Eliminate and reduce overlapping data ranges using SQL - sql

Question

i got a dataset in SQL Server Management Studio. The data looks like the following. i have a identifier for each people userID, date of the record, start timestartime and finish time endtime.
UserID date startime endtime
1 20110203 09:30 09:35
1 20110203 09:31 09:38
1 20110203 10:03 10:05
1 20110203 10:04:00 10:35:00
2 20110203 11:02 11:05
For each people, i want check if there is any overlapping time. If there is, I want to keep the smallest startime and largest endtime. if no overlapping time, I keep the original data. In addition, I want to calculate the duration of maxi endtime and smallest startime.
The result I want should looks like the following. Can anyone teach me how to code this please.
UserID date startime endtime diff
1 20110203 09:30 09:38 00:08
1 20110203 10:03 10:35 00:02
2 20110203 11:02 11:05 00:03

Answer 1

It seems that SELECT with CTE needs to recursively merge undetermined number of rows. In that case I would prefer safe CURSOR based solution:
DECLARE #t TABLE
(
UserId int,
[Date] date,
StartTime time,
EndTime time
);
INSERT INTO #t VALUES
(1, '2011-02-03', '09:30:00', '09:35:00'),
(1, '2011-02-03', '09:31:00', '09:38:00'),
(1, '2011-02-03', '09:36:00', '09:41:00'),
(1, '2011-02-03', '09:40:00', '09:45:00'),
(1, '2011-02-03', '09:42:00', '09:43:00'),
(1, '2011-02-03', '10:03:00', '10:05:00'),
(2, '2011-02-03', '11:02:00', '11:05:00'),
(1, '2011-02-03', '12:00:00', '12:05:00'),
(1, '2011-02-03', '12:04:00', '12:06:00');
------------------
DECLARE #result TABLE
(
UserId int,
[Date] date,
StartTime time,
EndTime time
)
DECLARE cur CURSOR FOR
SELECT UserId, [Date], StartTime, EndTime
FROM #t
ORDER BY UserId, [Date], StartTime;
DECLARE #UserId int
DECLARE #Date date
DECLARE #StartTime time
DECLARE #EndTime time
DECLARE #LastUserId int
DECLARE #LastDate date
DECLARE #LastStartTime time
DECLARE #LastEndTime time
OPEN cur
FETCH NEXT FROM cur INTO #UserId, #Date, #StartTime, #EndTime
SET #LastUserId = #UserId
SET #LastDate = #Date
SET #LastStartTime = #StartTime
SET #LastEndTime = #EndTime
WHILE ##FETCH_STATUS = 0
BEGIN
IF #UserId = #LastUserId AND #Date = #LastDate AND #StartTime <= #LastEndTime
SET #LastEndTime = CASE WHEN #LastEndTime > #EndTime THEN #LastEndTime ELSE #EndTime END
ELSE
BEGIN
INSERT #result(UserId, [Date], StartTime, EndTime) VALUES (#LastUserId, #LastDate, #LastStartTime, #LastEndTime)
SET #LastUserId = #UserId
SET #LastDate = #Date
SET #LastStartTime = #StartTime
SET #LastEndTime = #EndTime
END
FETCH NEXT FROM cur INTO #UserId, #Date, #StartTime, #EndTime
END
INSERT #result(UserId, [Date], StartTime, EndTime) VALUES (#LastUserId, #LastDate, #LastStartTime, #LastEndTime)
CLOSE cur
DEALLOCATE cur
SELECT UserId,
[Date],
StartTime,
EndTime,
CAST(DATEADD(second,DATEDIFF(second,StartTime,EndTime),'2000-01-01') AS time) Diff
FROM #result
which returns
1 2011-02-03 09:30:00.0000000 09:45:00.0000000 00:15:00.0000000
1 2011-02-03 10:03:00.0000000 10:05:00.0000000 00:02:00.0000000
1 2011-02-03 12:00:00.0000000 12:06:00.0000000 00:06:00.0000000
2 2011-02-03 11:02:00.0000000 11:05:00.0000000 00:03:00.0000000

Answer 2

Following a redesigned Version of my previous cte Approach. However, it will still have Problems if there are multiple records for the same user with identical start time... didn't have time to fix that one, but as far as I understood this is not possible in the described process!?
--
-- This part is temporary and has to be replaced by your tables
-- There several more records included now
-- There is still a glitch if the starttime is identical for two records - but as far as I understood, this is not possible in the described case?
--
declare #t table (userid int, date int, starttime time, endtime time);
insert into #t values (1, 20110203, '09:30:00', '09:35:00'), (1, 20110203, '09:31:00', '09:38:00'), (1, 20110203, '09:36:00', '09:41:00'), (1, 20110203, '10:03:00', '10:05:00'),(1, 20110203, '10:04:00', '10:35:00'),
(2, 20110203, '11:02:00', '11:05:00'), (2, 20110203, '11:03:00', '11:20:00'), (2, 20110203, '11:04:00', '11:35:00'), (2, 20110203, '13:02:00', '13:05:00'), (2, 20110203, '13:04:00', '13:15:00');
--
-- First cte: selects all start and endtimes and their - if existing - "overlaps"; recursive cte
--
WITH cte AS(
SELECT 1 lvl, a.userid
,CASE WHEN a.starttime <= ISNULL(b.starttime, a.starttime) THEN a.starttime ELSE b.starttime END AS starttime
,CASE WHEN a.endtime >= ISNULL(b.endtime, a.endtime) THEN a.endtime ELSE b.endtime END AS endtime
FROM #t as a
LEFT OUTER JOIN #t AS b ON b.userid = a.userid
AND b.starttime < a.starttime
AND b.endtime > a.starttime
UNION ALL
select a.lvl+1, a.userid
,CASE WHEN a.starttime <= ISNULL(b.starttime, a.starttime) THEN a.starttime ELSE b.starttime END AS xStart
,CASE WHEN a.endtime >= ISNULL(b.endtime, a.endtime) THEN a.endtime ELSE b.endtime END AS xEnd
from cte as a
INNER JOIN #t AS b ON b.userid = a.userid
AND b.starttime < a.starttime
AND b.endtime > a.starttime
),
--
-- Second cte: get the max. lvl result per user from the recursive cte
--
cteUserMaxLvl AS (
SELECT userid, max(lvl) AS MaxLvl
FROM cte
GROUP BY userid
),
--
-- third cte: get the rows matching the max.lvl; their timespan should cover the desired min. start and max. end
--
cteNoMoreOverlap AS(
SELECT a.userid, starttime, endtime
FROM cte AS a
JOIN cteUserMaxLvl AS b ON a.userid = b.userid AND a.lvl = b.MaxLvl
)
--
-- Select the rows from the "No more overlap" cte
--
SELECT userid, starttime, endtime
FROM cteNoMoreOverlap
UNION ALL
--
-- And finally select all rows, which are not covered by the previously selected timespan
--
SELECT a.userid, min(a.starttime) AS starttime, max(a.endtime) AS endtime
FROM cte AS a
JOIN cteNoMoreOverlap AS b ON a.userid = b.userid AND a.starttime NOT BETWEEN b.starttime AND b.endtime
GROUP BY a.userid
order by userid, starttime, endtime

Answer 3

I believe when you say overlapping time, you are saying within the same hour on the same day. If that is what you mean, following solution might work. Attached is the screenshot of my results.
CREATE TABLE #OverlappingDates
(
UserID INT
, [date] DATE
, starttime VARCHAR(5)
, endtime VARCHAR(5)
);
INSERT INTO #OverlappingDates
( UserID, date, starttime, endtime )
VALUES ( 1 -- UserID - int
, '20110203' -- date - date
, '09:30' -- starttime - time
, '09:35' -- endtime - time
),
( 1 -- UserID - int
, '20110203' -- date - date
, '09:31' -- starttime - time
, '09:38' -- endtime - time
),
( 1 -- UserID - int
, '20110203' -- date - date
, '10:03' -- starttime - time
, '10:05' -- endtime - time
),
( 2 -- UserID - int
, '20110203' -- date - date
, '11:02' -- starttime - time
, '11:05' -- endtime - time
),
( 2 -- UserID - int
, '20110203' -- date - date
, '11:05' -- starttime - time
, '11:15' -- endtime - time
),
( 2 -- UserID - int
, '20110203' -- date - date
, '11:05' -- starttime - time
, '12:00' -- endtime - time
);
WITH cte
AS ( SELECT UserID
, date
, MIN(starttime) AS StartTime
, MAX(endtime) AS EndTime
FROM #OverlappingDates
GROUP BY UserID
, date
, LEFT(starttime, 2)
, LEFT(endtime, 2)
)
SELECT cte.UserID
, cte.date
, cte.StartTime
, cte.EndTime
, ( RIGHT('0'
+ CAST(( DATEDIFF(SECOND,
( CAST(CONCAT(( CAST(cte.[date] AS VARCHAR(10)) ),
' ', cte.StartTime) AS DATETIME) ),
( CAST(CONCAT(( CAST(cte.[date] AS VARCHAR(10)) ),
' ', cte.EndTime) AS DATETIME) )) )
/ 3600 AS VARCHAR(2)), 2) + ':' + RIGHT('0'
+ CAST(( ( DATEDIFF(SECOND,
( CAST(CONCAT(( CAST(cte.[date] AS VARCHAR(10)) ),
' ',
cte.StartTime) AS DATETIME) ),
( CAST(CONCAT(( CAST(cte.[date] AS VARCHAR(10)) ),
' ', cte.EndTime) AS DATETIME) )) )
/ 60 ) % 60 AS VARCHAR(2)),
2) ) AS Diff
FROM cte;