逐行读取文本文件,具有精确的偏移/位置报告

Question

我的简单要求:读取一个巨大的(>一百万)行测试文件(对于这个例子假设它是某种类型的CSV)并保持对该行开头的引用以便将来更快地查找(读取一行,从X).

我首先尝试了一种天真而简单的方法,使用a StreamWriter并访问底层BaseStream.Position.不幸的是,这不符合我的意图:

给定包含以下内容的文件

Foo
Bar
Baz
Bla
Fasel

这个非常简单的代码

using (var sr = new StreamReader(@"C:\Temp\LineTest.txt")) {
  string line;
  long pos = sr.BaseStream.Position;
  while ((line = sr.ReadLine()) != null) {
    Console.Write("{0:d3} ", pos);
    Console.WriteLine(line);
    pos = sr.BaseStream.Position;
  }
}

输出是:

000 Foo
025 Bar
025 Baz
025 Bla
025 Fasel

我可以想象,流正在尝试提供帮助/效率,并且可能在需要新数据时读入(大)块.对我来说这很糟糕..

最后的问题是:在没有使用基本Stream并且手动搞乱\ r \n\r \n和字符串编码等的情况下逐行读取文件时获取(byte,char)偏移量的方法是什么？没什么大不了的,真的,我只是不喜欢建造可能存在的东西......

Answer 1

您可以创建一个TextReader包装器,它将跟踪基础中的当前位置TextReader:

public class TrackingTextReader : TextReader
{
    private TextReader _baseReader;
    private int _position;

    public TrackingTextReader(TextReader baseReader)
    {
        _baseReader = baseReader;
    }

    public override int Read()
    {
        _position++;
        return _baseReader.Read();
    }

    public override int Peek()
    {
        return _baseReader.Peek();
    }

    public int Position
    {
        get { return _position; }
    }
}

然后您可以按如下方式使用它:

string text = @"Foo
Bar
Baz
Bla
Fasel";

using (var reader = new StringReader(text))
using (var trackingReader = new TrackingTextReader(reader))
{
    string line;
    while ((line = trackingReader.ReadLine()) != null)
    {
        Console.WriteLine("{0:d3} {1}", trackingReader.Position, line);
    }
}

Answer 2

经过搜索、测试并做了一些疯狂的事情之后，我的代码需要解决（我目前在我的产品中使用此代码）。

public sealed class TextFileReader : IDisposable
{

    FileStream _fileStream = null;
    BinaryReader _binReader = null;
    StreamReader _streamReader = null;
    List<string> _lines = null;
    long _length = -1;

    /// <summary>
    /// Initializes a new instance of the <see cref="TextFileReader"/> class with default encoding (UTF8).
    /// </summary>
    /// <param name="filePath">The path to text file.</param>
    public TextFileReader(string filePath) : this(filePath, Encoding.UTF8) { }

    /// <summary>
    /// Initializes a new instance of the <see cref="TextFileReader"/> class.
    /// </summary>
    /// <param name="filePath">The path to text file.</param>
    /// <param name="encoding">The encoding of text file.</param>
    public TextFileReader(string filePath, Encoding encoding)
    {
        if (!File.Exists(filePath))
            throw new FileNotFoundException("File (" + filePath + ") is not found.");

        _fileStream = new FileStream(filePath, FileMode.Open, FileAccess.Read, FileShare.Read);
        _length = _fileStream.Length;
        _binReader = new BinaryReader(_fileStream, encoding);
    }

    /// <summary>
    /// Reads a line of characters from the current stream at the current position and returns the data as a string.
    /// </summary>
    /// <returns>The next line from the input stream, or null if the end of the input stream is reached</returns>
    public string ReadLine()
    {
        if (_binReader.PeekChar() == -1)
            return null;

        string line = "";
        int nextChar = _binReader.Read();
        while (nextChar != -1)
        {
            char current = (char)nextChar;
            if (current.Equals('\n'))
                break;
            else if (current.Equals('\r'))
            {
                int pickChar = _binReader.PeekChar();
                if (pickChar != -1 && ((char)pickChar).Equals('\n'))
                    nextChar = _binReader.Read();
                break;
            }
            else
                line += current;
            nextChar = _binReader.Read();
        }
        return line;
    }

    /// <summary>
    /// Reads some lines of characters from the current stream at the current position and returns the data as a collection of string.
    /// </summary>
    /// <param name="totalLines">The total number of lines to read (set as 0 to read from current position to end of file).</param>
    /// <returns>The next lines from the input stream, or empty collectoin if the end of the input stream is reached</returns>
    public List<string> ReadLines(int totalLines)
    {
        if (totalLines < 1 && this.Position == 0)
            return this.ReadAllLines();

        _lines = new List<string>();
        int counter = 0;
        string line = this.ReadLine();
        while (line != null)
        {
            _lines.Add(line);
            counter++;
            if (totalLines > 0 && counter >= totalLines)
                break;
            line = this.ReadLine();
        }
        return _lines;
    }

    /// <summary>
    /// Reads all lines of characters from the current stream (from the begin to end) and returns the data as a collection of string.
    /// </summary>
    /// <returns>The next lines from the input stream, or empty collectoin if the end of the input stream is reached</returns>
    public List<string> ReadAllLines()
    {
        if (_streamReader == null)
            _streamReader = new StreamReader(_fileStream);
        _streamReader.BaseStream.Seek(0, SeekOrigin.Begin);
        _lines = new List<string>();
        string line = _streamReader.ReadLine();
        while (line != null)
        {
            _lines.Add(line);
            line = _streamReader.ReadLine();
        }
        return _lines;
    }

    /// <summary>
    /// Gets the length of text file (in bytes).
    /// </summary>
    public long Length
    {
        get { return _length; }
    }

    /// <summary>
    /// Gets or sets the current reading position.
    /// </summary>
    public long Position
    {
        get
        {
            if (_binReader == null)
                return -1;
            else
                return _binReader.BaseStream.Position;
        }
        set
        {
            if (_binReader == null)
                return;
            else if (value >= this.Length)
                this.SetPosition(this.Length);
            else
                this.SetPosition(value);
        }
    }

    void SetPosition(long position)
    {
        _binReader.BaseStream.Seek(position, SeekOrigin.Begin);
    }

    /// <summary>
    /// Gets the lines after reading.
    /// </summary>
    public List<string> Lines
    {
        get
        {
            return _lines;
        }
    }

    /// <summary>
    /// Performs application-defined tasks associated with freeing, releasing, or resetting unmanaged resources.
    /// </summary>
    public void Dispose()
    {
        if (_binReader != null)
            _binReader.Close();
        if (_streamReader != null)
        {
            _streamReader.Close();
            _streamReader.Dispose();
        }
        if (_fileStream != null)
        {
            _fileStream.Close();
            _fileStream.Dispose();
        }
    }

    ~TextFileReader()
    {
        this.Dispose();
    }
}