spark streaming

discretized
离散化的

http://spark.apache.org/docs/1.6.0/streaming-programming-guide.html#overview

[root@node5 ~]# yum install nc

[root@node5 ~]# nc -lk 9999






package com.bjsxt.spark;

import java.util.Arrays;

import org.apache.spark.SparkConf;
import org.apache.spark.SparkContext;
import org.apache.spark.api.java.JavaPairRDD;
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 org.apache.spark.broadcast.Broadcast;
import org.apache.spark.streaming.Duration;
import org.apache.spark.streaming.Durations;
import org.apache.spark.streaming.api.java.JavaDStream;
import org.apache.spark.streaming.api.java.JavaPairDStream;
import org.apache.spark.streaming.api.java.JavaReceiverInputDStream;
import org.apache.spark.streaming.api.java.JavaStreamingContext;

import scala.Tuple2;

public class SparkStreamingTest {
	public static void main(String[] args) {
		// local[1] 时只有一个task，被占用为接收数据，打印输出没有任务线程执行
		SparkConf conf = new SparkConf().setMaster("local[2]").setAppName("SparkStreamingTest");
		
		final JavaSparkContext sc = new JavaSparkContext(conf);
		
		sc.setLogLevel("WARN");
		
		JavaStreamingContext jsc = new JavaStreamingContext(sc,Durations.seconds(5));
		
		JavaReceiverInputDStream<String> socketTextStream = jsc.socketTextStream("node5",9999);
		
		JavaDStream<String> words = socketTextStream.flatMap(new FlatMapFunction<String,String>() {

			/**
			 * 
			 */
			private static final long serialVersionUID = 1L;

			@Override
			public Iterable<String> call(String lines) throws Exception {
				return Arrays.asList(lines.split(" "));
			}
		});
		
		
		JavaPairDStream<String,Integer> pairWords = words.mapToPair(new PairFunction<String, String, Integer>() {

			/**
			 * 
			 */
			private static final long serialVersionUID = 1L;

			@Override
			public Tuple2<String, Integer> call(String word) throws Exception {
				return new Tuple2<String, Integer>(word,1);
			}
		});
		JavaPairDStream<String, Integer> reduceByKey = pairWords.reduceByKey(new Function2<Integer, Integer, Integer>() {
			
			/**
			 * 
			 */
			private static final long serialVersionUID = 1L;

			@Override
			public Integer call(Integer v1, Integer v2) throws Exception {
				System.out.println("rdd reduceByKey************************");
				return v1 + v2;
			}
		});
		
		
//		reduceByKey.print(1000);
		/**
		 * foreachRDD 可以拿到DStream中的RDD,对拿到的RDD可以使用RDD的transformation类算子转换，要对拿到的RDD使用action算子触发执行，否则，foreachRDD也不会执行。
		 * foreachRDD中call方法内，拿到的RDD的算子外，代码是在Driver端执行；可以使用这个算子动态改变广播变量（使用配置文件的方式）
		 */
		reduceByKey.foreachRDD(new VoidFunction<JavaPairRDD<String,Integer>>() {

			/**
			 * 
			 */
			private static final long serialVersionUID = 1L;

			@Override
			public void call(JavaPairRDD<String, Integer> rdd)
					throws Exception {
				// Driver中获取SparkContext的正确方式； 中获取广播变量的正确方式。
				SparkContext context = rdd.context();
				JavaSparkContext sc = new JavaSparkContext(context);
				Broadcast<String> broadcast = sc.broadcast("hello");
				String value = broadcast.value();
				
				System.out.println("Driver.........");
				JavaPairRDD<String, Integer> mapToPair = rdd.mapToPair(new PairFunction<Tuple2<String,Integer>, String, Integer>() {

					/**
					 * 
					 */
					private static final long serialVersionUID = 1L;

					@Override
					public Tuple2<String, Integer> call(
							Tuple2<String, Integer> tuple) throws Exception {
						System.out.println("Executor.........");
						
						return new Tuple2<String,Integer>(tuple._1,tuple._2);
					}
				});
				
				mapToPair.foreach(new VoidFunction<Tuple2<String,Integer>>() {

					/**
					 * 
					 */
					private static final long serialVersionUID = 1L;

					@Override
					public void call(Tuple2<String, Integer> arg0)
							throws Exception {
						System.out.println(arg0);
					}
				});
			}
		});
		jsc.start();
		jsc.awaitTermination();
		jsc.stop();
		
		
	}
}



[root@node5 ~]# nc -lk 9999   ## linux 发送socket数据。
hello sxt 
hello bj
hello
hello
zhongguo
zhngguo
zhongguo