Spark学习之WordCount（Java版）

二、代码实现

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.FlatMapFunction;

import org.apache.spark.api.java.function.Function;

import scala.Tuple2;

import java.util.Arrays;

import java.util.Iterator;

import java.util.List;

public class SparkWordCountForJava {

public static void main(String[] args) {

// 初始化spark , local[]：以核心数在本地运行

SparkConf conf = new SparkConf().setMaster(“local[*]”).setAppName(“SparkWordCountForJava”);

JavaSparkContext jsc = new JavaSparkContext(conf);

JavaRDD textFileRdd = jsc.textFile(“C:\Users\com\Desktop\test.txt”);

// 将数据按照切分规则分成一个个单词

JavaRDD flatMapRdd = textFileRdd.fl