大数据学习——关于hive中的各种join

准备数据
2,b
3,c
4,d
7,y
8,u

2,bb
3,cc
7,yy
9,pp

建表：
create table a(id int,name string)
row format delimited fields terminated by ‘,‘;

create table b(id int,name string)
row format delimited fields terminated by ‘,‘;

导入数据：
load data local inpath ‘/root/hivedata/a.txt‘ into table a;
load data local inpath ‘/root/hivedata/b.txt‘ into table b;

 select * from a inner join b on a.id =b.id;

 select * from a left join b on a.id=b.id;

select * from a right join b on a.id=b.id;

select * from a full outer join b on a.id=b.id;

select * from a  left semi join b on a.id=b.id;

相当于
 select * from a where a.id exists(select b.id from b); 在hive中效率极低