我有一张包含如下数据的表格，
id code data1 data2 country
1 1 A NULL IND
1 1 B B NZ
1 1 CA
1 1 C Z WI
1 1 D S UK
2 2 NULL NULL IND
2 2 S NULL NZ
2 2 NULL K CA
2 2 T T WI
2 2 R K UK
3 3 NULL A WI
3 3 NULL a UK
记录将根据国家/地区字段的优先级填充。优先考虑的是IND，NZ，CA，WI，UK
如果在data1中有任何NULL，空白，则data2字段数据将从下一个优先级记录中填充。
所以，我的预期结果是： 目标表：
id code data1 data2 country
1 1 A B IND
2 2 S K IND
3 3 NULL A WI
任何人都可以帮我查询以获得上述结果集。
为了更好地理解查询，我添加了更多行。
答案 0 :(得分：1)
Hive具有select distinct id, code,
first_value(data1) over (partition by id, code
order by (case when data1 is not null then 1 else 2 end),
(case country when 'IND' then 1 when 'NZ' then 2 when 'CA' then 3 when 'WI' then 4 when 'UK' then 5 else 6 end)
) as data1,
first_value(data2) over (partition by id, code
order by (case when data2 is not null then 1 else 2 end),
(case country when 'IND' then 1 when 'NZ' then 2 when 'CA' then 3 when 'WI' then 4 when 'UK' then 5 else 6 end)
) as data2,
first_value(country) over (partition by id, code
order by (case when data1 is not null then 1 else 2 end),
(case country when 'IND' then 1 when 'NZ' then 2 when 'CA' then 3 when 'WI' then 4 when 'UK' then 5 else 6 end)
) as country
from t;
功能，可用于此目的：
select distinct我不是 (function () {
var itemCtx = {};
itemCtx.Templates = {};
itemCtx.Templates.Header = "<div><b>Announcements</b></div><table>";
itemCtx.Templates.Item = ItemOverrideFun;
itemCtx.Templates.Footer = "</table>";
itemCtx.BaseViewID = 1;
itemCtx.ListTemplateType = 104;
SPClientTemplates.TemplateManager.RegisterTemplateOverrides(itemCtx);
})();
function ItemOverrideFun(ctx) {
var _announcementTitle = ctx.CurrentItem.Title;
var _announcementDesc = ctx.CurrentItem.Body;
var _announcementID = ctx.CurrentItem.ID;
return "<tr><td><p><b>" + _announcementTitle + "</b></p>" + _announcementDesc +"<a href='/Lists/Company%20Announcements/DispForm.aspx?ID=" _announcementID +"'> Read More…</a></td></tr>";
窗口函数的忠实粉丝。在这种情况下，它似乎是最简单的解决方案。
答案 1 :(得分：0)
用例来获取优先级并在其上使用first_value。
select id, max(code), max(data1), max(data2), max(country)
from (
select
id,
code,
first_value(data1) over (partition by id
order by case when data1 is null or data1 = '' then 1 else 0 end * 10 + priority) data1,
first_value(data2) over (partition by id
order by case when data2 is null or data2 = '' then 1 else 0 end * 10 + priority) data2,
first_value(country) over (partition by id
order by case when country is null or country = '' then 1 else 0 end * 10 + priority) country
from (
select
t.*,
case country
when 'IND' then 1
when 'NZ' then 2
when 'CA' then 3
when 'WI' then 4
when 'UK' then 5
end priority
from your_table t
) t
) t group by id;
产地：
ID MAX(CODE) MAX(DATA1) MAX(DATA2) MAX(COUNTRY)
1 1 A B IND
2 2 S K IND
3 3 NULL A WI
您也可以使用FIELD函数（在hive，MySQL中提供）来生成@Dudu在以下评论中建议的优先级：
field(country,'IND','NZ','CA','WI','UK')
请参阅：
答案 2 :(得分：0)
另一种基于STRUCT的MIN的方法。
对于我使用函数field（field(country,'IND','NZ','CA','WI','UK')）的订单
由于它丢失了，我已将其添加到文档中。
https://cwiki.apache.org/confluence/display/Hive/LanguageManual+UDF
select id
,min (code) as code
,min (case when coalesce(trim(data1),'') <> '' then struct(field(country,'IND','NZ','CA','WI','UK'),data1) end).col2 as data1
,min (case when coalesce(trim(data2),'') <> '' then struct(field(country,'IND','NZ','CA','WI','UK'),data2) end).col2 as data2
,min (struct(field(country,'IND','NZ','CA','WI','UK'),country)).col2 as country
from mytable
group by id
order by id
;
create table mytable
(
id int
,code int
,data1 string
,data2 string
,country string
);
insert into mytable values
(1 ,1 ,'A' ,NULL ,'IND')
,(1 ,1 ,'B' ,'B' ,'NZ' )
,(1 ,1 ,'' ,'' ,'CA' )
,(1 ,1 ,'C' ,'Z' ,'WI' )
,(1 ,1 ,'D' ,'S' ,'UK' )
,(2 ,2 ,NULL ,NULL ,'IND')
,(2 ,2 ,'S' ,NULL ,'NZ' )
,(2 ,2 ,NULL ,'K' ,'CA' )
,(2 ,2 ,'T' ,'T' ,'WI' )
,(2 ,2 ,'R' ,'K' ,'UK' )
,(3 ,3 ,NULL ,'A' ,'WI' )
,(3 ,3 ,NULL ,'a' ,'UK' )
;
select id
,min (code) as code
,min (case when coalesce(trim(data1),'') <> '' then struct(field(country,'IND','NZ','CA','WI','UK'),data1) end).col2 as data1
,min (case when coalesce(trim(data2),'') <> '' then struct(field(country,'IND','NZ','CA','WI','UK'),data2) end).col2 as data2
,min (struct(field(country,'IND','NZ','CA','WI','UK'),country)).col2 as country
from mytable
group by id
order by id
;
+----+------+-------+-------+---------+
| id | code | data1 | data2 | country |
+----+------+-------+-------+---------+
| 1 | 1 | A | B | IND |
| 2 | 2 | S | K | IND |
| 3 | 3 | NULL | A | WI |
+----+------+-------+-------+---------+