view src/syntax.h @ 4139:0b32ee899a3a

Consistently use the mark bit of the root interval's parent field to say whether or not the interval tree has been visited (and skip it when revisited), and the mark bit of the plist field to say whether or not that interval has been visited (and abort if revisited); don't try to use the plist mark bit for both meanings. * alloc.c (mark_interval_tree): Don't test if the interval tree has already been visited here; let the MARK_INTERVAL_TREE macro do that; avoid function call overhead. Mark the interval tree as having been visited by setting TREE->parent's mark bit. (MARK_INTERVAL_TREE): If the tree has been visited (according to I->parent's mark bit), don't call mark_interval_tree. (gc_sweep): Rebalance the interval trees of those large strings which are still alive. This also clears the mark bits of those trees' root intervals' parent fields. (compact_strings): Rebalance the interval tree of each small strings which is still alive. This also clears the mark bits of that tree's root interval's parent field. Since the string has moved, update the root interval's parent pointer to contain the new address. * lisp.h (struct interval): Doc fix; explain the roles of the mark bits of the parent and plist members.

/* Declarations having to do with GNU Emacs syntax tables.
   Copyright (C) 1985, 1993 Free Software Foundation, Inc.

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 1, 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, 675 Mass Ave, Cambridge, MA 02139, USA.  */


extern Lisp_Object Qsyntax_table_p;
extern Lisp_Object Fsyntax_table_p (), Fsyntax_table (), Fset_syntax_table ();

/* The standard syntax table is stored where it will automatically
   be used in all new buffers.  */
#define Vstandard_syntax_table buffer_defaults.syntax_table

/* A syntax table is a Lisp vector of length 0400, whose elements are integers.

The low 8 bits of the integer is a code, as follows:
*/

enum syntaxcode
  {
    Swhitespace, /* for a whitespace character */
    Spunct,	 /* for random punctuation characters */
    Sword,	 /* for a word constituent */
    Ssymbol,	 /* symbol constituent but not word constituent */
    Sopen,	 /* for a beginning delimiter */
    Sclose,      /* for an ending delimiter */
    Squote,	 /* for a prefix character like Lisp ' */
    Sstring,	 /* for a string-grouping character like Lisp " */
    Smath,	 /* for delimiters like $ in Tex. */
    Sescape,	 /* for a character that begins a C-style escape */
    Scharquote,  /* for a character that quotes the following character */
    Scomment,    /* for a comment-starting character */
    Sendcomment, /* for a comment-ending character */
    Smax	 /* Upper bound on codes that are meaningful */
  };

#define SYNTAX(c) \
  ((enum syntaxcode) (XINT (XVECTOR (current_buffer->syntax_table)->contents[(unsigned char) (c)]) & 0377))

/* The next 8 bits of the number is a character,
 the matching delimiter in the case of Sopen or Sclose. */

#define SYNTAX_MATCH(c) \
  ((XINT (XVECTOR (current_buffer->syntax_table)->contents[(unsigned char) (c)]) >> 8) & 0377)

/* Then there are six single-bit flags that have the following meanings:
  1. This character is the first of a two-character comment-start sequence.
  2. This character is the second of a two-character comment-start sequence.
  3. This character is the first of a two-character comment-end sequence.
  4. This character is the second of a two-character comment-end sequence.
  5. This character is a prefix, for backward-prefix-chars.
  Note that any two-character sequence whose first character has flag 1
  and whose second character has flag 2 will be interpreted as a comment start.

  bit 6 is used to discriminate between two different comment styles.
  Languages such as C++ allow two orthogonal syntax start/end pairs
  and bit 6 is used to determine whether a comment-end or Scommentend
  ends style a or b. Comment start sequences can start style a or b.
  Style a is always the default.
  */

#define SYNTAX_COMSTART_FIRST(c) \
  ((XINT (XVECTOR (current_buffer->syntax_table)->contents[(unsigned char) (c)]) >> 16) & 1)

#define SYNTAX_COMSTART_SECOND(c) \
  ((XINT (XVECTOR (current_buffer->syntax_table)->contents[(unsigned char) (c)]) >> 17) & 1)

#define SYNTAX_COMEND_FIRST(c) \
  ((XINT (XVECTOR (current_buffer->syntax_table)->contents[(unsigned char) (c)]) >> 18) & 1)

#define SYNTAX_COMEND_SECOND(c) \
  ((XINT (XVECTOR (current_buffer->syntax_table)->contents[(unsigned char) (c)]) >> 19) & 1)

#define SYNTAX_PREFIX(c) \
  ((XINT (XVECTOR (current_buffer->syntax_table)->contents[(unsigned char) (c)]) >> 20) & 1)

/* extract the comment style bit from the syntax table entry */
#define SYNTAX_COMMENT_STYLE(c) \
  ((XINT (XVECTOR (current_buffer->syntax_table)->contents[c]) >> 21) & 1)

/* This array, indexed by a character, contains the syntax code which that
 character signifies (as a char).  For example,
 (enum syntaxcode) syntax_spec_code['w'] is Sword. */

extern unsigned char syntax_spec_code[0400];

/* Indexed by syntax code, give the letter that describes it. */

extern char syntax_code_spec[13];