chinese-journal/rudict/rudict/utf8utf16.cpp

96 lines
2.5 KiB
C++

#include "utf8utf16.h"
#include <string>
#include <boost/locale.hpp>
#include <locale>
std::string wstring_to_string(std::wstring in)
{
/*
std::string out;
unsigned int codepoint = 0;
for (in; *in != 0; ++in)
{
if (*in >= 0xd800 && *in <= 0xdbff)
codepoint = ((*in - 0xd800) << 10) + 0x10000;
else
{
if (*in >= 0xdc00 && *in <= 0xdfff)
codepoint |= *in - 0xdc00;
else
codepoint = *in;
if (codepoint <= 0x7f)
out.append(1, static_cast<char>(codepoint));
else if (codepoint <= 0x7ff)
{
out.append(1, static_cast<char>(0xc0 | ((codepoint >> 6) & 0x1f)));
out.append(1, static_cast<char>(0x80 | (codepoint & 0x3f)));
}
else if (codepoint <= 0xffff)
{
out.append(1, static_cast<char>(0xe0 | ((codepoint >> 12) & 0x0f)));
out.append(1, static_cast<char>(0x80 | ((codepoint >> 6) & 0x3f)));
out.append(1, static_cast<char>(0x80 | (codepoint & 0x3f)));
}
else
{
out.append(1, static_cast<char>(0xf0 | ((codepoint >> 18) & 0x07)));
out.append(1, static_cast<char>(0x80 | ((codepoint >> 12) & 0x3f)));
out.append(1, static_cast<char>(0x80 | ((codepoint >> 6) & 0x3f)));
out.append(1, static_cast<char>(0x80 | (codepoint & 0x3f)));
}
codepoint = 0;
}
}
return out;*/
std::string out = boost::locale::conv::utf_to_utf<char>(in);
return out;
}
std::wstring string_to_wstring(std::string in)
{
/*
std::wstring out;
if (in == NULL)
return out;
unsigned int codepoint;
while (*in != 0)
{
unsigned char ch = static_cast<unsigned char>(*in);
if (ch <= 0x7f)
codepoint = ch;
else if (ch <= 0xbf)
codepoint = (codepoint << 6) | (ch & 0x3f);
else if (ch <= 0xdf)
codepoint = ch & 0x1f;
else if (ch <= 0xef)
codepoint = ch & 0x0f;
else
codepoint = ch & 0x07;
++in;
if (((*in & 0xc0) != 0x80) && (codepoint <= 0x10ffff))
{
if (codepoint > 0xffff)
{
out.append(1, static_cast<wchar_t>(0xd800 + (codepoint >> 10)));
out.append(1, static_cast<wchar_t>(0xdc00 + (codepoint & 0x03ff)));
}
else if (codepoint < 0xd800 || codepoint >= 0xe000)
out.append(1, static_cast<wchar_t>(codepoint));
}
}
return out;
*/
std::wstring out = boost::locale::conv::utf_to_utf<wchar_t>(in);
return out;
}