Levenshtein Distance,判断字符串的相似性

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
private int LevenshteinDistance(string s1,string s2,int maxValue)
{
    if (s1 == null|| s1.Length == 0) return maxValue;
    if (s2 == null|| s2.Length == 0) return maxValue;
    if (s1.Trim() == s2.Trim()) return 0;
    // create two work vectors of integer distances
    int[] v0 = new int[s2.Length + 1];
    int[] v1 = new int[s2.Length + 1];
    int[] vtemp;
    // initialize v0 (the previous row of distances)
    // this row is A[0][i]: edit distance for an empty s
    // the distance is just the number of characters to delete from t
    for (int i = 0; i < v0.Length; i++)
    {
        v0[i] = i;
    }
    for (int i = 0; i < s1.Length; i++)
    {
        // calculate v1 (current row distances) from the previous row v0
        // first element of v1 is A[i+1][0]
        //   edit distance is delete (i+1) chars from s to match empty t
        v1[0] = i + 1;
        // use formula to fill in the rest of the row
        for (int j = 0; j < s2.Length; j++)
        {
            int cost = 1;
            if (s1.Substring(i, 1) == s2.Substring(j, 1))
            {
                cost = 0;
            }
            v1[j + 1] = Math.Min(
                v1[j] + 1,              // Cost of insertion
                Math.Min(
                    v0[j + 1] + 1,  // Cost of remove
                    v0[j] + cost)); // Cost of substitution
        }
        // copy v1 (current row) to v0 (previous row) for next iteration
        //System.arraycopy(v1, 0, v0, 0, v0.length);
        // Flip references to current and previous row
        vtemp = v0;
        v0 = v1;
        v1 = vtemp;
    }
    return Math.Min(v0[s2.Length],maxValue);
}

  

posted @   PanPan003  阅读(274)  评论(0编辑  收藏  举报
编辑推荐:
· 没有源码,如何修改代码逻辑?
· 一个奇形怪状的面试题:Bean中的CHM要不要加volatile?
· [.NET]调用本地 Deepseek 模型
· 一个费力不讨好的项目,让我损失了近一半的绩效!
· .NET Core 托管堆内存泄露/CPU异常的常见思路
阅读排行:
· 微软正式发布.NET 10 Preview 1:开启下一代开发框架新篇章
· DeepSeek R1 简明指南:架构、训练、本地部署及硬件要求
· 没有源码,如何修改代码逻辑?
· NetPad:一个.NET开源、跨平台的C#编辑器
· 面试官:你是如何进行SQL调优的?
历史上的今天:
2016-08-29 数据库设计
点击右上角即可分享
微信分享提示