xml输出格式

ni65a41a  于 2021-06-02  发布在  Hadoop
关注(0)|答案(0)|浏览(258)

我正在尝试使用sparkscala在spark中实现xml输出格式。我已经用hadoop编写了一个自定义输出格式，并且能够成功地实现它。但是，当我尝试在spark中实现时，我得到了一个错误：

java.io.NotSerializableException: org.apache.hadoop.io.Text
Serialization stack:
    - object not serializable (class: org.apache.hadoop.io.Text, value: hadoop)
    at org.apache.spark.serializer.SerializationDebugger$.improveException(SerializationDebugger.scala:40)
    at org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:47)
    at org.apache.spark.serializer.SerializationStream.writeKey(Serializer.scala:145)
    at org.apache.spark.storage.DiskBlockObjectWriter.write(DiskBlockObjectWriter.scala:180)
    at org.apache.spark.util.collection.WritablePartitionedPairCollection$$anon$1.writeNext(WritablePartitionedPairCollection.scala:55)
    at org.apache.spark.util.collection.ExternalSorter.writePartitionedFile(ExternalSorter.scala:681)
    at org.apache.spark.shuffle.sort.SortShuffleWriter.write(SortShuffleWriter.scala:80)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
    at org.apache.spark.scheduler.Task.run(Task.scala:88)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
    at java.lang.Thread.run(Thread.java:745)
16/06/17 18:22:04 ERROR Executor: Exception in task 0.0 in stage 30.0 (TID 34)
java.io.NotSerializableException: org.apache.hadoop.io.Text
Serialization stack:
    - object not serializable (class: org.apache.hadoop.io.Text, value: Hadoop)
    at org.apache.spark.serializer.SerializationDebugger$.improveException(SerializationDebugger.scala:40)
    at org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:47)
    at org.apache.spark.serializer.SerializationStream.writeKey(Serializer.scala:145)
    at org.apache.spark.storage.DiskBlockObjectWriter.write(DiskBlockObjectWriter.scala:180)
    at org.apache.spark.util.collection.WritablePartitionedPairCollection$$anon$1.writeNext(WritablePartitionedPairCollection.scala:55)
    at org.apache.spark.util.collection.ExternalSorter.writePartitionedFile(ExternalSorter.scala:681)
    at org.apache.spark.shuffle.sort.SortShuffleWriter.write(SortShuffleWriter.scala:80)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
    at org.apache.spark.scheduler.Task.run(Task.scala:88)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
    at java.lang.Thread.run(Thread.java:745)
16/06/17 18:22:04 ERROR TaskSetManager: Task 0.0 in stage 30.0 (TID 34) had a not serializable result: org.apache.hadoop.io.Text
Serialization stack:
    - object not serializable (class: org.apache.hadoop.io.Text, value: Hadoop); not retrying
16/06/17 18:22:04 ERROR TaskSetManager: Task 1.0 in stage 30.0 (TID 35) had a not serializable result: org.apache.hadoop.io.Text
Serialization stack:
    - object not serializable (class: org.apache.hadoop.io.Text, value: hadoop); not retrying
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0.0 in stage 30.0 (TID 34) had a not serializable result: org.apache.hadoop.io.Text
Serialization stack:
    - object not serializable (class: org.apache.hadoop.io.Text, value: Hadoop)
    at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1283)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1271)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1270)
    at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
    at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
    at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1270)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
    at scala.Option.foreach(Option.scala:236)
    at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1496)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1458)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1447)
    at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
    at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1822)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1835)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1848)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1919)
    at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:905)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:108)
    at org.apache.spark.rdd.RDD.withScope(RDD.scala:306)
    at org.apache.spark.rdd.RDD.collect(RDD.scala:904)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:35)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:40)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:42)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:44)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:46)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:48)
    at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:50)
    at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:52)
    at $iwC$$iwC$$iwC$$iwC.<init>(<console>:54)
    at $iwC$$iwC$$iwC.<init>(<console>:56)
    at $iwC$$iwC.<init>(<console>:58)
    at $iwC.<init>(<console>:60)
    at <init>(<console>:62)
    at .<init>(<console>:66)
    at .<clinit>(<console>)
    at .<init>(<console>:7)
    at .<clinit>(<console>)
    at $print(<console>)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:606)
    at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065)
    at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1340)
    at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840)
    at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871)
    at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819)
    at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857)
    at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902)
    at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814)
    at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657)
    at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665)
    at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670)
    at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997)
    at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
    at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945)
    at scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
    at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945)
    at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059)
    at org.apache.spark.repl.Main$.main(Main.scala:31)
    at org.apache.spark.repl.Main.main(Main.scala)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:606)
    at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:672)
    at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:180)
    at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:205)
    at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:120)
    at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)

我也使用了kyro序列化，但是没有用，我为自定义输出格式类构建了一个jar文件，并成功地将其包含在sparkshell中。这是我用过的代码。

:cp custom_out.jar
val sparkConf = new SparkConf().setAppName("myAPP").setMaster("local");
sparkConf.registerKryoClasses(Array(classOf[org.apache.hadoop.io.IntWritable], classOf[org.apache.hadoop.io.Text],classOf[XMLOutputFormat]))
val textFile = sc.textFile("/home/kiran/word_count_input")
val counts = textFile.flatMap(line => line.split(" ")).map(word => (new Text(word), 1)).reduceByKey(_ + _)
val test: RDD[(Text,IntWritable)] =counts.map(x => (x._1,new IntWritable(x._2)))
test.collect

您可以从下面的链接下载jar文件https://drive.google.com/open?id=0byjlbtmjojjzzxbxuvbkzw95u2c

Javahadoopscalaapache-spark

暂无答案！

目前还没有任何答案，快来回答吧！

我来回答

相关问题

    查看更多

    热门标签

    更多
    JavaquerypythonNode开发语言requestUtil数据库Table后端算法LoggerMessageElementParser

    最新问答

    更多
    • 蜀ICP备2022004421号-2 NULL123 https://www.null123.com © All rights reserved
    • 本站内容来源互联网,如果侵犯您的权益请联系我们删除, 联系方式：448109455@qq.com