我知道这是一个较老的问题,但我已经遇到过很多次了,到目前为止,仍然没有找到具有以下特征的模板化解决方案:
- 可以转换任何碱基(并检测碱基类型)
- 将检测错误数据(即确保整个字符串、较少的前导/尾随空格被转换消耗)
- 将确保无论转换为何种类型,字符串值的范围都是可接受的。
所以,这是我的,带有测试带。因为它在底层使用了 C 函数 strtoull/strtoll,所以它总是首先转换为可用的最大类型。然后,如果您没有使用最大的类型,它将执行额外的范围检查以验证您的类型没有溢出(下)。为此,它比正确选择 strtol/strtoul 的性能要差一些。但是,它也适用于 shorts/chars,据我所知,也没有标准库函数可以做到这一点。
享受;希望有人觉得它有用。
#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;
}
StringToDecimal 是用户态方法;它是重载的,所以它可以这样调用:
int a; a = StringToDecimal<int>("100");
或者这个:
int a; StringToDecimal(a, "100");
我讨厌重复 int 类型,所以更喜欢后者。这确保了如果 'a' 的类型发生变化,一个不会得到不好的结果。我希望编译器可以像这样理解它:
int a; a = StringToDecimal("100");
...但是,C++ 不推断模板返回类型,所以这是我能得到的最好的。
实现非常简单:
CstrtoxllWrapper 包装strtoull 和strtoll,根据模板类型的有符号性调用任何必要的,并提供一些额外的保证(例如,如果无符号则不允许负输入,并确保整个字符串被转换) .
CstrtoxllWrapper 被StringToSigned 和StringToUnsigned 使用,编译器可用的最大类型(long long/unsigned long long);这允许执行最大转换。然后,如果有必要,StringToSigned/StringToUnsigned 对基础类型执行最终范围检查。最后,端点方法StringToDecimal 根据底层类型的签名决定调用哪个 StringTo* 模板方法。
我认为大部分垃圾都可以被编译器优化掉;几乎所有东西都应该是编译时确定的。任何关于这方面的评论都会让我感兴趣!