spark 读取hive 数据

最新推荐文章于 2024-08-04 00:33:27 发布

瓦力冫

最新推荐文章于 2024-08-04 00:33:27 发布

阅读量6.8k

点赞数

分类专栏： spark

本文链接：https://blog.csdn.net/fox64194167/article/details/80777689

版权

spark 专栏收录该内容

12 篇文章 0 订阅

订阅专栏

1.启动spark-shell 需要加上mysql jar位置

spark-shell --master local[2] --jars /Users/walle/app/mysql-connector-java-8.0.11.jar

2. 简单sql

spark.sql("show databases").show
spark.sql("show tables").show
spark.sql("use sparktest")
spark.sql("select * from student").show

3. 代码中用SparkSession

package com.waitingfy

object sparkhive {
  def main(args: Array[String]): Unit = {
    import java.io.File

    import org.apache.spark.sql.{Row, SaveMode, SparkSession}

    case class Record(key: Int, value: String)

    // warehouseLocation points to the default location for managed databases and tables
    val warehouseLocation = new File("spark-warehouse").getAbsolutePath

    val spark = SparkSession
      .builder()
      .master("local[2]")
      .appName("Spark Hive Example")
      .config("spark.sql.warehouse.dir", warehouseLocation)
      .enableHiveSupport()
      .getOrCreate()

    import spark.implicits._
    import spark.sql

    sql("CREATE TABLE IF NOT EXISTS src (key INT, value STRING) USING hive")
    sql("LOAD DATA LOCAL INPATH '/usr/local/Cellar/spark-2.3.0/examples/src/main/resources/kv1.txt' INTO TABLE src")

    // Queries are expressed in HiveQL
//    sql("SELECT * FROM src").show()

    val sqlDF = sql("SELECT key, value FROM src WHERE key < 10 ORDER BY key")

    sqlDF.show()

    spark.close()
  }
}

http://www.waitingfy.com/archives/4352