How to replace a string value with single character - sql

I want to mask the data except the last four characters.
For example:
If there is a varchar column (Name) with the value Rio De janerio, I want to mask it as xxx xx xxxerio.
If it is a numeric column (acc number) with value 123 453 6987,then I want it to be displayed as 000 000 6987.
I tried using right and replace function. But I could not find the solution.
Mask the data except last four characters/numbers

On Oracle, You can try below query to replace numbers with 0s -
SELECT REGEXP_REPLACE (SUBSTR('123 453 6987', 1, LENGTH('123 453 6987')-4), '\d', '0') || SUBSTR('123 453 6987', -4, 4) PROCESSED_STRING
FROM DUAL;
PROCESSED_STRING
000 000 6987
For Replacing strings with #s -
SELECT REGEXP_REPLACE (SUBSTR('Rio De janerio', 1, LENGTH('Rio De janerio')-4), '\S', '#') || SUBSTR('Rio De janerio', -4, 4) PROCESSED_STRING
FROM DUAL;
PROCESSED_STRING
### ## ###erio
Here is the fiddle.

This is not a complete solution but it is just a idea and a head up to move you in the right direction . You can modify the query as per your requirement .
In SQL SERVER :
create table place
(
place_name varchar(100),
place_pincode varchar(100)
)
insert into place values ('Rio De janerio',1234536987)
select substring(place_pincode,len(place_pincode)-3,len(place_pincode)),
case when isnumeric(place_pincode)=1 then
concat('000000',substring(place_pincode,len(place_pincode)-3,len(place_pincode))) end as place_pincode,
case when isnumeric(place_name)<>1 then
concat('XXXXXX',substring(place_name,len(place_name)-3,len(place_name))) end as place_name
from place

If you are using SQL Server 2016 and above you can use Translate function:
declare #name varchar(50) = 'Rio De janerio'
select translate(substring(#name,1,len(#name)-4),'abcdefghijklmnopqrstuvwxyz','**************************') + right(#name,4)
declare #i int = 1234536987
select translate(substring(convert(varchar(50),#i),1,len(#i)-4),'0123456789','0000000000') + right(#i,4)

Using SQLSERVER STUFF() and PATINDEX() will solve this question
FOR MASKING THE NAME
declare #str varchar(20)
declare #rcInt int
set #str ='Rio De janerio'
set #rcInt = 4;
with cte as
(select left(#str, len(#str)-#rcInt) as name
),
rn as
(select stuff(name, patindex('%[a-z]%',name), 1, 'X') as ch, patindex('%[a-z]%',name)as rn, name from cte
union all
select stuff(ch, rn+patindex('%[a-z]%',substring(name, rn+1, len(name))), 1, 'X') as ch, rn+patindex('%[a-z]%',substring(name, rn+1, len(name)))as rn, name from rn
where patindex('%[a-z]%',substring(name, rn+1, len(name)))>0
)
select top 1 ch + right(#str, #rcInt) from rn order by rn desc
FOR TELEPHONE NUMBER (as function)
create function ufn_MaskPhoneNum(
#str varchar(20),
#rcInt int
)
returns #tblReturn table(maskedStr varchar(100))
as
begin
with cte as
(select left(#str, len(#str)-#rcInt) as name
),
rn as
(select stuff(name, patindex('%[0-9]%',name), 1, 'X') as ch, patindex('%[0-9]%',name)as rn, name from cte
union all
select stuff(ch, rn+patindex('%[0-9]%',substring(name, rn+1, len(name))), 1, 'X') as ch,
rn+patindex('%[0-9]%',substring(name, rn+1, len(name)))as rn, name from rn
where patindex('%[0-9]%',substring(name, rn+1, len(name)))>0
)
insert into #tblReturn
select top 1 ch + right(#str, #rcInt) from rn order by rn desc
return;
end
sample:
select * from ufn_MaskPhoneNum('123 453 6987', 4)

Related

How to replace anything between 2 specific characters in SQL Server

I'm trying to replace anything between 2 specific characters in a string that contains multiples of those 2 caracters. Take it as a csv format.
Here an example of what i got as data in that field:
0001, ABCD1234;0002, EFGH432562;0003, IJKL1345hsth;...
What I need to retreive from it is all parts before the ',' but not what are between ',' and ';'
I tried with those formula but no success
SELECT REPLACE(fieldname, ',[A-Z];', ' ') FROM ...
or
SELECT REPLACE(fieldname, ',*;', ' ') FROM ...
I need to get
0001 0002 0003
Is there a way to achieve that?
You can CROSS APPLY to a STRING_SPLIT that uses STRING_AGG (since Sql Server 2017) to stick the numbers back together.
select id, codes
from your_table
cross apply (
select string_agg(left(value, patindex('%_,%', value)), ' ') as codes
from string_split(fieldname, ';') s
where value like '%_,%'
) ca;
GO
id
codes
1
0001 0002 0003
Demo on db<>fiddle here
Extra
Here is a version that also works in Sql Server 2014.
Inspired by the research from #AaronBertrand
The UDF uses a recursive CTE to split the string.
And the FOR XML trick is used to stick the numbers back together.
CREATE FUNCTION dbo.fnString_Split
(
#str nvarchar(4000),
#delim nchar(1)
)
RETURNS TABLE
WITH SCHEMABINDING
AS
RETURN
(
WITH RCTE AS (
SELECT
1 AS ordinal
, ISNULL(NULLIF(CHARINDEX(#delim, #str),0), LEN(#str)) AS pos
, LEFT(#str, ISNULL(NULLIF(CHARINDEX(#delim, #str),0)-1, LEN(#str))) AS value
UNION ALL
SELECT
ordinal+1
, ISNULL(NULLIF(CHARINDEX(#delim, #str, pos+1), 0), LEN(#str))
, SUBSTRING(#str, pos+1, ISNULL(NULLIF(CHARINDEX(#delim, #str, pos+1),0)-pos-1, LEN(#str)-pos ))
FROM RCTE
WHERE pos < LEN(#str)
)
SELECT ordinal, value
FROM RCTE
);
SELECT id, codes
FROM your_table
CROSS APPLY (
SELECT RTRIM((
SELECT LEFT(value, PATINDEX('%_,%', value))+' '
FROM dbo.fnString_Split(fieldname, ';') AS spl
WHERE value LIKE '%_,%'
ORDER BY ordinal
FOR XML PATH(''), TYPE).value(N'./text()[1]', N'nvarchar(max)')
) AS codes
) ca
OPTION (MAXRECURSION 250);
id
codes
1
0001 0002 0003
Demo on db<>fiddle here
Alternative version of the UDF (no recursion)
CREATE FUNCTION dbo.fnString_Split
(
#str NVARCHAR(4000),
#delim NCHAR(1)
)
RETURNS #tbl TABLE (ordinal INT, value NVARCHAR(4000))
WITH SCHEMABINDING
AS
BEGIN
DECLARE #value NVARCHAR(4000)
, #pos INT = 0
, #ordinal INT = 0;
WHILE (LEN(#str) > 0)
BEGIN
SET #ordinal += 1;
SET #pos = ISNULL(NULLIF(CHARINDEX(#delim, #str),0), LEN(#str)+1);
SET #value = LEFT(#str, #pos-1);
SET #str = SUBSTRING(#str, #pos+1, LEN(#str));
INSERT INTO #tbl (ordinal, value)
VALUES (#ordinal, #value);
END;
RETURN;
END;
If you're on SQL Server 2017 and don't need a guarantee that the order will be maintained, then LukStorms' answer is perfectly adequate.
However, if you:
care about an order guarantee; or,
are on an older version than 2017 (and can't use STRING_AGG); or,
are on an even older version than 2016 or are in an older compatibility level (and can't use STRING_SPLIT):
Here's an ordered split function that can help (it's long and ugly but you only have to create it once):
CREATE FUNCTION dbo.SplitOrdered
(
#list nvarchar(max),
#delim nvarchar(10)
)
RETURNS TABLE
WITH SCHEMABINDING
AS
RETURN
(
WITH w(n) AS (SELECT 0 FROM (VALUES (0),(0),(0),(0)) w(n)),
k(n) AS (SELECT 0 FROM w a, w b),
r(n) AS (SELECT 0 FROM k a, k b, k c, k d, k e, k f, k g, k h),
p(n) AS (SELECT TOP (COALESCE(LEN(#list), 0))
ROW_NUMBER() OVER (ORDER BY ##SPID) -1 FROM r),
spots(p) AS
(
SELECT n FROM p
WHERE (SUBSTRING(#list, n, LEN(#delim + 'x') - 1) LIKE #delim OR n = 0)
),
parts(p,val) AS
(
SELECT p, SUBSTRING(#list, p + LEN(#delim + 'x') - 1,
LEAD(p, 1, 2147483647) OVER (ORDER BY p) - p - LEN(#delim))
FROM spots AS s
)
SELECT listpos = ROW_NUMBER() OVER (ORDER BY p),
Item = LTRIM(RTRIM(val))
FROM parts
);
Then the query can become:
;WITH x AS
(
SELECT id, listpos,
codes = LEFT(Item, COALESCE(NULLIF(CHARINDEX(',', Item),0),1)-1)
FROM dbo.your_table
CROSS APPLY dbo.SplitOrdered(fieldname, ';') AS c
)
SELECT id, codes = (
(SELECT x2.codes + ' '
FROM x AS x2
WHERE x2.id = x.id
ORDER BY x2.listpos
FOR XML PATH(''), TYPE).value(N'./text()[1]', N'nvarchar(max)')
)
FROM x GROUP BY id;
Example borrowing from LukStorms' db<>fiddle
Note that, in addition to guaranteeing order and being backward compatible (well, only back so many versions), it also ignores garbage data, e.g. try:
0001, ABCD1234;0002 but no comma

SQL get average of a list in sql select

We have this column in the table named "pricehistory"
1634913730;48.38,1634916509;48.38,1635162352;37.96,1635177904;49.14,1635337722;1219.98,1635340811;27.17
that is an example data.
first is the timestamp than after ; is the price at this timestamp
But i want the average price from every timestamp in a select... is that possible?
I dont find any similiar examples somewhere and my tries to select doesnt work... i am not so good with sql
so i want average of all prices behind that ; and before ,
The , split the timestamp and prices
Some test data :
create table test ( id int not null, pricehistory text not null );
insert into test values ( 1, '1634913730;48.38,1634916509;48.38,1635162352;37.96,1635177904;49.14,1635337722;1219.98,1635340811;27.17' );
insert into test values ( 2, '1634913731;42.42,1634916609;21.21' );
If your RDBMS has some splitting function
Then it's quite easy, just split and use AVG. Here is an example using PostgreSQL :
SELECT id, AVG(SUBSTRING(v, 12, 42)::decimal) AS average
FROM test
INNER JOIN LATERAL regexp_split_to_table(pricehistory, E',') t(v) ON TRUE
GROUP BY id;
Then you get:
id | average
----+----------------------
2 | 31.8150000000000000
1 | 238.5016666666666667
(2 rows)
Otherwise
You can use a CTE to split the values manually. This is a bit more involved. Here is an example using PostgreSQL again :
WITH RECURSIVE T AS (
SELECT id,
-- We get the last value ...
SUBSTRING(pricehistory, LENGTH(pricehistory) - STRPOS(REVERSE(pricehistory), ',') + 2) AS oneprice,
pricehistory AS remaining
FROM test
UNION ALL
-- ... as we get the other values from the recursive CTE.
SELECT id,
LEFT(remaining, STRPOS(remaining, ',') - 1),
SUBSTRING(remaining, STRPOS(remaining, ',') + 1)
FROM T
WHERE STRPOS(remaining, ',') > 0
)
SELECT id, AVG(SUBSTRING(oneprice, 12)::decimal) AS average
FROM T
GROUP BY id;
Then you get:
id | average
----+----------------------
2 | 31.8150000000000000
1 | 238.5016666666666667
(2 rows)
MySql >= 8.0
I used Recursive Common Table Expressions (cte) to split pricehistory string by ','. Then I split price from timestamp by ';', cast price as decimal(10,2) and group by id to get average price by id.
WITH RECURSIVE
cte AS (SELECT id,
SUBSTRING_INDEX(pricehistory, ',', 1) AS price,
CASE WHEN POSITION(',' IN pricehistory) > 0
THEN SUBSTR(pricehistory, POSITION(',' IN pricehistory) + 1)
ELSE NULL END AS rest
FROM t
UNION ALL
SELECT id,
SUBSTRING_INDEX(rest, ',', 1) AS price,
CASE WHEN POSITION(',' IN rest) > 0
THEN SUBSTR(rest, POSITION(',' IN rest) + 1)
ELSE NULL END AS rest
FROM cte
WHERE rest IS NOT NULL)
SELECT id, AVG(CAST(SUBSTR(price, POSITION(';' IN price) + 1) AS decimal(10,2))) AS price_average
FROM cte
GROUP BY id;
A similar way to do the same (using regular expressions functions):
WITH RECURSIVE
cte AS (SELECT Id, concat(pricehistory, ',') AS pricehistory FROM t),
unnest AS (SELECT id,
pricehistory,
1 AS i,
REGEXP_SUBSTR(pricehistory, ';[0-9.]*,', 1, 1) AS price
FROM cte
UNION ALL
SELECT id,
pricehistory,
i + 1,
REGEXP_SUBSTR(pricehistory, ';[0-9.]*,', 1, i + 1)
FROM unnest
WHERE REGEXP_SUBSTR(pricehistory, ';[0-9.]*,', 1, i + 1) IS NOT NULL)
SELECT id, AVG(CAST(SUBSTR(price, 2, LENGTH(price) - 2) AS decimal(10,2))) AS price_average
FROM unnest
GROUP BY id;
you don't write what DBMS you are using.
In MS SQL-SERVER you can write something like this.
Create a function to convert string to multiple rows, and then use that in the query.
CREATE or ALTER FUNCTION dbo.BreakStringIntoRows (#CommadelimitedString varchar(1000), #Separator VARCHAR(1))
RETURNS #Result TABLE (Column1 VARCHAR(max))
AS
BEGIN
DECLARE #IntLocation INT
WHILE (CHARINDEX(#Separator, #CommadelimitedString, 0) > 0)
BEGIN
SET #IntLocation = CHARINDEX(#Separator, #CommadelimitedString, 0)
INSERT INTO #Result (Column1)
--LTRIM and RTRIM to ensure blank spaces are removed
SELECT RTRIM(LTRIM(SUBSTRING(#CommadelimitedString, 0, #IntLocation)))
SET #CommadelimitedString = STUFF(#CommadelimitedString, 1, #IntLocation, '')
END
INSERT INTO #Result (Column1)
SELECT RTRIM(LTRIM(#CommadelimitedString))--LTRIM and RTRIM to ensure blank spaces are removed
RETURN
END
create table test1 ( id int not null, pricehistory varchar(max) not null );
insert into test1 values ( 1, '1634913730;48.38,1634916509;48.38,1635162352;37.96,1635177904;49.14,1635337722;1219.98,1635340811;27.17' );
insert into test1 values ( 2, '1634913731;42.42,1634916609;21.21' );
Select *,
(
Select avg(CAST(RTRIM(LTRIM(SUBSTRING(column1, 0, CHARINDEX(';', column1, 0)))) as decimal)) From dbo.BreakStringIntoRows(pricehistory, ',')
) as AVG
FRom test1
sample output:

Add character in front and at the end of each character

In SQL I want to add 0 in front and , at the end of each character.
Example: A30F1 -> 0A,03,00,0F,01
I don't want to use cursor if possible.
Thanks!
EIDT:
I apologize for not asking the most appropriate question at the beginning.
In short, I have a table and for each value in the column name I have to convert it to the desired format. For example, we have a #Temp table:
CREATE TABLE #Temp (id INT, name VARCHAR(25))
INSERT INTO #Temp VALUES (1, 'A30F1'), (2, 'B51R9'), (3, 'L1721')
SELECT * FROM #Temp
One method would be to use a Tally to split the string into it's individual characters, and then use concatenation to add the 0 to the start, and STRING_AGG to comma delimit the results:
DECLARE #YourValue varchar(5) = 'A30F1';
WITH N AS(
SELECT N
FROM (VALUES(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL))N(N)),
Tally AS(
SELECT TOP (LEN(#YourValue))
ROW_NUMBER() OVER (ORDER BY (SELECT NULL)) AS I
FROM N N1, N N2) --Up to 100 characters, add more cross joins for more characters
SELECT STRING_AGG(CONCAT('0',SS.C),',') WITHIN GROUP (ORDER BY T.I) AS NewString
FROM (VALUES(#YourValue))V(YourValue)
CROSS JOIN Tally T
CROSS APPLY (VALUES(SUBSTRING(V.YourValue,T.I,1)))SS(C);
It appears this is meant to be against a table, not a single value. This needs, however, very few changes to work against a table:
WITH N AS(
SELECT N
FROM (VALUES(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL))N(N)),
Tally AS(
SELECT TOP (SELECT MAX(LEN(YourColumn)) FROM dbo.YourTable)
ROW_NUMBER() OVER (ORDER BY (SELECT NULL)) AS I
FROM N N1, N N2) --Up to 100 characters, add more cross joins for more characters
SELECT STRING_AGG(CONCAT('0',SS.C),',') WITHIN GROUP (ORDER BY T.I) AS NewString
FROM dbo.YourTable YT
JOIN Tally T ON LEN(YT.YourColumn) >= T.I
CROSS APPLY (VALUES(SUBSTRING(YT.YourColumn,T.I,1)))SS(C)
GROUP BY YT.YourColumn;
db<>fiddle
I solved the simplest possible with a few variables, WHILE and SUBSTRING
DECLARE #var VARCHAR(20) = 'A30F1', #i INT = 1, #res NVARCHAR(20)
WHILE (#i <= LEN(#var))
BEGIN
SET #res = #res + '0' + SUBSTRING(#var, #i, 1) + ','
SET #i = #i + 1
END
SELECT LEFT(#res, LEN(#res) - 1) output
Check demo on DB<>FIDDLE.
Original answer:
A recursive CTE and a STRING_AGG() call is also an option (SQL Server 2017+ is needed):
DECLARE #text varchar(max) = 'A30F1';
WITH rCTE AS
(
SELECT 1 AS CharacterPosition, SUBSTRING(#text, 1, 1) AS Character
UNION ALL
SELECT CharacterPosition + 1, SUBSTRING(#text, CharacterPosition + 1, 1)
FROM rCTE
WHERE CharacterPosition < LEN(#text)
)
SELECT STRING_AGG('0' + Character, ',') WITHIN GROUP (ORDER BY CharacterPosition)
FROM rCTE
OPTION (MAXRECURSION 0);
Update:
You need a different statement, if the names are stored in a table, again using recursion and STRING_AGG():
Table:
CREATE TABLE #Temp (id INT, name VARCHAR(25))
INSERT INTO #Temp VALUES (1, 'A30F1'), (2, 'B51R9'), (3, 'L1721')
Statement:
; WITH rCTE AS (
SELECT
t.id AS id,
LEFT(t.name, 1) AS Character,
STUFF(t.name, 1, 1, '') AS CharactersRemaining,
1 AS CharacterPosition
FROM #Temp t
UNION ALL
SELECT
r.id,
LEFT(r.CharactersRemaining, 1),
STUFF(r.CharactersRemaining, 1, 1, ''),
CharacterPosition + 1
FROM rCTE r
WHERE LEN(r.CharactersRemaining) > 0
)
SELECT
id,
STRING_AGG('0' + Character, ',') WITHIN GROUP (ORDER BY CharacterPosition) AS name
FROM rCTE
GROUP BY id
OPTION (MAXRECURSION 0);
Result:
id name
1 0A,03,00,0F,01
2 0B,05,01,0R,09
3 0L,01,07,02,01
If you are only applying this to English alphabet characters and digits as in your example you could do this.
CREATE TABLE #Temp (id INT, name VARCHAR(25))
INSERT INTO #Temp VALUES (1, 'A30F1'), (2, 'B51R9'), (3, 'L1721'), (4, 'A')
SELECT SUBSTRING(REPLACE(
0x00 + CAST(CAST(name AS NVARCHAR(25)) AS BINARY(50)), CHAR(0), '0,')
, 3
, LEN(name) * 3 - 1)
FROM #Temp
returns
0A,03,00,0F,01
0B,05,01,0R,09
0L,01,07,02,01
0A
This takes advantage of the fact that the binary representation of the nvarchar and varchar is the same for this limited character set except for padding out with 0x00
'A30F1' -> 0x4133304631
N'A30F1' -> 0x41003300300046003100

Generate a comma-separated list of numbers in a single string

Is there a way to generate a comma-separated string of a series of numbers where the "begin" and "end" numbers are provided?
For example, provide the numbers 1 and 10 and the output would be a single value of: 1,2,3,4,5,6,7,8,9,10
10/10/2019 edit explaining why I'm interested in this:
My workplace writes queries with several columns in the SELECT statement plus aggregate functions. Then a GROUP BY clause using the column numbers. I figured using a macro that creates a comma-separated list to copy/paste in would save some time.
SELECT t.colA
, t.colB
, t.colC
, t.colD
, t.colE
, t.colF
, t.colG
, t.colH
, t.colI
, t.colJ
, sum(t.colK) as sumK
, sum(t.colL) as sumL
, sum(t.colM) as sumM
FROM t
GROUP BY 1, 2, 3, 4, 5, 6, 7, 8, 9, 10
;
You can use a recursive CTE to generate your numbers, and xml_agg to generate your string:
with recursive nums (counter) as
( select * from (select cast(1 as bigint) as counter) t
union all
select
counter + 1
from nums
where counter between 1 and 9
)
select
trim(trailing ',' from cast(xmlagg(cast(counter as varchar(2)) || ',' order by counter) as varchar(100)))
from nums
Check these methods in SQL Server-
IF OBJECT_ID('TEMPDB..#Sample') IS NOT NULL
DROP TABLE #Sample
Create table #Sample
(
NUM int
)
declare #n int
select #n=10
insert into #Sample(NUM)
SELECT NUM FROM (select row_number() over (order by (select null)) AS NUM from sys.columns) A WHERE NUM<=#N
--Method 1 (For SQL SERVER -NEW VERSION Support)
SELECT STRING_AGG(NUM,',') AS EXPECTED_RESULT FROM #Sample
--Method 1 (For SQL SERVER -OLD VERSION Support)
select DISTINCT STUFF(CAST((
SELECT ' ,' +CAST(c.num AS VARCHAR(MAX))
FROM (
SELECT num
FROM #Sample
) c
FOR XML PATH(''), TYPE) AS VARCHAR(MAX)), 1, 2, '') AS EXPECTED_RESULT
from #Sample t
While loop seems appropriate
declare #begin int=1
declare #end int=11
declare #list varchar(500)
if #begin > #end
begin
select 'error, beginning number ' + convert(varchar(500),#begin)
+ ' must not be greater than ending number '
+ convert(varchar(500),#end) + '.' err
return
end
else
set #list = convert(varchar(500),#begin)
;
while #begin < #end
begin
set #begin += 1
set #list = #list + ',' + convert(varchar(500),#begin)
end
select #list
You might want to use varchar(5000) or something depending on how big you want it to get.
disclaimer -- I don't know if this works with teradata
I'm not sure there is a good direct way to generate a series in Teradata. You can fake it a few different ways though. Here's a comma separated list of numbers from 5 to 15, for example:
SELECT TRIM(TRAILING ',' FROM (XMLAGG(TRIM(rn)|| ',' ) (VARCHAR(10000))))
FROM (SELECT 4 + ROW_NUMBER() OVER (ORDER BY Sys_Calendar."CALENDAR".day_of_calendar) as rn FROM Sys_Calendar."CALENDAR" QUALIFY rn <= 15) t
I've only used sys_calendar.calendar here because it's a big table. Any big table would do here though.
Here's one way to do it in Teradata:
SELECT ARRAY_AGG(src.RowNum)
FROM (
SELECT ROW_NUMBER() OVER() AS RowNum
FROM sys_calendar.calendar
QUALIFY RowNum BETWEEN <begin_num> AND <end_num>
) src
This will give you the output as an ARRAY data type, which you can probably cast as a VARCHAR. It also assumes begin_num > 0 and <end_num> is less than the number of rows in the sys_calendar.calendar view. You can always fiddle with this to fit your required range of values.
There are also DelimitedBuild UDFs out there (if you can find one) that can be used to convert row values into delimited strings.
The cheapest way to achieve your goal is this one (no functions, or joins to tables required):
WITH RECURSIVE NumberRanges(TheNumber,TheString) AS
(
SELECT 1 AS TheNumber,casT(1 as VARCHAR(500)) as TheString
FROM
(
SELECT * FROM (SELECT NULL AS X) X
) DUMMYTABLE
UNION ALL
SELECT
TheNumber + 1 AS TheNumber,
TheString ||',' || TRIM(TheNumber+1)
FROM NumberRanges
WHERE
TheNumber < 10
)
SELECT TheString
FROM NumberRanges
QUALIFY ROW_NUMBER() OVER ( ORDER BY TheNumber DESC) = 1;
Result String: 1,2,3,4,5,6,7,8,9,10

Tricky SQL query requiring search for contains

I have data such as this:
Inventors column in my table
Hundley; Edward; Ana
Isler; Hunsberger
Hunsberger;Hundley
Names are separated by ;. I want to write a SQL query which sums up the count.
Eg. The result should be:
Hundley 2
Isler 1
Hunsberger 2
Edward 1
Ana 1
I could do a group by but this is not a simple group by as you can see. Any ideas/thoughts on how to get this output?
Edit: Changed results so it doesn't create any confusion that a row only contains 2 names.
You can take a look at this. I certainly do not recommend this way if you have lots of data, BUT you can do some modifications and use it and it works like a charm!
This is the new code for supporting unlimited splits:
Declare #Table Table (
Name Nvarchar(50)
);
Insert #Table (
Name
) Select 'Hundley; Edward; Anna'
Union Select 'Isler; Hunsberger'
Union Select 'Hunsberger; Hundley'
Union Select 'Anna'
;
With Result (
Part
, Remained
, [Index]
, Level
) As (
Select Case When CharIndex(';', Name, 1) = 0
Then Name
Else Left(Name, CharIndex(';', Name, 1) - 1)
End
, Right(Name, Len(Name) - CharIndex(';', Name, 1))
, CharIndex(';', Name, 1)
, 1
From #Table
Union All
Select LTrim(
Case When CharIndex(';', Remained, 1) = 0
Then Remained
Else Left(Remained, CharIndex(';', Remained, 1) - 1)
End
)
, Right(Remained, Len(Remained) - CharIndex(';', Remained, 1))
, CharIndex(';', Remained, 1)
, Level
+ 1
From Result
Where [Index] <> 0
) Select Part
, Count(*)
From Result
Group By Part
Cheers
;with cte as
(
select 1 as Item, 1 as Start, CHARINDEX(';',inventors, 1) as Split, Inventors from YourInventorsTable
union all
select cte.Item+1, cte.Split+1, nullif(CHARINDEX(';',inventors, cte.Split+1),0), inventors as Split
from cte
where cte.Split<>0
)
select rTRIM(lTRIM(SUBSTRING(inventors, start,isnull(split,len(inventors)+1)-start))), count(*)
from cte
group by rTRIM(lTRIM(SUBSTRING(inventors, start,isnull(split,len(inventors)+1)-start)))
You can create a split function to split the col values
select splittedValues.items,count(splittedValues) from table1
cross apply dbo.split(col1,';') splittedValues
group by splittedValues.items
DEMO in Sql fiddle
first make one function who take your comma or any other operator(;) separated string into one table and by using that temp table, apply GROUP function on that table.
So you will get count for separate value.
"select d.number,count(*) from (select number from dbo.CommaseparedListToTable('Hundley;Edward;Ana;Isler;Hunsberger;Hunsberger;Hundley',';'))d
group by d.number"
declare #text nvarchar(255) = 'Edward; Hundley; AnaIsler; Hunsberger; Hunsberger; Hundley ';
declare #table table(id int identity,name varchar(50));
while #text like '%;%'
Begin
insert into #table (name)
select SUBSTRING(#text,1,charindex(';',#text)-1)
set #text = SUBSTRING(#text, charindex(';',#text)+1,LEN(#text))
end
insert into #table (name)
select #text
select name , count(name ) counts from #table group by name
Output
name count
AnaIsler 1
Hundley 2
Hunsberger 2
Edward 1