I've got a byte array that was created using a hash function. I would like to convert this array into a string. So far so good, it will give me hexadecimal string.
Now I would like to use something different than hexadecimal characters, I would like to encode the byte array with these 36 characters: [a-z][0-9].
How would I go about?
Edit: the reason I would to do this, is because I would like to have a smaller string, than a hexadecimal string.
I adapted my arbitrary-length base conversion function from this answer to C#:
static string BaseConvert(string number, int fromBase, int toBase)
{
var digits = "0123456789abcdefghijklmnopqrstuvwxyz";
var length = number.Length;
var result = string.Empty;
var nibbles = number.Select(c => digits.IndexOf(c)).ToList();
int newlen;
do {
var value = 0;
newlen = 0;
for (var i = 0; i < length; ++i) {
value = value * fromBase + nibbles[i];
if (value >= toBase) {
if (newlen == nibbles.Count) {
nibbles.Add(0);
}
nibbles[newlen++] = value / toBase;
value %= toBase;
}
else if (newlen > 0) {
if (newlen == nibbles.Count) {
nibbles.Add(0);
}
nibbles[newlen++] = 0;
}
}
length = newlen;
result = digits[value] + result; //
}
while (newlen != 0);
return result;
}
As it's coming from PHP it might not be too idiomatic C#, there are also no parameter validity checks. However, you can feed it a hex-encoded string and it will work just fine with
var result = BaseConvert(hexEncoded, 16, 36);
It's not exactly what you asked for, but encoding the byte[] into hex is trivial.
See it in action.
Earlier tonight I came across a codereview question revolving around the same algorithm being discussed here. See: https://codereview.stackexchange.com/questions/14084/base-36-encoding-of-a-byte-array/
I provided a improved implementation of one of its earlier answers (both use BigInteger). See: https://codereview.stackexchange.com/a/20014/20654. The solution takes a byte[] and returns a Base36 string. Both the original and mine include simple benchmark information.
For completeness, the following is the method to decode a byte[] from an string. I'll include the encode function from the link above as well. See the text after this code block for some simple benchmark info for decoding.
const int kByteBitCount= 8; // number of bits in a byte
// constants that we use in FromBase36String and ToBase36String
const string kBase36Digits= "0123456789abcdefghijklmnopqrstuvwxyz";
static readonly double kBase36CharsLengthDivisor= Math.Log(kBase36Digits.Length, 2);
static readonly BigInteger kBigInt36= new BigInteger(36);
// assumes the input 'chars' is in big-endian ordering, MSB->LSB
static byte[] FromBase36String(string chars)
{
var bi= new BigInteger();
for (int x= 0; x < chars.Length; x++)
{
int i= kBase36Digits.IndexOf(chars[x]);
if (i < 0) return null; // invalid character
bi *= kBigInt36;
bi += i;
}
return bi.ToByteArray();
}
// characters returned are in big-endian ordering, MSB->LSB
static string ToBase36String(byte[] bytes)
{
// Estimate the result's length so we don't waste time realloc'ing
int result_length= (int)
Math.Ceiling(bytes.Length * kByteBitCount / kBase36CharsLengthDivisor);
// We use a List so we don't have to CopyTo a StringBuilder's characters
// to a char[], only to then Array.Reverse it later
var result= new System.Collections.Generic.List<char>(result_length);
var dividend= new BigInteger(bytes);
// IsZero's computation is less complex than evaluating "dividend > 0"
// which invokes BigInteger.CompareTo(BigInteger)
while (!dividend.IsZero)
{
BigInteger remainder;
dividend= BigInteger.DivRem(dividend, kBigInt36, out remainder);
int digit_index= Math.Abs((int)remainder);
result.Add(kBase36Digits[digit_index]);
}
// orientate the characters in big-endian ordering
result.Reverse();
// ToArray will also trim the excess chars used in length prediction
return new string(result.ToArray());
}
"A test 1234. Made slightly larger!" encodes to Base64 as "165kkoorqxin775ct82ist5ysteekll7kaqlcnnu6mfe7ag7e63b5"
To decode that Base36 string 1,000,000 times takes 12.6558909 seconds on my machine (I used the same build and machine conditions as provided in my answer on codereview)
You mentioned that you were dealing with a byte[] for the MD5 hash, rather than a hexadecimal string representation of it, so I think this solution provide the least overhead for you.
If you want a shorter string and can accept [a-zA-Z0-9] and + and / then look at Convert.ToBase64String
Using BigInteger (needs the System.Numerics reference)
Using BigInteger (needs the System.Numerics reference)
const string chars = "0123456789abcdefghijklmnopqrstuvwxyz";
// The result is padded with chars[0] to make the string length
// (int)Math.Ceiling(bytes.Length * 8 / Math.Log(chars.Length, 2))
// (so that for any value [0...0]-[255...255] of bytes the resulting
// string will have same length)
public static string ToBaseN(byte[] bytes, string chars, bool littleEndian = true, int len = -1)
{
if (bytes.Length == 0 || len == 0)
{
return String.Empty;
}
// BigInteger saves in the last byte the sign. > 7F negative,
// <= 7F positive.
// If we have a "negative" number, we will prepend a 0 byte.
byte[] bytes2;
if (littleEndian)
{
if (bytes[bytes.Length - 1] <= 0x7F)
{
bytes2 = bytes;
}
else
{
// Note that Array.Resize doesn't modify the original array,
// but creates a copy and sets the passed reference to the
// new array
bytes2 = bytes;
Array.Resize(ref bytes2, bytes.Length + 1);
}
}
else
{
bytes2 = new byte[bytes[0] > 0x7F ? bytes.Length + 1 : bytes.Length];
// We copy and reverse the array
for (int i = bytes.Length - 1, j = 0; i >= 0; i--, j++)
{
bytes2[j] = bytes[i];
}
}
BigInteger bi = new BigInteger(bytes2);
// A little optimization. We will do many divisions based on
// chars.Length .
BigInteger length = chars.Length;
// We pre-calc the length of the string. We know the bits of
// "information" of a byte are 8. Using Log2 we calc the bits of
// information of our new base.
if (len == -1)
{
len = (int)Math.Ceiling(bytes.Length * 8 / Math.Log(chars.Length, 2));
}
// We will build our string on a char[]
var chs = new char[len];
int chsIndex = 0;
while (bi > 0)
{
BigInteger remainder;
bi = BigInteger.DivRem(bi, length, out remainder);
chs[littleEndian ? chsIndex : len - chsIndex - 1] = chars[(int)remainder];
chsIndex++;
if (chsIndex < 0)
{
if (bi > 0)
{
throw new OverflowException();
}
}
}
// We append the zeros that we skipped at the beginning
if (littleEndian)
{
while (chsIndex < len)
{
chs[chsIndex] = chars[0];
chsIndex++;
}
}
else
{
while (chsIndex < len)
{
chs[len - chsIndex - 1] = chars[0];
chsIndex++;
}
}
return new string(chs);
}
public static byte[] FromBaseN(string str, string chars, bool littleEndian = true, int len = -1)
{
if (str.Length == 0 || len == 0)
{
return new byte[0];
}
// This should be the maximum length of the byte[] array. It's
// the opposite of the one used in ToBaseN.
// Note that it can be passed as a parameter
if (len == -1)
{
len = (int)Math.Ceiling(str.Length * Math.Log(chars.Length, 2) / 8);
}
BigInteger bi = BigInteger.Zero;
BigInteger length2 = chars.Length;
BigInteger mult = BigInteger.One;
for (int j = 0; j < str.Length; j++)
{
int ix = chars.IndexOf(littleEndian ? str[j] : str[str.Length - j - 1]);
// We didn't find the character
if (ix == -1)
{
throw new ArgumentOutOfRangeException();
}
bi += ix * mult;
mult *= length2;
}
var bytes = bi.ToByteArray();
int len2 = bytes.Length;
// BigInteger adds a 0 byte for positive numbers that have the
// last byte > 0x7F
if (len2 >= 2 && bytes[len2 - 1] == 0)
{
len2--;
}
int len3 = Math.Min(len, len2);
byte[] bytes2;
if (littleEndian)
{
if (len == bytes.Length)
{
bytes2 = bytes;
}
else
{
bytes2 = new byte[len];
Array.Copy(bytes, bytes2, len3);
}
}
else
{
bytes2 = new byte[len];
for (int i = 0; i < len3; i++)
{
bytes2[len - i - 1] = bytes[i];
}
}
for (int i = len3; i < len2; i++)
{
if (bytes[i] != 0)
{
throw new OverflowException();
}
}
return bytes2;
}
Be aware that they are REALLY slow! REALLY REALLY slow! (2 minutes for 100k). To speed them up you would probably need to rewrite the division/mod operation so that they work directly on a buffer, instead of each time recreating the scratch pads as it's done by BigInteger. And it would still be SLOW. The problem is that the time needed to encode the first byte is O(n) where n is the length of the byte array (this because all the array needs to be divided by 36). Unless you want to work with blocks of 5 bytes and lose some bits. Each symbol of Base36 carries around 5.169925001 bits. So 8 of these symbols would carry 41.35940001 bits. Very near 40 bytes.
Note that these methods can work both in little-endian mode and in big-endian mode. The endianness of the input and of the output is the same. Both methods accept a len parameter. You can use it to trim excess 0 (zeroes). Note that if you try to make an output too much small to contain the input, an OverflowException will be thrown.
System.Text.Encoding enc = System.Text.Encoding.ASCII;
string myString = enc.GetString(myByteArray);
You can play with what encoding you need:
System.Text.ASCIIEncoding,
System.Text.UnicodeEncoding,
System.Text.UTF7Encoding,
System.Text.UTF8Encoding
To match the requrements [a-z][0-9] you can use it:
Byte[] bytes = new Byte[] { 200, 180, 34 };
string result = String.Join("a", bytes.Select(x => x.ToString()).ToArray());
You will have string representation of bytes with char separator. To convert back you will need to split, and convert the string[] to byte[] using the same approach with .Select().
Usually a power of 2 is used - that way one character maps to a fixed number of bits. An alphabet of 32 bits for instance would map to 5 bits. The only challenge in that case is how to deserialize variable-length strings.
For 36 bits you could treat the data as a large number, and then:
divide by 36
add the remainder as character to your result
repeat until the division results in 0
Easier said than done perhaps.
you can use modulu.
this example encode your byte array to string of [0-9][a-z].
change it if you want.
public string byteToString(byte[] byteArr)
{
int i;
char[] charArr = new char[byteArr.Length];
for (i = 0; i < byteArr.Length; i++)
{
int byt = byteArr[i] % 36; // 36=num of availible charachters
if (byt < 10)
{
charArr[i] = (char)(byt + 48); //if % result is a digit
}
else
{
charArr[i] = (char)(byt + 87); //if % result is a letter
}
}
return new String(charArr);
}
If you don't want to lose data for de-encoding you can use this example:
public string byteToString(byte[] byteArr)
{
int i;
char[] charArr = new char[byteArr.Length*2];
for (i = 0; i < byteArr.Length; i++)
{
charArr[2 * i] = (char)((int)byteArr[i] / 36+48);
int byt = byteArr[i] % 36; // 36=num of availible charachters
if (byt < 10)
{
charArr[2*i+1] = (char)(byt + 48); //if % result is a digit
}
else
{
charArr[2*i+1] = (char)(byt + 87); //if % result is a letter
}
}
return new String(charArr);
}
and now you have a string double-lengthed when odd char is the multiply of 36 and even char is the residu. for example: 200=36*5+20 => "5k".
I am trying to integrate a Serial-port device into my application, which needs CRC-CCTT validation for the bytes that I send to it.
I'm kinda new into managing byte packets, and need help for this.
It uses this formula for making the CRC calculus:
[CRC-CCITT P(X)= X16 + C12 + C8 + 1]
So for example for the packet: 0xFC 0x05 0x11, the CRC is 0x5627.
Then I send this packet to the device: 0xFC 0x05 0x11 0x27 0x56
Also, packet lenghts will vary from 5 to 255 (including CRC checks bytes)
I don't know how to implement this, so any idea/suggestions will be welcome.
Hope I made myself clear,
Thanks in Advance.
EDIT:
here is the specification of what I need to do:
standard crc-ccitt is x16 + x12 + x5 + 1 I wrote the one # http://www.sanity-free.com/133/crc_16_ccitt_in_csharp.html If I have time I'll see if I can't modify it to run with the x16 + x12 + x8 + 1 poly.
EDIT:
here you go:
public class Crc16CcittKermit {
private static ushort[] table = {
0x0000, 0x1189, 0x2312, 0x329B, 0x4624, 0x57AD, 0x6536, 0x74BF,
0x8C48, 0x9DC1, 0xAF5A, 0xBED3, 0xCA6C, 0xDBE5, 0xE97E, 0xF8F7,
0x1081, 0x0108, 0x3393, 0x221A, 0x56A5, 0x472C, 0x75B7, 0x643E,
0x9CC9, 0x8D40, 0xBFDB, 0xAE52, 0xDAED, 0xCB64, 0xF9FF, 0xE876,
0x2102, 0x308B, 0x0210, 0x1399, 0x6726, 0x76AF, 0x4434, 0x55BD,
0xAD4A, 0xBCC3, 0x8E58, 0x9FD1, 0xEB6E, 0xFAE7, 0xC87C, 0xD9F5,
0x3183, 0x200A, 0x1291, 0x0318, 0x77A7, 0x662E, 0x54B5, 0x453C,
0xBDCB, 0xAC42, 0x9ED9, 0x8F50, 0xFBEF, 0xEA66, 0xD8FD, 0xC974,
0x4204, 0x538D, 0x6116, 0x709F, 0x0420, 0x15A9, 0x2732, 0x36BB,
0xCE4C, 0xDFC5, 0xED5E, 0xFCD7, 0x8868, 0x99E1, 0xAB7A, 0xBAF3,
0x5285, 0x430C, 0x7197, 0x601E, 0x14A1, 0x0528, 0x37B3, 0x263A,
0xDECD, 0xCF44, 0xFDDF, 0xEC56, 0x98E9, 0x8960, 0xBBFB, 0xAA72,
0x6306, 0x728F, 0x4014, 0x519D, 0x2522, 0x34AB, 0x0630, 0x17B9,
0xEF4E, 0xFEC7, 0xCC5C, 0xDDD5, 0xA96A, 0xB8E3, 0x8A78, 0x9BF1,
0x7387, 0x620E, 0x5095, 0x411C, 0x35A3, 0x242A, 0x16B1, 0x0738,
0xFFCF, 0xEE46, 0xDCDD, 0xCD54, 0xB9EB, 0xA862, 0x9AF9, 0x8B70,
0x8408, 0x9581, 0xA71A, 0xB693, 0xC22C, 0xD3A5, 0xE13E, 0xF0B7,
0x0840, 0x19C9, 0x2B52, 0x3ADB, 0x4E64, 0x5FED, 0x6D76, 0x7CFF,
0x9489, 0x8500, 0xB79B, 0xA612, 0xD2AD, 0xC324, 0xF1BF, 0xE036,
0x18C1, 0x0948, 0x3BD3, 0x2A5A, 0x5EE5, 0x4F6C, 0x7DF7, 0x6C7E,
0xA50A, 0xB483, 0x8618, 0x9791, 0xE32E, 0xF2A7, 0xC03C, 0xD1B5,
0x2942, 0x38CB, 0x0A50, 0x1BD9, 0x6F66, 0x7EEF, 0x4C74, 0x5DFD,
0xB58B, 0xA402, 0x9699, 0x8710, 0xF3AF, 0xE226, 0xD0BD, 0xC134,
0x39C3, 0x284A, 0x1AD1, 0x0B58, 0x7FE7, 0x6E6E, 0x5CF5, 0x4D7C,
0xC60C, 0xD785, 0xE51E, 0xF497, 0x8028, 0x91A1, 0xA33A, 0xB2B3,
0x4A44, 0x5BCD, 0x6956, 0x78DF, 0x0C60, 0x1DE9, 0x2F72, 0x3EFB,
0xD68D, 0xC704, 0xF59F, 0xE416, 0x90A9, 0x8120, 0xB3BB, 0xA232,
0x5AC5, 0x4B4C, 0x79D7, 0x685E, 0x1CE1, 0x0D68, 0x3FF3, 0x2E7A,
0xE70E, 0xF687, 0xC41C, 0xD595, 0xA12A, 0xB0A3, 0x8238, 0x93B1,
0x6B46, 0x7ACF, 0x4854, 0x59DD, 0x2D62, 0x3CEB, 0x0E70, 0x1FF9,
0xF78F, 0xE606, 0xD49D, 0xC514, 0xB1AB, 0xA022, 0x92B9, 0x8330,
0x7BC7, 0x6A4E, 0x58D5, 0x495C, 0x3DE3, 0x2C6A, 0x1EF1, 0x0F78
};
public static ushort ComputeChecksum( params byte[] buffer ) {
if ( buffer == null ) throw new ArgumentNullException( );
ushort crc = 0;
for ( int i = 0; i < buffer.Length; ++i ) {
crc = (ushort)( ( crc >> 8 ) ^ table[( crc ^ buffer[i] ) & 0xff] );
}
return crc;
}
public static byte[] ComputeChecksumBytes( params byte[] buffer ) {
return BitConverter.GetBytes( ComputeChecksum( buffer ) );
}
}
sample:
ushort crc = Crc16CcittKermit.ComputeChecksum( 0xFC, 0x05, 0x11 );
byte[] crcBuffer = Crc16CcittKermit.ComputeChecksumBytes( 0xFC, 0x05, 0x11 )
// crc = 0x5627
// crcBuffer = { 0x27, 0x56 }
Have you tried Googling for an example? There are many of them.
Example 1: http://tomkaminski.com/crc32-hashalgorithm-c-net
Example 2: http://www.sanity-free.com/12/crc32_implementation_in_csharp.html
You also have native MD5 support in .Net through System.Security.Cryptography.MD5CryptoServiceProvider.
EDIT:
If you are looking for an 8-bit algorithm: http://www.codeproject.com/KB/cs/csRedundancyChckAlgorithm.aspx
And 16-bit: http://www.sanity-free.com/133/crc_16_ccitt_in_csharp.html
LOL, I've encountered exactly the same STATUS REQUEST sequense, i'm currently developing software to use with CashCode Bill Validator:). Here's the code worked for me, it's CRC16-CCITT with reversed polynomial equals 0x8408 (BDPConstants.Polynomial in the code). That's the code worked for me:
// TableCRC16Size is 256 of course, don't forget to set in somewhere
protected ushort[] TableCRC16 = new ushort[BDPConstants.TableCRC16Size];
protected void InitCRC16Table()
{
for (ushort i = 0; i < BDPConstants.TableCRC16Size; ++i)
{
ushort CRC = 0;
ushort c = i;
for (int j = 0; j < 8; ++j)
{
if (((CRC ^ c) & 0x0001) > 0)
CRC = (ushort)((CRC >> 1) ^ BDPConstants.Polynominal);
else
CRC = (ushort)(CRC >> 1);
c = (ushort)(c >> 1);
}
TableCRC16[i] = CRC;
}
}
protected ushort CalcCRC16(byte[] aData)
{
ushort CRC = 0;
for (int i = 0; i < aData.Length; ++i)
CRC = (ushort)(TableCRC16[(CRC ^ aData[i]) & 0xFF] ^ (CRC >> 8));
return CRC;
}
Initialize the table somewhere (e.g. Form constructor):
InitCRC16Table();
then use it in your code just like that,
You can use List of bytes instead of array, more convinient to pack byte data in the 'packet' for sending
uint CRC = CalcCRC16(byte[] aByte)
// You need to split your CRC in two bytes of course
byte CRCHW = (byte)((CRC) / 256); // that's your 0x56
byte CRCLW = (byte)(CRC); // that's your 0x27
it works and dose not need table:
/// <summary>
/// Gens the CRC16.
/// CRC-1021 = X(16)+x(12)+x(5)+1
/// </summary>
/// <param name="c">The c.</param>
/// <param name="nByte">The n byte.</param>
/// <returns>System.Byte[][].</returns>
public ushort GenCrc16(byte[] c, int nByte)
{
ushort Polynominal = 0x1021;
ushort InitValue = 0x0;
ushort i, j, index = 0;
ushort CRC = InitValue;
ushort Remainder, tmp, short_c;
for (i = 0; i < nByte; i++)
{
short_c = (ushort)(0x00ff & (ushort) c[index]);
tmp = (ushort)((CRC >> 8) ^ short_c);
Remainder = (ushort)(tmp << 8);
for (j = 0; j < 8; j++)
{
if ((Remainder & 0x8000) != 0)
{
Remainder = (ushort)((Remainder << 1) ^ Polynominal);
}
else
{
Remainder = (ushort)(Remainder << 1);
}
}
CRC = (ushort)((CRC << 8) ^ Remainder);
index++;
}
return CRC;
}
You are actually using CRC-XMODEM LSB-reverse (with 0x8408 coefficient). C# code for this calculus is:
public void crc_bytes(int[] int_input)
{
int_array = int_input;
int int_crc = 0x0; // or 0xFFFF;
int int_lsb;
for (int int_i = 0; int_i < int_array.Length; int_i++)
{
int_crc = int_crc ^ int_array[int_i];
for (int int_j = 0; int_j < 8; int_j ++ )
{
int_lsb = int_crc & 0x0001; // Mask of LSB
int_crc = int_crc >> 1;
int_crc = int_crc & 0x7FFF;
if (int_lsb == 1)
int_crc = int_crc ^ 0x8408;
}
}
int_crc_byte_a = int_crc & 0x00FF;
int_crc_byte_b = (int_crc >> 8) & 0x00FF;
}
Read more (or download project):
http://www.cirvirlab.com/index.php/c-sharp-code-examples/141-c-sharp-crc-computation.html
I have two byte arrays with the same length. I need to perform XOR operation between each byte and after this calculate sum of bits.
For example:
11110000^01010101 = 10100101 -> so 1+1+1+1 = 4
I need do the same operation for each element in byte array.
Use a lookup table. There are only 256 possible values after XORing, so it's not exactly going to take a long time. Unlike izb's solution though, I wouldn't suggest manually putting all the values in though - compute the lookup table once at startup using one of the looping answers.
For example:
public static class ByteArrayHelpers
{
private static readonly int[] LookupTable =
Enumerable.Range(0, 256).Select(CountBits).ToArray();
private static int CountBits(int value)
{
int count = 0;
for (int i=0; i < 8; i++)
{
count += (value >> i) & 1;
}
return count;
}
public static int CountBitsAfterXor(byte[] array)
{
int xor = 0;
foreach (byte b in array)
{
xor ^= b;
}
return LookupTable[xor];
}
}
(You could make it an extension method if you really wanted...)
Note the use of byte[] in the CountBitsAfterXor method - you could make it an IEnumerable<byte> for more generality, but iterating over an array (which is known to be an array at compile-time) will be faster. Probably only microscopically faster, but hey, you asked for the fastest way :)
I would almost certainly actually express it as
public static int CountBitsAfterXor(IEnumerable<byte> data)
in real life, but see which works better for you.
Also note the type of the xor variable as an int. In fact, there's no XOR operator defined for byte values, and if you made xor a byte it would still compile due to the nature of compound assignment operators, but it would be performing a cast on each iteration - at least in the IL. It's quite possible that the JIT would take care of this, but there's no need to even ask it to :)
Fastest way would probably be a 256-element lookup table...
int[] lut
{
/*0x00*/ 0,
/*0x01*/ 1,
/*0x02*/ 1,
/*0x03*/ 2
...
/*0xFE*/ 7,
/*0xFF*/ 8
}
e.g.
11110000^01010101 = 10100101 -> lut[165] == 4
This is more commonly referred to as bit counting. There are literally dozens of different algorithms for doing this. Here is one site which lists a few of the more well known methods. There are even CPU specific instructions for doing this.
Theorectically, Microsoft could add a BitArray.CountSetBits function that gets JITed with the best algorithm for that CPU architecture. I, for one, would welcome such an addition.
As I understood it you want to sum the bits of each XOR between the left and right bytes.
for (int b = 0; b < left.Length; b++) {
int num = left[b] ^ right[b];
int sum = 0;
for (int i = 0; i < 8; i++) {
sum += (num >> i) & 1;
}
// do something with sum maybe?
}
I'm not sure if you mean sum the bytes or the bits.
To sum the bits within a byte, this should work:
int nSum = 0;
for (int i=0; i<=7; i++)
{
nSum += (byte_val>>i) & 1;
}
You would then need the xoring, and array looping around this, of course.
The following should do
int BitXorAndSum(byte[] left, byte[] right) {
int sum = 0;
for ( var i = 0; i < left.Length; i++) {
sum += SumBits((byte)(left[i] ^ right[i]));
}
return sum;
}
int SumBits(byte b) {
var sum = 0;
for (var i = 0; i < 8; i++) {
sum += (0x1) & (b >> i);
}
return sum;
}
It can be rewritten as ulong and use unsafe pointer, but byte is easier to understand:
static int BitCount(byte num)
{
// 0x5 = 0101 (bit) 0x55 = 01010101
// 0x3 = 0011 (bit) 0x33 = 00110011
// 0xF = 1111 (bit) 0x0F = 00001111
uint count = num;
count = ((count >> 1) & 0x55) + (count & 0x55);
count = ((count >> 2) & 0x33) + (count & 0x33);
count = ((count >> 4) & 0xF0) + (count & 0x0F);
return (int)count;
}
A general function to count bits could look like:
int Count1(byte[] a)
{
int count = 0;
for (int i = 0; i < a.Length; i++)
{
byte b = a[i];
while (b != 0)
{
count++;
b = (byte)((int)b & (int)(b - 1));
}
}
return count;
}
The less 1-bits, the faster this works. It simply loops over each byte, and toggles the lowest 1 bit of that byte until the byte becomes 0. The castings are necessary so that the compiler stops complaining about the type widening and narrowing.
Your problem could then be solved by using this:
int Count1Xor(byte[] a1, byte[] a2)
{
int count = 0;
for (int i = 0; i < Math.Min(a1.Length, a2.Length); i++)
{
byte b = (byte)((int)a1[i] ^ (int)a2[i]);
while (b != 0)
{
count++;
b = (byte)((int)b & (int)(b - 1));
}
}
return count;
}
A lookup table should be the fastest, but if you want to do it without a lookup table, this will work for bytes in just 10 operations.
public static int BitCount(byte value) {
int v = value - ((value >> 1) & 0x55);
v = (v & 0x33) + ((v >> 2) & 0x33);
return ((v + (v >> 4) & 0x0F));
}
This is a byte version of the general bit counting function described at Sean Eron Anderson's bit fiddling site.
I have a BitArray with the length of 8, and I need a function to convert it to a byte. How to do it?
Specifically, I need a correct function of ConvertToByte:
BitArray bit = new BitArray(new bool[]
{
false, false, false, false,
false, false, false, true
});
//How to write ConvertToByte
byte myByte = ConvertToByte(bit);
var recoveredBit = new BitArray(new[] { myByte });
Assert.AreEqual(bit, recoveredBit);
This should work:
byte ConvertToByte(BitArray bits)
{
if (bits.Count != 8)
{
throw new ArgumentException("bits");
}
byte[] bytes = new byte[1];
bits.CopyTo(bytes, 0);
return bytes[0];
}
A bit late post, but this works for me:
public static byte[] BitArrayToByteArray(BitArray bits)
{
byte[] ret = new byte[(bits.Length - 1) / 8 + 1];
bits.CopyTo(ret, 0);
return ret;
}
Works with:
string text = "Test";
byte[] bytes = System.Text.Encoding.ASCII.GetBytes(text);
BitArray bits = new BitArray(bytes);
bytes[] bytesBack = BitArrayToByteArray(bits);
string textBack = System.Text.Encoding.ASCII.GetString(bytesBack);
// bytes == bytesBack
// text = textBack
.
A poor man's solution:
protected byte ConvertToByte(BitArray bits)
{
if (bits.Count != 8)
{
throw new ArgumentException("illegal number of bits");
}
byte b = 0;
if (bits.Get(7)) b++;
if (bits.Get(6)) b += 2;
if (bits.Get(5)) b += 4;
if (bits.Get(4)) b += 8;
if (bits.Get(3)) b += 16;
if (bits.Get(2)) b += 32;
if (bits.Get(1)) b += 64;
if (bits.Get(0)) b += 128;
return b;
}
Unfortunately, the BitArray class is partially implemented in .Net Core class (UWP). For example BitArray class is unable to call the CopyTo() and Count() methods. I wrote this extension to fill the gap:
public static IEnumerable<byte> ToBytes(this BitArray bits, bool MSB = false)
{
int bitCount = 7;
int outByte = 0;
foreach (bool bitValue in bits)
{
if (bitValue)
outByte |= MSB ? 1 << bitCount : 1 << (7 - bitCount);
if (bitCount == 0)
{
yield return (byte) outByte;
bitCount = 8;
outByte = 0;
}
bitCount--;
}
// Last partially decoded byte
if (bitCount < 7)
yield return (byte) outByte;
}
The method decodes the BitArray to a byte array using LSB (Less Significant Byte) logic. This is the same logic used by the BitArray class. Calling the method with the MSB parameter set on true will produce a MSB decoded byte sequence. In this case, remember that you maybe also need to reverse the final output byte collection.
This should do the trick. However the previous answer is quite likely the better option.
public byte ConvertToByte(BitArray bits)
{
if (bits.Count > 8)
throw new ArgumentException("ConvertToByte can only work with a BitArray containing a maximum of 8 values");
byte result = 0;
for (byte i = 0; i < bits.Count; i++)
{
if (bits[i])
result |= (byte)(1 << i);
}
return result;
}
In the example you posted the resulting byte will be 0x80. In other words the first value in the BitArray coresponds to the first bit in the returned byte.
That's should be the ultimate one. Works with any length of array.
private List<byte> BoolList2ByteList(List<bool> values)
{
List<byte> ret = new List<byte>();
int count = 0;
byte currentByte = 0;
foreach (bool b in values)
{
if (b) currentByte |= (byte)(1 << count);
count++;
if (count == 7) { ret.Add(currentByte); currentByte = 0; count = 0; };
}
if (count < 7) ret.Add(currentByte);
return ret;
}
In addition to #JonSkeet's answer you can use an Extension Method as below:
public static byte ToByte(this BitArray bits)
{
if (bits.Count != 8)
{
throw new ArgumentException("bits");
}
byte[] bytes = new byte[1];
bits.CopyTo(bytes, 0);
return bytes[0];
}
And use like:
BitArray foo = new BitArray(new bool[]
{
false, false, false, false,false, false, false, true
});
foo.ToByte();
byte GetByte(BitArray input)
{
int len = input.Length;
if (len > 8)
len = 8;
int output = 0;
for (int i = 0; i < len; i++)
if (input.Get(i))
output += (1 << (len - 1 - i)); //this part depends on your system (Big/Little)
//output += (1 << i); //depends on system
return (byte)output;
}
Cheers!
Little endian byte array converter : First bit (indexed with "0") in the BitArray
assumed to represents least significant bit (rightmost bit in the bit-octet) which interpreted as "zero" or "one" as binary.
public static class BitArrayExtender {
public static byte[] ToByteArray( this BitArray bits ) {
const int BYTE = 8;
int length = ( bits.Count / BYTE ) + ( (bits.Count % BYTE == 0) ? 0 : 1 );
var bytes = new byte[ length ];
for ( int i = 0; i < bits.Length; i++ ) {
int bitIndex = i % BYTE;
int byteIndex = i / BYTE;
int mask = (bits[ i ] ? 1 : 0) << bitIndex;
bytes[ byteIndex ] |= (byte)mask;
}//for
return bytes;
}//ToByteArray
}//class