sparksql 求差集

最新推荐文章于 2024-01-27 19:41:39 发布

QJ_Aivin

最新推荐文章于 2024-01-27 19:41:39 发布

阅读量1.6k

点赞数

文章标签： spark sql

本文链接：https://blog.csdn.net/QJ_Aivin/article/details/105669719

版权

package test;

import org.apache.spark.SparkConf;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;


public class TestSparkSql {
    public static void main(String[] args) {
        SparkSession spark = SparkSession
                .builder()
                .appName("Java Spark Hive Example")
                .master("local[1]")
                .enableHiveSupport()
                .getOrCreate();


        spark.sql("drop table if exists src");
        spark.sql("CREATE TABLE IF NOT EXISTS src (key INT, value STRING)");

        Dataset<Row> resCount = spark.sql("select count(*) from src");
        spark.sql("insert into src values (1,\"张三\")");
        spark.sql("insert into src values (2,\"李四\")");
        spark.sql("insert into src values (3,\"王五\")");
        Dataset<Row> resSql = spark.sql("select key as stuID ,value name from src");
        resSql.show();
        resSql.createOrReplaceTempView("tempStu");

        spark.sql("drop table if exists score");
        spark.sql("create table if not exists score (stu_id int ,score int)");
        spark.sql("insert into score values(1,98),(2,78),(4,65)");

        Dataset<Row> updateRows = spark.sql("select score.* from tempStu,score where tempStu.stuId = score.stu_id");
        Dataset<Row> allDataOfScore = spark.sql("select * from score");
        allDataOfScore.except(updateRows).show();

        spark.close();
    }
}