The question I have is quite simple, but I couldn't find a solution so far:
How can I convert a UTF8 encoded string
to a latin1 encoded string
in C++ without using any extra libs like libiconv?
Every example I could find so far is for latin1 to UTF8 conversion?
typedef unsigned value_type;
template <typename Iterator>
size_t get_length (Iterator p)
{
unsigned char c = static_cast<unsigned char> (*p);
if (c < 0x80) return 1;
else if (!(c & 0x20)) return 2;
else if (!(c & 0x10)) return 3;
else if (!(c & 0x08)) return 4;
else if (!(c & 0x04)) return 5;
else return 6;
}
template <typename Iterator>
value_type get_value (Iterator p)
{
size_t len = get_length (p);
if (len == 1)
return *p;
value_type res = static_cast<unsigned char> (
*p & (0xff >> (len + 1)))
<< ((len - 1) * 6);
for (--len; len; --len)
res |= (static_cast<unsigned char> (*(++p)) - 0x80) << ((len - 1) * 6);
return res;
}
This function will return the unicode code point at p
. You can now convert a string using
for (std::string::iterator p = s_utf8.begin(); p != s_utf8.end(); ++p)
{
value_type value = get_value<std::string::iterator&>(p));
if (value > 0xff)
throw "AAAAAH!";
s_latin1.append(static_cast<char>(value));
}
No guarantees, the code is quite old :)