如何更改此XML字符串，以便XDocument.Parse将其读入？

Question

在下面的代码中，我将序列化为一个对象为XML 字符串。

但是，当我尝试读取这个XML字符串到一个XDocument与XDocument.Parse，它给了我这个错误：

无效的数据在根目录下。

的XML是：

<?xml version="1.0" encoding="utf-8"?> 
<Customer xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"> 
    <Id>1</Id> 
    <FirstName>Jim</FirstName> 
    <LastName>Jones</LastName> 
    <ZipCode>23434</ZipCode> 
</Customer> 

UPDATE：这里是十六进制：

alt text http://www.deviantsart.com/upload/hhcvmu.png

我有什么做的这个XML，以便它读入XDocument没有错误？

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

namespace TestSerialize2342 
{ 
    class Program 
    { 
     static void Main(string[] args) 
     { 
      List<Customer> customers = Customer.GetCustomers(); 

      Console.WriteLine("--- Serializing ------------------"); 

      foreach (var customer in customers) 
      { 
       Console.WriteLine("Serializing " + customer.GetFullName() + "..."); 
       string xml = XmlHelpers.SerializeObject<Customer>(customer); 

       XDocument xdoc = XDocument.Parse(xml); 

      } 

      Console.ReadLine(); 
     } 

    } 

    public static class StringHelpers 
    { 
     public static String UTF8ByteArrayToString(Byte[] characters) 
     { 
      UTF8Encoding encoding = new UTF8Encoding(); 
      String constructedString = encoding.GetString(characters); 
      return (constructedString); 
     } 

     public static Byte[] StringToUTF8ByteArray(String pXmlString) 
     { 
      UTF8Encoding encoding = new UTF8Encoding(); 
      Byte[] byteArray = encoding.GetBytes(pXmlString); 
      return byteArray; 
     } 
    } 

    public static class XmlHelpers 
    { 
     public static string SerializeObject<T>(object o) 
     { 
      MemoryStream ms = new MemoryStream(); 
      XmlSerializer xs = new XmlSerializer(typeof(T)); 
      XmlTextWriter xtw = new XmlTextWriter(ms, Encoding.UTF8); 
      xs.Serialize(xtw, o); 
      ms = (MemoryStream)xtw.BaseStream; 
      return StringHelpers.UTF8ByteArrayToString(ms.ToArray()); 
     } 

     public static T DeserializeObject<T>(string xml) 
     { 
      XmlSerializer xs = new XmlSerializer(typeof(T)); 
      MemoryStream ms = new MemoryStream(StringHelpers.StringToUTF8ByteArray(xml)); 
      XmlTextWriter xtw = new XmlTextWriter(ms, Encoding.UTF8); 
      return (T)xs.Deserialize(ms); 
     } 
    } 

    public class Customer 
    { 
     public int Id { get; set; } 
     public string FirstName { get; set; } 
     public string LastName { get; set; } 
     public string Street { get; set; } 
     public string Location { get; set; } 
     public string ZipCode { get; set; } 

     private int internalValue = 23; 

     public static List<Customer> GetCustomers() 
     { 
      List<Customer> customers = new List<Customer>(); 
      customers.Add(new Customer { Id = 1, FirstName = "Jim", LastName = "Jones", ZipCode = "23434" }); 
      customers.Add(new Customer { Id = 2, FirstName = "Joe", LastName = "Adams", ZipCode = "12312" }); 
      customers.Add(new Customer { Id = 3, FirstName = "Jack", LastName = "Johnson", ZipCode = "23111" }); 
      customers.Add(new Customer { Id = 4, FirstName = "Angie", LastName = "Reckar", ZipCode = "54343" }); 
      customers.Add(new Customer { Id = 5, FirstName = "Henry", LastName = "Anderson", ZipCode = "16623" }); 
      return customers; 
     } 

     public string GetFullName() 
     { 
      return FirstName + " " + LastName + "(" + internalValue + ")"; 
     } 

    } 
} 

答：

感谢安德拉斯，GetPreamble（）固定，所以对任何人处理这个，这里是清洁您的BOM的XML少许方法：

public static string RemoveUtf8ByteOrderMark(string xml) 
{ 
    string byteOrderMarkUtf8 = Encoding.UTF8.GetString(Encoding.UTF8.GetPreamble()); 
    if (xml.StartsWith(byteOrderMarkUtf8)) 
    { 
     xml = xml.Remove(0, byteOrderMarkUtf8.Length); 
    } 
    return xml; 
} 

Answer 1

这是因为数据包含流的开始处的unicode或utf8 BOM marks。

您需要跳过流中的任何字节顺序标记 - 您可以使用System.Text.Encoding.GetPreamble()方法识别这些标记。

Answer 2

您可以通过使用StreamReader在MemoryStream将数据转换为字符串，而不是解决问题的方法：

public static string SerializeObject<T>(object o) 
{ 
    using (MemoryStream ms = new MemoryStream()) 
    { 
     XmlSerializer xs = new XmlSerializer(typeof(T)); 
     using (XmlWriter xtw = XmlWriter.Create(ms)) 
     { 
      xs.Serialize(xtw, o); 
      xtw.Flush(); 
      ms.Seek(0, SeekOrigin.Begin); 
      using (StreamReader reader = new StreamReader(ms)) 
      { 
       return reader.ReadToEnd(); 
      } 
     } 
    } 
} 

Answer 3

以上所有是正确的，这里要说的是，你应该使用的，而不是你的代码跳过BOM：

public static string SerializeObject<T>(object o) 
     { 
      MemoryStream ms = new MemoryStream(); 
      XmlSerializer xs = new XmlSerializer(typeof(T)); 
      //here is my code 
      UTF8Encoding encoding = new UTF8Encoding(false); 
      XmlTextWriter xtw = new XmlTextWriter(ms, encoding); 
      //XmlTextWriter xtw = new XmlTextWriter(ms, Encoding.UTF8); 
      xs.Serialize(xtw, o); 
      ms = (MemoryStream)xtw.BaseStream; 
      return StringHelpers.UTF8ByteArrayToString(ms.ToArray()); 
     } 

通过构造函数中指定假你说 “BOM不提供”。请享用！ =）