Masking ID and Name in SQL - sql

Question

I have a use case where there is a free text field and the user id in the format ab12345 (fixed) and name (dynamic) can appear anywhere in the string.
Now I need to replace the ab12345 with xxxxxxx and the names also with XXXX wherever I find them in the string.
I used:
select *
from dbo.TEST
WHERE DESCRIPTION like '%[a-zA-z][a-zA-Z][0-9][0-9][0-9][0-9][0-9]%';
to get the user id ab12345 but I am unable to write the replace function for this since the result is dynamic.
Same with the name as well.

Answer 1

the following may help in redacting the userID
USE tempdb
GO
CREATE TABLE #CustComments
( CustomerID INT
, CustomerNotes VARCHAR(8000)
)
GO
INSERT dbo.#CustComments
( CustomerID
, CustomerNotes
)
VALUES
( 1, 'An infraction was raised on user id ab12345, and the name of the complainant is John')
, ( 2, 'The customer was not happy with person CD45678 and is going to ask William Jones to speak with George Hillman about this matter' )
, ( 3, 'A customer called and repeatedly mentioned the name of employee ZX98765 and assumes their name was Janet which is not correct')
SELECT * ,
PATINDEX('%[a-zA-z][a-zA-Z][0-9][0-9][0-9][0-9][0-9]%', CustomerNotes) start_pos,
SUBSTRING (customernotes, (PATINDEX('%[a-zA-z][a-zA-Z][0-9][0-9][0-9][0-9][0-9]%', CustomerNotes)) ,7 ) extractstring,
REPLACE(customernotes, substring (customernotes, (PATINDEX('%[a-zA-z][a-zA-Z][0-9][0-9][0-9][0-9][0-9]%', CustomerNotes)) ,7 ), 'XXXXXXX') redacted
FROM #CustComments
--TIDY UP
DROP TABLE #CustComments

Answer 2

if you have or can create a table of "names"...this may work
USE tempdb
GO
CREATE TABLE #CustComments (
CustomerID int,
CustomerNotes varchar(8000)
)
GO
INSERT #CustComments (CustomerID
, CustomerNotes)
VALUES (1, 'An infraction was raised on user id ab12345 , and the name of the complainant is Ann')
, (2, 'The customer was not happy with person CD45678 and is going to ask Richard Jones to speak with Todd Hillman about this matter')
, (3, 'A customer called and repeatedly mentioned the name of employee ZX98765 and assumes their name was Shana which is not correct')
CREATE TABLE #empname (
ename varchar(255) NOT NULL
)
GO
INSERT INTO #empname ([ename])
VALUES ('Zeph'), ('Ebony'), ('Felicia'), ('Benedict'), ('Ahmed'), ('Ira'), ('Julie'), ('Levi'),
('Sebastian'), ('Fiona'), ('Lamar'), ('Russell'), ('Abdul'), ('Lev'), ('Isaiah'), ('Charlotte'),
('Rowan'), ('Ivory'), ('Quinn'), ('Jordan'), ('Xantha'), ('Shana'), ('Mufutau'), ('Jessamine'),
('Desirae'), ('Yvette'), ('Odessa'), ('Ray'), ('Ori'), ('Zenaida'), ('Allegra'), ('Allistair'),
('Raymond'), ('Martena'), ('Cameron'), ('Ila'), ('Nigel'), ('Dale'), ('Emerald'), ('Guinevere'),
('Boris'), ('Dolan'), ('Ainsley'), ('Madeson'), ('Kadeem'), ('Ciaran'), ('Hop'), ('Louis'),
('Maia'), ('Hiroko'), ('Hakeem'), ('Cole'), ('Tyrone'), ('Amy'), ('Doris'), ('Keaton'),
('Carlos'), ('Richard'), ('Lysandra'), ('Beverly'), ('Hamish'), ('Demetria'), ('Eric'), ('Nayda'),
('Sydney'), ('Fritz'), ('Blaze'), ('Regina'), ('Ciara'), ('Ina'), ('Joan'), ('Risa'),
('Alea'), ('Denton'), ('Daryl'), ('Mollie'), ('Keane'), ('Jarrod'), ('Ann'), ('Juliet'),
('Germaine'), ('Alexa'), ('Zane'), ('Kiona'), ('Armand'), ('Jin'), ('Geraldine'), ('Natalie'),
('Nomlanga'), ('Todd'), ('Rajah'),('Lucian'), ('Idona'), ('Autumn'), ('Briar'),
-- add surname
('Hillman');
;
-- redact the userID std format
SELECT
CustomerID ,
--PATINDEX('%[a-zA-z][a-zA-Z][0-9][0-9][0-9][0-9][0-9]%', CustomerNotes) start_pos,
--SUBSTRING (customernotes, (PATINDEX('%[a-zA-z][a-zA-Z][0-9][0-9][0-9][0-9][0-9]%', CustomerNotes)) ,7 ) extractstring,
REPLACE(customernotes, substring (customernotes, (PATINDEX('%[a-zA-z][a-zA-Z][0-9][0-9][0-9][0-9][0-9]%', CustomerNotes)) ,7 ), 'XXXXXXX') ID_redacted
INTO #ID_REDACT
FROM #CustComments
-- split into rows
SELECT customerId, value
into #SPLIT
FROM #ID_REDACT
CROSS APPLY STRING_SPLIT(ID_redacted, ' ');
--redact based on join with a ""name"" table
SELECT s.customerid,
CASE
WHEN e.ename IS NULL THEN s.value
ELSE 'XXXXXXX'
END AS name_redact
INTO #NAME_REDACT
FROM #split AS s
LEFT OUTER JOIN #empname AS e
ON s.value = e.ename
SELECT customerId,
STRING_AGG(name_redact, ' ') as full_redact
INTO #RESULTS
from #NAME_REDACT
group by CustomerID
-- RESULTS WITH COMPARISON
SELECT
C.CustomerID,
C.CustomerNotes AS Original,
R.full_redact AS Redacted
FROM #CustComments AS C
INNER JOIN #RESULTS AS R
ON C.CustomerID = R.customerId
--TIDY UP
DROP TABLE #CustComments
DROP TABLE #empname
DROP TABLE #ID_REDACT
DROP TABLE #SPLIT
DROP TABLE #NAME_REDACT
DROP TABLE #RESULTS