Spark- JdbcRDD以及注意事项

package com.rz.spark.base

import java.sql.DriverManager

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

object JdbcRDDDemo {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName(this.getClass.getSimpleName).setMaster("local[2]")
    val sc = new SparkContext(conf)

    val getConn=()=>{
      DriverManager.getConnection("jdbc:mysql://localhost:3306/bigdata?characterEncoding=utf-8","root","root")
    }

    // 创建RDD，这个RDD会记录以后从MySQL中读取数据
    val jdbcRDD: JdbcRDD[(Int, String, Int)] = new JdbcRDD(sc,
      getConn,
      "select * from logs where id >= ? and id <= ?",
      1,
      5,
      2, //分区数量
      rs => {
        val id = rs.getInt(1)
        val name = rs.getString(2)
        val age = rs.getInt(3)
        (id, name, age) //将数据库查询出来的数据集转成想要的数据格式
      }
    )
    val rs = jdbcRDD.collect()
    print(rs.toBuffer)
  }
}

"select * from logs where id >= ? and id < ?"