Related
I has posted this question before: SQL Server: Using cursor to loop and insert incremental values (thanks for those who give me the solutions)
So I create the query as stored procedure and it will run daily. Here it is:
CREATE PROC [dbo].[sp_est_busrequest]
As
declare #ReqDocNo int = 0;
set nocount on
Select #ReqDocNo = isnull(convert(int, max(ReqDocNo)), 0)
from est_Request;
insert into est_Request (ReqDocNo,Reason,PickUpDate,PickUpTime,SendBackDate,SendBackTime,Requester,DeptID,Ext,RequestDate,RequestTime,ApprovedBy,ApprovedDate,Remark1,Remark2,Status )
select Distinct ReqDocNo = right('0000000000'
+ convert(varchar(10),
#ReqDocNo + dense_rank() over (order by ot.pick_up_date, ot.shift_time)),
10),
'', pick_up_date ,shift_time , send_back_date, send_back_time ,pic,'',ext,convert(date, getdate()), convert(time, getdate()),'','','','',UPPER(status)
FROM ot
insert into est_RequestDetail
Select ReqDocNo = right('0000000000'
+ convert(varchar(10),
#ReqDocNo + dense_rank() over (order by ot.pick_up_date, ot.shift_time)),
10), ot.empid, RouteNo,BusStopID,'',''
from est_BusGuest , ot
where est_BusGuest.empid = ot.empid
and routeNo in (select routeno from est_busroute a, est_buszone b
where a.zoneno = b.zoneno
and b.branchid = '2')
set nocount off
truncate table ot
table ot need to truncate because it will retrieve data from another system daily.
table est_Request and est_RequestDetail has index and primary key. Here is the info for index:
Index description for table est_Request:
PK_est_Request | nonclustered, unique, primary key located on PRIMARY | ReqDocNo
Request_ix1 | clustered, unique located on PRIMARY | ReqDocNo, PickUpDate, SendBackDate
Index description for table est_RequestDetail:
PK_est_RequestDetail | nonclustered, unique, primary key located on PRIMARY | ReqDocNo, empID
Request_ix1 | clustered located on PRIMARY | ReqDocNo
Request_ix2 | nonclustered located on PRIMARY | ReqDocNo, empID
So if the SQL Job run one time per day, data will insert successfully and no error. However, I'm worried if there are need to run the SQL Job more than one in a day, maybe has error with data that require to manually trigger the job so it will create duplicate error. My question is, is this the right way to do, or do I need to change table structure like drop the index.
your script is fine, but you don't need to duplicate your ReqDocNo generation during insert of your main table and details table. here's what i would suggest, using cte as storage of your generated ReqDocNo
declare #ReqDocNoTb table(
ReqDocNo varchar(50),
EmpId int
);
with cte as (
select distinct ReqDocNo = right('0000000000'
+ convert(varchar(10),
(select isnull(convert(int, max(ReqDocNo)), 0) from est_Request) + dense_rank() over (order by ot.pick_up_date, ot.shift_time)),
10) as ReqDocNo,
EmpId
from ot
)
insert into #ReqDocNoTb(ReqDocNo, EmpId)
select ReqDocNo, EmpId from cte
--uncomment to check generated RecDocNo before inserting
--select * from #ReqDocNoTb
insert into est_Request (ReqDocNo,Reason,PickUpDate,PickUpTime,SendBackDate,SendBackTime,Requester,DeptID,Ext,RequestDate,RequestTime,ApprovedBy,ApprovedDate,Remark1,Remark2,Status)
select c.ReqDocNo,'', pick_up_date ,shift_time , send_back_date, send_back_time ,pic,'',ext,convert(date, getdate()), convert(time, getdate()),'','','','',UPPER(status) from #ReqDocNoTb c
inner join ot o on o.EmpId = c.EmpId
insert into est_RequestDetail
select c.ReqDocNo, c.empid, b.RouteNo, b.BusStopID,'',''
from est_BusGuest b, #ReqDocNoTb c
where est_BusGuest.empid = c.empid
and routeNo in (select routeno from est_busroute a, est_buszone b
where a.zoneno = b.zoneno
and b.branchid = '2')
I need to store simple data - suppose I have some products with codes as a primary key, some properties and validity ranges. So data could look like this:
Products
code value begin_date end_date
10905 13 2005-01-01 2016-12-31
10905 11 2017-01-01 null
Those ranges are not overlapping, so on every date I have a list of unique products and their properties. So to ease the use of it I've created the function:
create function dbo.f_Products
(
#date date
)
returns table
as
return (
select
from dbo.Products as p
where
#date >= p.begin_date and
#date <= p.end_date
)
This is how I'm going to use it:
select
*
from <some table with product codes> as t
left join dbo.f_Products(#date) as p on
p.code = t.product_code
This is all fine, but how I can let optimizer know that those rows are unique to have better execution plan?
I did some googling, and found a couple of really nice articles for DDL which prevents storing overlapping ranges in the table:
Self-maintaining, Contiguous Effective Dates in Temporal Tables
Storing intervals of time with no overlaps
But even if I try those constraint I see that optimizer cannot understand that resulting recordset will return unique codes.
What I'd like to have is certain approach which gives me basically the same performance as if I stored those products list on certain date and selected it with date = #date.
I know that some RDMBS (like PostgreSQL) have special data types for this (Range Types). But SQL Server doesn't have anything like this.
Am I missing something or there're no way to do this properly in SQL Server?
You can create an indexed view that contains a row for each code/date in the range.
ProductDate (indexed view)
code value date
10905 13 2005-01-01
10905 13 2005-01-02
10905 13 ...
10905 13 2016-12-31
10905 11 2017-01-01
10905 11 2017-01-02
10905 11 ...
10905 11 Today
Like this:
create schema digits
go
create table digits.Ones (digit tinyint not null primary key)
insert into digits.Ones (digit) values (0),(1),(2),(3),(4),(5),(6),(7),(8),(9)
create table digits.Tens (digit tinyint not null primary key)
insert into digits.Tens (digit) values (0),(1),(2),(3),(4),(5),(6),(7),(8),(9)
create table digits.Hundreds (digit tinyint not null primary key)
insert into digits.Hundreds (digit) values (0),(1),(2),(3),(4),(5),(6),(7),(8),(9)
create table digits.Thousands (digit tinyint not null primary key)
insert into digits.Thousands (digit) values (0),(1),(2),(3),(4),(5),(6),(7),(8),(9)
create table digits.TenThousands (digit tinyint not null primary key)
insert into digits.TenThousands (digit) values (0),(1),(2),(3),(4),(5),(6),(7),(8),(9)
go
create schema info
go
create table info.Products (code int not null, [value] int not null, begin_date date not null, end_date date null, primary key (code, begin_date))
insert into info.Products (code, [value], begin_date, end_date) values
(10905, 13, '2005-01-01', '2016-12-31'),
(10905, 11, '2017-01-01', null)
create table info.DateRange ([begin] date not null, [end] date not null, [singleton] bit not null default(1) check ([singleton] = 1))
insert into info.DateRange ([begin], [end]) values ((select min(begin_date) from info.Products), getdate())
go
create view info.ProductDate with schemabinding
as
select
p.code,
p.value,
dateadd(day, ones.digit + tens.digit*10 + huns.digit*100 + thos.digit*1000 + tthos.digit*10000, dr.[begin]) as [date]
from
info.DateRange as dr
cross join
digits.Ones as ones
cross join
digits.Tens as tens
cross join
digits.Hundreds as huns
cross join
digits.Thousands as thos
cross join
digits.TenThousands as tthos
join
info.Products as p on
dateadd(day, ones.digit + tens.digit*10 + huns.digit*100 + thos.digit*1000 + tthos.digit*10000, dr.[begin]) between p.begin_date and isnull(p.end_date, datefromparts(9999, 12, 31))
go
create unique clustered index idx_ProductDate on info.ProductDate ([date], code)
go
select *
from info.ProductDate with (noexpand)
where
date = '2014-01-01'
drop view info.ProductDate
drop table info.Products
drop table info.DateRange
drop table digits.Ones
drop table digits.Tens
drop table digits.Hundreds
drop table digits.Thousands
drop table digits.TenThousands
drop schema digits
drop schema info
go
A solution without gaps might be this:
DECLARE #tbl TABLE(ID INT IDENTITY,[start_date] DATE);
INSERT INTO #tbl VALUES({d'2016-10-01'}),({d'2016-09-01'}),({d'2016-08-01'}),({d'2016-07-01'}),({d'2016-06-01'});
SELECT * FROM #tbl;
DECLARE #DateFilter DATE={d'2016-08-13'};
SELECT TOP 1 *
FROM #tbl
WHERE [start_date]<=#DateFilter
ORDER BY [start_date] DESC
Important: Be sure that there is an (unique) index on start_date
UPDATE: for different products
DECLARE #tbl TABLE(ID INT IDENTITY,ProductID INT,[start_date] DATE);
INSERT INTO #tbl VALUES
--product 1
(1,{d'2016-10-01'}),(1,{d'2016-09-01'}),(1,{d'2016-08-01'}),(1,{d'2016-07-01'}),(1,{d'2016-06-01'})
--product 1
,(2,{d'2016-10-17'}),(2,{d'2016-09-16'}),(2,{d'2016-08-15'}),(2,{d'2016-07-10'}),(2,{d'2016-06-11'});
DECLARE #DateFilter DATE={d'2016-08-13'};
WITH PartitionedCount AS
(
SELECT ROW_NUMBER() OVER(PARTITION BY ProductID ORDER BY [start_date] DESC) AS Nr
,*
FROM #tbl
WHERE [start_date]<=#DateFilter
)
SELECT *
FROM PartitionedCount
WHERE Nr=1
First you need to create a unique clustered index for (begin_date, end_date, code)
Then SQL engine will be able to do INDEX SEEK.
Additionally, you can also try to create a view for dbo.Products table to join that table with pre-populated dbo.Dates table.
select p.code, p.val, p.begin_date, p.end_date, d.[date]
from dbo.Product as p
inner join dbo.dates d on p.begin_date <= d.[date] and d.[date] <= p.end_date
Then in your function, you use that view as "where #date = view.date". The result can be either better or slightly worse... it depends on the actual data.
You also can try to make that view indexed (depends on how often it is being updated).
Alternatively, you can have better performance if you populate dbo.Products table for every date in the [begin_date] .. [end_date] range.
Approach with ROW_NUMBER scans the whole Products table once. It is the best method if you have a lot of product codes in the Products table and few validity ranges for each code.
WITH
CTE_rn
AS
(
SELECT
code
,value
,ROW_NUMBER() OVER (PARTITION BY code ORDER BY begin_date DESC) AS rn
FROM Products
WHERE begin_date <= #date
)
SELECT *
FROM
<some table with product codes> as t
LEFT JOIN CTE_rn ON CTE_rn.code = t.product_code AND CTE_rn.rn = 1
;
If you have few product codes and a lot of validity ranges for each code in the Products table, then it is better to seek the Products table for each code using OUTER APPLY.
SELECT *
FROM
<some table with product codes> as t
OUTER APPLY
(
SELECT TOP(1)
Products.value
FROM Products
WHERE
Products.code = t.product_code
AND Products.begin_date <= #date
ORDER BY Products.begin_date DESC
) AS A
;
Both variants need unique index on (code, begin_date DESC) include (value).
Note how the queries don't even look at end_date, because they assume that intervals don't have gaps. They will work in SQL Server 2008.
EDIT: My original answer was using an INNER JOIN, but the questioner wanted a LEFT JOIN.
CREATE TABLE Products
(
[Code] INT NOT NULL
, [Value] VARCHAR(30) NOT NULL
, Begin_Date DATETIME NOT NULL
, End_Date DATETIME NULL
)
/*
Products
code value begin_date end_date
10905 13 2005-01-01 2016-12-31
10905 11 2017-01-01 null
*/
INSERT INTO Products ([Code], [Value], Begin_Date, End_Date) VALUES (10905, 13, '2005-01-01', '2016-12-31')
INSERT INTO Products ([Code], [Value], Begin_Date, End_Date) VALUES (10905, 11, '2017-01-01', NULL)
CREATE NONCLUSTERED INDEX SK_ProductDate ON Products ([Code], Begin_Date, End_Date) INCLUDE ([Value])
CREATE TABLE SomeTableWithProductCodes
(
[CODE] INT NOT NULL
)
INSERT INTO SomeTableWithProductCodes ([Code]) VALUES (10905)
Here is a prototypical query, with a date predicate. Note that there are more optimal ways to do this in a bulletproof fashion, using a "less than" operator on the upper bound, but that's a different discussion.
SELECT
P.[Code]
, P.[Value]
, P.[Begin_Date]
, P.[End_Date]
FROM
SomeTableWithProductCodes ST
LEFT JOIN Products AS P ON
ST.[Code] = P.[Code]
AND '2016-06-30' BETWEEN P.[Begin_Date] AND ISNULL(P.[End_Date], '9999-12-31')
This query will perform an Index Seek on the Product table.
Here is a SQL Fiddle: SQL Fiddle - Products and Dates
EDITED:
I'm working in Sql Server 2005 and I'm trying to get a year over year (YOY) count of distinct users for the current fiscal year (say Jun 1-May 30) and the past 3 years. I'm able to do what I need by running a select statement four times, but I can't seem to find a better way at this point. I'm able to get a distinct count for each year in one query, but I need it to a cumulative distinct count. Below is a mockup of what I have so far:
SELECT [Year], COUNT(DISTINCT UserID)
FROM
(
SELECT u.uID AS UserID,
CASE
WHEN dd.ddEnd BETWEEN #yearOneStart AND #yearOneEnd THEN 'Year1'
WHEN dd.ddEnd BETWEEN #yearTwoStart AND #yearTwoEnd THEN 'Year2'
WHEN dd.ddEnd BETWEEN #yearThreeStart AND #yearThreeEnd THEN 'Year3'
WHEN dd.ddEnd BETWEEN #yearFourStart AND #yearFourEnd THEN 'Year4'
ELSE 'Other'
END AS [Year]
FROM Users AS u
INNER JOIN UserDataIDMatch AS udim
ON u.uID = udim.udim_FK_uID
INNER JOIN DataDump AS dd
ON udim.udimUserSystemID = dd.ddSystemID
) AS Data
WHERE LOWER([Year]) 'other'
GROUP BY
[Year]
I get something like:
Year1 1
Year2 1
Year3 1
Year4 1
But I really need:
Year1 1
Year2 2
Year3 3
Year4 4
Below is a rough schema and set of values (updated for simplicity). I tried to create a SQL Fiddle, but I'm getting a disk space error when I attempt to build the schema.
CREATE TABLE Users
(
uID int identity primary key,
uFirstName varchar(75),
uLastName varchar(75)
);
INSERT INTO Users (uFirstName, uLastName)
VALUES
('User1', 'User1'),
('User2', 'User2')
('User3', 'User3')
('User4', 'User4');
CREATE TABLE UserDataIDMatch
(
udimID int indentity primary key,
udim.udim_FK_uID int foreign key references Users(uID),
udimUserSystemID varchar(75)
);
INSERT INTO UserDataIDMatch (udim_FK_uID, udimUserSystemID)
VALUES
(1, 'SystemID1'),
(2, 'SystemID2'),
(3, 'SystemID3'),
(4, 'SystemID4');
CREATE TABLE DataDump
(
ddID int identity primary key,
ddSystemID varchar(75),
ddEnd datetime
);
INSERT INTO DataDump (ddSystemID, ddEnd)
VALUES
('SystemID1', '10-01-2013'),
('SystemID2', '10-01-2014'),
('SystemID3', '10-01-2015'),
('SystemID4', '10-01-2016');
Unless I'm missing something, you just want to know how many records there are where the date is less than or equal to the current fiscal year.
DECLARE #YearOneStart DATETIME, #YearOneEnd DATETIME,
#YearTwoStart DATETIME, #YearTwoEnd DATETIME,
#YearThreeStart DATETIME, #YearThreeEnd DATETIME,
#YearFourStart DATETIME, #YearFourEnd DATETIME
SELECT #YearOneStart = '06/01/2013', #YearOneEnd = '05/31/2014',
#YearTwoStart = '06/01/2014', #YearTwoEnd = '05/31/2015',
#YearThreeStart = '06/01/2015', #YearThreeEnd = '05/31/2016',
#YearFourStart = '06/01/2016', #YearFourEnd = '05/31/2017'
;WITH cte AS
(
SELECT u.uID AS UserID,
CASE
WHEN dd.ddEnd BETWEEN #yearOneStart AND #yearOneEnd THEN 'Year1'
WHEN dd.ddEnd BETWEEN #yearTwoStart AND #yearTwoEnd THEN 'Year2'
WHEN dd.ddEnd BETWEEN #yearThreeStart AND #yearThreeEnd THEN 'Year3'
WHEN dd.ddEnd BETWEEN #yearFourStart AND #yearFourEnd THEN 'Year4'
ELSE 'Other'
END AS [Year]
FROM Users AS u
INNER JOIN UserDataIDMatch AS udim
ON u.uID = udim.udim_FK_uID
INNER JOIN DataDump AS dd
ON udim.udimUserSystemID = dd.ddSystemID
)
SELECT
DISTINCT [Year],
(SELECT COUNT(*) FROM cte cteInner WHERE cteInner.[Year] <= cteMain.[Year] )
FROM cte cteMain
Concept using an existing query
I have done something similar for finding out the number of distinct customers who bought something in between years, I modified it to use your concept of year, the variables you add would be that start day and start month of the year and the start year and end year.
Technically there is a way to avoid using a loop but this is very clear and you can't go past year 9999 so don't feel like putting clever code to avoid a loop makes sense
Tips for speeding up the query
Also when matching dates make sure you are comparing dates, and not comparing a function evaluation of the column as that would mean running the function on every record set and would make indices useless if they existed on dates (which they should). Use date add on
zero to initiate your target dates subtracting 1900 from the year, one from the month and one from the target date.
Then self join on the table where the dates create a valid range (i.e. yearlessthan to yearmorethan) and use a subquery to create a sum based on that range. Since you want accumulative from the first year to the last limit the results to starting at the first year.
At the end you will be missing the first year as by our definition it does not qualify as a range, to fix this just do a union all on the temp table you created to add the missing year and the number of distinct values in it.
DECLARE #yearStartMonth INT = 6, #yearStartDay INT = 1
DECLARE #yearStart INT = 2008, #yearEnd INT = 2012
DECLARE #firstYearStart DATE =
DATEADD(day,#yearStartDay-1,
DATEADD(month, #yearStartMonth-1,
DATEADD(year, #yearStart- 1900,0)))
DECLARE #lastYearEnd DATE =
DATEADD(day, #yearStartDay-2,
DATEADD(month, #yearStartMonth-1,
DATEADD(year, #yearEnd -1900,0)))
DECLARE #firstdayofcurrentyear DATE = #firstYearStart
DECLARE #lastdayofcurrentyear DATE = DATEADD(day,-1,DATEADD(year,1,#firstdayofcurrentyear))
DECLARE #yearnumber INT = YEAR(#firstdayofcurrentyear)
DECLARE #tempTableYearBounds TABLE
(
startDate DATE NOT NULL,
endDate DATE NOT NULL,
YearNumber INT NOT NULL
)
WHILE #firstdayofcurrentyear < #lastYearEnd
BEGIN
INSERT INTO #tempTableYearBounds
VALUES(#firstdayofcurrentyear,#lastdayofcurrentyear,#yearNumber)
SET #firstdayofcurrentyear = DATEADD(year,1,#firstdayofcurrentyear)
SET #lastdayofcurrentyear = DATEADD(year,1,#lastdayofcurrentyear)
SET #yearNumber = #yearNumber + 1
END
DECLARE #tempTableCustomerCount TABLE
(
[Year] INT NOT NULL,
[CustomerCount] INT NOT NULL
)
INSERT INTO #tempTableCustomerCount
SELECT
YearNumber as [Year],
COUNT(DISTINCT CustomerNumber) as CutomerCount
FROM Ticket
JOIN #tempTableYearBounds ON
TicketDate >= startDate AND TicketDate <=endDate
GROUP BY YearNumber
SELECT * FROM(
SELECT t2.Year as [Year],
(SELECT
SUM(CustomerCount)
FROM #tempTableCustomerCount
WHERE Year>=t1.Year
AND Year <=t2.Year) AS CustomerCount
FROM #tempTableCustomerCount t1 JOIN #tempTableCustomerCount t2
ON t1.Year < t2.Year
WHERE t1.Year = #yearStart
UNION
SELECT [Year], [CustomerCount]
FROM #tempTableCustomerCount
WHERE [YEAR] = #yearStart
) tt
ORDER BY tt.Year
It isn't efficient but at the end the temp table you are dealing with is so small I don't think it really matters, and adds a lot more versatility versus the method you are using.
Update: I updated the query to reflect the result you wanted with my data set, I was basically testing to see if this was faster, it was faster by 10 seconds but the dataset I am dealing with is relatively small. (from 12 seconds to 2 seconds).
Using your data
I changed the tables you gave to temp tables so it didn't effect my environment and I removed the foreign key because they are not supported for temp tables, the logic is the same as the example included but just changed for your dataset.
DECLARE #startYear INT = 2013, #endYear INT = 2016
DECLARE #yearStartMonth INT = 10 , #yearStartDay INT = 1
DECLARE #startDate DATETIME = DATEADD(day,#yearStartDay-1,
DATEADD(month, #yearStartMonth-1,
DATEADD(year,#startYear-1900,0)))
DECLARE #endDate DATETIME = DATEADD(day,#yearStartDay-1,
DATEADD(month,#yearStartMonth-1,
DATEADD(year,#endYear-1899,0)))
DECLARE #tempDateRangeTable TABLE
(
[Year] INT NOT NULL,
StartDate DATETIME NOT NULL,
EndDate DATETIME NOT NULL
)
DECLARE #currentDate DATETIME = #startDate
WHILE #currentDate < #endDate
BEGIN
DECLARE #nextDate DATETIME = DATEADD(YEAR, 1, #currentDate)
INSERT INTO #tempDateRangeTable(Year,StartDate,EndDate)
VALUES(YEAR(#currentDate),#currentDate,#nextDate)
SET #currentDate = #nextDate
END
CREATE TABLE Users
(
uID int identity primary key,
uFirstName varchar(75),
uLastName varchar(75)
);
INSERT INTO Users (uFirstName, uLastName)
VALUES
('User1', 'User1'),
('User2', 'User2'),
('User3', 'User3'),
('User4', 'User4');
CREATE TABLE UserDataIDMatch
(
udimID int indentity primary key,
udim.udim_FK_uID int foreign key references Users(uID),
udimUserSystemID varchar(75)
);
INSERT INTO UserDataIDMatch (udim_FK_uID, udimUserSystemID)
VALUES
(1, 'SystemID1'),
(2, 'SystemID2'),
(3, 'SystemID3'),
(4, 'SystemID4');
CREATE TABLE DataDump
(
ddID int identity primary key,
ddSystemID varchar(75),
ddEnd datetime
);
INSERT INTO DataDump (ddSystemID, ddEnd)
VALUES
('SystemID1', '10-01-2013'),
('SystemID2', '10-01-2014'),
('SystemID3', '10-01-2015'),
('SystemID4', '10-01-2016');
DECLARE #tempIndividCount TABLE
(
[Year] INT NOT NULL,
UserCount INT NOT NULL
)
-- no longer need to filter out other because you are using an
--inclusion statement rather than an exclusion one, this will
--also make your query faster (when using real tables not temp ones)
INSERT INTO #tempIndividCount(Year,UserCount)
SELECT tdr.Year, COUNT(DISTINCT UId) FROM
Users u JOIN UserDataIDMatch um
ON um.udim_FK_uID = u.uID
JOIN DataDump dd ON
um.udimUserSystemID = dd.ddSystemID
JOIN #tempDateRangeTable tdr ON
dd.ddEnd >= tdr.StartDate AND dd.ddEnd < tdr.EndDate
GROUP BY tdr.Year
-- will show you your result
SELECT * FROM #tempIndividCount
--add any ranges that did not have an entry but were in your range
--can easily remove this by taking this part out.
INSERT INTO #tempIndividCount
SELECT t1.Year,0 FROM
#tempDateRangeTable t1 LEFT OUTER JOIN #tempIndividCount t2
ON t1.Year = t2.Year
WHERE t2.Year IS NULL
SELECT YearNumber,UserCount FROM (
SELECT 'Year'+CAST(((t2.Year-t1.Year)+1) AS CHAR) [YearNumber] ,t2.Year,(
SELECT SUM(UserCount)
FROM #tempIndividCount
WHERE Year >= t1.Year AND Year <=t2.Year
) AS UserCount
FROM #tempIndividCount t1
JOIN #tempIndividCount t2
ON t1.Year < t2.Year
WHERE t1.Year = #startYear
UNION ALL
--add the missing first year, union it to include the value
SELECT 'Year1',Year, UserCount FROM #tempIndividCount
WHERE Year = #startYear) tt
ORDER BY tt.Year
Benefits over using a WHEN CASE based approach
More Robust
Do not need to explicitly determine the end and start dates of each year, just like in a logical year just need to know the start and end date. Can easily change what you are looking for with some simple modifications(i.e. say you want all 2 year ranges or 3 year).
Will be faster if the database is indexed properly
Since you are searching based on the same data type you can utilize the indices that should be created on the date columns in the database.
Cons
More Complicated
The query is a lot more complicated to follow, even though it is more robust there is a lot of extra logic in the actual query.
In some circumstance will not provide good boost to execution time
If the dataset is very small, or the number of dates being compared isn't significant then this could not save enough time to be worth it.
In SQL Server once you match a WHEN inside a CASE, it stop evaluating will not going on evaluating next WHEN clauses. Hence you can't accumulate that way.
if I understand you correctly, this would show your results.
;WITH cte AS
(F
SELECT dd.ddEnd [dateEnd], u.uID AS UserID
FROM Users AS u
INNER JOIN UserDataIDMatch AS udim
ON u.uID = udim.udim_FK_uID
INNER JOIN DataDump AS dd
ON udim.udimUserSystemID = dd.ddSystemID
WHERE ddEnd BETWEEN #FiscalYearStart AND #FiscalYearEnd3
)
SELECT datepart(year, #FiscalYearStart) AS [Year], COUNT(DISTINCT UserID) AS CntUserID
FROM cte
WHERE dateEnd BETWEEN #FiscalYearStart AND #FiscalYearEnd1
GROUP BY #FiscalYearStart
UNION
SELECT datepart(year, #FiscalYearEnd1) AS [Year], COUNT(DISTINCT UserID) AS CntUserID
FROM cte
WHERE dateEnd BETWEEN #FiscalYearStart AND #FiscalYearEnd2
GROUP BY #FiscalYearEnd1
UNION
SELECT datepart(year, #FiscalYearEnd3) AS [Year], COUNT(DISTINCT UserID) AS CntUserID
FROM cte
WHERE dateEnd BETWEEN #FiscalYearStart AND #FiscalYearEnd3
GROUP BY #FiscalYearEnd2
Suppose I have following table in Sql Server 2008:
ItemId StartDate EndDate
1 NULL 2011-01-15
2 2011-01-16 2011-01-25
3 2011-01-26 NULL
As you can see, this table has StartDate and EndDate columns. I want to validate data in these columns. Intervals cannot conflict with each other. So, the table above is valid, but the next table is invalid, becase first row has End Date greater than StartDate in the second row.
ItemId StartDate EndDate
1 NULL 2011-01-17
2 2011-01-16 2011-01-25
3 2011-01-26 NULL
NULL means infinity here.
Could you help me to write a script for data validation?
[The second task]
Thanks for the answers.
I have a complication. Let's assume, I have such table:
ItemId IntervalId StartDate EndDate
1 1 NULL 2011-01-15
2 1 2011-01-16 2011-01-25
3 1 2011-01-26 NULL
4 2 NULL 2011-01-17
5 2 2011-01-16 2011-01-25
6 2 2011-01-26 NULL
Here I want to validate intervals within a groups of IntervalId, but not within the whole table. So, Interval 1 will be valid, but Interval 2 will be invalid.
And also. Is it possible to add a constraint to the table in order to avoid such invalid records?
[Final Solution]
I created function to check if interval is conflicted:
CREATE FUNCTION [dbo].[fnIntervalConflict]
(
#intervalId INT,
#originalItemId INT,
#startDate DATETIME,
#endDate DATETIME
)
RETURNS BIT
AS
BEGIN
SET #startDate = ISNULL(#startDate,'1/1/1753 12:00:00 AM')
SET #endDate = ISNULL(#endDate,'12/31/9999 11:59:59 PM')
DECLARE #conflict BIT = 0
SELECT TOP 1 #conflict = 1
FROM Items
WHERE IntervalId = #intervalId
AND ItemId <> #originalItemId
AND (
(ISNULL(StartDate,'1/1/1753 12:00:00 AM') >= #startDate
AND ISNULL(StartDate,'1/1/1753 12:00:00 AM') <= #endDate)
OR (ISNULL(EndDate,'12/31/9999 11:59:59 PM') >= #startDate
AND ISNULL(EndDate,'12/31/9999 11:59:59 PM') <= #endDate)
)
RETURN #conflict
END
And then I added 2 constraints to my table:
ALTER TABLE dbo.Items ADD CONSTRAINT
CK_Items_Dates CHECK (StartDate IS NULL OR EndDate IS NULL OR StartDate <= EndDate)
GO
and
ALTER TABLE dbo.Items ADD CONSTRAINT
CK_Items_ValidInterval CHECK (([dbo].[fnIntervalConflict]([IntervalId], ItemId,[StartDate],[EndDate])=(0)))
GO
I know, the second constraint slows insert and update operations, but it is not very important for my application.
And also, now I can call function fnIntervalConflict from my application code before inserts and updates of data in the table.
Something like this should give you all overlaping periods
SELECT
*
FROM
mytable t1
JOIN mytable t2 ON t1.EndDate>t2.StartDate AND t1.StartDate < t2.StartDate
Edited for Adrians comment bellow
This will give you the rows that are incorrect.
Added ROW_NUMBER() as I didnt know if all entries where in order.
-- Testdata
declare #date datetime = '2011-01-17'
;with yourTable(itemID, startDate, endDate)
as
(
SELECT 1, NULL, #date
UNION ALL
SELECT 2, dateadd(day, -1, #date), DATEADD(day, 10, #date)
UNION ALL
SELECT 3, DATEADD(day, 60, #date), NULL
)
-- End testdata
,tmp
as
(
select *
,ROW_NUMBER() OVER(order by startDate) as rowno
from yourTable
)
select *
from tmp t1
left join tmp t2
on t1.rowno = t2.rowno - 1
where t1.endDate > t2.startDate
EDIT:
As for the updated question:
Just add a PARTITION BY clause to the ROW_NUMBER() query and alter the join.
-- Testdata
declare #date datetime = '2011-01-17'
;with yourTable(itemID, startDate, endDate, intervalID)
as
(
SELECT 1, NULL, #date, 1
UNION ALL
SELECT 2, dateadd(day, 1, #date), DATEADD(day, 10, #date),1
UNION ALL
SELECT 3, DATEADD(day, 60, #date), NULL, 1
UNION ALL
SELECT 4, NULL, #date, 2
UNION ALL
SELECT 5, dateadd(day, -1, #date), DATEADD(day, 10, #date),2
UNION ALL
SELECT 6, DATEADD(day, 60, #date), NULL, 2
)
-- End testdata
,tmp
as
(
select *
,ROW_NUMBER() OVER(partition by intervalID order by startDate) as rowno
from yourTable
)
select *
from tmp t1
left join tmp t2
on t1.rowno = t2.rowno - 1
and t1.intervalID = t2.intervalID
where t1.endDate > t2.startDate
declare #T table (ItemId int, IntervalID int, StartDate datetime, EndDate datetime)
insert into #T
select 1, 1, NULL, '2011-01-15' union all
select 2, 1, '2011-01-16', '2011-01-25' union all
select 3, 1, '2011-01-26', NULL union all
select 4, 2, NULL, '2011-01-17' union all
select 5, 2, '2011-01-16', '2011-01-25' union all
select 6, 2, '2011-01-26', NULL
select T1.*
from #T as T1
inner join #T as T2
on coalesce(T1.StartDate, '1753-01-01') < coalesce(T2.EndDate, '9999-12-31') and
coalesce(T1.EndDate, '9999-12-31') > coalesce(T2.StartDate, '1753-01-01') and
T1.IntervalID = T2.IntervalID and
T1.ItemId <> T2.ItemId
Result:
ItemId IntervalID StartDate EndDate
----------- ----------- ----------------------- -----------------------
5 2 2011-01-16 00:00:00.000 2011-01-25 00:00:00.000
4 2 NULL 2011-01-17 00:00:00.000
Not directly related to the OP, but since Adrian's expressed an interest. Here's a table than SQL Server maintains the integrity of, ensuring that only one valid value is present at any time. In this case, I'm dealing with a current/history table, but the example can be modified to work with future data also (although in that case, you can't have the indexed view, and you need to write the merge's directly, rather than maintaining through triggers).
In this particular case, I'm dealing with a link table that I want to track the history of. First, the tables that we're linking:
create table dbo.Clients (
ClientID int IDENTITY(1,1) not null,
Name varchar(50) not null,
/* Other columns */
constraint PK_Clients PRIMARY KEY (ClientID)
)
go
create table dbo.DataItems (
DataItemID int IDENTITY(1,1) not null,
Name varchar(50) not null,
/* Other columns */
constraint PK_DataItems PRIMARY KEY (DataItemID),
constraint UQ_DataItem_Names UNIQUE (Name)
)
go
Now, if we were building a normal table, we'd have the following (Don't run this one):
create table dbo.ClientAnswers (
ClientID int not null,
DataItemID int not null,
IntValue int not null,
Comment varchar(max) null,
constraint PK_ClientAnswers PRIMARY KEY (ClientID,DataItemID),
constraint FK_ClientAnswers_Clients FOREIGN KEY (ClientID) references dbo.Clients (ClientID),
constraint FK_ClientAnswers_DataItems FOREIGN KEY (DataItemID) references dbo.DataItems (DataItemID)
)
But, we want a table that can represent a complete history. In particular, we want to design the structure such that overlapping time periods can never appear in the database. We always know which record was valid at any particular time:
create table dbo.ClientAnswerHistories (
ClientID int not null,
DataItemID int not null,
IntValue int null,
Comment varchar(max) null,
/* Temporal columns */
Deleted bit not null,
ValidFrom datetime2 null,
ValidTo datetime2 null,
constraint UQ_ClientAnswerHistories_ValidFrom UNIQUE (ClientID,DataItemID,ValidFrom),
constraint UQ_ClientAnswerHistories_ValidTo UNIQUE (ClientID,DataItemID,ValidTo),
constraint CK_ClientAnswerHistories_NoTimeTravel CHECK (ValidFrom < ValidTo),
constraint FK_ClientAnswerHistories_Clients FOREIGN KEY (ClientID) references dbo.Clients (ClientID),
constraint FK_ClientAnswerHistories_DataItems FOREIGN KEY (DataItemID) references dbo.DataItems (DataItemID),
constraint FK_ClientAnswerHistories_Prev FOREIGN KEY (ClientID,DataItemID,ValidFrom)
references dbo.ClientAnswerHistories (ClientID,DataItemID,ValidTo),
constraint FK_ClientAnswerHistories_Next FOREIGN KEY (ClientID,DataItemID,ValidTo)
references dbo.ClientAnswerHistories (ClientID,DataItemID,ValidFrom),
constraint CK_ClientAnswerHistory_DeletionNull CHECK (
Deleted = 0 or
(
IntValue is null and
Comment is null
)),
constraint CK_ClientAnswerHistory_IntValueNotNull CHECK (Deleted=1 or IntValue is not null)
)
go
That's a lot of constraints. The only way to maintain this table is through merge statements (see examples below, and try to reason about why yourself). We're now going to build a view that mimics that ClientAnswers table defined above:
create view dbo.ClientAnswers
with schemabinding
as
select
ClientID,
DataItemID,
ISNULL(IntValue,0) as IntValue,
Comment
from
dbo.ClientAnswerHistories
where
Deleted = 0 and
ValidTo is null
go
create unique clustered index PK_ClientAnswers on dbo.ClientAnswers (ClientID,DataItemID)
go
And we have the PK constraint we originally wanted. We've also used ISNULL to reinstate the not null-ness of the IntValue column (even though the check constraints already guarantee this, SQL Server is unable to derive this information). If we're working with an ORM, we let it target ClientAnswers, and the history gets automatically built. Next, we can have a function that lets us look back in time:
create function dbo.ClientAnswers_At (
#At datetime2
)
returns table
with schemabinding
as
return (
select
ClientID,
DataItemID,
ISNULL(IntValue,0) as IntValue,
Comment
from
dbo.ClientAnswerHistories
where
Deleted = 0 and
(ValidFrom is null or ValidFrom <= #At) and
(ValidTo is null or ValidTo > #At)
)
go
And finally, we need the triggers on ClientAnswers that build this history. We need to use merge statements, since we need to simultaneously insert new rows, and update the previous "valid" row to end date it with a new ValidTo value.
create trigger T_ClientAnswers_I
on dbo.ClientAnswers
instead of insert
as
set nocount on
;with Dup as (
select i.ClientID,i.DataItemID,i.IntValue,i.Comment,CASE WHEN cah.ClientID is not null THEN 1 ELSE 0 END as PrevDeleted,t.Dupl
from
inserted i
left join
dbo.ClientAnswerHistories cah
on
i.ClientID = cah.ClientID and
i.DataItemID = cah.DataItemID and
cah.ValidTo is null and
cah.Deleted = 1
cross join
(select 0 union all select 1) t(Dupl)
)
merge into dbo.ClientAnswerHistories cah
using Dup on cah.ClientID = Dup.ClientID and cah.DataItemID = Dup.DataItemID and cah.ValidTo is null and Dup.Dupl = 0 and Dup.PrevDeleted = 1
when matched then update set ValidTo = SYSDATETIME()
when not matched and Dup.Dupl=1 then insert (ClientID,DataItemID,IntValue,Comment,Deleted,ValidFrom)
values (Dup.ClientID,Dup.DataItemID,Dup.IntValue,Dup.Comment,0,CASE WHEN Dup.PrevDeleted=1 THEN SYSDATETIME() END);
go
create trigger T_ClientAnswers_U
on dbo.ClientAnswers
instead of update
as
set nocount on
;with Dup as (
select i.ClientID,i.DataItemID,i.IntValue,i.Comment,t.Dupl
from
inserted i
cross join
(select 0 union all select 1) t(Dupl)
)
merge into dbo.ClientAnswerHistories cah
using Dup on cah.ClientID = Dup.ClientID and cah.DataItemID = Dup.DataItemID and cah.ValidTo is null and Dup.Dupl = 0
when matched then update set ValidTo = SYSDATETIME()
when not matched then insert (ClientID,DataItemID,IntValue,Comment,Deleted,ValidFrom)
values (Dup.ClientID,Dup.DataItemID,Dup.IntValue,Dup.Comment,0,SYSDATETIME());
go
create trigger T_ClientAnswers_D
on dbo.ClientAnswers
instead of delete
as
set nocount on
;with Dup as (
select d.ClientID,d.DataItemID,t.Dupl
from
deleted d
cross join
(select 0 union all select 1) t(Dupl)
)
merge into dbo.ClientAnswerHistories cah
using Dup on cah.ClientID = Dup.ClientID and cah.DataItemID = Dup.DataItemID and cah.ValidTo is null and Dup.Dupl = 0
when matched then update set ValidTo = SYSDATETIME()
when not matched then insert (ClientID,DataItemID,Deleted,ValidFrom)
values (Dup.ClientID,Dup.DataItemID,1,SYSDATETIME());
go
Obviously, I could have built a simpler table (not a join table), but this is my standard go-to example (albeit it took me a while to reconstruct it - I forgot the set nocount on statements for a while). But the strength here is that, the base table, ClientAnswerHistories is incapable of storing overlapping time ranges for the same ClientID and DataItemID values.
Things get more complex when you need to deal with temporal foreign keys.
Of course, if you don't want any real gaps, then you can remove the Deleted column (and associated checks), make the not null columns really not null, modify the insert trigger to do a plain insert, and make the delete trigger raise an error instead.
I've always taken a slightly different approach to the design if I have data that is never to have overlapping intervals... namely don't store intervals, but only start times. Then, have a view that helps with displaying the intervals.
CREATE TABLE intervalStarts
(
ItemId int,
IntervalId int,
StartDate datetime
)
CREATE VIEW intervals
AS
with cte as (
select ItemId, IntervalId, StartDate,
row_number() over(partition by IntervalId order by isnull(StartDate,'1753-01-01')) row
from intervalStarts
)
select c1.ItemId, c1.IntervalId, c1.StartDate,
dateadd(dd,-1,c2.StartDate) as 'EndDate'
from cte c1
left join cte c2 on c1.IntervalId=c2.IntervalId
and c1.row=c2.row-1
So, sample data might look like:
INSERT INTO intervalStarts
select 1, 1, null union
select 2, 1, '2011-01-16' union
select 3, 1, '2011-01-26' union
select 4, 2, null union
select 5, 2, '2011-01-26' union
select 6, 2, '2011-01-14'
and a simple SELECT * FROM intervals yields:
ItemId | IntervalId | StartDate | EndDate
1 | 1 | null | 2011-01-15
2 | 1 | 2011-01-16 | 2011-01-25
3 | 1 | 2011-01-26 | null
4 | 2 | null | 2011-01-13
6 | 2 | 2011-01-14 | 2011-01-25
5 | 2 | 2011-01-26 | null
Following is the sample data. I need to make 3 copies of this data in t sql without using loop and return as one resultset. This is sample data not real.
42 South Yorkshire
43 Lancashire
44 Norfolk
Edit: I need multiple copies and I have no idea in advance that how many copies I need I have to decide this on the basis of dates. Date might be 1st jan to 3rd Jan OR 1st jan to 8th Jan.
Thanks.
Don't know about better but this is definatley more creative! you can use a CROSS JOIN.
EDIT: put some code in to generate a date range, you can change the date range, the rows in the #date are your multiplier.
declare #startdate datetime
, #enddate datetime
create table #data1 ([id] int , [name] nvarchar(100))
create table #dates ([date] datetime)
INSERT #data1 SELECT 42, 'South Yorkshire'
INSERT #data1 SELECT 43, 'Lancashire'
INSERT #data1 SELECT 44, 'Norfolk'
set #startdate = '1Jan2010'
set #enddate = '3Jan2010'
WHILE (#startdate <= #enddate)
BEGIN
INSERT #dates SELECT #startdate
set #startdate=#startdate+1
END
SELECT [id] , [name] from #data1 cross join #dates
drop table #data1
drop table #dates
You could always use a CTE to do the dirty work
Replace the WHERE Counter < 4 with the amount of duplicates you need.
CREATE TABLE City (ID INTEGER PRIMARY KEY, Name VARCHAR(32))
INSERT INTO City VALUES (42, 'South Yorkshire')
INSERT INTO City VALUES (43, 'Lancashire')
INSERT INTO City VALUES (44, 'Norfolk')
/*
The CTE duplicates every row from CTE for the amount
specified by Counter
*/
;WITH CityCTE (ID, Name, Counter) AS
(
SELECT c.ID, c.Name, 0 AS Counter
FROM City c
UNION ALL
SELECT c.ID, c.Name, Counter + 1
FROM City c
INNER JOIN CityCTE cte ON cte.ID = c.ID
WHERE Counter < 4
)
SELECT ID, Name
FROM CityCTE
ORDER BY 1, 2
DROP TABLE City
This may not be the most efficient way of doing it, but it should work.
(select ....)
union all
(select ....)
union all
(select ....)
Assume the table is named CountyPopulation:
SELECT * FROM CountyPopulation
UNION ALL
SELECT * FROM CountyPopulation
UNION ALL
SELECT * FROM CountyPopulation
Share and enjoy.
There is no need to use a cursor. The set-based approach would be to use a Calendar table. So first we make our calendar table which need only be done once and be somewhat permanent:
Create Table dbo.Calendar ( Date datetime not null Primary Key Clustered )
GO
; With Numbers As
(
Select ROW_NUMBER() OVER( ORDER BY S1.object_id ) As [Counter]
From sys.columns As s1
Cross Join sys.columns As s2
)
Insert dbo.Calendar([Date])
Select DateAdd(d, [Counter], '19000101')
From Numbers
Where [Counter] <= 100000
GO
I populated it with a 100K dates which goes into 2300. Obviously you can always expand it. Next we generate our test data:
Create Table dbo.Data(Id int not null, [Name] nvarchar(20) not null)
GO
Insert dbo.Data(Id, [Name]) Values(42,'South Yorkshire')
Insert dbo.Data(Id, [Name]) Values(43, 'Lancashire')
Insert dbo.Data(Id, [Name]) Values(44, 'Norfolk')
GO
Now the problem becomes trivial:
Declare #Start datetime
Declare #End datetime
Set #Start = '2010-01-01'
Set #End = '2010-01-03'
Select Dates.[Date], Id, [Name]
From dbo.Data
Cross Join (
Select [Date]
From dbo.Calendar
Where [Date] >= #Start
And [Date] <= #End
) As Dates
By far the best solution is CROSS JOIN. Most natural.
See my answer here: How to retrieve rows multiple times in SQL Server?
If you have a Numbers table lying around, it's even easier. You can DATEDIFF the dates to give you the filter on the Numbers table