Check output size using .NET XmlTextWriter

Question

I need to generate an XML file and i need to stick as much data into it as possible BUT there is a filesize limit. So i need to keep inserting data until something says no more. How do i figure out the XML file size without repeatably writing it to file?

Answer 1

I agree with John Saunders. Here's some code that will basically do what he's talking about but as an XmlSerializer except as a FileStream and uses a MemoryStream as intermediate storage. It may be more effective to extend stream though.

public class PartitionedXmlSerializer<TObj>
{
    private readonly int _fileSizeLimit;

    public PartitionedXmlSerializer(int fileSizeLimit)
    {
        _fileSizeLimit = fileSizeLimit;
    }

    public void Serialize(string filenameBase, TObj obj)
    {
        using (var memoryStream = new MemoryStream())
        {
            // serialize the object in the memory stream
            using (var xmlWriter = XmlWriter.Create(memoryStream))
                new XmlSerializer(typeof(TObj))
                    .Serialize(xmlWriter, obj);

            memoryStream.Seek(0, SeekOrigin.Begin);

            var extensionFormat = GetExtensionFormat(memoryStream.Length);

            var buffer = new char[_fileSizeLimit];

            var i = 0;
            // split the stream into files
            using (var streamReader = new StreamReader(memoryStream))
            {
                int readLength;
                while ((readLength = streamReader.Read(buffer, 0, _fileSizeLimit)) > 0)
                {
                    var filename 
                        = Path.ChangeExtension(filenameBase, 
                            string.Format(extensionFormat, i++));
                    using (var fileStream = new StreamWriter(filename))
                        fileStream.Write(buffer, 0, readLength);
                }
            }
        }
    }

    /// <summary>
    /// Gets the a file extension formatter based on the 
    /// <param name="fileLength">length of the file</param> 
    /// and the max file length
    /// </summary>
    private string GetExtensionFormat(long fileLength)
    {
        var numFiles = fileLength / _fileSizeLimit;
        var extensionLength = Math.Ceiling(Math.Log10(numFiles));
        var zeros = string.Empty;
        for (var j = 0; j < extensionLength; j++)
        {
            zeros += "0";
        }
        return string.Format("xml.part{{0:{0}}}", zeros);
    }
}

To use it, you'd initialize it with the max file length and then serialize using the base file path and then the object.

public class MyType
{
    public int MyInt;
    public string MyString;
}

public void Test()
{
    var myObj = new MyType { MyInt = 42, 
                             MyString = "hello there this is my string" };
    new PartitionedXmlSerializer<MyType>(2)
        .Serialize("myFilename", myObj);
}

This particular example will generate an xml file partitioned into

myFilename.xml.part001
myFilename.xml.part002
myFilename.xml.part003
...
myFilename.xml.part110