Compare the two tables and update the value in a Flag column - sql-server

Question

I have two tables and the values like this
`create table InputLocationTable(SKUID int,InputLocations varchar(100),Flag varchar(100))
create table Location(SKUID int,Locations varchar(100))
insert into InputLocationTable(SKUID,InputLocations) values(11,'Loc1, Loc2, Loc3, Loc4, Loc5, Loc6')
insert into InputLocationTable(SKUID,InputLocations) values(12,'Loc1, Loc2')
insert into InputLocationTable(SKUID,InputLocations) values(13,'Loc4,Loc5')
insert into Location(SKUID,Locations) values(11,'Loc3')
insert into Location(SKUID,Locations) values(11,'Loc4')
insert into Location(SKUID,Locations) values(11,'Loc5')
insert into Location(SKUID,Locations) values(11,'Loc7')
insert into Location(SKUID,Locations) values(12,'Loc10')
insert into Location(SKUID,Locations) values(12,'Loc1')
insert into Location(SKUID,Locations) values(12,'Loc5')
insert into Location(SKUID,Locations) values(13,'Loc4')
insert into Location(SKUID,Locations) values(13,'Loc2')
insert into Location(SKUID,Locations) values(13,'Loc2')`
I need to get the output by matching SKUID's from Each tables and Update the value in Flag column as shown in the screenshot, I have tried something like this code
`SELECT STUFF((select ','+ Data.C1
FROM
(select
n.r.value('.', 'varchar(50)') AS C1
from InputLocation as T
cross apply (select cast('<r>'+replace(replace(Location,'&','&'), ',', '</r><r>')+'</r>' as xml)) as S(XMLCol)
cross apply S.XMLCol.nodes('r') as n(r)) DATA
WHERE data.C1 NOT IN (SELECT Location
FROM Location) for xml path('')),1,1,'') As Output`
But not convinced with output and also i am trying to avoid xml path code, because performance is not first place for this code, I need the output like the below screenshot. Any help would be greatly appreciated.

Answer 1

I think you need to first look at why you think the XML approach is not performing well enough for your needs, as it has actually been shown to perform very well for larger input strings.
If you only need to handle input strings of up to either 4000 or 8000 characters (non max nvarchar and varchar types respectively), you can utilise a tally table contained within an inline table valued function which will also perform very well. The version I use can be found at the end of this post.
Utilising this function we can split out the values in your InputLocations column, though we still need to use for xml to concatenate them back together for your desired format:
-- Define data
declare #InputLocationTable table (SKUID int,InputLocations varchar(100),Flag varchar(100));
declare #Location table (SKUID int,Locations varchar(100));
insert into #InputLocationTable(SKUID,InputLocations) values (11,'Loc1, Loc2, Loc3, Loc4, Loc5, Loc6'),(12,'Loc1, Loc2'),(13,'Loc4,Loc5'),(14,'Loc1');
insert into #Location(SKUID,Locations) values (11,'Loc3'),(11,'Loc4'),(11,'Loc5'),(11,'Loc7'),(12,'Loc10'),(12,'Loc1'),(12,'Loc5'),(13,'Loc4'),(13,'Loc2'),(13,'Loc2'),(14,'Loc1');
--Query
-- Derived table splits out the values held within the InputLocations column
with i as
(
select i.SKUID
,i.InputLocations
,s.item as Loc
from #InputLocationTable as i
cross apply dbo.fn_StringSplit4k(replace(i.InputLocations,' ',''),',',null) as s
)
select il.SKUID
,il.InputLocations
,isnull('Add ' -- The split Locations are then matched to those already in #Location and those not present are concatenated together.
+ stuff((select ', ' + i.Loc
from i
left join #Location as l
on i.SKUID = l.SKUID
and i.Loc = l.Locations
where il.SKUID = i.SKUID
and l.SKUID is null
for xml path('')
)
,1,2,''
)
,'No Flag') as Flag
from #InputLocationTable as il
order by il.SKUID;
Output:
+-------+------------------------------------+----------------------+
| SKUID | InputLocations | Flag |
+-------+------------------------------------+----------------------+
| 11 | Loc1, Loc2, Loc3, Loc4, Loc5, Loc6 | Add Loc1, Loc2, Loc6 |
| 12 | Loc1, Loc2 | Add Loc2 |
| 13 | Loc4,Loc5 | Add Loc5 |
| 14 | Loc1 | No Flag |
+-------+------------------------------------+----------------------+
For nvarchar input (I have different functions for varchar and max type input) this is my version of the string splitting function linked above:
create function [dbo].[fn_StringSplit4k]
(
#str nvarchar(4000) = ' ' -- String to split.
,#delimiter as nvarchar(1) = ',' -- Delimiting value to split on.
,#num as int = null -- Which value in the list to return. NULL returns all.
)
returns table
as
return
-- Start tally table with 10 rows.
with n(n) as (select 1 union all select 1 union all select 1 union all select 1 union all select 1 union all select 1 union all select 1 union all select 1 union all select 1 union all select 1)
-- Select the same number of rows as characters in #str as incremental row numbers.
-- Cross joins increase exponentially to a max possible 10,000 rows to cover largest #str length.
,t(t) as (select top (select len(isnull(#str,'')) a) row_number() over (order by (select null)) from n n1,n n2,n n3,n n4)
-- Return the position of every value that follows the specified delimiter.
,s(s) as (select 1 union all select t+1 from t where substring(isnull(#str,''),t,1) = #delimiter)
-- Return the start and length of every value, to use in the SUBSTRING function.
-- ISNULL/NULLIF combo handles the last value where there is no delimiter at the end of the string.
,l(s,l) as (select s,isnull(nullif(charindex(#delimiter,isnull(#str,''),s),0)-s,4000) from s)
select rn
,item
from(select row_number() over(order by s) as rn
,substring(#str,s,l) as item
from l
) a
where rn = #num
or #num is null;
go