将许多 XML 文件合并为单个流

Question

我有数百个一个接一个地处理的 XML 文件。我想将其他现有代码应用于文件中的数据。但是，编写该代码是为了期望单个文件或表示单个文件的流。

我看过

How do I concatenate two System.Io.Stream instances into one?

但是，Marc 的答案中提出的StreamEnumerator 要求同时打开所有相关文件的流。考虑到我的文件数量很多，这似乎不是一个好方法。

现有代码像这样使用流：

XmlReader reader = XmlReader.Create(xmlStream);

有没有更好的方法将多个文件合并到一个流中？

Answer 1

好吧，我会编写自己的扩展 System.IO.Stream 的类，并通过重载 CanRead 和 Read 方法按需加入这些流。像这样的东西（只是一个概念，你需要微调这段代码）：

using System;
using System.Diagnostics;
using System.IO;
using System.Xml;

namespace ConsoleApplication1
{

    public class CombinedXmlStream : Stream
    {
        private Stream currentStream, startStream, endStream;
        private String[] files;
        private int currentFile = -2;
        private bool endReached = false;

        private static Stream ToStream(String str)
        {
            MemoryStream stream = new MemoryStream();
            StreamWriter writer = new StreamWriter(stream);
            writer.Write(str);
            writer.Flush();
            stream.Position = 0;
            return stream;
        }

        public CombinedXmlStream(String start, String end, params String[] files)
        {
            this.files = files;
            startStream = ToStream(start);
            endStream = ToStream(end);

        }

        public override bool CanRead { get { return true; } }

        public override bool CanSeek { get { return false; } }

        public override bool CanWrite { get { return false; } }

        public override long Length { get { throw new NotImplementedException(); } }

        public override long Position { get { return 0; } set { } }

        public override void Flush() { throw new NotImplementedException(); }

        public override long Seek(long offset, SeekOrigin origin) { throw new NotImplementedException(); }

        public override void SetLength(long value) { throw new NotImplementedException(); }

        public override void Write(byte[] buffer, int offset, int count) { throw new NotImplementedException(); }

        public override int Read(byte[] buffer, int offset, int count)
        {
            doSwitching();

            int output = currentStream.Read(buffer, offset, count);

            if (output == 0)
            {
                doSwitching(true);
                if (currentStream != null)
                {
                    return Read(buffer, offset, count);
                }
            }

            return output;
        }

        private void doSwitching(bool force = false)
        {
            if (force || currentStream == null || !currentStream.CanRead)
            {
                if (currentStream != null)
                {
                    currentStream.Close();
                    currentStream = null;
                }

                currentFile++;
                if (currentFile == -1)
                {
                    currentStream = startStream;
                }
                else if (currentFile >= files.Length && !endReached)
                {
                    currentStream = endStream;
                    endReached = true;
                }
                else if (!endReached)
                {
                    currentStream = new FileStream(files[currentFile], FileMode.Open);
                }
            }
        }
    }

    class Program
    {
        static void Main(string[] args)
        {
            Debug.WriteLine("Test me");
            using (XmlReader reader = XmlReader.Create(new CombinedXmlStream("<combined>", "</combined>", @"D:\test.xml", @"D:\test2.xml")))
            {
                //reader.MoveToContent();
                while (reader.Read())
                {
                    if (reader.NodeType == XmlNodeType.Element)
                    {
                        Debug.WriteLine("Node: " + reader.Name);
                    }
                }
            }
        }
    }
}