我正在尝试使用scala将SparkRDD写入HBase表(之前没有使用过)。整个代码是这样的:
import org.apache.hadoop.hbase.client.{HBaseAdmin, Result}
import org.apache.hadoop.hbase.{HBaseConfiguration, HTableDescriptor}
import org.apache.hadoop.hbase.mapreduce.TableInputFormat
import org.apache.hadoop.hbase.io.ImmutableBytesWritable
import scala.collection.JavaConverters._
import org.apache.hadoop.hbase.util.Bytes
import org.apache.spark._
import org.apache.hadoop.mapred.JobConf
import org.apache.spark.rdd.PairRDDFunctions
import org.apache.spark.SparkContext._
import org.apache.hadoop.mapred.Partitioner;
import org.apache.hadoop.hbase.mapred.TableOutputFormat
import org.apache.hadoop.hbase.client._
object HBaseWrite {
def main(args: Array[String]) {
val sparkConf = new SparkConf().setAppName("HBaseWrite").setMaster("local").set("spark.driver.allowMultipleContexts","true").set("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
val sc = new SparkContext(sparkConf)
val conf = HBaseConfiguration.create()
val outputTable = "tablename"
System.setProperty("user.name", "hdfs")
System.setProperty("HADOOP_USER_NAME", "hdfs")
conf.set("hbase.master", "localhost:60000")
conf.setInt("timeout", 120000)
conf.set("hbase.zookeeper.quorum", "localhost")
conf.set("zookeeper.znode.parent", "/hbase-unsecure")
conf.setInt("hbase.client.scanner.caching", 10000)
sparkConf.registerKryoClasses(Array(classOf[org.apache.hadoop.hbase.client.Result]))
val jobConfig: JobConf = new JobConf(conf,this.getClass)
jobConfig.setOutputFormat(classOf[TableOutputFormat])
jobConfig.set(TableOutputFormat.OUTPUT_TABLE,outputTable)
val x = 12
val y = 15
val z = 25
var newarray = Array(x,y,z)
val newrddtohbase = sc.parallelize(newarray)
def convert(a:Int) : Tuple2[ImmutableBytesWritable,Put] = {
val p = new Put(Bytes.toBytes(a))
p.add(Bytes.toBytes("columnfamily"),
Bytes.toBytes("col_1"), Bytes.toBytes(a))
new Tuple2[ImmutableBytesWritable,Put](new ImmutableBytesWritable(a.toString.getBytes()), p);
}
new PairRDDFunctions(newrddtohbase.map(convert)).saveAsHadoopDataset(jobConfig)
sc.stop()
}
}
执行HBaseWrite(main(Array())后得到的错误是:
org.apache.spark.SparkException: Task not serializable
如何完成工作?
答案 0 :(得分:2)
你在这里做错的是定义convert
里面main
如果以这种方式编写此代码,它可能会起作用:
object HBaseWrite {
def main(args: Array[String]) {
val sparkConf = new SparkConf().setAppName("HBaseWrite").setMaster("local").set("spark.driver.allowMultipleContexts","true").set("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
val sc = new SparkContext(sparkConf)
val conf = HBaseConfiguration.create()
val outputTable = "tablename"
System.setProperty("user.name", "hdfs")
System.setProperty("HADOOP_USER_NAME", "hdfs")
conf.set("hbase.master", "localhost:60000")
conf.setInt("timeout", 120000)
conf.set("hbase.zookeeper.quorum", "localhost")
conf.set("zookeeper.znode.parent", "/hbase-unsecure")
conf.setInt("hbase.client.scanner.caching", 10000)
sparkConf.registerKryoClasses(Array(classOf[org.apache.hadoop.hbase.client.Result]))
val jobConfig: JobConf = new JobConf(conf,this.getClass)
jobConfig.setOutputFormat(classOf[TableOutputFormat])
jobConfig.set(TableOutputFormat.OUTPUT_TABLE,outputTable)
val x = 12
val y = 15
val z = 25
var newarray = Array(x,y,z)
val newrddtohbase = sc.parallelize(newarray)
val convertFunc = convert _
new PairRDDFunctions(newrddtohbase.map(convertFunc)).saveAsHadoopDataset(jobConfig)
sc.stop()
}
def convert(a:Int) : Tuple2[ImmutableBytesWritable,Put] = {
val p = new Put(Bytes.toBytes(a))
p.add(Bytes.toBytes("columnfamily"),
Bytes.toBytes("col_1"), Bytes.toBytes(a))
new Tuple2[ImmutableBytesWritable,Put](new ImmutableBytesWritable(a.toString.getBytes()), p);
}
}
P.S。:代码未经过测试,但应该可以使用!
答案 1 :(得分:0)
例如,下面的方法将Int作为参数并返回Double
var toDouble: (Int) => Double = a => {
a.toDouble
}
您可以使用toDouble(2)
并返回2.0
您可以将方法转换为函数文字,方法如下所示。
val convert: (Int) => Tuple2[ImmutableBytesWritable,Put] = a => {
val p = new Put(Bytes.toBytes(a))
p.add(Bytes.toBytes("columnfamily"),
Bytes.toBytes("col_1"), Bytes.toBytes(a))
new Tuple2[ImmutableBytesWritable,Put](new ImmutableBytesWritable(a.toString.getBytes()), p);
}