scala

最新推荐文章于 2025-09-11 20:53:34 发布

weixin_34323858

最新推荐文章于 2025-09-11 20:53:34 发布

阅读量65

点赞数

CC 4.0 BY-SA版权

文章标签： scala 数据库大数据

原文链接：http://www.cnblogs.com/vbiao/p/7128603.html

本文介绍了使用Beeline创建表并执行复杂查询的过程，同时展示了如何利用Spark SQL从MySQL读取数据并展示结果。涉及Beeline语法、SQL连接操作及Spark SQL的整合应用。

beeline>create table testThrift (field1 String , field2 Int);

beeline>insert into table testThrift select c.theyear,max(d.sumofamount) from tbDate c join (select a.dateid,a.ordernumber,sum(b.amount) as sumofamount from tbStock a join tbStockDetail b on a.ordernumber=b.ordernumber group by a.dateid,a.ordernumber ) d on c.dateid=d.dateid group by c.theyear sort by c.theyear;

scala
scala>
import org.apache.spark.sql.SQLContext
var sqlContext = new SQLContext(sc)
import sqlContext.implicits._
var url = "jdbc:mysql://slave02:3306/testdb?useUnicode=true&characterEncoding=gbk&zeroDateTimeBehavior=convertToNull"
var table = "stu_score"
var reader = sqlContext.read.format("jdbc")
var reader = sqlContext.read.format("jdbc")
reader.option("url",url)
reader.option("dbtable",table)
reader.option("driver","com.mysql.jdbc.driver")
reader.option("user","feifyu")
reader.option("password","feiyu")
var DF = reader.load();
DF.show();

select c.theyear,max(d.sumofamount) from tbDate c join
(select a.dateid,a.ordernumber,sum(b.amount) as sumofamount from tbStock a join
tbStockDetail b
on a.ordernumber=b.ordernumber group by a.dateid,a.ordernumber ) d
on c.dateid=d.dateid group by c.theyear sort by c.theyear;

转载于:https://www.cnblogs.com/vbiao/p/7128603.html