作者:翁松秀
SparkDemo——JavaSparkWordCount
package org.apache.spark.examples;
import scala.Tuple2;
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 java.util.Arrays;
import java.util.List;
import java.util.regex.Pattern;
public final class JavaWordCount {
private static final Pattern SPACE = Pattern.compile(" ");
public static void main(String[] args) throws Exception {
if (args.length < 1) {
System.err.println("Usage: JavaWordCount <file>");
System.exit(1);
}
//通过SparkConf对象来配置Spark应用
SparkConf sparkConf = new SparkConf().setAppName("JavaWordCount").setMaster("local");
//Spark应用的入口
JavaSparkContext ctx = new JavaSparkContext(sparkConf);
//创建RDD:从文件中读取待统计文本
JavaRDD<String> lines = ctx.textFile(args[0], 1);
//转换RDD:将文本内容按空格分割成单词
JavaRDD<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
@Override
public Iterable<String> call(String s) {
return Arrays.asList(SPACE.split(s));
}
});
//转换RDD:将单词<String>转换成<String,Integer>,每个单词初始化次数为1
JavaPairRDD<String, Integer> ones = words.mapToPair(new PairFunction<String, String, Integer>() {
@Override
public Tuple2<String, Integer> call(String s) {
return new Tuple2<String, Integer>(s, 1);
}
});
//行动RDD:统计每个单词的次数<String,Integer>
JavaPairRDD<String, Integer> counts = ones.reduceByKey(new Function2<Integer, Integer, Integer>() {
@Override
public Integer call(Integer i1, Integer i2) {
return i1 + i2;
}
});
//获取整个RDD的数据
List<Tuple2<String, Integer>> output = counts.collect();
for (Tuple2<?, ?> tuple : output) {
System.out.println(tuple._1() + ": " + tuple._2());
}
ctx.stop();
ctx.close();
}
}