c# - 清洁绳子？有没有更好的方法呢？

Question

我正在使用这种方法来清理字符串

public static string CleanString(string dirtyString)
{
    string removeChars = " ?&^$#@!()+-,:;<>’\'-_*";
    string result = dirtyString;

    foreach (char c in removeChars)
    {
        result = result.Replace(c.ToString(), string.Empty);
    }

    return result;
}

此方法工作正常。但是此方法存在性能故障。每次我传递字符串时，每个字符都会进入循环，如果我有一个大字符串，那么返回对象会花费太多时间。

有没有其他更好的方法来做同样的事情？就像在 LINQ 或 JQUERY/Javascript 中一样

如有任何建议，我们将不胜感激。

Answer 1

好的，考虑下面的测试:

public class CleanString
{
    //by MSDN http://msdn.microsoft.com/en-us/library/844skk0h(v=vs.71).aspx
    public static string UseRegex(string strIn)
    {
        // Replace invalid characters with empty strings.
        return Regex.Replace(strIn, @"[^\w\.@-]", "");
    }

    // by Paolo Tedesco
    public static String UseStringBuilder(string strIn)
    {
        const string removeChars = " ?&^$#@!()+-,:;<>’\'-_*";
        // specify capacity of StringBuilder to avoid resizing
        StringBuilder sb = new StringBuilder(strIn.Length);
        foreach (char x in strIn.Where(c => !removeChars.Contains(c)))
        {
            sb.Append(x);
        }
        return sb.ToString();
    }

    // by Paolo Tedesco, but using a HashSet
    public static String UseStringBuilderWithHashSet(string strIn)
    {
        var hashSet = new HashSet<char>(" ?&^$#@!()+-,:;<>’\'-_*");
        // specify capacity of StringBuilder to avoid resizing
        StringBuilder sb = new StringBuilder(strIn.Length);
        foreach (char x in strIn.Where(c => !hashSet.Contains(c)))
        {
            sb.Append(x);
        }
        return sb.ToString();
    }

    // by SteveDog
    public static string UseStringBuilderWithHashSet2(string dirtyString)
    {
        HashSet<char> removeChars = new HashSet<char>(" ?&^$#@!()+-,:;<>’\'-_*");
        StringBuilder result = new StringBuilder(dirtyString.Length);
        foreach (char c in dirtyString)
            if (removeChars.Contains(c))
                result.Append(c);
        return result.ToString();
    }

    // original by patel.milanb
    public static string UseReplace(string dirtyString)
    {
        string removeChars = " ?&^$#@!()+-,:;<>’\'-_*";
        string result = dirtyString;

        foreach (char c in removeChars)
        {
            result = result.Replace(c.ToString(), string.Empty);
        }

        return result;
    }

    // by L.B
    public static string UseWhere(string dirtyString)
    {
        return new String(dirtyString.Where(Char.IsLetterOrDigit).ToArray());
    }
}

static class Program
{
    /// <summary>
    /// The main entry point for the application.
    /// </summary>
    [STAThread]
    static void Main()
    {
        var dirtyString = "sdfdf.dsf8908()=(=(sadfJJLef@ssyd€sdöf////fj()=/§(§&/(\"&sdfdf.dsf8908()=(=(sadfJJLef@ssyd€sdöf////fj()=/§(§&/(\"&sdfdf.dsf8908()=(=(sadfJJLef@ssyd€sdöf";
        var sw = new Stopwatch();

        var iterations = 50000;

        sw.Start();
        for (var i = 0; i < iterations; i++)
            CleanString.<SomeMethod>(dirtyString);
        sw.Stop();
        Debug.WriteLine("CleanString.<SomeMethod>: " + sw.ElapsedMilliseconds.ToString());
        sw.Reset();

        ....
        <repeat>
        ....       
    }
}

---

输出

CleanString.UseReplace: 791
CleanString.UseStringBuilder: 2805
CleanString.UseStringBuilderWithHashSet: 521
CleanString.UseStringBuilderWithHashSet2: 331
CleanString.UseRegex: 1700
CleanString.UseWhere: 233

---

结论

使用哪种方法可能无关紧要。

当连续调用 50000(!) 次时，禁食(UseWhere:233ms)和最慢(UseStringBuilder:2805ms)方法之间的时间差为 2572ms .如果不经常运行该方法，您可能不需要关心它。

但是如果你这样做，使用UseWhere方法(L.B写的)；但也要注意它略有不同。