Regex pattern inside REPLACE function - sql

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

Related

Datatype mismatch in anchor and recursive part of a recursive CTE

I am running this SQL code on SQL Server to print alphabets from A to Z:
;with alphaCte as
(
select 'A' as letter
union all
select char(ascii(letter)+1)
from alphaCte
where letter < 'Z'
)
select * from alphaCte
I get this error:
Types don't match between the anchor and the recursive part in column "letter" of recursive query "alphaCte".
To rectify it, I have to make below change.
;with alphaCte as
(
select char(ascii('A')) as letter
union all
select char(ascii(letter)+1)
from alphaCte
where letter < 'Z'
)
select * from alphaCte
which works fine.
Could anyone please explain why my original code is throwing this datatype mismatch error?
To expand on my comment
Select column_ordinal
,name
,system_type_name
From sys.dm_exec_describe_first_result_set('select ''A'' as letter,char(ascii(''A'')+1) as letter2',null,null )
Results
column_ordinal name system_type_name
1 letter varchar(1)
2 letter2 char(1)
EDIT: Just an aside... Recursive CTEs are great but datasets are better :)
Select Top 26 C=char(64+Row_Number() Over (Order By (Select NULL)) )
From master..spt_values n

BQ function to transform caron character from a string to character without caron

I am trying to get rid of a caron characters (č,ć,š,ž) and transform them to c,c,s,z :
with my_table as (
select 'abcčd sštuv' caron, 'abccd sstuv' no_caron union all
select 'uvzž', 'uvzz' union all
select 'ijkl cČd', 'ijkl cCd' union ALL
select 'Ćdef', 'Cdef'
)
SELECT *
FROM my_table
I was trying to get rid of them with
SELECT *,
regexp_replace(caron, r'š', 's') as no_caron
FROM my_table
but I think this is inefficient. I know there is an option to write your on function as described
here, but I have no idea how to use it in my case.
Thanks in advance!
Use below
SELECT *, regexp_replace(normalize(caron, NFD), r"\pM", '') output
FROM my_table
if applied to sample data in your question - output is

Remove Substring according to specific pattern

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);

How to combine return results of query in one row

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

sql server string split last but one

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