Converting between character encodings

suggest change

Converting between encodings is easy with C++11 and most compilers are able to deal with it in a cross-platform manner through <codecvt> and <locale> headers.

#include <iostream>
#include <codecvt>
#include <locale>
#include <string>
using namespace std;

int main() {
    // converts between wstring and utf8 string
    wstring_convert<codecvt_utf8_utf16<wchar_t>> wchar_to_utf8;
    // converts between u16string and utf8 string
    wstring_convert<codecvt_utf8_utf16<char16_t>, char16_t> utf16_to_utf8;
    
    wstring wstr = L"foobar";
    string utf8str = wchar_to_utf8.to_bytes(wstr);
    wstring wstr2 = wchar_to_utf8.from_bytes(utf8str);
    
    wcout << wstr << endl;
    cout << utf8str << endl;
    wcout << wstr2 << endl;
    
    u16string u16str = u"foobar";
    string utf8str2 = utf16_to_utf8.to_bytes(u16str);
    u16string u16str2 = utf16_to_utf8.from_bytes(utf8str2);
    
    return 0;
}

Mind that Visual Studio 2015 provides supports for these conversion but a bug in their library implementation requires to use a different template for wstring_convert when dealing with char16_t:

using utf16_char = unsigned short;
wstring_convert<codecvt_utf8_utf16<utf16_char>, utf16_char> conv_utf8_utf16;

void strings::utf16_to_utf8(const std::u16string& utf16, std::string& utf8)
{
  std::basic_string<utf16_char> tmp;
  tmp.resize(utf16.length());
  std::copy(utf16.begin(), utf16.end(), tmp.begin());
  utf8 = conv_utf8_utf16.to_bytes(tmp);
}
void strings::utf8_to_utf16(const std::string& utf8, std::u16string& utf16)
{ 
  std::basic_string<utf16_char> tmp = conv_utf8_utf16.from_bytes(utf8);
  utf16.clear();
  utf16.resize(tmp.length());
  std::copy(tmp.begin(), tmp.end(), utf16.begin());
}

Feedback about page:

Feedback:
Optional: your email if you want me to get back to you:


std::string:
* Converting between character encodings

Table Of Contents
8 Arrays
11 Loops
20 std::string
39 Streams
51 Unions
56 Lambdas
60 SFINAE
62 RAII
67 Sorting
84 RTTI
87 Scopes
104 Profiling
107 Recursion
117 Iteration
125 Alignment
134 Semaphore
136 Debugging
139 Mutexes
142 decltype