问题描述
我是第一次使用.ndjson。我正在尝试将其加载到具有以下规格的笔记本电脑中：
- 火花2.4
- Python 3.6.1
- Java 1.8.0_222
我正在尝试执行以下查询。
患者= sqlContext.read.json（“ https://ssufhiranondlg2.dfs.core.windows.net/202010230105-output/Patient.ndjson”）
我收到以下错误：
Py4JJavaError: An error occurred while calling o168.json.
: java.lang.UnsupportedOperationException
at org.apache.hadoop.fs.http.AbstractHttpFileSystem.listStatus(AbstractHttpFileSystem.java:91)
at org.apache.hadoop.fs.http.HttpsFileSystem.listStatus(HttpsFileSystem.java:23)
at org.apache.spark.sql.execution.datasources.InMemoryFileIndex$.org$apache$spark$sql$execution$datasources$InMemoryFileIndex$$listLeafFiles(InMemoryFileIndex.scala:281)
at org.apache.spark.sql.execution.datasources.InMemoryFileIndex$$anonfun$bulkListLeafFiles$1.apply(InMemoryFileIndex.scala:177)
at org.apache.spark.sql.execution.datasources.InMemoryFileIndex$$anonfun$bulkListLeafFiles$1.apply(InMemoryFileIndex.scala:176)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at org.apache.spark.sql.execution.datasources.InMemoryFileIndex$.bulkListLeafFiles(InMemoryFileIndex.scala:176)
at org.apache.spark.sql.execution.datasources.InMemoryFileIndex.listLeafFiles(InMemoryFileIndex.scala:127)
at org.apache.spark.sql.execution.datasources.InMemoryFileIndex.refresh0(InMemoryFileIndex.scala:91)
at org.apache.spark.sql.execution.datasources.InMemoryFileIndex.<init>(InMemoryFileIndex.scala:67)
at org.apache.spark.sql.execution.datasources.DataSource.org$apache$spark$sql$execution$datasources$DataSource$$createInMemoryFileIndex(DataSource.scala:532)
at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:370)
at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:223)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:211)
at org.apache.spark.sql.DataFrameReader.json(DataFrameReader.scala:392)
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 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:748)
Traceback (most recent call last):
File "/opt/spark/python/lib/pyspark.zip/pyspark/sql/readwriter.py",line 274,in json
return self._df(self._jreader.json(self._spark._sc._jvm.PythonUtils.toSeq(path)))
File "/opt/spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py",line 1257,in __call__
answer,self.gateway_client,self.target_id,self.name)
File "/opt/spark/python/lib/pyspark.zip/pyspark/sql/utils.py",line 69,in deco
return f(*a,**kw)
File "/opt/spark/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py",line 328,in get_return_value
format(target_id,".",name),value)
py4j.protocol.Py4JJavaError: An error occurred while calling o168.json.
: java.lang.UnsupportedOperationException
at org.apache.hadoop.fs.http.AbstractHttpFileSystem.listStatus(AbstractHttpFileSystem.java:91)
at org.apache.hadoop.fs.http.HttpsFileSystem.listStatus(HttpsFileSystem.java:23)
at org.apache.spark.sql.execution.datasources.InMemoryFileIndex$.org$apache$spark$sql$execution$datasources$InMemoryFileIndex$$listLeafFiles(InMemoryFileIndex.scala:281)
at org.apache.spark.sql.execution.datasources.InMemoryFileIndex$$anonfun$bulkListLeafFiles$1.apply(InMemoryFileIndex.scala:177)
at org.apache.spark.sql.execution.datasources.InMemoryFileIndex$$anonfun$bulkListLeafFiles$1.apply(InMemoryFileIndex.scala:176)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at org.apache.spark.sql.execution.datasources.InMemoryFileIndex$.bulkListLeafFiles(InMemoryFileIndex.scala:176)
at org.apache.spark.sql.execution.datasources.InMemoryFileIndex.listLeafFiles(InMemoryFileIndex.scala:127)
at org.apache.spark.sql.execution.datasources.InMemoryFileIndex.refresh0(InMemoryFileIndex.scala:91)
at org.apache.spark.sql.execution.datasources.InMemoryFileIndex.<init>(InMemoryFileIndex.scala:67)
at org.apache.spark.sql.execution.datasources.DataSource.org$apache$spark$sql$execution$datasources$DataSource$$createInMemoryFileIndex(DataSource.scala:532)
at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:370)
at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:223)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:211)
at org.apache.spark.sql.DataFrameReader.json(DataFrameReader.scala:392)
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 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:748)
解决方法
暂无找到可以解决该程序问题的有效方法，小编努力寻找整理中！
如果你已经找到好的解决方法，欢迎将解决方案带上本链接一起发送给小编。
小编邮箱:dio#foxmail.com (将#修改为@）