#title Levenshtein Distance

'리벤슈타인 거리'라고 읽는다. [http://jzcafe.blogspot.kr/2012/05/levenshtein-distance.html?utm_source=feedburner&utm_medium=feed&utm_campaign=Feed:+blogspot/OyMV+(Full+of+Aroma+%26+Bouquet) 여기]에 아주 자세히 설명되어 있다.

R소스
{{{
library(vwr)
levenshtein.distance('cat', 'hat')
levenshtein.distance('cat', 'catwalk')
levenshtein.distance('catwalk', 'sidewalk')

EW = english.words
ew1 = sample(EW, 20)
dx = levenshtein.distance('cat', ew1)
}}}

T-SQL소스
{{{
CREATE FUNCTION levenshtein_distance(@s1 nvarchar(3999), @s2 nvarchar(3999))
RETURNS int
AS
BEGIN
 DECLARE @s1_len int, @s2_len int
 DECLARE @i int, @j int, @s1_char nchar, @c int, @c_temp int
 DECLARE @cv0 varbinary(8000), @cv1 varbinary(8000)

 SELECT
  @s1_len = LEN(@s1),
  @s2_len = LEN(@s2),
  @cv1 = 0x0000,
  @j = 1, @i = 1, @c = 0

 WHILE @j <= @s2_len
  SELECT @cv1 = @cv1 + CAST(@j AS binary(2)), @j = @j + 1

 WHILE @i <= @s1_len
 BEGIN
  SELECT
   @s1_char = SUBSTRING(@s1, @i, 1),
   @c = @i,
   @cv0 = CAST(@i AS binary(2)),
   @j = 1

  WHILE @j <= @s2_len
  BEGIN
   SET @c = @c + 1
   SET @c_temp = CAST(SUBSTRING(@cv1, @j+@j-1, 2) AS int) +
    CASE WHEN @s1_char = SUBSTRING(@s2, @j, 1) THEN 0 ELSE 1 END
   IF @c > @c_temp SET @c = @c_temp
   SET @c_temp = CAST(SUBSTRING(@cv1, @j+@j+1, 2) AS int)+1
   IF @c > @c_temp SET @c = @c_temp
   SELECT @cv0 = @cv0 + CAST(@c AS binary(2)), @j = @j + 1
 END

 SELECT @cv1 = @cv0, @i = @i + 1
 END

 RETURN @c
END
}}}
--http://www.kodyaz.com/articles/fuzzy-string-matching-using-levenshtein-distance-sql-server.aspx

{{{
select
    dbo.levenshtein_distance('cat', 'hat'),
    dbo.levenshtein_distance('cat', 'catwalk'),
    dbo.levenshtein_distance('catwalk', 'sidewalk')
}}}