我有一个JSON文件，我正在尝试通过
将其读入数据框 df = ss.read.json("foo.json")
当我读取文件时，它会引发异常：
java.util.NoSuchElementException: None.get
我已经能够将数据文件缩减为以下内容以重现该问题：
{"HTTP":[{"ETag":"foo"}]}
{"HTTP":[{"Etag":"bar"}]}
引发的完整异常是：
WARN TaskSetManager: Lost task 0.0 in stage 37.0 (TID 89, f, executor 11): java.util.NoSuchElementException: None.get
at scala.None$.get(Option.scala:347)
at scala.None$.get(Option.scala:345)
at org.apache.spark.sql.catalyst.analysis.TypeCoercion$$anonfun$1$$anonfun$apply$4.apply(TypeCoercion.scala:111)
at org.apache.spark.sql.catalyst.analysis.TypeCoercion$$anonfun$1$$anonfun$apply$4.apply(TypeCoercion.scala:106)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:186)
at org.apache.spark.sql.catalyst.analysis.TypeCoercion$$anonfun$1.apply(TypeCoercion.scala:106)
at org.apache.spark.sql.catalyst.analysis.TypeCoercion$$anonfun$1.apply(TypeCoercion.scala:86)
at org.apache.spark.sql.execution.datasources.json.JsonInferSchema$.compatibleType(JsonInferSchema.scala:271)
at org.apache.spark.sql.execution.datasources.json.JsonInferSchema$$anonfun$org$apache$spark$sql$execution$datasources$json$JsonInferSchema$$compatibleRootType$1.apply(JsonInferSchema.scala:262)
at org.apache.spark.sql.execution.datasources.json.JsonInferSchema$$anonfun$org$apache$spark$sql$execution$datasources$json$JsonInferSchema$$compatibleRootType$1.apply(JsonInferSchema.scala:246)
at scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:157)
at scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:157)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at scala.collection.TraversableOnce$class.foldLeft(TraversableOnce.scala:157)
at scala.collection.AbstractIterator.foldLeft(Iterator.scala:1336)
at scala.collection.TraversableOnce$class.fold(TraversableOnce.scala:212)
at scala.collection.AbstractIterator.fold(Iterator.scala:1336)
at org.apache.spark.rdd.RDD$$anonfun$fold$1$$anonfun$19.apply(RDD.scala:1096)
at org.apache.spark.rdd.RDD$$anonfun$fold$1$$anonfun$19.apply(RDD.scala:1096)
at org.apache.spark.SparkContext$$anonfun$33.apply(SparkContext.scala:2130)
at org.apache.spark.SparkContext$$anonfun$33.apply(SparkContext.scala:2130)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:109)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
19/07/10 15:00:29 ERROR TaskSetManager: Task 0 in stage 37.0 failed 4 times; aborting job
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/opt/mapr/spark/spark-2.3.2/python/pyspark/sql/readwriter.py", line 261, in json
return self._df(self._jreader.json(self._spark._sc._jvm.PythonUtils.toSeq(path)))
File "/opt/mapr/spark/spark-2.3.2/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py", line 1257, in __call__
File "/opt/mapr/spark/spark-2.3.2/python/pyspark/sql/utils.py", line 63, in deco
return f(*a, **kw)
File "/opt/mapr/spark/spark-2.3.2/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py", line 328, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o2229.json.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 37.0 failed 4 times, most recent failure: Lost task 0.3 in stage 37.0 (TID 92, tip-hd1-0613.cisco.com, executor 11): java.util.NoSuchElementException: None.get
at scala.None$.get(Option.scala:347)
at scala.None$.get(Option.scala:345)
at org.apache.spark.sql.catalyst.analysis.TypeCoercion$$anonfun$1$$anonfun$apply$4.apply(TypeCoercion.scala:111)
at org.apache.spark.sql.catalyst.analysis.TypeCoercion$$anonfun$1$$anonfun$apply$4.apply(TypeCoercion.scala:106)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:186)
at org.apache.spark.sql.catalyst.analysis.TypeCoercion$$anonfun$1.apply(TypeCoercion.scala:106)
at org.apache.spark.sql.catalyst.analysis.TypeCoercion$$anonfun$1.apply(TypeCoercion.scala:86)
at org.apache.spark.sql.execution.datasources.json.JsonInferSchema$.compatibleType(JsonInferSchema.scala:271)
at org.apache.spark.sql.execution.datasources.json.JsonInferSchema$$anonfun$org$apache$spark$sql$execution$datasources$json$JsonInferSchema$$compatibleRootType$1.apply(JsonInferSchema.scala:262)
at org.apache.spark.sql.execution.datasources.json.JsonInferSchema$$anonfun$org$apache$spark$sql$execution$datasources$json$JsonInferSchema$$compatibleRootType$1.apply(JsonInferSchema.scala:246)
at scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:157)
at scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:157)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at scala.collection.TraversableOnce$class.foldLeft(TraversableOnce.scala:157)
at scala.collection.AbstractIterator.foldLeft(Iterator.scala:1336)
at scala.collection.TraversableOnce$class.fold(TraversableOnce.scala:212)
at scala.collection.AbstractIterator.fold(Iterator.scala:1336)
at org.apache.spark.rdd.RDD$$anonfun$fold$1$$anonfun$19.apply(RDD.scala:1096)
at org.apache.spark.rdd.RDD$$anonfun$fold$1$$anonfun$19.apply(RDD.scala:1096)
at org.apache.spark.SparkContext$$anonfun$33.apply(SparkContext.scala:2130)
at org.apache.spark.SparkContext$$anonfun$33.apply(SparkContext.scala:2130)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:109)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1651)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1639)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1638)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1638)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:831)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:831)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:831)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1872)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1821)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1810)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:642)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2034)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2131)
at org.apache.spark.rdd.RDD$$anonfun$fold$1.apply(RDD.scala:1098)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
at org.apache.spark.rdd.RDD.fold(RDD.scala:1092)
at org.apache.spark.sql.execution.datasources.json.JsonInferSchema$.infer(JsonInferSchema.scala:70)
at org.apache.spark.sql.execution.datasources.json.TextInputJsonDataSource$.inferFromDataset(JsonDataSource.scala:102)
at org.apache.spark.sql.execution.datasources.json.TextInputJsonDataSource$.infer(JsonDataSource.scala:96)
at org.apache.spark.sql.execution.datasources.json.JsonDataSource.inferSchema(JsonDataSource.scala:63)
at org.apache.spark.sql.execution.datasources.json.JsonFileFormat.inferSchema(JsonFileFormat.scala:57)
at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$8.apply(DataSource.scala:203)
at org.apache.spark.sql.execution.datasources.DataSource$$anonfun$8.apply(DataSource.scala:203)
at scala.Option.orElse(Option.scala:289)
at org.apache.spark.sql.execution.datasources.DataSource.getOrInferFileFormatSchema(DataSource.scala:202)
at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:393)
at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:239)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:227)
at org.apache.spark.sql.DataFrameReader.json(DataFrameReader.scala:397)
at sun.reflect.GeneratedMethodAccessor110.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.util.NoSuchElementException: None.get
at scala.None$.get(Option.scala:347)
at scala.None$.get(Option.scala:345)
at org.apache.spark.sql.catalyst.analysis.TypeCoercion$$anonfun$1$$anonfun$apply$4.apply(TypeCoercion.scala:111)
at org.apache.spark.sql.catalyst.analysis.TypeCoercion$$anonfun$1$$anonfun$apply$4.apply(TypeCoercion.scala:106)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:186)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.mutable.ArrayOps$ofRef.map(ArrayOps.scala:186)
at org.apache.spark.sql.catalyst.analysis.TypeCoercion$$anonfun$1.apply(TypeCoercion.scala:106)
at org.apache.spark.sql.catalyst.analysis.TypeCoercion$$anonfun$1.apply(TypeCoercion.scala:86)
at org.apache.spark.sql.execution.datasources.json.JsonInferSchema$.compatibleType(JsonInferSchema.scala:271)
at org.apache.spark.sql.execution.datasources.json.JsonInferSchema$$anonfun$org$apache$spark$sql$execution$datasources$json$JsonInferSchema$$compatibleRootType$1.apply(JsonInferSchema.scala:262)
at org.apache.spark.sql.execution.datasources.json.JsonInferSchema$$anonfun$org$apache$spark$sql$execution$datasources$json$JsonInferSchema$$compatibleRootType$1.apply(JsonInferSchema.scala:246)
at scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:157)
at scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:157)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at scala.collection.TraversableOnce$class.foldLeft(TraversableOnce.scala:157)
at scala.collection.AbstractIterator.foldLeft(Iterator.scala:1336)
at scala.collection.TraversableOnce$class.fold(TraversableOnce.scala:212)
at scala.collection.AbstractIterator.fold(Iterator.scala:1336)
at org.apache.spark.rdd.RDD$$anonfun$fold$1$$anonfun$19.apply(RDD.scala:1096)
at org.apache.spark.rdd.RDD$$anonfun$fold$1$$anonfun$19.apply(RDD.scala:1096)
at org.apache.spark.SparkContext$$anonfun$33.apply(SparkContext.scala:2130)
at org.apache.spark.SparkContext$$anonfun$33.apply(SparkContext.scala:2130)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:109)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
... 1 more
该问题似乎是区分大小写的问题，可能与推断模式的过程有关。我试图将'spark.sql.caseSensitive'设置为true，但这没有任何区别。
考虑到需要对列名区分大小写，是否有任何想法如何能够正确读取和推断模式？