other/chinese-journal
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

utf8 dammit

Browse Source
This commit is contained in:
Vladislav Khorev 2014-11-26 22:40:06 +00:00
parent cae8c7c0f4
commit 3de09db922
1 changed files with 37 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
rudict/rudict/utf8utf16.cpp
View File

@ -1,15 +1,47 @@
#include "utf8utf16.h"
#include <string>
#include <locale>
#include <codecvt>
std::string UTF16to8(const wchar_t * in)
{
std::wstring_convert<std::codecvt_utf8<wchar_t>> conv;
std::string s = conv.to_bytes(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;
return s;
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::wstring UTF8to16(const char * in)