XML 1.0

[2] Char ::= #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF] /* any Unicode character, excluding the surrogate blocks, FFFE, and FFFF. */

XML 1.1

[2] Char ::= [#x1-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF] /* any Unicode character, excluding the surrogate blocks, FFFE, and FFFF. */

[2a] RestrictedChar ::= [#x1-#x8] | [#xB-#xC] | [#xE-#x1F] | [#x7F-#x84] | [#x86-#x9F]

public static string CleanInvalidXmlChars(string text) 
{ 
    // From xml spec valid chars: 
    // #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]     
    // any Unicode character, excluding the surrogate blocks, FFFE, and FFFF. 
    string re = @"[^\x09\x0A\x0D\x20-\uD7FF\uE000-\uFFFD\u10000-\u10FFFF]"; 
    return Regex.Replace(text, re, ""); 
}
Copy the code

[#x1-#x8], [#xB-#xC], [#xE-#x1F], [#x7F-#x84], [#x86-#x9F], [#xFDD0-#xFDDF],
[#x1FFFE-#x1FFFF], [#x2FFFE-#x2FFFF], [#x3FFFE-#x3FFFF],
[#x4FFFE-#x4FFFF], [#x5FFFE-#x5FFFF], [#x6FFFE-#x6FFFF],
[#x7FFFE-#x7FFFF], [#x8FFFE-#x8FFFF], [#x9FFFE-#x9FFFF],
[#xAFFFE-#xAFFFF], [#xBFFFE-#xBFFFF], [#xCFFFE-#xCFFFF],
[#xDFFFE-#xDFFFF], [#xEFFFE-#xEFFFF], [#xFFFFE-#xFFFFF],
[#x10FFFE-#x10FFFF].
Copy the code

string.replaceAll("[\\x00-\\x08\\x0b-\\x0c\\x0e-\\x1f\\x7f-\\x84\\ud800-\\udfff\\ufdd0-\\ufddf\\ufffe-\\uffff]"."") 
Copy the code