How can I write a query to extract individual changes from snapshots of data?

Question

I need to create a process that will extract the changes from a table where each row is a snapshot of a row in another table. The real-world problem involves many tables wit

Answer 1

Here's a working sample that uses UNPIVOT. It's based on my answer to my question Better way to Partially UNPIVOT in Pairs in SQL

This has some nice features.

1. Adding additional fields is easy. Just add values to the SELECT and UNPIVOT clause. You don't have to add additional UNION clauses

2. The where clause WHERE curr.value <> prev.value never changes regardless of how many fields are added.

3. The performance is surprisingly fast.

4. Its portable to Current versions of Oracle if you need that

---

SQL

Declare @Snapshots as table(
Sequence int,
DateTaken      datetime,
[id] int,
field1 varchar(20),
field2 int)



INSERT INTO @Snapshots VALUES 

      (1,    '2011-01-01',      1,     'Red',          2),
      (2,    '2011-01-01',      2,     'Blue',        10),
      (3,    '2011-02-01',      1,     'Green',        2),
      (4,    '2011-03-01',      1,     'Green' ,       3),
      (5,    '2011-03-01',      2,     'Purple',       2),
      (6,    '2011-04-01',      1,     'Yellow',       2)

;WITH Snapshots (Sequence, DateTaken, ID, Field1, Field2, _Index)
AS
(
    SELECT Sequence, DateTaken, ID, Field1, Field2, ROW_NUMBER() OVER (ORDER BY ID, Sequence) _Index
    FROM @Snapshots
)
,  data as(
SELECT
     c._Index
    , c.DateTaken
    ,  c.ID
    , cast(c.Field1  as varchar(max)) Field1
    , cast(p.Field1  as varchar(max))Field1_Previous
    , cast(c.Field2   as varchar(max))Field2
    , cast(p.Field2  as varchar(max)) Field2_Previous 


FROM Snapshots c
JOIN Snapshots p ON p.ID = c.ID AND (p._Index + 1) = c._Index
)


, fieldsToRows 
     AS (SELECT DateTaken, 
                id,
                _Index,
                value,
                field

         FROM   data p UNPIVOT (value FOR field IN (field1, field1_previous, 
                                                        field2, field2_previous) ) 
                AS unpvt
        ) 
SELECT 
    curr.DateTaken,
    curr.ID,
    curr.field,
    prev.value previous,
    curr.value 'current'

FROM 
        fieldsToRows curr 
        INNER  JOIN  fieldsToRows prev
        ON curr.ID = prev.id
            AND curr._Index = prev._Index 
            AND curr.field + '_Previous' = prev.field
WHERE 
    curr.value <> prev.value

---

Output

DateTaken               ID          field     previous current
----------------------- ----------- --------- -------- -------
2011-02-01 00:00:00.000 1           Field1    Red      Green
2011-03-01 00:00:00.000 1           Field2    2        3
2011-04-01 00:00:00.000 1           Field1    Green    Yellow
2011-04-01 00:00:00.000 1           Field2    3        2
2011-03-01 00:00:00.000 2           Field1    Blue     Purple
2011-03-01 00:00:00.000 2           Field2    10       2

Answer 2

WITH Snapshots (Sequence, DateTaken, ID, Field, FieldValue, _Index) AS
(
    SELECT
        Sequence,
        DateTaken,
        ID,
        'Field1' AS Field
        CAST(Field1 AS VARCHAR(100)) AS FieldValue,  -- Find an appropriate length
        ROW_NUMBER() OVER (ORDER BY ID, Sequence)
    FROM
        #Snapshots
    UNION ALL
    SELECT
        Sequence,
        DateTaken,
        ID,
        'Field2' AS Field
        CAST(Field2 AS VARCHAR(100)) AS FieldValue,  -- Find an appropriate length
        ROW_NUMBER() OVER (ORDER BY ID, Sequence)
    FROM
        #Snapshots
)
SELECT
    S1.DateTaken,
    S1.ID,
    S1.Field,
    S1.FieldValue AS Previous,
    S2.FieldValue As New   -- Not necessarily "Current"
FROM
    Snapshots S1
INNER JOIN Snapshots S2 ON
    S2.ID = S1.ID AND
    S2.Field = S1.Field AND
    S2._Index = S1._Index + 1 AND
    S2.FieldValue <> S1.FieldValue    -- Might need to handle NULL values