您不需要正则表达式来清除非字母。这将删除所有非 Unicode 字母。
public string RemoveNonUnicodeLetters(string input)
{
StringBuilder sb = new StringBuilder();
foreach(char c in input)
{
if(Char.IsLetter(c))
sb.Append(c);
}
return sb.ToString();
}
或者,如果你只想允许拉丁字母,你可以使用这个
public string RemoveNonLatinLetters(string input)
{
StringBuilder sb = new StringBuilder();
foreach(char c in input)
{
if(c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z')
sb.Append(c);
}
return sb.ToString();
}
基准与正则表达式
public static string RemoveNonUnicodeLetters(string input)
{
StringBuilder sb = new StringBuilder();
foreach (char c in input)
{
if (Char.IsLetter(c))
sb.Append(c);
}
return sb.ToString();
}
static readonly Regex nonUnicodeRx = new Regex("\\P{L}");
public static string RemoveNonUnicodeLetters2(string input)
{
return nonUnicodeRx.Replace(input, "");
}
static void Main(string[] args)
{
Stopwatch sw = new Stopwatch();
StringBuilder sb = new StringBuilder();
//generate guids as input
for (int j = 0; j < 1000; j++)
{
sb.Append(Guid.NewGuid().ToString());
}
string input = sb.ToString();
sw.Start();
for (int i = 0; i < 1000; i++)
{
RemoveNonUnicodeLetters(input);
}
sw.Stop();
Console.WriteLine("SM: " + sw.ElapsedMilliseconds);
sw.Restart();
for (int i = 0; i < 1000; i++)
{
RemoveNonUnicodeLetters2(input);
}
sw.Stop();
Console.WriteLine("RX: " + sw.ElapsedMilliseconds);
}
输出(SM = 字符串操作,RX = 正则表达式)
SM: 581
RX: 9882
SM: 545
RX: 9557
SM: 664
RX: 10196