字符相似度算法及应用

最新推荐文章于 2021-03-26 16:25:12 发布

牧马人xxx

最新推荐文章于 2021-03-26 16:25:12 发布

阅读量288

点赞数

分类专栏：语言编程问题

语言编程问题专栏收录该内容

39 篇文章 0 订阅

订阅专栏

应用场景
配置映射时，每次均要都待配置的列表里面去搜索去对应，效率低下且非常麻烦，采用相似度，可以自动过滤相似的部分，快速实现映射配置。

举例：

算法代码：

C#代码
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
namespace Tech.Tools.Common
{
/// <summary>
/// 计算两个字符串相似度管理类(算法是由俄国科学家Levenshtein提出)
/// </summary>
public class StrSimilarityDegreeParser
{
/// <summary>
/// 返回两个字符串相似度
/// </summary>
/// <param name="str1"></param>
/// <param name="str2"></param>
/// <returns></returns>
public float LevenshteinDistancePercent(String str1, String str2)
{
int maxLenth = str1.Length > str2.Length ? str1.Length : str2.Length;
int val = Levenshtein_Distance(str1, str2);
return 1 - float.Parse(val.ToString()) / maxLenth;
}
/**
*取最小的一位数
* @param first
* @param second
* @param third
* @return
*
*/
private int LowerOfThree(int first, int second, int third)
{
int min = first;
if (second < min)
min = second;
if (third < min)
min = third;
return min;
}
private int Levenshtein_Distance(String str1, String str2)
{
int n = str1.Length;
int m = str2.Length;
int[][] Matrix = new int[n + 1][];
int temp = 0;
char ch1;
char ch2;
int i = 0;
int j = 0;
if (n == 0)
{
return m;
}
if (m == 0)
{
return n;
}
for (i = 0; i <= n; i++)
{
Matrix[i] = new int[m + 1];
for (j = 0; j <= m; j++)
{
if (j == 0)
{
Matrix[i][j] = i;
}
else if (i == 0)
{
Matrix[i][j] = j;
}
}
}
for (i = 1; i <= n; i++)
{
ch1 = str1.ToCharArray()[i - 1];
for (j = 1; j <= m; j++)
{
ch2 = str2.ToCharArray()[j - 1];
if (ch1 == ch2)
{
temp = 0;
}
else
{
temp = 1;
}
Matrix[i][j] = LowerOfThree(Matrix[i - 1][j] + 1, Matrix[i][j - 1] + 1, Matrix[i - 1][j - 1] + temp);
}
}
return Matrix[n][m];
}
}
}

复制代码

Delphi代码
function LowerOfThree(nFirst,nSecond,nThird:Integer):Integer;
var
nMin:Integer;
begin
nMin := nFirst;
if nSecond < nMin then nMin := nSecond;
if nThird < nMin then nMin := nThird;
Result := nMin;
end;
//------------------------------------------------------------------------------
function Levenshtein_Distance(Str1:WideString;Str2:WideString):Integer;
var
n,m,i,j,temp:Integer;
char1,char2:WideString;
Matrix:array of array of Integer;
begin
n := Length(Str1);m := Length(Str2);
if n=0 then
begin
Result := m;
Exit;
end;
if m=0 then
begin
Result := n;
Exit;
end;
SetLength(Matrix,n+1,m+1);
temp := 0; i := 0; j := 0;
for i := 0 to n do
begin
for j:=0 to m do
begin
if j=0 then Matrix[i][j] := i
else if i=0 then Matrix[i][j] := j;
end;
end;
for i := 1 to n do
begin
char1 := Copy(Str1,i,1);
for j:=1 to m do
begin
char2 := Copy(Str2,j,1);
if char1 = char2 then temp := 0
else temp := 1;
Matrix[i][j] := LowerOfThree(Matrix[i-1][j]+1,Matrix[i][j-1]+1,Matrix[i-1][j-1]+temp);
end;
end;
Result := Matrix[n][m];
end;
//------------------------------------------------------------------------------
function LevenshteinDistancePercent(Str1:WideString;Str2:WideString):Real;
var
nMaxLen,Val:Integer;
begin
if Length(Str1) > Length(Str2) then nMaxLen := Length(Str1)
else nMaxLen := Length(Str2);
Val := Levenshtein_Distance(Str1,Str2);
Result := 1- (Val * 1.0)/(nMaxLen*1.0);
end;
//------------------------------------------------------------------------------
--调用示例
procedure TFrmMainForm.CompareDataSet(Str1: String);
var
Str2:WideString;
nResult:Real;
begin
cdsPlat.DisableControls;
cdsPlat.Filtered := False;
if cdsPlat.IsEmpty then Exit;
try
cdsPlat.First;
while not cdsPlat.Eof do
begin
Str2 := cdsPlat.FieldByName('ITEMNAME').AsString;
nResult := LevenshteinDistancePercent(Str1,Str2);
cdsPlat.Edit;
cdsPlat.FieldByName('LIKEBYTE').AsFloat := nResult*100;
cdsPlat.Post;
cdsPlat.Next;
end;
finally
cdsPlat.EnableControls;
end;
end;