java - Spark数据帧将JSON转换为ORC满足 "column ambigous exception"

Question

我正在使用spark数据框，读取JSON数据，然后将其保存到orc。 代码很简单:

DataFrame json = sqlContext.read().json(input);

json.write().format("orc").save(output);

作业失败。这个异常有什么问题吗？谢谢。

Exception in thread "main" org.apache.spark.sql.AnalysisException: Reference 'Canonical_URL' is ambiguous, could be: Canonical_URL#960, Canonical_URL#1010.; at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolve(LogicalPlan.scala:279) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveChildren(LogicalPlan.scala:116) at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$8$$anonfun$applyOrElse$4$$anonfun$16.apply(Analyzer.scala:350) at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$8$$anonfun$applyOrElse$4$$anonfun$16.apply(Analyzer.scala:350) at org.apache.spark.sql.catalyst.analysis.package$.withPosition(package.scala:48) at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$8$$anonfun$applyOrElse$4.applyOrElse(Analyzer.scala:350) at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$8$$anonfun$applyOrElse$4.applyOrElse(Analyzer.scala:341) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:286) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:286) at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:51) at org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:285) at org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$transformExpressionUp$1(QueryPlan.scala:108) at org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$2$$anonfun$apply$2.apply(QueryPlan.scala:123) at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) at scala.collection.immutable.List.foreach(List.scala:318) at scala.collection.TraversableLike$class.map(TraversableLike.scala:244) at scala.collection.AbstractTraversable.map(Traversable.scala:105) at org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$2.apply(QueryPlan.scala:122) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$class.foreach(Iterator.scala:727) at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48) at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103) at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47) at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273) at scala.collection.AbstractIterator.to(Iterator.scala:1157) at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265) at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157) at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252) at scala.collection.AbstractIterator.toArray(Iterator.scala:1157) at org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionsUp(QueryPlan.scala:127) at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$8.applyOrElse(Analyzer.scala:341) at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$8.applyOrElse(Analyzer.scala:243) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:286) at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:286) at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:51) at org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:285) at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$.apply(Analyzer.scala:243) at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$.apply(Analyzer.scala:242) at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:61) at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:59) at scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:111) at scala.collection.immutable.List.foldLeft(List.scala:84) at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:59) at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:51) at scala.collection.immutable.List.foreach(List.scala:318) at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:51) at org.apache.spark.sql.SQLContext$QueryExecution.analyzed$lzycompute(SQLContext.scala:933) at org.apache.spark.sql.SQLContext$QueryExecution.analyzed(SQLContext.scala:933) at org.apache.spark.sql.SQLContext$QueryExecution.assertAnalyzed(SQLContext.scala:931) at org.apache.spark.sql.DataFrame.(DataFrame.scala:131) at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:51) at org.apache.spark.sql.sources.InsertIntoHadoopFsRelation.run(commands.scala:132) at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:57) at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:57) at org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:68) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:88) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:88) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:87) at org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:950) at org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:950) at org.apache.spark.sql.sources.ResolvedDataSource$.apply(ddl.scala:336) at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:144) at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:135) at com.es.infrastructure.spark.orc.transformer.JsonTransformer.run(JsonTransformer.java:22) at Main.main(Main.java:70) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:606) at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:665) at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:170) at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:193) at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:112) at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)

Answer 1

key 必须具有相同的名称。在创建 df 并进行一些连接时，您需要删除其中一个键。