Get string between two specific characters - sql-server

Question

I have a table fileslist with column Filetext which contains text data
create table fileslist
(
FileID int identity (1,1),
Filetext nvarchar(max)
)
insert into fileslist select 'this file(''SQL_SCALAR1'') has been created to test your tricks of (''SQL_SCALAR2'')'
insert into fileslist select 'this file(''SCALAR3'') created to test your tricks of (''SQL_SCALAR4'')'
insert into fileslist select 'this file(''SQL_SCALAR5'') has been created to test your tricks of (''SQL_SCALAR6'')'
insert into fileslist select 'this file(''SQL_7'') has been created'
insert into fileslist select 'this file(''SQL_SCALAR8'') has been created to test your tricks of (''SQL_SCALAR9''), ohh i have more text than other (''SQL_SCALAR10'')files'
I need help to read all records one by one to extract string between two specific characters '(' and ')' and Output should be
SQL_SCALAR1
SQL_SCALAR2
SCALAR3
SQL_SCALAR4
SQL_SCALAR5
SQL_SCALAR6
SQL_7
SQL_SCALAR8
SQL_SCALAR9
SQL_SCALAR10

Answer 1

The reason I would choose this approach is that it handles a dynamic number of the patterns you are searching for, per row, very well.
First I would use Jeff Moden's string splitter;
/*
* Jeff Moden's famous string spliiter
* http://www.sqlservercentral.com/articles/Tally+Table/72993/
*/
CREATE FUNCTION [dbo].[DelimitedSplit8K]
--===== Define I/O parameters
(#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
;
Then, I would write the following;
SELECT SUBSTRING (
Item,
2,
CHARINDEX(')', Item) - 3
)
FROM FilesList
CROSS
APPLY [dbo].[DelimitedSplit8K](FileText, '(')
WHERE Item LIKE '''SQL%'
As requested in comment; (I'm not thrilled about butchering Jeff's code this way...)
CREATE FUNCTION [dbo].[DelimitedSplit8K_Butchered]
--===== Define I/O parameters
(#pString VARCHAR(8000), #DelimiterA CHAR(1), #DelimiterB 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) = #DelimiterA
),
cteLen(N1,L1) AS(--==== Return start and length (for use in substring)
SELECT s.N1,
ISNULL(NULLIF(CHARINDEX(#DelimiterA,#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.
OriginalOutput AS
(
SELECT ItemNumber = ROW_NUMBER() OVER(ORDER BY l.N1),
Item = SUBSTRING(#pString, l.N1, l.L1)
FROM cteLen l
)
SELECT
Item = SUBSTRING (
Item,
1,
CHARINDEX(#DelimiterB, Item) - 1
)
FROM OriginalOutput
WHERE Item LIKE '%' + #DelimiterB + '%'
--AND SUBSTRING(#pString, l.N1, l.L1) LIKE '%' + #DelimiterB + '%'
;
GO
Used as follows;
SELECT *
FROM FilesList
CROSS
APPLY [dbo].[DelimitedSplit8K_Butchered](FileText, '(', ')')

Answer 2

declare #ss varchar(100)= 'this file(''SQL_SCALAR1'') has been created to test your tricks of (''SQL_SCALAR2'')'
Not sure how you want to display
SELECT SUBSTRING ( (LEFT(#ss,CHARINDEX(')',#ss) - 1)),CHARINDEX('(',#ss)+1,LEN(LEFT(#ss,CHARINDEX(')',#ss) - 1))),
SUBSTRING ((RIGHT(#ss,CHARINDEX('(',REVERSE(#ss)) - 1)),1,LEN(RIGHT(#ss,CHARINDEX('(',REVERSE(#ss)) - 1))-1)
OR
SELECT SUBSTRING ( (LEFT(#ss,CHARINDEX(')',#ss) - 1)),CHARINDEX('(',#ss)+1,LEN(LEFT(#ss,CHARINDEX(')',#ss) - 1)))
Union
SELECT SUBSTRING ((RIGHT(#ss,CHARINDEX('(',REVERSE(#ss)) - 1)),1,LEN(RIGHT(#ss,CHARINDEX('(',REVERSE(#ss)) - 1))-1)

Answer 3

this is the solution what you are looking for, cheer....
;WITH CTE AS
(
SELECT SUBSTRING(FILETEXT,CHARINDEX('(',FileText,1)+2,11) 'Result'
FROM FILESLIST
UNION ALL
SELECT * FROM
(
SELECT
SUBSTRING(
(SUBSTRING(FILETEXT,CHARINDEX(')',FILETEXT,1)+1,LEN(FILETEXT)-
CHARINDEX(')',FILETEXT,1)) )
,CHARINDEX('(',(SUBSTRING(FILETEXT,CHARINDEX(')',FILETEXT,1)+1,LEN(FILETEXT)-
CHARINDEX(')',FILETEXT,1)) ) ,1)+2,11
) 'Result'
FROM FILESLIST
) T1
WHERE Result like '%SQL%'
)
SELECT * FROM CTE
ORDER BY RESULT ASC

Answer 4

A solution with recursive CTE is
WITH REP AS (
SELECT FileID
, Filetext = REPLACE(Filetext, ')', '(')
FROM fileslist
), Splitter AS (
SELECT FileID
, FileText
, NextStart = CHARINDEX('(', FileText)
, Pos = 0
, Token = CAST(SubString(FileText, 0, CHARINDEX('(', FileText))
AS NVarchar(50))
FROM REP
UNION ALL
SELECT FileId
, FileText
, NextStart = CHARINDEX('(', FileText, NextStart + 1)
, Pos = Pos + 1
, Token = CAST(SubString(FileText, NextStart + 1
, CHARINDEX('(', FileText, NextStart + 1)
- NextStart - 1) AS NVarchar(50))
FROM Splitter
WHERE CHARINDEX('(', FileText, NextStart + 1) - NextStart - 1 > 0
)
SELECT FileID, Token
FROM REC
WHERE Pos % 2 = 1
order by FileID, Pos
The Splitter CTE split the rows using a single delimiter, so before use it we need to make the two delimiter the same. Only the odd token are returned by the main query because the even token are other part of the string, for example the string 'this file(''SQL_7'') has been created' will be returned by the Splitter like (with only the interesting columns):
Pos | Token
----+------------------
0 | this file
1 | SQL_7
2 | has been created