如何将一个可变长度的十六进制字符串(例如"01A1"
)转换为包含该数据的字节数组。
即将此转换为:
std::string = "01A1";
变成这样
char* hexArray;
int hexLength;
或者这个
std::vector<char> hexArray;
我希望将其写入文件,并使用hexdump -C
命令,以便获取包含01A1
的二进制数据。
如何将一个可变长度的十六进制字符串(例如"01A1"
)转换为包含该数据的字节数组。
即将此转换为:
std::string = "01A1";
变成这样
char* hexArray;
int hexLength;
或者这个
std::vector<char> hexArray;
我希望将其写入文件,并使用hexdump -C
命令,以便获取包含01A1
的二进制数据。
我建议使用标准函数sscanf
将字符串读入无符号整数,这样你就已经在内存中拥有所需的字节。如果你在大端机器上,可以直接从第一个非零字节开始写出整数的内存(使用memcpy
)。然而,在一般情况下你不能安全地假设这一点,因此需要使用一些位掩码和移位操作来提取字节。
const char* src = "01A1";
char hexArray[256] = {0};
int hexLength = 0;
// read in the string
unsigned int hex = 0;
sscanf(src, "%x", &hex);
// write it out
for (unsigned int mask = 0xff000000, bitPos=24; mask; mask>>=8, bitPos-=8) {
unsigned int currByte = hex & mask;
if (currByte || hexLength) {
hexArray[hexLength++] = currByte>>bitPos;
}
}
这可能对某些人有用。将一组字节转换为字符串然后再转回去的逻辑,解决了零字符问题。
#include <sstream>
#include <iomanip>
std::string BytesToHex(const std::vector<char>& data, size_t len)
{
std::stringstream ss;
ss << std::hex << std::setfill('0');
for(size_t index(0); index < len; ++index)
{
ss << std::setw(2) << static_cast<unsigned short>(data[index]);
}
return ss.str();
}
std::vector<char> HexToBytes(const std::string& data)
{
std::stringstream ss;
ss << data;
std::vector<char> resBytes;
size_t count = 0;
const auto len = data.size();
while(ss.good() && count < len)
{
unsigned short num;
char hexNum[2];
ss.read(hexNum, 2);
sscanf(hexNum, "%2hX", &num);
resBytes.push_back(static_cast<char>(num));
count += 2;
}
return resBytes;
}
如何在编译时实现这个功能
#pragma once
#include <memory>
#include <iostream>
#include <string>
#include <array>
#define DELIMITING_WILDCARD ' '
// @sean :)
constexpr int _char_to_int( char ch )
{
if( ch >= '0' && ch <= '9' )
return ch - '0';
if( ch >= 'A' && ch <= 'F' )
return ch - 'A' + 10;
return ch - 'a' + 10;
};
template <char wildcard, typename T, size_t N = sizeof( T )>
constexpr size_t _count_wildcard( T &&str )
{
size_t count = 1u;
for( const auto &character : str )
{
if( character == wildcard )
{
++count;
}
}
return count;
}
// construct a base16 hex and emplace it at make_count
// change 16 to 256 if u want the result to be when:
// sig[0] == 0xA && sig[1] == 0xB = 0xA0B
// or leave as is for the scenario to return 0xAB
#define CONCATE_HEX_FACTOR 16
#define CONCATE_HEX(a, b) ( CONCATE_HEX_FACTOR * ( a ) + ( b ) )
template
< char skip_wildcard,
// How many occurances of a delimiting wildcard do we find in sig
size_t delimiter_count,
typename T, size_t N = sizeof( T )>
constexpr auto _make_array( T &&sig )
{
static_assert( delimiter_count > 0, "this is a logical error, delimiter count can't be of size 0" );
static_assert( N > 1, "sig length must be bigger than 1" );
// Resulting byte array, for delimiter_count skips we should have delimiter_count integers
std::array<int, delimiter_count> ret{};
// List of skips that point to the position of the delimiter wildcard in skip
std::array<size_t, delimiter_count> skips{};
// Current skip
size_t skip_count = 0u;
// Character count, traversed for skip
size_t skip_traversed_character_count = 0u;
for( size_t i = 0u; i < N; ++i )
{
if( sig[i] == DELIMITING_WILDCARD )
{
skips[skip_count] = skip_traversed_character_count;
++skip_count;
}
++skip_traversed_character_count;
}
// Finally traversed character count
size_t traversed_character_count = 0u;
// Make count (we will supposedly have at least an instance in our return array)
size_t make_count = 1u;
// Traverse signature
for( size_t i = 0u; i < N; ++i )
{
// Read before
if( i == 0u )
{
// We don't care about this, and we don't want to use 0
if( sig[0u] == skip_wildcard )
{
ret[0u] = -1;
continue;
}
ret[0u] = CONCATE_HEX( _char_to_int( sig[0u] ), _char_to_int( sig[1u] ) );
continue;
}
// Make result by skip data
for( const auto &skip : skips )
{
if( ( skip == i ) && skip < N - 1u )
{
// We don't care about this, and we don't want to use 0
if( sig[i + 1u] == skip_wildcard )
{
ret[make_count] = -1;
++make_count;
continue;
}
ret[make_count] = CONCATE_HEX( _char_to_int( sig[i + 1u] ), _char_to_int( sig[i + 2u] ) );
++make_count;
}
}
}
return ret;
}
#define SKIP_WILDCARD '?'
#define BUILD_ARRAY(a) _make_array<SKIP_WILDCARD, _count_wildcard<DELIMITING_WILDCARD>( a )>( a )
#define BUILD_ARRAY_MV(a) _make_array<SKIP_WILDCARD, _count_wildcard<DELIMITING_WILDCARD>( std::move( a ) )>( std::move( a ) )
// -----
// usage
// -----
template <int n>
constexpr int combine_two()
{
constexpr auto numbers = BUILD_ARRAY( "55 8B EC 83 E4 F8 8B 4D 08 BA ? ? ? ? E8 ? ? ? ? 85 C0 75 12 ?" );
constexpr int number = numbers[0];
constexpr int number_now = n + number;
return number_now;
}
int main()
{
constexpr auto shit = BUILD_ARRAY( "?? AA BB CC DD ? ? ? 02 31 32" );
for( const auto &hex : shit )
{
printf( "%x ", hex );
}
combine_two<3>();
constexpr auto saaahhah = combine_two<3>();
static_assert( combine_two<3>() == 88 );
static_assert( combine_two<3>() == saaahhah );
printf( "\n%d", saaahhah );
}
这个方法也可以用于运行时,但是对于这个你可能更喜欢其他更快的东西。
uint8_t buf[32] = {};
std::string hex = "0123";
while (hex.length() % 2)
hex = "0" + hex;
std::stringstream stream;
stream << std::hex << hex;
for (size_t i= 0; i <sizeof(buf); i++)
stream >> buf[i];
#include <iostream>
using byte = unsigned char;
static int charToInt(char c) {
if (c >= '0' && c <= '9') {
return c - '0';
}
if (c >= 'A' && c <= 'F') {
return c - 'A' + 10;
}
if (c >= 'a' && c <= 'f') {
return c - 'a' + 10;
}
return -1;
}
// Decodes specified HEX string to bytes array. Specified nBytes is length of bytes
// array. Returns -1 if fails to decode any of bytes. Returns number of bytes decoded
// on success. Maximum number of bytes decoded will be equal to nBytes. It is assumed
// that specified string is '\0' terminated.
int hexStringToBytes(const char* str, byte* bytes, int nBytes) {
int nDecoded {0};
for (int i {0}; str[i] != '\0' && nDecoded < nBytes; i += 2, nDecoded += 1) {
if (str[i + 1] != '\0') {
int m {charToInt(str[i])};
int n {charToInt(str[i + 1])};
if (m != -1 && n != -1) {
bytes[nDecoded] = (m << 4) | n;
} else {
return -1;
}
} else {
return -1;
}
}
return nDecoded;
}
int main(int argc, char* argv[]) {
if (argc < 2) {
return 1;
}
byte bytes[0x100];
int ret {hexStringToBytes(argv[1], bytes, 0x100)};
if (ret < 0) {
return 1;
}
std::cout << "number of bytes: " << ret << "\n" << std::hex;
for (int i {0}; i < ret; ++i) {
if (bytes[i] < 0x10) {
std::cout << "0";
}
std::cout << (bytes[i] & 0xff);
}
std::cout << "\n";
return 0;
}
typedef uint8_t BYTE;
BYTE* ByteUtils::HexStringToBytes(BYTE* HexString, int ArrayLength)
{
BYTE* returnBytes;
returnBytes = (BYTE*) malloc(ArrayLength/2);
int j=0;
for(int i = 0; i < ArrayLength; i++)
{
if(i % 2 == 0)
{
int valueHigh = (int)(*(HexString+i));
int valueLow = (int)(*(HexString+i+1));
valueHigh = ByteUtils::HexAsciiToDec(valueHigh);
valueLow = ByteUtils::HexAsciiToDec(valueLow);
valueHigh *= 16;
int total = valueHigh + valueLow;
*(returnBytes+j++) = (BYTE)total;
}
}
return returnBytes;
}
int ByteUtils::HexAsciiToDec(int value)
{
if(value > 47 && value < 59)
{
value -= 48;
}
else if(value > 96 && value < 103)
{
value -= 97;
value += 10;
}
else if(value > 64 && value < 71)
{
value -= 65;
value += 10;
}
else
{
value = 0;
}
return value;
}
输入:"303132",输出:"012"。输入字符串可以是奇数或偶数长度。
char char2int(char input)
{
if (input >= '0' && input <= '9')
return input - '0';
if (input >= 'A' && input <= 'F')
return input - 'A' + 10;
if (input >= 'a' && input <= 'f')
return input - 'a' + 10;
throw std::runtime_error("Incorrect symbol in hex string");
};
string hex2str(string &hex)
{
string out;
out.resize(hex.size() / 2 + hex.size() % 2);
string::iterator it = hex.begin();
string::iterator out_it = out.begin();
if (hex.size() % 2 != 0) {
*out_it++ = char(char2int(*it++));
}
for (; it < hex.end() - 1; it++) {
*out_it++ = char2int(*it++) << 4 | char2int(*it);
};
return out;
}
static bool Hexadec2xdigit(const std::string& data, std::string& buffer, std::size_t offset = sizeof(uint16_t))
{
if (data.empty())
{
return false;
}
try
{
constexpr auto s_function_lambda = [] (const char* string) noexcept { return *static_cast<const uint16_t*>(reinterpret_cast<const uint16_t*>(string)); };
{
for (std::size_t i = 0, tmp = s_function_lambda(data.c_str() + i); i < data.size(); i += offset, tmp = s_function_lambda(data.c_str() + i))
{
if (std::isxdigit(data[i]))
{
buffer += static_cast<char>(/*std::stoul*/std::strtoul(reinterpret_cast<const char*>(std::addressof(tmp)), NULL, 16));
}
}
}
return true;
}
catch (const std::invalid_argument& ex)
{
}
catch (const std::out_of_range& ex)
{
}
return false;
}
void hex2bin(const char* src, char* target, size_t size_target)
{
int countdgts=0; // count hex digits
for (const char *p=src; *p && isxdigit(*p); p++)
countdgts++;
if ((countdgts+1)/2+1>size_target)
throw exception("Risk of buffer overflow");
isxdigit()
,您需要#include <cctype>
。bool ishi = !(countdgts%2);
然后我们可以逐位循环,使用二进制移位和二进制或运算符将每一对组合起来,并在每次迭代时切换“高”指示器:
for (*target=0; *src; ishi = !ishi) {
char tmp = char2int(*src++); // hex digit on 4 lower bits
if (ishi)
*target = (tmp << 4); // high: shift by 4
else *target++ |= tmp; // low: complete previous
}
*target=0; // null terminated target (if desired)
}