Edit for better clarification.
I have a table created with two columns around 60 rows
----SiteDboTable---
SELECT
[SiteName]
, CASE WHEN [Type] = 'Wind' THEN CONCAT('[YYY].[dbo].', '[', Replace(Translate([SiteName], ' -\','???'),'?',''), 'Turbine]')
ELSE CONCAT('[YYY].[dbo].', '[', Replace(Translate([SiteName], ' -\','???'),'?',''), 'Inverter]')
END AS dboName
FROM [XXX].[dbo].[Site]
Order By SiteName
Table output:
SiteName dboName
site1 [YYY].[dbo].[site1Inverter]
.... .....
.... .....
site4 [YYY].[dbo].[site4Inverter]
..n.. ..n..
I want to loop through each row of SiteDboTable and insert each rows data into HLEEtmp_table
Using SiteDboTabletable above, I want to use the two columns (SiteName, dboName) each as a variable. Each variable will be updated/changed in the script below. So that when I run HLEEtmp_table it is changing the SiteName and FROM statement each time. Then the data from each iteration of ``HLEEtmp_table``` iteration, this data will be inputted into another table to store all the data.
---HLEEtmp_table---
'SELECT
dateadd(hour, datediff(hour, 0, DataTimeStamp), 0) AS DataTimeStamp
,'+#SiteName+' AS Site
, DeviceID
, AVG([RealPowerAC]) AS RealPowerAC_MEAN
FROM'+#TableName+' WHERE DataTimeStamp >= DATEADD(day,-30,GETDATE())
GROUP BY dateadd(hour, datediff(hour, 0, DataTimeStamp), 0)
, datepart(hour,DataTimeStamp)
, [DeviceID];'
Below is what I was trying. Not sure if this is the correct approach. A cursor approach might not work, I think.
Any Ideas or help would be appreciated.
First, I am creating my two temp tables needed for my data table to INSERT into and my table containing my FROM statement schemas.
IF (OBJECT_ID('tempdb..#HLEEtmp_table') IS NOT NULL )
DROP TABLE #HLEEtmp_table;
IF (OBJECT_ID('tempdb..#SiteDboTable') IS NOT NULL )
DROP TABLE #SiteDboTable;
IF (OBJECT_ID('tempdb..#HLEEtmp_table2') IS NOT NULL )
DROP TABLE #HLEEtmp_table2;
--Create Temp Table #HLEEtmp_table; this table will hold the data I need---------
CREATE TABLE #HLEEtmp_table (
DataTimeStamp VARCHAR(50),
Site VARCHAR(50),
DeviceID VARCHAR(50),
RealPowerAC_MEAN VARCHAR(50)
)
----------------------------------------------------------
/*Create Temp Table #SiteDboTable:
- This table will list of all [DB].[dbo].[table] names in column [AssetName]
- #SiteDboTable will create a table with 60 rows and 2 columns.
- From #SiteDboTable: need [Site] column and [dboName] column for insert into #HLEEtmp_table
- #SiteDboTable.[Site] = #HLEEtmp_table.[Site]
- #SiteDboTable.[dboName] will be #HLEEtmp_table FROM statement: FROM #SiteDboTable.[dboName] "i.e. [XXX].[dbo].[AVInverter]"*/
SELECT
[SiteName]
, CASE WHEN [Type] = 'Wind' THEN CONCAT('[XXX].[dbo].', '[', Replace(Translate([SiteName], ' -\','???'),'?',''), 'Turbine]')
ELSE CONCAT('[XXX].[dbo].', '[', Replace(Translate([SiteName], ' -\','???'),'?',''), 'Inverter]')
END AS dboName
INTO #SiteDboTable
FROM [YYY].[dbo].[Site]
Order By SiteName
With the data from Temp Table #SiteDboTable, I want to use #SiteDboTable columns in the below table #HLEEtmp_table2. Pull my data from #HLEEtmp_table2 and INSERT into my temp data table #HLEEtmp_table.
---------------------------------
--INSERT INTO #HLEEtmp_table VALUES ('DataTimeStamp','Site','DeviceID','RealPowerAC_MEAN')
DECLARE #TableCount int
DECLARE #SiteName varchar(50)
DECLARE #SQL varchar(max)
DECLARE #TableName varchar(256)
SELECT #TableCount = COUNT(1) from #SiteDboTable
WHILE #TableCount > 0
BEGIN
SELECT TOP 1 #SiteName = SiteName from #SiteDboTable ORDER BY SiteName
SELECT #SQL = '
SELECT
dateadd(hour, datediff(hour, 0, DataTimeStamp), 0) AS DataTimeStamp
,'+#SiteName+' AS Site
, DeviceID
, AVG([RealPowerAC]) AS RealPowerAC_MEAN
INTO #HLEEtmp_table2
FROM
'+#TableName+'
WHERE
DataTimeStamp >= DATEADD(day,-30,GETDATE())
GROUP BY
dateadd(hour, datediff(hour, 0, DataTimeStamp), 0)
, datepart(hour,DataTimeStamp)
, [DeviceID];
-- Drop the Primary Key Column from the temp table
-- Alter Table #HLEEtmp_table2 Drop Column [PrimaryKeyColumn]
-- Insert that into your other big table
Insert Into #HLEEtmp_table
Select * From #HLEEtmp_table2
-- Drop the temp table you created
Drop Table #HLEEtmp_table2
'
EXEC (#SQL)
DELETE #SiteDboTable WHERE dboName = #TableName
SELECT #SiteName = COUNT(1) from #SiteDboTable
END
if I where I could have added
Print (#SQL)
EXEC (#SQL)
and that should give me the dynamic SQL which you are executing and that way it will be easy to troubleshoot .
HTH
Related
I created a temp table #test containing 3 fields: ColumnName, TableName, and Id.
I would like to see which rows in the #test table (columns in their respective tables) are not empty? I.e., for every column name that i have in the ColumnName field, and for the corresponding table found in the TableName field, i would like to see whether the column is empty or not. Tried some things (see below) but didn't get anywhere. Help, please.
declare #LoopCounter INT = 1, #maxloopcounter int, #test varchar(100),
#test2 varchar(100), #check int
set #maxloopcounter = (select count(TableName) from #test)
while #LoopCounter <= #maxloopcounter
begin
DECLARE #PropIDs TABLE (tablename varchar(max), id int )
Insert into #PropIDs (tablename, id)
SELECT [tableName], id FROM #test
where id = #LoopCounter
set #test2 = (select columnname from #test where id = #LoopCounter)
declare #sss varchar(max)
set #sss = (select tablename from #PropIDs where id = #LoopCounter)
set #check = (select count(#test2)
from (select tablename
from #PropIDs
where id = #LoopCounter) A
)
print #test2
print #sss
print #check
set #LoopCounter = #LoopCounter + 1
end
In order to use variables as column names and table names in your #Check= query, you will need to use Dynamic SQL.
There is most likely a better way to do this but I cant think of one off hand. Here is what I would do.
Use the select and declare a cursor rather than a while loop as you have it. That way you dont have to count on sequential id's. The cursor would fetch fields columnname, id and tablename
In the loop build a dynamic sql statement
Set #Sql = 'Select Count(*) Cnt Into #Temp2 From ' + TableName + ' Where ' + #columnname + ' Is not null And ' + #columnname <> '''''
Exec(#Sql)
Then check #Temp2 for a value greater than 0 and if this is what you desire you can use the #id that was fetched to update your #Temp table. Putting the result into a scalar variable rather than a temp table would be preferred but cant remember the best way to do that and using a temp table allows you to use an update join so it would well in my opinion.
https://www.mssqltips.com/sqlservertip/1599/sql-server-cursor-example/
http://www.sommarskog.se/dynamic_sql.html
Found a way to extract all non-empty tables from the schema, then just joined with the initial temp table that I had created.
select A.tablename, B.[row_count]
from (select * from #test) A
left join
(SELECT r.table_name, r.row_count, r.[object_id]
FROM sys.tables t
INNER JOIN (
SELECT OBJECT_NAME(s.[object_id]) table_name, SUM(s.row_count) row_count, s.[object_id]
FROM sys.dm_db_partition_stats s
WHERE s.index_id in (0,1)
GROUP BY s.[object_id]
) r on t.[object_id] = r.[object_id]
WHERE r.row_count > 0 ) B
on A.[TableName] = B.[table_name]
WHERE ROW_COUNT > 0
order by b.row_count desc
How about this one - bitmask computed column checks for NULLability. Value in the bitmask tells you if a column is NULL or not. Counting base 2.
CREATE TABLE FindNullComputedMask
(ID int
,val int
,valstr varchar(3)
,NotEmpty as
CASE WHEN ID IS NULL THEN 0 ELSE 1 END
|
CASE WHEN val IS NULL THEN 0 ELSE 2 END
|
CASE WHEN valstr IS NULL THEN 0 ELSE 4 END
)
INSERT FindNullComputedMask
SELECT 1,1,NULL
INSERT FindNullComputedMask
SELECT NULL,2,NULL
INSERT FindNullComputedMask
SELECT 2,NULL, NULL
INSERT FindNullComputedMask
SELECT 3,3,3
SELECT *
FROM FindNullComputedMask
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
I am using SQL Server 2012 and have a table that has the following columns:
ID, Date, CustomFieldName, CustomFieldValue
The CustomFieldName column has 100 values (I know how stupid this sounds) but for the sake of simplicity lets say they are CustomField1, CustomField2, CustomField3
I would like to create a pivot where the out put looks like
ID, Date, CustomField1, CustomField2, CustomField3 where the Max date of CustomFieldVaue's is aggregated.
I have failed horribly in this, but have some progress (though my max isnt right and getting a lot of wrong data)
Any help would be appreciated!
SELECT [date],[id], [CustomField1], [CustomField2], [CustomField3]
from
(
SELECT [date], [id], [CustomFieldValue], [CustomFieldName],
row_number() over(partition by [CustomFieldName] order by [CustomFieldValue]) rn
from CustomTable
) as st
pivot
(
max([CustomFieldValue])
FOR [CustomFieldName] in ([CustomField1], CustomField2, [CustomField3])
) as pivottable
order by [id]
Hope I got it right, you want to pivot the rows (COlumnName1,2,...etc) as columns, so I've made a little script that's ready to run.
I recommend CTE's when it comes to pivoting, makes it easier, if you want to see the whole structure of the query just do a select #xSqlString
set nocount on;
create table
#testTable
(
ID int identity(1,1),
[Date] datetime default getdate(),
CustomFieldName nvarchar(50),
CustomFieldValue date
);
declare
#i int = 0,
#xSqlStringPivot nvarchar(max) = '',
#xSqlString nvarchar(max) = '';
while(#i<=100)
begin
set
#xSqlStringPivot += concat('CustomFieldName',cast(#i as nvarchar(50)),char(13), case when #i<100 then ', ' else '' end);
insert into #testTable
(
CustomFieldName,
CustomFieldValue
)
values
(
concat('CustomFieldName', cast(#i as nvarchar(50))),
dateAdd(day,-#i,getdate())
);
set
#i += 1;
end;
select * from
#testTable
set
#xSqlString =
(
'with ctePiv as
(
select
t.CustomFieldName,
t.CustomFieldValue
from
#testTable t
)
select
*
from
ctePiv
pivot
(
max(customFieldValue) for customFieldName in
(
'+ #xSqlStringPivot +'
)
)p'
);
exec sp_executeSQL #xSqlString
drop table #testTable;
Edit 1
I am referencing the custom table on the while block, basically I'm iterating 100 times to populate the table with 100 rows. This is just to simulate your case.
while(#i<=100)
begin
set
#xSqlStringPivot += concat('CustomFieldName',cast(#i as nvarchar(50)),char(13), case when #i<100 then ', ' else '' end);
insert into #testTable
(
CustomFieldName,
CustomFieldValue
)
values
(
concat('CustomFieldName', cast(#i as nvarchar(50))),
dateAdd(day,-#i,getdate())
);
set
#i += 1;
end;
#xSqlStringPivot is just a small trick to make a list of elements (CustomFieldName0, CustomFieldName1, etc) and to concatenate it to a dynamic SQL string, notice that I'm doing this in the while block, I just concatenate 'CustomField' with the current iteration number and with a carry feed (space).
Here is what I am trying to do:
IF len(Variable) > 1
BEGIN
SELECT * INTO #TEMPTAB FROM multiple joins
END
ELSE
BEGIN
SELECT * INTO #TEMPTAB FROM different multiple joins
END
SELECT * FROM #TEMPTAB more large number of multiple joins & where & groupby
ERROR: There is already an object #TEMPTAB defined
-- Because of select * into in IF and ELSE both
I don't want to create a temp table prior cause it has a lot of columns to be defined.
Is there a way around it?
This was a fun problem for me that is... Well I figured out four ways to do it. One is with a view, one with a temp Table, one with a physical table, and one with a stored procedure and global temp table. Let me know if you have any questions.
View
DECLARE #Variable VARCHAR(10) = 'aa';
IF LEN(#Variable) > 1
BEGIN
EXEC('CREATE VIEW yourView AS SELECT ''Greater than 1'' col')
END
ELSE
BEGIN
EXEC('CREATE VIEW yourView AS SELECT ''Less than 1'' col')
END
SELECT *
FROM yourView;
DROP VIEW yourView;
Temp Table
DECLARE #Variable VARCHAR(100) = 'aa',
--Default value is 0
#percent INT = 0;
--If the length > 1, then change percent to 100 as to return the whole table
IF LEN(#Variable) > 1
SET #percent = 100;
--If the length <=1, then #percent stays 0 and you return 0 percent of the table
SELECT TOP(#percent) PERCENT 'Greater than 1' col INTO #TEMPTAB
--If you didn't populate the table with rows, then use this query to populate it
IF(#percent = 0)
BEGIN
INSERT INTO #TEMPTAB
SELECT 'Less than 1' col
END
/*your 1k lines of code here*/
SELECT *
FROM #TEMPTAB
--Cleanup
DROP TABLE #tempTab
Physical Table
DECLARE #Variable VARCHAR(10) = 'A';
IF len(#Variable) > 1
BEGIN
SELECT 'Greater than 1' col INTO TEMPTAB
END
ELSE
BEGIN
SELECT 'Less than 1' col INTO TEMPTAB2
END
IF OBJECT_ID('TEMPTAB2') IS NOT NULL
--SP_Rename doesn't work on temp tables so that's why it's an actual table
EXEC SP_RENAME 'TEMPTAB2','TEMPTAB','Object'
SELECT *
FROM TEMPTAB
DROP TABLE TEMPTAB;
Stored Procedure with Global Temp Table
IF OBJECT_ID('yourProcedure') IS NOT NULL
DROP PROCEDURE yourProcedure;
GO
CREATE PROCEDURE yourProcedure
AS
IF OBJECT_ID('tempdb..##TEMPTAB') IS NOT NULL
DROP TABLE ##tempTab;
SELECT 'Greater than 1' col INTO ##TEMPTAB
GO
DECLARE #Variable VARCHAR(10) = 'aaa';
IF LEN(#Variable) > 1
BEGIN
EXEC yourProcedure;
END
ELSE
BEGIN
SELECT 'Less than 1' col INTO ##TEMPTAB
END
SELECT *
FROM ##TEMPTAB
IF OBJECT_ID('tempdb..##TEMPTAB') IS NOT NULL
DROP TABLE ##TEMPTab;
Didn't you consider dynamic query with global temporary tables? This works for me:
DECLARE #sql NVARCHAR(MAX) = CASE WHEN 1 = 2
THEN 'SELECT * INTO ##TEMPTAB FROM dbo.SomeTable1'
ELSE 'SELECT * INTO ##TEMPTAB FROM dbo.SomeTable2'
END
EXEC (#sql)
SELECT * FROM ##TEMPTAB
DROP TABLE ##TEMPTAB
The first time you ran this code it created the table #TEMPTAB. The next time you ran SQL Server is telling you the table already exists. You should precede your code with the following:
if object_ID('tempdb..#TEMPTAB','U') is not null
drop table #TEMPTAB
This will drop (delete the table if it already exists) and the code that follows will always be able to recreate(or create) the table.
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