SQL FIFO query with group by - sql

Question

I have 3 tables:
INVENTORY_IN:
ID INV_TIMESTAMP PRODUCT_ID IN_QUANTITY SUPPLIER_ID
...
1 10.03.21 01:00:00 101 100 4
2 11.03.21 02:00:00 101 50 3
3 14.03.21 01:00:00 101 10 2
INVENTORY_OUT:
ID INV_TIMESTAMP PRODUCT_ID OUT_QUANTITY CUSTOMER_ID
...
1 10.03.21 02:00:00 101 30 1
2 11.03.21 01:00:00 101 40 2
3 12.03.21 01:00:00 101 80 1
INVENTORY_BALANCE:
INV_DATE PRODUCT_ID QUANTITY
...
09.03.21 101 20
10.03.21 101 90
11.03.21 101 100
12.03.21 101 20
13.03.21 101 20
14.03.21 101 30
I want to use FIFO (first in-first out) logic for the inventory, and to see which quantities correspond to each SUPPLIER-CUSTOMER combination.
The desired ouput looks like this (queried for dates >= 2021-03-10):
PRODUCT_ID SUPPLIER_ID CUSTOMER_ID QUANTITY
101 1 20
101 4 1 60
101 4 2 40
101 3 1 30
101 3 20
101 2 10
edit. fixed little typo in numbers.
edit. Added a diagram which explains every row. All of the black arrows correspond to supplier and customer combinations, there are 7 of them, because for supplier_id = 4 and customer_id = 1 the desired results is the sum of matched quantities happening between them. So, it explains why there are 7 arrows, while the desired results contains only 6 rows.

Answer 1

Option 1
This is probably a job for PL/SQL. Starting with the data types to output:
CREATE TYPE supply_details_obj AS OBJECT(
product_id NUMBER,
quantity NUMBER,
supplier_id NUMBER,
customer_id NUMBER
);
CREATE TYPE supply_details_tab AS TABLE OF supply_details_obj;
Then we can define a pipelined function to read the INVENTORY_IN and INVENTORY_OUT tables one row at a time and merge the two keeping a running total of the remaining inventory or amount to supply:
CREATE FUNCTION assign_suppliers_to_customers (
i_product_id IN INVENTORY_IN.PRODUCT_ID%TYPE
)
RETURN supply_details_tab PIPELINED
IS
v_supplier_id INVENTORY_IN.SUPPLIER_ID%TYPE;
v_customer_id INVENTORY_OUT.CUSTOMER_ID%TYPE;
v_quantity_in INVENTORY_IN.IN_QUANTITY%TYPE := NULL;
v_quantity_out INVENTORY_OUT.OUT_QUANTITY%TYPE := NULL;
v_cur_in SYS_REFCURSOR;
v_cur_out SYS_REFCURSOR;
BEGIN
OPEN v_cur_in FOR
SELECT in_quantity, supplier_id
FROM INVENTORY_IN
WHERE product_id = i_product_id
ORDER BY inv_timestamp;
OPEN v_cur_out FOR
SELECT out_quantity, customer_id
FROM INVENTORY_OUT
WHERE product_id = i_product_id
ORDER BY inv_timestamp;
LOOP
IF v_quantity_in IS NULL THEN
FETCH v_cur_in INTO v_quantity_in, v_supplier_id;
IF v_cur_in%NOTFOUND THEN
v_supplier_id := NULL;
END IF;
END IF;
IF v_quantity_out IS NULL THEN
FETCH v_cur_out INTO v_quantity_out, v_customer_id;
IF v_cur_out%NOTFOUND THEN
v_customer_id := NULL;
END IF;
END IF;
EXIT WHEN v_cur_in%NOTFOUND AND v_cur_out%NOTFOUND;
IF v_quantity_in > v_quantity_out THEN
PIPE ROW(
supply_details_obj(
i_product_id,
v_quantity_out,
v_supplier_id,
v_customer_id
)
);
v_quantity_in := v_quantity_in - v_quantity_out;
v_quantity_out := NULL;
ELSE
PIPE ROW(
supply_details_obj(
i_product_id,
v_quantity_in,
v_supplier_id,
v_customer_id
)
);
v_quantity_out := v_quantity_out - v_quantity_in;
v_quantity_in := NULL;
END IF;
END LOOP;
END;
/
Then, for the sample data:
CREATE TABLE INVENTORY_IN ( ID, INV_TIMESTAMP, PRODUCT_ID, IN_QUANTITY, SUPPLIER_ID ) AS
SELECT 0, TIMESTAMP '2021-03-09 00:00:00', 101, 20, 0 FROM DUAL UNION ALL
SELECT 1, TIMESTAMP '2021-03-10 01:00:00', 101, 100, 4 FROM DUAL UNION ALL
SELECT 2, TIMESTAMP '2021-03-11 02:00:00', 101, 50, 3 FROM DUAL UNION ALL
SELECT 3, TIMESTAMP '2021-03-14 01:00:00', 101, 10, 2 FROM DUAL;
CREATE TABLE INVENTORY_OUT ( ID, INV_TIMESTAMP, PRODUCT_ID, OUT_QUANTITY, CUSTOMER_ID ) AS
SELECT 1, TIMESTAMP '2021-03-10 02:00:00', 101, 30, 1 FROM DUAL UNION ALL
SELECT 2, TIMESTAMP '2021-03-11 01:00:00', 101, 40, 2 FROM DUAL UNION ALL
SELECT 3, TIMESTAMP '2021-03-12 01:00:00', 101, 80, 1 FROM DUAL;
The query:
SELECT product_id,
supplier_id,
customer_id,
SUM( quantity ) AS quantity
FROM TABLE( assign_suppliers_to_customers( 101 ) )
GROUP BY
product_id,
supplier_id,
customer_id
ORDER BY
MIN( inv_timestamp )
Outputs:
PRODUCT_ID | SUPPLIER_ID | CUSTOMER_ID | QUANTITY
---------: | ----------: | ----------: | -------:
101 | 0 | 1 | 20
101 | 4 | 1 | 60
101 | 4 | 2 | 40
101 | 3 | 1 | 30
101 | 3 | null | 20
101 | 2 | null | 10
Option 2
A (very) complicated SQL query:
WITH in_totals ( ID, INV_TIMESTAMP, PRODUCT_ID, IN_QUANTITY, SUPPLIER_ID, TOTAL_QUANTITY ) AS (
SELECT i.*,
SUM( in_quantity ) OVER ( PARTITION BY product_id ORDER BY inv_timestamp )
FROM inventory_in i
),
out_totals ( ID, INV_TIMESTAMP, PRODUCT_ID, OUT_QUANTITY, CUSTOMER_ID, TOTAL_QUANTITY ) AS (
SELECT o.*,
SUM( out_quantity ) OVER ( PARTITION BY product_id ORDER BY inv_timestamp )
FROM inventory_out o
),
split_totals ( product_id, inv_timestamp, supplier_id, customer_id, quantity ) AS (
SELECT i.product_id,
MIN( COALESCE( LEAST( i.inv_timestamp, o.inv_timestamp ), i.inv_timestamp ) )
AS inv_timestamp,
i.supplier_id,
o.customer_id,
SUM(
COALESCE(
LEAST(
i.total_quantity - o.total_quantity + o.out_quantity,
o.total_quantity - i.total_quantity + i.in_quantity,
i.in_quantity,
o.out_quantity
),
0
)
)
FROM in_totals i
LEFT OUTER JOIN
out_totals o
ON ( i.product_id = o.product_id
AND i.total_quantity - i.in_quantity <= o.total_quantity
AND i.total_quantity >= o.total_quantity - o.out_quantity )
GROUP BY
i.product_id,
i.supplier_id,
o.customer_id
ORDER BY
inv_timestamp
),
missing_totals ( product_id, inv_timestamp, supplier_id, customer_id, quantity ) AS (
SELECT i.product_id,
i.inv_timestamp,
i.supplier_id,
NULL,
i.in_quantity - COALESCE( s.quantity, 0 )
FROM inventory_in i
INNER JOIN (
SELECT product_id,
supplier_id,
SUM( quantity ) AS quantity
FROM split_totals
GROUP BY product_id, supplier_id
) s
ON ( i.product_id = s.product_id
AND i.supplier_id = s.supplier_id )
ORDER BY i.inv_timestamp
)
SELECT product_id, supplier_id, customer_id, quantity
FROM (
SELECT product_id, inv_timestamp, supplier_id, customer_id, quantity
FROM split_totals
WHERE quantity > 0
UNION ALL
SELECT product_id, inv_timestamp, supplier_id, customer_id, quantity
FROM missing_totals
WHERE quantity > 0
ORDER BY inv_timestamp
);
Which, for the sample data above, outputs:
PRODUCT_ID | SUPPLIER_ID | CUSTOMER_ID | QUANTITY
---------: | ----------: | ----------: | -------:
101 | 0 | 1 | 20
101 | 4 | 1 | 60
101 | 4 | 2 | 40
101 | 3 | 1 | 30
101 | 3 | null | 20
101 | 2 | null | 10
db<>fiddle here

Answer 2

If your system controls the timestamps so you cannot consume what was not supplied (I've met systems, that didn't track intraday balance), then you can use SQL solution with interval join. The only thing to take care here is to track the last supply that was not consumed in full: it should be added as supply with no customer.
Here's the query with comments:
CREATE TABLE INVENTORY_IN ( ID, INV_TIMESTAMP, PRODUCT_ID, IN_QUANTITY, SUPPLIER_ID ) AS
SELECT 0, TIMESTAMP '2021-03-09 00:00:00', 101, 20, 0 FROM DUAL UNION ALL
SELECT 1, TIMESTAMP '2021-03-10 01:00:00', 101, 100, 4 FROM DUAL UNION ALL
SELECT 2, TIMESTAMP '2021-03-11 02:00:00', 101, 50, 3 FROM DUAL UNION ALL
SELECT 3, TIMESTAMP '2021-03-14 01:00:00', 101, 10, 2 FROM DUAL;
CREATE TABLE INVENTORY_OUT ( ID, INV_TIMESTAMP, PRODUCT_ID, OUT_QUANTITY, CUSTOMER_ID ) AS
SELECT 1, TIMESTAMP '2021-03-10 02:00:00', 101, 30, 1 FROM DUAL UNION ALL
SELECT 2, TIMESTAMP '2021-03-11 01:00:00', 101, 40, 2 FROM DUAL UNION ALL
SELECT 3, TIMESTAMP '2021-03-12 01:00:00', 101, 80, 1 FROM DUAL;
with i as (
select
/*Get total per product, supplier at each timestamp
to calculate running sum on timestamps without need to resolve ties with over(... rows between) addition*/
inv_timestamp
, product_id
, supplier_id
, sum(in_quantity) as quan
, sum(sum(in_quantity)) over(
partition by product_id
order by
inv_timestamp asc
, supplier_id asc
) as rsum
from INVENTORY_IN
group by
product_id
, supplier_id
, inv_timestamp
)
, o as (
select /*The same for customer*/
inv_timestamp
, product_id
, customer_id
, sum(out_quantity) as quan
, sum(sum(out_quantity)) over(
partition by product_id
order by
inv_timestamp asc
, customer_id asc
) as rsum
/*Last consumption per product: when lead goes beyond the current window*/
, lead(0, 1, 1) over(
partition by product_id
order by
inv_timestamp asc
, customer_id asc
) as last_consumption
from INVENTORY_OUT
group by
product_id
, customer_id
, inv_timestamp
)
, distr as (
select
/*Distribute the quantity. This is the basic interval intersection:
new_value_to = least(t1.value_to, t2.value_to)
new_value_from = greatest(t1.value_from, t2.value_from)
So we need a capacity of the interval
*/
i.product_id
, least(i.rsum, nvl(o.rsum, i.rsum))
- greatest(i.rsum - i.quan, nvl(o.rsum - o.quan, i.rsum - i.quan)) as supplied_quan
/*At the last supply we can have something not used.
Calculate it to add later as not consumed
*/
, case
when last_consumption = 1
and i.rsum > nvl(o.rsum, i.rsum)
then i.rsum - o.rsum
end as rest_quan
, i.supplier_id
, o.customer_id
, i.inv_timestamp as i_ts
, o.inv_timestamp as o_ts
from i
left join o
on i.product_id = o.product_id
/*No equality here, because values are continuous:
>= will include the same value in two intervals if some of value_to of one table equals
another's table value_to (which is value_from for the next interval)*/
and i.rsum > o.rsum - o.quan
and o.rsum > i.rsum - i.quan
)
select
product_id
, supplier_id
, customer_id
, sum(quan) as quan
from (
select /*Get distributed quantities*/
product_id
, supplier_id
, customer_id
, supplied_quan as quan
, i_ts
, o_ts
from distr
union all
select /*Add not consumed part of last consumed supply*/
product_id
, supplier_id
, null
, rest_quan
, i_ts
, null /*No consumption*/
from distr
where rest_quan is not null
)
group by
product_id
, supplier_id
, customer_id
order by
min(i_ts) asc
/*To order not consumed last*/
, min(o_ts) asc nulls last
PRODUCT_ID | SUPPLIER_ID | CUSTOMER_ID | QUAN
---------: | ----------: | ----------: | ---:
101 | 0 | 1 | 20
101 | 4 | 1 | 60
101 | 4 | 2 | 40
101 | 3 | 1 | 30
101 | 3 | null | 20
101 | 2 | null | 10
db<>fiddle here