我有一个包含以下列的表:
[name_of_pos] varchar,
[date_from] datetime,
[date_to] datetime
下面是我的示例数据:
name_of_pos date_from date_to
----------------------------------------------------------------
Asystent 2015-08-26 08:57:49.000 2015-09-04 08:57:49.000
Biuro 2015-09-01 08:53:32.000 2015-09-01 08:53:32.000
Biuro 2015-09-02 09:00:41.000 2015-09-02 09:00:41.000
Biuro 2015-09-03 11:46:03.000 2015-09-03 11:46:03.000
Biuro 2015-09-10 09:02:11.000 2015-09-15 09:02:11.000
Koordynator 2015-09-01 09:04:06.000 2015-09-01 09:04:06.000
Projektant 2015-08-31 08:59:46.000 2015-09-01 08:59:46.000
Projektant 2015-09-02 08:00:54.000 2015-09-02 08:00:54.000
Projektant 2015-09-14 12:34:50.000 2015-09-14 12:34:50.000
我想返回的是每个name_of_pos的日期范围(date_from的min到date_to的max)，但只有在日期值连续的情况下(时间部分不重要，可以在结果中忽略)。
期望的输出将是:
name_of_pos date_from date_to
------------------------------------
Asystent 2015-08-26 2015-09-04
Biuro 2015-09-01 2015-09-03
Biuro 2015-09-10 2015-09-15
Koordynator 2015-09-01 2015-09-01
Projektant 2015-08-31 2015-09-02
Projektant 2015-09-14 2015-09-14
我尝试了一个类似于这个问题的解决方案:
如何对连续区间进行分组
但是没有运气，因为我有两个日期时间列。
这是一个使用cte迭代行(在它们被排序之后)并在分组之前检查连续天数的解决方案:
-- dummy table
CREATE TABLE #TableA
(
[name_of_pos] VARCHAR(11) ,
[date_from] DATETIME ,
[date_to] DATETIME
);
-- insert dummy data
INSERT INTO #TableA
( [name_of_pos], [date_from], [date_to] )
VALUES ( 'Asystent', '2015-08-26 08:57:49', '2015-09-04 08:57:49' ),
( 'Biuro', '2015-09-01 08:53:32', '2015-09-01 08:53:32' ),
( 'Biuro', '2015-09-02 09:00:41', '2015-09-02 09:00:41' ),
( 'Biuro', '2015-09-03 11:46:03', '2015-09-03 11:46:03' ),
( 'Biuro', '2015-09-10 09:02:11', '2015-09-15 09:02:11' ),
( 'Koordynator', '2015-09-01 09:04:06', '2015-09-01 09:04:06' ),
( 'Projektant', '2015-08-31 08:59:46', '2015-09-01 08:59:46' ),
( 'Projektant', '2015-09-02 08:00:54', '2015-09-02 08:00:54' ),
( 'Projektant', '2015-09-14 12:34:50', '2015-09-14 12:34:50' );
-- new temp table used to add row numbers for data order
SELECT name_of_pos, CAST(date_from AS DATE) date_from, CAST(date_to AS DATE) date_to,
ROW_NUMBER() OVER ( ORDER BY name_of_pos, date_from ) rn
INTO #temp
FROM #TableA
-- GroupingColumn in cte used to identify and group consecutive dates
;WITH cte
AS ( SELECT name_of_pos ,
date_from ,
date_to ,
1 AS GroupingColumn ,
rn
FROM #temp
WHERE rn = 1
UNION ALL
SELECT t2.name_of_pos ,
t2.date_from ,
t2.date_to ,
CASE WHEN t2.date_from = DATEADD(day, 1, cte.date_to)
AND cte.name_of_pos = t2.name_of_pos
THEN cte.GroupingColumn
ELSE cte.GroupingColumn + 1
END AS GroupingColumn ,
t2.rn
FROM #temp t2
INNER JOIN cte ON t2.rn = cte.rn + 1
)
SELECT name_of_pos, MIN(date_from) AS date_from, MAX(date_to) AS date_to
FROM cte
GROUP BY name_of_pos, GroupingColumn
DROP TABLE #temp
DROP TABLE #TableA
产生你想要的输出:
name_of_pos date_from date_to
Asystent 2015-08-26 2015-09-04
Biuro 2015-09-01 2015-09-03
Biuro 2015-09-10 2015-09-15
Koordynator 2015-09-01 2015-09-01
Projektant 2015-08-31 2015-09-02
Projektant 2015-09-14 2015-09-14
您可以使用cte，但根据我的经验，最快的方法是在循环中使用update:
declare @temp table
(
name_of_pos varchar(128),
date_from datetime,
date_to datetime
)
insert into @temp (
name_of_pos, date_from, date_to
)
values
('Asystent', '2015-08-26 08:57:49', '2015-09-04 08:57:49'),
('Biuro', '2015-09-01 08:53:32', '2015-09-01 08:53:32'),
('Biuro', '2015-09-02 09:00:41', '2015-09-02 09:00:41'),
('Biuro', '2015-09-03 11:46:03', '2015-09-03 11:46:03'),
('Biuro', '2015-09-10 09:02:11', '2015-09-15 09:02:11'),
('Koordynator', '2015-09-01 09:04:06', '2015-09-01 09:04:06'),
('Projektant', '2015-08-31 08:59:46', '2015-09-01 08:59:46'),
('Projektant', '2015-09-02 08:00:54', '2015-09-02 08:00:54'),
('Projektant', '2015-09-14 12:34:50', '2015-09-14 12:34:50')
----------------------------------------------------------------------------------------------------
declare @temp_new table (
name_of_pos varchar(128),
date_from date,
date_to date
)
insert into @temp_new (
name_of_pos, date_from, date_to
)
select
name_of_pos, date_from, date_to
from @temp
while @@rowcount > 0
begin
update t1 set
date_to = t2.date_to
from @temp_new as t1
inner join @temp_new as t2 on
t2.name_of_pos = t1.name_of_pos and
dateadd(dd, 1, t1.date_to) = t2.date_from
end
select name_of_pos, min(date_from), date_to
from @temp_new
group by name_of_pos, date_to
order by name_of_pos, date_to
这是一个缺口和岛屿问题。这是经过调整的官方方式来完成它，这将作为解决方案进行检查:
;with
cte as (
SELECT *,
dateadd( day,
- (ROW_NUMBER() OVER (
partition by name_of_pos
ORDER BY t.date_from
) + -- here starts tuned part --
isnull(
sum( datediff(day, date_from, date_to ) ) OVER (
partition by name_of_pos
ORDER BY t.date_from
ROWS BETWEEN UNBOUNDED PRECEDING and 1 PRECEDING
) ,0) -- here ends tuned part --
),
date_from
) as Grp
FROM t
)
SELECT name_of_pos
,min(date_from) AS date_from
,max(date_to) AS date_to
FROM cte
GROUP BY name_of_pos, Grp
ORDER BY name_of_pos, date_from
在sqlfiddle上进行了测试(使用了一些不同的样本数据)
试一次:
SELECT name_of_pos, date_from,date_to
FROM table
ORDER BY
name_of_pos asc, date_from desc;