hive> use mmzs;
hive> create table if not exists emp(eno int,ename string,eage int,bithday date,sal double,com double,gender string,dno int) row format delimited fields terminated by '\t';
hive> create table if not exists dept(dno int,dname string,loc string) row format delimited fields terminated by '\t';

cd /home/hadoop/test/hive/src

hdfs dfs -put emp01 /user/hive/warehouse/mmzs.db/emp
hdfs dfs -put dept01 /user/hive/warehouse/mmzs.db/dept

hive> use mmzs;

select dno,gender,count(1) renshu from emp where eage>25 group by gender,dno order by renshu desc;

select e.*,d.* from emp e,dept d where e.dno=d.dno;

select eno,ename,e.dno,d.dname from emp e inner join dept d on e.dno=d.dno;

select dno,eno,ename,sal,com from emp order by sal desc,com desc;

select dno,eno,ename,sal,com from emp group by dno,eno,ename,sal,com order by sal desc,com desc;

select d.dno,avg(sal) avgsal from emp e inner join dept d on e.dno=d.dno where eage>20 group by d.dno order by avgsal;

select d.dname,avgsal from (select d.dno,avg(sal) avgsal from emp e inner join dept d on e.dno=d.dno where eage>20 group by d.dno order by avgsal)mid,dept d where mid.dno=d.dno;

select e.* from emp e where e.sal>(select avg(sal) from emp dno=e.dno);

select * from emp limit 6;  //不产生Job
select * from emp limit 2,5;//会产生错误

select row_number() over() seq,e.* from emp e;
//row_number()是标识添加行号的关键字，按照over内的条件进行排列后，添加行号seq字段,
//over内不写条件，默认是在,将按照第一个字段降序排列后的结果,前加行号

select * from (select row_number() over(order by sal desc) seq,e.* from emp e) mid where mid.seq>5 and mid.seq<11;  //分页查询

create table t_user(userid int,username string,userage int) partitioned by(dno int) row format delimited fields terminated by '\t';//单级分区；dno是分区的字段名，添加分区时必须名字一样
create table t_user(userid int,username string,userage int) partitioned by(dno int,gender string) row format delimited fields terminated by '\t';//多级分区；dno是分区的字段名，添加分区时必须名字一样

alter table t_user add partition(dno=1);//添加分区，分区名是"dno=1"
alter table t_user drop partition(dno=1);//删除分区名是"dno=1"的分区 

truncate table t_user;//清空表中的数据
drop table t_user;//删除表

[hadoop@CloudDeskTop src]$ pwd
/home/hadoop/test/hive/src

 //创建表后hdfs dfs -put testarray /user/hive/warehouse/mmzs.db/tuser01hdfs dfs -put testmap /user/hive/warehouse/mmzs.db/tuser02hdfs dfs -put testarraymap user/hive/warehouse/mmzs.db/tuser03hdfs dfs -put teststruct /user/hive/warehouse/mmzs.db/tuser04

#创建的外部表不会因为表的删除而删除数据；
#外部表不会在默认的数据存放地址新建文件夹，从始至终都只有指定的目录下有数据//表的数据存放在指定外部hdfs集群地址"/test"目录中：
hive> create external table tuser00(userid int,username string,userage int) row format delimited fields terminated by '\t' location '/test';//在数据库下创建外部表就需要添加数据库的前缀
hive> use mmzs;
hive> create external table mmzs.tuser00(userid int,username string,userage int) row format delimited fields terminated by '\t' location '/test';

//创建一个带有数组的表：
hive> create table if not exists mmzs.tuser01(id bigint,name string,loves array<string>) row format delimited fields terminated by '\t' collection items terminated by ',';

select id,name,loves[1] from mmzs.tuser01;

//创建一个带有map的表：
hive> create table if not exists mmzs.tuser02(id bigint,name string,info map<string,double>) row format delimited fields terminated by '\t' collection items terminated by ',' map keys terminated by ':';
//注：map keys terminated by ':'中的 ：号是元素之间的分隔符，为了解析数据，可以是任意符号。

hive> select id,name,info["age"],info['height'] from mmzs.tuser02;//(如果查询的字段没有，会返回一个人Null)

//创建一个带有数组和map的表
hive> create table mmzs.tuser03(id bigint,name string,loves array<string>,info map<String,double>) row format delimited fields terminated by '\t' collection items terminated by ',' map keys terminated by ':';

//Struct类型(info是一个STRUCT类型，那么可以通过info.height得到这个用户的身高)
hive> create table mmzs.tuser04(id bigint,name string,info struct<age:int,height:double>) row format delimited fields terminated by '\t' collection items terminated by ',';//(如果查询的字段没有，会报异常)
hive> select id,name,info.age,info.height from mmzs.tuser04;