VC中实现GB2312、BIG5、Unicode编码转换的方法

Z时代
2024-01-10
分类：综合

本文主要以实例形式讨论了VC编译环境下，实现字符串和文件编码方式转换的方法，在linux下请使用Strconv来实现。具体方法如下：

一、文件编码格式转换


//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


//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;
}