How can I retrieve first second and third word of a String in SQL? - sql

Question

I need a query which would extract the first second and third word of a string.
I have approximately 5 words in each row and I need only the first three words out of 5 in the same row (1 row). Example "ATV BDSG 232 continue with other words".
I need only the first three words together in one row (in the same row) like "ATV BDSG 232" as a first row. The table has about 1000 rows and at the end of it I should have 1000 rows again but each row should contain only the first three words of the string.
I found a query which works fine for extracting first two like "ATV BDSG" discussed in stack overflow. The query is
"SELECT SUBSTRING(field1, 0, CHARINDEX(' ', field1, CHARINDEX(' ', field1, 0)+1))
FROM Table"
Can we derive this for extracting first three words?
Thanks in advance

Answer 1

If you don't want to create a dedicated function, you can use successive CROSS APPLYs:
SELECT
T.s,
FirstSpace.i,
SecondSpace.j,
ThirdSpace.k,
CASE
When ThirdSpace.k > 0 THEN LEFT(T.s, Thirdspace.k - 1)
ELSE T.S
END AS Phrase
FROM t
CROSS APPLY (SELECT CHARINDEX(' ', T.s, 1)) AS FirstSpace(i)
CROSS APPLY (SELECT CHARINDEX(' ', T.S, FirstSpace.i + 1)) AS SecondSpace(j)
CROSS APPLY (SELECT CHARINDEX(' ', T.s, SecondSpace.j + 1)) AS ThirdSpace(k)
gives you the results you need:
| s | i | j | k | phrase |
|----------------------------------------|---|---|----|------------------|
| ATV BDSG 232 Continue with other words | 4 | 9 | 13 | ATV BDSG 232 |

Answer 2

Things are easy, SQL Server provide STRING_SPLIT() function make that too easy
DECLARE #Var VARCHAR(100) = 'ATV BDSG 232 Continue with other words';
SELECT Word
FROM
(
SELECT Value AS Word,
ROW_NUMBER()OVER(ORDER BY (SELECT NULL)) RN
FROM STRING_SPLIT(#Var, ' ')
) T
WHERE RN <= 3;
But since you are working on 2012 version, you need to define your own function.
You can also take the hard way, first you need to get the first word, then replace it with '' and get the second word, then do the same for the 3rd word as
DECLARE #Var VARCHAR(100) = 'ATV BDSG 232 Continue with other words';
WITH FW AS
(
SELECT LEFT(#Var, CHARINDEX(' ', #Var)) FirstWord
),
SW AS
(
SELECT LEFT(REPLACE(#Var, FirstWord, ''),
CHARINDEX(' ', REPLACE(#Var, FirstWord, ''))) SecondWord
FROM FW
)
SELECT FirstWord,
SecondWord,
LEFT(REPLACE(REPLACE(V, FirstWord, ''), SecondWord, ''),
CHARINDEX(' ', REPLACE(REPLACE(V, FirstWord, ''), SecondWord, ''))
) ThirdWord
FROM
(
SELECT *, #Var V
FROM FW CROSS APPLY SW
) T
Demo
UPDATE
If you want to select the three first words then simply
SELECT SUBSTRING(Str, 0, CHARINDEX(' ', Str, CHARINDEX(' ', Str, CHARINDEX(' ', Str, 0)+1)+1)) Words
FROM Strings
Demo

Answer 3

--make some test data
declare #test as nvarchar(100) = 'my test string for words';
select 1 id, cast('my test string for words' as nvarchar(max)) word into #test;
insert #test (id,word) values (2,'a b c d e f g hhh yyyyyy') ;
insert #test (id,word) values (3,' a required test string d e f g hhh yyyyyy') ;
insert #test (id,word) values (4,'a quick test') ;
insert #test (id,word) values (5,'a test') ;
insert #test (id,word) values (6,'last') ;
--break up letters, count the first 3 words
;WITH CTE AS (SELECT 1 x, substring(#test,1,1) charx
UNION ALL
SELECT X + 1, substring(#test,x + 1,1) from CTE WHERE x < len(#test)
)
select * from cte c3 where (SELECT count(0) cnt FROM CTE c1 JOIN CTE c2 on c1.x <= c3.x and c1.x + 1 = c2.x and c1.charx =' ' and c2.charx != ' ') < 3
;WITH tabx as (select id, cast(ltrim(word) as nvarchar(max)) 'word' from #test), --do some ltrim
CTE AS (
SELECT id, 1 x, substring(word,1,1) charx from tabx
UNION ALL
SELECT t.id, c.X + 1, substring(t.word,x + 1,1)
from tabx t
JOIN CTE c on c.id = t.id and x < len(t.word)
),
disj as
(select * from cte c3 where
(SELECT count(0) cnt
FROM CTE c1
JOIN CTE c2 on c1.id = c3.id and c1.id = c2.id and c1.x <= c3.x and c1.x + 1 = c2.x and c1.charx =' ' and c2.charx != ' '
) < 3
),
rj as
(select disj.id,disj.x, disj.charx z
from disj
where disj.x = 1
UNION ALL
select d.id, d.x, r.z + d.charx
FROM rj r
join disj d on r.id = d.id and r.x + 1 = d.x
)
select *
from rj r1
cross apply (select max(r2.x) TheRow from rj r2 where r1.id = r2.id) dq
where r1.x = dq.TheRow
order by r1.id;
--delete test data
drop table #test

Answer 4

/* This is not perfect - but interesting */
declare #t table (fullname varchar(100))
insert #t values('Mr Jones'),('Mrs Amy smith'),('Jim Smith'),('Dr Harry Web '),('Paul Fred andrew jones')
select fullname,
a.value as a ,
b.Value as b,
c.Value as c,
d.Value as d,
e.Value as e,
f.value as f
from #t
outer apply (select top 1 value from STRING_SPLIT(fullname, ' ')) a
outer apply (select top 1 value from STRING_SPLIT(fullname, ' ') where value not in (a.value )) b
outer apply (select top 1 value from STRING_SPLIT(fullname, ' ') where value not in (a.value,b.value ) ) c
outer apply (select top 1 value from STRING_SPLIT(fullname, ' ') where value not in (a.value,b.value,c.value )) d
outer apply (select top 1 value from STRING_SPLIT(fullname, ' ') where value not in (a.value,b.value,c.value,d.value) ) e
outer apply (select top 1 value from STRING_SPLIT(fullname, ' ') where value not in (a.value,b.value ,c.value,d.value,e.value) ) f

Answer 5

To Select First Word -
Select top 1 Ltrim(Rtrim(value)) FROM STRING_SPLIT(#input,' ')
To Select Only Second Word -
Select Ltrim(Rtrim(value)) from STRING_SPLIT(#input,' ') Order by (Select NULL) OFFSET 1 ROWS FETCH NEXT 1 ROWS ONLY