import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.VoidFunction;
import java.util.*;
/**
* mapPartitions 算子
* 针对partition的操作,一次会处理一个partition的所有数据
*/
public class MapPartitionsOperator {
public static void main(String[] args){
SparkConf conf = new SparkConf().setMaster("local").setAppName("mapPartitions");
JavaSparkContext sc = new JavaSparkContext(conf);
List<String> names = Arrays.asList("w1","w2","w3","w4");
JavaRDD<String> nameRdd = sc.parallelize(names,2);
final Map<String,Integer> scoreMap = new HashMap<>();
scoreMap.put("w1",1);
scoreMap.put("w2",2);
scoreMap.put("w3",3);
scoreMap.put("w4",4);
JavaRDD<Integer> result = nameRdd.mapPartitions(new FlatMapFunction<Iterator<String>, Integer>() {
private static final long serialVersionUID = 1L;
@Override
public Iterator<Integer> call(Iterator<String> iterator) throws Exception{
List<Integer> list = new ArrayList<>();
while(iterator.hasNext()){
String name = iterator.next();
int score = scoreMap.get(name);
list.add(score);
}
return list.iterator();
}
});
result.foreach(new VoidFunction<Integer>() {
@Override
public void call(Integer integer) throws Exception {
System.err.println("mapPartitions算子:"+integer);
}
});
result.foreachPartition(new VoidFunction<Iterator<Integer>>() {
@Override
public void call(Iterator<Integer> integerIterator) throws Exception {
while (integerIterator.hasNext()){
System.err.println("mapPartitions算子遍历:"+integerIterator.next());
}
}
});
}
}
微信扫描下图二维码加入博主知识星球,获取更多大数据、人工智能、算法等免费学习资料哦!