Unicode(UTF-8)编码问题请教！谢谢！！！

[xingworld]

猫咪一词。

WCHAR szTemp[] = L"猫咪";
二进制代码是：2B 73 AA 54

但是 IIS 输出的网页里“猫咪”一词的二进制代码是：
E7 8C AB E5 92 AA

请教是为什么啊？
如何得到 E7 8C AB E5 92 AA ？

谢谢！！！

[ydyn1988]

IIS 默认的是 gb2312 编码

[ydyn1988]

将asp文件中<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />这样的句子，
改为：<meta http-equiv="Content-Type" content="text/html; charset=GB2312" />

试试行不行

[xingworld]

谢谢楼上的回答，我是想知道如何用 C++ 代码来获得这样的编码，如何将“猫咪”两个字转换成二进制码为 E7 8C AB E5 92 AA Unicode(UTF-8) 的字符。
谢谢！

[用户 昵称]

	//2B 73 AA 54 - utf16 little endian
	猫咪

	//E7 8C AB E5 92 AA - utf8
	猫咪


这是utf16格式的，utf16与utf8本质是一样的，只是utf16使用固定两个字节表示一个字符，而utf8则使用1-3个字节表示一个字符。

utf16可按公式自己转为utf8，也可以使用WideCharToMultiByte函数转。

[newasoft]

#pragma once
#include "stdafx.h"
#include "string"
using namespace std;
class CChineseCode
{
public:
static void UTF_8ToUnicode(wchar_t* pOut,char *pText); // 把UTF-8转换成Unicode
static void UnicodeToUTF_8(char* pOut,wchar_t* pText); //Unicode 转换成UTF-8
static void UnicodeToGB2312(char* pOut,wchar_t uData); // 把Unicode 转换成 GB2312
static void Gb2312ToUnicode(wchar_t* pOut,char *gbBuffer);// GB2312 转换成　Unicode
static void GB2312ToUTF_8(string& pOut,char *pText, int pLen);//GB2312 转为 UTF-8
static void UTF_8ToGB2312(char* pOut, char *pText, int pLen);//UTF-8 转为 GB2312
};

------------------------------------------------------------------------------------
#include ".\chinesecode.h"

void CChineseCode::UTF_8ToUnicode(wchar_t* pOut,char *pText)
{
char* uchar = (char *)pOut;

uchar[1] = ((pText[0] & 0x0F) << 4) + ((pText[1] >> 2) & 0x0F);
uchar[0] = ((pText[1] & 0x03) << 6) + (pText[2] & 0x3F);
return;
}

void CChineseCode::UnicodeToUTF_8(char* pOut,wchar_t* pText)
{
// 注意 WCHAR高低字的顺序,低字节在前，高字节在后
char* pchar = (char *)pText;

pOut[0] = (0xE0 | ((pchar[1] & 0xF0) >> 4));
pOut[1] = (0x80 | ((pchar[1] & 0x0F) << 2)) + ((pchar[0] & 0xC0) >> 6);
pOut[2] = (0x80 | (pchar[0] & 0x3F));

return;
}

void CChineseCode::UnicodeToGB2312(char* pOut,wchar_t uData)
{
WideCharToMultiByte(CP_ACP,NULL,&uData,1,pOut,sizeof(wchar_t),NULL,NULL);
return;
}

void CChineseCode::Gb2312ToUnicode(wchar_t* pOut,char *gbBuffer)
{
::MultiByteToWideChar(CP_ACP,MB_PRECOMPOSED,gbBuffer,2,pOut,1);
return ;
}

void CChineseCode::GB2312ToUTF_8(string& pOut,char *pText, int pLen)
{
char buf[4];
int nLength = pLen* 3;
char* rst = new char[nLength];

memset(buf,0,4);
memset(rst,0,nLength);

int i = 0;
int j = 0;
while(i < pLen)
{
//如果是英文直接复制就可以
if( *(pText + i) >= 0)
{
rst[j++] = pText[i++];
}
else
{
wchar_t pbuffer;
Gb2312ToUnicode(&pbuffer,pText+i);

UnicodeToUTF_8(buf,&pbuffer);

unsigned short int tmp = 0;
tmp = rst[j] = buf[0];
tmp = rst[j+1] = buf[1];
tmp = rst[j+2] = buf[2];

j += 3;
i += 2;
}
}
rst[j] = '\0';

//返回结果
pOut = rst;
delete []rst;

return;
}

void CChineseCode::UTF_8ToGB2312(char* newBuf, char *pText, int pLen)
{
char Ctemp[4];
memset(Ctemp,0,4);

int i =0;
int j = 0;

while(i < pLen)
{
if(pText[i] > 0)
{
newBuf[j++] = pText[i++];
}
else
{
WCHAR Wtemp;
UTF_8ToUnicode(&Wtemp,pText + i);

UnicodeToGB2312(Ctemp,Wtemp);

newBuf[j] = Ctemp[0];
newBuf[j + 1] = Ctemp[1];

i += 3;
j += 2;
}
}
newBuf[j] = '\0';
return;
}

inline BYTE toHex(const BYTE &x)
{
return x > 9 ? x + 55: x + 48;
}
inline BYTE toByte(const BYTE &x)
{
return x > 57? x - 55: x - 48;
}
CString URLDecode(CString sIn)
{
CString sOut;
const int nLen = sIn.GetLength() + 1;
register LPBYTE pOutTmp = NULL;
LPBYTE pOutBuf = NULL;
register LPBYTE pInTmp = NULL;
LPBYTE pInBuf =(LPBYTE)sIn.GetBuffer(nLen);
//alloc out buffer
pOutBuf = (LPBYTE)sOut.GetBuffer(nLen);

if(pOutBuf)
{
pInTmp = pInBuf;
pOutTmp = pOutBuf;
// do encoding
while (*pInTmp)
{
if('%'==*pInTmp)
{
pInTmp++;
*pOutTmp++ = (toByte(*pInTmp)%16<<4) + toByte(*(pInTmp+1))%16;//高4位+低4位
pInTmp++;
}
else if('+'==*pInTmp)
*pOutTmp++ = ' ';
else
*pOutTmp++ = *pInTmp;
pInTmp++;
}
*pOutTmp = '\0';
sOut.ReleaseBuffer();
}
sIn.ReleaseBuffer();

return sOut;
}
CString URLEncode(CString sIn)
{
CString sOut;
const int nLen = sIn.GetLength() + 1;
register LPBYTE pOutTmp = NULL;
LPBYTE pOutBuf = NULL;
register LPBYTE pInTmp = NULL;
LPBYTE pInBuf =(LPBYTE)sIn.GetBuffer(nLen);
//alloc out buffer
pOutBuf = (LPBYTE)sOut.GetBuffer(nLen*3);

if(pOutBuf)
{
pInTmp = pInBuf;
pOutTmp = pOutBuf;
// do encoding
while (*pInTmp)
{
if(isalnum(*pInTmp) || '-'==*pInTmp || '_'==*pInTmp || '.'==*pInTmp)
*pOutTmp++ = *pInTmp;
else if(isspace(*pInTmp))
*pOutTmp++ = '+';
else
{
*pOutTmp++ = '%';
*pOutTmp++ = toHex(*pInTmp>>4);//高4位
*pOutTmp++ = toHex(*pInTmp%16);//低4位
}
pInTmp++;
}
*pOutTmp = '\0';
sOut.ReleaseBuffer();
}
sIn.ReleaseBuffer();

return sOut;
}

[Eleven]

URL Encode编码吧

[似水流年__]

懂得编码就可以了
用GB2312