我目前正在研究一个网络工具,该工具需要解码/编码一个特定的协议,该协议将字段打包成任意位置的密集位数组。例如,协议的一部分使用3个字节来表示许多不同的字段:
Bit Position(s) Length (In Bits) Type
0 1 bool
1-5 5 int
6-13 8 int
14-22 9 uint
23 1 bool
可以看到,有几个字段跨越多个字节。许多(大多数)也比可能用于表示它们的内置类型短,例如第一个int字段只有5位长。在这种情况下,目标类型(如Int32或Int16)的最高有效位应该用0填充以弥补差异。
我的问题是我很难处理这类数据。具体来说,我很难弄清楚如何有效地获得任意长度的位数组,用来自源缓冲区的适当位填充它们,填充它们以匹配目标类型,并将填充的位数组转换为目标类型。在理想的情况下,我将能够在上面的例子中获取字节[3]并调用类似GetInt32(byte[] bytes, int startBit, int length)
的方法。
我发现最接近的是一个BitStream类,但它似乎希望单个值在字节/字边界上排列(类的半流/半索引访问约定使其有点混乱)。
我自己的第一次尝试是使用BitArray类,但这被证明有些笨拙。很容易将缓冲区中的所有位填充到一个大的BitArray
中,仅将您想要的位从源BitArray
转移到新的临时BitArray
,然后将其转换为目标值……但这似乎是错误的,而且非常耗时。
我现在正在考虑一个像下面这样的类,它引用(或创建)一个源/目标字节[]缓冲区以及一个偏移量,并为某些目标类型提供get和set方法。棘手的部分是获取/设置值可能跨越多个字节。
class BitField
{
private readonly byte[] _bytes;
private readonly int _offset;
public BitField(byte[] bytes)
: this(bytes, 0)
{
}
public BitField(byte[] bytes, int offset)
{
_bytes = bytes;
_offset = offset;
}
public BitField(int size)
: this(new byte[size], 0)
{
}
public bool this[int bit]
{
get { return IsSet(bit); }
set { if (value) Set(bit); else Clear(bit); }
}
public bool IsSet(int bit)
{
return (_bytes[_offset + (bit / 8)] & (1 << (bit % 8))) != 0;
}
public void Set(int bit)
{
_bytes[_offset + (bit / 8)] |= unchecked((byte)(1 << (bit % 8)));
}
public void Clear(int bit)
{
_bytes[_offset + (bit / 8)] &= unchecked((byte)~(1 << (bit % 8)));
}
//startIndex = the index of the bit at which to start fetching the value
//length = the number of bits to include - may be less than 32 in which case
//the most significant bits of the target type should be padded with 0
public int GetInt32(int startIndex, int length)
{
//NEED CODE HERE
}
//startIndex = the index of the bit at which to start storing the value
//length = the number of bits to use, if less than the number of bits required
//for the source type, precision may be lost
//value = the value to store
public void SetValue(int startIndex, int length, int value)
{
//NEED CODE HERE
}
//Other Get.../Set... methods go here
}
我正在寻找这方面的任何指导,例如第三方库,在跨越多个字节的任意位位置获取/设置值的算法,对我的方法的反馈等。我包含上面的类是为了澄清,并不一定要寻找代码来填充它(尽管如果有人想要解决它,我不会争论!)。
正如所承诺的,这是我最终为此目的创建的类。它将在可选指定的索引处包装任意字节数组,并允许在位级别上读/写。它提供了从其他字节数组读取/写入任意位块的方法,或读取/写入带有用户定义偏移量和长度的原始值的方法。它非常适合我的情况,并解决了我上面问的确切问题。然而,它确实有一些缺点。首先,它显然没有大量的文档记录——我只是没有时间。第二是没有边界或其他检查。它目前还需要MiscUtil库提供端序转换。说了这么多,希望这能帮助解决问题,或者为其他有类似用例的人提供一个起点。
internal class BitField
{
private readonly byte[] _bytes;
private readonly int _offset;
private EndianBitConverter _bitConverter = EndianBitConverter.Big;
public BitField(byte[] bytes)
: this(bytes, 0)
{
}
//offset = the offset (in bytes) into the wrapped byte array
public BitField(byte[] bytes, int offset)
{
_bytes = bytes;
_offset = offset;
}
public BitField(int size)
: this(new byte[size], 0)
{
}
//fill == true = initially set all bits to 1
public BitField(int size, bool fill)
: this(new byte[size], 0)
{
if (!fill) return;
for(int i = 0 ; i < size ; i++)
{
_bytes[i] = 0xff;
}
}
public byte[] Bytes
{
get { return _bytes; }
}
public int Offset
{
get { return _offset; }
}
public EndianBitConverter BitConverter
{
get { return _bitConverter; }
set { _bitConverter = value; }
}
public bool this[int bit]
{
get { return IsBitSet(bit); }
set { if (value) SetBit(bit); else ClearBit(bit); }
}
public bool IsBitSet(int bit)
{
return (_bytes[_offset + (bit / 8)] & (1 << (7 - (bit % 8)))) != 0;
}
public void SetBit(int bit)
{
_bytes[_offset + (bit / 8)] |= unchecked((byte)(1 << (7 - (bit % 8))));
}
public void ClearBit(int bit)
{
_bytes[_offset + (bit / 8)] &= unchecked((byte)~(1 << (7 - (bit % 8))));
}
//index = the index of the source BitField at which to start getting bits
//length = the number of bits to get
//size = the total number of bytes required (0 for arbitrary length return array)
//fill == true = set all padding bits to 1
public byte[] GetBytes(int index, int length, int size, bool fill)
{
if(size == 0) size = (length + 7) / 8;
BitField bitField = new BitField(size, fill);
for(int s = index, d = (size * 8) - length ; s < index + length && d < (size * 8) ; s++, d++)
{
bitField[d] = IsBitSet(s);
}
return bitField._bytes;
}
public byte[] GetBytes(int index, int length, int size)
{
return GetBytes(index, length, size, false);
}
public byte[] GetBytes(int index, int length)
{
return GetBytes(index, length, 0, false);
}
//bytesIndex = the index (in bits) into the bytes array at which to start copying
//index = the index (in bits) in this BitField at which to put the value
//length = the number of bits to copy from the bytes array
public void SetBytes(byte[] bytes, int bytesIndex, int index, int length)
{
BitField bitField = new BitField(bytes);
for (int i = 0; i < length; i++)
{
this[index + i] = bitField[bytesIndex + i];
}
}
public void SetBytes(byte[] bytes, int index, int length)
{
SetBytes(bytes, 0, index, length);
}
public void SetBytes(byte[] bytes, int index)
{
SetBytes(bytes, 0, index, bytes.Length * 8);
}
//UInt16
//index = the index (in bits) at which to start getting the value
//length = the number of bits to use for the value, if less than required the value is padded with 0
public ushort GetUInt16(int index, int length)
{
return _bitConverter.ToUInt16(GetBytes(index, length, 2), 0);
}
public ushort GetUInt16(int index)
{
return GetUInt16(index, 16);
}
//valueIndex = the index (in bits) of the value at which to start copying
//index = the index (in bits) in this BitField at which to put the value
//length = the number of bits to copy from the value
public void Set(ushort value, int valueIndex, int index, int length)
{
SetBytes(_bitConverter.GetBytes(value), valueIndex, index, length);
}
public void Set(ushort value, int index)
{
Set(value, 0, index, 16);
}
//UInt32
public uint GetUInt32(int index, int length)
{
return _bitConverter.ToUInt32(GetBytes(index, length, 4), 0);
}
public uint GetUInt32(int index)
{
return GetUInt32(index, 32);
}
public void Set(uint value, int valueIndex, int index, int length)
{
SetBytes(_bitConverter.GetBytes(value), valueIndex, index, length);
}
public void Set(uint value, int index)
{
Set(value, 0, index, 32);
}
//UInt64
public ulong GetUInt64(int index, int length)
{
return _bitConverter.ToUInt64(GetBytes(index, length, 8), 0);
}
public ulong GetUInt64(int index)
{
return GetUInt64(index, 64);
}
public void Set(ulong value, int valueIndex, int index, int length)
{
SetBytes(_bitConverter.GetBytes(value), valueIndex, index, length);
}
public void Set(ulong value, int index)
{
Set(value, 0, index, 64);
}
//Int16
public short GetInt16(int index, int length)
{
return _bitConverter.ToInt16(GetBytes(index, length, 2, IsBitSet(index)), 0);
}
public short GetInt16(int index)
{
return GetInt16(index, 16);
}
public void Set(short value, int valueIndex, int index, int length)
{
SetBytes(_bitConverter.GetBytes(value), valueIndex, index, length);
}
public void Set(short value, int index)
{
Set(value, 0, index, 16);
}
//Int32
public int GetInt32(int index, int length)
{
return _bitConverter.ToInt32(GetBytes(index, length, 4, IsBitSet(index)), 0);
}
public int GetInt32(int index)
{
return GetInt32(index, 32);
}
public void Set(int value, int valueIndex, int index, int length)
{
SetBytes(_bitConverter.GetBytes(value), valueIndex, index, length);
}
public void Set(int value, int index)
{
Set(value, 0, index, 32);
}
//Int64
public long GetInt64(int index, int length)
{
return _bitConverter.ToInt64(GetBytes(index, length, 8, IsBitSet(index)), 0);
}
public long GetInt64(int index)
{
return GetInt64(index, 64);
}
public void Set(long value, int valueIndex, int index, int length)
{
SetBytes(_bitConverter.GetBytes(value), valueIndex, index, length);
}
public void Set(long value, int index)
{
Set(value, 0, index, 64);
}
//Char
public char GetChar(int index, int length)
{
return _bitConverter.ToChar(GetBytes(index, length, 2), 0);
}
public char GetChar(int index)
{
return GetChar(index, 16);
}
public void Set(char value, int valueIndex, int index, int length)
{
SetBytes(_bitConverter.GetBytes(value), valueIndex, index, length);
}
public void Set(char value, int index)
{
Set(value, 0, index, 16);
}
//Bool
public bool GetBool(int index, int length)
{
return _bitConverter.ToBoolean(GetBytes(index, length, 1), 0);
}
public bool GetBool(int index)
{
return GetBool(index, 8);
}
public void Set(bool value, int valueIndex, int index, int length)
{
SetBytes(_bitConverter.GetBytes(value), valueIndex, index, length);
}
public void Set(bool value, int index)
{
Set(value, 0, index, 8);
}
//Single and double precision floating point values must always use the correct number of bits
public float GetSingle(int index)
{
return _bitConverter.ToSingle(GetBytes(index, 32, 4), 0);
}
public void SetSingle(float value, int index)
{
SetBytes(_bitConverter.GetBytes(value), 0, index, 32);
}
public double GetDouble(int index)
{
return _bitConverter.ToDouble(GetBytes(index, 64, 8), 0);
}
public void SetDouble(double value, int index)
{
SetBytes(_bitConverter.GetBytes(value), 0, index, 64);
}
}
如果您的数据包总是小于8或4字节,那么将每个数据包存储在Int32
或Int64
中会更容易。字节数组只会使事情复杂化。你必须注意高端存储和低端存储。
然后,对于3字节的包:
public static void SetValue(Int32 message, int startIndex, int length, int value)
{
// we want lengthx1
int mask = (1 << length) - 1;
value = value & mask; // or check and throw
int offset = 24 - startIndex - length; // 24 = 3 * 8
message = message | (value << offset);
}
首先,你似乎用System.Collections.BitArray类重新发明了轮子。至于实际查找特定位字段的值,我认为可以通过以下伪代码的一点数学魔法轻松完成:
- 从您选择的最远处的数字开始(startIndex + length)。
- 如果设置了,则加2^(到数字的距离)。在这种情况下,它将是0 (mostDistance - self = 0),所以添加2^0(1)。
- 左移一位
- 重复您想要的长度中的每个数字。
10001010
你想要0到3的数字的值,你会得到这样的:
[Index 3] [Index 2] [Index 1] [Index 0]
(3 - 3) (3 - 2) (3 - 1) (3 - 0)
=============================================
(0 * 2^0) + (0 * 2^1) + (0 * 2^2) + (1 * 2^3) = 8
因为1000(二进制)== 8,所以数学是正确的。
仅仅使用简单的位移位来获得您的值有什么问题?
int data = Convert.ToInt32( "110000000010000000100001", 2 );
bool v1 = ( data & 1 ) == 1; // True
int v2 = ( data >> 1 ) & 0x1F; // 16
int v3 = ( data >> 6 ) & 0xFF; // 128
uint v4 = (uint )( data >> 14 ) & 0x1FF; // 256
bool v5 = ( data >> 23 ) == 1; // True
这是一篇很好的关于这个主题的文章。