Multibyte Conversion Example (The GNU C Library)

6.3.5 A Complete Multibyte Conversion Example

The example programs given in the last sections are only brief and do not contain all the error checking, etc. Presented here is a complete and documented example. It features the mbrtowc function but it should be easy to derive versions using the other functions.

int
file_mbsrtowcs (int input, int output)
{
  /* Note the use of MB_LEN_MAX.
     MB_CUR_MAX cannot portably be used here.  */
  char buffer[BUFSIZ + MB_LEN_MAX];
  mbstate_t state;
  int filled = 0;
  int eof = 0;

  /* Initialize the state.  */
  memset (&state, '\0', sizeof (state));

  while (!eof)
    {
      ssize_t nread;
      ssize_t nwrite;
      char *inp = buffer;
      wchar_t outbuf[BUFSIZ];
      wchar_t *outp = outbuf;

      /* Fill up the buffer from the input file.  */
      nread = read (input, buffer + filled, BUFSIZ);
      if (nread < 0)
        {
          perror ("read");
          return 0;
        }
      /* If we reach end of file, make a note to read no more. */
      if (nread == 0)
        eof = 1;

      /* filled is now the number of bytes in buffer. */
      filled += nread;

      /* Convert those bytes to wide characters–as many as we can. */
      while (1)
        {
          size_t thislen = mbrtowc (outp, inp, filled, &state);
          /* Stop converting at invalid character;
             this can mean we have read just the first part
             of a valid character.  */
          if (thislen == (size_t) -1)
            break;
          /* We want to handle embedded NUL bytes
             but the return value is 0.  Correct this.  */
          if (thislen == 0)
            thislen = 1;
          /* Advance past this character. */
          inp += thislen;
          filled -= thislen;
          ++outp;
        }

      /* Write the wide characters we just made.  */
      nwrite = write (output, outbuf,
                      (outp - outbuf) * sizeof (wchar_t));
      if (nwrite < 0)
        {
          perror ("write");
          return 0;
        }

      /* See if we have a real invalid character. */
      if ((eof && filled > 0) || filled >= MB_CUR_MAX)
        {
          error (0, 0, "invalid multibyte character");
          return 0;
        }

      /* If any characters must be carried forward,
         put them at the beginning of buffer. */
      if (filled > 0)
        memmove (buffer, inp, filled);
    }

  return 1;
}