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);
}
其他回答
另一个快速功能。。。
private static readonly byte[] HexNibble = new byte[] {
0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
0x8, 0x9, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
0x0, 0xA, 0xB, 0xC, 0xD, 0xE, 0xF, 0x0,
0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
0x0, 0xA, 0xB, 0xC, 0xD, 0xE, 0xF
};
public static byte[] HexStringToByteArray( string str )
{
int byteCount = str.Length >> 1;
byte[] result = new byte[byteCount + (str.Length & 1)];
for( int i = 0; i < byteCount; i++ )
result[i] = (byte) (HexNibble[str[i << 1] - 48] << 4 | HexNibble[str[(i << 1) + 1] - 48]);
if( (str.Length & 1) != 0 )
result[byteCount] = (byte) HexNibble[str[str.Length - 1] - 48];
return result;
}
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。
可以使用从.NET 5开始的Convert.ToHexString。还有一个用于反向操作的方法:Convert.FromHexString。
对于较旧版本的.NET,您可以使用:
public static string ByteArrayToString(byte[] ba)
{
StringBuilder hex = new StringBuilder(ba.Length * 2);
foreach (byte b in ba)
hex.AppendFormat("{0:x2}", b);
return hex.ToString();
}
or:
public static string ByteArrayToString(byte[] ba)
{
return BitConverter.ToString(ba).Replace("-","");
}
举个例子,这里有更多的方法。
反向转换如下:
public static byte[] StringToByteArray(String hex)
{
int NumberChars = hex.Length;
byte[] bytes = new byte[NumberChars / 2];
for (int i = 0; i < NumberChars; i += 2)
bytes[i / 2] = Convert.ToByte(hex.Substring(i, 2), 16);
return bytes;
}
使用Substring是与Convert.ToByte结合使用的最佳选项。有关详细信息,请参阅此答案。如果需要更好的性能,必须避免Convert.ToByte,然后才能删除SubString。
测试:十六进制字符串到字节数组
我注意到,大多数测试都是在将Bytes数组转换为十六进制字符串的函数上执行的。因此,在这篇文章中,我将关注另一方面:将十六进制字符串转换为字节数组的函数。若您只对结果感兴趣,可以跳到“摘要”部分。测试代码文件在文章末尾提供。
标签
我想根据接受的答案(Tomalak)将函数命名为StringToByteArrayV1,或将其快捷到V1。其余函数将以相同的方式命名:V2、V3、V4、…、。。。,等
参与功能索引
Tomalak的StringToByteArrayV1(公认答案)Mykroft的StringToByteArrayV2(使用SoapHexBinary)drphrozen的StringToByteArrayV3(查找表)CoperNick的StringToByteArrayV4(字节操作)Chris F编写的StringToByteArrayV5_1(字节操作)Chris F的StringToByteArrayV5_2(V5_1+根据Amir Rezaei的评论修改)Chris F的StringToByteArrayV5_3(V5_2+根据Ben Voigt的评论对其进行了修改)(您可以在发布后的测试代码中看到它的最终形状)Ben Mosher编写的StringToByteArrayV6(字节操作)Maratius的StringToByteArrayV7(字节操作-安全版本)Maratius的StringToByteArrayV8(字节操作-不安全版本)StringToByteArrayV9(按Geograph)AlejandroAlis编写的StringToByteArrayV10Fredrik Hu编写的StringToByteArrayV11Maarten Bodewes编写的StringToByteArrayV12ClausAndersen编写的StringToByteArrayV13Stas Makutin编写的StringToByteArrayV14JJJ的StringToByteArrayV15JamieSee的StringToByteArrayV16spacepille的StringToByteArrayV17Gregory Morse编写的StringToByteArrayV18Rick编写的StringToByteArrayV19SandRock的StringToByteArrayV20Paul编写的StringToByteArrayV21
正确性测试
我通过传递1字节的所有256个可能值来测试正确性,然后检查输出是否正确。结果:
V18中以“00”开头的字符串有问题(请参阅Roger Stewart对此的评论)。除了通过所有测试。如果十六进制字符串字母是大写的:所有函数都成功传递如果十六进制字符串字母是小写的,则以下函数失败:V5_1、V5_2、v7、V8、V15、V19
注:V5_3解决了这个问题(V5_1和V5_2)
性能测试
我已经使用Stopwatch类进行了性能测试。
长字符串的性能
input length: 10,000,000 bytes
runs: 100
average elapsed time per run:
V1 = 136.4ms
V2 = 104.5ms
V3 = 22.0ms
V4 = 9.9ms
V5_1 = 10.2ms
V5_2 = 9.0ms
V5_3 = 9.3ms
V6 = 18.3ms
V7 = 9.8ms
V8 = 8.8ms
V9 = 10.2ms
V10 = 19.0ms
V11 = 12.2ms
V12 = 27.4ms
V13 = 21.8ms
V14 = 12.0ms
V15 = 14.9ms
V16 = 15.3ms
V17 = 9.5ms
V18 got excluded from this test, because it was very slow when using very long string
V19 = 222.8ms
V20 = 66.0ms
V21 = 15.4ms
V1 average ticks per run: 1363529.4
V2 is more fast than V1 by: 1.3 times (ticks ratio)
V3 is more fast than V1 by: 6.2 times (ticks ratio)
V4 is more fast than V1 by: 13.8 times (ticks ratio)
V5_1 is more fast than V1 by: 13.3 times (ticks ratio)
V5_2 is more fast than V1 by: 15.2 times (ticks ratio)
V5_3 is more fast than V1 by: 14.8 times (ticks ratio)
V6 is more fast than V1 by: 7.4 times (ticks ratio)
V7 is more fast than V1 by: 13.9 times (ticks ratio)
V8 is more fast than V1 by: 15.4 times (ticks ratio)
V9 is more fast than V1 by: 13.4 times (ticks ratio)
V10 is more fast than V1 by: 7.2 times (ticks ratio)
V11 is more fast than V1 by: 11.1 times (ticks ratio)
V12 is more fast than V1 by: 5.0 times (ticks ratio)
V13 is more fast than V1 by: 6.3 times (ticks ratio)
V14 is more fast than V1 by: 11.4 times (ticks ratio)
V15 is more fast than V1 by: 9.2 times (ticks ratio)
V16 is more fast than V1 by: 8.9 times (ticks ratio)
V17 is more fast than V1 by: 14.4 times (ticks ratio)
V19 is more SLOW than V1 by: 1.6 times (ticks ratio)
V20 is more fast than V1 by: 2.1 times (ticks ratio)
V21 is more fast than V1 by: 8.9 times (ticks ratio)
V18的长串性能
V18 took long time at the previous test,
so let's decrease length for it:
input length: 1,000,000 bytes
runs: 100
average elapsed time per run: V1 = 14.1ms , V18 = 146.7ms
V1 average ticks per run: 140630.3
V18 is more SLOW than V1 by: 10.4 times (ticks ratio)
短字符串的性能
input length: 100 byte
runs: 1,000,000
V1 average ticks per run: 14.6
V2 is more fast than V1 by: 1.4 times (ticks ratio)
V3 is more fast than V1 by: 5.9 times (ticks ratio)
V4 is more fast than V1 by: 15.7 times (ticks ratio)
V5_1 is more fast than V1 by: 15.1 times (ticks ratio)
V5_2 is more fast than V1 by: 18.4 times (ticks ratio)
V5_3 is more fast than V1 by: 16.3 times (ticks ratio)
V6 is more fast than V1 by: 5.3 times (ticks ratio)
V7 is more fast than V1 by: 15.7 times (ticks ratio)
V8 is more fast than V1 by: 18.0 times (ticks ratio)
V9 is more fast than V1 by: 15.5 times (ticks ratio)
V10 is more fast than V1 by: 7.8 times (ticks ratio)
V11 is more fast than V1 by: 12.4 times (ticks ratio)
V12 is more fast than V1 by: 5.3 times (ticks ratio)
V13 is more fast than V1 by: 5.2 times (ticks ratio)
V14 is more fast than V1 by: 13.4 times (ticks ratio)
V15 is more fast than V1 by: 9.9 times (ticks ratio)
V16 is more fast than V1 by: 9.2 times (ticks ratio)
V17 is more fast than V1 by: 16.2 times (ticks ratio)
V18 is more fast than V1 by: 1.1 times (ticks ratio)
V19 is more SLOW than V1 by: 1.6 times (ticks ratio)
V20 is more fast than V1 by: 1.9 times (ticks ratio)
V21 is more fast than V1 by: 11.4 times (ticks ratio)
测试代码
在使用以下代码之前,最好先阅读本文下面的免责声明部分https://github.com/Ghosticollis/performance-tests/blob/main/MTestPerformance.cs
总结
由于性能良好,我建议使用以下函数之一,并支持大写和小写:
CoperNick的StringToByteArrayV4StringToByteArrayV9(按Geograph)spacepille的StringToByteArrayV17StringToByteArrayV5_3基本上由Chris F开发(它基于V5_1,但我根据Amir Rezaei和Ben Voigt的评论对其进行了增强)。
以下是V5_3的最终形状:
static byte[] HexStringToByteArrayV5_3(string hexString) {
int hexStringLength = hexString.Length;
byte[] b = new byte[hexStringLength / 2];
for (int i = 0; i < hexStringLength; i += 2) {
int topChar = hexString[i];
topChar = (topChar > 0x40 ? (topChar & ~0x20) - 0x37 : topChar - 0x30) << 4;
int bottomChar = hexString[i + 1];
bottomChar = bottomChar > 0x40 ? (bottomChar & ~0x20) - 0x37 : bottomChar - 0x30;
b[i / 2] = (byte)(topChar + bottomChar);
}
return b;
}
免责声明
警告:我没有适当的测试知识。这些原始测试的主要目的是快速概述所有发布的函数的优点。如果您需要准确的结果,请使用适当的测试工具。
最后,我想说,我是新来的,在斯塔科弗洛活跃,如果我的职位空缺,我很抱歉。如果您能发表评论,我们将不胜感激。
用@CodesInChaus补充答案(反向方法)
public static byte[] HexToByteUsingByteManipulation(string s)
{
byte[] bytes = new byte[s.Length / 2];
for (int i = 0; i < bytes.Length; i++)
{
int hi = s[i*2] - 65;
hi = hi + 10 + ((hi >> 31) & 7);
int lo = s[i*2 + 1] - 65;
lo = lo + 10 + ((lo >> 31) & 7) & 0x0f;
bytes[i] = (byte) (lo | hi << 4);
}
return bytes;
}
说明:
&0x0f还支持小写字母
hi=hi+10+((hi>>31)&7);与以下内容相同:
hi=ch-65+10+((ch-65)>>31)&7);
对于“0”9’与hi=ch-65+10+7相同;其为hi=ch-48(这是因为0xffffff&7)。
对于“A”F’为hi=ch-65+10;(这是因为0x00000000&7)。
对于“a”我们必须使用大数字,所以我们必须通过使用&0x0f使某些位为0,从默认版本中减去32。
65是“A”的代码
48是“0”的代码
7是ASCII表中“9”和“A”之间的字母数(…456789:;<=>?@ABCD…)。
推荐文章
- 实体框架核心:在上一个操作完成之前,在此上下文中开始的第二个操作
- 如何为构造函数定制Visual Studio的私有字段生成快捷方式?
- 如何使用JSON确保字符串是有效的JSON。网
- 使用C返回一个数组
- AppSettings从.config文件中获取值
- 通过HttpClient向REST API发布一个空体
- 如何检查IEnumerable是否为空或空?
- 自动化invokerrequired代码模式
- 在c#代码中设置WPF文本框的背景颜色
- 在c#中,什么是单子?
- c#和Java中的泛型有什么不同?和模板在c++ ?
- 向对象数组添加属性
- c#线程安全快速(est)计数器
- 如何将此foreach代码转换为Parallel.ForEach?
- 如何分裂()一个分隔字符串到一个列表<字符串>