Mercurial > emacs
annotate src/charset.c @ 23640:51102c1dc0c3
(describe-variable): Don't quote link to source.
author | Dave Love <fx@gnu.org> |
---|---|
date | Thu, 05 Nov 1998 18:55:38 +0000 |
parents | 4a0a107fac9e |
children | 9e74943ac418 |
rev | line source |
---|---|
18341
33e78cc7f058
Change copyright notices.
Richard M. Stallman <rms@gnu.org>
parents:
18003
diff
changeset
|
1 /* Basic multilingual character support. |
20705
a949dc65fbea
(nonascii_insert_offset): Variable moved from cmds.c.
Richard M. Stallman <rms@gnu.org>
parents:
20636
diff
changeset
|
2 Copyright (C) 1995, 1997, 1998 Electrotechnical Laboratory, JAPAN. |
18341
33e78cc7f058
Change copyright notices.
Richard M. Stallman <rms@gnu.org>
parents:
18003
diff
changeset
|
3 Licensed to the Free Software Foundation. |
17052 | 4 |
17071 | 5 This file is part of GNU Emacs. |
6 | |
7 GNU Emacs is free software; you can redistribute it and/or modify | |
8 it under the terms of the GNU General Public License as published by | |
9 the Free Software Foundation; either version 2, or (at your option) | |
10 any later version. | |
17052 | 11 |
17071 | 12 GNU Emacs is distributed in the hope that it will be useful, |
13 but WITHOUT ANY WARRANTY; without even the implied warranty of | |
14 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
15 GNU General Public License for more details. | |
17052 | 16 |
17071 | 17 You should have received a copy of the GNU General Public License |
18 along with GNU Emacs; see the file COPYING. If not, write to | |
19 the Free Software Foundation, Inc., 59 Temple Place - Suite 330, | |
20 Boston, MA 02111-1307, USA. */ | |
17052 | 21 |
22 /* At first, see the document in `charset.h' to understand the code in | |
23 this file. */ | |
24 | |
25 #include <stdio.h> | |
26 | |
27 #ifdef emacs | |
28 | |
29 #include <sys/types.h> | |
30 #include <config.h> | |
31 #include "lisp.h" | |
32 #include "buffer.h" | |
33 #include "charset.h" | |
34 #include "coding.h" | |
17843 | 35 #include "disptab.h" |
17052 | 36 |
37 #else /* not emacs */ | |
38 | |
39 #include "mulelib.h" | |
40 | |
41 #endif /* emacs */ | |
42 | |
43 Lisp_Object Qcharset, Qascii, Qcomposition; | |
44 | |
45 /* Declaration of special leading-codes. */ | |
46 int leading_code_composition; /* for composite characters */ | |
47 int leading_code_private_11; /* for private DIMENSION1 of 1-column */ | |
48 int leading_code_private_12; /* for private DIMENSION1 of 2-column */ | |
49 int leading_code_private_21; /* for private DIMENSION2 of 1-column */ | |
50 int leading_code_private_22; /* for private DIMENSION2 of 2-column */ | |
51 | |
52 /* Declaration of special charsets. */ | |
53 int charset_ascii; /* ASCII */ | |
54 int charset_composition; /* for a composite character */ | |
55 int charset_latin_iso8859_1; /* ISO8859-1 (Latin-1) */ | |
56 int charset_jisx0208_1978; /* JISX0208.1978 (Japanese Kanji old set) */ | |
57 int charset_jisx0208; /* JISX0208.1983 (Japanese Kanji) */ | |
58 int charset_katakana_jisx0201; /* JISX0201.Kana (Japanese Katakana) */ | |
59 int charset_latin_jisx0201; /* JISX0201.Roman (Japanese Roman) */ | |
60 int charset_big5_1; /* Big5 Level 1 (Chinese Traditional) */ | |
61 int charset_big5_2; /* Big5 Level 2 (Chinese Traditional) */ | |
62 | |
20720
f084bb8d535f
(min_composite_char): New variable.
Kenichi Handa <handa@m17n.org>
parents:
20705
diff
changeset
|
63 int min_composite_char; |
f084bb8d535f
(min_composite_char): New variable.
Kenichi Handa <handa@m17n.org>
parents:
20705
diff
changeset
|
64 |
17052 | 65 Lisp_Object Qcharset_table; |
66 | |
67 /* A char-table containing information of each character set. */ | |
68 Lisp_Object Vcharset_table; | |
69 | |
70 /* A vector of charset symbol indexed by charset-id. This is used | |
71 only for returning charset symbol from C functions. */ | |
72 Lisp_Object Vcharset_symbol_table; | |
73 | |
74 /* A list of charset symbols ever defined. */ | |
75 Lisp_Object Vcharset_list; | |
76 | |
22185
80a2aa51a6e1
Change term "character translation table" to
Kenichi Handa <handa@m17n.org>
parents:
22168
diff
changeset
|
77 /* Vector of translation table ever defined. |
80a2aa51a6e1
Change term "character translation table" to
Kenichi Handa <handa@m17n.org>
parents:
22168
diff
changeset
|
78 ID of a translation table is used to index this vector. */ |
80a2aa51a6e1
Change term "character translation table" to
Kenichi Handa <handa@m17n.org>
parents:
22168
diff
changeset
|
79 Lisp_Object Vtranslation_table_vector; |
20720
f084bb8d535f
(min_composite_char): New variable.
Kenichi Handa <handa@m17n.org>
parents:
20705
diff
changeset
|
80 |
23489
09201cebfa21
(Vauto_fill_chars, Qauto_fill_chars): New variables.
Kenichi Handa <handa@m17n.org>
parents:
23427
diff
changeset
|
81 /* A char-table for characters which may invoke auto-filling. */ |
09201cebfa21
(Vauto_fill_chars, Qauto_fill_chars): New variables.
Kenichi Handa <handa@m17n.org>
parents:
23427
diff
changeset
|
82 Lisp_Object Vauto_fill_chars; |
09201cebfa21
(Vauto_fill_chars, Qauto_fill_chars): New variables.
Kenichi Handa <handa@m17n.org>
parents:
23427
diff
changeset
|
83 |
09201cebfa21
(Vauto_fill_chars, Qauto_fill_chars): New variables.
Kenichi Handa <handa@m17n.org>
parents:
23427
diff
changeset
|
84 Lisp_Object Qauto_fill_chars; |
09201cebfa21
(Vauto_fill_chars, Qauto_fill_chars): New variables.
Kenichi Handa <handa@m17n.org>
parents:
23427
diff
changeset
|
85 |
17052 | 86 /* Tables used by macros BYTES_BY_CHAR_HEAD and WIDTH_BY_CHAR_HEAD. */ |
87 int bytes_by_char_head[256]; | |
88 int width_by_char_head[256]; | |
89 | |
90 /* Mapping table from ISO2022's charset (specified by DIMENSION, | |
91 CHARS, and FINAL-CHAR) to Emacs' charset. */ | |
92 int iso_charset_table[2][2][128]; | |
93 | |
17186
65bc06706714
Adjusted for the change of MAX_CHARSET.
Kenichi Handa <handa@m17n.org>
parents:
17121
diff
changeset
|
94 /* Table of pointers to the structure `cmpchar_info' indexed by |
65bc06706714
Adjusted for the change of MAX_CHARSET.
Kenichi Handa <handa@m17n.org>
parents:
17121
diff
changeset
|
95 CMPCHAR-ID. */ |
65bc06706714
Adjusted for the change of MAX_CHARSET.
Kenichi Handa <handa@m17n.org>
parents:
17121
diff
changeset
|
96 struct cmpchar_info **cmpchar_table; |
65bc06706714
Adjusted for the change of MAX_CHARSET.
Kenichi Handa <handa@m17n.org>
parents:
17121
diff
changeset
|
97 /* The current size of `cmpchar_table'. */ |
65bc06706714
Adjusted for the change of MAX_CHARSET.
Kenichi Handa <handa@m17n.org>
parents:
17121
diff
changeset
|
98 static int cmpchar_table_size; |
65bc06706714
Adjusted for the change of MAX_CHARSET.
Kenichi Handa <handa@m17n.org>
parents:
17121
diff
changeset
|
99 /* Number of the current composite characters. */ |
65bc06706714
Adjusted for the change of MAX_CHARSET.
Kenichi Handa <handa@m17n.org>
parents:
17121
diff
changeset
|
100 int n_cmpchars; |
65bc06706714
Adjusted for the change of MAX_CHARSET.
Kenichi Handa <handa@m17n.org>
parents:
17121
diff
changeset
|
101 |
17052 | 102 /* Variables used locally in the macro FETCH_MULTIBYTE_CHAR. */ |
103 unsigned char *_fetch_multibyte_char_p; | |
104 int _fetch_multibyte_char_len; | |
105 | |
20705
a949dc65fbea
(nonascii_insert_offset): Variable moved from cmds.c.
Richard M. Stallman <rms@gnu.org>
parents:
20636
diff
changeset
|
106 /* Offset to add to a non-ASCII value when inserting it. */ |
a949dc65fbea
(nonascii_insert_offset): Variable moved from cmds.c.
Richard M. Stallman <rms@gnu.org>
parents:
20636
diff
changeset
|
107 int nonascii_insert_offset; |
a949dc65fbea
(nonascii_insert_offset): Variable moved from cmds.c.
Richard M. Stallman <rms@gnu.org>
parents:
20636
diff
changeset
|
108 |
20890
c7cfd531cf2b
(Vnonascii_translate_table): New variable.
Richard M. Stallman <rms@gnu.org>
parents:
20833
diff
changeset
|
109 /* Translation table for converting non-ASCII unibyte characters |
c7cfd531cf2b
(Vnonascii_translate_table): New variable.
Richard M. Stallman <rms@gnu.org>
parents:
20833
diff
changeset
|
110 to multibyte codes, or nil. */ |
22121
6e79a15594ab
Change terms unify/unification to
Kenichi Handa <handa@m17n.org>
parents:
21718
diff
changeset
|
111 Lisp_Object Vnonascii_translation_table; |
20890
c7cfd531cf2b
(Vnonascii_translate_table): New variable.
Richard M. Stallman <rms@gnu.org>
parents:
20833
diff
changeset
|
112 |
22703
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
113 /* List of all possible generic characters. */ |
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
114 Lisp_Object Vgeneric_character_list; |
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
115 |
19384 | 116 #define min(X, Y) ((X) < (Y) ? (X) : (Y)) |
117 #define max(X, Y) ((X) > (Y) ? (X) : (Y)) | |
118 | |
20933
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
119 void |
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
120 invalid_character (c) |
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
121 int c; |
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
122 { |
23397
2fe04027242e
(invalid_character): Prepend `0' to octal
Kenichi Handa <handa@m17n.org>
parents:
23210
diff
changeset
|
123 error ("Invalid character: 0%o, %d, 0x%x", c, c, c); |
20933
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
124 } |
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
125 |
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
126 |
17052 | 127 /* Set STR a pointer to the multi-byte form of the character C. If C |
128 is not a composite character, the multi-byte form is set in WORKBUF | |
129 and STR points WORKBUF. The caller should allocate at least 4-byte | |
130 area at WORKBUF in advance. Returns the length of the multi-byte | |
17834
e154b943bbba
(non_ascii_char_to_string): Signal error if the
Kenichi Handa <handa@m17n.org>
parents:
17818
diff
changeset
|
131 form. If C is an invalid character to have a multi-byte form, |
e154b943bbba
(non_ascii_char_to_string): Signal error if the
Kenichi Handa <handa@m17n.org>
parents:
17818
diff
changeset
|
132 signal an error. |
17052 | 133 |
134 Use macro `CHAR_STRING (C, WORKBUF, STR)' instead of calling this | |
135 function directly if C can be an ASCII character. */ | |
136 | |
137 int | |
138 non_ascii_char_to_string (c, workbuf, str) | |
139 int c; | |
140 unsigned char *workbuf, **str; | |
141 { | |
17322
a7d9b8e167ca
(non_ascii_char_to_string, update_charset_table,
Kenichi Handa <handa@m17n.org>
parents:
17186
diff
changeset
|
142 int charset, c1, c2; |
17052 | 143 |
144 if (COMPOSITE_CHAR_P (c)) | |
145 { | |
146 int cmpchar_id = COMPOSITE_CHAR_ID (c); | |
147 | |
148 if (cmpchar_id < n_cmpchars) | |
149 { | |
150 *str = cmpchar_table[cmpchar_id]->data; | |
151 return cmpchar_table[cmpchar_id]->len; | |
152 } | |
153 else | |
154 { | |
20933
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
155 invalid_character (c); |
17052 | 156 } |
157 } | |
158 | |
159 SPLIT_NON_ASCII_CHAR (c, charset, c1, c2); | |
17834
e154b943bbba
(non_ascii_char_to_string): Signal error if the
Kenichi Handa <handa@m17n.org>
parents:
17818
diff
changeset
|
160 if (!charset |
e154b943bbba
(non_ascii_char_to_string): Signal error if the
Kenichi Handa <handa@m17n.org>
parents:
17818
diff
changeset
|
161 || ! CHARSET_DEFINED_P (charset) |
e154b943bbba
(non_ascii_char_to_string): Signal error if the
Kenichi Handa <handa@m17n.org>
parents:
17818
diff
changeset
|
162 || c1 >= 0 && c1 < 32 |
e154b943bbba
(non_ascii_char_to_string): Signal error if the
Kenichi Handa <handa@m17n.org>
parents:
17818
diff
changeset
|
163 || c2 >= 0 && c2 < 32) |
20933
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
164 invalid_character (c); |
17052 | 165 |
166 *str = workbuf; | |
167 *workbuf++ = CHARSET_LEADING_CODE_BASE (charset); | |
168 if (*workbuf = CHARSET_LEADING_CODE_EXT (charset)) | |
169 workbuf++; | |
170 *workbuf++ = c1 | 0x80; | |
17322
a7d9b8e167ca
(non_ascii_char_to_string, update_charset_table,
Kenichi Handa <handa@m17n.org>
parents:
17186
diff
changeset
|
171 if (c2 >= 0) |
17052 | 172 *workbuf++ = c2 | 0x80; |
173 | |
174 return (workbuf - *str); | |
175 } | |
176 | |
177 /* Return a non-ASCII character of which multi-byte form is at STR of | |
178 length LEN. If ACTUAL_LEN is not NULL, the actual length of the | |
22185
80a2aa51a6e1
Change term "character translation table" to
Kenichi Handa <handa@m17n.org>
parents:
22168
diff
changeset
|
179 multibyte form is set to the address ACTUAL_LEN. |
80a2aa51a6e1
Change term "character translation table" to
Kenichi Handa <handa@m17n.org>
parents:
22168
diff
changeset
|
180 |
80a2aa51a6e1
Change term "character translation table" to
Kenichi Handa <handa@m17n.org>
parents:
22168
diff
changeset
|
181 If exclude_tail_garbage is nonzero, ACTUAL_LEN excludes gabage |
80a2aa51a6e1
Change term "character translation table" to
Kenichi Handa <handa@m17n.org>
parents:
22168
diff
changeset
|
182 bytes following the non-ASCII character. |
17052 | 183 |
184 Use macro `STRING_CHAR (STR, LEN)' instead of calling this function | |
185 directly if STR can hold an ASCII character. */ | |
186 | |
21514 | 187 int |
22185
80a2aa51a6e1
Change term "character translation table" to
Kenichi Handa <handa@m17n.org>
parents:
22168
diff
changeset
|
188 string_to_non_ascii_char (str, len, actual_len, exclude_tail_garbage) |
21419
95aae2ff5fcd
(string_to_non_ascii_char, multibyte_form_length)
Karl Heuer <kwzh@gnu.org>
parents:
21255
diff
changeset
|
189 const unsigned char *str; |
22185
80a2aa51a6e1
Change term "character translation table" to
Kenichi Handa <handa@m17n.org>
parents:
22168
diff
changeset
|
190 int len, *actual_len, exclude_tail_garbage; |
17052 | 191 { |
192 int charset; | |
193 unsigned char c1, c2; | |
21445
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
194 register int c, bytes; |
17052 | 195 |
21445
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
196 c = *str; |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
197 bytes = 1; |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
198 |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
199 if (BASE_LEADING_CODE_P (c)) |
17052 | 200 { |
21445
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
201 while (bytes < len && ! CHAR_HEAD_P (str[bytes])) bytes++; |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
202 |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
203 if (c == LEADING_CODE_COMPOSITION) |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
204 { |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
205 int cmpchar_id = str_cmpchar_id (str, bytes); |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
206 |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
207 if (cmpchar_id >= 0) |
22333
8d612a46dac6
(string_to_non_ascii_char): Don't check the arg
Kenichi Handa <handa@m17n.org>
parents:
22289
diff
changeset
|
208 { |
8d612a46dac6
(string_to_non_ascii_char): Don't check the arg
Kenichi Handa <handa@m17n.org>
parents:
22289
diff
changeset
|
209 c = MAKE_COMPOSITE_CHAR (cmpchar_id); |
8d612a46dac6
(string_to_non_ascii_char): Don't check the arg
Kenichi Handa <handa@m17n.org>
parents:
22289
diff
changeset
|
210 if (exclude_tail_garbage) |
8d612a46dac6
(string_to_non_ascii_char): Don't check the arg
Kenichi Handa <handa@m17n.org>
parents:
22289
diff
changeset
|
211 bytes = cmpchar_table[cmpchar_id]->len; |
8d612a46dac6
(string_to_non_ascii_char): Don't check the arg
Kenichi Handa <handa@m17n.org>
parents:
22289
diff
changeset
|
212 } |
21445
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
213 } |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
214 else |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
215 { |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
216 int charset = c, c1, c2 = 0; |
22185
80a2aa51a6e1
Change term "character translation table" to
Kenichi Handa <handa@m17n.org>
parents:
22168
diff
changeset
|
217 int char_bytes = BYTES_BY_CHAR_HEAD (c); |
21445
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
218 |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
219 str++; |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
220 if (c >= LEADING_CODE_PRIVATE_11) |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
221 charset = *str++; |
23628
4a0a107fac9e
(string_to_non_ascii_char): Change the check for the
Kenichi Handa <handa@m17n.org>
parents:
23576
diff
changeset
|
222 if (CHARSET_DEFINED_P (charset) && char_bytes <= bytes) |
21445
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
223 { |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
224 c1 = *str++ & 0x7f; |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
225 if (CHARSET_DIMENSION (charset) == 2) |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
226 c2 = *str & 0x7F; |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
227 c = MAKE_NON_ASCII_CHAR (charset, c1, c2); |
22185
80a2aa51a6e1
Change term "character translation table" to
Kenichi Handa <handa@m17n.org>
parents:
22168
diff
changeset
|
228 if (exclude_tail_garbage) |
80a2aa51a6e1
Change term "character translation table" to
Kenichi Handa <handa@m17n.org>
parents:
22168
diff
changeset
|
229 bytes = char_bytes; |
21445
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
230 } |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
231 } |
17052 | 232 } |
233 | |
234 if (actual_len) | |
21445
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
235 *actual_len = bytes; |
17052 | 236 return c; |
237 } | |
238 | |
239 /* Return the length of the multi-byte form at string STR of length LEN. */ | |
240 int | |
241 multibyte_form_length (str, len) | |
21419
95aae2ff5fcd
(string_to_non_ascii_char, multibyte_form_length)
Karl Heuer <kwzh@gnu.org>
parents:
21255
diff
changeset
|
242 const unsigned char *str; |
17052 | 243 int len; |
244 { | |
21445
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
245 int bytes = 1; |
17052 | 246 |
21445
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
247 if (BASE_LEADING_CODE_P (*str)) |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
248 while (bytes < len && ! CHAR_HEAD_P (str[bytes])) bytes++; |
17052 | 249 |
21445
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
250 return bytes; |
17052 | 251 } |
252 | |
253 /* Check if string STR of length LEN contains valid multi-byte form of | |
254 a character. If valid, charset and position codes of the character | |
255 is set at *CHARSET, *C1, and *C2, and return 0. If not valid, | |
256 return -1. This should be used only in the macro SPLIT_STRING | |
257 which checks range of STR in advance. */ | |
258 | |
21514 | 259 int |
17052 | 260 split_non_ascii_string (str, len, charset, c1, c2) |
21419
95aae2ff5fcd
(string_to_non_ascii_char, multibyte_form_length)
Karl Heuer <kwzh@gnu.org>
parents:
21255
diff
changeset
|
261 register const unsigned char *str; |
95aae2ff5fcd
(string_to_non_ascii_char, multibyte_form_length)
Karl Heuer <kwzh@gnu.org>
parents:
21255
diff
changeset
|
262 register unsigned char *c1, *c2; |
17052 | 263 register int len, *charset; |
264 { | |
265 register unsigned int cs = *str++; | |
266 | |
267 if (cs == LEADING_CODE_COMPOSITION) | |
268 { | |
269 int cmpchar_id = str_cmpchar_id (str - 1, len); | |
270 | |
271 if (cmpchar_id < 0) | |
272 return -1; | |
273 *charset = cs, *c1 = cmpchar_id >> 7, *c2 = cmpchar_id & 0x7F; | |
274 } | |
275 else if ((cs < LEADING_CODE_PRIVATE_11 || (cs = *str++) >= 0xA0) | |
276 && CHARSET_DEFINED_P (cs)) | |
277 { | |
278 *charset = cs; | |
279 if (*str < 0xA0) | |
280 return -1; | |
281 *c1 = (*str++) & 0x7F; | |
282 if (CHARSET_DIMENSION (cs) == 2) | |
283 { | |
284 if (*str < 0xA0) | |
285 return -1; | |
286 *c2 = (*str++) & 0x7F; | |
287 } | |
288 } | |
289 else | |
290 return -1; | |
291 return 0; | |
292 } | |
293 | |
22185
80a2aa51a6e1
Change term "character translation table" to
Kenichi Handa <handa@m17n.org>
parents:
22168
diff
changeset
|
294 /* Translate character C by translation table TABLE. If C |
22121
6e79a15594ab
Change terms unify/unification to
Kenichi Handa <handa@m17n.org>
parents:
21718
diff
changeset
|
295 is negative, translate a character specified by CHARSET, C1, and C2 |
6e79a15594ab
Change terms unify/unification to
Kenichi Handa <handa@m17n.org>
parents:
21718
diff
changeset
|
296 (C1 and C2 are code points of the character). If no translation is |
6e79a15594ab
Change terms unify/unification to
Kenichi Handa <handa@m17n.org>
parents:
21718
diff
changeset
|
297 found in TABLE, return C. */ |
21514 | 298 int |
22121
6e79a15594ab
Change terms unify/unification to
Kenichi Handa <handa@m17n.org>
parents:
21718
diff
changeset
|
299 translate_char (table, c, charset, c1, c2) |
17727
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
300 Lisp_Object table; |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
301 int c, charset, c1, c2; |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
302 { |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
303 Lisp_Object ch; |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
304 int alt_charset, alt_c1, alt_c2, dimension; |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
305 |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
306 if (c < 0) c = MAKE_CHAR (charset, c1, c2); |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
307 if (!CHAR_TABLE_P (table) |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
308 || (ch = Faref (table, make_number (c)), !INTEGERP (ch)) |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
309 || XINT (ch) < 0) |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
310 return c; |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
311 |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
312 SPLIT_CHAR (XFASTINT (ch), alt_charset, alt_c1, alt_c2); |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
313 dimension = CHARSET_DIMENSION (alt_charset); |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
314 if (dimension == 1 && alt_c1 > 0 || dimension == 2 && alt_c2 > 0) |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
315 /* CH is not a generic character, just return it. */ |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
316 return XFASTINT (ch); |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
317 |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
318 /* Since CH is a generic character, we must return a specific |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
319 charater which has the same position codes as C from CH. */ |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
320 if (charset < 0) |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
321 SPLIT_CHAR (c, charset, c1, c2); |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
322 if (dimension != CHARSET_DIMENSION (charset)) |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
323 /* We can't make such a character because of dimension mismatch. */ |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
324 return c; |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
325 return MAKE_CHAR (alt_charset, c1, c2); |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
326 } |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
327 |
21034
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
328 /* Convert the unibyte character C to multibyte based on |
22121
6e79a15594ab
Change terms unify/unification to
Kenichi Handa <handa@m17n.org>
parents:
21718
diff
changeset
|
329 Vnonascii_translation_table or nonascii_insert_offset. If they can't |
21034
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
330 convert C to a valid multibyte character, convert it based on |
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
331 DEFAULT_NONASCII_INSERT_OFFSET which makes C a Latin-1 character. */ |
20705
a949dc65fbea
(nonascii_insert_offset): Variable moved from cmds.c.
Richard M. Stallman <rms@gnu.org>
parents:
20636
diff
changeset
|
332 |
21514 | 333 int |
20705
a949dc65fbea
(nonascii_insert_offset): Variable moved from cmds.c.
Richard M. Stallman <rms@gnu.org>
parents:
20636
diff
changeset
|
334 unibyte_char_to_multibyte (c) |
a949dc65fbea
(nonascii_insert_offset): Variable moved from cmds.c.
Richard M. Stallman <rms@gnu.org>
parents:
20636
diff
changeset
|
335 int c; |
a949dc65fbea
(nonascii_insert_offset): Variable moved from cmds.c.
Richard M. Stallman <rms@gnu.org>
parents:
20636
diff
changeset
|
336 { |
23154
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
337 if (c < 0400) |
20705
a949dc65fbea
(nonascii_insert_offset): Variable moved from cmds.c.
Richard M. Stallman <rms@gnu.org>
parents:
20636
diff
changeset
|
338 { |
21034
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
339 int c_save = c; |
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
340 |
22121
6e79a15594ab
Change terms unify/unification to
Kenichi Handa <handa@m17n.org>
parents:
21718
diff
changeset
|
341 if (! NILP (Vnonascii_translation_table)) |
23154
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
342 { |
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
343 c = XINT (Faref (Vnonascii_translation_table, make_number (c))); |
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
344 if (c >= 0400 && ! VALID_MULTIBYTE_CHAR_P (c)) |
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
345 c = c_save + DEFAULT_NONASCII_INSERT_OFFSET; |
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
346 } |
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
347 else if (c >= 0240 && nonascii_insert_offset > 0) |
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
348 { |
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
349 c += nonascii_insert_offset; |
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
350 if (c < 0400 || ! VALID_MULTIBYTE_CHAR_P (c)) |
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
351 c = c_save + DEFAULT_NONASCII_INSERT_OFFSET; |
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
352 } |
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
353 else if (c >= 0240) |
21034
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
354 c = c_save + DEFAULT_NONASCII_INSERT_OFFSET; |
20705
a949dc65fbea
(nonascii_insert_offset): Variable moved from cmds.c.
Richard M. Stallman <rms@gnu.org>
parents:
20636
diff
changeset
|
355 } |
a949dc65fbea
(nonascii_insert_offset): Variable moved from cmds.c.
Richard M. Stallman <rms@gnu.org>
parents:
20636
diff
changeset
|
356 return c; |
a949dc65fbea
(nonascii_insert_offset): Variable moved from cmds.c.
Richard M. Stallman <rms@gnu.org>
parents:
20636
diff
changeset
|
357 } |
22927
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
358 |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
359 |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
360 /* Convert the multibyte character C to unibyte 8-bit character based |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
361 on Vnonascii_translation_table or nonascii_insert_offset. If |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
362 REV_TBL is non-nil, it should be a reverse table of |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
363 Vnonascii_translation_table, i.e. what given by: |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
364 Fchar_table_extra_slot (Vnonascii_translation_table, make_number (0)) */ |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
365 |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
366 int |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
367 multibyte_char_to_unibyte (c, rev_tbl) |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
368 int c; |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
369 Lisp_Object rev_tbl; |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
370 { |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
371 if (!SINGLE_BYTE_CHAR_P (c)) |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
372 { |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
373 int c_save = c; |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
374 |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
375 if (! CHAR_TABLE_P (rev_tbl) |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
376 && CHAR_TABLE_P (Vnonascii_translation_table)) |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
377 rev_tbl = Fchar_table_extra_slot (Vnonascii_translation_table, |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
378 make_number (0)); |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
379 if (CHAR_TABLE_P (rev_tbl)) |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
380 { |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
381 Lisp_Object temp; |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
382 temp = Faref (rev_tbl, make_number (c)); |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
383 if (INTEGERP (temp)) |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
384 c = XINT (temp); |
23154
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
385 if (c >= 256) |
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
386 c = (c_save & 0177) + 0200; |
22927
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
387 } |
23154
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
388 else |
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
389 { |
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
390 if (nonascii_insert_offset > 0) |
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
391 c -= nonascii_insert_offset; |
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
392 if (c < 128 || c >= 256) |
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
393 c = (c_save & 0177) + 0200; |
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
394 } |
22927
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
395 } |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
396 |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
397 return c; |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
398 } |
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
399 |
20705
a949dc65fbea
(nonascii_insert_offset): Variable moved from cmds.c.
Richard M. Stallman <rms@gnu.org>
parents:
20636
diff
changeset
|
400 |
17052 | 401 /* Update the table Vcharset_table with the given arguments (see the |
402 document of `define-charset' for the meaning of each argument). | |
403 Several other table contents are also updated. The caller should | |
404 check the validity of CHARSET-ID and the remaining arguments in | |
405 advance. */ | |
406 | |
407 void | |
408 update_charset_table (charset_id, dimension, chars, width, direction, | |
409 iso_final_char, iso_graphic_plane, | |
410 short_name, long_name, description) | |
411 Lisp_Object charset_id, dimension, chars, width, direction; | |
412 Lisp_Object iso_final_char, iso_graphic_plane; | |
413 Lisp_Object short_name, long_name, description; | |
414 { | |
415 int charset = XINT (charset_id); | |
416 int bytes; | |
417 unsigned char leading_code_base, leading_code_ext; | |
418 | |
17322
a7d9b8e167ca
(non_ascii_char_to_string, update_charset_table,
Kenichi Handa <handa@m17n.org>
parents:
17186
diff
changeset
|
419 if (NILP (CHARSET_TABLE_ENTRY (charset))) |
a7d9b8e167ca
(non_ascii_char_to_string, update_charset_table,
Kenichi Handa <handa@m17n.org>
parents:
17186
diff
changeset
|
420 CHARSET_TABLE_ENTRY (charset) |
a7d9b8e167ca
(non_ascii_char_to_string, update_charset_table,
Kenichi Handa <handa@m17n.org>
parents:
17186
diff
changeset
|
421 = Fmake_vector (make_number (CHARSET_MAX_IDX), Qnil); |
17052 | 422 |
423 /* Get byte length of multibyte form, base leading-code, and | |
424 extended leading-code of the charset. See the comment under the | |
425 title "GENERAL NOTE on CHARACTER SET (CHARSET)" in charset.h. */ | |
426 bytes = XINT (dimension); | |
427 if (charset < MIN_CHARSET_PRIVATE_DIMENSION1) | |
428 { | |
429 /* Official charset, it doesn't have an extended leading-code. */ | |
430 if (charset != CHARSET_ASCII) | |
431 bytes += 1; /* For a base leading-code. */ | |
432 leading_code_base = charset; | |
433 leading_code_ext = 0; | |
434 } | |
435 else | |
436 { | |
437 /* Private charset. */ | |
438 bytes += 2; /* For base and extended leading-codes. */ | |
439 leading_code_base | |
440 = (charset < LEADING_CODE_EXT_12 | |
441 ? LEADING_CODE_PRIVATE_11 | |
442 : (charset < LEADING_CODE_EXT_21 | |
443 ? LEADING_CODE_PRIVATE_12 | |
444 : (charset < LEADING_CODE_EXT_22 | |
445 ? LEADING_CODE_PRIVATE_21 | |
446 : LEADING_CODE_PRIVATE_22))); | |
447 leading_code_ext = charset; | |
448 } | |
449 | |
23628
4a0a107fac9e
(string_to_non_ascii_char): Change the check for the
Kenichi Handa <handa@m17n.org>
parents:
23576
diff
changeset
|
450 if (BYTES_BY_CHAR_HEAD (leading_code_base) != bytes) |
4a0a107fac9e
(string_to_non_ascii_char): Change the check for the
Kenichi Handa <handa@m17n.org>
parents:
23576
diff
changeset
|
451 error ("Invalid dimension for the charset-ID %d", charset); |
4a0a107fac9e
(string_to_non_ascii_char): Change the check for the
Kenichi Handa <handa@m17n.org>
parents:
23576
diff
changeset
|
452 |
17052 | 453 CHARSET_TABLE_INFO (charset, CHARSET_ID_IDX) = charset_id; |
454 CHARSET_TABLE_INFO (charset, CHARSET_BYTES_IDX) = make_number (bytes); | |
455 CHARSET_TABLE_INFO (charset, CHARSET_DIMENSION_IDX) = dimension; | |
456 CHARSET_TABLE_INFO (charset, CHARSET_CHARS_IDX) = chars; | |
457 CHARSET_TABLE_INFO (charset, CHARSET_WIDTH_IDX) = width; | |
458 CHARSET_TABLE_INFO (charset, CHARSET_DIRECTION_IDX) = direction; | |
459 CHARSET_TABLE_INFO (charset, CHARSET_LEADING_CODE_BASE_IDX) | |
460 = make_number (leading_code_base); | |
461 CHARSET_TABLE_INFO (charset, CHARSET_LEADING_CODE_EXT_IDX) | |
462 = make_number (leading_code_ext); | |
463 CHARSET_TABLE_INFO (charset, CHARSET_ISO_FINAL_CHAR_IDX) = iso_final_char; | |
464 CHARSET_TABLE_INFO (charset, CHARSET_ISO_GRAPHIC_PLANE_IDX) | |
465 = iso_graphic_plane; | |
466 CHARSET_TABLE_INFO (charset, CHARSET_SHORT_NAME_IDX) = short_name; | |
467 CHARSET_TABLE_INFO (charset, CHARSET_LONG_NAME_IDX) = long_name; | |
468 CHARSET_TABLE_INFO (charset, CHARSET_DESCRIPTION_IDX) = description; | |
469 CHARSET_TABLE_INFO (charset, CHARSET_PLIST_IDX) = Qnil; | |
470 | |
471 { | |
472 /* If we have already defined a charset which has the same | |
473 DIMENSION, CHARS and ISO-FINAL-CHAR but the different | |
474 DIRECTION, we must update the entry REVERSE-CHARSET of both | |
475 charsets. If there's no such charset, the value of the entry | |
476 is set to nil. */ | |
477 int i; | |
478 | |
17186
65bc06706714
Adjusted for the change of MAX_CHARSET.
Kenichi Handa <handa@m17n.org>
parents:
17121
diff
changeset
|
479 for (i = 0; i <= MAX_CHARSET; i++) |
17052 | 480 if (!NILP (CHARSET_TABLE_ENTRY (i))) |
481 { | |
482 if (CHARSET_DIMENSION (i) == XINT (dimension) | |
483 && CHARSET_CHARS (i) == XINT (chars) | |
484 && CHARSET_ISO_FINAL_CHAR (i) == XINT (iso_final_char) | |
485 && CHARSET_DIRECTION (i) != XINT (direction)) | |
486 { | |
487 CHARSET_TABLE_INFO (charset, CHARSET_REVERSE_CHARSET_IDX) | |
488 = make_number (i); | |
489 CHARSET_TABLE_INFO (i, CHARSET_REVERSE_CHARSET_IDX) = charset_id; | |
490 break; | |
491 } | |
492 } | |
17186
65bc06706714
Adjusted for the change of MAX_CHARSET.
Kenichi Handa <handa@m17n.org>
parents:
17121
diff
changeset
|
493 if (i > MAX_CHARSET) |
17052 | 494 /* No such a charset. */ |
495 CHARSET_TABLE_INFO (charset, CHARSET_REVERSE_CHARSET_IDX) | |
496 = make_number (-1); | |
497 } | |
498 | |
499 if (charset != CHARSET_ASCII | |
500 && charset < MIN_CHARSET_PRIVATE_DIMENSION1) | |
501 { | |
502 width_by_char_head[leading_code_base] = XINT (width); | |
503 | |
504 /* Update table emacs_code_class. */ | |
505 emacs_code_class[charset] = (bytes == 2 | |
506 ? EMACS_leading_code_2 | |
507 : (bytes == 3 | |
508 ? EMACS_leading_code_3 | |
509 : EMACS_leading_code_4)); | |
510 } | |
511 | |
512 /* Update table iso_charset_table. */ | |
513 if (ISO_CHARSET_TABLE (dimension, chars, iso_final_char) < 0) | |
514 ISO_CHARSET_TABLE (dimension, chars, iso_final_char) = charset; | |
515 } | |
516 | |
517 #ifdef emacs | |
518 | |
519 /* Return charset id of CHARSET_SYMBOL, or return -1 if CHARSET_SYMBOL | |
520 is invalid. */ | |
521 int | |
522 get_charset_id (charset_symbol) | |
523 Lisp_Object charset_symbol; | |
524 { | |
525 Lisp_Object val; | |
526 int charset; | |
527 | |
528 return ((SYMBOLP (charset_symbol) | |
529 && (val = Fget (charset_symbol, Qcharset), VECTORP (val)) | |
530 && (charset = XINT (XVECTOR (val)->contents[CHARSET_ID_IDX]), | |
531 CHARSET_VALID_P (charset))) | |
532 ? charset : -1); | |
533 } | |
534 | |
535 /* Return an identification number for a new private charset of | |
536 DIMENSION and WIDTH. If there's no more room for the new charset, | |
537 return 0. */ | |
538 Lisp_Object | |
539 get_new_private_charset_id (dimension, width) | |
540 int dimension, width; | |
541 { | |
542 int charset, from, to; | |
543 | |
544 if (dimension == 1) | |
545 { | |
546 if (width == 1) | |
547 from = LEADING_CODE_EXT_11, to = LEADING_CODE_EXT_12; | |
548 else | |
549 from = LEADING_CODE_EXT_12, to = LEADING_CODE_EXT_21; | |
550 } | |
551 else | |
552 { | |
553 if (width == 1) | |
554 from = LEADING_CODE_EXT_21, to = LEADING_CODE_EXT_22; | |
555 else | |
20720
f084bb8d535f
(min_composite_char): New variable.
Kenichi Handa <handa@m17n.org>
parents:
20705
diff
changeset
|
556 from = LEADING_CODE_EXT_22, to = LEADING_CODE_EXT_MAX + 1; |
17052 | 557 } |
558 | |
559 for (charset = from; charset < to; charset++) | |
560 if (!CHARSET_DEFINED_P (charset)) break; | |
561 | |
562 return make_number (charset < to ? charset : 0); | |
563 } | |
564 | |
565 DEFUN ("define-charset", Fdefine_charset, Sdefine_charset, 3, 3, 0, | |
566 "Define CHARSET-ID as the identification number of CHARSET with INFO-VECTOR.\n\ | |
17727
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
567 If CHARSET-ID is nil, it is decided automatically, which means CHARSET is\n\ |
17052 | 568 treated as a private charset.\n\ |
569 INFO-VECTOR is a vector of the format:\n\ | |
570 [DIMENSION CHARS WIDTH DIRECTION ISO-FINAL-CHAR ISO-GRAPHIC-PLANE\n\ | |
571 SHORT-NAME LONG-NAME DESCRIPTION]\n\ | |
572 The meanings of each elements is as follows:\n\ | |
573 DIMENSION (integer) is the number of bytes to represent a character: 1 or 2.\n\ | |
574 CHARS (integer) is the number of characters in a dimension: 94 or 96.\n\ | |
575 WIDTH (integer) is the number of columns a character in the charset\n\ | |
576 occupies on the screen: one of 0, 1, and 2.\n\ | |
577 \n\ | |
578 DIRECTION (integer) is the rendering direction of characters in the\n\ | |
22774
a0909e59257d
(Fdefine_charset): Fix doc-string.
Kenichi Handa <handa@m17n.org>
parents:
22739
diff
changeset
|
579 charset when rendering. If 0, render from left to right, else\n\ |
a0909e59257d
(Fdefine_charset): Fix doc-string.
Kenichi Handa <handa@m17n.org>
parents:
22739
diff
changeset
|
580 render from right to left.\n\ |
17052 | 581 \n\ |
582 ISO-FINAL-CHAR (character) is the final character of the\n\ | |
583 corresponding ISO 2022 charset.\n\ | |
584 \n\ | |
585 ISO-GRAPHIC-PLANE (integer) is the graphic plane to be invoked\n\ | |
586 while encoding to variants of ISO 2022 coding system, one of the\n\ | |
587 following: 0/graphic-plane-left(GL), 1/graphic-plane-right(GR).\n\ | |
588 \n\ | |
589 SHORT-NAME (string) is the short name to refer to the charset.\n\ | |
590 \n\ | |
591 LONG-NAME (string) is the long name to refer to the charset.\n\ | |
592 \n\ | |
593 DESCRIPTION (string) is the description string of the charset.") | |
594 (charset_id, charset_symbol, info_vector) | |
595 Lisp_Object charset_id, charset_symbol, info_vector; | |
596 { | |
597 Lisp_Object *vec; | |
598 | |
599 if (!NILP (charset_id)) | |
600 CHECK_NUMBER (charset_id, 0); | |
601 CHECK_SYMBOL (charset_symbol, 1); | |
602 CHECK_VECTOR (info_vector, 2); | |
603 | |
604 if (! NILP (charset_id)) | |
605 { | |
606 if (! CHARSET_VALID_P (XINT (charset_id))) | |
607 error ("Invalid CHARSET: %d", XINT (charset_id)); | |
608 else if (CHARSET_DEFINED_P (XINT (charset_id))) | |
609 error ("Already defined charset: %d", XINT (charset_id)); | |
610 } | |
611 | |
612 vec = XVECTOR (info_vector)->contents; | |
613 if (XVECTOR (info_vector)->size != 9 | |
614 || !INTEGERP (vec[0]) || !(XINT (vec[0]) == 1 || XINT (vec[0]) == 2) | |
615 || !INTEGERP (vec[1]) || !(XINT (vec[1]) == 94 || XINT (vec[1]) == 96) | |
616 || !INTEGERP (vec[2]) || !(XINT (vec[2]) == 1 || XINT (vec[2]) == 2) | |
617 || !INTEGERP (vec[3]) || !(XINT (vec[3]) == 0 || XINT (vec[3]) == 1) | |
618 || !INTEGERP (vec[4]) || !(XINT (vec[4]) >= '0' && XINT (vec[4]) <= '~') | |
619 || !INTEGERP (vec[5]) || !(XINT (vec[5]) == 0 || XINT (vec[5]) == 1) | |
620 || !STRINGP (vec[6]) | |
621 || !STRINGP (vec[7]) | |
622 || !STRINGP (vec[8])) | |
623 error ("Invalid info-vector argument for defining charset %s", | |
624 XSYMBOL (charset_symbol)->name->data); | |
625 | |
626 if (NILP (charset_id)) | |
627 { | |
628 charset_id = get_new_private_charset_id (XINT (vec[0]), XINT (vec[2])); | |
629 if (XINT (charset_id) == 0) | |
630 error ("There's no room for a new private charset %s", | |
631 XSYMBOL (charset_symbol)->name->data); | |
632 } | |
633 | |
634 update_charset_table (charset_id, vec[0], vec[1], vec[2], vec[3], | |
635 vec[4], vec[5], vec[6], vec[7], vec[8]); | |
17322
a7d9b8e167ca
(non_ascii_char_to_string, update_charset_table,
Kenichi Handa <handa@m17n.org>
parents:
17186
diff
changeset
|
636 Fput (charset_symbol, Qcharset, CHARSET_TABLE_ENTRY (XINT (charset_id))); |
17052 | 637 CHARSET_SYMBOL (XINT (charset_id)) = charset_symbol; |
638 Vcharset_list = Fcons (charset_symbol, Vcharset_list); | |
639 return Qnil; | |
640 } | |
641 | |
22703
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
642 DEFUN ("generic-character-list", Fgeneric_character_list, |
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
643 Sgeneric_character_list, 0, 0, 0, |
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
644 "Return a list of all possible generic characters.\n\ |
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
645 It includes a generic character for a charset not yet defined.") |
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
646 () |
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
647 { |
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
648 return Vgeneric_character_list; |
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
649 } |
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
650 |
20435
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
651 DEFUN ("get-unused-iso-final-char", Fget_unused_iso_final_char, |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
652 Sget_unused_iso_final_char, 2, 2, 0, |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
653 "Return an unsed ISO's final char for a charset of DIMENISION and CHARS.\n\ |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
654 DIMENSION is the number of bytes to represent a character: 1 or 2.\n\ |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
655 CHARS is the number of characters in a dimension: 94 or 96.\n\ |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
656 \n\ |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
657 This final char is for private use, thus the range is `0' (48) .. `?' (63).\n\ |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
658 If there's no unused final char for the specified kind of charset,\n\ |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
659 return nil.") |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
660 (dimension, chars) |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
661 Lisp_Object dimension, chars; |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
662 { |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
663 int final_char; |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
664 |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
665 CHECK_NUMBER (dimension, 0); |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
666 CHECK_NUMBER (chars, 1); |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
667 if (XINT (dimension) != 1 && XINT (dimension) != 2) |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
668 error ("Invalid charset dimension %d, it should be 1 or 2", |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
669 XINT (dimension)); |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
670 if (XINT (chars) != 94 && XINT (chars) != 96) |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
671 error ("Invalid charset chars %d, it should be 94 or 96", |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
672 XINT (chars)); |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
673 for (final_char = '0'; final_char <= '?'; final_char++) |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
674 { |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
675 if (ISO_CHARSET_TABLE (dimension, chars, make_number (final_char)) < 0) |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
676 break; |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
677 } |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
678 return (final_char <= '?' ? make_number (final_char) : Qnil); |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
679 } |
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
680 |
17052 | 681 DEFUN ("declare-equiv-charset", Fdeclare_equiv_charset, Sdeclare_equiv_charset, |
682 4, 4, 0, | |
683 "Declare a charset of DIMENSION, CHARS, FINAL-CHAR is the same as CHARSET.\n\ | |
684 CHARSET should be defined by `defined-charset' in advance.") | |
685 (dimension, chars, final_char, charset_symbol) | |
686 Lisp_Object dimension, chars, final_char, charset_symbol; | |
687 { | |
688 int charset; | |
689 | |
690 CHECK_NUMBER (dimension, 0); | |
691 CHECK_NUMBER (chars, 1); | |
692 CHECK_NUMBER (final_char, 2); | |
693 CHECK_SYMBOL (charset_symbol, 3); | |
694 | |
695 if (XINT (dimension) != 1 && XINT (dimension) != 2) | |
696 error ("Invalid DIMENSION %d, it should be 1 or 2", XINT (dimension)); | |
697 if (XINT (chars) != 94 && XINT (chars) != 96) | |
698 error ("Invalid CHARS %d, it should be 94 or 96", XINT (chars)); | |
699 if (XINT (final_char) < '0' || XFASTINT (final_char) > '~') | |
700 error ("Invalid FINAL-CHAR %c, it should be `0'..`~'", XINT (chars)); | |
701 if ((charset = get_charset_id (charset_symbol)) < 0) | |
702 error ("Invalid charset %s", XSYMBOL (charset_symbol)->name->data); | |
703 | |
704 ISO_CHARSET_TABLE (dimension, chars, final_char) = charset; | |
705 return Qnil; | |
706 } | |
707 | |
708 /* Return number of different charsets in STR of length LEN. In | |
709 addition, for each found charset N, CHARSETS[N] is set 1. The | |
18003
ac148c939dec
(Ffind_charset_string): The variable CHARSETS is
Kenichi Handa <handa@m17n.org>
parents:
17880
diff
changeset
|
710 caller should allocate CHARSETS (MAX_CHARSET + 1 elements) in advance. |
22168
2156ac6d054f
(find_charset_in_str): New arg CMPCHARP.
Kenichi Handa <handa@m17n.org>
parents:
22121
diff
changeset
|
711 It may lookup a translation table TABLE if supplied. |
2156ac6d054f
(find_charset_in_str): New arg CMPCHARP.
Kenichi Handa <handa@m17n.org>
parents:
22121
diff
changeset
|
712 |
2156ac6d054f
(find_charset_in_str): New arg CMPCHARP.
Kenichi Handa <handa@m17n.org>
parents:
22121
diff
changeset
|
713 If CMPCHARP is nonzero and some composite character is found, |
2156ac6d054f
(find_charset_in_str): New arg CMPCHARP.
Kenichi Handa <handa@m17n.org>
parents:
22121
diff
changeset
|
714 CHARSETS[128] is also set 1 and the returned number is incremented |
2156ac6d054f
(find_charset_in_str): New arg CMPCHARP.
Kenichi Handa <handa@m17n.org>
parents:
22121
diff
changeset
|
715 by 1. */ |
17052 | 716 |
717 int | |
22168
2156ac6d054f
(find_charset_in_str): New arg CMPCHARP.
Kenichi Handa <handa@m17n.org>
parents:
22121
diff
changeset
|
718 find_charset_in_str (str, len, charsets, table, cmpcharp) |
17880
06f58d8a59ba
(Ffind_charset_region): Change the declaration of
Kenichi Handa <handa@m17n.org>
parents:
17863
diff
changeset
|
719 unsigned char *str; |
06f58d8a59ba
(Ffind_charset_region): Change the declaration of
Kenichi Handa <handa@m17n.org>
parents:
17863
diff
changeset
|
720 int len, *charsets; |
17727
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
721 Lisp_Object table; |
22168
2156ac6d054f
(find_charset_in_str): New arg CMPCHARP.
Kenichi Handa <handa@m17n.org>
parents:
22121
diff
changeset
|
722 int cmpcharp; |
17052 | 723 { |
20228
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
724 register int num = 0, c; |
17052 | 725 |
17727
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
726 if (! CHAR_TABLE_P (table)) |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
727 table = Qnil; |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
728 |
17052 | 729 while (len > 0) |
730 { | |
19983
a62008636710
(find_charset_in_str): Return also charsets in
Kenichi Handa <handa@m17n.org>
parents:
19444
diff
changeset
|
731 int bytes, charset; |
20228
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
732 c = *str; |
17727
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
733 |
20228
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
734 if (c == LEADING_CODE_COMPOSITION) |
19983
a62008636710
(find_charset_in_str): Return also charsets in
Kenichi Handa <handa@m17n.org>
parents:
19444
diff
changeset
|
735 { |
20228
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
736 int cmpchar_id = str_cmpchar_id (str, len); |
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
737 GLYPH *glyph; |
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
738 |
22168
2156ac6d054f
(find_charset_in_str): New arg CMPCHARP.
Kenichi Handa <handa@m17n.org>
parents:
22121
diff
changeset
|
739 if (cmpchar_id >= 0) |
19983
a62008636710
(find_charset_in_str): Return also charsets in
Kenichi Handa <handa@m17n.org>
parents:
19444
diff
changeset
|
740 { |
23427
4acd4faa545a
(Fstring): Call make_string instead of
Kenichi Handa <handa@m17n.org>
parents:
23397
diff
changeset
|
741 struct cmpchar_info *cmp_p = cmpchar_table[cmpchar_id]; |
20228
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
742 int i; |
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
743 |
23427
4acd4faa545a
(Fstring): Call make_string instead of
Kenichi Handa <handa@m17n.org>
parents:
23397
diff
changeset
|
744 for (i = 0; i < cmp_p->glyph_len; i++) |
20228
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
745 { |
23427
4acd4faa545a
(Fstring): Call make_string instead of
Kenichi Handa <handa@m17n.org>
parents:
23397
diff
changeset
|
746 c = cmp_p->glyph[i]; |
20228
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
747 if (!NILP (table)) |
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
748 { |
22121
6e79a15594ab
Change terms unify/unification to
Kenichi Handa <handa@m17n.org>
parents:
21718
diff
changeset
|
749 if ((c = translate_char (table, c, 0, 0, 0)) < 0) |
23427
4acd4faa545a
(Fstring): Call make_string instead of
Kenichi Handa <handa@m17n.org>
parents:
23397
diff
changeset
|
750 c = cmp_p->glyph[i]; |
20228
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
751 } |
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
752 if ((charset = CHAR_CHARSET (c)) < 0) |
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
753 charset = CHARSET_ASCII; |
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
754 if (!charsets[charset]) |
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
755 { |
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
756 charsets[charset] = 1; |
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
757 num += 1; |
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
758 } |
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
759 } |
23427
4acd4faa545a
(Fstring): Call make_string instead of
Kenichi Handa <handa@m17n.org>
parents:
23397
diff
changeset
|
760 str += cmp_p->len; |
4acd4faa545a
(Fstring): Call make_string instead of
Kenichi Handa <handa@m17n.org>
parents:
23397
diff
changeset
|
761 len -= cmp_p->len; |
4acd4faa545a
(Fstring): Call make_string instead of
Kenichi Handa <handa@m17n.org>
parents:
23397
diff
changeset
|
762 if (cmpcharp && !charsets[CHARSET_COMPOSITION]) |
4acd4faa545a
(Fstring): Call make_string instead of
Kenichi Handa <handa@m17n.org>
parents:
23397
diff
changeset
|
763 { |
4acd4faa545a
(Fstring): Call make_string instead of
Kenichi Handa <handa@m17n.org>
parents:
23397
diff
changeset
|
764 charsets[CHARSET_COMPOSITION] = 1; |
4acd4faa545a
(Fstring): Call make_string instead of
Kenichi Handa <handa@m17n.org>
parents:
23397
diff
changeset
|
765 num += 1; |
4acd4faa545a
(Fstring): Call make_string instead of
Kenichi Handa <handa@m17n.org>
parents:
23397
diff
changeset
|
766 } |
20228
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
767 continue; |
19983
a62008636710
(find_charset_in_str): Return also charsets in
Kenichi Handa <handa@m17n.org>
parents:
19444
diff
changeset
|
768 } |
20228
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
769 |
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
770 charset = CHARSET_ASCII; |
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
771 bytes = 1; |
19983
a62008636710
(find_charset_in_str): Return also charsets in
Kenichi Handa <handa@m17n.org>
parents:
19444
diff
changeset
|
772 } |
a62008636710
(find_charset_in_str): Return also charsets in
Kenichi Handa <handa@m17n.org>
parents:
19444
diff
changeset
|
773 else |
17727
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
774 { |
20228
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
775 c = STRING_CHAR_AND_LENGTH (str, len, bytes); |
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
776 if (! NILP (table)) |
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
777 { |
22121
6e79a15594ab
Change terms unify/unification to
Kenichi Handa <handa@m17n.org>
parents:
21718
diff
changeset
|
778 int c1 = translate_char (table, c, 0, 0, 0); |
20228
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
779 if (c1 >= 0) |
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
780 c = c1; |
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
781 } |
acb7aa0aa71f
(find_charset_in_str): Handle the case that STR
Kenichi Handa <handa@m17n.org>
parents:
20188
diff
changeset
|
782 charset = CHAR_CHARSET (c); |
17727
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
783 } |
17052 | 784 |
785 if (!charsets[charset]) | |
786 { | |
787 charsets[charset] = 1; | |
788 num += 1; | |
789 } | |
790 str += bytes; | |
791 len -= bytes; | |
792 } | |
793 return num; | |
794 } | |
795 | |
796 DEFUN ("find-charset-region", Ffind_charset_region, Sfind_charset_region, | |
17727
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
797 2, 3, 0, |
17052 | 798 "Return a list of charsets in the region between BEG and END.\n\ |
17727
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
799 BEG and END are buffer positions.\n\ |
23427
4acd4faa545a
(Fstring): Call make_string instead of
Kenichi Handa <handa@m17n.org>
parents:
23397
diff
changeset
|
800 If the region contains any composite character,\n\ |
4acd4faa545a
(Fstring): Call make_string instead of
Kenichi Handa <handa@m17n.org>
parents:
23397
diff
changeset
|
801 `composition' is included in the returned list.\n\ |
22121
6e79a15594ab
Change terms unify/unification to
Kenichi Handa <handa@m17n.org>
parents:
21718
diff
changeset
|
802 Optional arg TABLE if non-nil is a translation table to look up.") |
17727
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
803 (beg, end, table) |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
804 Lisp_Object beg, end, table; |
17052 | 805 { |
17880
06f58d8a59ba
(Ffind_charset_region): Change the declaration of
Kenichi Handa <handa@m17n.org>
parents:
17863
diff
changeset
|
806 int charsets[MAX_CHARSET + 1]; |
20534
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
807 int from, from_byte, to, stop, stop_byte, i; |
17052 | 808 Lisp_Object val; |
809 | |
810 validate_region (&beg, &end); | |
811 from = XFASTINT (beg); | |
812 stop = to = XFASTINT (end); | |
20534
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
813 |
23210
53c330e846d0
(Ffind_charset_region): Optimization for unibyte buffer.
Kenichi Handa <handa@m17n.org>
parents:
23154
diff
changeset
|
814 if (NILP (current_buffer->enable_multibyte_characters)) |
53c330e846d0
(Ffind_charset_region): Optimization for unibyte buffer.
Kenichi Handa <handa@m17n.org>
parents:
23154
diff
changeset
|
815 return (from == to |
53c330e846d0
(Ffind_charset_region): Optimization for unibyte buffer.
Kenichi Handa <handa@m17n.org>
parents:
23154
diff
changeset
|
816 ? Qnil |
53c330e846d0
(Ffind_charset_region): Optimization for unibyte buffer.
Kenichi Handa <handa@m17n.org>
parents:
23154
diff
changeset
|
817 : Fcons (Qascii, Qnil)); |
53c330e846d0
(Ffind_charset_region): Optimization for unibyte buffer.
Kenichi Handa <handa@m17n.org>
parents:
23154
diff
changeset
|
818 |
17052 | 819 if (from < GPT && GPT < to) |
20534
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
820 { |
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
821 stop = GPT; |
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
822 stop_byte = GPT_BYTE; |
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
823 } |
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
824 else |
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
825 stop_byte = CHAR_TO_BYTE (stop); |
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
826 |
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
827 from_byte = CHAR_TO_BYTE (from); |
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
828 |
17880
06f58d8a59ba
(Ffind_charset_region): Change the declaration of
Kenichi Handa <handa@m17n.org>
parents:
17863
diff
changeset
|
829 bzero (charsets, (MAX_CHARSET + 1) * sizeof (int)); |
17052 | 830 while (1) |
831 { | |
20534
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
832 find_charset_in_str (BYTE_POS_ADDR (from_byte), stop_byte - from_byte, |
23427
4acd4faa545a
(Fstring): Call make_string instead of
Kenichi Handa <handa@m17n.org>
parents:
23397
diff
changeset
|
833 charsets, table, 1); |
17052 | 834 if (stop < to) |
20534
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
835 { |
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
836 from = stop, from_byte = stop_byte; |
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
837 stop = to, stop_byte = CHAR_TO_BYTE (stop); |
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
838 } |
17052 | 839 else |
840 break; | |
841 } | |
20534
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
842 |
17052 | 843 val = Qnil; |
17186
65bc06706714
Adjusted for the change of MAX_CHARSET.
Kenichi Handa <handa@m17n.org>
parents:
17121
diff
changeset
|
844 for (i = MAX_CHARSET; i >= 0; i--) |
17052 | 845 if (charsets[i]) |
846 val = Fcons (CHARSET_SYMBOL (i), val); | |
847 return val; | |
848 } | |
849 | |
850 DEFUN ("find-charset-string", Ffind_charset_string, Sfind_charset_string, | |
17727
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
851 1, 2, 0, |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
852 "Return a list of charsets in STR.\n\ |
23427
4acd4faa545a
(Fstring): Call make_string instead of
Kenichi Handa <handa@m17n.org>
parents:
23397
diff
changeset
|
853 If the string contains any composite characters,\n\ |
4acd4faa545a
(Fstring): Call make_string instead of
Kenichi Handa <handa@m17n.org>
parents:
23397
diff
changeset
|
854 `composition' is included in the returned list.\n\ |
22121
6e79a15594ab
Change terms unify/unification to
Kenichi Handa <handa@m17n.org>
parents:
21718
diff
changeset
|
855 Optional arg TABLE if non-nil is a translation table to look up.") |
17727
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
856 (str, table) |
9d39361ce928
(unify_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
17366
diff
changeset
|
857 Lisp_Object str, table; |
17052 | 858 { |
18003
ac148c939dec
(Ffind_charset_string): The variable CHARSETS is
Kenichi Handa <handa@m17n.org>
parents:
17880
diff
changeset
|
859 int charsets[MAX_CHARSET + 1]; |
17052 | 860 int i; |
861 Lisp_Object val; | |
862 | |
863 CHECK_STRING (str, 0); | |
20614
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
864 |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
865 if (! STRING_MULTIBYTE (str)) |
23210
53c330e846d0
(Ffind_charset_region): Optimization for unibyte buffer.
Kenichi Handa <handa@m17n.org>
parents:
23154
diff
changeset
|
866 return (XSTRING (str)->size == 0 |
53c330e846d0
(Ffind_charset_region): Optimization for unibyte buffer.
Kenichi Handa <handa@m17n.org>
parents:
23154
diff
changeset
|
867 ? Qnil |
53c330e846d0
(Ffind_charset_region): Optimization for unibyte buffer.
Kenichi Handa <handa@m17n.org>
parents:
23154
diff
changeset
|
868 : Fcons (Qascii, Qnil)); |
20614
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
869 |
18003
ac148c939dec
(Ffind_charset_string): The variable CHARSETS is
Kenichi Handa <handa@m17n.org>
parents:
17880
diff
changeset
|
870 bzero (charsets, (MAX_CHARSET + 1) * sizeof (int)); |
21244
50929073a0ba
Use STRING_BYTES and SET_STRING_BYTES.
Richard M. Stallman <rms@gnu.org>
parents:
21063
diff
changeset
|
871 find_charset_in_str (XSTRING (str)->data, STRING_BYTES (XSTRING (str)), |
23427
4acd4faa545a
(Fstring): Call make_string instead of
Kenichi Handa <handa@m17n.org>
parents:
23397
diff
changeset
|
872 charsets, table, 1); |
17052 | 873 val = Qnil; |
17186
65bc06706714
Adjusted for the change of MAX_CHARSET.
Kenichi Handa <handa@m17n.org>
parents:
17121
diff
changeset
|
874 for (i = MAX_CHARSET; i >= 0; i--) |
17052 | 875 if (charsets[i]) |
876 val = Fcons (CHARSET_SYMBOL (i), val); | |
877 return val; | |
878 } | |
879 | |
880 DEFUN ("make-char-internal", Fmake_char_internal, Smake_char_internal, 1, 3, 0, | |
17186
65bc06706714
Adjusted for the change of MAX_CHARSET.
Kenichi Handa <handa@m17n.org>
parents:
17121
diff
changeset
|
881 "") |
17052 | 882 (charset, code1, code2) |
883 Lisp_Object charset, code1, code2; | |
884 { | |
885 CHECK_NUMBER (charset, 0); | |
886 | |
887 if (NILP (code1)) | |
888 XSETFASTINT (code1, 0); | |
889 else | |
890 CHECK_NUMBER (code1, 1); | |
891 if (NILP (code2)) | |
892 XSETFASTINT (code2, 0); | |
893 else | |
894 CHECK_NUMBER (code2, 2); | |
895 | |
896 if (!CHARSET_DEFINED_P (XINT (charset))) | |
897 error ("Invalid charset: %d", XINT (charset)); | |
898 | |
899 return make_number (MAKE_CHAR (XINT (charset), XINT (code1), XINT (code2))); | |
900 } | |
901 | |
902 DEFUN ("split-char", Fsplit_char, Ssplit_char, 1, 1, 0, | |
903 "Return list of charset and one or two position-codes of CHAR.") | |
904 (ch) | |
905 Lisp_Object ch; | |
906 { | |
907 Lisp_Object val; | |
17322
a7d9b8e167ca
(non_ascii_char_to_string, update_charset_table,
Kenichi Handa <handa@m17n.org>
parents:
17186
diff
changeset
|
908 int charset, c1, c2; |
17052 | 909 |
910 CHECK_NUMBER (ch, 0); | |
911 SPLIT_CHAR (XFASTINT (ch), charset, c1, c2); | |
17322
a7d9b8e167ca
(non_ascii_char_to_string, update_charset_table,
Kenichi Handa <handa@m17n.org>
parents:
17186
diff
changeset
|
912 return (c2 >= 0 |
17052 | 913 ? Fcons (CHARSET_SYMBOL (charset), |
914 Fcons (make_number (c1), Fcons (make_number (c2), Qnil))) | |
915 : Fcons (CHARSET_SYMBOL (charset), Fcons (make_number (c1), Qnil))); | |
916 } | |
917 | |
918 DEFUN ("char-charset", Fchar_charset, Schar_charset, 1, 1, 0, | |
919 "Return charset of CHAR.") | |
920 (ch) | |
921 Lisp_Object ch; | |
922 { | |
923 CHECK_NUMBER (ch, 0); | |
924 | |
925 return CHARSET_SYMBOL (CHAR_CHARSET (XINT (ch))); | |
926 } | |
927 | |
21445
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
928 DEFUN ("charset-after", Fcharset_after, Scharset_after, 0, 1, 0, |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
929 "Return charset of a character in current buffer at position POS.\n\ |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
930 If POS is nil, it defauls to the current point.") |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
931 (pos) |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
932 Lisp_Object pos; |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
933 { |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
934 register int pos_byte, c, charset; |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
935 register unsigned char *p; |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
936 |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
937 if (NILP (pos)) |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
938 pos_byte = PT_BYTE; |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
939 else if (MARKERP (pos)) |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
940 pos_byte = marker_byte_position (pos); |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
941 else |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
942 { |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
943 CHECK_NUMBER (pos, 0); |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
944 pos_byte = CHAR_TO_BYTE (XINT (pos)); |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
945 } |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
946 p = BYTE_POS_ADDR (pos_byte); |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
947 c = STRING_CHAR (p, Z_BYTE - pos_byte); |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
948 charset = CHAR_CHARSET (c); |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
949 return CHARSET_SYMBOL (charset); |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
950 } |
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
951 |
17052 | 952 DEFUN ("iso-charset", Fiso_charset, Siso_charset, 3, 3, 0, |
20833
cf404f800d2c
(Fiso_charset): Doc-string modified.
Kenichi Handa <handa@m17n.org>
parents:
20720
diff
changeset
|
953 "Return charset of ISO's specification DIMENSION, CHARS, and FINAL-CHAR.\n\ |
cf404f800d2c
(Fiso_charset): Doc-string modified.
Kenichi Handa <handa@m17n.org>
parents:
20720
diff
changeset
|
954 \n\ |
cf404f800d2c
(Fiso_charset): Doc-string modified.
Kenichi Handa <handa@m17n.org>
parents:
20720
diff
changeset
|
955 ISO 2022's designation sequence (escape sequence) distinguishes charsets\n\ |
cf404f800d2c
(Fiso_charset): Doc-string modified.
Kenichi Handa <handa@m17n.org>
parents:
20720
diff
changeset
|
956 by their DIMENSION, CHARS, and FINAL-CHAR,\n\ |
cf404f800d2c
(Fiso_charset): Doc-string modified.
Kenichi Handa <handa@m17n.org>
parents:
20720
diff
changeset
|
957 where as Emacs distinguishes them by charset symbol.\n\ |
cf404f800d2c
(Fiso_charset): Doc-string modified.
Kenichi Handa <handa@m17n.org>
parents:
20720
diff
changeset
|
958 See the documentation of the function `charset-info' for the meanings of\n\ |
cf404f800d2c
(Fiso_charset): Doc-string modified.
Kenichi Handa <handa@m17n.org>
parents:
20720
diff
changeset
|
959 DIMENSION, CHARS, and FINAL-CHAR.") |
17052 | 960 (dimension, chars, final_char) |
961 Lisp_Object dimension, chars, final_char; | |
962 { | |
963 int charset; | |
964 | |
965 CHECK_NUMBER (dimension, 0); | |
966 CHECK_NUMBER (chars, 1); | |
967 CHECK_NUMBER (final_char, 2); | |
968 | |
969 if ((charset = ISO_CHARSET_TABLE (dimension, chars, final_char)) < 0) | |
970 return Qnil; | |
971 return CHARSET_SYMBOL (charset); | |
972 } | |
973 | |
20152
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
974 /* If GENERICP is nonzero, return nonzero iff C is a valid normal or |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
975 generic character. If GENERICP is zero, return nonzero iff C is a |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
976 valid normal character. Do not call this function directly, |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
977 instead use macro CHAR_VALID_P. */ |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
978 int |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
979 char_valid_p (c, genericp) |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
980 int c, genericp; |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
981 { |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
982 int charset, c1, c2; |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
983 |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
984 if (c < 0) |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
985 return 0; |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
986 if (SINGLE_BYTE_CHAR_P (c)) |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
987 return 1; |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
988 SPLIT_NON_ASCII_CHAR (c, charset, c1, c2); |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
989 if (!CHARSET_VALID_P (charset)) |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
990 return 0; |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
991 return (c < MIN_CHAR_COMPOSITION |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
992 ? ((c & CHAR_FIELD1_MASK) /* i.e. dimension of C is two. */ |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
993 ? (genericp && c1 == 0 && c2 == 0 |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
994 || c1 >= 32 && c2 >= 32) |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
995 : (genericp && c1 == 0 |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
996 || c1 >= 32)) |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
997 : c < MIN_CHAR_COMPOSITION + n_cmpchars); |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
998 } |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
999 |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
1000 DEFUN ("char-valid-p", Fchar_valid_p, Schar_valid_p, 1, 2, 0, |
20636
5ab6701a2b4b
(Fchar_valid_p): Fix bare newlines in doc string.
Dave Love <fx@gnu.org>
parents:
20614
diff
changeset
|
1001 "Return t if OBJECT is a valid normal character.\n\ |
5ab6701a2b4b
(Fchar_valid_p): Fix bare newlines in doc string.
Dave Love <fx@gnu.org>
parents:
20614
diff
changeset
|
1002 If optional arg GENERICP is non-nil, also return t if OBJECT is\n\ |
20152
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
1003 a valid generic character.") |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
1004 (object, genericp) |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
1005 Lisp_Object object, genericp; |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
1006 { |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
1007 if (! NATNUMP (object)) |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
1008 return Qnil; |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
1009 return (CHAR_VALID_P (XFASTINT (object), !NILP (genericp)) ? Qt : Qnil); |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
1010 } |
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
1011 |
21034
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
1012 DEFUN ("unibyte-char-to-multibyte", Funibyte_char_to_multibyte, |
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
1013 Sunibyte_char_to_multibyte, 1, 1, 0, |
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
1014 "Convert the unibyte character CH to multibyte character.\n\ |
22185
80a2aa51a6e1
Change term "character translation table" to
Kenichi Handa <handa@m17n.org>
parents:
22168
diff
changeset
|
1015 The conversion is done based on `nonascii-translation-table' (which see)\n\ |
21715
98c5740d198b
(Funibyte_char_to_multibyte): Doc fix.
Richard M. Stallman <rms@gnu.org>
parents:
21519
diff
changeset
|
1016 or `nonascii-insert-offset' (which see).") |
21034
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
1017 (ch) |
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
1018 Lisp_Object ch; |
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
1019 { |
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
1020 int c; |
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
1021 |
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
1022 CHECK_NUMBER (ch, 0); |
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
1023 c = XINT (ch); |
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
1024 if (c < 0 || c >= 0400) |
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
1025 error ("Invalid unibyte character: %d", c); |
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
1026 c = unibyte_char_to_multibyte (c); |
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
1027 if (c < 0) |
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
1028 error ("Can't convert to multibyte character: %d", XINT (ch)); |
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
1029 return make_number (c); |
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
1030 } |
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
1031 |
23060
5036ee3de0ac
(Fmultibyte_char_to_unibyte): New function.
Richard M. Stallman <rms@gnu.org>
parents:
22927
diff
changeset
|
1032 DEFUN ("multibyte-char-to-unibyte", Fmultibyte_char_to_unibyte, |
5036ee3de0ac
(Fmultibyte_char_to_unibyte): New function.
Richard M. Stallman <rms@gnu.org>
parents:
22927
diff
changeset
|
1033 Smultibyte_char_to_unibyte, 1, 1, 0, |
5036ee3de0ac
(Fmultibyte_char_to_unibyte): New function.
Richard M. Stallman <rms@gnu.org>
parents:
22927
diff
changeset
|
1034 "Convert the multibyte character CH to unibyte character.\n\ |
5036ee3de0ac
(Fmultibyte_char_to_unibyte): New function.
Richard M. Stallman <rms@gnu.org>
parents:
22927
diff
changeset
|
1035 The conversion is done based on `nonascii-translation-table' (which see)\n\ |
5036ee3de0ac
(Fmultibyte_char_to_unibyte): New function.
Richard M. Stallman <rms@gnu.org>
parents:
22927
diff
changeset
|
1036 or `nonascii-insert-offset' (which see).") |
5036ee3de0ac
(Fmultibyte_char_to_unibyte): New function.
Richard M. Stallman <rms@gnu.org>
parents:
22927
diff
changeset
|
1037 (ch) |
5036ee3de0ac
(Fmultibyte_char_to_unibyte): New function.
Richard M. Stallman <rms@gnu.org>
parents:
22927
diff
changeset
|
1038 Lisp_Object ch; |
5036ee3de0ac
(Fmultibyte_char_to_unibyte): New function.
Richard M. Stallman <rms@gnu.org>
parents:
22927
diff
changeset
|
1039 { |
5036ee3de0ac
(Fmultibyte_char_to_unibyte): New function.
Richard M. Stallman <rms@gnu.org>
parents:
22927
diff
changeset
|
1040 int c; |
5036ee3de0ac
(Fmultibyte_char_to_unibyte): New function.
Richard M. Stallman <rms@gnu.org>
parents:
22927
diff
changeset
|
1041 |
5036ee3de0ac
(Fmultibyte_char_to_unibyte): New function.
Richard M. Stallman <rms@gnu.org>
parents:
22927
diff
changeset
|
1042 CHECK_NUMBER (ch, 0); |
5036ee3de0ac
(Fmultibyte_char_to_unibyte): New function.
Richard M. Stallman <rms@gnu.org>
parents:
22927
diff
changeset
|
1043 c = XINT (ch); |
5036ee3de0ac
(Fmultibyte_char_to_unibyte): New function.
Richard M. Stallman <rms@gnu.org>
parents:
22927
diff
changeset
|
1044 if (c < 0) |
5036ee3de0ac
(Fmultibyte_char_to_unibyte): New function.
Richard M. Stallman <rms@gnu.org>
parents:
22927
diff
changeset
|
1045 error ("Invalid multibyte character: %d", c); |
5036ee3de0ac
(Fmultibyte_char_to_unibyte): New function.
Richard M. Stallman <rms@gnu.org>
parents:
22927
diff
changeset
|
1046 c = multibyte_char_to_unibyte (c, Qnil); |
5036ee3de0ac
(Fmultibyte_char_to_unibyte): New function.
Richard M. Stallman <rms@gnu.org>
parents:
22927
diff
changeset
|
1047 if (c < 0) |
5036ee3de0ac
(Fmultibyte_char_to_unibyte): New function.
Richard M. Stallman <rms@gnu.org>
parents:
22927
diff
changeset
|
1048 error ("Can't convert to unibyte character: %d", XINT (ch)); |
5036ee3de0ac
(Fmultibyte_char_to_unibyte): New function.
Richard M. Stallman <rms@gnu.org>
parents:
22927
diff
changeset
|
1049 return make_number (c); |
5036ee3de0ac
(Fmultibyte_char_to_unibyte): New function.
Richard M. Stallman <rms@gnu.org>
parents:
22927
diff
changeset
|
1050 } |
5036ee3de0ac
(Fmultibyte_char_to_unibyte): New function.
Richard M. Stallman <rms@gnu.org>
parents:
22927
diff
changeset
|
1051 |
17052 | 1052 DEFUN ("char-bytes", Fchar_bytes, Schar_bytes, 1, 1, 0, |
23140
17ad9953ff42
(Fchar_bytes): Add \n\ in doc-string.
Kenichi Handa <handa@m17n.org>
parents:
23131
diff
changeset
|
1053 "Return 1 regardless of the argument CHAR.\n\ |
23576 | 1054 This is now an obsolete function. We keep it just for backward compatibility.") |
17052 | 1055 (ch) |
1056 Lisp_Object ch; | |
1057 { | |
1058 Lisp_Object val; | |
1059 | |
1060 CHECK_NUMBER (ch, 0); | |
23131
f7e486faa1ad
(Fchar_bytes): Now always return 1.
Kenichi Handa <handa@m17n.org>
parents:
23060
diff
changeset
|
1061 return make_number (1); |
f7e486faa1ad
(Fchar_bytes): Now always return 1.
Kenichi Handa <handa@m17n.org>
parents:
23060
diff
changeset
|
1062 } |
f7e486faa1ad
(Fchar_bytes): Now always return 1.
Kenichi Handa <handa@m17n.org>
parents:
23060
diff
changeset
|
1063 |
f7e486faa1ad
(Fchar_bytes): Now always return 1.
Kenichi Handa <handa@m17n.org>
parents:
23060
diff
changeset
|
1064 /* Return how many bytes C will occupy in a multibyte buffer. |
f7e486faa1ad
(Fchar_bytes): Now always return 1.
Kenichi Handa <handa@m17n.org>
parents:
23060
diff
changeset
|
1065 Don't call this function directly, instead use macro CHAR_BYTES. */ |
f7e486faa1ad
(Fchar_bytes): Now always return 1.
Kenichi Handa <handa@m17n.org>
parents:
23060
diff
changeset
|
1066 int |
f7e486faa1ad
(Fchar_bytes): Now always return 1.
Kenichi Handa <handa@m17n.org>
parents:
23060
diff
changeset
|
1067 char_bytes (c) |
f7e486faa1ad
(Fchar_bytes): Now always return 1.
Kenichi Handa <handa@m17n.org>
parents:
23060
diff
changeset
|
1068 int c; |
f7e486faa1ad
(Fchar_bytes): Now always return 1.
Kenichi Handa <handa@m17n.org>
parents:
23060
diff
changeset
|
1069 { |
f7e486faa1ad
(Fchar_bytes): Now always return 1.
Kenichi Handa <handa@m17n.org>
parents:
23060
diff
changeset
|
1070 int bytes; |
f7e486faa1ad
(Fchar_bytes): Now always return 1.
Kenichi Handa <handa@m17n.org>
parents:
23060
diff
changeset
|
1071 |
f7e486faa1ad
(Fchar_bytes): Now always return 1.
Kenichi Handa <handa@m17n.org>
parents:
23060
diff
changeset
|
1072 if (COMPOSITE_CHAR_P (c)) |
17052 | 1073 { |
23131
f7e486faa1ad
(Fchar_bytes): Now always return 1.
Kenichi Handa <handa@m17n.org>
parents:
23060
diff
changeset
|
1074 unsigned int id = COMPOSITE_CHAR_ID (c); |
17052 | 1075 |
1076 bytes = (id < n_cmpchars ? cmpchar_table[id]->len : 1); | |
1077 } | |
1078 else | |
1079 { | |
23131
f7e486faa1ad
(Fchar_bytes): Now always return 1.
Kenichi Handa <handa@m17n.org>
parents:
23060
diff
changeset
|
1080 int charset = CHAR_CHARSET (c); |
17052 | 1081 |
1082 bytes = CHARSET_DEFINED_P (charset) ? CHARSET_BYTES (charset) : 1; | |
1083 } | |
1084 | |
23576 | 1085 return bytes; |
17052 | 1086 } |
1087 | |
1088 /* Return the width of character of which multi-byte form starts with | |
1089 C. The width is measured by how many columns occupied on the | |
1090 screen when displayed in the current buffer. */ | |
1091 | |
1092 #define ONE_BYTE_CHAR_WIDTH(c) \ | |
1093 (c < 0x20 \ | |
1094 ? (c == '\t' \ | |
17366
f7809ff2c65f
(ONE_BYTE_CHAR_WIDTH, Fconcat_chars): Don't use Lisp_Object as integer.
Karl Heuer <kwzh@gnu.org>
parents:
17322
diff
changeset
|
1095 ? XFASTINT (current_buffer->tab_width) \ |
17052 | 1096 : (c == '\n' ? 0 : (NILP (current_buffer->ctl_arrow) ? 4 : 2))) \ |
1097 : (c < 0x7f \ | |
1098 ? 1 \ | |
1099 : (c == 0x7F \ | |
1100 ? (NILP (current_buffer->ctl_arrow) ? 4 : 2) \ | |
1101 : ((! NILP (current_buffer->enable_multibyte_characters) \ | |
1102 && BASE_LEADING_CODE_P (c)) \ | |
1103 ? WIDTH_BY_CHAR_HEAD (c) \ | |
22121
6e79a15594ab
Change terms unify/unification to
Kenichi Handa <handa@m17n.org>
parents:
21718
diff
changeset
|
1104 : 4)))) |
17052 | 1105 |
1106 DEFUN ("char-width", Fchar_width, Schar_width, 1, 1, 0, | |
1107 "Return width of CHAR when displayed in the current buffer.\n\ | |
1108 The width is measured by how many columns it occupies on the screen.") | |
1109 (ch) | |
1110 Lisp_Object ch; | |
1111 { | |
17818
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1112 Lisp_Object val, disp; |
17052 | 1113 int c; |
18537
6a726658dfa9
(Fchar_width): Check if the current buffer has display
Kenichi Handa <handa@m17n.org>
parents:
18341
diff
changeset
|
1114 struct Lisp_Char_Table *dp = buffer_display_table (); |
17052 | 1115 |
1116 CHECK_NUMBER (ch, 0); | |
1117 | |
17818
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1118 c = XINT (ch); |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1119 |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1120 /* Get the way the display table would display it. */ |
18537
6a726658dfa9
(Fchar_width): Check if the current buffer has display
Kenichi Handa <handa@m17n.org>
parents:
18341
diff
changeset
|
1121 disp = dp ? DISP_CHAR_VECTOR (dp, c) : Qnil; |
17818
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1122 |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1123 if (VECTORP (disp)) |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1124 XSETINT (val, XVECTOR (disp)->size); |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1125 else if (SINGLE_BYTE_CHAR_P (c)) |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1126 XSETINT (val, ONE_BYTE_CHAR_WIDTH (c)); |
17052 | 1127 else if (COMPOSITE_CHAR_P (c)) |
1128 { | |
1129 int id = COMPOSITE_CHAR_ID (XFASTINT (ch)); | |
1130 XSETFASTINT (val, (id < n_cmpchars ? cmpchar_table[id]->width : 0)); | |
1131 } | |
1132 else | |
1133 { | |
1134 int charset = CHAR_CHARSET (c); | |
1135 | |
1136 XSETFASTINT (val, CHARSET_WIDTH (charset)); | |
1137 } | |
1138 return val; | |
1139 } | |
1140 | |
1141 /* Return width of string STR of length LEN when displayed in the | |
1142 current buffer. The width is measured by how many columns it | |
1143 occupies on the screen. */ | |
17818
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1144 |
17052 | 1145 int |
1146 strwidth (str, len) | |
1147 unsigned char *str; | |
1148 int len; | |
1149 { | |
1150 unsigned char *endp = str + len; | |
1151 int width = 0; | |
20362
67bcb068070c
(strwidth): Remove extra argument to buffer_display_table.
Kenichi Handa <handa@m17n.org>
parents:
20228
diff
changeset
|
1152 struct Lisp_Char_Table *dp = buffer_display_table (); |
17052 | 1153 |
17818
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1154 while (str < endp) |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1155 { |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1156 if (*str == LEADING_CODE_COMPOSITION) |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1157 { |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1158 int id = str_cmpchar_id (str, endp - str); |
17052 | 1159 |
17818
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1160 if (id < 0) |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1161 { |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1162 width += 4; |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1163 str++; |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1164 } |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1165 else |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1166 { |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1167 width += cmpchar_table[id]->width; |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1168 str += cmpchar_table[id]->len; |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1169 } |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1170 } |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1171 else |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1172 { |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1173 Lisp_Object disp; |
21063
44845df088bc
(strwidth): Make it work for invalid bytes sequence.
Kenichi Handa <handa@m17n.org>
parents:
21034
diff
changeset
|
1174 int thislen; |
44845df088bc
(strwidth): Make it work for invalid bytes sequence.
Kenichi Handa <handa@m17n.org>
parents:
21034
diff
changeset
|
1175 int c = STRING_CHAR_AND_LENGTH (str, endp - str, thislen); |
17818
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1176 |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1177 /* Get the way the display table would display it. */ |
17863
bc8774c7999b
(strwidth): Fix previous change.
Richard M. Stallman <rms@gnu.org>
parents:
17843
diff
changeset
|
1178 if (dp) |
bc8774c7999b
(strwidth): Fix previous change.
Richard M. Stallman <rms@gnu.org>
parents:
17843
diff
changeset
|
1179 disp = DISP_CHAR_VECTOR (dp, c); |
bc8774c7999b
(strwidth): Fix previous change.
Richard M. Stallman <rms@gnu.org>
parents:
17843
diff
changeset
|
1180 else |
bc8774c7999b
(strwidth): Fix previous change.
Richard M. Stallman <rms@gnu.org>
parents:
17843
diff
changeset
|
1181 disp = Qnil; |
17818
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1182 |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1183 if (VECTORP (disp)) |
21063
44845df088bc
(strwidth): Make it work for invalid bytes sequence.
Kenichi Handa <handa@m17n.org>
parents:
21034
diff
changeset
|
1184 width += XVECTOR (disp)->size; |
17818
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1185 else |
21063
44845df088bc
(strwidth): Make it work for invalid bytes sequence.
Kenichi Handa <handa@m17n.org>
parents:
21034
diff
changeset
|
1186 width += ONE_BYTE_CHAR_WIDTH (*str); |
17818
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1187 |
21063
44845df088bc
(strwidth): Make it work for invalid bytes sequence.
Kenichi Handa <handa@m17n.org>
parents:
21034
diff
changeset
|
1188 str += thislen; |
17818
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1189 } |
76c6740bd736
(strwidth, Fchar_width): Handle display table.
Richard M. Stallman <rms@gnu.org>
parents:
17727
diff
changeset
|
1190 } |
17052 | 1191 return width; |
1192 } | |
1193 | |
1194 DEFUN ("string-width", Fstring_width, Sstring_width, 1, 1, 0, | |
1195 "Return width of STRING when displayed in the current buffer.\n\ | |
1196 Width is measured by how many columns it occupies on the screen.\n\ | |
19384 | 1197 When calculating width of a multibyte character in STRING,\n\ |
1198 only the base leading-code is considered; the validity of\n\ | |
1199 the following bytes is not checked.") | |
17052 | 1200 (str) |
1201 Lisp_Object str; | |
1202 { | |
1203 Lisp_Object val; | |
1204 | |
1205 CHECK_STRING (str, 0); | |
21244
50929073a0ba
Use STRING_BYTES and SET_STRING_BYTES.
Richard M. Stallman <rms@gnu.org>
parents:
21063
diff
changeset
|
1206 XSETFASTINT (val, strwidth (XSTRING (str)->data, |
50929073a0ba
Use STRING_BYTES and SET_STRING_BYTES.
Richard M. Stallman <rms@gnu.org>
parents:
21063
diff
changeset
|
1207 STRING_BYTES (XSTRING (str)))); |
17052 | 1208 return val; |
1209 } | |
1210 | |
1211 DEFUN ("char-direction", Fchar_direction, Schar_direction, 1, 1, 0, | |
1212 "Return the direction of CHAR.\n\ | |
1213 The returned value is 0 for left-to-right and 1 for right-to-left.") | |
1214 (ch) | |
1215 Lisp_Object ch; | |
1216 { | |
1217 int charset; | |
1218 | |
1219 CHECK_NUMBER (ch, 0); | |
1220 charset = CHAR_CHARSET (XFASTINT (ch)); | |
1221 if (!CHARSET_DEFINED_P (charset)) | |
20933
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
1222 invalid_character (XINT (ch)); |
17052 | 1223 return CHARSET_TABLE_INFO (charset, CHARSET_DIRECTION_IDX); |
1224 } | |
1225 | |
19415
309b9a0d8a45
(Fchars_in_region): Renamed form Fcount_chars_region.
Kenichi Handa <handa@m17n.org>
parents:
19384
diff
changeset
|
1226 DEFUN ("chars-in-region", Fchars_in_region, Schars_in_region, 2, 2, 0, |
20534
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
1227 "Return number of characters between BEG and END.") |
19384 | 1228 (beg, end) |
1229 Lisp_Object beg, end; | |
1230 { | |
20534
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
1231 int from, to; |
19384 | 1232 |
22739
f0c8af6c2dfd
(Fchars_in_region): Coerce markers.
Richard M. Stallman <rms@gnu.org>
parents:
22703
diff
changeset
|
1233 CHECK_NUMBER_COERCE_MARKER (beg, 0); |
f0c8af6c2dfd
(Fchars_in_region): Coerce markers.
Richard M. Stallman <rms@gnu.org>
parents:
22703
diff
changeset
|
1234 CHECK_NUMBER_COERCE_MARKER (end, 1); |
f0c8af6c2dfd
(Fchars_in_region): Coerce markers.
Richard M. Stallman <rms@gnu.org>
parents:
22703
diff
changeset
|
1235 |
19384 | 1236 from = min (XFASTINT (beg), XFASTINT (end)); |
19444
752afe97eaa4
(Fchars_in_region): Fix gap handling.
Richard M. Stallman <rms@gnu.org>
parents:
19415
diff
changeset
|
1237 to = max (XFASTINT (beg), XFASTINT (end)); |
20534
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
1238 |
21519
9b26f9300d41
(Fchars_in_region): Fix mixing of Lisp_Object and int.
Andreas Schwab <schwab@suse.de>
parents:
21514
diff
changeset
|
1239 return make_number (to - from); |
20534
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
1240 } |
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
1241 |
20614
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1242 /* Return the number of characters in the NBYTES bytes at PTR. |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1243 This works by looking at the contents and checking for multibyte sequences. |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1244 However, if the current buffer has enable-multibyte-characters = nil, |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1245 we treat each byte as a character. */ |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1246 |
20534
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
1247 int |
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
1248 chars_in_text (ptr, nbytes) |
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
1249 unsigned char *ptr; |
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
1250 int nbytes; |
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
1251 { |
20933
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
1252 unsigned char *endp, c; |
20534
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
1253 int chars; |
19384 | 1254 |
20614
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1255 /* current_buffer is null at early stages of Emacs initialization. */ |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1256 if (current_buffer == 0 |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1257 || NILP (current_buffer->enable_multibyte_characters)) |
20534
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
1258 return nbytes; |
20188
d4ad4463384d
(Fchars_in_string): Pay attention to
Kenichi Handa <handa@m17n.org>
parents:
20152
diff
changeset
|
1259 |
20534
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
1260 endp = ptr + nbytes; |
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
1261 chars = 0; |
19384 | 1262 |
20534
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
1263 while (ptr < endp) |
19384 | 1264 { |
20933
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
1265 c = *ptr++; |
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
1266 |
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
1267 if (BASE_LEADING_CODE_P (c)) |
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
1268 while (ptr < endp && ! CHAR_HEAD_P (*ptr)) ptr++; |
19384 | 1269 chars++; |
1270 } | |
1271 | |
20534
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
1272 return chars; |
19384 | 1273 } |
1274 | |
20614
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1275 /* Return the number of characters in the NBYTES bytes at PTR. |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1276 This works by looking at the contents and checking for multibyte sequences. |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1277 It ignores enable-multibyte-characters. */ |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1278 |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1279 int |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1280 multibyte_chars_in_text (ptr, nbytes) |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1281 unsigned char *ptr; |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1282 int nbytes; |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1283 { |
20933
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
1284 unsigned char *endp, c; |
20614
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1285 int chars; |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1286 |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1287 endp = ptr + nbytes; |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1288 chars = 0; |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1289 |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1290 while (ptr < endp) |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1291 { |
20933
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
1292 c = *ptr++; |
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
1293 |
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
1294 if (BASE_LEADING_CODE_P (c)) |
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
1295 while (ptr < endp && ! CHAR_HEAD_P (*ptr)) ptr++; |
20614
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1296 chars++; |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1297 } |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1298 |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1299 return chars; |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1300 } |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1301 |
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1302 DEFUN ("string", Fstring, Sstring, 1, MANY, 0, |
17052 | 1303 "Concatenate all the argument characters and make the result a string.") |
17366
f7809ff2c65f
(ONE_BYTE_CHAR_WIDTH, Fconcat_chars): Don't use Lisp_Object as integer.
Karl Heuer <kwzh@gnu.org>
parents:
17322
diff
changeset
|
1304 (n, args) |
f7809ff2c65f
(ONE_BYTE_CHAR_WIDTH, Fconcat_chars): Don't use Lisp_Object as integer.
Karl Heuer <kwzh@gnu.org>
parents:
17322
diff
changeset
|
1305 int n; |
17052 | 1306 Lisp_Object *args; |
1307 { | |
17366
f7809ff2c65f
(ONE_BYTE_CHAR_WIDTH, Fconcat_chars): Don't use Lisp_Object as integer.
Karl Heuer <kwzh@gnu.org>
parents:
17322
diff
changeset
|
1308 int i; |
17052 | 1309 unsigned char *buf |
17834
e154b943bbba
(non_ascii_char_to_string): Signal error if the
Kenichi Handa <handa@m17n.org>
parents:
17818
diff
changeset
|
1310 = (unsigned char *) alloca (MAX_LENGTH_OF_MULTI_BYTE_FORM * n); |
17052 | 1311 unsigned char *p = buf; |
1312 Lisp_Object val; | |
1313 | |
1314 for (i = 0; i < n; i++) | |
1315 { | |
1316 int c, len; | |
1317 unsigned char *str; | |
1318 | |
1319 if (!INTEGERP (args[i])) | |
20720
f084bb8d535f
(min_composite_char): New variable.
Kenichi Handa <handa@m17n.org>
parents:
20705
diff
changeset
|
1320 CHECK_NUMBER (args[i], 0); |
17052 | 1321 c = XINT (args[i]); |
1322 len = CHAR_STRING (c, p, str); | |
1323 if (p != str) | |
1324 /* C is a composite character. */ | |
1325 bcopy (str, p, len); | |
1326 p += len; | |
1327 } | |
1328 | |
23427
4acd4faa545a
(Fstring): Call make_string instead of
Kenichi Handa <handa@m17n.org>
parents:
23397
diff
changeset
|
1329 /* Here, we can't use make_string_from_bytes because of byte |
4acd4faa545a
(Fstring): Call make_string instead of
Kenichi Handa <handa@m17n.org>
parents:
23397
diff
changeset
|
1330 combining problem. */ |
4acd4faa545a
(Fstring): Call make_string instead of
Kenichi Handa <handa@m17n.org>
parents:
23397
diff
changeset
|
1331 val = make_string (buf, p - buf); |
17052 | 1332 return val; |
1333 } | |
1334 | |
1335 #endif /* emacs */ | |
1336 | |
1337 /*** Composite characters staffs ***/ | |
1338 | |
1339 /* Each composite character is identified by CMPCHAR-ID which is | |
1340 assigned when Emacs needs the character code of the composite | |
1341 character (e.g. when displaying it on the screen). See the | |
1342 document "GENERAL NOTE on COMPOSITE CHARACTER" in `charset.h' how a | |
1343 composite character is represented in Emacs. */ | |
1344 | |
1345 /* If `static' is defined, it means that it is defined to null string. */ | |
1346 #ifndef static | |
1347 /* The following function is copied from lread.c. */ | |
1348 static int | |
1349 hash_string (ptr, len) | |
1350 unsigned char *ptr; | |
1351 int len; | |
1352 { | |
1353 register unsigned char *p = ptr; | |
1354 register unsigned char *end = p + len; | |
1355 register unsigned char c; | |
1356 register int hash = 0; | |
1357 | |
1358 while (p != end) | |
1359 { | |
1360 c = *p++; | |
1361 if (c >= 0140) c -= 40; | |
1362 hash = ((hash<<3) + (hash>>28) + c); | |
1363 } | |
1364 return hash & 07777777777; | |
1365 } | |
1366 #endif | |
1367 | |
1368 #define CMPCHAR_HASH_TABLE_SIZE 0xFFF | |
1369 | |
1370 static int *cmpchar_hash_table[CMPCHAR_HASH_TABLE_SIZE]; | |
1371 | |
1372 /* Each element of `cmpchar_hash_table' is a pointer to an array of | |
1373 integer, where the 1st element is the size of the array, the 2nd | |
1374 element is how many elements are actually used in the array, and | |
1375 the remaining elements are CMPCHAR-IDs of composite characters of | |
1376 the same hash value. */ | |
1377 #define CMPCHAR_HASH_SIZE(table) table[0] | |
1378 #define CMPCHAR_HASH_USED(table) table[1] | |
1379 #define CMPCHAR_HASH_CMPCHAR_ID(table, i) table[i] | |
1380 | |
1381 /* Return CMPCHAR-ID of the composite character in STR of the length | |
1382 LEN. If the composite character has not yet been registered, | |
1383 register it in `cmpchar_table' and assign new CMPCHAR-ID. This | |
1384 is the sole function for assigning CMPCHAR-ID. */ | |
1385 int | |
1386 str_cmpchar_id (str, len) | |
21419
95aae2ff5fcd
(string_to_non_ascii_char, multibyte_form_length)
Karl Heuer <kwzh@gnu.org>
parents:
21255
diff
changeset
|
1387 const unsigned char *str; |
17052 | 1388 int len; |
1389 { | |
1390 int hash_idx, *hashp; | |
1391 unsigned char *buf; | |
1392 int embedded_rule; /* 1 if composition rule is embedded. */ | |
1393 int chars; /* number of components. */ | |
1394 int i; | |
1395 struct cmpchar_info *cmpcharp; | |
1396 | |
1397 /* The second byte 0xFF means compostion rule is embedded. */ | |
1398 embedded_rule = (str[1] == 0xFF); | |
1399 | |
1400 /* At first, get the actual length of the composite character. */ | |
1401 { | |
21419
95aae2ff5fcd
(string_to_non_ascii_char, multibyte_form_length)
Karl Heuer <kwzh@gnu.org>
parents:
21255
diff
changeset
|
1402 const unsigned char *p, *endp = str + 1, *lastp = str + len; |
17052 | 1403 int bytes; |
1404 | |
20534
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
1405 while (endp < lastp && ! CHAR_HEAD_P (*endp)) endp++; |
20933
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
1406 if (endp - str < 5) |
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
1407 /* Any composite char have at least 5-byte length. */ |
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
1408 return -1; |
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
1409 |
17052 | 1410 chars = 0; |
20933
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
1411 p = str + 1; |
17052 | 1412 while (p < endp) |
1413 { | |
20933
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
1414 if (embedded_rule) p++; |
17052 | 1415 /* No need of checking if *P is 0xA0 because |
20933
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
1416 BYTES_BY_CHAR_HEAD (0x80) surely returns 2. */ |
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
1417 p += BYTES_BY_CHAR_HEAD (*p - 0x20); |
17052 | 1418 chars++; |
1419 } | |
20933
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
1420 if (p > endp || chars < 2 || chars > MAX_COMPONENT_COUNT) |
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
1421 /* Invalid components. */ |
17052 | 1422 return -1; |
20933
5ceea9d50194
(invalid_character): New function.
Kenichi Handa <handa@m17n.org>
parents:
20890
diff
changeset
|
1423 len = p - str; |
17052 | 1424 } |
1425 hash_idx = hash_string (str, len) % CMPCHAR_HASH_TABLE_SIZE; | |
1426 hashp = cmpchar_hash_table[hash_idx]; | |
1427 | |
1428 /* Then, look into the hash table. */ | |
1429 if (hashp != NULL) | |
1430 /* Find the correct one among composite characters of the same | |
1431 hash value. */ | |
1432 for (i = 2; i < CMPCHAR_HASH_USED (hashp); i++) | |
1433 { | |
1434 cmpcharp = cmpchar_table[CMPCHAR_HASH_CMPCHAR_ID (hashp, i)]; | |
1435 if (len == cmpcharp->len | |
1436 && ! bcmp (str, cmpcharp->data, len)) | |
1437 return CMPCHAR_HASH_CMPCHAR_ID (hashp, i); | |
1438 } | |
1439 | |
1440 /* We have to register the composite character in cmpchar_table. */ | |
17186
65bc06706714
Adjusted for the change of MAX_CHARSET.
Kenichi Handa <handa@m17n.org>
parents:
17121
diff
changeset
|
1441 if (n_cmpchars > (CHAR_FIELD2_MASK | CHAR_FIELD3_MASK)) |
65bc06706714
Adjusted for the change of MAX_CHARSET.
Kenichi Handa <handa@m17n.org>
parents:
17121
diff
changeset
|
1442 /* No, we have no more room for a new composite character. */ |
65bc06706714
Adjusted for the change of MAX_CHARSET.
Kenichi Handa <handa@m17n.org>
parents:
17121
diff
changeset
|
1443 return -1; |
65bc06706714
Adjusted for the change of MAX_CHARSET.
Kenichi Handa <handa@m17n.org>
parents:
17121
diff
changeset
|
1444 |
17052 | 1445 /* Make the entry in hash table. */ |
1446 if (hashp == NULL) | |
1447 { | |
1448 /* Make a table for 8 composite characters initially. */ | |
1449 hashp = (cmpchar_hash_table[hash_idx] | |
1450 = (int *) xmalloc (sizeof (int) * (2 + 8))); | |
1451 CMPCHAR_HASH_SIZE (hashp) = 10; | |
1452 CMPCHAR_HASH_USED (hashp) = 2; | |
1453 } | |
1454 else if (CMPCHAR_HASH_USED (hashp) >= CMPCHAR_HASH_SIZE (hashp)) | |
1455 { | |
1456 CMPCHAR_HASH_SIZE (hashp) += 8; | |
1457 hashp = (cmpchar_hash_table[hash_idx] | |
1458 = (int *) xrealloc (hashp, | |
1459 sizeof (int) * CMPCHAR_HASH_SIZE (hashp))); | |
1460 } | |
1461 CMPCHAR_HASH_CMPCHAR_ID (hashp, CMPCHAR_HASH_USED (hashp)) = n_cmpchars; | |
1462 CMPCHAR_HASH_USED (hashp)++; | |
1463 | |
1464 /* Set information of the composite character in cmpchar_table. */ | |
1465 if (cmpchar_table_size == 0) | |
1466 { | |
1467 /* This is the first composite character to be registered. */ | |
1468 cmpchar_table_size = 256; | |
1469 cmpchar_table | |
1470 = (struct cmpchar_info **) xmalloc (sizeof (cmpchar_table[0]) | |
1471 * cmpchar_table_size); | |
1472 } | |
1473 else if (cmpchar_table_size <= n_cmpchars) | |
1474 { | |
1475 cmpchar_table_size += 256; | |
1476 cmpchar_table | |
1477 = (struct cmpchar_info **) xrealloc (cmpchar_table, | |
1478 sizeof (cmpchar_table[0]) | |
1479 * cmpchar_table_size); | |
1480 } | |
1481 | |
1482 cmpcharp = (struct cmpchar_info *) xmalloc (sizeof (struct cmpchar_info)); | |
1483 | |
1484 cmpcharp->len = len; | |
1485 cmpcharp->data = (unsigned char *) xmalloc (len + 1); | |
1486 bcopy (str, cmpcharp->data, len); | |
1487 cmpcharp->data[len] = 0; | |
1488 cmpcharp->glyph_len = chars; | |
1489 cmpcharp->glyph = (GLYPH *) xmalloc (sizeof (GLYPH) * chars); | |
1490 if (embedded_rule) | |
1491 { | |
1492 cmpcharp->cmp_rule = (unsigned char *) xmalloc (chars); | |
1493 cmpcharp->col_offset = (float *) xmalloc (sizeof (float) * chars); | |
1494 } | |
1495 else | |
1496 { | |
1497 cmpcharp->cmp_rule = NULL; | |
1498 cmpcharp->col_offset = NULL; | |
1499 } | |
1500 | |
1501 /* Setup GLYPH data and composition rules (if any) so as not to make | |
1502 them every time on displaying. */ | |
1503 { | |
1504 unsigned char *bufp; | |
1505 int width; | |
1506 float leftmost = 0.0, rightmost = 1.0; | |
1507 | |
1508 if (embedded_rule) | |
1509 /* At first, col_offset[N] is set to relative to col_offset[0]. */ | |
1510 cmpcharp->col_offset[0] = 0; | |
1511 | |
1512 for (i = 0, bufp = cmpcharp->data + 1; i < chars; i++) | |
1513 { | |
1514 if (embedded_rule) | |
1515 cmpcharp->cmp_rule[i] = *bufp++; | |
1516 | |
1517 if (*bufp == 0xA0) /* This is an ASCII character. */ | |
1518 { | |
1519 cmpcharp->glyph[i] = FAST_MAKE_GLYPH ((*++bufp & 0x7F), 0); | |
1520 width = 1; | |
1521 bufp++; | |
1522 } | |
1523 else /* Multibyte character. */ | |
1524 { | |
1525 /* Make `bufp' point normal multi-byte form temporally. */ | |
1526 *bufp -= 0x20; | |
1527 cmpcharp->glyph[i] | |
22185
80a2aa51a6e1
Change term "character translation table" to
Kenichi Handa <handa@m17n.org>
parents:
22168
diff
changeset
|
1528 = FAST_MAKE_GLYPH (string_to_non_ascii_char (bufp, 4, 0, 0), 0); |
17052 | 1529 width = WIDTH_BY_CHAR_HEAD (*bufp); |
1530 *bufp += 0x20; | |
1531 bufp += BYTES_BY_CHAR_HEAD (*bufp - 0x20); | |
1532 } | |
1533 | |
1534 if (embedded_rule && i > 0) | |
1535 { | |
1536 /* Reference points (global_ref and new_ref) are | |
1537 encoded as below: | |
1538 | |
1539 0--1--2 -- ascent | |
1540 | | | |
1541 | | | |
1542 | 4 -+--- center | |
1543 -- 3 5 -- baseline | |
1544 | | | |
1545 6--7--8 -- descent | |
1546 | |
1547 Now, we calculate the column offset of the new glyph | |
1548 from the left edge of the first glyph. This can avoid | |
1549 the same calculation everytime displaying this | |
1550 composite character. */ | |
1551 | |
1552 /* Reference points of global glyph and new glyph. */ | |
1553 int global_ref = (cmpcharp->cmp_rule[i] - 0xA0) / 9; | |
1554 int new_ref = (cmpcharp->cmp_rule[i] - 0xA0) % 9; | |
1555 /* Column offset relative to the first glyph. */ | |
1556 float left = (leftmost | |
1557 + (global_ref % 3) * (rightmost - leftmost) / 2.0 | |
1558 - (new_ref % 3) * width / 2.0); | |
1559 | |
1560 cmpcharp->col_offset[i] = left; | |
1561 if (left < leftmost) | |
1562 leftmost = left; | |
1563 if (left + width > rightmost) | |
1564 rightmost = left + width; | |
1565 } | |
1566 else | |
1567 { | |
1568 if (width > rightmost) | |
1569 rightmost = width; | |
1570 } | |
1571 } | |
1572 if (embedded_rule) | |
1573 { | |
1574 /* Now col_offset[N] are relative to the left edge of the | |
1575 first component. Make them relative to the left edge of | |
1576 overall glyph. */ | |
1577 for (i = 0; i < chars; i++) | |
1578 cmpcharp->col_offset[i] -= leftmost; | |
1579 /* Make rightmost holds width of overall glyph. */ | |
1580 rightmost -= leftmost; | |
1581 } | |
1582 | |
1583 cmpcharp->width = rightmost; | |
1584 if (cmpcharp->width < rightmost) | |
1585 /* To get a ceiling integer value. */ | |
1586 cmpcharp->width++; | |
1587 } | |
1588 | |
1589 cmpchar_table[n_cmpchars] = cmpcharp; | |
1590 | |
1591 return n_cmpchars++; | |
1592 } | |
1593 | |
1594 /* Return the Nth element of the composite character C. */ | |
1595 int | |
1596 cmpchar_component (c, n) | |
1597 unsigned int c, n; | |
1598 { | |
1599 int id = COMPOSITE_CHAR_ID (c); | |
1600 | |
1601 if (id >= n_cmpchars /* C is not a valid composite character. */ | |
1602 || n >= cmpchar_table[id]->glyph_len) /* No such component. */ | |
1603 return -1; | |
1604 /* No face data is stored in glyph code. */ | |
1605 return ((int) (cmpchar_table[id]->glyph[n])); | |
1606 } | |
1607 | |
1608 DEFUN ("cmpcharp", Fcmpcharp, Scmpcharp, 1, 1, 0, | |
1609 "T if CHAR is a composite character.") | |
1610 (ch) | |
1611 Lisp_Object ch; | |
1612 { | |
1613 CHECK_NUMBER (ch, 0); | |
1614 return (COMPOSITE_CHAR_P (XINT (ch)) ? Qt : Qnil); | |
1615 } | |
1616 | |
1617 DEFUN ("composite-char-component", Fcmpchar_component, Scmpchar_component, | |
1618 2, 2, 0, | |
1619 "Return the IDXth component character of composite character CHARACTER.") | |
1620 (character, idx) | |
1621 Lisp_Object character, idx; | |
1622 { | |
1623 int c; | |
1624 | |
1625 CHECK_NUMBER (character, 0); | |
1626 CHECK_NUMBER (idx, 1); | |
1627 | |
1628 if ((c = cmpchar_component (XINT (character), XINT (idx))) < 0) | |
1629 args_out_of_range (character, idx); | |
1630 | |
1631 return make_number (c); | |
1632 } | |
1633 | |
1634 DEFUN ("composite-char-composition-rule", Fcmpchar_cmp_rule, Scmpchar_cmp_rule, | |
1635 2, 2, 0, | |
17121
f8e2cd94c274
(Fcmpchar_cmp_rule): Escape newlines in docstring.
Kenichi Handa <handa@m17n.org>
parents:
17071
diff
changeset
|
1636 "Return the Nth composition rule embedded in composite character CHARACTER.\n\ |
f8e2cd94c274
(Fcmpchar_cmp_rule): Escape newlines in docstring.
Kenichi Handa <handa@m17n.org>
parents:
17071
diff
changeset
|
1637 The returned rule is for composing the Nth component\n\ |
f8e2cd94c274
(Fcmpchar_cmp_rule): Escape newlines in docstring.
Kenichi Handa <handa@m17n.org>
parents:
17071
diff
changeset
|
1638 on the (N-1)th component. If N is 0, the returned value is always 255.") |
f8e2cd94c274
(Fcmpchar_cmp_rule): Escape newlines in docstring.
Kenichi Handa <handa@m17n.org>
parents:
17071
diff
changeset
|
1639 (character, n) |
f8e2cd94c274
(Fcmpchar_cmp_rule): Escape newlines in docstring.
Kenichi Handa <handa@m17n.org>
parents:
17071
diff
changeset
|
1640 Lisp_Object character, n; |
17052 | 1641 { |
1642 int id, i; | |
1643 | |
1644 CHECK_NUMBER (character, 0); | |
17121
f8e2cd94c274
(Fcmpchar_cmp_rule): Escape newlines in docstring.
Kenichi Handa <handa@m17n.org>
parents:
17071
diff
changeset
|
1645 CHECK_NUMBER (n, 1); |
17052 | 1646 |
1647 id = COMPOSITE_CHAR_ID (XINT (character)); | |
1648 if (id < 0 || id >= n_cmpchars) | |
1649 error ("Invalid composite character: %d", XINT (character)); | |
17121
f8e2cd94c274
(Fcmpchar_cmp_rule): Escape newlines in docstring.
Kenichi Handa <handa@m17n.org>
parents:
17071
diff
changeset
|
1650 i = XINT (n); |
17052 | 1651 if (i > cmpchar_table[id]->glyph_len) |
17121
f8e2cd94c274
(Fcmpchar_cmp_rule): Escape newlines in docstring.
Kenichi Handa <handa@m17n.org>
parents:
17071
diff
changeset
|
1652 args_out_of_range (character, n); |
17052 | 1653 |
1654 return make_number (cmpchar_table[id]->cmp_rule[i]); | |
1655 } | |
1656 | |
1657 DEFUN ("composite-char-composition-rule-p", Fcmpchar_cmp_rule_p, | |
1658 Scmpchar_cmp_rule_p, 1, 1, 0, | |
1659 "Return non-nil if composite character CHARACTER contains a embedded rule.") | |
1660 (character) | |
1661 Lisp_Object character; | |
1662 { | |
1663 int id; | |
1664 | |
1665 CHECK_NUMBER (character, 0); | |
1666 id = COMPOSITE_CHAR_ID (XINT (character)); | |
1667 if (id < 0 || id >= n_cmpchars) | |
1668 error ("Invalid composite character: %d", XINT (character)); | |
1669 | |
1670 return (cmpchar_table[id]->cmp_rule ? Qt : Qnil); | |
1671 } | |
1672 | |
1673 DEFUN ("composite-char-component-count", Fcmpchar_cmp_count, | |
1674 Scmpchar_cmp_count, 1, 1, 0, | |
1675 "Return number of compoents of composite character CHARACTER.") | |
1676 (character) | |
1677 Lisp_Object character; | |
1678 { | |
1679 int id; | |
1680 | |
1681 CHECK_NUMBER (character, 0); | |
1682 id = COMPOSITE_CHAR_ID (XINT (character)); | |
1683 if (id < 0 || id >= n_cmpchars) | |
1684 error ("Invalid composite character: %d", XINT (character)); | |
1685 | |
1686 return (make_number (cmpchar_table[id]->glyph_len)); | |
1687 } | |
1688 | |
1689 DEFUN ("compose-string", Fcompose_string, Scompose_string, | |
1690 1, 1, 0, | |
1691 "Return one char string composed from all characters in STRING.") | |
1692 (str) | |
1693 Lisp_Object str; | |
1694 { | |
1695 unsigned char buf[MAX_LENGTH_OF_MULTI_BYTE_FORM], *p, *pend, *ptemp; | |
1696 int len, i; | |
1697 | |
1698 CHECK_STRING (str, 0); | |
1699 | |
1700 buf[0] = LEADING_CODE_COMPOSITION; | |
1701 p = XSTRING (str)->data; | |
21244
50929073a0ba
Use STRING_BYTES and SET_STRING_BYTES.
Richard M. Stallman <rms@gnu.org>
parents:
21063
diff
changeset
|
1702 pend = p + STRING_BYTES (XSTRING (str)); |
17052 | 1703 i = 1; |
1704 while (p < pend) | |
1705 { | |
1706 if (*p < 0x20 || *p == 127) /* control code */ | |
1707 error ("Invalid component character: %d", *p); | |
1708 else if (*p < 0x80) /* ASCII */ | |
1709 { | |
1710 if (i + 2 >= MAX_LENGTH_OF_MULTI_BYTE_FORM) | |
1711 error ("Too long string to be composed: %s", XSTRING (str)->data); | |
1712 /* Prepend an ASCII charset indicator 0xA0, set MSB of the | |
1713 code itself. */ | |
1714 buf[i++] = 0xA0; | |
1715 buf[i++] = *p++ + 0x80; | |
1716 } | |
1717 else if (*p == LEADING_CODE_COMPOSITION) /* composite char */ | |
1718 { | |
1719 /* Already composed. Eliminate the heading | |
1720 LEADING_CODE_COMPOSITION, keep the remaining bytes | |
1721 unchanged. */ | |
1722 p++; | |
1723 ptemp = p; | |
20534
066251bcf9f7
(Fchars_in_string): Update call to CHAR_HEAD_P.
Richard M. Stallman <rms@gnu.org>
parents:
20435
diff
changeset
|
1724 while (! CHAR_HEAD_P (*p)) p++; |
17052 | 1725 if (i + (p - ptemp) >= MAX_LENGTH_OF_MULTI_BYTE_FORM) |
1726 error ("Too long string to be composed: %s", XSTRING (str)->data); | |
1727 bcopy (ptemp, buf + i, p - ptemp); | |
1728 i += p - ptemp; | |
1729 } | |
1730 else /* multibyte char */ | |
1731 { | |
1732 /* Add 0x20 to the base leading-code, keep the remaining | |
1733 bytes unchanged. */ | |
1734 len = BYTES_BY_CHAR_HEAD (*p); | |
1735 if (i + len >= MAX_LENGTH_OF_MULTI_BYTE_FORM) | |
1736 error ("Too long string to be composed: %s", XSTRING (str)->data); | |
1737 bcopy (p, buf + i, len); | |
1738 buf[i] += 0x20; | |
1739 p += len, i += len; | |
1740 } | |
1741 } | |
1742 | |
1743 if (i < 5) | |
1744 /* STR contains only one character, which can't be composed. */ | |
1745 error ("Too short string to be composed: %s", XSTRING (str)->data); | |
1746 | |
21255
3d75330ce275
(Fstring): Use make_string_from_bytes.
Richard M. Stallman <rms@gnu.org>
parents:
21244
diff
changeset
|
1747 return make_string_from_bytes (buf, 1, i); |
17052 | 1748 } |
1749 | |
1750 | |
21514 | 1751 int |
17052 | 1752 charset_id_internal (charset_name) |
1753 char *charset_name; | |
1754 { | |
22927
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
1755 Lisp_Object val; |
17052 | 1756 |
22927
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
1757 val= Fget (intern (charset_name), Qcharset); |
17052 | 1758 if (!VECTORP (val)) |
1759 error ("Charset %s is not defined", charset_name); | |
1760 | |
1761 return (XINT (XVECTOR (val)->contents[0])); | |
1762 } | |
1763 | |
1764 DEFUN ("setup-special-charsets", Fsetup_special_charsets, | |
1765 Ssetup_special_charsets, 0, 0, 0, "Internal use only.") | |
1766 () | |
1767 { | |
1768 charset_latin_iso8859_1 = charset_id_internal ("latin-iso8859-1"); | |
1769 charset_jisx0208_1978 = charset_id_internal ("japanese-jisx0208-1978"); | |
1770 charset_jisx0208 = charset_id_internal ("japanese-jisx0208"); | |
1771 charset_katakana_jisx0201 = charset_id_internal ("katakana-jisx0201"); | |
1772 charset_latin_jisx0201 = charset_id_internal ("latin-jisx0201"); | |
1773 charset_big5_1 = charset_id_internal ("chinese-big5-1"); | |
1774 charset_big5_2 = charset_id_internal ("chinese-big5-2"); | |
1775 return Qnil; | |
1776 } | |
1777 | |
21514 | 1778 void |
17052 | 1779 init_charset_once () |
1780 { | |
1781 int i, j, k; | |
1782 | |
1783 staticpro (&Vcharset_table); | |
1784 staticpro (&Vcharset_symbol_table); | |
22703
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
1785 staticpro (&Vgeneric_character_list); |
17052 | 1786 |
1787 /* This has to be done here, before we call Fmake_char_table. */ | |
1788 Qcharset_table = intern ("charset-table"); | |
1789 staticpro (&Qcharset_table); | |
1790 | |
1791 /* Intern this now in case it isn't already done. | |
1792 Setting this variable twice is harmless. | |
1793 But don't staticpro it here--that is done in alloc.c. */ | |
1794 Qchar_table_extra_slots = intern ("char-table-extra-slots"); | |
1795 | |
1796 /* Now we are ready to set up this property, so we can | |
1797 create the charset table. */ | |
1798 Fput (Qcharset_table, Qchar_table_extra_slots, make_number (0)); | |
1799 Vcharset_table = Fmake_char_table (Qcharset_table, Qnil); | |
1800 | |
17186
65bc06706714
Adjusted for the change of MAX_CHARSET.
Kenichi Handa <handa@m17n.org>
parents:
17121
diff
changeset
|
1801 Vcharset_symbol_table = Fmake_vector (make_number (MAX_CHARSET + 1), Qnil); |
17052 | 1802 |
1803 /* Setup tables. */ | |
1804 for (i = 0; i < 2; i++) | |
1805 for (j = 0; j < 2; j++) | |
1806 for (k = 0; k < 128; k++) | |
1807 iso_charset_table [i][j][k] = -1; | |
1808 | |
1809 bzero (cmpchar_hash_table, sizeof cmpchar_hash_table); | |
1810 cmpchar_table_size = n_cmpchars = 0; | |
1811 | |
23628
4a0a107fac9e
(string_to_non_ascii_char): Change the check for the
Kenichi Handa <handa@m17n.org>
parents:
23576
diff
changeset
|
1812 for (i = 0; i < 128; i++) |
17052 | 1813 BYTES_BY_CHAR_HEAD (i) = 1; |
23628
4a0a107fac9e
(string_to_non_ascii_char): Change the check for the
Kenichi Handa <handa@m17n.org>
parents:
23576
diff
changeset
|
1814 for (i = MIN_CHARSET_OFFICIAL_DIMENSION1; |
4a0a107fac9e
(string_to_non_ascii_char): Change the check for the
Kenichi Handa <handa@m17n.org>
parents:
23576
diff
changeset
|
1815 i <= MAX_CHARSET_OFFICIAL_DIMENSION1; i++) |
4a0a107fac9e
(string_to_non_ascii_char): Change the check for the
Kenichi Handa <handa@m17n.org>
parents:
23576
diff
changeset
|
1816 BYTES_BY_CHAR_HEAD (i) = 2; |
4a0a107fac9e
(string_to_non_ascii_char): Change the check for the
Kenichi Handa <handa@m17n.org>
parents:
23576
diff
changeset
|
1817 for (i = MIN_CHARSET_OFFICIAL_DIMENSION2; |
4a0a107fac9e
(string_to_non_ascii_char): Change the check for the
Kenichi Handa <handa@m17n.org>
parents:
23576
diff
changeset
|
1818 i <= MAX_CHARSET_OFFICIAL_DIMENSION2; i++) |
4a0a107fac9e
(string_to_non_ascii_char): Change the check for the
Kenichi Handa <handa@m17n.org>
parents:
23576
diff
changeset
|
1819 BYTES_BY_CHAR_HEAD (i) = 3; |
17052 | 1820 BYTES_BY_CHAR_HEAD (LEADING_CODE_PRIVATE_11) = 3; |
1821 BYTES_BY_CHAR_HEAD (LEADING_CODE_PRIVATE_12) = 3; | |
1822 BYTES_BY_CHAR_HEAD (LEADING_CODE_PRIVATE_21) = 4; | |
1823 BYTES_BY_CHAR_HEAD (LEADING_CODE_PRIVATE_22) = 4; | |
23628
4a0a107fac9e
(string_to_non_ascii_char): Change the check for the
Kenichi Handa <handa@m17n.org>
parents:
23576
diff
changeset
|
1824 /* The followings don't reflect the actual bytes, but just to tell |
17052 | 1825 that it is a start of a multibyte character. */ |
1826 BYTES_BY_CHAR_HEAD (LEADING_CODE_COMPOSITION) = 2; | |
23628
4a0a107fac9e
(string_to_non_ascii_char): Change the check for the
Kenichi Handa <handa@m17n.org>
parents:
23576
diff
changeset
|
1827 BYTES_BY_CHAR_HEAD (0x9E) = 2; |
4a0a107fac9e
(string_to_non_ascii_char): Change the check for the
Kenichi Handa <handa@m17n.org>
parents:
23576
diff
changeset
|
1828 BYTES_BY_CHAR_HEAD (0x9F) = 2; |
17052 | 1829 |
1830 for (i = 0; i < 128; i++) | |
1831 WIDTH_BY_CHAR_HEAD (i) = 1; | |
1832 for (; i < 256; i++) | |
1833 WIDTH_BY_CHAR_HEAD (i) = 4; | |
1834 WIDTH_BY_CHAR_HEAD (LEADING_CODE_PRIVATE_11) = 1; | |
1835 WIDTH_BY_CHAR_HEAD (LEADING_CODE_PRIVATE_12) = 2; | |
1836 WIDTH_BY_CHAR_HEAD (LEADING_CODE_PRIVATE_21) = 1; | |
1837 WIDTH_BY_CHAR_HEAD (LEADING_CODE_PRIVATE_22) = 2; | |
22703
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
1838 |
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
1839 { |
22927
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
1840 Lisp_Object val; |
22703
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
1841 |
22927
209acf11198c
(multibyte_char_to_unibyte): New function.
Kenichi Handa <handa@m17n.org>
parents:
22774
diff
changeset
|
1842 val = Qnil; |
22703
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
1843 for (i = 0x81; i < 0x90; i++) |
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
1844 val = Fcons (make_number ((i - 0x70) << 7), val); |
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
1845 for (; i < 0x9A; i++) |
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
1846 val = Fcons (make_number ((i - 0x8F) << 14), val); |
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
1847 for (i = 0xA0; i < 0xF0; i++) |
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
1848 val = Fcons (make_number ((i - 0x70) << 7), val); |
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
1849 for (; i < 0xFF; i++) |
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
1850 val = Fcons (make_number ((i - 0xE0) << 14), val); |
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
1851 val = Fcons (make_number (GENERIC_COMPOSITION_CHAR), val); |
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
1852 Vgeneric_character_list = Fnreverse (val); |
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
1853 } |
23154
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
1854 |
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
1855 nonascii_insert_offset = 0; |
a9cbf64603ca
(unibyte_char_to_multibyte):
Kenichi Handa <handa@m17n.org>
parents:
23140
diff
changeset
|
1856 Vnonascii_translation_table = Qnil; |
17052 | 1857 } |
1858 | |
1859 #ifdef emacs | |
1860 | |
21514 | 1861 void |
17052 | 1862 syms_of_charset () |
1863 { | |
1864 Qascii = intern ("ascii"); | |
1865 staticpro (&Qascii); | |
1866 | |
1867 Qcharset = intern ("charset"); | |
1868 staticpro (&Qcharset); | |
1869 | |
1870 /* Define ASCII charset now. */ | |
1871 update_charset_table (make_number (CHARSET_ASCII), | |
1872 make_number (1), make_number (94), | |
1873 make_number (1), | |
1874 make_number (0), | |
1875 make_number ('B'), | |
1876 make_number (0), | |
1877 build_string ("ASCII"), | |
1878 build_string ("ASCII"), | |
1879 build_string ("ASCII (ISO646 IRV)")); | |
1880 CHARSET_SYMBOL (CHARSET_ASCII) = Qascii; | |
1881 Fput (Qascii, Qcharset, CHARSET_TABLE_ENTRY (CHARSET_ASCII)); | |
1882 | |
1883 Qcomposition = intern ("composition"); | |
1884 staticpro (&Qcomposition); | |
1885 CHARSET_SYMBOL (CHARSET_COMPOSITION) = Qcomposition; | |
1886 | |
23489
09201cebfa21
(Vauto_fill_chars, Qauto_fill_chars): New variables.
Kenichi Handa <handa@m17n.org>
parents:
23427
diff
changeset
|
1887 Qauto_fill_chars = intern ("auto-fill-chars"); |
09201cebfa21
(Vauto_fill_chars, Qauto_fill_chars): New variables.
Kenichi Handa <handa@m17n.org>
parents:
23427
diff
changeset
|
1888 staticpro (&Qauto_fill_chars); |
09201cebfa21
(Vauto_fill_chars, Qauto_fill_chars): New variables.
Kenichi Handa <handa@m17n.org>
parents:
23427
diff
changeset
|
1889 Fput (Qauto_fill_chars, Qchar_table_extra_slots, make_number (0)); |
09201cebfa21
(Vauto_fill_chars, Qauto_fill_chars): New variables.
Kenichi Handa <handa@m17n.org>
parents:
23427
diff
changeset
|
1890 |
17052 | 1891 defsubr (&Sdefine_charset); |
22703
15e0119749cf
(Vgeneric_character_list): New variable.
Kenichi Handa <handa@m17n.org>
parents:
22524
diff
changeset
|
1892 defsubr (&Sgeneric_character_list); |
20435
099812ea310f
(Fget_unused_iso_final_char): New function.
Kenichi Handa <handa@m17n.org>
parents:
20362
diff
changeset
|
1893 defsubr (&Sget_unused_iso_final_char); |
17052 | 1894 defsubr (&Sdeclare_equiv_charset); |
1895 defsubr (&Sfind_charset_region); | |
1896 defsubr (&Sfind_charset_string); | |
1897 defsubr (&Smake_char_internal); | |
1898 defsubr (&Ssplit_char); | |
1899 defsubr (&Schar_charset); | |
21445
4c0b4a1025cd
(string_to_non_ascii_char): Include garbage bytes (if
Kenichi Handa <handa@m17n.org>
parents:
21419
diff
changeset
|
1900 defsubr (&Scharset_after); |
17052 | 1901 defsubr (&Siso_charset); |
20152
9a3343c36e83
(char_valid_p): New function
Kenichi Handa <handa@m17n.org>
parents:
19983
diff
changeset
|
1902 defsubr (&Schar_valid_p); |
21034
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
1903 defsubr (&Sunibyte_char_to_multibyte); |
23060
5036ee3de0ac
(Fmultibyte_char_to_unibyte): New function.
Richard M. Stallman <rms@gnu.org>
parents:
22927
diff
changeset
|
1904 defsubr (&Smultibyte_char_to_unibyte); |
17052 | 1905 defsubr (&Schar_bytes); |
1906 defsubr (&Schar_width); | |
1907 defsubr (&Sstring_width); | |
1908 defsubr (&Schar_direction); | |
19415
309b9a0d8a45
(Fchars_in_region): Renamed form Fcount_chars_region.
Kenichi Handa <handa@m17n.org>
parents:
19384
diff
changeset
|
1909 defsubr (&Schars_in_region); |
20614
a4800f9842e4
(multibyte_chars_in_text): New function.
Richard M. Stallman <rms@gnu.org>
parents:
20575
diff
changeset
|
1910 defsubr (&Sstring); |
17052 | 1911 defsubr (&Scmpcharp); |
1912 defsubr (&Scmpchar_component); | |
1913 defsubr (&Scmpchar_cmp_rule); | |
1914 defsubr (&Scmpchar_cmp_rule_p); | |
1915 defsubr (&Scmpchar_cmp_count); | |
1916 defsubr (&Scompose_string); | |
1917 defsubr (&Ssetup_special_charsets); | |
1918 | |
1919 DEFVAR_LISP ("charset-list", &Vcharset_list, | |
1920 "List of charsets ever defined."); | |
1921 Vcharset_list = Fcons (Qascii, Qnil); | |
1922 | |
22185
80a2aa51a6e1
Change term "character translation table" to
Kenichi Handa <handa@m17n.org>
parents:
22168
diff
changeset
|
1923 DEFVAR_LISP ("translation-table-vector", &Vtranslation_table_vector, |
22121
6e79a15594ab
Change terms unify/unification to
Kenichi Handa <handa@m17n.org>
parents:
21718
diff
changeset
|
1924 "Vector of cons cell of a symbol and translation table ever defined.\n\ |
6e79a15594ab
Change terms unify/unification to
Kenichi Handa <handa@m17n.org>
parents:
21718
diff
changeset
|
1925 An ID of a translation table is an index of this vector."); |
22185
80a2aa51a6e1
Change term "character translation table" to
Kenichi Handa <handa@m17n.org>
parents:
22168
diff
changeset
|
1926 Vtranslation_table_vector = Fmake_vector (make_number (16), Qnil); |
20720
f084bb8d535f
(min_composite_char): New variable.
Kenichi Handa <handa@m17n.org>
parents:
20705
diff
changeset
|
1927 |
17052 | 1928 DEFVAR_INT ("leading-code-composition", &leading_code_composition, |
1929 "Leading-code of composite characters."); | |
1930 leading_code_composition = LEADING_CODE_COMPOSITION; | |
1931 | |
1932 DEFVAR_INT ("leading-code-private-11", &leading_code_private_11, | |
1933 "Leading-code of private TYPE9N charset of column-width 1."); | |
1934 leading_code_private_11 = LEADING_CODE_PRIVATE_11; | |
1935 | |
1936 DEFVAR_INT ("leading-code-private-12", &leading_code_private_12, | |
1937 "Leading-code of private TYPE9N charset of column-width 2."); | |
1938 leading_code_private_12 = LEADING_CODE_PRIVATE_12; | |
1939 | |
1940 DEFVAR_INT ("leading-code-private-21", &leading_code_private_21, | |
1941 "Leading-code of private TYPE9Nx9N charset of column-width 1."); | |
1942 leading_code_private_21 = LEADING_CODE_PRIVATE_21; | |
1943 | |
1944 DEFVAR_INT ("leading-code-private-22", &leading_code_private_22, | |
1945 "Leading-code of private TYPE9Nx9N charset of column-width 2."); | |
1946 leading_code_private_22 = LEADING_CODE_PRIVATE_22; | |
20705
a949dc65fbea
(nonascii_insert_offset): Variable moved from cmds.c.
Richard M. Stallman <rms@gnu.org>
parents:
20636
diff
changeset
|
1947 |
a949dc65fbea
(nonascii_insert_offset): Variable moved from cmds.c.
Richard M. Stallman <rms@gnu.org>
parents:
20636
diff
changeset
|
1948 DEFVAR_INT ("nonascii-insert-offset", &nonascii_insert_offset, |
21034
f3128abaf8aa
(DEFAULT_NONASCII_INSERT_OFFSET): Macro definition is
Kenichi Handa <handa@m17n.org>
parents:
20933
diff
changeset
|
1949 "Offset for converting non-ASCII unibyte codes 0240...0377 to multibyte.\n\ |
20890
c7cfd531cf2b
(Vnonascii_translate_table): New variable.
Richard M. Stallman <rms@gnu.org>
parents:
20833
diff
changeset
|
1950 This is used for converting unibyte text to multibyte,\n\ |
c7cfd531cf2b
(Vnonascii_translate_table): New variable.
Richard M. Stallman <rms@gnu.org>
parents:
20833
diff
changeset
|
1951 and for inserting character codes specified by number.\n\n\ |
21718
361e50e075d8
(syms_of_charset): Doc fix for nonascii-insert-offset.
Richard M. Stallman <rms@gnu.org>
parents:
21715
diff
changeset
|
1952 This serves to convert a Latin-1 or similar 8-bit character code\n\ |
361e50e075d8
(syms_of_charset): Doc fix for nonascii-insert-offset.
Richard M. Stallman <rms@gnu.org>
parents:
21715
diff
changeset
|
1953 to the corresponding Emacs multibyte character code.\n\ |
361e50e075d8
(syms_of_charset): Doc fix for nonascii-insert-offset.
Richard M. Stallman <rms@gnu.org>
parents:
21715
diff
changeset
|
1954 Typically the value should be (- (make-char CHARSET 0) 128),\n\ |
361e50e075d8
(syms_of_charset): Doc fix for nonascii-insert-offset.
Richard M. Stallman <rms@gnu.org>
parents:
21715
diff
changeset
|
1955 for your choice of character set.\n\ |
22185
80a2aa51a6e1
Change term "character translation table" to
Kenichi Handa <handa@m17n.org>
parents:
22168
diff
changeset
|
1956 If `nonascii-translation-table' is non-nil, it overrides this variable."); |
20705
a949dc65fbea
(nonascii_insert_offset): Variable moved from cmds.c.
Richard M. Stallman <rms@gnu.org>
parents:
20636
diff
changeset
|
1957 nonascii_insert_offset = 0; |
20720
f084bb8d535f
(min_composite_char): New variable.
Kenichi Handa <handa@m17n.org>
parents:
20705
diff
changeset
|
1958 |
22121
6e79a15594ab
Change terms unify/unification to
Kenichi Handa <handa@m17n.org>
parents:
21718
diff
changeset
|
1959 DEFVAR_LISP ("nonascii-translation-table", &Vnonascii_translation_table, |
22185
80a2aa51a6e1
Change term "character translation table" to
Kenichi Handa <handa@m17n.org>
parents:
22168
diff
changeset
|
1960 "Translation table to convert non-ASCII unibyte codes to multibyte.\n\ |
20890
c7cfd531cf2b
(Vnonascii_translate_table): New variable.
Richard M. Stallman <rms@gnu.org>
parents:
20833
diff
changeset
|
1961 This is used for converting unibyte text to multibyte,\n\ |
c7cfd531cf2b
(Vnonascii_translate_table): New variable.
Richard M. Stallman <rms@gnu.org>
parents:
20833
diff
changeset
|
1962 and for inserting character codes specified by number.\n\n\ |
c7cfd531cf2b
(Vnonascii_translate_table): New variable.
Richard M. Stallman <rms@gnu.org>
parents:
20833
diff
changeset
|
1963 Conversion is performed only when multibyte characters are enabled,\n\ |
c7cfd531cf2b
(Vnonascii_translate_table): New variable.
Richard M. Stallman <rms@gnu.org>
parents:
20833
diff
changeset
|
1964 and it serves to convert a Latin-1 or similar 8-bit character code\n\ |
c7cfd531cf2b
(Vnonascii_translate_table): New variable.
Richard M. Stallman <rms@gnu.org>
parents:
20833
diff
changeset
|
1965 to the corresponding Emacs character code.\n\n\ |
22289
141f0392fb81
(syms_of_charset): Put \n\ at eol of docstring.
Karl Heuer <kwzh@gnu.org>
parents:
22185
diff
changeset
|
1966 If this is nil, `nonascii-insert-offset' is used instead.\n\ |
22121
6e79a15594ab
Change terms unify/unification to
Kenichi Handa <handa@m17n.org>
parents:
21718
diff
changeset
|
1967 See also the docstring of `make-translation-table'."); |
6e79a15594ab
Change terms unify/unification to
Kenichi Handa <handa@m17n.org>
parents:
21718
diff
changeset
|
1968 Vnonascii_translation_table = Qnil; |
20890
c7cfd531cf2b
(Vnonascii_translate_table): New variable.
Richard M. Stallman <rms@gnu.org>
parents:
20833
diff
changeset
|
1969 |
20720
f084bb8d535f
(min_composite_char): New variable.
Kenichi Handa <handa@m17n.org>
parents:
20705
diff
changeset
|
1970 DEFVAR_INT ("min-composite-char", &min_composite_char, |
f084bb8d535f
(min_composite_char): New variable.
Kenichi Handa <handa@m17n.org>
parents:
20705
diff
changeset
|
1971 "Minimum character code of a composite character."); |
f084bb8d535f
(min_composite_char): New variable.
Kenichi Handa <handa@m17n.org>
parents:
20705
diff
changeset
|
1972 min_composite_char = MIN_CHAR_COMPOSITION; |
23489
09201cebfa21
(Vauto_fill_chars, Qauto_fill_chars): New variables.
Kenichi Handa <handa@m17n.org>
parents:
23427
diff
changeset
|
1973 |
09201cebfa21
(Vauto_fill_chars, Qauto_fill_chars): New variables.
Kenichi Handa <handa@m17n.org>
parents:
23427
diff
changeset
|
1974 DEFVAR_LISP ("auto-fill-chars", &Vauto_fill_chars, |
09201cebfa21
(Vauto_fill_chars, Qauto_fill_chars): New variables.
Kenichi Handa <handa@m17n.org>
parents:
23427
diff
changeset
|
1975 "A char-table for characters which invoke auto-filling.\n\ |
09201cebfa21
(Vauto_fill_chars, Qauto_fill_chars): New variables.
Kenichi Handa <handa@m17n.org>
parents:
23427
diff
changeset
|
1976 Such characters has value t in this table."); |
09201cebfa21
(Vauto_fill_chars, Qauto_fill_chars): New variables.
Kenichi Handa <handa@m17n.org>
parents:
23427
diff
changeset
|
1977 Vauto_fill_chars = Fmake_char_table (Qauto_fill_chars, Qnil); |
23576 | 1978 CHAR_TABLE_SET (Vauto_fill_chars, make_number (' '), Qt); |
1979 CHAR_TABLE_SET (Vauto_fill_chars, make_number ('\n'), Qt); | |
17052 | 1980 } |
1981 | |
1982 #endif /* emacs */ |