.NET XML serialization gotchas?

Kalid picture Kalid · Sep 16, 2008 · Viewed 66.3k times · Source

I've run into a few gotchas when doing C# XML serialization that I thought I'd share:


using System;
using System.Collections.Generic;
using System.Text;
using System.Xml.Serialization;

[XmlRoot("dictionary")]
public class SerializableDictionary<TKey, TValue> : Dictionary<TKey, TValue>, IXmlSerializable
{      
    public System.Xml.Schema.XmlSchema GetSchema()
    {
        return null;
    }

    public void ReadXml(System.Xml.XmlReader reader)
    {
        XmlSerializer keySerializer = new XmlSerializer(typeof(TKey));
        XmlSerializer valueSerializer = new XmlSerializer(typeof(TValue));

        bool wasEmpty = reader.IsEmptyElement;
        reader.Read();

        if (wasEmpty)
            return;

        while (reader.NodeType != System.Xml.XmlNodeType.EndElement)
        {
            reader.ReadStartElement("item");

            reader.ReadStartElement("key");
            TKey key = (TKey)keySerializer.Deserialize(reader);
            reader.ReadEndElement();

            reader.ReadStartElement("value");
            TValue value = (TValue)valueSerializer.Deserialize(reader);
            reader.ReadEndElement();

            this.Add(key, value);

            reader.ReadEndElement();
            reader.MoveToContent();
        }
        reader.ReadEndElement();
    }

    public void WriteXml(System.Xml.XmlWriter writer)
    {
        XmlSerializer keySerializer = new XmlSerializer(typeof(TKey));
        XmlSerializer valueSerializer = new XmlSerializer(typeof(TValue));

        foreach (TKey key in this.Keys)
        {
            writer.WriteStartElement("item");

            writer.WriteStartElement("key");
            keySerializer.Serialize(writer, key);
            writer.WriteEndElement();

            writer.WriteStartElement("value");
            TValue value = this[key];
            valueSerializer.Serialize(writer, value);
            writer.WriteEndElement();

            writer.WriteEndElement();
        }
    }
}

Any other XML Serialization gotchas out there?

Answer

Kalid picture Kalid · Sep 18, 2008

Another huge gotcha: when outputting XML through a web page (ASP.NET), you don't want to include the Unicode Byte-Order Mark. Of course, the ways to use or not use the BOM are almost the same:

BAD (includes BOM):

XmlTextWriter wr = new XmlTextWriter(stream, new System.Text.Encoding.UTF8);

GOOD:

XmlTextWriter  wr = new XmlTextWriter(stream, new System.Text.UTF8Encoding(false))

You can explicitly pass false to indicate you don't want the BOM. Notice the clear, obvious difference between Encoding.UTF8 and UTF8Encoding.

The three extra BOM Bytes at the beginning are (0xEFBBBF) or (239 187 191).

Reference: http://chrislaco.com/blog/troubleshooting-common-problems-with-the-xmlserializer/