大数据实时计算Spark学习笔记（11）—— Spark Streaming

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/u012292754/article/details/85338559

1 Spark Streaming

• spark core 的扩展，针对实时数据处理，具有可扩展、高吞吐、容错；
• 内部，spark 接受实时数据流，分成 batch 进行处理，最终在每个 batch 产生结果；

1.1 discretized stream or DStream

• 通过kafka,flume 等输入产生，或者通过其他的 DStream 进行高阶变换产生；
• 在内部，DStream 表现为 RDD 序列；

2 Spark Streaming 测试案例

• POM 添加依赖

<dependency>
      <groupId>org.apache.spark</groupId>
      <artifactId>spark-streaming_2.11</artifactId>
      <version>${spark.version}</version>
    </dependency>

2.1 Scala 流式单词统计

package sparkstreaming

import org.apache.spark.SparkConf
import org.apache.spark.streaming.{Seconds, StreamingContext}

object StramingWordCount {
    def main(args: Array[String]): Unit = {
        val conf = new SparkConf().setMaster("local[4]").setAppName("NetWordCount")

        val ssc = new StreamingContext(conf, Seconds(10))

        val lines = ssc.socketTextStream("localhost", 9999)

        val words = lines.flatMap(_.split(" "))

        val pairs = words.map((_, 1))

        val count = pairs.reduceByKey(_ + _)
        count.print

        ssc.start()

        ssc.awaitTermination()


    }
}

2.2 Java 版流式单词统计

import org.apache.spark.SparkConf;
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.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;

import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;

public class JavaStreamingWordcount {
    public static void main(String[] args) throws InterruptedException {

        SparkConf conf = new SparkConf().setAppName("JavaStreamingWordcount").setMaster("local[2]");

        JavaStreamingContext jsc = new JavaStreamingContext(conf, Durations.seconds(5));

        JavaReceiverInputDStream sock = jsc.socketTextStream("localhost", 9999);

        JavaDStream<String> wordsDS = sock.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public Iterator call(String str) throws Exception {
                List<String> list = new ArrayList<String>();
                String[] arr = str.split(" ");
                for (String s : arr) {
                    list.add(s);
                }
                return list.iterator();
            }
        });

        JavaPairDStream<String, Integer> pairDS = wordsDS.mapToPair(new PairFunction<String, String, Integer>() {

            @Override
            public Tuple2<String, Integer> call(String s) throws Exception {
                return new Tuple2<String, Integer>(s, 1);
            }
        });

        JavaPairDStream<String, Integer> countDS = pairDS.reduceByKey(new Function2<Integer, Integer, Integer>() {
            @Override
            public Integer call(Integer v1, Integer v2) throws Exception {
                return v1 + v2;
            }
        });

        countDS.print();

        jsc.start();

        jsc.awaitTermination();

    }
}