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

这可以从字符串到字节数组。。。

public static byte[] StrToByteArray(string str)
    {
        Dictionary<string, byte> hexindex = new Dictionary<string, byte>();
        for (byte i = 0; i < 255; i++)
            hexindex.Add(i.ToString("X2"), i);

        List<byte> hexres = new List<byte>();
        for (int i = 0; i < str.Length; i += 2)
            hexres.Add(hexindex[str.Substring(i, 2)]);

        return hexres.ToArray();
    }

其他回答

性能分析

注:2015-08-20新领导。

我通过一些粗略的Stopwatch性能测试运行了各种转换方法,一次使用随机语句(n=61,1000次迭代),另一次使用Project Gutenburg文本(n=1238957,150次迭代)。以下是结果,大致从最快到最慢。所有测量值都以刻度为单位(10000刻度=1毫秒),所有相关注释都与[最慢]StringBuilder实现进行比较。对于所使用的代码,请参阅下面的测试框架repo,我现在在那里维护运行该代码。

免责声明

警告:不要依赖这些统计数据来获取任何具体信息;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,请在代表您生产需求的环境中测试这些方法,并使用代表您将使用的数据。

后果

按字节不安全查找(通过CodesInChaos)(通过空气呼吸器添加到测试报告中)文本:4727.85(105.2X)句子:0.28(99.7X)按字节查找(通过CodesInChaos)文本:10853.96(速度快45.8倍)句子:0.65(快42.7X)字节操作2(通过CodesInChaos)文本:12967.69(38.4X更快)句子:0.73(快37.9倍)字节操作(通过Waleed Eissa)文本:16856.64(快29.5倍)句子:0.70(快39.5倍)查找/轮班(通过Nathan Moinvaziri)文本:23201.23(速度快21.4倍)句子:1.24(快22.3倍)通过半字节查找(通过Brian Lambert)文本:23879.41(速度加快20.8倍)句子:1.15(快23.9倍)BitConverter(通过Tomalak)文本:113269.34(速度快4.4倍)句子:9.98(快2.8倍){SoapHexBinary}.ToString(通过Mykroft)文本:178601.39(速度快2.8倍)句子:10.68(快2.6倍){byte}.ToString(“X2”)(使用foreach)(源自Will Dean的答案)文本:308805.38(速度快2.4倍)句子:16.89(快2.4倍){byte}.ToString(“X2”)(使用{IEnumerable}.Agregate,需要System.Linq)(通过Mark)文本:352828.20(快2.1倍)句子:16.87(快2.4倍)Array.ConvertAll(使用string.Join)(通过Will Dean)文本:675451.57(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)文本:752078.70(速度快1.0倍)句子:18.28(快2.2倍){StringBuilder}.AppendFormat(使用foreach)(通过Tomalak)文本:672115.77(快1.1倍)句子:36.82(快1.1倍){StringBuilder}.AppendFormat(使用{IEnumerable}.Agregate,需要System.Linq)(源自Tomalak的答案)文本:718380.63(速度快1.0倍)句子:39.71(快1.0X)

查找表已经领先于字节操作。基本上,有某种形式的预先计算任何给定的半字节或字节将是十六进制的。然后,当您读取数据时,只需查找下一部分,看看它是什么十六进制字符串。然后以某种方式将该值添加到结果字符串输出中。在很长一段时间里,字节操作是性能最好的方法,而某些开发人员可能更难阅读。

您最好的选择仍然是找到一些具有代表性的数据,并在类似于生产的环境中进行测试。如果您有不同的内存限制,您可能更喜欢分配更少的方法,而不是更快但消耗更多内存的方法。

测试代码

请随意使用我使用的测试代码。此处包含一个版本,但您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东西或希望帮助改进它使用的测试框架,请提交一个拉取请求。

将新的静态方法(Func<byte[],string>)添加到/Tests/ConvertByteArrayToHexString/Test.cs。将该方法的名称添加到同一类中的TestCandidate返回值中。通过切换同一类中GenerateTestInput中的注释,确保您正在运行所需的输入版本(句子或文本)。单击F5并等待输出(/bin文件夹中也会生成HTML转储)。

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)

添加了瓦利德对分析的回答。速度相当快。

更新(2011-10-05)

为了完整性,添加了string.Concat Array.ConvertAll变量(需要.NET 4.0)。与string.Join版本相同。

更新(2012-02-05)

测试回购包括更多变体,如StringBuilder.Append(b.ToString(“X2”))。没有一个会影响结果。foreach比{IEnumerable}更快。例如,Aggregate,但BitConverter仍然获胜。

更新(2012-04-03)

将Mykroft的SoapHexBinary答案添加到分析中,获得第三名。

更新(2013-01-15)

增加了CodesInChaos的字节操作答案,该答案占据了第一位(在大块文本上有很大的空白)。

更新(2013-05-23)

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

更新(2014-07-31)

添加了@CodesInChaos基于字节的新查找答案。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)

将空气助燃器的优化和不安全变体添加到这个答案的repo中。如果你想在不安全的游戏中玩,你可以在短字符串和大文本上比之前的任何一个冠军获得巨大的性能提升。

这是我的尝试。我创建了一对扩展类来扩展字符串和字节。在大文件测试中,性能与Byte Manipulation 2相当。

下面的ToHexString代码是查找和移位算法的优化实现。它与Behrooz的方法几乎相同,但使用foreach进行迭代,计数器比显式索引更快。

在我的机器上,它排在Byte Manipulation 2之后,排在第二位,是非常可读的代码。以下测试结果也值得关注:

ToHexStringCharArrayWithCharArrayLookup:41589.69平均刻度(超过1000次),1.5倍ToHexStringCharArrayWithStringLookup:50764.06平均滴答(超过1000次),1.2XToHexStringStringBuilderWithCharArrayLookup:62812.87平均滴答(超过1000次),1.0X

根据上述结果,可以得出以下结论:

索引到字符串以执行查找与char数组在大型文件测试中非常重要。使用已知容量的StringBuilder与使用字符的惩罚创建字符串的已知大小的数组甚至更重要。

代码如下:

using System;

namespace ConversionExtensions
{
    public static class ByteArrayExtensions
    {
        private readonly static char[] digits = new char[] { '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B', 'C', 'D', 'E', 'F' };

        public static string ToHexString(this byte[] bytes)
        {
            char[] hex = new char[bytes.Length * 2];
            int index = 0;

            foreach (byte b in bytes)
            {
                hex[index++] = digits[b >> 4];
                hex[index++] = digits[b & 0x0F];
            }

            return new string(hex);
        }
    }
}


using System;
using System.IO;

namespace ConversionExtensions
{
    public static class StringExtensions
    {
        public static byte[] ToBytes(this string hexString)
        {
            if (!string.IsNullOrEmpty(hexString) && hexString.Length % 2 != 0)
            {
                throw new FormatException("Hexadecimal string must not be empty and must contain an even number of digits to be valid.");
            }

            hexString = hexString.ToUpperInvariant();
            byte[] data = new byte[hexString.Length / 2];

            for (int index = 0; index < hexString.Length; index += 2)
            {
                int highDigitValue = hexString[index] <= '9' ? hexString[index] - '0' : hexString[index] - 'A' + 10;
                int lowDigitValue = hexString[index + 1] <= '9' ? hexString[index + 1] - '0' : hexString[index + 1] - 'A' + 10;

                if (highDigitValue < 0 || lowDigitValue < 0 || highDigitValue > 15 || lowDigitValue > 15)
                {
                    throw new FormatException("An invalid digit was encountered. Valid hexadecimal digits are 0-9 and A-F.");
                }
                else
                {
                    byte value = (byte)((highDigitValue << 4) | (lowDigitValue & 0x0F));
                    data[index / 2] = value;
                }
            }

            return data;
        }
    }
}

下面是当我将代码放在我机器上的@patridge测试项目中时得到的测试结果。我还添加了一个从十六进制转换为字节数组的测试。使用我的代码的测试运行是ByteArrayToHexViaOptimizedLookupAndShift和HexToByteArrayViaByteManipulation。HexToByteArrayViaConvertToByte取自XXXX。HexToByteArrayViaSoapHexBinary是@Mykroft的答案。

Intel Pentium III Xeon处理器核心:4<br/>当前时钟速度:1576<br/>最大时钟速度:3092<br/>将字节数组转换为十六进制字符串表示ByteArrayToHexViaByteManipulation2:39366.64平均滴答(超过1000次),22.4倍ByteArrayToHexViaOptimizedLookupAndShift:41588.64平均刻度(超过1000次),21.2倍ByteArrayToHexViaLookup:55509.56次平均点击(超过1000次),15.9倍ByteArrayToHexViaByteManipulation:65349.12平均刻度(超过1000次),13.5XByteArrayToHexViaLookupAndShift:86926.87平均刻度(超过1000运行),10.2XByteArrayToHexStringViaBitConverter:平均139353.73滴答声(超过1000次),6.3XByteArrayToHexViaSoapHexBinary:314598.77平均刻度(超过1000次),2.8XByteArrayToHexStringViaStringBuilderForEachByteToString:344264.63平均刻度(超过1000次),2.6XByteArrayToHexStringViaStringBuilderAggregateByteToString:382623.44平均滴答声(超过1000次),2.3XByteArrayToHexStringViaStringBuilderForEachAppend格式:818111.95平均滴答声(超过1000次),1.1倍ByteArrayToHexStringViaStringConcatArray ConvertAll:839424.84平均值滴答声(超过1000次),1.1XByteArrayToHexStringViaStringBuilderAggregateAppend格式:867303.98平均刻度(超过1000次),1.0XByteArrayToHexStringViaStringJoinArray ConvertAll:平均882710.28滴答声(超过1000次),1.0X

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。

未针对速度进行优化,但比大多数答案(.NET 4.0)更LINQy:

<Extension()>
Public Function FromHexToByteArray(hex As String) As Byte()
    hex = If(hex, String.Empty)
    If hex.Length Mod 2 = 1 Then hex = "0" & hex
    Return Enumerable.Range(0, hex.Length \ 2).Select(Function(i) Convert.ToByte(hex.Substring(i * 2, 2), 16)).ToArray
End Function

<Extension()>
Public Function ToHexString(bytes As IEnumerable(Of Byte)) As String
    Return String.Concat(bytes.Select(Function(b) b.ToString("X2")))
End Function

如果你想得到wcoenen报告的“4倍速度增长”,那么如果不明显:用hex[i]+hex[i+1]替换hex.Substring(i,2)

您还可以再进一步,通过在两个地方使用i++来消除i+=2。