如何将字节数组转换为十六进制字符串,反之亦然?


当前回答

我将参加这个比特拨弄比赛,因为我有一个同样使用比特拨弄来解码十六进制的答案。请注意,使用字符数组可能会更快,因为调用StringBuilder方法也需要时间。

public static String ToHex (byte[] data)
{
    int dataLength = data.Length;
    // pre-create the stringbuilder using the length of the data * 2, precisely enough
    StringBuilder sb = new StringBuilder (dataLength * 2);
    for (int i = 0; i < dataLength; i++) {
        int b = data [i];

        // check using calculation over bits to see if first tuple is a letter
        // isLetter is zero if it is a digit, 1 if it is a letter
        int isLetter = (b >> 7) & ((b >> 6) | (b >> 5)) & 1;

        // calculate the code using a multiplication to make up the difference between
        // a digit character and an alphanumerical character
        int code = '0' + ((b >> 4) & 0xF) + isLetter * ('A' - '9' - 1);
        // now append the result, after casting the code point to a character
        sb.Append ((Char)code);

        // do the same with the lower (less significant) tuple
        isLetter = (b >> 3) & ((b >> 2) | (b >> 1)) & 1;
        code = '0' + (b & 0xF) + isLetter * ('A' - '9' - 1);
        sb.Append ((Char)code);
    }
    return sb.ToString ();
}

public static byte[] FromHex (String hex)
{

    // pre-create the array
    int resultLength = hex.Length / 2;
    byte[] result = new byte[resultLength];
    // set validity = 0 (0 = valid, anything else is not valid)
    int validity = 0;
    int c, isLetter, value, validDigitStruct, validDigit, validLetterStruct, validLetter;
    for (int i = 0, hexOffset = 0; i < resultLength; i++, hexOffset += 2) {
        c = hex [hexOffset];

        // check using calculation over bits to see if first char is a letter
        // isLetter is zero if it is a digit, 1 if it is a letter (upper & lowercase)
        isLetter = (c >> 6) & 1;

        // calculate the tuple value using a multiplication to make up the difference between
        // a digit character and an alphanumerical character
        // minus 1 for the fact that the letters are not zero based
        value = ((c & 0xF) + isLetter * (-1 + 10)) << 4;

        // check validity of all the other bits
        validity |= c >> 7; // changed to >>, maybe not OK, use UInt?

        validDigitStruct = (c & 0x30) ^ 0x30;
        validDigit = ((c & 0x8) >> 3) * (c & 0x6);
        validity |= (isLetter ^ 1) * (validDigitStruct | validDigit);

        validLetterStruct = c & 0x18;
        validLetter = (((c - 1) & 0x4) >> 2) * ((c - 1) & 0x2);
        validity |= isLetter * (validLetterStruct | validLetter);

        // do the same with the lower (less significant) tuple
        c = hex [hexOffset + 1];
        isLetter = (c >> 6) & 1;
        value ^= (c & 0xF) + isLetter * (-1 + 10);
        result [i] = (byte)value;

        // check validity of all the other bits
        validity |= c >> 7; // changed to >>, maybe not OK, use UInt?

        validDigitStruct = (c & 0x30) ^ 0x30;
        validDigit = ((c & 0x8) >> 3) * (c & 0x6);
        validity |= (isLetter ^ 1) * (validDigitStruct | validDigit);

        validLetterStruct = c & 0x18;
        validLetter = (((c - 1) & 0x4) >> 2) * ((c - 1) & 0x2);
        validity |= isLetter * (validLetterStruct | validLetter);
    }

    if (validity != 0) {
        throw new ArgumentException ("Hexadecimal encoding incorrect for input " + hex);
    }

    return result;
}

从Java代码转换而来。

其他回答

这是一篇很棒的帖子。我喜欢瓦利德的解决方案。我还没有通过帕特里奇的测试,但似乎很快。我还需要反向过程,将十六进制字符串转换为字节数组,因此我将其作为Waleed解决方案的反向来编写。不确定它是否比托马拉克的原始解决方案更快。同样,我也没有通过帕特里奇的测试运行相反的过程。

private byte[] HexStringToByteArray(string hexString)
{
    int hexStringLength = hexString.Length;
    byte[] b = new byte[hexStringLength / 2];
    for (int i = 0; i < hexStringLength; i += 2)
    {
        int topChar = (hexString[i] > 0x40 ? hexString[i] - 0x37 : hexString[i] - 0x30) << 4;
        int bottomChar = hexString[i + 1] > 0x40 ? hexString[i + 1] - 0x37 : hexString[i + 1] - 0x30;
        b[i / 2] = Convert.ToByte(topChar + bottomChar);
    }
    return b;
}

这是我的纯二进制解决方案,不需要库查找,也支持大写/小写:

public static String encode(byte[] bytes, boolean uppercase) {
    char[] result = new char[2 * bytes.length];
    for (int i = 0; i < bytes.length; i++) {
        byte word = bytes[i];
        byte left = (byte) ((0XF0 & word) >>> 4);
        byte right = (byte) ((byte) 0X0F & word);

        int resultIndex = i * 2;
        result[resultIndex] = encode(left, uppercase);
        result[resultIndex + 1] = encode(right, uppercase);
    }
    return new String(result);
}

public static char encode(byte value, boolean uppercase) {
    int characterCase = uppercase ? 0 : 32;
    if (value > 15 || value < 0) {
        return '0';
    }
    if (value > 9) {
        return (char) (value + 0x37 | characterCase);
    }
    return (char) (value + 0x30);
}
static string ByteArrayToHexViaLookupPerByte2(byte[] bytes)
{                
        var result3 = new uint[bytes.Length];
        for (int i = 0; i < bytes.Length; i++)
                result3[i] = _Lookup32[bytes[i]];
        var handle = GCHandle.Alloc(result3, GCHandleType.Pinned);
        try
        {
                var result = Marshal.PtrToStringUni(handle.AddrOfPinnedObject(), bytes.Length * 2);
                return result;
        }
        finally
        {
                handle.Free();
        }
}

在我的测试中,这个函数总是不安全实现之后的第二个条目。

不幸的是,测试台不太可靠。。。如果你多次运行它,列表会被打乱,以至于谁知道在不安全之后哪个才是最快的!它没有考虑预热、jit编译时间和GC性能影响。我很想重写它以获得更多信息,但我真的没有时间。

我想出了一个不同的代码,它可以容忍额外的字符(空格、破折号…)。它的灵感主要来自这里一些可以接受的快速答案。它允许解析以下“文件”

00-aa-84-fb
12 32 FF CD
12 00
12_32_FF_CD
1200d5e68a
/// <summary>Reads a hex string into bytes</summary>
public static IEnumerable<byte> HexadecimalStringToBytes(string hex) {
    if (hex == null)
        throw new ArgumentNullException(nameof(hex));

    char c, c1 = default(char);
    bool hasc1 = false;
    unchecked   {
        for (int i = 0; i < hex.Length; i++) {
            c = hex[i];
            bool isValid = 'A' <= c && c <= 'f' || 'a' <= c && c <= 'f' || '0' <= c && c <= '9';
            if (!hasc1) {
                if (isValid) {
                    hasc1 = true;
                }
            } else {
                hasc1 = false;
                if (isValid) {
                    yield return (byte)((GetHexVal(c1) << 4) + GetHexVal(c));
                }
            }

            c1 = c;
        } 
    }
}

/// <summary>Reads a hex string into a byte array</summary>
public static byte[] HexadecimalStringToByteArray(string hex)
{
    if (hex == null)
        throw new ArgumentNullException(nameof(hex));

    var bytes = new List<byte>(hex.Length / 2);
    foreach (var item in HexadecimalStringToBytes(hex)) {
        bytes.Add(item);
    }

    return bytes.ToArray();
}

private static byte GetHexVal(char val)
{
    return (byte)(val - (val < 0x3A ? 0x30 : val < 0x5B ? 0x37 : 0x57));
    //                   ^^^^^^^^^^^^^^^^^   ^^^^^^^^^^^^^^^^^   ^^^^
    //                       digits 0-9       upper char A-Z     a-z
}

复制时请参考完整代码。包括单元测试。

有些人可能会说它对额外的字符太宽容了。因此,不要依赖此代码来执行验证(或更改)。

您可以使用BitConverter.ToString方法:

byte[] bytes = {0, 1, 2, 4, 8, 16, 32, 64, 128, 256}
Console.WriteLine( BitConverter.ToString(bytes));

输出:

00-01-02-04-08-10-20-40-80-FF

更多信息:BitConverter.ToString方法(Byte[])