Different behaviour between “new XmlTextReader” and “XmlReader.Create”

问题

Given the following source code:

 using System;
 using System.IO;
 using System.Xml;
 using System.Xml.Schema;

 namespace TheXMLGames
 {
   class Program
   {
     static void Main(string[] args)
     {
       XmlReaderSettings settings = new XmlReaderSettings {
         Async = false,
         ConformanceLevel = ConformanceLevel.Fragment,
         DtdProcessing = DtdProcessing.Ignore,
         ValidationFlags = XmlSchemaValidationFlags.None,
         ValidationType = ValidationType.None,
         XmlResolver = null,
       };

       string head = File.ReadAllText("sample.xml");
       Stream stringStream = GenerateStreamFromString(head);

       // Variant 1
       //XmlReader reader = XmlReader.Create(stringStream);

       // Variant 2
       //XmlReader reader = XmlReader.Create(stringStream, settings);

       // Variant 3
       XmlTextReader reader = new XmlTextReader(stringStream);

       while (reader.Read())
         if (reader.NodeType != XmlNodeType.Whitespace)
           Console.WriteLine(reader.Name + ": " + reader.Value);

       // No Variant gets here without an exception,
       // but that's not the point!

       Console.ReadKey();
     }

     public static Stream GenerateStreamFromString(string s)
     {
       MemoryStream stream = new MemoryStream();
       StreamWriter writer = new StreamWriter(stream);
       writer.Write(s);
       writer.Flush();
       stream.Position = 0;
       return stream;
     }
   }
 }

sample.xml

 <?xml version="1.0" encoding="utf-8"?>
 <!DOCTYPE TestingFacility >
 <TestingFacility id="MACHINE_2015-11-11T11_11_11" version="2015-11-11">

 <Program>
   <Title>title</Title>
   <Steps>16</Steps>
 </Program>
 <Calibration>
   <Current offset="0" gain="111.11" />
   <Voltage offset="0" gain="111.11" />
 </Calibration>
 <Info type="Facilityname" value="MACHINE" />
 <Info type="Hardwareversion" value="HW11" />
 <Info type="Account" value="DJohn" />
 <Info type="Teststart" value="2015-11-11T11:11:11" />
 <Info type="Description" value="desc" />
 <Info type="Profiler" value="prof" />
 <Info type="Target" value="trgt" />

The behaviour is the following:

Variant 1
XmlReader.Create(stream)
An unhandled exception of type 'System.Xml.XmlException' occurred in System.Xml.dll Additional information: For security reasons DTD is prohibited in this XML document. To enable DTD processing set the DtdProcessing property on XmlReaderSettings to Parse and pass the settings into XmlReader.Create method.

Variant 2
XmlReader.Create(stream, settings)
An unhandled exception of type 'System.Xml.XmlException' occurred in System.Xml.dll Additional information: Unexpected DTD declaration. Line 2, position 3.

Variant 3
new XmlTextReader(stringStream)
An unhandled exception of type 'System.Xml.XmlException' occurred in System.Xml.dll Additional information: Unexpected end of file has occurred. The following elements are not closed: TestingFacility. Line 19, position 36.

Variant 1 and 2 throw after the first line.
Variant 3 outputs the whole file as expected and when it gets to the end, it complains (correctly!).

The software works as I obviously use Variant 3, but the (now) recommended way is to use the Factory via XmlReader.Create

If I fiddle with the settings, it starts getting even more weird.

How can I get the code up-to-date and use XmlReader.Create?

The full project can be found here: https://drive.google.com/file/d/0B55cC50M31_8T0lub25oS2QxQ00/view

回答1:

I don't normally recommend using a NON XML method for parsing an XML file. But sometimes when the XML is not valid other methods are a better choice. Since you have a huge XML file and you are only trying to get one line of data the code below may be the best choice.

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Data;
using System.IO;
using System.Text.RegularExpressions;


namespace ConsoleApplication1
{
    class Program
    {
        static void Main(string[] args)
        {
            string xml =
                "<?xml version=\"1.0\" encoding=\"utf-8\"?>\n" +
                "<!DOCTYPE SomeDocTypeIdidntPutThere>\n" +
                "<TestingFacility id=\"MACHINE2_1970-01-01T11_22_33\" version=\"1970-01-01\">\n" +
                "<Program>\n" +
                  "<Title>Fancy Title</Title>\n" +
                  "<Steps>136</Steps>\n" +
                "</Program>\n" +
                "<Info type=\"Start\" value=\"2070-01-01T11:22:33\" />\n" +
                "<Info type=\"LotMoreOfThem\" value=\"42\" />\n";

            MemoryStream stream = new MemoryStream(Encoding.UTF8.GetBytes(xml));
            StreamReader reader = new StreamReader(stream);
            string inputLine = "";
            string timeStr = "";
            while ((inputLine = reader.ReadLine()) != null)
            {
                inputLine = inputLine.Trim();
                if(inputLine.StartsWith("<Info type=\"Start\""))
                {
                    string pattern = "value=\"(?'time'[^\"]+)";
                    timeStr = Regex.Match(inputLine, pattern).Groups["time"].Value;
                    break;
                }
            }
            DateTime time;
            if (timeStr.Length > 0)
            {
                time = DateTime.Parse(timeStr);
            }
        }
    }
}

​

回答2:

You xml is invalid. You are missing the closing tag and the DOCTYPE must match the root tag

<?xml version="1.0" encoding="utf-8"?>
<!DOCTYPE TestingFacility>
<TestingFacility id="MACHINE2_1970-01-01T11_22_33" version="1970-01-01">

  <Program>
    <Title>Fancy Title</Title>
    <Steps>136</Steps>
  </Program>
  <Info type="Start" value="2070-01-01T11:22:33" />
  <Info type="LotMoreOfThem" value="42" />
</TestingFacility>​

来源：https://stackoverflow.com/questions/34257204/different-behaviour-between-new-xmltextreader-and-xmlreader-create