spark读取Oracle教程

一、pom.xml中配置

<dependency>
  <groupId>com.oracle</groupId>
  <artifactId>ojdbc6</artifactId>
  <version>11.2.0.3</version>
</dependency>

二、show the code

import java.util.Properties
import org.apache.spark.sql.SQLContext
import org.apache.spark.{SparkConf,SparkContext}
import org.apache.spark.sql.{Row,SparkSession,Dataset}
object readOracle {
  def main(args: Array[String]): Unit = {

//    val spark = SparkSession
//      .builder()
//      .master("local[*]")
//      .appName("ReadOracle")
//      .config("spark.driver.cores","1")
//      .getOrCreate()
//
//    val jdbcDF = spark.read
//      .format("jdbc")
//      .option("url","jdbc:oracle:thin:@10.86.15.145:1521:ODRPT")
//      .option("dbtable", "ds.task_list")
//      .option("user", "***")
//      .option("password", "fwed_1656")
//      .option("driver", "oracle.jdbc.driver.OracleDriver")
//      .load();
//
//    jdbcDF.show()
//    import org.apache.spark.sql.Dataset
//    jdbcDF.createOrReplaceTempView("TEST_TABLE")
//    val result = spark.sql("SELECT * FROM TEST_TABLE")
//    result.show()

//
    val sparlkConf = new SparkConf().setAppName("ReadOralce").setMaster("local[*]")
    val sc = new SparkContext(sparlkConf)
    val sqlContext = new SQLContext(sc)
    val property = new Properties()
    val url = "jdbc:oracle:thin:@//10.86.15.145:1521/ODRPT"
//    property.put("driver","oracle.jdbc.OracleDriver")
    property.put("user","DM0011695")
    property.put("password","***")
    val jdbcDF = sqlContext.read.jdbc(url,"ds.task_list",property)
    jdbcDF.registerTempTable("records")
    sqlContext.sql("select * from records where id=4").collect().foreach(println)
//    一些SQL语句
    result.select("ID").show()
    result.filter("ID>1").show()
    result.groupBy("ID").count().show();

  }

}