Spark 的JAVA版 wordCount

package os.unix;

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 org.apache.spark.api.java.function.VoidFunction;
import scala.Tuple2;

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

public class WordCount {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf().setMaster("local").setAppName("WordCount");
        JavaSparkContext jsc = new JavaSparkContext(conf);

        /**
         * 将文件中的内容加载到linesRdd中
         */
        JavaRDD<String> linesRDD = jsc.textFile("C:\\Users\\os\\Desktop\\test\\word.txt", 3);
        /**
         * 每一行数据根据空格分割
         */
        JavaRDD<String> wordsRDD = linesRDD.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public Iterator<String> call(String s) throws Exception {
                /**
                 * 参数s代表linesRdd中的每一条数据
                 */
                String[] split = s.split(" ");
                List<String> asList = Arrays.asList(split);
                return asList.iterator();
            }
        });

        /**
         * wordsRDD是一个非kv格式的RDD变成kv格式RDD
         * 在java api中必须使用mapToPARI
         */
        JavaPairRDD<String, Integer> pariRDD = wordsRDD.mapToPair(new PairFunction<String, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(String s) throws Exception {

                return new Tuple2<String, Integer>(s, 1);
            }
        });
        /**
         * 使用reduceByKey进行聚合
         * groupByKey将相同的key分到相同组里面
         */

        JavaPairRDD<String, Integer> resultRDD = pariRDD.reduceByKey(new Function2<Integer, Integer, Integer>() {
            @Override
            public Integer call(Integer integer, Integer integer2) throws Exception {
                return integer + integer2;
            }
        });

        /**
         * 按照单词出现的次数进行排序
         */

        JavaPairRDD<String, Integer> result = resultRDD.mapToPair(new PairFunction<Tuple2<String, Integer>, Integer, String>() {
            @Override
            public Tuple2<Integer, String> call(Tuple2<String, Integer> stringIntegerTuple2) throws Exception {
                return new Tuple2<>(stringIntegerTuple2._2, stringIntegerTuple2._1);
            }
        }).sortByKey().mapToPair(new PairFunction<Tuple2<Integer, String>, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(Tuple2<Integer, String> integerStringTuple2) throws Exception {
                return new Tuple2<>(integerStringTuple2._2, integerStringTuple2._1);
            }
        });

        result.foreach(new VoidFunction<Tuple2<String, Integer>>() {
            @Override
            public void call(Tuple2<String, Integer> stringIntegerTuple2) throws Exception {
                System.out.println(stringIntegerTuple2);
            }
        });
    }
}