486
|
1 /* Declarations having to do with GNU Emacs syntax tables.
|
2961
|
2 Copyright (C) 1985, 1993 Free Software Foundation, Inc.
|
486
|
3
|
|
4 This file is part of GNU Emacs.
|
|
5
|
|
6 GNU Emacs is free software; you can redistribute it and/or modify
|
|
7 it under the terms of the GNU General Public License as published by
|
|
8 the Free Software Foundation; either version 1, or (at your option)
|
|
9 any later version.
|
|
10
|
|
11 GNU Emacs is distributed in the hope that it will be useful,
|
|
12 but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
13 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
14 GNU General Public License for more details.
|
|
15
|
|
16 You should have received a copy of the GNU General Public License
|
|
17 along with GNU Emacs; see the file COPYING. If not, write to
|
|
18 the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. */
|
|
19
|
|
20
|
|
21 extern Lisp_Object Qsyntax_table_p;
|
|
22 extern Lisp_Object Fsyntax_table_p (), Fsyntax_table (), Fset_syntax_table ();
|
|
23
|
|
24 /* The standard syntax table is stored where it will automatically
|
|
25 be used in all new buffers. */
|
|
26 #define Vstandard_syntax_table buffer_defaults.syntax_table
|
|
27
|
|
28 /* A syntax table is a Lisp vector of length 0400, whose elements are integers.
|
|
29
|
|
30 The low 8 bits of the integer is a code, as follows:
|
|
31 */
|
|
32
|
|
33 enum syntaxcode
|
|
34 {
|
|
35 Swhitespace, /* for a whitespace character */
|
|
36 Spunct, /* for random punctuation characters */
|
|
37 Sword, /* for a word constituent */
|
|
38 Ssymbol, /* symbol constituent but not word constituent */
|
|
39 Sopen, /* for a beginning delimiter */
|
|
40 Sclose, /* for an ending delimiter */
|
|
41 Squote, /* for a prefix character like Lisp ' */
|
|
42 Sstring, /* for a string-grouping character like Lisp " */
|
|
43 Smath, /* for delimiters like $ in Tex. */
|
|
44 Sescape, /* for a character that begins a C-style escape */
|
|
45 Scharquote, /* for a character that quotes the following character */
|
|
46 Scomment, /* for a comment-starting character */
|
|
47 Sendcomment, /* for a comment-ending character */
|
5441
|
48 Sinherit, /* use the standard syntax table for this character */
|
486
|
49 Smax /* Upper bound on codes that are meaningful */
|
|
50 };
|
|
51
|
5441
|
52 #define RAW_SYNTAX(table, c) \
|
|
53 ((enum syntaxcode) (XINT (XVECTOR (table)->contents[(unsigned char) (c)]) & 0377))
|
|
54
|
|
55 #ifdef __GNUC__
|
|
56 #define SYNTAX(c) \
|
|
57 ({ unsigned char character = c; \
|
|
58 enum syntaxcode syntax \
|
|
59 = RAW_SYNTAX (current_buffer->syntax_table, character); \
|
|
60 if (syntax == Sinherit) \
|
|
61 syntax = RAW_SYNTAX (Vstandard_syntax_table, character); \
|
|
62 syntax; })
|
|
63 #else
|
|
64 #define SYNTAX(c) \
|
|
65 (RAW_SYNTAX (current_buffer->syntax_table, c) == Sinherit \
|
|
66 ? RAW_SYNTAX (Vstandard_syntax_table, c) \
|
5725
|
67 : RAW_SYNTAX (current_buffer->syntax_table, c))
|
5441
|
68 #endif
|
486
|
69
|
|
70 /* The next 8 bits of the number is a character,
|
|
71 the matching delimiter in the case of Sopen or Sclose. */
|
|
72
|
5441
|
73 #define RAW_SYNTAX_MATCH(table, c) \
|
|
74 ((XINT (XVECTOR (table)->contents[(unsigned char) (c)]) >> 8) & 0377)
|
|
75
|
|
76 #ifdef __GNUC__
|
|
77 #define SYNTAX_MATCH(c) \
|
|
78 ({ unsigned char character = c; \
|
|
79 enum syntaxcode syntax \
|
|
80 = RAW_SYNTAX (current_buffer->syntax_table, character); \
|
|
81 int matcher; \
|
|
82 if (syntax == Sinherit) \
|
|
83 matcher = RAW_SYNTAX_MATCH (Vstandard_syntax_table, character); \
|
|
84 else \
|
|
85 matcher = RAW_SYNTAX_MATCH (current_buffer->syntax_table, character); \
|
|
86 syntax; })
|
|
87 #else
|
|
88 #define SYNTAX_MATCH(c) \
|
|
89 (RAW_SYNTAX (current_buffer->syntax_table, c) == Sinherit \
|
|
90 ? RAW_SYNTAX_MATCH (Vstandard_syntax_table, c) \
|
5725
|
91 : RAW_SYNTAX_MATCH (current_buffer->syntax_table, c))
|
5441
|
92 #endif
|
486
|
93
|
1073
|
94 /* Then there are six single-bit flags that have the following meanings:
|
486
|
95 1. This character is the first of a two-character comment-start sequence.
|
|
96 2. This character is the second of a two-character comment-start sequence.
|
|
97 3. This character is the first of a two-character comment-end sequence.
|
|
98 4. This character is the second of a two-character comment-end sequence.
|
|
99 5. This character is a prefix, for backward-prefix-chars.
|
1073
|
100 Note that any two-character sequence whose first character has flag 1
|
|
101 and whose second character has flag 2 will be interpreted as a comment start.
|
|
102
|
|
103 bit 6 is used to discriminate between two different comment styles.
|
|
104 Languages such as C++ allow two orthogonal syntax start/end pairs
|
|
105 and bit 6 is used to determine whether a comment-end or Scommentend
|
|
106 ends style a or b. Comment start sequences can start style a or b.
|
|
107 Style a is always the default.
|
|
108 */
|
486
|
109
|
5441
|
110 #define SYNTAX_CHOOSE_TABLE(c) \
|
|
111 (RAW_SYNTAX (current_buffer->syntax_table, c) == Sinherit \
|
|
112 ? Vstandard_syntax_table : current_buffer->syntax_table)
|
|
113
|
|
114 #ifdef __GNUC__
|
|
115
|
|
116 #define SYNTAX_COMSTART_FIRST(c) \
|
|
117 ({ unsigned char ch = c; \
|
|
118 Lisp_Object table = SYNTAX_CHOOSE_TABLE (ch); \
|
|
119 (XINT (XVECTOR (table)->contents[ch]) >> 16) & 1; \
|
|
120 })
|
486
|
121
|
|
122 #define SYNTAX_COMSTART_SECOND(c) \
|
5441
|
123 ({ unsigned char ch = c; \
|
|
124 Lisp_Object table = SYNTAX_CHOOSE_TABLE (ch); \
|
|
125 (XINT (XVECTOR (table)->contents[ch]) >> 17) & 1; \
|
|
126 })
|
486
|
127
|
|
128 #define SYNTAX_COMEND_FIRST(c) \
|
5441
|
129 ({ unsigned char ch = c; \
|
|
130 Lisp_Object table = SYNTAX_CHOOSE_TABLE (ch); \
|
|
131 (XINT (XVECTOR (table)->contents[ch]) >> 18) & 1; \
|
|
132 })
|
486
|
133
|
|
134 #define SYNTAX_COMEND_SECOND(c) \
|
5441
|
135 ({ unsigned char ch = c; \
|
|
136 Lisp_Object table = SYNTAX_CHOOSE_TABLE (ch); \
|
|
137 (XINT (XVECTOR (table)->contents[ch]) >> 19) & 1; \
|
|
138 })
|
486
|
139
|
|
140 #define SYNTAX_PREFIX(c) \
|
5441
|
141 ({ unsigned char ch = c; \
|
|
142 Lisp_Object table = SYNTAX_CHOOSE_TABLE (ch); \
|
|
143 (XINT (XVECTOR (table)->contents[ch]) >> 20) & 1; \
|
|
144 })
|
486
|
145
|
1073
|
146 /* extract the comment style bit from the syntax table entry */
|
|
147 #define SYNTAX_COMMENT_STYLE(c) \
|
5441
|
148 ({ unsigned char ch = c; \
|
|
149 Lisp_Object table = SYNTAX_CHOOSE_TABLE (ch); \
|
|
150 (XINT (XVECTOR (table)->contents[ch]) >> 21) & 1; \
|
|
151 })
|
|
152
|
|
153 #else
|
|
154
|
|
155 #define SYNTAX_COMSTART_FIRST(c) \
|
|
156 ((XINT (XVECTOR (SYNTAX_CHOOSE_TABLE (c))->contents[(unsigned char) (c)]) >> 16) & 1)
|
|
157
|
|
158 #define SYNTAX_COMSTART_SECOND(c) \
|
|
159 ((XINT (XVECTOR (SYNTAX_CHOOSE_TABLE (c))->contents[(unsigned char) (c)]) >> 17) & 1)
|
|
160
|
|
161 #define SYNTAX_COMEND_FIRST(c) \
|
|
162 ((XINT (XVECTOR (SYNTAX_CHOOSE_TABLE (c))->contents[(unsigned char) (c)]) >> 18) & 1)
|
|
163
|
|
164 #define SYNTAX_COMEND_SECOND(c) \
|
|
165 ((XINT (XVECTOR (SYNTAX_CHOOSE_TABLE (c))->contents[(unsigned char) (c)]) >> 19) & 1)
|
|
166
|
|
167 #define SYNTAX_PREFIX(c) \
|
|
168 ((XINT (XVECTOR (SYNTAX_CHOOSE_TABLE (c))->contents[(unsigned char) (c)]) >> 20) & 1)
|
|
169
|
|
170 /* extract the comment style bit from the syntax table entry */
|
|
171 #define SYNTAX_COMMENT_STYLE(c) \
|
|
172 ((XINT (XVECTOR (SYNTAX_CHOOSE_TABLE (c))->contents[(unsigned char) (c)]) >> 21) & 1)
|
|
173
|
|
174 #endif
|
1073
|
175
|
486
|
176 /* This array, indexed by a character, contains the syntax code which that
|
|
177 character signifies (as a char). For example,
|
|
178 (enum syntaxcode) syntax_spec_code['w'] is Sword. */
|
|
179
|
|
180 extern unsigned char syntax_spec_code[0400];
|
|
181
|
|
182 /* Indexed by syntax code, give the letter that describes it. */
|
|
183
|
5441
|
184 extern char syntax_code_spec[14];
|