Java maven开发spark 统计文本中每行单词出现的次数

package spark;

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

/*
统计每行单词出现的次数

 */
public class LineCount {
    public static void main(String[] args) {

        //创建SparkConf
        SparkConf conf = new SparkConf()
                .setAppName("LineCount")
                .setMaster("local");

        //创建javaSparkContext
        JavaSparkContext sc = new JavaSparkContext(conf);

        //创建初始RDD，lines,每个元素是一行文本
        JavaRDD<String> lines = sc.textFile("E:\\hello.txt");
        JavaPairRDD<String, Integer> pairs = lines.mapToPair(
                new PairFunction<String, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(String t) throws Exception {
                return new Tuple2<String, Integer>(t,1);
            }
        });

        //对pairsRDD执行reduceByKey算子，统计出每一行出现的总次数
        JavaPairRDD<String,Integer> lineCounts = pairs.reduceByKey(new Function2<Integer, Integer, Integer>() {
            @Override
            public Integer call(Integer v1, Integer v2) throws Exception {
                return v1 + v2;
            }
        });

        //执行一个action操作，foreach，打印出，每一行出现的次数
        lineCounts.foreach(new VoidFunction<Tuple2<String, Integer>>() {
            @Override
            public void call(Tuple2<String, Integer> t) throws Exception {
                System.out.println(t._1+ "出现" + t._2 + " 次");
            }
        });
        //关闭JavaSparkContext
        sc.close();
    }
}