Subquery using multiple IN operator - sql

Question

I am trying to fetch all the id's in list 1 and with those id's from list 1, I am trying to fetch all the values in list 2 along with the count based on values in list 2.
DECLARE #Table1 AS TABLE (
id int,
l1 varchar(20)
);
INSERT INTO #Table1 VALUES
(1,'sun'),
(2,'shine'),
(3,'moon'),
(4,'light'),
(5,'earth'),
(6,'revolves'),
(7,'flow'),
(8,'fire'),
(9,'fighter'),
(10,'sun'),
(10,'shine'),
(11,'shine'),
(12,'moon'),
(1,'revolves'),
(10,'revolves'),
(2,'air'),
(3,'shine'),
(4,'fire'),
(5,'love'),
(6,'sun'),
(7,'rises');
/*
OPERATION 1
fetch all distinct ID's that has values from List 1
List1
sun
moon
earth
Initial OUTPUT1:
distinct_id list1_value
1 sun
3 moon
5 earth
10 sun
12 moon
6 sun
OPERATION2
fetch all the id, count_of_list2_values, list2_values
based on the id's that we recieved from OPERATION1
List2
shine
revolves
Expected Output:
id list1-value count_of_list2_values, list2_values
1 sun 1 revolves
3 moon 1 shine
5 earth 0 NULL
10 sun 2 shine,revolves
12 moon 0 NULL
6 sun 1 revolves
*/
My query:
Here is what I tried
select id, count(l1),l1
from #table1
where id in ('shine','revolves') and id in ('sun','moon','earth')
How can I achieve this.
I know this should be a subquery, having multiple in. How can this be achieved?
SQL fiddle Link:
https://dbfiddle.uk/?rdbms=sqlserver_2017&fiddle=7a85dbf51ca5b5d35e87d968c46300bb
foo
foo

Answer 1

There are several ways this could be done. Here's how I'd do it:
First set up the data:
DECLARE #Table1 AS TABLE (
id int,
l1 varchar(20)
) ;
INSERT INTO #Table1 VALUES
(1,'sun'),
(2,'shine'),
(3,'moon'),
(4,'light'),
(5,'earth'),
(6,'revolves'),
(7,'flow'),
(8,'fire'),
(9,'fighter'),
(10,'sun'),
(10,'shine'),
(11,'shine'),
(12,'moon'),
(1,'revolves'),
(10,'revolves'),
(2,'air'),
(3,'shine'),
(4,'fire'),
(5,'love'),
(6,'sun'),
(7,'rises') ;
Since this is a known list, set the "target" data up as it's own set. (In SQL, tables are almost invariably better to work with than demented lists. Oops, typo! I meant delimited lists.)
DECLARE #Targets AS TABLE (
l2 varchar(20)
) ;
INSERT INTO #Targets VALUES
('sun'),
('moon'),
('earth') ;
OPERATION 1
fetch all distinct ID's that has values from List 1
(sun, moon, earth)
Easy enough with a join:
SELECT Id
from #Table1 t1
inner join #Targets tg
on tg.l2 = t1.l1
OPERATION 2
fetch all the id, count_of_list2_values, list2_values
based on the id's that we recieved from OPERATION1
If I'm following the desired logic correctly, then (read the "join" comments first):
SELECT
tt.Id
-- This next counts how many items in the Operation 1 list are not in the target list
-- (Spaced out, to make it easier to compare with the next line)
,sum( case when tg2.l2 is null then 1 else 0 end)
-- And this concatenates them together in a string (in later editions of SQL Server)
,string_agg(case when tg2.l2 is null then tt.l1 else null end, ', ')
from #Table1 tt
inner join (-- Operation 1 as a subquery, produce list of the Ids to work with
select t1.id
from #Table1 t1
inner join #Targets tg
on tg.l2 = t1.l1
) xx
on xx.id = tt.id
-- This is used to identify the target values vs. the non-target values
left outer join #Targets tg2
on tg2.l2 = tt.l1
-- Aggregate, because that's what we need to do
group by tt.Id
-- Order it, because why not?
order by tt.Id

Answer 2

If you're using Sql Server 2017 then you can use string_agg function and outer apply operator:
select
l1.id,
l1.l1,
l2.cnt as count_of_list2_values,
l2.l1 as list2_values
from #Table1 as l1
outer apply (
select
count(*) as cnt,
string_agg(tt.l1, ',') as l1
from #Table1 as tt
where
tt.l1 in ('shine','revolves') and
tt.id = l1.id
) as l2
where
l1.l1 in ('sun','moon','earth')
db fiddle demo
In previous editions, I'm not sure it's possible to aggregate and count in one pass without creation of the special function for this. You can, of course, do it like this with xquery, but it might be a bit of an overkill (I'd not do this in production code at least):
select
l1.id,
l1.l1,
l2.data.value('count(l1)', 'int'),
stuff(l2.data.query('for $i in l1 return concat(",",$i/text()[1])').value('.','nvarchar(max)'),1,1,'')
from #Table1 as l1
outer apply (
select
tt.l1
from #Table1 as tt
where
tt.l1 in ('shine','revolves') and
tt.id = l1.id
for xml path(''), type
) as l2(data)
where
l1.l1 in ('sun','moon','earth')
db fiddle demo
If you don't mind to do it with double scan / seek of the table then you can either use #forpas answer or do something like this:
with cte_list2 as (
select tt.l1, tt.id
from #Table1 as tt
where
tt.l1 in ('shine','revolves')
)
select
l1.id,
l1.l1,
l22.cnt as count_of_list2_values,
stuff(l21.data.value('.', 'nvarchar(max)'),1,1,'') as list2_values
from #Table1 as l1
outer apply (
select
',' + tt.l1
from cte_list2 as tt
where
tt.id = l1.id
for xml path(''), type
) as l21(data)
outer apply (
select count(*) as cnt
from cte_list2 as tt
where
tt.id = l1.id
) as l22(cnt)
where
l1.l1 in ('sun','moon','earth')

Answer 3

With this:
with
cte as(
select t1.id, t2.l1
from table1 t1 left join (
select * from table1 where l1 in ('shine','revolves')
) t2 on t2.id = t1.id
where t1.l1 in ('sun','moon','earth')
),
cte1 as(
select
c.id,
stuff(( select ',' + cte.l1 from cte where id = c.id for xml path(''), type).value('.', 'NVARCHAR(MAX)'), 1, 1, '') col
from cte c
)
select
id,
count(col) count_of_list2_values,
max(col) list2_values
from cte1
group by id
The 1st CTE gives these results:
id | l1
-: | :-------
1 | revolves
3 | shine
5 | null
10 | shine
10 | revolves
12 | null
6 | revolves
and the 2nd operates on these results to concatenate the common grouped values of l1.
Finally I use group by id and aggergation on the results of the 2nd CTE.
See the demo
Results:
id | count_of_list2_values | list2_values
-: | --------------------: | :-------------
1 | 1 | revolves
3 | 1 | shine
5 | 0 | null
6 | 1 | revolves
10 | 2 | shine,revolves
12 | 0 | null