hadoop离线阶段（第二十二节—1）impala查询语句及Java代码操作impala

impala查询语句

基本语句

impala适用绝大多数的hive查询语句，如：

创建表
create table employee (Id INT, name STRING, age INT,address STRING, salary BIGINT)
row  format  delimited fields terminated  by  '\t'
location  '/input/impala/external'; 
#需要注意，impala一般不具有hdfs路径的读写权限，所以在指定路径时需要对路径进行权限修改

插入数据
insert into employee (ID,NAME,AGE,ADDRESS,SALARY)VALUES (1, 'Ramesh', 32, 'Ahmedabad', 20000 );
insert into employee values (2, 'Khilan', 25, 'Delhi', 15000 );

数据的覆盖
Insert overwrite employee values (1, 'Ram', 26, 'Vishakhapatnam', 37000 );

数据的查询
select * from employee;
select name,age from employee;

删除表
DROP table  mydb1.employee;

清空表数据
truncate  employee;

创建视图
CREATE VIEW IF NOT EXISTS employee_view AS select name, age from employee;

查看视图数据
select * from employee_view;

order  by语句
Select * from employee ORDER BY id asc;

group  by语句
Select name, sum(salary) from employee Group BY name;

having语句（按年龄进行分组，基于年龄分组求每组最高的薪资，并筛选最高薪资在20000以上的） 
select a.age_g,max(a.salary) from
(select *,case when age<30 then '20-29'
when age between 30 and 39 then '30-39' else '40up' end as age_g