Can't get table function to work with if statement - sql

trying to create a table function that returns a two column table that must be conditioned with an if statement.
I have two other functions that do this separate but cant get it to work when combined.
create function dbo.PDM_GetCategorytable (#Mystring varchar(200) ,#appid int)
returns table
as -- begin
--return
begin
-- declare #MyString varchar(200);
--set #MyString= 'Fred mtf is dead'--'RE: [Encrypt]]FW: MTF Military ---
--UPDATE URGENT'
--declare #AppId int =5
declare #Dubb Table (Col varchar(200));
insert into #dubb
(Col )
values ( #Mystring);
if ((select top 1 categoryid from #dubb a
left join
(SELECT (pass.Recordid) as categoryid , pass.appid,
pass.Priority_Identifier, pass.PrioritySortorder, pass.Category,
ps.Search_String AS SrchVar
FROM dbo.PDM_PriorityAssignments AS pass INNER JOIN
dbo.PDM_Priority_Search AS ps ON pass.Recordid =
ps.PriorityAssignmentid where pass.appid=#AppId ) b on a.col like '%' +
b.SrchVar + '%'
order by PrioritySortorder) is not null)--'where
appid=#AppId
begin
select top 1 categoryid,Category from #dubb a
left join
(SELECT (pass.Recordid) as categoryid , pass.appid,
pass.Priority_Identifier, pass.PrioritySortorder, pass.Category,
ps.Search_String AS SrchVar
FROM dbo.PDM_PriorityAssignments AS pass INNER JOIN
dbo.PDM_Priority_Search AS ps ON pass.Recordid =
ps.PriorityAssignmentid where pass.appid=#AppId ) b on a.col like '%' +
b.SrchVar + '%'
order by PrioritySortorder;
end
else
begin
select recordid as categoryid,Category FROM dbo.PDM_PriorityAssignments
AS pass where appid=#AppId and Priority_Identifier like 'Routine'
end
return
end;
expected results will be the returning of two columns , category id, and category.

seems like a duplicate for Multi statement table valued function
Multi-statement Table Valued Function vs Inline Table Valued Function
here is an example how to achieve this.
CREATE FUNCTION foo
(#param int)
RETURNS
#T TABLE (id int, val varchar)
As
BEGIN
IF (#param = 1)
insert into #t Select 1, 'a';
else
insert into #t Select 0, 'a';
return ;
END
GO

The problem is exactly because of the algorithm you need to use.
That requirement prevents you from returning just a table. On this scenarios you need to do something a bit different.
First define the resulting table and then, insert the values as you need.
I canĀ“t run it without your data but it should work.
CREATE FUNCTION dbo.PDM_GetCategorytable (
#Mystring VARCHAR(200)
,#appid INT
)
RETURNS #GetCategorytable TABLE
(
[CategoryId] INT,
[Category] VARCHAR(200))
AS -- begin
--return
BEGIN
-- declare #MyString varchar(200);
--set #MyString= 'Fred mtf is dead'--'RE: [Encrypt]]FW: MTF Military ---
--UPDATE URGENT'
--declare #AppId int =5
DECLARE #Dubb TABLE (Col VARCHAR(200));
INSERT INTO #dubb (Col)
VALUES (#Mystring);
IF (
(
SELECT TOP 1 categoryid
FROM #dubb a
LEFT JOIN (
SELECT (pass.Recordid) AS categoryid
,pass.appid
,pass.Priority_Identifier
,pass.PrioritySortorder
,pass.Category
,ps.Search_String AS SrchVar
FROM dbo.PDM_PriorityAssignments AS pass
INNER JOIN dbo.PDM_Priority_Search AS ps ON pass.Recordid = ps.PriorityAssignmentid
WHERE pass.appid = #AppId
) b ON a.col LIKE '%' + b.SrchVar + '%'
ORDER BY PrioritySortorder
) IS NOT NULL
) --'where
-- NOT SURE WHAT YOU ARE TRYING TO DO WITH THIS -- appid = #AppId
BEGIN
insert into #GetCategorytable(Categoryid, Category)
SELECT TOP 1 categoryid
,Category
FROM #dubb a
LEFT JOIN (
SELECT (pass.Recordid) AS categoryid
,pass.appid
,pass.Priority_Identifier
,pass.PrioritySortorder
,pass.Category
,ps.Search_String AS SrchVar
FROM dbo.PDM_PriorityAssignments AS pass
INNER JOIN dbo.PDM_Priority_Search AS ps ON pass.Recordid = ps.PriorityAssignmentid
WHERE pass.appid = #AppId
) b ON a.col LIKE '%' + b.SrchVar + '%'
ORDER BY PrioritySortorder;
END
ELSE
BEGIN
insert into #GetCategorytable(Categoryid, Category)
SELECT recordid AS categoryid ,Category FROM dbo.PDM_PriorityAssignments AS pass
WHERE appid = #AppId
AND Priority_Identifier LIKE 'Routine'
END
RETURN
END;

Related

Outer apply with INSERT statement

I want to do something like this
CREATE TABLE #tempFacilitiesAssociated
(
FacilityID BIGINT,
FacilityName VARCHAR(MAX),
IsPrimary BIT
)
-- Insert statements for procedure here
;WITH CTE_RESULT AS
(
SELECT
usr_id, t.name AS Title,
usr_fname, usr_lname, primaryAddress.add_suburb,
CASE
WHEN primaryAddress.add_suburb = #suburb THEN 1
WHEN t.name = #Title THEN 2
ELSE 3
END AS MatchOrder
FROM
core_users u
LEFT JOIN
RIDE_ct_title t ON t.title_id = u.usr_title
OUTER APPLY
(INSERT INTO #tempFacilitiesAssociated
EXEC dbo.[sp_Common_Get_AllFacilitiesForSupervisor] usr_id, 5
SELECT TOP 1 fa.*
FROM CORE_Facilities f
LEFT JOIN CORE_FacilityAddresses fa ON fac_id = fa.add_owner
WHERE fac_id = (SELECT TOP 1 FacilityID
FROM #tempFacilitiesAssociated
WHERE IsPrimary = 1)) primaryAddress
WHERE
u.usr_fname = #FirstName AND usr_lname = #LastName
)
So, first I want to get all facilities of that user through a stored procedure, and then use it to outer apply and select its suburb
UPDATE
I tried using function instead
CREATE FUNCTION fn_GetAddressForUserFacility
(#UserID BIGINT)
RETURNS #Address TABLE (FacilityID BIGINT,
add_address NVARCHAR(MAX),
add_addressline2 NVARCHAR(MAX),
add_suburb NVARCHAR(MAX)
)
AS
BEGIN
DECLARE #FacilitiesAssociated TABLE
(FacilityID BIGINT,
FacilityName NVARCHAR(MAX),
IsPrimary BIT)
INSERT INTO #FacilitiesAssociated
EXEC dbo.[sp_Common_Get_AllFacilitiesForSupervisor] #UserID, 5
INSERT INTO #Address
SELECT TOP 1
fa.add_owner, fa.add_address, fa.add_addressline2, fa.add_suburb
FROM
CORE_Facilities f
LEFT JOIN
CORE_FacilityAddresses fa ON f.fac_id = fa.add_owner AND add_type = 5
WHERE
fac_id = (SELECT TOP 1 FacilityID
FROM #FacilitiesAssociated
WHERE IsPrimary = 1)
RETURN
END
But now its returning
Invalid use of a side-effecting operator 'INSERT EXEC' within a function.

SQL dynamic columns and Update multiple columns

I have a table UserPermission which has a number of columns of TINYINT type. e.g Read, Write, Update, Delete, Access etc.
I get three parameters in the stored procedure: #UserId, #ColNames, #ColValues where #ColNames and #ColValues are comma separated values.
How can I insert or update the table row (if already exists) with the passed column names and corresponding values.
I try to write the dynamic query which runs fine for INSERT but I was unable to write the UPDATE query dynamically with each column and its value to be concatenate.
Any response would be appreciated
Thanks in advance.
This is a somewhat dirty way to do what you require. However, if you create the following Stored Procedure:
CREATE FUNCTION [dbo].[stringSplit]
(
#String NVARCHAR(4000),
#Delimiter NCHAR(1)
)
RETURNS TABLE
AS
RETURN
(
WITH Split(stpos,endpos)
AS(
SELECT 0 AS stpos, CHARINDEX(#Delimiter,#String) AS endpos
UNION ALL
SELECT endpos+1, CHARINDEX(#Delimiter,#String,endpos+1)
FROM Split
WHERE endpos > 0
)
SELECT 'Id' = ROW_NUMBER() OVER (ORDER BY (SELECT 1)),
'Data' = SUBSTRING(#String,stpos,COALESCE(NULLIF(endpos,0),LEN(#String)+1)-stpos)
FROM Split
)
You can then use that Procedure to join the data together:
DECLARE #TotalCols INT
DECLARE #TotalVals INT
SET #TotalCols = (
SELECT COUNT(ID) AS Total
FROM dbo.stringSplit('department, teamlead', ',')
);
SET #TotalVals = (
SELECT COUNT(ID) AS Total
FROM dbo.stringSplit('IT, Bob', ',')
);
IF #TotalCols = #TotalVals
BEGIN
IF OBJECT_ID('tempdb..#temptable') IS NOT NULL
DROP TABLE #temptable
CREATE TABLE #temptable (
ColName VARCHAR(MAX) NULL
,ColValue VARCHAR(MAX) NULL
)
INSERT INTO #temptable
SELECT a.DATA
,b.DATA
FROM dbo.stringSplit('department, teamlead', ',') AS a
INNER JOIN dbo.stringSplit('IT, Bob', ',') AS b ON a.Id = b.Id
SELECT *
FROM #temptable;
END
It's not very efficient, but it will bring you the desired results.
You can then use the temp table to update, insert and delete as required.
Instead of having a comma delimited list I would create a separate parameter for each Column and make its default value to NULL and in the code update nothing if its null or insert 0. Something like this....
CREATE PROCEDURE usp_UserPermissions
#UserID INT
,#Update INT = NULL --<-- Make default values NULL
,#Delete INT = NULL
,#Read INT = NULL
,#Write INT = NULL
,#Access INT = NULL
AS
BEGIN
SET NOCOUNT ON;
Declare #t TABLE (UserID INT, [Update] INT,[Read] INT
,[Write] INT,[Delete] INT,[Access] INT)
INSERT INTO #t (Userid, [Update],[Read],[Write],[Delete],[Access])
VALUES (#UserID , #Update , #Read, #Write , #Delete, #Access)
IF EXISTS (SELECT 1 FROM UserPermission WHERE UserID = #UserID)
BEGIN
UPDATE up -- Only update if a value was provided else update to itself
SET up.[Read] = ISNULL(t.[Read] , up.[Read])
,up.[Write] = ISNULL(t.[Write] , up.[Write])
,up.[Update] = ISNULL(t.[Update] , up.[Update])
,up.[Delete] = ISNULL(t.[Delete] , up.[Delete])
,up.[Access] = ISNULL(t.[Access] , up.[Access])
FROM UserPermission up
INNER JOIN #t t ON up.UserID = t.UserID
END
ELSE
BEGIN
-- if already no row exists for that User add a row
-- If no value was passed for a column add 0 as default
INSERT INTO UserPermission (Userid, [Update],[Read],[Write],[Delete],[Access])
SELECT Userid
, ISNULL([Update], 0)
, ISNULL([Read], 0)
, ISNULL([Write], 0)
, ISNULL([Delete], 0)
, ISNULL([Access], 0)
FROM #t
END
END

dynamic alias in sql server

I want query field with different alias in stored procedure
select COUNT(EmpCode) as CountEmp+#para
result shoud be
CountEmp1
45
CountEmp2
54
CountEmp1
76
Query loop in c# code:
select COUNT(EmpCode) where something = #something as CountEmp+#para
Approach without dynamic SQL:
--I create temp table for demonstration
DECLARE #some_table TABLE (
Something int,
EmpCode INT
)
INSERT INTO #some_table (Something, EmpCode)
VALUES (1, 10),(1, 22),(1, 12),(2, 12),(2, 30),(3, 65),(3, 15),(3, 11),(3, 5)
--Declare parameter we want to search
DECLARE #param int = 1
--Query
--In cte we select what we need based on parameter
;WITH cte AS (
SELECT 'CountEmp'+CAST(#param as nvarchar(10)) as SomeThing,
CAST(COUNT(EmpCode) as nvarchar(10)) as EmpCodeCount,
ROW_NUMBER() OVER (ORDER BY SomeThing ) as rn
FROM #some_table
WHERE SomeThing = #param
GROUP BY SomeThing
)
--And here comes UNION
SELECT SomeThing as Result
FROM (
SELECT SomeThing,rn
FROM cte
UNION ALL
SELECT EmpCodeCount ,rn
FROM cte
) as t
ORDER BY rn, SomeThing DESC
Output:
Result
------------------
CountEmp1
3
(2 row(s) affected)
Please try to make use of below code. Its working fine with SQL Server 2012.
IF OBJECT_ID ('temp..#Mytable') IS NOT NULL
CREATE TABLE #Mytable (ID INT IDENTITY (1,1),EmpCode INT)
DECLARE #max int ,#count int
SET #max =0;
DECLARE #str varchar(10)
INSERT #Mytable
(EmpCode)
VALUES
(10),
(45),
(35),
(63),
(56),
(65)
SET #count = (SELECT COUNT (ID) FROM #Mytable )
WHILE #count > #max
BEGIN
SET #max = #max+1
SET #str = CONVERT(varchar(10),#max)
EXEC('SELECT EmpCode AS Empcode'+#str+ ' FROM #Mytable WHERE ID = '+#str)
END

Convert Comma Delimited String to bigint in SQL Server

I have a varchar string of delimited numbers separated by commas that I want to use in my SQL script but I need to compare with a bigint field in the database. Need to know to convert it:
DECLARE #RegionID varchar(200) = null
SET #RegionID = '853,834,16,467,841,460,495,44,859,457,437,836,864,434,86,838,458,472,832,433,142,154,159,839,831,469,442,275,840,299,446,220,300,225,227,447,301,450,230,837,441,835,302,477,855,411,395,279,303'
SELECT a.ClassAdID, -- 1
a.AdURL, -- 2
a.AdTitle, -- 3
a.ClassAdCatID, -- 4
b.ClassAdCat, -- 5
a.Img1, -- 6
a.AdText, -- 7
a.MemberID, -- 9
a.Viewed, -- 10
c.Domain, -- 11
a.CreateDate -- 12
FROM ClassAd a
INNER JOIN ClassAdCat b ON b.ClassAdCAtID = a.ClassAdCAtID
INNER JOIN Region c ON c.RegionID = a.RegionID
AND a.PostType = 'CPN'
AND DATEDIFF(d, GETDATE(), ExpirationDate) >= 0
AND a.RegionID IN (#RegionID)
AND Viewable = 'Y'
This fails with the following error:
Error converting data type varchar to bigint.
RegionID In the database is a bigint field.. need to convert the varchar to bigint.. any ideas..?
Many thanks in advance,
neojakey
create this function:
CREATE function [dbo].[f_split]
(
#param nvarchar(max),
#delimiter char(1)
)
returns #t table (val nvarchar(max), seq int)
as
begin
set #param += #delimiter
;with a as
(
select cast(1 as bigint) f, charindex(#delimiter, #param) t, 1 seq
union all
select t + 1, charindex(#delimiter, #param, t + 1), seq + 1
from a
where charindex(#delimiter, #param, t + 1) > 0
)
insert #t
select substring(#param, f, t - f), seq from a
option (maxrecursion 0)
return
end
change this part:
AND a.RegionID IN (select val from dbo.f_split(#regionID, ','))
Change this for better overall performance:
AND DATEDIFF(d, 0, GETDATE()) <= ExpirationDate
Your query does not know that those are separate values, you can use dynamic sql for this:
DECLARE #RegionID varchar(200) = null
SET #RegionID = '853,834,16,467,841,460,495,44,859,457,437,836,864,434,86,838,458,472,832,433,142,154,159,839,831,469,442,275,840,299,446,220,300,225,227,447,301,450,230,837,441,835,302,477,855,411,395,279,303'
declare #sql nvarchar(Max)
set #sql = 'SELECT a.ClassAdID, -- 1
a.AdURL, -- 2
a.AdTitle, -- 3
a.ClassAdCatID, -- 4
b.ClassAdCat, -- 5
a.Img1, -- 6
a.AdText, -- 7
a.MemberID, -- 9
a.Viewed, -- 10
c.Domain, -- 11
a.CreateDate -- 12
FROM ClassAd a
INNER JOIN ClassAdCat b ON b.ClassAdCAtID = a.ClassAdCAtID
INNER JOIN Region c ON c.RegionID = a.RegionID
AND a.PostType = ''CPN''
AND DATEDIFF(d, GETDATE(), ExpirationDate) >= 0
AND a.RegionID IN ('+#RegionID+')
AND Viewable = ''Y'''
exec sp_executesql #sql
I use this apporach sometimes and find it very good.
It transfors your comma-separated string into an AUX table (called #ARRAY) and then query the main table based on the AUX table:
declare #RegionID varchar(50)
SET #RegionID = '853,834,16,467,841,460,495,44,859,457,437,836,864,434,86,838,458,472,832,433,142,154,159,839,831,469,442,275,840,299,446,220,300,225,227,447,301,450,230,837,441,835,302,477,855,411,395,279,303'
declare #S varchar(20)
if LEN(#RegionID) > 0 SET #RegionID = #RegionID + ','
CREATE TABLE #ARRAY(region_ID VARCHAR(20))
WHILE LEN(#RegionID) > 0 BEGIN
SELECT #S = LTRIM(SUBSTRING(#RegionID, 1, CHARINDEX(',', #RegionID) - 1))
INSERT INTO #ARRAY (region_ID) VALUES (#S)
SELECT #RegionID = SUBSTRING(#RegionID, CHARINDEX(',', #RegionID) + 1, LEN(#RegionID))
END
select * from your_table
where regionID IN (select region_ID from #ARRAY)
It avoids you from ahving to concatenate the query string and then use EXEC to execute it, which I dont think it is a very good approach.
if you need to run the code twice you will need to drop the temp table
I think the answer should be kept simple.
Try using CHARINDEX like this:
DECLARE #RegionID VARCHAR(200) = NULL
SET #RegionID =
'853,834,16,467,841,460,495,44,859,457,437,836,864,434,86,838,458,472,832,433,142,154,159,839,831,469,442,275,840,299,446,220,300,225,227,447,301,450,230,837,441,835,302,477,855,411,395,279,303'
SELECT 1
WHERE Charindex('834', #RegionID) > 0
SELECT 1
WHERE Charindex('999', #RegionID) > 0
When CHARINDEX finds the value in the large string variable, it will return it's position, otherwise it return 0.
Use this as a search tool.
The easiest way to change this query is to replace the IN function with a string function. Here is what I consider the safest approach using LIKE (which is portable among databases):
AND ','+#RegionID+',' like '%,'+cast(a.RegionID as varchar(255))+',%'
Or CHARINDEX:
AND charindex(','+cast(a.RegionID as varchar(255))+',', ','+#RegionID+',') > 0
However, if you are explicitly putting the list in your code, why not use a temporary table?
declare #RegionIds table (RegionId int);
insert into #RegionIds
select 853 union all
select 834 union all
. . .
select 303
Then you can use the table in the IN clause:
AND a.RegionId in (select RegionId from #RegionIds)
or in a JOIN clause.
I like Diego's answer some, but I think my modification is a little better because you are declaring a table variable and not creating an actual table. I know the "in" statement can be a little slow, so I did an inner join since I needed some info from the Company table anyway.
declare #companyIdList varchar(1000)
set #companyIdList = '1,2,3'
if LEN(#companyIdList) > 0 SET #companyIdList = #companyIdList + ','
declare #CompanyIds TABLE (CompanyId bigint)
declare #S varchar(20)
WHILE LEN(#companyIdList) > 0 BEGIN
SELECT #S = LTRIM(SUBSTRING(#companyIdList, 1, CHARINDEX(',', #companyIdList) - 1))
INSERT INTO #CompanyIds (CompanyId) VALUES (#S)
SELECT #companyIdList = SUBSTRING(#companyIdList, CHARINDEX(',', #companyIdList) + 1, LEN(#companyIdList))
END
select d.Id, d.Name, c.Id, c.Name
from [Division] d
inner join [Company] c on d.CompanyId = c.Id
inner join #CompanyIds cids on c.Id = cids.CompanyId

Delete duplicate records in SQL Server?

Consider a column named EmployeeName table Employee. The goal is to delete repeated records, based on the EmployeeName field.
EmployeeName
------------
Anand
Anand
Anil
Dipak
Anil
Dipak
Dipak
Anil
Using one query, I want to delete the records which are repeated.
How can this be done with TSQL in SQL Server?
You can do this with window functions. It will order the dupes by empId, and delete all but the first one.
delete x from (
select *, rn=row_number() over (partition by EmployeeName order by empId)
from Employee
) x
where rn > 1;
Run it as a select to see what would be deleted:
select *
from (
select *, rn=row_number() over (partition by EmployeeName order by empId)
from Employee
) x
where rn > 1;
Assuming that your Employee table also has a unique column (ID in the example below), the following will work:
delete from Employee
where ID not in
(
select min(ID)
from Employee
group by EmployeeName
);
This will leave the version with the lowest ID in the table.
Edit
Re McGyver's comment - as of SQL 2012
MIN can be used with numeric, char, varchar, uniqueidentifier, or datetime columns, but not with bit columns
For 2008 R2 and earlier,
MIN can be used with numeric, char, varchar, or datetime columns, but not with bit columns (and it also doesn't work with GUID's)
For 2008R2 you'll need to cast the GUID to a type supported by MIN, e.g.
delete from GuidEmployees
where CAST(ID AS binary(16)) not in
(
select min(CAST(ID AS binary(16)))
from GuidEmployees
group by EmployeeName
);
SqlFiddle for various types in Sql 2008
SqlFiddle for various types in Sql 2012
You could try something like the following:
delete T1
from MyTable T1, MyTable T2
where T1.dupField = T2.dupField
and T1.uniqueField > T2.uniqueField
(this assumes that you have an integer based unique field)
Personally though I'd say you were better off trying to correct the fact that duplicate entries are being added to the database before it occurs rather than as a post fix-it operation.
DELETE
FROM MyTable
WHERE ID NOT IN (
SELECT MAX(ID)
FROM MyTable
GROUP BY DuplicateColumn1, DuplicateColumn2, DuplicateColumn3)
WITH TempUsers (FirstName, LastName, duplicateRecordCount)
AS
(
SELECT FirstName, LastName,
ROW_NUMBER() OVER (PARTITIONBY FirstName, LastName ORDERBY FirstName) AS duplicateRecordCount
FROM dbo.Users
)
DELETE
FROM TempUsers
WHERE duplicateRecordCount > 1
WITH CTE AS
(
SELECT EmployeeName,
ROW_NUMBER() OVER(PARTITION BY EmployeeName ORDER BY EmployeeName) AS R
FROM employee_table
)
DELETE CTE WHERE R > 1;
The magic of common table expressions.
Try
DELETE
FROM employee
WHERE rowid NOT IN (SELECT MAX(rowid) FROM employee
GROUP BY EmployeeName);
If you're looking for a way to remove duplicates, yet you have a foreign key pointing to the table with duplicates, you could take the following approach using a slow yet effective cursor.
It will relocate the duplicate keys on the foreign key table.
create table #properOlvChangeCodes(
id int not null,
name nvarchar(max) not null
)
DECLARE #name VARCHAR(MAX);
DECLARE #id INT;
DECLARE #newid INT;
DECLARE #oldid INT;
DECLARE OLVTRCCursor CURSOR FOR SELECT id, name FROM Sales_OrderLineVersionChangeReasonCode;
OPEN OLVTRCCursor;
FETCH NEXT FROM OLVTRCCursor INTO #id, #name;
WHILE ##FETCH_STATUS = 0
BEGIN
-- determine if it should be replaced (is already in temptable with name)
if(exists(select * from #properOlvChangeCodes where Name=#name)) begin
-- if it is, finds its id
Select top 1 #newid = id
from Sales_OrderLineVersionChangeReasonCode
where Name = #name
-- replace terminationreasoncodeid in olv for the new terminationreasoncodeid
update Sales_OrderLineVersion set ChangeReasonCodeId = #newid where ChangeReasonCodeId = #id
-- delete the record from the terminationreasoncode
delete from Sales_OrderLineVersionChangeReasonCode where Id = #id
end else begin
-- insert into temp table if new
insert into #properOlvChangeCodes(Id, name)
values(#id, #name)
end
FETCH NEXT FROM OLVTRCCursor INTO #id, #name;
END;
CLOSE OLVTRCCursor;
DEALLOCATE OLVTRCCursor;
drop table #properOlvChangeCodes
delete from person
where ID not in
(
select t.id from
(select min(ID) as id from person
group by email
) as t
);
Please see the below way of deletion too.
Declare #Employee table (EmployeeName varchar(10))
Insert into #Employee values
('Anand'),('Anand'),('Anil'),('Dipak'),
('Anil'),('Dipak'),('Dipak'),('Anil')
Select * from #Employee
Created a sample table named #Employee and loaded it with given data.
Delete aliasName from (
Select *,
ROW_NUMBER() over (Partition by EmployeeName order by EmployeeName) as rowNumber
From #Employee) aliasName
Where rowNumber > 1
Select * from #Employee
Result:
I know, this is asked six years ago, posting just incase it is helpful for anyone.
Here's a nice way of deduplicating records in a table that has an identity column based on a desired primary key that you can define at runtime. Before I start I'll populate a sample data set to work with using the following code:
if exists (select 1 from sys.all_objects where type='u' and name='_original')
drop table _original
declare #startyear int = 2017
declare #endyear int = 2018
declare #iterator int = 1
declare #income money = cast((SELECT round(RAND()*(5000-4990)+4990 , 2)) as money)
declare #salesrepid int = cast(floor(rand()*(9100-9000)+9000) as varchar(4))
create table #original (rowid int identity, monthyear varchar(max), salesrepid int, sale money)
while #iterator<=50000 begin
insert #original
select (Select cast(floor(rand()*(#endyear-#startyear)+#startyear) as varchar(4))+'-'+ cast(floor(rand()*(13-1)+1) as varchar(2)) ), #salesrepid , #income
set #salesrepid = cast(floor(rand()*(9100-9000)+9000) as varchar(4))
set #income = cast((SELECT round(RAND()*(5000-4990)+4990 , 2)) as money)
set #iterator=#iterator+1
end
update #original
set monthyear=replace(monthyear, '-', '-0') where len(monthyear)=6
select * into _original from #original
Next I'll create a Type called ColumnNames:
create type ColumnNames AS table
(Columnnames varchar(max))
Finally I will create a stored proc with the following 3 caveats:
1. The proc will take a required parameter #tablename that defines the name of the table you are deleting from in your database.
2. The proc has an optional parameter #columns that you can use to define the fields that make up the desired primary key that you are deleting against. If this field is left blank, it is assumed that all the fields besides the identity column make up the desired primary key.
3. When duplicate records are deleted, the record with the lowest value in it's identity column will be maintained.
Here is my delete_dupes stored proc:
create proc delete_dupes (#tablename varchar(max), #columns columnnames readonly)
as
begin
declare #table table (iterator int, name varchar(max), is_identity int)
declare #tablepartition table (idx int identity, type varchar(max), value varchar(max))
declare #partitionby varchar(max)
declare #iterator int= 1
if exists (select 1 from #columns) begin
declare #columns1 table (iterator int, columnnames varchar(max))
insert #columns1
select 1, columnnames from #columns
set #partitionby = (select distinct
substring((Select ', '+t1.columnnames
From #columns1 t1
Where T1.iterator = T2.iterator
ORDER BY T1.iterator
For XML PATH ('')),2, 1000) partition
From #columns1 T2 )
end
insert #table
select 1, a.name, is_identity from sys.all_columns a join sys.all_objects b on a.object_id=b.object_id
where b.name = #tablename
declare #identity varchar(max)= (select name from #table where is_identity=1)
while #iterator>=0 begin
insert #tablepartition
Select distinct case when #iterator=1 then 'order by' else 'over (partition by' end ,
substring((Select ', '+t1.name
From #table t1
Where T1.iterator = T2.iterator and is_identity=#iterator
ORDER BY T1.iterator
For XML PATH ('')),2, 5000) partition
From #table T2
set #iterator=#iterator-1
end
declare #originalpartition varchar(max)
if #partitionby is null begin
select #originalpartition = replace(b.value+','+a.type+a.value ,'over (partition by','') from #tablepartition a cross join #tablepartition b where a.idx=2 and b.idx=1
select #partitionby = a.type+a.value+' '+b.type+a.value+','+b.value+') rownum' from #tablepartition a cross join #tablepartition b where a.idx=2 and b.idx=1
end
else
begin
select #originalpartition=b.value +','+ #partitionby from #tablepartition a cross join #tablepartition b where a.idx=2 and b.idx=1
set #partitionby = (select 'OVER (partition by'+ #partitionby + ' ORDER BY'+ #partitionby + ','+b.value +') rownum'
from #tablepartition a cross join #tablepartition b where a.idx=2 and b.idx=1)
end
exec('select row_number() ' + #partitionby +', '+#originalpartition+' into ##temp from '+ #tablename+'')
exec(
'delete a from _original a
left join ##temp b on a.'+#identity+'=b.'+#identity+' and rownum=1
where b.rownum is null')
drop table ##temp
end
Once this is complied, you can delete all your duplicate records by running the proc. To delete dupes without defining a desired primary key use this call:
exec delete_dupes '_original'
To delete dupes based on a defined desired primary key use this call:
declare #table1 as columnnames
insert #table1
values ('salesrepid'),('sale')
exec delete_dupes '_original' , #table1