如何将UNICODE码转换为UTF8字符？

[yoogle]

比如我输入548E，这个是一个汉字的UNICODE码，我想得到这个汉子的UTF8码，如何得到？

[oyljerry]

WideCharToMultiyBytes，然后MultiBytesToWideChar再设置字符集为UTF8

[bragi523]

WideCharToMultiByte

[华亭真人]

	int  len=str.GetLength();   
    int  unicodeLen=MultiByteToWideChar(CP_UTF8,0,str,-1,NULL,0);   
    wchar_t * pUnicode;   
    pUnicode=new  wchar_t[unicodeLen+1];   
    memset(pUnicode,0,(unicodeLen+1)*sizeof(wchar_t));   
    MultiByteToWideChar(CP_UTF8,0,str,-1,(LPWSTR)pUnicode,unicodeLen);   
    BYTE  *  pTargetData=NULL;   
    int  targetLen=WideCharToMultiByte(936,0,(LPWSTR)pUnicode,-1,(char  *)pTargetData,0,NULL,NULL);   
    pTargetData=new  BYTE[targetLen+1];   
    memset(pTargetData,0,targetLen+1);   
    WideCharToMultiByte(936,0,(LPWSTR)pUnicode,-1,(char  *)pTargetData,targetLen,NULL,NULL);   
    CString  rt;   
    rt.Format("%s",pTargetData);   
    delete  pUnicode;   
    delete  pTargetData;
	return rt;

[yoogle]

我说的不是字符串，是将unicode值转换成utf8码。

[AllenTing]

LZ只要根据Unicode和UTF8之间转换关系就可以知道了，比如：

　　Unicode编码(16进制)　║　UTF-8 字节流(二进制)
000000 - 00007F　║　0xxxxxxx
000080 - 0007FF　║　110xxxxx 10xxxxxx
000800 - 00FFFF　║　1110xxxx 10xxxxxx 10xxxxxx
010000 - 10FFFF　║　11110xxx 10xxxxxx 10xxxxxx 10xxxxxx


BOOL UnicodeToUTF8(DWORD dwSrc, DWORD& dwDest)
{
if(dwSrc <= 0x000007F)
{
dwDest = dwSrc;
}else if(dwSrc >= 0x000080 && dwSrc <=0x0007FF)
{
BYTE byFirst = 0;
BYTE bySecond = 0;
byFirst = (3<<6) + (dwSrc>>6&0x1F);
bySecond = (1<<7) + (dwSrc&0x3F);
dwDest = (byFirst<<8) + bySecond;
}else if(dwSrc >= 0x000800 && dwSrc <= 0x00FFFF)
{
BYTE byFirst = 0;
BYTE bySecond = 0;
BYTE byThird = 0;
byFirst = (14<<4) + (dwSrc>>12&0xF);
bySecond = (2<<6) + (dwSrc>>6&0x3F);
byThird = (2<<6) + (dwSrc&0x3F);
dwDest = (byFirst<<16) + (bySecond<<8) + byThird;
}else if(dwSrc >= 0x010000 && dwSrc <= 0x10FFFF)
{
BYTE byFirst = 0;
BYTE bySecond = 0;
BYTE byThird = 0;
BYTE byFouth = 0;
byFirst = (30<<3) + (dwSrc>>18);
bySecond = (2<<6) + (dwSrc>>12&0x3F);
byThird = (2<<6) + (dwSrc>>6&0x3F);
byFouth = (2<<6) + (dwSrc&0x3F);
dwDest = (byFirst<<24) + (bySecond<<16) + (byThird<<8) + byFouth;
}else
return FALSE;
return TRUE;
}

[AllenTing]

详细解释可以见这：
http://baike.baidu.com/view/40801.htm

[ok1234567]

WORD w=0x548E;
char sz[4]={0};
char *d=sz;
//下面的代码将一个汉字的UNICODE码转换为3字节的utf-8

					*d = HIBYTE(w);
					*d >>= 4;
					*d |= 0xE0;
					
					d++;
					*d = HIBYTE(w);
					*d <<= 4;
					*d >>= 2;
					*d |= (LOBYTE(w)>>6);
					*d |= 0x80;
					
					d++;
					*d = (LOBYTE(w)<<2);
					*d >>= 2;
					*d |= 0x80;

[zhouzheng1982]

utf16: 548E -> 1000111001010100
utf8: 11101000 10111001 10010100 -> E8B994

[用户 昵称]

utf8与unicode是对应的，utf8通过移位就能获得unicode，反之也可以。简单来说，使用WideCharToMultiByte。

[zhouzheng1982]

utf8规则：

0xxxxxxx (00-7f) 7bit
110yyyyx 10xxxxxx (c0-df)(80-bf) 11bit
1110yyyy 10yxxxxx 10xxxxxx (e0-ef)(80-bf)(80-bf) 16bit
11110yyy 10yyxxxx 10xxxxxx 10xxxxxx (f0-f7)(80-bf)(80-bf)(80-bf) 21bit
111110yy 10yyyxxx 10xxxxxx 10xxxxxx 10xxxxxx (f8-fb)(80-bf)(80-bf)(80-bf)(80-bf) 26bit
1111110y 10yyyyxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx (fc-fd)(80-bf)(80-bf)(80-bf)(80-bf)(80-bf) 31bit

[smartdog2008]

xie xie