通过ip规则 匹配业务数据的地址(经纬度或省市 城市) 用到广播变量,并将规则写入到mysql中
工具类:
1.将ip地址转为十进制
2.匹配ip规则时 用二分法查找
import scala.collection.mutable.ArrayBuffer
object IpUtils {
/**
* 将IP地址转成十进制
*
* @param ip
* @return
*/
def ip2Long(ip: String): Long = {
val fragments = ip.split("[.]")
var ipNum = 0L
for (i <- 0 until fragments.length) {
ipNum = fragments(i).toLong | ipNum << 8L
}
ipNum
}
/**
* 二分法查找
*
* @param lines
* @param ip
* @return
*/
def binarySearch(lines: ArrayBuffer[(Long, Long, String, String)], ip: Long): Int = {
var low = 0 //起始
var high = lines.length - 1 //结束
while (low <= high) {
val middle = (low + high) / 2
if ((ip >= lines(middle)._1) && (ip <= lines(middle)._2))
return middle
if (ip < lines(middle)._1)
high = middle - 1
else {
low = middle + 1
}
}
-1 //没有找到
}
def binarySearch(lines: Array[(Long, Long, String, String)], ip: Long): Int = {
var low = 0 //起始
var high = lines.length - 1 //结束
while (low <= high) {
val middle = (low + high) / 2
if ((ip >= lines(middle)._1) && (ip <= lines(middle)._2))
return middle
if (ip < lines(middle)._1)
high = middle - 1
else {
low = middle + 1
}
}
-1 //没有找到
}
}
开始正菜
1.读取ip规则数据-->rdd-->切分数据,留下要用的数据-->将数据收集到driver端 然后广播变量到对应所有的executor端
2.读取业务数据-->rdd-->切分数据,留下能用的信息-->将数据通过工具类中的方法转为十进制,并进行二分查找,返回相应经纬度或城市,这里要的是城市.-->reduceByKey-->得到结果
3.将结果写入到mysql数据库内:
- res.foearchpartition(data2Mysql)
- 定义这个data2Mysql:
- 创建数据库连接,最好是每个分区创建一次,重复使用这个链接
- 批量写入到数据库中(具体见以下代码)
import java.sql.{Connection, Date, DriverManager, PreparedStatement}
import com.hjm.spark.utils.IpUtils
import org.apache.spark.broadcast.Broadcast
import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}
object IpLocation {
def main(args: Array[String]): Unit = {
val isLocal = args(0).toBoolean
val conf = new SparkConf().setAppName(this.getClass.getCanonicalName)
if (isLocal) {
conf.setMaster("local[*]")
}
val sc = new SparkContext(conf)
//先读取iP规则数据
val ipRuleLines: RDD[String] = sc.textFile(args(1))
val ipRulesInDriver: Array[(Long, Long, String, String)] = ipRuleLines.map(line => {
val fields = line.split("[|]")
val startNum = fields(2).toLong
val endNum = fields(3).toLong
val province = fields(6)
val city = fields(7)
(startNum, endNum, province, city)
}).collect //将ip规则收集到driver
//将dirver端准备好的数据广播的Executor中
//返回一个广播变量的引用(是在driver端),该方法是一个阻塞的方法
val broadcastRef: Broadcast[Array[(Long, Long, String, String)]] = sc.broadcast(ipRulesInDriver)
//读取访问日志数据
val accessLog: RDD[String] = sc.textFile(args(2))
//对访问日志进行整理
val provinceAndOne: RDD[(String, Int)] = accessLog.map(line => {
val fields = line.split("[|]")
val ip = fields(1)
val ipNum = IpUtils.ip2Long(ip)
//在Executor中关联事先广播好的数据
//通过广播变量的引用,可以获取到事先广播到Exector中的数据
val ipRulesInExecutor: Array[(Long, Long, String, String)] = broadcastRef.value
//使用二分法查找
val index = IpUtils.binarySearch(ipRulesInExecutor, ipNum)
var province = "未知"
if (index != -1) {
province = ipRulesInExecutor(index)._3
}
(province, 1)
})
val res = provinceAndOne.reduceByKey(_ + _)
//打印输出
// res.foreach(println)
println(res.collect().toBuffer)
//ArrayBuffer((陕西,1824), (河北,383), (云南,126), (未知,1), (重庆,868), (北京,1535))
/**
*
* 将结果保存到mysql表中
*/
res.foreachPartition(dataMysql)
//关闭sc
sc.stop()
}
val dataMysql = (it: Iterator[(String, Int)]) => {
var conn: Connection = null
var ps: PreparedStatement = null
try {
//需要把Class.forName("com.mysql.jdbc.Driver").newInstance()加上 否则在分布式提交的时候,数据没有插入到数据库中。
Class.forName("com.mysql.jdbc.Driver").newInstance()
//准备mysql数据 不加这个可能会报错 :&useSSL=false
conn = DriverManager.getConnection("jdbc:mysql://localhost:3306/hjm?characterEncoding=utf-8&useSSL=false", "root", "123456")
//写sql语句对象
ps = conn.prepareStatement("insert into ip values (null,?,?)")
//将数据set进数据表 //必须在数据库创建一个新表 用于接受数据
it.foreach(t => {
ps.setString(1, t._1)
ps.setInt(2, t._2)
//批量写入
ps.addBatch()
})
//写入到数据库
ps.executeBatch()
//返回迭代器
()
} catch {
case e: Exception => {}
} finally {
//关闭资源
if (conn != null) conn.close()
if (ps != null) ps.close()
}
}
}