The vendor data we load in our staging table is rather dirty. One column in particular captures number data but 40% of the time has garbage characters or random strings. >
WITH x (stringval) AS
(
VALUES ('x2'),(''),('2.2.'),('5-'),('-5-'),('--5'),('.5'),('2 2'),('0.5-'),(' 1 '),('2 '),('3.'),('-4.0')
)
SELECT stringval,
CASE WHEN (
-- Whitespace must not appear in the middle of a number
-- (but trailing and/or leading whitespace is permitted)
RTRIM(LTRIM( stringval )) NOT LIKE '% %'
-- A number cannot start with a decimal point
AND LTRIM( stringval ) NOT LIKE '.%'
-- A negative decimal number must contain at least one digit between
-- the negative sign and the decimal point
AND LTRIM( stringval ) NOT LIKE '-.%'
-- The negative sign may only appear at the beginning of the number
AND LOCATE( '-', LTRIM(stringval)) IN ( 0, 1 )
-- A number must contain at least one digit
AND TRANSLATE( stringval, '0000000000', '123456789') LIKE '%0%'
-- Allow up to one negative sign, followed by up to one decimal point
AND REPLACE(
TRANSLATE( RTRIM(LTRIM(stringval)), '000000000', '123456789'),
'0', '') IN ('','-','.','-.')
)
THEN 'VALID'
ELSE 'INVALID'
END AS stringisvalidnumber
FROM x
;