Sql Server: How do you select a column only if it exists? - sql-server

Question

I have a situation where I have many tables that are similar data structures but not exactly the same along these lines:
Table 1
A int not null
B int not null
C int not null
Table 2
A int not null
B int not null
What I want to end up with after doing some data transformation is:
Table 3
A int not null
B int not null
C int null
There are several more tables that have varied but similar schemas so I am working on a script that will import to Table 3 from a variety of tables that are missing some columns.
Based on this question I've tried a query like this:
SELECT A
,B
,case
when COL_LENGTH('t2', 'C') IS NULL
then NULL
ELSE C
end as C
FROM t2
But it throws an error of "Invalid column name C" even though it would be selecting null.
Is there another way to select a column only if it exists and NULL if it doesn't?

Answer 1

This script generate dynamic SQL for any table structure.
Query:
SET NOCOUNT ON
IF OBJECT_ID (N'dbo.Table_1') IS NOT NULL
DROP TABLE dbo.Table_1
IF OBJECT_ID (N'dbo.Table_2') IS NOT NULL
DROP TABLE dbo.Table_2
CREATE TABLE dbo.Table_1 (A INT NOT NULL, B INT NOT NULL, C INT NOT NULL)
CREATE TABLE dbo.Table_2 (A INT NOT NULL, B INT NOT NULL)
INSERT INTO dbo.Table_1 (A, B, C)
VALUES (1, 1, 1), (2, 2, 2)
INSERT INTO dbo.Table_2 (A, B)
VALUES (6, 1), (8, 2)
DECLARE #SQL NVARCHAR(2000)
;WITH cte AS
(
SELECT
column_name = '[' + c.name + ']'
, table_name = '[' + s.name + '].[' + o.name + ']'
FROM sys.columns c WITH (NOLOCK)
JOIN sys.objects o WITH (NOLOCK) ON c.[object_id] = o.[object_id]
JOIN sys.schemas s WITH (NOLOCK) ON o.[schema_id] = s.[schema_id]
WHERE o.name IN ('Table_1', 'Table_2')
AND s.name = 'dbo'
AND o.[type] = 'U'
), cols AS
(
SELECT DISTINCT column_name
FROM cte
), tbl AS
(
SELECT DISTINCT table_name
FROM cte
), rs AS
(
SELECT
tbl.table_name
, column_name = ISNULL(cte.column_name, cols.column_name + ' = NULL')
FROM cols
CROSS JOIN tbl
LEFT JOIN cte ON cols.column_name = cte.column_name AND cte.table_name = tbl.table_name
), rs2 AS (
SELECT uni = ' UNION ALL' + CHAR(13) + 'SELECT ' + STUFF((
SELECT ', ' + rs.column_name
FROM rs
WHERE tbl.table_name = rs.table_name
GROUP BY rs.column_name
ORDER BY rs.column_name
FOR XML PATH(''), TYPE).value('.', 'NVARCHAR(MAX)'), 1, 2, '') +
' FROM ' + table_name
FROM tbl
)
SELECT #SQL = 'SELECT
' + STUFF((
SELECT CHAR(13) + ', ' + cols.column_name
FROM cols
FOR XML PATH(''), TYPE).value('.', 'NVARCHAR(MAX)'), 1, 2, ' ')
+ '
FROM
(' + STUFF((
SELECT CHAR(10) + uni
FROM rs2
FOR XML PATH(''), TYPE).value('.', 'NVARCHAR(MAX)'), 1, 11, '') + CHAR(13) +
') t'
PRINT #SQL
EXECUTE sys.sp_executesql #SQL
Output:
SELECT
[A]
, [B]
, [C]
FROM
(
SELECT [A], [B], [C] FROM [dbo].[Table_1]
UNION ALL
SELECT [A], [B], [C] = NULL FROM [dbo].[Table_2]
) t
Results:
A B C
----------- ----------- -----------
1 1 1
2 2 2
6 1 NULL
8 2 NULL

Answer 2

Can you just use a UNION?
select A, B, C FROM Table1
UNION
Select A, B, null FROM Table2