http://www.vckbase.com/document/viewdoc/?id=1444
此文介绍了UTF8和GB2312间的互换并提供代码,但是代码有误,现修改如下:
class CChineseCodeLib
{
public:
static void UTF_8ToGB2312(string& pOut,char *pText, int pLen);
static void GB2312ToUTF_8(string& pOut,char *pText, int pLen);
// Unicode 转换成UTF-8
static void UnicodeToUTF_8(char* pOut,WCHAR* pText);
// GB2312 转换成 Unicode
static void Gb2312ToUnicode(WCHAR* pOut,char *gbBuffer);
// 把Unicode 转换成 GB2312
static void UnicodeToGB2312(char* pOut,WCHAR uData);
// 把UTF-8转换成Unicode
static void UTF_8ToUnicode(WCHAR* pOut,char* pText);
CChineseCodeLib();
virtual ~CChineseCodeLib();
};
void CChineseCodeLib::UTF_8ToUnicode(WCHAR* 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 CChineseCodeLib::UnicodeToGB2312(char* pOut,WCHAR uData)
{
WideCharToMultiByte(CP_ACP,NULL,&uData,1,pOut,sizeof(WCHAR),NULL,NULL);
return;
}
void CChineseCodeLib::Gb2312ToUnicode(WCHAR* pOut,char *gbBuffer)
{
::MultiByteToWideChar(CP_ACP,MB_PRECOMPOSED,gbBuffer,2,pOut,1);
return;
}
void CChineseCodeLib::UnicodeToUTF_8(char* pOut,WCHAR* 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); // 此处也有错误,该文作者已提出!
pOut[2] = (0x80 | (pchar[0] & 0x3F));
return;
}
void CChineseCodeLib::GB2312ToUTF_8(string& pOut,char *pText, int pLen)
{
char buf[4];
char* rst = new char[(pLen/2)*3+1]; // 原代码此处分配的空间不够,导致越界!
memset(buf,0,4);
memset(rst,0,sizeof(rst));
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 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 CChineseCodeLib::UTF_8ToGB2312(string &pOut, char *pText, int pLen)
{
char * newBuf = new char[pLen+1]; // 原代码此处分配空间不够,当pText全部为英文时会出错。pLen为pText字 // 符串的长度,不包含终止符
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';
pOut = newBuf;
delete []newBuf;
return;
}
修改后的源文件请到此处下载。
关于UTF8可以参考:http://www.linuxforum.net/books/UTF-8-Unicode.html