Hi Ryan, On Tue, May 21, 2019 at 2:48 PM Ryan Blue <rb...@netflix.com> wrote: > > Are you sure that your schema conversion is correct? If you're running with a > recent Spark version, then that line is probably `name.hashCode()`. That file > was last updated 6 months ago so I think it is likely that `name` is the null > in your version.
Thanks for taking a look -- in my traceback, "line 264" of attributeReference.hashCode() is: h = h * 37 + metadata.hashCode() If I look within the StructType at the top of the schema, each StructField indeed has null for the metadata, which I improperly passing in instead of Metadata.empty() Thanks again, Andrew > > On Tue, May 21, 2019 at 11:39 AM Andrew Melo <andrew.m...@gmail.com> wrote: >> >> Hello, >> >> I'm developing a DataSourceV2 reader for the ROOT (https://root.cern/) >> file format to replace a previous DSV1 source that was in use before. >> >> I have a bare skeleton of the reader, which can properly load the >> files and pass their schema into Spark 2.4.3, but any operation on the >> resulting DataFrame (except for printSchema()) causes an NPE deep in >> the guts of spark [1]. I'm baffled, though, since both logging >> statements and coverage says that neither planBatchInputPartitions nor >> any of the methods in my partition class are called -- the only thing >> called is readSchema and the constructors. >> >> I followed the pattern from "JavaBatchDataSourceV2.java" -- is it >> possible that test-case isn't up to date? Are there any other example >> Java DSV2 readers out in the wild I could compare against? >> >> Thanks! >> Andrew >> >> [1] >> >> java.lang.NullPointerException >> at >> org.apache.spark.sql.catalyst.expressions.AttributeReference.hashCode(namedExpressions.scala:264) >> at >> scala.collection.mutable.FlatHashTable$class.findElemImpl(FlatHashTable.scala:129) >> at >> scala.collection.mutable.FlatHashTable$class.containsElem(FlatHashTable.scala:124) >> at scala.collection.mutable.HashSet.containsElem(HashSet.scala:40) >> at scala.collection.mutable.HashSet.contains(HashSet.scala:57) >> at scala.collection.GenSetLike$class.apply(GenSetLike.scala:44) >> at scala.collection.mutable.AbstractSet.apply(Set.scala:46) >> at scala.collection.SeqLike$$anonfun$distinct$1.apply(SeqLike.scala:506) >> at scala.collection.immutable.List.foreach(List.scala:392) >> at scala.collection.SeqLike$class.distinct(SeqLike.scala:505) >> at scala.collection.AbstractSeq.distinct(Seq.scala:41) >> at >> org.apache.spark.sql.catalyst.expressions.package$AttributeSeq$$anonfun$unique$1.apply(package.scala:147) >> at >> org.apache.spark.sql.catalyst.expressions.package$AttributeSeq$$anonfun$unique$1.apply(package.scala:147) >> at >> scala.collection.MapLike$MappedValues$$anonfun$foreach$3.apply(MapLike.scala:245) >> at >> scala.collection.MapLike$MappedValues$$anonfun$foreach$3.apply(MapLike.scala:245) >> at >> scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:733) >> at scala.collection.immutable.HashMap$HashMap1.foreach(HashMap.scala:221) >> at scala.collection.immutable.HashMap$HashTrieMap.foreach(HashMap.scala:428) >> at >> scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:732) >> at scala.collection.MapLike$MappedValues.foreach(MapLike.scala:245) >> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234) >> at scala.collection.AbstractTraversable.map(Traversable.scala:104) >> at >> org.apache.spark.sql.catalyst.expressions.package$AttributeSeq.unique(package.scala:147) >> at >> org.apache.spark.sql.catalyst.expressions.package$AttributeSeq.direct$lzycompute(package.scala:152) >> at >> org.apache.spark.sql.catalyst.expressions.package$AttributeSeq.direct(package.scala:151) >> at >> org.apache.spark.sql.catalyst.expressions.package$AttributeSeq.resolve(package.scala:229) >> at >> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveChildren(LogicalPlan.scala:101) >> at >> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$40.apply(Analyzer.scala:890) >> at >> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$40.apply(Analyzer.scala:892) >> at >> org.apache.spark.sql.catalyst.analysis.package$.withPosition(package.scala:53) >> at >> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$.org$apache$spark$sql$catalyst$analysis$Analyzer$ResolveReferences$$resolve(Analyzer.scala:889) >> at >> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$org$apache$spark$sql$catalyst$analysis$Analyzer$ResolveReferences$$resolve$2.apply(Analyzer.scala:898) >> at >> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$org$apache$spark$sql$catalyst$analysis$Analyzer$ResolveReferences$$resolve$2.apply(Analyzer.scala:898) >> at >> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:326) >> at >> org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187) >> at >> org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:324) >> at >> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$.org$apache$spark$sql$catalyst$analysis$Analyzer$ResolveReferences$$resolve(Analyzer.scala:898) >> at >> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$9$$anonfun$applyOrElse$35.apply(Analyzer.scala:958) >> at >> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$9$$anonfun$applyOrElse$35.apply(Analyzer.scala:958) >> at >> org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$1.apply(QueryPlan.scala:105) >> at >> org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$1.apply(QueryPlan.scala:105) >> at >> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70) >> at >> org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpression$1(QueryPlan.scala:104) >> at >> org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$1(QueryPlan.scala:116) >> at >> org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$org$apache$spark$sql$catalyst$plans$QueryPlan$$recursiveTransform$1$2.apply(QueryPlan.scala:121) >> 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$$recursiveTransform$1(QueryPlan.scala:121) >> at >> org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$2.apply(QueryPlan.scala:126) >> at >> org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187) >> at >> org.apache.spark.sql.catalyst.plans.QueryPlan.mapExpressions(QueryPlan.scala:126) >> at >> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$9.applyOrElse(Analyzer.scala:958) >> at >> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$9.applyOrElse(Analyzer.scala:901) >> at >> org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$apply$1.apply(AnalysisHelper.scala:90) >> at >> org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$apply$1.apply(AnalysisHelper.scala:90) >> at >> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70) >> at >> org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:89) >> at >> org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:86) >> at >> org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194) >> at >> org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsUp(AnalysisHelper.scala:86) >> at >> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsUp(LogicalPlan.scala:29) >> at >> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$.apply(Analyzer.scala:901) >> at >> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$.apply(Analyzer.scala:758) >> at >> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:87) >> at >> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:84) >> at >> scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:124) >> at scala.collection.immutable.List.foldLeft(List.scala:84) >> at >> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:84) >> at >> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:76) >> at scala.collection.immutable.List.foreach(List.scala:392) >> at >> org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:76) >> at >> org.apache.spark.sql.catalyst.analysis.Analyzer.org$apache$spark$sql$catalyst$analysis$Analyzer$$executeSameContext(Analyzer.scala:127) >> at >> org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:121) >> at >> org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:106) >> at >> org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:105) >> at >> org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.markInAnalyzer(AnalysisHelper.scala:201) >> at >> org.apache.spark.sql.catalyst.analysis.Analyzer.executeAndCheck(Analyzer.scala:105) >> at >> org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:57) >> at >> org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:55) >> at >> org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:47) >> at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:78) >> at >> org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$withPlan(Dataset.scala:3406) >> at org.apache.spark.sql.Dataset.select(Dataset.scala:1334) >> at org.apache.spark.sql.Dataset.select(Dataset.scala:1352) >> at org.apache.spark.sql.Dataset.select(Dataset.scala:1352) >> at >> edu.vanderbilt.accre.spark_ttree.TTreeDataSourceIntegrationTest.testLoadDataFrame(TTreeDataSourceIntegrationTest.java:47) >> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) >> at >> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) >> at >> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) >> at java.lang.reflect.Method.invoke(Method.java:498) >> at >> org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:47) >> at >> org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12) >> at >> org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:44) >> at >> org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17) >> at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:271) >> at >> org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:70) >> at >> org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:50) >> at org.junit.runners.ParentRunner$3.run(ParentRunner.java:238) >> at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:63) >> at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:236) >> at org.junit.runners.ParentRunner.access$000(ParentRunner.java:53) >> at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:229) >> at >> org.junit.internal.runners.statements.RunBefores.evaluate(RunBefores.java:26) >> at >> org.junit.internal.runners.statements.RunAfters.evaluate(RunAfters.java:27) >> at org.junit.runners.ParentRunner.run(ParentRunner.java:309) >> at >> org.eclipse.jdt.internal.junit4.runner.JUnit4TestReference.run(JUnit4TestReference.java:89) >> at >> org.eclipse.jdt.internal.junit.runner.TestExecution.run(TestExecution.java:41) >> at >> org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:541) >> at >> org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:763) >> at >> org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.run(RemoteTestRunner.java:463) >> at >> org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.main(RemoteTestRunner.java:209)] >> >> --------------------------------------------------------------------- >> To unsubscribe e-mail: dev-unsubscr...@spark.apache.org >> > > > -- > Ryan Blue > Software Engineer > Netflix --------------------------------------------------------------------- To unsubscribe e-mail: dev-unsubscr...@spark.apache.org
