简单的字符串相似度计算

计算Levenshtein 距离,再和较长字符串求比率

代码
/// <summary>
/// Levenshtein Distance
/// </summary>
static class StringExt
{
/// <summary>
/// 计算两个字符串的差异距离
/// </summary>
/// <param name="source">来源字符串</param>
/// <param name="target">目标字符串</param>
/// <returns>字符串差距</returns>
public static int CalcDistance(this string source, string target)
{
int n = source.Length;
int m = target.Length;
if (m == 0) return n;
if (n == 0) return m;
var matrix
= new int[n + 1, m + 1];
for (int i = 1; i <= n; i++)
{
matrix[i,
0] = i;
}
for (int i = 1; i <= m; i++)
{
matrix[
0, i] = i;
}

for (int i = 1; i <= n; i++)
{
var si
= source[i - 1];
for (int j = 1; j <= m; j++)
{
var tj
= target[j - 1];

int cost;
if (si == tj)
cost
= 0;
else
cost
= 1;

int above = matrix[i - 1, j] + 1;
int left = matrix[i, j - 1] + 1;
int diag = matrix[i - 1, j - 1] + cost;
matrix[i, j]
= Math.Min(above, Math.Min(left, diag));
}
}
return matrix[n, m];
}

/// <summary>
/// 计算两个字符串的相似度
/// </summary>
/// <param name="source">来源字符串</param>
/// <param name="target">目标字符串</param>
/// <returns>相似度</returns>
public static double CalcSimilarity(this string source, string target)
{
int n = source.Length;
int m = target.Length;
if (n == 0 || m == 0)
return 0;
int distance = source.CalcDistance(target);
int max = Math.Max(n, m);
return 1.0 * (max - distance) / max;
}
}

 

posted @ 2010-12-19 15:05  heros  阅读(458)  评论(2编辑  收藏  举报