Missing Value Search in string seperated by comma - sql

Please help me if it is possible in sql.
Hello, may anyone please share their expertise, i am not very sure whether it is possible in SQL
SIZE OF TABLE: 5GB
I am trying to see invalid VALIDATION_ID present in a child table for a given PRODUCT_LINE
SO in below scenario 114 is not present for PRODUCT_LINE Passive in master table but present in child table.
DECLARE #CHILD TABLE
(
PRODUCT_LINE VARCHAR (50),
COMPONENT VARCHAR (50),
MODEL VARCHAR (50),
YEARS VARCHAR (50),
VALIDATION_ID VARCHAR (50)
)
INSERT #CHILD
SELECT 'PASSIVE','RESISTOR','CARBON','2005','V114' UNION ALL
SELECT 'PASSIVE','RESISTOR','CARBON','2005','V098, E009, V034' UNION ALL
SELECT 'PASSIVE','RESISTOR','CARBON','2005','V201' UNION ALL
SELECT 'PASSIVE','RESISTOR','CARBON','2005','V201,V098,V114' UNION ALL
SELECT 'PASSIVE','RESISTOR','CARBON','2005',null UNION ALL
SELECT 'PASSIVE','RESISTOR','CARBON','2005','null,V098,E009' UNION ALL
SELECT 'PASSIVE','RESISTOR','CARBON','2005','null,V114' UNION ALL
SELECT * FROM #CHILD
DECLARE #PARENT TABLE
(
PRODUCT_LINE VARCHAR (50),
VALIDATION_ID VARCHAR (50)
)
INSERT #PARENT
SELECT 'PASSIVE','V098' UNION ALL
SELECT 'PASSIVE','E009' UNION ALL
SELECT 'PASSIVE','V201' UNION ALL
SELECT 'PASSIVE','V034'
EXPECTED OUTPUT
PRODUCT_LINE COMPONENT MODEL YEARS VALIDATION_ID INVALID_VALIDATION_ID
PASSIVE RESISTOR CARBON 2005 V114 V114
PASSIVE RESISTOR CARBON 2005 V201,V098,V114 V114
'PASSIVE','RESISTOR','CARBON','2005','null,V114',V114
Thanks ....

you will definately required a CSV splitter. There are many, just search for it. Here I am using Jeff's DelimitedSplit8K()
SELECT c.*, INVALID_VALIDATION_ID = v.Item
FROM #CHILD c
CROSS APPLY dbo.DelimitedSplit8K(c.VALIDATION_ID, ',') v
WHERE NOT EXISTS
(
SELECT *
FROM #PARENT p
WHERE p.PRODUCT_LINE = c.PRODUCT_LINE
and p.VALIDATION_ID = LTRIM(v.Item)
)
if there are more than one invalid ID, it will appear as multiple line. If you want the multiple invalid ID to appear as CSV, you will need additional query to concatenate it. Let me know if you required that
EDIT : Updated query to show invalid ID in CSV
; WITH
CTE AS
(
SELECT c.*, INVALID_VALIDATION_ID = v.Item,
RN = DENSE_RANK() OVER (ORDER BY PRODUCT_LINE, COMPONENT, MODEL, YEARS, VALIDATION_ID)
FROM #CHILD c
CROSS APPLY dbo.DelimitedSplit8K(c.VALIDATION_ID, ',') v
WHERE c.VALIDATION_ID IS NOT NULL -- edit [2]
AND NOT EXISTS
(
SELECT *
FROM #PARENT p
WHERE p.PRODUCT_LINE = c.PRODUCT_LINE
and p.VALIDATION_ID = LTRIM(v.Item)
)
)
SELECT DISTINCT
PRODUCT_LINE, COMPONENT, MODEL, YEARS, VALIDATION_ID,
INVALID_VALIDATION_ID = STUFF(csv, 1, 1, '')
FROM CTE c
CROSS APPLY
(
SELECT ',' + x.INVALID_VALIDATION_ID
FROM CTE x
WHERE x.RN = c.RN
ORDER BY INVALID_VALIDATION_ID
FOR XML PATH('')
) i (csv)

You Need to Try This...
SELECT *
FROM
(
SELECT c.*, INVALID_VALIDATION_ID = x.Value
FROM #CHILD c
CROSS APPLY dbo.Split(c.VALIDATION_ID, ',') x
WHERE NOT EXISTS
(
SELECT *
FROM #PARENT p
WHERE p.PRODUCT_LINE = c.PRODUCT_LINE
and p.VALIDATION_ID = x.Value
)
) AS Q
WHERE INVALID_VALIDATION_ID IS NOT NULL AND INVALID_VALIDATION_ID != 'null'
Here dbo.split function is ..
CREATE FUNCTION [dbo].[Split]
(#List varchar(8000),#SplitOn varchar(5))
RETURNS #RtnValue table
(Id int identity(1,1),Value nvarchar(100))
AS
BEGIN
Set #List = Replace(#List,'''','')
While (Charindex(#SplitOn,#List)>0)
Begin
Insert Into #RtnValue (value)
Select
Value = ltrim(rtrim(Substring(#List,1,Charindex(#SplitOn,#List)-1)))
Set #List = Substring(#List,Charindex(#SplitOn,#List)+len(#SplitOn),len(#List))
End
Insert Into #RtnValue (Value)
Select Value = ltrim(rtrim(#List))
Return
END
try this......

Related

SELECT only numeric without function in sql

I need sql query WITHOUT FUNCTION with SELECT only numeric characters.
For example, I have in sql table 0f-gh 14-2t-4 /// and I want get this -> 01424. How I can do it with sql query SELECT, without anything, only with SELECT
This is the logic from digitsonlyEE which is the fastest T-SQL based "digits only" function available today.
declare #table table (somestring varchar(50));
insert #table VALUES('abc123xxx555!!!999'),('##123ttt999'),('555222!');
SELECT *
FROM #table t
CROSS APPLY
(
SELECT DigitsOnly =
(
SELECT SUBSTRING(t.somestring,n,1)
FROM
(
SELECT TOP (LEN(ISNULL(t.somestring,CHAR(32))))
(CHECKSUM(ROW_NUMBER() OVER (ORDER BY (SELECT NULL))))
FROM
(VALUES ($),($),($),($),($),($),($),($),($),($)) a(x),
(VALUES ($),($),($),($),($),($),($),($),($),($)) b(x),
(VALUES ($),($),($),($),($),($),($),($),($),($)) c(x),
(VALUES ($),($),($),($),($),($),($),($),($),($)) d(x)
) iTally(n)
WHERE ((ASCII(SUBSTRING(t.somestring,N,1)) - 48) & 0x7FFF) < 10
FOR XML PATH('')
)
) digitsOnlyEE(digitsOnly);
Results:
somestring digitsOnly
--------------------- ----------
abc123xxx555!!!999 123555999
##123ttt999 123999
555222! 555222
Here is an inline approach
Declare #YourTable table (ID int,SomeCol varchar(max))
Insert Into #YourTable values
(1,'0f-gh 14-2t-4 ///')
Select A.ID
,B.*
From #YourTable A
Cross Apply (
Select NewValue = (Select substring(A.SomeCol,N,1)
From (Select Top (len(A.SomeCol)) N=Row_Number() Over (Order By (Select NULL)) From master..spt_values n1) S
Where substring(A.SomeCol,N,1) like '[0-9]%'
Order By N
For XML Path (''))
) B
Returns
ID NewValue
1 01424
Note: Use Outer Apply if you want to see null values in the event where the string has NO numerics.

Split Comma seperated value other than split function

FOR EACH LINE THERE IS AN VALID Patient_id ASSOCIATED WITH IT in Parent table
i try to validate whether correct Patient_id linked with line.
problem:
In child table Patient_id is comma seperated.
if i am using function to split value, the query is not completing even after
15 hours.
can anyone suggest some other alternate, without using finction Please if possible
DECLARE #PARENT_TABLE TABLE
(
Line VARCHAR (50),
Patient_id VARCHAR (50)
)
INSERT #PARENT_TABLE
SELECT 'ABSRB', 'E001' UNION ALL
SELECT 'ABSRB', 'E067' UNION ALL
SELECT 'ABSRB', 'E068'
DECLARE #CHILD_TABLE TABLE
(
LINE VARCHAR (50),
SKU VARCHAR (50),
Patient_id VARCHAR (50)
)
INSERT #CHILD_TABLE
SELECT 'ABSRB', 'PRS317580', NULL UNION ALL
SELECT 'ABSRB', 'RANRS7371', 'E001' UNION ALL
SELECT 'ABSRB', 'KYBKG54327', 'E067' UNION ALL
SELECT 'ABSRB', 'KYB344615', 'V048, V055, E068' UNION ALL
SELECT 'ABSRB', 'ZZZZ15245', 'S128, V048, V055'
SELECT * FROM #CHILD_TABLE
can anyone suggest some other alternate, without using finction Please if possible
i have not included split function code here.
Code:
CREATE FUNCTION [dbo].[fnSplitString](
#string NVARCHAR(MAX),
#delimiter CHAR(1),
#keylist nvarchar(50))
RETURNS TABLE
AS
RETURN(
WITH CTE AS(
SELECT 1 as n
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
),CTE2 AS(
SELECT ROW_NUMBER() OVER(ORDER BY c.n) as n
FROM CTE c
CROSS JOIN CTE c2
CROSS JOIN CTE c3
CROSS JOIN CTE c4
CROSS JOIN CTE c5
CROSS JOIN CTE c6
)
SELECT TOP(LEN(COALESCE(#string,'')))
splitdata = ltrim(rtrim(
SUBSTRING(#string, n, CHARINDEX(#delimiter, #string + #delimiter, n)-n)
)),
keyname= #keylist
FROM CTE2
WHERE n<= LEN(#string)
AND SUBSTRING(#Delimiter + #string , n, LEN(#Delimiter)) = #Delimiter
)
DECLARE #SplittedTable TABLE
(
splitted VARCHAR (50),
keys VARCHAR (50)
)
INSERT INTO #SplittedTable(splitted,keys)
SELECT ss.splitdata, ss.keyname
FROM #CHILD_TABLE ct
CROSS APPLY dbo.fnSplitString(ct.Patient_id,',',ct.Patient_id) ss
SELECT * FROM #CHILD_TABLE ct WHERE ct.Patient_id IN (
SELECT DISTINCT st.keys
FROM #SplittedTable AS st
WHERE st.splitted NOT IN (SELECT Patient_id FROM #Parent_table m ));
SELECT DISTINCT ct.*
FROM #CHILD_TABLE ct
CROSS APPLY dbo.fnSplitString(ct.Patient_id,',',ct.Patient_id) ss
WHERE ss.splitdata NOT IN (SELECT Patient_id FROM #Parent_table)
The below code took more than 15 hours to execute. table size: 20GB
CODE:
--selecting by keys and finding them into master
SELECT * FROM #child ct WHERE ct.patientid IN (
SELECT DISTINCT st.keys
FROM #SplittedTable AS st
WHERE st.splitted NOT IN (SELECT patientid FROM #parent m ));
--Use CROSS APPLY to get this done for all rows.
SELECT DISTINCT ct.*
FROM #child ct
CROSS APPLY dbo.fnSplitString(ct.patientid,',',ct.patientid) ss
WHERE ss.splitdata NOT IN (SELECT patientid FROM #parent)

UPDATE set FROM select [duplicate]

How do I get:
id Name Value
1 A 4
1 B 8
2 C 9
to
id Column
1 A:4, B:8
2 C:9
No CURSOR, WHILE loop, or User-Defined Function needed.
Just need to be creative with FOR XML and PATH.
[Note: This solution only works on SQL 2005 and later. Original question didn't specify the version in use.]
CREATE TABLE #YourTable ([ID] INT, [Name] CHAR(1), [Value] INT)
INSERT INTO #YourTable ([ID],[Name],[Value]) VALUES (1,'A',4)
INSERT INTO #YourTable ([ID],[Name],[Value]) VALUES (1,'B',8)
INSERT INTO #YourTable ([ID],[Name],[Value]) VALUES (2,'C',9)
SELECT
[ID],
STUFF((
SELECT ', ' + [Name] + ':' + CAST([Value] AS VARCHAR(MAX))
FROM #YourTable
WHERE (ID = Results.ID)
FOR XML PATH(''),TYPE).value('(./text())[1]','VARCHAR(MAX)')
,1,2,'') AS NameValues
FROM #YourTable Results
GROUP BY ID
DROP TABLE #YourTable
If it is SQL Server 2017 or SQL Server Vnext, SQL Azure you can use STRING_AGG as below:
SELECT id, STRING_AGG(CONCAT(name, ':', [value]), ', ')
FROM #YourTable
GROUP BY id
using XML path will not perfectly concatenate as you might expect... it will replace "&" with "&" and will also mess with <" and ">
...maybe a few other things, not sure...but you can try this
I came across a workaround for this... you need to replace:
FOR XML PATH('')
)
with:
FOR XML PATH(''),TYPE
).value('(./text())[1]','VARCHAR(MAX)')
...or NVARCHAR(MAX) if thats what youre using.
why the hell doesn't SQL have a concatenate aggregate function? this is a PITA.
I ran into a couple of problems when I tried converting Kevin Fairchild's suggestion to work with strings containing spaces and special XML characters (&, <, >) which were encoded.
The final version of my code (which doesn't answer the original question but may be useful to someone) looks like this:
CREATE TABLE #YourTable ([ID] INT, [Name] VARCHAR(MAX), [Value] INT)
INSERT INTO #YourTable ([ID],[Name],[Value]) VALUES (1,'Oranges & Lemons',4)
INSERT INTO #YourTable ([ID],[Name],[Value]) VALUES (1,'1 < 2',8)
INSERT INTO #YourTable ([ID],[Name],[Value]) VALUES (2,'C',9)
SELECT [ID],
STUFF((
SELECT ', ' + CAST([Name] AS VARCHAR(MAX))
FROM #YourTable WHERE (ID = Results.ID)
FOR XML PATH(''),TYPE
/* Use .value to uncomment XML entities e.g. > < etc*/
).value('.','VARCHAR(MAX)')
,1,2,'') as NameValues
FROM #YourTable Results
GROUP BY ID
DROP TABLE #YourTable
Rather than using a space as a delimiter and replacing all the spaces with commas, it just pre-pends a comma and space to each value then uses STUFF to remove the first two characters.
The XML encoding is taken care of automatically by using the TYPE directive.
Another option using Sql Server 2005 and above
---- test data
declare #t table (OUTPUTID int, SCHME varchar(10), DESCR varchar(10))
insert #t select 1125439 ,'CKT','Approved'
insert #t select 1125439 ,'RENO','Approved'
insert #t select 1134691 ,'CKT','Approved'
insert #t select 1134691 ,'RENO','Approved'
insert #t select 1134691 ,'pn','Approved'
---- actual query
;with cte(outputid,combined,rn)
as
(
select outputid, SCHME + ' ('+DESCR+')', rn=ROW_NUMBER() over (PARTITION by outputid order by schme, descr)
from #t
)
,cte2(outputid,finalstatus,rn)
as
(
select OUTPUTID, convert(varchar(max),combined), 1 from cte where rn=1
union all
select cte2.outputid, convert(varchar(max),cte2.finalstatus+', '+cte.combined), cte2.rn+1
from cte2
inner join cte on cte.OUTPUTID = cte2.outputid and cte.rn=cte2.rn+1
)
select outputid, MAX(finalstatus) from cte2 group by outputid
Install the SQLCLR Aggregates from http://groupconcat.codeplex.com
Then you can write code like this to get the result you asked for:
CREATE TABLE foo
(
id INT,
name CHAR(1),
Value CHAR(1)
);
INSERT INTO dbo.foo
(id, name, Value)
VALUES (1, 'A', '4'),
(1, 'B', '8'),
(2, 'C', '9');
SELECT id,
dbo.GROUP_CONCAT(name + ':' + Value) AS [Column]
FROM dbo.foo
GROUP BY id;
Eight years later... Microsoft SQL Server vNext Database Engine has finally enhanced Transact-SQL to directly support grouped string concatenation. The Community Technical Preview version 1.0 added the STRING_AGG function and CTP 1.1 added the WITHIN GROUP clause for the STRING_AGG function.
Reference: https://msdn.microsoft.com/en-us/library/mt775028.aspx
SQL Server 2005 and later allow you to create your own custom aggregate functions, including for things like concatenation- see the sample at the bottom of the linked article.
This is just an addition to Kevin Fairchild's post (very clever by the way). I would have added it as a comment, but I don't have enough points yet :)
I was using this idea for a view I was working on, however the items I was concatinating contained spaces. So I modified the code slightly to not use spaces as delimiters.
Again thanks for the cool workaround Kevin!
CREATE TABLE #YourTable ( [ID] INT, [Name] CHAR(1), [Value] INT )
INSERT INTO #YourTable ([ID], [Name], [Value]) VALUES (1, 'A', 4)
INSERT INTO #YourTable ([ID], [Name], [Value]) VALUES (1, 'B', 8)
INSERT INTO #YourTable ([ID], [Name], [Value]) VALUES (2, 'C', 9)
SELECT [ID],
REPLACE(REPLACE(REPLACE(
(SELECT [Name] + ':' + CAST([Value] AS VARCHAR(MAX)) as A
FROM #YourTable
WHERE ( ID = Results.ID )
FOR XML PATH (''))
, '</A><A>', ', ')
,'<A>','')
,'</A>','') AS NameValues
FROM #YourTable Results
GROUP BY ID
DROP TABLE #YourTable
An example would be
In Oracle you can use LISTAGG aggregate function.
Original records
name type
------------
name1 type1
name2 type2
name2 type3
Sql
SELECT name, LISTAGG(type, '; ') WITHIN GROUP(ORDER BY name)
FROM table
GROUP BY name
Result in
name type
------------
name1 type1
name2 type2; type3
This kind of question is asked here very often, and the solution is going to depend a lot on the underlying requirements:
https://stackoverflow.com/search?q=sql+pivot
and
https://stackoverflow.com/search?q=sql+concatenate
Typically, there is no SQL-only way to do this without either dynamic sql, a user-defined function, or a cursor.
Just to add to what Cade said, this is usually a front-end display thing and should therefore be handled there. I know that sometimes it's easier to write something 100% in SQL for things like file export or other "SQL only" solutions, but most of the times this concatenation should be handled in your display layer.
Don't need a cursor... a while loop is sufficient.
------------------------------
-- Setup
------------------------------
DECLARE #Source TABLE
(
id int,
Name varchar(30),
Value int
)
DECLARE #Target TABLE
(
id int,
Result varchar(max)
)
INSERT INTO #Source(id, Name, Value) SELECT 1, 'A', 4
INSERT INTO #Source(id, Name, Value) SELECT 1, 'B', 8
INSERT INTO #Source(id, Name, Value) SELECT 2, 'C', 9
------------------------------
-- Technique
------------------------------
INSERT INTO #Target (id)
SELECT id
FROM #Source
GROUP BY id
DECLARE #id int, #Result varchar(max)
SET #id = (SELECT MIN(id) FROM #Target)
WHILE #id is not null
BEGIN
SET #Result = null
SELECT #Result =
CASE
WHEN #Result is null
THEN ''
ELSE #Result + ', '
END + s.Name + ':' + convert(varchar(30),s.Value)
FROM #Source s
WHERE id = #id
UPDATE #Target
SET Result = #Result
WHERE id = #id
SET #id = (SELECT MIN(id) FROM #Target WHERE #id < id)
END
SELECT *
FROM #Target
Let's get very simple:
SELECT stuff(
(
select ', ' + x from (SELECT 'xxx' x union select 'yyyy') tb
FOR XML PATH('')
)
, 1, 2, '')
Replace this line:
select ', ' + x from (SELECT 'xxx' x union select 'yyyy') tb
With your query.
You can improve performance significant the following way if group by contains mostly one item:
SELECT
[ID],
CASE WHEN MAX( [Name]) = MIN( [Name]) THEN
MAX( [Name]) NameValues
ELSE
STUFF((
SELECT ', ' + [Name] + ':' + CAST([Value] AS VARCHAR(MAX))
FROM #YourTable
WHERE (ID = Results.ID)
FOR XML PATH(''),TYPE).value('(./text())[1]','VARCHAR(MAX)')
,1,2,'') AS NameValues
END
FROM #YourTable Results
GROUP BY ID
didn't see any cross apply answers, also no need for xml extraction. Here is a slightly different version of what Kevin Fairchild wrote. It's faster and easier to use in more complex queries:
select T.ID
,MAX(X.cl) NameValues
from #YourTable T
CROSS APPLY
(select STUFF((
SELECT ', ' + [Name] + ':' + CAST([Value] AS VARCHAR(MAX))
FROM #YourTable
WHERE (ID = T.ID)
FOR XML PATH(''))
,1,2,'') [cl]) X
GROUP BY T.ID
Using the Stuff and for xml path operator to concatenate rows to string :Group By two columns -->
CREATE TABLE #YourTable ([ID] INT, [Name] CHAR(1), [Value] INT)
INSERT INTO #YourTable ([ID],[Name],[Value]) VALUES (1,'A',4)
INSERT INTO #YourTable ([ID],[Name],[Value]) VALUES (1,'B',8)
INSERT INTO #YourTable ([ID],[Name],[Value]) VALUES (1,'B',5)
INSERT INTO #YourTable ([ID],[Name],[Value]) VALUES (2,'C',9)
-- retrieve each unique id and name columns and concatonate the values into one column
SELECT
[ID],
STUFF((
SELECT ', ' + [Name] + ':' + CAST([Value] AS VARCHAR(MAX)) -- CONCATONATES EACH APPLICATION : VALUE SET
FROM #YourTable
WHERE (ID = Results.ID and Name = results.[name] )
FOR XML PATH(''),TYPE).value('(./text())[1]','VARCHAR(MAX)')
,1,2,'') AS NameValues
FROM #YourTable Results
GROUP BY ID
SELECT
[ID],[Name] , --these are acting as the group by clause
STUFF((
SELECT ', '+ CAST([Value] AS VARCHAR(MAX)) -- CONCATONATES THE VALUES FOR EACH ID NAME COMBINATION
FROM #YourTable
WHERE (ID = Results.ID and Name = results.[name] )
FOR XML PATH(''),TYPE).value('(./text())[1]','VARCHAR(MAX)')
,1,2,'') AS NameValues
FROM #YourTable Results
GROUP BY ID, name
DROP TABLE #YourTable
Using Replace Function and FOR JSON PATH
SELECT T3.DEPT, REPLACE(REPLACE(T3.ENAME,'{"ENAME":"',''),'"}','') AS ENAME_LIST
FROM (
SELECT DEPT, (SELECT ENAME AS [ENAME]
FROM EMPLOYEE T2
WHERE T2.DEPT=T1.DEPT
FOR JSON PATH,WITHOUT_ARRAY_WRAPPER) ENAME
FROM EMPLOYEE T1
GROUP BY DEPT) T3
For sample data and more ways click here
If you have clr enabled you could use the Group_Concat library from GitHub
Another example without the garbage: ",TYPE).value('(./text())[1]','VARCHAR(MAX)')"
WITH t AS (
SELECT 1 n, 1 g, 1 v
UNION ALL
SELECT 2 n, 1 g, 2 v
UNION ALL
SELECT 3 n, 2 g, 3 v
)
SELECT g
, STUFF (
(
SELECT ', ' + CAST(v AS VARCHAR(MAX))
FROM t sub_t
WHERE sub_t.g = main_t.g
FOR XML PATH('')
)
, 1, 2, ''
) cg
FROM t main_t
GROUP BY g
Input-output is
************************* -> *********************
* n * g * v * * g * cg *
* - * - * - * * - * - *
* 1 * 1 * 1 * * 1 * 1, 2 *
* 2 * 1 * 2 * * 2 * 3 *
* 3 * 2 * 3 * *********************
*************************
I used this approach which may be easier to grasp. Get a root element, then concat to choices any item with the same ID but not the 'official' name
Declare #IdxList as Table(id int, choices varchar(max),AisName varchar(255))
Insert into #IdxLIst(id,choices,AisName)
Select IdxId,''''+Max(Title)+'''',Max(Title) From [dbo].[dta_Alias]
where IdxId is not null group by IdxId
Update #IdxLIst
set choices=choices +','''+Title+''''
From #IdxLIst JOIN [dta_Alias] ON id=IdxId And Title <> AisName
where IdxId is not null
Select * from #IdxList where choices like '%,%'
For all my healthcare folks out there:
SELECT
s.NOTE_ID
,STUFF ((
SELECT
[note_text] + ' '
FROM
HNO_NOTE_TEXT s1
WHERE
(s1.NOTE_ID = s.NOTE_ID)
ORDER BY [line] ASC
FOR XML PATH(''),TYPE).value('(./text())[1]','VARCHAR(MAX)')
,
1,
2,
'') AS NOTE_TEXT_CONCATINATED
FROM
HNO_NOTE_TEXT s
GROUP BY NOTE_ID

Parsing text to multiple columns

I have a feed that is populating a single text field in a table with statistics.
I need to pull this data into multiple fields in another table
but the strange format makes importing automatically difficult.
The file format is flat text but an example is below:
08:34:52 Checksum=180957248,TicketType=6,InitialUserType=G,InitialUserID=520,CommunicationType=Incoming,Date=26-03-2012,Time=08:35:00,Service=ST,Duration=00:00:14,Cost=0.12
Effectively it's made up of:
[timestamp] [Field1 name]=[Field1 value],[Field2 name]=[Field2 value],[Field4 name]=[Field4 value]...[CR]
All fields are always in the same order but not always present.
Total columns could be anywhere from 5 to 30.
I've tried the below function to translate it which seems to work mostly but seems to randomly skip fields:
Parsing the data:
(SELECT [Data].[dbo].[GetFromTextString] ( 'Checksum=' ,',' ,RAWTEXT)) AS RowCheckSum,
(SELECT [Data].[dbo].[GetFromTextString] ( 'TicketType=' ,',' ,RAWTEXT)) AS TicketType,
And the Function:
CREATE FUNCTION [dbo].[GetFromTextString]
-- Input start and end and return value.
(#uniqueprefix VARCHAR(100),
#commonsuffix VARCHAR(100),
#datastring VARCHAR(MAX) )
RETURNS VARCHAR(MAX) -- Picked Value.
AS
BEGIN
DECLARE #ADJLEN INT = LEN(#uniqueprefix)
SET #datastring = #datastring + #commonsuffix
RETURN (
CASE WHEN (CHARINDEX(#uniqueprefix,#datastring) > 0)
AND (CHARINDEX(#uniqueprefix + #commonsuffix,#datastring) = 0)
THEN SUBSTRING(#datastring, PATINDEX('%' + #uniqueprefix + '%',#datastring)+#ADJLEN, CHARINDEX(#commonsuffix,#datastring,PATINDEX('%' + #uniqueprefix + '%',#datastring))- PATINDEX('%' + #uniqueprefix + '%',#datastring)-#ADJLEN) ELSE NULL END
)
END
Could anyone suggest a better/cleaner way to strip out the data or could someone work out why this formula skips rows?
Any help really appreciated.
NOTE - THE FIRST SOLUTION IS RUBBISH. I HAVE LEFT IN IT FOR HISTORICAL REASONS, BUT A BETTER SOLUTION IS CONTAINED BELOW
I am not even sure if this will be faster than your current method, but it is the way I would approach the issue (If i was forced into an SQL only solution). The first thing that is required is a table valued function that will perform a split function:
CREATE FUNCTION dbo.Split (#TextToSplit VARCHAR(MAX), #Delimiter VARCHAR(MAX))
RETURNS #Values TABLE (Position INT IDENTITY(1, 1) NOT NULL, TextValues VARCHAR(MAX) NOT NULL)
AS
BEGIN
WHILE CHARINDEX(#Delimiter, #TextToSplit) > 0
BEGIN
INSERT #Values
SELECT LEFT(#TextToSplit, CHARINDEX(#Delimiter, #TextToSplit) - 1)
SET #TextToSplit = SUBSTRING(#TextToSplit, CHARINDEX(#Delimiter, #TextToSplit) + 1, LEN(#TextToSplit))
END
INSERT #Values VALUES (#TextToSplit)
RETURN
END
For my example I am working from a temp table #Worklist, you may need to adapt yours accordingly, or you could just insert the relevant data into #Worklist where I have used dummy data:
DECLARE #WorkList TABLE (ID INT IDENTITY(1, 1) NOT NULL, TextField VARCHAR(MAX))
INSERT #WorkList
SELECT '08:34:52 Checksum=180957248,TicketType=6,InitialUserType=G,InitialUserID=520,CommunicationType=Incoming,Date=26-03-2012,Time=08:35:00,Service=ST,Duration=00:00:14,Cost=0.12'
UNION
SELECT '08:34:52 Checksum=180957249,TicketType=5,InitialUserType=H,InitialUserID=521,CommunicationType=Outgoing,Date=27-03-2012,Time=14:27:00,Service=ST,Duration=00:15:12,Cost=0.37'
The main bit of the query is done here. It is quite long, so I have tried to comment it as well as possible. If further clarification is required I can add more comments.
DECLARE #Output TABLE (ID INT IDENTITY(1, 1) NOT NULL, TextField VARCHAR(MAX))
DECLARE #KeyPairs TABLE (WorkListID INT NOT NULL, KeyField VARCHAR(MAX), ValueField VARCHAR(MAX))
-- STORE TIMESTAMP DATA - THIS ASSUMES THE FIRST SPACE IS THE END OF THE TIMESTAMP
INSERT #KeyPairs
SELECT ID, 'TimeStamp', LEFT(TextField, CHARINDEX(' ', TextField))
FROM #WorkList
-- CLEAR THE TIMESTAMP FROM THE WORKLIST
UPDATE #WorkList
SET TextField = SUBSTRING(TextField, CHARINDEX(' ', TextField) + 1, LEN(TextField))
DECLARE #ID INT = (SELECT MIN(ID) FROM #WorkList)
WHILE #ID IS NOT NULL
BEGIN
-- SPLIT THE STRING FIRST INTO ALL THE PAIRS (e.g. Checksum=180957248)
INSERT #Output
SELECT TextValues
FROM dbo.Split((SELECT TextField FROM #WorkList WHERE ID = #ID), ',')
DECLARE #ID2 INT = (SELECT MIN(ID) FROM #Output)
-- FOR ALL THE PAIRS SPLIT THEM INTO A KEY AND A VALUE (USING THE POSITION OF THE SPLIT FUNCTION)
WHILE #ID2 IS NOT NULL
BEGIN
INSERT #KeyPairs
SELECT #ID,
MAX(CASE WHEN Position = 1 THEN TextValues ELSE '' END),
MAX(CASE WHEN Position = 2 THEN TextValues ELSE '' END)
FROM dbo.Split((SELECT TextField FROM #Output WHERE ID = #ID2), '=')
DELETE #Output
WHERE ID = #ID2
SET #ID2 = (SELECT MIN(ID) FROM #Output)
END
DELETE #WorkList
WHERE ID = #ID
SET #ID = (SELECT MIN(ID) FROM #WorkList)
END
-- WE NOW HAVE A TABLE CONTAINING EAV MODEL STYLE DATA. THIS NEEDS TO BE PIVOTED INTO THE CORRECT FORMAT
-- ENSURE COLUMNS ARE LISTED IN THE ORDER YOU WANT THEM TO APPEAR
SELECT *
FROM #KeyPairs p
PIVOT
( MAX(ValueField)
FOR KeyField IN
( [TimeStamp], [Checksum], [TicketType], [InitialUserType],
[InitialUserID], [CommunicationType], [Date], [Time],
[Service], [Duration], [Cost]
)
) AS PivotTable;
EDIT (4 YEARS LATER)
A recent upvote brought this to my attention and the I hate myself a little bit for ever posting this answer in its current form.
A much better split function would be:
CREATE FUNCTION dbo.Split
(
#List NVARCHAR(MAX),
#Delimiter NVARCHAR(255)
)
RETURNS TABLE
WITH SCHEMABINDING AS
RETURN
( WITH N1 AS (SELECT N FROM (VALUES (1),(1),(1),(1),(1),(1),(1),(1),(1), (1)) n (N)),
N2(N) AS (SELECT 1 FROM N1 a CROSS JOIN N1 b),
N3(N) AS (SELECT 1 FROM N2 a CROSS JOIN N2 b),
N4(N) AS (SELECT 1 FROM N3 a CROSS JOIN N3 b),
cteTally(N) AS
( SELECT 0 UNION ALL
SELECT TOP (DATALENGTH(ISNULL(#List,1))) ROW_NUMBER() OVER (ORDER BY (SELECT NULL))
FROM n4
),
cteStart(N1) AS
( SELECT t.N+1
FROM cteTally t
WHERE (SUBSTRING(#List,t.N,1) = #Delimiter OR t.N = 0)
)
SELECT Item = SUBSTRING(#List, s.N1, ISNULL(NULLIF(CHARINDEX(#Delimiter,#List,s.N1),0)-s.N1,8000)),
Position = s.N1,
ItemNumber = ROW_NUMBER() OVER(ORDER BY s.N1)
FROM cteStart s
);
Then there is no need for looping at all, you just have a proper set based solution by calling the split function twice to get your EAV style data set:
DECLARE #WorkList TABLE (ID INT IDENTITY(1, 1) NOT NULL, TextField VARCHAR(MAX))
INSERT #WorkList
SELECT '08:34:52 Checksum=180957248,TicketType=6,InitialUserType=G,InitialUserID=520,CommunicationType=Incoming,Date=26-03-2012,Time=08:35:00,Service=ST,Duration=00:00:14,Cost=0.12'
UNION
SELECT '08:34:52 Checksum=180957249,TicketType=5,InitialUserType=H,InitialUserID=521,CommunicationType=Outgoing,Date=27-03-2012,Time=14:27:00,Service=ST,Duration=00:15:12,Cost=0.37';
WITH KeyPairs AS
( SELECT w.ID,
[Timestamp] = LEFT(w.TextField, CHARINDEX(' ', w.TextField)),
KeyField = MAX(CASE WHEN v.ItemNumber = 1 THEN v.Item END),
ValueField = MAX(CASE WHEN v.ItemNumber = 2 THEN v.Item END)
FROM #WorkList AS w
CROSS APPLY dbo.Split(SUBSTRING(TextField, CHARINDEX(' ', TextField) + 1, LEN(TextField)), ',') AS kp
CROSS APPLY dbo.Split(kp.Item, '=') AS v
GROUP BY w.ID, kp.ItemNumber,w.TextField
)
SELECT *
FROM KeyPairs AS kp
PIVOT
( MAX(ValueField)
FOR KeyField IN
( [Checksum], [TicketType], [InitialUserType],
[InitialUserID], [CommunicationType], [Date], [Time],
[Service], [Duration], [Cost]
)
) AS pvt;

How to use GROUP BY to concatenate strings in SQL Server?

How do I get:
id Name Value
1 A 4
1 B 8
2 C 9
to
id Column
1 A:4, B:8
2 C:9
No CURSOR, WHILE loop, or User-Defined Function needed.
Just need to be creative with FOR XML and PATH.
[Note: This solution only works on SQL 2005 and later. Original question didn't specify the version in use.]
CREATE TABLE #YourTable ([ID] INT, [Name] CHAR(1), [Value] INT)
INSERT INTO #YourTable ([ID],[Name],[Value]) VALUES (1,'A',4)
INSERT INTO #YourTable ([ID],[Name],[Value]) VALUES (1,'B',8)
INSERT INTO #YourTable ([ID],[Name],[Value]) VALUES (2,'C',9)
SELECT
[ID],
STUFF((
SELECT ', ' + [Name] + ':' + CAST([Value] AS VARCHAR(MAX))
FROM #YourTable
WHERE (ID = Results.ID)
FOR XML PATH(''),TYPE).value('(./text())[1]','VARCHAR(MAX)')
,1,2,'') AS NameValues
FROM #YourTable Results
GROUP BY ID
DROP TABLE #YourTable
If it is SQL Server 2017 or SQL Server Vnext, SQL Azure you can use STRING_AGG as below:
SELECT id, STRING_AGG(CONCAT(name, ':', [value]), ', ')
FROM #YourTable
GROUP BY id
using XML path will not perfectly concatenate as you might expect... it will replace "&" with "&" and will also mess with <" and ">
...maybe a few other things, not sure...but you can try this
I came across a workaround for this... you need to replace:
FOR XML PATH('')
)
with:
FOR XML PATH(''),TYPE
).value('(./text())[1]','VARCHAR(MAX)')
...or NVARCHAR(MAX) if thats what youre using.
why the hell doesn't SQL have a concatenate aggregate function? this is a PITA.
I ran into a couple of problems when I tried converting Kevin Fairchild's suggestion to work with strings containing spaces and special XML characters (&, <, >) which were encoded.
The final version of my code (which doesn't answer the original question but may be useful to someone) looks like this:
CREATE TABLE #YourTable ([ID] INT, [Name] VARCHAR(MAX), [Value] INT)
INSERT INTO #YourTable ([ID],[Name],[Value]) VALUES (1,'Oranges & Lemons',4)
INSERT INTO #YourTable ([ID],[Name],[Value]) VALUES (1,'1 < 2',8)
INSERT INTO #YourTable ([ID],[Name],[Value]) VALUES (2,'C',9)
SELECT [ID],
STUFF((
SELECT ', ' + CAST([Name] AS VARCHAR(MAX))
FROM #YourTable WHERE (ID = Results.ID)
FOR XML PATH(''),TYPE
/* Use .value to uncomment XML entities e.g. > < etc*/
).value('.','VARCHAR(MAX)')
,1,2,'') as NameValues
FROM #YourTable Results
GROUP BY ID
DROP TABLE #YourTable
Rather than using a space as a delimiter and replacing all the spaces with commas, it just pre-pends a comma and space to each value then uses STUFF to remove the first two characters.
The XML encoding is taken care of automatically by using the TYPE directive.
Another option using Sql Server 2005 and above
---- test data
declare #t table (OUTPUTID int, SCHME varchar(10), DESCR varchar(10))
insert #t select 1125439 ,'CKT','Approved'
insert #t select 1125439 ,'RENO','Approved'
insert #t select 1134691 ,'CKT','Approved'
insert #t select 1134691 ,'RENO','Approved'
insert #t select 1134691 ,'pn','Approved'
---- actual query
;with cte(outputid,combined,rn)
as
(
select outputid, SCHME + ' ('+DESCR+')', rn=ROW_NUMBER() over (PARTITION by outputid order by schme, descr)
from #t
)
,cte2(outputid,finalstatus,rn)
as
(
select OUTPUTID, convert(varchar(max),combined), 1 from cte where rn=1
union all
select cte2.outputid, convert(varchar(max),cte2.finalstatus+', '+cte.combined), cte2.rn+1
from cte2
inner join cte on cte.OUTPUTID = cte2.outputid and cte.rn=cte2.rn+1
)
select outputid, MAX(finalstatus) from cte2 group by outputid
Install the SQLCLR Aggregates from http://groupconcat.codeplex.com
Then you can write code like this to get the result you asked for:
CREATE TABLE foo
(
id INT,
name CHAR(1),
Value CHAR(1)
);
INSERT INTO dbo.foo
(id, name, Value)
VALUES (1, 'A', '4'),
(1, 'B', '8'),
(2, 'C', '9');
SELECT id,
dbo.GROUP_CONCAT(name + ':' + Value) AS [Column]
FROM dbo.foo
GROUP BY id;
Eight years later... Microsoft SQL Server vNext Database Engine has finally enhanced Transact-SQL to directly support grouped string concatenation. The Community Technical Preview version 1.0 added the STRING_AGG function and CTP 1.1 added the WITHIN GROUP clause for the STRING_AGG function.
Reference: https://msdn.microsoft.com/en-us/library/mt775028.aspx
SQL Server 2005 and later allow you to create your own custom aggregate functions, including for things like concatenation- see the sample at the bottom of the linked article.
This is just an addition to Kevin Fairchild's post (very clever by the way). I would have added it as a comment, but I don't have enough points yet :)
I was using this idea for a view I was working on, however the items I was concatinating contained spaces. So I modified the code slightly to not use spaces as delimiters.
Again thanks for the cool workaround Kevin!
CREATE TABLE #YourTable ( [ID] INT, [Name] CHAR(1), [Value] INT )
INSERT INTO #YourTable ([ID], [Name], [Value]) VALUES (1, 'A', 4)
INSERT INTO #YourTable ([ID], [Name], [Value]) VALUES (1, 'B', 8)
INSERT INTO #YourTable ([ID], [Name], [Value]) VALUES (2, 'C', 9)
SELECT [ID],
REPLACE(REPLACE(REPLACE(
(SELECT [Name] + ':' + CAST([Value] AS VARCHAR(MAX)) as A
FROM #YourTable
WHERE ( ID = Results.ID )
FOR XML PATH (''))
, '</A><A>', ', ')
,'<A>','')
,'</A>','') AS NameValues
FROM #YourTable Results
GROUP BY ID
DROP TABLE #YourTable
An example would be
In Oracle you can use LISTAGG aggregate function.
Original records
name type
------------
name1 type1
name2 type2
name2 type3
Sql
SELECT name, LISTAGG(type, '; ') WITHIN GROUP(ORDER BY name)
FROM table
GROUP BY name
Result in
name type
------------
name1 type1
name2 type2; type3
This kind of question is asked here very often, and the solution is going to depend a lot on the underlying requirements:
https://stackoverflow.com/search?q=sql+pivot
and
https://stackoverflow.com/search?q=sql+concatenate
Typically, there is no SQL-only way to do this without either dynamic sql, a user-defined function, or a cursor.
Just to add to what Cade said, this is usually a front-end display thing and should therefore be handled there. I know that sometimes it's easier to write something 100% in SQL for things like file export or other "SQL only" solutions, but most of the times this concatenation should be handled in your display layer.
Don't need a cursor... a while loop is sufficient.
------------------------------
-- Setup
------------------------------
DECLARE #Source TABLE
(
id int,
Name varchar(30),
Value int
)
DECLARE #Target TABLE
(
id int,
Result varchar(max)
)
INSERT INTO #Source(id, Name, Value) SELECT 1, 'A', 4
INSERT INTO #Source(id, Name, Value) SELECT 1, 'B', 8
INSERT INTO #Source(id, Name, Value) SELECT 2, 'C', 9
------------------------------
-- Technique
------------------------------
INSERT INTO #Target (id)
SELECT id
FROM #Source
GROUP BY id
DECLARE #id int, #Result varchar(max)
SET #id = (SELECT MIN(id) FROM #Target)
WHILE #id is not null
BEGIN
SET #Result = null
SELECT #Result =
CASE
WHEN #Result is null
THEN ''
ELSE #Result + ', '
END + s.Name + ':' + convert(varchar(30),s.Value)
FROM #Source s
WHERE id = #id
UPDATE #Target
SET Result = #Result
WHERE id = #id
SET #id = (SELECT MIN(id) FROM #Target WHERE #id < id)
END
SELECT *
FROM #Target
Let's get very simple:
SELECT stuff(
(
select ', ' + x from (SELECT 'xxx' x union select 'yyyy') tb
FOR XML PATH('')
)
, 1, 2, '')
Replace this line:
select ', ' + x from (SELECT 'xxx' x union select 'yyyy') tb
With your query.
You can improve performance significant the following way if group by contains mostly one item:
SELECT
[ID],
CASE WHEN MAX( [Name]) = MIN( [Name]) THEN
MAX( [Name]) NameValues
ELSE
STUFF((
SELECT ', ' + [Name] + ':' + CAST([Value] AS VARCHAR(MAX))
FROM #YourTable
WHERE (ID = Results.ID)
FOR XML PATH(''),TYPE).value('(./text())[1]','VARCHAR(MAX)')
,1,2,'') AS NameValues
END
FROM #YourTable Results
GROUP BY ID
didn't see any cross apply answers, also no need for xml extraction. Here is a slightly different version of what Kevin Fairchild wrote. It's faster and easier to use in more complex queries:
select T.ID
,MAX(X.cl) NameValues
from #YourTable T
CROSS APPLY
(select STUFF((
SELECT ', ' + [Name] + ':' + CAST([Value] AS VARCHAR(MAX))
FROM #YourTable
WHERE (ID = T.ID)
FOR XML PATH(''))
,1,2,'') [cl]) X
GROUP BY T.ID
Using the Stuff and for xml path operator to concatenate rows to string :Group By two columns -->
CREATE TABLE #YourTable ([ID] INT, [Name] CHAR(1), [Value] INT)
INSERT INTO #YourTable ([ID],[Name],[Value]) VALUES (1,'A',4)
INSERT INTO #YourTable ([ID],[Name],[Value]) VALUES (1,'B',8)
INSERT INTO #YourTable ([ID],[Name],[Value]) VALUES (1,'B',5)
INSERT INTO #YourTable ([ID],[Name],[Value]) VALUES (2,'C',9)
-- retrieve each unique id and name columns and concatonate the values into one column
SELECT
[ID],
STUFF((
SELECT ', ' + [Name] + ':' + CAST([Value] AS VARCHAR(MAX)) -- CONCATONATES EACH APPLICATION : VALUE SET
FROM #YourTable
WHERE (ID = Results.ID and Name = results.[name] )
FOR XML PATH(''),TYPE).value('(./text())[1]','VARCHAR(MAX)')
,1,2,'') AS NameValues
FROM #YourTable Results
GROUP BY ID
SELECT
[ID],[Name] , --these are acting as the group by clause
STUFF((
SELECT ', '+ CAST([Value] AS VARCHAR(MAX)) -- CONCATONATES THE VALUES FOR EACH ID NAME COMBINATION
FROM #YourTable
WHERE (ID = Results.ID and Name = results.[name] )
FOR XML PATH(''),TYPE).value('(./text())[1]','VARCHAR(MAX)')
,1,2,'') AS NameValues
FROM #YourTable Results
GROUP BY ID, name
DROP TABLE #YourTable
Using Replace Function and FOR JSON PATH
SELECT T3.DEPT, REPLACE(REPLACE(T3.ENAME,'{"ENAME":"',''),'"}','') AS ENAME_LIST
FROM (
SELECT DEPT, (SELECT ENAME AS [ENAME]
FROM EMPLOYEE T2
WHERE T2.DEPT=T1.DEPT
FOR JSON PATH,WITHOUT_ARRAY_WRAPPER) ENAME
FROM EMPLOYEE T1
GROUP BY DEPT) T3
For sample data and more ways click here
If you have clr enabled you could use the Group_Concat library from GitHub
Another example without the garbage: ",TYPE).value('(./text())[1]','VARCHAR(MAX)')"
WITH t AS (
SELECT 1 n, 1 g, 1 v
UNION ALL
SELECT 2 n, 1 g, 2 v
UNION ALL
SELECT 3 n, 2 g, 3 v
)
SELECT g
, STUFF (
(
SELECT ', ' + CAST(v AS VARCHAR(MAX))
FROM t sub_t
WHERE sub_t.g = main_t.g
FOR XML PATH('')
)
, 1, 2, ''
) cg
FROM t main_t
GROUP BY g
Input-output is
************************* -> *********************
* n * g * v * * g * cg *
* - * - * - * * - * - *
* 1 * 1 * 1 * * 1 * 1, 2 *
* 2 * 1 * 2 * * 2 * 3 *
* 3 * 2 * 3 * *********************
*************************
I used this approach which may be easier to grasp. Get a root element, then concat to choices any item with the same ID but not the 'official' name
Declare #IdxList as Table(id int, choices varchar(max),AisName varchar(255))
Insert into #IdxLIst(id,choices,AisName)
Select IdxId,''''+Max(Title)+'''',Max(Title) From [dbo].[dta_Alias]
where IdxId is not null group by IdxId
Update #IdxLIst
set choices=choices +','''+Title+''''
From #IdxLIst JOIN [dta_Alias] ON id=IdxId And Title <> AisName
where IdxId is not null
Select * from #IdxList where choices like '%,%'
For all my healthcare folks out there:
SELECT
s.NOTE_ID
,STUFF ((
SELECT
[note_text] + ' '
FROM
HNO_NOTE_TEXT s1
WHERE
(s1.NOTE_ID = s.NOTE_ID)
ORDER BY [line] ASC
FOR XML PATH(''),TYPE).value('(./text())[1]','VARCHAR(MAX)')
,
1,
2,
'') AS NOTE_TEXT_CONCATINATED
FROM
HNO_NOTE_TEXT s
GROUP BY NOTE_ID