SparkStreaming的实时单词统计小例子

最新推荐文章于 2023-09-10 09:05:55 发布

DT平哥

最新推荐文章于 2023-09-10 09:05:55 发布

阅读量818

点赞数 2

分类专栏： spark

本文链接：https://blog.csdn.net/jp413670706/article/details/78150281

版权

spark 专栏收录该内容

3 篇文章 0 订阅

订阅专栏

package com.yc.spark

import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.sql.SQLContext
import org.apache.spark.sql.Row
import org.apache.spark.sql.types.{ StructType, StructField, StringType, IntegerType }
import java.util.Properties
import org.apache.spark.sql.hive.HiveContext
import org.apache.spark.sql.SparkSession
import org.apache.spark.streaming.StreamingContext
import org.apache.spark.SparkConf
import org.apache.spark.streaming.Seconds
import org.apache.spark.graphx.Graph

object SparkStreaming1 {
def main(args: Array[String]): Unit = {
val conf = new SparkConf().setMaster("local[2]").setAppName("Stream")
val ssc = new StreamingContext(conf, Seconds(5)) //spark实时数据流处理对象
ssc.sparkContext.setLogLevel("error")

// val ds = ssc.textFileStream("/data/stream") //DStream 是spark streaming的数据处理类型

var ds = ssc.socketTextStream("master", 7777)

val words = ds.flatMap(_.split(" ")).map((_, 1)).reduceByKey(_ + _)
words.print()

Graph
ssc.start()
ssc.awaitTermination()
}
}