How do I HTML-/ URL-Encode a std::wstring containing Unicode characters?

Question

I have another question yet. If I had a std::wstring looking like this:

ドイツ語で検索していてこちらのサイトにたどり着きました。

How could I possibly get it

Answer 1

Here is an example which shows two methods, one based on the Qt library and one based on the ICU library. Both should be fairly platform-independent:

#include 
#include 
#include 
#include 

#include 

#include 
#include 
#include 

#include 
#include 
#include 
#include 

void encodeQt() {
  const QString str = QString::fromWCharArray(L"ドイツ語で検索していてこちらのサイトにたどり着きました。");
  const QUrl url = str;
  std::cout << "URL encoded: " << url.toEncoded().constData() << std::endl;
  typedef QVector CodePointVector;
  const CodePointVector codePoints = str.toUcs4();
  std::stringstream htmlEncoded;
  for (CodePointVector::const_iterator it = codePoints.constBegin(); it != codePoints.constEnd(); ++it) {
    htmlEncoded << "&#" << *it << ';';
  }
  std::cout << "HTML encoded: " << htmlEncoded.str() << std::endl;
}

void encodeICU() {
  const std::wstring cppString = L"ドイツ語で検索していてこちらのサイトにたどり着きました。";
  int bufSize = cppString.length() * 2;
  boost::scoped_array strBuffer(new UChar[bufSize]);
  int size = 0;
  UErrorCode error = U_ZERO_ERROR;
  u_strFromWCS(strBuffer.get(), bufSize, &size, cppString.data(), cppString.length(), &error);
  if (error) return;
  const UnicodeString str(strBuffer.get(), size);
  bufSize = str.length() * 4;
  boost::scoped_array buffer(new char[bufSize]);
  u_strToUTF8(buffer.get(), bufSize, &size, str.getBuffer(), str.length(), &error);
  if (error) return;
  const std::string urlUtf8(buffer.get(), size);
  std::stringstream urlEncoded;
  urlEncoded << std::hex << std::setfill('0');
  for (std::string::const_iterator it = urlUtf8.begin(); it != urlUtf8.end(); ++it) {
    urlEncoded << '%' << std::setw(2) << static_cast(static_cast(*it));
  }
  std::cout << "URL encoded: " << urlEncoded.str() << std::endl;
  std::stringstream htmlEncoded;
  StringCharacterIterator it = str;
  while (it.hasNext()) {
    const UChar32 pt = it.next32PostInc();
    htmlEncoded << "&#" << pt << ';';
  }
  std::cout << "HTML encoded: " << htmlEncoded.str() << std::endl;
}


int main() {
  encodeQt();
  encodeICU();
}