【miscellaneous】【C/C++语言】UTF8与GBK字符编码之间的相互转换

#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;
}

  1 class CChineseCode  
  2 
  3 {  
  4 
  5   public:  
  6 
  7       static void UTF_8ToUnicode(wchar_t* pOut,char *pText);  // 把UTF-8转换成Unicode  
  8 
  9       static void UnicodeToUTF_8(char* pOut,wchar_t* pText);  //Unicode 转换成UTF-8  
 10 
 11       static void UnicodeToGB2312(char* pOut,wchar_t uData);  // 把Unicode 转换成 GB2312    
 12 
 13       static void Gb2312ToUnicode(wchar_t* pOut,char *gbBuffer);// GB2312 转换成　Unicode  
 14 
 15       static void GB2312ToUTF_8(string& pOut,char *pText, int pLen);//GB2312 转为 UTF-8  
 16 
 17       static void UTF_8ToGB2312(string &pOut, char *pText, int pLen);//UTF-8 转为 GB2312  
 18 
 19 };  
 20 
 21 类实现  
 22 
 23 void CChineseCode::UTF_8ToUnicode(wchar_t* pOut,char *pText)  
 24 
 25 {  
 26 
 27    char* uchar = (char *)pOut;  
 28 
 29    uchar[1] = ((pText[0] & 0x0F) << 4) + ((pText[1] >> 2) & 0x0F);  
 30 
 31    uchar[0] = ((pText[1] & 0x03) << 6) + (pText[2] & 0x3F);  
 32 
 33    return;  
 34 
 35 }  
 36 
 37 void CChineseCode::UnicodeToUTF_8(char* pOut,wchar_t* pText)  
 38 
 39 {  
 40 
 41    // 注意 WCHAR高低字的顺序,低字节在前，高字节在后  
 42 
 43    char* pchar = (char *)pText;  
 44 
 45    pOut[0] = (0xE0 | ((pchar[1] & 0xF0) >> 4));  
 46 
 47    pOut[1] = (0x80 | ((pchar[1] & 0x0F) << 2)) + ((pchar[0] & 0xC0) >> 6);  
 48 
 49    pOut[2] = (0x80 | (pchar[0] & 0x3F));  
 50 
 51    return;  
 52 
 53 }  
 54 
 55 void CChineseCode::UnicodeToGB2312(char* pOut,wchar_t uData)  
 56 
 57 {  
 58 
 59   WideCharToMultiByte(CP_ACP,NULL,&uData,1,pOut,sizeof(wchar_t),NULL,NULL);  
 60 
 61    return;  
 62 
 63 }        
 64 
 65 void CChineseCode::Gb2312ToUnicode(wchar_t* pOut,char *gbBuffer)  
 66 
 67 {  
 68 
 69    ::MultiByteToWideChar(CP_ACP,MB_PRECOMPOSED,gbBuffer,2,pOut,1);  
 70 
 71    return ;  
 72 
 73 }  
 74 
 75 void CChineseCode::GB2312ToUTF_8(string& pOut,char *pText, int pLen)  
 76 
 77 {  
 78 
 79    char buf[4];  
 80 
 81    int nLength = pLen* 3;  
 82 
 83    char* rst = new char[nLength];  
 84 
 85    memset(buf,0,4);  
 86 
 87    memset(rst,0,nLength);  
 88 
 89    int i = 0;  
 90 
 91    int j = 0;        
 92 
 93    while(i < pLen)  
 94 
 95    {  
 96 
 97            //如果是英文直接复制就可以  
 98 
 99            if( *(pText + i) >= 0)  
100 
101            {  
102 
103                    rst[j++] = pText[i++];  
104 
105            }  
106 
107            else  
108 
109            {  
110 
111                    wchar_t pbuffer;  
112 
113                    Gb2312ToUnicode(&pbuffer,pText+i);  
114 
115                    UnicodeToUTF_8(buf,&pbuffer);  
116 
117                    unsigned short int tmp = 0;  
118 
119                    tmp = rst[j] = buf[0];  
120 
121                    tmp = rst[j+1] = buf[1];  
122 
123                    tmp = rst[j+2] = buf[2];      
124 
125                    j += 3;  
126 
127                    i += 2;  
128 
129            }  
130 
131    }  
132 
133    rst[j] = '';  
134 
135    //返回结果  
136 
137    pOut = rst;                
138 
139    delete []rst;     
140 
141    return;  
142 
143 }  
144 
145 void CChineseCode::UTF_8ToGB2312(string &pOut, char *pText, int pLen)  
146 
147 {  
148 
149    char * newBuf = new char[pLen];  
150 
151    char Ctemp[4];  
152 
153    memset(Ctemp,0,4);  
154 
155    int i =0;  
156 
157    int j = 0;  
158 
159    while(i < pLen)  
160 
161    {  
162 
163        if(pText > 0)  
164 
165        {  
166 
167                newBuf[j++] = pText[i++];                          
168 
169        }  
170 
171        else                    
172 
173        {  
174 
175                WCHAR Wtemp;  
176 
177                UTF_8ToUnicode(&Wtemp,pText + i);        
178 
179                UnicodeToGB2312(Ctemp,Wtemp);                
180 
181                newBuf[j] = Ctemp[0];  
182 
183                newBuf[j + 1] = Ctemp[1];    
184 
185                i += 3;      
186 
187                j += 2;     
188 
189        }  
190 
191    }  
192 
193    newBuf[j] = '';    
194 
195    pOut = newBuf;    
196 
197    delete []newBuf;  
198 
199    return;    
200 
201 }