我正在尝试使用spark解析xml文件中的数据 databrics 图书馆
这是我的密码：

import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.sql.SQLContext
import org.apache.spark.sql.functions
import java.text.Format
import org.apache.spark.sql.functions.concat_ws
import org.apache.spark.sql
import org.apache.spark.sql.types._
import org.apache.spark.sql.catalyst.plans.logical.With
import org.apache.spark.sql.functions.lit
import org.apache.spark.sql.functions.udf
import scala.sys.process._
import org.apache.spark.sql.functions.lit
import org.apache.spark.sql.functions.udf
import org.apache.spark.sql.functions._ 
object printschema 
{
   def main(args: Array[String]): Unit = 
  {
      val conf = new SparkConf().setAppName("printschema").setMaster("local")
      conf.set("spark.debug.maxToStringFields", "10000000") 
      val context = new SparkContext(conf)
      val sqlCotext = new SQLContext(context)
      import sqlCotext.implicits._
      val df = sqlCotext.read.format("com.databricks.spark.xml")
     .option("rowTag", "us-bibliographic-data-application")
     .option("treatEmptyValuesAsNulls", true)
     .load("/Users/praveen/Desktop/ipa0105.xml")
    val q1= df.withColumn("document",$"application-reference.document-id.doc-number".cast(sql.types.StringType))
           .withColumn("document_number",$"application-reference.document-id.doc-number".cast(sql.types.StringType)).select("document","document_number").collect()
           for(l<-q1)
           {
             val m1=l.get(0)
             val m2=l.get(1)
             println(m1,m2)
           }         
  }
}

当我在scalaide/intellij idea上运行代码时，它运行得很好，下面是我的输出。

(14789882,14789882)
(14755945,14755945)
(14755919,14755919)

但是，当我构建一个jar并使用 spark-submit 它只返回空值
输出：

NULL,NULL
NULL,NULL
NULL,NULL

以下是我的spark提交： ./spark-submit --jars /home/hadoop/spark-xml_2.11-0.4.0.jar --class inndata.praveen --master local[2] /home/hadoop/ip/target/scala-2.11/ip_2.11-1.0.jar