C# Sanitize File Name

I recently have been moving a bunch of MP3s from various locations into a repository. I had been constructing the new file names using the ID3 tags (thanks, TagLib-Sharp!), and I noticed that I was getting a System.NotSupportedException:

"The given path's format is not supported."

This was generated by either File.Copy() or Directory.CreateDirectory().

It didn't take long to realize that my file names needed to be sanitized. So I did the obvious thing:

public static string SanitizePath_(string path, char replaceChar)
{
    string dir = Path.GetDirectoryName(path);
    foreach (char c in Path.GetInvalidPathChars())
        dir = dir.Replace(c, replaceChar);

    string name = Path.GetFileName(path);
    foreach (char c in Path.GetInvalidFileNameChars())
        name = name.Replace(c, replaceChar);

    return dir + name;
}

To my surprise, I continued to get exceptions. It turned out that ':' is not in the set of Path.GetInvalidPathChars(), because it is valid in a path root. I suppose that makes sense - but this has to be a pretty common problem. Does anyone have some short code that sanitizes a path? The most thorough I've come up with this, but it feels like it is probably overkill.

    // replaces invalid characters with replaceChar
    public static string SanitizePath(string path, char replaceChar)
    {
        // construct a list of characters that can't show up in filenames.
        // need to do this because ":" is not in InvalidPathChars
        if (_BadChars == null)
        {
            _BadChars = new List<char>(Path.GetInvalidFileNameChars());
            _BadChars.AddRange(Path.GetInvalidPathChars());
            _BadChars = Utility.GetUnique<char>(_BadChars);
        }

        // remove root
        string root = Path.GetPathRoot(path);
        path = path.Remove(0, root.Length);

        // split on the directory separator character. Need to do this
        // because the separator is not valid in a filename.
        List<string> parts = new List<string>(path.Split(new char[]{Path.DirectorySeparatorChar}));

        // check each part to make sure it is valid.
        for (int i = 0; i < parts.Count; i++)
        {
            string part = parts[i];
            foreach (char c in _BadChars)
            {
                part = part.Replace(c, replaceChar);
            }
            parts[i] = part;
        }

        return root + Utility.Join(parts, Path.DirectorySeparatorChar.ToString());
    }

Any improvements to make this function faster and less baroque would be much appreciated.

To clean up a file name you could do this

private static string MakeValidFileName( string name )
{
   string invalidChars = System.Text.RegularExpressions.Regex.Escape( new string( System.IO.Path.GetInvalidFileNameChars() ) );
   string invalidRegStr = string.Format( @"([{0}]*\.+$)|([{0}]+)", invalidChars );

   return System.Text.RegularExpressions.Regex.Replace( name, invalidRegStr, "_" );
}

A shorter solution:

var invalids = System.IO.Path.GetInvalidFileNameChars();
var newName = String.Join("_", origFileName.Split(invalids, StringSplitOptions.RemoveEmptyEntries) ).TrimEnd('.');

Based on Andre's excellent answer but taking into account Spud's comment on reserved words, I made this version:

/// <summary>
/// Strip illegal chars and reserved words from a candidate filename (should not include the directory path)
/// </summary>
/// <remarks>
/// http://stackoverflow.com/questions/309485/c-sharp-sanitize-file-name
/// </remarks>
public static string CoerceValidFileName(string filename)
{
    var invalidChars = Regex.Escape(new string(Path.GetInvalidFileNameChars()));
    var invalidReStr = string.Format(@"[{0}]+", invalidChars);

    var reservedWords = new []
    {
        "CON", "PRN", "AUX", "CLOCK$", "NUL", "COM0", "COM1", "COM2", "COM3", "COM4",
        "COM5", "COM6", "COM7", "COM8", "COM9", "LPT0", "LPT1", "LPT2", "LPT3", "LPT4",
        "LPT5", "LPT6", "LPT7", "LPT8", "LPT9"
    };

    var sanitisedNamePart = Regex.Replace(filename, invalidReStr, "_");
    foreach (var reservedWord in reservedWords)
    {
        var reservedWordPattern = string.Format("^{0}\\.", reservedWord);
        sanitisedNamePart = Regex.Replace(sanitisedNamePart, reservedWordPattern, "_reservedWord_.", RegexOptions.IgnoreCase);
    }

    return sanitisedNamePart;
}

And these are my unit tests

[Test]
public void CoerceValidFileName_SimpleValid()
{
    var filename = @"thisIsValid.txt";
    var result = PathHelper.CoerceValidFileName(filename);
    Assert.AreEqual(filename, result);
}

[Test]
public void CoerceValidFileName_SimpleInvalid()
{
    var filename = @"thisIsNotValid\3\\_3.txt";
    var result = PathHelper.CoerceValidFileName(filename);
    Assert.AreEqual("thisIsNotValid_3__3.txt", result);
}

[Test]
public void CoerceValidFileName_InvalidExtension()
{
    var filename = @"thisIsNotValid.t\xt";
    var result = PathHelper.CoerceValidFileName(filename);
    Assert.AreEqual("thisIsNotValid.t_xt", result);
}

[Test]
public void CoerceValidFileName_KeywordInvalid()
{
    var filename = "aUx.txt";
    var result = PathHelper.CoerceValidFileName(filename);
    Assert.AreEqual("_reservedWord_.txt", result);
}

[Test]
public void CoerceValidFileName_KeywordValid()
{
    var filename = "auxillary.txt";
    var result = PathHelper.CoerceValidFileName(filename);
    Assert.AreEqual("auxillary.txt", result);
}

string clean = String.Concat(dirty.Split(Path.GetInvalidFileNameChars()));