es:2.2.0
spark :1.6.1
hadoop:2.6.0
问题描述:spark读取指定索引/类型的数据,其中有自定义格式的日期数据,读取该日期时报异常,日期定义格式:"start_time" : {
"type" : "date",
"format" : "yyyy-MM-dd HH:mm:ss"
},
异常信息:
16/06/12 15:54:17 INFO DAGScheduler: Job 0 failed: saveAsTextFile at BrowersDataJob.java:84, took 6.235458 s
Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 4 times, most recent failure: Lost task 0.3 in stage 0.0 (TID 6, 172.16.7.82): org.elasticsearch.hadoop.rest.EsHadoopParsingException: Cannot parse value [2016-05-12 05:49:07] for field [start_time]
at org.elasticsearch.hadoop.serialization.ScrollReader.read(ScrollReader.java:701)
at org.elasticsearch.hadoop.serialization.ScrollReader.map(ScrollReader.java:794)
at org.elasticsearch.hadoop.serialization.ScrollReader.read(ScrollReader.java:692)
at org.elasticsearch.hadoop.serialization.ScrollReader.readHitAsMap(ScrollReader.java:457)
at org.elasticsearch.hadoop.serialization.ScrollReader.readHit(ScrollReader.java:382)
at org.elasticsearch.hadoop.serialization.ScrollReader.read(ScrollReader.java:277)
at org.elasticsearch.hadoop.serialization.ScrollReader.read(ScrollReader.java:250)
at org.elasticsearch.hadoop.rest.RestRepository.scroll(RestRepository.java:456)
at org.elasticsearch.hadoop.rest.ScrollQuery.hasNext(ScrollQuery.java:86)
at org.elasticsearch.spark.rdd.AbstractEsRDDIterator.hasNext(AbstractEsRDDIterator.scala:43)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:126)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: org.elasticsearch.hadoop.EsHadoopIllegalArgumentException: Cannot invoke method public org.joda.time.DateTime org.joda.time.format.DateTimeFormatter.parseDateTime(java.lang.String)
at org.elasticsearch.hadoop.util.ReflectionUtils.invoke(ReflectionUtils.java:93)
at org.elasticsearch.hadoop.util.DateUtils$JodaTime.parseDate(DateUtils.java:105)
at org.elasticsearch.hadoop.util.DateUtils.parseDate(DateUtils.java:122)
at org.elasticsearch.hadoop.serialization.builder.JdkValueReader.parseDate(JdkValueReader.java:406)
at org.elasticsearch.hadoop.serialization.builder.JdkValueReader.date(JdkValueReader.java:394)
at org.elasticsearch.hadoop.serialization.builder.JdkValueReader.readValue(JdkValueReader.java:84)
at org.elasticsearch.hadoop.serialization.ScrollReader.parseValue(ScrollReader.java:714)
at org.elasticsearch.hadoop.serialization.ScrollReader.read(ScrollReader.java:699)
... 19 more
Caused by: java.lang.reflect.InvocationTargetException
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.elasticsearch.hadoop.util.ReflectionUtils.invoke(ReflectionUtils.java:91)
... 26 more
Caused by: java.lang.IllegalArgumentException: Invalid format: "2016-05-12 05:49:07" is malformed at " 05:49:07"
at org.joda.time.format.DateTimeFormatter.parseDateTime(DateTimeFormatter.java:945)
... 31 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1431)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1845)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1922)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1.apply$mcV$sp(PairRDDFunctions.scala:1213)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1.apply(PairRDDFunctions.scala:1156)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1.apply(PairRDDFunctions.scala:1156)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.PairRDDFunctions.saveAsHadoopDataset(PairRDDFunctions.scala:1156)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$4.apply$mcV$sp(PairRDDFunctions.scala:1060)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$4.apply(PairRDDFunctions.scala:1026)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$4.apply(PairRDDFunctions.scala:1026)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.PairRDDFunctions.saveAsHadoopFile(PairRDDFunctions.scala:1026)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$1.apply$mcV$sp(PairRDDFunctions.scala:952)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$1.apply(PairRDDFunctions.scala:952)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$1.apply(PairRDDFunctions.scala:952)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.PairRDDFunctions.saveAsHadoopFile(PairRDDFunctions.scala:951)
at org.apache.spark.rdd.RDD$$anonfun$saveAsTextFile$1.apply$mcV$sp(RDD.scala:1457)
at org.apache.spark.rdd.RDD$$anonfun$saveAsTextFile$1.apply(RDD.scala:1436)
at org.apache.spark.rdd.RDD$$anonfun$saveAsTextFile$1.apply(RDD.scala:1436)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.RDD.saveAsTextFile(RDD.scala:1436)
at org.apache.spark.api.java.JavaRDDLike$class.saveAsTextFile(JavaRDDLike.scala:507)
at org.apache.spark.api.java.AbstractJavaRDDLike.saveAsTextFile(JavaRDDLike.scala:46)
at com.djdg.bigdata.dataclean.job.BrowersDataJob.excute(BrowersDataJob.java:84)
at com.djdg.bigdata.dataclean.job.BrowersDataJob.main(BrowersDataJob.java:98)
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$$runMain(SparkSubmit.scala:731)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: org.elasticsearch.hadoop.rest.EsHadoopParsingException: Cannot parse value [2016-05-12 05:49:07] for field [start_time]
at org.elasticsearch.hadoop.serialization.ScrollReader.read(ScrollReader.java:701)
at org.elasticsearch.hadoop.serialization.ScrollReader.map(ScrollReader.java:794)
at org.elasticsearch.hadoop.serialization.ScrollReader.read(ScrollReader.java:692)
at org.elasticsearch.hadoop.serialization.ScrollReader.readHitAsMap(ScrollReader.java:457)
at org.elasticsearch.hadoop.serialization.ScrollReader.readHit(ScrollReader.java:382)
at org.elasticsearch.hadoop.serialization.ScrollReader.read(ScrollReader.java:277)
at org.elasticsearch.hadoop.serialization.ScrollReader.read(ScrollReader.java:250)
at org.elasticsearch.hadoop.rest.RestRepository.scroll(RestRepository.java:456)
at org.elasticsearch.hadoop.rest.ScrollQuery.hasNext(ScrollQuery.java:86)
at org.elasticsearch.spark.rdd.AbstractEsRDDIterator.hasNext(AbstractEsRDDIterator.scala:43)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:126)
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:89)
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)
Caused by: org.elasticsearch.hadoop.EsHadoopIllegalArgumentException: Cannot invoke method public org.joda.time.DateTime org.joda.time.format.DateTimeFormatter.parseDateTime(java.lang.String)
at org.elasticsearch.hadoop.util.ReflectionUtils.invoke(ReflectionUtils.java:93)
at org.elasticsearch.hadoop.util.DateUtils$JodaTime.parseDate(DateUtils.java:105)
at org.elasticsearch.hadoop.util.DateUtils.parseDate(DateUtils.java:122)
at org.elasticsearch.hadoop.serialization.builder.JdkValueReader.parseDate(JdkValueReader.java:406)
at org.elasticsearch.hadoop.serialization.builder.JdkValueReader.date(JdkValueReader.java:394)
at org.elasticsearch.hadoop.serialization.builder.JdkValueReader.readValue(JdkValueReader.java:84)
at org.elasticsearch.hadoop.serialization.ScrollReader.parseValue(ScrollReader.java:714)
at org.elasticsearch.hadoop.serialization.ScrollReader.read(ScrollReader.java:699)
... 19 more
Caused by: java.lang.reflect.InvocationTargetException
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.elasticsearch.hadoop.util.ReflectionUtils.invoke(ReflectionUtils.java:91)
... 26 more
Caused by: java.lang.IllegalArgumentException: Invalid format: "2016-05-12 05:49:07" is malformed at " 05:49:07"
at org.joda.time.format.DateTimeFormatter.parseDateTime(DateTimeFormatter.java:945)
... 31 more
spark :1.6.1
hadoop:2.6.0
问题描述:spark读取指定索引/类型的数据,其中有自定义格式的日期数据,读取该日期时报异常,日期定义格式:"start_time" : {
"type" : "date",
"format" : "yyyy-MM-dd HH:mm:ss"
},
异常信息:
16/06/12 15:54:17 INFO DAGScheduler: Job 0 failed: saveAsTextFile at BrowersDataJob.java:84, took 6.235458 s
Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 4 times, most recent failure: Lost task 0.3 in stage 0.0 (TID 6, 172.16.7.82): org.elasticsearch.hadoop.rest.EsHadoopParsingException: Cannot parse value [2016-05-12 05:49:07] for field [start_time]
at org.elasticsearch.hadoop.serialization.ScrollReader.read(ScrollReader.java:701)
at org.elasticsearch.hadoop.serialization.ScrollReader.map(ScrollReader.java:794)
at org.elasticsearch.hadoop.serialization.ScrollReader.read(ScrollReader.java:692)
at org.elasticsearch.hadoop.serialization.ScrollReader.readHitAsMap(ScrollReader.java:457)
at org.elasticsearch.hadoop.serialization.ScrollReader.readHit(ScrollReader.java:382)
at org.elasticsearch.hadoop.serialization.ScrollReader.read(ScrollReader.java:277)
at org.elasticsearch.hadoop.serialization.ScrollReader.read(ScrollReader.java:250)
at org.elasticsearch.hadoop.rest.RestRepository.scroll(RestRepository.java:456)
at org.elasticsearch.hadoop.rest.ScrollQuery.hasNext(ScrollQuery.java:86)
at org.elasticsearch.spark.rdd.AbstractEsRDDIterator.hasNext(AbstractEsRDDIterator.scala:43)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:126)
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:89)
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)
Caused by: org.elasticsearch.hadoop.EsHadoopIllegalArgumentException: Cannot invoke method public org.joda.time.DateTime org.joda.time.format.DateTimeFormatter.parseDateTime(java.lang.String)
at org.elasticsearch.hadoop.util.ReflectionUtils.invoke(ReflectionUtils.java:93)
at org.elasticsearch.hadoop.util.DateUtils$JodaTime.parseDate(DateUtils.java:105)
at org.elasticsearch.hadoop.util.DateUtils.parseDate(DateUtils.java:122)
at org.elasticsearch.hadoop.serialization.builder.JdkValueReader.parseDate(JdkValueReader.java:406)
at org.elasticsearch.hadoop.serialization.builder.JdkValueReader.date(JdkValueReader.java:394)
at org.elasticsearch.hadoop.serialization.builder.JdkValueReader.readValue(JdkValueReader.java:84)
at org.elasticsearch.hadoop.serialization.ScrollReader.parseValue(ScrollReader.java:714)
at org.elasticsearch.hadoop.serialization.ScrollReader.read(ScrollReader.java:699)
... 19 more
Caused by: java.lang.reflect.InvocationTargetException
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.elasticsearch.hadoop.util.ReflectionUtils.invoke(ReflectionUtils.java:91)
... 26 more
Caused by: java.lang.IllegalArgumentException: Invalid format: "2016-05-12 05:49:07" is malformed at " 05:49:07"
at org.joda.time.format.DateTimeFormatter.parseDateTime(DateTimeFormatter.java:945)
... 31 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1431)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1845)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1922)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1.apply$mcV$sp(PairRDDFunctions.scala:1213)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1.apply(PairRDDFunctions.scala:1156)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1.apply(PairRDDFunctions.scala:1156)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.PairRDDFunctions.saveAsHadoopDataset(PairRDDFunctions.scala:1156)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$4.apply$mcV$sp(PairRDDFunctions.scala:1060)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$4.apply(PairRDDFunctions.scala:1026)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$4.apply(PairRDDFunctions.scala:1026)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.PairRDDFunctions.saveAsHadoopFile(PairRDDFunctions.scala:1026)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$1.apply$mcV$sp(PairRDDFunctions.scala:952)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$1.apply(PairRDDFunctions.scala:952)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopFile$1.apply(PairRDDFunctions.scala:952)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.PairRDDFunctions.saveAsHadoopFile(PairRDDFunctions.scala:951)
at org.apache.spark.rdd.RDD$$anonfun$saveAsTextFile$1.apply$mcV$sp(RDD.scala:1457)
at org.apache.spark.rdd.RDD$$anonfun$saveAsTextFile$1.apply(RDD.scala:1436)
at org.apache.spark.rdd.RDD$$anonfun$saveAsTextFile$1.apply(RDD.scala:1436)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.RDD.saveAsTextFile(RDD.scala:1436)
at org.apache.spark.api.java.JavaRDDLike$class.saveAsTextFile(JavaRDDLike.scala:507)
at org.apache.spark.api.java.AbstractJavaRDDLike.saveAsTextFile(JavaRDDLike.scala:46)
at com.djdg.bigdata.dataclean.job.BrowersDataJob.excute(BrowersDataJob.java:84)
at com.djdg.bigdata.dataclean.job.BrowersDataJob.main(BrowersDataJob.java:98)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: org.elasticsearch.hadoop.rest.EsHadoopParsingException: Cannot parse value [2016-05-12 05:49:07] for field [start_time]
at org.elasticsearch.hadoop.serialization.ScrollReader.read(ScrollReader.java:701)
at org.elasticsearch.hadoop.serialization.ScrollReader.map(ScrollReader.java:794)
at org.elasticsearch.hadoop.serialization.ScrollReader.read(ScrollReader.java:692)
at org.elasticsearch.hadoop.serialization.ScrollReader.readHitAsMap(ScrollReader.java:457)
at org.elasticsearch.hadoop.serialization.ScrollReader.readHit(ScrollReader.java:382)
at org.elasticsearch.hadoop.serialization.ScrollReader.read(ScrollReader.java:277)
at org.elasticsearch.hadoop.serialization.ScrollReader.read(ScrollReader.java:250)
at org.elasticsearch.hadoop.rest.RestRepository.scroll(RestRepository.java:456)
at org.elasticsearch.hadoop.rest.ScrollQuery.hasNext(ScrollQuery.java:86)
at org.elasticsearch.spark.rdd.AbstractEsRDDIterator.hasNext(AbstractEsRDDIterator.scala:43)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:126)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: org.elasticsearch.hadoop.EsHadoopIllegalArgumentException: Cannot invoke method public org.joda.time.DateTime org.joda.time.format.DateTimeFormatter.parseDateTime(java.lang.String)
at org.elasticsearch.hadoop.util.ReflectionUtils.invoke(ReflectionUtils.java:93)
at org.elasticsearch.hadoop.util.DateUtils$JodaTime.parseDate(DateUtils.java:105)
at org.elasticsearch.hadoop.util.DateUtils.parseDate(DateUtils.java:122)
at org.elasticsearch.hadoop.serialization.builder.JdkValueReader.parseDate(JdkValueReader.java:406)
at org.elasticsearch.hadoop.serialization.builder.JdkValueReader.date(JdkValueReader.java:394)
at org.elasticsearch.hadoop.serialization.builder.JdkValueReader.readValue(JdkValueReader.java:84)
at org.elasticsearch.hadoop.serialization.ScrollReader.parseValue(ScrollReader.java:714)
at org.elasticsearch.hadoop.serialization.ScrollReader.read(ScrollReader.java:699)
... 19 more
Caused by: java.lang.reflect.InvocationTargetException
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.elasticsearch.hadoop.util.ReflectionUtils.invoke(ReflectionUtils.java:91)
... 26 more
Caused by: java.lang.IllegalArgumentException: Invalid format: "2016-05-12 05:49:07" is malformed at " 05:49:07"
at org.joda.time.format.DateTimeFormatter.parseDateTime(DateTimeFormatter.java:945)
... 31 more
1 个回复
gene
赞同来自: sunyizhen