Replace Cursor Next number assignment Operation with Set based equivalent - sql

Good day all,
I have the following cursor query and would like to replace it with a set based query to address performance issues.
DECLARE #EmpIDM CHAR(21);
DECLARE #EmpName CHAR(21);
DECLARE #EMPCatID INT;
DECLARE Assign_Emp SCROLL CURSOR
FOR
SELECT DISTINCT EMP
, EMPNAME
FROM HR_EMPLOYEES
SET NOCOUNT ON
OPEN Assign_Emp;
FETCH NEXT
FROM Assign_Emp
INTO #EmpIDM
, #EmpName
WHILE ##FETCH_STATUS = 0
BEGIN
SET #EMPCatID = (
SELECT TOP 1 CategoryID
FROM Categories
)
UPDATE Categories
SET CategoryID = (CategoryID + 1) /*Increment Category ID for next Insert*/
INSERT INTO Table1 (
EmpNumber
, EmployeeName
, EmployeeCategoryID
)
VALUES (
#EmpIDM
, #EmpName
, #EMPCatID
)
FETCH NEXT
FROM Assign_Emp
INTO #EmpIDM
, #EmpName
END
CLOSE Assign_Emp;
CLOSE Assign_Emp;
SET NOCOUNT OFF
My challenge is adapting the following code segment into a set based operation
SET #EMPCatID = (
SELECT TOP 1 CategoryID
FROM Categories
)
UPDATE Categories
SET CategoryID = (CategoryID + 1) /*Increment Category ID for next Insert*/
I humbly appreciate any insight on how I can achieve this.
Many Thanks,

Re-write using temp. table with identity column:
declare #offset int
select #offset = isnull(max(CategoryID),0) from Categories
create table #data (
EmpNumber CHAR(21),
EmployeeName CHAR(21),
EmployeeCategoryID int identity
)
INSERT INTO #data (
EmpNumber
, EmployeeName)
SELECT DISTINCT EmpIDM
, EmpName
FROM HR_EMPLOYEES
insert into Table1 (
EmpNumber
, EmployeeName
, EmployeeCategoryID
) select
EmpNumber
, EmployeeName
, EmployeeCategoryID + #offset
from #data
update Categories
set CategoryID = (select max(EmployeeCategoryID) from #data) + #offset

Related

How to shorten SQL script

According to my code below, I was using cursor to get all information in WInstance table. However, my query may have a problem with performance due to cursor. Is there any way to use nested-select instead of cursor? Please share me your idea.
My business here is to get only 1 of the same ItemID, SequenceID, TaskStatus, ListID, WebID, SiteID.
Technically, there are lots of the same ItemID, SequenceID, TaskStatus, ListID, WebID, SiteID in the joining tables of WInstance and WProgress with AssignTask = 'Assign task'. Therefore, I used distinct and cursorto loop through to get only the top 1 with order by.
Here is my code:
CREATE PROCEDURE dbo.CustomTasksHistory
(
#Username NVARCHAR(255)
)
AS
DECLARE #TempTableStatus TABLE
(
ItemID INT ,
SequenceID INT ,
TaskStatus NVARCHAR(25) ,
ListID UNIQUEIDENTIFIER ,
WebID UNIQUEIDENTIFIER ,
SiteID UNIQUEIDENTIFIER
);
DECLARE #ItemID INT;
DECLARE #SequenceID INT;
DECLARE #ListID UNIQUEIDENTIFIER;
DECLARE #WebID UNIQUEIDENTIFIER;
DECLARE #SiteID UNIQUEIDENTIFIER;
DECLARE #AssignTask VARCHAR(25);
SET #AssignTask = 'Assign task';
-- Select final TaskStatus of each ItemID with its SequenceID --
DECLARE cursor_ItemID CURSOR FAST_FORWARD READ_ONLY FOR
SELECT DISTINCT
WI.ItemID ,
WP.SequenceID ,
WI.ListID ,
WI.WebID ,
WI.SiteID
FROM dbo.WInstance WI
INNER JOIN dbo.WProgress WP ON WI.InstanceID = WP.InstanceID
WHERE WP.CurrentActivityTitle = #AssignTask;
OPEN cursor_ItemID;
FETCH NEXT FROM cursor_ItemID INTO #ItemID, #SequenceID, #ListID, #WebID, #SiteID;
WHILE ##FETCH_STATUS = 0
BEGIN
INSERT INTO #TempTableStatus
( ItemID ,
SequenceID ,
TaskStatus ,
ListID ,
WebID ,
SiteID
)
SELECT TOP 1
WI.ItemID ,
WP.SequenceID ,
CASE WHEN WP.ActivityComplete = 0
THEN 'Not Started'
ELSE 'Completed'
END AS 'TaskStatus' ,
WI.ListID ,
WI.WebID ,
WI.SiteID
FROM dbo.WInstance WI
INNER JOIN dbo.WProgress WP ON WI.InstanceID = WP.InstanceID
WHERE WP.CurrentActivityTitle = #AssignTask
AND WI.ItemID = #ItemID
AND WP.SequenceID = #SequenceID
AND WI.ListID = #ListID
AND WI.WebID = #WebID
AND WI.SiteID = #SiteID
ORDER BY TimeStamp DESC;
FETCH NEXT FROM cursor_ItemID INTO #ItemID, #SequenceID, #ListID, #WebID, #SiteID;
END;
CLOSE cursor_ItemID;
DEALLOCATE cursor_ItemID;
SELECT *
FROM #TempTableStatus;
You don't need to use cursor. Replace it with below query
SELECT ItemID, SequenceID, TaskStatus, ListID, WebID, SiteID
FROM
(
SELECT RN = ROW_NUMBER() OVER (PARTITION BY WP.CurrentActivityTitle,
WI.ItemID, WP.SequenceID,
WI.ListID, WI.WebID, WI.SiteID
ORDER BY TimeStamp DESC),
WI.ItemID ,
WP.SequenceID ,
CASE WHEN WP.ActivityComplete = 0
THEN 'Not Started'
ELSE 'Completed'
END AS 'TaskStatus' ,
WI.ListID ,
WI.WebID ,
WI.SiteID
FROM dbo.WInstance WI
INNER JOIN dbo.WProgress WP ON WI.InstanceID = WP.InstanceID
WHERE WP.CurrentActivityTitle = #AssignTask
) D
WHERE RN = 1;

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

Auto increment Alphanumeric ID in MSSQL

I have an existing Stored procedure that generate employee ID. The employee ID have a format of EPXXXX, EP then 4 numeric values. I want my stored procedure to be shorten.
given the table (tblEmployee) above. Below is the stored procedure for inserting the new employee with the new employee number. The process is I have to get the last employee id, get the last 4 digits (which is the number), convert it to integer, add 1 to increment, check if the number is less than 10, 100 or 1000 or equal/greater than 1000, add the prefix before inserting the new records to the table.
create procedure NewEmployee
#EmployeeName VARCHAR(50)
AS
BEGIN
SET NOCOUNT ON
DECLARE #lastEmpID as VARCHAR(6)
SET #lastEmpID =
(
SELECT TOP 1 Employee_ID
FROM tblEmployee
ORDER BY Employee_ID DESC
)
DECLARE #empID as VARCHAR(4)
SET #empID =
(
SELECT RIGHT(#lastEmpID, 4)
)
DECLARE #numEmpID as INT
#numEmpID =
(
SELECT CONVERT(INT, #empID) + 1
)
DECLARE #NewEmployeeID as VARCHAR(6)
IF #numEmp < 10
SET #NewEmployee = SELECT 'EP000' + CONVERT(#EmpID)
IF #numEmp < 100
SET #NewEmployee = SELECT 'EP00' + CONVERT(#EmpID)
IF #numEmp < 1000
SET #NewEmployee = SELECT 'EP0' + CONVERT(#EmpID)
IF #numEmp >= 1000
SET #NewEmployee = SELECT 'EP' + CONVERT(#EmpID)
INSERT INTO tblEmployee(Employee_ID, Name)
VALUES (#NewEmployeeID, #EmployeeName)
END
Try this one -
CREATE PROCEDURE dbo.NewEmployee
#EmployeeName VARCHAR(50)
AS BEGIN
SET NOCOUNT ON;
INSERT INTO dbo.tblEmployee(Employee_ID, Name)
SELECT
'EP' + RIGHT('0000' + CAST(Employee_ID + 1 AS VARCHAR(4)), 4)
, #EmployeeName
FROM (
SELECT TOP 1 Employee_ID = CAST(RIGHT(Employee_ID, 4) AS INT)
FROM dbo.tblEmployee
ORDER BY Employee_ID DESC
) t
END
I'm not suggesting over what you have currently but, i'd do this way. This is the way I've implemented in my application. Which im gonna give you. Hope you Like this. This is fully Dynamic and Works for all the Transaction you could have.
I've a table Which hold the Document Number as :
CREATE TABLE INV_DOC_FORMAT(
DOC_CODE VARCHAR(10),
DOC_NAME VARCHAR(100),
PREFIX VARCHAR(10),
SUFFIX VARCHAR(10),
[LENGTH] INT,
[CURRENT] INT
)
Which would hold the Data Like :
INSERT INTO INV_DOC_FORMAT(DOC_CODE,DOC_NAME,PREFIX,SUFFIX,[LENGTH],[CURRENT])
VALUES('01','INV_UNIT','U','',5,0)
INSERT INTO INV_DOC_FORMAT(DOC_CODE,DOC_NAME,PREFIX,SUFFIX,[LENGTH],[CURRENT])
VALUES('02','INV_UNIT_GROUP','UG','',5,0)
And, i'd have a fUNCTION OR Procedure but, i've an function here Which would generate the Document Number.
CREATE FUNCTION GET_DOC_FORMAT(#DOC_CODE VARCHAR(100))RETURNS VARCHAR(100)
AS
BEGIN
DECLARE #PRE VARCHAR(10)
DECLARE #SUF VARCHAR(10)
DECLARE #LENTH INT
DECLARE #CURRENT INT
DECLARE #FORMAT VARCHAR(100)
DECLARE #REPEAT VARCHAR(10)
IF NOT EXISTS(SELECT DOC_CODE FROM INV_DOC_FORMAT WHERE DOC_CODE=#DOC_CODE)
RETURN ''
SELECT #PRE= PREFIX FROM INV_DOC_FORMAT WHERE DOC_CODE=#DOC_CODE
SELECT #SUF= SUFFIX FROM INV_DOC_FORMAT WHERE DOC_CODE=#DOC_CODE
SELECT #LENTH= [LENGTH] FROM INV_DOC_FORMAT WHERE DOC_CODE=#DOC_CODE
SELECT #CURRENT= [CURRENT] FROM INV_DOC_FORMAT WHERE DOC_CODE=#DOC_CODE
SET #REPEAT=REPLICATE('0',(#LENTH-LEN(CONVERT(VARCHAR, #CURRENT))))
SET #FORMAT=#PRE + #REPEAT +CONVERT(VARCHAR, #CURRENT+1) + #SUF
RETURN #FORMAT
END
You can use the Function like :
INSERT INTO INV_UNIT(UNIT_CODE,UNIT_NAME,UNIT_ALIAS,APPROVED,APPROVED_USER_ID,APPROVED_DATE)
VALUES(DBO.GET_DOC_FORMAT('01'),#Unit_Name,#Unit_Alias,#APPROVED,#APPROVED_USER_ID,#APPROVED_DATE)
--After Transaction Successfully complete, You can
UPDATE INV_DOC_FORMAT SET [CURRENT]=[CURRENT]+1 WHERE DOC_CODE='01'
Or, you can create an Single Procedure which would handle all the things alone too.
Hope you got the way...
Hence,
Looking at your Way, you are making an Mistake.
You are getting
SET #lastEmpID =
(
SELECT TOP 1 Employee_ID
FROM tblEmployee
ORDER BY Employee_ID DESC
)
Last employee id, and then you are manipulating the rest of the ID. This would create or reuse the ID that was generated earlier however deleted now.
Suppose EMP0010 was there. After some day that EMP has been Deleted. So, When you again create an Employeee next time, You gonna have Same Emp ID you had before for anohter Employe but no more exits however. I dont think thats a good idea.
And, Instead of this :
DECLARE #NewEmployeeID as VARCHAR(6)
IF #numEmp < 10
SET #NewEmployee = SELECT 'EP000' + CONVERT(#EmpID)
IF #numEmp < 100
SET #NewEmployee = SELECT 'EP00' + CONVERT(#EmpID)
IF #numEmp < 1000
SET #NewEmployee = SELECT 'EP0' + CONVERT(#EmpID)
IF #numEmp >= 1000
SET #NewEmployee = SELECT 'EP' + CONVERT(#EmpID)
Which you used to repeat an Zero. You would use Replicate Function() of SQL. Like above on the Example of Mine.
SET #REPEAT=REPLICATE('0',(#LENTH-LEN(CONVERT(VARCHAR, #CURRENT))))
I don't think you need a Stored Procedure , Try using Ranking Functions
select
'EP'+RIGHT('000000'+ CAST(ROW_NUMBER() OVER (ORDER BY Name) AS VARCHAR(6)), 4)
AS [emp_code]
,
Name
FROM emp1 WITH(NOLOCK)
SQL Fiddle
EDIT
select
'EP'+RIGHT('000000'+ CAST((ROW_NUMBER() OVER (ORDER BY Name)+10) AS VARCHAR(6)), 4)
AS [emp_code] --^Add the last Emp no.
,
Name
FROM emp1 WITH(NOLOCK)
SQL Fiddle
of course the accepted answer is working fine, but it is not working if we have numm in previous values. so modified it as below, hope this will help others as well
CREATE PROCEDURE dbo.NewEmployee
#EmployeeName VARCHAR(50)
AS BEGIN
SET NOCOUNT ON;
INSERT INTO dbo.tblEmployee(Employee_ID, Name)
SELECT
'EP' + RIGHT('0000' + CAST(Employee_ID + 1 AS VARCHAR(4)), 4)
, #EmployeeName
FROM (
SELECT TOP 1 Employee_ID = CAST(RIGHT(Employee_ID, 4) AS INT)
FROM dbo.tblEmployee
ORDER BY Employee_ID DESC
) t
END

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

SQL query to find Missing sequence numbers

I have a column named sequence. The data in this column looks like 1, 2, 3, 4, 5, 7, 9, 10, 15.
I need to find the missing sequence numbers from the table. What SQL query will find the missing sequence numbers from my table? I am expecting results like
Missing numbers
---------------
6
8
11
12
13
14
I am using only one table. I tried the query below, but am not getting the results I want.
select de.sequence + 1 as sequence from dataentry as de
left outer join dataentry as de1 on de.sequence + 1 = de1.sequence
where de1.sequence is null order by sequence asc;
How about something like:
select (select isnull(max(val)+1,1) from mydata where val < md.val) as [from],
md.val - 1 as [to]
from mydata md
where md.val != 1 and not exists (
select 1 from mydata md2 where md2.val = md.val - 1)
giving summarised results:
from to
----------- -----------
6 6
8 8
11 14
I know this is a very old post but I wanted to add this solution that I found HERE so that I can find it easier:
WITH Missing (missnum, maxid)
AS
(
SELECT 1 AS missnum, (select max(id) from #TT)
UNION ALL
SELECT missnum + 1, maxid FROM Missing
WHERE missnum < maxid
)
SELECT missnum
FROM Missing
LEFT OUTER JOIN #TT tt on tt.id = Missing.missnum
WHERE tt.id is NULL
OPTION (MAXRECURSION 0);
Try with this:
declare #min int
declare #max int
select #min = min(seq_field), #max = max(seq_field) from [Table]
create table #tmp (Field_No int)
while #min <= #max
begin
if not exists (select * from [Table] where seq_field = #min)
insert into #tmp (Field_No) values (#min)
set #min = #min + 1
end
select * from #tmp
drop table #tmp
The best solutions are those that use a temporary table with the sequence. Assuming you build such a table, LEFT JOIN with NULL check should do the job:
SELECT #sequence.value
FROM #sequence
LEFT JOIN MyTable ON #sequence.value = MyTable.value
WHERE MyTable.value IS NULL
But if you have to repeat this operation often (and more then for 1 sequence in the database), I would create a "static-data" table and have a script to populate it to the MAX(value) of all the tables you need.
SELECT CASE WHEN MAX(column_name) = COUNT(*)
THEN CAST(NULL AS INTEGER)
-- THEN MAX(column_name) + 1 as other option
WHEN MIN(column_name) > 1
THEN 1
WHEN MAX(column_name) <> COUNT(*)
THEN (SELECT MIN(column_name)+1
FROM table_name
WHERE (column_name+ 1)
NOT IN (SELECT column_name FROM table_name))
ELSE NULL END
FROM table_name;
Here is a script to create a stored procedure that returns missing sequential numbers for a given date range.
CREATE PROCEDURE dbo.ddc_RolledBackOrders
-- Add the parameters for the stored procedure here
#StartDate DATETIME ,
#EndDate DATETIME
AS
BEGIN
SET NOCOUNT ON;
DECLARE #Min BIGINT
DECLARE #Max BIGINT
DECLARE #i BIGINT
IF OBJECT_ID('tempdb..#TempTable') IS NOT NULL
BEGIN
DROP TABLE #TempTable
END
CREATE TABLE #TempTable
(
TempOrderNumber BIGINT
)
SELECT #Min = ( SELECT MIN(ordernumber)
FROM dbo.Orders WITH ( NOLOCK )
WHERE OrderDate BETWEEN #StartDate AND #EndDate)
SELECT #Max = ( SELECT MAX(ordernumber)
FROM dbo.Orders WITH ( NOLOCK )
WHERE OrderDate BETWEEN #StartDate AND #EndDate)
SELECT #i = #Min
WHILE #i <= #Max
BEGIN
INSERT INTO #TempTable
SELECT #i
SELECT #i = #i + 1
END
SELECT TempOrderNumber
FROM #TempTable
LEFT JOIN dbo.orders o WITH ( NOLOCK ) ON tempordernumber = o.OrderNumber
WHERE o.OrderNumber IS NULL
END
GO
Aren't all given solutions way too complex?
wouldn't this be much simpler:
SELECT *
FROM (SELECT row_number() over(order by number) as N from master..spt_values) t
where N not in (select 1 as sequence union
select 2 union
select 3 union
select 4 union
select 5 union
select 7 union
select 10 union
select 15
)
This is my interpretation of this issue, placing the contents in a Table variable that I can easily access in the remainder of my script.
DECLARE #IDS TABLE (row int, ID int)
INSERT INTO #IDS
select ROW_NUMBER() OVER (ORDER BY x.[Referred_ID]), x.[Referred_ID] FROM
(SELECT b.[Referred_ID] + 1 [Referred_ID]
FROM [catalog].[dbo].[Referrals] b) as x
LEFT JOIN [catalog].[dbo].[Referrals] a ON x.[Referred_ID] = a.[Referred_ID]
WHERE a.[Referred_ID] IS NULL
select * from #IDS
Just for fun, I decided to post my solution.
I had an identity column in my table and I wanted to find missing invoice numbers.
I reviewed all the examples I could find but they were not elegant enough.
CREATE VIEW EENSkippedInvoicveNo
AS
SELECT CASE WHEN MSCNT = 1 THEN CAST(MSFIRST AS VARCHAR (8)) ELSE
CAST(MSFIRST AS VARCHAR (8)) + ' - ' + CAST(MSlAST AS VARCHAR (8)) END AS MISSING,
MSCNT, INV_DT FROM (
select invNo+1 as Msfirst, inv_no -1 as Mslast, inv_no - invno -1 as msCnt, dbo.fmtdt(Inv_dt) AS INV_dT
from (select inv_no as invNo, a4glidentity + 1 as a4glid
from oehdrhst_sql where inv_dt > 20140401) as s
inner Join oehdrhst_sql as h
on a4glid = a4glidentity
where inv_no - invno <> 1
) AS SS
DECLARE #MaxID INT = (SELECT MAX(timerecordid) FROM dbo.TimeRecord)
SELECT SeqID AS MissingSeqID
FROM (SELECT ROW_NUMBER() OVER (ORDER BY column_id) SeqID from sys.columns) LkUp
LEFT JOIN dbo.TimeRecord t ON t.timeRecordId = LkUp.SeqID
WHERE t.timeRecordId is null and SeqID < #MaxID
I found this answer here:
http://sql-developers.blogspot.com/2012/10/how-to-find-missing-identitysequence.html
I was looking for a solution and found many answers. This is the one I used and it worked very well. I hope this helps anyone looking for a similar answer.
-- This will return better Results
-- ----------------------------------
;With CTERange
As (
select (select isnull(max(ArchiveID)+1,1) from tblArchives where ArchiveID < md.ArchiveID) as [from],
md.ArchiveID - 1 as [to]
from tblArchives md
where md.ArchiveID != 1 and not exists (
select 1 from tblArchives md2 where md2.ArchiveID = md.ArchiveID - 1)
) SELECT [from], [to], ([to]-[from])+1 [total missing]
From CTERange
ORDER BY ([to]-[from])+1 DESC;
from to total missing
------- ------- --------------
6 6 1
8 8 1
11 14 4
DECLARE #TempSujith TABLE
(MissingId int)
Declare #Id Int
DECLARE #mycur CURSOR
SET #mycur = CURSOR FOR Select Id From tbl_Table
OPEN #mycur
FETCH NEXT FROM #mycur INTO #Id
Declare #index int
Set #index = 1
WHILE ##FETCH_STATUS = 0
BEGIN
if (#index < #Id)
begin
while #index < #Id
begin
insert into #TempSujith values (#index)
set #index = #index + 1
end
end
set #index = #index + 1
FETCH NEXT FROM #mycur INTO #Id
END
Select Id from tbl_Table
select MissingId from #TempSujith
Create a useful Tally table:
-- can go up to 4 million or 2^22
select top 100000 identity(int, 1, 1) Id
into Tally
from master..spt_values
cross join master..spt_values
Index it, or make that single column as PK.
Then use EXCEPT to get your missing number.
select Id from Tally where Id <= (select max(Id) from TestTable)
except
select Id from TestTable
You could also solve using something like a CTE to generate the full sequence:
create table #tmp(sequence int)
insert into #tmp(sequence) values (1)
insert into #tmp(sequence) values (2)
insert into #tmp(sequence) values (3)
insert into #tmp(sequence) values (5)
insert into #tmp(sequence) values (6)
insert into #tmp(sequence) values (8)
insert into #tmp(sequence) values (10)
insert into #tmp(sequence) values (11)
insert into #tmp(sequence) values (14)
DECLARE #max INT
SELECT #max = max(sequence) from #tmp;
with full_sequence
(
Sequence
)
as
(
SELECT 1 Sequence
UNION ALL
SELECT Sequence + 1
FROM full_sequence
WHERE Sequence < #max
)
SELECT
full_sequence.sequence
FROM
full_sequence
LEFT JOIN
#tmp
ON
full_sequence.sequence = #tmp.sequence
WHERE
#tmp.sequence IS NULL
Hmmmm - the formatting is not working on here for some reason? Can anyone see the problem?
i had made a proc so you can send the table name and the key and the result is a list of missing numbers from the given table
SET ANSI_NULLS ON
GO
SET QUOTED_IDENTIFIER ON
GO
create PROCEDURE [dbo].[action_FindMissing_Autoincremnt]
(
#tblname as nvarchar(50),
#tblKey as nvarchar(50)
)
AS
BEGIN
SET NOCOUNT ON;
declare #qry nvarchar(4000)
set #qry = 'declare #min int '
set #qry = #qry + 'declare #max int '
set #qry = #qry +'select #min = min(' + #tblKey + ')'
set #qry = #qry + ', #max = max('+ #tblKey +') '
set #qry = #qry + ' from '+ #tblname
set #qry = #qry + ' create table #tmp (Field_No int)
while #min <= #max
begin
if not exists (select * from '+ #tblname +' where '+ #tblKey +' = #min)
insert into #tmp (Field_No) values (#min)
set #min = #min + 1
end
select * from #tmp order by Field_No
drop table #tmp '
exec sp_executesql #qry
END
GO
SELECT TOP 1 (Id + 1)
FROM CustomerNumberGenerator
WHERE (Id + 1) NOT IN ( SELECT Id FROM CustomerNumberGenerator )
Working on a customer number generator for my company. Not the most efficient but definitely most readable
The table has one Id column.
The table allows for Ids to be inserted at manually by a user off sequence.
The solution solves the case where the user decided to pick a high number