我尝试使用sparksql查询来自kafka的数据，使用zeppelin进行实时趋势分析，但没有成功。
下面是我在齐柏林飞艇中运行的简单代码片段

//Load Dependency
%dep 
    z.reset()
    z.addRepo("Spark Packages Repo").url("http://repo1.maven.org/maven2/")
    z.load("org.apache.spark:spark-streaming-kafka-0-8_2.11:2.0.1")
    z.load("org.apache.spark:spark-core_2.11:2.0.1")
    z.load("org.apache.spark:spark-sql_2.11:2.0.1")
    z.load("org.apache.spark:spark-streaming_2.11:2.0.1"

//simple streaming 
%spark
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkContext, SparkConf}
import org.apache.spark.sql.{Row, SQLContext}
import org.apache.spark.storage.StorageLevel
import org.apache.spark.streaming.kafka.KafkaUtils
import _root_.kafka.serializer.StringDecoder
import org.apache.spark.sql.SparkSession

val conf = new SparkConf()
    .setAppName("clickstream")
    .setMaster("local[*]")
    .set("spark.streaming.stopGracefullyOnShutdown", "true")
    .set("spark.driver.allowMultipleContexts","true")

val spark = SparkSession
  .builder()
  .appName("Spark SQL basic example")
  .config(conf)
  .getOrCreate()

val ssc = new StreamingContext(conf, Seconds(1))

val topicsSet = Set("timer")
val kafkaParams = Map[String, String]("metadata.broker.list" -> "192.168.25.1:9091,192.168.25.1:9092,192.168.25.1:9093")

val lines = KafkaUtils.createDirectStream[String, String, StringDecoder, StringDecoder](
                                   ssc, kafkaParams, topicsSet).map(_._2)

lines.window(Seconds(60)).foreachRDD{ rdd =>
    val clickDF = spark.read.json(rdd) //doesn't have to be json
    clickDF.createOrReplaceTempView("testjson1")
    //olderway
    //clickDF.registerTempTable("testjson2")
    clickDF.show

}

lines.print()
ssc.start()
ssc.awaitTermination()

我可以打印每个kafka消息，但是当我运行简单的sql时 %sql select * from testjson1 // or testjson2 ，我得到以下错误

java.util.NoSuchElementException: None.get
at scala.None$.get(Option.scala:347)
at scala.None$.get(Option.scala:345)
at org.apache.spark.storage.BlockInfoManager.releaseAllLocksForTask(BlockInfoManager.scala:343)
at org.apache.spark.storage.BlockManager.releaseAllLocksForTask(BlockManager.scala:646)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:281)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)

在本文中，正在查询流式处理后的数据（以twitter为例）。所以我认为Kafka流媒体应该是可能的。所以我想，也许，我做错了什么，或者遗漏了什么？
欢迎提出任何意见、建议、建议