大数据学习——spark-steaming学习

package cn.itcast.spark.streaming

import cn.itcast.spark.util.LoggerLevel
import org.apache.spark.SparkConf
import org.apache.spark.streaming.{Seconds, StreamingContext}

object NetworkWordCount {
  def main(args: Array[String]) {
    //设置日志级别
    LoggerLevel.setStreamingLogLevels()
    //创建SparkConf并设置为本地模式运行
    //注意local[2]代表开两个线程
    val conf = new SparkConf().setMaster("local[2]").setAppName("NetworkWordCount")
    //设置DStream批次时间间隔为2秒
    val ssc = new StreamingContext(conf, Seconds(2))
    //通过网络读取数据
    val lines = ssc.socketTextStream("192.168.10.101", 9999)
    //将读到的数据用空格切成单词
    val words = lines.flatMap(_.split(" "))
    //将单词和1组成一个pair
    val pairs = words.map(word => (word, 1))
    //按单词进行分组求相同单词出现的次数
    val wordCounts = pairs.reduceByKey(_ + _)
    //打印结果到控制台
    wordCounts.print()
    //开始计算
    ssc.start()
    //等待停止
    ssc.awaitTermination()
  }
}

package cn.itcast.spark.streaming

import cn.itcast.spark.util.LoggerLevel
import org.apache.spark.{HashPartitioner, SparkConf}
import org.apache.spark.streaming.{StreamingContext, Seconds}

object NetworkUpdateStateWordCount {
  /**
    * String : 单词 hello
    * Seq[Int] ：单词在当前批次出现的次数
    * Option[Int] ： 历史结果
    */
  val updateFunc = (iter: Iterator[(String, Seq[Int], Option[Int])]) => {
    //iter.flatMap(it=>Some(it._2.sum + it._3.getOrElse(0)).map(x=>(it._1,x)))
    iter.flatMap{case(x,y,z)=>Some(y.sum + z.getOrElse(0)).map(m=>(x, m))}
  }

  def main(args: Array[String]) {
    LoggerLevel.setStreamingLogLevels()
    val conf = new SparkConf().setMaster("local[2]").setAppName("NetworkUpdateStateWordCount")
    val ssc = new StreamingContext(conf, Seconds(5))
    //做checkpoint 写入共享存储中
    ssc.checkpoint("c://aaa")
    val lines = ssc.socketTextStream("192.168.10.100", 9999)
    //reduceByKey 结果不累加
    //val result = lines.flatMap(_.split(" ")).map((_, 1)).reduceByKey(_+_)
    //updateStateByKey结果可以累加但是需要传入一个自定义的累加函数：updateFunc
    val results = lines.flatMap(_.split(" ")).map((_,1)).updateStateByKey(updateFunc, new HashPartitioner(ssc.sparkContext.defaultParallelism), true)
    results.print()
    ssc.start()
    ssc.awaitTermination()
  }
}

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

/**
  * Created by wangsenfeng on 2016/10/27.
  */
object SparkSqlTest {
  def main(args: Array[String]) {
    LoggerLevels.setStreamingLogLevels()
    val conf = new SparkConf().setAppName("sparksql").setMaster("local[2]")
    val ssc = new StreamingContext(conf,Seconds(5))
    ssc.checkpoint("./")
    val textStream: ReceiverInputDStream[String] = ssc.socketTextStream("192.168.56.151",9999)
    val result: DStream[(String, Int)] = textStream.flatMap(_.split(" ")).map((_,1)).reduceByKeyAndWindow((a:Int,b:Int) => (a + b),Seconds(5),Seconds(5))
    result.print()
    ssc.start()
    ssc.awaitTermination()
  }
}

package cn.itcast.spark.streaming

package cn.itcast.spark

import org.apache.spark.{HashPartitioner, SparkConf}
import org.apache.spark.storage.StorageLevel
import org.apache.spark.streaming.kafka.KafkaUtils
import org.apache.spark.streaming.{Seconds, StreamingContext}

object UrlCount {
  val updateFunc = (iterator: Iterator[(String, Seq[Int], Option[Int])]) => {
    iterator.flatMap{case(x,y,z)=> Some(y.sum + z.getOrElse(0)).map(n=>(x, n))}
  }

  def main(args: Array[String]) {
    //接收命令行中的参数
   // val Array(zkQuorum, groupId, topics, numThreads, hdfs) = args
val Array(zkQuorum, groupId, topics, numThreads) = Array[String]("master1ha:2181,master2:2181,master2ha:2181","g1","wangsf-test","2")
    //创建SparkConf并设置AppName
    val conf = new SparkConf().setAppName("UrlCount")
    //创建StreamingContext
    val ssc = new StreamingContext(conf, Seconds(2))
    //设置检查点
    ssc.checkpoint(hdfs)
    //设置topic信息
    val topicMap = topics.split(",").map((_, numThreads.toInt)).toMap
    //重Kafka中拉取数据创建DStream
    val lines = KafkaUtils.createStream(ssc, zkQuorum ,groupId, topicMap, StorageLevel.MEMORY_AND_DISK).map(_._2)
    //切分数据，截取用户点击的url
    val urls = lines.map(x=>(x.split(" ")(6), 1))
    //统计URL点击量
    val result = urls.updateStateByKey(updateFunc, new HashPartitioner(ssc.sparkContext.defaultParallelism), true)
    //将结果打印到控制台
    result.print()
    ssc.start()
    ssc.awaitTermination()
  }
}