Table has a column with values
ColA
------
a.b.c.d.e (car.make.model, car.la, kg)
ab.cd.ef (car.make.model)
a1.b2.c3.d4.e5(car.make.model, car.la, kg, av.vc.de)
I want to write a sql query to split the ColA by delimiter "." and pick last but one.
Expected output
Result
------
d
cd
d4
I have tried ParseName but dont see option to pick last but one.
Thank you
Using Jeff Moden's DelimitedSplit8K:
USE Sandbox;
GO
CREATE TABLE #Sample (ColA varchar(500));
GO
INSERT INTO #Sample
VALUES ('a.b.c.d.e'),
('ab.cd.ef'),
('a1.b2.c3.d4.e5');
GO
SELECT *
FROM #Sample;
WITH Split AS(
SELECT S.ColA,
DS.*,
MAX(DS.ItemNumber) OVER (PARTITION BY S.ColA) AS Items
FROM #Sample S
CROSS APPLY DelimitedSplit8K(S.ColA,'.') DS)
SELECT Item
FROM Split
WHERE ItemNumber = Items - 1;
GO
DROP TABLE #Sample
Ideally, though, don't store your data in a delimited format. :)
Just to play around using STRING_SPLIT:
SELECT ColA, t.value
FROM table1
CROSS APPLY(SELECT value,
COUNT(*) OVER () as cnt,
ROW_NUMBER() OVER (ORDER BY (SELECT NULL)) AS rn
FROM STRING_SPLIT(ColA, '.')) AS t
WHERE t.rn = t.cnt - 1
Note: The function is available from SQL Server 2016.
Note 2: The query works provided that the function returns each value in the same order as the one it appears inside the string.
Why not simply using substring?
DECLARE #ColA NVARCHAR(100) = 'a1.b2.c3.d4.e5(car.make.model, car.la, kg, av.vc.de)';
SELECT REVERSE(LEFT(RIGHT(REVERSE(LEFT(#ColA, CHARINDEX('(', #ColA)-1)), LEN(LEFT(#ColA, CHARINDEX('(', #ColA)-1))-CHARINDEX('.',REVERSE(LEFT(#ColA, CHARINDEX('(', #ColA)-1)))), CHARINDEX('.',RIGHT(REVERSE(LEFT(#ColA, CHARINDEX('(', #ColA)-1)), LEN(LEFT(#ColA, CHARINDEX('(', #ColA)-1))-CHARINDEX('.',REVERSE(LEFT(#ColA, CHARINDEX('(', #ColA)-1)))))-1))
However, this last edit does NOT handle the case when there is no . or no ( in the string - feel free t o extend the query accordingly
Try This
;WITH CTE(ColA)
AS
(
SELECT 'a.b.c.d.e' UNION ALL
SELECT 'ab.cd.ef' UNION ALL
SELECT 'a1.b2.c3.d4.e5'
)
SELECT ColA,REVERSE(SUBSTRING(ReqColA,0,CHARINDEX('.',(ColA)))) AS ReqColA
FROM
(
SELECT ColA ,SUBSTRING(REVERSE(ColA),CHARINDEX('.',REVERSE(ColA))+1,LEN(REVERSE(ColA))) AS ReqColA FROM CTE
)dt
Result
ColA ReqColA
-----------------------
a.b.c.d.e d
ab.cd.ef cd
a1.b2.c3.d4.e5 d4
Related
I need to remove in a SQL Server database a substring according to a pattern:
Before: Winter_QZ6P91712017_115BPM
After: Winter_115BPM
Or
Before: cpx_Note In My Calendar_QZ6P91707044
After: cpx_Note In My Calendar
Basically delete the substring that has pattern _ + 12 chars.
I've tried PatIndex('_\S{12}', myCol) to get the index of the substring but it doesn't match anything.
Assuming you mean underscore followed by 12 characters that are not underscores you can use this pattern:
SELECT *,
CASE WHEN PATINDEX('%[_][^_][^_][^_][^_][^_][^_][^_][^_][^_][^_][^_][^_]%', str) > 0
THEN STUFF(str, PATINDEX('%[_][^_][^_][^_][^_][^_][^_][^_][^_][^_][^_][^_][^_]%', str), 13, '')
ELSE str
END
FROM (VALUES
('Winter_QZ6P91712017_115BPM'),
('Winter_115BPM_QZ6P91712017')
) AS tests(str)
late to the party, but you could also use latest STRING_SPLIT function to explode the string by underscores and count length of each segment between underscores. If the length is >=12, these sections must be replaced from original string via replace function recursively.
drop table if exists Tbl;
drop table if exists #temptable;
create table Tbl (input nvarchar(max));
insert into Tbl VALUES
('Winter_QZ6P91712017_115BPM'),
('cpx_Note In My Calendar_QZ6P91707044'),
('stuff_asdasd_QZ6P91712017'),
('stuff_asdasd_QZ6P91712017_stuff_asdasd_QZ6P91712017'),
('stuff_asdasd_QZ6P917120117_stuff_asdasd_QZ6P91712017');
select
input, value as replacethisstring,
rn = row_number() over (partition by input order by (select 1))
into #temptable
from
(
select
input,value as hyphensplit
from Tbl
cross apply string_split(input,'_')
)T cross apply string_split(hyphensplit,' ')
where len(value)>=12
; with cte as (
select input, inputtrans= replace(input,replacethisstring,''), level=1 from #temptable where rn=1
union all
select T.input,inputtrans=replace(cte.inputtrans,T.replacethisstring,''),level=level+1
from cte inner join #temptable T on T.input=cte.input and rn=level+1
--where level=rn
)
select input, inputtrans
from (
select *, rn=row_number() over (partition by input order by level desc) from cte
) T where rn=1
sample output
SQL Server doesn't support Regex. Considering, however, you just want to remove the first '_' and the 12 characters afterwards, you could use CHARINDEX to find the location of said underscore, and then STUFF to remove the 13 characters:
SELECT V.YourString,
STUFF(V.YourString, CHARINDEX('_',V.YourString),13,'') AS NewString
FROM (VALUES('Winter_QZ6P91712017_115BPM'))V(YourString);
I have a table that save personnel code.
When I select from this table I get 3 rows result such as:
2129,3394,3508,3534
2129,3508
4056
I want when create select result combine in one row such as:
2129,3394,3508,3534,2129,3508,4056
or distinct value such as:
2129,3394,3508,3534,4056
You should ideally avoid storing CSV data at all in your tables. That being said, for your first result set we can try using STRING_AGG:
SELECT STRING_AGG(col, ',') AS output
FROM yourTable;
Your second requirement is more tricky, and we can try going through a table to remove duplicates:
WITH cte AS (
SELECT DISTINCT VALUE AS col
FROM yourTable t
CROSS APPLY STRING_SPLIT(t.col, ',')
)
SELECT STRING_AGG(col, ',') WITHIN GROUP (ORDER BY CAST(col AS INT)) AS output
FROM cte;
Demo
I solved this by using STUFF and FOR XML PATH:
SELECT
STUFF((SELECT ',' + US.remain_uncompleted
FROM Table_request US
WHERE exclusive = 0 AND reqact = 1 AND reqend = 0
FOR XML PATH('')), 1, 1, '')
Thank you Tim
Have a column ID that I would like to ORDER in a specific format. Column has a varchar data type and always has an alphabetic value, typically P in front followed by three to four numeric values. Possibly even followed by an underscore or another alphabetic value. I have tried few options and none are returning what I desire.
SELECT [ID] FROM MYTABLE
ORDER BY
(1) LEN(ID), ID ASC
/ (2) LEFT(ID,2)
OPTIONS TRIED (3) SUBSTRING(ID,2,4) ASC
\ (4) ROW_NUMBER() OVER (ORDER BY SUBSTRING(ID,2,4))
(5) SUBSTRING(ID,PATINDEX('%[0-9]%',ID),LEN(ID))
(6) LEFT(ID, PATINDEX('%[0-9]%', ID)-1)
Option 1 seems to be closest to what I am looking for except when an _ or Alphabetic values follow the numeric value. See results from Option 1 below
P100
P208
P218
P301
P305
P306
P4200
P4510
P4511
P4512
P5011
P1400A
P4125H
P4202A
P4507L
P4706A
P1001_2
P2103_B
P4368_RL
Would like to see..
P100
P208
P218
P301
P305
P306
P1001_2
P1400A
P2103_B
P4125H
P4200
P4202A
P4368_RL
P4507L
P4510
P4511
P4512
P4706A
P5011
ORDER BY
CAST(SUBSTRING(id, 2, 4) AS INT),
SUBSTRING(id, 6, 3)
http://sqlfiddle.com/#!6/9eecb7db59d16c80417c72d1e1f4fbf1/9464
And one that's still less complex than a getOnlyNumbers() UDF, but copes with varying length of numeric part.
CROSS APPLY
(
SELECT
tail_start = PATINDEX('%[0-9][^0-9]%', id + '_')
)
stats
CROSS APPLY
(
SELECT
numeric = CAST(SUBSTRING(id, 2, stats.tail_start-1) AS INT),
alpha = RIGHT(id, LEN(id) - stats.tail_start)
)
id_tuple
ORDER BY
id_tuple.numeric,
id_tuple.alpha
http://sqlfiddle.com/#!6/9eecb7db59d16c80417c72d1e1f4fbf1/9499
Finally, one that can cope with there being no number at all (but still assumes the first character exists and should be ignored).
CROSS APPLY
(
SELECT
tail_start = NULLIF(PATINDEX('%[0-9][^0-9]%', id + '_'), 0)
)
stats
CROSS APPLY
(
SELECT
numeric = CAST(SUBSTRING(id, 2, stats.tail_start-1) AS INT),
alpha = RIGHT(id, LEN(id) - ISNULL(stats.tail_start, 1))
)
id_tuple
ORDER BY
id_tuple.numeric,
id_tuple.alpha
http://sqlfiddle.com/#!6/9eecb7db59d16c80417c72d1e1f4fbf1/9507
This is a rather strange way to sort but now that I understand it I figured out a solution. I am using a table valued function here to strip out only the numbers from a string. Since the function returns all numeric characters I also need to check for the _ and only pass in the part of the string before that.
Here is the function.
create function GetOnlyNumbers
(
#SearchVal varchar(8000)
) returns table as return
with MyValues as
(
select substring(#SearchVal, N, 1) as number
, t.N
from cteTally t
where N <= len(#SearchVal)
and substring(#SearchVal, N, 1) like '[0-9]'
)
select distinct NumValue = STUFF((select number + ''
from MyValues mv2
order by mv2.N
for xml path('')), 1, 0, '')
from MyValues mv
This function is using a tally table. If you have one you can tweak that code slightly to fit. Here is my tally table. I keep it as a view.
create View [dbo].[cteTally] as
WITH
E1(N) AS (select 1 from (values (1),(1),(1),(1),(1),(1),(1),(1),(1),(1))dt(n)),
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
(
SELECT ROW_NUMBER() OVER (ORDER BY (SELECT NULL)) FROM E4
)
select N from cteTally
GO
Next of course we need to have some data to work. In this case I just created a table variable to represent your actual table.
declare #Something table
(
SomeVal varchar(10)
)
insert #Something values
('P100')
, ('P208')
, ('P218')
, ('P301')
, ('P305')
, ('P306')
, ('P4200')
, ('P4510')
, ('P4511')
, ('P4512')
, ('P5011')
, ('P1400A')
, ('P4125H')
, ('P4202A')
, ('P4507L')
, ('P4706A')
, ('P1001_2')
, ('P2103_B')
, ('P4368_RL')
With all the legwork and setup behind us we can get to the actual query needed to accomplish this.
select s.SomeVal
from #Something s
cross apply dbo.GetOnlyNumbers(case when charindex('_', s.SomeVal) = 0 then s.SomeVal else left(s.SomeVal, charindex('_', s.SomeVal) - 1) end) x
order by convert(int, x.NumValue)
This returns the rows in the order you listed them in your question.
You can break down ID in steps to extract the number. Then, order by the number and ID. I like to break down long string manipulation into steps using CROSS APPLY. You can do it inline (it'd be long) or bundle it into an inline TVF.
SELECT t.*
FROM MYTABLE t
CROSS APPLY (SELECT NoP = STUFF(ID, 1, 1, '')) nop
CROSS APPLY (SELECT FindNonNumeric = LEFT(NoP, ISNULL(NULLIF(PATINDEX('%[^0-9]%', NoP)-1, -1), LEN(NoP)))) fnn
CROSS APPLY (SELECT Number = CONVERT(INT, FindNonNumeric)) num
ORDER BY Number
, ID;
I think your best bet is to create a function that strips the numbers out of the string, like this one, and then sort by that. Even better, as #SeanLange suggested, would be to use that function to store the number value in a new column and sort by that.
SELECT REPLACE('ABCTemplate1', 'Template\d+', '');
SELECT REPLACE('ABC_XYZTemplate21', 'Template\d+', '');
I am trying to remove the part Template followed by n digits from a string. The result should be
ABC
ABC_XYZ
However REPLACE is not able to read regex. I am using SQLSERVER 2008. Am I doing something wrong here? Any suggestions?
SELECT SUBSTRING('ABCTemplate1', 1, CHARINDEX('Template','ABCTemplate1')-1)
or
SELECT SUBSTRING('ABC_XYZTemplate21',1,PATINDEX('%Template[0-9]%','ABC_XYZTemplate21')-1)
More generally,
SELECT SUBSTRING(column_name,1,PATINDEX('%Template[0-9]%',column_name)-1)
FROM sometable
WHERE PATINDEX('%Template[0-9]%',column_name) > 0
You can use substring with charindex or patindex if the pattern being looked for is fixed.
select SUBSTRING('ABCTemplate1',1, CHARINDEX ( 'Template' ,'ABCTemplate1')-1)
My answer expects that "Template" is enough to determine where to cut the string:
select LEFT('ABCTemplate1', CHARINDEX('Template', 'ABCTemplate1') - 1)
Using numbers table..
;with cte
as
(select 'ABCTemplate1' as string--this can simulate your table column
)
select * from cte c
cross apply
(
select replace('ABCTemplate1','template'+cast(n as varchar(2)),'') as rplcd
from
numbers
where n<=9
)
b
where c.string<>b.rplcd
Using Recursive CTE..
;with cte
as
(
select cast(replace('ABCTemplate21','template','') as varchar(100)) as string,0 as num
union all
select cast(replace(string,cast(num as varchar(2)),'') as varchar(100)),num+1
from cte
where num<=9
)
select top 1 string from cte
order by num desc
If I have a string with numbers separated by commas, like this:
Declare #string varchar(20) = '123,456,789'
And would like to return every possible combination + sort order of the values by doing this:
Select Combination FROM dbo.GetAllCombinations(#string)
Which would in result return this:
123
456
789
123,456
456,123
123,789
789,123
456,789
789,456
123,456,789
123,789,456
456,789,123
456,123,789
789,456,123
789,123,456
As you can see not only is every combination returned, but also each combination+sort order as well. The example shows only 3 values separated by commas, but should parse any amount--Recursive.
The logic needed would be somewhere in the realm of using a WITH CUBE statement, but the problem with using WITH CUBE (in a table structure instead of CSV of course), is that it won't shuffle the order of the values 123,456 456,123 etc., and will only provide each combination, which is only half of the battle.
Currently I have no idea what to try. If someone can provide some assistance it would be appreciated.
I use a User Defined Table-valued Function called split_delimiter that takes 2 values: the #delimited_string and the #delimiter_type.
CREATE FUNCTION [dbo].[split_delimiter](#delimited_string VARCHAR(8000), #delimiter_type CHAR(1))
RETURNS TABLE AS
RETURN
WITH cte10(num) 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
)
,cte100(num) AS
(
SELECT 1
FROM cte10 t1, cte10 t2
)
,cte10000(num) AS
(
SELECT 1
FROM cte100 t1, cte100 t2
)
,cte1(num) AS
(
SELECT TOP (ISNULL(DATALENGTH(#delimited_string),0)) ROW_NUMBER() OVER (ORDER BY (SELECT NULL))
FROM cte10000
)
,cte2(num) AS
(
SELECT 1
UNION ALL
SELECT t.num+1
FROM cte1 t
WHERE SUBSTRING(#delimited_string,t.num,1) = #delimiter_type
)
,cte3(num,[len]) AS
(
SELECT t.num
,ISNULL(NULLIF(CHARINDEX(#delimiter_type,#delimited_string,t.num),0)-t.num,8000)
FROM cte2 t
)
SELECT delimited_item_num = ROW_NUMBER() OVER(ORDER BY t.num)
,delimited_value = SUBSTRING(#delimited_string, t.num, t.[len])
FROM cte3 t;
Using that I was able to parse the CSV to a table and join it back to itself multiple times and use WITH ROLLUP to get the permutations you are looking for.
WITH Numbers as
(
SELECT delimited_value
FROM dbo.split_delimiter('123,456,789',',')
)
SELECT CAST(Nums1.delimited_value AS VARCHAR)
,ISNULL(CAST(Nums2.delimited_value AS VARCHAR),'')
,ISNULL(CAST(Nums3.delimited_value AS VARCHAR),'')
,CAST(Nums4.delimited_value AS VARCHAR)
FROM Numbers as Nums1
LEFT JOIN Numbers as Nums2
ON Nums2.delimited_value not in (Nums1.delimited_value)
LEFT JOIN Numbers as Nums3
ON Nums3.delimited_value not in (Nums1.delimited_value, Nums2.delimited_value)
LEFT JOIN Numbers as Nums4
ON Nums4.delimited_value not in (Nums1.delimited_value, Nums2.delimited_value, Nums3.delimited_value)
GROUP BY CAST(Nums1.delimited_value AS VARCHAR)
,ISNULL(CAST(Nums2.delimited_value AS VARCHAR),'')
,ISNULL(CAST(Nums3.delimited_value AS VARCHAR),'')
,CAST(Nums4.delimited_value AS VARCHAR) WITH ROLLUP
If you will potentially have more than 3 or 4, you'll want to expand your code accordingly.