Question

c++标准库中unicode ,utf8 ,gbk字符转化的函数叫什么

Answer 1

没有现成的，需要自己实现函数，给你贴几段

GBK转UTF-8
#include <stdio.h>
#include <windows.h>

//GBK编码转换到UTF8编码
int GBKToUTF8(unsigned char * lpGBKStr,unsigned char * lpUTF8Str,int nUTF8StrLen)
{
wchar_t * lpUnicodeStr = NULL;
int nRetLen = 0;

if(!lpGBKStr) //如果GBK字符串为NULL则出错退出
return 0;

nRetLen = ::MultiByteToWideChar(CP_ACP,0,(char *)lpGBKStr,-1,NULL,NULL); //获取转换到Unicode编码后所需要的字符空间长度
lpUnicodeStr = new WCHAR[nRetLen + 1]; //为Unicode字符串空间
nRetLen = ::MultiByteToWideChar(CP_ACP,0,(char *)lpGBKStr,-1,lpUnicodeStr,nRetLen); //转换到Unicode编码
if(!nRetLen) //转换失败则出错退出
return 0;

nRetLen = ::WideCharToMultiByte(CP_UTF8,0,lpUnicodeStr,-1,NULL,0,NULL,NULL); //获取转换到UTF8编码后所需要的字符空间长度

if(!lpUTF8Str) //输出缓冲区为空则返回转换后需要的空间大小
{
if(lpUnicodeStr)
delete []lpUnicodeStr;
return nRetLen;
}

if(nUTF8StrLen < nRetLen) //如果输出缓冲区长度不够则退出
{
if(lpUnicodeStr)
delete []lpUnicodeStr;
return 0;
}

nRetLen = ::WideCharToMultiByte(CP_UTF8,0,lpUnicodeStr,-1,(char *)lpUTF8Str,nUTF8StrLen,NULL,NULL); //转换到UTF8编码

if(lpUnicodeStr)
delete []lpUnicodeStr;

return nRetLen;
}

//使用这两个函数的例子
int main()
{
char cGBKStr[] = "我是中国人!";
char * lpGBKStr = NULL;
char * lpUTF8Str = NULL;
FILE * fp = NULL;
int nRetLen = 0;

nRetLen = GBKToUTF8((unsigned char *) cGBKStr,NULL,NULL);
printf("转换后的字符串需要的空间长度为：%d ",nRetLen);
lpUTF8Str = new char[nRetLen + 1];
nRetLen = GBKToUTF8((unsigned char *)cGBKStr,(unsigned char *)lpUTF8Str,nRetLen);
if(nRetLen)
{
printf("GBKToUTF8转换成功！");
}
else
{
printf("GBKToUTF8转换失败！");
goto Ret0;
}
fp = fopen("C:\\GBKtoUTF8.txt","wb"); //保存到文本文件
fwrite(lpUTF8Str,nRetLen,1,fp);
fclose(fp);
getchar(); //先去打开那个文本文件看看，单击记事本的“文件”-“另存为”菜单，在对话框中看到编码框变为了“UTF-8”说明转换成功了

Ret0:

{
if(lpGBKStr)
delete []lpGBKStr;
if(lpUTF8Str)
delete []lpUTF8Str;
}
return 0;
}

Unicode UTF_8互转

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(string &pOut, char *pText, int pLen);//UTF-8 转为 GB2312

};

类实现

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] = '';

//返回结果

pOut = rst;

delete []rst;

return;

}

void CChineseCode::UTF_8ToGB2312(string &pOut, char *pText, int pLen)

{

char * newBuf = new char[pLen];

char Ctemp[4];

memset(Ctemp,0,4);

int i =0;

int j = 0;

while(i < pLen)

{

if(pText > 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] = '';

pOut = newBuf;

delete []newBuf;

return;

}

将GBK转换成UTF8

string GBKToUTF8(const std::string& strGBK)
{ string strOutUTF8 = "";
WCHAR * str1;
int n = MultiByteToWideChar(CP_ACP, 0, strGBK.c_str(), -1, NULL, 0);
str1 = new WCHAR[n];
MultiByteToWideChar(CP_ACP, 0, strGBK.c_str(), -1, str1, n); n = WideCharToMultiByte(CP_UTF8, 0, str1, -1, NULL, 0, NULL, NULL);
char * str2 = new char[n];
WideCharToMultiByte(CP_UTF8, 0, str1, -1, str2, n, NULL, NULL);
strOutUTF8 = str2;
delete[]str1;
str1 = NULL;
delete[]str2;
str2 = NULL;
return strOutUTF8;
}

将UTF8转换成GBK

string UTF8ToGBK(const std::string& strUTF8)
{
int len = MultiByteToWideChar(CP_UTF8, 0, strUTF8.c_str(), -1, NULL, 0);
unsigned short * wszGBK = new unsigned short[len + 1]; memset(wszGBK, 0, len * 2 + 2);
MultiByteToWideChar(CP_UTF8, 0, (LPCTSTR)strUTF8.c_str(), -1, wszGBK, len);

len = WideCharToMultiByte(CP_ACP, 0, wszGBK, -1, NULL, 0, NULL, NULL);
char *szGBK = new char[len + 1];
memset(szGBK, 0, len + 1);
WideCharToMultiByte(CP_ACP,0, wszGBK, -1, szGBK, len, NULL, NULL); //strUTF8 = szGBK;
std::string strTemp(szGBK);
delete[]szGBK;
delete[]wszGBK;
return strTemp;
}