How to join sequential numbers to unrelated data (SQL Server) - sql-server

This question is a followup to a previous question I had about discovering unused sequential number ranges without having to resort to cursors (Working with sequential numbers in SQL Server 2005 without cursors). I'm using SQL Server 2005.
What I need to do with those numbers is to assign those numbers to records in a table. I just can't seem to come up with a way to actually relate the numbers table with the records that need those numbers.
One possible solution that came to mind was insert the records in a temp table using an identity and using the beginning of the number range as an identity seed. The only problem with this approach is that if there are gaps in the number sequence then I'll end up with duplicate control numbers.
This is how my tables look like (overly simplified):
Numbers table:
Number
-------
102314
102315
102319
102320
102324
102329
Data table:
CustomerId PaymentAmt ControlNumber
---------- ---------- -------------
1001 4502.01 NULL
1002 890.00 NULL
9830 902923.34 NULL
I need a way to make it so i end up with:
CustomerId PaymentAmt ControlNumber
---------- ---------- -------------
1001 4502.01 102314
1002 890.00 102315
9830 902923.34 102319
Is this possible without having to use cursors? The reason I'm avoiding cursors is because our current implementation uses cursors and since its so slow (8 minutes over 12,000 records) I was looking for alternatives.
Note: Thanks to all who posted answers. All of them were great, I had to pick the one that seemed easier to implement and easiest to maintain for whomever comes after me. Much appreciated.

Try this:
;WITH CTE AS
(
SELECT *, ROW_NUMBER() OVER(ORDER BY CustomerId) Corr
FROM DataTable
)
UPDATE CTE
SET CTE.ControlNumber = B.Number
FROM CTE
JOIN ( SELECT Number, ROW_NUMBER() OVER(ORDER BY Number) Corr
FROM NumberTable) B
ON CTE.Corr = B.Corr

Buidling on Martin's code from the linked question, you could give all rows without control number a row number. Then give all unused numbers a row number. Join the two sets together, and you get a unique number per row:
DECLARE #StartRange int, #EndRange int
SET #StartRange = 790123401
SET #EndRange = 790123450;
; WITH YourTable(ControlNumber, CustomerId) AS
(
SELECT 790123401, 1000
UNION ALL SELECT 790123402, 1001
UNION ALL SELECT 790123403, 1002
UNION ALL SELECT 790123406, 1003
UNION ALL SELECT NULL, 1004
UNION ALL SELECT NULL, 1005
UNION ALL SELECT NULL, 1006
)
, YourTableNumbered(rn, ControlNumber, CustomerId) AS
(
select row_number() over (
partition by IsNull(ControlNumber, -1)
order by ControlNumber)
, *
from YourTable
)
, Nums(N) AS
(
SELECT #StartRange
UNION ALL
SELECT N+1
FROM Nums
WHERE N < #EndRange
)
, UnusedNums(rn, N) as
(
select row_number() over (order by Nums.N)
, Nums.N
from Nums
where not exists
(
select *
from YourTable yt
where yt.ControlNumber = Nums.N
)
)
select ytn.CustomerId
, IsNull(ytn.ControlNumber, un.N)
from YourTableNumbered ytn
left join
UnusedNums un
on un.rn = ytn.rn
OPTION (MAXRECURSION 0)

All you need is a deterministic order in data table. If you have that, you can use ROW_NUMBER() as a join condition:
with cte as (
select row_number() over (order by CustomerId) as [row_number],
ControlNumber
from [Data Table]
where ControlNumber is null),
nte as (
select row_number() over (order by Number) as [row_number],
Number
from [Numbers])
update cte
set ControlNumber = Number
from cte
join nte on nte.[row_number] = cte.[row_number];
If you need it to be concurency proof, it does get more complex.

EDITED added in code to remove used values from #Number, via the OUTPUT caluse of the UPDATE and a DELETE
try using ROW_NUMBER() to join them:
DECLARE #Number table (Value int)
INSERT #Number VALUES (102314)
INSERT #Number VALUES (102315)
INSERT #Number VALUES (102319)
INSERT #Number VALUES (102320)
INSERT #Number VALUES (102324)
INSERT #Number VALUES (102329)
DECLARE #Data table (CustomerId int, PaymentAmt numeric(10,2),ControlNumber int)
INSERT #Data VALUES (1001, 4502.01 ,NULL)
INSERT #Data VALUES (1002, 890.00 ,NULL)
INSERT #Data VALUES (9830, 902923.34 ,NULL)
DECLARE #Used table (Value int)
;WITH RowNumber AS
(
SELECT Value,ROW_NUMBER() OVER(ORDER BY Value) AS RowNumber FROM #Number
)
,RowData AS
(
SELECT CustomerId,ROW_NUMBER() OVER(ORDER BY CustomerId) AS RowNumber, ControlNumber FROM #Data WHERE ControlNumber IS NULL
)
UPDATE d
SET ControlNumber=r.Value
OUTPUT r.Value INTO #Used
FROM RowData d
INNER JOIN RowNumber r ON d.RowNumber=r.RowNumber
DELETE #Number WHERE Value IN (SELECT Value FROM #Used)
SELECT * FROM #Data
SELECT * FROM #Number
OUTPUT:
CustomerId PaymentAmt ControlNumber
----------- --------------------------------------- -------------
1001 4502.01 102314
1002 890.00 102315
9830 902923.34 102319
(3 row(s) affected)
Value
-----------
102320
102324
102329
(3 row(s) affected)

You'll need something to join the two tables together. Some data value that you can match between the two tables.
I'm assuming there's more to your numbers table than just one column of numbers. If there's anything in there that you can match to your data table you can get away with an update.
How are you updating the data table using cursors?

Related

Delete only one row from a table where the duplicate (value, maybe date even) is not in all columns [duplicate]

How can I delete duplicate rows where no unique row id exists?
My table is
col1 col2 col3 col4 col5 col6 col7
john 1 1 1 1 1 1
john 1 1 1 1 1 1
sally 2 2 2 2 2 2
sally 2 2 2 2 2 2
I want to be left with the following after the duplicate removal:
john 1 1 1 1 1 1
sally 2 2 2 2 2 2
I've tried a few queries but I think they depend on having a row id as I don't get the desired result. For example:
DELETE
FROM table
WHERE col1 IN (
SELECT id
FROM table
GROUP BY id
HAVING (COUNT(col1) > 1)
)
I like CTEs and ROW_NUMBER as the two combined allow us to see which rows are deleted (or updated), therefore just change the DELETE FROM CTE... to SELECT * FROM CTE:
WITH CTE AS(
SELECT [col1], [col2], [col3], [col4], [col5], [col6], [col7],
RN = ROW_NUMBER()OVER(PARTITION BY col1 ORDER BY col1)
FROM dbo.Table1
)
DELETE FROM CTE WHERE RN > 1
DEMO (result is different; I assume that it's due to a typo on your part)
COL1 COL2 COL3 COL4 COL5 COL6 COL7
john 1 1 1 1 1 1
sally 2 2 2 2 2 2
This example determines duplicates by a single column col1 because of the PARTITION BY col1. If you want to include multiple columns simply add them to the PARTITION BY:
ROW_NUMBER()OVER(PARTITION BY Col1, Col2, ... ORDER BY OrderColumn)
I would prefer CTE for deleting duplicate rows from sql server table
strongly recommend to follow this article ::http://codaffection.com/sql-server-article/delete-duplicate-rows-in-sql-server/
by keeping original
WITH CTE AS
(
SELECT *,ROW_NUMBER() OVER (PARTITION BY col1,col2,col3 ORDER BY col1,col2,col3) AS RN
FROM MyTable
)
DELETE FROM CTE WHERE RN<>1
without keeping original
WITH CTE AS
(SELECT *,R=RANK() OVER (ORDER BY col1,col2,col3)
FROM MyTable)
 
DELETE CTE
WHERE R IN (SELECT R FROM CTE GROUP BY R HAVING COUNT(*)>1)
Without using CTE and ROW_NUMBER() you can just delete the records just by using group by with MAX function here is an example
DELETE
FROM MyDuplicateTable
WHERE ID NOT IN
(
SELECT MAX(ID)
FROM MyDuplicateTable
GROUP BY DuplicateColumn1, DuplicateColumn2, DuplicateColumn3)
If you have no references, like foreign keys, you can do this. I do it a lot when testing proofs of concept and the test data gets duplicated.
SELECT DISTINCT [col1],[col2],[col3],[col4],[col5],[col6],[col7]
INTO [newTable]
FROM [oldTable]
Go into the object explorer and delete the old table.
Rename the new table with the old table's name.
Remove all duplicates, but the very first ones (with min ID)
should work equally in other SQL servers, like Postgres:
DELETE FROM table
WHERE id NOT IN (
select min(id) from table
group by col1, col2, col3, col4, col5, col6, col7
)
DELETE from search
where id not in (
select min(id) from search
group by url
having count(*)=1
union
SELECT min(id) FROM search
group by url
having count(*) > 1
)
There are two solutions in mysql:
A) Delete duplicate rows using DELETE JOIN statement
DELETE t1 FROM contacts t1
INNER JOIN contacts t2
WHERE
t1.id < t2.id AND
t1.email = t2.email;
This query references the contacts table twice, therefore, it uses the table alias t1 and t2.
The output is:
1
Query OK, 4 rows affected (0.10 sec)
In case you want to delete duplicate rows and keep the lowest id, you can use the following statement:
DELETE c1 FROM contacts c1
INNER JOIN contacts c2
WHERE
c1.id > c2.id AND
c1.email = c2.email;
B) Delete duplicate rows using an intermediate table
The following shows the steps for removing duplicate rows using an intermediate table:
1. Create a new table with the structure the same as the original table that you want to delete duplicate rows.
2. Insert distinct rows from the original table to the immediate table.
3. Insert distinct rows from the original table to the immediate table.
Step 1. Create a new table whose structure is the same as the original table:
CREATE TABLE source_copy LIKE source;
Step 2. Insert distinct rows from the original table to the new table:
INSERT INTO source_copy
SELECT * FROM source
GROUP BY col; -- column that has duplicate values
Step 3. drop the original table and rename the immediate table to the original one
DROP TABLE source;
ALTER TABLE source_copy RENAME TO source;
Source: http://www.mysqltutorial.org/mysql-delete-duplicate-rows/
Please see the below way of deletion too.
Declare #table table
(col1 varchar(10),col2 int,col3 int, col4 int, col5 int, col6 int, col7 int)
Insert into #table values
('john',1,1,1,1,1,1),
('john',1,1,1,1,1,1),
('sally',2,2,2,2,2,2),
('sally',2,2,2,2,2,2)
Created a sample table named #table and loaded it with given data.
Delete aliasName from (
Select *,
ROW_NUMBER() over (Partition by col1,col2,col3,col4,col5,col6,col7 order by col1) as rowNumber
From #table) aliasName
Where rowNumber > 1
Select * from #table
Note: If you are giving all columns in the Partition by part, then order by do not have much significance.
I know, the question is asked three years ago, and my answer is another version of what Tim has posted, But posting just incase it is helpful for anyone.
It can be done by many ways in sql server
the most simplest way to do so is:
Insert the distinct rows from the duplicate rows table to new temporary table. Then delete all the data from duplicate rows table then insert all data from temporary table which has no duplicates as shown below.
select distinct * into #tmp From table
delete from table
insert into table
select * from #tmp drop table #tmp
select * from table
Delete duplicate rows using Common Table Expression(CTE)
With CTE_Duplicates as
(select id,name , row_number()
over(partition by id,name order by id,name ) rownumber from table )
delete from CTE_Duplicates where rownumber!=1
To delete the duplicate rows from the table in SQL Server, you follow these steps:
Find duplicate rows using GROUP BY clause or ROW_NUMBER() function.
Use DELETE statement to remove the duplicate rows.
Setting up a sample table
DROP TABLE IF EXISTS contacts;
CREATE TABLE contacts(
contact_id INT IDENTITY(1,1) PRIMARY KEY,
first_name NVARCHAR(100) NOT NULL,
last_name NVARCHAR(100) NOT NULL,
email NVARCHAR(255) NOT NULL,
);
Insert values
INSERT INTO contacts
(first_name,last_name,email)
VALUES
('Syed','Abbas','syed.abbas#example.com'),
('Catherine','Abel','catherine.abel#example.com'),
('Kim','Abercrombie','kim.abercrombie#example.com'),
('Kim','Abercrombie','kim.abercrombie#example.com'),
('Kim','Abercrombie','kim.abercrombie#example.com'),
('Hazem','Abolrous','hazem.abolrous#example.com'),
('Hazem','Abolrous','hazem.abolrous#example.com'),
('Humberto','Acevedo','humberto.acevedo#example.com'),
('Humberto','Acevedo','humberto.acevedo#example.com'),
('Pilar','Ackerman','pilar.ackerman#example.com');
Query
SELECT
contact_id,
first_name,
last_name,
email
FROM
contacts;
Delete duplicate rows from a table
WITH cte AS (
SELECT
contact_id,
first_name,
last_name,
email,
ROW_NUMBER() OVER (
PARTITION BY
first_name,
last_name,
email
ORDER BY
first_name,
last_name,
email
) row_num
FROM
contacts
)
DELETE FROM cte
WHERE row_num > 1;
Should delete the record now
Try to Use:
SELECT linkorder
,Row_Number() OVER (
PARTITION BY linkorder ORDER BY linkorder DESC
) AS RowNum
FROM u_links
Microsoft has a vey ry neat guide on how to remove duplicates. Check out http://support.microsoft.com/kb/139444
In brief, here is the easiest way to delete duplicates when you have just a few rows to delete:
SET rowcount 1;
DELETE FROM t1 WHERE myprimarykey=1;
myprimarykey is the identifier for the row.
I set rowcount to 1 because I only had two rows that were duplicated. If I had had 3 rows duplicated then I would have set rowcount to 2 so that it deletes the first two that it sees and only leaves one in table t1.
with myCTE
as
(
select productName,ROW_NUMBER() over(PARTITION BY productName order by slno) as Duplicate from productDetails
)
Delete from myCTE where Duplicate>1
After trying the suggested solution above, that works for small medium tables.
I can suggest that solution for very large tables. since it runs in iterations.
Drop all dependency views of the LargeSourceTable
you can find the dependecies by using sql managment studio, right click on the table and click "View Dependencies"
Rename the table:
sp_rename 'LargeSourceTable', 'LargeSourceTable_Temp'; GO
Create the LargeSourceTable again, but now, add a primary key with all the columns that define the duplications add WITH (IGNORE_DUP_KEY = ON)
For example:
CREATE TABLE [dbo].[LargeSourceTable]
(
ID int IDENTITY(1,1),
[CreateDate] DATETIME CONSTRAINT [DF_LargeSourceTable_CreateDate] DEFAULT (getdate()) NOT NULL,
[Column1] CHAR (36) NOT NULL,
[Column2] NVARCHAR (100) NOT NULL,
[Column3] CHAR (36) NOT NULL,
PRIMARY KEY (Column1, Column2) WITH (IGNORE_DUP_KEY = ON)
);
GO
Create again the views that you dropped in the first place for the new created table
Now, Run the following sql script, you will see the results in 1,000,000 rows per page, you can change the row number per page to see the results more often.
Note, that I set the IDENTITY_INSERT on and off because one the columns contains auto incremental id, which I'm also copying
SET IDENTITY_INSERT LargeSourceTable ON
DECLARE #PageNumber AS INT, #RowspPage AS INT
DECLARE #TotalRows AS INT
declare #dt varchar(19)
SET #PageNumber = 0
SET #RowspPage = 1000000
select #TotalRows = count (*) from LargeSourceTable_TEMP
While ((#PageNumber - 1) * #RowspPage < #TotalRows )
Begin
begin transaction tran_inner
; with cte as
(
SELECT * FROM LargeSourceTable_TEMP ORDER BY ID
OFFSET ((#PageNumber) * #RowspPage) ROWS
FETCH NEXT #RowspPage ROWS ONLY
)
INSERT INTO LargeSourceTable
(
ID
,[CreateDate]
,[Column1]
,[Column2]
,[Column3]
)
select
ID
,[CreateDate]
,[Column1]
,[Column2]
,[Column3]
from cte
commit transaction tran_inner
PRINT 'Page: ' + convert(varchar(10), #PageNumber)
PRINT 'Transfered: ' + convert(varchar(20), #PageNumber * #RowspPage)
PRINT 'Of: ' + convert(varchar(20), #TotalRows)
SELECT #dt = convert(varchar(19), getdate(), 121)
RAISERROR('Inserted on: %s', 0, 1, #dt) WITH NOWAIT
SET #PageNumber = #PageNumber + 1
End
SET IDENTITY_INSERT LargeSourceTable OFF
-- this query will keep only one instance of a duplicate record.
;WITH cte
AS (SELECT ROW_NUMBER() OVER (PARTITION BY col1, col2, col3-- based on what? --can be multiple columns
ORDER BY ( SELECT 0)) RN
FROM Mytable)
delete FROM cte
WHERE RN > 1
You need to group by the duplicate records according to the field(s), then hold one of the records and delete the rest.
For example:
DELETE prg.Person WHERE Id IN (
SELECT dublicateRow.Id FROM
(
select MIN(Id) MinId, NationalCode
from prg.Person group by NationalCode having count(NationalCode ) > 1
) GroupSelect
JOIN prg.Person dublicateRow ON dublicateRow.NationalCode = GroupSelect.NationalCode
WHERE dublicateRow.Id <> GroupSelect.MinId)
Deleting duplicates from a huge(several millions of records) table might take long time . I suggest that you do a bulk insert into a temp table of the selected rows rather than deleting.
--REWRITING YOUR CODE(TAKE NOTE OF THE 3RD LINE) WITH CTE AS(SELECT NAME,ROW_NUMBER()
OVER (PARTITION BY NAME ORDER BY NAME) ID FROM #TB) SELECT * INTO #unique_records FROM
CTE WHERE ID =1;
This might help in your case
DELETE t1 FROM table t1 INNER JOIN table t2 WHERE t1.id > t2.id AND t1.col1 = t2.col1
With reference to https://support.microsoft.com/en-us/help/139444/how-to-remove-duplicate-rows-from-a-table-in-sql-server
The idea of removing duplicate involves
a) Protecting those rows that are not duplicate
b) Retain one of the many rows that qualified together as duplicate.
Step-by-step
1) First identify the rows those satisfy the definition of duplicate
and insert them into temp table, say #tableAll .
2) Select non-duplicate(single-rows) or distinct rows into temp table
say #tableUnique.
3) Delete from source table joining #tableAll to delete the
duplicates.
4) Insert into source table all the rows from #tableUnique.
5) Drop #tableAll and #tableUnique
If you have the ability to add a column to the table temporarily, this was a solution that worked for me:
ALTER TABLE dbo.DUPPEDTABLE ADD RowID INT NOT NULL IDENTITY(1,1)
Then perform a DELETE using a combination of MIN and GROUP BY
DELETE b
FROM dbo.DUPPEDTABLE b
WHERE b.RowID NOT IN (
SELECT MIN(RowID) AS RowID
FROM dbo.DUPPEDTABLE a WITH (NOLOCK)
GROUP BY a.ITEM_NUMBER,
a.CHARACTERISTIC,
a.INTVALUE,
a.FLOATVALUE,
a.STRINGVALUE
);
Verify that the DELETE performed correctly:
SELECT a.ITEM_NUMBER,
a.CHARACTERISTIC,
a.INTVALUE,
a.FLOATVALUE,
a.STRINGVALUE, COUNT(*)--MIN(RowID) AS RowID
FROM dbo.DUPPEDTABLE a WITH (NOLOCK)
GROUP BY a.ITEM_NUMBER,
a.CHARACTERISTIC,
a.INTVALUE,
a.FLOATVALUE,
a.STRINGVALUE
ORDER BY COUNT(*) DESC
The result should have no rows with a count greater than 1. Finally, remove the rowid column:
ALTER TABLE dbo.DUPPEDTABLE DROP COLUMN RowID;
Oh wow, i feel so stupid by ready all this answers, they are like experts' answer with all CTE and temp table and etc.
And all I did to get it working was simply aggregated the ID column by using MAX.
DELETE FROM table WHERE col1 IN (
SELECT MAX(id) FROM table GROUP BY id HAVING ( COUNT(col1) > 1 )
)
NOTE: you might need to run it multiple time to remove duplicate as this will only delete one set of duplicate rows at a time.
please simply add the keyword DISTINCT right after the SELECT command,
for example:
SELECT DISTICNT ColumnOne, ColumnTwo, ColumnThree
FROM YourTable
Another way of removing dublicated rows without loosing information in one step is like following:
delete from dublicated_table t1 (nolock)
join (
select t2.dublicated_field
, min(len(t2.field_kept)) as min_field_kept
from dublicated_table t2 (nolock)
group by t2.dublicated_field having COUNT(*)>1
) t3
on t1.dublicated_field=t3.dublicated_field
and len(t1.field_kept)=t3.min_field_kept
DECLARE #TB TABLE(NAME VARCHAR(100));
INSERT INTO #TB VALUES ('Red'),('Red'),('Green'),('Blue'),('White'),('White')
--**Delete by Rank**
;WITH CTE AS(SELECT NAME,DENSE_RANK() OVER (PARTITION BY NAME ORDER BY NEWID()) ID FROM #TB)
DELETE FROM CTE WHERE ID>1
SELECT NAME FROM #TB;
--**Delete by Row Number**
;WITH CTE AS(SELECT NAME,ROW_NUMBER() OVER (PARTITION BY NAME ORDER BY NAME) ID FROM #TB)
DELETE FROM CTE WHERE ID>1;
SELECT NAME FROM #TB;
DELETE FROM TBL1 WHERE ID IN
(SELECT ID FROM TBL1 a WHERE ID!=
(select MAX(ID) from TBL1 where DUPVAL=a.DUPVAL
group by DUPVAL
having count(DUPVAL)>1))
DELETE p1 FROM Person p1,
Person p2
WHERE
p1.Email = p2.Email AND p1.Id > p2.Id

Order by first row,last row and rest with 2 tables in SQL Server 2017

I have following two tables. I need to merge 2 tables based also sorted on
few conditions.
DROP TABLE IF EXISTS #t1
CREATE TABLE #t1
(
id INT IDENTITY PRIMARY KEY,
value INT
)
DROP TABLE IF EXISTS #t2
CREATE TABLE #t2
(
id INT IDENTITY PRIMARY KEY,
value int
)
INSERT INTO #t1 (value)
VALUES (1), (30), (19), (10), (40);
INSERT INTO #t2 (value)
VALUES (100), (70), (20);
SELECT * FROM #t1
UNION
SELECT * FROM #t2
I need to union 2 tables and sorted value based on below condition
#t1 first row (fixed)
#t1 last row (fixed)
#t1 rest (other than first row) based on value
4 #t2 only sorted based on value
Expected output:
why are you using varchar to store numeric value ? you will need to perform a cast() or convert() before you will be to sort it.
Assumption : by first or last you are referring with row with minimum and maximum value in column id.
select value, seq as [order]
from
(
select id, value,
seq = case when row_number() over(order by id) = 1 then 1
when row_number() over(order by id desc) = 1 then 2
else 3
end
from #t1
union all
select id, value, seq = 4
from #t2
) d
order by seq, convert(int, value)
You can check this below logic of ordering the output using CASE statement in the ORDER clause-
SELECT *
FROM
(
select 'T1' T_Name,* from #t1
union
select 'T2',* from #t2
)A
ORDER BY
CASE
WHEN t_name = 'T1' AND id = (SELECT MIN(ID) FROM #t1) THEN 1
WHEN t_name = 'T2' AND id = (SELECT MAX(ID) FROM #t2) THEN 2
WHEN t_name = 'T1' THEN 3
ELSE 4
END,
Id -- Or you can order by Value. Just keep in mind that Value is VARCHAR as per your setup. So, Ordering will be also impact accordingly.

row number without using the ROW_NUMBER window function

Suppose you have a table with non-unique values such as this:
CREATE TABLE accounts ( fname VARCHAR(20), lname VARCHAR(20))
GO
INSERT accounts VALUES ('Fred', 'Flintstone')
INSERT accounts VALUES ('Fred', 'Flintstone')
INSERT accounts VALUES ('Fred', 'Flintstone')
SELECT * FROM accounts
GO
Now using a ROW_NUMBER function, you can get a unique incrementing row number.
select *, ROW_NUMBER() over(order by (select null)) as rn
from accounts
But how do we this without using a ROW_NUMBER function. I tried giving each row a unique ID using NEWID() and then counting the rows as given below but it did not work as it gives me a non-unique number which does not start with 1.
Note that I do not want to alter the table to add a new column.
;with cte as
(select *
from accounts as e
cross apply (select newid()) as a(id)
)
select *, (select count(*)+1 from cte as c1 where c.id > c1.id) as rn
from cte as c
order by rn
SQL Fiddle for toying around is http://sqlfiddle.com/#!18/c270f/3/0
The following demonstrates why your code fails, but does not provide an alternative to Row_Number().
A column, TopId, is added to the final select that should get the minimum value generated by NewId() and report it in every row. Instead, a new value is generated for each row.
-- Sample data.
declare #Samples as Table ( FName VarChar(20), LName VarChar(20) );
insert into #Samples ( FName, LName ) values
( 'Fred', 'Flintstone' ), ( 'Fred', 'Flintstone' ), ( 'Fred', 'Flintstone' );
select * from #Samples;
-- Cross apply NewId() in a CTE.
;with cte as
( select *
from #Samples as S
cross apply ( select NewId() ) as Ph( Id ) )
select *, ( select count(*) from cte as c1 where c1.Id >= c.Id ) as RN,
-- The following column should output the minimum Id value from the table for every row.
-- Instead, it generates a new unique identifier for each row.
( select top 1 id from cte order by id ) as TopId
from cte as c
order by RN;
The execution plan shows that the CTE is treated as a view that is being evaluated repeatedly, thus generating conflicting Id values.
How about this:
SELECT
src.*,
SUM(DummyVal) OVER(ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW) AS RowId
FROM (
SELECT a.*, 1 AS DummyVal
FROM MyTable a
) src
It's still a window function, though, not sure if that matters.
Fiddle me this
You can create an function yourself to compute the row_number,
In this example, I had to calculate an index for a lesson within a course.
Window Function version:
SELECT *, ROW_NUMBER() OVER(PARTITION BY courseId) AS row_num FROM lessons;
I created helper-function, to compute the row_number without window function:
DELIMITER $$
CREATE FUNCTION getRowNumber (lessonId int, courseId int)
RETURNS int
DETERMINISTIC
BEGIN
DECLARE count int;
select count(l2.id) into count from lessons l2 where l2.courseId=courseId
and l2.id<=lessonId;
RETURN count;
END$$
DELIMITER ;
so, the final query is:
SELECT l.*, getRowNumber(l.id,l.courseId) as row_num FROM lessons l;
got the same result as the first query!
MySQL:
SELECT #rownum := #rownum + 1 AS rank, a.*
FROM accounts a,(SELECT #rownum := 0) r;
In ORACLE it would simply be
SELECT ROWNUM, a.*
FROM accounts a;
Both without window

SQL update column with random numbers from set list of values

I have a table that gets rewritten each night. I have two columns that need to be populated with a random number from a set list of values. Angle column needs to be populated with 15,30,45,60,90 and Distance needs to populated with 9,15,21. The insert statements may process up to 700 records.
I have tried creating a temp table (#MyRandomVal1) with
select 15 union
select 30 union
select 45 etc...
Then use (select top 1 val from #MyRandomVal1 order by newid()). This populates the column with the same random number for all rows. It seems that I might need to loop through the inserted rows so it runs (select top 1 val from #MyRandomVal1 order by newid()) for each row, however in my research I have read that Loops are not recommended. Is there another method for populating 700+ rows with a random sampling from a set list during an insert?
Below is my existing code (for angle only). SQL Server 2012.
DECLARE #MyRandomVal1 Table (
id int identity (1,1),
val int not null)
INSERT INTO #MyRandomVal1 (val)
SELECT 15
union
SELECT 30
union
SELECT 45
union
SELECT 60
union
SELECT 90
INSERT INTO MyTable (AUTO_KEY,E3_KEY,EMPID,ENAME,COLOR,ANGLE)
SELECT dbo.getautokey(),dbo.GetAutoKey(),[EMPID],[ENAME],abs(checksum(NewId()) % 256),(select top 1 val from #MyRandomVal1 order by newid())
FROM MyTable2 WHERE [JOBLEVEL]='SVP'
Thanks.
One way to do it is with a cte. Join your #MyRandomVal1 to MyTable2 on true. Add a row number that is ordered by newid(). Then get all the rownumber 1's. You'll want to check the logic in the PARTITION BY. I didn't know if there was a column that was unique. If not you may have to partition by all columns since we are joining each row to every row in the random value table.
DECLARE #MyRandomVal1 Table (
id int identity (1,1),
val int not null)
INSERT INTO #MyRandomVal1 (val)
SELECT 15
union
SELECT 30
union
SELECT 45
union
SELECT 60
union
SELECT 90
;WITH cte AS (
SELECT
dbo.getautokey() AS AUTO_KEY
, dbo.GetAutoKey() AS E3_KEY
, [EMPID]
, [ENAME]
, ABS(checksum(NewId()) % 256) AS COLOR
, a.val
, ROW_NUMBER() OVER (PARTITION BY empid ORDER BY NEWID()) AS rn
FROM MyTable2
JOIN #MyRandomVal1 a ON 1 = 1
WHERE [JOBLEVEL]='SVP')
INSERT INTO MyTable (AUTO_KEY, E3_KEY, EMPID,ENAME, COLOR, ANGLE)
SELECT * FROM cte
WHERE rn = 1
Here's a simple DEMO since we don't have example data.

SQL Server: How do I get the highest value not set of an int column?

Let's take an example. These are the rows of the table I want get the data:
The column I'm talking about is the reference one. The user can set this value on the web form, but the system I'm developing must suggest the lowest reference value still not used.
As you can see, the smallest value of this column is 35. I could just take the smaller reference and sum 1, but, in that case, the value 36 is already used. So, the value I want is 37.
Is there a way to do this without a loop verification? This table will grow so much.
This is for 2012+
DECLARE #Tbl TABLE (id int, reference int)
INSERT INTO #Tbl
( id, reference )
VALUES
(1, 49),
(2, 125),
(3, 35),
(4, 1345),
(5, 36),
(6, 37)
SELECT
MIN(A.reference) + 1 Result
FROM
(
SELECT
*,
LEAD(reference) OVER (ORDER BY reference) Tmp
FROM
#Tbl
) A
WHERE
A.reference - A.Tmp != -1
Result: 37
Here is yet another place where the tally table is going to prove invaluable. In fact it is so useful I keep a view on my system that looks like this.
create View [dbo].[cteTally] as
WITH
E1(N) AS (select 1 from (values (1),(1),(1),(1),(1),(1),(1),(1),(1),(1))dt(n)),
E2(N) AS (SELECT 1 FROM E1 a cross join E1 b), --10E+2 or 100 rows
E4(N) AS (SELECT 1 FROM E2 a cross join E2 b), --10E+4 or 10,000 rows max
cteTally(N) AS
(
SELECT ROW_NUMBER() OVER (ORDER BY (SELECT NULL)) FROM E4
)
select N from cteTally
Next of course we need some sample data and table to hold it.
create table #Something
(
id int identity
, reference int
, description varchar(10)
)
insert #Something (reference, description)
values (49, 'data1')
, (125, 'data2')
, (35, 'data3')
, (1345, 'data4')
, (36, 'data5')
, (7784, 'data6')
Now comes the magic of the tally table.
select top 1 t.N
from cteTally t
left join #Something s on t.N = s.reference
where t.N >= (select MIN(reference) from #Something)
and s.id is null
order by t.N
This is ugly, but should get the job done:
select
top 1 reference+1
from
[table]
where
reference+1 not in (select reference from [table])
order by reference
I used a table valued express to get the next value. I first left outer joined the table to itself (shifting the key in the join by +1). I then looked only at rows that had no corresponding match (b.ID is null). The minimum a.ReferenceID + 1 gives us the answer we are looking for.
create table MyTable
(
ID int identity,
Reference int,
Description varchar(20)
)
insert into MyTable values (10,'Data')
insert into MyTable values (11,'Data')
insert into MyTable values (12,'Data')
insert into MyTable values (15,'Data')
-- Find gap
;with Gaps as
(
select a.Reference+1 as 'GapID'
from MyTable a
left join MyTable b on a.Reference = b.Reference-1
where b.ID is null
)
select min(GapID) as 'NewReference'
from Gaps
NewReference
------------
13
I hope the code was clearer than my description.
CREATE TABLE #T(ID INT , REFERENCE INT, [DESCRIPTION] VARCHAR(50))
INSERT INTO #T
SELECT 1,49 , 'data1' UNION ALL
SELECT 2,125 , 'data2' UNION ALL
SELECT 3,35 , 'data3' UNION ALL
SELECT 4,1345, 'data4' UNION ALL
SELECT 5,36 , 'data5' UNION ALL
SELECT 6,7784, 'data6'
SELECT TOP 1 REFERENCE + 1
FROM #T T1
WHERE
NOT EXISTS
(
SELECT 1 FROM #T T2 WHERE T2.REFERENCE = T1.REFERENCE + 1
)
ORDER BY T1.REFERENCE
--- OR
SELECT MIN(REFERENCE) + 1
FROM #T T1
WHERE
NOT EXISTS
(
SELECT 1 FROM #T T2 WHERE T2.REFERENCE = T1.REFERENCE + 1
)
How about using a Tally table. The following illustrates the concept. It would be better to use a persisted numbers table as opposed to the cte however the code below illustrates the concept.
For further reading as to why you should use a persisted table, check out the following link: sql-auxiliary-table-of-numbers
DECLARE #START int = 1, #END int = 1000
CREATE TABLE #TEST(UsedValues INT)
INSERT INTO #TEST(UsedValues) VALUES
(1),(3),(5),(7),(9),(11),(13),(15),(17)
;With NumberSequence( Number ) as
(
Select #start as Number
union all
Select Number + 1
from NumberSequence
where Number < #end
)
SELECT MIN(Number)
FROM NumberSequence n
LEFT JOIN #TEST t
ON n.Number = t.UsedValues
WHERE UsedValues IS NULL
OPTION ( MAXRECURSION 1000 )
You could try using a descending order:
SELECT DISTINCT reference
FROM `Resultsados`
ORDER BY `reference` ASC;
As far as I know, there is no way to do this without a loop. To prevent multiple values from returning be sure to use DISTINCT.

Resources