spark程序解析——WordCount

本篇解析spark的词频统计源程序代码。

java源码如下：

</pre><pre name="code" class="java">package sparkTest;

import java.util.Arrays;

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;

public class WordCount {
	
	public static void main(String[] args) {
		String logFile = "file:///home/hadoop/workspace/sparkTest/input/README.md"; // Should be some file on your system
		SparkConf conf = new SparkConf().setAppName("Simple Application").setMaster("local");
		JavaSparkContext sc = new JavaSparkContext(conf);
		JavaRDD<String> textFile = sc.te