Extract email address from string using tsql

Question

I\'m trying to extract email addresses from an existing comments field and put it into its own column. The string may be something like this \"this is an example comment wit

Answer 1

DECLARE @t TABLE (row_id INT, email VARCHAR(100))

INSERT @t (row_id, email)
VALUES (1, 'drgkls, info@gvi.com, @ dgh507-16-65@'),
        (2, 'hjshfkjshfj@kjs.kjsehf herwfjewr@kjsd.com adjfhja@.com u3483dhj@hhb@.dfj'),
        (3, 'kjsdghfjs4254.23detygh@jhjdfg.dgb лдоврывплдоо isgfsi@ klsdfksdl@,dd.com')

DECLARE @pat VARCHAR(100) = '%[^a-z0-9@._ ]%';

WITH f AS (
         SELECT    row_id,
                 CAST(' ' + email + ' ' AS VARCHAR(102)) email,
                 SUBSTRING(email, PATINDEX(@pat, email), 1) bad,
                 PATINDEX(@pat, email) pat
         FROM    @t
         UNION ALL
         SELECT    row_id,
                 CAST(REPLACE(email, bad, ' ') AS VARCHAR(102)),
                 SUBSTRING(REPLACE(email, bad, ' '), PATINDEX(@pat, REPLACE(email, bad, ' ')), 1) bad,
                 PATINDEX(@pat, REPLACE(email, bad, ' '))
         FROM    f
         WHERE    PATINDEX(@pat, email) > 0
     ),
     s AS 
     (
         SELECT    row_id,
                 email, PATINDEX('%@%', email) pos 
         FROM    f 
         WHERE    pat = 0
                 AND    PATINDEX('%@%', email) > 0
         UNION ALL
         SELECT    row_id,
                 SUBSTRING(email, pos + 1, 102), 
                 PATINDEX('%@%', SUBSTRING(email, pos + 1, 102))
         FROM    s
         WHERE    PATINDEX('%@%', SUBSTRING(email, pos + 1, 102)) > 0
     )

SELECT  row_id, o1 + pp
FROM    s   
        CROSS APPLY (SELECT    REVERSE(LEFT(email, pos -1)) s1) x
        CROSS APPLY (SELECT    CHARINDEX(' ', s1) i1) y
        CROSS APPLY (SELECT    REVERSE(LEFT(s1, i1 -1)) o1 WHERE i1 > 0) z
        CROSS APPLY (SELECT    CHARINDEX(' ', email, pos) i2) e
        CROSS APPLY (SELECT    SUBSTRING(email, pos, i2 -pos) pp WHERE    i2 > pos + 1) q
WHERE    LEN(o1) > 1
        AND CHARINDEX('.', pp) > 0
        AND PATINDEX('%@%@%', pp) = 0
        AND PATINDEX('%@.%', pp) = 0
        AND PATINDEX('%.', pp) = 0