XmlWriter xmlWriter = XmlWriter.Create(memoryStream, xmlWriterSettings);
xmlWriter.WriteStartDocument();
xmlWriter.WriteStartElement(“root”, “http://www.timvw.be/ns”);
xmlWriter.WriteEndElement();
xmlWriter.WriteEndDocument();
xmlWriter.Flush();
xmlWriter.Close();

string xmlString = Encoding.UTF8.GetString(memoryStream.ToArray());

font: http://www.timvw.be/2007/01/08/generating-utf-8-with-systemxmlxmlwriter/

public class StringWriterWithEncoding : StringWriter
{
private readonly Encoding encoding;
public StringWriterWithEncoding(StringBuilder sb, Encoding newEncoding) : base(sb) { encoding = newEncoding; }
public override Encoding Encoding { get { return encoding ?? base.Encoding; } }
}

private static string GenerateXML()
{
var stringBuilder = new StringBuilder();
var xmlTextWriter = new XmlTextWriter(new StringWriterWithEncoding(stringBuilder, Encoding.UTF8)) { Formatting = Formatting.None };
xmlTextWriter.WriteStartDocument();

#region Generatere your xml
#endregion

xmlTextWriter.WriteEndDocument();
xmlTextWriter.Flush();
xmlTextWriter.Close();
return stringBuilder.ToString();
}

“A string is an object of type String whose value is text. Internally, the text is stored as a readonly collection of Char objects, each of which represents one Unicode character encoded in UTF-16.” (See this reference)

(note that this was true from the very first version of .NET. In fact, they all follow the Unicode version 3.0 standard pretty flawlessly internally. Unfortunately, Microsoft never upgraded, not even for the recent VS 2010)

http://techrepublic.com.com/5208-6230-0.html?forumID=102&threadID=226398&messageID=3222797

At the other end, when you need string output (i.e. for display purposes), it is debatable whether such optimizations are needed.

Though I can agree that your approach is the obvious more “correct” way, and the OmitXmlDeclaration is yet another “dirty” way because you have to prepend it by hand, which you just want to prevent by using a standardized writer, I don’t see an easy way of implementing this more correct way as a simple accessible extension so that users do not need to worry about this issue.

I don’t see it as forcing something it is not, because a string is always a UTF-16 string internally and here it should represent a data stream as a string. I don’t force the string to be something else, the string will remain UTF-16, but will output with the intended encoding just like any other XmlWriter.

– Abel –

An easier and more “correct” way would be:

using (MemoryStream buffer = new MemoryStream())
{
using (StreamWriter stream = new StreamWriter(buffer, Encoding.UTF8))
{
using (XmlWriter writer = XmlWriter.Create(stream))
{
writer.WriteStartElement(“should-be utf-8″);
writer.WriteEndElement();
}
}
byte[] xmlData = buffer.ToArray();
}

// For testing or to put into a textbox:
string xml = Encoding.UTF8.GetString(xmlData); // You might want to strip the BOM here

This method does create the underlying data in the correct encoding and it does write the BOM.

Why force something (StringBuilder) to UTF-8 if it is not? If using StringBuilder you can create the XML with XmlWriter and the setting OmitXmlDeclaration and then prepend the XML declaration yourself when converting the StringBuilder string to UTF-8 or whatever encoding.