我有一个SQL表，From和To日期如下：
Row From To
--------------------------------------------------
1 2017-10-28 00:00:00 2017-10-30 00:00:00
2 2017-10-30 00:00:00 2017-10-31 00:00:00
3 2017-10-31 00:00:00 2017-10-31 07:30:00
4 2017-10-31 14:41:00 2017-10-31 15:14:00
5 2017-10-31 17:13:00 2017-11-01 00:00:00
6 2017-11-01 00:00:00 2017-11-01 23:45:00
7 2017-11-02 03:13:00 2017-11-02 07:56:00
我需要将连续数据分组到岛屿中。数据不重叠。使用此查询可以轻松完成此操作：
;with Islands as
(
SELECT
min([From]) as [From]
,max([To]) as [To]
FROM
(
select
[From],
[To],
sum(startGroup) over (order by [From]) StartGroup
from
(
SELECT
[From],
[To],
(case when [From] <= lag([To]) over (order by [From])
then 0
else 1
end) as StartGroup
FROM dbo.DateTable
) IsNewIsland
) GroupedIsland
group by StartGroup
)
select *
from Islands
并给我这些结果：
From To Rows
-----------------------------------------------------
2017-10-28 00:00:00 2017-10-31 07:30:00 1-3
2017-10-31 14:41:00 2017-10-31 15:14:00 4
2017-10-31 17:13:00 2017-11-01 23:45:00 5-6
2017-11-02 03:13:00 2017-11-02 07:56:00 7
我遇到的问题是，一旦他们获得了足够的记录到一定的总持续时间，我需要修改查询以限制/拆分岛屿。这是输入/硬编码值。拆分包括整个记录，而不是在记录From-To范围的中间分割。例如，我需要将岛屿分成 27 小时。这会得到这个结果：
From To Rows
-----------------------------------------------------
2017-10-29 00:00:00 2017-10-30 00:00:00 1
2017-10-30 00:00:00 2017-10-31 07:30:00 2-3
2017-10-31 17:13:00 2017-11-01 23:45:00 5-6
第一个岛屿被拆分，因为第1和第2行仅创造了27个小时的时间段。第4行和第7行不足以创建一个岛屿，因此它们会被忽略。
我尝试通过内部选择中的lag函数来提取此信息，以计算跨行的“滚动持续时间”，但它不适用于跨越2行的岛屿，因为它只跟踪最后一行行的持续时间，我无法“携带”计算。
SELECT
[From],
[To],
(case when [From] <= lag([To]) over (order by [From]
then (datediff(minute, [From], [To]) + lag(datediff(minute, [From], [To])) over (order by [From]))
else datediff(minute, [From], [To])
end) as RollingDuration,
(case when [From] <= lag([To]) over (order by [From])
then 0
else 1
end) as StartGroup
FROM dbo.DateTable
答案 0 :(得分：1)
＆＃34;最差的＆＃34;我能想到这样做的方式是一个古怪的更新＆＃34;。 （谷歌，老实说，我没有做到。）
UPDATE和用户变量迭代行并存储计算结果
使用它我可以在有间隙或总计达到27小时的情况下开始一个新组。然后照常进行。
-- New table to work through
----------------------------------------------------------------------
-- Addition [group_start] field (identifies groups, and useful data)
-- PRIMARY KEY CLUSTERED to enforce the order rows will be processed
----------------------------------------------------------------------
CREATE TABLE sample (
id INT,
start DATETIME,
cease DATETIME,
group_start DATETIME DEFAULT(0),
PRIMARY KEY CLUSTERED (group_start, start) -- To force the order we will iterate the rows, and is useful in last step
);
INSERT INTO
sample (
id,
start,
cease
)
VALUES
(1, '2017-10-28 00:00:00', '2017-10-30 00:00:00'),
(2, '2017-10-30 00:00:00', '2017-10-31 00:00:00'),
(3, '2017-10-31 00:00:00', '2017-10-31 07:30:00'),
(4, '2017-10-31 14:41:00', '2017-10-31 15:14:00'),
(5, '2017-10-31 17:13:00', '2017-11-01 00:00:00'),
(6, '2017-11-01 00:00:00', '2017-11-01 23:45:00'),
(7, '2017-11-02 03:13:00', '2017-11-02 07:56:00')
;
-- Quirky Update
----------------------------------------------------------------------
-- Update [group_start] to the start of the current group
-- -> new group if gap since previous row
-- -> new group if previous row took group to 27 hours
-- -> else same group as previous row
----------------------------------------------------------------------
DECLARE @grp_start DATETIME = 0;
WITH
lagged AS
(
SELECT *, LAG(cease) OVER (ORDER BY group_start, start) AS lag_cease FROM sample
)
UPDATE
lagged
SET
@grp_start
= group_start
= CASE WHEN start <> lag_cease THEN start
WHEN start >= DATEADD(hour, 27, @grp_start) THEN start
ELSE @grp_start END
OPTION
(MAXDOP 1)
;
-- Standard SQL to apply other logic
----------------------------------------------------------------------
-- MAX() OVER () to find end time of each group
-- WHERE to filter out any groups under 12 hours long
----------------------------------------------------------------------
SELECT
*
FROM
(
SELECT
*,
MAX(cease) OVER (PARTITION BY group_start) AS group_cease
FROM
sample
)
bounded_groups
WHERE
group_cease >= DATEADD(hour, 12, group_start)
;
http://dbfiddle.uk/?rdbms=sqlserver_2017&fiddle=1bec5b3fe920c1affd58f23a11e280a0