I have 2 in memory tables #Holding and #P1
if the row is in #P1 I want to remove it from #Holding
With my code below the duplicates are not being removed. I do not have a primary Id key like many examples, For a unique row I have Drawing, Method and Location.
DELETE h
FROM #Holding h
INNER JOIN #P1 p1 ON p1.DRAWING = h.DRAWING and p1.Method = h.Method and
p1.LOCATION = h.LOCATION
You could try using a where exists
DELETE h
FROM #Holding h
WHERE EXISTS (
SELECT *
FROM #P1 p1
WHERE p1.DRAWING = h.DRAWING and p1.Method = h.Method and p1.LOCATION = h.LOCATION
)
if your duplicates are not being removed, is because the requirement to join with #P1 to find them is incorrect.
Just to show an example that the delete/join works as expected:
declare #t1 table (c1 int)
declare #t2 table (c1 int)
insert into #t1 values (1),(2),(3)
insert into #t2 values (1)
delete #t1
from #t1 t1
join #t2 t2
on t1.c1=t2.c1
select * from #t1
Related
I have two tables where TableA has latest data and TableB has some old data. I want to update TableB's data if it matches id with TableA and if doesn't match insert new row in TableB.
I got a solution from stackOverflow
begin tran
if exists (select * from t with (updlock,serializable) where pk = #id)
begin
update t set hitCount = hitCount+1
where pk = #id
end
else
begin
insert t (pk, hitCount)
values (#id, 1)
end
commit tran
But it seems I need to pass #id each time, may be I am not getting it in the correct way. I have hundreds of row to update/insert from tableA.
Think relationally.
SQL Server always operates sets. A single row is just a set of 1 row.
Here is a simple example of two step update - insert operations
create table #tableA(id int, [year] int, updated_value int)
insert #tableA(id,[year],updated_value)
values
(1,1990,85),
(2,1991,70),
(3,1992,80)
create table #tableB(id int, [year] int, score int)
insert #tableB(id,[year],score)
values
(1,1990,50),
(4,1995,20)
update #tableA set
updated_value=b.score
from #tableA a
inner join #tableB b on a.id=b.id --inner is important
insert #tableA(id,[year],updated_value)
select b.id,b.[year],b.score
from #tableB b
left join #tableA a on a.id=b.id --left is important
where a.id is null -- and this line too
select * from #tableA
If you wish you can combine update and insert in a single merge operation.
merge #tableA as tgt
using #tableB as src
on src.id=tgt.id
when matched then
update set updated_value=src.score
when not matched then
insert(id,[year],updated_value)
values(id,[year],score)
; -- semicoloumn is required
select * from #tableA
I need to replace the column value if exists to another column have a same text as like below example.
create table #t1
(
a varchar(100)
)
create table #t2
(
b varchar(100),
c varchar(100)
)
insert into #t1 values('she is a girl teacher and he is a boy doctor')
insert into #t2 values('girl','G')
insert into #t2 values('boy','B')
select *from #t1
select *from #t2
select a=replace (t1.a,t2.b,t2.c)
from #t1 t1 inner join #t2 t2 on t1.a like '%'+t2.b+'%'
while i'm selecting the query the result displays like
she is a G teacher and he is a boy doctor
she is a girl teacher and he is a B doctor
but i have need the output like
she is a G teacher and he is a B doctor
How need to change my query for the above output.
The only solution I can think if using recursive queries.
create table #t1
(
a varchar(100)
)
create table #t2
(
b varchar(100),
c varchar(100)
)
insert into #t1 values('she is a girl teacher and he is a boy doctor')
, ('she is a girl soldier and he is a boy doctor')
, ('she is a girl dentist and he is a boy farmer')
insert into #t2 values('girl','G')
insert into #t2 values('boy','B')
select *from #t1
select *from #t2
select a=replace(t1.a,t2.b,t2.c), *
from #t1 t1
inner join #t2 t2 on t1.a like '%'+t2.b+'%';
with cte as (
select a, 1 as ct from #t1
union all
select cast(replace(a,t2.b,t2.c) as varchar(100)) as a, ct+1 from cte
cross apply #t2 t2 where a like '%'+t2.b+'%'
)select distinct a from (select a, ct as ct from cte) as t1 where t1.ct = (select max(ct) from cte);
drop table #t1
drop table #t2
-- she is a G teacher and he is a B doctor
The most straightforward way is to just use a cursor to loop through all the replacements, applying them.
create table #t1
(
a varchar(100)
)
create table #t2
(
b varchar(100),
c varchar(100)
)
insert into #t1 values('she is a girl teacher and he is a boy doctor')
insert into #t2 values('girl','G')
insert into #t2 values('boy','B')
-- We create a couple of variables and a temporal table to hold the incremental replacements
declare #Pattern varchar(64)
declare #Value varchar(64)
select * into #TempReplacements from #1
-- Apply the replacements
declare Replacements cursor for select b, c from #t2
open Replacements
fetch next from Replacements into #Pattern, #Value
while ##fetch_status = 0
update #TempReplacements set a = replace(a, #Pattern, #Value)
fetch next from Replacements into #Pattern, #Value
end
close Replacements
deallocate Replacements
-- We return the results
select * from #TempRelacements
-- Drop temporary Table
drop table #TempReplacements
drop table #t1
drop table #t2
This might be a stupid question, but I am not a DBA and kind of stuck with this issue. I have an application that trickles down all effects (asdf) under an applied ID (IDParent).
The data tables are setup like this:
Data Tables
3rd Data Table
I want to write a query that when using IDChild it will reference that entry's IDParent to get the parent ID while referencing it as an IDChild. For example for the data entry starting at 116 I want to use the parent ID (124) and get 321 in T1. I want to use this to get the RandoName associated with RandoID for all of the entries that has a parent ID of 321.
Right now I am using a script something like:
Select t.[NAME]
From T2 tv
Inner join T3 t on t.RandoID = tv.RandoId
Where
tv.IDChild = T1.IDChild OR tv.IDChild = T1.IDParent
but I'm not sure how to get the whole applied hierarchy.
This would yield something like this:
Resulting Query
PS. I can not change the tables/db schema. But maybe I can add one to do all the referencing? Please tell me what you think.
EDIT I'm sorry I forgot about this other stupid table that RandoID uses which contains the name of the RandoID. I am trying to get the name of RandoID
I think a loop could help you.
Try this:
CREATE TABLE #t1 (IDChild Int, IDParent Int);
CREATE TABLE #t2 (RandoID NVARCHAR(10) , IDChild Int);
CREATE TABLE #RandoName (RandoID NVARCHAR(10), RandoName VARCHAR(50));
INSERT INTO #t1 VALUES (321, NULL), (123,321),(124,123),(116,124)
INSERT INTO #t2 VALUES ('asdf', 123)
INSERT INTO #RandoName VALUES ('asdf', 'something')
SELECT ROW_NUMBER() OVER (ORDER BY (SELECT 100)) [RowNum], a.IDChild a, a.IDParent b, b.IDChild c INTO #t3 FROM #t1 a
LEFT OUTER JOIN #t1 b ON b.IDParent = a.IDChild
DECLARE #rownum INT;
DECLARE cbcursor CURSOR for Select RowNum FROM #t3;
OPEN cbcursor;
Fetch Next from cbcursor into #rownum
WHILE ##FETCH_STATUS = 0
BEGIN
UPDATE #t3
SET c = (SELECT b from #t3 where RowNum = #rownum-1)
WHERE RowNum = #rownum
Fetch Next from cbcursor into #rownum;
END;
Close cbcursor;
Deallocate cbcursor;
SELECT a,b,t2.RandoID, r.RandoName FROM #t3
LEFT OUTER JOIN #t2 t2 on t2.IDChild = #t3.c OR t2.IDChild = #t3.b OR t2.IDChild = #t3.a
LEFT OUTER JOIN #RandoName r on t2.RandoID = r.RandoID
This is what I get:
If you have any changes in your tables, like more records for T2, this script should be modified.
Using recursion:
declare #t table (IDc int , Idp int)
insert into #t
values
(321,null)
,(123,321)
,(124,123)
,(116,124)
declare #t2 table (RandoID varchar(10), IDChild int)
insert into #t2
values('asdf',123)
;with cte as
(
select anchor = IDChild
,ParentOrSelf = IDc
,RandoID
,RandomName
from #t
cross join (select RandoID,RandoName from #t2 t2 join #t3 t3 on t2.RandoID=t3.RandoID) crossed
where IDc=#anchor
union all
select t2.IDChild
,IDc
, t2.RandoID,RandomName
from #t t
cross join (select RandoID,RandoName from #t2 t2 join #t3 t3 on t2.RandoID=t3.RandoID) t2
join cte on cte.ParentOrSelf = t.Idp
)
select IDc
, cte.RandoID,cte.RandomName
from #t t
left join cte on t.IDc = cte.ParentOrSelf
Results:
IDc RandoID
321 NULL
123 asdf
124 asdf
116 asdf
I want to delete from t2 if same value of itemid,storeid,MSRTime does not exist on t1 and Same value of itemid,storeid,MSRTime exist on t3 and status is D. In below example i should be able to delete second row on t2 but not 1st row.
Table 1: t1
itemid |storeid|MSRTime
x y z
Table 2: t2
itemid |storeid|MSRTime
x y z
a b c
Table 3: t3
itemid |storeid|MSRTime|status
x y z D
a b c D
I tried doing this using join but i could not reach the desired result. Please help.
Thank You.
You can write the query almost exactly as you've described it:
declare #t1 table(itemid varchar(7),storeid varchar(9),MSRTime varchar(3))
insert into #t1(itemid,storeid,MSRTime) values
('x','y','z')
declare #t2 table(itemid varchar(7),storeid varchar(9),MSRTime varchar(3))
insert into #t2(itemid,storeid,MSRTime) values
('x','y','z'),
('a','b','c')
declare #t3 table(itemid varchar(7),storeid varchar(9),MSRTime varchar(3),status varchar(4))
insert into #t3(itemid,storeid,MSRTime,status) values
('x','y','z','D'),
('a','b','c','D')
delete from t2
from #t2 t2
inner join
#t3 t3
on
t2.itemid = t3.itemid and
t2.storeid = t3.storeid and
t2.MSRTime = t3.MSRTime and
t3.status = 'D'
where
not exists (
select *
from #t1 t1
where t1.itemid = t2.itemid and
t1.storeid = t2.storeid and
t1.MSRTime = t2.MSRTime
)
select * from #t2
Result:
itemid storeid MSRTime
------- --------- -------
x y z
Should be something like this
-- delete t2
select *
from table2 t2
JOIN table3 t3 on t2.itemid = t3.itemid and
t2.storeid = t3.storeid and
t2.MSRTime = t3.MSRTime
LEFT JOIN table1 t1 on t2.itemid = t1.itemid and
t2.storeid = t1.storeid and
t2.MSRTime = t1.MSRTime
where t1.itemID IS NULL
Run the select first, if it gives you back right row, just un-comment delete and you are good to go
I have created the whole script for your reference. Please use the last DELETE query for your scenario. That will do the trick.
CREATE TABLE #T1
(itemid VARCHAR(10)
,storeid VARCHAR(10)
,MSRTime VARCHAR(10))
INSERT INTO #T1 VALUES ('x','y','z')
SELECT * FROM #T1
GO
CREATE TABLE #T2
(itemid VARCHAR(10)
,storeid VARCHAR(10)
,MSRTime VARCHAR(10))
INSERT INTO #T2 VALUES ('x','y','z'),('a','b','c')
SELECT * FROM #T2
GO
CREATE TABLE #T3
(itemid VARCHAR(10)
,storeid VARCHAR(10)
,MSRTime VARCHAR(10)
,status VARCHAR(10))
INSERT INTO #T3 VALUES ('x','y','z','D'),('a','b','c','D')
SELECT * FROM #T3
GO
DELETE M
FROM #T2 AS M INNER JOIN
(SELECT itemid,storeid,MSRTime FROM
(SELECT itemid,storeid,MSRTime FROM #T3 WHERE status='D') T1
INTERSECT
(SELECT itemid,storeid,MSRTime FROM
(SELECT * FROM #T2
EXCEPT
SELECT * FROM #T1) T2)) X
ON X.itemid = M.itemid AND X.storeid = M.storeid AND X.MSRTime = M.MSRTime
GO
Not sure if this matches your environment, but programmatically it may be beneficial to limit the results you are comparing with the joins to only those that have a value of D in status. I would also try making a compound key using Coalese so that you are not having to match on three separate joins.
For example -
itemid |storeid|MSRTime|Key
x y z xyz
a b c abc
How do I Delete duplicated rows in one Table and update References in another table to the remaining row? The duplication only occurs in the name. The Id Columns are Identity columns.
Example:
Assume we have two tables Doubles and Data.
Doubles table (
Id int,
Name varchar(50)
)
Data Table (
Id int,
DoublesId int
)
Now I Have Two entries in the Doubls table:
Id Name
1 Foo
2 Foo
And two entries in the Data Table:
ID DoublesId
1 1
2 2
At the end there should be only one entry in the Doubles Table:
Id Name
1 Foo
And two entries in the Data Table:
Id DoublesId
1 1
2 1
In the doubles Table there can be any number of duplicated rows per name (up to 30) and also regular 'single' rows.
I've not run this, but hopefully it should be correct, and close enough to the final soln to get you there. Let me know any mistakes if you like and I'll update the answer.
--updates the data table to the min ids for each name
update Data
set id = final_id
from
Data
join
Doubles
on Doubles.id = Data.id
join
(
select
name
min(id) as final_id
from Doubles
group by name
) min_ids
on min_ids.name = Doubles.name
--deletes redundant ids from the Doubles table
delete
from Doubles
where id not in
(
select
min(id) as final_id
from Doubles
group by name
)
Note: I have taken the liberty to rename your Id's to DoubleID and DataID respectively. I find that eassier to work with.
DECLARE #Doubles TABLE (DoubleID INT, Name VARCHAR(50))
DECLARE #Data TABLE (DataID INT, DoubleID INT)
INSERT INTO #Doubles VALUES (1, 'Foo')
INSERT INTO #Doubles VALUES (2, 'Foo')
INSERT INTO #Doubles VALUES (3, 'Bar')
INSERT INTO #Doubles VALUES (4, 'Bar')
INSERT INTO #Data VALUES (1, 1)
INSERT INTO #Data VALUES (1, 2)
INSERT INTO #Data VALUES (1, 3)
INSERT INTO #Data VALUES (1, 4)
SELECT * FROM #Doubles
SELECT * FROM #Data
UPDATE #Data
SET DoubleID = MinDoubleID
FROM #Data dt
INNER JOIN #Doubles db ON db.DoubleID = dt.DoubleID
INNER JOIN (
SELECT db.Name, MinDoubleID = MIN(db.DoubleID)
FROM #Doubles db
GROUP BY db.Name
) dbmin ON dbmin.Name = db.Name
/* Kudos to quassnoi */
;WITH q AS (
SELECT Name, ROW_NUMBER() OVER (PARTITION BY Name ORDER BY Name) AS rn
FROM #Doubles
)
DELETE
FROM q
WHERE rn > 1
SELECT * FROM #Doubles
SELECT * FROM #Data
Take a look at this one, i have tried this, working fine
--create table Doubles ( Id int, Name varchar(50))
--create table Data( Id int, DoublesId int)
--select * from doubles
--select * from data
Declare #NonDuplicateID int
Declare #NonDuplicateName varchar(max)
DECLARE #sqlQuery nvarchar(max)
DECLARE DeleteDuplicate CURSOR FOR
SELECT Max(id),name AS SingleID FROM Doubles
GROUP BY [NAME]
OPEN DeleteDuplicate
FETCH NEXT FROM DeleteDuplicate INTO #NonDuplicateID, #NonDuplicateName
--Fetch next record
WHILE ##FETCH_STATUS = 0
BEGIN
--select b.ID , b.DoublesID, a.[name],a.id asdasd
--from doubles a inner join data b
--on
--a.ID=b.DoublesID
--where b.DoublesID<>#NonDuplicateID
--and a.[name]=#NonDuplicateName
print '---------------------------------------------';
select
#sqlQuery =
'update b
set b.DoublesID=' + cast(#NonDuplicateID as varchar(50)) + '
from
doubles a
inner join
data b
on
a.ID=b.DoublesID
where b.DoublesID<>' + cast(#NonDuplicateID as varchar(50)) +
' and a.[name]=''' + cast(#NonDuplicateName as varchar(max)) +'''';
print #sqlQuery
exec sp_executeSQL #sqlQuery
print '---------------------------------------------';
-- now move the cursor
FETCH NEXT FROM DeleteDuplicate INTO #NonDuplicateID ,#NonDuplicateName
END
CLOSE DeleteDuplicate --Close cursor
DEALLOCATE DeleteDuplicate --Deallocate cursor
---- Delete duplicate rows from original table
DELETE
FROM doubles
WHERE ID NOT IN
(
SELECT MAX(ID)
FROM doubles
GROUP BY [NAME]
)
Please try and let me know if this helped you
Thanks
~ Aamod
If you are using MYSQL following worked for me. I did it for 2 steps
Step 1 -> Update all Data rows to one Double table reference (with lowest id)
Step 2 -> Delete all duplicates with keeping lowest id
Step 1 ->
update Data
join
Doubles
on Data.DoublesId = Doubles.id
join
(
select name, min(id) as final_id
from Doubles
group by name
) min_ids
on min_ids.name = Doubles.name
set DoublesId = min_ids.final_id;
Step 2 ->
DELETE c1 FROM Doubles c1
INNER JOIN Doubles c2
WHERE
c1.id > c2.id AND
c1.name = c2.name;