字符串處理 - ANSI - Unicode - UTF8 轉換

#include <stdio.h> 
#include <windows.h> 
#include <locale.h> 
#define BUFF_SIZE 1024 
 
wchar_t * ANSIToUnicode( const char* str ) 
{ 
     int textlen ; 
     wchar_t * result; 
     textlen = MultiByteToWideChar( CP_ACP, 0, str,-1, NULL,0 ); 
     result = (wchar_t *)malloc((textlen+1)*sizeof(wchar_t)); 
     memset(result,0,(textlen+1)*sizeof(wchar_t)); 
     MultiByteToWideChar(CP_ACP, 0,str,-1,(LPWSTR)result,textlen ); 
     return result; 
} 
 
char * UnicodeToANSI( const wchar_t* str ) 
{ 
     char* result; 
     int textlen; 
     textlen = WideCharToMultiByte( CP_ACP, 0, str, -1, NULL, 0, NULL, NULL ); 
     result =(char *)malloc((textlen+1)*sizeof(char)); 
     memset( result, 0, sizeof(char) * ( textlen + 1 ) ); 
     WideCharToMultiByte( CP_ACP, 0, str, -1, result, textlen, NULL, NULL ); 
     return result; 
} 
 
wchar_t * UTF8ToUnicode( const char* str ) 
{ 
     int textlen ; 
     wchar_t * result; 
     textlen = MultiByteToWideChar( CP_UTF8, 0, str,-1, NULL,0 ); 
     result = (wchar_t *)malloc((textlen+1)*sizeof(wchar_t)); 
     memset(result,0,(textlen+1)*sizeof(wchar_t)); 
     MultiByteToWideChar(CP_UTF8, 0,str,-1,(LPWSTR)result,textlen ); 
     return result; 
} 
 
char * UnicodeToUTF8( const wchar_t* str ) 
{ 
     char* result; 
     int textlen; 
     textlen = WideCharToMultiByte( CP_UTF8, 0, str, -1, NULL, 0, NULL, NULL ); 
     result =(char *)malloc((textlen+1)*sizeof(char)); 
     memset(result, 0, sizeof(char) * ( textlen + 1 ) ); 
     WideCharToMultiByte( CP_UTF8, 0, str, -1, result, textlen, NULL, NULL ); 
     return result; 
} 
/*寬字符轉換為多字符Unicode - ANSI*/ 
char* w2m(const wchar_t* wcs) 
{ 
      int len; 
      char* buf; 
      len =wcstombs(NULL,wcs,0); 
      if (len == 0) 
          return NULL; 
      buf = (char *)malloc(sizeof(char)*(len+1)); 
      memset(buf, 0, sizeof(char) *(len+1)); 
      len =wcstombs(buf,wcs,len+1); 
      return buf; 
} 
/*多字符轉換為寬字符ANSI - Unicode*/ 
wchar_t* m2w(const char* mbs) 
{ 
      int len; 
      wchar_t* buf; 
      len =mbstowcs(NULL,mbs,0); 
      if (len == 0) 
          return NULL; 
      buf = (wchar_t *)malloc(sizeof(wchar_t)*(len+1)); 
      memset(buf, 0, sizeof(wchar_t) *(len+1)); 
      len =mbstowcs(buf,mbs,len+1); 
      return buf; 
} 
 
char* ANSIToUTF8(const char* str) 
{ 
     return UnicodeToUTF8(ANSIToUnicode(str)); 
} 
 
char* UTF8ToANSI(const char* str) 
{ 
     return UnicodeToANSI(UTF8ToUnicode(str)); 
} 
 
int main() 
{ 
     /*使用wcstombs和mbstowcs之前必須調用setlocale，以便決定內碼*/ 
     setlocale(LC_ALL,".936"); 
     /*假定有一個Unicode(UTF-16LE)編碼的文件，將其打開，重新編碼為ANSI
，寫入aa.txt中，再繼續編碼回Unicode，寫入aw.txt中*/ 
     /*如果不存在a.txt文件，則程序出錯，沒有做錯誤處理*/ 
     char* filename = "a.txt"; 
     char* filenamea = "aa.txt"; 
     char* filenamew = "aw.txt"; 
     FILE*     input=fopen( filename, "rb"); 
     FILE*     inputa=fopen( filenamea, "wb"); 
     FILE*     inputw=fopen( filenamew, "wb"); 
     wchar_t * buf ; 
     /*BOE設置，UTF-16LE的BOE為FEFF，如果不先將其讀取出來，wcstombs會調用失敗*/ 
     fgetwc(input); 
     fputwc(0xFEFF,inputw); 
     /*開始讀取文件*/ 
     while(!feof(input)) 
     { 
        buf = (wchar_t *)malloc(sizeof(wchar_t)*BUFF_SIZE)         ; 
        memset(buf,    0, sizeof(wchar_t) * BUFF_SIZE ); 
        fgetws(buf,    BUFF_SIZE,    input); 
        fputs(w2m(buf),    inputa); 
        fputws(m2w(w2m(buf)),    inputw); 
     } 
     /*后續處理*/ 
     fclose(input); 
     fclose(inputa); 
     fclose(inputw); 
     free(buf); 
 
     return 0; 
}