spark的aggregateByKey简单用法

问题：求key只出现一次的数据， 如果用groupByKey或reduceByKey很容易就做出来了，现在用aggregateByKey求解一下。

输入数据：

asdfgh	546346
retr	4567
asdfgh	7685678
ghj	2345
asd	234
hadoop	435
ghj	23454
asdfgh	54675
asdfgh	546759878
asd	234
asdfgh	5467598782

代码：

package scala

import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}

import scala.collection.mutable
import scala.collection.JavaConverters._

object AaidTest {
  def main(args: Array[String]): Unit = {
    val conf=new SparkConf().setAppName("AaidTest").setMaster("local")
    val sc=new SparkContext(conf)

    sc.textFile("D://sparkmllibData/sparkml/mllibdata/arrregation.txt")
      .map(line=>{
        (line.split("\t")(0),line.split("\t")(1).toLong)
      }).aggregateByKey(0L)(seqOp,seqOp)
        .filter(line=> line._2!=-1L)
      .collect().foreach(println)

  }

  def seqOp(U : (Long), v : (Long)) : Long = {
    println("seqOp")
    println("U="+U)
    println("v="+v)
    var count:Int=0
    if(U!=0L){
      count+=1
    }
    if(v!=0L){
      count+=1
    }
    if(count>1){
      -1L
    }else{
      v
    }
  }
}

输出结果：

seqOp
U=0
v=546346
seqOp
U=0
v=4567
seqOp
U=546346
v=7685678
seqOp
U=0
v=2345
seqOp
U=0
v=234
seqOp
U=0
v=435
seqOp
U=2345
v=23454
seqOp
U=1
v=54675
seqOp
U=1
v=546759878
seqOp
U=234
v=234
seqOp
U=1
v=5467598782

(hadoop,435)
(retr,4567)

很明显，达到最后的要求了。