使用SparkSQL SAS（sas7bdat）输入库时遇到问题

Question

我正在使用以下的spark包读取SAS文件，下面是我正在使用的代码以及我得到的错误。我正在使用数据库云。

import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.mapreduce.Job
import org.apache.spark.sql.SQLContext
import com.databricks.spark.csv._
import com.github.saurfang.sas.spark._
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat
val cars = sqlContext.sasFile("/mnt/networkimp/Testfiles/dsc_optima.sas7bdat")
cars.select("*").saveAsCsvFile("dsc_optima.csv")'`

输出：

java.lang.IncompatibleClassChangeError: Found class org.apache.hadoop.mapreduce.JobContext, but interface was expected
    at com.github.saurfang.sas.mapreduce.SasInputFormat.isSplitable(SasInputFormat.scala:23)
    at org.apache.hadoop.mapreduce.lib.input.FileInputFormat.getSplits(FileInputFormat.java:258)
    at org.apache.spark.rdd.NewHadoopRDD.getPartitions(NewHadoopRDD.scala:95)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217)
    at scala.Option.getOrElse(Option.scala:120)
    at org.apache.spark.rdd.RDD.partitions(RDD.scala:217)
    at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:32)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217)
    at scala.Option.getOrElse(Option.scala:120)
    at org.apache.spark.rdd.RDD.partitions(RDD.scala:217)
    at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:32)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217)
    at scala.Option.getOrElse(Option.scala:120)
    at org.apache.spark.rdd.RDD.partitions(RDD.scala:217)
    at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:32)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217)
    at scala.Option.getOrElse(Option.scala:120)
    at org.apache.spark.rdd.RDD.partitions(RDD.scala:217)
    at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:32)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217)
    at scala.Option.getOrElse(Option.scala:120)
    at org.apache.spark.rdd.RDD.partitions(RDD.scala:217)
    at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:32)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:219)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:217)
    at scala.Option.getOrElse(Option.scala:120)
    at org.apache.spark.rdd.RDD.partitions(RDD.scala:217)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1502)
    at org.apache.spark.rdd.PairRDDFunctions.saveAsHadoopDataset(PairRDDFunctions.scala:1087)
    at org.apache.spark.rdd.PairRDDFunctions.saveAsHadoopFile(PairRDDFunctions.scala:954)
    at org.apache.spark.rdd.PairRDDFunctions.saveAsHadoopFile(PairRDDFunctions.scala:863)
    at org.apache.spark.rdd.RDD.saveAsTextFile(RDD.scala:1290)
    at com.databricks.spark.csv.package$CsvSchemaRDD.saveAsCsvFile(package.scala:125)