I am currently asked to validate the result of a global search which to find all records containing some keywords cross whole database. To do so, I need to check all the rows in each table that have keywords. The result for this global search is ready and partially of the result looks like the one below:
table_name
column_name
keyword
cnt
Wf_Process
Name_EN
FEC
11
Wf_Process
FTABLENAME
GB
14
ICCClass
Name_EN
GB
4
What I am trying to do is using the 'like' operator to extract all the data in each table where columns containing keywords. That is, I will use query such as:
select distinct Name_EN, FTABLENAME from Wf_Process where Name_EN like '%FEC%' or FTABLENAME like '%GB%'
and
select distinct Name_EN from ICCClass where Name_EN like '%GB%'
to pull out all data I need in whole database. If I only have three records, then it is not a problem. However my result returned over thousands tables have more than 10K rows containing keywords in total. Therefore, I was trying to use a loop to do this mission but I failed.
My question therefore is, does anyone have any idea to write a loop to do the 'like' search for all the tables in one time? Or is there another way rather than loop can do this in SQL Server?
Thank you very much!
You need dynamic SQL for this. You can generate a big UNION ALL query of all the tables together.
DECLARE #sql nvarchar(max) = (
SELECT STRING_AGG(CAST('
SELECT
' + QUOTENAME(con.table_name, '''') + ' table_name,
' + QUOTENAME(con.column_name, '''') + ' column_name,
' + QUOTENAME(con.keyword, '''') + ' keyword,
COUNT(*) cnt
FROM ' + QUOTENAME(s.name) + '.' + QUOTENAME(t.name) + ' t
WHERE t.' + QUOTENAME(c.name) + ' LIKE ' + QUOTENAME('%' + con.keyword + '%', '''')
AS nvarchar(max)), '
UNION ALL')
FROM YourConditions con
JOIN sys.tables t ON t.table_name
JOIN sys.schemas s ON s.schema_id = t.schema_id
JOIN sys.columns c ON c.object_id = t.object_id
WHERE t.name = con.table_name
AND c.name = con.column_name
);
PRINT #sql; -- your friend
EXEC sp_executesql #sql;
There are more efficient ways to do this if there are many columns or keywords per table, but this should get you started.
The question looks odd, thou can be done via dynamic sql, but not as a regular solution more like a one off or POC/test.
use tempdb
GO
drop table if exists search_result
go
create table search_result (
table_name sysname
,column_name sysname
,keyword varchar(100))
go
insert into search_result values
('Wf_Process', 'Name_EN', 'FEC')
,('Wf_Process' , 'FTABLENAME', 'GB')
,('ICCClass', 'Name_EN', 'GB')
GO
drop table if exists result
create table result (val varchar(500))
go
declare #col sysname
declare #tab sysname
declare #kw varchar(100)
declare #sql varchar(1000)
while exists (select * from search_result)
begin
select top 1
#tab = table_name
, #col = column_name
, #kw = keyword
from search_result
set #sql = concat('insert into result select ', #col, ' from ', #tab, ' where ', #col, ' like ''%', #kw, '%''' )
print(#sql)
exec (#sql)
delete from search_result
where table_name = #tab and column_name = #col and keyword = #kw
end
GO
select * from result
--initially trying to get all the column name with its respective table name, finding out if there is that particular keyword in all table,
--if yes, insert into temp table, if there aint keyword, it will insert the record too but the count of record will be zero.
--trying to make it dynamic and running it inside the loop by assigning row number to each table with different column.
IF OBJECT_ID('tempdb..#TEMP') IS NOT NULL
DROP TABLE #TEMP
CREATE TABLE #TEMP (TABLE_NAME NVARCHAR(200), COLUMN_NAME NVARCHAR(200), KEYWORD NVARCHAR(200), CNT INT)
DECLARE #TABLE NVARCHAR(200)
DECLARE #TABLE_ID INT
SET #TABLE_ID = 1
DECLARE #TABLE_NAME NVARCHAR (200)
DECLARE #FOR_LOOP INT
DECLARE #COLUMN NVARCHAR(200)
DECLARE #COLUMN_NAME NVARCHAR(200)
--TOTAL NO OF RECORDS FOR LOOP
SET #FOR_LOOP = (SELECT COUNT(*)
FROM SYS.tables T
JOIN SYS.all_columns C ON T.object_id = C.object_id
JOIN INFORMATION_SCHEMA.TABLES S ON S.TABLE_NAME = T.name)
DECLARE #STRINGS NVARCHAR(200)
SET #STRINGS = '%FEC%' --------->ENTER YOUR KEYWORD HERE, TRY ONE AT A TIME
DECLARE #COUNT INT
WHILE #TABLE_ID <= #FOR_LOOP
BEGIN
SET #TABLE = (SELECT CAST(TABLE_NAME AS NVARCHAR(200))
FROM
(SELECT ROW_NUMBER()OVER(ORDER BY T.NAME) TABLE_ID
,S.TABLE_SCHEMA SCHEMA_NAME ,T.NAME TABLE_NAME, C.name COLUMN_NAME
FROM SYS.tables T
JOIN SYS.all_columns C ON T.object_id = C.object_id
JOIN INFORMATION_SCHEMA.TABLES S ON S.TABLE_NAME = T.name)A
WHERE TABLE_ID = #TABLE_ID)
SET #TABLE_NAME = '['+#TABLE+']'
SET #COLUMN = (SELECT CAST(COLUMN_NAME AS NVARCHAR(200))
FROM
(SELECT ROW_NUMBER()OVER(ORDER BY T.NAME) TABLE_ID
,S.TABLE_SCHEMA SCHEMA_NAME ,T.NAME TABLE_NAME, C.name COLUMN_NAME
FROM SYS.tables T
JOIN SYS.all_columns C ON T.object_id = C.object_id
JOIN INFORMATION_SCHEMA.TABLES S ON S.TABLE_NAME = T.name)A
WHERE TABLE_ID = #TABLE_ID)
SET #COLUMN_NAME = '['+#COLUMN+']'
DECLARE #EXEC NVARCHAR(200) = 'SELECT ' + #COLUMN_NAME +' FROM ' + #TABLE_NAME + ' WHERE ' + #COLUMN_NAME + ' LIKE ' + ''''+#STRINGS+''''
--THERE MUST BE ANOTHER WAY TO REPLACE SP_EXECUTESQL FOR BETTER PERFORMANCE, AS IT WILL BE EXECUTED AS MANY TIMES AS THERE ARE RECORDS IN #FOR_LOOP
EXEC SP_EXECUTESQL #EXEC
SET #COUNT = (SELECT ##ROWCOUNT)
IF (SELECT ##ROWCOUNT) >=1
BEGIN
INSERT INTO #TEMP VALUES
(#TABLE_NAME, #COLUMN_NAME, #STRINGS, #COUNT)
SET #TABLE_ID = #TABLE_ID + 1
END
ELSE
--DONT KNOW WHY THIS ELSE PART IS NOT TOUCHED, WHEREAS I THINK IT SHOULD HAVE
BEGIN
PRINT 'RECORD NOT FOUND'
END
END
GO
--AFTER THE ABOVE BLOCK IS EXECUTED THEN TRY RUNNING BELOW ONE
SELECT *FROM #TEMP WHERE CNT>0
--THERE MAY BE MULTIPLE ERROS, MUST BE EDITED AND CAN MAKE IT AS A PROCEDURE TOO.
Related
Let’s say I’m looking for a specific column in my database so I have something like this
SELECT COLUMN_NAME, TABLE_NAME FROM INFORMATION_SCHEMA.COLUMNS WHERE COLUMN_NAME like ‘%employeeid%’
But I also want to know how many rows each table has, I was told I can do this using Dynamic SQL so I have this now
DECLARE
#tableName NVARCHAR(MAX),
#sql NVARCHAR(MAX),
#colName NVARCHAR(MAX);
DECLARE CUR_TABLE CURSOR FOR
SELECT TABLE_NAME FROM INFORMATION_SCHEMA.COLUMNS
OPEN CUR_TABLE
FETCH NEXT FROM CUR_TABLE
INTO #tableName
WHILE ##FETCH_STATUS = 0
BEGIN
SET #colName = '%employeeid%'
SET #sql = 'SELECT COLUMN_NAME, TABLE_NAME, (SELECT COUNT(*) FROM ' + #tableName +') AS ROWS FROM INFORMATION_SCHEMA.COLUMNS where column_name like ' + ''' + #colName + ''';
FETCH NEXT FROM CUR_TABLE
INTO #tableName
END;
CLOSE CUR_TABLE
DEALLOCATE CUR_TABLE
EXEC sp_executesql #sql
But this doesn't work, What I'm trying to do is query a table with the column I am looking for, with the table name, and number of rows in the table.
How can I fix this?
You can make use of SQL Server's dynamic management views to quickly obtain the row counts*.
Find all tables with a column named 'MyColumn' and their current rows:
select Schema_Name(t.schema_id) schemaName, t.name TableName, s.row_count
from sys.columns c
join sys.tables t on t.object_id = c.object_id
join sys.dm_db_partition_stats s on s.object_id = c.object_id and s.index_id <= 1
where c.name='MyColumn';
* Accurate except for frequently updated tables where there could be some lag
The following uses INFORMATION_SCHEMA, dynamic SQL, and STRING_AGG() to build a query that will return a single result set.
DECLARE #ColumnName sysname = 'ProductID'
DECLARE #Newline VARCHAR(2) = CHAR(13) + CHAR(10)
DECLARE #SqlTemplate NVARCHAR(MAX) =
+ 'SELECT'
+ ' ColumnName = <ColumnNameString>,'
+ ' TableName = <TableSchemaAndNameString>,'
+ ' Rows = (SELECT COUNT(*) FROM <TableSchemaAndName>)'
+ #Newline
DECLARE #UnionSql NVARCHAR(100) = 'UNION ALL ' + #Newline
DECLARE #Sql NVARCHAR(MAX) = (
SELECT STRING_AGG(
REPLACE(REPLACE(REPLACE(
#SqlTemplate
, '<ColumnNameString>', QUOTENAME(C.COLUMN_NAME, ''''))
, '<TableSchemaAndNameString>', QUOTENAME(C.TABLE_SCHEMA + '.' + C.TABLE_NAME, ''''))
, '<TableSchemaAndName>', QUOTENAME(C.TABLE_SCHEMA) + '.' + QUOTENAME(C.TABLE_NAME))
, #UnionSql)
WITHIN GROUP(ORDER BY C.TABLE_SCHEMA, C.TABLE_NAME)
FROM INFORMATION_SCHEMA.TABLES T
JOIN INFORMATION_SCHEMA.COLUMNS C
ON C.TABLE_SCHEMA = T.TABLE_SCHEMA
AND C.TABLE_NAME = T.TABLE_NAME
WHERE T.TABLE_TYPE = 'BASE TABLE' -- Omit views
AND C.COLUMN_NAME = #ColumnName
)
SET #Sql = #Sql + 'ORDER BY Rows DESC, TableName' + #Newline
--PRINT #Sql
EXEC (#Sql)
I generalized it a bit by adding TABLE_SCHEMA so that it could be used with the AdventureWorks database. See this db<>fiddle for a working demo. Also included is equivalent logic that uses FOR XML instead of STRING_AGG for older SQL Server versions.
Assuming that you are using SQL Server, here is a shorthand way using sp_msforeachtable.
DECLARE #ColumnName NVARCHAR(200) = 'ContactID'
CREATE TABLE #T
(
ColumnName NVARCHAR(200),
TableName NVARCHAR(200),
RecordCount INT
)
INSERT INTO #T (ColumnName, TableName)
SELECT
ColumnName = C.COLUMN_NAME,
TableName = '['+C.TABLE_SCHEMA+'].['+C.TABLE_NAME+']'
FROM
INFORMATION_SCHEMA.COLUMNS C
WHERE
C.COLUMN_NAME LIKE '%' + #ColumnName + '%'
EXEC SP_MSFOREACHTABLE 'IF EXISTS(SELECT * FROM #T WHERE TableName = ''?'') UPDATE #T SET RecordCount = (SELECT COUNT(*) FROM ? ) WHERE TableName = ''?'''
SELECT
ColumnName,TableName,
TableType = CASE
WHEN RecordCount IS NULL
THEN 'View'
ELSE 'Table'
END,
RecordCount
FROM
#T
ORDER BY
CASE WHEN RecordCount IS NULL THEN 'View' ELSE 'Table' END
DROP TABLE #T
My purpose is to produce a table containing the table_name, column_name, number of row each column and number of null value in each column. But I get an error:
Conversion failed when converting the varchar value ', ' to data type int
These are my queries:
DECLARE #BANG TABLE
(
TABLE_NAME NVARCHAR(MAX),
COLUMN_NAME NVARCHAR(MAX),
ID INT IDENTITY(1, 1)
)
INSERT INTO #BANG (TABLE_NAME, COLUMN_NAME)
SELECT A.NAME AS TABLE_NAME, B.NAME AS COLUMN_NAME
FROM SYS.TABLES AS A
LEFT JOIN SYS.COLUMNS AS B ON A.OBJECT_ID = B.OBJECT_ID
WHERE 1=1
AND A.NAME IN ('CTHD', 'HOADON', 'SANPHAM', 'KHACHHANG', 'NHANVIEN')
DECLARE #RESULT TABLE
(
TABLE_NAME NVARCHAR(MAX),
COLUMN_NAME NVARCHAR(MAX),
TOTAL_ROW INT,
TOTAL_NULL INT
)
DECLARE #ID INT = 0
WHILE #ID <= (SELECT COUNT(*) FROM #BANG)
BEGIN
DECLARE #TABLE_NAME NVARCHAR(MAX)
SET #TABLE_NAME = (SELECT TABLE_NAME FROM #BANG WHERE #ID = ID)
DECLARE #COLUMN_NAME NVARCHAR(MAX)
SET #COLUMN_NAME = (SELECT COLUMN_NAME FROM #BANG WHERE ID = #ID)
DECLARE #TOTAL_ROW INT
DECLARE #TOTAL_NULL INT
DECLARE #SQL NVARCHAR(MAX)
SET #SQL = 'SET #TOTAL_ROW = (SELECT COUNT(*) FROM '+#TABLE_NAME+')
SET #TOTAL_NULL = (SELECT COUNT(*) FROM '+#TABLE_NAME+' WHERE '+#COLUMN_NAME+' IS NULL)
INSERT INTO #RESULT
VALUES ('+#TABLE_NAME+', '+#COLUMN_NAME+', '+#TOTAL_ROW+', '+#TOTAL_NULL+')
'
SET #ID += 1
EXEC (#SQL)
END
I need your help. Thanks in advance
You should be using parameterized SQL. But honestly, the code is such a mess that I'm not going to attempt that fix.
The problem is that parameters such as #TOTAL_ROW are integers, not strings. So, the + is treated as addition rather than string concatenation.
The simplest immediate fix is to use CONCAT():
SET #SQL = CONCAT('
INSERT INTO #RESULT
VALUES (''', #TABLE_NAME, ''', ''', #COLUMN_NAME, ''', ''', #TOTAL_ROW, ', ', #TOTAL_NULL, ')';
You may have the same error elsewhere in the code. You need to fix all places where you have a number and string combined with + and you intend string concatenation rather than addition.
However, the real fix is to not munge query strings with such values. Instead use sp_executesql passing the values in as parameters.
The conversion error is during the generation of the dynamic SQL query, not during execution of the statement.
There are a number of issues with the script in your question. Below is a script that uses QUOTENAME to more security build the SQL statement and uses a parameterized query to execute it. The WHILE pseudo cursor doesn't provide any value in this case so this version uses a real cursor.
DECLARE #RESULT TABLE (SCHEMA_NAME sysname, TABLE_NAME sysname, COLUMN_NAME sysname, TOTAL_ROW int, TOTAL_NULL int);
DECLARE #SQL nvarchar(MAX), #SchemaName sysname, #TableName sysname, #ColumnName sysname;
DECLARE BANG CURSOR LOCAL FAST_FORWARD FOR
SELECT s.name AS SCHEMA_NAME, t.name AS TABLE_NAME, c.name AS COLUMN_NAME
FROM sys.tables AS t
JOIN sys.schemas AS s ON s.schema_id = t.schema_id
JOIN sys.columns AS c ON c.object_id = t.object_id
WHERE t.name IN (N'CTHD', N'HOADON', N'SANPHAM', N'KHACHHANG', N'NHANVIEN');
OPEN BANG;
WHILE 1 = 1
BEGIN
FETCH NEXT FROM BANG INTO #SchemaName, #TableName, #ColumnName;
IF ##FETCH_STATUS = -1 BREAK;
SET #SQL = N'SELECT #SchemaName, #TableName, #ColumnName, COUNT(*), COALESCE(SUM(CASE WHEN ' + QUOTENAME(#ColumnName) + N' IS NULL THEN 1 ELSE 0 END),0)
FROM ' + QUOTENAME(#SchemaName) + N'.' + QUOTENAME(#TableName) + N';'
PRINT #SQL
INSERT INTO #RESULT(SCHEMA_NAME, TABLE_NAME, COLUMN_NAME, TOTAL_ROW, TOTAL_NULL)
EXEC sp_executesql #SQL
, N'#SchemaName sysname, #TableName sysname, #ColumnName sysname'
, #SchemaName = #SchemaName
, #TableName = #TableName
, #ColumnName = #ColumnName;
END;
CLOSE BANG;
DEALLOCATE BANG;
SELECT SCHEMA_NAME, TABLE_NAME, COLUMN_NAME, TOTAL_ROW, TOTAL_NULL
FROM #RESULT
ORDER BY SCHEMA_NAME, TABLE_NAME, COLUMN_NAME;
GO
If you don't have many tables/columns, you could use a single UNION ALL query and ditch the (pseudo)cursor entirely:
DECLARE #SQL nvarchar(MAX) = (SELECT STRING_AGG(
N'SELECT ' + QUOTENAME(s.name,'''') + N' AS SCHEMA_NAME,'
+ QUOTENAME(t.name, '''') + N' AS TABLE_NAME,'
+ QUOTENAME(c.name,'''') + N' AS COLUMN_NAME,'
+ 'COUNT(*) AS TOTAL_ROW,'
+ 'COALESCE(SUM(CASE WHEN ' + QUOTENAME(c.name) + ' IS NULL THEN 1 ELSE 0 END),0) AS TOTAL_NULL '
+ 'FROM ' + QUOTENAME(s.name) + N'.' + QUOTENAME(t.name)
, ' UNION ALL ') + N';'
FROM sys.tables AS t
JOIN sys.schemas AS s ON s.schema_id = t.schema_id
JOIN sys.columns AS c ON c.object_id = t.object_id
WHERE t.name IN (N'CTHD', N'HOADON', N'SANPHAM', N'KHACHHANG', N'NHANVIEN');
EXEC sp_executesql #SQL;
As Gordon said, use sp_execute properly to execute dynamics sql. And there's some others issue with this code, not related to the question.
"the more important" when investigating is to use the print statement before the exec statement, to know what's being execute. Then, you'll realize where the errors is and why it won't work....
the first execution of the loop is useless (or maybe this is the one that produce the error....). You initialize #Id with the value of 0 and then compare it with the value of the identity in the table #BANG, starting at 1. This result to #TABLE_NAME and #COLUMN_NAME set to NULL, thus, concatening string without using CONCAT will end up in a NULL value. Nothing is execute on the first loop.
However, using concat with null value will not result in a null value, but an incorrect value (query in your case). As an exemple, this code
SET #SQL = CONCAT('
INSERT INTO #RESULT
VALUES (''', #TABLE_NAME, ''', ''', #COLUMN_NAME, ''', ''', #TOTAL_ROW, ', ', #TOTAL_NULL, ')';
will result in something like "INSERT INTO #RESULT VALUES (''CTHD'',''COL1'',,)" since both #TOTAL_ROW AND #TOTAL_NULL are null values. you need to use parametrized query using sp_executesql.
There's no need to execute two count on the same table, one for total rows, the second for null values. select count(1) return the total number of rows, and select count(#column_name) return the number of non-null value. So, Count(1) - count(#column_name) will gives you the number of null value. Then, use something like this to insert into #result :
INSERT INTO #RESULT (...) SELECT TABLE_NAME, COLUMN_NAME, COUNT(1), COUNT(1) - COUNT(#COLUMN_NAME) FROM ...
when dealing with SQL Server object, you the quotename function. You'll never know when someone will put a space, quote, bracket or whatever in a schema/table/column name that might break you query.
Do not use "WHILE #ID <= (SELECT COUNT(*) FROM #BANG)" to test if there are more rows to process. Use a "WHILE EXISTS (SELECT 1 FROM #BANG)"
I need to prepare a dynamic query to find the length of all the rows in a column in sql server. let say if there are 10 columns for a table with 100 rows. I need to find the row length for each column dynamically.
Assuming that your all columns are string columns, though len function should work anyways.
-- replace 'mytable' with the actual table name
declare #tableName nvarchar(128) = 'mytable';
declare #queryToRun nvarchar(max) = '';
-- IMPORTANT: following query is putting each column name as len_columnName
select #queryToRun = #queryToRun + ', len([' + c.name + ']) as [len_' + c.name + ']
'
from sys.tables as t
inner join sys.columns as c on t.object_id = c.object_id
where t.name = #tableName
-- removing the first comma
set #queryToRun = SUBSTRING(#queryToRun, 2, len(#queryToRun) - 1);
-- creating the query with dynamic column names
set #queryToRun = 'select ' + #queryToRun + ' from ' + #tableName;
--print #queryToRun
exec (#queryToRun)
you can use sys.tables and sys.all_columns
declare #Sql nvarchar(max)='select '
select #Sql=#sql+'Sum(len('+QUOTENAME(c.name)+')) as Len'+QUOTENAME(c.name)+',' from sys.tables t join sys.all_columns c on t.object_id=c.object_id
where t.Name='YourTableName'
set #Sql = left(#Sql,len(#sql)-1)+' from YourTableName'
select #Sql
Try this Script you will get data length of each columns in table dynamically
IF OBJECT_ID('dbo.LenghtOfRows')IS NOT NULL
DROP TABLE LenghtOfRows
CREATE TABLE LenghtOfRows (
Id Int IDENTITY,
Sqlode nvarchar(max)
)
DECLARE #SQL NVARCHAR(max),
#MinId INT,
#MaxId INT,
#tableName Varchar(100) ='StudentLabExamScore', --Give Table name here
#GetSQL NVARCHAR(max)
SET #SQL = 'SELECT ''SELECT DATALENGTH(''+COLUMN_NAME+'') As Len_'' +COLUMN_NAME +'' FROM ''+TABLE_NAME
FROM INFORMATION_SCHEMA.COLUMNS
WHERE TABLE_NAME = '''+#tableName+''''
PRINT #SQL
INSERT INTO LenghtOfRows(Sqlode)
EXEC ( #SQL)
SELECT #MinId = MIN(Id) from LenghtOfRows
SELECT #MaxId = MAX(Id) from LenghtOfRows
WHILE (#MInId <=#MaxId)
BEGIN
SELECT #GetSQL= Sqlode FROM LenghtOfRows WHERE id=#MInId
EXEC (#GetSQL)
PRINT #GetSQL
SET #MInId=#MInId+1
END
I have a SQL database with 60+ tables, almost all of which are populated with a CLIENTID field. I want to count the number of unique client IDs in each table.
The results I'm looking for are:
TABLE_NAME; CLIENTID_COUNT
dbo.HISTORY; 650
dbo.VISITS; 596
dbo.SALES; 1053
...; ...
This seems like it should be so simple but I've been playing around with cursors for hours and can't figure this one out. Please help!
IF OBJECT_ID('tempdb..#temp_RESULTS') IS NOT NULL DROP TABLE #temp_RESULTS
CREATE TABLE #TEMP_RESULTS
(
TABLENAME VARCHAR(MAX),
CLIENTCNT BIGINT
)
DECLARE #TABLENAME VARCHAR(MAX)
DECLARE #command VARCHAR(MAX)
IF OBJECT_ID('tempdb..#temp_PROCESS') IS NOT NULL DROP TABLE #temp_PROCESS
SELECT * INTO #TEMP_PROCESS FROM sys.tables
WHILE EXISTS(SELECT * FROM [#TEMP_PROCESS])
BEGIN
SET #TABLENAME = (SELECT TOP 1 [NAME] FROM [#TEMP_PROCESS])
SET #command = ('SELECT ''' + #TABLENAME + ''', COUNT(DISTINCT CLIENTID) AS CLIENTCNT FROM ' + #TABLENAME)
SELECT #command
INSERT INTO #TEMP_RESULTS
EXEC(#command)
DELETE FROM [#TEMP_PROCESS] WHERE [NAME] = #TABLENAME
END
SELECT * FROM [#TEMP_RESULTS]
Assuming the column is exactly ClientId in every table, you should be able to use this as is:
DROP TABLE IF EXISTS #clientId
CREATE TABLE #clientId
(
TableName nvarchar(1000),
ClientIdCount bigint
)
DECLARE #TableName nvarchar(1000);
DECLARE #CurrentQuery nvarchar(2000);
DECLARE result_cursor CURSOR local fast_forward FOR
SELECT DISTINCT
'['+TABLE_SCHEMA + '].[' + TABLE_NAME + ']'
FROM
INFORMATION_SCHEMA.COLUMNS
WHERE
COLUMN_NAME = 'ClientId'
OPEN result_cursor
FETCH NEXT FROM result_cursor into #TableName
WHILE ##FETCH_STATUS = 0
BEGIN
SET #CurrentQuery = 'SELECT ''' + #TableName + ''', COUNT(DISTINCT ClientId) FROM ' + #TableName
--print #CurrentQuery
INSERT INTO
#clientId
(
TableName,
ClientIdCount
)
EXEC(#CurrentQuery)
FETCH NEXT FROM result_cursor into #TableName
END
--end loop
--clean up
CLOSE result_cursor
DEALLOCATE result_cursor
GO
SELECT
*
FROM
#clientId
You could use dynamic sql.
This will read through your system tables, find those that have a ClientID column, and build the text of a query that's in the general shape of 'Select Count(DISTINCT ClientID)' from each table.
DECLARE #SQLQuery as nvarchar(max) = ''
------------------------------------
-- GET THE TABLES THAT HAVE A CLIENTID FROM SCHEMA
SELECT #SQLQuery = #SQLQuery + qryTxt FROM (
SELECT DISTINCT 'SELECT ''' + tables.name + ''', COUNT(DISTINCT CLIENTID) FROM ' + tables.name + ' UNION ' AS qryTxt
FROM sys.columns left join sys.tables on columns.object_id = tables.object_id where columns.name = CLIENTID AND isnull(tables.name, '') <> '') subquery
------------------------------------
-- REMOVE THE LAST 'UNION' KEYWORD FROM SQLQUERY
SET #SQLQuery = left(#sqlQuery, len(#sqlQuery) - 5)
------------------------------------
-- EXECUTE
execute sp_executesql #SQLQuery
I really dislike cursors and loops. Even though this is not going to be much difference for a performance perspective I like to share how you can leverage the system tables and dynamic sql to avoid using a cursor, while loop or temp tables for something like this.
This code is literally all you need to to do this.
declare #SQL nvarchar(max) = ''
select #SQL = #SQL + 'select TableName = ''' + t.name + ''', ClientID_Count = count(distinct clientID)
from ' + QUOTENAME(t.name) + ' UNION ALL '
from sys.tables t
join sys.columns c on c.object_id = t.object_id
where c.name = 'clientID'
select #SQL = left(#SQL, len(#SQL) - 10) --removes the last UNION ALL
select #SQL
--once your comfortable the dynamic sql is correct just uncomment the line below.
--exec sp_executesql #SQL
A similar pattern to other answers here, but this is how I would tackle it:
IF OBJECT_ID('#Tables', 'U') IS NOT NULL
DROP TABLE #Tables;
SELECT ID = IDENTITY(INT, 1, 1),
SchemaName = OBJECT_SCHEMA_NAME([object_id]),
TableName = OBJECT_NAME([object_id]),
ColumnName = name,
DistinctCount = 0
INTO #Tables
FROM sys.columns
WHERE name = 'CLIENTID';
DECLARE #ID INT = 1,
#MaxID INT = (SELECT MAX(ID) FROM #Tables);
WHILE #ID < #MaxID
BEGIN;
DECLARE #SQLCommand VARCHAR(MAX);
SELECT #SQLCommand = FORMATMESSAGE('
UPDATE #Tables SET DistinctCount = (
SELECT COUNT(DISTINCT %s) FROM %s.%s
)
WHERE ID = %i;',
QUOTENAME(ColumnName), QUOTENAME(SchemaName), QUOTENAME(TableName), ID)
FROM #Tables
WHERE ID = #ID;
EXEC (#SQLCommand);
SET #ID += 1;
END;
SELECT *
FROM #Tables;
I'll preface this by letting you all know that I promised myself a few years ago never to use a cursor in SQL where it's not needed. Unfortunately I think I may have to use one in my current situation but it's been so long that I'm struggling to remember the correct syntax.
Basically, I've got a problem with CONVERT_IMPLICIT happening in queries because I have data types that are different for the same field in different tables so I'd like to eventually convert these to int. But to do this I need to check whether all data can be converted to int or not to see how big the job is.
I've got the query below which gives me a list of all tables in the database that contain the relevant field in a list;
IF OBJECT_ID('tempdb..#BaseData') IS NOT NULL DROP TABLE #BaseData
GO
CREATE TABLE #BaseData (Table_Name varchar(100), Field_Name varchar(100), Data_Type_Desc varchar(20), Data_Max_Length int, Convertible bit)
DECLARE #FieldName varchar(20); SET #FieldName = 'TestFieldName'
INSERT INTO #BaseData (Table_Name, Field_Name, Data_Type_Desc, Data_Max_Length)
SELECT
o.name ,c.name ,t.name ,t.max_length
FROM sys.columns c
JOIN sys.types t
ON c.user_type_id = t.user_type_id
JOIN sys.objects o
ON c.object_id = o.object_id
WHERE c.name LIKE '%' + #FieldName + '%'
AND o.type_desc = 'USER_TABLE'
Which gives results like this;
Table_Name Field_Name Data_Type_Desc Data_Max_Length Convertible
Table1 TestFieldName varchar 8000 NULL
Table2 TestFieldName nvarchar 8000 NULL
Table3 TestFieldName int 4 NULL
Table4 TestFieldName varchar 8000 NULL
Table5 TestFieldName varchar 8000 NULL
What I'd like to do is to check if all data in the relevant table & field can be converted to an int and update the 'convertible' field (1 if there's data that can't be converted, 0 if the data is fine). I've got the following calculation which works perfectly fine;
'SELECT
CASE
WHEN COUNT(' + #FieldName + ') - SUM(ISNUMERIC(' + #FieldName + ')) > 0
THEN 1
ELSE 0
END
FROM ' + #TableName
And gives the result that I'm after. But I'm struggling to get to the correct syntax to create the cursor which will look at each row in my temp table and run this SQL accordingly. It then needs to update the final column of the temp table with the result of the query (1 or 0).
This will have to be run on a couple of hundred databases which is why I need this list to be dynamic, there may well be custom tables in some databases (in fact, it's pretty likely).
If anybody could give any guidance it would be greatly appreciated.
Thanks
I made a couple of changes to your original query but here is something that should work. I have done similar things in the past :-)
Changes:
Added schema to the source table - my test database had matches in multiple schemas
Changed datatypes to sysname, smallint to match table definitions or names could get truncated
IF OBJECT_ID('tempdb..#BaseData') IS NOT NULL DROP TABLE #BaseData;
GO
CREATE TABLE #BaseData (Schema_Name sysname, Table_Name sysname, Field_Name sysname, Data_Type_Desc sysname, Data_Max_Length smallint, Convertible bit);
DECLARE #FieldName varchar(20); SET #FieldName = 'TestFieldName';
INSERT INTO #BaseData (Schema_Name, Table_Name, Field_Name, Data_Type_Desc, Data_Max_Length)
SELECT
s.name, o.name ,c.name ,t.name ,t.max_length
FROM sys.columns c
JOIN sys.types t
ON c.user_type_id = t.user_type_id
JOIN sys.objects o
ON c.object_id = o.object_id
JOIN sys.schemas s ON o.schema_id=s.schema_id
WHERE c.name LIKE '%' + #FieldName + '%'
AND o.type_desc = 'USER_TABLE';
--select * from #BaseData;
DECLARE #sName sysname,
#tName sysname,
#fName sysname,
#sql VARCHAR(MAX);
DECLARE c CURSOR LOCAL FAST_FORWARD FOR
SELECT Schema_Name,
Table_Name,
Field_Name
FROM #BaseData;
OPEN c;
FETCH NEXT FROM c INTO #sName, #tName, #fName;
WHILE ##FETCH_STATUS = 0
BEGIN
SET #sql = 'UPDATE #BaseData SET Convertible =
(SELECT
CASE
WHEN COUNT(' + #fName + ') - SUM(ISNUMERIC(' + #fName + ')) > 0
THEN 1
ELSE 0
END Convertible
FROM ' + #sName + '.' + #tName + ')
FROM #BaseData WHERE Schema_Name = ''' + #sName + ''' AND Table_Name = ''' + #tName + ''' AND Field_Name = ''' + #fName + '''';
--select #sql;
EXEC(#sql);
FETCH NEXT FROM c INTO #sName, #tName, #fName;
END
CLOSE c;
DEALLOCATE c;
select *
from #BaseData;
If I understand your question, I would do something like this to identify those records that do not cast as an [int].
You didn't state which version of SQL Server you're using; TRY_CAST and TRY_CONVERT are 2012 or later.
DECLARE #test AS TABLE ( [field] [sysname] );
INSERT INTO #test
( [field] )
VALUES ( N'1' ),
( N'a' );
SELECT [field]
FROM #test
WHERE TRY_CAST([field] AS [INT]) IS NULL;
-- this is the basic sql syntax for a cursor
CURSOR (https://msdn.microsoft.com/en-us/library/ms180169.aspx)
DECLARE #parameter [sysname];
BEGIN
DECLARE [field_cursor] CURSOR
FOR
SELECT [value]
FROM [<schema>].[<table>];
OPEN [field_cursor];
FETCH NEXT FROM [field_cursor] INTO #parameter;
WHILE ##FETCH_STATUS = 0
BEGIN
-- do something really interesting here
FETCH NEXT FROM [field_cursor] INTO #parameter;
END;
CLOSE [field_cursor];
DEALLOCATE [field_cursor];
END;
I wasn't able to test this but it should do what you're looking for. Just plop this in after you create your temp table:
DECLARE #tName VARCHAR(20),
#fName VARCHAR(20),
#dType VARCHAR(20),
#dLength INT,
#sql VARCHAR(MAX);
DECLARE c CURSOR LOCAL FAST_FORWARD FOR
SELECT Table_Name,
Field_Name,
Data_Type_Desc,
Data_Max_Length
FROM #BaseData;
OPEN c;
FETCH NEXT FROM c INTO #tName, #fName, #dType, #dLength;
WHILE ##FETCH_STATUS = 0
BEGIN
IF((COUNT(#FieldName) - SUM(ISNUMERIC(#FieldName))) > 0)
BEGIN
SET #sql = 'UPDATE ' + #tName + ' SET Convertible = 1 WHERE Table_Name = ''' + #tName + '''';
END
ELSE
BEGIN
SET #sql = 'UPDATE ' + #tName + ' SET Convertible = 0 WHERE Table_Name = ''' + #tName + '''';
END
EXEC(#sql);
FETCH NEXT FROM c INTO #TableName, #FieldName, #DataType, #DataLength;
END
CLOSE c;
DEALLOCATE c;