c# - byte array to hex java




如何将字节数组转换为十六进制字符串,反之亦然? (20)

性能分析

注:截至2015-08-20新领导者。

我通过一些粗略的Stopwatch性能测试,一个随机句子(n = 61,1000次迭代)和一个带有古登堡项目(n = 1,238,957,150次迭代)的运行来运行各种转换方法。 以下是结果,大致从最快到最慢。 所有的测量都是以滴答( 10,000 ticks = 1 ms ),所有的相关音符都与[最慢的] StringBuilder实现进行比较。 对于使用的代码,请参阅下面或测试框架回购 ,我现在维护用于运行此代码的代码。

放弃

警告:不要将这些统计数据用于任何具体的事情; 它们只是样本数据的一个样本运行。 如果您确实需要一流的性能,请在代表您的生产需求的环境中使用代表您将使用的数据的数据来测试这些方法。

结果

  • 按字节查找unsafe (通过CodesInChaos) (添加到airbreather测试回购)
    • 文本:4,727.85(105.2X)
    • 一句话:0.28(99.7X)
  • 按字节查找(通过CodesInChaos)
    • 文本:10,853.96(快45.8倍)
    • 句子:0.65(快42.7倍)
  • 字节操作2(通过CodesInChaos)
    • 文字:12,967.69(快38.4倍)
    • 句子:0.73(快37.9倍)
  • 字节操作(通过Waleed Eissa)
    • 文本:16,856.64(快29.5倍)
    • 句子:0.70(快39.5倍)
  • Lookup / Shift(通过Nathan Moinvaziri)
    • 文字:23,201.23(快21.4倍)
    • 句子:1.24(快22.3倍)
  • 通过轻咬查找(通过Brian Lambert)
    • 文本:23,879.41(快20.8倍)
    • 句子:1.15(快23.9倍)
  • BitConverter (通过Tomalak)
    • 文字:113,269.34(快4.4倍)
    • 一句话:9.98(快2.8倍)
  • {SoapHexBinary}.ToString (通过Mykroft)
    • 文字:178,601.39(快2.8倍)
    • 句子:10.68(快2.6倍)
  • {byte}.ToString("X2") (使用foreach )(源自Will Dean的答案)
    • 文字:308,805.38(快2.4倍)
    • 一句话:16.89(快2.4倍)
  • {byte}.ToString("X2") (使用{IEnumerable}.Aggregate ,需要System.Linq)(通过Mark)
    • 文字:352,828.20(快2.1倍)
    • 一句话:16.87(快2.4倍)
  • Array.ConvertAll (使用string.Join )(通过Will Dean)
    • 文字:675,451.57(快1.1倍)
    • 句子:17.95(快2.2倍)
  • Array.ConvertAll (使用string.Concat ,需要.NET 4.0)(通过Will Dean)
    • 文字:752,078.70(快1.0倍)
    • 一句话:18.28(快2.2倍)
  • {StringBuilder}.AppendFormat (使用foreach )(通过Tomalak)
    • 文字:672,115.77(快1.1倍)
    • 一句话:36.82(快1.1倍)
  • {StringBuilder}.AppendFormat (使用{IEnumerable}.Aggregate ,需要System.Linq)(来自Tomalak的回答)
    • 文字:718,380.63(加快1.0倍)
    • 句子:39.71(快1.0倍)

查找表在字节操作上占据了领先地位。 基本上,预先计算任何给定的半字节或字节在十六进制中的形式。 然后,在翻阅数据时,只需查看下一部分即可查看它将是什么十六进制字符串。 然后该值以某种方式添加到结果字符串输出中。 对于很长时间的字节操作,一些开发人员可能难以阅读,是最高性能的方法。

你最好的选择仍然是找到一些有代表性的数据,并在类似生产的环境中试用它。 如果你有不同的内存限制,你可能更喜欢一种分配较少的方法,这种方法速度更快但消耗的内存更多。

测试代码

随意使用我使用的测试代码。 这里包括一个版本,但可以随意克隆回购并添加自己的方法。 如果您发现任何有趣的内容或想要帮助改进它所使用的测试框架,请提交拉取请求。

  1. 将新的静态方法( Func<byte[], string> )添加到/Tests/ConvertByteArrayToHexString/Test.cs。
  2. 将该方法的名称添加到同一个类中的TestCandidates返回值。
  3. 通过在同一个类中切换GenerateTestInput中的注释,确保您正在运行所需的输入版本,句子或文本。
  4. F5并等待输出(HTML转储也在/ bin文件夹中生成)。
static string ByteArrayToHexStringViaStringJoinArrayConvertAll(byte[] bytes) {
    return string.Join(string.Empty, Array.ConvertAll(bytes, b => b.ToString("X2")));
}
static string ByteArrayToHexStringViaStringConcatArrayConvertAll(byte[] bytes) {
    return string.Concat(Array.ConvertAll(bytes, b => b.ToString("X2")));
}
static string ByteArrayToHexStringViaBitConverter(byte[] bytes) {
    string hex = BitConverter.ToString(bytes);
    return hex.Replace("-", "");
}
static string ByteArrayToHexStringViaStringBuilderAggregateByteToString(byte[] bytes) {
    return bytes.Aggregate(new StringBuilder(bytes.Length * 2), (sb, b) => sb.Append(b.ToString("X2"))).ToString();
}
static string ByteArrayToHexStringViaStringBuilderForEachByteToString(byte[] bytes) {
    StringBuilder hex = new StringBuilder(bytes.Length * 2);
    foreach (byte b in bytes)
        hex.Append(b.ToString("X2"));
    return hex.ToString();
}
static string ByteArrayToHexStringViaStringBuilderAggregateAppendFormat(byte[] bytes) {
    return bytes.Aggregate(new StringBuilder(bytes.Length * 2), (sb, b) => sb.AppendFormat("{0:X2}", b)).ToString();
}
static string ByteArrayToHexStringViaStringBuilderForEachAppendFormat(byte[] bytes) {
    StringBuilder hex = new StringBuilder(bytes.Length * 2);
    foreach (byte b in bytes)
        hex.AppendFormat("{0:X2}", b);
    return hex.ToString();
}
static string ByteArrayToHexViaByteManipulation(byte[] bytes) {
    char[] c = new char[bytes.Length * 2];
    byte b;
    for (int i = 0; i < bytes.Length; i++) {
        b = ((byte)(bytes[i] >> 4));
        c[i * 2] = (char)(b > 9 ? b + 0x37 : b + 0x30);
        b = ((byte)(bytes[i] & 0xF));
        c[i * 2 + 1] = (char)(b > 9 ? b + 0x37 : b + 0x30);
    }
    return new string(c);
}
static string ByteArrayToHexViaByteManipulation2(byte[] bytes) {
    char[] c = new char[bytes.Length * 2];
    int b;
    for (int i = 0; i < bytes.Length; i++) {
        b = bytes[i] >> 4;
        c[i * 2] = (char)(55 + b + (((b - 10) >> 31) & -7));
        b = bytes[i] & 0xF;
        c[i * 2 + 1] = (char)(55 + b + (((b - 10) >> 31) & -7));
    }
    return new string(c);
}
static string ByteArrayToHexViaSoapHexBinary(byte[] bytes) {
    SoapHexBinary soapHexBinary = new SoapHexBinary(bytes);
    return soapHexBinary.ToString();
}
static string ByteArrayToHexViaLookupAndShift(byte[] bytes) {
    StringBuilder result = new StringBuilder(bytes.Length * 2);
    string hexAlphabet = "0123456789ABCDEF";
    foreach (byte b in bytes) {
        result.Append(hexAlphabet[(int)(b >> 4)]);
        result.Append(hexAlphabet[(int)(b & 0xF)]);
    }
    return result.ToString();
}
static readonly uint* _lookup32UnsafeP = (uint*)GCHandle.Alloc(_Lookup32, GCHandleType.Pinned).AddrOfPinnedObject();
static string ByteArrayToHexViaLookup32UnsafeDirect(byte[] bytes) {
    var lookupP = _lookup32UnsafeP;
    var result = new string((char)0, bytes.Length * 2);
    fixed (byte* bytesP = bytes)
    fixed (char* resultP = result) {
        uint* resultP2 = (uint*)resultP;
        for (int i = 0; i < bytes.Length; i++) {
            resultP2[i] = lookupP[bytesP[i]];
        }
    }
    return result;
}
static uint[] _Lookup32 = Enumerable.Range(0, 255).Select(i => {
    string s = i.ToString("X2");
    return ((uint)s[0]) + ((uint)s[1] << 16);
}).ToArray();
static string ByteArrayToHexViaLookupPerByte(byte[] bytes) {
    var result = new char[bytes.Length * 2];
    for (int i = 0; i < bytes.Length; i++)
    {
        var val = _Lookup32[bytes[i]];
        result[2*i] = (char)val;
        result[2*i + 1] = (char) (val >> 16);
    }
    return new string(result);
}
static string ByteArrayToHexViaLookup(byte[] bytes) {
    string[] hexStringTable = new string[] {
        "00", "01", "02", "03", "04", "05", "06", "07", "08", "09", "0A", "0B", "0C", "0D", "0E", "0F",
        "10", "11", "12", "13", "14", "15", "16", "17", "18", "19", "1A", "1B", "1C", "1D", "1E", "1F",
        "20", "21", "22", "23", "24", "25", "26", "27", "28", "29", "2A", "2B", "2C", "2D", "2E", "2F",
        "30", "31", "32", "33", "34", "35", "36", "37", "38", "39", "3A", "3B", "3C", "3D", "3E", "3F",
        "40", "41", "42", "43", "44", "45", "46", "47", "48", "49", "4A", "4B", "4C", "4D", "4E", "4F",
        "50", "51", "52", "53", "54", "55", "56", "57", "58", "59", "5A", "5B", "5C", "5D", "5E", "5F",
        "60", "61", "62", "63", "64", "65", "66", "67", "68", "69", "6A", "6B", "6C", "6D", "6E", "6F",
        "70", "71", "72", "73", "74", "75", "76", "77", "78", "79", "7A", "7B", "7C", "7D", "7E", "7F",
        "80", "81", "82", "83", "84", "85", "86", "87", "88", "89", "8A", "8B", "8C", "8D", "8E", "8F",
        "90", "91", "92", "93", "94", "95", "96", "97", "98", "99", "9A", "9B", "9C", "9D", "9E", "9F",
        "A0", "A1", "A2", "A3", "A4", "A5", "A6", "A7", "A8", "A9", "AA", "AB", "AC", "AD", "AE", "AF",
        "B0", "B1", "B2", "B3", "B4", "B5", "B6", "B7", "B8", "B9", "BA", "BB", "BC", "BD", "BE", "BF",
        "C0", "C1", "C2", "C3", "C4", "C5", "C6", "C7", "C8", "C9", "CA", "CB", "CC", "CD", "CE", "CF",
        "D0", "D1", "D2", "D3", "D4", "D5", "D6", "D7", "D8", "D9", "DA", "DB", "DC", "DD", "DE", "DF",
        "E0", "E1", "E2", "E3", "E4", "E5", "E6", "E7", "E8", "E9", "EA", "EB", "EC", "ED", "EE", "EF",
        "F0", "F1", "F2", "F3", "F4", "F5", "F6", "F7", "F8", "F9", "FA", "FB", "FC", "FD", "FE", "FF",
    };
    StringBuilder result = new StringBuilder(bytes.Length * 2);
    foreach (byte b in bytes) {
        result.Append(hexStringTable[b]);
    }
    return result.ToString();
}

更新(2010-01-13)

Waleed的分析答案增加了。 蛮快。

更新(2011-10-05)

为了完整性添加了string.Concat Array.ConvertAll变体(需要.NET 4.0)。 与string.Join版本一致。

更新(2012-02-05)

测试回购包括更多变体,如StringBuilder.Append(b.ToString("X2")) 。 没有打乱任何结果。 foreach{IEnumerable}.Aggregate 。例如, {IEnumerable}.Aggregate ,但BitConverter仍然赢。

更新(2012-04-03)

分析中添加了Mykroft的SoapHexBinary答案,并获得了第三名。

更新(2013-01-15)

添加了CodesInChaos的字节操作答案,该答案占据了第一名(在大块文本上大幅度增加)。

更新(2013-05-23)

添加了Nathan Moinvaziri的查找答案以及Brian Lambert博客中的变体。 两者相当快,但在我使用的测试机器(AMD Phenom 9750)上没有领先。

更新(2014-07-31)

增加了@ CodesInChaos的新的基于字节的查找答案。 它似乎在句子测试和全文测试中都处于领先地位。

更新(2015-08-20)

回答的回购添加了airbreather优化和unsafe变体。 如果你想玩不安全的游戏,你可以在短字符串和大文本上获得比以前任何优胜者都大的性能提升。

如何将字节数组转换为十六进制字符串,反之亦然?


Extension methods (disclaimer: completely untested code, BTW...):

public static class ByteExtensions
{
    public static string ToHexString(this byte[] ba)
    {
        StringBuilder hex = new StringBuilder(ba.Length * 2);

        foreach (byte b in ba)
        {
            hex.AppendFormat("{0:x2}", b);
        }
        return hex.ToString();
    }
}

etc.. Use either of Tomalak's three solutions (with the last one being an extension method on a string).


And for inserting into an SQL string (if you're not using command parameters):

public static String ByteArrayToSQLHexString(byte[] Source)
{
    return = "0x" + BitConverter.ToString(Source).Replace("-", "");
}

Another way is by using stackalloc to reduce GC memory pressure:

static string ByteToHexBitFiddle(byte[] bytes)
{
        var c = stackalloc char[bytes.Length * 2 + 1];
        int b; 
        for (int i = 0; i < bytes.Length; ++i)
        {
            b = bytes[i] >> 4;
            c[i * 2] = (char)(55 + b + (((b - 10) >> 31) & -7));
            b = bytes[i] & 0xF;
            c[i * 2 + 1] = (char)(55 + b + (((b - 10) >> 31) & -7));
        }
        c[bytes.Length * 2 ] = '\0';
        return new string(c);
}

For performance I would go with drphrozens solution. A tiny optimization for the decoder could be to use a table for either char to get rid of the "<< 4".

Clearly the two method calls are costly. If some kind of check is made either on input or output data (could be CRC, checksum or whatever) the if (b == 255)... could be skipped and thereby also the method calls altogether.

Using offset++ and offset instead of offset and offset + 1 might give some theoretical benefit but I suspect the compiler handles this better than me.

private static readonly byte[] LookupTableLow = new byte[] {
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF
};

private static readonly byte[] LookupTableHigh = new byte[] {
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0x00, 0x10, 0x20, 0x30, 0x40, 0x50, 0x60, 0x70, 0x80, 0x90, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0xA0, 0xB0, 0xC0, 0xD0, 0xE0, 0xF0, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0xA0, 0xB0, 0xC0, 0xD0, 0xE0, 0xF0, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF
};

private static byte LookupLow(char c)
{
  var b = LookupTableLow[c];
  if (b == 255)
    throw new IOException("Expected a hex character, got " + c);
  return b;
}

private static byte LookupHigh(char c)
{
  var b = LookupTableHigh[c];
  if (b == 255)
    throw new IOException("Expected a hex character, got " + c);
  return b;
}

public static byte ToByte(char[] chars, int offset)
{
  return (byte)(LookupHigh(chars[offset++]) | LookupLow(chars[offset]));
}

This is just off the top of my head and has not been tested or benchmarked.


From Microsoft's developers, a nice, simple conversion:

public static string ByteArrayToString(byte[] ba) 
{
    // Concatenate the bytes into one long string
    return ba.Aggregate(new StringBuilder(32),
                            (sb, b) => sb.Append(b.ToString("X2"))
                            ).ToString();
}

While the above is clean an compact, performance junkies will scream about it using enumerators. You can get peak performance with an improved version of Tomolak's original answer:

public static string ByteArrayToString(byte[] ba)   
{   
   StringBuilder hex = new StringBuilder(ba.Length * 2);   

   for(int i=0; i < ga.Length; i++)       // <-- Use for loop is faster than foreach   
       hex.Append(ba[i].ToString("X2"));   // <-- ToString is faster than AppendFormat   

   return hex.ToString();   
} 

This is the fastest of all the routines I've seen posted here so far. Don't just take my word for it... performance test each routine and inspect its CIL code for yourself.


I did not get the code you suggested to work, Olipro. hex[i] + hex[i+1] apparently returned an int .

I did, however have some success by taking some hints from Waleeds code and hammering this together. It's ugly as hell but it seems to work and performs at 1/3 of the time compared to the others according to my tests (using patridges testing mechanism). Depending on input size. Switching around the ?:s to separate out 0-9 first would probably yield a slightly faster result since there are more numbers than letters.

public static byte[] StringToByteArray2(string hex)
{
    byte[] bytes = new byte[hex.Length/2];
    int bl = bytes.Length;
    for (int i = 0; i < bl; ++i)
    {
        bytes[i] = (byte)((hex[2 * i] > 'F' ? hex[2 * i] - 0x57 : hex[2 * i] > '9' ? hex[2 * i] - 0x37 : hex[2 * i] - 0x30) << 4);
        bytes[i] |= (byte)(hex[2 * i + 1] > 'F' ? hex[2 * i + 1] - 0x57 : hex[2 * i + 1] > '9' ? hex[2 * i + 1] - 0x37 : hex[2 * i + 1] - 0x30);
    }
    return bytes;
}

I'll enter this bit fiddling competition as I have an answer that also uses bit-fiddling to decode hexadecimals. Note that using character arrays may be even faster as calling StringBuilder methods will take time as well.

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;
}

Converted from Java code.


In terms of speed, this seems to be better than anything here:

  public static string ToHexString(byte[] data) {
    byte b;
    int i, j, k;
    int l = data.Length;
    char[] r = new char[l * 2];
    for (i = 0, j = 0; i < l; ++i) {
      b = data[i];
      k = b >> 4;
      r[j++] = (char)(k > 9 ? k + 0x37 : k + 0x30);
      k = b & 15;
      r[j++] = (char)(k > 9 ? k + 0x37 : k + 0x30);
    }
    return new string(r);
  }

Inverse function for Waleed Eissa code (Hex String To Byte Array):

    public static byte[] HexToBytes(this string hexString)        
    {
        byte[] b = new byte[hexString.Length / 2];            
        char c;
        for (int i = 0; i < hexString.Length / 2; i++)
        {
            c = hexString[i * 2];
            b[i] = (byte)((c < 0x40 ? c - 0x30 : (c < 0x47 ? c - 0x37 : c - 0x57)) << 4);
            c = hexString[i * 2 + 1];
            b[i] += (byte)(c < 0x40 ? c - 0x30 : (c < 0x47 ? c - 0x37 : c - 0x57));
        }

        return b;
    }

Waleed Eissa function with lower case support:

    public static string BytesToHex(this byte[] barray, bool toLowerCase = true)
    {
        byte addByte = 0x37;
        if (toLowerCase) addByte = 0x57;
        char[] c = new char[barray.Length * 2];
        byte b;
        for (int i = 0; i < barray.Length; ++i)
        {
            b = ((byte)(barray[i] >> 4));
            c[i * 2] = (char)(b > 9 ? b + addByte : b + 0x30);
            b = ((byte)(barray[i] & 0xF));
            c[i * 2 + 1] = (char)(b > 9 ? b + addByte : b + 0x30);
        }

        return new string(c);
    }

Not to pile on to the many answers here, but I found a fairly optimal (~4.5x better than accepted), straightforward implementation of the hex string parser. First, output from my tests (the first batch is my implementation):

Give me that string:
04c63f7842740c77e545bb0b2ade90b384f119f6ab57b680b7aa575a2f40939f

Time to parse 100,000 times: 50.4192 ms
Result as base64: BMY/eEJ0DHflRbsLKt6Qs4TxGfarV7aAt6pXWi9Ak58=
BitConverter'd: 04-C6-3F-78-42-74-0C-77-E5-45-BB-0B-2A-DE-90-B3-84-F1-19-F6-AB-5
7-B6-80-B7-AA-57-5A-2F-40-93-9F

Accepted answer: (StringToByteArray)
Time to parse 100000 times: 233.1264ms
Result as base64: BMY/eEJ0DHflRbsLKt6Qs4TxGfarV7aAt6pXWi9Ak58=
BitConverter'd: 04-C6-3F-78-42-74-0C-77-E5-45-BB-0B-2A-DE-90-B3-84-F1-19-F6-AB-5
7-B6-80-B7-AA-57-5A-2F-40-93-9F

With Mono's implementation:
Time to parse 100000 times: 777.2544ms
Result as base64: BMY/eEJ0DHflRbsLKt6Qs4TxGfarV7aAt6pXWi9Ak58=
BitConverter'd: 04-C6-3F-78-42-74-0C-77-E5-45-BB-0B-2A-DE-90-B3-84-F1-19-F6-AB-5
7-B6-80-B7-AA-57-5A-2F-40-93-9F

With SoapHexBinary:
Time to parse 100000 times: 845.1456ms
Result as base64: BMY/eEJ0DHflRbsLKt6Qs4TxGfarV7aAt6pXWi9Ak58=
BitConverter'd: 04-C6-3F-78-42-74-0C-77-E5-45-BB-0B-2A-DE-90-B3-84-F1-19-F6-AB-5
7-B6-80-B7-AA-57-5A-2F-40-93-9F

The base64 and 'BitConverter'd' lines are there to test for correctness. Note that they are equal.

The implementation:

public static byte[] ToByteArrayFromHex(string hexString)
{
  if (hexString.Length % 2 != 0) throw new ArgumentException("String must have an even length");
  var array = new byte[hexString.Length / 2];
  for (int i = 0; i < hexString.Length; i += 2)
  {
    array[i/2] = ByteFromTwoChars(hexString[i], hexString[i + 1]);
  }
  return array;
}

private static byte ByteFromTwoChars(char p, char p_2)
{
  byte ret;
  if (p <= '9' && p >= '0')
  {
    ret = (byte) ((p - '0') << 4);
  }
  else if (p <= 'f' && p >= 'a')
  {
    ret = (byte) ((p - 'a' + 10) << 4);
  }
  else if (p <= 'F' && p >= 'A')
  {
    ret = (byte) ((p - 'A' + 10) << 4);
  } else throw new ArgumentException("Char is not a hex digit: " + p,"p");

  if (p_2 <= '9' && p_2 >= '0')
  {
    ret |= (byte) ((p_2 - '0'));
  }
  else if (p_2 <= 'f' && p_2 >= 'a')
  {
    ret |= (byte) ((p_2 - 'a' + 10));
  }
  else if (p_2 <= 'F' && p_2 >= 'A')
  {
    ret |= (byte) ((p_2 - 'A' + 10));
  } else throw new ArgumentException("Char is not a hex digit: " + p_2, "p_2");

  return ret;
}

I tried some stuff with unsafe and moving the (clearly redundant) character-to-nibble if sequence to another method, but this was the fastest it got.

(I concede that this answers half the question. I felt that the string->byte[] conversion was underrepresented, while the byte[]->string angle seems to be well covered. Thus, this answer.)


This is a great post. I like Waleed's solution. I haven't run it through patridge's test but it seems to be quite fast. I also needed the reverse process, converting a hex string to a byte array, so I wrote it as a reversal of Waleed's solution. Not sure if it's any faster than Tomalak's original solution. Again, I did not run the reverse process through patridge's test either.

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;
}

Two mashups which folds the two nibble operations into one.

Probably pretty efficient version:

public static string ByteArrayToString2(byte[] ba)
{
    char[] c = new char[ba.Length * 2];
    for( int i = 0; i < ba.Length * 2; ++i)
    {
        byte b = (byte)((ba[i>>1] >> 4*((i&1)^1)) & 0xF);
        c[i] = (char)(55 + b + (((b-10)>>31)&-7));
    }
    return new string( c );
}

Decadent linq-with-bit-hacking version:

public static string ByteArrayToString(byte[] ba)
{
    return string.Concat( ba.SelectMany( b => new int[] { b >> 4, b & 0xF }).Select( b => (char)(55 + b + (((b-10)>>31)&-7))) );
}

And reverse:

public static byte[] HexStringToByteArray( string s )
{
    byte[] ab = new byte[s.Length>>1];
    for( int i = 0; i < s.Length; i++ )
    {
        int b = s[i];
        b = (b - '0') + ((('9' - b)>>31)&-7);
        ab[i>>1] |= (byte)(b << 4*((i&1)^1));
    }
    return ab;
}

Why make it complex? This is simple in Visual Studio 2008:

C#:

string hex = BitConverter.ToString(YourByteArray).Replace("-", "");

VB:

Dim hex As String = BitConverter.ToString(YourByteArray).Replace("-", "")

另一种基于查找表的方法。 这个对每个字节只使用一个查找表,而不是每个半字节的查找表。

private static readonly uint[] _lookup32 = CreateLookup32();

private static uint[] CreateLookup32()
{
    var result = new uint[256];
    for (int i = 0; i < 256; i++)
    {
        string s=i.ToString("X2");
        result[i] = ((uint)s[0]) + ((uint)s[1] << 16);
    }
    return result;
}

private static string ByteArrayToHexViaLookup32(byte[] bytes)
{
    var lookup32 = _lookup32;
    var result = new char[bytes.Length * 2];
    for (int i = 0; i < bytes.Length; i++)
    {
        var val = lookup32[bytes[i]];
        result[2*i] = (char)val;
        result[2*i + 1] = (char) (val >> 16);
    }
    return new string(result);
}

我还在查找表中使用ushortstruct{char X1, X2}struct{byte X1, X2}测试了这种变体。

根据编译目标(x86,X64)的不同,它们的性能大致相同,或者略低于该变体。

而对于更高的表现,它的unsafe兄弟姐妹:

private static readonly uint[] _lookup32Unsafe = CreateLookup32Unsafe();
private static readonly uint* _lookup32UnsafeP = (uint*)GCHandle.Alloc(_lookup32Unsafe,GCHandleType.Pinned).AddrOfPinnedObject();

private static uint[] CreateLookup32Unsafe()
{
    var result = new uint[256];
    for (int i = 0; i < 256; i++)
    {
        string s=i.ToString("X2");
        if(BitConverter.IsLittleEndian)
            result[i] = ((uint)s[0]) + ((uint)s[1] << 16);
        else
            result[i] = ((uint)s[1]) + ((uint)s[0] << 16);
    }
    return result;
}

public static string ByteArrayToHexViaLookup32Unsafe(byte[] bytes)
{
    var lookupP = _lookup32UnsafeP;
    var result = new char[bytes.Length * 2];
    fixed(byte* bytesP = bytes)
    fixed (char* resultP = result)
    {
        uint* resultP2 = (uint*)resultP;
        for (int i = 0; i < bytes.Length; i++)
        {
            resultP2[i] = lookupP[bytesP[i]];
        }
    }
    return new string(result);
}

或者如果您认为可以直接写入字符串:

public static string ByteArrayToHexViaLookup32UnsafeDirect(byte[] bytes)
{
    var lookupP = _lookup32UnsafeP;
    var result = new string((char)0, bytes.Length * 2);
    fixed (byte* bytesP = bytes)
    fixed (char* resultP = result)
    {
        uint* resultP2 = (uint*)resultP;
        for (int i = 0; i < bytes.Length; i++)
        {
            resultP2[i] = lookupP[bytesP[i]];
        }
    }
    return result;
}

在编写加密代码时,通常避免依赖数据的分支和表查找以确保运行时不依赖于数据,因为数据相关的时序可能会导致旁路通道攻击。

它也很快。

static string ByteToHexBitFiddle(byte[] bytes)
{
    char[] c = new char[bytes.Length * 2];
    int b;
    for (int i = 0; i < bytes.Length; i++) {
        b = bytes[i] >> 4;
        c[i * 2] = (char)(55 + b + (((b-10)>>31)&-7));
        b = bytes[i] & 0xF;
        c[i * 2 + 1] = (char)(55 + b + (((b-10)>>31)&-7));
    }
    return new string(c);
}

Ph'nglui mglw'nafh Cthulhu R'lyeh wgah'nagl fhtagn

放弃所有希望,谁进入这里

奇怪的位的解释:

  1. bytes[i] >> 4提取一个字节的高半字节
    bytes[i] & 0xF提取一个字节的低半字节
  2. b - 10
    对于值b < 10 < 0 ,它将变成十进制数字
    对于值b > 10>= 0 ,这将成为从AF一个字母。
  3. 感谢符号扩展名,在有符号的32位整数上使用i >> 31提取符号。 对于i < 0 ,它将为-1 ,对于i >= 0则为i >= 0
  4. 结合2)和3),显示(b-10)>>31对于字母将为0 ,对于数字则为-1
  5. 看字母的情况,最后一个加数变为0b在10到15的范围内。我们想把它映射到A (65)到F (70),这意味着加入55( 'A'-10 ) 。
  6. 看一下数字的情况,我们想调整最后的加数,因此它将范围从0到9的b映射到范围0 (48)到9 (57)。 这意味着它需要变成-7( '0' - 55 )。
    现在我们可以乘以7.但是因为-1代表所有位为1,所以我们可以使用& -7(0 & -7) == 0(-1 & -7) == -7

进一步考虑:

  • 我没有使用第二个循环变量来索引c ,因为测量显示从i计算它更便宜。
  • 正好使用i < bytes.Length作为循环的上限允许JITter消除bytes[i]边界检查,因此我选择了该变体。
  • 使b成为一个int允许从字节到字节进行不必要的转换。

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(字节[])


我今天遇到了同样的问题,并且遇到了这样的代码:

private static string ByteArrayToHex(byte[] barray)
{
    char[] c = new char[barray.Length * 2];
    byte b;
    for (int i = 0; i < barray.Length; ++i)
    {
        b = ((byte)(barray[i] >> 4));
        c[i * 2] = (char)(b > 9 ? b + 0x37 : b + 0x30);
        b = ((byte)(barray[i] & 0xF));
        c[i * 2 + 1] = (char)(b > 9 ? b + 0x37 : b + 0x30);
    }
    return new string(c);
}

来源:论坛帖子here (请参阅PZahra的帖子)。 我稍微修改了代码以删除0x前缀。

我对代码做了一些性能测试,比使用BitConverter.ToString()快了近8倍(根据patridge的帖子,速度最快)。


有一个叫做SoapHexBinary的类,它完全符合你的要求。

using System.Runtime.Remoting.Metadata.W3cXsd2001;

public static byte[] GetStringToBytes(string value)
{
    SoapHexBinary shb = SoapHexBinary.Parse(value);
    return shb.Value;
}

public static string GetBytesToString(byte[] value)
{
    SoapHexBinary shb = new SoapHexBinary(value);
    return shb.ToString();
}

这个问题也可以使用查找表来解决。 这将需要编码器和解码器的少量静态存储器。 然而这种方法会很快:

  • 编码器表512字节或1024字节(如果需要大写和小写两种大小)
  • 解码器表256字节或64 KiB(单字符查找或双字符查找)

我的解决方案使用1024个字节的编码表和256个字节的解码。

解码

private static readonly byte[] LookupTable = new byte[] {
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
  0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF
};

private static byte Lookup(char c)
{
  var b = LookupTable[c];
  if (b == 255)
    throw new IOException("Expected a hex character, got " + c);
  return b;
}

public static byte ToByte(char[] chars, int offset)
{
  return (byte)(Lookup(chars[offset]) << 4 | Lookup(chars[offset + 1]));
}

编码

private static readonly char[][] LookupTableUpper;
private static readonly char[][] LookupTableLower;

static Hex()
{
  LookupTableLower = new char[256][];
  LookupTableUpper = new char[256][];
  for (var i = 0; i < 256; i++)
  {
    LookupTableLower[i] = i.ToString("x2").ToCharArray();
    LookupTableUpper[i] = i.ToString("X2").ToCharArray();
  }
}

public static char[] ToCharLower(byte[] b, int bOffset)
{
  return LookupTableLower[b[bOffset]];
}

public static char[] ToCharUpper(byte[] b, int bOffset)
{
  return LookupTableUpper[b[bOffset]];
}

对照

StringBuilderToStringFromBytes:   106148
BitConverterToStringFromBytes:     15783
ArrayConvertAllToStringFromBytes:  54290
ByteManipulationToCharArray:        8444
TableBasedToCharArray:              5651 *

*这个解决方案

注意

在解码过程中,IOException和IndexOutOfRangeException可能发生(如果一个字符的值> 256)。 应该实施对流或数组进行解码/编码的方法,这只是一个概念证明。





hex