hive函数之collect_set,collect_list,concat_ws,array_contains 联合使用

hive函数之collect_set/collect_list,concat_ws,array_contains 联合使用

1 表数据

select id,act_status from ods.ods_ta_task limit 6;

+----------------------+-------------+
|          id          | act_status  |
+----------------------+-------------+
| 3499945599152603749  | TEMP        |
| 3499945624922542181  | TEMP        |
| 3499945633511348581  | TEMP        |
| 3499945667872782181  | TEMP        |
| 3499945689346313829  | ANSWER      |
| 3499945766654782464  | GRADE       |
+----------------------+-------------+

2 sql

--查看状态里包括’TEMP‘的id
select  id, 
array_contains(split(concat_ws(',',collect_set(act_status)),','),'TEMP') 
from 
ods.ods_ta_task 
group by  id  
limit 5;
--返回值
+----------------------+--------+
|          id          |  _c1   |
+----------------------+--------+
| 3499945667872782181  | true   |
| 3499945766654782464  | true   |
| 3499945766655250944  | true   |
| 3499945766655834624  | true   |
| 3499945766656443648  | true   |
+----------------------+--------+