[bpt/emacs.git] / src / character.h

/* Header for multibyte character handler.
   Copyright (C) 1995, 1997, 1998 Electrotechnical Laboratory, JAPAN.
   Licensed to the Free Software Foundation.
   Copyright (C) 2001, 2002
     National Institute of Advanced Industrial Science and Technology (AIST)
     Registration Number H13PRO009

This file is part of GNU Emacs.

GNU Emacs is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.

GNU Emacs is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU General Public License for more details.

You should have received a copy of the GNU General Public License
along with GNU Emacs; see the file COPYING.  If not, write to
the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
Boston, MA 02111-1307, USA.  */

#ifndef EMACS_CHARACTER_H
#define EMACS_CHARACTER_H

/* character code	1st byte   byte sequence
   --------------	--------   -------------
        0-7F		00..7F	   0xxxxxxx
       80-7FF		C2..DF	   110xxxxx 10xxxxxx
      800-FFFF		E0..EF	   1110xxxx 10xxxxxx 10xxxxxx
    10000-1FFFFF	F0..F7	   11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
   200000-3FFF7F	F8	   11111000 1000xxxx 10xxxxxx 10xxxxxx 10xxxxxx
      invalid		F9..FF

   raw-8-bit
   3FFF80-3FFFFF	C0..C1	   1100000x 10xxxxxx
*/

/* Maximum character code ((1 << CHARACTERBITS) - 1).  */
#define MAX_CHAR  0x3FFFFF

/* Maximum Unicode character code.  */
#define MAX_UNICODE_CHAR 0x10FFFF

/* Maximum N-byte character codes.  */
#define MAX_1_BYTE_CHAR 0x7F
#define MAX_2_BYTE_CHAR 0x7FF
#define MAX_3_BYTE_CHAR 0xFFFF
#define MAX_4_BYTE_CHAR 0x1FFFFF
#define MAX_5_BYTE_CHAR 0x3FFF7F

/* Return the character code for raw 8-bit byte BYTE.  */
#define BYTE8_TO_CHAR(byte) ((byte) + 0x3FFF00)

/* Return the raw 8-bit byte for character C.  */
#define CHAR_TO_BYTE8(c) ((c) - 0x3FFF00)

/* Nonzero iff C is a character that corresponds to a raw 8-bit
   byte.  */
#define CHAR_BYTE8_P(c) ((c) > MAX_5_BYTE_CHAR)

/* Nonzero iff BYTE is the 1st byte of a multibyte form of a character
   that corresponds to a raw 8-bit byte.  */
#define CHAR_BYTE8_HEAD_P(byte) ((byte) == 0xC0 || (byte) == 0xC1)

/* This is the maximum byte length of multibyte form.  */
#define MAX_MULTIBYTE_LENGTH 5

/* Return a Lisp character whose character code is C. */
#define make_char(c) make_number (c)

/* Nonzero iff C is an ASCII byte.  */
#define ASCII_BYTE_P(c) ((unsigned) (c) < 0x80)

/* Nonzero iff X is a character.  */
#define CHARACTERP(x) (NATNUMP (x) && XFASTINT (x) <= MAX_CHAR)

/* Nonzero iff C is valid as a character code.  GENERICP is not used
   now.  */
#define CHAR_VALID_P(c, genericp) ((unsigned) (c) <= MAX_CHAR)

/* Check if Lisp object X is a character or not.  */
#define CHECK_CHARACTER(x)						\
  do {									\
    if (! CHARACTERP(x)) x = wrong_type_argument (Qcharacterp, (x));	\
  } while (0)

/* Nonzero iff C is an ASCII character.  */
#define ASCII_CHAR_P(c) ((unsigned) (c) < 0x80)

/* Nonzero iff C is a character of code less than 0x100.  */
#define SINGLE_BYTE_CHAR_P(c) ((unsigned) (c) < 0x100)

/* Nonzero if character C has a printable glyph.  */
#define CHAR_PRINTABLE_P(c)	\
  (((c) >= 32 && ((c) < 127)	\
    || ! NILP (CHAR_TABLE_REF (Vprintable_chars, (c)))))

/* Return byte length of multibyte form for character C.  */
#define CHAR_BYTES(c)			\
  ( (c) <= MAX_1_BYTE_CHAR ? 1		\
    : (c) <= MAX_2_BYTE_CHAR ? 2	\
    : (c) <= MAX_3_BYTE_CHAR ? 3	\
    : (c) <= MAX_4_BYTE_CHAR ? 4	\
    : (c) <= MAX_5_BYTE_CHAR ? 5	\
    : 2)

/* Store multibyte form of the character C in P.  The caller should
   allocate at least MAX_MULTIBYTE_LENGTH bytes area at P in advance.
   Returns the length of the multibyte form.  */

#define CHAR_STRING(c, p)			\
  ((unsigned) (c) <= MAX_1_BYTE_CHAR		\
   ? ((p)[0] = (c),				\
      1)					\
   : (unsigned) (c) <= MAX_2_BYTE_CHAR		\
   ? ((p)[0] = (0xC0 | ((c) >> 6)),		\
      (p)[1] = (0x80 | ((c) & 0x3F)),		\
      2)					\
   : (unsigned) (c) <= MAX_3_BYTE_CHAR		\
   ? ((p)[0] = (0xE0 | ((c) >> 12)),		\
      (p)[1] = (0x80 | (((c) >> 6) & 0x3F)),	\
      (p)[2] = (0x80 | ((c) & 0x3F)),		\
      3)					\
   : (unsigned) (c) <= MAX_5_BYTE_CHAR		\
   ? char_string_with_unification (c, p)	\
   : ((p)[0] = (0xC0 | (((c) >> 6) & 0x01)),	\
      (p)[1] = (0x80 | ((c) & 0x3F)),		\
      2))


/* Store multibyte form of the character C in P.  The caller should
   allocate at least MAX_MULTIBYTE_LENGTH bytes area at P in advance.
   And, advance P to the end of the multibyte form.  */

#define CHAR_STRING_ADVANCE(c, p)			\
  do {							\
    if ((c) <= MAX_1_BYTE_CHAR)				\
      *(p)++ = (c);					\
    else if ((c) <= MAX_2_BYTE_CHAR)			\
      *(p)++ = (0xC0 | ((c) >> 6)),			\
	*(p)++ = (0x80 | ((c) & 0x3F));			\
    else if ((c) <= MAX_3_BYTE_CHAR)			\
      *(p)++ = (0xE0 | ((c) >> 12)),			\
	*(p)++ = (0x80 | (((c) >> 6) & 0x3F)),		\
	*(p)++ = (0x80 | ((c) & 0x3F));			\
    else if ((c) <= MAX_5_BYTE_CHAR)			\
      (p) += char_string_with_unification ((c), (p));	\
    else						\
      *(p)++ = (0xC0 | (((c) >> 6) & 0x01)),		\
	*(p)++ = (0x80 | ((c) & 0x3F));			\
  } while (0)

/* Nonzero iff BYTE starts a non-ASCII character in a multibyte
   form.  */
#define LEADING_CODE_P(byte) (((byte) & 0xC0) == 0xC0)

/* Nonzero iff BYTE is a trailing code of a non-ASCII character in a
   multibyte form.  */
#define TRAILING_CODE_P(byte) (((byte) & 0xC0) == 0x80)

/* Nonzero iff BYTE starts a character in a multibyte form.
   This is equivalent to:
	(ASCII_BYTE_P (byte) || LEADING_CODE_P (byte))  */
#define CHAR_HEAD_P(byte) (((byte) & 0xC0) != 0x80)

/* Just kept for backward compatibility.  This macro will be removed
   in the future.  */
#define BASE_LEADING_CODE_P LEADING_CODE_P

/* How many bytes a character that starts with BYTE occupies in a
   multibyte form.  */
#define BYTES_BY_CHAR_HEAD(byte)	\
  (!((byte) & 0x80) ? 1			\
   : !((byte) & 0x20) ? 2		\
   : !((byte) & 0x10) ? 3		\
   : !((byte) & 0x08) ? 4		\
   : 5)


/* Return the length of the multi-byte form at string STR of length
   LEN while assuming that STR points a valid multi-byte form.  As
   this macro isn't necessary anymore, all callers will be changed to
   use BYTES_BY_CHAR_HEAD directly in the future.  */

#define MULTIBYTE_FORM_LENGTH(str, len)		\
  BYTES_BY_CHAR_HEAD (*(str))

/* Parse multibyte string STR of length LENGTH and set BYTES to the
   byte length of a character at STR while assuming that STR points a
   valid multibyte form.  As this macro isn't necessary anymore, all
   callers will be changed to use BYTES_BY_CHAR_HEAD directly in the
   future.  */

#define PARSE_MULTIBYTE_SEQ(str, length, bytes)	\
  (bytes) = BYTES_BY_CHAR_HEAD (*(str))

/* The byte length of multibyte form at unibyte string P ending at
   PEND.  If STR doesn't point a valid multibyte form, return 0.  */

#define MULTIBYTE_LENGTH(p, pend)				\
  (p >= pend ? 0						\
   : !((p)[0] & 0x80) ? 1					\
   : ((p + 1 >= pend) || (((p)[1] & 0xC0) != 0x80)) ? 0		\
   : ((p)[0] & 0xE0) == 0xC0 ? 2				\
   : ((p + 2 >= pend) || (((p)[2] & 0xC0) != 0x80)) ? 0		\
   : ((p)[0] & 0xF0) == 0xE0 ? 3				\
   : ((p + 3 >= pend) || (((p)[3] & 0xC0) != 0x80)) ? 0		\
   : ((p)[0] & 0xF8) == 0xF0 ? 4				\
   : ((p + 4 >= pend) || (((p)[4] & 0xC0) != 0x80)) ? 0		\
   : (p)[0] == 0xF8 && ((p)[1] & 0xF0) == 0x80 ? 5		\
   : 0)


/* Like MULTIBYTE_LENGTH but don't check the ending address.  */

#define MULTIBYTE_LENGTH_NO_CHECK(p)			\
  (!((p)[0] & 0x80) ? 1					\
   : ((p)[1] & 0xC0) != 0x80 ? 0			\
   : ((p)[0] & 0xE0) == 0xC0 ? 2			\
   : ((p)[2] & 0xC0) != 0x80 ? 0			\
   : ((p)[0] & 0xF0) == 0xE0 ? 3			\
   : ((p)[3] & 0xC0) != 0x80 ? 0			\
   : ((p)[0] & 0xF8) == 0xF0 ? 4			\
   : ((p)[4] & 0xC0) != 0x80 ? 0			\
   : (p)[0] == 0xF8 && ((p)[1] & 0xF0) == 0x80 ? 5	\
   : 0)


/* Return the character code of character whose multibyte form is at
   P.  The argument LEN is ignored.  It will be removed in the
   future.  */

#define STRING_CHAR(p, len)					\
  (!((p)[0] & 0x80)						\
   ? (p)[0]							\
   : ! ((p)[0] & 0x20)						\
   ? (((((p)[0] & 0x1F) << 6)					\
       | ((p)[1] & 0x3F))					\
      + (((unsigned char) (p)[0]) < 0xC2 ? 0x3FFF80 : 0))	\
   : ! ((p)[0] & 0x10)						\
   ? ((((p)[0] & 0x0F) << 12)					\
      | (((p)[1] & 0x3F) << 6)					\
      | ((p)[2] & 0x3F))					\
   : string_char_with_unification ((p), NULL, NULL))


/* Like STRING_CHAR but set ACTUAL_LEN to the length of multibyte
   form.  The argument LEN is ignored.  It will be removed in the
   future.  */

#define STRING_CHAR_AND_LENGTH(p, len, actual_len)		\
  (!((p)[0] & 0x80)						\
   ? ((actual_len) = 1, (p)[0])					\
   : ! ((p)[0] & 0x20)						\
   ? ((actual_len) = 2,						\
      (((((p)[0] & 0x1F) << 6)					\
	| ((p)[1] & 0x3F))					\
       + (((unsigned char) (p)[0]) < 0xC2 ? 0x3FFF80 : 0)))	\
   : ! ((p)[0] & 0x10)						\
   ? ((actual_len) = 3,						\
      ((((p)[0] & 0x0F) << 12)					\
       | (((p)[1] & 0x3F) << 6)					\
       | ((p)[2] & 0x3F)))					\
   : string_char_with_unification ((p), NULL, &actual_len))


/* Like STRING_CHAR but advacen P to the end of multibyte form.  */

#define STRING_CHAR_ADVANCE(p)					\
  (!((p)[0] & 0x80)						\
   ? *(p)++							\
   : ! ((p)[0] & 0x20)						\
   ? ((p) += 2,							\
      ((((p)[-2] & 0x1F) << 6)					\
       | ((p)[-1] & 0x3F)					\
       | (((unsigned char) (p)[-2]) < 0xC2 ? 0x3FFF80 : 0)))	\
   : ! ((p)[0] & 0x10)						\
   ? ((p) += 3,							\
      ((((p)[-3] & 0x0F) << 12)					\
       | (((p)[-2] & 0x3F) << 6)				\
       | ((p)[-1] & 0x3F)))					\
   : string_char_with_unification ((p), &(p), NULL))


/* Fetch the "next" character from Lisp string STRING at byte position
   BYTEIDX, character position CHARIDX.  Store it into OUTPUT.

   All the args must be side-effect-free.
   BYTEIDX and CHARIDX must be lvalues;
   we increment them past the character fetched.  */

#define FETCH_STRING_CHAR_ADVANCE(OUTPUT, STRING, CHARIDX, BYTEIDX)	\
  if (1)								\
    {									\
      CHARIDX++;							\
      if (STRING_MULTIBYTE (STRING))					\
	{								\
	  unsigned char *ptr = &XSTRING (STRING)->data[BYTEIDX];	\
	  int len;							\
									\
	  OUTPUT = STRING_CHAR_AND_LENGTH (ptr, 0, len);		\
	  BYTEIDX += len;						\
	}								\
      else								\
	OUTPUT = XSTRING (STRING)->data[BYTEIDX++];			\
    }									\
  else


/* Like FETCH_STRING_CHAR_ADVANCE but assumes STRING is multibyte.  */

#define FETCH_STRING_CHAR_ADVANCE_NO_CHECK(OUTPUT, STRING, CHARIDX, BYTEIDX) \
  if (1)								     \
    {									     \
      unsigned char *ptr = &XSTRING (STRING)->data[BYTEIDX];		     \
      int len;								     \
									     \
      OUTPUT = STRING_CHAR_AND_LENGTH (ptr, 0, len);			     \
      BYTEIDX += len;							     \
      CHARIDX++;							     \
    }									     \
  else


/* Like FETCH_STRING_CHAR_ADVANCE but fetch character from the current
   buffer.  */

#define FETCH_CHAR_ADVANCE(OUTPUT, CHARIDX, BYTEIDX)		\
  if (1)							\
    {								\
      CHARIDX++;						\
      if (!NILP (current_buffer->enable_multibyte_characters))	\
	{							\
	  unsigned char *ptr = BYTE_POS_ADDR (BYTEIDX);		\
	  int len;						\
								\
	  OUTPUT= STRING_CHAR_AND_LENGTH (ptr, 0, len);		\
	  BYTEIDX += len;					\
	}							\
      else							\
	{							\
	  OUTPUT = *(BYTE_POS_ADDR (BYTEIDX));			\
	  BYTEIDX++;						\
	}							\
    }								\
  else


/* Like FETCH_CHAR_ADVANCE but assumes STRING is multibyte.  */

#define FETCH_CHAR_ADVANCE_NO_CHECK(OUTPUT, CHARIDX, BYTEIDX)	\
  if (1)							\
    {								\
      unsigned char *ptr = BYTE_POS_ADDR (BYTEIDX);		\
      int len;							\
								\
      OUTPUT= STRING_CHAR_AND_LENGTH (ptr, 0, len);		\
      BYTEIDX += len;						\
      CHARIDX++;						\
    }								\
  else


/* Increase the buffer byte position POS_BYTE of the current buffer to
   the next character boundary.  No range checking of POS.  */

#define INC_POS(pos_byte)				\
  do {							\
    unsigned char *p = BYTE_POS_ADDR (pos_byte);	\
    pos_byte += BYTES_BY_CHAR_HEAD (*p);		\
  } while (0)


/* Decrease the buffer byte position POS_BYTE of the current buffer to
   the previous character boundary.  No range checking of POS.  */

#define DEC_POS(pos_byte)			\
  do {						\
    unsigned char *p;				\
    						\
    pos_byte--;					\
    if (pos_byte < GPT_BYTE)			\
      p = BEG_ADDR + pos_byte - 1;		\
    else					\
      p = BEG_ADDR + GAP_SIZE + pos_byte - 1;	\
    while (!CHAR_HEAD_P (*p))			\
      {						\
	p--;					\
	pos_byte--;				\
      }						\
  } while (0)

/* Increment both CHARPOS and BYTEPOS, each in the appropriate way.  */

#define INC_BOTH(charpos, bytepos)				\
  do								\
    {								\
      (charpos)++;						\
      if (NILP (current_buffer->enable_multibyte_characters))	\
	(bytepos)++;						\
      else							\
	INC_POS ((bytepos));					\
    }								\
  while (0)


/* Decrement both CHARPOS and BYTEPOS, each in the appropriate way.  */

#define DEC_BOTH(charpos, bytepos)				\
  do								\
    {								\
      (charpos)--;						\
      if (NILP (current_buffer->enable_multibyte_characters))	\
	(bytepos)--;						\
      else							\
	DEC_POS ((bytepos));					\
    }								\
  while (0)


/* Increase the buffer byte position POS_BYTE of the current buffer to
   the next character boundary.  This macro relies on the fact that
   *GPT_ADDR and *Z_ADDR are always accessible and the values are
   '\0'.  No range checking of POS_BYTE.  */

#define BUF_INC_POS(buf, pos_byte)				\
  do {								\
    unsigned char *p = BUF_BYTE_ADDRESS (buf, pos_byte);	\
    pos_byte += BYTES_BY_CHAR_HEAD (*p);			\
  } while (0)


/* Decrease the buffer byte position POS_BYTE of the current buffer to
   the previous character boundary.  No range checking of POS_BYTE.  */

#define BUF_DEC_POS(buf, pos_byte)					\
  do {									\
    unsigned char *p;							\
    pos_byte--;								\
    if (pos_byte < BUF_GPT_BYTE (buf))					\
      p = BUF_BEG_ADDR (buf) + pos_byte - 1;				\
    else								\
      p = BUF_BEG_ADDR (buf) + BUF_GAP_SIZE (buf) + pos_byte - 1;	\
    while (!CHAR_HEAD_P (*p))						\
      {									\
	p--;								\
	pos_byte--;							\
      }									\
  } while (0)


#define MAYBE_UNIFY_CHAR(c)					\
  if (CHAR_TABLE_P (Vchar_unify_table))				\
    {								\
      Lisp_Object val;						\
      int unified;						\
								\
      val = CHAR_TABLE_REF (Vchar_unify_table, c);		\
      if (! NILP (val))						\
	{							\
	  if (SYMBOLP (val))					\
	    {							\
	      Funify_charset (val, Qnil, Qnil);			\
	      val = CHAR_TABLE_REF (Vchar_unify_table, c);	\
	    }							\
	  if ((unified = XINT (val)) >= 0)			\
	    c = unified;					\
	}							\
    }								\
  else


/* Return the width of ASCII character C.  The width is measured by
   how many columns occupied on the screen when displayed in the
   current buffer.  */

#define ASCII_CHAR_WIDTH(c)						\
  (c < 0x20								\
   ? (c == '\t'								\
      ? XFASTINT (current_buffer->tab_width)				\
      : (c == '\n' ? 0 : (NILP (current_buffer->ctl_arrow) ? 4 : 2)))	\
   : (c < 0x7f								\
      ? 1								\
      : ((NILP (current_buffer->ctl_arrow) ? 4 : 2))))

/* Return the width of character C.  The width is measured by how many
   columns occupied on the screen when displayed in the current
   buffer.  */

#define CHAR_WIDTH(c)		\
  (ASCII_CHAR_P (c)		\
   ? ASCII_CHAR_WIDTH (c)	\
   : XINT (CHAR_TABLE_REF (Vchar_width_table, c)))

extern int char_string_with_unification P_ ((int, unsigned char *));
extern int string_char_with_unification P_ ((const unsigned char *,
					     const unsigned char **, int *));

extern int translate_char P_ ((Lisp_Object, int c));
extern int char_printable_p P_ ((int c));
extern void parse_str_as_multibyte P_ ((unsigned char *, int, int *, int *));
extern int parse_str_to_multibyte P_ ((unsigned char *, int));
extern int str_as_multibyte P_ ((unsigned char *, int, int, int *));
extern int str_to_multibyte P_ ((unsigned char *, int, int));
extern int str_as_unibyte P_ ((unsigned char *, int));
extern int strwidth P_ ((unsigned char *, int));
extern int c_string_width P_ ((unsigned char *, int, int, int *, int *));
extern int lisp_string_width P_ ((Lisp_Object, int, int *, int *));

extern Lisp_Object Vprintable_chars;

extern Lisp_Object Qcharacterp, Qauto_fill_chars;
extern Lisp_Object Vtranslation_table_vector;
extern Lisp_Object Vchar_width_table;
extern Lisp_Object Vchar_direction_table;
extern Lisp_Object Vchar_unify_table;

extern Lisp_Object string_escape_byte8 P_ ((Lisp_Object));

/* Return a translation table of id number ID.  */
#define GET_TRANSLATION_TABLE(id) \
  (XCDR(XVECTOR(Vtranslation_table_vector)->contents[(id)]))

/* A char-table for characters which may invoke auto-filling.  */
extern Lisp_Object Vauto_fill_chars;

extern Lisp_Object Vchar_script_table;

/* Copy LEN bytes from FROM to TO.  This macro should be used only
   when a caller knows that LEN is short and the obvious copy loop is
   faster than calling bcopy which has some overhead.  Copying a
   multibyte sequence of a character is the typical case.  */

#define BCOPY_SHORT(from, to, len)		\
  do {						\
    int i = len;				\
    unsigned char *from_p = from, *to_p = to;	\
    while (i--) *to_p++ = *from_p++;		\
  } while (0)

#define DEFSYM(sym, name)	\
  do { (sym) = intern ((name)); staticpro (&(sym)); } while (0)

#endif /* EMACS_CHARACTER_H */
Commit	Line	Data
0168c3d8 KH	1	/* Header for multibyte character handler.
	2	Copyright (C) 1995, 1997, 1998 Electrotechnical Laboratory, JAPAN.
	3	Licensed to the Free Software Foundation.
	4	Copyright (C) 2001, 2002
	5	National Institute of Advanced Industrial Science and Technology (AIST)
	6	Registration Number H13PRO009
	7
	8	This file is part of GNU Emacs.
	9
	10	GNU Emacs is free software; you can redistribute it and/or modify
	11	it under the terms of the GNU General Public License as published by
	12	the Free Software Foundation; either version 2, or (at your option)
	13	any later version.
	14
	15	GNU Emacs is distributed in the hope that it will be useful,
	16	but WITHOUT ANY WARRANTY; without even the implied warranty of
	17	MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
	18	GNU General Public License for more details.
	19
	20	You should have received a copy of the GNU General Public License
	21	along with GNU Emacs; see the file COPYING. If not, write to
	22	the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
	23	Boston, MA 02111-1307, USA. */
	24
	25	#ifndef EMACS_CHARACTER_H
	26	#define EMACS_CHARACTER_H
	27
885317d8 KH	28	/* character code 1st byte byte sequence
	29	-------------- -------- -------------
	30	0-7F 00..7F 0xxxxxxx
	31	80-7FF C2..DF 110xxxxx 10xxxxxx
	32	800-FFFF E0..EF 1110xxxx 10xxxxxx 10xxxxxx
	33	10000-1FFFFF F0..F7 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
	34	200000-3FFF7F F8 11111000 1000xxxx 10xxxxxx 10xxxxxx 10xxxxxx
	35	invalid F9..FF
0168c3d8 KH	36
0168c3d8 KH	37	raw-8-bit
885317d8	38	3FFF80-3FFFFF C0..C1 1100000x 10xxxxxx
0168c3d8 KH	39	*/
0168c3d8 KH	40
885317d8	41	/* Maximum character code ((1 << CHARACTERBITS) - 1). */
0168c3d8 KH	42	#define MAX_CHAR 0x3FFFFF
0168c3d8 KH	43
885317d8	44	/* Maximum Unicode character code. */
0168c3d8 KH	45	#define MAX_UNICODE_CHAR 0x10FFFF
0168c3d8 KH	46
885317d8	47	/* Maximum N-byte character codes. */
0168c3d8 KH	48	#define MAX_1_BYTE_CHAR 0x7F
	49	#define MAX_2_BYTE_CHAR 0x7FF
	50	#define MAX_3_BYTE_CHAR 0xFFFF
	51	#define MAX_4_BYTE_CHAR 0x1FFFFF
	52	#define MAX_5_BYTE_CHAR 0x3FFF7F
	53
885317d8	54	/* Return the character code for raw 8-bit byte BYTE. */
0168c3d8	55	#define BYTE8_TO_CHAR(byte) ((byte) + 0x3FFF00)
885317d8 KH	56
885317d8 KH	57	/* Return the raw 8-bit byte for character C. */
0168c3d8	58	#define CHAR_TO_BYTE8(c) ((c) - 0x3FFF00)
885317d8 KH	59
	60	/* Nonzero iff C is a character that corresponds to a raw 8-bit
	61	byte. */
0168c3d8	62	#define CHAR_BYTE8_P(c) ((c) > MAX_5_BYTE_CHAR)
885317d8 KH	63
	64	/* Nonzero iff BYTE is the 1st byte of a multibyte form of a character
	65	that corresponds to a raw 8-bit byte. */
0168c3d8 KH	66	#define CHAR_BYTE8_HEAD_P(byte) ((byte) == 0xC0 \|\| (byte) == 0xC1)
0168c3d8 KH	67
885317d8	68	/* This is the maximum byte length of multibyte form. */
0168c3d8 KH	69	#define MAX_MULTIBYTE_LENGTH 5
0168c3d8 KH	70
885317d8	71	/* Return a Lisp character whose character code is C. */
0168c3d8 KH	72	#define make_char(c) make_number (c)
	73
	74	/* Nonzero iff C is an ASCII byte. */
	75	#define ASCII_BYTE_P(c) ((unsigned) (c) < 0x80)
	76
	77	/* Nonzero iff X is a character. */
	78	#define CHARACTERP(x) (NATNUMP (x) && XFASTINT (x) <= MAX_CHAR)
	79
f65c6d94	80	/* Nonzero iff C is valid as a character code. GENERICP is not used
885317d8 KH	81	now. */
885317d8 KH	82	#define CHAR_VALID_P(c, genericp) ((unsigned) (c) <= MAX_CHAR)
0168c3d8 KH	83
	84	/* Check if Lisp object X is a character or not. */
	85	#define CHECK_CHARACTER(x) \
	86	do { \
	87	if (! CHARACTERP(x)) x = wrong_type_argument (Qcharacterp, (x)); \
	88	} while (0)
	89
	90	/* Nonzero iff C is an ASCII character. */
	91	#define ASCII_CHAR_P(c) ((unsigned) (c) < 0x80)
	92
	93	/* Nonzero iff C is a character of code less than 0x100. */
	94	#define SINGLE_BYTE_CHAR_P(c) ((unsigned) (c) < 0x100)
	95
	96	/* Nonzero if character C has a printable glyph. */
	97	#define CHAR_PRINTABLE_P(c) \
	98	(((c) >= 32 && ((c) < 127) \
	99	\|\| ! NILP (CHAR_TABLE_REF (Vprintable_chars, (c)))))
	100
885317d8	101	/* Return byte length of multibyte form for character C. */
0168c3d8 KH	102	#define CHAR_BYTES(c) \
	103	( (c) <= MAX_1_BYTE_CHAR ? 1 \
	104	: (c) <= MAX_2_BYTE_CHAR ? 2 \
	105	: (c) <= MAX_3_BYTE_CHAR ? 3 \
	106	: (c) <= MAX_4_BYTE_CHAR ? 4 \
	107	: (c) <= MAX_5_BYTE_CHAR ? 5 \
	108	: 2)
	109
885317d8 KH	110	/* Store multibyte form of the character C in P. The caller should
	111	allocate at least MAX_MULTIBYTE_LENGTH bytes area at P in advance.
	112	Returns the length of the multibyte form. */
0168c3d8 KH	113
	114	#define CHAR_STRING(c, p) \
	115	((unsigned) (c) <= MAX_1_BYTE_CHAR \
	116	? ((p)[0] = (c), \
	117	1) \
	118	: (unsigned) (c) <= MAX_2_BYTE_CHAR \
	119	? ((p)[0] = (0xC0 \| ((c) >> 6)), \
	120	(p)[1] = (0x80 \| ((c) & 0x3F)), \
	121	2) \
	122	: (unsigned) (c) <= MAX_3_BYTE_CHAR \
	123	? ((p)[0] = (0xE0 \| ((c) >> 12)), \
	124	(p)[1] = (0x80 \| (((c) >> 6) & 0x3F)), \
	125	(p)[2] = (0x80 \| ((c) & 0x3F)), \
	126	3) \
	127	: (unsigned) (c) <= MAX_5_BYTE_CHAR \
885317d8	128	? char_string_with_unification (c, p) \
0168c3d8 KH	129	: ((p)[0] = (0xC0 \| (((c) >> 6) & 0x01)), \
	130	(p)[1] = (0x80 \| ((c) & 0x3F)), \
	131	2))
	132
	133
885317d8 KH	134	/* Store multibyte form of the character C in P. The caller should
	135	allocate at least MAX_MULTIBYTE_LENGTH bytes area at P in advance.
	136	And, advance P to the end of the multibyte form. */
0168c3d8	137
885317d8 KH	138	#define CHAR_STRING_ADVANCE(c, p) \
	139	do { \
	140	if ((c) <= MAX_1_BYTE_CHAR) \
	141	*(p)++ = (c); \
	142	else if ((c) <= MAX_2_BYTE_CHAR) \
	143	*(p)++ = (0xC0 \| ((c) >> 6)), \
	144	*(p)++ = (0x80 \| ((c) & 0x3F)); \
	145	else if ((c) <= MAX_3_BYTE_CHAR) \
	146	*(p)++ = (0xE0 \| ((c) >> 12)), \
	147	*(p)++ = (0x80 \| (((c) >> 6) & 0x3F)), \
	148	*(p)++ = (0x80 \| ((c) & 0x3F)); \
	149	else if ((c) <= MAX_5_BYTE_CHAR) \
	150	(p) += char_string_with_unification ((c), (p)); \
	151	else \
	152	*(p)++ = (0xC0 \| (((c) >> 6) & 0x01)), \
	153	*(p)++ = (0x80 \| ((c) & 0x3F)); \
	154	} while (0)
0168c3d8 KH	155
	156	/* Nonzero iff BYTE starts a non-ASCII character in a multibyte
	157	form. */
	158	#define LEADING_CODE_P(byte) (((byte) & 0xC0) == 0xC0)
	159
b5c7dbe6 KH	160	/* Nonzero iff BYTE is a trailing code of a non-ASCII character in a
	161	multibyte form. */
	162	#define TRAILING_CODE_P(byte) (((byte) & 0xC0) == 0x80)
	163
885317d8 KH	164	/* Nonzero iff BYTE starts a character in a multibyte form.
	165	This is equivalent to:
	166	(ASCII_BYTE_P (byte) \|\| LEADING_CODE_P (byte)) */
	167	#define CHAR_HEAD_P(byte) (((byte) & 0xC0) != 0x80)
	168
0168c3d8 KH	169	/* Just kept for backward compatibility. This macro will be removed
	170	in the future. */
	171	#define BASE_LEADING_CODE_P LEADING_CODE_P
	172
	173	/* How many bytes a character that starts with BYTE occupies in a
	174	multibyte form. */
	175	#define BYTES_BY_CHAR_HEAD(byte) \
	176	(!((byte) & 0x80) ? 1 \
	177	: !((byte) & 0x20) ? 2 \
	178	: !((byte) & 0x10) ? 3 \
	179	: !((byte) & 0x08) ? 4 \
	180	: 5)
	181
	182
	183	/* Return the length of the multi-byte form at string STR of length
	184	LEN while assuming that STR points a valid multi-byte form. As
	185	this macro isn't necessary anymore, all callers will be changed to
	186	use BYTES_BY_CHAR_HEAD directly in the future. */
	187
	188	#define MULTIBYTE_FORM_LENGTH(str, len) \
	189	BYTES_BY_CHAR_HEAD (*(str))
	190
	191	/* Parse multibyte string STR of length LENGTH and set BYTES to the
	192	byte length of a character at STR while assuming that STR points a
	193	valid multibyte form. As this macro isn't necessary anymore, all
	194	callers will be changed to use BYTES_BY_CHAR_HEAD directly in the
	195	future. */
	196
	197	#define PARSE_MULTIBYTE_SEQ(str, length, bytes) \
	198	(bytes) = BYTES_BY_CHAR_HEAD (*(str))
	199
	200	/* The byte length of multibyte form at unibyte string P ending at
	201	PEND. If STR doesn't point a valid multibyte form, return 0. */
	202
	203	#define MULTIBYTE_LENGTH(p, pend) \
	204	(p >= pend ? 0 \
	205	: !((p)[0] & 0x80) ? 1 \
	206	: ((p + 1 >= pend) \|\| (((p)[1] & 0xC0) != 0x80)) ? 0 \
	207	: ((p)[0] & 0xE0) == 0xC0 ? 2 \
	208	: ((p + 2 >= pend) \|\| (((p)[2] & 0xC0) != 0x80)) ? 0 \
	209	: ((p)[0] & 0xF0) == 0xE0 ? 3 \
	210	: ((p + 3 >= pend) \|\| (((p)[3] & 0xC0) != 0x80)) ? 0 \
	211	: ((p)[0] & 0xF8) == 0xF0 ? 4 \
	212	: ((p + 4 >= pend) \|\| (((p)[4] & 0xC0) != 0x80)) ? 0 \
	213	: (p)[0] == 0xF8 && ((p)[1] & 0xF0) == 0x80 ? 5 \
	214	: 0)
	215
	216
	217	/* Like MULTIBYTE_LENGTH but don't check the ending address. */
	218
	219	#define MULTIBYTE_LENGTH_NO_CHECK(p) \
	220	(!((p)[0] & 0x80) ? 1 \
	221	: ((p)[1] & 0xC0) != 0x80 ? 0 \
	222	: ((p)[0] & 0xE0) == 0xC0 ? 2 \
	223	: ((p)[2] & 0xC0) != 0x80 ? 0 \
	224	: ((p)[0] & 0xF0) == 0xE0 ? 3 \
	225	: ((p)[3] & 0xC0) != 0x80 ? 0 \
	226	: ((p)[0] & 0xF8) == 0xF0 ? 4 \
	227	: ((p)[4] & 0xC0) != 0x80 ? 0 \
	228	: (p)[0] == 0xF8 && ((p)[1] & 0xF0) == 0x80 ? 5 \
	229	: 0)
	230
	231
	232	/* Return the character code of character whose multibyte form is at
233	P. The argument LEN is ignored. It will be removed in the
234	future. */
235
236	#define STRING_CHAR(p, len) \
237	(!((p)[0] & 0x80) \
238	? (p)[0] \
239	: ! ((p)[0] & 0x20) \
240	? (((((p)[0] & 0x1F) << 6) \
241	\| ((p)[1] & 0x3F)) \
242	+ (((unsigned char) (p)[0]) < 0xC2 ? 0x3FFF80 : 0)) \
243	: ! ((p)[0] & 0x10) \
244	? ((((p)[0] & 0x0F) << 12) \
245	\| (((p)[1] & 0x3F) << 6) \
246	\| ((p)[2] & 0x3F)) \
885317d8	247	: string_char_with_unification ((p), NULL, NULL))
0168c3d8 KH	248
	249
	250	/* Like STRING_CHAR but set ACTUAL_LEN to the length of multibyte
	251	form. The argument LEN is ignored. It will be removed in the
	252	future. */
	253
	254	#define STRING_CHAR_AND_LENGTH(p, len, actual_len) \
	255	(!((p)[0] & 0x80) \
	256	? ((actual_len) = 1, (p)[0]) \
	257	: ! ((p)[0] & 0x20) \
	258	? ((actual_len) = 2, \
	259	(((((p)[0] & 0x1F) << 6) \
	260	\| ((p)[1] & 0x3F)) \
	261	+ (((unsigned char) (p)[0]) < 0xC2 ? 0x3FFF80 : 0))) \
	262	: ! ((p)[0] & 0x10) \
	263	? ((actual_len) = 3, \
	264	((((p)[0] & 0x0F) << 12) \
	265	\| (((p)[1] & 0x3F) << 6) \
	266	\| ((p)[2] & 0x3F))) \
885317d8	267	: string_char_with_unification ((p), NULL, &actual_len))
0168c3d8 KH	268
	269
	270	/* Like STRING_CHAR but advacen P to the end of multibyte form. */
	271
	272	#define STRING_CHAR_ADVANCE(p) \
	273	(!((p)[0] & 0x80) \
	274	? *(p)++ \
	275	: ! ((p)[0] & 0x20) \
	276	? ((p) += 2, \
	277	((((p)[-2] & 0x1F) << 6) \
	278	\| ((p)[-1] & 0x3F) \
	279	\| (((unsigned char) (p)[-2]) < 0xC2 ? 0x3FFF80 : 0))) \
	280	: ! ((p)[0] & 0x10) \
	281	? ((p) += 3, \
	282	((((p)[-3] & 0x0F) << 12) \
	283	\| (((p)[-2] & 0x3F) << 6) \
	284	\| ((p)[-1] & 0x3F))) \
885317d8	285	: string_char_with_unification ((p), &(p), NULL))
0168c3d8 KH	286
	287
	288	/* Fetch the "next" character from Lisp string STRING at byte position
	289	BYTEIDX, character position CHARIDX. Store it into OUTPUT.
	290
	291	All the args must be side-effect-free.
	292	BYTEIDX and CHARIDX must be lvalues;
	293	we increment them past the character fetched. */
	294
	295	#define FETCH_STRING_CHAR_ADVANCE(OUTPUT, STRING, CHARIDX, BYTEIDX) \
	296	if (1) \
	297	{ \
	298	CHARIDX++; \
	299	if (STRING_MULTIBYTE (STRING)) \
	300	{ \
	301	unsigned char *ptr = &XSTRING (STRING)->data[BYTEIDX]; \
	302	int len; \
	303	\
	304	OUTPUT = STRING_CHAR_AND_LENGTH (ptr, 0, len); \
	305	BYTEIDX += len; \
	306	} \
	307	else \
	308	OUTPUT = XSTRING (STRING)->data[BYTEIDX++]; \
	309	} \
	310	else
	311
	312
	313	/* Like FETCH_STRING_CHAR_ADVANCE but assumes STRING is multibyte. */
	314
	315	#define FETCH_STRING_CHAR_ADVANCE_NO_CHECK(OUTPUT, STRING, CHARIDX, BYTEIDX) \
	316	if (1) \
	317	{ \
	318	unsigned char *ptr = &XSTRING (STRING)->data[BYTEIDX]; \
	319	int len; \
	320	\
	321	OUTPUT = STRING_CHAR_AND_LENGTH (ptr, 0, len); \
	322	BYTEIDX += len; \
	323	CHARIDX++; \
	324	} \
	325	else
	326
	327
	328	/* Like FETCH_STRING_CHAR_ADVANCE but fetch character from the current
	329	buffer. */
	330
	331	#define FETCH_CHAR_ADVANCE(OUTPUT, CHARIDX, BYTEIDX) \
	332	if (1) \
	333	{ \
	334	CHARIDX++; \
	335	if (!NILP (current_buffer->enable_multibyte_characters)) \
	336	{ \
	337	unsigned char *ptr = BYTE_POS_ADDR (BYTEIDX); \
	338	int len; \
	339	\
	340	OUTPUT= STRING_CHAR_AND_LENGTH (ptr, 0, len); \
	341	BYTEIDX += len; \
	342	} \
	343	else \
	344	{ \
	345	OUTPUT = *(BYTE_POS_ADDR (BYTEIDX)); \
	346	BYTEIDX++; \
	347	} \
	348	} \
	349	else
350
351
352	/* Like FETCH_CHAR_ADVANCE but assumes STRING is multibyte. */
353
354	#define FETCH_CHAR_ADVANCE_NO_CHECK(OUTPUT, CHARIDX, BYTEIDX) \
355	if (1) \
356	{ \
357	unsigned char *ptr = BYTE_POS_ADDR (BYTEIDX); \
358	int len; \
359	\
360	OUTPUT= STRING_CHAR_AND_LENGTH (ptr, 0, len); \
361	BYTEIDX += len; \
362	CHARIDX++; \
363	} \
364	else
365
366
367	/* Increase the buffer byte position POS_BYTE of the current buffer to
368	the next character boundary. No range checking of POS. */
369
370	#define INC_POS(pos_byte) \
371	do { \
372	unsigned char *p = BYTE_POS_ADDR (pos_byte); \
373	pos_byte += BYTES_BY_CHAR_HEAD (*p); \
374	} while (0)
375
376
377	/* Decrease the buffer byte position POS_BYTE of the current buffer to
378	the previous character boundary. No range checking of POS. */
379
380	#define DEC_POS(pos_byte) \
381	do { \
382	unsigned char *p; \
383	\
384	pos_byte--; \
385	if (pos_byte < GPT_BYTE) \
386	p = BEG_ADDR + pos_byte - 1; \
387	else \
388	p = BEG_ADDR + GAP_SIZE + pos_byte - 1; \
389	while (!CHAR_HEAD_P (*p)) \
390	{ \
391	p--; \
392	pos_byte--; \
393	} \
394	} while (0)
395
396	/* Increment both CHARPOS and BYTEPOS, each in the appropriate way. */
397
398	#define INC_BOTH(charpos, bytepos) \
399	do \
400	{ \
401	(charpos)++; \
402	if (NILP (current_buffer->enable_multibyte_characters)) \
403	(bytepos)++; \
404	else \
405	INC_POS ((bytepos)); \
406	} \
407	while (0)
408
409
410	/* Decrement both CHARPOS and BYTEPOS, each in the appropriate way. */
411
412	#define DEC_BOTH(charpos, bytepos) \
413	do \
414	{ \
415	(charpos)--; \
416	if (NILP (current_buffer->enable_multibyte_characters)) \
417	(bytepos)--; \
418	else \
419	DEC_POS ((bytepos)); \
420	} \
421	while (0)
422
423
424	/* Increase the buffer byte position POS_BYTE of the current buffer to
425	the next character boundary. This macro relies on the fact that
426	GPT_ADDR and Z_ADDR are always accessible and the values are
427	'\0'. No range checking of POS_BYTE. */
428
429	#define BUF_INC_POS(buf, pos_byte) \
430	do { \
431	unsigned char *p = BUF_BYTE_ADDRESS (buf, pos_byte); \
432	pos_byte += BYTES_BY_CHAR_HEAD (*p); \
433	} while (0)
434
435
436	/* Decrease the buffer byte position POS_BYTE of the current buffer to
437	the previous character boundary. No range checking of POS_BYTE. */
438
439	#define BUF_DEC_POS(buf, pos_byte) \
440	do { \
441	unsigned char *p; \
442	pos_byte--; \
443	if (pos_byte < BUF_GPT_BYTE (buf)) \
444	p = BUF_BEG_ADDR (buf) + pos_byte - 1; \
445	else \
446	p = BUF_BEG_ADDR (buf) + BUF_GAP_SIZE (buf) + pos_byte - 1; \
447	while (!CHAR_HEAD_P (*p)) \
448	{ \
449	p--; \
450	pos_byte--; \
451	} \
452	} while (0)
453
454
fc9d9d2a KH	455	#define MAYBE_UNIFY_CHAR(c) \
	456	if (CHAR_TABLE_P (Vchar_unify_table)) \
	457	{ \
	458	Lisp_Object val; \
	459	int unified; \
	460	\
	461	val = CHAR_TABLE_REF (Vchar_unify_table, c); \
	462	if (! NILP (val)) \
	463	{ \
	464	if (SYMBOLP (val)) \
	465	{ \
b5c7dbe6	466	Funify_charset (val, Qnil, Qnil); \
fc9d9d2a KH	467	val = CHAR_TABLE_REF (Vchar_unify_table, c); \
	468	} \
	469	if ((unified = XINT (val)) >= 0) \
	470	c = unified; \
	471	} \
	472	} \
0168c3d8 KH	473	else
0168c3d8 KH	474
fc9d9d2a	475
0168c3d8 KH	476	/* Return the width of ASCII character C. The width is measured by
	477	how many columns occupied on the screen when displayed in the
	478	current buffer. */
	479
	480	#define ASCII_CHAR_WIDTH(c) \
	481	(c < 0x20 \
	482	? (c == '\t' \
	483	? XFASTINT (current_buffer->tab_width) \
	484	: (c == '\n' ? 0 : (NILP (current_buffer->ctl_arrow) ? 4 : 2))) \
	485	: (c < 0x7f \
	486	? 1 \
	487	: ((NILP (current_buffer->ctl_arrow) ? 4 : 2))))
	488
	489	/* Return the width of character C. The width is measured by how many
	490	columns occupied on the screen when displayed in the current
	491	buffer. */
	492
	493	#define CHAR_WIDTH(c) \
	494	(ASCII_CHAR_P (c) \
	495	? ASCII_CHAR_WIDTH (c) \
	496	: XINT (CHAR_TABLE_REF (Vchar_width_table, c)))
	497
885317d8	498	extern int char_string_with_unification P_ ((int, unsigned char *));
b5c7dbe6 KH	499	extern int string_char_with_unification P_ ((const unsigned char *,
b5c7dbe6 KH	500	const unsigned char *, int ));
0168c3d8 KH	501
	502	extern int translate_char P_ ((Lisp_Object, int c));
	503	extern int char_printable_p P_ ((int c));
	504	extern void parse_str_as_multibyte P_ ((unsigned char , int, int , int *));
	505	extern int parse_str_to_multibyte P_ ((unsigned char *, int));
	506	extern int str_as_multibyte P_ ((unsigned char , int, int, int ));
	507	extern int str_to_multibyte P_ ((unsigned char *, int, int));
	508	extern int str_as_unibyte P_ ((unsigned char *, int));
	509	extern int strwidth P_ ((unsigned char *, int));
	510	extern int c_string_width P_ ((unsigned char , int, int, int , int *));
	511	extern int lisp_string_width P_ ((Lisp_Object, int, int , int ));
	512
	513	extern Lisp_Object Vprintable_chars;
	514
	515	extern Lisp_Object Qcharacterp, Qauto_fill_chars;
	516	extern Lisp_Object Vtranslation_table_vector;
	517	extern Lisp_Object Vchar_width_table;
	518	extern Lisp_Object Vchar_direction_table;
	519	extern Lisp_Object Vchar_unify_table;
	520
fac2bdc4 DL	521	extern Lisp_Object string_escape_byte8 P_ ((Lisp_Object));
fac2bdc4 DL	522
0168c3d8 KH	523	/* Return a translation table of id number ID. */
	524	#define GET_TRANSLATION_TABLE(id) \
	525	(XCDR(XVECTOR(Vtranslation_table_vector)->contents[(id)]))
	526
	527	/* A char-table for characters which may invoke auto-filling. */
	528	extern Lisp_Object Vauto_fill_chars;
	529
e18ef64a	530	extern Lisp_Object Vchar_script_table;
b5c7dbe6	531
0168c3d8 KH	532	/* Copy LEN bytes from FROM to TO. This macro should be used only
	533	when a caller knows that LEN is short and the obvious copy loop is
	534	faster than calling bcopy which has some overhead. Copying a
	535	multibyte sequence of a character is the typical case. */
	536
	537	#define BCOPY_SHORT(from, to, len) \
	538	do { \
	539	int i = len; \
	540	unsigned char from_p = from, to_p = to; \
	541	while (i--) to_p++ = from_p++; \
	542	} while (0)
	543
	544	#define DEFSYM(sym, name) \
	545	do { (sym) = intern ((name)); staticpro (&(sym)); } while (0)
	546
	547	#endif /* EMACS_CHARACTER_H */