duplicates: SPARK-11102 Uninformative exception when specifing non-exist input for JSON data source
• is duplicated by: SPARK-11220 SQL data source gives confusing error message when file not found
• is duplicated by: SPARK-11102 Uninformative exception when specifing non-exist input for JSON data source
• links to: [Github] Pull Request #8899 (navis)