Spark组件之Spark Streaming学习1--NetworkWordCount学习

更多代码请见：https://github.com/xubo245/SparkLearning

NetworkWordCount：每个1秒将接收的数据进行wordCount，不累加

使用

1.方法1：在集群的examples中启动

一个terminal：

nc -lk 9999

可以在这个terminal发送数据，前面一个terminal就会统计信息

另一个terminal：

./bin/run-example streaming.NetworkWordCount localhost 9999

2.运行方法2：打成jar包上传运行：

运行脚本：

#!/usr/bin/env bash
spark-submit --name WordCountSpark  \
--class org.apache.spark.Streaming.learning.NetworkWordCount \
--master spark://<strong>Master</strong>:7077 \
--executor-memory 512M \
--total-executor-cores 10 Streaming.jar localhost 9999

然后一个ternimal运行nc，一个运行这个脚本，同上

输入数据：

hadoop@Master:~$ sudo nc -lk 9999
a
hello
world

a
hello
world
hello
hw^Hello
word
a
a
a
a
a
a
a

结果输出：

hadoop@Master:~/cloud/testByXubo/spark/Streaming$ ./submitJob.sh
-------------------------------------------
Time: 1461661853000 ms
-------------------------------------------

-------------------------------------------
Time: 1461661854000 ms
-------------------------------------------
(,1)
(hello,1)
(world,1)
(a,1)

-------------------------------------------
Time: 1461661855000 ms
-------------------------------------------
(a,1)

-------------------------------------------
Time: 1461661856000 ms
-------------------------------------------

-------------------------------------------
Time: 1461661857000 ms
-------------------------------------------
(hello,1)

-------------------------------------------
Time: 1461661858000 ms
-------------------------------------------
(world,1)

-------------------------------------------
Time: 1461661859000 ms
-------------------------------------------

-------------------------------------------
Time: 1461661860000 ms
-------------------------------------------
(hello,1)

-------------------------------------------
Time: 1461661861000 ms
-------------------------------------------

-------------------------------------------
Time: 1461661862000 ms
-------------------------------------------
(hello,1)

-------------------------------------------
Time: 1461661863000 ms
-------------------------------------------
(word,1)

-------------------------------------------
Time: 1461661864000 ms
-------------------------------------------
(a,5)

-------------------------------------------
Time: 1461661865000 ms
-------------------------------------------

代码：

/*
* 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.
*/

// scalastyle:off println
package org.apache.spark.Streaming.learning

import org.apache.spark.SparkConf
import org.apache.spark.storage.StorageLevel
import org.apache.spark.streaming.Seconds
import org.apache.spark.streaming.StreamingContext
import org.apache.spark.streaming.dstream.DStream.toPairDStreamFunctions

/**
* Counts words in UTF8 encoded, '\n' delimited text received from the network every second.
*
* Usage: NetworkWordCount <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.NetworkWordCount localhost 9999`
*/
object NetworkWordCount {
def main(args: Array[String]) {
if (args.length < 2) {
System.err.println("Usage: NetworkWordCount <hostname> <port>")
System.exit(1)
}

StreamingExamples.setStreamingLogLevels()

// Create the context with a 1 second batch size
val sparkConf = new SparkConf().setAppName("NetworkWordCount")
val ssc = new StreamingContext(sparkConf, Seconds(1))

// Create a socket stream 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.
val lines = ssc.socketTextStream(args(0), args(1).toInt, StorageLevel.MEMORY_AND_DISK_SER)
val words = lines.flatMap(_.split(" "))
val wordCounts = words.map(x => (x, 1)).reduceByKey(_ + _)
wordCounts.print()
ssc.start()
ssc.awaitTermination()
}
}
// scalastyle:on println

参考：

【1】 http://spark.apache.org/docs/1.5.2/streaming-programming-guide.html