I have an issue with parsing XML which has utf-16 encoding but it works perfectly
fine with utf-8.
Can any help me out on this issue?.
I get the following error :
System.Web.HttpUnhandledException' was thrown.
System.Xml.XmlException: There is no Unicode byte order mark.
Cannot switch to Unicode
XML Header:
<?xml version="1.0" encoding="utf-16"?>
<RiskAssessmentRequestValue xmlns:xsd="http://www.w3.org/2001/XMLSchema"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
C# CODE BEHIND :
rptTransformedXml.DataSource = parser.ExtractData(xml);
rptTransformedXml.DataBind();
public List<XmlDataExtract> ExtractData(string xml)
{
MemoryStream stream = new MemoryStream(Encoding.ASCII.GetBytes(xml));
return ExtractData(stream);
}
public List<XmlDataExtract> ExtractData(Stream xmlStream)
{
XmlReaderSettings settings = new XmlReaderSettings
{
IgnoreComments = true,
IgnoreWhitespace = true,
CloseInput = true
};
XmlReader reader = XmlReader.Create(xmlStream, settings);
XmlPathBuilder pathBuilder = new XmlPathBuilder(reader);
List<XmlDataExtract> xmlDataList = new List<XmlDataExtract>();
while (reader.Read())
{
if (reader.NodeType == XmlNodeType.XmlDeclaration)
continue;
pathBuilder.Add();
CollectAttributeData(reader, xmlDataList, pathBuilder);
CollectElementData(reader, xmlDataList, pathBuilder);
}
return xmlDataList;
}
You can create an encoder based on the encoding of the xml content :
string encoding = "UTF-8"; // should match encoding in XML
string xml = @"<?xml version='1.0' encoding='UTF-8'?><table><row>1</row></table>";
var ms = new MemoryStream(Encoding.GetEncoding(encoding).GetBytes(xml));
var xdrs = new XmlReaderSettings()
{IgnoreComments = true,
IgnoreWhitespace = true,
CloseInput = true};
var xdr = XmlReader.Create(ms, xdrs);
while (xdr.Read())
{
Console.Write("qqq");
}
For more information about encoding, there is a related question