scala mapPartitionsWithIndex函数的使用

Posted 2020-11-01 chengjunde

var rdd1=sc.makeRDD(Array((1,"A"),(2,"B"),(3,"C"),(4,"D")),2)

rdd1.partitions.size

res20:int=2

rdd1.mapPartitionsWithIndex{

(partIdx,iter)=>{

 var part_map=scala.collection.mutable.Map[string,List[(Int,String)]]()

 while(iter.hasNext)

{

  var part_name="part_"+partIdx;

  var elem=iter.next();

 if(part_map.contains(part_name)){

 var elems=part_map(part_name)

elems::=elem

part_map(part_name)=elems

} else{

  part_map(part_name)=List[(Int,String)]{elem}

}

}

part_map.iterator

}}.collect