Spark进阶（四）

1.Spark与MySQL或者其他的关系型数据库

package scala

import java.sql.{DriverManager, PreparedStatement, Connection}
import org.apache.spark.{SparkContext, SparkConf}

object RDDtoMysql {

//这里按需设置数据库Blog表
  case class Blog(name: String, count: Int)

 //往数据库存
  def myFun(iterator: Iterator[(String, Int)]): Unit = {

    var conn: Connection = null

    var ps: PreparedStatement = null
//存时间有NOW()函数？
    val sql = "insert into blog(name, count) values (?, ?)"

    try {

      conn =DriverManager.getConnection("jdbc:mysql://localhost:3306/spark",

　　　　"root", "123456")

      iterator.foreach(data => {

        ps = conn.prepareStatement(sql)

        ps.setString(1, data._1)

        ps.setInt(2, data._2)

        ps.executeUpdate()

      }

      )

    } catch {

      case e: Exception => println("Mysql Exception")

    } finally {

      if (ps != null) {

        ps.close()

      }

      if (conn != null) {

        conn.close()

      }

    }

  }



  def main(args: Array[String]) {

    val conf = new SparkConf().setAppName("RDDToMysql").setMaster("local")

    val sc = new SparkContext(conf)

    val data = sc.parallelize(List(("www", 10), ("iteblog", 20), ("com", 30)))

    data.foreachPartition(myFun)

  }

}

使用maven+spring MVC中涉及到hadoop maven包等

 <!--hadoop-->
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-client</artifactId>
        <version>2.6.0</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-common</artifactId>
        <version>2.6.0</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-hdfs</artifactId>
        <version>2.6.0</version>
    </dependency>

mysql 和gson包

<dependency>
        <groupId>mysql</groupId>
        <artifactId>mysql-connector-java</artifactId>
        <version>5.1.24</version>
    </dependency>
    <dependency>
        <groupId>com.google.code.gson</groupId>
        <artifactId>gson</artifactId>
        <version>2.7</version>
    </dependency>

运行代码示例：

package sql

import java.util.Properties

import org.apache.spark.sql.{DataFrame, SQLContext}
import org.apache.spark.{SparkConf, SparkContext}

/**
  * 生产环境：下提交任务
  * spark-submit --class sql.SparkSqlMysqlDatasource --master yarn-cluster --executor-memory 2G --num-executors 2 --driver-memory 1g --executor-cores 1  /data1/e_heyutao/sparktest/sparkEnn.jar
  *
  */
object SparkSqlMysqlDatasource {
  //数据库配置
  lazy val url = "jdbc:mysql://your_ip:3306/my_test"
  lazy val username = "root"
  lazy val password = "secret_password"

  def main(args: Array[String]) {
//    val sparkConf = new SparkConf().setAppName("sparkSqlTest").setMaster("local[2]").set("spark.app.id", "sql")
    val sparkConf = new SparkConf().setAppName("sparkSqlTest").setMaster("yarn-cluster").set("spark.app.id", "sqlTest")
    //序列化
    sparkConf.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
    sparkConf.set("spark.kryoserializer.buffer", "256m")
    sparkConf.set("spark.kryoserializer.buffer.max", "2046m")
    sparkConf.set("spark.akka.frameSize", "500")
    sparkConf.set("spark.rpc.askTimeout", "30")
    //获取context
    val sc = new SparkContext(sparkConf)
    //获取sqlContext
    val sqlContext = new SQLContext(sc)

    //引入隐式转换，可以使用spark sql内置函数
    import sqlContext.implicits._

    //创建jdbc连接信息
    val uri = url + "?user=" + username + "&password=" + password + "&useUnicode=true&characterEncoding=UTF-8"
    val prop = new Properties()
    //注意：集群上运行时，一定要添加这句话，否则会报找不到mysql驱动的错误
    prop.put("driver", "com.mysql.jdbc.Driver")
    //加载mysql数据表
    val df_test1: DataFrame = sqlContext.read.jdbc(uri, "user_t", prop)
    val df_test2: DataFrame = sqlContext.read.jdbc(uri, "t_user2", prop)

    //从dataframe中获取所需字段
    df_test2.select("id", "name", "age").collect()
      .foreach(row => {
        println("id  " + row(0) + " ,name  " + row(1) + ", age  " + row(2))
      })
    //注册成临时表
    df_test1.registerTempTable("temp_table")

    val total_sql = "select * from temp_table "
    val total_df: DataFrame = sqlContext.sql(total_sql)

     //将结果写入数据库中
    val properties=new Properties()
    properties.setProperty("user","root")
    properties.setProperty("password","secret_password")
    total_df.write.mode("append").jdbc("jdbc:mysql://your_ip:3306/my_test?useUnicode=true&characterEncoding=UTF-8","t_result",properties)

    /**
      * 注意：查看源码可以知道详细意思
    def mode(saveMode: String): DataFrameWriter = {
          this.mode = saveMode.toLowerCase match {
          case "overwrite" => SaveMode.Overwrite
          case "append" => SaveMode.Append
          case "ignore" => SaveMode.Ignore
          case "error" | "default" => SaveMode.ErrorIfExists
          case _ => throw new IllegalArgumentException(s"Unknown save mode: $saveMode. " +
            "Accepted modes are 'overwrite', 'append', 'ignore', 'error'.")
    }
      */

    //分组后求平均值
    total_df.groupBy("name").avg("age").collect().foreach(x => {
      println("name " + x(0))
      println("age " + x(1))
    })

  }
}

2.Scala语言学习

正则表达式：构造正则对象Regex直接使用r方法：val regx=”[0-9]+”.r。返回所有匹配的迭代器：val matchiterator=regx.findAllIn(“带匹配字符串”)。首个匹配项：findFirstIn，匹配字符串的开始部分：findPrefixOf