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
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。
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,这种方法很快:
编码器表512字节或1024字节(两次大小写(如果是大写和小写)需要)解码器表256字节或64 KiB(单个字符查找或双字符查找)
我的解决方案使用1024字节作为编码表,256字节用于解码。
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]];
}
比较
StringBuilderToStringFromBytes: 106148
BitConverterToStringFromBytes: 15783
ArrayConvertAllToStringFromBytes: 54290
ByteManipulationToCharArray: 8444
TableBasedToCharArray: 5651 *
*这个解决方案
Note
在解码过程中,可能会发生IOException和IndexOutOfRangeException(如果字符的值太高>256)。应该实现对流或数组进行去/编码的方法,这只是概念的证明。
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[])
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;
}
这里不想赘述很多答案,但我发现了一个十六进制字符串解析器的相当优化(比公认的好4.5倍)、简单的实现。首先,我的测试输出(第一批是我的实现):
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
base64和“BitConverter'd”行用于测试正确性。请注意,它们是相等的。
实施:
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;
}
我尝试了一些不安全的东西,并将(显然是冗余的)字符移动到另一个方法来蚕食if序列,但这是最快的。
(我承认这回答了一半的问题。我觉得字符串->字节[]转换不足,而字节[]->字符串角度似乎被很好地覆盖了。因此,这个答案。)