How to convert UTF-8 std::string to UTF-16 std::wstring?
This is how you do it with C++11:
std::string str = "your string in utf8";
std::wstring_convert<std::codecvt_utf8_utf16<char16_t>> converter;
std::wstring wstr = converter.from_bytes(str);
And these are the headers you need:
#include <iostream>
#include <string>
#include <locale>
#include <codecvt>
A more complete example available here: http://en.cppreference.com/w/cpp/locale/wstring_convert/from_bytes
Here's some code. Only lightly tested and there's probably a few improvements. Call this function to convert a UTF-8 string to a UTF-16 wstring. If it thinks the input string is not UTF-8 then it will throw an exception, otherwise it returns the equivalent UTF-16 wstring.
std::wstring utf8_to_utf16(const std::string& utf8)
{
std::vector<unsigned long> unicode;
size_t i = 0;
while (i < utf8.size())
{
unsigned long uni;
size_t todo;
bool error = false;
unsigned char ch = utf8[i++];
if (ch <= 0x7F)
{
uni = ch;
todo = 0;
}
else if (ch <= 0xBF)
{
throw std::logic_error("not a UTF-8 string");
}
else if (ch <= 0xDF)
{
uni = ch&0x1F;
todo = 1;
}
else if (ch <= 0xEF)
{
uni = ch&0x0F;
todo = 2;
}
else if (ch <= 0xF7)
{
uni = ch&0x07;
todo = 3;
}
else
{
throw std::logic_error("not a UTF-8 string");
}
for (size_t j = 0; j < todo; ++j)
{
if (i == utf8.size())
throw std::logic_error("not a UTF-8 string");
unsigned char ch = utf8[i++];
if (ch < 0x80 || ch > 0xBF)
throw std::logic_error("not a UTF-8 string");
uni <<= 6;
uni += ch & 0x3F;
}
if (uni >= 0xD800 && uni <= 0xDFFF)
throw std::logic_error("not a UTF-8 string");
if (uni > 0x10FFFF)
throw std::logic_error("not a UTF-8 string");
unicode.push_back(uni);
}
std::wstring utf16;
for (size_t i = 0; i < unicode.size(); ++i)
{
unsigned long uni = unicode[i];
if (uni <= 0xFFFF)
{
utf16 += (wchar_t)uni;
}
else
{
uni -= 0x10000;
utf16 += (wchar_t)((uni >> 10) + 0xD800);
utf16 += (wchar_t)((uni & 0x3FF) + 0xDC00);
}
}
return utf16;
}
There are some relevant Q&A here and here which is worth a read.
Basically you need to convert the string to a common format -- my preference is always to convert to UTF-8, but your mileage may wary.
There have been lots of software written for doing the conversion -- the conversion is straigth forwards and can be written in a few hours -- however why not pick up something already done such as the UTF-8 CPP