using System;

using System.Text.RegularExpressions;

using System.Text;

using System.Xml;

​

public class Program

{

    public static void Main()

    {

        string hex = string.Empty;

        Console.WriteLine("-------------Example 1-------------------");

        Console.WriteLine("");

        hex = GetHexString("©Ø");

        Console.WriteLine("");

        string a = @"This" + hex + " "+ hex + "is " + hex + "a " + hex + "text";

        a = RemoveTroublesomeCharacters(a);

        Console.WriteLine(a);

        //Expected: This is a test

        Console.WriteLine("");

        Console.WriteLine("-------------Example 2-------------------");

        // ---- Example 2

        hex = "0x1D"; // Value reported in the mail

        Console.WriteLine("");

        a = @"This" + hex + " "+ hex + "is " + hex + "a " + hex + "text";

        a = RemoveTroublesomeCharacters(a);

        Console.WriteLine(a);

        //Expected: This is a test

    }

    public static string CleanInvalidXmlChars(string text)

    {

        string pattern = @"&#x((10?|[2-F])FFF[EF]|FDD[0-9A-F]|[19][0-9A-F]|7F|8[0-46-9A-F]|0?[1-8BCEF]);";

        //string pattern = @"[^\x09\x0A\x0D\x20-\xD7FF\xE000-\xFFFD\x10000-x10FFFF]";

        Regex regex = new Regex(pattern, RegexOptions.IgnoreCase);

        if(regex.IsMatch(text))

            text = regex.Replace(text, string.Empty);

        return text;

    }

    public static string GetHexString(string strToHex)

    {

        char [] values = strToHex.ToCharArray();

        StringBuilder sb = new StringBuilder();

        foreach(char letter in values)

        {

            int newValue = Convert.ToInt32(letter);

            sb.AppendFormat("0x{0:X2}", newValue);

        }

        Console.WriteLine(sb.ToString() + " // This is the hex value for: " + strToHex);

        return sb.ToString();

    }

    public static string RemoveTroublesomeCharacters(string inString)

    {

        if (inString == null) return null;

​

        StringBuilder newString = new StringBuilder();

        char ch;

​

        for (int i = 0; i < inString.Length; i++)

        {

​

            ch = inString[i];

            // remove any characters outside the valid UTF-8 range as well as all control characters

            // except tabs and new lines

            //if ((ch < 0x00FD && ch > 0x001F) || ch == '\t' || ch == '\n' || ch == '\r')

            //if using .NET version prior to 4, use above logic

            if (XmlConvert.IsXmlChar(ch)) //this method is new in .NET 4

            {

                newString.Append(ch);

            }

        }

        return newString.ToString();

​

    }

}