Sé que esta es una pregunta anterior, pero me la he encontrado muchas veces y, hasta la fecha, todavía no he encontrado una solución bien diseñada que tenga las siguientes características:
- Puede convertir cualquier base (y detectar el tipo de base)
- Detectará datos erróneos (es decir, garantizará que la conversión consuma toda la cadena, menos espacios en blanco iniciales / finales)
- Se asegurará de que, independientemente del tipo convertido, el rango del valor de la cadena sea aceptable.
Entonces, aquí está el mío, con una correa de prueba. Debido a que usa las funciones C strtoull / strtoll debajo del capó, siempre se convierte primero al tipo más grande disponible. Luego, si no está utilizando el tipo más grande, realizará comprobaciones de rango adicionales para verificar que su tipo no se haya desbordado. Para esto, es un poco menos eficaz que si uno eligiera correctamente strtol / strtoul. Sin embargo, también funciona para cortos / caracteres y, que yo sepa, no existe una función de biblioteca estándar que haga eso también.
Disfrutar; ojalá alguien lo encuentre útil.
#include <cstdlib>
#include <cerrno>
#include <limits>
#include <stdexcept>
#include <sstream>
static const int DefaultBase = 10;
template<typename T>
static inline T CstrtoxllWrapper(const char *str, int base = DefaultBase)
{
while (isspace(*str)) str++; // remove leading spaces; verify there's data
if (*str == '\0') { throw std::invalid_argument("str; no data"); } // nothing to convert
// NOTE: for some reason strtoull allows a negative sign, we don't; if
// converting to an unsigned then it must always be positive!
if (!std::numeric_limits<T>::is_signed && *str == '-')
{ throw std::invalid_argument("str; negative"); }
// reset errno and call fn (either strtoll or strtoull)
errno = 0;
char *ePtr;
T tmp = std::numeric_limits<T>::is_signed ? strtoll(str, &ePtr, base)
: strtoull(str, &ePtr, base);
// check for any C errors -- note these are range errors on T, which may
// still be out of the range of the actual type we're using; the caller
// may need to perform additional range checks.
if (errno != 0)
{
if (errno == ERANGE) { throw std::range_error("str; out of range"); }
else if (errno == EINVAL) { throw std::invalid_argument("str; EINVAL"); }
else { throw std::invalid_argument("str; unknown errno"); }
}
// verify everything converted -- extraneous spaces are allowed
if (ePtr != NULL)
{
while (isspace(*ePtr)) ePtr++;
if (*ePtr != '\0') { throw std::invalid_argument("str; bad data"); }
}
return tmp;
}
template<typename T>
T StringToSigned(const char *str, int base = DefaultBase)
{
static const long long max = std::numeric_limits<T>::max();
static const long long min = std::numeric_limits<T>::min();
long long tmp = CstrtoxllWrapper<typeof(tmp)>(str, base); // use largest type
// final range check -- only needed if not long long type; a smart compiler
// should optimize this whole thing out
if (sizeof(T) == sizeof(tmp)) { return tmp; }
if (tmp < min || tmp > max)
{
std::ostringstream err;
err << "str; value " << tmp << " out of " << sizeof(T) * 8
<< "-bit signed range (";
if (sizeof(T) != 1) err << min << ".." << max;
else err << (int) min << ".." << (int) max; // don't print garbage chars
err << ")";
throw std::range_error(err.str());
}
return tmp;
}
template<typename T>
T StringToUnsigned(const char *str, int base = DefaultBase)
{
static const unsigned long long max = std::numeric_limits<T>::max();
unsigned long long tmp = CstrtoxllWrapper<typeof(tmp)>(str, base); // use largest type
// final range check -- only needed if not long long type; a smart compiler
// should optimize this whole thing out
if (sizeof(T) == sizeof(tmp)) { return tmp; }
if (tmp > max)
{
std::ostringstream err;
err << "str; value " << tmp << " out of " << sizeof(T) * 8
<< "-bit unsigned range (0..";
if (sizeof(T) != 1) err << max;
else err << (int) max; // don't print garbage chars
err << ")";
throw std::range_error(err.str());
}
return tmp;
}
template<typename T>
inline T
StringToDecimal(const char *str, int base = DefaultBase)
{
return std::numeric_limits<T>::is_signed ? StringToSigned<T>(str, base)
: StringToUnsigned<T>(str, base);
}
template<typename T>
inline T
StringToDecimal(T &out_convertedVal, const char *str, int base = DefaultBase)
{
return out_convertedVal = StringToDecimal<T>(str, base);
}
/*============================== [ Test Strap ] ==============================*/
#include <inttypes.h>
#include <iostream>
static bool _g_anyFailed = false;
template<typename T>
void TestIt(const char *tName,
const char *s, int base,
bool successExpected = false, T expectedValue = 0)
{
#define FAIL(s) { _g_anyFailed = true; std::cout << s; }
T x;
std::cout << "converting<" << tName << ">b:" << base << " [" << s << "]";
try
{
StringToDecimal<T>(x, s, base);
// get here on success only
if (!successExpected)
{
FAIL(" -- TEST FAILED; SUCCESS NOT EXPECTED!" << std::endl);
}
else
{
std::cout << " -> ";
if (sizeof(T) != 1) std::cout << x;
else std::cout << (int) x; // don't print garbage chars
if (x != expectedValue)
{
FAIL("; FAILED (expected value:" << expectedValue << ")!");
}
std::cout << std::endl;
}
}
catch (std::exception &e)
{
if (successExpected)
{
FAIL( " -- TEST FAILED; EXPECTED SUCCESS!"
<< " (got:" << e.what() << ")" << std::endl);
}
else
{
std::cout << "; expected exception encounterd: [" << e.what() << "]" << std::endl;
}
}
}
#define TEST(t, s, ...) \
TestIt<t>(#t, s, __VA_ARGS__);
int main()
{
std::cout << "============ variable base tests ============" << std::endl;
TEST(int, "-0xF", 0, true, -0xF);
TEST(int, "+0xF", 0, true, 0xF);
TEST(int, "0xF", 0, true, 0xF);
TEST(int, "-010", 0, true, -010);
TEST(int, "+010", 0, true, 010);
TEST(int, "010", 0, true, 010);
TEST(int, "-10", 0, true, -10);
TEST(int, "+10", 0, true, 10);
TEST(int, "10", 0, true, 10);
std::cout << "============ base-10 tests ============" << std::endl;
TEST(int, "-010", 10, true, -10);
TEST(int, "+010", 10, true, 10);
TEST(int, "010", 10, true, 10);
TEST(int, "-10", 10, true, -10);
TEST(int, "+10", 10, true, 10);
TEST(int, "10", 10, true, 10);
TEST(int, "00010", 10, true, 10);
std::cout << "============ base-8 tests ============" << std::endl;
TEST(int, "777", 8, true, 0777);
TEST(int, "-0111 ", 8, true, -0111);
TEST(int, "+0010 ", 8, true, 010);
std::cout << "============ base-16 tests ============" << std::endl;
TEST(int, "DEAD", 16, true, 0xDEAD);
TEST(int, "-BEEF", 16, true, -0xBEEF);
TEST(int, "+C30", 16, true, 0xC30);
std::cout << "============ base-2 tests ============" << std::endl;
TEST(int, "-10011001", 2, true, -153);
TEST(int, "10011001", 2, true, 153);
std::cout << "============ irregular base tests ============" << std::endl;
TEST(int, "Z", 36, true, 35);
TEST(int, "ZZTOP", 36, true, 60457993);
TEST(int, "G", 17, true, 16);
TEST(int, "H", 17);
std::cout << "============ space deliminated tests ============" << std::endl;
TEST(int, "1337 ", 10, true, 1337);
TEST(int, " FEAD", 16, true, 0xFEAD);
TEST(int, " 0711 ", 0, true, 0711);
std::cout << "============ bad data tests ============" << std::endl;
TEST(int, "FEAD", 10);
TEST(int, "1234 asdfklj", 10);
TEST(int, "-0xF", 10);
TEST(int, "+0xF", 10);
TEST(int, "0xF", 10);
TEST(int, "-F", 10);
TEST(int, "+F", 10);
TEST(int, "12.4", 10);
TEST(int, "ABG", 16);
TEST(int, "10011002", 2);
std::cout << "============ int8_t range tests ============" << std::endl;
TEST(int8_t, "7F", 16, true, std::numeric_limits<int8_t>::max());
TEST(int8_t, "80", 16);
TEST(int8_t, "-80", 16, true, std::numeric_limits<int8_t>::min());
TEST(int8_t, "-81", 16);
TEST(int8_t, "FF", 16);
TEST(int8_t, "100", 16);
std::cout << "============ uint8_t range tests ============" << std::endl;
TEST(uint8_t, "7F", 16, true, std::numeric_limits<int8_t>::max());
TEST(uint8_t, "80", 16, true, std::numeric_limits<int8_t>::max()+1);
TEST(uint8_t, "-80", 16);
TEST(uint8_t, "-81", 16);
TEST(uint8_t, "FF", 16, true, std::numeric_limits<uint8_t>::max());
TEST(uint8_t, "100", 16);
std::cout << "============ int16_t range tests ============" << std::endl;
TEST(int16_t, "7FFF", 16, true, std::numeric_limits<int16_t>::max());
TEST(int16_t, "8000", 16);
TEST(int16_t, "-8000", 16, true, std::numeric_limits<int16_t>::min());
TEST(int16_t, "-8001", 16);
TEST(int16_t, "FFFF", 16);
TEST(int16_t, "10000", 16);
std::cout << "============ uint16_t range tests ============" << std::endl;
TEST(uint16_t, "7FFF", 16, true, std::numeric_limits<int16_t>::max());
TEST(uint16_t, "8000", 16, true, std::numeric_limits<int16_t>::max()+1);
TEST(uint16_t, "-8000", 16);
TEST(uint16_t, "-8001", 16);
TEST(uint16_t, "FFFF", 16, true, std::numeric_limits<uint16_t>::max());
TEST(uint16_t, "10000", 16);
std::cout << "============ int32_t range tests ============" << std::endl;
TEST(int32_t, "7FFFFFFF", 16, true, std::numeric_limits<int32_t>::max());
TEST(int32_t, "80000000", 16);
TEST(int32_t, "-80000000", 16, true, std::numeric_limits<int32_t>::min());
TEST(int32_t, "-80000001", 16);
TEST(int32_t, "FFFFFFFF", 16);
TEST(int32_t, "100000000", 16);
std::cout << "============ uint32_t range tests ============" << std::endl;
TEST(uint32_t, "7FFFFFFF", 16, true, std::numeric_limits<int32_t>::max());
TEST(uint32_t, "80000000", 16, true, std::numeric_limits<int32_t>::max()+1);
TEST(uint32_t, "-80000000", 16);
TEST(uint32_t, "-80000001", 16);
TEST(uint32_t, "FFFFFFFF", 16, true, std::numeric_limits<uint32_t>::max());
TEST(uint32_t, "100000000", 16);
std::cout << "============ int64_t range tests ============" << std::endl;
TEST(int64_t, "7FFFFFFFFFFFFFFF", 16, true, std::numeric_limits<int64_t>::max());
TEST(int64_t, "8000000000000000", 16);
TEST(int64_t, "-8000000000000000", 16, true, std::numeric_limits<int64_t>::min());
TEST(int64_t, "-8000000000000001", 16);
TEST(int64_t, "FFFFFFFFFFFFFFFF", 16);
TEST(int64_t, "10000000000000000", 16);
std::cout << "============ uint64_t range tests ============" << std::endl;
TEST(uint64_t, "7FFFFFFFFFFFFFFF", 16, true, std::numeric_limits<int64_t>::max());
TEST(uint64_t, "8000000000000000", 16, true, std::numeric_limits<int64_t>::max()+1);
TEST(uint64_t, "-8000000000000000", 16);
TEST(uint64_t, "-8000000000000001", 16);
TEST(uint64_t, "FFFFFFFFFFFFFFFF", 16, true, std::numeric_limits<uint64_t>::max());
TEST(uint64_t, "10000000000000000", 16);
std::cout << std::endl << std::endl
<< (_g_anyFailed ? "!! SOME TESTS FAILED !!" : "ALL TESTS PASSED")
<< std::endl;
return _g_anyFailed;
}
StringToDecimales el método de usuario-tierra; está sobrecargado, por lo que puede llamarse así:
int a; a = StringToDecimal<int>("100");
o esto:
int a; StringToDecimal(a, "100");
Odio repetir el tipo int, así que prefiero el último. Esto asegura que si el tipo de 'a' cambia, uno no obtendrá malos resultados. Desearía que el compilador pudiera resolverlo como:
int a; a = StringToDecimal("100");
... pero, C ++ no deduce los tipos de retorno de plantilla, así que eso es lo mejor que puedo obtener.
La implementación es bastante simple:
CstrtoxllWrapperenvuelve ambos strtoully strtoll, llamando lo que sea necesario en función de la firma del tipo de plantilla y brindando algunas garantías adicionales (por ejemplo, la entrada negativa no se permite si no está firmada y asegura que se haya convertido toda la cadena).
CstrtoxllWrapperes utilizado por StringToSignedy StringToUnsignedcon el tipo más grande (largo largo / sin signo largo largo) disponible para el compilador; Esto permite que se realice la conversión máxima. Luego, si es necesario, StringToSigned/ StringToUnsignedrealiza las comprobaciones de rango final en el tipo subyacente. Finalmente, el método del punto final,StringToDecimal , decide a cuál de los métodos de plantilla StringTo * llamar en función de la firma del tipo subyacente.
Creo que la mayoría de la basura puede ser optimizada por el compilador; casi todo debería ser determinista en tiempo de compilación. ¡Cualquier comentario sobre este aspecto sería interesante para mí!