我有一些带有非法字符的大型XML Feed文件（0x1等）。这些文件是第三方的，我无法改变编写它们的过程。
我想使用XmlReader处理这些文件，但它会破坏这些非法字符。
我可以读取文件，过滤掉坏的字符，保存它们，然后处理它们......但这是很多I / O，看起来它应该是不必要的。
我想做的是这样的事情：
using(var origStream = File.OpenRead(fileName))
using(var cleanStream = new CleansedXmlStream(origStream))
using(var streamReader = new StreamReader(cleanStream))
using(var xmlReader = XmlReader.Create(streamReader))
{
//do stuff with reader
}
我尝试继承Stream，但是当我开始实施Read(byte[] buffer, int offset, int count)时，我失去了一些信心。毕竟，我打算删除字符，所以看起来计数会关闭，我必须将每个字节转换为char，这似乎很昂贵（特别是在大文件上）我不清楚这是怎么回事可以使用Unicode编码，但我的问题的答案并不直观明显。
在Google搜索“c＃stream wrapper”或“c＃filter stream”时，我的结果并不理想。我可能会使用错误的词语或描述错误的概念，所以我希望SO社区能够让我失望。
使用上面的示例，CleansedXmlStream会是什么样的？
这是我的第一次尝试：
public class CleansedXmlStream : Stream
{
private readonly Stream _baseStream;
public CleansedXmlStream(Stream stream)
{
this._baseStream = stream;
}
public new void Dispose()
{
if (this._baseStream != null)
{
this._baseStream.Dispose();
}
base.Dispose();
}
public override bool CanRead
{
get { return this._baseStream.CanRead; }
}
public override bool CanSeek
{
get { return this._baseStream.CanSeek; }
}
public override bool CanWrite
{
get { return this._baseStream.CanWrite; }
}
public override long Length
{
get { return this._baseStream.Length; }
}
public override long Position
{
get { return this._baseStream.Position; }
set { this._baseStream.Position = value; }
}
public override void Flush()
{
this._baseStream.Flush();
}
public override int Read(byte[] buffer, int offset, int count)
{
//what does this look like?
throw new NotImplementedException();
}
public override long Seek(long offset, SeekOrigin origin)
{
return this._baseStream.Seek(offset, origin);
}
public override void SetLength(long value)
{
this._baseStream.SetLength(value);
}
public override void Write(byte[] buffer, int offset, int count)
{
throw new NotSupportedException();
}
}
答案 0 :(得分：1)
受到@ CharlesMager评论的启发，我最终没有成为Stream，而是像StreamReader一样：
public class CleanTextReader : StreamReader
{
private readonly ILog _logger;
public CleanTextReader(Stream stream, ILog logger) : base(stream)
{
this._logger = logger;
}
public CleanTextReader(Stream stream) : this(stream, LogManager.GetLogger<CleanTextReader>())
{
//nothing to do here.
}
/// <summary>
/// Reads a specified maximum of characters from the current stream into a buffer, beginning at the specified index.
/// </summary>
/// <returns>
/// The number of characters that have been read, or 0 if at the end of the stream and no data was read. The number
/// will be less than or equal to the <paramref name="count" /> parameter, depending on whether the data is available
/// within the stream.
/// </returns>
/// <param name="buffer">
/// When this method returns, contains the specified character array with the values between
/// <paramref name="index" /> and (<paramref name="index + count - 1" />) replaced by the characters read from the
/// current source.
/// </param>
/// <param name="index">The index of <paramref name="buffer" /> at which to begin writing. </param>
/// <param name="count">The maximum number of characters to read. </param>
/// <exception cref="T:System.ArgumentException">
/// The buffer length minus <paramref name="index" /> is less than
/// <paramref name="count" />.
/// </exception>
/// <exception cref="T:System.ArgumentNullException"><paramref name="buffer" /> is null. </exception>
/// <exception cref="T:System.ArgumentOutOfRangeException">
/// <paramref name="index" /> or <paramref name="count" /> is
/// negative.
/// </exception>
/// <exception cref="T:System.IO.IOException">An I/O error occurs, such as the stream is closed. </exception>
public override int Read(char[] buffer, int index, int count)
{
try
{
var rVal = base.Read(buffer, index, count);
var filteredBuffer = buffer.Select(x => XmlConvert.IsXmlChar(x) ? x : ' ').ToArray();
Buffer.BlockCopy(filteredBuffer, 0, buffer, 0, count);
return rVal;
}
catch (Exception ex)
{
this._logger.Error("Read(char[], int, int)", ex);
throw;
}
}
/// <summary>
/// Reads a maximum of <paramref name="count" /> characters from the current stream, and writes the data to
/// <paramref name="buffer" />, beginning at <paramref name="index" />.
/// </summary>
/// <returns>
/// The position of the underlying stream is advanced by the number of characters that were read into
/// <paramref name="buffer" />.The number of characters that have been read. The number will be less than or equal to
/// <paramref name="count" />, depending on whether all input characters have been read.
/// </returns>
/// <param name="buffer">
/// When this method returns, this parameter contains the specified character array with the values
/// between <paramref name="index" /> and (<paramref name="index" /> + <paramref name="count" /> -1) replaced by the
/// characters read from the current source.
/// </param>
/// <param name="index">The position in <paramref name="buffer" /> at which to begin writing.</param>
/// <param name="count">The maximum number of characters to read. </param>
/// <exception cref="T:System.ArgumentNullException"><paramref name="buffer" /> is null. </exception>
/// <exception cref="T:System.ArgumentException">
/// The buffer length minus <paramref name="index" /> is less than
/// <paramref name="count" />.
/// </exception>
/// <exception cref="T:System.ArgumentOutOfRangeException">
/// <paramref name="index" /> or <paramref name="count" /> is
/// negative.
/// </exception>
/// <exception cref="T:System.ObjectDisposedException">The <see cref="T:System.IO.TextReader" /> is closed. </exception>
/// <exception cref="T:System.IO.IOException">An I/O error occurs. </exception>
public override int ReadBlock(char[] buffer, int index, int count)
{
try
{
var rVal = base.ReadBlock(buffer, index, count);
var filteredBuffer = buffer.Select(x => XmlConvert.IsXmlChar(x) ? x : ' ').ToArray();
Buffer.BlockCopy(filteredBuffer, 0, buffer, 0, count);
return rVal;
}
catch (Exception ex)
{
this._logger.Error("ReadBlock(char[], in, int)", ex);
throw;
}
}
/// <summary>
/// Reads the stream from the current position to the end of the stream.
/// </summary>
/// <returns>
/// The rest of the stream as a string, from the current position to the end. If the current position is at the end of
/// the stream, returns an empty string ("").
/// </returns>
/// <exception cref="T:System.OutOfMemoryException">
/// There is insufficient memory to allocate a buffer for the returned
/// string.
/// </exception>
/// <exception cref="T:System.IO.IOException">An I/O error occurs. </exception>
public override string ReadToEnd()
{
var chars = new char[4096];
int len;
var sb = new StringBuilder(4096);
while ((len = Read(chars, 0, chars.Length)) != 0)
{
sb.Append(chars, 0, len);
}
return sb.ToString();
}
}
我的单元测试如下：
[TestMethod]
public void CleanTextReaderCleans()
{
//arrange
var originalString = "The quick brown fox jumped over the lazy dog.";
var badChars = new string(new[] {(char) 0x1});
var concatenated = string.Concat(badChars, originalString);
//act
using (var stream = new MemoryStream(Encoding.UTF8.GetBytes(concatenated)))
{
using (var reader = new CleanTextReader(stream))
{
var newString = reader.ReadToEnd().Trim();
//assert
Assert.IsTrue(originalString.Equals(newString));
}
}
}
...并且用法如下：
using(var origStream = File.OpenRead(fileName))
using(var streamReader = new CleanTextReader(origStream))
using(var xmlReader = XmlReader.Create(streamReader))
{
//do stuff with reader
}
如果有人提出改进建议，我很乐意听到。
答案 1 :(得分：1)
我尝试了@JeremyHolovacs流实现，但它仍然不足以用于我的用例：
using (var fstream = File.OpenRead(dlpath))
{
using (var zstream = new GZipStream(fstream, CompressionMode.Decompress))
{
using (var xstream = new CleanTextReader(zstream))
{
var ser = new XmlSerializer(typeof(MyType));
prods = ser.Deserialize(XmlReader.Create(xstream, new XmlReaderSettings() { CheckCharacters = false })) as MyType;
}
}
}
不知道所有相关的重载都不是必须实现的。 我按照以下方式改编了课程，它按预期工作：
public class CleanTextReader : StreamReader
{
public CleanTextReader(Stream stream) : base(stream)
{
}
public override int Read()
{
var val = base.Read();
return XmlConvert.IsXmlChar((char)val) ? val : (char)' ';
}
public override int Read(char[] buffer, int index, int count)
{
var ret = base.Read(buffer, index, count);
for (int i=0; i<ret; i++)
{
int idx = index + i;
if (!XmlConvert.IsXmlChar(buffer[idx]))
buffer[idx] = ' ';
}
return ret;
}
public override int ReadBlock(char[] buffer, int index, int count)
{
var ret = base.ReadBlock(buffer, index, count);
for (int i = 0; i < ret; i++)
{
int idx = index + i;
if (!XmlConvert.IsXmlChar(buffer[idx]))
buffer[idx] = ' ';
}
return ret;
}
}