C#反序列化xml而忽略命名空间

Question

I have to load and deserialize an Xml file into an object. I can read the xml, get to the point where the object is described and parse the xml only from that part which is great, but there is a namespace declared in the root of the xml.

I don't understand why but when reading the xml, even though I read it from a given node, the xmlns attribute gets added to it, resulting in my program not being able to deserialize that into an object, due to the unexpected member.

My code:

public static SomeClass GetObjectFromXml (string path)
    {
        XmlReader reader = XmlReader.Create(path);
        string wantedNodeContents = string.Empty;
        while (reader.Read())
        {
            if (reader.NodeType == XmlNodeType.Element && reader.Name == "IWantThis")
            {
                wantedNodeContents = reader.ReadOuterXml();
                break;
            }
        }
        XmlSerializer xmlSerializer = new XmlSerializer(typeof(SomeClass));
        System.IO.StringReader stringReader = new System.IO.StringReader(wantedNodeContents);
        SomeClass loadedSomeClassXml = xmlSerializer.Deserialize(stringReader) as SomeClass;
        return loadedSomeClassXml;
    }

How could I get rid of the xmlns and deserialize the xml into an object?

Answer 1

XDocument provides you a bit of more flexibility at time of deserialize any XML. I had a similiar problem and it was resolve using the next snippet code:

///Type T must have a default constructor

private T XMLToObject (string pathXML)
{
   T myObjectParsedFromXML= default(T);

   LoadOptions loadOpt = LoadOptions.SetLineInfo;
   XDocument xmlDocument = XDocument.Load(pathXML , loadOpt);

   string namespaceXML = xmlDocument.Root.Name.Namespace.NamespaceName;
   XmlSerializer serializer = new XmlSerializer(typeof(T), defaultNamespace: namespaceXML); 
   
   XmlReader XMLreader = xmlDocument.CreateReader();

   myObjectParsedFromXML= (T)serializer.Deserialize(XMLreader);   
   
   return myObjectParsedFromXML;
}

In addition, XmlSerializer provides you a set of events for register any issue or error during serialization process:

 XmlSerializer serializer = new XmlSerializer(typeof(T), defaultNamespace: namespaceXML);
 
 serializer.UnknownAttribute += new XmlAttributeEventHandler((sender, args) =>
            {
                //Your code for manage the errors during serialization
            });

 serializer.UnknownElement += new XmlElementEventHandler((sender, args) =>
            {  
               //Your code for manage the errors during serialization  
            });

Answer 2

You have a few issues here:

1. The default namespace attribute is added to the string returned by ReadOuterXml() because ReadOuterXml() is designed not to change the semantics of the returned XML . Apparently in your XML there is a default namespace applied to some parent node of <IWantThis> -- which, being a default namespace, recursively applies to <IWantThis> itself. To retain this namespace membership, ReadOuterXml() must emit a default namespace as it writes out the nested XML.

   If you really want to completely ignore namespaces on XML, you need to create a custom XmlReader , eg as shown in

   • this answer to Can I make XmlSerializer ignore the namespace on deserialization? by Cheeso .
   • this answer to How do I create a XmlTextReader that ignores Namespaces and does not check characters by Alterant .

2. You need to construct an XmlSerializer for SomeClass whose expected root node is <IWantThis> . You can do this using the XmlSerializer(Type, XmlRootAttribute) constructor, however, if you do, you must statically cache and reuse the serializer to avoid a severe memory leak , as explained in Memory Leak using StreamReader and XmlSerializer .

3. You are creating a local copy wantedNodeContents of the element you want to deserialize, then re-parsing that local copy. There is no need to do this, you can use XmlReader.ReadSubtree() to deserialize just a portion of the XML.

Putting all these issues together, your GetObjectFromXml() could look like:

public static partial class XmlExtensions
{
    public static T GetObjectFromXml<T>(string path, string localName, string namespaceURI, bool ignoreNamespaces = false)
    {
        using (var textReader = new StreamReader(path))
            return GetObjectFromXml<T>(textReader, localName, namespaceURI);
    }
    
    public static T GetObjectFromXml<T>(TextReader textReader, string localName, string namespaceURI, bool ignoreNamespaces = false)
    {
        using (var xmlReader = ignoreNamespaces ? new NamespaceIgnorantXmlTextReader(textReader) : XmlReader.Create(textReader))
            return GetObjectFromXml<T>(xmlReader, localName, namespaceURI);
    }
    
    public static T GetObjectFromXml<T>(XmlReader reader, string localName, string namespaceURI)
    {
        while (reader.Read())
        {
            if (reader.NodeType == XmlNodeType.Element && reader.LocalName == "IWantThis" && reader.NamespaceURI == namespaceURI)
            {
                var serializer = XmlSerializerFactory.Create(typeof(T), localName, namespaceURI);
                using (var subReader = reader.ReadSubtree())
                    return (T)serializer.Deserialize(subReader);
            }
        }
        // Or throw an exception?
        return default(T);
    }
}

// This class copied from this answer https://stackoverflow.com/a/873281/3744182
// To https://stackoverflow.com/questions/870293/can-i-make-xmlserializer-ignore-the-namespace-on-deserialization
// By https://stackoverflow.com/users/48082/cheeso
// helper class to ignore namespaces when de-serializing
public class NamespaceIgnorantXmlTextReader : XmlTextReader
{
    public NamespaceIgnorantXmlTextReader(System.IO.TextReader reader): base(reader) { }

    public override string NamespaceURI { get { return ""; } }
}

public static class XmlSerializerFactory
{
    // To avoid a memory leak the serializer must be cached.
    // https://stackoverflow.com/questions/23897145/memory-leak-using-streamreader-and-xmlserializer
    // This factory taken from 
    // https://stackoverflow.com/questions/34128757/wrap-properties-with-cdata-section-xml-serialization-c-sharp/34138648#34138648

    readonly static Dictionary<Tuple<Type, string, string>, XmlSerializer> cache;
    readonly static object padlock;

    static XmlSerializerFactory()
    {
        padlock = new object();
        cache = new Dictionary<Tuple<Type, string, string>, XmlSerializer>();
    }

    public static XmlSerializer Create(Type serializedType, string rootName, string rootNamespace)
    {
        if (serializedType == null)
            throw new ArgumentNullException();
        if (rootName == null && rootNamespace == null)
            return new XmlSerializer(serializedType);
        lock (padlock)
        {
            XmlSerializer serializer;
            var key = Tuple.Create(serializedType, rootName, rootNamespace);
            if (!cache.TryGetValue(key, out serializer))
            {
                cache[key] = serializer = new XmlSerializer(serializedType, new XmlRootAttribute { ElementName = rootName, Namespace = rootNamespace });
            }
            return serializer;
        }
    }
}

Demo fiddle here .