/// <summary>
/// Calculate Text Edit Distance Utility Class
/// </summary>
public static class TextEditDistanceUtility
{
/// <summary>
/// get edit distance between two string
/// </summary>
/// <param name="str1"></param>
/// <param name="str2"></param>
/// <returns></returns>
public static int GetEditDistance(string str1, string str2)
{
if (str1 == str2) return 0;
else if (String.IsNullOrEmpty(str1) && String.IsNullOrEmpty(str2)) return 0;
else if (String.IsNullOrEmpty(str1) && !String.IsNullOrEmpty(str2)) return str2.Length;
else if (!String.IsNullOrEmpty(str1) && String.IsNullOrEmpty(str2)) return str1.Length;
int[,] d = new int[str1.Length + 1, str2.Length + 1];
d.Initialize();
int cost = 0;
for (int i = 0; i < d.GetLength(0); i++)
{
d[i, 0] = i;
}
for (int j = 0; j < d.GetLength(1); j++)
{
d[0, j] = j;
}
for (int i = 0; i < str1.Length; i++)
{
for (int j = 0; j < str2.Length; j++)
{
if (str1[i] == str2[j]) cost = 0;
else cost = 1;
d[i + 1, j + 1] = Math.Min(Math.Min(d[i, j + 1] + 1, d[i + 1, j] + 1), Math.Min(d[i + 1, j] + 1, d[i, j] + cost));
}
}
return d[str1.Length, str2.Length];
}
}
Edit Distance是比较两个字符串之间需要多少次基础操作才能变成对方的操作,增加一个字符,删除一个字符,修改一个字符,均算作一次操作
比如abb和bbb,编辑距离就是1,abc变成aa,编辑距离就是2
这个算法比较多的应用就是比较两次结果之间差别有多大