spark 查询mysql_Spark新手求教 SparkStreaming能否连接MySQL进行查询操作

最新推荐文章于 2021-02-11 10:08:59 发布

C丶X

最新推荐文章于 2021-02-11 10:08:59 发布

阅读量178

点赞数

文章标签： spark 查询mysql

本文链接：https://blog.csdn.net/weixin_34442022/article/details/113166981

版权

支持mysql的，下面是示例

spark streaming使用数据源方式插入mysql数据

[mw_shl_code=bash,true]import java.sql.{Connection, ResultSet}

import com.jolbox.bonecp.{BoneCP, BoneCPConfig}

import org.slf4j.LoggerFactory

object ConnectionPool {

val logger = LoggerFactory.getLogger(this.getClass)

private val connectionPool = {

try{

Class.forName("com.mysql.jdbc.Driver")

val config = new BoneCPConfig()

config.setJdbcUrl("jdbc:mysql://192.168.0.46:3306/test")

config.setUsername("test")

config.setPassword("test")

config.setMinConnectionsPerPartition(2)

config.setMaxConnectionsPerPartition(5)

config.setPartitionCount(3)

config.setCloseConnectionWatch(true)

config.setLogStatementsEnabled(true)

Some(new BoneCP(config))

} catch {

case exception:Exception=>

logger.warn("Error in creation of connection pool"+exception.printStackTrace())

None

}

def getConnection:Option[Connection] ={

connectionPool match {

case Some(connPool) => Some(connPool.getConnection)

case None => None

}

def closeConnection(connection:Connection): Unit = {

if(!connection.isClosed) connection.close()

}

import java.sql.{Connection, DriverManager, PreparedStatement}

import org.apache.spark.streaming.kafka.KafkaUtils

import org.apache.spark.streaming.{Seconds, StreamingContext}

import org.apache.spark.{SparkConf, SparkContext}

import org.slf4j.LoggerFactory

/**

* 记录最近五秒钟的数据

object RealtimeCount1{

case class Loging(vtime:Long,muid:String,uid:String,ucp:String,category:String,autoSid:Int,dealerId:String,tuanId:String,newsId:String)

case class Record(vtime:Long,muid:String,uid:String,item:String,types:String)

val logger = LoggerFactory.getLogger(this.getClass)

def main(args: Array[String]) {

val argc = new Array[String](4)

argc(0) = "10.0.0.37"

argc(1) = "test-1"

argc(2) = "test22"

argc(3) = "1"

val Array(zkQuorum, group, topics, numThreads) = argc

val sparkConf = new SparkConf().setAppName("RealtimeCount").setMaster("local[2]")

val sc = new SparkContext(sparkConf)

val ssc = new StreamingContext(sc, Seconds(5))

val topicMap = topics.split(",").map((_,numThreads.toInt)).toMap

val lines = KafkaUtils.createStream(ssc, zkQuorum, group, topicMap).map(x=>x._2)

val sql = "insert into loging_realtime1(vtime,muid,uid,item,category) values (?,?,?,?,?)"

val tmpdf = lines.map(_.split("\t")).map(x=>Loging(x(9).toLong,x(1),x(0),x(3),x(25),x(18).toInt,x(29),x(30),x(28))).filter(x=>(x.muid!=null && !x.muid.equals("null") && !("").equals(x.muid))).map(x=>Record(x.vtime,x.muid,x.uid,getItem(x.category,x.ucp,x.newsId,x.autoSid.toInt,x.dealerId,x.tuanId),getType(x.category,x.ucp,x.newsId,x.autoSid.toInt,x.dealerId,x.tuanId)))

tmpdf.filter(x=>x.types!=null).foreachRDD{rdd =>

//rdd.foreach(println)

rdd.foreachPartition(partitionRecords=>{

val connection = ConnectionPool.getConnection.getOrElse(null)

if(connection!=null){

partitionRecords.foreach(record=>process(connection,sql,record))

ConnectionPool.closeConnection(connection)

}

})

}

ssc.start()

ssc.awaitTermination()