代码之家 › 专栏 › 技术社区 › Searene

使用C++ [复制]转换UTF-16字符到UTF-8字符串

c++

Searene · 技术社区 · 7 年前

STDMETHODIMP CFileSystemAPI::setRRConfig( BSTR config_str, VARIANT* ret )
{
mReportReaderFactory.reset( new sbis::report_reader::ReportReaderFactory() );

USES_CONVERSION;
std::string configuration_str = W2A( config_str );

0 回复 | 直到 8 年前

Peter Mortensen icecrime 8 年前

如果你使用C++ 11,你可以检查一下:

http://www.cplusplus.com/reference/codecvt/codecvt_utf8_utf16/

AndersK 8 年前

std::string WstrToUtf8Str(const std::wstring& wstr)
{
  std::string retStr;
  if (!wstr.empty())
  {
    int sizeRequired = WideCharToMultiByte(CP_UTF8, 0, wstr.c_str(), -1, NULL, 0, NULL, NULL);

    if (sizeRequired > 0)
    {
      std::vector<char> utf8String(sizeRequired);
      int bytesConverted = WideCharToMultiByte(CP_UTF8, 0, wstr.c_str(),    
                           -1, &utf8String[0], utf8String.size(), NULL, 
                           NULL);
      if (bytesConverted != 0)
      {
        retStr = &utf8String[0];
      }
      else
      {
        std::stringstream err;
        err << __FUNCTION__ 
            << " std::string WstrToUtf8Str failed to convert wstring '"
            << wstr.c_str() << L"'";
        throw std::runtime_error( err.str() );
      }
    }
  }
  return retStr;
}

可以将BSTR作为std::wstring给函数

kvv 11 年前

void encode_unicode_character(char* buffer, int* offset, wchar_t ucs_character)
{
    if (ucs_character <= 0x7F)
    {
        // Plain single-byte ASCII.
        buffer[(*offset)++] = (char) ucs_character;
    }
    else if (ucs_character <= 0x7FF)
    {
        // Two bytes.
        buffer[(*offset)++] = 0xC0 | (ucs_character >> 6);
        buffer[(*offset)++] = 0x80 | ((ucs_character >> 0) & 0x3F);
    }
    else if (ucs_character <= 0xFFFF)
    {
        // Three bytes.
        buffer[(*offset)++] = 0xE0 | (ucs_character >> 12);
        buffer[(*offset)++] = 0x80 | ((ucs_character >> 6) & 0x3F);
        buffer[(*offset)++] = 0x80 | ((ucs_character >> 0) & 0x3F);
    }
    else if (ucs_character <= 0x1FFFFF)
    {
        // Four bytes.
        buffer[(*offset)++] = 0xF0 | (ucs_character >> 18);
        buffer[(*offset)++] = 0x80 | ((ucs_character >> 12) & 0x3F);
        buffer[(*offset)++] = 0x80 | ((ucs_character >> 6) & 0x3F);
        buffer[(*offset)++] = 0x80 | ((ucs_character >> 0) & 0x3F);
    }
    else if (ucs_character <= 0x3FFFFFF)
    {
        // Five bytes.
        buffer[(*offset)++] = 0xF8 | (ucs_character >> 24);
        buffer[(*offset)++] = 0x80 | ((ucs_character >> 18) & 0x3F);
        buffer[(*offset)++] = 0x80 | ((ucs_character >> 12) & 0x3F);
        buffer[(*offset)++] = 0x80 | ((ucs_character >> 6) & 0x3F);
        buffer[(*offset)++] = 0x80 | ((ucs_character >> 0) & 0x3F);
    }
    else if (ucs_character <= 0x7FFFFFFF)
    {
        // Six bytes.
        buffer[(*offset)++] = 0xFC | (ucs_character >> 30);
        buffer[(*offset)++] = 0x80 | ((ucs_character >> 24) & 0x3F);
        buffer[(*offset)++] = 0x80 | ((ucs_character >> 18) & 0x3F);
        buffer[(*offset)++] = 0x80 | ((ucs_character >> 12) & 0x3F);
        buffer[(*offset)++] = 0x80 | ((ucs_character >> 6) & 0x3F);
        buffer[(*offset)++] = 0x80 | ((ucs_character >> 0) & 0x3F);
    }
    else
    {
        // Invalid char; don't encode anything.
    }
}

ISO10646-2012这是所有你需要了解的UCS。