T-SQL Get percentage of character match of 2 strings

Question

Let's say I have a set of 2 words:

Alexander and Alecsander OR Alexander and Alegzander

Alexander and Aleaxnder, or any other combination. In general we are talking about human error in typing of a word or a set of words.

What I want to achieve is to get the percentage of matching of the characters of the 2 strings.

Here is what I have so far:

    DECLARE @table1 TABLE
(
  nr INT
  , ch CHAR
)

DECLARE @table2 TABLE
(
  nr INT
  , ch CHAR
)


INSERT INTO @table1
SELECT nr,ch FROM  [dbo].[SplitStringIntoCharacters] ('WORD w') --> return a table of characters(spaces included)

INSERT INTO @table2
SELECT nr,ch FROM  [dbo].[SplitStringIntoCharacters] ('WORD 5')

DECLARE @resultsTable TABLE
( 
 ch1 CHAR
 , ch2 CHAR
)
INSERT INTO @resultsTable
SELECT DISTINCt t1.ch ch1, t2.ch ch2 FROM @table1 t1
FULL JOIN @table2 t2 ON  t1.ch = t2.ch  --> returns both matches and missmatches

SELECT * FROM @resultsTable
DECLARE @nrOfMathches INT, @nrOfMismatches INT, @nrOfRowsInResultsTable INT
SELECT  @nrOfMathches = COUNT(1) FROM  @resultsTable WHERE ch1 IS NOT NULL AND ch2 IS NOT NULL
SELECT @nrOfMismatches = COUNT(1) FROM  @resultsTable WHERE ch1 IS NULL OR ch2 IS NULL


SELECT @nrOfRowsInResultsTable = COUNT(1)  FROM @resultsTable


SELECT @nrOfMathches * 100 / @nrOfRowsInResultsTable

The SELECT * FROM @resultsTable will return the following:

ch1         ch2
NULL        5
[blank]     [blank] 
D           D
O           O
R           R
W           W

Answer 1

Ok, here is my solution so far:

SELECT  [dbo].[GetPercentageOfTwoStringMatching]('valentin123456'  ,'valnetin123456')

returns 86%

CREATE FUNCTION [dbo].[GetPercentageOfTwoStringMatching]
(
    @string1 NVARCHAR(100)
    ,@string2 NVARCHAR(100)
)
RETURNS INT
AS
BEGIN

    DECLARE @levenShteinNumber INT

    DECLARE @string1Length INT = LEN(@string1)
    , @string2Length INT = LEN(@string2)
    DECLARE @maxLengthNumber INT = CASE WHEN @string1Length > @string2Length THEN @string1Length ELSE @string2Length END

    SELECT @levenShteinNumber = [dbo].[LEVENSHTEIN] (   @string1  ,@string2)

    DECLARE @percentageOfBadCharacters INT = @levenShteinNumber * 100 / @maxLengthNumber

    DECLARE @percentageOfGoodCharacters INT = 100 - @percentageOfBadCharacters

    -- Return the result of the function
    RETURN @percentageOfGoodCharacters

END




-- =============================================     
-- Create date: 2011.12.14
-- Description: http://blog.sendreallybigfiles.com/2009/06/improved-t-sql-levenshtein-distance.html
-- =============================================

CREATE FUNCTION [dbo].[LEVENSHTEIN](@left  VARCHAR(100),
                                    @right VARCHAR(100))
returns INT
AS
  BEGIN
      DECLARE @difference    INT,
              @lenRight      INT,
              @lenLeft       INT,
              @leftIndex     INT,
              @rightIndex    INT,
              @left_char     CHAR(1),
              @right_char    CHAR(1),
              @compareLength INT

      SET @lenLeft = LEN(@left)
      SET @lenRight = LEN(@right)
      SET @difference = 0

      IF @lenLeft = 0
        BEGIN
            SET @difference = @lenRight

            GOTO done
        END

      IF @lenRight = 0
        BEGIN
            SET @difference = @lenLeft

            GOTO done
        END

      GOTO comparison

      COMPARISON:

      IF ( @lenLeft >= @lenRight )
        SET @compareLength = @lenLeft
      ELSE
        SET @compareLength = @lenRight

      SET @rightIndex = 1
      SET @leftIndex = 1

      WHILE @leftIndex <= @compareLength
        BEGIN
            SET @left_char = substring(@left, @leftIndex, 1)
            SET @right_char = substring(@right, @rightIndex, 1)

            IF @left_char <> @right_char
              BEGIN -- Would an insertion make them re-align?
                  IF( @left_char = substring(@right, @rightIndex + 1, 1) )
                    SET @rightIndex = @rightIndex + 1
                  -- Would an deletion make them re-align?
                  ELSE IF( substring(@left, @leftIndex + 1, 1) = @right_char )
                    SET @leftIndex = @leftIndex + 1

                  SET @difference = @difference + 1
              END

            SET @leftIndex = @leftIndex + 1
            SET @rightIndex = @rightIndex + 1
        END

      GOTO done

      DONE:

      RETURN @difference
  END