1 /* Declarations having to do with XEmacs syntax tables.
2 Copyright (C) 1985, 1992, 1993 Free Software Foundation, Inc.
4 This file is part of XEmacs.
6 XEmacs is free software; you can redistribute it and/or modify it
7 under the terms of the GNU General Public License as published by the
8 Free Software Foundation; either version 2, or (at your option) any
11 XEmacs is distributed in the hope that it will be useful, but WITHOUT
12 ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
16 You should have received a copy of the GNU General Public License
17 along with XEmacs; see the file COPYING. If not, write to
18 the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
19 Boston, MA 02111-1307, USA. */
21 /* Synched up with: FSF 19.28. */
23 #ifndef _XEMACS_SYNTAX_H_
24 #define _XEMACS_SYNTAX_H_
28 /* A syntax table is a type of char table.
30 The low 7 bits of the integer is a code, as follows. The 8th bit is
31 used as the prefix bit flag (see below).
33 The values in a syntax table are either integers or conses of
34 integers and chars. The lowest 7 bits of the integer are the syntax
35 class. If this is Sinherit, then the actual syntax value needs to
36 be retrieved from the standard syntax table.
38 Since the logic involved in finding the actual integer isn't very
39 complex, you'd think the time required to retrieve it is not a
40 factor. If you thought that, however, you'd be wrong, due to the
41 high number of times (many per character) that the syntax value is
42 accessed in functions such as scan_lists(). To speed this up,
43 we maintain a mirror syntax table that contains the actual
44 integers. We can do this successfully because syntax tables are
45 now an abstract type, where we control all access.
50 Swhitespace, /* whitespace character */
51 Spunct, /* random punctuation character */
52 Sword, /* word constituent */
53 Ssymbol, /* symbol constituent but not word constituent */
54 Sopen, /* a beginning delimiter */
55 Sclose, /* an ending delimiter */
56 Squote, /* a prefix character like Lisp ' */
57 Sstring, /* a string-grouping character like Lisp " */
58 Smath, /* delimiters like $ in TeX. */
59 Sescape, /* a character that begins a C-style escape */
60 Scharquote, /* a character that quotes the following character */
61 Scomment, /* a comment-starting character */
62 Sendcomment, /* a comment-ending character */
63 Sinherit, /* use the standard syntax table for this character */
64 Smax /* Upper bound on codes that are meaningful */
67 enum syntaxcode charset_syntax (struct buffer *buf, Lisp_Object charset,
70 /* Return the syntax code for a particular character and mirror table. */
72 #define SYNTAX_CODE_UNSAFE(table, c) \
73 XINT (CHAR_TABLE_VALUE_UNSAFE (table, c))
75 INLINE int SYNTAX_CODE (struct Lisp_Char_Table *table, Emchar c);
77 SYNTAX_CODE (struct Lisp_Char_Table *table, Emchar c)
79 return SYNTAX_CODE_UNSAFE (table, c);
82 #define SYNTAX_UNSAFE(table, c) \
83 ((enum syntaxcode) (SYNTAX_CODE_UNSAFE (table, c) & 0177))
85 #define SYNTAX_FROM_CODE(code) ((enum syntaxcode) ((code) & 0177))
86 #define SYNTAX(table, c) SYNTAX_FROM_CODE (SYNTAX_CODE (table, c))
88 INLINE int WORD_SYNTAX_P (struct Lisp_Char_Table *table, Emchar c);
90 WORD_SYNTAX_P (struct Lisp_Char_Table *table, Emchar c)
92 return SYNTAX (table, c) == Sword;
95 /* OK, here's a graphic diagram of the format of the syntax values:
99 [ 3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 0 0 0 0 0 0 0 0 0 0 ]
100 [ 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 ]
102 <-----> <-----> <-------------> <-------------> ^ <----------->
103 ELisp unused |comment bits | unused | syntax code
104 tag | | | | | | | | |
105 stuff | | | | | | | | |
107 | | | | | | | | `--> prefix flag
109 | | | | | | | `--> comment end style B, second char
110 | | | | | | `----> comment end style A, second char
111 | | | | | `------> comment end style B, first char
112 | | | | `--------> comment end style A, first char
113 | | | `----------> comment start style B, second char
114 | | `------------> comment start style A, second char
115 | `--------------> comment start style B, first char
116 `----------------> comment start style A, first char
118 In a 64-bit integer, there would be 32 more unused bits between
119 the tag and the comment bits.
121 Clearly, such a scheme will not work for Mule, because the matching
122 paren could be any character and as such requires 19 bits, which
125 Remember that under Mule we use char tables instead of vectors.
126 So what we do is use another char table for the matching paren
127 and store a pointer to it in the first char table. (This frees
128 code from having to worry about passing two tables around.)
132 /* The prefix flag bit for backward-prefix-chars is now put into bit 7. */
134 #define SYNTAX_PREFIX_UNSAFE(table, c) \
135 ((SYNTAX_CODE_UNSAFE (table, c) >> 7) & 1)
136 #define SYNTAX_PREFIX(table, c) \
137 ((SYNTAX_CODE (table, c) >> 7) & 1)
139 /* Bits 23-16 are used to implement up to two comment styles
140 in a single buffer. They have the following meanings:
142 1. first of a one or two character comment-start sequence of style a.
143 2. first of a one or two character comment-start sequence of style b.
144 3. second of a two-character comment-start sequence of style a.
145 4. second of a two-character comment-start sequence of style b.
146 5. first of a one or two character comment-end sequence of style a.
147 6. first of a one or two character comment-end sequence of style b.
148 7. second of a two-character comment-end sequence of style a.
149 8. second of a two-character comment-end sequence of style b.
152 #define SYNTAX_COMMENT_BITS(table, c) \
153 ((SYNTAX_CODE (table, c) >> 16) &0xff)
155 #define SYNTAX_FIRST_OF_START_A 0x80
156 #define SYNTAX_FIRST_OF_START_B 0x40
157 #define SYNTAX_SECOND_OF_START_A 0x20
158 #define SYNTAX_SECOND_OF_START_B 0x10
159 #define SYNTAX_FIRST_OF_END_A 0x08
160 #define SYNTAX_FIRST_OF_END_B 0x04
161 #define SYNTAX_SECOND_OF_END_A 0x02
162 #define SYNTAX_SECOND_OF_END_B 0x01
164 #define SYNTAX_COMMENT_STYLE_A 0xaa
165 #define SYNTAX_COMMENT_STYLE_B 0x55
166 #define SYNTAX_FIRST_CHAR_START 0xc0
167 #define SYNTAX_FIRST_CHAR_END 0x0c
168 #define SYNTAX_FIRST_CHAR 0xcc
169 #define SYNTAX_SECOND_CHAR_START 0x30
170 #define SYNTAX_SECOND_CHAR_END 0x03
171 #define SYNTAX_SECOND_CHAR 0x33
173 #define SYNTAX_START_P(table, a, b) \
174 ((SYNTAX_COMMENT_BITS (table, a) & SYNTAX_FIRST_CHAR_START) \
175 && (SYNTAX_COMMENT_BITS (table, b) & SYNTAX_SECOND_CHAR_START))
177 #define SYNTAX_END_P(table, a, b) \
178 ((SYNTAX_COMMENT_BITS (table, a) & SYNTAX_FIRST_CHAR_END) \
179 && (SYNTAX_COMMENT_BITS (table, b) & SYNTAX_SECOND_CHAR_END))
181 #define SYNTAX_STYLES_MATCH_START_P(table, a, b, mask) \
182 ((SYNTAX_COMMENT_BITS (table, a) & SYNTAX_FIRST_CHAR_START & (mask)) \
183 && (SYNTAX_COMMENT_BITS (table, b) & SYNTAX_SECOND_CHAR_START & (mask)))
185 #define SYNTAX_STYLES_MATCH_END_P(table, a, b, mask) \
186 ((SYNTAX_COMMENT_BITS (table, a) & SYNTAX_FIRST_CHAR_END & (mask)) \
187 && (SYNTAX_COMMENT_BITS (table, b) & SYNTAX_SECOND_CHAR_END & (mask)))
189 #define SYNTAX_STYLES_MATCH_1CHAR_P(table, a, mask) \
190 ((SYNTAX_COMMENT_BITS (table, a) & (mask)))
192 #define STYLE_FOUND_P(table, a, b, startp, style) \
193 ((SYNTAX_COMMENT_BITS (table, a) & \
194 ((startp) ? SYNTAX_FIRST_CHAR_START : \
195 SYNTAX_FIRST_CHAR_END) & (style)) \
196 && (SYNTAX_COMMENT_BITS (table, b) & \
197 ((startp) ? SYNTAX_SECOND_CHAR_START : \
198 SYNTAX_SECOND_CHAR_END) & (style)))
200 #define SYNTAX_COMMENT_MASK_START(table, a, b) \
201 ((STYLE_FOUND_P (table, a, b, 1, SYNTAX_COMMENT_STYLE_A) \
202 ? SYNTAX_COMMENT_STYLE_A \
203 : (STYLE_FOUND_P (table, a, b, 1, SYNTAX_COMMENT_STYLE_B) \
204 ? SYNTAX_COMMENT_STYLE_B \
207 #define SYNTAX_COMMENT_MASK_END(table, a, b) \
208 ((STYLE_FOUND_P (table, a, b, 0, SYNTAX_COMMENT_STYLE_A) \
209 ? SYNTAX_COMMENT_STYLE_A \
210 : (STYLE_FOUND_P (table, a, b, 0, SYNTAX_COMMENT_STYLE_B) \
211 ? SYNTAX_COMMENT_STYLE_B \
214 #define STYLE_FOUND_1CHAR_P(table, a, style) \
215 ((SYNTAX_COMMENT_BITS (table, a) & (style)))
217 #define SYNTAX_COMMENT_1CHAR_MASK(table, a) \
218 ((STYLE_FOUND_1CHAR_P (table, a, SYNTAX_COMMENT_STYLE_A) \
219 ? SYNTAX_COMMENT_STYLE_A \
220 : (STYLE_FOUND_1CHAR_P (table, a, SYNTAX_COMMENT_STYLE_B) \
221 ? SYNTAX_COMMENT_STYLE_B \
224 EXFUN (Fchar_syntax, 2);
225 EXFUN (Fforward_word, 2);
227 /* The standard syntax table is stored where it will automatically
228 be used in all new buffers. */
229 extern Lisp_Object Vstandard_syntax_table;
231 /* This array, indexed by a character, contains the syntax code which
232 that character signifies (as a char).
233 For example, (enum syntaxcode) syntax_spec_code['w'] is Sword. */
235 extern CONST unsigned char syntax_spec_code[0400];
237 /* Indexed by syntax code, give the letter that describes it. */
239 extern CONST unsigned char syntax_code_spec[];
241 Lisp_Object scan_lists (struct buffer *buf, int from, int count,
242 int depth, int sexpflag, int no_error);
243 int char_quoted (struct buffer *buf, int pos);
245 /* NOTE: This does not refer to the mirror table, but to the
246 syntax table itself. */
247 Lisp_Object syntax_match (Lisp_Object table, Emchar ch);
249 extern int no_quit_in_re_search;
250 extern struct buffer *regex_emacs_buffer;
252 void update_syntax_table (struct Lisp_Char_Table *ct);
254 #endif /* _XEMACS_SYNTAX_H_ */