System.Xml.XmlException '根级别的数据无效，第 1 行，position 1' 当我从 1 Z0F635D0E0F3874FFF8B581C1532E6C7A7Z 文件更改时出现错误

Question

Hello everyone recently i have been making a c# app to read a xml file and it worked but now i was tasked with making it do that and read certain nodes from multiple xml files inside a certain folder and now i doesen´t work and shows that error in the title.

using System;
using System.Xml;
using System.IO;
namespace XmlReaderConsoleAPP
{
    class Program
    {
       
        static void Main()
        {
            ProcessFile(@"C:\XMLFiles\SaintGobain_Pam_20210118.xml");
            try
            {
               
                var path = @"C:\XMLFiles\SaintGobain_Pam_20210118.xml";
                DirectoryInfo di = new DirectoryInfo(path);

                foreach (var file in Directory.GetFiles(path))
                {
                   
                }
                Console.ReadKey();
            }
             catch(Exception ex)
            {

                Console.WriteLine("Erro: {0}", ex.Message);
                return;
            }

            static void ProcessFile(string Filename)
            {
                XmlDocument xml = new XmlDocument();
                xml.LoadXml(Filename);
                XmlNodeList xnLista = xml.SelectNodes(@"//ImportSession/Batches/batch/Documents/Document/Pages/Page");
                Console.WriteLine($"Selected {xnLista.Count} nodes");
                int i = 0;

                foreach (XmlNode xn in xnLista)
                {

                    Console.WriteLine($"{++i} {xn.Name}: {xn.Attributes["ImportFileName"].Value}");



                }

                XmlNodeList xnLista2 = xml.SelectNodes(@"//IndexFields/IndexField");
                Console.WriteLine($"Selected {xnLista2.Count} nodes");
               int j = 0;
                foreach (XmlNode xn in xnLista2)
                {


                    Console.WriteLine($"{++j} {xn.Name}: {xn.Attributes["Value"].Value}");

                    //string error = xn.Attributes["ErrorMessage"]?.Value;
                    //if (string.IsNullOrEmpty(error))
                    //{



                    //}

                    //elsex
                    //{


                    //}
                }
                Console.WriteLine(Filename);
            }

           
        }
    }
}

If you guys find the error help me out cause i need it. Ps: the xml files follow the same roots ImportSession/Batches/Batch/Documents/Document/Pages/Page

Answer 1

Let's first clean up a little:

namespace XmlReaderConsoleAPP
{
    class Program
    {
        static void Main()
        {
                var path = @"C:\XMLFiles";
                var filter = @"*.xml"; // Add filter to only enumerate .xml files

                foreach (var file in Directory.EnumerateFiles(path, filter))
                {
// Move try/catch inside the loop to skip errornous files.
                   try
                   {
                       ProcessFile( file );
                   }
                   catch(Exception ex) // Usually, try to catch the specific as possible
                   {
                        Console.WriteLine("Error: {0} {1}in File {2}", 
                                            ex.Message, Environment.NewLine, file);
                   }
                }
                Console.ReadKey();
            }
        } // End of Main

            static void ProcessFile(string Filename)
            {
                XmlDocument xml = new XmlDocument();
                xml.LoadXml(Filename);
                XmlNodeList xnLista = xml.SelectNodes(@"//ImportSession/Batches/batch/Documents/Document/Pages/Page");
                Console.WriteLine($"Selected {xnLista.Count} nodes");
                int i = 0;

                foreach (XmlNode xn in xnLista)
                {
                    Console.WriteLine($"{++i} {xn.Name}: {xn.Attributes["ImportFileName"].Value}");
                }

                XmlNodeList xnLista2 = xml.SelectNodes(@"//IndexFields/IndexField");
                Console.WriteLine($"Selected {xnLista2.Count} nodes");
               int j = 0;
                foreach (XmlNode xn in xnLista2)
                {
                    Console.WriteLine($"{++j} {xn.Name}: {xn.Attributes["Value"].Value}");
                }
                Console.WriteLine(Filename);
            }
           
    } // class
} // namespace

Next: System.Xml.XmlException means there is something wrong with the xml input file.

What can you do about that?

• Skip it, so the others may still be processed. Log the error, so you can later deep dive into the file, or request it be fixed and sent again.

• If you have an XML Schema, you can validate the xml and easier find what exactly is wrong. See XML schema (XSD) validation with XmlSchemaSet and/or XmlDocument.Validate Method .

• You can examine the input file manually and find the error. Mind that the message may sometimes be deceiving. I'd start with checking if it is well-formed and valid xml (there are tools for that).

Answer 2

I was able to resolve the problem with objects and their serialization. You can find a way to do it with these two posts:

Objects: https://docs.microsoft.com/en-us/dotnet/csharp/programming-guide/classes-and-structs/objects

Objects serialization: https://docs.microsoft.com/en-us/dotnet/standard/serialization/how-to-serialize-an-object

Giving some more context.

Start by making empty strings at the start of the method you're doing, it being a foreach loop or a if statement

class Program
{
    static DataAccess da = new DataAccess();

    public static void Main()
    {
        XmlSerializer serializer = new XmlSerializer(typeof(ImportSession));

        foreach (string filename in Directory.EnumerateFiles(Properties.Settings.Default.PastaXML, "*.xml"))
        {
            string fName = "";
            string BatchCName = "";
            string batchName = "";
            string description = "";

            ProcessFile(filename, serializer, fName, BatchCName, batchName, description );
        }

        Console.ReadKey();
    }
}

After that start in my case my processfile function

private static void ProcessFile(string filename, XmlSerializer serializer, string fName, string batchName, string description, string BatchCName)
    {
        Console.WriteLine("A processar xml: " + filename);
        bool temErro = false;
       
        using (FileStream file = File.OpenRead(filename))
        {
            var session = (ImportSession)serializer.Deserialize(file);
     
            foreach (Batch batch in session.Batches)
            {
                fName = Path.GetFileName(filename);
                BatchCName = batch.BatchClassName;
                batchName = batch.Name;
                description = batch.Description;
                foreach (Document doc in batch.Documents)
                {
                    foreach (Page page in doc.Pages)
                    {
            @            if (!string.IsNullOrEmpty(batch.Processed.ToString()))
                        {
                            if (page.HasError)
                            {
                               
                                string Import = page.ImportFileName;
                                Console.WriteLine("Página com erro:" + Import + fName);
                                temErro = true;                                
                                da.SP_Insert(filename,fName,BatchCName,batchName,description,1,Import,0, "");

There are two if statements inside this processfile that run checks on if there is a error inside the file and if the file as already been processed.

I also added Insert into a stored procedure to make sure everything is complete in this edit I'm making.

The objects I used are as follows

public class ImportSession
{
    public Batch[] Batches { get; set; }
}

public class Batch
{
    [XmlAttribute]
    public string Name { get; set; }
    [XmlAttribute]
    public string Description { get; set; }
    [XmlAttribute]
    public string BatchClassName { get; set; }
    [XmlAttribute]
    public bool Processed { get; set; }
    public Document[] Documents { get; set; }
}

public class Document
{
    [XmlAttribute]
    public string FormTypeName { get; set; }
    public IndexField[] IndexFields { get; set; }
    public Page[] Pages { get; set; }
}

public class IndexField
{
    [XmlAttribute]
    public string Name { get; set; }
    [XmlAttribute]
    public string Value { get; set; }
}

public class Page
{
    [XmlAttribute]
    public string ImportFileName { get; set; }
    [XmlAttribute]
    public string ErrorCode { get; set; }
    [XmlAttribute]
    public string ErrorMessage { get; set; }
    [XmlIgnore]
    public bool HasError => !string.IsNullOrWhiteSpace(ErrorMessage);
}

And my stored procedure insert in case any of you are wondering how to do it

public void SP_Insert(string XMLPath, string XMLName, string BatchClassName, string BatchName,
        string BatchDescription, int Error, string ErrorImagePath, int Done, string DonePath)
    {

        try
        {
            ManageConnectionState();
            SqlCommand command = new SqlCommand("Sp_Insert", connection);
            command.CommandType = CommandType.StoredProcedure;
            command.Parameters.Add("@XMLPath",SqlDbType.NText).Value = XMLPath;
            command.Parameters.Add("@XMLName",SqlDbType.NText).Value = XMLName;
            command.Parameters.Add("@BatchClassName",SqlDbType.NText).Value= BatchClassName;
            command.Parameters.Add("@BatchName",SqlDbType.NText ).Value = BatchName;
            command.Parameters.Add("@BatchDescription", SqlDbType.NText ).Value = BatchDescription;
            command.Parameters.Add("@Error",SqlDbType.Bit).Value = Error;
            command.Parameters.Add("@ErrorImagePath", SqlDbType.NText).Value = ErrorImagePath;
            command.Parameters.Add("@Done", SqlDbType.Bit ).Value=Done;
            command.Parameters.Add("@DonePath", SqlDbType.NText).Value = DonePath;
            command.ExecuteScalar();


        }
        catch (Exception ex)
        {
            Console.WriteLine("Erro: " + ex.Message);
        }
        finally
        {
            ManageConnectionState();
            connection.Close();
        }
    }

Please comment if you don´t understand something ill help out.