SQL Sting Split into Single Column - sql

Question

Very new to SQL but I require some help with something that I am sure is a simple fix.
I have a single column of data within a table called 'Produce' where types of fruit are stored in a column called 'Fruit'. Some values within this column are separated by commas.
Is there an easy way to split the below so that the results come as a single column of unique entries?
E.g. Example Table
Fruit
-----
Apple
Plum
Pear, Mango
Pear
What I am hoping to return is the below:
Fruit
-----
Apple
Plum
Pear
Mango
I have tried to use the string split function but I think I have it completely. Can anyone help provide some explanation as to how to do this, please? I am using T-SQL if that helps.
Thanks in advance.

Answer 1

The core problem to fix would be to stop storing your values as comma separated lists. Keep your data normalized. With that being said... everyone needs a good splitter...
declare #table table (Fruit varchar(64))
insert into #table
values
('Apple'),
('Plum'),
('Pear,Mango'),
('Pear')
select distinct
Item
from
#table
cross apply
dbo.DelimitedSplit8K(Fruit,',')
OR, If you are on SQL Server 2016...
select distinct
Item
from
#table
cross apply
string_split(Fruit,',')
THE FUNCTION
SET ANSI_NULLS ON
GO
SET QUOTED_IDENTIFIER ON
GO
CREATE FUNCTION [dbo].[DelimitedSplit8K] (#pString VARCHAR(8000), #pDelimiter CHAR(1))
--WARNING!!! DO NOT USE MAX DATA-TYPES HERE! IT WILL KILL PERFORMANCE!
RETURNS TABLE WITH SCHEMABINDING AS
RETURN
/* "Inline" CTE Driven "Tally Table" produces values from 1 up to 10,000...
enough to cover VARCHAR(8000)*/
WITH E1(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
), --10E+1 or 10 rows
E2(N) AS (SELECT 1 FROM E1 a, E1 b), --10E+2 or 100 rows
E4(N) AS (SELECT 1 FROM E2 a, E2 b), --10E+4 or 10,000 rows max
cteTally(N) AS (--==== This provides the "base" CTE and limits the number of rows right up front
-- for both a performance gain and prevention of accidental "overruns"
SELECT TOP (ISNULL(DATALENGTH(#pString),0)) ROW_NUMBER() OVER (ORDER BY (SELECT NULL)) FROM E4
),
cteStart(N1) AS (--==== This returns N+1 (starting position of each "element" just once for each delimiter)
SELECT 1 UNION ALL
SELECT t.N+1 FROM cteTally t WHERE SUBSTRING(#pString,t.N,1) = #pDelimiter
),
cteLen(N1,L1) AS(--==== Return start and length (for use in substring)
SELECT s.N1,
ISNULL(NULLIF(CHARINDEX(#pDelimiter,#pString,s.N1),0)-s.N1,8000)
FROM cteStart s
)
--===== Do the actual split. The ISNULL/NULLIF combo handles the length for the final element when no delimiter is found.
SELECT ItemNumber = ROW_NUMBER() OVER(ORDER BY l.N1),
Item = SUBSTRING(#pString, l.N1, l.L1)
FROM cteLen l
;
GO
Jeff Moden Article for Function

Answer 2

This can be done with pure SQL, no user written functions needed.
SQL Server
WITH
fruittable
AS
( SELECT 'Apple' fruit, 1 id
UNION ALL
SELECT 'Banana,Apple', 2
UNION ALL
SELECT 'Tomato,Grapefruit,Apple', 3
UNION ALL
SELECT 'Watermelon,Persimmons', 4
),
split (fruit, id, leftover)
AS
(SELECT case when len(fruit) = 0 or fruit is null then null else left(fruit + ',', charindex(',',fruit + ',') -1 ) end AS fruit
, id
, case when len(fruit) = 0 or fruit is null then null else right(fruit + ',', len(fruit) - charindex(',',fruit + ',') + 1) end as leftover
FROM fruittable
UNION ALL
SELECT case when len(leftover) = 0 or leftover is null then null else left(leftover, charindex(',',leftover) - 1) end AS fruit
, id
, case when len(leftover) = 0 or leftover is null then null else substring(leftover, charindex(',',leftover) + 1, len(leftover)) end as leftover
FROM split
WHERE fruit IS NOT NULL)
SELECT fruit, id
FROM split where fruit is not null
order by fruit, id;
Oracle
WITH
fruittable
AS
(SELECT 'Apple' fruit, 1 id
FROM DUAL
UNION ALL
SELECT 'Banana,Apple', 2
FROM DUAL
UNION ALL
SELECT 'Tomato,Grapefruit,Apple', 3
FROM DUAL
UNION ALL
SELECT 'Watermelon,Persimmons', 4
FROM DUAL),
split (fruit, id, leftover)
AS
(SELECT SUBSTR (fruit || ',', 1, INSTR (fruit || ',', ',') - 1) AS fruit
, id
, SUBSTR (fruit || ',', INSTR (fruit || ',', ',') + 1) AS leftover
FROM fruittable
UNION ALL
SELECT SUBSTR (leftover, 1, INSTR (leftover, ',') - 1) AS fruit
, id
, SUBSTR (leftover, INSTR (leftover, ',') + 1) AS leftover
FROM split
WHERE fruit IS NOT NULL)
SELECT fruit, id
FROM split
WHERE fruit IS NOT NULL
ORDER BY fruit, id