I've a problem of duplicates in tsql. How can I remove?
This is my output:
id name ref
----------- ---------- --------------
1 John null
1 John RE
2 Smith null
2 Smith DOS
3 Van null
4 Sam CR
5 Bob null
Code:
SELECT DISTINCT
u.id,
u.name,
c.ref
FROM users u
LEFT JOIN con c on c.id=u.id
I would like the output to be like this:
id name ref
----------- ---------- --------------
1 John RE
2 Smith DOS
3 Van null
4 Sam CR
5 Bob null
This is just an example, I've few of them.
thanks
What about using MAX and GROUP BY:
SELECT
u.id,
u.name,
MAX(c.ref) as Ref
FROM users u
LEFT JOIN con c on c.id=u.id
GROUP BY
u.id,
u.name
Try below query, this will give you the exact required output:
DECLARE #SAMPLEDATA TABLE(id INT, name VARCHAR(100), ref VARCHAR(100))
INSERT INTO #SAMPLEDATA VALUES
(1, 'John', null),
(1, 'John', 'RE'),
(2, 'Smith', null),
(2, 'Smith', 'DOS'),
(3, 'Van', null),
(4, 'Sam', 'CR'),
(5, 'Bob', null)
;WITH SAMPLEDATA
AS
(
SELECT ROW_NUMBER()OVER (ORDER BY (SELECT 100))SNO,* FROM #SAMPLEDATA
)
SELECT ID,NAME,REF FROM(
SELECT * ,ISNULL((SELECT CASE WHEN T2.ID=T1.id AND T1.ref IS NULL THEN 'R' ELSE 'NR' END
FROM SAMPLEDATA T2 WHERE T2.SNO=T1.SNO+1),'NR')COL FROM SAMPLEDATA T1) DATA WHERE COL='NR'
OUTPUT
------------------
ID NAME REF
------------------
1 John RE
2 Smith DOS
3 Van NULL
4 Sam CR
5 Bob NULL
------------------
Please make use of below query:
DECLARE #TABLE TABLE
(id INT, name VARCHAR(10),ref VARCHAR(10))
INSERT INTO #TABLE VALUES
(1,'John',null),
(1,'John','RE'),
(2,'Smith',null),
(2,'Smith','DOS'),
(3,'Van',null),
(4,'Sam','CR'),
(5,'Bob',null)
SELECT id,name,ref FROM
(
SELECT
id,name,ref,RN = ROW_NUMBER() OVER (PARTITION BY id,name ORDER BY ref DESC)
FROM
#TABLE
) AS A
WHERE RN < 2
You can use this too:
SELECT
u.id,
u.name,
MAX(u.ref) as Ref
FROM
#TABLE u
GROUP BY
u.id,
u.name
Related
BEGIN;
CREATE temp TABLE teacher (
name text,
salary numeric
);
INSERT INTO teacher
VALUES ('b1', 90000);
INSERT INTO teacher
VALUES ('f1', 87000);
INSERT INTO teacher
VALUES ('a', 65000),
('b', 90000),
('c', 40000),
('d', 95000),
('e', 60000),
('f', 87000);
COMMIT;
query
with recursive cte as(
(select name, salary, 1 as rn
from teacher order by salary desc limit 1)
union all
select l.* from cte c cross join lateral(
select name, salary, rn + 1 from teacher t
where t.salary < c.salary
order by salary desc
limit 1
) l
)
table cte order by salary desc;
If all salary are distinct,then above mentioned query can imitate as rank/row_number.
I am wondering how to use recursive query to replicate/imitate dense_rank.
related post: https://dba.stackexchange.com/questions/286627/get-top-two-rows-per-group-efficiently
I want to change the 20 rows with one column to 1 row with 20 columns to insert it later in a second database
Name
----------
- Frank
- Dora
- ...
- Michael
to
Name1 | Name2 | ... | Name20
Frank | Dora | ... | Michael
I tried
SELECT *
FROM (SELECT TOP 20 firstname AS NAME
FROM database) AS d
PIVOT (Min(NAME)
FOR NAME IN (name1,
name2,
name3,
name4,
name5,
name6,
name7,
name8,
name9,
name10,
name11,
name12,
name13,
name14,
name15,
name16,
name18,
name19,
name20) ) AS f
But all names are NULL. DEMO
You were close... But your inner select must carry the new column name. Try it like this:
DECLARE #tbl TABLE(Name VARCHAR(100));
INSERT INTO #tbl VALUES('Frank'),('Dora'),('Michael');
SELECT p.*
FROM
(
SELECT 'Name' + CAST(ROW_NUMBER() OVER(ORDER BY Name) AS VARCHAR(150)) AS ColumnName
,Name
From #tbl
) AS tbl
PIVOT
(
MIN(Name) FOR ColumnName IN(Name1,Name2,Name3)
) AS p
I am using SSMS 2008 and trying to concatenate one of the rows together based on a different field's grouping. I have two columns, people_id and address_desc. They look like this:
address_desc people_id
---------- ------------
Murfreesboro, TN 37130 F15D1135-9947-4F66-B778-00E43EC44B9E
11 Mohawk Rd., Burlington, MA 01803 C561918F-C2E9-4507-BD7C-00FB688D2D6E
Unknown, UN 00000 C561918F-C2E9-4507-BD7C-00FB688D2D6E Jacksonville, NC 28546 FC7C78CD-8AEA-4C8E-B93D-010BF8E4176D
Memphis, TN 38133 8ED8C601-5D35-4EB7-9217-012905D6E9F1
44 Maverick St., Fitchburg, MA 8ED8C601-5D35-4EB7-9217-012905D6E9F1
Now I want to concatenate the address_desc field / people_id. So the first one here should just display "Murfreesboro, TN 37130" for address_desc. But second person should have just one line instead of two which says "11 Mohawk Rd., Burlington, MA 01803;Unknown, UN 00000" for address_desc.
How do I do this? I tried using CTE, but this was giving me ambiguity error:
WITH CTE ( people_id, address_list, address_desc, length )
AS ( SELECT people_id, CAST( '' AS VARCHAR(8000) ), CAST( '' AS VARCHAR(8000) ), 0
FROM dbo.address_view
GROUP BY people_id
UNION ALL
SELECT p.people_id, CAST( address_list +
CASE WHEN length = 0 THEN '' ELSE ', ' END + c.address_desc AS VARCHAR(8000) ),
CAST( c.address_desc AS VARCHAR(8000)), length + 1
FROM CTE c
INNER JOIN dbo.address_view p
ON c.people_id = p.people_id
WHERE p.address_desc > c.address_desc )
SELECT people_id, address_list
FROM ( SELECT people_id, address_list,
RANK() OVER ( PARTITION BY people_id ORDER BY length DESC )
FROM CTE ) D ( people_id, address_list, rank )
WHERE rank = 1 ;
Here was my initial SQL query:
SELECT a.address_desc, a.people_id
FROM dbo.address_view a
INNER JOIN (SELECT people_id
FROM dbo.address_view
GROUP BY people_id
HAVING COUNT(*) > 1) t
ON a.people_id = t.people_id
order by a.people_id
You can use FOR XML PATH('') like this:
DECLARE #TestData TABLE
(
address_desc NVARCHAR(100) NOT NULL
,people_id UNIQUEIDENTIFIER NOT NULL
);
INSERT #TestData
SELECT 'Murfreesboro, TN 37130', 'F15D1135-9947-4F66-B778-00E43EC44B9E'
UNION ALL
SELECT '11 Mohawk Rd., Burlington, MA 01803', 'C561918F-C2E9-4507-BD7C-00FB688D2D6E'
UNION ALL
SELECT 'Unknown, UN 00000', 'C561918F-C2E9-4507-BD7C-00FB688D2D6E'
UNION ALL
SELECT 'Memphis, TN 38133', '8ED8C601-5D35-4EB7-9217-012905D6E9F1'
UNION ALL
SELECT '44 Maverick St., Fitchburg, MA', '8ED8C601-5D35-4EB7-9217-012905D6E9F1';
SELECT a.people_id,
(SELECT SUBSTRING(
(SELECT ';'+b.address_desc
FROM #TestData b
WHERE a.people_id = b.people_id
FOR XML PATH(''), TYPE).value('.', 'NVARCHAR(MAX)')
,2
,4000)
) GROUP_CONCATENATE
FROM #TestData a
GROUP BY a.people_id
Results:
people_id GROUP_CONCATENATE
------------------------------------ ------------------------------------------------------
F15D1135-9947-4F66-B778-00E43EC44B9E Murfreesboro, TN 37130
C561918F-C2E9-4507-BD7C-00FB688D2D6E 11 Mohawk Rd., Burlington, MA 01803;Unknown, UN 00000
8ED8C601-5D35-4EB7-9217-012905D6E9F1 Memphis, TN 38133;44 Maverick St., Fitchburg, MA
Table name: Table1
id name
1 1-aaa-14 milan road
2 23-abcde-lsd road
3 2-mnbvcx-welcoome street
I want the result like this:
Id name name1 name2
1 1 aaa 14 milan road
2 23 abcde lsd road
3 2 mnbvcx welcoome street
This function ought to give you what you need.
--Drop Function Dbo.Part
Create Function Dbo.Part
(#Value Varchar(8000)
,#Part Int
,#Sep Char(1)='-'
)Returns Varchar(8000)
As Begin
Declare #Start Int
Declare #Finish Int
Set #Start=1
Set #Finish=CharIndex(#Sep,#Value,#Start)
While (#Part>1 And #Finish>0)Begin
Set #Start=#Finish+1
Set #Finish=CharIndex(#Sep,#Value,#Start)
Set #Part=#Part-1
End
If #Part>1 Set #Start=Len(#Value)+1 -- Not found
If #Finish=0 Set #Finish=Len(#Value)+1 -- Last token on line
Return SubString(#Value,#Start,#Finish-#Start)
End
Usage:
Select ID
,Dbo.Part(Name,1,Default)As Name
,Dbo.Part(Name,2,Default)As Name1
,Dbo.Part(Name,3,Default)As Name2
From Dbo.Table1
It's rather compute-intensive, so if Table1 is very long you ought to write the results to another table, which you could refresh from time to time (perhaps once a day, at night).
Better yet, you could create a trigger, which automatically updates Table2 whenever a change is made to Table1. Assuming that column ID is primary key:
Create Table Dbo.Table2(
ID Int Constraint PK_Table2 Primary Key,
Name Varchar(8000),
Name1 Varchar(8000),
Name2 Varchar(8000))
Create Trigger Trigger_Table1 on Dbo.Table1 After Insert,Update,Delete
As Begin
If (Select Count(*)From Deleted)>0
Delete From Dbo.Table2 Where ID=(Select ID From Deleted)
If (Select Count(*)From Inserted)>0
Insert Dbo.Table2(ID, Name, Name1, Name2)
Select ID
,Dbo.Part(Name,1,Default)
,Dbo.Part(Name,2,Default)
,Dbo.Part(Name,3,Default)
From Inserted
End
Now, do your data manipulation (Insert, Update, Delete) on Table1, but do your Select statements on Table2 instead.
The below solution uses a recursive CTE for splitting the strings, and PIVOT for displaying the parts in their own columns.
WITH Table1 (id, name) AS (
SELECT 1, '1-aaa-14 milan road' UNION ALL
SELECT 2, '23-abcde-lsd road' UNION ALL
SELECT 3, '2-mnbvcx-welcoome street'
),
cutpositions AS (
SELECT
id, name,
rownum = 1,
startpos = 1,
nextdash = CHARINDEX('-', name + '-')
FROM Table1
UNION ALL
SELECT
id, name,
rownum + 1,
nextdash + 1,
CHARINDEX('-', name + '-', nextdash + 1)
FROM cutpositions c
WHERE nextdash < LEN(name)
)
SELECT
id,
[1] AS name,
[2] AS name1,
[3] AS name2
/* add more columns here */
FROM (
SELECT
id, rownum,
part = SUBSTRING(name, startpos, nextdash - startpos)
FROM cutpositions
) s
PIVOT ( MAX(part) FOR rownum IN ([1], [2], [3] /* extend the list here */) ) x
Without additional modifications this query can split names consisting of up to 100 parts (that's the default maximum recursion depth, which can be changed), but can only display no more than 3 of them. You can easily extend it to however many parts you want it to display, just follow the instructions in the comments.
select T.id,
substring(T.Name, 1, D1.Pos-1) as Name,
substring(T.Name, D1.Pos+1, D2.Pos-D1.Pos-1) as Name1,
substring(T.Name, D2.Pos+1, len(T.name)) as Name2
from Table1 as T
cross apply (select charindex('-', T.Name, 1)) as D1(Pos)
cross apply (select charindex('-', T.Name, D1.Pos+1)) as D2(Pos)
Testing performance of suggested solutions
Setup:
create table Table1
(
id int identity primary key,
Name varchar(50)
)
go
insert into Table1
select '1-aaa-14 milan road' union all
select '23-abcde-lsd road' union all
select '2-mnbvcx-welcoome street'
go 10000
Result:
if you always will have 2 dashes, you can do the following by using PARSENAME
--testing table
CREATE TABLE #test(id INT, NAME VARCHAR(1000))
INSERT #test VALUES(1, '1-aaa-14 milan road')
INSERT #test VALUES(2, '23-abcde-lsd road')
INSERT #test VALUES(3, '2-mnbvcx-welcoome street')
SELECT id,PARSENAME(name,3) AS name,
PARSENAME(name,2) AS name1,
PARSENAME(name,1)AS name2
FROM (
SELECT id,REPLACE(NAME,'-','.') NAME
FROM #test)x
if you have dots in the name column you have to first replace them and then replace them back to dots in the end
example, by using a tilde to substitute the dot
INSERT #test VALUES(3, '5-mnbvcx-welcoome street.')
SELECT id,REPLACE(PARSENAME(name,3),'~','.') AS name,
REPLACE(PARSENAME(name,2),'~','.') AS name1,
REPLACE(PARSENAME(name,1),'~','.') AS name2
FROM (
SELECT id,REPLACE(REPLACE(NAME,'.','~'),'-','.') NAME
FROM #test)x
From the table below, how can I convert the Values column into multiple columns, populated with individual values that are currently separated by commas? Before the conversion:
Name Values
---- ------
John val,val2,val3
Peter val5,val7,val9,val14
Lesli val8,val34,val36,val65,val71,val
Amy val3,val5,val99
The result of the conversion should look like:
Name Col1 Col2 Col3 Col4 Col5 Col6
---- ---- ---- ---- ---- ---- ----
John val val2 val3
Peter val5 val7 val9 val14
Lesli val8 val34 val36 val65 val71 val
Amy val3 val5 val99
First, what database product and version are you using? If you are using SQL Server 2005 and later, you can write a Split user-defined function like so:
CREATE FUNCTION [dbo].[Split]
(
#DelimitedList nvarchar(max)
, #Delimiter varchar(2) = ','
)
RETURNS TABLE
AS
RETURN
(
With CorrectedList As
(
Select Case When Left(#DelimitedList, DataLength(#Delimiter)) <> #Delimiter Then #Delimiter Else '' End
+ #DelimitedList
+ Case When Right(#DelimitedList, DataLength(#Delimiter)) <> #Delimiter Then #Delimiter Else '' End
As List
, DataLength(#Delimiter) As DelimiterLen
)
, Numbers As
(
Select TOP (Coalesce(Len(#DelimitedList),1)) Row_Number() Over ( Order By c1.object_id ) As Value
From sys.objects As c1
Cross Join sys.columns As c2
)
Select CharIndex(#Delimiter, CL.list, N.Value) + CL.DelimiterLen As Position
, Substring (
CL.List
, CharIndex(#Delimiter, CL.list, N.Value) + CL.DelimiterLen
, CharIndex(#Delimiter, CL.list, N.Value + 1)
- ( CharIndex(#Delimiter, CL.list, N.Value) + CL.DelimiterLen )
) As Value
From CorrectedList As CL
Cross Join Numbers As N
Where N.Value < Len(CL.List)
And Substring(CL.List, N.Value, CL.DelimiterLen) = #Delimiter
)
You can then split out the values in you want using something akin to:
Select Name, Values
From Table1 As T1
Where Exists (
Select 1
From Table2 As T2
Cross Apply dbo.Split (T1.Values, ',') As T1Values
Cross Apply dbo.Split (T2.Values, ',') As T2Values
Where T2.Values.Value = T1Values.Value
And T1.Name = T2.Name
)
Here is a solution that uses a recursive cte to generate a "table of numbers" (courtesy of Itzik Ben-Gan), which is useful for all manner of problems including string splitting, and PIVOT. SQL Server 2005 onwards. Full table create, insert and select script included.
CREATE TABLE dbo.Table1
(
Name VARCHAR(30),
[Values] VARCHAR(128)
)
GO
INSERT INTO dbo.Table1 VALUES ('John', 'val,val2,val3')
INSERT INTO dbo.Table1 VALUES ('Peter', 'val5,val7,val9,val14')
INSERT INTO dbo.Table1 VALUES ('Lesli', 'val8,val34,val36,val65,val71,val')
INSERT INTO dbo.Table1 VALUES ('Amy', 'val3,val5,val99')
GO
SELECT * FROM dbo.Table1;
GO
WITH
L0 AS(SELECT 1 AS c UNION ALL SELECT 1),
L1 AS(SELECT 1 AS c FROM L0 AS A, L0 AS B),
L2 AS(SELECT 1 AS c FROM L1 AS A, L1 AS B),
L3 AS(SELECT 1 AS c FROM L2 AS A, L2 AS B),
Numbers AS(SELECT ROW_NUMBER() OVER(ORDER BY c) AS n FROM L3)
SELECT Name, [1] AS Column1, [2] AS Column2, [3] AS Column3, [4] AS Column4, [5] AS Column5, [6] AS Column6, [7] AS Column7
FROM
(SELECT Name,
ROW_NUMBER() OVER (PARTITION BY Name ORDER BY nums.n) AS PositionInList,
LTRIM(RTRIM(SUBSTRING(valueTable.[Values], nums.n, charindex(N',', valueTable.[Values] + N',', nums.n) - nums.n))) AS [Value]
FROM Numbers AS nums INNER JOIN dbo.Table1 AS valueTable ON nums.n <= CONVERT(int, LEN(valueTable.[Values])) AND SUBSTRING(N',' + valueTable.[Values], n, 1) = N',') AS SourceTable
PIVOT
(
MAX([VALUE]) FOR PositionInList IN ([1], [2], [3], [4], [5], [6], [7])
) AS Table2
GO
--DROP TABLE dbo.Table1
Which converts this output
Name Values
John val,val2,val3
Peter val5,val7,val9,val14
Lesli val8,val34,val36,val65,val71,val
Amy val3,val5,val99
to
Name Column1 Column2 Column3 Column4 Column5 Column6 Column7
Amy val3 val5 val99 NULL NULL NULL NULL
John val val2 val3 NULL NULL NULL NULL
Lesli val8 val34 val36 val65 val71 val NULL
Peter val5 val7 val9 val14 NULL NULL NULL