最近由于业务的需要,自己手写了一个UTF8到GBK相互转换的程序,分别为linux版本和windows版本,需要注意的是:
不管是UTF8到GBK还是GBK到UTF8,中间都必须转换到UNICODE,然后再从UNICODE转换到目标代码:
从UTF8到GBK的转换有固定的算法可以转换过去,但是从GBK到UNICODE和从UNICODE到GBK必须使用系统所提供的函数:
其中标准c提供了相应的函数分别是:
GBK—>UNICODE :mbstowcs
UNICODE->GBK : wcstombs
需要注意的是在使用上面两个函数之前必须使用setlocale函数制定所使用的字符集为GBK
另外在windows系统上,还提供了两个操作系统级别的函数,分别是:
UNICODE->GBK :WideCharToMultiByte
UNICODE->GBK : MultiByteToWideChar
以下为windows下的源码:
#include "windows.h" #include <string.h> #include <stdlib.h> #include <locale.h> char* GB18030ToUTF_8(const char *pText,int pLen); char* UTF_8ToGB18030(const char *pText,int pLen); void GB18030ToUnicode(wchar_t* pOut,const char *gbBuffer); void UnicodeToUTF_8(char* pOut,WCHAR* pText); void UnicodeToGB18030(char* pOut,unsigned short* uData) ; void UTF_8ToUnicode(wchar_t* pOut,const char *pText); char* GB18030ToUTF_8(const char *pText,int pLen) { char buf[1024]; char* rst = new char[pLen+(pLen>>2)+2]; memset(buf,0,1024); memset(rst,0,pLen+(pLen>>2)+2); int i = 0; int j = 0; while(i < pLen) { if( *(pText + i) >= 0) { rst[j++] = pText[i++]; } else { wchar_t pbuffer; GB18030ToUnicode(&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; } } strcpy(&rst[j],"/0"); return rst; } void GB18030ToUnicode(wchar_t* pOut,const char *gbBuffer) { ::MultiByteToWideChar(CP_ACP,MB_PRECOMPOSED,gbBuffer,2,pOut,1); } void UnicodeToUTF_8(char* pOut,wchar_t* pText) { 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)); } char* UTF_8ToGB18030(const 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[i] > 0) { newBuf[j++] = pText[i++]; } else { wchar_t Wtemp; UTF_8ToUnicode(&Wtemp,pText+i); UnicodeToGB18030(Ctemp,&Wtemp); newBuf[j] = Ctemp[0]; newBuf[j+1] = Ctemp[1]; i+= 3; j+= 2; } } strcpy(&newBuf[j],"/0"); return newBuf; } void UTF_8ToUnicode(wchar_t* pOut,const 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); } void UnicodeToGB18030(char* pOut,unsigned short* uData) { ::WideCharToMultiByte(CP_ACP,NULL,LPCWSTR(uData),1,pOut,sizeof(WCHAR),NULL,NULL); }
以下是linux系统上的源码:
void UnicodeToUTF_8(char* pUTF8,wchar_t* pUnicode) { char* pchar = (char*)pUnicode; pUTF8[0] = (0xE0|((pchar[1]&0xF0)>>4)); pUTF8[1] = (0x80|((pchar[1]&0x0F)<<2))+((pchar[0]&0xC0)>>6); pUTF8[2] = (0x80|(pchar[0]&0x3F)); } char* GBToUTF_8(const char* pText, int pLen) { setlocale(LC_ALL,"zh_CN.gbk"); char buf[1024]; char* rst = new char[pLen + (pLen >> 2) + 2]; memset(rst,0,pLen + (pLen >> 2) +2); int i = 0; int j = 0; while(i < pLen) { if(*(pText + i) >=0 ) { rst[j++] = pText[i++]; } else { wchar_t pwbuffer; mbstowcs(&pwbuffer,pText + i,1); UnicodeToUTF_8(buf,&pwbuffer); unsigned short tmp = 0; rst[j] = buf[0]; rst[j+1] = buf[1]; rst[j+2] = buf[2]; j+=3; i+=2; } } return rst; } char* UTF_8ToGB(const char* pText,int pLen) { char* newBuf = new char[pLen]; char temp[4]; memset(newBuf,0,pLen); memset(temp,0,4); int i = 0; int j = 0; setlocale(LC_ALL,"zh_CN.gbk"); while(i < pLen) { if(pText[i] > 0) { newBuf[j++] = pText[i++]; } else { wchar_t wTemp; UTF_8ToUnicode(&wTemp,pText+i); wcstombs(temp,&wTemp,2); newBuf[j] = temp[0]; newBuf[j+1] = temp[1]; i+= 3; j+= 2; } } return newBuf; } void UTF_8ToUnicode(wchar_t* pUnicode,const char* pUTF_8) { char* uchar = (char*)pUnicode; uchar[1] = ((pUTF_8[0]&0x0F)<<4)+((pUTF_8[1]>>2)&0x0F); uchar[0] = ((pUTF_8[1]&0x03)<<6)+(pUTF_8[2]&0x3F); }