Character-by-character comparison strings in sql - sql-server

Question

How to compare the strings on characters, check that the strings consist of the same symbols using T-SQL?
For example:
'aaabbcd' vs 'ddbca' (TRUE): both strings consist of the same symbols
'abcddd' vs 'cda' (FALSE): both strings do not consist of the same symbols

Answer 1

If performance is important then I would suggest a purely set-based solution using Ngrams8k.
This will give you the correct answer:
SELECT AllSame = COALESCE(MAX(0),1)
FROM dbo.ngrams8k(#string1, 1) ng1
FULL JOIN dbo.ngrams8k(#string2, 1) ng2 ON ng1.token = ng2.token
WHERE ng1.token IS NULL OR ng2.token IS NULL;
To use this logic against a table you could use CROSS APPLY like so:
-- Sample data
DECLARE #table TABLE (string1 varchar(100), string2 varchar(100));
INSERT #table VALUES ('aaabbcd','ddbca'),('abcddd','cda');
-- Solution using CROSS APPLY
SELECT *
FROM #table t
CROSS APPLY
(
SELECT AllSame = COALESCE(MAX(0),1)
FROM dbo.ngrams8k(t.string1, 1) ng1
FULL JOIN dbo.ngrams8k(t.string2, 1) ng2 ON ng1.token = ng2.token
WHERE ng1.token IS NULL OR ng2.token IS NULL
) x;
Results:
string1 string2 AllSame
--------- --------- --------
aaabbcd ddbca 1
abcddd cda 0
Not only will this be the fastest solution presented thus far, notice that we're getting the job done with as little code possible.
UPDATE TO INCLUDE COMPARE PERFORMANCE TO MARTIN SMITH'S SOLUTION
-- sample data
IF OBJECT_ID('tempdb..#sample') IS NOT NULL DROP TABLE #sample;
SELECT TOP (10000)
string1 = replicate('a',abs(checksum(newid())%5))+replicate('b',abs(checksum(newid())%4))+
replicate('c',abs(checksum(newid())%5))+replicate('d',abs(checksum(newid())%4))+
replicate('e',abs(checksum(newid())%5))+replicate('f',abs(checksum(newid())%4)),
string2 = replicate('a',abs(checksum(newid())%5))+replicate('b',abs(checksum(newid())%4))+
replicate('c',abs(checksum(newid())%5))+replicate('d',abs(checksum(newid())%4))+
replicate('e',abs(checksum(newid())%5))+replicate('f',abs(checksum(newid())%4))
INTO #sample
FROM sys.all_columns a, sys.all_columns b;
SET NOCOUNT ON;
SET STATISTICS TIME ON;
PRINT 'ajb serial'+char(10)+replicate('-',50);
SELECT flag
FROM #sample t
CROSS APPLY
(
SELECT Flag = COALESCE(MAX(0),1)
FROM dbo.ngrams8k(t.string1, 1) ng1
FULL JOIN dbo.ngrams8k(t.string2, 1) ng2 ON ng1.token = ng2.token
WHERE ng1.token IS NULL OR ng2.token IS NULL
) x
OPTION (MAXDOP 1);
PRINT 'ajb parallel'+char(10)+replicate('-',50);
SELECT flag
FROM #sample t
CROSS APPLY
(
SELECT Flag = COALESCE(MAX(0),1)
FROM dbo.ngrams8k(t.string1, 1) ng1
FULL JOIN dbo.ngrams8k(t.string2, 1) ng2 ON ng1.token = ng2.token
WHERE ng1.token IS NULL OR ng2.token IS NULL
) x
OPTION (querytraceon 8649);
PRINT 'M Smith - serial'+char(10)+replicate('-',50);
WITH Nums AS
(
SELECT TOP (100) ROW_NUMBER() OVER ( ORDER BY (SELECT NULL)) number
FROM sys.all_columns
)
SELECT flag
FROM #sample T
CROSS APPLY (SELECT CASE WHEN Min(Cnt) = 2 THEN 1 ELSE 0 END AS Flag
FROM (SELECT Count(*) AS Cnt
FROM (SELECT 1 AS s,
Substring(t.string1, N1.number, 1) AS c
FROM Nums N1
WHERE N1.number <= Len(t.string1)
UNION
SELECT 2 AS s,
Substring(t.string2, N2.number, 1) AS c
FROM Nums N2
WHERE N2.number <= Len(t.string2)) D1
GROUP BY c) D2
) Ca
OPTION (MAXDOP 1);
SET STATISTICS TIME OFF;
Results:
ajb serial
--------------------------------------------------
SQL Server Execution Times:
CPU time = 656 ms, **elapsed time = 660 ms**.
ajb parallel
--------------------------------------------------
SQL Server Execution Times:
CPU time = 1281 ms, **elapsed time = 204 ms**.
M Smith serial
--------------------------------------------------
SQL Server Execution Times:
CPU time = 1390 ms, **elapsed time = 1393 ms**.
Note that I did not test Martin's solution with a parallel plan because, as is, that query cannot run in parallel.

Answer 2

An inline method.
This uses a numbers table
CREATE TABLE dbo.Numbers (number INT PRIMARY KEY);
INSERT INTO dbo.Numbers
SELECT TOP 8000 ROW_NUMBER() OVER (ORDER BY ##SPID)
FROM sys.all_columns c1,
sys.all_columns c2
A version without but with lesser performance is in the edit history if you'd prefer trading off performance against not having to use one.
WITH T(S1, S2)
AS (SELECT 'aaabbcd',
'ddbca'
UNION ALL
SELECT 'abcddd',
'cda')
SELECT *
FROM T
CROSS APPLY (SELECT CASE WHEN Min(Cnt) = 2 THEN 1 ELSE 0 END AS Flag
FROM (SELECT Count(*) AS Cnt
FROM (SELECT 1 AS s,
Substring(S1, N1.number, 1) AS c
FROM dbo.Numbers N1
WHERE N1.number <= Len(S1)
UNION
SELECT 2 AS s,
Substring(S2, N2.number, 1) AS c
FROM dbo.Numbers N2
WHERE N2.number <= Len(S2)) D1
GROUP BY c) D2
) Ca

Answer 3

You can use this'%your-search-string%' to find your string contains any substring.
SELECT * FROM TableName
WHERE Name LIKE '%searchText%'
You can use the stored procedure for checking that characters of the string.
CREATE PROCEDURE IsStringMatching
(
#originalString NVARCHAR(32) ,
#stringToBeChecked NVARCHAR(32),
#IsMatching BIT OUTPUT
)
AS
BEGIN
DECLARE #inputStringCount INT = LEN(#originalString);
DECLARE #loopCount INT = 0, #temp INT;
DECLARE #char VARCHAR;
SET #IsMatching = 1
WHILE #loopCount < #inputStringCount
BEGIN
SET #char = SUBSTRING(#originalString,#loopCount+1,1);
SET #temp = CHARINDEX(#char, #stringToBeChecked,1);
IF(#temp = 0)
BEGIN
SET #IsMatching = 0;
BREAK;
END
SET #loopCount = #loopCount + 1;
END;
END
You can validate like this:
DECLARE #IsMatching BIT;
SELECT EXECUTE IsStringMatchingQ 'aaabbcd', 'ABC';
SELECT #IsMatching