我的问题是这个问题的延续：（loop for reading different data types & sizes off very large byte array from file）
我有一个存储在文件（rawbytes.txt或bytes.data）上的原始字节流，我需要解析并输出到CSV样式的文本文件。
原始字节的输入（当读取为字符/ long / int等时）看起来像这样：
A2401028475764B241102847576511001200C...
解析它应该看起来像：
OutputA.txt
(Field1,Field2,Field3) - heading
A,240,1028475764
OutputB.txt
(Field1,Field2,Field3,Field4,Field5) - heading
B,241,1028475765,1100,1200
OutputC.txt
C,...//and so on
本质上，它是一个十六进制转储式的字节输入，它是连续的，没有任何行终止符或需要解析的数据之间的间隙。如上所示，数据一个接一个地包含不同的数据类型。
这是我的代码片段 - 因为在任何字段中都没有逗号，并且不需要使用“”（即CSV包装器），我只是使用TextWriter来创建CSV样式的文本文件，如下所示：
if (File.Exists(fileName))
{
using (BinaryReader reader = new BinaryReader(File.Open(fileName, FileMode.Open)))
{
while (reader.BaseStream.Position != reader.BaseStream.Length)
{
inputCharIdentifier = reader.ReadChar();
switch (inputCharIdentifier)
case 'A':
field1 = reader.ReadUInt64();
field2 = reader.ReadUInt64();
field3 = reader.ReadChars(10);
string strtmp = new string(field3);
//and so on
using (TextWriter writer = File.AppendText("outputA.txt"))
{
writer.WriteLine(field1 + "," + field2 + "," + strtmp); // +
}
case 'B':
//code...
我的问题是基于以下事实：一些原始字节数据包含很难解析的空值 - 因为有一个未知个空字节数（或非空字节数，连续数据块之间的异常字节（如果数据块没有损坏，则每个字节以A，B或C开头）。
问题
那么，如果因为数据损坏或错误而可能出现错误，我如何添加默认情况或其他机制来继续循环？以下代码是否有效？
inputCharIdentifier = reader.ReadChar();
...
case default:
//I need to know what to add here, instead of default
//(i.e. the case when the character could not be read)
while (binReader.PeekChar() != -1)
{
filling = binReader.readByte();
//filling is a single byte
try {
fillingChar = Convert.ToChar(filling);
break;
}
catch (Exception ex) { break; }
if (fillingChar == 'A' || fillingChar == 'B')
break;
剩下的部分 - 在没有停止程序的情况下向每个开关案例（例如'A'）添加代码以继续 - 是否有办法在没有多个try-catch块的情况下执行此操作？ [即代码块字符标识符是A，但A之后的字节是损坏的 - 在这种情况下我需要退出循环或读取（即跳过）一定数量的字节 - 如果消息头正确识别，这里将是已知的剩余的字节。
[注意：情况A，B等具有不同大小的输入 - 换句话说，A可能总共40个字节，而B是50个字节。因此，使用固定大小的缓冲区，例如inputBuf [1000]或[50] - 如果它们的大小相同 - 也不会很好用，AFAIK。]
有什么建议吗？请帮忙！我对C＃相对较新（2个月）...
更新：我的整个代码如下：
class Program
{
const string fileName = "rawbytes.txt";
static void Main(string[] args)
{
try
{
var program = new Program();
program.Parser();
}
catch (Exception e)
{
Console.WriteLine(e);
}
Console.ReadLine();
}
public void Parser()
{
char inputCharIdentifier = 'Z';
//only because without initializing inputCharIdentifier I ended up with an error
//note that in the real code, 'Z' is not a switch-case alphabet
//it's an "inconsequential character", i.e. i have defined it to be 'Z'
//just to avoid that error, and to avoid leaving it as a null value
ulong field1common = 0;
ulong field2common = 0;
char[] charArray = new char[10];
char char1;
char char2;
char char3;
int valint1 = 0;
int valint2 = 0;
int valint3 = 0;
int valint4 = 0;
int valint5 = 0;
int valint6 = 0;
int valint7 = 0;
double valdouble;
/*
char[] filler = new char[53];
byte[] filling = new byte[4621];
byte[] unifiller = new byte[8];
//these values above were temporary measures to manually filter through
//null bytes - unacceptable for the final program
*/
if (File.Exists(fileName))
{
using (BinaryReader reader = new BinaryReader(File.Open(fileName, FileMode.Open)))
{
while (reader.BaseStream.Position != reader.BaseStream.Length)
{
//inputCharIdentifier = reader.ReadChar();
//if (inputCharIdentifier != null)
//{
try
{
inputCharIdentifier = reader.ReadChar();
try
{
switch (inputCharIdentifier)
{
case 'A':
field1common = reader.ReadUInt64();
field2common = reader.ReadUInt64();
//unifiller = reader.ReadBytes(8);
//charArray = reader.ReadString();
//result.ToString("o");
//Console.WriteLine(result.ToString());
charArray = reader.ReadChars(10);
string charArraystr = new string(charArray);
char1 = reader.ReadChar();
valint1 = reader.ReadInt32();
valint2 = reader.ReadInt32();
valint3 = reader.ReadInt32();
valint4 = reader.ReadInt32();
using (TextWriter writer = File.AppendText("A.txt"))
{
writer.WriteLine(field1common + "," + /*result.ToString("o")*/ field2common + "," + charArraystr + "," + char1 + "," + valint1 + "," + valint2 + "," + valint3 + "," + valint4);
writer.Close();
}
break;
case 'B':
case 'C':
field1common = reader.ReadUInt64();
field2common = reader.ReadUInt64();
//charArray = reader.ReadString();
charArray = reader.ReadChars(10);
string charArraystr2 = new string(charArray);
char1 = reader.ReadChar();
valint1 = reader.ReadInt32();
valint2 = reader.ReadInt32();
using (TextWriter writer = File.AppendText("C.txt"))
{
writer.WriteLine(field1common + "," + result2.ToString("o") + "," + charArraystr2 + "," + char1 + "," + valint1 + "," + valint2);
writer.Close();
}
break;
case 'S':
//market status message
field1common = reader.ReadUInt64();
char2 = reader.ReadChar();
char3 = reader.ReadChar();
break;
case 'L':
filling = reader.ReadBytes(4);
break;
case 'D':
case 'E':
field1common = reader.ReadUInt64();
field2common = reader.ReadUInt64();
//charArray = reader.ReadString();
charArray = reader.ReadChars(10);
string charArraystr3 = new string(charArray);
//char1 = reader.ReadChar();
valint1 = reader.ReadInt32();
valint2 = reader.ReadInt32();
valint5 = reader.ReadInt32();
valint7 = reader.ReadInt32();
valint6 = reader.ReadInt32();
valdouble = reader.ReadDouble();
using (TextWriter writer = File.AppendText("D.txt"))
{
writer.WriteLine(field1common + "," + result3.ToString("o") + "," + charArraystr3 + "," + valint1 + "," + valint2 + "," + valint5 + "," + valint7 + "," + valint6 + "," + valdouble);
writer.Close();
}
break;
}
}
catch (Exception ex)
{
Console.WriteLine("Parsing didn't work");
Console.WriteLine(ex.ToString());
break;
}
}
catch (Exception ex)
{
Console.WriteLine("Here's why the character read attempt didn't work");
Console.WriteLine(ex.ToString());
continue;
//continue;
}
//}
}
}
}
}
我收到的错误如下：
Here's why the character read attempt didn't work
System.ArgumentException: The output char buffer is too small to contain the decoded characters, encoding 'Unicode (UTF-8)' fallback 'System.Text.DecoderReplacementFallback'.
Parameter name: chars
at System.Text.Encoding.ThrowCharsOverflow()
at System.Text.Encoding.ThrowCharsOverflow(DecoderNLS decoder, Boolean nothingDecoded)
at System.Text.UTF8Encoding.GetChars(Byte* bytes, Int32 byteCount, Char* chars, Int32 charCount, DecoderNLS baseDecoder)
at System.Text.DecoderNLS.GetChars(Byte* bytes, Int32 byteCount, Char* chars, Int32 charCount, Boolean flush)
at System.Text.DecoderNLS.GetChars(Byte[] bytes, Int32 byteIndex, Int32 byteCount, Char[] chars, Int32 charIndex, Boolean flush)
at System.Text.DecoderNLS.GetChars(Byte[] bytes, Int32 byteIndex, Int32 byteCount, Char[] chars, Int32 charIndex)
at System.IO.BinaryReader.InternalReadOneChar()
at System.IO.BinaryReader.Read()
at System.IO.BinaryReader.ReadChar()
at line 69: i.e. inputCharIdentifier = reader.ReadChar();
更新：生成相同错误的示例文件位于以下链接： http://www.wikisend.com/download/106394/rawbytes.txt
特别注意连续数据块之间的8个意外空字节，即使数据块标题 - 即 inputCharIdentifier - 有效。此类标头后面的字节数始终不可预测并且通常会有所不同。我的问题是，当出现下一个可用的非损坏数据块时，我需要能够删除或跳过这种情况 - 在示例文件的情况下，最后一个（单个）数据块发生在8个不合适的空字节。
8个空字节可以在文件中找到，如下所示： 字节计数器：1056 第2行，第783栏（根据记事本++）
问题的关键在于8个空字节可以是任何大小--3,7,15,50等。它总是未知 - 作为数据损坏的直接结果。但与“传统”数据损坏不同，即在数据块内部固定数量的字节（例如50）可能不可读并因此可以跳过（通过确切的字节数） - 我面临的数据损坏包括：有效数据块之间的字节数未知。
答案 0 :(得分：2)
您无法为这些情况分配案例，因为目标变量（inputCharIdentifier）为null;因此，在避免这些情况的条件下就足够了。我还包括一个try ... catch，只是为了完全确定（执行所有给定操作时的任何错误都会使代码自动跳转到下面的迭代）。
try
{
using (BinaryReader reader = new BinaryReader(File.Open(fileName, FileMode.Open), Encoding.ASCII))
{
while (reader.BaseStream.Position != reader.BaseStream.Length)
{
inputCharIdentifier = reader.ReadChar();
if(inputCharIdentifier != null)
{
switch (inputCharIdentifier)
case 'A':
field1 = reader.ReadUInt64();
field2 = reader.ReadUInt64();
field3 = reader.ReadChars(10);
string strtmp = new string(field3);
//and so on
using (TextWriter writer = File.AppendText("outputA.txt"))
{
writer.WriteLine(field1 + "," + field2 + "," + strtmp);
}
case 'B':
//code...
}
}
}
}
catch
{
}