字符串轉碼UTF8轉碼爲GBK的C語言程序源代碼

GBK和UTF8之間的轉換能夠使用MultiByteToWideChar和WideCharToMultiByte兩個API，方法是先把它們轉換爲中間編碼Unicode，再轉換爲對應的編碼便可。

#include <stdio.h>

#include <windows.h>

 

//GBK編碼轉換到UTF8編碼

int GBKToUTF8(unsigned char * lpGBKStr,unsigned char * lpUTF8Str,int nUTF8StrLen)

{

wchar_t * lpUnicodeStr = NULL;

int nRetLen = 0;

 

if(!lpGBKStr) //若是GBK字符串爲NULL則出錯退出

return 0;

 

nRetLen = ::MultiByteToWideChar(CP_ACP,0,(char *)lpGBKStr,-1,NULL,NULL); //獲取轉換到Unicode編碼後所須要的字符空間長度

lpUnicodeStr = new WCHAR[nRetLen + 1]; //爲Unicode字符串空間

nRetLen = ::MultiByteToWideChar(CP_ACP,0,(char *)lpGBKStr,-1,lpUnicodeStr,nRetLen); //轉換到Unicode編碼

if(!nRetLen) //轉換失敗則出錯退出

return 0;

 

nRetLen = ::WideCharToMultiByte(CP_UTF8,0,lpUnicodeStr,-1,NULL,0,NULL,NULL); //獲取轉換到UTF8編碼後所須要的字符空間長度

 

if(!lpUTF8Str) //輸出緩衝區爲空則返回轉換後須要的空間大小

{

if(lpUnicodeStr)

delete []lpUnicodeStr;

return nRetLen;

}

 

if(nUTF8StrLen < nRetLen) //若是輸出緩衝區長度不夠則退出

{

if(lpUnicodeStr)

delete []lpUnicodeStr;

return 0;

}

 

nRetLen = ::WideCharToMultiByte(CP_UTF8,0,lpUnicodeStr,-1,(char *)lpUTF8Str,nUTF8StrLen,NULL,NULL); //轉換到UTF8編碼

 

if(lpUnicodeStr)

delete []lpUnicodeStr;

 

return nRetLen;

}

 

// UTF8編碼轉換到GBK編碼

int UTF8ToGBK(unsigned char * lpUTF8Str,unsigned char * lpGBKStr,int nGBKStrLen)

{

wchar_t * lpUnicodeStr = NULL;

int nRetLen = 0;

 

if(!lpUTF8Str) //若是UTF8字符串爲NULL則出錯退出

return 0;

 

nRetLen = ::MultiByteToWideChar(CP_UTF8,0,(char *)lpUTF8Str,-1,NULL,NULL); //獲取轉換到Unicode編碼後所須要的字符空間長度

lpUnicodeStr = new WCHAR[nRetLen + 1]; //爲Unicode字符串空間

nRetLen = ::MultiByteToWideChar(CP_UTF8,0,(char *)lpUTF8Str,-1,lpUnicodeStr,nRetLen); //轉換到Unicode編碼

if(!nRetLen) //轉換失敗則出錯退出

return 0;

 

nRetLen = ::WideCharToMultiByte(CP_ACP,0,lpUnicodeStr,-1,NULL,NULL,NULL,NULL); //獲取轉換到GBK編碼後所須要的字符空間長度

 

if(!lpGBKStr) //輸出緩衝區爲空則返回轉換後須要的空間大小

{

if(lpUnicodeStr)

delete []lpUnicodeStr;

return nRetLen;

}

 

if(nGBKStrLen < nRetLen) //若是輸出緩衝區長度不夠則退出

{

if(lpUnicodeStr)

delete []lpUnicodeStr;

return 0;

}

 

nRetLen = ::WideCharToMultiByte(CP_ACP,0,lpUnicodeStr,-1,(char *)lpGBKStr,nRetLen,NULL,NULL); //轉換到GBK編碼

 

if(lpUnicodeStr)

delete []lpUnicodeStr;

 

return nRetLen;

}

 

//使用這兩個函數的例子

int main()

{

char cGBKStr[] = "我是中國人!";

char * lpGBKStr = NULL;

char * lpUTF8Str = NULL;

FILE * fp = NULL;

int nRetLen = 0;

 

nRetLen = GBKToUTF8((unsigned char *)cGBKStr,NULL,NULL);

printf("轉換後的字符串須要的空間長度爲：%d ",nRetLen);

lpUTF8Str = new char[nRetLen + 1];

nRetLen = GBKToUTF8((unsigned char *)cGBKStr,(unsigned char *)lpUTF8Str,nRetLen);

if(nRetLen)

{

printf("GBKToUTF8轉換成功！");

}

else

{

printf("GBKToUTF8轉換失敗！");

goto Ret0;

}

 

fp = fopen("C:\GBK轉UTF8.txt","wb"); //保存到文本文件

fwrite(lpUTF8Str,nRetLen,1,fp);

fclose(fp);

 

getchar(); //先去打開那個文本文件看看，單擊記事本的「文件」-「另存爲」菜單，在對話框中看到編碼框變爲了「UTF-8」說明轉換成功了

 

nRetLen = UTF8ToGBK((unsigned char *)lpUTF8Str,NULL,NULL); //再轉回來

printf("轉換後的字符串須要的空間長度爲：%d ",nRetLen);

lpGBKStr = new char[nRetLen + 1];

nRetLen = UTF8ToGBK((unsigned char *)lpUTF8Str,(unsigned char *)lpGBKStr,nRetLen);

if(nRetLen)

{

printf("UTF8ToGBK轉換成功！ ");

}

else

{

printf("UTF8ToGBK轉換失敗！ ");

goto Ret0;

}

 

fp = fopen("C:\UTF8轉GBK.txt","wb"); //保存到文本文件

fwrite(lpGBKStr,nRetLen,1,fp);

fclose(fp);

 

getchar(); //再去打開文本文件看看，發現編碼框又變爲了「ANSI」說明轉換成功了

 

Ret0:

if(lpGBKStr)

delete []lpGBKStr;

 

if(lpUTF8Str)

delete []lpUTF8Str;

 

return 0;

}