已解决的属性＃s缺少c1＃0，c2＃1在运营商！项目[c1＃0，c2＃1，月＃2 AS月＃7];

Question

我正在尝试根据某些分隔符或正则表达式模式拆分列。 这是输入文件。

c1             c2
jan$100     u1*21/10/15
feb$200     u2*30/12/15
mar$300$400  u1*26/2/16

无法找到错误原因。这是原始代码。

 override def execute(dataFrames: List[DataFrame], sc: SparkContext, sqlContext: SQLContext, params: String, productId: Int) : List[DataFrame] = {
    val explodeData = parse(params).extractOpt[ExplodeDataSchema].get
    logger.info(s"EXPLODE - explodeData --> $explodeData")

    val inputDf = dataFrames.head

    val outputDfList = explodeData.explodeExpr flatMap{
      explodeItem =>
        explodeItem.outputCol map{
          outputColItem =>
            logger.info("(split("+explodeItem.inputCol+", '"+explodeItem.delimeter+"'))["+outputColItem.index+"]")
            (outputColItem.outputCol,inputDf.select(expr("(split("+explodeItem.inputCol+", '"+explodeItem.delimeter+"'))["+outputColItem.index+"]").cast("string").as(outputColItem.outputCol)))
        }
    }

    val outCol = outputDfList map{
      x => x._1
    }
    logger.info(outCol.toString)

    var outputDf = inputDf
    logger.info(outputDf.columns.toList.toString)
    logger.info(outputDf.schema.toString)

    for(i <- outputDfList){
      logger.info(i._1)
      logger.info(i._2.columns.toList.toString)
      logger.info(i._2.schema.toString)
      //error comes in this line
      outputDf = outputDf.withColumn(i._1, i._2.col(i._1))
    }
    List(outputDf)
  }
}

这些是相关的日志声明。

17/02/06 10:21:10 INFO Explode$: EXPLODE - explodeData --> ExplodeDataSchema(List(SchemaDetectData(s3n://com.tookitaki.dev.product-2/uploads/generic_data/explodedata3.csv,None,None)),List(ExplodeExpr(c1,\$,List(OutputExpr(0,month), OutputExpr(1,sales), OutputExpr(2,sales2))), ExplodeExpr(c2,\*,List(OutputExpr(0,user), OutputExpr(1,date)))))
17/02/06 10:21:10 INFO Explode$: (split(c1, '\$'))[0]
17/02/06 10:21:10 INFO Explode$: (split(c1, '\$'))[1]
17/02/06 10:21:10 INFO Explode$: (split(c1, '\$'))[2]
17/02/06 10:21:11 INFO Explode$: (split(c2, '\*'))[0]
17/02/06 10:21:11 INFO Explode$: (split(c2, '\*'))[1]
17/02/06 10:21:11 INFO Explode$: List(month, sales, sales2, user, date)
17/02/06 10:21:11 INFO Explode$: List(c1, c2)
17/02/06 10:21:11 INFO Explode$: StructType(StructField(c1,StringType,true), StructField(c2,StringType,true))
17/02/06 10:21:11 INFO Explode$: month
17/02/06 10:21:11 INFO Explode$: List(month)
17/02/06 10:21:11 INFO Explode$: StructType(StructField(month,StringType,true))
17/02/06 10:21:11 ERROR Main$: resolved attribute(s) month#2 missing from c1#0,c2#1 in operator !Project [c1#0,c2#1,month#2 AS month#7];
org.apache.spark.sql.AnalysisException: resolved attribute(s) month#2 missing from c1#0,c2#1 in operator !Project [c1#0,c2#1,month#2 AS month#7];
    at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.failAnalysis(CheckAnalysis.scala:38)
    at org.apache.spark.sql.catalyst.analysis.Analyzer.failAnalysis(Analyzer.scala:44)
    at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:183)
    at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:50)
    at org.apache.spark.sql.catalyst.trees.TreeNode.foreachUp(TreeNode.scala:121)
    at org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.checkAnalysis(CheckAnalysis.scala:50)
    at org.apache.spark.sql.catalyst.analysis.Analyzer.checkAnalysis(Analyzer.scala:44)
    at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:34)
    at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:133)
    at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$withPlan(DataFrame.scala:2126)
    at org.apache.spark.sql.DataFrame.select(DataFrame.scala:707)
    at org.apache.spark.sql.DataFrame.withColumn(DataFrame.scala:1188)
    at com.tookitaki.aip.transformation.operations.Explode$$anonfun$execute$1.apply(Explode.scala:67)
    at com.tookitaki.aip.transformation.operations.Explode$$anonfun$execute$1.apply(Explode.scala:62)
    at scala.collection.immutable.List.foreach(List.scala:318)
    at com.tookitaki.aip.transformation.operations.Explode$.execute(Explode.scala:62)
    at com.tookitaki.aip.transformation.ExecuteTransformationJob$.run(ExecuteTransformationJob.scala:27)
    at com.tookitaki.aip.transformation.Main$.processTransformationJobs(Main.scala:111)
    at com.tookitaki.aip.transformation.Main$.main(Main.scala:61)
    at com.tookitaki.aip.transformation.Main.main(Main.scala)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:498)
    at org.apache.spark.deploy.worker.DriverWrapper$.main(DriverWrapper.scala:58)
    at org.apache.spark.deploy.worker.DriverWrapper.main(DriverWrapper.scala)
17/02/06 10:21:11 INFO Main$: Job failed

请帮助删除错误。