我需要一个强大的和简单的方法来删除非法的路径和文件字符从一个简单的字符串。我已经使用了下面的代码,但它似乎没有做任何事情,我错过了什么?

using System;
using System.IO;

namespace ConsoleApplication1
{
    class Program
    {
        static void Main(string[] args)
        {
            string illegal = "\"M<>\"\\a/ry/ h**ad:>> a\\/:*?\"<>| li*tt|le|| la\"mb.?";

            illegal = illegal.Trim(Path.GetInvalidFileNameChars());
            illegal = illegal.Trim(Path.GetInvalidPathChars());

            Console.WriteLine(illegal);
            Console.ReadLine();
        }
    }
}

当前回答

这是我的一点小小的贡献。在同一字符串中替换而不创建新字符串或stringbuilder的方法。它快速,易于理解,是本文中所有提到的一个很好的选择。

private static HashSet<char> _invalidCharsHash;
private static HashSet<char> InvalidCharsHash
{
  get { return _invalidCharsHash ?? (_invalidCharsHash = new HashSet<char>(Path.GetInvalidFileNameChars())); }
}

private static string ReplaceInvalidChars(string fileName, string newValue)
{
  char newChar = newValue[0];

  char[] chars = fileName.ToCharArray();
  for (int i = 0; i < chars.Length; i++)
  {
    char c = chars[i];
    if (InvalidCharsHash.Contains(c))
      chars[i] = newChar;
  }

  return new string(chars);
}

你可以这样调用它:

string illegal = "\"M<>\"\\a/ry/ h**ad:>> a\\/:*?\"<>| li*tt|le|| la\"mb.?";
string legal = ReplaceInvalidChars(illegal);

并返回:

_M ____a_ry_ h__ad___ a_________ li_tt_le__ la_mb._

值得注意的是,该方法总是将无效字符替换为给定值,但不会删除它们。如果你想删除无效字符,这个替代方法可以做到:

private static string RemoveInvalidChars(string fileName, string newValue)
{
  char newChar = string.IsNullOrEmpty(newValue) ? char.MinValue : newValue[0];
  bool remove = newChar == char.MinValue;

  char[] chars = fileName.ToCharArray();
  char[] newChars = new char[chars.Length];
  int i2 = 0;
  for (int i = 0; i < chars.Length; i++)
  {
    char c = chars[i];
    if (InvalidCharsHash.Contains(c))
    {
      if (!remove)
        newChars[i2++] = newChar;
    }
    else
      newChars[i2++] = c;

  }

  return new string(newChars, 0, i2);
}

基准

如果性能是你所追求的,我用这篇文章中发现的大多数方法执行了定时测试运行。其中一些方法不会替换为给定的char,因为OP要求清除字符串。我添加了用给定字符替换的测试,如果您的预期场景只需要删除不需要的字符,还添加了一些用空字符替换的测试。用于此基准测试的代码位于末尾,因此您可以运行自己的测试。

注意:方法Test1和Test2都在本文中提出。

第一次运行

替换为'_',1000000次迭代

结果:

============Test1===============
Elapsed=00:00:01.6665595
Result=_M ____a_ry_ h__ad___ a_________ li_tt_le__ la_mb._

============Test2===============
Elapsed=00:00:01.7526835
Result=_M ____a_ry_ h__ad___ a_________ li_tt_le__ la_mb._

============Test3===============
Elapsed=00:00:05.2306227
Result=_M ____a_ry_ h__ad___ a_________ li_tt_le__ la_mb._

============Test4===============
Elapsed=00:00:14.8203696
Result=_M ____a_ry_ h__ad___ a_________ li_tt_le__ la_mb._

============Test5===============
Elapsed=00:00:01.8273760
Result=_M ____a_ry_ h__ad___ a_________ li_tt_le__ la_mb._

============Test6===============
Elapsed=00:00:05.4249985
Result=_M ____a_ry_ h__ad___ a_________ li_tt_le__ la_mb._

============Test7===============
Elapsed=00:00:07.5653833
Result=_M ____a_ry_ h__ad___ a_________ li_tt_le__ la_mb._

============Test8===============
Elapsed=00:12:23.1410106
Result=_M ____a_ry_ h__ad___ a_________ li_tt_le__ la_mb._

============Test9===============
Elapsed=00:00:02.1016708
Result=_M ____a_ry_ h__ad___ a_________ li_tt_le__ la_mb._

============Test10===============
Elapsed=00:00:05.0987225
Result=M ary had a little lamb.

============Test11===============
Elapsed=00:00:06.8004289
Result=M ary had a little lamb.

第二次运行

去除无效字符,100万次迭代

注意:Test1不会移除,只会替换。

结果:

============Test1===============
Elapsed=00:00:01.6945352
Result= M     a ry  h  ad    a          li tt le   la mb.

============Test2===============
Elapsed=00:00:01.4798049
Result=M ary had a little lamb.

============Test3===============
Elapsed=00:00:04.0415688
Result=M ary had a little lamb.

============Test4===============
Elapsed=00:00:14.3397960
Result=M ary had a little lamb.

============Test5===============
Elapsed=00:00:01.6782505
Result=M ary had a little lamb.

============Test6===============
Elapsed=00:00:04.9251707
Result=M ary had a little lamb.

============Test7===============
Elapsed=00:00:07.9562379
Result=M ary had a little lamb.

============Test8===============
Elapsed=00:12:16.2918943
Result=M ary had a little lamb.

============Test9===============
Elapsed=00:00:02.0770277
Result=M ary had a little lamb.

============Test10===============
Elapsed=00:00:05.2721232
Result=M ary had a little lamb.

============Test11===============
Elapsed=00:00:05.2802903
Result=M ary had a little lamb.

基准测试结果

方法Test1、Test2和Test5是最快的。方法Test8是最慢的。

CODE

以下是基准测试的完整代码:

private static HashSet<char> _invalidCharsHash;
private static HashSet<char> InvalidCharsHash
{
  get { return _invalidCharsHash ?? (_invalidCharsHash = new HashSet<char>(Path.GetInvalidFileNameChars())); }
}

private static string _invalidCharsValue;
private static string InvalidCharsValue
{
  get { return _invalidCharsValue ?? (_invalidCharsValue = new string(Path.GetInvalidFileNameChars())); }
}

private static char[] _invalidChars;
private static char[] InvalidChars
{
  get { return _invalidChars ?? (_invalidChars = Path.GetInvalidFileNameChars()); }
}

static void Main(string[] args)
{
  string testPath = "\"M <>\"\\a/ry/ h**ad:>> a\\/:*?\"<>| li*tt|le|| la\"mb.?";

  int max = 1000000;
  string newValue = "";

  TimeBenchmark(max, Test1, testPath, newValue);
  TimeBenchmark(max, Test2, testPath, newValue);
  TimeBenchmark(max, Test3, testPath, newValue);
  TimeBenchmark(max, Test4, testPath, newValue);
  TimeBenchmark(max, Test5, testPath, newValue);
  TimeBenchmark(max, Test6, testPath, newValue);
  TimeBenchmark(max, Test7, testPath, newValue);
  TimeBenchmark(max, Test8, testPath, newValue);
  TimeBenchmark(max, Test9, testPath, newValue);
  TimeBenchmark(max, Test10, testPath, newValue);
  TimeBenchmark(max, Test11, testPath, newValue);

  Console.Read();
}

private static void TimeBenchmark(int maxLoop, Func<string, string, string> func, string testString, string newValue)
{
  var sw = new Stopwatch();
  sw.Start();
  string result = string.Empty;

  for (int i = 0; i < maxLoop; i++)
    result = func?.Invoke(testString, newValue);

  sw.Stop();

  Console.WriteLine($"============{func.Method.Name}===============");
  Console.WriteLine("Elapsed={0}", sw.Elapsed);
  Console.WriteLine("Result={0}", result);
  Console.WriteLine("");
}

private static string Test1(string fileName, string newValue)
{
  char newChar = string.IsNullOrEmpty(newValue) ? char.MinValue : newValue[0];

  char[] chars = fileName.ToCharArray();
  for (int i = 0; i < chars.Length; i++)
  {
    if (InvalidCharsHash.Contains(chars[i]))
      chars[i] = newChar;
  }

  return new string(chars);
}

private static string Test2(string fileName, string newValue)
{
  char newChar = string.IsNullOrEmpty(newValue) ? char.MinValue : newValue[0];
  bool remove = newChar == char.MinValue;

  char[] chars = fileName.ToCharArray();
  char[] newChars = new char[chars.Length];
  int i2 = 0;
  for (int i = 0; i < chars.Length; i++)
  {
    char c = chars[i];
    if (InvalidCharsHash.Contains(c))
    {
      if (!remove)
        newChars[i2++] = newChar;
    }
    else
      newChars[i2++] = c;

  }

  return new string(newChars, 0, i2);
}

private static string Test3(string filename, string newValue)
{
  foreach (char c in InvalidCharsValue)
  {
    filename = filename.Replace(c.ToString(), newValue);
  }

  return filename;
}

private static string Test4(string filename, string newValue)
{
  Regex r = new Regex(string.Format("[{0}]", Regex.Escape(InvalidCharsValue)));
  filename = r.Replace(filename, newValue);
  return filename;
}

private static string Test5(string filename, string newValue)
{
  return string.Join(newValue, filename.Split(InvalidChars));
}

private static string Test6(string fileName, string newValue)
{
  return InvalidChars.Aggregate(fileName, (current, c) => current.Replace(c.ToString(), newValue));
}

private static string Test7(string fileName, string newValue)
{
  string regex = string.Format("[{0}]", Regex.Escape(InvalidCharsValue));
  return Regex.Replace(fileName, regex, newValue, RegexOptions.Compiled);
}

private static string Test8(string fileName, string newValue)
{
  string regex = string.Format("[{0}]", Regex.Escape(InvalidCharsValue));
  Regex removeInvalidChars = new Regex(regex, RegexOptions.Singleline | RegexOptions.Compiled | RegexOptions.CultureInvariant);
  return removeInvalidChars.Replace(fileName, newValue);
}

private static string Test9(string fileName, string newValue)
{
  StringBuilder sb = new StringBuilder(fileName.Length);
  bool changed = false;

  for (int i = 0; i < fileName.Length; i++)
  {
    char c = fileName[i];
    if (InvalidCharsHash.Contains(c))
    {
      changed = true;
      sb.Append(newValue);
    }
    else
      sb.Append(c);
  }

  if (sb.Length == 0)
    return newValue;

  return changed ? sb.ToString() : fileName;
}

private static string Test10(string fileName, string newValue)
{
  if (!fileName.Any(c => InvalidChars.Contains(c)))
  {
    return fileName;
  }

  return new string(fileName.Where(c => !InvalidChars.Contains(c)).ToArray());
}

private static string Test11(string fileName, string newValue)
{
  string invalidCharsRemoved = new string(fileName
    .Where(x => !InvalidChars.Contains(x))
    .ToArray());

  return invalidCharsRemoved;
}

其他回答

上面的大多数解决方案都将路径和文件名的非法字符组合在一起,这是错误的(即使两个调用当前返回相同的字符集)。我将首先在path和filename中分割path+filename,然后应用适当的集,如果它们,然后再次结合两者。

wvd_vegt

这样做会想要你想要的,避免碰撞

 static string SanitiseFilename(string key)
    {
        var invalidChars = Path.GetInvalidFileNameChars();
        var sb = new StringBuilder();
        foreach (var c in key)
        {
            var invalidCharIndex = -1;
            for (var i = 0; i < invalidChars.Length; i++)
            {
                if (c == invalidChars[i])
                {
                    invalidCharIndex = i;
                }
            }
            if (invalidCharIndex > -1)
            {
                sb.Append("_").Append(invalidCharIndex);
                continue;
            }

            if (c == '_')
            {
                sb.Append("__");
                continue;
            }

            sb.Append(c);
        }
        return sb.ToString();

    }

这些都是很好的解决方案,但它们都依赖于Path。getinvalidfilenamecars,它可能不像您想象的那么可靠。请注意MSDN文档中关于Path的以下注释。GetInvalidFileNameChars:

此方法返回的数组不保证包含文件和目录名中无效的完整字符集。完整的无效字符集可能因文件系统而异。例如,在基于windows的桌面平台上,无效路径字符可能包括ASCII/Unicode字符1到31,以及引号(")、小于(<)、大于(>)、管道(|)、退格(\b)、null(\0)和制表符(\t)。

Path的情况也好不到哪里去。GetInvalidPathChars方法。它包含了完全相同的评论。

下面的代码片段应该对。net 3及更高版本有所帮助。

using System.IO;
using System.Text.RegularExpressions;

public static class PathValidation
{
    private static string pathValidatorExpression = "^[^" + string.Join("", Array.ConvertAll(Path.GetInvalidPathChars(), x => Regex.Escape(x.ToString()))) + "]+$";
    private static Regex pathValidator = new Regex(pathValidatorExpression, RegexOptions.Compiled);

    private static string fileNameValidatorExpression = "^[^" + string.Join("", Array.ConvertAll(Path.GetInvalidFileNameChars(), x => Regex.Escape(x.ToString()))) + "]+$";
    private static Regex fileNameValidator = new Regex(fileNameValidatorExpression, RegexOptions.Compiled);

    private static string pathCleanerExpression = "[" + string.Join("", Array.ConvertAll(Path.GetInvalidPathChars(), x => Regex.Escape(x.ToString()))) + "]";
    private static Regex pathCleaner = new Regex(pathCleanerExpression, RegexOptions.Compiled);

    private static string fileNameCleanerExpression = "[" + string.Join("", Array.ConvertAll(Path.GetInvalidFileNameChars(), x => Regex.Escape(x.ToString()))) + "]";
    private static Regex fileNameCleaner = new Regex(fileNameCleanerExpression, RegexOptions.Compiled);

    public static bool ValidatePath(string path)
    {
        return pathValidator.IsMatch(path);
    }

    public static bool ValidateFileName(string fileName)
    {
        return fileNameValidator.IsMatch(fileName);
    }

    public static string CleanPath(string path)
    {
        return pathCleaner.Replace(path, "");
    }

    public static string CleanFileName(string fileName)
    {
        return fileNameCleaner.Replace(fileName, "");
    }
}

下面是一个用替换字符替换文件名中所有非法字符的函数:

public static string ReplaceIllegalFileChars(string FileNameWithoutPath, char ReplacementChar)
{
  const string IllegalFileChars = "*?/\\:<>|\"";
  StringBuilder sb = new StringBuilder(FileNameWithoutPath.Length);
  char c;

  for (int i = 0; i < FileNameWithoutPath.Length; i++)
  {
    c = FileNameWithoutPath[i];
    if (IllegalFileChars.IndexOf(c) >= 0)
    {
      c = ReplacementChar;
    }
    sb.Append(c);
  }
  return (sb.ToString());
}

例如,下划线可以用作替换字符:

NewFileName = ReplaceIllegalFileChars(FileName, '_');