spark java 报错_python,spark_spark读入文件，报错 java.io.IOException:No input paths specified in job，python,s...

spark读入文件，报错 java.io.IOException:No input paths specified in job

想尝试着处理一下文本，结果都载入不进来。。。

文件路径肯定没问题

求大神指教

fileName = "file:///Users/liuchong/Desktop/Animal Farm.txt"

liuDF = sqlContext.read.text(fileName).select('value')

print type(liuDF)

liuDF.show()

报错：

---------------------------------------------------------------------------

Py4JJavaError Traceback (most recent call last)

in ()

5 liuDF = sqlContext.read.text(fileName).select('value')

6 print type(liuDF)

----> 7 liuDF.show()

8 #print liuDF.count()

9 def removePunctuation(column):

/databricks/spark/python/pyspark/sql/dataframe.py in show(self, n, truncate)

255 +---+-----+

256 """

--> 257 print(self._jdf.showString(n, truncate))

258

259 def __repr__(self):

/databricks/spark/python/lib/py4j-0.9-src.zip/py4j/java_gateway.py in __call__(self, *args)

811 answer = self.gateway_client.send_command(command)

812 return_value = get_return_value(

--> 813 answer, self.gateway_client, self.target_id, self.name)

814

815 for temp_arg in temp_args:

/databricks/spark/python/pyspark/sql/utils.py in deco(*a, **kw)

43 def deco(*a, **kw):

44 try:

---> 45 return f(*a, **kw)

46 except py4j.protocol.Py4JJavaError as e:

47 s = e.java_exception.toString()

/databricks/spark/python/lib/py4j-0.9-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)

306 raise Py4JJavaError(

307 "An error occurred while calling {0}{1}{2}.\n".

--> 308 format(target_id, ".", name), value)

309 else:

310 raise Py4JError(

Py4JJavaError: An error occurred while calling o77.showString.

: java.io.IOException: No input paths specified in job

at org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:156)

at org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:208)

at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:199)

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.sql.execution.SparkPlan.executeTake(SparkPlan.scala:190)

at org.apache.spark.sql.execution.Limit.executeCollect(basicOperators.scala:165)

at org.apache.spark.sql.execution.SparkPlan.executeCollectPublic(SparkPlan.scala:174)

at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1499)

at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1499)

at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)

at org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:2086)

at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$execute$1(DataFrame.scala:1498)

at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$collect(DataFrame.scala:1505)

at org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala:1375)

at org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala:1374)

at org.apache.spark.sql.DataFrame.withCallback(DataFrame.scala:2099)

at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1374)

at org.apache.spark.sql.DataFrame.take(DataFrame.scala:1456)

at org.apache.spark.sql.DataFrame.showString(DataFrame.scala:170)

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:497)

at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)

at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381)

at py4j.Gateway.invoke(Gateway.java:259)

at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)

at py4j.commands.CallCommand.execute(CallCommand.java:79)

at py4j.GatewayConnection.run(GatewayConnection.java:209)

at java.lang.Thread.run(Thread.java:745)

相关阅读:

两个文件夹中文件交换，存在同名文件

vue-cli 配置proxyTable 无法请求

如何用curl/wget或者其他方式抓取多次302重定向并要求登录的网页？

前端，研究生毕设求指点

nsdictionary转nsarray,要求一对key--value转为nasty的一个元素

ms-html标签去掉依附节点

React-Native中，组件要获取Redux Store的数据，只能手动调用connect方法吗？

JS 的一个设计上的bug(疑似)

express渲染网站首页时，怎样把多个表中的数据获取并传递给模版？

php用sp_executesql执行插入操作时成功返回-1，不返回受影响行数，怎么才能返回受影响行数？

Zabbix Latest data没有数据

获取protobuf 对象的编码

bootstrap-table怎么进行搜索？在官方文档中没有找到呢？

css布局问题

服务器上编码转换问题

C语言中，判断a+b与c的大小，if(a+b > c)为什么会判断错误？

vh计算的问题

用ajax把json抛到node后台，number类型变成了string怎么办

如何在video上显示视频的第一帧

thinkphp是怎么链接数据库的，文档上面显示操作表都是M()函数，之后进行连贯操作，