我的简单要求：读取一个巨大的（>一百万行）测试文件（对于此示例，假设它是某种类型的CSV）并保留对该行开头的引用，以便将来更快地查找（读取行，从X开始。
我首先尝试使用StreamWriter并访问基础BaseStream.Position的简单方法。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..
问题，最后：在不使用基本流并且手动搞乱\ r \ n \ r \ n和字符串编码等的情况下逐行读取文件时获取（字节，字符）偏移的任何方法？没什么大不了的，真的，我只是不喜欢建造可能存在的东西......
答案 0 :(得分：11)
您可以创建一个TextReader包装器，它会跟踪基座TextReader中的当前位置：
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);
}
}
答案 1 :(得分：4)
在搜索，测试并做一些疯狂的事情之后，我的代码就要解决了（我目前正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();
}
}
答案 2 :(得分：2)
虽然Thomas Levesque的解决方案运作良好，但这是我的。它使用反射，因此速度较慢，但它与编码无关。另外我也添加了Seek扩展。
/// <summary>Useful <see cref="StreamReader"/> extentions.</summary>
public static class StreamReaderExtentions
{
/// <summary>Gets the position within the <see cref="StreamReader.BaseStream"/> of the <see cref="StreamReader"/>.</summary>
/// <remarks><para>This method is quite slow. It uses reflection to access private <see cref="StreamReader"/> fields. Don't use it too often.</para></remarks>
/// <param name="streamReader">Source <see cref="StreamReader"/>.</param>
/// <exception cref="ArgumentNullException">Occurs when passed <see cref="StreamReader"/> is null.</exception>
/// <returns>The current position of this stream.</returns>
public static long GetPosition(this StreamReader streamReader)
{
if (streamReader == null)
throw new ArgumentNullException("streamReader");
var charBuffer = (char[])streamReader.GetType().InvokeMember("charBuffer", BindingFlags.DeclaredOnly | BindingFlags.NonPublic | BindingFlags.Instance | BindingFlags.GetField, null, streamReader, null);
var charPos = (int)streamReader.GetType().InvokeMember("charPos", BindingFlags.DeclaredOnly | BindingFlags.NonPublic | BindingFlags.Instance | BindingFlags.GetField, null, streamReader, null);
var charLen = (int)streamReader.GetType().InvokeMember("charLen", BindingFlags.DeclaredOnly | BindingFlags.NonPublic | BindingFlags.Instance | BindingFlags.GetField, null, streamReader, null);
var offsetLength = streamReader.CurrentEncoding.GetByteCount(charBuffer, charPos, charLen - charPos);
return streamReader.BaseStream.Position - offsetLength;
}
/// <summary>Sets the position within the <see cref="StreamReader.BaseStream"/> of the <see cref="StreamReader"/>.</summary>
/// <remarks>
/// <para><see cref="StreamReader.BaseStream"/> should be seekable.</para>
/// <para>This method is quite slow. It uses reflection and flushes the charBuffer of the <see cref="StreamReader.BaseStream"/>. Don't use it too often.</para>
/// </remarks>
/// <param name="streamReader">Source <see cref="StreamReader"/>.</param>
/// <param name="position">The point relative to origin from which to begin seeking.</param>
/// <param name="origin">Specifies the beginning, the end, or the current position as a reference point for origin, using a value of type <see cref="SeekOrigin"/>. </param>
/// <exception cref="ArgumentNullException">Occurs when passed <see cref="StreamReader"/> is null.</exception>
/// <exception cref="ArgumentException">Occurs when <see cref="StreamReader.BaseStream"/> is not seekable.</exception>
/// <returns>The new position in the stream. This position can be different to the <see cref="position"/> because of the preamble.</returns>
public static long Seek(this StreamReader streamReader, long position, SeekOrigin origin)
{
if (streamReader == null)
throw new ArgumentNullException("streamReader");
if (!streamReader.BaseStream.CanSeek)
throw new ArgumentException("Underlying stream should be seekable.", "streamReader");
var preamble = (byte[])streamReader.GetType().InvokeMember("_preamble", BindingFlags.DeclaredOnly | BindingFlags.NonPublic | BindingFlags.Instance | BindingFlags.GetField, null, streamReader, null);
if (preamble.Length > 0 && position < preamble.Length) // preamble or BOM must be skipped
position += preamble.Length;
var newPosition = streamReader.BaseStream.Seek(position, origin); // seek
streamReader.DiscardBufferedData(); // this updates the buffer
return newPosition;
}
}
答案 3 :(得分：2)
这是一个非常棘手的问题。 经过互联网上不同解决方案的漫长而耗尽的计算（包括此线程的解决方案，谢谢！）我不得不创建自己的自行车。
我有以下要求：
稳定 - 在使用过程中立即看到单字节错误。对我来说不幸的是，我发现的几个实现都存在稳定性问题
public class OffsetStreamReader
{
private const int InitialBufferSize = 4096;
private readonly char _bom;
private readonly byte _end;
private readonly Encoding _encoding;
private readonly Stream _stream;
private readonly bool _tail;
private byte[] _buffer;
private int _processedInBuffer;
private int _informationInBuffer;
public OffsetStreamReader(Stream stream, bool tail)
{
_buffer = new byte[InitialBufferSize];
_processedInBuffer = InitialBufferSize;
if (stream == null || !stream.CanRead)
throw new ArgumentException("stream");
_stream = stream;
_tail = tail;
_encoding = Encoding.UTF8;
_bom = '\uFEFF';
_end = _encoding.GetBytes(new [] {'\n'})[0];
}
public long Offset { get; private set; }
public string ReadLine()
{
// Underlying stream closed
if (!_stream.CanRead)
return null;
// EOF
if (_processedInBuffer == _informationInBuffer)
{
if (_tail)
{
_processedInBuffer = _buffer.Length;
_informationInBuffer = 0;
ReadBuffer();
}
return null;
}
var lineEnd = Search(_buffer, _end, _processedInBuffer);
var haveEnd = true;
// File ended but no finalizing newline character
if (lineEnd.HasValue == false && _informationInBuffer + _processedInBuffer < _buffer.Length)
{
if (_tail)
return null;
else
{
lineEnd = _informationInBuffer;
haveEnd = false;
}
}
// No end in current buffer
if (!lineEnd.HasValue)
{
ReadBuffer();
if (_informationInBuffer != 0)
return ReadLine();
return null;
}
var arr = new byte[lineEnd.Value - _processedInBuffer];
Array.Copy(_buffer, _processedInBuffer, arr, 0, arr.Length);
Offset = Offset + lineEnd.Value - _processedInBuffer + (haveEnd ? 1 : 0);
_processedInBuffer = lineEnd.Value + (haveEnd ? 1 : 0);
return _encoding.GetString(arr).TrimStart(_bom).TrimEnd('\r', '\n');
}
private void ReadBuffer()
{
var notProcessedPartLength = _buffer.Length - _processedInBuffer;
// Extend buffer to be able to fit whole line to the buffer
// Was [NOT_PROCESSED]
// Become [NOT_PROCESSED ]
if (notProcessedPartLength == _buffer.Length)
{
var extendedBuffer = new byte[_buffer.Length + _buffer.Length/2];
Array.Copy(_buffer, extendedBuffer, _buffer.Length);
_buffer = extendedBuffer;
}
// Copy not processed information to the begining
// Was [PROCESSED NOT_PROCESSED]
// Become [NOT_PROCESSED ]
Array.Copy(_buffer, (long) _processedInBuffer, _buffer, 0, notProcessedPartLength);
// Read more information to the empty part of buffer
// Was [ NOT_PROCESSED ]
// Become [ NOT_PROCESSED NEW_NOT_PROCESSED ]
_informationInBuffer = notProcessedPartLength + _stream.Read(_buffer, notProcessedPartLength, _buffer.Length - notProcessedPartLength);
_processedInBuffer = 0;
}
private int? Search(byte[] buffer, byte byteToSearch, int bufferOffset)
{
for (int i = bufferOffset; i < buffer.Length - 1; i++)
{
if (buffer[i] == byteToSearch)
return i;
}
return null;
}
}
答案 4 :(得分：0)
这会有效吗？
using (var sr = new StreamReader(@"C:\Temp\LineTest.txt")) {
string line;
long pos = 0;
while ((line = sr.ReadLine()) != null) {
Console.Write("{0:d3} ", pos);
Console.WriteLine(line);
pos += line.Length;
}
}