Related
I have a simple query:
declare #manual varchar(80) = '''Discount'',''Misc Charges'''
select *
from #Final
where charge_type in (#manual)
Now I've gone as far as verifying my declared variable is setup correctly by using the PRINT command as follows: PRINT '''Discount'',''Misc Charges''' and it in fact returns as I would expect: 'Discount','Misc Charges'.
However, when I run this query, I get no results.
If I instead simply use:
select *
from #Final
where charge_type in ('Discount','Misc Charges')
Then no problem, I get my results. I'm sure I'll kick myself once I get the answer, but as of right now, this is just not making sense. No errors, it's just not giving me my columns without any rows as if there's no data. What am I missing?
Because
IN ('''Discount'',''Misc Charges''')
is the same as
= '''Discount'',''Misc Charges'''
In other words, that is one single string that contains a bunch of escaped string delimiters, not a comma-separated list of individual string values. Which is why you can do this without SQL Server barfing:
PRINT '''Discount'',''Misc Charges''';
What you want is:
declare #manual varchar(80) = 'Discount,Misc Charges';
select f.*
from #Final AS f
INNER JOIN STRING_SPLIT(#manual, ',') AS s
ON f.charge_type = s.value;
However that can fail on compatibility_level < 130, in which case:
declare #manual varchar(80) = 'Discount,Misc Charges';
select f.*
from #Final AS f
INNER JOIN
OPENJSON('["' + REPLACE(#manual, ',', '","') + '"]') AS s
ON f.charge_type = s.value;
In the latter case you can make the query itself a little nicer by using slightly different jacked-up strings in the variable declaration:
declare #manual varchar(80) = '["Discount","Misc Charges"]';
select f.*
from #Final AS f
INNER JOIN
OPENJSON(#manual) AS s ON f.charge_type = s.value;
Or if you are on an older version and you really are hand-crafting these strings inline, you can use a table variable or CTE like #SMor suggested.
Table variable:
DECLARE #d table(str varchar(32));
INSERT #d VALUES('Discount'),('Misc Charges');
SELECT f.*
from #Final AS f
INNER JOIN #d AS d
ON f.charge_type = d.str;
CTE:
;WITH cte AS
(
SELECT str = 'Discount'
UNION ALL
SELECT str = 'Misc Charges'
)
SELECT f.*
from #Final AS f
INNER JOIN cte
ON f.charge_type = cte.str;
If you'll have more values at some point, it tips to writing a table constructor instead of multiple UNION ALLs, e.g.
;WITH cte AS
(
SELECT str FROM
(
VALUES('Discount','Misc Charges')
) AS s(str)
)
SELECT f.*
from #Final AS f
INNER JOIN cte
ON f.charge_type = cte.str;
You can use just use your list of values as comma seperated string & then use STRING_SPLIT.
declare #manual varchar(80) = 'Discount,Misc Charges'
select *from #Final
where charge_type in (SELECT * from STRING_SPLIT(#manual,',))
Here is to to do in SQL Server 2016 onwards.
SQL
DECLARE #manual VARCHAR(80) = 'Discount,Misc Charges';
DECLARE #tbl TABLE (ID INT IDENTITY PRIMARY KEY, charge_type VARCHAR(30));
INSERT INTO #tbl (charge_type) VALUES
('Discount'),
('No Discount'),
('Misc Charges');
SELECT *
FROM #tbl
WHERE charge_type in (SELECT value FROM STRING_SPLIT(#manual, ','))
I have an array of json in a SQL Server column, I am trying to update all names to 'Joe'.
I tried the below code , but it is updating only first element of the json array
CREATE TABLE #t (I INT, JsonColumn NVARCHAR(MAX) CHECK (ISJSON(JsonColumn) > 0))
INSERT INTO #t
VALUES (1, '[{"id":"101","name":"John"}, {"id":"102","name":"peter"}]')
INSERT INTO #t VALUES (2,'[{"id":"103","name":"dave"}, {"id":"104","name":"mark"}]')
SELECT * FROM #t
SELECT * FROM #t
CROSS APPLY OPENJSON(JsonColumn) s
WITH cte AS
(
SELECT *
FROM #t
CROSS APPLY OPENJSON(JsonColumn) s
)
UPDATE cte
SET JsonColumn = JSON_MODIFY(JsonColumn, '$[' + cte.[key] + '].name', 'Joe')
SELECT * FROM #t
-- DROP TABLE #t
It is only updating the first element of array to joe
Current result:
[{"id":"101","name":"Joe"}, {"id":"102","name":"cd"}]
[{"id":"103","name":"Joe"}, {"id":"104","name":"mark"}]
Expected
[{"id":"101","name":"Joe"}, {"id":"102","name":"Joe"}]
[{"id":"103","name":"Joe"}, {"id":"104","name":"Joe"}]
Since you want to do in one transaction, I could not think of any other ways than to create another table and store the values into new table and use for XML path with the value. Problem is you are trying to update JSON array and I am not sure how would you update the same row twice with different value. With cross apply as you have shown it creates two rows and then only you can update it to JOE.
Your query will update name = Joe for ID = 101 for first row, and Name = Joe for ID = 102 based on value column. Since these are on two different rows you are seeing only one change in your temp table.
I created one more #temp2 table to store those values and use XML path to concatenate. The final table will be #t2 table for your expected results.
SELECT *
into #t2
FROM #t
CROSS APPLY OPENJSON(JsonColumn) s
select *, json_value (value, '$.name') from #t2
UPDATE #t2
SET value = JSON_MODIFY(value, '$.name', 'Joe')
select t.I ,
JSONValue = concat('[',stuff((select ',' + value from #t2 t1
where t1.i = t.i
for XML path('')),1,1,''),']')
from #t2 t
group by t.I
Output:
I JSONValue
1 [{"id":"101","name":"Joe"},{"id":"102","name":"Joe"}]
Updating original table:
update t
set t.JsonColumn =t2.JSONValue
from #t t
join (select t.I ,
JSONValue = concat('[',stuff((select ',' + value from #t2 t1
where t1.i = t.i
for XML path('')),1,1,''),']')
from #t2 t
group by t.I ) t2 on t.I = t2.i
I think that it is impossible to apply more updates to one record with one command. So you need to explode JSON array to records.
You can do this with a Temporary or Variable Table and a Cursor.
-- Declare the Variable Table
DECLARE #JsonTable TABLE (
RecordKey UNIQUEIDENTIFIER,
ArrayIndex INT,
ObjKey NVARCHAR(100),
ObjValue NVARCHAR(1000)
);
-- Fill the Variable Table
INSERT INTO #JsonTable
SELECT TB1.pk as RecordKey,
TB1data.[key] AS ArrayIndex,
TB1dataItem.[key] as ObjKey,
TB1dataItem.[value] as ObjValue
FROM MyTable TB1
CROSS APPLY OPENJSON(JSON_QUERY(TB1.data, '$.list')) TB1data
CROSS APPLY OPENJSON(JSON_QUERY(TB1data.value, '$')) TB1dataItem
WHERE TB1dataItem.[key] = 'name'
-- Declare Cursor and relative variables
DECLARE #recordKey UNIQUEIDENTIFIER,
#recordData NVARCHAR(MAX),
#arrayIndex INT,
#objKey NVARCHAR(100),
#objValue NVARCHAR(1000);
DECLARE JsonCursor CURSOR FAST_FORWARD READ_ONLY FOR
SELECT * FROM #JsonTable;
-- Use Cursor to read any json array item
OPEN JsonCursor;
FETCH NEXT
FROM JsonCursor
INTO #recordKey, #arrayIndex, #objKey, #objValue;
WHILE ##FETCH_STATUS = 0 BEGIN
UPDATE TB1
SET data = JSON_MODIFY(
data,
'$.list[' + CAST(#arrayIndex as VARCHAR(20)) + '].name',
'Joe'
)
FROM MyTable TB1
WHERE TB1.pk = #recordKey;
FETCH NEXT
FROM JsonCursor
INTO #recordKey, #arrayIndex, #objKey, #objValue;
END;
CLOSE JsonCursor;
DEALLOCATE JsonCursor;
Do you need this?
CREATE TABLE #t (
I INT,
JsonColumn NVARCHAR(MAX) CHECK (ISJSON(JsonColumn) > 0)
);
INSERT INTO #t
VALUES (1, '[{"id":"101","name":"John"}, {"id":"102","name":"peter"}]');
INSERT INTO #t
VALUES (2, '[{"id":"103","name":"dave"}, {"id":"104","name":"mark"}]');
SELECT CONCAT('[', STRING_AGG(JSON_MODIFY(JSON_MODIFY('{}', '$.id', j.id), '$.name', 'John'), ','), ']')
FROM #t t
CROSS APPLY OPENJSON(JsonColumn) WITH (id INT, name sysname) j
GROUP BY t.I
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 can´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;
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
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