Dynamic SQL to generate column names? - sql

I have a query where I'm trying pivot row values into column names and currently I'm using SUM(Case...) As 'ColumnName' statements, like so:
SELECT
SKU1,
SUM(Case When Sku2=157 Then Quantity Else 0 End) As '157',
SUM(Case When Sku2=158 Then Quantity Else 0 End) As '158',
SUM(Case When Sku2=167 Then Quantity Else 0 End) As '167'
FROM
OrderDetailDeliveryReview
Group By
OrderShipToID,
DeliveryDate,
SKU1
The above query works great and gives me exactly what I need. However, I'm writing out the SUM(Case... statements by hand based on the results of the following query:
Select Distinct Sku2 From OrderDetailDeliveryReview
Is there a way, using T-SQL inside a stored procedure, that I can dynamically generate the SUM(Case... statements from the Select Distinct Sku2 From OrderDetailDeliveryReview query and then execute the resulting SQL code?

Having answered a lot of these over the years by generating dynamic pivot SQL from the metadata, have a look at these examples:
SQL Dynamic Pivot - how to order columns
SQL Server 2005 Pivot on Unknown Number of Columns
What SQL query or view will show "dynamic columns"
How do I Pivot on an XML column's attributes in T-SQL
How to apply the DRY principle to SQL Statements that Pivot Months
In your particular case (using the ANSI pivot instead of SQL Server 2005's PIVOT feature):
DECLARE #template AS varchar(max)
SET #template = 'SELECT
SKU1
{COLUMN_LIST}
FROM
OrderDetailDeliveryReview
Group By
OrderShipToID,
DeliveryDate,
SKU1
'
DECLARE #column_list AS varchar(max)
SELECT #column_list = COALESCE(#column_list, ',') + 'SUM(Case When Sku2=' + CONVERT(varchar, Sku2) + ' Then Quantity Else 0 End) As [' + CONVERT(varchar, Sku2) + '],'
FROM OrderDetailDeliveryReview
GROUP BY Sku2
ORDER BY Sku2
Set #column_list = Left(#column_list,Len(#column_list)-1)
SET #template = REPLACE(#template, '{COLUMN_LIST}', #column_list)
EXEC (#template)

I know that SO search engine is not perfect, but your question has been answered in SQL Server PIVOT Column Data.
Also see Creating cross tab queries and pivot tables in SQL.

Why do this using hard coded column names when you can pull all this dynamically from any table?
Using UNPIVOT and COALESCE, I can dynamically pull a list of columns from any table and associated column values for any record in a record listing and combine them in a list of column names with values by row. Here is the code. Just drop in your database and table name. The column/value table will be generated for you in SQL Server. Keep in mind, to get a shared column of values for the columns you want to convert to sql variant or text strings. But a great way to get a sample column list of values with matching column names and types with our while loops or cursors. Its pretty fast:
-- First get a list of all known columns in your database, dynamically...
DECLARE #COLUMNS nvarchar(max)
SELECT #COLUMNS =
CASE
WHEN A.DATA_TYPE = 'nvarchar' OR A.DATA_TYPE = 'ntext' THEN
COALESCE(#COLUMNS + ',','') + 'CAST(CONVERT(nvarchar(4000),['+A.[name]+']) AS sql_variant) AS ['+A.[name]+']'
WHEN A.DATA_TYPE = 'datetime' OR A.DATA_TYPE = 'smalldatetime' THEN
COALESCE(#COLUMNS + ',','') + 'CAST(CONVERT(nvarchar,['+A.[name]+'],101) AS sql_variant) AS ['+A.[name]+']'
ELSE
COALESCE(#COLUMNS + ',','') + 'CAST(['+A.[name]+'] AS sql_variant) AS ['+A.[name]+']'
END
FROM
(
SELECT
A.name,
C.DATA_TYPE
FROM YOURDATABASENAME.dbo.syscolumns A
INNER JOIN YOURDATABASENAME.dbo.sysobjects B ON B.id = A.id
LEFT JOIN
(
SELECT
COLUMN_NAME,
DATA_TYPE
FROM YOURDATABASENAME.INFORMATION_SCHEMA.COLUMNS
WHERE TABLE_NAME = 'YOURTABLENAME'
) C ON C.COLUMN_NAME = A.name
WHERE B.name = 'YOURTABLENAME'
AND C.DATA_TYPE <> 'timestamp'
) A
-- Test that the formatted columns list is returned...
--SELECT #COLUMNS
-- This gets a second string list of all known columns in your database, dynamically...
DECLARE #COLUMNS2 nvarchar(max)
SELECT #COLUMNS2 = COALESCE(#COLUMNS2 + ',','') + '['+A.[name]+']'
FROM
(
SELECT
A.name,
C.DATA_TYPE
FROM YOURDATABASENAME.dbo.syscolumns A
INNER JOIN YOURDATABASENAME.dbo.sysobjects B ON B.id = A.id
LEFT JOIN
(
SELECT
COLUMN_NAME,
DATA_TYPE
FROM YOURDATABASENAME.INFORMATION_SCHEMA.COLUMNS
WHERE TABLE_NAME = 'YOURTABLENAME'
) C ON C.COLUMN_NAME = A.name
WHERE B.name = 'YOURTABLENAME'
AND C.DATA_TYPE <> 'timestamp'
) A
-- Test that the formatted columns list is returned...
--SELECT #COLUMNS2
-- Now plug in the list of the dynamic columns list into an UNPIVOT to get a Column Name / Column Value list table...
DECLARE #sql nvarchar(max)
SET #sql =
'
SELECT
ColumnName,ColumnValue
FROM
(
SELECT
'+#COLUMNS+'
FROM YOURDATABASENAME.dbo.YOURTABLENAME
WHERE CHANGE_ID IN (SELECT ChangeId FROM YOURDATABASENAME.dbo.OperatorProcess WHERE OperatorProcessID = 3)
) AS SourceTable
UNPIVOT
(
ColumnValue FOR ColumnName IN ('+#COLUMNS2+')
) AS PivotTable
'
EXEC (#sql)

-- Darshankar Madhusudan i can do dynamic columnheading table easly...
--thanks
declare #incr int = 1,
#col int,
#str varchar(max),
#tblcrt varchar(max),
#insrt varchar(max),
set #tblcrt = 'DECLARE #Results table ('
set #str = ''
set #insrt = ''
select #col = max(column_id) From tempdb.sys.all_columns where object_id = object_id('tempdb.dbo.#aaa')
while #incr <= #col
BEGIN
SELECT #STR = #STR +case when #incr = 1 then '''' else ',''' end +rtrim(ltrim(NAME))+'''' FROM TEMPDB.SYS.ALL_COLUMNS WHERE OBJECT_ID = OBJECT_ID('TEMPDB.DBO.#AAA') and column_id = #incr
set #tblcrt = #tblcrt + case when #incr = 1 then '' else ',' end + 'Fld'+CAST(#incr as varchar(3)) +' varchar(50)'
set #insrt = #insrt + case when #incr = 1 then '' else ',' end + 'Fld'+CAST(#incr as varchar(3))
SET #INCR = #INCR + 1
END
set #tblcrt = #tblcrt + ')'
set #insrt = 'insert into #Results('+#insrt+') values (' + #STR +')'
set #tblcrt = #tblcrt+ ';' + #insrt + 'select * from #Results '
exec(#tblcrt)

Related

SQL count distinct or not null for each column for many columns

I need to analyze a large table with hundreds of columns. A lot of columns are unused.
To investigate I could do something like
SELECT DISTINCT Column1
FROM myTable
or
WITH C AS
(
SELECT DISTINCT Column1
FROM MyTable
)
SELECT COUNT(*)
FROM C
Then I do the same for column2 and so on. However these queries only work for one column which is time consuming and does not give overview in one glance.
Any idea how to build such investigation query for all columns in one?
You need only 1 query where you have to list all the columns of the table:
SELECT COUNT(DISTINCT Column1) column1_count,
COUNT(DISTINCT Column2) column2_count,
COUNT(DISTINCT Column3) column3_count
.....................................
FROM MyTable;
For local purposes only, you can make it dynamic like this:
Get the columns of the table
the query is created as the colleagues did and then it is executed with the EXEC()
DECLARE #columns as Table(RowId INT IDENTITY(1,1), ColumnName nVarchar(50))
DECLARE #ii int = 0
DECLARE #max int = 0
DECLARE #sqlQuery nVarchar(MAX)
INSERT INTO #columns
SELECT COLUMN_NAME
FROM INFORMATION_SCHEMA.COLUMNS
WHERE TABLE_NAME = N'Customer'
SET #sqlQuery = 'SELECT '
SELECT #max = COUNT(*) FROM #columns
WHILE #ii <= #max
BEGIN
SELECT #sqlQuery = CONCAT(#sqlQuery,'COUNT(DISTINCT ',ColumnName,') ',LOWER(ColumnName),'_count, ')
FROM #columns
WHERE RowId = #ii
SET #ii = #ii + 1
END
SELECT #sqlQuery = CONCAT(#sqlQuery,'FROM Customer')
SELECT #sqlQuery = REPLACE(#sqlQuery,', FROM',' FROM')
select #sqlQuery
EXEC (#sqlQuery)
You should flesh out your requirement a bit more. If all you want to know is if a column contains only NULLs, you'll want to check for max(ColumnName) is null
declare #sql table (id int identity(1,1), QueryString nvarchar(max))
create table ##emptyColumns (emptyColumn nvarchar(128))
declare #i int = 0
declare #iMax int
declare #runthis nvarchar(max)
insert #sql
select 'select ''' + QUOTENAME(s.name) + '.' + QUOTENAME(o.name) + quotename(c.name) + ''' as ''column''
from ' + QUOTENAME(s.name) + '.' + QUOTENAME(o.name) + '
having max(' + c.name + ') is null'
from sys.sysobjects o
inner join sys.syscolumns c on c.id = o.id
inner join sys.schemas s on s.schema_id = o.uid
where o.type = 'U'
order by s.name
, o.name
, c.colorder
select #iMax = count(*)
from #sql
print #iMax
while #i < #iMax
begin
set #i = #i + 1
select #runthis = 'insert into ##emptyColumns
' + QueryString
from #sql
where id = #i
execute sp_executesql #runthis
end
select *
from ##emptyColumns
drop table ##emptyColumns
One further option you might consider:
declare #sql nvarchar(max)
select #sql = isnull(#sql + ' union all ', '') + 'select ''' + COLUMN_NAME + ''',
sum(case when ' + COLUMN_NAME + ' is null then 1 else 0 end) as null_values,
count(distinct ' + COLUMN_NAME + ') as count_distinct
from ' + TABLE_SCHEMA + '.' + TABLE_NAME + '
'
from information_schema.columns
where TABLE_SCHEMA = 'MySchema' and TABLE_NAME = 'MyTable'
exec (#sql)
If you had very big tables with large numbers of columns and were only interested in empty columns you could look into something like checksum_agg(checksum(column_name)). It may help improve performance.
You'd need to be wary of column data types, as they are not all compatible with distinct.

how to select Columns using SQL which has data length greater than given length

I have a table with specific columns and rows. I would like to select columns which has data more than length 7.
For ex:
Table has columns
Name Address PhoneNumber
AAA AAAAAAAA 12345678
BBBBB BBBBBBB 47854
CCC FFFF 76643
Here columns 'Address ' and 'Phone Number' has data length more than 7. So it should display,
Address
PhoneNumber
as results. This is for a particular table. Here I do not know already that Address and PhoneNumber are the columns which have data greater than length 7. Only from the query result I will be able to find it.
SELECT <<all_columns>> from table where length(columns)>7 is my input requirement.
The LENGTH or LEN functions in 'Where' clause gives option to give only one specific column name
instead of LENGTH(COL_NAME) , I need option as where LENGTH(<> or something like LENGTH(*)) > 7 should be given as input.
How that can be achieved?
So HAVING is probably the clause youd want to use. Obviously, you can expand to include all columns and increase the having. see this:
SELECT
Name,
Address,
Phonenumber,
LEN(Address) AS AddyLength
FROM
yourTables
GROUP BY
Name,
Address,
Phonenumber,
HAVING
LEN(Address)>7
If you can live with the results in columns rather than rows:
select (case when max(length(name)) > 7 then 'Name;' else '' end) ||
(case when max(length(address)) > 7 then 'address;' else '' end) ||
(case when max(length(phone)) > 7 then 'phone;' else '' end)
from t;
As I read you need a dynamic sql for larger tables than your example (that should be part of your question)
I used unpivot to compare all lengths at once
DECLARE #TableName VARCHAR(100) = 'YourTableName'
DECLARE #MaxLen INT = 7
DECLARE #Definition
TABLE (
ColumnName VARCHAR(50)
)
INSERT #Definition
SELECT C.Name
FROM
sys.columns C
JOIN sys.tables T
ON C.object_id = T.object_id
WHERE t.name = #TableName
DECLARE #Columns VARCHAR(MAX) = ''
DECLARE #ColumnsWithCast VARCHAR(MAX) = ''
SET #Columns = STUFF(
(SELECT ',' + ColumnName
FROM #Definition
FOR XML PATH('')
),
1,
1,
'')
SET #ColumnsWithCast = STUFF(
(SELECT ',CAST(' + ColumnName + ' AS VARCHAR(MAX)) AS ' + ColumnName
FROM #Definition
FOR XML PATH('')
),
1,
1,
'')
DECLARE #SQL NVARCHAR(MAX) = N'
SELECT DISTINCT
Field
FROM (
SELECT
' + #ColumnsWithCast + '
FROM ' + #TableName + ' A
) p
UNPIVOT (
Value FOR Field IN (
' + #Columns + '
)
)AS unpvt
WHERE LEN(Value) > #MaxLen
'
DECLARE #ParamDefinition NVARCHAR(100) = N'#MaxLen INT'
EXEC sp_executesql #SQL, #ParamDefinition, #MaxLen = #MaxLen
It will generate this code with all the existing columns
SELECT DISTINCT
Field
FROM (
SELECT
CAST(Name AS VARCHAR(MAX)) AS Name,
CAST(Address AS VARCHAR(MAX)) AS Address,
CAST(PhoneNumber AS VARCHAR(MAX)) AS PhoneNumber,
FROM HIERARCHY A
) p
UNPIVOT (
Value FOR Field IN (
Name, Address, PhoneNumber
)
)AS unpvt
WHERE LEN(Value) > #MaxLen

How to check a condition against all the columns of a table?

I have a table which has more than 30 columns(all are varchar). I need to list out all the columns which contains blank i.e.' ' values.
I tried using 'coalesce' but it is only for NULL.
The following query will give you all the columns in a table that might have null or '' values.
It is written so that you can run it for all tables in your database but you can limit it to a single table, as I have done for this specific example, checking a table called testingNulls:
--two variables needed for table name and column name, when looping through all tables
declare #table varchar(255), #col varchar(255), #sql varchar(max)
--this will be used to store the result, to have one result set instead of one row per each cursor cycle
if object_id('tempdb..#nullcolumns') is not null drop table #nullcolumns
create table #nullcolumns (tablename varchar(255), columnname varchar(255))
declare getinfo cursor for
select t.name tablename, c.name
from sys.tables t join sys.columns c on t.object_id = c.object_id
where t.name = 'testingnulls' --here the condition for the table name
open getinfo
fetch next from getinfo into #table, #col
while ##fetch_status = 0
begin
select #sql = 'if exists (select top 1 * from [' + #table + '] where [' + #col + '] is null or [' + #col + '] like '''' ) begin insert into #nullcolumns select ''' + #table + ''' as tablename, ''' + #col + ''' as all_nulls end'
print(#sql)
exec(#sql)
fetch next from getinfo into #table, #col
end
close getinfo
deallocate getinfo
--this should be the result you need:
select * from #nullcolumns
You can see a working example here. I hope this is what you need.
List all columns that contain a blank in some record? You'd use a query per column and collect the results with UNION ALL:
select 'COL1' where exists (select * from mytable where col1 like '% %')
union all
select 'COL2' where exists (select * from mytable where col2 like '% %')
union all
...
union all
select 'COL30' where exists (select * from mytable where col30 like '% %');
If you want like select * from [your_table_name] where [col1] = '' and [col2] = ''....., then use dynamic sql query like below.
Query
declare #sql as varchar(max);
select #sql = 'select * from [your_table_name] where '
+ stuff((
select ' and [' + [column_name] + '] = ' + char(39) + char(39)
from information_schema.columns
where table_name = 'your_table_name'
for xml path('')
)
, 1, 5, ''
);
exec(#sql);
Update
Or else if you want to list the column names which have a blank value, then you can use the below dynamic sql query.
Query
declare #sql as varchar(max);
select #sql = stuff((
select ' union all select ' + [column_name] + ' as [col1], '
+ char(39) + [column_name] + char(39) + ' as [col2]'
+ ' from your_table_name'
from information_schema.columns
where table_name = 'your_table_name'
for xml path('')
)
, 1, 11, ''
);
set #sql = 'select distinct t.col2 as [blank_cols] from(' + #sql
+ ')t
where coalesce(ltrim(rtrim(t.col1)), ' + char(39) + char(39) + ') = '
+ char(39) + char(39) + ';';
exec(#sql);
Find a demo here
But still I'm not sure that this is what you are looking out for.
you have not many choices but to specify all the columns in your where clause
WHERE COL1 = '' AND COL2 = '' AND COL3 = '' AND . . .
or you can use Dynamic SQL to form your query, but that is not an easy path to go
If you want to count number of columns having '' value in a table (not for each row) then use the following
SELECT max(CASE WHEN col1 = '' THEN 1 ELSE 0 END) +
max(CASE WHEN col2 = '' THEN 1 ELSE 0 END) +
max(CASE WHEN col3 = '' THEN 1 ELSE 0 END) +
...
FROM t
demo
I created a dynamic SQL script that you can use by providing the table name only
Here it is
declare #sql nvarchar(max)
declare #table sysname = 'ProductAttributes'
select #sql =
'select * from ' + #table + ' where ' +
string_agg('[' + name + '] = '' '' ', ' and ')
from sys.columns
where object_id = OBJECT_ID(#table)
select #sql
exec sp_executesql #sql
Unfortunately, for SQL string concatenation String_Agg function is new with SQL Server 2017
But it is also possible to use SQL XML Path to concatenate WHERE clause fragments
SELECT #sql = 'select * from ' + #table + ' where ' +
STUFF(
(
SELECT
' and ' + '[' + [name] + '] = '' '' '
from sys.columns
where object_id = OBJECT_ID(#table)
FOR XML PATH(''),TYPE
).value('.','VARCHAR(MAX)'
), 1, 5, ''
)
select #sql as sqlscript
exec sp_executesql #sql

sum columns dynamically sql

I have multiple columns with some amount in a table and I want to show the total of all those amounts in the last Total column. I have a table in sql which looks somewhat like this,
A_Amt B_Amt C_Amt D_Amt E_Amt F_Amt ...
------------------------------------------------
15 20 25 30 35 40
i have written a query as
declare #xmlResult xml=
(
select *
from Foo
for xml PATH
);
SELECT Nodes.node.value('sum(*[contains(local-name(.), "_Amt")])', 'decimal(15,2)') AS Total
FROM
#xmlResult.nodes('//row') as Nodes(node);
but the result I am getting has only one column total but i want all the columns in resultant table like A_amt etc..
This should be what you need, BUT ATTENTION! You should NOT do this. Aggregate rows should NEVER be fetched together with the "raw" data. This is - in most cases - something your UI should do (or a report...)
declare #table TABLE(ID INT IDENTITY, a INT,b INT,c INT);
insert into #table VALUES(1,1,1),(2,3,4),(5,6,7);
SELECT a,b,c
FROM
(
SELECT ROW_NUMBER() OVER(ORDER BY t.ID) AS inx
,a,b,c
FROM #table AS t
UNION SELECT 999999,SUM(a),SUM(b),SUM(c)
FROM #table
) AS tbl
ORDER BY tbl.inx
I think this is what you are looking for, try this (replace spt_values with your table) :
USE MASTER
GO
declare #lsql nvarchar(max)
declare #lsql2 nvarchar(max)
declare #yourTable nvarchar(255) = 'spt_values'
Select #lsql = isnull(#lsql+'+','') + 'Case When ISNUMERIC('+name+') = 1 Then '+name+' else 0 end' from sys.Columns where Object_id = Object_id(#yourTable)
Print #lsql
SET #lsql2 = 'Select *, '+#lsql+' as Total_allcolumns From '+#yourTable+''
Exec(#lsql2)
Using Microsoft's system table is one way to achieve dynamic SQL and thus your goal. The code below is what you want or will at least get you started.
I wasn't sure what output you expected, so I included two outputs. Just use the one you want and discard the other one. Given your question, it is probably result1. (Result1 or Result2)
!!You have to write the table name in the script at the place indicated prior to executing it!!
--DISCLAIMER
--It assume you use SQL SERVER 2012. (Probably work on 2005+ with little adjustment)
--It assume data is in a table, (Not a view for example)
--Changing SQL SERVER version may break the code as Microsoft could change "system views".
--I don't remember well, but EXEC may be limited to 4000 characters in dynamic query. (But there is a work around, just look around if you need it)
--So use at your own risk
DECLARE #objectIDTable INT,
#AllColumnAdditionStatement NVARCHAR(MAX) = '',
#TableName NVARCHAR(250) = 'WriteYourTableNameHere',--!!!OVERWRITE THE TABLE NAME HERE
#Query NVARCHAR(MAX),
#AllSumStatement NVARCHAR(MAX) = ''
SELECT TOP 1 #objectIDTable = [object_id],
#AllColumnAdditionStatement = ''
FROM sys.objects
WHERE type_desc = 'USER_TABLE'
AND name = #TableName
SELECT #AllColumnAdditionStatement = #AllColumnAdditionStatement + 'CONVERT(DECIMAL(18, 4), (CASE WHEN ISNUMERIC(' + name + ') = 1 THEN ISNULL(' + name + ', ''0'') ELSE 0 END))' + ' + ',
#AllSumStatement = #AllSumStatement + name + 'Total = SUM(CONVERT(DECIMAL(18, 4), (CASE WHEN ISNUMERIC(' + name + ') = 1 THEN ISNULL(' + name + ', ''0'') ELSE 0 END))), ' + CHAR(10)
FROM sys.columns
WHERE object_id = #objectIDTable
AND name LIKE '%_Amt' --!!!Here is a column filter/selector to sum only column ending with _Amt
SELECT #AllColumnAdditionStatement = #AllColumnAdditionStatement + '0', --just too lazy to chop off last three char
#AllSumStatement = #AllSumStatement + 'Total_ = SUM(' + #AllColumnAdditionStatement + ')' + CHAR(10),
#Query = 'SELECT *,
Total_ = ' + #AllColumnAdditionStatement +'
FROM ' + #TableName
PRINT (#Query)
/********************************************************************************************/
EXEC (#Query) --or use sp_execute if you prefer
--Result1 : addition of all selected columns into total column with all column return as well
/********************************************************************************************/
SELECT #Query = 'SELECT ' + #AllSumStatement + '
FROM ' + #TableName
EXEC (#Query) --or use sp_execute if you prefer
--Result2 : Summation of all column individualy and summation of all of them into total column
/********************************************************************************************/

Get top three most common values from every column in a table

I'm trying to write a query that will produce a very small sample of data from each column of a table, in which the sample is made up of the top 3 most common values. This particular problem is part of a bigger task, which is to write scripts that can characterize a database and its tables, its data integrity, and also quickly survey common values in the table on a per-column basis. Think of this as an automated "analysis" of a table.
On a single column basis, I do this already by simply calculating the frequency of values and then sorting by frequency. If I had a column called "color" and all colors were in it, and it just so happened that the color "blue" was in most rows, then the top 1 most frequently occurring value would be "blue". In SQL that is easy to calculate.
However, I'm not sure how I would do this over multiple columns.
Currently, when I do a calculation over all columns of a table, I perform the following type of query:
USE database;
DECLARE #t nvarchar(max)
SET #t = N'SELECT '
SELECT #t = #t + 'count(DISTINCT CAST(' + c.name + ' as varchar(max))) "' + c.name + '",'
FROM sys.columns c
WHERE c.object_id = object_id('table');
SET #t = SUBSTRING(#t, 1, LEN(#t) - 1) + ' FROM table;'
EXEC sp_executesql #t
However, its not entirely clear to me how I would do that here.
(Sidenote:columns that are of type text, ntext, and image, since those would cause errors while counting distinct values, but i'm less concerned about solving that)
But the problem of getting top three most frequent values per column has got me absolutely stumped.
Ideally, I'd like to end up with something like this:
Col1 Col2 Col3 Col4 Col5
---------------------------------------------------------------------
1,2,3 red,blue,green 29,17,0 c,d,j nevada,california,utah
I hacked this together, but it seems to work:
I cant help but think I should be using RANK().
USE <DB>;
DECLARE #query nvarchar(max)
DECLARE #column nvarchar(max)
DECLARE #table nvarchar(max)
DECLARE #i INT = 1
DECLARE #maxi INT = 10
DECLARE #target NVARCHAR(MAX) = <table>
declare #stage TABLE (i int IDENTITY(1,1), col nvarchar(max), tbl nvarchar(max))
declare #results table (ColumnName nvarchar(max), ColumnValue nvarchar(max), ColumnCount int, TableName NVARCHAR(MAX))
insert into #stage
select c.name, o.name
from sys.columns c
join sys.objects o on o.object_id=c.object_id and o.type = 'u'
and c.system_type_id IN (select system_type_id from sys.types where [name] not in ('text','ntext','image'))
and o.name like #target
SET #maxi = (select max(i) from #stage)
while #i <= #maxi
BEGIN
set #column = (select col from #stage where i = #i)
set #table = (select tbl from #stage where i = #i)
SET #query = N'SELECT ' +''''+#column+''''+' , '+ #column
SELECT #query = #query + ', COUNT( ' + #column + ' ) as count' + #column + ' , ''' + #table + ''' as tablename'
select #query = #query + ' from ' + #table + ' group by ' + #column
--Select #query
insert into #results
EXEC sp_executesql #query
SET #i = #i + 1
END
select * from #results
; with cte as (
select *, ROW_NUMBER() over (partition by Columnname order by ColumnCount desc) as rn from #results
)
select * from cte where rn <=3
Start with this SQL Statement builder, and modify it to suit your liking:
EDIT Added Order by Desc
With ColumnSet As
(
Select TABLE_SCHEMA, TABLE_NAME, COLUMN_NAME
From INFORMATION_SCHEMA.COLUMNS
Where 1=1
And TABLE_NAME IN ('Table1')
And COLUMN_NAME IN ('Column1', 'Column2')
)
Select 'Select Top 3 ' + COLUMN_NAME + ', Count (*) NumInstances From ' + TABLE_SCHEMA + '.'+ TABLE_NAME + ' Group By ' + COLUMN_NAME + ' Order by Count (*) Desc'
From ColumnSet