0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

文字コード判別と変換

Posted at

英数字のみのテキストファイルに、Win10メモ帳で漢字を追記すると、
メモ帳での保存時にUTF8が選択されるから、昔ながらのANSI/SJISを前提とした
アプリだとエラーが出るんだと。
久しぶりのWin32、以下のように修正してやりました。
MultiByteToWideChar()/WideCharToMultiByte()はBOMを削除しないので、ファイルから読み込んだバイナリーデータを変換する場合には、BOMのバイト分ずらす必要がありました。

#include <mlang.h>
...
  IMultiLanguage2* mlang = NULL;
  DetectEncodingInfo detectEnc{};
  HRESULT hres=CoCreateInstance(CLSID_CMultiLanguage, NULL, CLSCTX_INPROC_SERVER, IID_IMultiLanguage2, (void**)&mlang);
  {
    int encCount=1;
    DWORD size_i;
    char txtdata[MAX_BUFFERBLOCK];
    
    HANDLE h=CreateFile(filename, GENERIC_READ, FILE_SHARE_READ, NULL, OPEN_EXISTING, FILE_ATTRIBUTE_NORMAL, NULL);
    ReadFile(h, txtdata, MAX_BUFFERBLOCK, &size_i, NULL);
    CloseHandle(h);
    hres=mlang->DetectInputCodepage(MLDETECTCP_NONE, 0, txtdata, (INT *)&size_i, &detectEnc, &encCount);
    }
  }
  mlang->Release();
  
  if(detectEnc.nCodePage==65001){ // UTF8
    char b_filename[MAX_PATH]{};
    strcpy(b_filename, filename);
    PathRenameExtension(b_filename, ".ini_UTF8");
    MoveFileEx(filename, b_filename, MOVEFILE_REPLACE_EXISTING);

    HANDLE h;
    DWORD srcsize, medsize, dstsize, rwsize;
    unsigned char *mtxt=NULL, *mtxt_a=NULL;
    wchar_t *wtxt=NULL;
    bool wBOM=false;
    {
      h=CreateFile(b_filename, GENERIC_READ, FILE_SHARE_READ, NULL, OPEN_EXISTING, FILE_ATTRIBUTE_NORMAL, NULL);
      srcsize=GetFileSize(hFile, NULL);
      mtxt=(unsigned char *)malloc(srcsize);
      ReadFile(h, (char *)mtxt, srcsize, &rwsize, NULL);
      CloseHandle(h);

      if((mtxt[0]==0xef)&&(mtxt[1]==0xbb)&&(mtxt[2]==0xbf)) wBOM=true;

      if(wBOM==true){
        mtxt_a=&mtxt[3];
        srcsize=rwsize-3;
      }else{
        mtxt_a=&mtxt[0];
        srcsize=rwsize;
      }

      medsize=MultiByteToWideChar(CP_UTF8, 0, (LPCCH)mtxt_a, srcsize, NULL, 0);
      wtxt=(wchar_t *)malloc(medsize*sizeof(wchar_t));
      MultiByteToWideChar(CP_UTF8, 0, (LPCCH)mtxt_a, srcsize, wtxt, medsize);

      dstsize=WideCharToMultiByte(CP_ACP, 0, wtxt, medsize, NULL, 0, NULL, NULL);
      mtxt=(unsigned char *)realloc(mtxt, dstsize*sizeof(unsigned char));
      WideCharToMultiByte(CP_ACP, 0, wtxt, medsize, (LPSTR)mtxt, dstsize, NULL, NULL);

      h=CreateFile(filename, GENERIC_WRITE, 0, NULL, CREATE_NEW, FILE_ATTRIBUTE_NORMAL, NULL);
      WriteFile(hFile, (char *)(mtxt), dstsize, &rwsize, NULL);
      CloseHandle(h);
    }
    if(mtxt!=NULL) free(mtxt);
    if(wtxt!=NULL) free(wtxt);
0
0
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?