初见spark streaming之JavaNetWorkWordCount

背景

  接触了一点spark，看到网上关于实时处理系统的博文也是铺天盖地，觉得还是有比要了解一下，作为时下比较热门的大数据，还是要多看多听多用。

对象

 spark streaming JavaNetworkWordCount.java运行例

 代码链接：https://github.com/apache/spark/blob/master/examples/src/main/java/org/apache/spark/examples/streaming/JavaNetworkWordCount.java

源码如下所示：

/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/

package org.apache.spark.examples.streaming;

import java.util.Arrays;
import java.util.Iterator;
import java.util.regex.Pattern;

import scala.Tuple2;

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.api.java.StorageLevels;
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;

/**
* Counts words in UTF8 encoded, '\n' delimited text received from the network every second.
*
* Usage: JavaNetworkWordCount <hostname> <port>
* <hostname> and <port> describe the TCP server that Spark Streaming would connect to receive data.
*
* To run this on your local machine, you need to first run a Netcat server
* `$ nc -lk 9999`
* and then run the example
* `$ bin/run-example org.apache.spark.examples.streaming.JavaNetworkWordCount localhost 9999`
*/
public final class JavaNetworkWordCount {
private static final Pattern SPACE = Pattern.compile(" ");

public static void main(String[] args) throws Exception {
if (args.length < 2) {
System.err.println("Usage: JavaNetworkWordCount <hostname> <port>");
System.exit(1);
}

StreamingExamples.setStreamingLogLevels();

// Create the context with a 1 second batch size
SparkConf sparkConf = new SparkConf().setAppName("JavaNetworkWordCount");
JavaStreamingContext ssc = new JavaStreamingContext(sparkConf, Durations.seconds(1));

// Create a JavaReceiverInputDStream on target ip:port and count the
// words in input stream of \n delimited text (eg. generated by 'nc')
// Note that no duplication in storage level only for running locally.
// Replication necessary in distributed scenario for fault tolerance.
JavaReceiverInputDStream<String> lines = ssc.socketTextStream(
args[0], Integer.parseInt(args[1]), StorageLevels.MEMORY_AND_DISK_SER);
JavaDStream<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
@Override
public Iterator<String> call(String x) {
return Arrays.asList(SPACE.split(x)).iterator();
}
});
JavaPairDStream<String, Integer> wordCounts = words.mapToPair(
new PairFunction<String, String, Integer>() {
@Override
public Tuple2<String, Integer> call(String s) {
return new Tuple2<>(s, 1);
}
}).reduceByKey(new Function2<Integer, Integer, Integer>() {
@Override
public Integer call(Integer i1, Integer i2) {
return i1 + i2;
}
});

wordCounts.print();
ssc.start();
ssc.awaitTermination();
}
}

关于代码的理解，有些难解的地方，作为笔记，记录下来。

1. 设置拉去数据的频率ÿ