VC中实现GB2312、BIG5、Unicode编码转换

转载：http://www.jb51.net/article/52477.htm

一、文件编码格式转换

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22

//GB2312 编码文件转换成 Unicode： if ((file_handle = fopen (filenam, "rb" )) != NULL) {      //从GB2312源文件以二进制的方式读取buffer      numread = fread (str_buf_pool, sizeof ( char ),POOL_BUFF_SIZE,file_handle);      fclose (file_handle);     //GB2312文件buffer转换成UNICODE     nLen  =MultiByteToWideChar(CP_ACP,0,str_buf_pool,-1,NULL,0);     MultiByteToWideChar(CP_ACP,0,str_buf_pool,-1,( LPWSTR )str_unicode_buf_pool,nLen);     //组装UNICODE Little Endian编码文件文件头标示符"0xFF 0xFE"     //备注：UNICODE Big Endian编码文件文件头标示符"0xFF 0xFE"     //Little Endian与Big Endian编码差异此处不详述     unicode_little_file_header[0]=0xFF;     unicode_little_file_header[1]=0xFE;     //存储目标文件     if ((file_handle= fopen (filenewname, "wb+" )) != NULL)     {     fwrite (unicode_little_file_header, sizeof ( char ),2,file_handle);     numwrite = fwrite (str_unicode_buf_pool, sizeof ( LPWSTR ),nLen,file_handle);     fclose (file_handle);     } }

二、字符串编码格式转换

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69

//GB2312 转换成 Unicode： wchar_t * GB2312ToUnicode( const char * szGBString) {      UINT nCodePage = 936; //GB2312      int nLength=MultiByteToWideChar(nCodePage,0,szGBString,-1,NULL,0);      wchar_t * pBuffer = new wchar_t [nLength+1];      MultiByteToWideChar(nCodePage,0,szGBString,-1,pBuffer,nLength);      pBuffer[nLength]=0;      return pBuffer; } //BIG5 转换成 Unicode： wchar_t * BIG5ToUnicode( const char * szBIG5String) {      UINT nCodePage = 950; //BIG5      int nLength=MultiByteToWideChar(nCodePage,0,szBIG5String,-1,NULL,0);      wchar_t * pBuffer = new wchar_t [nLength+1];      MultiByteToWideChar(nCodePage,0,szBIG5String,-1,pBuffer,nLength);      pBuffer[nLength]=0;      return pBuffer; } //Unicode 转换成 GB2312： char * UnicodeToGB2312( const wchar_t * szUnicodeString) {      UINT nCodePage = 936; //GB2312      int nLength=WideCharToMultiByte(nCodePage,0,szUnicodeString,-1,NULL,0,NULL,NULL);      char * pBuffer= new char [nLength+1];      WideCharToMultiByte(nCodePage,0,szUnicodeString,-1,pBuffer,nLength,NULL,NULL);      pBuffer[nLength]=0;      return pBuffer; } //Unicode 转换成 BIG5： char * UnicodeToBIG5( const wchar_t * szUnicodeString) {      UINT nCodePage = 950; //BIG5      int nLength=WideCharToMultiByte(nCodePage,0,szUnicodeString,-1,NULL,0,NULL,NULL);      char * pBuffer= new char [nLength+1];      WideCharToMultiByte(nCodePage,0,szUnicodeString,-1,pBuffer,nLength,NULL,NULL);      pBuffer[nLength]=0;      return pBuffer; } //繁体中文BIG5 转换成 简体中文 GB2312 char * BIG5ToGB2312( const char * szBIG5String) {      LCID lcid = MAKELCID(MAKELANGID(LANG_CHINESE,SUBLANG_CHINESE_SIMPLIFIED),SORT_CHINESE_PRC);      wchar_t * szUnicodeBuff = BIG5ToUnicode(szBIG5String);      char * szGB2312Buff = UnicodeToGB2312(szUnicodeBuff);      int nLength = LCMapString(lcid,LCMAP_SIMPLIFIED_CHINESE, szGB2312Buff,-1,NULL,0);      char * pBuffer = new char [nLength + 1];      LCMapString(0x0804,LCMAP_SIMPLIFIED_CHINESE,szGB2312Buff,-1,pBuffer,nLength);      pBuffer[nLength] = 0;            delete [] szUnicodeBuff;      delete [] szGB2312Buff;      return pBuffer; } //简体中文 GB2312 转换成 繁体中文BIG5 char * GB2312ToBIG5( const char * szGBString) {      LCID lcid = MAKELCID(MAKELANGID(LANG_CHINESE,SUBLANG_CHINESE_SIMPLIFIED),SORT_CHINESE_PRC);      int nLength = LCMapString(lcid,LCMAP_TRADITIONAL_CHINESE,szGBString,-1,NULL,0);      char * pBuffer= new char [nLength+1];      LCMapString(lcid,LCMAP_TRADITIONAL_CHINESE,szGBString,-1,pBuffer,nLength);      pBuffer[nLength]=0;      wchar_t * pUnicodeBuff = GB2312ToUnicode(pBuffer);      char * pBIG5Buff = UnicodeToBIG5(pUnicodeBuff);      delete [] pBuffer;      delete [] pUnicodeBuff;      return pBIG5Buff; }

//GB2312到UTF-8的转换
static int GB2312ToUtf8(const char* gb2312, char* utf8)
{
int len = MultiByteToWideChar(CP_ACP, 0, gb2312, -1, NULL, 0);
wchar_t* wstr = new wchar_t[len+1];
memset(wstr, 0, len+1);
MultiByteToWideChar(CP_ACP, 0, gb2312, -1, wstr, len);
len = WideCharToMultiByte(CP_UTF8, 0, wstr, -1, NULL, 0, NULL, NULL);
WideCharToMultiByte(CP_UTF8, 0, wstr, -1, utf8, len, NULL, NULL);
if(wstr) delete[] wstr;
return len;
}


//UTF-8到GB2312的转换
static int Utf8ToGB2312(const char* utf8,char* gb2312)
{
int len = MultiByteToWideChar(CP_UTF8, 0, utf8, -1, NULL, 0);
wchar_t* wstr = new wchar_t[len+1];
memset(wstr, 0, len+1);
MultiByteToWideChar(CP_UTF8, 0, utf8, -1, wstr, len);
len = WideCharToMultiByte(CP_ACP, 0, wstr, -1, NULL, 0, NULL, NULL);
WideCharToMultiByte(CP_ACP, 0, wstr, -1, gb2312, len, NULL, NULL);
if(wstr) delete[] wstr;
return len;
}


//GB2312到Unicode的转换
static int GB2312ToUnicode(const char* gb2312, char* unicode)
{
UINT nCodePage = 936; //GB2312
int len = MultiByteToWideChar(nCodePage, 0, gb2312, -1, NULL, 0);
wchar_t* wstr = new wchar_t[len+1];
memset(wstr, 0, len+1);
MultiByteToWideChar(nCodePage, 0, gb2312, -1, wstr, len);
len = len*sizeof(wchar_t);
memcpy(unicode, wstr, len);
if(wstr) delete[] wstr;
return len;
}


//Unicode到GB2312的转换
static int UnicodeToGB2312(const char* unicode, int size, char*gb2312)
{
UINT nCodePage = 936; //GB2312
wchar_t* wstr = new wchar_t[size/2+1];
memcpy(wstr, unicode, size);
int len = WideCharToMultiByte(nCodePage, 0, wstr, -1, NULL, 0, NULL, NULL);
WideCharToMultiByte(nCodePage, 0, wstr, -1, gb2312, len, NULL, NULL);
if(wstr) delete[] wstr;
return len;
}


//UTF-8到Unicode的转换
static int Utf8ToUnicode(const char* utf8, char*unicode)
{
int len = MultiByteToWideChar(CP_UTF8, 0, utf8, -1, NULL, 0);
wchar_t* wstr = new wchar_t[len+1];
memset(wstr, 0, len+1);
MultiByteToWideChar(CP_UTF8, 0, utf8, -1, wstr, len);
memcpy(unicode, wstr, len);
if(wstr) delete[] wstr;
return len;
}


//Unicode到UTF-8的转换
static int UnicodeToUtf8(const char* unicode, int size, char* utf8)
{
wchar_t* wstr = new wchar_t[size/2+1];
memcpy(wstr, unicode, size);
int len = WideCharToMultiByte(CP_UTF8, 0, wstr, -1, NULL, 0, NULL, NULL);
WideCharToMultiByte(CP_UTF8, 0, wstr, -1, utf8, len, NULL, NULL);
if(wstr) delete[] wstr;
return len;
}

三、API 函数：MultiByteToWideChar参数说明

第一个参数为代码页, 用 GetLocaleInfo 函数获取当前系统的代码页，936: 简体中文, 950: 繁体中文
第二个参数为选项，一般用 0 就可以了
第三个参数为 ANSI 字符串的地址, 这个字符串是第一个参数指定的语言的 ANSI 字符串 (AnsiString)
第四个参数为 ANSI 字符串的长度，如果用 -1, 就表示是用 0 作为结束符的字符串
第五个参数为转化生成的 unicode 字符串 (WideString) 的地址, 如果为 NULL, 就是代表计算生成的字符串的长度
第六个参数为转化生成的 unicode 字符串缓存的容量,也就是有多少个UNICODE字符。