Split string and divide value - sql

I got a table Test with columns A and B.
The A column contains different values in one entry, e.g. abc;def;ghi, all separated by ;. And the B column contains numeric values, but only one.
What I want is to seperate the values from column A into multiple rows.
So:
abc;def;ghi;jkl
-->
abc
def
ghi
jkl
In column B is one value, e.g. 20 and I want that value split to the amount of rows,
So the final result shut be:
abc 5
def 5
ghi 5
jkl 5
The issue is that the amount of values in column A must be variable.

First you need to create this function
REATE FUNCTION Split
(
#delimited nvarchar(max),
#delimiter nvarchar(100)
) RETURNS #t TABLE
(
-- Id column can be commented out, not required for sql splitting string
id int identity(1,1), -- I use this column for numbering splitted parts
val nvarchar(max),
origVal nvarchar(max)
)
AS
BEGIN
declare #xml xml
set #xml = N'<root><r>' + replace(#delimited,#delimiter,'</r><r>') + '</r></root>'
insert into #t(val,origval)
select
r.value('.','varchar(max)') as item, #delimited
from #xml.nodes('//root/r') as records(r)
RETURN
END
GO
then this query might help
Select x.Val, test.B / (len(test.A) - len(replace(Test.A, ';', '')) + 1) from Test
inner join dbo.Split(Test.A,';') x on x.origVal = Test.A
this part len(test.A) - len(replace(Test.A, ';', '')) will count the number of ; in string
Be aware this query might have some malfunctioning if there will be duplicate strings in A column, in this situation you need to pass the unique value (for example ID) to split function and return it in the result table, then join it by this value (ie. x.origVal = Test.A => x.origID = Test.ID)

You can use some tricks with CTE, STUFF and windows functions
DECLARE #t TABLE
(
ID INT ,
A NVARCHAR(MAX) ,
B INT
)
INSERT INTO #t
VALUES ( 1, 'a;b;c;d;', 20 ),
( 2, 'x;y;z;', 40 );
WITH cte ( ID, B, D, A )
AS ( SELECT ID ,
B ,
LEFT(A, CHARINDEX(';', A + ';') - 1) ,
STUFF(A, 1, CHARINDEX(';', A + ';'), '')
FROM #t
UNION ALL
SELECT ID ,
B ,
LEFT(A, CHARINDEX(';', A + ';') - 1) ,
STUFF(A, 1, CHARINDEX(';', A + ';'), '')
FROM cte
WHERE A > ''
)
SELECT ID ,
B ,
D,
CAST(B AS DECIMAL) / COUNT(*) OVER (PARTITION BY ID) AS Portion
FROM cte
Output:
ID B D Portion
1 20 a 5.00000000000
1 20 b 5.00000000000
1 20 c 5.00000000000
1 20 d 5.00000000000
2 40 x 13.33333333333
2 40 y 13.33333333333
2 40 z 13.33333333333

this an example how you can achieve required result
DECLARE #table AS TABLE
(
ColumnA VARCHAR(100) ,
ColumnB FLOAT
)
INSERT INTO #table
( ColumnA, ColumnB )
VALUES ( 'abc;def;ghi;jkl', 20 ),
( 'asf;ret;gsd;jas', 30 ),
( 'dfa;aef;gffhi;fjfkl', 40 );
WITH C AS ( SELECT n = 1
UNION ALL
SELECT n + 1
FROM C
WHERE n <= 100
),
SetForSplit
AS ( SELECT T.ColumnA ,
T.ColumnB ,
C.n ,
( CASE WHEN LEFT(SUBSTRING(T.ColumnA, n, 100), 1) = ';'
THEN SUBSTRING(T.ColumnA, n + 1, 100) + ';'
ELSE SUBSTRING(T.ColumnA, n, 100) + ';'
END ) AS SomeText
FROM #table AS T
JOIN C ON C.n <= LEN(T.ColumnA)
WHERE SUBSTRING(T.ColumnA, n, 1) = ';'
OR n = 1
)
SELECT ROW_NUMBER() OVER ( PARTITION BY columnA ORDER BY LEFT(SomeText,
CHARINDEX(';',
SomeText) - 1) ) AS RowN,
LEFT(SomeText, CHARINDEX(';', SomeText) - 1) AS ColA ,
ColumnB / COUNT(*) OVER ( PARTITION BY ColumnA ) AS ColB
FROM SetForSplit
ORDER BY ColumnA

This is full working exmaple:
DECLARE #DataSource TABLE
(
[A] VARCHAR(MAX)
,[B] INT
);
INSERT INTO #DataSource ([A], [B])
VALUES ('a;b;c;d', 20 ),
('x;y;z', 40 );
SELECT T.c.value('.', 'VARCHAR(100)')
,[B] / COUNT([B]) OVER (PARTITION BY [B])
FROM #DataSource
CROSS APPLY
(
SELECT CONVERT(XML, '<t>' + REPLACE([A], ';', '</t><t>') + '</t>')
) DS([Bxml])
CROSS APPLY [Bxml].nodes('/t') AS T(c)
and of couse you can ROUND the devision as you like.

Related

Reverse order of elements in a string

I have the following string:
1119/2/483/11021
I would like to reverse the order of the elements in that string. Desired output:
11021/483/2/1119
T-SQL Version 2014
You need an ordered split function, e.g. (inspiration):
CREATE FUNCTION dbo.SplitOrdered
(
#list nvarchar(max),
#delim nvarchar(10)
)
RETURNS TABLE
WITH SCHEMABINDING
AS
RETURN
(
WITH w(n) AS (SELECT 0 FROM (VALUES (0),(0),(0),(0)) w(n)),
k(n) AS (SELECT 0 FROM w a, w b),
r(n) AS (SELECT 0 FROM k a, k b, k c, k d, k e, k f, k g, k h),
p(n) AS (SELECT TOP (COALESCE(LEN(#list), 0))
ROW_NUMBER() OVER (ORDER BY ##SPID) -1 FROM r),
spots(p) AS
(
SELECT n FROM p
WHERE (SUBSTRING(#list, n, LEN(#delim + 'x') - 1) LIKE #delim OR n = 0)
),
parts(p,val) AS
(
SELECT p, SUBSTRING(#list, p + LEN(#delim + 'x') - 1,
LEAD(p, 1, 2147483647) OVER (ORDER BY p) - p - LEN(#delim))
FROM spots AS s
)
SELECT listpos = ROW_NUMBER() OVER (ORDER BY p),
Item = LTRIM(RTRIM(val))
FROM parts
);
Then you can reassemble using STRING_AGG() (if SQL Server 2017 or better) or FOR XML PATH on lower versions:
SQL Server 2017 +
DECLARE #OriginalString nvarchar(255) = N'1119/2/483/11021';
SELECT NewString = STRING_AGG(o.Item, N'/')
WITHIN GROUP (ORDER BY listpos DESC)
FROM dbo.SplitOrdered(#OriginalString, N'/') AS o;
SQL Server < 2017
DECLARE #OriginalString nvarchar(255) = N'1119/2/483/11021';
SELECT NewString = STUFF(
(SELECT N'/' + o.Item
FROM dbo.SplitOrdered(#OriginalString, N'/') AS o
ORDER BY o.listpos DESC
FOR XML PATH(''), TYPE).value(N'./text()[1]', N'nvarchar(max)'),1,1,N'');
Example db<>fiddle
Please try the following solution based on the built-in PARSENAME() T-SQL function.
SQL
-- DDL and sample data population, start
DECLARE #tbl TABLE (ID INT IDENTITY PRIMARY KEY, Tokens VARCHAR(MAX));
INSERT INTO #tbl (Tokens) VALUES
('1119/2/483/11021'),
('1120/25/484/1102');
-- DDL and sample data population, end
SELECT tbl.*
, PARSENAME(c, 1) + '/' +
PARSENAME(c, 2) + '/' +
PARSENAME(c, 3) + '/' +
PARSENAME(c, 4) AS Result
FROM #tbl AS tbl
CROSS APPLY (VALUES (REPLACE(Tokens, '/', '.') )) AS t(c);
Output
+----+------------------+------------------+
| ID | Tokens | Result |
+----+------------------+------------------+
| 1 | 1119/2/483/11021 | 11021/483/2/1119 |
| 2 | 1120/25/484/1102 | 1102/484/25/1120 |
+----+------------------+------------------+
First, split the string and convert it into a column then order by desc and display into multiple row values into a single row. In the following code, you can set any string and split char.
Try following way.
DECLARE #S varchar(max) ,
#Split char(1),
#X xml
DECLARE #Names VARCHAR(8000)
SELECT #S = '1119/2/483/11021',
#Split = '/'
SELECT #X = CONVERT(xml,' <root> <myvalue>' +
REPLACE(#S,#Split,'</myvalue> <myvalue>') + '</myvalue> </root> ')
select #Names = COALESCE(#Names + '/', '') + Value from (
select rowno,Value from (
select ROW_NUMBER() OVER(ORDER BY d) AS rowno , Value from (
SELECT T.c.value('.','varchar(20)') as Value,0 as d
FROM #X.nodes('/root/myvalue') T(c)
) m
) r
) t order by t.rowno desc
select #Names as ReverseString
Splitting the string into sub-strings, and then joining them back up, is most likely going to be a good approach.
Some comments mention using string-reverse, but that doesnt seem to be a good approach at all in your case, since you just want to reverse the order of words within the current string, not actually reverse the entire text-string character-by-character.
PS: string_split does not guarantee the order of the chunks!

Compare 2 or more column values in arbitrary order

I need a quick way to compare 2 or more values from different tables where the orders are arbitrarily stored in sql server. The data comes from a 3rd party who will not change.
Example data below shows the same item described in two ways. the remaining columns contain other data that i am joining.
table1
i j other columns...
1 2 ...
table2
i j other columns
2 1 ...
1 2 ...
right now for 2, i do a union query to cover both directions (i=i, j=j / i=j, j=i) . but if you expand to 3, that is 9 possible orders.
SELECT * FROM Table1 INNER JOIN Table2 ON Table1.i = Table2.i AND Table1.j = Table2.j
UNION
SELECT * FROM Table1 INNER JOIN Table2 ON Table1.i = Table2.j AND Table1.j = Table2.i
is there a way to order data returned from the first two columns before doing the comparison so i don't have to create all the unions?
Edit: New xml approach
I wonder how this approach performs:
select *, cast( '<c>' + cast(i as varchar) + '</c>' +
'<c>' + cast(j as varchar) + '</c>' +
'<c>' + cast(k as varchar) + '</c>'
as xml).query('for $a in /c order by $a return concat($a, "/")').value('.', 'varchar(100)')
from #Table1 o
This can be wrapped in a function and referenced in a persisted column... which should scale very well for you:
create table dbo.Table1 (pk int identity(1,1) primary key, i int, j int, k int);
insert into dbo.Table1
values(1, 2, 3), (3, 1, 2), (4, 5, 6), (9,9,9);
go
create function dbo.fn_GenerateCompare(#i int, #j int, #k int)
returns varchar(100)
with schemabinding
as
begin
return
(
select cast('<c>' + cast(#i as varchar) + '</c>' +
'<c>' + cast(#j as varchar) + '</c>' +
'<c>' + cast(#k as varchar) + '</c>'
as xml).query('for $a in /c order by $a return concat($a, "/")').value('.', 'varchar(100)')
);
end
alter table dbo.Table1
add Compare as dbo.fn_GenerateCompare(i, j, k) persisted;
select * from dbo.Table1
Returns:
pk i j k Compare
-- - - - -------
1 1 2 3 1/2/3
2 3 1 2 1/2/3
3 4 5 6 4/5/6
4 9 9 9 9/9/9
Your query should now be really simple. Slap an index on the new Compare column and it should fly.
Original Post:
I like the sorted list idea proposed by Thorsten. Heres a rough idea of how it might be done. Performance would be greatly improved by persisting this compare column on the table (trigger or persisted computed column?)
declare #Table1 table (pk int identity(1,1) primary key, i int, j int, k int)
declare #Table2 table (pk int identity(1,1) primary key, i int, j int, k int)
insert into #Table1
values(1, 2, 3), (3, 1, 2), (4, 5, 6), (9,9,9)
insert into #Table2
values (2, 1, 3), (6, 4, 5)
--since the order is unimportant, concatenate the columns into a sorted array
--note how 1,2,3 and 3,1,2 both result in the same compare value:
select *
from #Table1 o
cross
apply ( select cast(value as varchar) + '/'
from #Table1
unpivot (value for c in (i,j,k)) as u
where pk = o.pk
order
by value
for xml path('')
)d(compare)
--now, bring in the 2nd table
select [src] = 1, pk, compare
from #Table1 o
cross
apply ( select cast(value as varchar) + '/'
from #Table1
unpivot (value for c in (i,j,k)) as u
where pk = o.pk
order
by value
for xml path('')
)d(compare)
union all
select [src] = 2, pk, compare
from #Table2 o
cross
apply ( select cast(value as varchar) + '/'
from #Table2
unpivot (value for c in (i,j,k)) as u
where pk = o.pk
order
by value
for xml path('')
)d(compare)
--now just group them to find the matching rows
select min(src), min(pk), compare
from (
select [src] = 1, pk, compare
from #Table1 o
cross
apply ( select cast(value as varchar) + '/'
from #Table1
unpivot (value for c in (i,j,k)) as u
where pk = o.pk
order
by value
for xml path('')
)d(compare)
union all
select [src] = 2, pk, compare
from #Table2 o
cross
apply ( select cast(value as varchar) + '/'
from #Table2
unpivot (value for c in (i,j,k)) as u
where pk = o.pk
order
by value
for xml path('')
)d(compare)
)grouped
group
by compare
having count(*) > 1;

Delete duplicate values from concatenated string

I have the following table:
Object Field Values
------------------------------------
1 1 A;A;A;B;A;A
2 1 A;B;C;C
2 2 X
3 1 X;Y;Z
3 2 V;V;V;V;V;V;V;V;V;V;V
How can I select from this table only the unique values from the concatenated values? So:
Object Field Values
---------------------
1 1 A;B
2 1 A;B;C
2 2 X
3 1 X;Y;Z
3 2 V
In any scripting language, I would loop through the values from Values, explode on ; and loop through that array with some logic filtering out duplicates. However, I need to do this only using SQL (Server 2008).
Can anybody tell me if and how this can be done?
Any help is greatly appreciated :-)
To do this first create a split function. This is the one I use but if you search the internet (or even SO) for "SQL Server Split Function" you will find a number of alternatives if you don't like this:
ALTER FUNCTION [dbo].[Split](#StringToSplit NVARCHAR(MAX), #Delimiter NCHAR(1))
RETURNS TABLE
AS
RETURN
(
SELECT ID = ROW_NUMBER() OVER(ORDER BY n.Number),
Position = Number,
Value = SUBSTRING(#StringToSplit, Number, CHARINDEX(#Delimiter, #StringToSplit + #Delimiter, Number) - Number)
FROM ( SELECT TOP (LEN(#StringToSplit) + 1) Number = ROW_NUMBER() OVER(ORDER BY a.object_id)
FROM sys.all_objects a
CROSS JOIN sys.all_objects b
) n
WHERE SUBSTRING(#Delimiter + #StringToSplit + #Delimiter, n.Number, 1) = #Delimiter
);
Then you can split your field, So running:
SELECT t.Object, t.Field, s.Value
FROM T
CROSS APPLY dbo.Split(t.[Values], ';') AS s
Will turn this:
Object Field Values
------------------------------------
1 1 A;A;A;B;A;A
into:
Object Field Values
------------------------------------
1 1 A
1 1 A
1 1 A
1 1 B
1 1 A
1 1 A
Then you can apply the DISTINCT Operator:
SELECT DISTINCT t.Object, t.Field, s.Value
FROM T
CROSS APPLY dbo.Split(t.[Values], ';') AS s;
To give:
Object Field Values
------------------------------------
1 1 A
1 1 B
Then you can concatenate your rows back into a single column giving a final query:
SELECT t.Object, t.Field, [Values] = STUFF(x.value('.', 'NVARCHAR(MAX)'), 1, 1, '')
FROM T
CROSS APPLY
( SELECT DISTINCT ';' + s.Value
FROM dbo.Split(t.[Values], ';') AS s
FOR XML PATH(''), TYPE
) AS s (x)
SQL Fiddle appears to be down, but once you have the Split function created the below is a full working example:
CREATE TABLE #T (Object INT, Field INT, [Values] VARCHAR(MAX));
INSERT #T
VALUES
(1, 1, 'A;A;A;B;A;A'),
(2, 1, 'A;B;C;C'),
(2, 2, 'X'),
(3, 1, 'X;Y;Z'),
(3, 2, 'V;V;V;V;V;V;V;V;V;V;V');
SELECT t.Object, t.Field, [Values] = STUFF(x.value('.', 'NVARCHAR(MAX)'), 1, 1, '')
FROM #T AS T
CROSS APPLY
( SELECT DISTINCT ';' + s.Value
FROM dbo.Split(t.[Values], ';') AS s
FOR XML PATH(''), TYPE
) AS s (x);
EDIT
Based on your comment that you can't create tables or modify the DDL, I thought I would account for the situation where you can't create a function either. You can expand the above split function out into your query, so you don't actually need to create a function:
CREATE TABLE #T (Object INT, Field INT, [Values] VARCHAR(MAX));
INSERT #T
VALUES
(1, 1, 'A;A;A;B;A;A'),
(2, 1, 'A;B;C;C'),
(2, 2, 'X'),
(3, 1, 'X;Y;Z'),
(3, 2, 'V;V;V;V;V;V;V;V;V;V;V');
SELECT t.Object,
t.Field,
[Values] = STUFF(x.value('.', 'NVARCHAR(MAX)'), 1, 1, '')
FROM #T AS T
CROSS APPLY
( SELECT DISTINCT ';' + SUBSTRING(t.[Values], Number, CHARINDEX(';', t.[Values] + ';', Number) - Number)
FROM ( SELECT TOP (LEN(t.[Values]) + 1) Number = ROW_NUMBER() OVER(ORDER BY a.object_id)
FROM sys.all_objects a
CROSS JOIN sys.all_objects b
) n
WHERE SUBSTRING(';' + t.[Values] + ';', n.Number, 1) = ';'
FOR XML PATH(''), TYPE
) AS s (x);
Here is a standalone solution:
DECLARE #t table(Object int, Field int, [Values] varchar(max))
INSERT #t values
(1, 1, 'A;A;A;B;A;A'),
(2, 1, 'A;B;C;C'),
(3, 1, 'X'),
(4, 1, 'X;Y;Z'),
(5, 1, 'V;V;V;V;V;V;V;V;V;V;V')
SELECT t.Object, t.Field, x.[NewValues]
FROM #t t
CROSS APPLY
(
SELECT STUFF((
SELECT distinct ';'+t.c.value('.', 'VARCHAR(2000)') value
FROM (
SELECT x = CAST('<t>' +
REPLACE([Values], ';', '</t><t>') + '</t>' AS XML)
) a
CROSS APPLY x.nodes('/t') t(c)
for xml path(''), type
).value('.', 'varchar(max)'), 1, 1, '') [NewValues]
) x
Result:
Object Field NewValues
1 1 A;B
2 1 A;B;C
3 1 X
4 1 X;Y;Z
5 1 V
According to #GarethD's comment this may perform slow.
Test data:
create table #t(Object int identity(1,1), Field int, [Values] varchar(max))
INSERT #t values
(1, 'A;A;A;B;A;A'),(1, 'A;B;C;C'), (1, 'X'), (1, 'X;Y;Z'),(1, 'V;V;V;V;V;V;V;V;V;V;V')
insert #t select field, [values] from #t union all select field, [values] from #t union all select field, [values] from #t
insert #t select field, [values] from #t union all select field, [values] from #t union all select field, [values] from #t
insert #t select field, [values] from #t union all select field, [values] from #t union all select field, [values] from #t
insert #t select field, [values] from #t union all select field, [values] from #t union all select field, [values] from #t
insert #t select field, [values] from #t union all select field, [values] from #t union all select field, [values] from #t
insert #t select field, [values] from #t union all select field, [values] from #t union all select field, [values] from #t
Performance testing my script:
SELECT t.Object, t.Field, x.[NewValues]
FROM #t t
CROSS APPLY
(
SELECT STUFF((
SELECT distinct ';'+t.c.value('.', 'VARCHAR(2000)') value
FROM (
SELECT x = CAST('<t>' +
REPLACE([Values], ';', '</t><t>') + '</t>' AS XML)
) a
CROSS APPLY x.nodes('/t') t(c)
for xml path(''), type
).value('.', 'varchar(max)'), 1, 1, '') [NewValues]
) x
Result less than 1 sec.
Performance testing Garath script
(had to edit testdata to get all rows. Identical rows were considered as 1 row):
WITH CTE AS
( SELECT DISTINCT t.Object, t.Field, s.Value
FROM #T AS T
CROSS APPLY
( SELECT ID = ROW_NUMBER() OVER(ORDER BY n.Number),
Position = Number,
Value = SUBSTRING(t.[Values], Number, CHARINDEX(';', t.[Values] + ';', Number) - Number)
FROM ( SELECT TOP (LEN(t.[Values]) + 1) Number = ROW_NUMBER() OVER(ORDER BY a.object_id)
FROM sys.all_objects a
CROSS JOIN sys.all_objects b
) n
WHERE SUBSTRING(';' + t.[Values] + ';', n.Number, 1) = ';'
) AS s
)
SELECT Object,
Field,
[Values] = STUFF((SELECT ';' + Value
FROM CTE AS T2
WHERE T2.Object = T.Object
AND T2.Field = T.Field
FOR XML PATH(''), TYPE
).value('.', 'VARCHAR(MAX)'), 1, 1, '')
FROM CTE AS T
GROUP BY Object, Field;
Result 6 seconds
If any row has null in values this script will also crash.
Just as a Scalar Value Function alternative without the CTE...
ALTER FUNCTION [SplitRemoveDupes] (
#String VARCHAR(MAX)
,#Delimiter VARCHAR(5)
)
RETURNS VARCHAR(MAX)
AS
BEGIN
DECLARE #SplitLength INT
DECLARE #DedupedValues VARCHAR(MAX)
DECLARE #SplittedValues TABLE
(
OccurenceId SMALLINT IDENTITY(1,1),
SplitValue VARCHAR(200)
)
WHILE LEN(#String) > 0
BEGIN
SELECT #SplitLength = (
CASE CHARINDEX(#Delimiter, #String)
WHEN 0
THEN LEN(#String)
ELSE CHARINDEX(#Delimiter, #String) - 1
END
)
INSERT INTO #SplittedValues
SELECT SUBSTRING(#String, 1, #SplitLength)
SELECT #String = (
CASE (LEN(#String) - #SplitLength)
WHEN 0
THEN ''
ELSE RIGHT(#String, LEN(#String) - #SplitLength - 1) END)
END
SET #DedupedValues=(SELECT DISTINCT STUFF((
SELECT DISTINCT (#Delimiter + SplitValue)
FROM #SplittedValues s
ORDER BY (#Delimiter + SplitValue)
FOR XML PATH('')
), 1, 1, '') AS a
FROM #SplittedValues ss)
RETURN #DedupedValues
END
Call it inline...
SELECT Object, Field, [dbo].[SplitRemoveDupes](Values,';') From Table

Return Distinct Rows That Contain The Same Value/Character In SQL

I have a bit of a tricky situation. I have a column that contains a pipe delimited set of numbers in numerous rows in a table. For example:
Courses
-------------------
1|2
1|2|3
1|2|8
10
11
11|12
What I want to achieve is to return rows where the number only appears once in my output.
Ideally, I want to try and carry this out using SQL rather than having to carry out checks at a web application level. Carrying out a DISTINCT does not achieve what I want.
The desired output would be:
Courses
-------------------
1
2
3
8
10
11
12
I would appreciated if anyone can guide me in the right direction.
Thanks.
Please try:
declare #tbl as table(Courses nvarchar(max))
insert into #tbl values
('1|2'),
('1|2|3'),
('1|2|8'),
('10'),
('11'),
('11|12')
select * from #tbl
SELECT
DISTINCT CAST(Split.a.value('.', 'VARCHAR(100)') AS INT) AS CVS
FROM
(
SELECT CAST ('<M>' + REPLACE(Courses, '|', '</M><M>') + '</M>' AS XML) AS CVS
FROM #tbl
) AS A CROSS APPLY CVS.nodes ('/M') AS Split(a)
ORDER BY 1
Try this one -
SET NOCOUNT ON;
DECLARE #temp TABLE
(
string VARCHAR(500)
)
DECLARE #Separator CHAR(1)
SELECT #Separator = '|'
INSERT INTO #temp (string)
VALUES
('1|2'),
('1|2|3'),
('1|2|8'),
('10'),
('11'),
('11|12')
-- 1. XML
SELECT p.value('(./s)[1]', 'VARCHAR(500)')
FROM (
SELECT field = CAST('<r><s>' + REPLACE(t.string, #Separator, '</s></r><r><s>') + '</s></r>' AS XML)
FROM #temp t
) d
CROSS APPLY field.nodes('/r') t(p)
-- 2. CTE
;WITH a AS
(
SELECT
start_pos = 1
, end_pos = CHARINDEX(#Separator, t.string)
, t.string
FROM #temp t
UNION ALL
SELECT
end_pos + 1
, CHARINDEX(#Separator, string, end_pos + 1)
, string
FROM a
WHERE end_pos > 0
)
SELECT d.name
FROM (
SELECT
name = SUBSTRING(
string
, start_pos
, ABS(end_pos - start_pos)
)
FROM a
) d
WHERE d.name != ''
Try this :
create table course (courses varchar(100))
insert into course values('1|2')
insert into course values('1|2|3')
insert into course values('1|2|8')
insert into course values('10')
insert into course values('11')
insert into course values('11|12')
Declare #col varchar(200)
SELECT
#col=(
SELECT DISTINCT c.courses + '|'
FROM course c
FOR XML PATH('')
);
select * from course
;with demo as(
select cast(substring(#col,1,charindex('|',#col,1)-1) AS INT) cou,charindex('|',#col,1) pos
union all
select cast(substring(#col,pos+1,charindex('|',#col,pos+1)-pos-1)AS INT) cou,charindex('|',#col,pos+1) pos
from demo where pos<LEN(#col))
select distinct cou from demo
Could not manage without recursion :( Something like this could do the trich?
WITH splitNum(num, r)
AS
(
SELECT
SUBSTRING(<field>,1, CHARINDEX('|', <field>)-1) num,
SUBSTRING(<field>,CHARINDEX('|', <field>)+1, len(<field>)) r
FROM <yourtable> as a
UNION ALL
SELECT
SUBSTRING(r,1, CHARINDEX('|', r)-1) num,
SUBSTRING(r,CHARINDEX('|', r)+1, len(r)) r
FROM <yourtable> b
WHERE CHARINDEX('|', r) > 0
inner join splitNum as c on <whatevertheprimarykeyis>
)
SELECT distinct num FROM splitNum
Didn't make it run, but it should do the trick, just replace the and with the correct info
One way would be to use a recursive CTE:
with cte as
(select cast(case charindex('|',courses) when 0 then courses
else left(courses,charindex('|',courses)-1) end as int) course,
case charindex('|',courses) when 0 then ''
else right(courses,len(courses)-charindex('|',courses)) end courses
from courses
union all
select cast(case charindex('|',courses) when 0 then courses
else left(courses,charindex('|',courses)-1) end as int) course,
case charindex('|',courses) when 0 then ''
else right(courses,len(courses)-charindex('|',courses)) end courses
from cte
where len(courses)>0)
select distinct course from cte
SQLFiddle here.

split comma separated values into distinct rows

I have a table which looks like this:
id fk_det userid
3 9 name1,name2
6 1 name3
9 2 name4,name5
12 3 name6,name7
I have already learned to regret having the values of the userid in comma separated values, so i want to split the rows up and end up with something that looks like
id fk_det userid
3 9 name1
x 9 name2
6 1 name3
9 2 name4
x 2 name5
12 3 name6
x 3 name7
i had been looking at something like this:
select fk_det, det, LEFT(userid, CHARINDEX(',',userid+',')-1),
STUFF(userid, 1, CHARINDEX(',',userid+','), '')
from global_permissions
but i'm not sure how to make it work when userid contains more than 2 items (which it might, some might have none, some might have multiple, just depends)
this is what I tend to use:
IF EXISTS (
SELECT 1
FROM dbo.sysobjects
WHERE id = object_id(N'[dbo].[ParseString]')
AND xtype in (N'FN', N'IF', N'TF'))
BEGIN
DROP FUNCTION [dbo].[ParseString]
END
GO
CREATE FUNCTION dbo.ParseString (#String VARCHAR(8000), #Delimiter VARCHAR(10))
RETURNS TABLE
AS
/*******************************************************************************************************
* dbo.ParseString
*
* Creator: magicmike
* Date: 9/12/2006
*
*
* Outline: A set-based string tokenizer
* Takes a string that is delimited by another string (of one or more characters),
* parses it out into tokens and returns the tokens in table format. Leading
* and trailing spaces in each token are removed, and empty tokens are thrown
* away.
*
*
* Usage examples/test cases:
Single-byte delimiter:
select * from dbo.ParseString2('|HDI|TR|YUM|||', '|')
select * from dbo.ParseString2('HDI| || TR |YUM', '|')
select * from dbo.ParseString2(' HDI| || S P A C E S |YUM | ', '|')
select * from dbo.ParseString2('HDI|||TR|YUM', '|')
select * from dbo.ParseString2('', '|')
select * from dbo.ParseString2('YUM', '|')
select * from dbo.ParseString2('||||', '|')
select * from dbo.ParseString2('HDI TR YUM', ' ')
select * from dbo.ParseString2(' HDI| || S P A C E S |YUM | ', ' ') order by Ident
select * from dbo.ParseString2(' HDI| || S P A C E S |YUM | ', ' ') order by StringValue
Multi-byte delimiter:
select * from dbo.ParseString2('HDI and TR', 'and')
select * from dbo.ParseString2('Pebbles and Bamm Bamm', 'and')
select * from dbo.ParseString2('Pebbles and sandbars', 'and')
select * from dbo.ParseString2('Pebbles and sandbars', ' and ')
select * from dbo.ParseString2('Pebbles and sand', 'and')
select * from dbo.ParseString2('Pebbles and sand', ' and ')
*
*
* Notes:
1. A delimiter is optional. If a blank delimiter is given, each byte is returned in it's own row (including spaces).
select * from dbo.ParseString3('|HDI|TR|YUM|||', '')
2. In order to maintain compatibility with SQL 2000, ident is not sequential but can still be used in an order clause
If you are running on SQL2005 or later
SELECT Ident, StringValue FROM
with
SELECT Ident = ROW_NUMBER() OVER (ORDER BY ident), StringValue FROM
*
*
* Modifications
*
*
********************************************************************************************************/
RETURN (
SELECT Ident, StringValue FROM
(
SELECT Num as Ident,
CASE
WHEN DATALENGTH(#delimiter) = 0 or #delimiter IS NULL
THEN LTRIM(SUBSTRING(#string, num, 1)) --replace this line with '' if you prefer it to return nothing when no delimiter is supplied. Remove LTRIM if you want to return spaces when no delimiter is supplied
ELSE
LTRIM(RTRIM(SUBSTRING(#String,
CASE
WHEN (Num = 1 AND SUBSTRING(#String,num ,DATALENGTH(#delimiter)) <> #delimiter) THEN 1
ELSE Num + DATALENGTH(#delimiter)
END,
CASE CHARINDEX(#Delimiter, #String, Num + DATALENGTH(#delimiter))
WHEN 0 THEN LEN(#String) - Num + DATALENGTH(#delimiter)
ELSE CHARINDEX(#Delimiter, #String, Num + DATALENGTH(#delimiter)) - Num -
CASE
WHEN Num > 1 OR (Num = 1 AND SUBSTRING(#String,num ,DATALENGTH(#delimiter)) = #delimiter)
THEN DATALENGTH(#delimiter)
ELSE 0
END
END
)))
End AS StringValue
FROM dbo.Numbers
WHERE Num <= LEN(#String)
AND (
SUBSTRING(#String, Num, DATALENGTH(ISNULL(#delimiter,''))) = #Delimiter
OR Num = 1
OR DATALENGTH(ISNULL(#delimiter,'')) = 0
)
) R WHERE StringValue <> ''
)
You would use it like this:
SELECT id, pk_det, V.StringValue as userid
FROM myTable T
OUTER APPLY dbo.ParseString(T.userId) V
The UDF requires a 'tally' or Number table which assumes the following schema:
IF NOT EXISTS (SELECT * FROM INFORMATION_SCHEMA.TABLES WHERE TABLE_NAME = 'Numbers')
BEGIN
CREATE TABLE dbo.Numbers
(
Num INT NOT NULL
CONSTRAINT [PKC__Numbers__Num] PRIMARY KEY CLUSTERED (Num) on [PRIMARY]
)
;WITH Nbrs_3( n ) AS ( SELECT 1 UNION SELECT 0 ),
Nbrs_2( n ) AS ( SELECT 1 FROM Nbrs_3 n1 CROSS JOIN Nbrs_3 n2 ),
Nbrs_1( n ) AS ( SELECT 1 FROM Nbrs_2 n1 CROSS JOIN Nbrs_2 n2 ),
Nbrs_0( n ) AS ( SELECT 1 FROM Nbrs_1 n1 CROSS JOIN Nbrs_1 n2 ),
Nbrs ( n ) AS ( SELECT 1 FROM Nbrs_0 n1 CROSS JOIN Nbrs_0 n2 )
INSERT INTO dbo.Numbers(Num)
SELECT n
FROM ( SELECT ROW_NUMBER() OVER (ORDER BY n)
FROM Nbrs ) D ( n )
WHERE n <= 50000 ;
END
Numbers tables are an invaluable addition to your toolset. To quote Adam Machanic:
Numbers tables are truly invaluable. I use them all of the time for
string manipulation, simulating window functions, populating test
tables with lots of data, eliminating cursor logic, and many other
tasks that would be incredibly difficult without them.
Is using a table of numbers a hack, as I've seen some people claim?
No. Show me another way to efficiently do all of the things a numbers
table can. Does it waste space? No. The script below will use up
around 900 KB of disk space in each database. That's absolutely
nothing. You'll end up getting millions, maybe billions of times the
disk space investment back in terms of ease of development and time
saved.
http://dataeducation.com/you-require-a-numbers-table/
Try this :)
DECLARE #Name TABLE
(
id INT NULL ,
fk_det INT NULL ,
userid NVARCHAR(100) NULL
)
INSERT INTO #Name
( id, fk_det, userid)
VALUES (3,9,'name1,name2' )
INSERT INTO #Name
( id, fk_det, userid)
VALUES (6,1,'name3' )
INSERT INTO #Name
( id, fk_det, userid)
VALUES (9,2,'name4,name5' )
INSERT INTO #Name
( id, fk_det, userid)
VALUES (12,3,'name6,name7' )
SELECT *
FROM #Name
SELECT id,A.fk_det,
Split.a.value('.', 'VARCHAR(100)') AS String
FROM (SELECT id,fk_det,
CAST ('<M>' + REPLACE(userid, ',', '</M><M>') + '</M>' AS XML) AS String
FROM #Name) AS A CROSS APPLY String.nodes ('/M') AS Split(a);
As an alternative to the standard sproc call you see everywhere:
with temp as(
select id,fk_det,cast('<comma>'+replace(userid,',','</comma><comma>')+'</comma>' as XMLcomma
from global_permissions
)
select id,fk_det,a.value('comma[1]','varchar(512)')
cross apply temp.XMLcomma.nodes('/comma') t(a)