How to get the abbreviation of a word in TSQL? - sql-server

For example, if I have an input string "OrderTrackingNumber", I want it to return "OTN". Or if I have an input string "MyOrder", I want it to return MO.

Providing your column names are always camel cased with the first letter capitalised, you can use the following:
create function fn_extractupper(#var varchar(50))
returns varchar(50)
as
begin
declare #aux varchar(50) = ''
declare #size int = len(#var)
declare #position int = 0
while #position < #size
begin
if ASCII(SUBSTRING(#var,#position,1)) = ASCII(UPPER(SUBSTRING(#var,#position,1)))
begin
set #aux = #aux + SUBSTRING(#var,#position,1)
end
set #position = #position + 1
end
return #aux
END

Starting with SQL Server 2017 you should read about the new function TRANSLATE. Together with a case sensitive collation this should be good for your issue.
But most people don't have this version (me too). So you might try this:
DECLARE #mockupTable TABLE(ID INT IDENTITY, InputString VARCHAR(100));
INSERT INTO #mockupTable VALUES('OrderTrackingNumber')
,('MyOrder')
,('OneMoreExample');
WITH recCTE AS
(
SELECT ID
,InputString
,2 AS NextPos
,SUBSTRING(InputString,1,1) AS Letter
FROM #mockupTable AS mt
UNION ALL
SELECT r.ID
,r.InputString
,r.NextPos+1
,SUBSTRING(r.InputString,r.NextPos,1)
FROM recCTE AS r
WHERE r.NextPos<LEN(r.InputString)+1
)
SELECT r1.ID
,(
SELECT r2.Letter AS [*]
FROM recCTE AS r2
WHERE ASCII(r2.Letter) BETWEEN ASCII('A') AND ASCII('Z')
AND r1.ID=r2.ID
FOR XML PATH('')
)
FROM recCTE AS r1
GROUP BY r1.ID
The recursive CTE will walk along the letters and return them one by one.
The final query uses a grouping query outside and a sub-select, returned as XML.
This will be the re-concatenated string.
Without the inner WHERE checking for the ASCII() values the result would be exactly the same as the initial values.

Related

PIVOT the data from single column in sql server [duplicate]

I have a table like this
Value String
-------------------
1 Cleo, Smith
I want to separate the comma delimited string into two columns
Value Name Surname
-------------------
1 Cleo Smith
I need only two fixed extra columns
Your purpose can be solved using following query -
Select Value , Substring(FullName, 1,Charindex(',', FullName)-1) as Name,
Substring(FullName, Charindex(',', FullName)+1, LEN(FullName)) as Surname
from Table1
There is no readymade Split function in sql server, so we need to create user defined function.
CREATE FUNCTION Split (
#InputString VARCHAR(8000),
#Delimiter VARCHAR(50)
)
RETURNS #Items TABLE (
Item VARCHAR(8000)
)
AS
BEGIN
IF #Delimiter = ' '
BEGIN
SET #Delimiter = ','
SET #InputString = REPLACE(#InputString, ' ', #Delimiter)
END
IF (#Delimiter IS NULL OR #Delimiter = '')
SET #Delimiter = ','
--INSERT INTO #Items VALUES (#Delimiter) -- Diagnostic
--INSERT INTO #Items VALUES (#InputString) -- Diagnostic
DECLARE #Item VARCHAR(8000)
DECLARE #ItemList VARCHAR(8000)
DECLARE #DelimIndex INT
SET #ItemList = #InputString
SET #DelimIndex = CHARINDEX(#Delimiter, #ItemList, 0)
WHILE (#DelimIndex != 0)
BEGIN
SET #Item = SUBSTRING(#ItemList, 0, #DelimIndex)
INSERT INTO #Items VALUES (#Item)
-- Set #ItemList = #ItemList minus one less item
SET #ItemList = SUBSTRING(#ItemList, #DelimIndex+1, LEN(#ItemList)-#DelimIndex)
SET #DelimIndex = CHARINDEX(#Delimiter, #ItemList, 0)
END -- End WHILE
IF #Item IS NOT NULL -- At least one delimiter was encountered in #InputString
BEGIN
SET #Item = #ItemList
INSERT INTO #Items VALUES (#Item)
END
-- No delimiters were encountered in #InputString, so just return #InputString
ELSE INSERT INTO #Items VALUES (#InputString)
RETURN
END -- End Function
GO
---- Set Permissions
--GRANT SELECT ON Split TO UserRole1
--GRANT SELECT ON Split TO UserRole2
--GO
;WITH Split_Names (Value,Name, xmlname)
AS
(
SELECT Value,
Name,
CONVERT(XML,'<Names><name>'
+ REPLACE(Name,',', '</name><name>') + '</name></Names>') AS xmlname
FROM tblnames
)
SELECT Value,
xmlname.value('/Names[1]/name[1]','varchar(100)') AS Name,
xmlname.value('/Names[1]/name[2]','varchar(100)') AS Surname
FROM Split_Names
and also check the link below for reference
http://jahaines.blogspot.in/2009/06/converting-delimited-string-of-values.html
xml based answer is simple and clean
refer this
DECLARE #S varchar(max),
#Split char(1),
#X xml
SELECT #S = 'ab,cd,ef,gh,ij',
#Split = ','
SELECT #X = CONVERT(xml,' <root> <myvalue>' +
REPLACE(#S,#Split,'</myvalue> <myvalue>') + '</myvalue> </root> ')
SELECT T.c.value('.','varchar(20)'), --retrieve ALL values at once
T.c.value('(/root/myvalue)[1]','VARCHAR(20)') , --retrieve index 1 only, which is the 'ab'
T.c.value('(/root/myvalue)[2]','VARCHAR(20)')
FROM #X.nodes('/root/myvalue') T(c)
I think this is cool
SELECT value,
PARSENAME(REPLACE(String,',','.'),2) 'Name' ,
PARSENAME(REPLACE(String,',','.'),1) 'Surname'
FROM table WITH (NOLOCK)
With CROSS APPLY
select ParsedData.*
from MyTable mt
cross apply ( select str = mt.String + ',,' ) f1
cross apply ( select p1 = charindex( ',', str ) ) ap1
cross apply ( select p2 = charindex( ',', str, p1 + 1 ) ) ap2
cross apply ( select Nmame = substring( str, 1, p1-1 )
, Surname = substring( str, p1+1, p2-p1-1 )
) ParsedData
There are multiple ways to solve this and many different ways have been proposed already. Simplest would be to use LEFT / SUBSTRING and other string functions to achieve the desired result.
Sample Data
DECLARE #tbl1 TABLE (Value INT,String VARCHAR(MAX))
INSERT INTO #tbl1 VALUES(1,'Cleo, Smith');
INSERT INTO #tbl1 VALUES(2,'John, Mathew');
Using String Functions like LEFT
SELECT
Value,
LEFT(String,CHARINDEX(',',String)-1) as Fname,
LTRIM(RIGHT(String,LEN(String) - CHARINDEX(',',String) )) AS Lname
FROM #tbl1
This approach fails if there are more 2 items in a String.
In such a scenario, we can use a splitter and then use PIVOT or convert the string into an XML and use .nodes to get string items. XML based solution have been detailed out by aads and bvr in their solution.
The answers for this question which use splitter, all use WHILE which is inefficient for splitting. Check this performance comparison. One of the best splitters around is DelimitedSplit8K, created by Jeff Moden. You can read more about it here
Splitter with PIVOT
DECLARE #tbl1 TABLE (Value INT,String VARCHAR(MAX))
INSERT INTO #tbl1 VALUES(1,'Cleo, Smith');
INSERT INTO #tbl1 VALUES(2,'John, Mathew');
SELECT t3.Value,[1] as Fname,[2] as Lname
FROM #tbl1 as t1
CROSS APPLY [dbo].[DelimitedSplit8K](String,',') as t2
PIVOT(MAX(Item) FOR ItemNumber IN ([1],[2])) as t3
Output
Value Fname Lname
1 Cleo Smith
2 John Mathew
DelimitedSplit8K by Jeff Moden
CREATE FUNCTION [dbo].[DelimitedSplit8K]
/**********************************************************************************************************************
Purpose:
Split a given string at a given delimiter and return a list of the split elements (items).
Notes:
1. Leading a trailing delimiters are treated as if an empty string element were present.
2. Consecutive delimiters are treated as if an empty string element were present between them.
3. Except when spaces are used as a delimiter, all spaces present in each element are preserved.
Returns:
iTVF containing the following:
ItemNumber = Element position of Item as a BIGINT (not converted to INT to eliminate a CAST)
Item = Element value as a VARCHAR(8000)
Statistics on this function may be found at the following URL:
http://www.sqlservercentral.com/Forums/Topic1101315-203-4.aspx
CROSS APPLY Usage Examples and Tests:
--=====================================================================================================================
-- TEST 1:
-- This tests for various possible conditions in a string using a comma as the delimiter. The expected results are
-- laid out in the comments
--=====================================================================================================================
--===== Conditionally drop the test tables to make reruns easier for testing.
-- (this is NOT a part of the solution)
IF OBJECT_ID('tempdb..#JBMTest') IS NOT NULL DROP TABLE #JBMTest
;
--===== Create and populate a test table on the fly (this is NOT a part of the solution).
-- In the following comments, "b" is a blank and "E" is an element in the left to right order.
-- Double Quotes are used to encapsulate the output of "Item" so that you can see that all blanks
-- are preserved no matter where they may appear.
SELECT *
INTO #JBMTest
FROM ( --# & type of Return Row(s)
SELECT 0, NULL UNION ALL --1 NULL
SELECT 1, SPACE(0) UNION ALL --1 b (Empty String)
SELECT 2, SPACE(1) UNION ALL --1 b (1 space)
SELECT 3, SPACE(5) UNION ALL --1 b (5 spaces)
SELECT 4, ',' UNION ALL --2 b b (both are empty strings)
SELECT 5, '55555' UNION ALL --1 E
SELECT 6, ',55555' UNION ALL --2 b E
SELECT 7, ',55555,' UNION ALL --3 b E b
SELECT 8, '55555,' UNION ALL --2 b B
SELECT 9, '55555,1' UNION ALL --2 E E
SELECT 10, '1,55555' UNION ALL --2 E E
SELECT 11, '55555,4444,333,22,1' UNION ALL --5 E E E E E
SELECT 12, '55555,4444,,333,22,1' UNION ALL --6 E E b E E E
SELECT 13, ',55555,4444,,333,22,1,' UNION ALL --8 b E E b E E E b
SELECT 14, ',55555,4444,,,333,22,1,' UNION ALL --9 b E E b b E E E b
SELECT 15, ' 4444,55555 ' UNION ALL --2 E (w/Leading Space) E (w/Trailing Space)
SELECT 16, 'This,is,a,test.' --E E E E
) d (SomeID, SomeValue)
;
--===== Split the CSV column for the whole table using CROSS APPLY (this is the solution)
SELECT test.SomeID, test.SomeValue, split.ItemNumber, Item = QUOTENAME(split.Item,'"')
FROM #JBMTest test
CROSS APPLY dbo.DelimitedSplit8K(test.SomeValue,',') split
;
--=====================================================================================================================
-- TEST 2:
-- This tests for various "alpha" splits and COLLATION using all ASCII characters from 0 to 255 as a delimiter against
-- a given string. Note that not all of the delimiters will be visible and some will show up as tiny squares because
-- they are "control" characters. More specifically, this test will show you what happens to various non-accented
-- letters for your given collation depending on the delimiter you chose.
--=====================================================================================================================
WITH
cteBuildAllCharacters (String,Delimiter) AS
(
SELECT TOP 256
'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789',
CHAR(ROW_NUMBER() OVER (ORDER BY (SELECT NULL))-1)
FROM master.sys.all_columns
)
SELECT ASCII_Value = ASCII(c.Delimiter), c.Delimiter, split.ItemNumber, Item = QUOTENAME(split.Item,'"')
FROM cteBuildAllCharacters c
CROSS APPLY dbo.DelimitedSplit8K(c.String,c.Delimiter) split
ORDER BY ASCII_Value, split.ItemNumber
;
-----------------------------------------------------------------------------------------------------------------------
Other Notes:
1. Optimized for VARCHAR(8000) or less. No testing or error reporting for truncation at 8000 characters is done.
2. Optimized for single character delimiter. Multi-character delimiters should be resolvedexternally from this
function.
3. Optimized for use with CROSS APPLY.
4. Does not "trim" elements just in case leading or trailing blanks are intended.
5. If you don't know how a Tally table can be used to replace loops, please see the following...
http://www.sqlservercentral.com/articles/T-SQL/62867/
6. Changing this function to use NVARCHAR(MAX) will cause it to run twice as slow. It's just the nature of
VARCHAR(MAX) whether it fits in-row or not.
7. Multi-machine testing for the method of using UNPIVOT instead of 10 SELECT/UNION ALLs shows that the UNPIVOT method
is quite machine dependent and can slow things down quite a bit.
-----------------------------------------------------------------------------------------------------------------------
Credits:
This code is the product of many people's efforts including but not limited to the following:
cteTally concept originally by Iztek Ben Gan and "decimalized" by Lynn Pettis (and others) for a bit of extra speed
and finally redacted by Jeff Moden for a different slant on readability and compactness. Hat's off to Paul White for
his simple explanations of CROSS APPLY and for his detailed testing efforts. Last but not least, thanks to
Ron "BitBucket" McCullough and Wayne Sheffield for their extreme performance testing across multiple machines and
versions of SQL Server. The latest improvement brought an additional 15-20% improvement over Rev 05. Special thanks
to "Nadrek" and "peter-757102" (aka Peter de Heer) for bringing such improvements to light. Nadrek's original
improvement brought about a 10% performance gain and Peter followed that up with the content of Rev 07.
I also thank whoever wrote the first article I ever saw on "numbers tables" which is located at the following URL
and to Adam Machanic for leading me to it many years ago.
http://sqlserver2000.databases.aspfaq.com/why-should-i-consider-using-an-auxiliary-numbers-table.html
-----------------------------------------------------------------------------------------------------------------------
Revision History:
Rev 00 - 20 Jan 2010 - Concept for inline cteTally: Lynn Pettis and others.
Redaction/Implementation: Jeff Moden
- Base 10 redaction and reduction for CTE. (Total rewrite)
Rev 01 - 13 Mar 2010 - Jeff Moden
- Removed one additional concatenation and one subtraction from the SUBSTRING in the SELECT List for that tiny
bit of extra speed.
Rev 02 - 14 Apr 2010 - Jeff Moden
- No code changes. Added CROSS APPLY usage example to the header, some additional credits, and extra
documentation.
Rev 03 - 18 Apr 2010 - Jeff Moden
- No code changes. Added notes 7, 8, and 9 about certain "optimizations" that don't actually work for this
type of function.
Rev 04 - 29 Jun 2010 - Jeff Moden
- Added WITH SCHEMABINDING thanks to a note by Paul White. This prevents an unnecessary "Table Spool" when the
function is used in an UPDATE statement even though the function makes no external references.
Rev 05 - 02 Apr 2011 - Jeff Moden
- Rewritten for extreme performance improvement especially for larger strings approaching the 8K boundary and
for strings that have wider elements. The redaction of this code involved removing ALL concatenation of
delimiters, optimization of the maximum "N" value by using TOP instead of including it in the WHERE clause,
and the reduction of all previous calculations (thanks to the switch to a "zero based" cteTally) to just one
instance of one add and one instance of a subtract. The length calculation for the final element (not
followed by a delimiter) in the string to be split has been greatly simplified by using the ISNULL/NULLIF
combination to determine when the CHARINDEX returned a 0 which indicates there are no more delimiters to be
had or to start with. Depending on the width of the elements, this code is between 4 and 8 times faster on a
single CPU box than the original code especially near the 8K boundary.
- Modified comments to include more sanity checks on the usage example, etc.
- Removed "other" notes 8 and 9 as they were no longer applicable.
Rev 06 - 12 Apr 2011 - Jeff Moden
- Based on a suggestion by Ron "Bitbucket" McCullough, additional test rows were added to the sample code and
the code was changed to encapsulate the output in pipes so that spaces and empty strings could be perceived
in the output. The first "Notes" section was added. Finally, an extra test was added to the comments above.
Rev 07 - 06 May 2011 - Peter de Heer, a further 15-20% performance enhancement has been discovered and incorporated
into this code which also eliminated the need for a "zero" position in the cteTally table.
**********************************************************************************************************************/
--===== Define I/O parameters
(#pString VARCHAR(8000), #pDelimiter CHAR(1))
RETURNS TABLE WITH SCHEMABINDING AS
RETURN
--===== "Inline" CTE Driven "Tally Table" produces values from 0 up to 10,000...
-- enough to cover NVARCHAR(4000)
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
With SQL Server 2016 we can use string_split to accomplish this:
create table commasep (
id int identity(1,1)
,string nvarchar(100) )
insert into commasep (string) values ('John, Adam'), ('test1,test2,test3')
select id, [value] as String from commasep
cross apply string_split(string,',')
CREATE FUNCTION [dbo].[fn_split_string_to_column] (
#string NVARCHAR(MAX),
#delimiter CHAR(1)
)
RETURNS #out_put TABLE (
[column_id] INT IDENTITY(1, 1) NOT NULL,
[value] NVARCHAR(MAX)
)
AS
BEGIN
DECLARE #value NVARCHAR(MAX),
#pos INT = 0,
#len INT = 0
SET #string = CASE
WHEN RIGHT(#string, 1) != #delimiter
THEN #string + #delimiter
ELSE #string
END
WHILE CHARINDEX(#delimiter, #string, #pos + 1) > 0
BEGIN
SET #len = CHARINDEX(#delimiter, #string, #pos + 1) - #pos
SET #value = SUBSTRING(#string, #pos, #len)
INSERT INTO #out_put ([value])
SELECT LTRIM(RTRIM(#value)) AS [column]
SET #pos = CHARINDEX(#delimiter, #string, #pos + #len) + 1
END
RETURN
END
SELECT id,
Substring(NAME, 0, Charindex(',', NAME)) AS firstname,
Substring(NAME, Charindex(',', NAME), Len(NAME) + 1) AS lastname
FROM spilt
Try this (change instances of ' ' to ',' or whatever delimiter you want to use)
CREATE FUNCTION dbo.Wordparser
(
#multiwordstring VARCHAR(255),
#wordnumber NUMERIC
)
returns VARCHAR(255)
AS
BEGIN
DECLARE #remainingstring VARCHAR(255)
SET #remainingstring=#multiwordstring
DECLARE #numberofwords NUMERIC
SET #numberofwords=(LEN(#remainingstring) - LEN(REPLACE(#remainingstring, ' ', '')) + 1)
DECLARE #word VARCHAR(50)
DECLARE #parsedwords TABLE
(
line NUMERIC IDENTITY(1, 1),
word VARCHAR(255)
)
WHILE #numberofwords > 1
BEGIN
SET #word=LEFT(#remainingstring, CHARINDEX(' ', #remainingstring) - 1)
INSERT INTO #parsedwords(word)
SELECT #word
SET #remainingstring= REPLACE(#remainingstring, Concat(#word, ' '), '')
SET #numberofwords=(LEN(#remainingstring) - LEN(REPLACE(#remainingstring, ' ', '')) + 1)
IF #numberofwords = 1
BREAK
ELSE
CONTINUE
END
IF #numberofwords = 1
SELECT #word = #remainingstring
INSERT INTO #parsedwords(word)
SELECT #word
RETURN
(SELECT word
FROM #parsedwords
WHERE line = #wordnumber)
END
Example usage:
SELECT dbo.Wordparser(COLUMN, 1),
dbo.Wordparser(COLUMN, 2),
dbo.Wordparser(COLUMN, 3)
FROM TABLE
I think PARSENAME is the neat function to use for this example, as described in this article: http://www.sqlshack.com/parsing-and-rotating-delimited-data-in-sql-server-2012/
The PARSENAME function is logically designed to parse four-part object names. The nice thing about PARSENAME is that it’s not limited to parsing just SQL Server four-part object names – it will parse any function or string data that is delimited by dots.
The first parameter is the object to parse, and the second is the integer value of the object piece to return. The article is discussing parsing and rotating delimited data - company phone numbers, but it can be used to parse name/surname data also.
Example:
USE COMPANY;
SELECT PARSENAME('Whatever.you.want.parsed',3) AS 'ReturnValue';
The article also describes using a Common Table Expression (CTE) called ‘replaceChars’, to run PARSENAME against the delimiter-replaced values. A CTE is useful for returning a temporary view or result set.
After that, the UNPIVOT function has been used to convert some columns into rows; SUBSTRING and CHARINDEX functions have been used for cleaning up the inconsistencies in the data, and the LAG function (new for SQL Server 2012) has been used in the end, as it allows referencing of previous records.
We can create a function as this
CREATE Function [dbo].[fn_CSVToTable]
(
#CSVList Varchar(max)
)
RETURNS #Table TABLE (ColumnData VARCHAR(100))
AS
BEGIN
IF RIGHT(#CSVList, 1) <> ','
SELECT #CSVList = #CSVList + ','
DECLARE #Pos BIGINT,
#OldPos BIGINT
SELECT #Pos = 1,
#OldPos = 1
WHILE #Pos < LEN(#CSVList)
BEGIN
SELECT #Pos = CHARINDEX(',', #CSVList, #OldPos)
INSERT INTO #Table
SELECT LTRIM(RTRIM(SUBSTRING(#CSVList, #OldPos, #Pos - #OldPos))) Col001
SELECT #OldPos = #Pos + 1
END
RETURN
END
We can then seperate the CSV values into our respective columns using a SELECT statement
You can use a table-valued function STRING_SPLIT, which is available only under compatibility level 130. If your database compatibility level is lower than 130, SQL Server will not be able to find and execute the STRING_SPLIT function. You can change a compatibility level of the database using the following command:
ALTER DATABASE DatabaseName SET COMPATIBILITY_LEVEL = 130
Syntax
SELECT * FROM STRING_SPLIT ( string, separator )
see documentation here
I think following function will work for you:
You have to create a function in SQL first. Like this
CREATE FUNCTION [dbo].[fn_split](
#str VARCHAR(MAX),
#delimiter CHAR(1)
)
RETURNS #returnTable TABLE (idx INT PRIMARY KEY IDENTITY, item VARCHAR(8000))
AS
BEGIN
DECLARE #pos INT
SELECT #str = #str + #delimiter
WHILE LEN(#str) > 0
BEGIN
SELECT #pos = CHARINDEX(#delimiter,#str)
IF #pos = 1
INSERT #returnTable (item)
VALUES (NULL)
ELSE
INSERT #returnTable (item)
VALUES (SUBSTRING(#str, 1, #pos-1))
SELECT #str = SUBSTRING(#str, #pos+1, LEN(#str)-#pos)
END
RETURN
END
You can call this function, like this:
select * from fn_split('1,24,5',',')
Implementation:
Declare #test TABLE (
ID VARCHAR(200),
Data VARCHAR(200)
)
insert into #test
(ID, Data)
Values
('1','Cleo,Smith')
insert into #test
(ID, Data)
Values
('2','Paul,Grim')
select ID,
(select item from fn_split(Data,',') where idx in (1)) as Name ,
(select item from fn_split(Data,',') where idx in (2)) as Surname
from #test
Result will like this:
Use Parsename() function
with cte as(
select 'Aria,Karimi' as FullName
Union
select 'Joe,Karimi' as FullName
Union
select 'Bab,Karimi' as FullName
)
SELECT PARSENAME(REPLACE(FullName,',','.'),2) as Name,
PARSENAME(REPLACE(FullName,',','.'),1) as Family
FROM cte
Result
Name Family
----- ------
Aria Karimi
Bab Karimi
Joe Karimi
Try this:
declare #csv varchar(100) ='aaa,bb,csda,daass';
set #csv = #csv+',';
with cte as
(
select SUBSTRING(#csv,1,charindex(',',#csv,1)-1) as val, SUBSTRING(#csv,charindex(',',#csv,1)+1,len(#csv)) as rem
UNION ALL
select SUBSTRING(a.rem,1,charindex(',',a.rem,1)-1)as val, SUBSTRING(a.rem,charindex(',',a.rem,1)+1,len(A.rem))
from cte a where LEN(a.rem)>=1
) select val from cte
This function is most fast:
CREATE FUNCTION dbo.F_ExtractSubString
(
#String VARCHAR(MAX),
#NroSubString INT,
#Separator VARCHAR(5)
)
RETURNS VARCHAR(MAX) AS
BEGIN
DECLARE #St INT = 0, #End INT = 0, #Ret VARCHAR(MAX)
SET #String = #String + #Separator
WHILE CHARINDEX(#Separator, #String, #End + 1) > 0 AND #NroSubString > 0
BEGIN
SET #St = #End + 1
SET #End = CHARINDEX(#Separator, #String, #End + 1)
SET #NroSubString = #NroSubString - 1
END
IF #NroSubString > 0
SET #Ret = ''
ELSE
SET #Ret = SUBSTRING(#String, #St, #End - #St)
RETURN #Ret
END
GO
Example usage:
SELECT dbo.F_ExtractSubString(COLUMN, 1, ', '),
dbo.F_ExtractSubString(COLUMN, 2, ', '),
dbo.F_ExtractSubString(COLUMN, 3, ', ')
FROM TABLE
I encountered a similar problem but a complex one and since this is the first thread i found regarding that issue i decided to post my finding. i know it is complex solution to a simple problem but i hope that i could help other people who go to this thread looking for a more complex solution. i had to split a string containing 5 numbers (column name: levelsFeed) and to show each number in a separate column.
for example: 8,1,2,2,2
should be shown as :
1 2 3 4 5
-------------
8 1 2 2 2
Solution 1: using XML functions:
this solution for the slowest solution by far
SELECT Distinct FeedbackID,
, S.a.value('(/H/r)[1]', 'INT') AS level1
, S.a.value('(/H/r)[2]', 'INT') AS level2
, S.a.value('(/H/r)[3]', 'INT') AS level3
, S.a.value('(/H/r)[4]', 'INT') AS level4
, S.a.value('(/H/r)[5]', 'INT') AS level5
FROM (
SELECT *,CAST (N'<H><r>' + REPLACE(levelsFeed, ',', '</r><r>') + '</r> </H>' AS XML) AS [vals]
FROM Feedbacks
) as d
CROSS APPLY d.[vals].nodes('/H/r') S(a)
Solution 2: using Split function and pivot. (the split function split a string to rows with the column name Data)
SELECT FeedbackID, [1],[2],[3],[4],[5]
FROM (
SELECT *, ROW_NUMBER() OVER (PARTITION BY feedbackID ORDER BY (SELECT null)) as rn
FROM (
SELECT FeedbackID, levelsFeed
FROM Feedbacks
) as a
CROSS APPLY dbo.Split(levelsFeed, ',')
) as SourceTable
PIVOT
(
MAX(data)
FOR rn IN ([1],[2],[3],[4],[5])
)as pivotTable
Solution 3: using string manipulations functions - fastest by small margin over solution 2
SELECT FeedbackID,
SUBSTRING(levelsFeed,0,CHARINDEX(',',levelsFeed)) AS level1,
PARSENAME(REPLACE(SUBSTRING(levelsFeed,CHARINDEX(',',levelsFeed)+1,LEN(levelsFeed)),',','.'),4) AS level2,
PARSENAME(REPLACE(SUBSTRING(levelsFeed,CHARINDEX(',',levelsFeed)+1,LEN(levelsFeed)),',','.'),3) AS level3,
PARSENAME(REPLACE(SUBSTRING(levelsFeed,CHARINDEX(',',levelsFeed)+1,LEN(levelsFeed)),',','.'),2) AS level4,
PARSENAME(REPLACE(SUBSTRING(levelsFeed,CHARINDEX(',',levelsFeed)+1,LEN(levelsFeed)),',','.'),1) AS level5
FROM Feedbacks
since the levelsFeed contains 5 string values i needed to use the substring function for the first string.
i hope that my solution will help other that got to this thread looking for a more complex split to columns methods
Using instring function :)
select Value,
substring(String,1,instr(String," ") -1) Fname,
substring(String,instr(String,",") +1) Sname
from tablename;
Used two functions,
1. substring(string, position, length) ==> returns string from positon to length
2. instr(string,pattern) ==> returns position of pattern.
If we don’t provide length argument in substring it returns until end of string
This worked for me
CREATE FUNCTION [dbo].[SplitString](
#delimited NVARCHAR(MAX),
#delimiter NVARCHAR(100)
) RETURNS #t TABLE ( val NVARCHAR(MAX))
AS
BEGIN
DECLARE #xml XML
SET #xml = N'<t>' + REPLACE(#delimited,#delimiter,'</t><t>') + '</t>'
INSERT INTO #t(val)
SELECT r.value('.','varchar(MAX)') as item
FROM #xml.nodes('/t') as records(r)
RETURN
END
mytable:
Value ColOne
--------------------
1 Cleo, Smith
The following should work if there aren't too many columns
ALTER TABLE mytable ADD ColTwo nvarchar(256);
UPDATE mytable SET ColTwo = LEFT(ColOne, Charindex(',', ColOne) - 1);
--'Cleo' = LEFT('Cleo, Smith', Charindex(',', 'Cleo, Smith') - 1)
UPDATE mytable SET ColTwo = REPLACE(ColOne, ColTwo + ',', '');
--' Smith' = REPLACE('Cleo, Smith', 'Cleo' + ',')
UPDATE mytable SET ColOne = REPLACE(ColOne, ',' + ColTwo, ''), ColTwo = LTRIM(ColTwo);
--'Cleo' = REPLACE('Cleo, Smith', ',' + ' Smith', '')
Result:
Value ColOne ColTwo
--------------------
1 Cleo Smith
DECLARE #INPUT VARCHAR (MAX)='N,A,R,E,N,D,R,A'
DECLARE #ELIMINATE_CHAR CHAR (1)=','
DECLARE #L_START INT=1
DECLARE #L_END INT=(SELECT LEN (#INPUT))
DECLARE #OUTPUT CHAR (1)
WHILE #L_START <=#L_END
BEGIN
SET #OUTPUT=(SUBSTRING (#INPUT,#L_START,1))
IF #OUTPUT!=#ELIMINATE_CHAR
BEGIN
PRINT #OUTPUT
END
SET #L_START=#L_START+1
END
You may find the solution in SQL User Defined Function to Parse a Delimited String helpful (from The Code Project).
This is the code part from this page:
CREATE FUNCTION [fn_ParseText2Table]
(#p_SourceText VARCHAR(MAX)
,#p_Delimeter VARCHAR(100)=',' --default to comma delimited.
)
RETURNS #retTable
TABLE([Position] INT IDENTITY(1,1)
,[Int_Value] INT
,[Num_Value] NUMERIC(18,3)
,[Txt_Value] VARCHAR(MAX)
,[Date_value] DATETIME
)
AS
/*
********************************************************************************
Purpose: Parse values from a delimited string
& return the result as an indexed table
Copyright 1996, 1997, 2000, 2003 Clayton Groom (Clayton_Groom#hotmail.com)
Posted to the public domain Aug, 2004
2003-06-17 Rewritten as SQL 2000 function.
Reworked to allow for delimiters > 1 character in length
and to convert Text values to numbers
2016-04-05 Added logic for date values based on "new" ISDATE() function, Updated to use XML approach, which is more efficient.
********************************************************************************
*/
BEGIN
DECLARE #w_xml xml;
SET #w_xml = N'<root><i>' + replace(#p_SourceText, #p_Delimeter,'</i><i>') + '</i></root>';
INSERT INTO #retTable
([Int_Value]
, [Num_Value]
, [Txt_Value]
, [Date_value]
)
SELECT CASE
WHEN ISNUMERIC([i].value('.', 'VARCHAR(MAX)')) = 1
THEN CAST(CAST([i].value('.', 'VARCHAR(MAX)') AS NUMERIC) AS INT)
END AS [Int_Value]
, CASE
WHEN ISNUMERIC([i].value('.', 'VARCHAR(MAX)')) = 1
THEN CAST([i].value('.', 'VARCHAR(MAX)') AS NUMERIC(18, 3))
END AS [Num_Value]
, [i].value('.', 'VARCHAR(MAX)') AS [txt_Value]
, CASE
WHEN ISDATE([i].value('.', 'VARCHAR(MAX)')) = 1
THEN CAST([i].value('.', 'VARCHAR(MAX)') AS DATETIME)
END AS [Num_Value]
FROM #w_xml.nodes('//root/i') AS [Items]([i]);
RETURN;
END;
GO
ALTER function get_occurance_index(#delimiter varchar(1),#occurence int,#String varchar(100))
returns int
AS Begin
--Declare #delimiter varchar(1)=',',#occurence int=2,#String varchar(100)='a,b,c'
Declare #result int
;with T as (
select 1 Rno,0 as row, charindex(#delimiter, #String) pos,#String st
union all
select Rno+1,pos + 1, charindex(#delimiter, #String, pos + 1), #String
from T
where pos > 0
)
select #result=pos
from T
where pos > 0 and rno = #occurence
return isnull(#result,0)
ENd
declare #data as table (data varchar(100))
insert into #data values('1,2,3')
insert into #data values('aaa,bbbbb,cccc')
select top 3 Substring (data,0,dbo.get_occurance_index( ',',1,data)) ,--First Record always starts with 0
Substring (data,dbo.get_occurance_index( ',',1,data)+1,dbo.get_occurance_index( ',',2,data)-dbo.get_occurance_index( ',',1,data)-1) ,
Substring (data,dbo.get_occurance_index( ',',2,data)+1,len(data)) , -- Last record cant be more than len of actual data
data
From #data
I found that using PARSENAME as above caused any name with a period to get nulled.
So if there was an initial or a title in the name followed by a dot they return NULL.
I found this worked for me:
SELECT
REPLACE(SUBSTRING(FullName, 1,CHARINDEX(',', FullName)), ',','') as Name,
REPLACE(SUBSTRING(FullName, CHARINDEX(',', FullName), LEN(FullName)), ',', '') as Surname
FROM Table1
it is so easy, you can take it by below query:
DECLARE #str NVARCHAR(MAX)='ControlID_05436b78-04ba-9667-fa01-9ff8c1b7c235,3'
SELECT LEFT(#str, CHARINDEX(',',#str)-1),RIGHT(#str,LEN(#str)-(CHARINDEX(',',#str)))
select distinct modelFileId,F4.*
from contract
cross apply (select XmlList=convert(xml, '<x>'+replace(modelFileId,';','</x><x>')+'</x>').query('.')) F2
cross apply (select mfid1=XmlNode.value('/x[1]','varchar(512)')
,mfid2=XmlNode.value('/x[2]','varchar(512)')
,mfid3=XmlNode.value('/x[3]','varchar(512)')
,mfid4=XmlNode.value('/x[4]','varchar(512)') from XmlList.nodes('x') F3(XmlNode)) F4
where modelFileId like '%;%'
order by modelFileId
Select distinct PROJ_UID,PROJ_NAME,RES_UID from E2E_ProjectWiseTimesheetActuals
where CHARINDEX(','+cast(PROJ_UID as varchar(8000))+',', #params) > 0 and CHARINDEX(','+cast(RES_UID as varchar(8000))+',', #res) > 0
I re-wrote an answer above and made it better:
CREATE FUNCTION [dbo].[CSVParser]
(
#s VARCHAR(255),
#idx NUMERIC
)
RETURNS VARCHAR(12)
BEGIN
DECLARE #comma int
SET #comma = CHARINDEX(',', #s)
WHILE 1=1
BEGIN
IF #comma=0
IF #idx=1
RETURN #s
ELSE
RETURN ''
IF #idx=1
BEGIN
DECLARE #word VARCHAR(12)
SET #word=LEFT(#s, #comma - 1)
RETURN #word
END
SET #s = RIGHT(#s,LEN(#s)-#comma)
SET #comma = CHARINDEX(',', #s)
SET #idx = #idx - 1
END
RETURN 'not used'
END
Example usage:
SELECT dbo.CSVParser(COLUMN, 1),
dbo.CSVParser(COLUMN, 2),
dbo.CSVParser(COLUMN, 3)
FROM TABLE
question is simple, but problem is hot :)
So I create some wrapper for string_split() which pivot result in more generic way. It's table function which returns values (nn, value1, value2, ... , value50) - enough for most CSV lines. If there are more values, they will wrap to next line - nn indicate line number. Set third parameter #columnCnt = [yourNumber] to wrap at specific position:
alter FUNCTION fn_Split50
(
#str varchar(max),
#delim char(1),
#columnCnt int = 50
)
RETURNS TABLE
AS
RETURN
(
SELECT *
FROM (SELECT
nn = (nn - 1) / #columnCnt + 1,
nnn = 'value' + cast(((nn - 1) % #columnCnt) + 1 as varchar(10)),
value
FROM (SELECT
nn = ROW_NUMBER() over (order by (select null)),
value
FROM string_split(#str, #delim) aa
) aa
where nn > 0
) bb
PIVOT
(
max(value)
FOR nnn IN (
value1, value2, value3, value4, value5, value6, value7, value8, value9, value10,
value11, value12, value13, value14, value15, value16, value17, value18, value19, value20,
value21, value22, value23, value24, value25, value26, value27, value28, value29, value30,
value31, value32, value33, value34, value35, value36, value37, value38, value39, value40,
value41, value42, value43, value44, value45, value46, value47, value48, value49, value50
)
) AS PivotTable
)
Example of using:
select * from dbo.fn_split50('zz1,aa2,ss3,dd4,ff5', ',', DEFAULT)
select * from dbo.fn_split50('zz1,aa2,ss3,dd4,ff5,gg6,hh7,jj8,ww9,qq10', ',', 3)
select * from dbo.fn_split50('zz1,11,aa2,22,ss3,33,dd4,44,ff5,55,gg6,66,hh7,77,jj8,88,ww9,99,qq10,1010', ',',2)
Hope, it will helps :)

Split Delimited strings and insert them into table columns SQL 2014 [duplicate]

I have a table like this
Value String
-------------------
1 Cleo, Smith
I want to separate the comma delimited string into two columns
Value Name Surname
-------------------
1 Cleo Smith
I need only two fixed extra columns
Your purpose can be solved using following query -
Select Value , Substring(FullName, 1,Charindex(',', FullName)-1) as Name,
Substring(FullName, Charindex(',', FullName)+1, LEN(FullName)) as Surname
from Table1
There is no readymade Split function in sql server, so we need to create user defined function.
CREATE FUNCTION Split (
#InputString VARCHAR(8000),
#Delimiter VARCHAR(50)
)
RETURNS #Items TABLE (
Item VARCHAR(8000)
)
AS
BEGIN
IF #Delimiter = ' '
BEGIN
SET #Delimiter = ','
SET #InputString = REPLACE(#InputString, ' ', #Delimiter)
END
IF (#Delimiter IS NULL OR #Delimiter = '')
SET #Delimiter = ','
--INSERT INTO #Items VALUES (#Delimiter) -- Diagnostic
--INSERT INTO #Items VALUES (#InputString) -- Diagnostic
DECLARE #Item VARCHAR(8000)
DECLARE #ItemList VARCHAR(8000)
DECLARE #DelimIndex INT
SET #ItemList = #InputString
SET #DelimIndex = CHARINDEX(#Delimiter, #ItemList, 0)
WHILE (#DelimIndex != 0)
BEGIN
SET #Item = SUBSTRING(#ItemList, 0, #DelimIndex)
INSERT INTO #Items VALUES (#Item)
-- Set #ItemList = #ItemList minus one less item
SET #ItemList = SUBSTRING(#ItemList, #DelimIndex+1, LEN(#ItemList)-#DelimIndex)
SET #DelimIndex = CHARINDEX(#Delimiter, #ItemList, 0)
END -- End WHILE
IF #Item IS NOT NULL -- At least one delimiter was encountered in #InputString
BEGIN
SET #Item = #ItemList
INSERT INTO #Items VALUES (#Item)
END
-- No delimiters were encountered in #InputString, so just return #InputString
ELSE INSERT INTO #Items VALUES (#InputString)
RETURN
END -- End Function
GO
---- Set Permissions
--GRANT SELECT ON Split TO UserRole1
--GRANT SELECT ON Split TO UserRole2
--GO
;WITH Split_Names (Value,Name, xmlname)
AS
(
SELECT Value,
Name,
CONVERT(XML,'<Names><name>'
+ REPLACE(Name,',', '</name><name>') + '</name></Names>') AS xmlname
FROM tblnames
)
SELECT Value,
xmlname.value('/Names[1]/name[1]','varchar(100)') AS Name,
xmlname.value('/Names[1]/name[2]','varchar(100)') AS Surname
FROM Split_Names
and also check the link below for reference
http://jahaines.blogspot.in/2009/06/converting-delimited-string-of-values.html
xml based answer is simple and clean
refer this
DECLARE #S varchar(max),
#Split char(1),
#X xml
SELECT #S = 'ab,cd,ef,gh,ij',
#Split = ','
SELECT #X = CONVERT(xml,' <root> <myvalue>' +
REPLACE(#S,#Split,'</myvalue> <myvalue>') + '</myvalue> </root> ')
SELECT T.c.value('.','varchar(20)'), --retrieve ALL values at once
T.c.value('(/root/myvalue)[1]','VARCHAR(20)') , --retrieve index 1 only, which is the 'ab'
T.c.value('(/root/myvalue)[2]','VARCHAR(20)')
FROM #X.nodes('/root/myvalue') T(c)
I think this is cool
SELECT value,
PARSENAME(REPLACE(String,',','.'),2) 'Name' ,
PARSENAME(REPLACE(String,',','.'),1) 'Surname'
FROM table WITH (NOLOCK)
With CROSS APPLY
select ParsedData.*
from MyTable mt
cross apply ( select str = mt.String + ',,' ) f1
cross apply ( select p1 = charindex( ',', str ) ) ap1
cross apply ( select p2 = charindex( ',', str, p1 + 1 ) ) ap2
cross apply ( select Nmame = substring( str, 1, p1-1 )
, Surname = substring( str, p1+1, p2-p1-1 )
) ParsedData
There are multiple ways to solve this and many different ways have been proposed already. Simplest would be to use LEFT / SUBSTRING and other string functions to achieve the desired result.
Sample Data
DECLARE #tbl1 TABLE (Value INT,String VARCHAR(MAX))
INSERT INTO #tbl1 VALUES(1,'Cleo, Smith');
INSERT INTO #tbl1 VALUES(2,'John, Mathew');
Using String Functions like LEFT
SELECT
Value,
LEFT(String,CHARINDEX(',',String)-1) as Fname,
LTRIM(RIGHT(String,LEN(String) - CHARINDEX(',',String) )) AS Lname
FROM #tbl1
This approach fails if there are more 2 items in a String.
In such a scenario, we can use a splitter and then use PIVOT or convert the string into an XML and use .nodes to get string items. XML based solution have been detailed out by aads and bvr in their solution.
The answers for this question which use splitter, all use WHILE which is inefficient for splitting. Check this performance comparison. One of the best splitters around is DelimitedSplit8K, created by Jeff Moden. You can read more about it here
Splitter with PIVOT
DECLARE #tbl1 TABLE (Value INT,String VARCHAR(MAX))
INSERT INTO #tbl1 VALUES(1,'Cleo, Smith');
INSERT INTO #tbl1 VALUES(2,'John, Mathew');
SELECT t3.Value,[1] as Fname,[2] as Lname
FROM #tbl1 as t1
CROSS APPLY [dbo].[DelimitedSplit8K](String,',') as t2
PIVOT(MAX(Item) FOR ItemNumber IN ([1],[2])) as t3
Output
Value Fname Lname
1 Cleo Smith
2 John Mathew
DelimitedSplit8K by Jeff Moden
CREATE FUNCTION [dbo].[DelimitedSplit8K]
/**********************************************************************************************************************
Purpose:
Split a given string at a given delimiter and return a list of the split elements (items).
Notes:
1. Leading a trailing delimiters are treated as if an empty string element were present.
2. Consecutive delimiters are treated as if an empty string element were present between them.
3. Except when spaces are used as a delimiter, all spaces present in each element are preserved.
Returns:
iTVF containing the following:
ItemNumber = Element position of Item as a BIGINT (not converted to INT to eliminate a CAST)
Item = Element value as a VARCHAR(8000)
Statistics on this function may be found at the following URL:
http://www.sqlservercentral.com/Forums/Topic1101315-203-4.aspx
CROSS APPLY Usage Examples and Tests:
--=====================================================================================================================
-- TEST 1:
-- This tests for various possible conditions in a string using a comma as the delimiter. The expected results are
-- laid out in the comments
--=====================================================================================================================
--===== Conditionally drop the test tables to make reruns easier for testing.
-- (this is NOT a part of the solution)
IF OBJECT_ID('tempdb..#JBMTest') IS NOT NULL DROP TABLE #JBMTest
;
--===== Create and populate a test table on the fly (this is NOT a part of the solution).
-- In the following comments, "b" is a blank and "E" is an element in the left to right order.
-- Double Quotes are used to encapsulate the output of "Item" so that you can see that all blanks
-- are preserved no matter where they may appear.
SELECT *
INTO #JBMTest
FROM ( --# & type of Return Row(s)
SELECT 0, NULL UNION ALL --1 NULL
SELECT 1, SPACE(0) UNION ALL --1 b (Empty String)
SELECT 2, SPACE(1) UNION ALL --1 b (1 space)
SELECT 3, SPACE(5) UNION ALL --1 b (5 spaces)
SELECT 4, ',' UNION ALL --2 b b (both are empty strings)
SELECT 5, '55555' UNION ALL --1 E
SELECT 6, ',55555' UNION ALL --2 b E
SELECT 7, ',55555,' UNION ALL --3 b E b
SELECT 8, '55555,' UNION ALL --2 b B
SELECT 9, '55555,1' UNION ALL --2 E E
SELECT 10, '1,55555' UNION ALL --2 E E
SELECT 11, '55555,4444,333,22,1' UNION ALL --5 E E E E E
SELECT 12, '55555,4444,,333,22,1' UNION ALL --6 E E b E E E
SELECT 13, ',55555,4444,,333,22,1,' UNION ALL --8 b E E b E E E b
SELECT 14, ',55555,4444,,,333,22,1,' UNION ALL --9 b E E b b E E E b
SELECT 15, ' 4444,55555 ' UNION ALL --2 E (w/Leading Space) E (w/Trailing Space)
SELECT 16, 'This,is,a,test.' --E E E E
) d (SomeID, SomeValue)
;
--===== Split the CSV column for the whole table using CROSS APPLY (this is the solution)
SELECT test.SomeID, test.SomeValue, split.ItemNumber, Item = QUOTENAME(split.Item,'"')
FROM #JBMTest test
CROSS APPLY dbo.DelimitedSplit8K(test.SomeValue,',') split
;
--=====================================================================================================================
-- TEST 2:
-- This tests for various "alpha" splits and COLLATION using all ASCII characters from 0 to 255 as a delimiter against
-- a given string. Note that not all of the delimiters will be visible and some will show up as tiny squares because
-- they are "control" characters. More specifically, this test will show you what happens to various non-accented
-- letters for your given collation depending on the delimiter you chose.
--=====================================================================================================================
WITH
cteBuildAllCharacters (String,Delimiter) AS
(
SELECT TOP 256
'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789',
CHAR(ROW_NUMBER() OVER (ORDER BY (SELECT NULL))-1)
FROM master.sys.all_columns
)
SELECT ASCII_Value = ASCII(c.Delimiter), c.Delimiter, split.ItemNumber, Item = QUOTENAME(split.Item,'"')
FROM cteBuildAllCharacters c
CROSS APPLY dbo.DelimitedSplit8K(c.String,c.Delimiter) split
ORDER BY ASCII_Value, split.ItemNumber
;
-----------------------------------------------------------------------------------------------------------------------
Other Notes:
1. Optimized for VARCHAR(8000) or less. No testing or error reporting for truncation at 8000 characters is done.
2. Optimized for single character delimiter. Multi-character delimiters should be resolvedexternally from this
function.
3. Optimized for use with CROSS APPLY.
4. Does not "trim" elements just in case leading or trailing blanks are intended.
5. If you don't know how a Tally table can be used to replace loops, please see the following...
http://www.sqlservercentral.com/articles/T-SQL/62867/
6. Changing this function to use NVARCHAR(MAX) will cause it to run twice as slow. It's just the nature of
VARCHAR(MAX) whether it fits in-row or not.
7. Multi-machine testing for the method of using UNPIVOT instead of 10 SELECT/UNION ALLs shows that the UNPIVOT method
is quite machine dependent and can slow things down quite a bit.
-----------------------------------------------------------------------------------------------------------------------
Credits:
This code is the product of many people's efforts including but not limited to the following:
cteTally concept originally by Iztek Ben Gan and "decimalized" by Lynn Pettis (and others) for a bit of extra speed
and finally redacted by Jeff Moden for a different slant on readability and compactness. Hat's off to Paul White for
his simple explanations of CROSS APPLY and for his detailed testing efforts. Last but not least, thanks to
Ron "BitBucket" McCullough and Wayne Sheffield for their extreme performance testing across multiple machines and
versions of SQL Server. The latest improvement brought an additional 15-20% improvement over Rev 05. Special thanks
to "Nadrek" and "peter-757102" (aka Peter de Heer) for bringing such improvements to light. Nadrek's original
improvement brought about a 10% performance gain and Peter followed that up with the content of Rev 07.
I also thank whoever wrote the first article I ever saw on "numbers tables" which is located at the following URL
and to Adam Machanic for leading me to it many years ago.
http://sqlserver2000.databases.aspfaq.com/why-should-i-consider-using-an-auxiliary-numbers-table.html
-----------------------------------------------------------------------------------------------------------------------
Revision History:
Rev 00 - 20 Jan 2010 - Concept for inline cteTally: Lynn Pettis and others.
Redaction/Implementation: Jeff Moden
- Base 10 redaction and reduction for CTE. (Total rewrite)
Rev 01 - 13 Mar 2010 - Jeff Moden
- Removed one additional concatenation and one subtraction from the SUBSTRING in the SELECT List for that tiny
bit of extra speed.
Rev 02 - 14 Apr 2010 - Jeff Moden
- No code changes. Added CROSS APPLY usage example to the header, some additional credits, and extra
documentation.
Rev 03 - 18 Apr 2010 - Jeff Moden
- No code changes. Added notes 7, 8, and 9 about certain "optimizations" that don't actually work for this
type of function.
Rev 04 - 29 Jun 2010 - Jeff Moden
- Added WITH SCHEMABINDING thanks to a note by Paul White. This prevents an unnecessary "Table Spool" when the
function is used in an UPDATE statement even though the function makes no external references.
Rev 05 - 02 Apr 2011 - Jeff Moden
- Rewritten for extreme performance improvement especially for larger strings approaching the 8K boundary and
for strings that have wider elements. The redaction of this code involved removing ALL concatenation of
delimiters, optimization of the maximum "N" value by using TOP instead of including it in the WHERE clause,
and the reduction of all previous calculations (thanks to the switch to a "zero based" cteTally) to just one
instance of one add and one instance of a subtract. The length calculation for the final element (not
followed by a delimiter) in the string to be split has been greatly simplified by using the ISNULL/NULLIF
combination to determine when the CHARINDEX returned a 0 which indicates there are no more delimiters to be
had or to start with. Depending on the width of the elements, this code is between 4 and 8 times faster on a
single CPU box than the original code especially near the 8K boundary.
- Modified comments to include more sanity checks on the usage example, etc.
- Removed "other" notes 8 and 9 as they were no longer applicable.
Rev 06 - 12 Apr 2011 - Jeff Moden
- Based on a suggestion by Ron "Bitbucket" McCullough, additional test rows were added to the sample code and
the code was changed to encapsulate the output in pipes so that spaces and empty strings could be perceived
in the output. The first "Notes" section was added. Finally, an extra test was added to the comments above.
Rev 07 - 06 May 2011 - Peter de Heer, a further 15-20% performance enhancement has been discovered and incorporated
into this code which also eliminated the need for a "zero" position in the cteTally table.
**********************************************************************************************************************/
--===== Define I/O parameters
(#pString VARCHAR(8000), #pDelimiter CHAR(1))
RETURNS TABLE WITH SCHEMABINDING AS
RETURN
--===== "Inline" CTE Driven "Tally Table" produces values from 0 up to 10,000...
-- enough to cover NVARCHAR(4000)
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
With SQL Server 2016 we can use string_split to accomplish this:
create table commasep (
id int identity(1,1)
,string nvarchar(100) )
insert into commasep (string) values ('John, Adam'), ('test1,test2,test3')
select id, [value] as String from commasep
cross apply string_split(string,',')
CREATE FUNCTION [dbo].[fn_split_string_to_column] (
#string NVARCHAR(MAX),
#delimiter CHAR(1)
)
RETURNS #out_put TABLE (
[column_id] INT IDENTITY(1, 1) NOT NULL,
[value] NVARCHAR(MAX)
)
AS
BEGIN
DECLARE #value NVARCHAR(MAX),
#pos INT = 0,
#len INT = 0
SET #string = CASE
WHEN RIGHT(#string, 1) != #delimiter
THEN #string + #delimiter
ELSE #string
END
WHILE CHARINDEX(#delimiter, #string, #pos + 1) > 0
BEGIN
SET #len = CHARINDEX(#delimiter, #string, #pos + 1) - #pos
SET #value = SUBSTRING(#string, #pos, #len)
INSERT INTO #out_put ([value])
SELECT LTRIM(RTRIM(#value)) AS [column]
SET #pos = CHARINDEX(#delimiter, #string, #pos + #len) + 1
END
RETURN
END
SELECT id,
Substring(NAME, 0, Charindex(',', NAME)) AS firstname,
Substring(NAME, Charindex(',', NAME), Len(NAME) + 1) AS lastname
FROM spilt
Try this (change instances of ' ' to ',' or whatever delimiter you want to use)
CREATE FUNCTION dbo.Wordparser
(
#multiwordstring VARCHAR(255),
#wordnumber NUMERIC
)
returns VARCHAR(255)
AS
BEGIN
DECLARE #remainingstring VARCHAR(255)
SET #remainingstring=#multiwordstring
DECLARE #numberofwords NUMERIC
SET #numberofwords=(LEN(#remainingstring) - LEN(REPLACE(#remainingstring, ' ', '')) + 1)
DECLARE #word VARCHAR(50)
DECLARE #parsedwords TABLE
(
line NUMERIC IDENTITY(1, 1),
word VARCHAR(255)
)
WHILE #numberofwords > 1
BEGIN
SET #word=LEFT(#remainingstring, CHARINDEX(' ', #remainingstring) - 1)
INSERT INTO #parsedwords(word)
SELECT #word
SET #remainingstring= REPLACE(#remainingstring, Concat(#word, ' '), '')
SET #numberofwords=(LEN(#remainingstring) - LEN(REPLACE(#remainingstring, ' ', '')) + 1)
IF #numberofwords = 1
BREAK
ELSE
CONTINUE
END
IF #numberofwords = 1
SELECT #word = #remainingstring
INSERT INTO #parsedwords(word)
SELECT #word
RETURN
(SELECT word
FROM #parsedwords
WHERE line = #wordnumber)
END
Example usage:
SELECT dbo.Wordparser(COLUMN, 1),
dbo.Wordparser(COLUMN, 2),
dbo.Wordparser(COLUMN, 3)
FROM TABLE
I think PARSENAME is the neat function to use for this example, as described in this article: http://www.sqlshack.com/parsing-and-rotating-delimited-data-in-sql-server-2012/
The PARSENAME function is logically designed to parse four-part object names. The nice thing about PARSENAME is that it’s not limited to parsing just SQL Server four-part object names – it will parse any function or string data that is delimited by dots.
The first parameter is the object to parse, and the second is the integer value of the object piece to return. The article is discussing parsing and rotating delimited data - company phone numbers, but it can be used to parse name/surname data also.
Example:
USE COMPANY;
SELECT PARSENAME('Whatever.you.want.parsed',3) AS 'ReturnValue';
The article also describes using a Common Table Expression (CTE) called ‘replaceChars’, to run PARSENAME against the delimiter-replaced values. A CTE is useful for returning a temporary view or result set.
After that, the UNPIVOT function has been used to convert some columns into rows; SUBSTRING and CHARINDEX functions have been used for cleaning up the inconsistencies in the data, and the LAG function (new for SQL Server 2012) has been used in the end, as it allows referencing of previous records.
We can create a function as this
CREATE Function [dbo].[fn_CSVToTable]
(
#CSVList Varchar(max)
)
RETURNS #Table TABLE (ColumnData VARCHAR(100))
AS
BEGIN
IF RIGHT(#CSVList, 1) <> ','
SELECT #CSVList = #CSVList + ','
DECLARE #Pos BIGINT,
#OldPos BIGINT
SELECT #Pos = 1,
#OldPos = 1
WHILE #Pos < LEN(#CSVList)
BEGIN
SELECT #Pos = CHARINDEX(',', #CSVList, #OldPos)
INSERT INTO #Table
SELECT LTRIM(RTRIM(SUBSTRING(#CSVList, #OldPos, #Pos - #OldPos))) Col001
SELECT #OldPos = #Pos + 1
END
RETURN
END
We can then seperate the CSV values into our respective columns using a SELECT statement
You can use a table-valued function STRING_SPLIT, which is available only under compatibility level 130. If your database compatibility level is lower than 130, SQL Server will not be able to find and execute the STRING_SPLIT function. You can change a compatibility level of the database using the following command:
ALTER DATABASE DatabaseName SET COMPATIBILITY_LEVEL = 130
Syntax
SELECT * FROM STRING_SPLIT ( string, separator )
see documentation here
I think following function will work for you:
You have to create a function in SQL first. Like this
CREATE FUNCTION [dbo].[fn_split](
#str VARCHAR(MAX),
#delimiter CHAR(1)
)
RETURNS #returnTable TABLE (idx INT PRIMARY KEY IDENTITY, item VARCHAR(8000))
AS
BEGIN
DECLARE #pos INT
SELECT #str = #str + #delimiter
WHILE LEN(#str) > 0
BEGIN
SELECT #pos = CHARINDEX(#delimiter,#str)
IF #pos = 1
INSERT #returnTable (item)
VALUES (NULL)
ELSE
INSERT #returnTable (item)
VALUES (SUBSTRING(#str, 1, #pos-1))
SELECT #str = SUBSTRING(#str, #pos+1, LEN(#str)-#pos)
END
RETURN
END
You can call this function, like this:
select * from fn_split('1,24,5',',')
Implementation:
Declare #test TABLE (
ID VARCHAR(200),
Data VARCHAR(200)
)
insert into #test
(ID, Data)
Values
('1','Cleo,Smith')
insert into #test
(ID, Data)
Values
('2','Paul,Grim')
select ID,
(select item from fn_split(Data,',') where idx in (1)) as Name ,
(select item from fn_split(Data,',') where idx in (2)) as Surname
from #test
Result will like this:
Use Parsename() function
with cte as(
select 'Aria,Karimi' as FullName
Union
select 'Joe,Karimi' as FullName
Union
select 'Bab,Karimi' as FullName
)
SELECT PARSENAME(REPLACE(FullName,',','.'),2) as Name,
PARSENAME(REPLACE(FullName,',','.'),1) as Family
FROM cte
Result
Name Family
----- ------
Aria Karimi
Bab Karimi
Joe Karimi
Try this:
declare #csv varchar(100) ='aaa,bb,csda,daass';
set #csv = #csv+',';
with cte as
(
select SUBSTRING(#csv,1,charindex(',',#csv,1)-1) as val, SUBSTRING(#csv,charindex(',',#csv,1)+1,len(#csv)) as rem
UNION ALL
select SUBSTRING(a.rem,1,charindex(',',a.rem,1)-1)as val, SUBSTRING(a.rem,charindex(',',a.rem,1)+1,len(A.rem))
from cte a where LEN(a.rem)>=1
) select val from cte
This function is most fast:
CREATE FUNCTION dbo.F_ExtractSubString
(
#String VARCHAR(MAX),
#NroSubString INT,
#Separator VARCHAR(5)
)
RETURNS VARCHAR(MAX) AS
BEGIN
DECLARE #St INT = 0, #End INT = 0, #Ret VARCHAR(MAX)
SET #String = #String + #Separator
WHILE CHARINDEX(#Separator, #String, #End + 1) > 0 AND #NroSubString > 0
BEGIN
SET #St = #End + 1
SET #End = CHARINDEX(#Separator, #String, #End + 1)
SET #NroSubString = #NroSubString - 1
END
IF #NroSubString > 0
SET #Ret = ''
ELSE
SET #Ret = SUBSTRING(#String, #St, #End - #St)
RETURN #Ret
END
GO
Example usage:
SELECT dbo.F_ExtractSubString(COLUMN, 1, ', '),
dbo.F_ExtractSubString(COLUMN, 2, ', '),
dbo.F_ExtractSubString(COLUMN, 3, ', ')
FROM TABLE
I encountered a similar problem but a complex one and since this is the first thread i found regarding that issue i decided to post my finding. i know it is complex solution to a simple problem but i hope that i could help other people who go to this thread looking for a more complex solution. i had to split a string containing 5 numbers (column name: levelsFeed) and to show each number in a separate column.
for example: 8,1,2,2,2
should be shown as :
1 2 3 4 5
-------------
8 1 2 2 2
Solution 1: using XML functions:
this solution for the slowest solution by far
SELECT Distinct FeedbackID,
, S.a.value('(/H/r)[1]', 'INT') AS level1
, S.a.value('(/H/r)[2]', 'INT') AS level2
, S.a.value('(/H/r)[3]', 'INT') AS level3
, S.a.value('(/H/r)[4]', 'INT') AS level4
, S.a.value('(/H/r)[5]', 'INT') AS level5
FROM (
SELECT *,CAST (N'<H><r>' + REPLACE(levelsFeed, ',', '</r><r>') + '</r> </H>' AS XML) AS [vals]
FROM Feedbacks
) as d
CROSS APPLY d.[vals].nodes('/H/r') S(a)
Solution 2: using Split function and pivot. (the split function split a string to rows with the column name Data)
SELECT FeedbackID, [1],[2],[3],[4],[5]
FROM (
SELECT *, ROW_NUMBER() OVER (PARTITION BY feedbackID ORDER BY (SELECT null)) as rn
FROM (
SELECT FeedbackID, levelsFeed
FROM Feedbacks
) as a
CROSS APPLY dbo.Split(levelsFeed, ',')
) as SourceTable
PIVOT
(
MAX(data)
FOR rn IN ([1],[2],[3],[4],[5])
)as pivotTable
Solution 3: using string manipulations functions - fastest by small margin over solution 2
SELECT FeedbackID,
SUBSTRING(levelsFeed,0,CHARINDEX(',',levelsFeed)) AS level1,
PARSENAME(REPLACE(SUBSTRING(levelsFeed,CHARINDEX(',',levelsFeed)+1,LEN(levelsFeed)),',','.'),4) AS level2,
PARSENAME(REPLACE(SUBSTRING(levelsFeed,CHARINDEX(',',levelsFeed)+1,LEN(levelsFeed)),',','.'),3) AS level3,
PARSENAME(REPLACE(SUBSTRING(levelsFeed,CHARINDEX(',',levelsFeed)+1,LEN(levelsFeed)),',','.'),2) AS level4,
PARSENAME(REPLACE(SUBSTRING(levelsFeed,CHARINDEX(',',levelsFeed)+1,LEN(levelsFeed)),',','.'),1) AS level5
FROM Feedbacks
since the levelsFeed contains 5 string values i needed to use the substring function for the first string.
i hope that my solution will help other that got to this thread looking for a more complex split to columns methods
Using instring function :)
select Value,
substring(String,1,instr(String," ") -1) Fname,
substring(String,instr(String,",") +1) Sname
from tablename;
Used two functions,
1. substring(string, position, length) ==> returns string from positon to length
2. instr(string,pattern) ==> returns position of pattern.
If we don’t provide length argument in substring it returns until end of string
This worked for me
CREATE FUNCTION [dbo].[SplitString](
#delimited NVARCHAR(MAX),
#delimiter NVARCHAR(100)
) RETURNS #t TABLE ( val NVARCHAR(MAX))
AS
BEGIN
DECLARE #xml XML
SET #xml = N'<t>' + REPLACE(#delimited,#delimiter,'</t><t>') + '</t>'
INSERT INTO #t(val)
SELECT r.value('.','varchar(MAX)') as item
FROM #xml.nodes('/t') as records(r)
RETURN
END
mytable:
Value ColOne
--------------------
1 Cleo, Smith
The following should work if there aren't too many columns
ALTER TABLE mytable ADD ColTwo nvarchar(256);
UPDATE mytable SET ColTwo = LEFT(ColOne, Charindex(',', ColOne) - 1);
--'Cleo' = LEFT('Cleo, Smith', Charindex(',', 'Cleo, Smith') - 1)
UPDATE mytable SET ColTwo = REPLACE(ColOne, ColTwo + ',', '');
--' Smith' = REPLACE('Cleo, Smith', 'Cleo' + ',')
UPDATE mytable SET ColOne = REPLACE(ColOne, ',' + ColTwo, ''), ColTwo = LTRIM(ColTwo);
--'Cleo' = REPLACE('Cleo, Smith', ',' + ' Smith', '')
Result:
Value ColOne ColTwo
--------------------
1 Cleo Smith
DECLARE #INPUT VARCHAR (MAX)='N,A,R,E,N,D,R,A'
DECLARE #ELIMINATE_CHAR CHAR (1)=','
DECLARE #L_START INT=1
DECLARE #L_END INT=(SELECT LEN (#INPUT))
DECLARE #OUTPUT CHAR (1)
WHILE #L_START <=#L_END
BEGIN
SET #OUTPUT=(SUBSTRING (#INPUT,#L_START,1))
IF #OUTPUT!=#ELIMINATE_CHAR
BEGIN
PRINT #OUTPUT
END
SET #L_START=#L_START+1
END
You may find the solution in SQL User Defined Function to Parse a Delimited String helpful (from The Code Project).
This is the code part from this page:
CREATE FUNCTION [fn_ParseText2Table]
(#p_SourceText VARCHAR(MAX)
,#p_Delimeter VARCHAR(100)=',' --default to comma delimited.
)
RETURNS #retTable
TABLE([Position] INT IDENTITY(1,1)
,[Int_Value] INT
,[Num_Value] NUMERIC(18,3)
,[Txt_Value] VARCHAR(MAX)
,[Date_value] DATETIME
)
AS
/*
********************************************************************************
Purpose: Parse values from a delimited string
& return the result as an indexed table
Copyright 1996, 1997, 2000, 2003 Clayton Groom (Clayton_Groom#hotmail.com)
Posted to the public domain Aug, 2004
2003-06-17 Rewritten as SQL 2000 function.
Reworked to allow for delimiters > 1 character in length
and to convert Text values to numbers
2016-04-05 Added logic for date values based on "new" ISDATE() function, Updated to use XML approach, which is more efficient.
********************************************************************************
*/
BEGIN
DECLARE #w_xml xml;
SET #w_xml = N'<root><i>' + replace(#p_SourceText, #p_Delimeter,'</i><i>') + '</i></root>';
INSERT INTO #retTable
([Int_Value]
, [Num_Value]
, [Txt_Value]
, [Date_value]
)
SELECT CASE
WHEN ISNUMERIC([i].value('.', 'VARCHAR(MAX)')) = 1
THEN CAST(CAST([i].value('.', 'VARCHAR(MAX)') AS NUMERIC) AS INT)
END AS [Int_Value]
, CASE
WHEN ISNUMERIC([i].value('.', 'VARCHAR(MAX)')) = 1
THEN CAST([i].value('.', 'VARCHAR(MAX)') AS NUMERIC(18, 3))
END AS [Num_Value]
, [i].value('.', 'VARCHAR(MAX)') AS [txt_Value]
, CASE
WHEN ISDATE([i].value('.', 'VARCHAR(MAX)')) = 1
THEN CAST([i].value('.', 'VARCHAR(MAX)') AS DATETIME)
END AS [Num_Value]
FROM #w_xml.nodes('//root/i') AS [Items]([i]);
RETURN;
END;
GO
ALTER function get_occurance_index(#delimiter varchar(1),#occurence int,#String varchar(100))
returns int
AS Begin
--Declare #delimiter varchar(1)=',',#occurence int=2,#String varchar(100)='a,b,c'
Declare #result int
;with T as (
select 1 Rno,0 as row, charindex(#delimiter, #String) pos,#String st
union all
select Rno+1,pos + 1, charindex(#delimiter, #String, pos + 1), #String
from T
where pos > 0
)
select #result=pos
from T
where pos > 0 and rno = #occurence
return isnull(#result,0)
ENd
declare #data as table (data varchar(100))
insert into #data values('1,2,3')
insert into #data values('aaa,bbbbb,cccc')
select top 3 Substring (data,0,dbo.get_occurance_index( ',',1,data)) ,--First Record always starts with 0
Substring (data,dbo.get_occurance_index( ',',1,data)+1,dbo.get_occurance_index( ',',2,data)-dbo.get_occurance_index( ',',1,data)-1) ,
Substring (data,dbo.get_occurance_index( ',',2,data)+1,len(data)) , -- Last record cant be more than len of actual data
data
From #data
I found that using PARSENAME as above caused any name with a period to get nulled.
So if there was an initial or a title in the name followed by a dot they return NULL.
I found this worked for me:
SELECT
REPLACE(SUBSTRING(FullName, 1,CHARINDEX(',', FullName)), ',','') as Name,
REPLACE(SUBSTRING(FullName, CHARINDEX(',', FullName), LEN(FullName)), ',', '') as Surname
FROM Table1
it is so easy, you can take it by below query:
DECLARE #str NVARCHAR(MAX)='ControlID_05436b78-04ba-9667-fa01-9ff8c1b7c235,3'
SELECT LEFT(#str, CHARINDEX(',',#str)-1),RIGHT(#str,LEN(#str)-(CHARINDEX(',',#str)))
select distinct modelFileId,F4.*
from contract
cross apply (select XmlList=convert(xml, '<x>'+replace(modelFileId,';','</x><x>')+'</x>').query('.')) F2
cross apply (select mfid1=XmlNode.value('/x[1]','varchar(512)')
,mfid2=XmlNode.value('/x[2]','varchar(512)')
,mfid3=XmlNode.value('/x[3]','varchar(512)')
,mfid4=XmlNode.value('/x[4]','varchar(512)') from XmlList.nodes('x') F3(XmlNode)) F4
where modelFileId like '%;%'
order by modelFileId
Select distinct PROJ_UID,PROJ_NAME,RES_UID from E2E_ProjectWiseTimesheetActuals
where CHARINDEX(','+cast(PROJ_UID as varchar(8000))+',', #params) > 0 and CHARINDEX(','+cast(RES_UID as varchar(8000))+',', #res) > 0
I re-wrote an answer above and made it better:
CREATE FUNCTION [dbo].[CSVParser]
(
#s VARCHAR(255),
#idx NUMERIC
)
RETURNS VARCHAR(12)
BEGIN
DECLARE #comma int
SET #comma = CHARINDEX(',', #s)
WHILE 1=1
BEGIN
IF #comma=0
IF #idx=1
RETURN #s
ELSE
RETURN ''
IF #idx=1
BEGIN
DECLARE #word VARCHAR(12)
SET #word=LEFT(#s, #comma - 1)
RETURN #word
END
SET #s = RIGHT(#s,LEN(#s)-#comma)
SET #comma = CHARINDEX(',', #s)
SET #idx = #idx - 1
END
RETURN 'not used'
END
Example usage:
SELECT dbo.CSVParser(COLUMN, 1),
dbo.CSVParser(COLUMN, 2),
dbo.CSVParser(COLUMN, 3)
FROM TABLE
question is simple, but problem is hot :)
So I create some wrapper for string_split() which pivot result in more generic way. It's table function which returns values (nn, value1, value2, ... , value50) - enough for most CSV lines. If there are more values, they will wrap to next line - nn indicate line number. Set third parameter #columnCnt = [yourNumber] to wrap at specific position:
alter FUNCTION fn_Split50
(
#str varchar(max),
#delim char(1),
#columnCnt int = 50
)
RETURNS TABLE
AS
RETURN
(
SELECT *
FROM (SELECT
nn = (nn - 1) / #columnCnt + 1,
nnn = 'value' + cast(((nn - 1) % #columnCnt) + 1 as varchar(10)),
value
FROM (SELECT
nn = ROW_NUMBER() over (order by (select null)),
value
FROM string_split(#str, #delim) aa
) aa
where nn > 0
) bb
PIVOT
(
max(value)
FOR nnn IN (
value1, value2, value3, value4, value5, value6, value7, value8, value9, value10,
value11, value12, value13, value14, value15, value16, value17, value18, value19, value20,
value21, value22, value23, value24, value25, value26, value27, value28, value29, value30,
value31, value32, value33, value34, value35, value36, value37, value38, value39, value40,
value41, value42, value43, value44, value45, value46, value47, value48, value49, value50
)
) AS PivotTable
)
Example of using:
select * from dbo.fn_split50('zz1,aa2,ss3,dd4,ff5', ',', DEFAULT)
select * from dbo.fn_split50('zz1,aa2,ss3,dd4,ff5,gg6,hh7,jj8,ww9,qq10', ',', 3)
select * from dbo.fn_split50('zz1,11,aa2,22,ss3,33,dd4,44,ff5,55,gg6,66,hh7,77,jj8,88,ww9,99,qq10,1010', ',',2)
Hope, it will helps :)

SQL split a colon and Space from the Description Field/Column [duplicate]

I have a table like this
Value String
-------------------
1 Cleo, Smith
I want to separate the comma delimited string into two columns
Value Name Surname
-------------------
1 Cleo Smith
I need only two fixed extra columns
Your purpose can be solved using following query -
Select Value , Substring(FullName, 1,Charindex(',', FullName)-1) as Name,
Substring(FullName, Charindex(',', FullName)+1, LEN(FullName)) as Surname
from Table1
There is no readymade Split function in sql server, so we need to create user defined function.
CREATE FUNCTION Split (
#InputString VARCHAR(8000),
#Delimiter VARCHAR(50)
)
RETURNS #Items TABLE (
Item VARCHAR(8000)
)
AS
BEGIN
IF #Delimiter = ' '
BEGIN
SET #Delimiter = ','
SET #InputString = REPLACE(#InputString, ' ', #Delimiter)
END
IF (#Delimiter IS NULL OR #Delimiter = '')
SET #Delimiter = ','
--INSERT INTO #Items VALUES (#Delimiter) -- Diagnostic
--INSERT INTO #Items VALUES (#InputString) -- Diagnostic
DECLARE #Item VARCHAR(8000)
DECLARE #ItemList VARCHAR(8000)
DECLARE #DelimIndex INT
SET #ItemList = #InputString
SET #DelimIndex = CHARINDEX(#Delimiter, #ItemList, 0)
WHILE (#DelimIndex != 0)
BEGIN
SET #Item = SUBSTRING(#ItemList, 0, #DelimIndex)
INSERT INTO #Items VALUES (#Item)
-- Set #ItemList = #ItemList minus one less item
SET #ItemList = SUBSTRING(#ItemList, #DelimIndex+1, LEN(#ItemList)-#DelimIndex)
SET #DelimIndex = CHARINDEX(#Delimiter, #ItemList, 0)
END -- End WHILE
IF #Item IS NOT NULL -- At least one delimiter was encountered in #InputString
BEGIN
SET #Item = #ItemList
INSERT INTO #Items VALUES (#Item)
END
-- No delimiters were encountered in #InputString, so just return #InputString
ELSE INSERT INTO #Items VALUES (#InputString)
RETURN
END -- End Function
GO
---- Set Permissions
--GRANT SELECT ON Split TO UserRole1
--GRANT SELECT ON Split TO UserRole2
--GO
;WITH Split_Names (Value,Name, xmlname)
AS
(
SELECT Value,
Name,
CONVERT(XML,'<Names><name>'
+ REPLACE(Name,',', '</name><name>') + '</name></Names>') AS xmlname
FROM tblnames
)
SELECT Value,
xmlname.value('/Names[1]/name[1]','varchar(100)') AS Name,
xmlname.value('/Names[1]/name[2]','varchar(100)') AS Surname
FROM Split_Names
and also check the link below for reference
http://jahaines.blogspot.in/2009/06/converting-delimited-string-of-values.html
xml based answer is simple and clean
refer this
DECLARE #S varchar(max),
#Split char(1),
#X xml
SELECT #S = 'ab,cd,ef,gh,ij',
#Split = ','
SELECT #X = CONVERT(xml,' <root> <myvalue>' +
REPLACE(#S,#Split,'</myvalue> <myvalue>') + '</myvalue> </root> ')
SELECT T.c.value('.','varchar(20)'), --retrieve ALL values at once
T.c.value('(/root/myvalue)[1]','VARCHAR(20)') , --retrieve index 1 only, which is the 'ab'
T.c.value('(/root/myvalue)[2]','VARCHAR(20)')
FROM #X.nodes('/root/myvalue') T(c)
I think this is cool
SELECT value,
PARSENAME(REPLACE(String,',','.'),2) 'Name' ,
PARSENAME(REPLACE(String,',','.'),1) 'Surname'
FROM table WITH (NOLOCK)
With CROSS APPLY
select ParsedData.*
from MyTable mt
cross apply ( select str = mt.String + ',,' ) f1
cross apply ( select p1 = charindex( ',', str ) ) ap1
cross apply ( select p2 = charindex( ',', str, p1 + 1 ) ) ap2
cross apply ( select Nmame = substring( str, 1, p1-1 )
, Surname = substring( str, p1+1, p2-p1-1 )
) ParsedData
There are multiple ways to solve this and many different ways have been proposed already. Simplest would be to use LEFT / SUBSTRING and other string functions to achieve the desired result.
Sample Data
DECLARE #tbl1 TABLE (Value INT,String VARCHAR(MAX))
INSERT INTO #tbl1 VALUES(1,'Cleo, Smith');
INSERT INTO #tbl1 VALUES(2,'John, Mathew');
Using String Functions like LEFT
SELECT
Value,
LEFT(String,CHARINDEX(',',String)-1) as Fname,
LTRIM(RIGHT(String,LEN(String) - CHARINDEX(',',String) )) AS Lname
FROM #tbl1
This approach fails if there are more 2 items in a String.
In such a scenario, we can use a splitter and then use PIVOT or convert the string into an XML and use .nodes to get string items. XML based solution have been detailed out by aads and bvr in their solution.
The answers for this question which use splitter, all use WHILE which is inefficient for splitting. Check this performance comparison. One of the best splitters around is DelimitedSplit8K, created by Jeff Moden. You can read more about it here
Splitter with PIVOT
DECLARE #tbl1 TABLE (Value INT,String VARCHAR(MAX))
INSERT INTO #tbl1 VALUES(1,'Cleo, Smith');
INSERT INTO #tbl1 VALUES(2,'John, Mathew');
SELECT t3.Value,[1] as Fname,[2] as Lname
FROM #tbl1 as t1
CROSS APPLY [dbo].[DelimitedSplit8K](String,',') as t2
PIVOT(MAX(Item) FOR ItemNumber IN ([1],[2])) as t3
Output
Value Fname Lname
1 Cleo Smith
2 John Mathew
DelimitedSplit8K by Jeff Moden
CREATE FUNCTION [dbo].[DelimitedSplit8K]
/**********************************************************************************************************************
Purpose:
Split a given string at a given delimiter and return a list of the split elements (items).
Notes:
1. Leading a trailing delimiters are treated as if an empty string element were present.
2. Consecutive delimiters are treated as if an empty string element were present between them.
3. Except when spaces are used as a delimiter, all spaces present in each element are preserved.
Returns:
iTVF containing the following:
ItemNumber = Element position of Item as a BIGINT (not converted to INT to eliminate a CAST)
Item = Element value as a VARCHAR(8000)
Statistics on this function may be found at the following URL:
http://www.sqlservercentral.com/Forums/Topic1101315-203-4.aspx
CROSS APPLY Usage Examples and Tests:
--=====================================================================================================================
-- TEST 1:
-- This tests for various possible conditions in a string using a comma as the delimiter. The expected results are
-- laid out in the comments
--=====================================================================================================================
--===== Conditionally drop the test tables to make reruns easier for testing.
-- (this is NOT a part of the solution)
IF OBJECT_ID('tempdb..#JBMTest') IS NOT NULL DROP TABLE #JBMTest
;
--===== Create and populate a test table on the fly (this is NOT a part of the solution).
-- In the following comments, "b" is a blank and "E" is an element in the left to right order.
-- Double Quotes are used to encapsulate the output of "Item" so that you can see that all blanks
-- are preserved no matter where they may appear.
SELECT *
INTO #JBMTest
FROM ( --# & type of Return Row(s)
SELECT 0, NULL UNION ALL --1 NULL
SELECT 1, SPACE(0) UNION ALL --1 b (Empty String)
SELECT 2, SPACE(1) UNION ALL --1 b (1 space)
SELECT 3, SPACE(5) UNION ALL --1 b (5 spaces)
SELECT 4, ',' UNION ALL --2 b b (both are empty strings)
SELECT 5, '55555' UNION ALL --1 E
SELECT 6, ',55555' UNION ALL --2 b E
SELECT 7, ',55555,' UNION ALL --3 b E b
SELECT 8, '55555,' UNION ALL --2 b B
SELECT 9, '55555,1' UNION ALL --2 E E
SELECT 10, '1,55555' UNION ALL --2 E E
SELECT 11, '55555,4444,333,22,1' UNION ALL --5 E E E E E
SELECT 12, '55555,4444,,333,22,1' UNION ALL --6 E E b E E E
SELECT 13, ',55555,4444,,333,22,1,' UNION ALL --8 b E E b E E E b
SELECT 14, ',55555,4444,,,333,22,1,' UNION ALL --9 b E E b b E E E b
SELECT 15, ' 4444,55555 ' UNION ALL --2 E (w/Leading Space) E (w/Trailing Space)
SELECT 16, 'This,is,a,test.' --E E E E
) d (SomeID, SomeValue)
;
--===== Split the CSV column for the whole table using CROSS APPLY (this is the solution)
SELECT test.SomeID, test.SomeValue, split.ItemNumber, Item = QUOTENAME(split.Item,'"')
FROM #JBMTest test
CROSS APPLY dbo.DelimitedSplit8K(test.SomeValue,',') split
;
--=====================================================================================================================
-- TEST 2:
-- This tests for various "alpha" splits and COLLATION using all ASCII characters from 0 to 255 as a delimiter against
-- a given string. Note that not all of the delimiters will be visible and some will show up as tiny squares because
-- they are "control" characters. More specifically, this test will show you what happens to various non-accented
-- letters for your given collation depending on the delimiter you chose.
--=====================================================================================================================
WITH
cteBuildAllCharacters (String,Delimiter) AS
(
SELECT TOP 256
'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789',
CHAR(ROW_NUMBER() OVER (ORDER BY (SELECT NULL))-1)
FROM master.sys.all_columns
)
SELECT ASCII_Value = ASCII(c.Delimiter), c.Delimiter, split.ItemNumber, Item = QUOTENAME(split.Item,'"')
FROM cteBuildAllCharacters c
CROSS APPLY dbo.DelimitedSplit8K(c.String,c.Delimiter) split
ORDER BY ASCII_Value, split.ItemNumber
;
-----------------------------------------------------------------------------------------------------------------------
Other Notes:
1. Optimized for VARCHAR(8000) or less. No testing or error reporting for truncation at 8000 characters is done.
2. Optimized for single character delimiter. Multi-character delimiters should be resolvedexternally from this
function.
3. Optimized for use with CROSS APPLY.
4. Does not "trim" elements just in case leading or trailing blanks are intended.
5. If you don't know how a Tally table can be used to replace loops, please see the following...
http://www.sqlservercentral.com/articles/T-SQL/62867/
6. Changing this function to use NVARCHAR(MAX) will cause it to run twice as slow. It's just the nature of
VARCHAR(MAX) whether it fits in-row or not.
7. Multi-machine testing for the method of using UNPIVOT instead of 10 SELECT/UNION ALLs shows that the UNPIVOT method
is quite machine dependent and can slow things down quite a bit.
-----------------------------------------------------------------------------------------------------------------------
Credits:
This code is the product of many people's efforts including but not limited to the following:
cteTally concept originally by Iztek Ben Gan and "decimalized" by Lynn Pettis (and others) for a bit of extra speed
and finally redacted by Jeff Moden for a different slant on readability and compactness. Hat's off to Paul White for
his simple explanations of CROSS APPLY and for his detailed testing efforts. Last but not least, thanks to
Ron "BitBucket" McCullough and Wayne Sheffield for their extreme performance testing across multiple machines and
versions of SQL Server. The latest improvement brought an additional 15-20% improvement over Rev 05. Special thanks
to "Nadrek" and "peter-757102" (aka Peter de Heer) for bringing such improvements to light. Nadrek's original
improvement brought about a 10% performance gain and Peter followed that up with the content of Rev 07.
I also thank whoever wrote the first article I ever saw on "numbers tables" which is located at the following URL
and to Adam Machanic for leading me to it many years ago.
http://sqlserver2000.databases.aspfaq.com/why-should-i-consider-using-an-auxiliary-numbers-table.html
-----------------------------------------------------------------------------------------------------------------------
Revision History:
Rev 00 - 20 Jan 2010 - Concept for inline cteTally: Lynn Pettis and others.
Redaction/Implementation: Jeff Moden
- Base 10 redaction and reduction for CTE. (Total rewrite)
Rev 01 - 13 Mar 2010 - Jeff Moden
- Removed one additional concatenation and one subtraction from the SUBSTRING in the SELECT List for that tiny
bit of extra speed.
Rev 02 - 14 Apr 2010 - Jeff Moden
- No code changes. Added CROSS APPLY usage example to the header, some additional credits, and extra
documentation.
Rev 03 - 18 Apr 2010 - Jeff Moden
- No code changes. Added notes 7, 8, and 9 about certain "optimizations" that don't actually work for this
type of function.
Rev 04 - 29 Jun 2010 - Jeff Moden
- Added WITH SCHEMABINDING thanks to a note by Paul White. This prevents an unnecessary "Table Spool" when the
function is used in an UPDATE statement even though the function makes no external references.
Rev 05 - 02 Apr 2011 - Jeff Moden
- Rewritten for extreme performance improvement especially for larger strings approaching the 8K boundary and
for strings that have wider elements. The redaction of this code involved removing ALL concatenation of
delimiters, optimization of the maximum "N" value by using TOP instead of including it in the WHERE clause,
and the reduction of all previous calculations (thanks to the switch to a "zero based" cteTally) to just one
instance of one add and one instance of a subtract. The length calculation for the final element (not
followed by a delimiter) in the string to be split has been greatly simplified by using the ISNULL/NULLIF
combination to determine when the CHARINDEX returned a 0 which indicates there are no more delimiters to be
had or to start with. Depending on the width of the elements, this code is between 4 and 8 times faster on a
single CPU box than the original code especially near the 8K boundary.
- Modified comments to include more sanity checks on the usage example, etc.
- Removed "other" notes 8 and 9 as they were no longer applicable.
Rev 06 - 12 Apr 2011 - Jeff Moden
- Based on a suggestion by Ron "Bitbucket" McCullough, additional test rows were added to the sample code and
the code was changed to encapsulate the output in pipes so that spaces and empty strings could be perceived
in the output. The first "Notes" section was added. Finally, an extra test was added to the comments above.
Rev 07 - 06 May 2011 - Peter de Heer, a further 15-20% performance enhancement has been discovered and incorporated
into this code which also eliminated the need for a "zero" position in the cteTally table.
**********************************************************************************************************************/
--===== Define I/O parameters
(#pString VARCHAR(8000), #pDelimiter CHAR(1))
RETURNS TABLE WITH SCHEMABINDING AS
RETURN
--===== "Inline" CTE Driven "Tally Table" produces values from 0 up to 10,000...
-- enough to cover NVARCHAR(4000)
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
With SQL Server 2016 we can use string_split to accomplish this:
create table commasep (
id int identity(1,1)
,string nvarchar(100) )
insert into commasep (string) values ('John, Adam'), ('test1,test2,test3')
select id, [value] as String from commasep
cross apply string_split(string,',')
CREATE FUNCTION [dbo].[fn_split_string_to_column] (
#string NVARCHAR(MAX),
#delimiter CHAR(1)
)
RETURNS #out_put TABLE (
[column_id] INT IDENTITY(1, 1) NOT NULL,
[value] NVARCHAR(MAX)
)
AS
BEGIN
DECLARE #value NVARCHAR(MAX),
#pos INT = 0,
#len INT = 0
SET #string = CASE
WHEN RIGHT(#string, 1) != #delimiter
THEN #string + #delimiter
ELSE #string
END
WHILE CHARINDEX(#delimiter, #string, #pos + 1) > 0
BEGIN
SET #len = CHARINDEX(#delimiter, #string, #pos + 1) - #pos
SET #value = SUBSTRING(#string, #pos, #len)
INSERT INTO #out_put ([value])
SELECT LTRIM(RTRIM(#value)) AS [column]
SET #pos = CHARINDEX(#delimiter, #string, #pos + #len) + 1
END
RETURN
END
SELECT id,
Substring(NAME, 0, Charindex(',', NAME)) AS firstname,
Substring(NAME, Charindex(',', NAME), Len(NAME) + 1) AS lastname
FROM spilt
Try this (change instances of ' ' to ',' or whatever delimiter you want to use)
CREATE FUNCTION dbo.Wordparser
(
#multiwordstring VARCHAR(255),
#wordnumber NUMERIC
)
returns VARCHAR(255)
AS
BEGIN
DECLARE #remainingstring VARCHAR(255)
SET #remainingstring=#multiwordstring
DECLARE #numberofwords NUMERIC
SET #numberofwords=(LEN(#remainingstring) - LEN(REPLACE(#remainingstring, ' ', '')) + 1)
DECLARE #word VARCHAR(50)
DECLARE #parsedwords TABLE
(
line NUMERIC IDENTITY(1, 1),
word VARCHAR(255)
)
WHILE #numberofwords > 1
BEGIN
SET #word=LEFT(#remainingstring, CHARINDEX(' ', #remainingstring) - 1)
INSERT INTO #parsedwords(word)
SELECT #word
SET #remainingstring= REPLACE(#remainingstring, Concat(#word, ' '), '')
SET #numberofwords=(LEN(#remainingstring) - LEN(REPLACE(#remainingstring, ' ', '')) + 1)
IF #numberofwords = 1
BREAK
ELSE
CONTINUE
END
IF #numberofwords = 1
SELECT #word = #remainingstring
INSERT INTO #parsedwords(word)
SELECT #word
RETURN
(SELECT word
FROM #parsedwords
WHERE line = #wordnumber)
END
Example usage:
SELECT dbo.Wordparser(COLUMN, 1),
dbo.Wordparser(COLUMN, 2),
dbo.Wordparser(COLUMN, 3)
FROM TABLE
I think PARSENAME is the neat function to use for this example, as described in this article: http://www.sqlshack.com/parsing-and-rotating-delimited-data-in-sql-server-2012/
The PARSENAME function is logically designed to parse four-part object names. The nice thing about PARSENAME is that it’s not limited to parsing just SQL Server four-part object names – it will parse any function or string data that is delimited by dots.
The first parameter is the object to parse, and the second is the integer value of the object piece to return. The article is discussing parsing and rotating delimited data - company phone numbers, but it can be used to parse name/surname data also.
Example:
USE COMPANY;
SELECT PARSENAME('Whatever.you.want.parsed',3) AS 'ReturnValue';
The article also describes using a Common Table Expression (CTE) called ‘replaceChars’, to run PARSENAME against the delimiter-replaced values. A CTE is useful for returning a temporary view or result set.
After that, the UNPIVOT function has been used to convert some columns into rows; SUBSTRING and CHARINDEX functions have been used for cleaning up the inconsistencies in the data, and the LAG function (new for SQL Server 2012) has been used in the end, as it allows referencing of previous records.
We can create a function as this
CREATE Function [dbo].[fn_CSVToTable]
(
#CSVList Varchar(max)
)
RETURNS #Table TABLE (ColumnData VARCHAR(100))
AS
BEGIN
IF RIGHT(#CSVList, 1) <> ','
SELECT #CSVList = #CSVList + ','
DECLARE #Pos BIGINT,
#OldPos BIGINT
SELECT #Pos = 1,
#OldPos = 1
WHILE #Pos < LEN(#CSVList)
BEGIN
SELECT #Pos = CHARINDEX(',', #CSVList, #OldPos)
INSERT INTO #Table
SELECT LTRIM(RTRIM(SUBSTRING(#CSVList, #OldPos, #Pos - #OldPos))) Col001
SELECT #OldPos = #Pos + 1
END
RETURN
END
We can then seperate the CSV values into our respective columns using a SELECT statement
You can use a table-valued function STRING_SPLIT, which is available only under compatibility level 130. If your database compatibility level is lower than 130, SQL Server will not be able to find and execute the STRING_SPLIT function. You can change a compatibility level of the database using the following command:
ALTER DATABASE DatabaseName SET COMPATIBILITY_LEVEL = 130
Syntax
SELECT * FROM STRING_SPLIT ( string, separator )
see documentation here
I think following function will work for you:
You have to create a function in SQL first. Like this
CREATE FUNCTION [dbo].[fn_split](
#str VARCHAR(MAX),
#delimiter CHAR(1)
)
RETURNS #returnTable TABLE (idx INT PRIMARY KEY IDENTITY, item VARCHAR(8000))
AS
BEGIN
DECLARE #pos INT
SELECT #str = #str + #delimiter
WHILE LEN(#str) > 0
BEGIN
SELECT #pos = CHARINDEX(#delimiter,#str)
IF #pos = 1
INSERT #returnTable (item)
VALUES (NULL)
ELSE
INSERT #returnTable (item)
VALUES (SUBSTRING(#str, 1, #pos-1))
SELECT #str = SUBSTRING(#str, #pos+1, LEN(#str)-#pos)
END
RETURN
END
You can call this function, like this:
select * from fn_split('1,24,5',',')
Implementation:
Declare #test TABLE (
ID VARCHAR(200),
Data VARCHAR(200)
)
insert into #test
(ID, Data)
Values
('1','Cleo,Smith')
insert into #test
(ID, Data)
Values
('2','Paul,Grim')
select ID,
(select item from fn_split(Data,',') where idx in (1)) as Name ,
(select item from fn_split(Data,',') where idx in (2)) as Surname
from #test
Result will like this:
Use Parsename() function
with cte as(
select 'Aria,Karimi' as FullName
Union
select 'Joe,Karimi' as FullName
Union
select 'Bab,Karimi' as FullName
)
SELECT PARSENAME(REPLACE(FullName,',','.'),2) as Name,
PARSENAME(REPLACE(FullName,',','.'),1) as Family
FROM cte
Result
Name Family
----- ------
Aria Karimi
Bab Karimi
Joe Karimi
Try this:
declare #csv varchar(100) ='aaa,bb,csda,daass';
set #csv = #csv+',';
with cte as
(
select SUBSTRING(#csv,1,charindex(',',#csv,1)-1) as val, SUBSTRING(#csv,charindex(',',#csv,1)+1,len(#csv)) as rem
UNION ALL
select SUBSTRING(a.rem,1,charindex(',',a.rem,1)-1)as val, SUBSTRING(a.rem,charindex(',',a.rem,1)+1,len(A.rem))
from cte a where LEN(a.rem)>=1
) select val from cte
This function is most fast:
CREATE FUNCTION dbo.F_ExtractSubString
(
#String VARCHAR(MAX),
#NroSubString INT,
#Separator VARCHAR(5)
)
RETURNS VARCHAR(MAX) AS
BEGIN
DECLARE #St INT = 0, #End INT = 0, #Ret VARCHAR(MAX)
SET #String = #String + #Separator
WHILE CHARINDEX(#Separator, #String, #End + 1) > 0 AND #NroSubString > 0
BEGIN
SET #St = #End + 1
SET #End = CHARINDEX(#Separator, #String, #End + 1)
SET #NroSubString = #NroSubString - 1
END
IF #NroSubString > 0
SET #Ret = ''
ELSE
SET #Ret = SUBSTRING(#String, #St, #End - #St)
RETURN #Ret
END
GO
Example usage:
SELECT dbo.F_ExtractSubString(COLUMN, 1, ', '),
dbo.F_ExtractSubString(COLUMN, 2, ', '),
dbo.F_ExtractSubString(COLUMN, 3, ', ')
FROM TABLE
I encountered a similar problem but a complex one and since this is the first thread i found regarding that issue i decided to post my finding. i know it is complex solution to a simple problem but i hope that i could help other people who go to this thread looking for a more complex solution. i had to split a string containing 5 numbers (column name: levelsFeed) and to show each number in a separate column.
for example: 8,1,2,2,2
should be shown as :
1 2 3 4 5
-------------
8 1 2 2 2
Solution 1: using XML functions:
this solution for the slowest solution by far
SELECT Distinct FeedbackID,
, S.a.value('(/H/r)[1]', 'INT') AS level1
, S.a.value('(/H/r)[2]', 'INT') AS level2
, S.a.value('(/H/r)[3]', 'INT') AS level3
, S.a.value('(/H/r)[4]', 'INT') AS level4
, S.a.value('(/H/r)[5]', 'INT') AS level5
FROM (
SELECT *,CAST (N'<H><r>' + REPLACE(levelsFeed, ',', '</r><r>') + '</r> </H>' AS XML) AS [vals]
FROM Feedbacks
) as d
CROSS APPLY d.[vals].nodes('/H/r') S(a)
Solution 2: using Split function and pivot. (the split function split a string to rows with the column name Data)
SELECT FeedbackID, [1],[2],[3],[4],[5]
FROM (
SELECT *, ROW_NUMBER() OVER (PARTITION BY feedbackID ORDER BY (SELECT null)) as rn
FROM (
SELECT FeedbackID, levelsFeed
FROM Feedbacks
) as a
CROSS APPLY dbo.Split(levelsFeed, ',')
) as SourceTable
PIVOT
(
MAX(data)
FOR rn IN ([1],[2],[3],[4],[5])
)as pivotTable
Solution 3: using string manipulations functions - fastest by small margin over solution 2
SELECT FeedbackID,
SUBSTRING(levelsFeed,0,CHARINDEX(',',levelsFeed)) AS level1,
PARSENAME(REPLACE(SUBSTRING(levelsFeed,CHARINDEX(',',levelsFeed)+1,LEN(levelsFeed)),',','.'),4) AS level2,
PARSENAME(REPLACE(SUBSTRING(levelsFeed,CHARINDEX(',',levelsFeed)+1,LEN(levelsFeed)),',','.'),3) AS level3,
PARSENAME(REPLACE(SUBSTRING(levelsFeed,CHARINDEX(',',levelsFeed)+1,LEN(levelsFeed)),',','.'),2) AS level4,
PARSENAME(REPLACE(SUBSTRING(levelsFeed,CHARINDEX(',',levelsFeed)+1,LEN(levelsFeed)),',','.'),1) AS level5
FROM Feedbacks
since the levelsFeed contains 5 string values i needed to use the substring function for the first string.
i hope that my solution will help other that got to this thread looking for a more complex split to columns methods
Using instring function :)
select Value,
substring(String,1,instr(String," ") -1) Fname,
substring(String,instr(String,",") +1) Sname
from tablename;
Used two functions,
1. substring(string, position, length) ==> returns string from positon to length
2. instr(string,pattern) ==> returns position of pattern.
If we don’t provide length argument in substring it returns until end of string
This worked for me
CREATE FUNCTION [dbo].[SplitString](
#delimited NVARCHAR(MAX),
#delimiter NVARCHAR(100)
) RETURNS #t TABLE ( val NVARCHAR(MAX))
AS
BEGIN
DECLARE #xml XML
SET #xml = N'<t>' + REPLACE(#delimited,#delimiter,'</t><t>') + '</t>'
INSERT INTO #t(val)
SELECT r.value('.','varchar(MAX)') as item
FROM #xml.nodes('/t') as records(r)
RETURN
END
mytable:
Value ColOne
--------------------
1 Cleo, Smith
The following should work if there aren't too many columns
ALTER TABLE mytable ADD ColTwo nvarchar(256);
UPDATE mytable SET ColTwo = LEFT(ColOne, Charindex(',', ColOne) - 1);
--'Cleo' = LEFT('Cleo, Smith', Charindex(',', 'Cleo, Smith') - 1)
UPDATE mytable SET ColTwo = REPLACE(ColOne, ColTwo + ',', '');
--' Smith' = REPLACE('Cleo, Smith', 'Cleo' + ',')
UPDATE mytable SET ColOne = REPLACE(ColOne, ',' + ColTwo, ''), ColTwo = LTRIM(ColTwo);
--'Cleo' = REPLACE('Cleo, Smith', ',' + ' Smith', '')
Result:
Value ColOne ColTwo
--------------------
1 Cleo Smith
DECLARE #INPUT VARCHAR (MAX)='N,A,R,E,N,D,R,A'
DECLARE #ELIMINATE_CHAR CHAR (1)=','
DECLARE #L_START INT=1
DECLARE #L_END INT=(SELECT LEN (#INPUT))
DECLARE #OUTPUT CHAR (1)
WHILE #L_START <=#L_END
BEGIN
SET #OUTPUT=(SUBSTRING (#INPUT,#L_START,1))
IF #OUTPUT!=#ELIMINATE_CHAR
BEGIN
PRINT #OUTPUT
END
SET #L_START=#L_START+1
END
You may find the solution in SQL User Defined Function to Parse a Delimited String helpful (from The Code Project).
This is the code part from this page:
CREATE FUNCTION [fn_ParseText2Table]
(#p_SourceText VARCHAR(MAX)
,#p_Delimeter VARCHAR(100)=',' --default to comma delimited.
)
RETURNS #retTable
TABLE([Position] INT IDENTITY(1,1)
,[Int_Value] INT
,[Num_Value] NUMERIC(18,3)
,[Txt_Value] VARCHAR(MAX)
,[Date_value] DATETIME
)
AS
/*
********************************************************************************
Purpose: Parse values from a delimited string
& return the result as an indexed table
Copyright 1996, 1997, 2000, 2003 Clayton Groom (Clayton_Groom#hotmail.com)
Posted to the public domain Aug, 2004
2003-06-17 Rewritten as SQL 2000 function.
Reworked to allow for delimiters > 1 character in length
and to convert Text values to numbers
2016-04-05 Added logic for date values based on "new" ISDATE() function, Updated to use XML approach, which is more efficient.
********************************************************************************
*/
BEGIN
DECLARE #w_xml xml;
SET #w_xml = N'<root><i>' + replace(#p_SourceText, #p_Delimeter,'</i><i>') + '</i></root>';
INSERT INTO #retTable
([Int_Value]
, [Num_Value]
, [Txt_Value]
, [Date_value]
)
SELECT CASE
WHEN ISNUMERIC([i].value('.', 'VARCHAR(MAX)')) = 1
THEN CAST(CAST([i].value('.', 'VARCHAR(MAX)') AS NUMERIC) AS INT)
END AS [Int_Value]
, CASE
WHEN ISNUMERIC([i].value('.', 'VARCHAR(MAX)')) = 1
THEN CAST([i].value('.', 'VARCHAR(MAX)') AS NUMERIC(18, 3))
END AS [Num_Value]
, [i].value('.', 'VARCHAR(MAX)') AS [txt_Value]
, CASE
WHEN ISDATE([i].value('.', 'VARCHAR(MAX)')) = 1
THEN CAST([i].value('.', 'VARCHAR(MAX)') AS DATETIME)
END AS [Num_Value]
FROM #w_xml.nodes('//root/i') AS [Items]([i]);
RETURN;
END;
GO
ALTER function get_occurance_index(#delimiter varchar(1),#occurence int,#String varchar(100))
returns int
AS Begin
--Declare #delimiter varchar(1)=',',#occurence int=2,#String varchar(100)='a,b,c'
Declare #result int
;with T as (
select 1 Rno,0 as row, charindex(#delimiter, #String) pos,#String st
union all
select Rno+1,pos + 1, charindex(#delimiter, #String, pos + 1), #String
from T
where pos > 0
)
select #result=pos
from T
where pos > 0 and rno = #occurence
return isnull(#result,0)
ENd
declare #data as table (data varchar(100))
insert into #data values('1,2,3')
insert into #data values('aaa,bbbbb,cccc')
select top 3 Substring (data,0,dbo.get_occurance_index( ',',1,data)) ,--First Record always starts with 0
Substring (data,dbo.get_occurance_index( ',',1,data)+1,dbo.get_occurance_index( ',',2,data)-dbo.get_occurance_index( ',',1,data)-1) ,
Substring (data,dbo.get_occurance_index( ',',2,data)+1,len(data)) , -- Last record cant be more than len of actual data
data
From #data
I found that using PARSENAME as above caused any name with a period to get nulled.
So if there was an initial or a title in the name followed by a dot they return NULL.
I found this worked for me:
SELECT
REPLACE(SUBSTRING(FullName, 1,CHARINDEX(',', FullName)), ',','') as Name,
REPLACE(SUBSTRING(FullName, CHARINDEX(',', FullName), LEN(FullName)), ',', '') as Surname
FROM Table1
it is so easy, you can take it by below query:
DECLARE #str NVARCHAR(MAX)='ControlID_05436b78-04ba-9667-fa01-9ff8c1b7c235,3'
SELECT LEFT(#str, CHARINDEX(',',#str)-1),RIGHT(#str,LEN(#str)-(CHARINDEX(',',#str)))
select distinct modelFileId,F4.*
from contract
cross apply (select XmlList=convert(xml, '<x>'+replace(modelFileId,';','</x><x>')+'</x>').query('.')) F2
cross apply (select mfid1=XmlNode.value('/x[1]','varchar(512)')
,mfid2=XmlNode.value('/x[2]','varchar(512)')
,mfid3=XmlNode.value('/x[3]','varchar(512)')
,mfid4=XmlNode.value('/x[4]','varchar(512)') from XmlList.nodes('x') F3(XmlNode)) F4
where modelFileId like '%;%'
order by modelFileId
Select distinct PROJ_UID,PROJ_NAME,RES_UID from E2E_ProjectWiseTimesheetActuals
where CHARINDEX(','+cast(PROJ_UID as varchar(8000))+',', #params) > 0 and CHARINDEX(','+cast(RES_UID as varchar(8000))+',', #res) > 0
I re-wrote an answer above and made it better:
CREATE FUNCTION [dbo].[CSVParser]
(
#s VARCHAR(255),
#idx NUMERIC
)
RETURNS VARCHAR(12)
BEGIN
DECLARE #comma int
SET #comma = CHARINDEX(',', #s)
WHILE 1=1
BEGIN
IF #comma=0
IF #idx=1
RETURN #s
ELSE
RETURN ''
IF #idx=1
BEGIN
DECLARE #word VARCHAR(12)
SET #word=LEFT(#s, #comma - 1)
RETURN #word
END
SET #s = RIGHT(#s,LEN(#s)-#comma)
SET #comma = CHARINDEX(',', #s)
SET #idx = #idx - 1
END
RETURN 'not used'
END
Example usage:
SELECT dbo.CSVParser(COLUMN, 1),
dbo.CSVParser(COLUMN, 2),
dbo.CSVParser(COLUMN, 3)
FROM TABLE
question is simple, but problem is hot :)
So I create some wrapper for string_split() which pivot result in more generic way. It's table function which returns values (nn, value1, value2, ... , value50) - enough for most CSV lines. If there are more values, they will wrap to next line - nn indicate line number. Set third parameter #columnCnt = [yourNumber] to wrap at specific position:
alter FUNCTION fn_Split50
(
#str varchar(max),
#delim char(1),
#columnCnt int = 50
)
RETURNS TABLE
AS
RETURN
(
SELECT *
FROM (SELECT
nn = (nn - 1) / #columnCnt + 1,
nnn = 'value' + cast(((nn - 1) % #columnCnt) + 1 as varchar(10)),
value
FROM (SELECT
nn = ROW_NUMBER() over (order by (select null)),
value
FROM string_split(#str, #delim) aa
) aa
where nn > 0
) bb
PIVOT
(
max(value)
FOR nnn IN (
value1, value2, value3, value4, value5, value6, value7, value8, value9, value10,
value11, value12, value13, value14, value15, value16, value17, value18, value19, value20,
value21, value22, value23, value24, value25, value26, value27, value28, value29, value30,
value31, value32, value33, value34, value35, value36, value37, value38, value39, value40,
value41, value42, value43, value44, value45, value46, value47, value48, value49, value50
)
) AS PivotTable
)
Example of using:
select * from dbo.fn_split50('zz1,aa2,ss3,dd4,ff5', ',', DEFAULT)
select * from dbo.fn_split50('zz1,aa2,ss3,dd4,ff5,gg6,hh7,jj8,ww9,qq10', ',', 3)
select * from dbo.fn_split50('zz1,11,aa2,22,ss3,33,dd4,44,ff5,55,gg6,66,hh7,77,jj8,88,ww9,99,qq10,1010', ',',2)
Hope, it will helps :)

Remove some characters from string sql [duplicate]

I've got dirty data in a column with variable alpha length. I just want to strip out anything that is not 0-9.
I do not want to run a function or proc. I have a script that is similar that just grabs the numeric value after text, it looks like this:
Update TableName
set ColumntoUpdate=cast(replace(Columnofdirtydata,'Alpha #','') as int)
where Columnofdirtydata like 'Alpha #%'
And ColumntoUpdate is Null
I thought it would work pretty good until I found that some of the data fields I thought would just be in the format Alpha # 12345789 are not.
Examples of data that needs to be stripped
AB ABCDE # 123
ABCDE# 123
AB: ABC# 123
I just want the 123. It is true that all data fields do have the # prior to the number.
I tried substring and PatIndex, but I'm not quite getting the syntax correct or something. Anyone have any advice on the best way to address this?
See this blog post on extracting numbers from strings in SQL Server. Below is a sample using a string in your example:
DECLARE #textval NVARCHAR(30)
SET #textval = 'AB ABCDE # 123'
SELECT LEFT(SUBSTRING(#textval, PATINDEX('%[0-9.-]%', #textval), 8000),
PATINDEX('%[^0-9.-]%', SUBSTRING(#textval, PATINDEX('%[0-9.-]%', #textval), 8000) + 'X') -1)
Here is an elegant solution if your server supports the TRANSLATE function (on sql server it's available on sql server 2017+ and also sql azure).
First, it replaces any non numeric characters with a # character.
Then, it removes all # characters.
You may need to add additional characters that you know may be present in the second parameter of the TRANSLATE call.
select REPLACE(TRANSLATE([Col], 'abcdefghijklmnopqrstuvwxyz+()- ,#+', '##################################'), '#', '')
You can use stuff and patindex.
stuff(Col, 1, patindex('%[0-9]%', Col)-1, '')
SQL Fiddle
This works well for me:
CREATE FUNCTION [dbo].[StripNonNumerics]
(
#Temp varchar(255)
)
RETURNS varchar(255)
AS
Begin
Declare #KeepValues as varchar(50)
Set #KeepValues = '%[^0-9]%'
While PatIndex(#KeepValues, #Temp) > 0
Set #Temp = Stuff(#Temp, PatIndex(#KeepValues, #Temp), 1, '')
Return #Temp
End
Then call the function like so to see the original something next to the sanitized something:
SELECT Something, dbo.StripNonNumerics(Something) FROM TableA
In case if there are some characters possible between digits (e.g. thousands separators), you may try following:
declare #table table (DirtyCol varchar(100))
insert into #table values
('AB ABCDE # 123')
,('ABCDE# 123')
,('AB: ABC# 123')
,('AB#')
,('AB # 1 000 000')
,('AB # 1`234`567')
,('AB # (9)(876)(543)')
;with tally as (select top (100) N=row_number() over (order by ##spid) from sys.all_columns),
data as (
select DirtyCol, Col
from #table
cross apply (
select (select C + ''
from (select N, substring(DirtyCol, N, 1) C from tally where N<=datalength(DirtyCol)) [1]
where C between '0' and '9'
order by N
for xml path(''))
) p (Col)
where p.Col is not NULL
)
select DirtyCol, cast(Col as int) IntCol
from data
Output is:
DirtyCol IntCol
--------------------- -------
AB ABCDE # 123 123
ABCDE# 123 123
AB: ABC# 123 123
AB # 1 000 000 1000000
AB # 1`234`567 1234567
AB # (9)(876)(543) 9876543
For update, add ColToUpdate to select list of the data cte:
;with num as (...),
data as (
select ColToUpdate, /*DirtyCol, */Col
from ...
)
update data
set ColToUpdate = cast(Col as int)
CREATE FUNCTION FN_RemoveNonNumeric (#Input NVARCHAR(512))
RETURNS NVARCHAR(512)
AS
BEGIN
DECLARE #Trimmed NVARCHAR(512)
SELECT #Trimmed = #Input
WHILE PATINDEX('%[^0-9]%', #Trimmed) > 0
SELECT #Trimmed = REPLACE(#Trimmed, SUBSTRING(#Trimmed, PATINDEX('%[^0-9]%', #Trimmed), 1), '')
RETURN #Trimmed
END
GO
SELECT dbo.FN_RemoveNonNumeric('ABCDE# 123')
Pretty late to the party, I found the following which I though worked brilliantialy.. if anyone is still looking
SELECT
(SELECT CAST(CAST((
SELECT SUBSTRING(FieldToStrip, Number, 1)
FROM master..spt_values
WHERE Type='p' AND Number <= LEN(FieldToStrip) AND
SUBSTRING(FieldToStrip, Number, 1) LIKE '[0-9]' FOR XML Path(''))
AS xml) AS varchar(MAX)))
FROM
SourceTable
Here's a version which pulls all digits from a string; i.e. given I'm 35 years old; I was born in 1982. The average family has 2.4 children. this would return 35198224. i.e. it's good where you've got numeric data which may have been formatted as a code (e.g. #123,456,789 / 123-00005), but isn't appropriate if you're looking to pull out specific numbers (i.e. as opposed to digits / just the numeric characters) from the text. Also it only handles digits; so won't return negative signs (-) or periods .).
declare #table table (id bigint not null identity (1,1), data nvarchar(max))
insert #table (data)
values ('hello 123 its 45613 then') --outputs: 12345613
,('1 some other string 98 example 4') --outputs: 1984
,('AB ABCDE # 123') --outputs: 123
,('ABCDE# 123') --outputs: 123
,('AB: ABC# 123') --outputs: 123
; with NonNumerics as (
select id
, data original
--the below line replaces all digits with blanks
, replace(replace(replace(replace(replace(replace(replace(replace(replace(replace(data,'0',''),'1',''),'2',''),'3',''),'4',''),'5',''),'6',''),'7',''),'8',''),'9','') nonNumeric
from #table
)
--each iteration of the below CTE removes another non-numeric character from the original string, putting the result into the numerics column
, Numerics as (
select id
, replace(original, substring(nonNumeric,1,1), '') numerics
, replace(nonNumeric, substring(nonNumeric,1,1), '') charsToreplace
, len(replace(nonNumeric, substring(nonNumeric,1,1), '')) charsRemaining
from NonNumerics
union all
select id
, replace(numerics, substring(charsToreplace,1,1), '') numerics
, replace(charsToreplace, substring(charsToreplace,1,1), '') charsToreplace
, len(replace(charsToreplace, substring(charsToreplace,1,1), '')) charsRemaining
from Numerics
where charsRemaining > 0
)
--we select only those strings with `charsRemaining=0`; i.e. the rows for which all non-numeric characters have been removed; there should be 1 row returned for every 1 row in the original data set.
select * from Numerics where charsRemaining = 0
This code works by removing all the digits (i.e. the characters we want) from a the given strings by replacing them with blanks. Then it goes through the original string (which includes the digits) removing all of the characters that were left (i.e. the non-numeric characters), thus leaving only the digits.
The reason we do this in 2 steps, rather than just removing all non-numeric characters in the first place is there are only 10 digits, whilst there are a huge number of possible characters; so replacing that small list is relatively fast; then gives us a list of those non-numeric characters which actually exist in the string, so we can then replace that small set.
The method makes use of recursive SQL, using common table expressions (CTEs).
To add on to Ken's answer, this handles commas and spaces and parentheses
--Handles parentheses, commas, spaces, hyphens..
declare #table table (c varchar(256))
insert into #table
values
('This is a test 111-222-3344'),
('Some Sample Text (111)-222-3344'),
('Hello there 111222 3344 / How are you?'),
('Hello there 111 222 3344 ? How are you?'),
('Hello there 111 222 3344. How are you?')
select
replace(LEFT(SUBSTRING(replace(replace(replace(replace(replace(c,'(',''),')',''),'-',''),' ',''),',',''), PATINDEX('%[0-9.-]%', replace(replace(replace(replace(replace(c,'(',''),')',''),'-',''),' ',''),',','')), 8000),
PATINDEX('%[^0-9.-]%', SUBSTRING(replace(replace(replace(replace(replace(c,'(',''),')',''),'-',''),' ',''),',',''), PATINDEX('%[0-9.-]%', replace(replace(replace(replace(replace(c,'(',''),')',''),'-',''),' ',''),',','')), 8000) + 'X') -1),'.','')
from #table
Create function fn_GetNumbersOnly(#pn varchar(100))
Returns varchar(max)
AS
BEGIN
Declare #r varchar(max) ='', #len int ,#c char(1), #x int = 0
Select #len = len(#pn)
while #x <= #len
begin
Select #c = SUBSTRING(#pn,#x,1)
if ISNUMERIC(#c) = 1 and #c <> '-'
Select #r = #r + #c
Select #x = #x +1
end
return #r
End
In your case It seems like the # will always be after teh # symbol so using CHARINDEX() with LTRIM() and RTRIM() would probably perform the best. But here is an interesting method of getting rid of ANY non digit. It utilizes a tally table and table of digits to limit which characters are accepted then XML technique to concatenate back to a single string without the non-numeric characters. The neat thing about this technique is it could be expanded to included ANY Allowed characters and strip out anything that is not allowed.
DECLARE #ExampleData AS TABLE (Col VARCHAR(100))
INSERT INTO #ExampleData (Col) VALUES ('AB ABCDE # 123'),('ABCDE# 123'),('AB: ABC# 123')
DECLARE #Digits AS TABLE (D CHAR(1))
INSERT INTO #Digits (D) VALUES ('0'),('1'),('2'),('3'),('4'),('5'),('6'),('7'),('8'),('9')
;WITH cteTally AS (
SELECT
I = ROW_NUMBER() OVER (ORDER BY (SELECT NULL))
FROM
#Digits d10
CROSS APPLY #Digits d100
--add more cross applies to cover longer fields this handles 100
)
SELECT *
FROM
#ExampleData e
OUTER APPLY (
SELECT CleansedPhone = CAST((
SELECT TOP 100
SUBSTRING(e.Col,t.I,1)
FROM
cteTally t
INNER JOIN #Digits d
ON SUBSTRING(e.Col,t.I,1) = d.D
WHERE
I <= LEN(e.Col)
ORDER BY
t.I
FOR XML PATH('')) AS VARCHAR(100))) o
Declare #MainTable table(id int identity(1,1),TextField varchar(100))
INSERT INTO #MainTable (TextField)
VALUES
('6B32E')
declare #i int=1
Declare #originalWord varchar(100)=''
WHile #i<=(Select count(*) from #MainTable)
BEGIN
Select #originalWord=TextField from #MainTable where id=#i
Declare #r varchar(max) ='', #len int ,#c char(1), #x int = 0
Select #len = len(#originalWord)
declare #pn varchar(100)=#originalWord
while #x <= #len
begin
Select #c = SUBSTRING(#pn,#x,1)
if(#c!='')
BEGIN
if ISNUMERIC(#c) = 0 and #c <> '-'
BEGIN
Select #r = cast(#r as varchar) + cast(replace((SELECT ASCII(#c)-64),'-','') as varchar)
end
ELSE
BEGIN
Select #r = #r + #c
END
END
Select #x = #x +1
END
Select #r
Set #i=#i+1
END
I have created a function for this
Create FUNCTION RemoveCharacters (#text varchar(30))
RETURNS VARCHAR(30)
AS
BEGIN
declare #index as int
declare #newtexval as varchar(30)
set #index = (select PATINDEX('%[A-Z.-/?]%', #text))
if (#index =0)
begin
return #text
end
else
begin
set #newtexval = (select STUFF ( #text , #index , 1 , '' ))
return dbo.RemoveCharacters(#newtexval)
end
return 0
END
GO
Here is the answer:
DECLARE #t TABLE (tVal VARCHAR(100))
INSERT INTO #t VALUES('123')
INSERT INTO #t VALUES('123S')
INSERT INTO #t VALUES('A123,123')
INSERT INTO #t VALUES('a123..A123')
;WITH cte (original, tVal, n)
AS
(
SELECT t.tVal AS original,
LOWER(t.tVal) AS tVal,
65 AS n
FROM #t AS t
UNION ALL
SELECT tVal AS original,
CAST(REPLACE(LOWER(tVal), LOWER(CHAR(n)), '') AS VARCHAR(100)),
n + 1
FROM cte
WHERE n <= 90
)
SELECT t1.tVal AS OldVal,
t.tval AS NewVal
FROM (
SELECT original,
tVal,
ROW_NUMBER() OVER(PARTITION BY tVal + original ORDER BY original) AS Sl
FROM cte
WHERE PATINDEX('%[a-z]%', tVal) = 0
) t
INNER JOIN #t t1
ON t.original = t1.tVal
WHERE t.sl = 1
You can create SQL CLR scalar function in order to be able to use regular expressions like replace patterns.
Here you can find example of how to create such function.
Having such function will solve the issue with just the following lines:
SELECT [dbo].[fn_Utils_RegexReplace] ('AB ABCDE # 123', '[^0-9]', '');
SELECT [dbo].[fn_Utils_RegexReplace] ('ABCDE# 123', '[^0-9]', '');
SELECT [dbo].[fn_Utils_RegexReplace] ('AB: ABC# 123', '[^0-9]', '');
More important, you will be able to solve more complex issues as the regular expressions will bring a whole new world of options directly in your T-SQL statements.
Use this:
REPLACE(TRANSLATE(SomeString, REPLACE(TRANSLATE(SomeString, '0123456789', '##########'), '#', ''), REPLICATE('#', LEN(REPLACE(TRANSLATE(SomeString, '0123456789', '##########'), '#', '') + 'x') - 1)), '#', '')
Demo:
DROP TABLE IF EXISTS #MyTempTable;
CREATE TABLE #MyTempTable (SomeString VARCHAR(255));
INSERT INTO #MyTempTable
VALUES ('ssss123ssg99d362sdg')
, ('hey 62q&*^(n43')
, (NULL)
, ('')
, ('hi')
, ('123');
SELECT SomeString
, REPLACE(TRANSLATE(SomeString, REPLACE(TRANSLATE(SomeString, '0123456789', '##########'), '#', ''), REPLICATE('#', LEN(REPLACE(TRANSLATE(SomeString, '0123456789', '##########'), '#', '') + 'x') - 1)), '#', '')
FROM #MyTempTable;
DROP TABLE IF EXISTS #MyTempTable;
Results:
SomeString
(No column name)
ssss123ssg99d362sdg
12399362
hey62q&*^(n43
6243
NULL
NULL
hi
123
123
While the OP wanted to "strip out anything that is not 0-9", the post is also tagged with "substring" and "patindex", and the OP mentioned the concern "not quite getting the syntax correct or something". To address that the requirements note that "all data fields do have the # prior to the number" and to provide an answer that addresses the challenges with substring/patindex, consider the following:
/* A sample select */
;WITH SampleValues AS
( SELECT 'AB ABCDE # 123' [Columnofdirtydata]
UNION ALL SELECT 'AB2: ABC# 123')
SELECT
s.Columnofdirtydata,
f1.pos1,
'['+ f2.substr +']' [InspectOutput]
FROM
SampleValues s
CROSS APPLY (SELECT PATINDEX('%# %',s.Columnofdirtydata) [pos1]) f1
CROSS APPLY (SELECT SUBSTRING(s.Columnofdirtydata, f1.pos1 + LEN('#-'),LEN(s.Columnofdirtydata)) [substr]) f2
/* Using update scenario from OP */
UPDATE t1
SET t1.Columntoupdate = CAST(f2.substr AS INT)
FROM
TableName t1
CROSS APPLY (SELECT PATINDEX('%# %',t1.Columnofdirtydata) [pos1]) f1
CROSS APPLY (SELECT SUBSTRING(t1.Columnofdirtydata, f1.pos1 + LEN('#-'),LEN(t1.Columnofdirtydata)) [substr]) f2
Note that my syntax advice for patindex/substring, is to:
consider using APPLY as a way to temporarily alias results from one function for use as parameters in the next. It's not uncommon to (in ETL, for example) need to parse out parameter/position-based substrings in an updatable column of a staging table. If you need to "debug" and potentially fix some parsing logic, this style will help.
consider using LEN('PatternSample') in your substring logic, to account for reusing this pattern or adjusting it when your source data changes (instead of "+ 1"
SUBSTRING() requires a length parameter, but it can be greater than the length of the string. Therefore, if you are getting "the rest of the string" after the pattern, you can just use "The source length"
DECLARE #STR VARCHAR(400)
DECLARE #specialchars VARCHAR(50) = '%[~,#,#,$,%,&,*,(,),!^?:]%'
SET #STR = '1, 45 4,3 68.00-'
WHILE PATINDEX( #specialchars, #STR ) > 0
---Remove special characters using Replace function
SET #STR = Replace(Replace(REPLACE( #STR, SUBSTRING( #STR, PATINDEX( #specialchars, #STR ), 1 ),''),'-',''), ' ','')
SELECT #STR
SELECT REGEXP_REPLACE( col, '[^[:digit:]]', '' ) AS new_col FROM my_table

How to use regular expression to remove number in MS SQL Server Management Studio?

I have a field in a table containing different IDs for different programmes like this:
ProgrammeID
-----------
Prog201604L
Prog201503L
Pro2015N
Pro2014N
Programme2010
Programme2011
Each programme ID has its meaning. The number in the mid of the string indicates the time or month. It is obvious that Prog201604L and Prog201503L indicate the same programme but in different years (so do the rest). What I want to do is to remove the numbers so after removal the programmeID will be like:
ProgrammeID
-----------
ProgL
ProgL
ProN
ProN
Programme
Programme
Then later I can aggregate this programmes together.
I am currently using SSMS 2012 not sure if there is a sql statement like RegEx. I have been searching for a long time but the solution online are mainly about Oracle and MySQL. What I found is PATINDEX() and it seems to support regular expression. Can anybody tell me how to create a pattern that suits my situation and what kind of statement I should use?
Thanks in advance
If the Number part is always 6 characters below can be used.
DECLARE #ProgrammeID VARCHAR(50) = 'Prog201604L'
SELECT STUFF(#ProgrammeID, PATINDEX( '%[0-9]%', #ProgrammeID), 6, '')
If the numbers are not fixed... to extend above
CREATE TABLE #Programme ( ProgrammeID VARCHAR(50) )
INSERT INTO #Programme
VALUES
('Prog201604L')
,('Pro2015N')
,('Programme2010')
,('Prog2016L')
,('Pro2N')
,('Prog')
,('2010')
SELECT ProgrammeID,
ISNULL(
STUFF(ProgrammeID,
PATINDEX( '%[0-9]%', ProgrammeID), -- get number start index
IIF(PATINDEX( '%[0-9][a-z]%',ProgrammeID)= 0, PATINDEX( '%[0-9]',ProgrammeID), PATINDEX( '%[0-9][a-z]%',ProgrammeID)) + 1 -- get the last number index
- PATINDEX( '%[0-9]%', ProgrammeID), -- get the number character length
'')
,ProgrammeID) -- Where there are no numbers in the string you will get Null, replace it with actual string
AS [Without Numbers]
FROM #Programme
this will handle cases with varying numbers and even string without number.
Hope this helps
You can create a function and pass the value of each row to function
as (just run this query)
Create Function [dbo].[RemoveNonAlphaCharacters](#Temp VarChar(1000))
Returns VarChar(1000)
AS
Begin
Declare #KeepValues as varchar(50)
Set #KeepValues = '%[^a-z]%'
While PatIndex(#KeepValues, #Temp) > 0
Set #Temp = Stuff(#Temp, PatIndex(#KeepValues, #Temp), 1, '')
Return #Temp
End
---Call it like this:
Declare #tbl table (ProgrammeID varchar(20))
insert into #tbl values ('ProgL'),('ProgL'),('ProN'),('ProN'),('Programme'),('Programme')
select * from #tbl
Select dbo.RemoveNonAlphaCharacters(ProgrammeID) from #tbl
How to strip all non-alphabetic characters from string in SQL Server?
Remove numbers from string sql server
One clever option is to take the substring of the ProgrammeID column from the left, until hitting the first number, and concatenate that with the reverse of the substring from the right until hitting the first number:
SELECT
SUBSTRING(ProgrammeID,
1,
PATINDEX('%[0-9]%', ProgrammeID) - 1) +
REVERSE(SUBSTRING(REVERSE(ProgrammeID),
1,
PATINDEX('%[0-9]%', REVERSE(ProgrammeID)) - 1))
FROM yourTable
I have created a user-defined function for SQL Server to remove non-numeric characters in a string expression
We can modify it to remove the opposite, numeric characters from the input string as follows
while patindex('%[0-9]%', #str) > 0
set #str = stuff(#str, patindex('%[0-9]%', #str), 1, '')
return #str
I hope it helps
Alan Burstein wrote an iTVF exactly for this. The function is called PatExclude8K. Here is the function definition (some comments removed):
CREATE FUNCTION dbo.PatExclude8K
(
#String VARCHAR(8000),
#Pattern VARCHAR(50)
)
/*******************************************************************************
Purpose:
Given a string (#String) and a pattern (#Pattern) of characters to remove,
remove the patterned characters from the string.
*******************************************************************************/
RETURNS TABLE WITH SCHEMABINDING AS
RETURN
WITH
E1(N) AS (SELECT N FROM (VALUES (NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL)) AS X(N)),
itally(N) AS
(
SELECT TOP(CONVERT(INT,LEN(#String),0)) ROW_NUMBER() OVER (ORDER BY (SELECT NULL))
FROM E1 T1 CROSS JOIN E1 T2 CROSS JOIN E1 T3 CROSS JOIN E1 T4
)
SELECT NewString =
((
SELECT SUBSTRING(#String,N,1)
FROM iTally
WHERE 0 = PATINDEX(#Pattern,SUBSTRING(#String COLLATE Latin1_General_BIN,N,1))
FOR XML PATH(''),TYPE
).value('.[1]','varchar(8000)'));
GO
And here is how you would use it:
SELECT *
FROM #Programme p
CROSS APPLY dbo.PatExclude8K(p.ProgrammeID, '[0-9]');
Using your sample data, here is the result:
ProgrammeID NewString
-------------------- -----------------
Prog201604L ProgL
Prog201503L ProgL
Pro2015N ProN
Pro2014N ProN
Programme2010 Programme
Programme2011 Programme
I created this solution building on a solution to extracting values from a comma separated list inside a string.
It seems to work find and even be a bit more effective than using while - I will be happy for feedback about that assumption, though.
On on table with 461.358 rows it takes 3 minutes and 27 seconds to do this (0.44 ms per row) (I put it into a function).
select count(*)
from Mytable
where dbo.StripNumeric(inputFromUser) is null
Here's the solutions
For stripping away numeric:
declare #input nvarchar(max) = null
select #input = '1a2 3b4' + char(13) + char(10) + '5(678)*90c'
DECLARE #output nvarchar(max) = '';
WITH cte AS
(
SELECT cast(1 as int) as [index]
UNION ALL
SELECT [index]+ 1 as [index]
from cte
where [index] < len(#input)
)
select #output = iif(PATINDEX('%[0-9]%', substring(#input, [index], 1))= 1, #output, #output + substring(#input, [index], 1))
from cte;
select iif(COALESCE( #output, '') = '', null, ltrim(rtrim(#output)))
For stripping away non-numeric:
declare #input nvarchar(max) = null
select #input = '1a2 3b4' + char(13) + char(10) + '5(678)*90c'
DECLARE #output nvarchar(max) = '';
WITH cte AS
(
SELECT cast(1 as int) as [index]
UNION ALL
SELECT [index]+ 1 as [index]
from cte
where [index] < len(#input) --len(substring(#input, index, 1)) >
)
select #output = iif(PATINDEX('%[0-9]%', substring(#input, [index], 1))= 1, #output + substring(#input, [index], 1), #output)
from cte;
select iif(COALESCE( #output, '') = '', null, ltrim(rtrim(#output)))

Resources