java 版wordcount

package javaTest;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
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.Function2;
import org.apache.spark.api.java.function.PairFunction;
import scala.Tuple2;

import java.util.Arrays;
import java.util.Iterator;

public class JavaWordCount {
    public static void main(String[] args) {
        //wordcount的基本思路

        SparkConf conf = new SparkConf();

        //java JavaSparkContext
        JavaSparkContext sc = new JavaSparkContext(conf);

        //读取文件
        JavaRDD<String> rdd1 = sc.textFile(args[0]);

        //切分<String,String> input output
        JavaRDD<String> words = rdd1.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public Iterator<String> call(String s) throws Exception {
                return Arrays.asList(s.split(" ")).iterator();
            }
        });

        //组装String ,String ,Integer 输入类型  返回值类型
        JavaPairRDD<String, Integer> wordsWithOne = words.mapToPair(new PairFunction<String, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(String s) throws Exception {
                //新建一个元组
                return new Tuple2<String, Integer>(s, 1);
            }
        });

        //reduceByKey((a,b)=> a+b)
        //分组聚合 Integer, Integer,Integer 前2个是输入类型,后一个是返回值类型
        JavaPairRDD<String, Integer> reduceRdd = wordsWithOne.reduceByKey(new Function2<Integer, Integer, Integer>() {
            @Override
            public Integer call(Integer integer, Integer integer2) throws Exception {
                return integer + integer2;
            }
        });

        //排序
        //先把k -v 反转
        //再按照key排序
        //再反转
        JavaPairRDD<Integer, String> beforeSort = reduceRdd.mapToPair(new PairFunction<Tuple2<String, Integer>, Integer, String>() {
            @Override
            public Tuple2<Integer, String> call(Tuple2<String, Integer> stringIntegerTuple2) throws Exception {
               //元素交换
                return stringIntegerTuple2.swap();
            }
        });

        //默认是升序,  降序,传递参数为false
        JavaPairRDD<Integer, String> sortedRdd = beforeSort.sortByKey(false);

        JavaPairRDD<String, Integer> finalRes = sortedRdd.mapToPair(new PairFunction<Tuple2<Integer, String>, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(Tuple2<Integer, String> integerStringTuple2) throws Exception {
                return integerStringTuple2.swap();
            }
        });

        //写文件
        finalRes.saveAsTextFile(args[1]);
        
        //释放资源
        sc.stop();
    }
}

提交任务:

spark-submit --master spark://hdp-01:7077 --class cn.spark.test.JavaWordCount /root/spark01-1.0-SNAPSHOT.jar hdfs://hdp-01:9000/wordcount/input hdfs://hdp-01:9000/wordcount/output