如何将 UTF-8 编码转换成 ANSI 编码？

我转换的时候基本上正确，但是有些空格会转换成"?"，有些却不会，不知道为什么？

12 个解决方案

#1

see
see

#2

see

#3

see too

#4

size_t wcstombs(
   char *mbstr,
   const wchar_t *wcstr,
   size_t count
);

Requirements
Routine Required header Compatibility
wcstombs <stdlib.h> ANSI, Win 98, Win Me, Win NT, Win 2000, Win XP

For additional compatibility information, see Compatibility in the Introduction.

Libraries

All versions of the C run-time libraries.

Example
/* WCSTOMBS.C illustrates the behavior of the wcstombs function. */

#include <stdio.h>
#include <stdlib.h>

void main( void )
{
   int      i;
   char    *pmbbuf   = (char *)malloc( MB_CUR_MAX );
   wchar_t *pwchello = L"Hello, world.";

   printf( "Convert wide-character string:\n" );
   i = wcstombs( pmbbuf, pwchello, MB_CUR_MAX );
   printf( "\tCharacters converted: %u\n", i );
   printf( "\tMultibyte character: %s\n\n", pmbbuf );
}

#5

用WideCharToMultiByte吧，功能强大。想怎么转都行。

#6

WideCharToMultiByte or W2A()

#7

我认Widechar和UTF8是两个概念，对于UTF8，一个汉字占三个字节，一个希腊字母占用两个字节，一个英文字母或数字占用1个字节。而WideChar即Unicode则所有字符占用两个字节。包括英文字母。使用WideCharToMultiByte参数是要求使用CP_UTF8参数实现转化。建议在使用前先使用NOTEPAD建立一个文本文件，分别输入几个汉字、希腊字母、英文字母、数字，然后使用不同的格式存盘，ANSI、 UNICODE、 UTF8 然后使用Visual C++以二进制方式打开文本文件，查看十六进制编码。UNICODE 不等于UTF8，上面的W2A以及wcstombs只适用于UNICODE，WideCharToMultiByte和W2A也不等价，WideCharToMultiByte提供了更多的参数，实现各种编码的转化。W2A只是ATL定义的一个宏充其量是WideCharToMultiByte众多参数版本中的一个。
下面我把发送ICQ短信的部分代码粘出来，自己分析一下ANSI UNICODE UTF8之间的转化
strcpy(szSubMessage,pThis->m_szMessage.Mid(nCurrent,(nMessageCount-nCurrent)>=nCharCountMax?nCharCountMax:remainder));
nCurrent+=nCharCountMax;
szRefer="Referer: ";
szRefer+=szHost;
szRefer+="\r\n";
szHost="https://web.icq.com/secure/sms/send_history/1,,,00.html";
lstrcpyW(wszChinese,A2W(szSubMessage));
WideCharToMultiByte(CP_UTF8,0,wszChinese,lstrlenW(wszChinese)
,szTemp,sizeof szTemp,NULL,NULL);
EscapeToCString(szTarget,szTemp);
if(pThis->m_bFlash)
szPostData="uSend=1&prefix=+86&tophone=%MOBILE%&msg=\1%E5%86%89%E6%9E%97%E4%BB%93\1";
else
szPostData="uSend=1&prefix=+86&tophone=%MOBILE%&msg=%E5%86%89%E6%9E%97%E4%BB%93";
szPostData.Replace ("%MOBILE%",pThis->m_szMobile.Right (11));
szPostData.Replace ("86",pThis->m_szCountry);
szPostData.Replace ("%E5%86%89%E6%9E%97%E4%BB%93",szTarget);
szHeaders="Accept: *//*\r\n"
  "User-Agent: Mozilla/4.0\r\n"
  "Content-Type: application/x-www-form-urlencoded\r\n"
   "Content-Length: %LENGTH%\r\n";

#8

1.What is UTF-8?
http://www.cl.cam.ac.uk/~mgk25/unicode.html#utf-8

2.Here is a UTF8ToHtml function, which converts from UTF-8 to HTML.

//utf8 - pointer to UTF8 formatted text. dwSize - size of UTF8 text; ptr is the pointer to Output buffer.

//The OnClickedPastehtml is the handler for BN_CLICK event of the button in Dialog box. IDC_TEXT is the multiline text box.

void UTF8ToHtml(BYTE *utf8, DWORD dwSize, CHAR *ptr )
{
  int code;
  BYTE *end = utf8 + dwSize;
  while( utf8 < end )
  {
    code = 0;
    if( (*utf8 & 0xF0) == 0xF0  )
    {
      code = (((*utf8)&0x0F) << 18) | (((*(utf8+1))
        & 0x7F)<<12) | (((*(utf8+2)) & 0x7F)<<6)
        | ((*(utf8+3)) & 0x7F );
      utf8+=3;
    }
    else
    {
      if( (*utf8 & 0xE0) == 0xE0 )
      {
        code = (((*utf8)&0x1F) << 12) | (((*(utf8+1))
         & 0x7F)<<6 ) | ((*(utf8+2)) & 0x7F );
        utf8+=2;
      }
      else
      {
        if( (*utf8 & 0xC0) == 0xC0 )
        {
          code = (((*utf8)&0x3F) << 6) | ((*(utf8+1)) & 0x7F) ;
          utf8+=1;
        }
      }
    }

    if( code == 0 )
    {
      *ptr = *utf8;
    }
    else
    {
      char s[10];
      switch(code)
      {
      case 160:
        strcpy(s, "& ");
        break;
      case 34:
        strcpy(s, "&");
        break;
      case 36:
        strcpy( s, "&&");
        break;
      case 60:
        strcpy( s, "&<");
        break;
      case 62:
        strcpy( s, "&>");
        break;
      default:
        sprintf( s, "&#%d;", code );
        break;
      }
      strcpy( ptr, s );
      ptr += strlen(s)-1;
    }
    utf8++;
    ptr++;
  }
  *ptr = 0;
}
LRESULT CDialog::OnClickedPastehtml( WORD wNotifyCode,
                                     WORD wID,
                                     HWND hWndCtl,
                                     BOOL& bHandled)
{
  if (!OpenClipboard() )
    return 0;
  UINT uHtmlFormat = RegisterClipboardFormat("HTML Format");
  UINT uFormat = uHtmlFormat;
  if( IsClipboardFormatAvailable( uHtmlFormat ) == FALSE )
  {
    if( IsClipboardFormatAvailable( CF_TEXT ) == FALSE )
      return 0;
    uFormat = CF_TEXT;
  }

  HGLOBAL   hglb;
  LPTSTR    lptstr;
  hglb = GetClipboardData(uFormat);
  if (hglb != NULL)
  {
    lptstr = (LPTSTR)GlobalLock(hglb);
    if (lptstr != NULL)
    {
      char *ptr1 = strstr( lptstr, "");
      if( ptr1 != 0 )
      {
        ptr1 += 20;
        char * ptr2 = strstr( lptstr, "");
        int iSize = (ptr2 - ptr1);
        char * tmp = (char*)_alloca( iSize *2);
        UTF8ToHtml((BYTE*)ptr1, iSize, tmp );
        //memcpy(tmp, ptr1, iSize );
        //tmp[iSize] = 0;
        SetDlgItemText(IDC_TEXT, tmp );
      }
      else
        SetDlgItemText(IDC_TEXT, lptstr );
      GlobalUnlock(hglb);
    }
  }
  CloseClipboard();
  return 0;
}

#9

About article was contributed by George Ter-Saakov.

--------

#10

Convert utf8 to htmel
http://www.codeguru.com/clipboard/HowToPasteHtml.html

#11

先使用MultiByteToWideChar 用CF-UTF8 参数转化成 UNICODE,然后再把unicode转化成ansi(此时可以用W2A()).

#12

public String getStr(String str)
{
try
{
String temp_p = str;
byte[] temp_t = temp_p.getBytes("ANSI");
String temp = new String(temp_t);
return temp;
}catch(Exception e)
{
}
return "null";
}

#1