comparison src/coding.c @ 83541:694bbb62a75d

Merged from [e-mail] Patches applied: * [e-mail]/emacs--devo--0--patch-371 Update from CVS * [e-mail]/emacs--devo--0--patch-372 Update from CVS * [e-mail]/emacs--devo--0--patch-373 Update from CVS * [e-mail]/emacs--devo--0--patch-374 Update from CVS * [e-mail]/emacs--devo--0--patch-375 Merge from gnus--rel--5.10 * [e-mail]/emacs--devo--0--patch-376 Update from CVS * [e-mail]/emacs--devo--0--patch-377 Update from CVS * [e-mail]/emacs--devo--0--patch-378 Update from CVS * [e-mail]/emacs--devo--0--patch-379 Merge from erc--emacs--21 * [e-mail]/emacs--devo--0--patch-380 Update from CVS * [e-mail]/emacs--devo--0--patch-381 Update from CVS * [e-mail]/emacs--devo--0--patch-382 Update from CVS * [e-mail]/emacs--devo--0--patch-383 Update from CVS * [e-mail]/emacs--devo--0--patch-384 Update from CVS * [e-mail]/emacs--devo--0--patch-385 Update from CVS * [e-mail]/emacs--devo--0--patch-386 Update from erc--emacs--22 * [e-mail]/emacs--devo--0--patch-387 Fix ERC bug introduced in last patch * [e-mail]/emacs--devo--0--patch-388 Update from erc--emacs--22 * [e-mail]/emacs--devo--0--patch-389 Update from CVS * [e-mail]/emacs--devo--0--patch-390 Update from CVS * [e-mail]/emacs--devo--0--patch-391 Update from CVS * [e-mail]/emacs--devo--0--patch-392 Update from CVS * [e-mail]/emacs--devo--0--patch-393 Update from CVS * [e-mail]/emacs--devo--0--patch-394 Update from CVS * [e-mail]/emacs--devo--0--patch-395 Update from CVS * [e-mail]/emacs--devo--0--patch-396 Update from CVS * [e-mail]/emacs--devo--0--patch-397 Update from CVS * [e-mail]/emacs--devo--0--patch-398 Merge from gnus--rel--5.10 * [e-mail]/emacs--devo--0--patch-399 Update from CVS * [e-mail]/emacs--devo--0--patch-400 Update from CVS * [e-mail]/emacs--devo--0--patch-401 Update from CVS * [e-mail]/emacs--devo--0--patch-402 Update from CVS * [e-mail]/emacs--devo--0--patch-403 Rcirc update from Ryan Yeske * [e-mail]/emacs--devo--0--patch-404 Update from CVS * [e-mail]/emacs--devo--0--patch-405 Update from CVS * [e-mail]/emacs--devo--0--patch-406 Update from CVS * [e-mail]/emacs--devo--0--patch-407 Update from CVS * [e-mail]/emacs--devo--0--patch-408 Update from CVS * [e-mail]/emacs--devo--0--patch-409 Update from CVS * [e-mail]/emacs--devo--0--patch-410 Merge from gnus--rel--5.10 * [e-mail]/emacs--devo--0--patch-411 Miscellaneous tq-related fixes. * [e-mail]/emacs--devo--0--patch-412 Update from CVS * [e-mail]/gnus--rel--5.10--patch-121 Update from CVS * [e-mail]/gnus--rel--5.10--patch-122 Update from CVS * [e-mail]/gnus--rel--5.10--patch-123 Update from CVS * [e-mail]/gnus--rel--5.10--patch-124 Update from CVS * [e-mail]/gnus--rel--5.10--patch-125 Update from CVS * [e-mail]/gnus--rel--5.10--patch-126 Merge from emacs--devo--0 * [e-mail]/gnus--rel--5.10--patch-127 Update from CVS git-archimport-id: [e-mail]--2004/emacs--multi-tty--0--patch-581

83540:0c89a85addc3

    c2 = *src++;						\
  } while (0)


/* Like ONE_MORE_BYTE, but 8-bit bytes of data at SRC are in multibyte
   form if MULTIBYTEP is nonzero.  */

#define ONE_MORE_BYTE_CHECK_MULTIBYTE(c1, multibytep)		\
  do {								\
    if (src >= src_end)						\
      {								\
	coding->result = CODING_FINISH_INSUFFICIENT_SRC;	\
	goto label_end_of_loop;					\
      }								\
    c1 = *src++;						\
    if (multibytep && c1 == LEADING_CODE_8_BIT_CONTROL)		\
      c1 = *src++ - 0x20;					\
  } while (0)

  struct coding_system dummy_coding;
  struct coding_system *coding = &dummy_coding;

  while (1)
    {
      ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep);

      if (composing)
	{
	  if (c < 0xA0)
	    composing = 0;
	  else if (c == 0xA0)
	    {
	      ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep);
	      c &= 0x7F;
	    }
	  else
	    c -= 0x20;
	}

		return 0;
	      src = src_base + bytes;
	    }
	}
    }
 label_end_of_loop:
  return CODING_CATEGORY_MASK_EMACS_MULE;
}


/* Record the starting position START and METHOD of one composition.  */

  struct coding_system dummy_coding;
  struct coding_system *coding = &dummy_coding;
  Lisp_Object safe_chars;

  reg[0] = CHARSET_ASCII, reg[1] = reg[2] = reg[3] = -1;
  while (mask && src < src_end)
    {
      ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep);
    retry:
      switch (c)
	{
	case ISO_CODE_ESC:
	  if (inhibit_iso_escape_detection)
	    break;
	  single_shifting = 0;
	  ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep);
	  if (c >= '(' && c <= '/')
	    {
	      /* Designation sequence for a charset of dimension 1.  */
	      ONE_MORE_BYTE_CHECK_MULTIBYTE (c1, multibytep);
	      if (c1 < ' ' || c1 >= 0x80
		  || (charset = iso_charset_table[0][c >= ','][c1]) < 0)
		/* Invalid designation sequence.  Just ignore.  */
		break;
	      reg[(c - '(') % 4] = charset;
	    }
	  else if (c == '$')
	    {
	      /* Designation sequence for a charset of dimension 2.  */
	      ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep);
	      if (c >= '@' && c <= 'B')
		/* Designation for JISX0208.1978, GB2312, or JISX0208.  */
		reg[0] = charset = iso_charset_table[1][0][c];
	      else if (c >= '(' && c <= '/')
		{
		  ONE_MORE_BYTE_CHECK_MULTIBYTE (c1, multibytep);
		  if (c1 < ' ' || c1 >= 0x80
		      || (charset = iso_charset_table[1][c >= ','][c1]) < 0)
		    /* Invalid designation sequence.  Just ignore.  */
		    break;
		  reg[(c - '(') % 4] = charset;

		  int i = 1;

		  c = -1;
		  while (src < src_end)
		    {
		      ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep);
		      if (c < 0xA0)
			break;
		      i++;
		    }

		}
	    }
	  break;
	}
    }
 label_end_of_loop:
  return (mask & mask_found);
}

/* Decode a character of which charset is CHARSET, the 1st position
   code is C1, the 2nd position code is C2, and return the decoded

  struct coding_system dummy_coding;
  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;
}

/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
   Check if a text is encoded in BIG5.  If it is, return
   CODING_CATEGORY_MASK_BIG5, else return 0.  */

  struct coding_system dummy_coding;
  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;
}

/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
   Check if a text is encoded in UTF-8.  If it is, return
   CODING_CATEGORY_MASK_UTF_8, else return 0.  */

  struct coding_system dummy_coding;
  struct coding_system *coding = &dummy_coding;

  while (1)
    {
      ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep);
      if (UTF_8_1_OCTET_P (c))
	continue;
      else if (UTF_8_2_OCTET_LEADING_P (c))
	seq_maybe_bytes = 1;
      else if (UTF_8_3_OCTET_LEADING_P (c))

      else
	return 0;

      do
	{
	  ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep);
	  if (!UTF_8_EXTRA_OCTET_P (c))
	    return 0;
	  seq_maybe_bytes--;
	}
      while (seq_maybe_bytes > 0);
    }

 label_end_of_loop:
  return CODING_CATEGORY_MASK_UTF_8;
}

/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
   Check if a text is encoded in UTF-16 Big Endian (endian == 1) or
   Little Endian (otherwise).  If it is, return

  unsigned char c1, c2;
  /* Dummy for ONE_MORE_BYTE_CHECK_MULTIBYTE.  */
  struct coding_system dummy_coding;
  struct coding_system *coding = &dummy_coding;

  ONE_MORE_BYTE_CHECK_MULTIBYTE (c1, multibytep);
  ONE_MORE_BYTE_CHECK_MULTIBYTE (c2, multibytep);

  if ((c1 == 0xFF) && (c2 == 0xFE))
    return CODING_CATEGORY_MASK_UTF_16_LE;
  else if ((c1 == 0xFE) && (c2 == 0xFF))
    return CODING_CATEGORY_MASK_UTF_16_BE;

 label_end_of_loop:
  return 0;
}

/* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions".
   If SJIS_P is 1, decode SJIS text, else decode BIG5 test.  */

    return 0;

  valid = coding_system_table[CODING_CATEGORY_IDX_CCL]->spec.ccl.valid_codes;
  while (1)
    {
      ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep);
      if (! valid[c])
	return 0;
    }
 label_end_of_loop:
  return CODING_CATEGORY_MASK_CCL;
}


/*** 6. End-of-line handlers ***/

	    return Qnil;
	  if (! NILP (Fcoding_system_p (val)))
	    return Fcons (val, val);
	  if (! NILP (Ffboundp (val)))
	    {
	      val = safe_call1 (val, Flist (nargs, args));
	      if (CONSP (val))
		return val;
	      if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val)))
		return Fcons (val, val);
	    }

If VAL is a coding system, it is used for both decoding and encoding
the file contents.
If VAL is a cons of coding systems, the car part is used for decoding,
and the cdr part is used for encoding.
If VAL is a function symbol, the function must return a coding system
or a cons of coding systems which are used as above.  The function gets
the arguments with which `find-operation-coding-system' was called.

See also the function `find-operation-coding-system'
and the variable `auto-coding-alist'.  */);
  Vfile_coding_system_alist = Qnil;

83541:694bbb62a75d

    c2 = *src++;						\
  } while (0)


/* Like ONE_MORE_BYTE, but 8-bit bytes of data at SRC are in multibyte
   form if MULTIBYTEP is nonzero.  In addition, if SRC is not less
   than SRC_END, return with RET.  */

#define ONE_MORE_BYTE_CHECK_MULTIBYTE(c1, multibytep, ret)	\
  do {								\
    if (src >= src_end)						\
      {								\
	coding->result = CODING_FINISH_INSUFFICIENT_SRC;	\
	return ret;						\
      }								\
    c1 = *src++;						\
    if (multibytep && c1 == LEADING_CODE_8_BIT_CONTROL)		\
      c1 = *src++ - 0x20;					\
  } while (0)

  struct coding_system dummy_coding;
  struct coding_system *coding = &dummy_coding;

  while (1)
    {
      ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep,
				     CODING_CATEGORY_MASK_EMACS_MULE);
      if (composing)
	{
	  if (c < 0xA0)
	    composing = 0;
	  else if (c == 0xA0)
	    {
	      ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep, 0);
	      c &= 0x7F;
	    }
	  else
	    c -= 0x20;
	}

		return 0;
	      src = src_base + bytes;
	    }
	}
    }
}


/* Record the starting position START and METHOD of one composition.  */

  struct coding_system dummy_coding;
  struct coding_system *coding = &dummy_coding;
  Lisp_Object safe_chars;

  reg[0] = CHARSET_ASCII, reg[1] = reg[2] = reg[3] = -1;
  while (mask)
    {
      ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep, mask & mask_found);
    retry:
      switch (c)
	{
	case ISO_CODE_ESC:
	  if (inhibit_iso_escape_detection)
	    break;
	  single_shifting = 0;
	  ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep, mask & mask_found);
	  if (c >= '(' && c <= '/')
	    {
	      /* Designation sequence for a charset of dimension 1.  */
	      ONE_MORE_BYTE_CHECK_MULTIBYTE (c1, multibytep, mask & mask_found);
	      if (c1 < ' ' || c1 >= 0x80
		  || (charset = iso_charset_table[0][c >= ','][c1]) < 0)
		/* Invalid designation sequence.  Just ignore.  */
		break;
	      reg[(c - '(') % 4] = charset;
	    }
	  else if (c == '$')
	    {
	      /* Designation sequence for a charset of dimension 2.  */
	      ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep, mask & mask_found);
	      if (c >= '@' && c <= 'B')
		/* Designation for JISX0208.1978, GB2312, or JISX0208.  */
		reg[0] = charset = iso_charset_table[1][0][c];
	      else if (c >= '(' && c <= '/')
		{
		  ONE_MORE_BYTE_CHECK_MULTIBYTE (c1, multibytep,
						 mask & mask_found);
		  if (c1 < ' ' || c1 >= 0x80
		      || (charset = iso_charset_table[1][c >= ','][c1]) < 0)
		    /* Invalid designation sequence.  Just ignore.  */
		    break;
		  reg[(c - '(') % 4] = charset;

		  int i = 1;

		  c = -1;
		  while (src < src_end)
		    {
		      ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep,
						     mask & mask_found);
		      if (c < 0xA0)
			break;
		      i++;
		    }

		}
	    }
	  break;
	}
    }
  return (mask & mask_found);
}

/* Decode a character of which charset is CHARSET, the 1st position
   code is C1, the 2nd position code is C2, and return the decoded

  struct coding_system dummy_coding;
  struct coding_system *coding = &dummy_coding;

  while (1)
    {
      ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep, CODING_CATEGORY_MASK_SJIS);
      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, 0);
	  if (c < 0x40 || c == 0x7F || c > 0xFC)
	    return 0;
	}
    }
}

/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
   Check if a text is encoded in BIG5.  If it is, return
   CODING_CATEGORY_MASK_BIG5, else return 0.  */

  struct coding_system dummy_coding;
  struct coding_system *coding = &dummy_coding;

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

/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
   Check if a text is encoded in UTF-8.  If it is, return
   CODING_CATEGORY_MASK_UTF_8, else return 0.  */

  struct coding_system dummy_coding;
  struct coding_system *coding = &dummy_coding;

  while (1)
    {
      ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep, CODING_CATEGORY_MASK_UTF_8);
      if (UTF_8_1_OCTET_P (c))
	continue;
      else if (UTF_8_2_OCTET_LEADING_P (c))
	seq_maybe_bytes = 1;
      else if (UTF_8_3_OCTET_LEADING_P (c))

      else
	return 0;

      do
	{
	  ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep, 0);
	  if (!UTF_8_EXTRA_OCTET_P (c))
	    return 0;
	  seq_maybe_bytes--;
	}
      while (seq_maybe_bytes > 0);
    }
}

/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
   Check if a text is encoded in UTF-16 Big Endian (endian == 1) or
   Little Endian (otherwise).  If it is, return

  unsigned char c1, c2;
  /* Dummy for ONE_MORE_BYTE_CHECK_MULTIBYTE.  */
  struct coding_system dummy_coding;
  struct coding_system *coding = &dummy_coding;

  ONE_MORE_BYTE_CHECK_MULTIBYTE (c1, multibytep, 0);
  ONE_MORE_BYTE_CHECK_MULTIBYTE (c2, multibytep, 0);

  if ((c1 == 0xFF) && (c2 == 0xFE))
    return CODING_CATEGORY_MASK_UTF_16_LE;
  else if ((c1 == 0xFE) && (c2 == 0xFF))
    return CODING_CATEGORY_MASK_UTF_16_BE;
  return 0;
}

/* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions".
   If SJIS_P is 1, decode SJIS text, else decode BIG5 test.  */

    return 0;

  valid = coding_system_table[CODING_CATEGORY_IDX_CCL]->spec.ccl.valid_codes;
  while (1)
    {
      ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep, CODING_CATEGORY_MASK_CCL);
      if (! valid[c])
	return 0;
    }
}


/*** 6. End-of-line handlers ***/

	    return Qnil;
	  if (! NILP (Fcoding_system_p (val)))
	    return Fcons (val, val);
	  if (! NILP (Ffboundp (val)))
	    {
	      /* We use call1 rather than safe_call1
		 so as to get bug reports about functions called here
		 which don't handle the current interface.  */
	      val = call1 (val, Flist (nargs, args));
	      if (CONSP (val))
		return val;
	      if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val)))
		return Fcons (val, val);
	    }

If VAL is a coding system, it is used for both decoding and encoding
the file contents.
If VAL is a cons of coding systems, the car part is used for decoding,
and the cdr part is used for encoding.
If VAL is a function symbol, the function must return a coding system
or a cons of coding systems which are used as above.  The function is
called with an argument that is a list of the arguments with which
`find-operation-coding-system' was called.

See also the function `find-operation-coding-system'
and the variable `auto-coding-alist'.  */);
  Vfile_coding_system_alist = Qnil;