实战

回到首页 个人中心 反馈问题 注册登录
下载APP
首页 课程 实战 体系课 手记 专栏 慕课教程

执行accessDF.show时报错： java.lang.ArrayIndexOutOfBoundsException

来源：9-8 -数据清洗之日志解析

BaconNUDT

2017-07-19

printSchema可以正常运行，但是show的时候报错，在Linux中也是这样的错误

17/07/19 17:03:35 ERROR Executor: Exception in task 0.0 in stage 0.0 (TID 0)
java.lang.RuntimeException: Error while encoding: java.lang.ArrayIndexOutOfBoundsException: 7
if (assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt) null else staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 0, url), StringType), true) AS url#0
+- if (assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt) null else staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 0, url), StringType), true)
   :- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt
   :  :- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object)
   :  :  +- input[0, org.apache.spark.sql.Row, true]
   :  +- 0
   :- null
   +- staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 0, url), StringType), true)
      +- validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 0, url), StringType)
         +- getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 0, url)
            +- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object)
               +- input[0, org.apache.spark.sql.Row, true]

if (assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt) null else staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 1, cmsType), StringType), true) AS cmsType#1
+- if (assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt) null else staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 1, cmsType), StringType), true)
   :- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt
   :  :- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object)
   :  :  +- input[0, org.apache.spark.sql.Row, true]
   :  +- 1
   :- null
   +- staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 1, cmsType), StringType), true)
      +- validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 1, cmsType), StringType)
         +- getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 1, cmsType)
            +- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object)
               +- input[0, org.apache.spark.sql.Row, true]

if (assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt) null else validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 2, cmsId), LongType) AS cmsId#2L
+- if (assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt) null else validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 2, cmsId), LongType)
   :- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt
   :  :- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object)
   :  :  +- input[0, org.apache.spark.sql.Row, true]
   :  +- 2
   :- null
   +- validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 2, cmsId), LongType)
      +- getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 2, cmsId)
         +- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object)
            +- input[0, org.apache.spark.sql.Row, true]

if (assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt) null else validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 3, traffic), LongType) AS traffic#3L
+- if (assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt) null else validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 3, traffic), LongType)
   :- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt
   :  :- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object)
   :  :  +- input[0, org.apache.spark.sql.Row, true]
   :  +- 3
   :- null
   +- validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 3, traffic), LongType)
      +- getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 3, traffic)
         +- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object)
            +- input[0, org.apache.spark.sql.Row, true]

if (assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt) null else staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 4, ip), StringType), true) AS ip#4
+- if (assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt) null else staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 4, ip), StringType), true)
   :- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt
   :  :- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object)
   :  :  +- input[0, org.apache.spark.sql.Row, true]
   :  +- 4
   :- null
   +- staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 4, ip), StringType), true)
      +- validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 4, ip), StringType)
         +- getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 4, ip)
            +- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object)
               +- input[0, org.apache.spark.sql.Row, true]

if (assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt) null else staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 5, city), StringType), true) AS city#5
+- if (assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt) null else staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 5, city), StringType), true)
   :- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt
   :  :- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object)
   :  :  +- input[0, org.apache.spark.sql.Row, true]
   :  +- 5
   :- null
   +- staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 5, city), StringType), true)
      +- validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 5, city), StringType)
         +- getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 5, city)
            +- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object)
               +- input[0, org.apache.spark.sql.Row, true]

if (assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt) null else staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 6, time), StringType), true) AS time#6
+- if (assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt) null else staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 6, time), StringType), true)
   :- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt
   :  :- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object)
   :  :  +- input[0, org.apache.spark.sql.Row, true]
   :  +- 6
   :- null
   +- staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 6, time), StringType), true)
      +- validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 6, time), StringType)
         +- getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 6, time)
            +- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object)
               +- input[0, org.apache.spark.sql.Row, true]

if (assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt) null else staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 7, day), StringType), true) AS day#7
+- if (assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt) null else staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 7, day), StringType), true)
   :- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt
   :  :- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object)
   :  :  +- input[0, org.apache.spark.sql.Row, true]
   :  +- 7
   :- null
   +- staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 7, day), StringType), true)
      +- validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 7, day), StringType)
         +- getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 7, day)
            +- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object)
               +- input[0, org.apache.spark.sql.Row, true]

	at org.apache.spark.sql.catalyst.encoders.ExpressionEncoder.toRow(ExpressionEncoder.scala:293)
	at org.apache.spark.sql.SparkSession$$anonfun$3.apply(SparkSession.scala:547)
	at org.apache.spark.sql.SparkSession$$anonfun$3.apply(SparkSession.scala:547)
	at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
	at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
	at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:232)
	at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:225)
	at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:826)
	at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:826)
	at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
	at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
	at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
	at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
	at org.apache.spark.scheduler.Task.run(Task.scala:99)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
	at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.ArrayIndexOutOfBoundsException: 7
	at org.apache.spark.sql.catalyst.expressions.GenericRow.get(rows.scala:173)
	at org.apache.spark.sql.Row$class.isNullAt(Row.scala:191)
	at org.apache.spark.sql.catalyst.expressions.GenericRow.isNullAt(rows.scala:165)
	at org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificUnsafeProjection.evalIfCondExpr7$(Unknown Source)
	at org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificUnsafeProjection.apply_2$(Unknown Source)
	at org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificUnsafeProjection.apply(Unknown Source)
	at org.apache.spark.sql.catalyst.encoders.ExpressionEncoder.toRow(ExpressionEncoder.scala:290)
	... 17 more
17/07/19 17:03:35 WARN TaskSetManager: Lost task 0.0 in stage 0.0 (TID 0, localhost, executor driver): java.lang.RuntimeException: Error while encoding: java.lang.ArrayIndexOutOfBoundsException: 7
if (assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt) null else staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 0, url), StringType), true) AS url#0
+- if (assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt) null else staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object), 0, url), StringType), true)
   :- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object).isNullAt
   :  :- assertnotnull(input[0, org.apache.spark.sql.Row, true], top level row object)
   :  :  +- input[0, org.apache.spark.sql.Row, true]
   :  +- 0


写回答

1回答

BaconNUDT

提问者

2017-07-19

自己检查了一下，数组下标的确越界了，在Row()的时候落下字段了。

0
1
Michael_PK
自己能定位到错误然后改正，也是能力的提升，大家都是在不断躺坑中成长
2017-07-19
共1条回复

以慕课网日志分析为例 进入大数据Spark SQL的世界

快速转型大数据：Hadoop，Hive，SparkSQL步步为赢

1644 学习 · 1129 问题

查看课程

相似问题

DataFrame在输出时如何关闭类型推断？？

回答 3

执行spark.table("emp").show时报错

回答 2

执行hivecontext报错了

回答 1

执行saveAsTextFile时出错

回答 1

将数据清洗存储到目标地址报错

回答 3

打开慕课网App查看更多内容