SQL - query for combining multiple rows - sql

I'm searching but i can't find a solution for my problem.
I've a table (say T1) with this data:
SampleCode
Name
Content
#
1
A#
#
2
B#
#
3
C#
#
1
A#
#
2
B#
#
3
C#
So i need a select query resulting in :
Column 1
Column 2
Column 3
SampleCode
#
#
Name.1
A#
A#
Name.2
B#
B#
Name.3
C#
C#
Does anyone has an hint?
Thanks
Fabio

Check out the 2 options in this article: https://www.sqlshack.com/multiple-options-to-transposing-rows-into-columns/
If using TSQL, you could use a TRANSPOSE statement. Or you can create the result set using cursors/loops and dynamic SQL.
Fully Dynamic Solution
I can't believe I hammered this out... maybe I did it just to see if I could. It's long and complicated and uses several loops. I think you should re-evaluate what you're trying to do. This can't be run in a view. You would have to put into a function or stored procedure. You may want to evaluate the temp table names to see if they are compatible with your environment. Also, since the temp table name are not unique, you cannot run multiple instances; if you want to run multiple instances, you would have to add a unique identifier to a column in the temp tables or to temp table names. This is fully dynamic... you don't have to know how many columns you need ahead of time.
--**************************************************
--Header area... sample data and temp tables.
--**************************************************
--Clean up sample and result tables if they exist.
IF OBJECT_ID(N'tempdb..#T1') IS NOT NULL
DROP TABLE #T1;
IF OBJECT_ID(N'tempdb..#ResultsTemp') IS NOT NULL
DROP TABLE #ResultsTemp;
IF OBJECT_ID(N'tempdb..#codeTable') IS NOT NULL
DROP TABLE #codeTable;
--For Debugging.
DECLARE #debug int = 1; --0=no debug, 1=show debug messages, do not exec all SQL statements.
--Table var to hold sample data.
CREATE TABLE #T1 (
SampleCode nvarchar(50),
[Name] nvarchar(50),
Content nvarchar(50),
row_num int
);
--Load Sample Data.
INSERT INTO #T1 (SampleCode, [Name], Content)
VALUES
('#', '1', 'A#')
, ('#', '2', 'B#')
, ('#', '3', 'C#')
, ('#', '1', 'A#')
, ('#', '2', 'B#')
, ('#', '3', 'C#')
;
--**********END HEADER**********
--Number the rows so we can loop over them.
UPDATE #T1
SET row_num = newT1.row_num
FROM
(
SELECT t12.SampleCode
, t12.[Name]
, T12.Content
, ROW_NUMBER()OVER(ORDER BY SampleCode, [Name], Content) as row_num
FROM #T1 as t12
) AS newT1
WHERE #T1.SampleCode = newT1.SampleCode
AND #T1.[Name] = newT1.[Name]
AND #T1.Content = newT1.Content
;
SELECT * FROM #T1; --Debugging... just show the contents of #T1 after adding row_num
--Create temp table to load results.
CREATE TABLE #ResultsTemp (
Column1 nvarchar(50)
);
--Create some variable to track looping (without a cursor).
DECLARE #loopCount int = 1;
DECLARE #maxLoops int = (SELECT COUNT(DISTINCT SampleCode) FROM #T1);
DECLARE #sql nvarchar(512);
--Add columns to #ResultsTable dynamically
WHILE (#loopCount <= (#maxLoops))
BEGIN
SET #sql = 'ALTER TABLE #ResultsTemp ADD ' + QUOTENAME('Column' + CAST((#loopCount + 1) as nvarchar)) + ' nvarchar(50) NULL';
IF (#debug = 1) PRINT #sql;
EXEC (#sql);
SET #loopCount = #loopCount + 1;
END
--************************************************************
--SECTION FOR INSERTING FIRST ROW for "SampleCode"
--************************************************************
--Vars for tracking the SampleCode variations processed.
DECLARE #sampleLoop int = 1;
DECLARE #sampleCount int = (SELECT COUNT(DISTINCT SampleCode) FROM #T1);
CREATE TABLE #codeTable (
SampleCode nvarchar(50)
, row_num int
);
--Create a list of unique SampleCodes to loop over.
INSERT INTO #codeTable (SampleCode)
SELECT DISTINCT
SampleCode
FROM #T1;
UPDATE #codeTable
SET row_num = newCT.row_num
FROM
(
SELECT ct2.SampleCode
, ROW_NUMBER()OVER(ORDER BY SampleCode) as row_num
FROM #codeTable as ct2
) AS newCT
WHERE #codeTable.SampleCode = newCT.SampleCode
;
SET #sql = 'INSERT INTO #ResultsTemp (Column1) SELECT ''SampleCode''';
IF (#debug = 1) PRINT #sql;
EXEC (#sql);
WHILE (#sampleLoop <= #sampleCount)
BEGIN
SET #sql = 'UPDATE #ResultsTemp SET Column' + CAST(#SampleLoop + 1 as nvarchar) + '=(SELECT TOP 1 SampleCode FROM #codeTable WHERE row_num = ' + CAST(#sampleLoop as nvarchar) + ');';
IF (#debug = 1) PRINT #sql;
EXEC (#sql);
SET #sampleLoop = #sampleLoop + 1;
END
IF (#debug = 1) SELECT * FROM #ResultsTemp;
--**********END SECTION**********
--**************************************************
--SECTION FOR INSERTING THE REST OF THE CONTENT DATA
--**************************************************
--Vars for tracking number of rows processed from T1.
SET #loopCount = 1;
SET #maxLoops = (SELECT MAX(row_num) FROM #T1);
--Loop over each row in T1.
WHILE (#loopCount <= #maxLoops)
BEGIN
--Create a name for this row.
DECLARE #nameRaw nvarchar(50) = (SELECT TOP 1 [Name] FROM #T1 WHERE row_num = #loopCount);
DECLARE #codeNum nvarchar(50) = (
SELECT TOP 1 ct.row_num
FROM #T1 as t
INNER JOIN #codeTable as ct
ON ct.SampleCode = t.SampleCode
WHERE t.row_num = #loopCount);
DECLARE #name nvarchar(50) = 'Name.' + #nameRaw;
--First insert a row for this Name... if not already in the list.
SET #sql = 'INSERT INTO #ResultsTemp (Column1)
SELECT ''Name.'' + t.[Name]
FROM #T1 as t
LEFT OUTER JOIN #ResultsTemp as rt
ON rt.Column1 = ''' + #name + '''
WHERE t.row_num = ' + CAST(#loopCount as nvarchar) + '
AND rt.Column1 IS NULL;';
IF (#debug = 1) PRINT #sql;
EXEC (#sql);
--Update this Name row with the "content".
SET #sql = 'UPDATE rt
SET Column' + CAST(#codeNum + 1 as nvarchar) + '=t.Content
FROM #ResultsTemp as rt
INNER JOIN #T1 as t
ON t.row_num = ' + CAST(#loopCount as nvarchar) + '
AND t.[Name] = ''' + #nameRaw + '''
WHERE rt.Column1 = ''' + #name + ''';';
IF (#debug = 1) PRINT #sql;
EXEC (#sql);
SET #loopCount = #loopCount + 1;
END
--Show everything in the temp Results table.
SELECT *
FROM #ResultsTemp;
Result Set:
Static Select Solution
This next option is not dynamic. You have to know how many columns you need and then you can copy the "Column3" code to any new columns. You have to change the column name and update the "Select TOP 1" statement as commented for each new column you would copy.
WITH CodeTable AS (
SELECT DISTINCT t.SampleCode
FROM #T1 as t
)
SELECT DISTINCT
'Name.' + [Name]
, (
SELECT TOP 1 Content
FROM #T1 as t2
WHERE t2.SampleCode = (
SELECT TOP 1 SampleCode
FROM CodeTable as ct
ORDER BY SampleCode
)
AND t2.[Name] = t.[Name]
) as Column2
, (
SELECT TOP 1 Content
FROM #T1 as t2
WHERE t2.SampleCode = (
SELECT TOP 1 SampleCode
FROM CodeTable as ct
WHERE ct.SampleCode NOT IN (
SELECT TOP 1 SampleCode --Update the TOP 1 to be TOP [number of previous columns]
FROM CodeTable as ct2
ORDER BY ct2.SampleCode
)
ORDER BY ct.SampleCode
)
AND t2.[Name] = t.[Name]
) as Column3
FROM #T1 as t
Static PivotTable Solution
This solution is from the link I posted. Again, you have to know the number of columns you need and it doesn't have generic column names like you specify. But, it is another solution if you reconsider your output.
--Use PivotTable.
SELECT *
FROM
(
SELECT [Name], Content
FROM #T1
) AS SourceTable PIVOT(MAX(Content) FOR [Content] IN([A#],
[A#]
)) AS PivotTable;

Pivot table can solve your prooblem:
DECLARE #T TABLE (SampleCode sysname, Name sysname, Content sysname)
INSERT #T (SampleCode, Name, Content)
VALUES
('#', '1', 'A#'),
('#', '2', 'B#'),
('#', '3', 'C#'),
('#', '1', 'A#'),
('#', '2', 'B#'),
('#', '3', 'C#')
SELECT CONCAT('Name.', PIVOTTABLE.Name), [#], [#]
FROM
(
SELECT * FROM #T AS t
) AS SOURCE
PIVOT (
MAX(Content)
FOR SampleCode IN ([#], [#])
) AS PIVOTTABLE
Of course this is the solution for what you provided in the question.
When the columns are too many to manually write down then use Dynamic query and the only parts needed to be generate is the values in FOR expression and the same value in SELECT

Related

SQL Loop through tables and columns to find which columns are NOT empty

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

T-SQL Pivot Row to Column

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).

Divide using formula from different table in sql

I need to evaluate a formula in sql server 2008
Table 1 contains
Entity Value
A 2424053.500000
B 1151425.412500
C 484810.700000
Table 2 contains
Entity Formula
A (2100*(1-0.0668)*24*mday*10)
B (1000*(1-0.0575)*24*mday*10)
C (1260*(1-0.09)*24*mday*10)
Where mday is number of days taken from user. Data type of Formula is a string.
I need to calculate the output of value/formula for each entity
can you provide me the query for the same
Example solution for SQL Server 2008, adjust as required...
IF EXISTS (SELECT * FROM sys.tables WHERE object_id = object_id('EntityValue'))
BEGIN
DROP TABLE EntityValue;
END;
CREATE TABLE EntityValue
(
Id CHAR(1),
mdayValue DECIMAL(13, 6)
)
INSERT INTO EntityValue
VALUES ('1', 2424053.500000)
, ('2', 1151425.412500)
, ('3', 484810.700000)
IF EXISTS (SELECT * FROM sys.tables WHERE object_id = object_id('EntityFormula'))
BEGIN
DROP TABLE EntityFormula;
END;
CREATE TABLE EntityFormula
(
Id CHAR(1),
Formula NVARCHAR(MAX)
)
INSERT INTO EntityFormula
VALUES ('1', '(2100*(1-0.0668)*24*mday*10)')
, ('2', '(1000*(1-0.0575)*24*mday*10)')
, ('3', '(1260*(1-0.09)*24*mday*10)')
DECLARE #FormulaTable AS TABLE
(
RowId INT IDENTITY(1,1)
,Formula NVarchar(max)
);
INSERT INTO #FormulaTable (Formula)
SELECT Formula = REPLACE(eFormula.Formula, 'mday', CAST(eValue.mdayValue AS NVARCHAR(MAX)))
FROM EntityFormula AS eFormula
INNER JOIN EntityValue AS eValue ON eValue.ID = eFormula.ID;
DECLARE #TSql NVarchar(max), #CurrentRowId INT;
SET #CurrentRowId = 1;
WHILE(1=1)
BEGIN
SELECT #TSql = 'SELECT ' + Formula
FROM #FormulaTable
WHERE RowID = #CurrentRowId
IF(##ROWCOUNT = 0)
BEGIN
BREAK;
END
EXEC sp_executesql #Tsql
SET #CurrentRowId = #CurrentRowId + 1;
END

Delete Duplicate Records with Same Values

I have a TSQL statement that is taking several hours to run. I'm sure I need to look into the import process to avoid duplicates being inserted but for the time being I'd just like to remove all records except one with duplicate values. ParameterValueId is the primary key on the table but I have many duplicate entries that need to be deleted. I only need one record for each ParameterId, SiteId, MeasurementDateTime, and ParameterValue. Below is my current method for deleting duplicate records. It finds all values that have a count > 1. It then finds the first Id with those values and deletes all of the records with those values that don't match the first ID found by those values. Besides the print statements is there a more efficient way of doing this. Can I do a way with the cursor at all to improve performance?
BEGIN TRANSACTION
SET NOCOUNT ON
DECLARE #BeginningRecordCount INT
SET #BeginningRecordCount =
(
SELECT COUNT(*)
FROM ParameterValues
)
DECLARE #ParameterId UNIQUEIDENTIFIER
DECLARE #SiteId UNIQUEIDENTIFIER
DECLARE #MeasurementDateTime DATETIME
DECLARE #ParameterValue FLOAT
DECLARE CDuplicateValues CURSOR FOR
SELECT
[ParameterId]
,[SiteId]
,[MeasurementDateTime]
,[ParameterValue]
FROM [ParameterValues]
GROUP BY
[ParameterId]
,[SiteId]
,[MeasurementDateTime]
,[ParameterValue]
HAVING COUNT(*) > 1
OPEN CDuplicateValues
FETCH NEXT FROM CDuplicateValues INTO
#ParameterId
,#SiteId
,#MeasurementDateTime
,#ParameterValue
DECLARE #FirstParameterValueId UNIQUEIDENTIFIER
DECLARE #DuplicateRecordsDeleting INT
WHILE ##FETCH_STATUS <> -1
BEGIN
SET #FirstParameterValueId =
(
SELECT TOP 1 ParameterValueId
FROM ParameterValues
WHERE
ParameterId = #ParameterId
AND SiteId = #SiteId
AND MeasurementDateTime = #MeasurementDateTime
AND ParameterValue = #ParameterValue
)
SET #DuplicateRecordsDeleting =
(
SELECT COUNT(*)
FROM ParameterValues
WHERE
ParameterId = #ParameterId
AND SiteId = #SiteId
AND MeasurementDateTime = #MeasurementDateTime
AND ParameterValue = #ParameterValue
AND ParameterValueId <> #FirstParameterValueId
)
PRINT 'DELETING ' + CAST(#DuplicateRecordsDeleting AS NVARCHAR(50))
+ ' records with values ParameterId : ' + CAST(#ParameterId AS NVARCHAR(50))
+ ', SiteId : ' + CAST (#SiteId AS NVARCHAR(50))
+ ', MeasurementDateTime : ' + CAST(#MeasurementDateTime AS NVARCHAR(50))
+ ', ParameterValue : ' + CAST(#ParameterValue AS NVARCHAR(50))
DELETE FROM ParameterValues
WHERE
ParameterId = #ParameterId
AND SiteId = #SiteId
AND MeasurementDateTime = #MeasurementDateTime
AND ParameterValue = #ParameterValue
AND ParameterValueId <> #FirstParameterValueId
FETCH NEXT FROM CDuplicateValues INTO
#ParameterId
,#SiteId
,#MeasurementDateTime
,#ParameterValue
END
CLOSE CDuplicateValues
DEALLOCATE CDuplicateValues
DECLARE #EndingRecordCount INT
SET #EndingRecordCount =
(
SELECT COUNT(*)
FROM ParameterValues
)
PRINT 'Beginning Record Count : ' + CAST(#BeginningRecordCount AS NVARCHAR(50))
PRINT 'Ending Record Count : ' + CAST(#EndingRecordCount AS NVARCHAR(50))
PRINT 'Total Records Deleted : ' + CAST((#BeginningRecordCount - #EndingRecordCount) AS NVARCHAR(50))
SET NOCOUNT OFF
PRINT 'RUN THE COMMIT OR ROLLBACK STATEMENT AFTER VERIFYING DATA.'
--COMMIT
--ROLLBACK
Use option with CTE and OVER clause. OUTPUT.. INTO clause saves the information from rows affected by an DELETE statement into #delParameterValues table. Further, in the body of procedure, you can use this table to print the affected rows.
DECLARE #delParameterValues TABLE
(
ParameterId UNIQUEIDENTIFIER,
SiteId UNIQUEIDENTIFIER,
MeasurementDateTime DATETIME,
ParameterValue FLOAT,
DeletedRecordCount int
)
;WITH cte AS
(
SELECT *, ROW_NUMBER() OVER (PARTITION BY [ParameterId],[SiteId],[MeasurementDateTime],[ParameterValue] ORDER BY 1/0) AS rn,
COUNT(*) OVER (PARTITION BY [ParameterId],[SiteId],[MeasurementDateTime],[ParameterValue]) AS cnt
FROM [ParameterValues]
)
DELETE cte
OUTPUT DELETED.[ParameterId],
DELETED.[SiteId],
DELETED.[MeasurementDateTime],
DELETED.[ParameterValue],
DELETED.cnt INTO #delParameterValues
WHERE rn != 1
SELECT DISTINCT *
FROM #delParameterValues
Demo on SQLFiddle
you can do it in a single sql:
DELETE p FROM ParameterValues p
LEFT JOIN
(SELECT ParameterId, SiteId, MeasurementDateTime, ParameterValue, MAX(ParameterValueId) AS MAX_PARAM
FROM ParameterValues
GROUP BY ParameterId, SiteId, MeasurementDateTime, ParameterValue
) m
ON m.ParameterId = p.ParameterId
AND m.SiteId = p.SiteId
AND m.MeasurementDateTime = p.MeasurementDateTime
AND m.ParameterValue = p.ParameterValue
AND m.MAX_PARAM = p.ParameterValueId
WHERE m.ParameterId IS NULL
Of course it will not print the output, but you can still print the rows before and after

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