【发布时间】:2015-09-08 23:01:24
【问题描述】:
我在开始时创建“gpsLookUpTable”并将其持久化,这样我就不需要一遍又一遍地拉它来进行映射。但是,当我尝试在 foreach 中访问它时,我得到空指针异常。感谢任何帮助。
下面是sn-ps代码:
def main(args: Array[String]): Unit = {
val conf = new SparkConf() ...
val sc = new SparkContext(conf)
val ssc = new StreamingContext(sc, Seconds(20))
val sqc = new SQLContext(sc)
//////Trying to cache table here to use it below
val gpsLookUpTable = MapInput.cacheMappingTables(sc, sqc).persist(StorageLevel.MEMORY_AND_DISK_SER_2)
//sc.broadcast(gpsLookUpTable)
ssc.textFileStream("hdfs://localhost:9000/inputDirectory/")
.foreachRDD { rdd =>
if (!rdd.partitions.isEmpty) {
val allRows = sc.textFile("hdfs://localhost:9000/supportFiles/GeoHashLookUpTable")
sqc.read.json(allRows).registerTempTable("GeoHashLookUpTable")
val header = rdd.first().split(",")
val rowsWithoutHeader = Utils.dropHeader(rdd)
rowsWithoutHeader.foreach { row =>
val singleRowArray = row.split(",")
singleRowArray.foreach(println)
(header, singleRowArray).zipped
.foreach { (x, y) =>
///Trying to access persisted table but getting null pointer exception
val selectedRow = gpsLookUpTable
.filter("geoCode LIKE '" + GeoHash.subString(lattitude, longitude) + "%'")
.withColumn("Distance", calculateDistance(col("Lat"), col("Lon")))
.orderBy("Distance")
.select("TrackKM", "TrackName").take(1)
if (selectedRow.length != 0) {
// do something
}
else {
// do something
}
}
} }}
【问题讨论】:
标签: apache-spark apache-spark-sql spark-streaming