我遇到了一个问题，即从HttpResponseStream读取失败，因为我所包含的StreamReader读取速度更快，而Response Stream获得实际响应。我正在检索一个相当小的文件（大约60k），但是将响应处理成一个实际对象的Parser失败了，因为它遇到了一个意外的角色（代码65535），根据我所知道的经验，我知道这是你从StreamReader并没有其他可用字符。
对于记录，我知道返回的内容是有效的，并且将正确解析，因为每次运行代码时，文件中的不同点都会发生故障。它是下面的parser.Load（）行，它失败了。
有没有办法确保我在尝试解析之前读取所有内容，而不是将响应流复制到MemoryStream或字符串中然后再处理它？</ p>
/// <summary>
/// Makes a Query where the expected Result is an RDF Graph ie. CONSTRUCT and DESCRIBE Queries
/// </summary>
/// <param name="sparqlQuery">SPARQL Query String</param>
/// <returns>RDF Graph</returns>
public Graph QueryWithResultGraph(String sparqlQuery)
{
try
{
//Build the Query URI
StringBuilder queryUri = new StringBuilder();
queryUri.Append(this._endpoint.ToString());
queryUri.Append("?query=");
queryUri.Append(Uri.EscapeDataString(sparqlQuery));
if (!this._defaultGraphUri.Equals(String.Empty))
{
queryUri.Append("&default-graph-uri=");
queryUri.Append(Uri.EscapeUriString(this._defaultGraphUri));
}
//Make the Query via HTTP
HttpWebResponse httpResponse = this.DoQuery(new Uri(queryUri.ToString()),false);
//Set up an Empty Graph ready
Graph g = new Graph();
g.BaseURI = this._endpoint;
//Parse into a Graph based on Content Type
String ctype = httpResponse.ContentType;
IRDFReader parser = MIMETypesHelper.GetParser(ctype);
parser.Load(g, new StreamReader(httpResponse.GetResponseStream()));
return g;
}
catch (UriFormatException uriEx)
{
//URI Format Invalid
throw new Exception("The format of the URI was invalid", uriEx);
}
catch (WebException webEx)
{
//Some sort of HTTP Error occurred
throw new Exception("A HTTP Error occurred", webEx);
}
catch (RDFException)
{
//Some problem with the RDF or Parsing thereof
throw;
}
catch (Exception)
{
//Other Exception
throw;
}
}
/// <summary>
/// Internal Helper Method which executes the HTTP Requests against the SPARQL Endpoint
/// </summary>
/// <param name="target">URI to make Request to</param>
/// <param name="sparqlOnly">Indicates if only SPARQL Result Sets should be accepted</param>
/// <returns>HTTP Response</returns>
private HttpWebResponse DoQuery(Uri target, bool sparqlOnly)
{
//Expect errors in this function to be handled by the calling function
//Set-up the Request
HttpWebRequest httpRequest;
HttpWebResponse httpResponse;
httpRequest = (HttpWebRequest)WebRequest.Create(target);
//Use HTTP GET/POST according to user set preference
if (!sparqlOnly)
{
httpRequest.Accept = MIMETypesHelper.HTTPAcceptHeader();
//For the time being drop the application/json as this doesn't play nice with Virtuoso
httpRequest.Accept = httpRequest.Accept.Replace("," + MIMETypesHelper.JSON[0], String.Empty);
}
else
{
httpRequest.Accept = MIMETypesHelper.HTTPSPARQLAcceptHeader();
}
httpRequest.Method = this._httpMode;
httpRequest.Timeout = this._timeout;
//HTTP Debugging
if (Options.HTTPDebugging)
{
Tools.HTTPDebugRequest(httpRequest);
}
httpResponse = (HttpWebResponse)httpRequest.GetResponse();
//HTTP Debugging
if (Options.HTTPDebugging)
{
Tools.HTTPDebugResponse(httpResponse);
}
return httpResponse;
}
修改
为了澄清我已经说过的，不是 Parser中的一个错误，这是一个StreamReader读取速度比响应流提供数据更快的问题。我可以通过执行以下操作来解决这个问题，但希望提出更好或更优雅的解决方案：
//Parse into a Graph based on Content Type
String ctype = httpResponse.ContentType;
IRDFReader parser = MIMETypesHelper.GetParser(ctype);
Stream response = httpResponse.GetResponseStream();
MemoryStream temp = new MemoryStream();
Tools.StreamCopy(response, temp);
response.Close();
temp.Seek(0, SeekOrigin.Begin);
parser.Load(g, new StreamReader(temp));
修改2
根据Eamon的建议BlockingStreamReader类：
/// <summary>
/// A wrapper to a Stream which does all its Read() and Peek() calls using ReadBlock() to handle slow underlying streams (eg Network Streams)
/// </summary>
public sealed class BlockingStreamReader : StreamReader
{
private bool _peeked = false;
private int _peekChar = -1;
public BlockingStreamReader(StreamReader reader) : base(reader.BaseStream) { }
public BlockingStreamReader(Stream stream) : base(stream) { }
public override int Read()
{
if (this._peeked)
{
this._peeked = false;
return this._peekChar;
}
else
{
if (this.EndOfStream) return -1;
char[] cs = new char[1];
base.ReadBlock(cs, 0, 1);
return cs[0];
}
}
public override int Peek()
{
if (this._peeked)
{
return this._peekChar;
}
else
{
if (this.EndOfStream) return -1;
this._peeked = true;
char[] cs = new char[1];
base.ReadBlock(cs, 0, 1);
this._peekChar = cs[0];
return this._peekChar;
}
}
public new bool EndOfStream
{
get
{
return (base.EndOfStream && !this._peeked);
}
}
}
编辑3
这是一个大大改进的解决方案，可以包装任何TextReader并提供EndOfStream属性。它使用内部缓冲区，在包装的ReadBlock()上使用TextReader填充。可以使用此缓冲区定义读取器的所有Read（）方法，缓冲区大小可配置：
/// <summary>
/// The BlockingTextReader is an implementation of a <see cref="TextReader">TextReader</see> designed to wrap other readers which may or may not have high latency.
/// </summary>
/// <remarks>
/// <para>
/// This is designed to avoid premature detection of end of input when the input has high latency and the consumer tries to read from the input faster than it can return data. All methods are defined by using an internal buffer which is filled using the <see cref="TextReader.ReadBlock">ReadBlock()</see> method of the underlying <see cref="TextReader">TextReader</see>
/// </para>
/// </remarks>
public sealed class BlockingTextReader : TextReader
{
private char[] _buffer;
private int _pos = -1;
private int _bufferAmount = -1;
private bool _finished = false;
private TextReader _reader;
public const int DefaultBufferSize = 1024;
public BlockingTextReader(TextReader reader, int bufferSize)
{
if (reader == null) throw new ArgumentNullException("reader", "Cannot read from a null TextReader");
if (bufferSize < 1) throw new ArgumentException("bufferSize must be >= 1", "bufferSize");
this._reader = reader;
this._buffer = new char[bufferSize];
}
public BlockingTextReader(TextReader reader)
: this(reader, DefaultBufferSize) { }
public BlockingTextReader(Stream input, int bufferSize)
: this(new StreamReader(input), bufferSize) { }
public BlockingTextReader(Stream input)
: this(new StreamReader(input)) { }
private void FillBuffer()
{
this._pos = -1;
if (this._finished)
{
this._bufferAmount = 0;
}
else
{
this._bufferAmount = this._reader.ReadBlock(this._buffer, 0, this._buffer.Length);
if (this._bufferAmount == 0 || this._bufferAmount < this._buffer.Length) this._finished = true;
}
}
public override int ReadBlock(char[] buffer, int index, int count)
{
if (count == 0) return 0;
if (buffer == null) throw new ArgumentNullException("buffer");
if (index < 0) throw new ArgumentException("index", "Index must be >= 0");
if (count < 0) throw new ArgumentException("count", "Count must be >= 0");
if ((buffer.Length - index) < count) throw new ArgumentException("Buffer too small");
if (this._bufferAmount == -1 || this._pos >= this._bufferAmount)
{
if (!this._finished)
{
this.FillBuffer();
if (this.EndOfStream) return 0;
}
else
{
return 0;
}
}
this._pos = Math.Max(0, this._pos);
if (count <= this._bufferAmount - this._pos)
{
//If we have sufficient things buffered to fufill the request just copy the relevant stuff across
Array.Copy(this._buffer, this._pos, buffer, index, count);
this._pos += count;
return count;
}
else
{
int copied = 0;
while (copied < count)
{
int available = this._bufferAmount - this._pos;
if (count < copied + available)
{
//We can finish fufilling this request this round
int toCopy = Math.Min(available, count - copied);
Array.Copy(this._buffer, this._pos, buffer, index + copied, toCopy);
copied += toCopy;
this._pos += toCopy;
return copied;
}
else
{
//Copy everything we currently have available
Array.Copy(this._buffer, this._pos, buffer, index + copied, available);
copied += available;
this._pos = this._bufferAmount;
if (!this._finished)
{
//If we haven't reached the end of the input refill our buffer and continue
this.FillBuffer();
if (this.EndOfStream) return copied;
this._pos = 0;
}
else
{
//Otherwise we have reached the end of the input so just return what we've managed to copy
return copied;
}
}
}
return copied;
}
}
public override int Read(char[] buffer, int index, int count)
{
return this.ReadBlock(buffer, index, count);
}
public override int Read()
{
if (this._bufferAmount == -1 || this._pos >= this._bufferAmount - 1)
{
if (!this._finished)
{
this.FillBuffer();
if (this.EndOfStream) return -1;
}
else
{
return -1;
}
}
this._pos++;
return (int)this._buffer[this._pos];
}
public override int Peek()
{
if (this._bufferAmount == -1 || this._pos >= this._bufferAmount - 1)
{
if (!this._finished)
{
this.FillBuffer();
if (this.EndOfStream) return -1;
}
else
{
return -1;
}
}
return (int)this._buffer[this._pos + 1];
}
public bool EndOfStream
{
get
{
return this._finished && (this._pos >= this._bufferAmount - 1);
}
}
public override void Close()
{
this._reader.Close();
}
protected override void Dispose(bool disposing)
{
this.Close();
this._reader.Dispose();
base.Dispose(disposing);
}
}
答案 0 :(得分：1)
在不知道你正在使用的解析器的具体细节的情况下，我只能猜到这个bug，但是.NET框架I / O库几乎鼓励你制作一个相当容易犯错误的错误......
您是否意识到Streams和TextReaders可能读取的字节数/字符数少于请求的数量？
特别是TextReader.Read（char [] buffer，int index，int count）的文档说：
返回值
类型：System .. ::。Int32
已读取的字符数。该数字将 小于 或等于count，具体取决于数据是否在流中可用。如果在没有剩余字符需要读取时调用此方法，则返回零。
强调我的。
例如，如果你调用reader.Read（buffer，0,100），不能假设已经读取了100个字符。
编辑：解析器很可能会假设这一点;和这解释了你观察到的行为：如果你在MemoryStream中完全缓存了流，总会有足够的字符来满足请求 - 但是如果你没有，那么解析器将收到的字符数少于请求的数量在底层流“缓慢”时，在不可预测的时间。
Edit2：您可以通过使用TextReader.ReadBlock（）替换解析器中的所有TextReader.Read（）实例来修复您的错误。
答案 1 :(得分：0)
为了支持阻塞读取方案，而不是子类化StreamReader，您可以继承TextReader：这可以避免EndOfStream的问题，这意味着您可以使任何读者阻止 - 不只是StreamReader s：
public sealed class BlockingReader : TextReader
{
bool hasPeeked;
int peekChar;
readonly TextReader reader;
public BlockingReader(TextReader reader) { this.reader = reader; }
public override int Read()
{
if (!hasPeeked)
return reader.Read();
hasPeeked = false;
return peekChar;
}
public override int Peek()
{
if (!hasPeeked)
{
peekChar = reader.Read();
hasPeeked = true;
}
return peekChar;
}
public override int Read(char[] buffer, int index, int count)
{
if (buffer == null)
throw new ArgumentNullException("buffer");
if (index < 0)
throw new ArgumentOutOfRangeException("index");
if (count < 0)
throw new ArgumentOutOfRangeException("count");
if ((buffer.Length - index) < count)
throw new ArgumentException("Buffer too small");
int peekCharsRead = 0;
if (hasPeeked)
{
buffer[index] = (char)peekChar;
hasPeeked = false;
index++;
count--;
peekCharsRead++;
}
return peekCharsRead + reader.ReadBlock(buffer, index, count);
}
protected override void Dispose(bool disposing)
{
try
{
if (disposing)
reader.Dispose();
}
finally
{
base.Dispose(disposing);
}
}
}