package com.atguigu.streaming
import java.io.{BufferedReader, InputStreamReader}
import java.net.Socket
import java.nio.charset.StandardCharsets
import org.apache.spark.SparkConf
import org.apache.spark.storage.StorageLevel
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.streaming.receiver.Receiver
/**
* Created by wuyufei on 06/09/2017.
*/
// String就是接收數據的類型
class CustomReceiver(host: String, port: Int) extends Receiver[String](StorageLevel.MEMORY_AND_DISK_2) {
override def onStart(): Unit = {
// Start the thread that receives data over a connection
new Thread("Socket Receiver") {
override def run() { receive() }
}.start()
}
override def onStop(): Unit = {
// There is nothing much to do as the thread calling receive()
// is designed to stop by itself if isStopped() returns false
}
/** Create a socket connection and receive data until receiver is stopped */
private def receive() {
var socket: Socket = null
var userInput: String = null
try {
// Connect to host:port
socket = new Socket(host, port)
// Until stopped or connection broken continue reading
val reader = new BufferedReader(new InputStreamReader(socket.getInputStream(), StandardCharsets.UTF_8))
userInput = reader.readLine()
while(!isStopped && userInput != null) {
// 內部的函數，將數據存儲下倆
store(userInput)
userInput = reader.readLine()
}
reader.close()
socket.close()
// Restart in an attempt to connect again when server is active again
restart("Trying to connect again")
} catch {
case e: java.net.ConnectException =>
// restart if could not connect to server
restart("Error connecting to " + host + ":" + port, e)
case t: Throwable =>
// restart if there is any other error
restart("Error receiving data", t)
}
}
}
object CustomReceiver {
def main(args: Array[String]) {
val conf = new SparkConf().setMaster("local[*]").setAppName("NetworkWordCount")
val ssc = new StreamingContext(conf, Seconds(1))
// Create a DStream that will connect to hostname:port, like localhost:9999
val lines = ssc.receiverStream(new CustomReceiver("master01", 9999))
// Split each line into words
val words = lines.flatMap(_.split(" "))
//import org.apache.spark.streaming.StreamingContext._ // not necessary since Spark 1.3
// Count each word in each batch
val pairs = words.map(word => (word, 1))
val wordCounts = pairs.reduceByKey(_ + _)
// Print the first ten elements of each RDD generated in this DStream to the console
wordCounts.print()
ssc.start() // Start the computation
ssc.awaitTermination() // Wait for the computation to terminate
//ssc.stop()
}
}
package com.atguigu.streaming
import org.apache.spark.SparkConf
import org.apache.spark.streaming.{Seconds, StreamingContext}
/**
* Created by wuyufei on 06/09/2017.
*/
object WorldCount {
def main(args: Array[String]) {
val conf = new SparkConf().setMaster("local[2]").setAppName("NetworkWordCount")
val ssc = new StreamingContext(conf, Seconds(1))
// Create a DStream that will connect to hostname:port, like localhost:9999
val lines = ssc.socketTextStream("zk1", 9999)
// Split each line into words
val words = lines.flatMap(_.split(" "))
//import org.apache.spark.streaming.StreamingContext._ // not necessary since Spark 1.3
// Count each word in each batch
val pairs = words.map(word => (word, 1))
val wordCounts = pairs.reduceByKey(_ + _)
// Print the first ten elements of each RDD generated in this DStream to the console
wordCounts.print()
ssc.start() // Start the computation
ssc.awaitTermination() // Wait for the computation to terminate
//ssc.stop()
}
}
package com.atguigu.streaming
import org.apache.spark.SparkConf
import org.apache.spark.rdd.RDD
import org.apache.spark.streaming.{Seconds, StreamingContext}
import scala.collection.mutable
object QueueRdd {
def main(args: Array[String]) {
val conf = new SparkConf().setMaster("local[*]").setAppName("QueueRdd")
val ssc = new StreamingContext(conf, Seconds(1))
// Create the queue through which RDDs can be pushed to
// a QueueInputDStream
//创建RDD队列
val rddQueue = new mutable.SynchronizedQueue[RDD[Int]]()
// Create the QueueInputDStream and use it do some processing
// 创建QueueInputDStream
val inputStream = ssc.queueStream(rddQueue)
//处理队列中的RDD数据
val mappedStream = inputStream.map(x => (x % 10, 1))
val reducedStream = mappedStream.reduceByKey(_ + _)
//打印结果
reducedStream.print()
//启动计算
ssc.start()
// Create and push some RDDs into
for (i <- 1 to 30) {
rddQueue += ssc.sparkContext.makeRDD(1 to 300, 10)
Thread.sleep(2000)
//通过程序停止StreamingContext的运行
//ssc.stop()
}
ssc.awaitTermination()
}
}
package com.atguigu.streaming
import org.apache.spark.SparkConf
import org.apache.spark.streaming.{Seconds, StreamingContext}
/**
* Created by wuyufei on 06/09/2017.
*/
object WorldCount {
def main(args: Array[String]) {
val conf = new SparkConf().setMaster("local[2]").setAppName("NetworkWordCount")
// batchInterval = 3s
val ssc = new StreamingContext(conf, Seconds(2))
ssc.checkpoint("./checkpoint")
// Create a DStream that will connect to hostname:port, like localhost:9999
val lines = ssc.socketTextStream("master01", 9000)
// Split each line into words
val words = lines.flatMap(_.split(" "))
//import org.apache.spark.streaming.StreamingContext._ // not necessary since Spark 1.3
// Count each word in each batch
val pairs = words.map(word => (word, 1))
//val wordCounts = pairs.reduceByKey((a:Int,b:Int) => (a + b))
// 窗口大小 为12s， 12/3 = 4 滑动步长 6S， 6/3 =2
//val wordCounts = pairs.reduceByKeyAndWindow((a:Int,b:Int) => (a + b),Seconds(12), Seconds(6))
val wordCounts2 = pairs.reduceByKeyAndWindow(_ + _,_ - _ ,Seconds(12), Seconds(6))
// Print the first ten elements of each RDD generated in this DStream to the console
wordCounts2.print()
ssc.start() // Start the computation
ssc.awaitTermination() // Wait for the computation to terminate
//ssc.stop()
}
}
创建Web工程，使用eclipse ee创建maven web工程 1.右键项目,选择Project Facets,点击Convert to faceted from 2.更改Dynamic Web Module的Version为2.5.(3.0为Java7的,Tomcat6不支持). 如果提示错误,可能需要在Java Compiler设置Compiler compl
最近一直在看python的document，打算在基础方面重点看一下python的keyword、Build-in Function、Build-in Constants、Build-in Types、Build-in Exception这四个方面，其实在看的时候发现整个《The Python Standard Library》章节都是很不错的，其中描述了很多不错的主题。先把Build-in Fu
学习函数式编程
package base;
import java.text.DecimalFormat;
public class Main {
public static void main(String[] args) {
// Integer a = 4;
// Double aa = (double)a / 100000;
// Decimal
Java中的泛型的使用：1.普通的泛型使用
在使用类的时候后面的<>中的类型就是我们确定的类型。
public class MyClass1<T> {//此处定义的泛型是T
private T var;
public T getVar() {
return var;
}
public void setVa
