asp.NET 脏字过滤算法 修改版

复制代码 代码如下:

private Dictionary<string, object> hash = new Dictionary<string, object>();
private BitArray firstCharCheck = new BitArray(char.MaxValue);
private BitArray allCharCheck = new BitArray(char.MaxValue);
private int maxLength = 0;

复制代码 代码如下:

foreach (string word in badwords)
{
if (!hash.ContainsKey(word))
{
hash.Add(word, null);
maxlength = Math.Max(maxlength, word.Length);
firstCharCheck[word[0]] = true;

foreach (char c in word)
{
allCharCheck[c] = true;
}
}
}

复制代码 代码如下:

int index = 0;
int offset = 0;
while (index < text.Length)
{
if (!firstCharCheck[text[index]])
{
while (index < text.Length - 1 && !firstCharCheck[text[++index]]) ;
}

for (int j = 1; j <= Math.Min(maxlength, text.Length - index); j++)
{
if (!allCharCheck[text[index + j - 1]])
{
break;
}

string sub = text.Substring(index, j);

if (hash.ContainsKey(sub))
{
return true;
}
}

index++;
}

return false;