我对在T-SQL中计算Levenshtein距离的算法很感兴趣。
我对在T-SQL中计算Levenshtein距离的算法很感兴趣。
edit_distance_within
函数快近三个数量级,返回答案需要0.073秒(73毫秒)而不是55秒。它还具有内存效率,使用空间等于两个输入字符串中较大的一个加上一些常量空间。它使用一个表示列的单个nvarchar“数组”,并在其中进行所有计算,再加上一些辅助int变量。-- =============================================
-- Computes and returns the Levenshtein edit distance between two strings, i.e. the
-- number of insertion, deletion, and sustitution edits required to transform one
-- string to the other, or NULL if @max is exceeded. Comparisons use the case-
-- sensitivity configured in SQL Server (case-insensitive by default).
--
-- Based on Sten Hjelmqvist's "Fast, memory efficient" algorithm, described
-- at http://www.codeproject.com/Articles/13525/Fast-memory-efficient-Levenshtein-algorithm,
-- with some additional optimizations.
-- =============================================
CREATE FUNCTION [dbo].[Levenshtein](
@s nvarchar(4000)
, @t nvarchar(4000)
, @max int
)
RETURNS int
WITH SCHEMABINDING
AS
BEGIN
DECLARE @distance int = 0 -- return variable
, @v0 nvarchar(4000)-- running scratchpad for storing computed distances
, @start int = 1 -- index (1 based) of first non-matching character between the two string
, @i int, @j int -- loop counters: i for s string and j for t string
, @diag int -- distance in cell diagonally above and left if we were using an m by n matrix
, @left int -- distance in cell to the left if we were using an m by n matrix
, @sChar nchar -- character at index i from s string
, @thisJ int -- temporary storage of @j to allow SELECT combining
, @jOffset int -- offset used to calculate starting value for j loop
, @jEnd int -- ending value for j loop (stopping point for processing a column)
-- get input string lengths including any trailing spaces (which SQL Server would otherwise ignore)
, @sLen int = datalength(@s) / datalength(left(left(@s, 1) + '.', 1)) -- length of smaller string
, @tLen int = datalength(@t) / datalength(left(left(@t, 1) + '.', 1)) -- length of larger string
, @lenDiff int -- difference in length between the two strings
-- if strings of different lengths, ensure shorter string is in s. This can result in a little
-- faster speed by spending more time spinning just the inner loop during the main processing.
IF (@sLen > @tLen) BEGIN
SELECT @v0 = @s, @i = @sLen -- temporarily use v0 for swap
SELECT @s = @t, @sLen = @tLen
SELECT @t = @v0, @tLen = @i
END
SELECT @max = ISNULL(@max, @tLen)
, @lenDiff = @tLen - @sLen
IF @lenDiff > @max RETURN NULL
-- suffix common to both strings can be ignored
WHILE(@sLen > 0 AND SUBSTRING(@s, @sLen, 1) = SUBSTRING(@t, @tLen, 1))
SELECT @sLen = @sLen - 1, @tLen = @tLen - 1
IF (@sLen = 0) RETURN @tLen
-- prefix common to both strings can be ignored
WHILE (@start < @sLen AND SUBSTRING(@s, @start, 1) = SUBSTRING(@t, @start, 1))
SELECT @start = @start + 1
IF (@start > 1) BEGIN
SELECT @sLen = @sLen - (@start - 1)
, @tLen = @tLen - (@start - 1)
-- if all of shorter string matches prefix and/or suffix of longer string, then
-- edit distance is just the delete of additional characters present in longer string
IF (@sLen <= 0) RETURN @tLen
SELECT @s = SUBSTRING(@s, @start, @sLen)
, @t = SUBSTRING(@t, @start, @tLen)
END
-- initialize v0 array of distances
SELECT @v0 = '', @j = 1
WHILE (@j <= @tLen) BEGIN
SELECT @v0 = @v0 + NCHAR(CASE WHEN @j > @max THEN @max ELSE @j END)
SELECT @j = @j + 1
END
SELECT @jOffset = @max - @lenDiff
, @i = 1
WHILE (@i <= @sLen) BEGIN
SELECT @distance = @i
, @diag = @i - 1
, @sChar = SUBSTRING(@s, @i, 1)
-- no need to look beyond window of upper left diagonal (@i) + @max cells
-- and the lower right diagonal (@i - @lenDiff) - @max cells
, @j = CASE WHEN @i <= @jOffset THEN 1 ELSE @i - @jOffset END
, @jEnd = CASE WHEN @i + @max >= @tLen THEN @tLen ELSE @i + @max END
WHILE (@j <= @jEnd) BEGIN
-- at this point, @distance holds the previous value (the cell above if we were using an m by n matrix)
SELECT @left = UNICODE(SUBSTRING(@v0, @j, 1))
, @thisJ = @j
SELECT @distance =
CASE WHEN (@sChar = SUBSTRING(@t, @j, 1)) THEN @diag --match, no change
ELSE 1 + CASE WHEN @diag < @left AND @diag < @distance THEN @diag --substitution
WHEN @left < @distance THEN @left -- insertion
ELSE @distance -- deletion
END END
SELECT @v0 = STUFF(@v0, @thisJ, 1, NCHAR(@distance))
, @diag = @left
, @j = case when (@distance > @max) AND (@thisJ = @i + @lenDiff) then @jEnd + 2 else @thisJ + 1 end
END
SELECT @i = CASE WHEN @j > @jEnd + 1 THEN @sLen + 1 ELSE @i + 1 END
END
RETURN CASE WHEN @distance <= @max THEN @distance ELSE NULL END
END
如此函数的评论所述,字符比较的大小写敏感性将遵循当前生效的排序规则。默认情况下,SQL Server的排序规则会导致不区分大小写的比较。
要始终进行大小写敏感的比较,一种方法是在比较两个字符串的两个位置添加特定的排序规则。但是,我尚未对此进行彻底测试,特别是当数据库使用非默认排序规则时可能会产生副作用。
以下是如何更改这两行以强制进行大小写敏感的比较:
-- prefix common to both strings can be ignored
WHILE (@start < @sLen AND SUBSTRING(@s, @start, 1) = SUBSTRING(@t, @start, 1) COLLATE SQL_Latin1_General_Cp1_CS_AS)
并且
SELECT @distance =
CASE WHEN (@sChar = SUBSTRING(@t, @j, 1) COLLATE SQL_Latin1_General_Cp1_CS_AS) THEN @diag --match, no change
Arnold Fribble在sqlteam.com/forums上有两个提议:
这是来自2006年的更新版本:
SET QUOTED_IDENTIFIER ON
GO
SET ANSI_NULLS ON
GO
CREATE FUNCTION edit_distance_within(@s nvarchar(4000), @t nvarchar(4000), @d int)
RETURNS int
AS
BEGIN
DECLARE @sl int, @tl int, @i int, @j int, @sc nchar, @c int, @c1 int,
@cv0 nvarchar(4000), @cv1 nvarchar(4000), @cmin int
SELECT @sl = LEN(@s), @tl = LEN(@t), @cv1 = '', @j = 1, @i = 1, @c = 0
WHILE @j <= @tl
SELECT @cv1 = @cv1 + NCHAR(@j), @j = @j + 1
WHILE @i <= @sl
BEGIN
SELECT @sc = SUBSTRING(@s, @i, 1), @c1 = @i, @c = @i, @cv0 = '', @j = 1, @cmin = 4000
WHILE @j <= @tl
BEGIN
SET @c = @c + 1
SET @c1 = @c1 - CASE WHEN @sc = SUBSTRING(@t, @j, 1) THEN 1 ELSE 0 END
IF @c > @c1 SET @c = @c1
SET @c1 = UNICODE(SUBSTRING(@cv1, @j, 1)) + 1
IF @c > @c1 SET @c = @c1
IF @c < @cmin SET @cmin = @c
SELECT @cv0 = @cv0 + NCHAR(@c), @j = @j + 1
END
IF @cmin > @d BREAK
SELECT @cv1 = @cv0, @i = @i + 1
END
RETURN CASE WHEN @cmin <= @d AND @c <= @d THEN @c ELSE -1 END
END
GO
据我所知,在SQL Server 2005以及之后的版本中,您可以使用任何.NET语言编写存储过程:在 SQL Server 2005 中使用 CLR 集成。有了这个,编写一个用于计算Levenstein距离的存储过程就不难了。
从帮助中提取出来的一个简单的“Hello, World!”:
using System;
using System.Data;
using Microsoft.SqlServer.Server;
using System.Data.SqlTypes;
public class HelloWorldProc
{
[Microsoft.SqlServer.Server.SqlProcedure]
public static void HelloWorld(out string text)
{
SqlContext.Pipe.Send("Hello world!" + Environment.NewLine);
text = "Hello world!";
}
}
在你的 SQL Server 中运行以下代码:
CREATE ASSEMBLY helloworld from 'c:\helloworld.dll' WITH PERMISSION_SET = SAFE
CREATE PROCEDURE hello
@i nchar(25) OUTPUT
AS
EXTERNAL NAME helloworld.HelloWorldProc.HelloWorld
现在你可以进行测试运行:
DECLARE @J nchar(25)
EXEC hello @J out
PRINT @J
希望这可以帮到你。CREATE FUNCTION edit_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
(由Joseph Gama开发的函数)
用法:
select
dbo.edit_distance('Fuzzy String Match','fuzzy string match'),
dbo.edit_distance('fuzzy','fuzy'),
dbo.edit_distance('Fuzzy String Match','fuzy string match'),
dbo.edit_distance('levenshtein distance sql','levenshtein sql server'),
dbo.edit_distance('distance','server')
CREATE FUNCTION [dbo].[f_LevenshteinDistance](@s1 nvarchar(3999), @s2 nvarchar(3999))
RETURNS int
AS
BEGIN
DECLARE @s1_len int;
DECLARE @s2_len int;
DECLARE @i int;
DECLARE @j int;
DECLARE @s1_char nchar;
DECLARE @c int;
DECLARE @c_temp int;
DECLARE @cv0 varbinary(8000);
DECLARE @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;
SET @i = @i + 1;
WHILE @j <= @s2_len
BEGIN
SET @c = @c + 1;
IF @j <= @i
BEGIN
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;
END;
SELECT @cv0 = @cv0 + CAST(@c AS binary(2)), @j = @j + 1;
END;
SET @cv1 = @cv0;
END;
RETURN @c;
END;
我为Azure Synapse编写的修改(改用SET而不是SELECT):
-- =============================================
-- Computes and returns the Levenshtein edit distance between two strings, i.e. the
-- number of insertion, deletion, and sustitution edits required to transform one
-- string to the other, or NULL if @max is exceeded. Comparisons use the case-
-- sensitivity configured in SQL Server (case-insensitive by default).
--
-- Based on Sten Hjelmqvist's "Fast, memory efficient" algorithm, described
-- at http://www.codeproject.com/Articles/13525/Fast-memory-efficient-Levenshtein-algorithm,
-- with some additional optimizations.
-- =============================================
CREATE FUNCTION [db0].[Levenshtein](
@s nvarchar(4000)
, @t nvarchar(4000)
, @max int
)
RETURNS int
WITH SCHEMABINDING
AS
BEGIN
DECLARE @distance int = 0 -- return variable
, @v0 nvarchar(4000)-- running scratchpad for storing computed distances
, @start int = 1 -- index (1 based) of first non-matching character between the two string
, @i int, @j int -- loop counters: i for s string and j for t string
, @diag int -- distance in cell diagonally above and left if we were using an m by n matrix
, @left int -- distance in cell to the left if we were using an m by n matrix
, @sChar nchar -- character at index i from s string
, @thisJ int -- temporary storage of @j to allow SELECT combining
, @jOffset int -- offset used to calculate starting value for j loop
, @jEnd int -- ending value for j loop (stopping point for processing a column)
-- get input string lengths including any trailing spaces (which SQL Server would otherwise ignore)
, @sLen int = datalength(@s) / datalength(left(left(@s, 1) + '.', 1)) -- length of smaller string
, @tLen int = datalength(@t) / datalength(left(left(@t, 1) + '.', 1)) -- length of larger string
, @lenDiff int -- difference in length between the two strings
-- if strings of different lengths, ensure shorter string is in s. This can result in a little
-- faster speed by spending more time spinning just the inner loop during the main processing.
IF (@sLen > @tLen) BEGIN
SET @v0 = @s
SET @i = @sLen -- temporarily use v0 for swap
SET @s = @t
SET @sLen = @tLen
SET @t = @v0
SET @tLen = @i
END
SET @max = ISNULL(@max, @tLen)
SET @lenDiff = @tLen - @sLen
IF @lenDiff > @max RETURN NULL
-- suffix common to both strings can be ignored
WHILE(@sLen > 0 AND SUBSTRING(@s, @sLen, 1) = SUBSTRING(@t, @tLen, 1))
SET @sLen = @sLen - 1
SET @tLen = @tLen - 1
IF (@sLen = 0) RETURN @tLen
-- prefix common to both strings can be ignored
WHILE (@start < @sLen AND SUBSTRING(@s, @start, 1) = SUBSTRING(@t, @start, 1))
SET @start = @start + 1
IF (@start > 1) BEGIN
SET @sLen = @sLen - (@start - 1)
SET @tLen = @tLen - (@start - 1)
-- if all of shorter string matches prefix and/or suffix of longer string, then
-- edit distance is just the delete of additional characters present in longer string
IF (@sLen <= 0) RETURN @tLen
SET @s = SUBSTRING(@s, @start, @sLen)
SET @t = SUBSTRING(@t, @start, @tLen)
END
-- initialize v0 array of distances
SET @v0 = ''
SET @j = 1
WHILE (@j <= @tLen) BEGIN
SET @v0 = @v0 + NCHAR(CASE WHEN @j > @max THEN @max ELSE @j END)
SET @j = @j + 1
END
SET @jOffset = @max - @lenDiff
SET @i = 1
WHILE (@i <= @sLen) BEGIN
SET @distance = @i
SET @diag = @i - 1
SET @sChar = SUBSTRING(@s, @i, 1)
-- no need to look beyond window of upper left diagonal (@i) + @max cells
-- and the lower right diagonal (@i - @lenDiff) - @max cells
SET @j = CASE WHEN @i <= @jOffset THEN 1 ELSE @i - @jOffset END
SET @jEnd = CASE WHEN @i + @max >= @tLen THEN @tLen ELSE @i + @max END
WHILE (@j <= @jEnd) BEGIN
-- at this point, @distance holds the previous value (the cell above if we were using an m by n matrix)
SET @left = UNICODE(SUBSTRING(@v0, @j, 1))
SET @thisJ = @j
SET @distance =
CASE WHEN (@sChar = SUBSTRING(@t, @j, 1)) THEN @diag --match, no change
ELSE 1 + CASE WHEN @diag < @left AND @diag < @distance THEN @diag --substitution
WHEN @left < @distance THEN @left -- insertion
ELSE @distance -- deletion
END
END
SET @v0 = STUFF(@v0, @thisJ, 1, NCHAR(@distance))
SET @diag = @left
SET @j = case when (@distance > @max) AND (@thisJ = @i + @lenDiff)
then @jEnd + 2
else @thisJ + 1 end
END
SET @i = CASE WHEN @j > @jEnd + 1 THEN @sLen + 1 ELSE @i + 1 END
END
RETURN CASE WHEN @distance <= @max THEN @distance ELSE NULL END
END
1234 52 Ab CD
和261 Eafghci Jai CD
应该有一个距离为13。我从我的C#实现和在线计算器中得到了13,但执行此函数却给出了12。 - Dave Cousineau