comparison src/coding.c @ 36647:0a75ccbe42b2

(detect_coding_sjis): Do more rigid check. (detect_coding_big5): Likewise. (decode_coding_sjis_big5): Likewise. (Fdetect_coding_region): Call detect_coding_system with tailing anchor byte `\0' for more rigid detection. (Fdetect_coding_string): Likewise.

36646:5c9e147d55d8

   so that it fits in the range below.

   --- CODE RANGE of SJIS ---
   (character set)	(range)
   ASCII		0x00 .. 0x7F
   KATAKANA-JISX0201	0xA0 .. 0xDF
   JISX0208 (1st byte)	0x81 .. 0x9F and 0xE0 .. 0xEF
	    (2nd byte)	0x40 .. 0x7E and 0x80 .. 0xFC
   -------------------------------

*/

  struct coding_system *coding = &dummy_coding;

  while (1)
    {
      ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep);
      if (c >= 0x81)
	{
	  if (c <= 0x9F || (c >= 0xE0 && c <= 0xEF))
	    {
	      ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep);
	      if (c < 0x40 || c == 0x7F || c > 0xFC)
		return 0;
	    }
	  else if (c > 0xDF)
	    return 0;
	}
    }
 label_end_of_loop:
  return CODING_CATEGORY_MASK_SJIS;

  struct coding_system *coding = &dummy_coding;

  while (1)
    {
      ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep);
      if (c >= 0xA1)
	{
	  ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep);
	  if (c < 0x40 || (c >= 0x7F && c <= 0xA0))
	    return 0;
	}
    }
 label_end_of_loop:
  return CODING_CATEGORY_MASK_BIG5;
}

	}
      else
        {
	  if (sjis_p)
	    {
	      if (c1 >= 0xF0)
		goto label_invalid_code;
	      if (c1 < 0xA0 || c1 >= 0xE0)
		{
		  /* SJIS -> JISX0208 */
		  ONE_MORE_BYTE (c2);
		  if (c2 < 0x40 || c2 == 0x7F || c2 > 0xFC)
		    goto label_invalid_code;

		charset = charset_katakana_jisx0201;
	    }
	  else
	    {
	      /* BIG5 -> Big5 */
	      if (c1 < 0xA1 || c1 > 0xFE)
		goto label_invalid_code;
	      ONE_MORE_BYTE (c2);
	      if (c2 < 0x40 || (c2 > 0x7E && c2 < 0xA1) || c2 > 0xFE)
		goto label_invalid_code;
	      DECODE_BIG5 (c1, c2, charset, c1, c2);

  (start, end, highest)
     Lisp_Object start, end, highest;
{
  int from, to;
  int from_byte, to_byte;

  CHECK_NUMBER_COERCE_MARKER (start, 0);
  CHECK_NUMBER_COERCE_MARKER (end, 1);

  validate_region (&start, &end);

  from_byte = CHAR_TO_BYTE (from);
  to_byte = CHAR_TO_BYTE (to);

  if (from < GPT && to >= GPT)
    move_gap_both (to, to_byte);

  return detect_coding_system (BYTE_POS_ADDR (from_byte),
			       to_byte - from_byte,
			       !NILP (highest),
			       !NILP (current_buffer
				      ->enable_multibyte_characters));
}

     Lisp_Object string, highest;
{
  CHECK_STRING (string, 0);

  return detect_coding_system (XSTRING (string)->data,
			       STRING_BYTES (XSTRING (string)),
			       !NILP (highest),
			       STRING_MULTIBYTE (string));
}

/* Return an intersection of lists L1 and L2.  */

36647:0a75ccbe42b2

   so that it fits in the range below.

   --- CODE RANGE of SJIS ---
   (character set)	(range)
   ASCII		0x00 .. 0x7F
   KATAKANA-JISX0201	0xA1 .. 0xDF
   JISX0208 (1st byte)	0x81 .. 0x9F and 0xE0 .. 0xEF
	    (2nd byte)	0x40 .. 0x7E and 0x80 .. 0xFC
   -------------------------------

*/

  struct coding_system *coding = &dummy_coding;

  while (1)
    {
      ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep);
      if (c < 0x80)
	continue;
      if (c == 0x80 || c == 0xA0 || c > 0xEF)
	return 0;
      if (c <= 0x9F || c >= 0xE0)
	{
	  ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep);
	  if (c < 0x40 || c == 0x7F || c > 0xFC)
	    return 0;
	}
    }
 label_end_of_loop:
  return CODING_CATEGORY_MASK_SJIS;

  struct coding_system *coding = &dummy_coding;

  while (1)
    {
      ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep);
      if (c < 0x80)
	continue;
      if (c < 0xA1 || c > 0xFE)
	return 0;
      ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep);
      if (c < 0x40 || (c > 0x7F && c < 0xA1) || c > 0xFE)
	return 0;
    }
 label_end_of_loop:
  return CODING_CATEGORY_MASK_BIG5;
}

	}
      else
        {
	  if (sjis_p)
	    {
	      if (c1 == 0x80 || c1 == 0xA0 || c1 > 0xEF)
		goto label_invalid_code;
	      if (c1 <= 0x9F || c1 >= 0xE0)
		{
		  /* SJIS -> JISX0208 */
		  ONE_MORE_BYTE (c2);
		  if (c2 < 0x40 || c2 == 0x7F || c2 > 0xFC)
		    goto label_invalid_code;

		charset = charset_katakana_jisx0201;
	    }
	  else
	    {
	      /* BIG5 -> Big5 */
	      if (c1 < 0xA0 || c1 > 0xFE)
		goto label_invalid_code;
	      ONE_MORE_BYTE (c2);
	      if (c2 < 0x40 || (c2 > 0x7E && c2 < 0xA1) || c2 > 0xFE)
		goto label_invalid_code;
	      DECODE_BIG5 (c1, c2, charset, c1, c2);

  (start, end, highest)
     Lisp_Object start, end, highest;
{
  int from, to;
  int from_byte, to_byte;
  int include_anchor_byte = 0;

  CHECK_NUMBER_COERCE_MARKER (start, 0);
  CHECK_NUMBER_COERCE_MARKER (end, 1);

  validate_region (&start, &end);

  from_byte = CHAR_TO_BYTE (from);
  to_byte = CHAR_TO_BYTE (to);

  if (from < GPT && to >= GPT)
    move_gap_both (to, to_byte);
  if (to == Z || (to == GPT && GAP_SIZE > 0))
    include_anchor_byte = 1;
  return detect_coding_system (BYTE_POS_ADDR (from_byte),
			       /* "+ include_anchor_byteq" is to
				  include the anchor byte `\0'.  With
				  this, code detectors can check if
				  tailing bytes are valid.  */
			       to_byte - from_byte + include_anchor_byte,
			       !NILP (highest),
			       !NILP (current_buffer
				      ->enable_multibyte_characters));
}

     Lisp_Object string, highest;
{
  CHECK_STRING (string, 0);

  return detect_coding_system (XSTRING (string)->data,
			       /* "+ 1" is to include the anchor byte
				  `\0'.  With this, code detectors can
				  check if tailing bytes are
				  valid.  */
			       STRING_BYTES (XSTRING (string)) + 1,
			       !NILP (highest),
			       STRING_MULTIBYTE (string));
}

/* Return an intersection of lists L1 and L2.  */