Spark-SQL 读写jdbc

• 读jdbc中的信息

import java.util.Properties

import org.apache.spark.sql.{DataFrame, SparkSession}

object CreateDataFrameFromJDBC {
  def main(args: Array[String]): Unit = {
    //创建SparkSession
    val spark = SparkSession.builder()
      .appName(this.getClass.getSimpleName)
      .master("local[*]")
      .getOrCreate()

    val properties = new Properties()
    properties.setProperty("user","root")
    properties.setProperty("password","123456")

    //一定要有schema信息
    //在执行时调用read.jdbc方法一定要或取数据库表的信息
    //read.jdbc是在Driver端跟数据库查询，返回指定表的schema信息作为DataFrame的信息
    val df: DataFrame = spark.read.jdbc("jdbc:mysql://localhost:3306/demo01?characterEncoding=utf8", "tb_user", properties)

    df.printSchema()
    df.show()
    spark.stop()
  }
}

• 写入到mysql中

import java.util.Properties

import org.apache.spark.rdd.RDD
import org.apache.spark.sql.types.{DoubleType, IntegerType, StringType, StructField, StructType}
import org.apache.spark.sql.{DataFrame, Row, SaveMode, SparkSession}

object WriteJDBC {
  def main(args: Array[String]): Unit = {

    //创建SparkSession
    val spark = SparkSession.builder()
      .appName(this.getClass.getSimpleName)
      .master("local[*]")
      .getOrCreate()

    val sc = spark.sparkContext

    val lines: RDD[String] = sc.textFile("src/main/scala/data/user.txt")
    //row的字段没有名字 没有类型
    val rdd1: RDD[Row] = lines.map(e => {
      val split = e.split(",")
      Row(split(0), split(1).toInt, split(2).toDouble)
    })
    //关联schema(字段名称、字段类型、是否可以为空)
    val schema: StructType = StructType(
      Array(
        StructField("name", StringType),
        StructField("age", IntegerType),
        StructField("fv", DoubleType)
      )
    )
    //将RowRDD与StructType中的schema关联
    val df: DataFrame = spark.createDataFrame(rdd1, schema)

    val properties = new Properties()

    properties.setProperty("user","root")
    properties.setProperty("password","123456")

    //ErrorIfExists如果输出的目录或表已经存在就报错
    //Append 追加
    //Overwrite 将原来的目录或数据库表删除，然后在新建目录或表将数据写入
    //Ignore 没有就写入，有就什么都不做
    df.write.mode(SaveMode.Append).jdbc("jdbc:mysql://localhost:3306/demo01?characterEncoding=utf8","tb_user",properties)

    sc.stop()
    spark.stop()

  }
}