|
70
|
1 /* Header for code conversion stuff
|
|
|
2 Copyright (C) 1991, 1995 Free Software Foundation, Inc.
|
|
|
3 Copyright (C) 1995 Sun Microsystems, Inc.
|
|
|
4
|
|
|
5 This file is part of XEmacs.
|
|
|
6
|
|
|
7 XEmacs is free software; you can redistribute it and/or modify it
|
|
|
8 under the terms of the GNU General Public License as published by the
|
|
|
9 Free Software Foundation; either version 2, or (at your option) any
|
|
|
10 later version.
|
|
|
11
|
|
|
12 XEmacs is distributed in the hope that it will be useful, but WITHOUT
|
|
|
13 ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
|
|
14 FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
|
|
|
15 for more details.
|
|
|
16
|
|
|
17 You should have received a copy of the GNU General Public License
|
|
|
18 along with XEmacs; 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. */
|
|
|
21
|
|
|
22 /* Synched up with: Mule 2.3. Not in FSF. */
|
|
|
23
|
|
|
24 /* 91.10.09 written by K.Handa <handa@etl.go.jp> */
|
|
|
25 /* Rewritten by Ben Wing <wing@666.com>. */
|
|
|
26
|
|
|
27 #ifndef _XEMACS_MULE_CODING_H_
|
|
|
28 #define _XEMACS_MULE_CODING_H_
|
|
|
29
|
|
|
30 struct decoding_stream;
|
|
|
31 struct encoding_stream;
|
|
|
32
|
|
|
33 /* Coding system types. These go into the TYPE field of a
|
|
|
34 struct Lisp_Coding_System. */
|
|
|
35
|
|
|
36 enum coding_system_type
|
|
|
37 {
|
|
|
38 CODESYS_AUTODETECT, /* Automatic conversion. */
|
|
|
39 CODESYS_SHIFT_JIS, /* Shift-JIS; Hankaku (half-width) KANA
|
|
|
40 is also supported. */
|
|
|
41 CODESYS_ISO2022, /* Any ISO2022-compliant coding system.
|
|
|
42 Includes JIS, EUC, CTEXT */
|
|
|
43 CODESYS_BIG5, /* BIG5 (used for Taiwanese). */
|
|
|
44 CODESYS_CCL, /* Converter written in CCL. */
|
|
|
45 CODESYS_NO_CONVERSION /* "No conversion"; used for binary files.
|
|
|
46 We use quotes because there really
|
|
|
47 is some conversion being applied,
|
|
|
48 but it appears to the user as if
|
|
|
49 the text is read in without conversion. */
|
|
|
50 #ifdef DEBUG_XEMACS
|
|
|
51 ,CODESYS_INTERNAL /* Raw (internally-formatted) data. */
|
|
|
52 #endif
|
|
|
53 };
|
|
|
54
|
|
|
55 enum eol_type
|
|
|
56 {
|
|
|
57 EOL_AUTODETECT,
|
|
|
58 EOL_LF,
|
|
|
59 EOL_CRLF,
|
|
|
60 EOL_CR
|
|
|
61 };
|
|
|
62
|
|
185
|
63 typedef struct charset_conversion_spec charset_conversion_spec;
|
|
70
|
64 struct charset_conversion_spec
|
|
|
65 {
|
|
|
66 Lisp_Object from_charset;
|
|
|
67 Lisp_Object to_charset;
|
|
|
68 };
|
|
|
69
|
|
185
|
70 typedef struct
|
|
70
|
71 {
|
|
185
|
72 Dynarr_declare (charset_conversion_spec);
|
|
70
|
73 } charset_conversion_spec_dynarr;
|
|
|
74
|
|
|
75 struct Lisp_Coding_System
|
|
|
76 {
|
|
|
77 struct lcrecord_header header;
|
|
|
78
|
|
|
79 /* Name and doc string of this coding system. */
|
|
|
80 Lisp_Object name, doc_string;
|
|
|
81
|
|
|
82 /* This is the major type of the coding system -- one of Big5, ISO2022,
|
|
|
83 Shift-JIS, etc. See the constants above. */
|
|
|
84 enum coding_system_type type;
|
|
|
85
|
|
|
86 /* Mnemonic string displayed in the modeline when this coding
|
|
|
87 system is active for a particular buffer. */
|
|
|
88 Lisp_Object mnemonic;
|
|
|
89
|
|
|
90 Lisp_Object post_read_conversion, pre_write_conversion;
|
|
|
91
|
|
|
92 enum eol_type eol_type;
|
|
|
93
|
|
|
94 /* Subsidiary coding systems that specify a particular type of EOL
|
|
|
95 marking, rather than autodetecting it. These will only be non-nil
|
|
|
96 if (eol_type == EOL_AUTODETECT). */
|
|
|
97 Lisp_Object eol_lf, eol_crlf, eol_cr;
|
|
|
98
|
|
|
99 struct
|
|
187
|
100 {
|
|
|
101 /* What are the charsets to be initially designated to G0, G1,
|
|
|
102 G2, G3? If t, no charset is initially designated. If nil,
|
|
|
103 no charset is initially designated and no charset is allowed
|
|
|
104 to be designated. */
|
|
|
105 Lisp_Object initial_charset[4];
|
|
70
|
106
|
|
187
|
107 /* If true, a designation escape sequence needs to be sent on output
|
|
|
108 for the charset in G[0-3] before that charset is used. */
|
|
|
109 unsigned char force_charset_on_output[4];
|
|
70
|
110
|
|
187
|
111 charset_conversion_spec_dynarr *input_conv;
|
|
|
112 charset_conversion_spec_dynarr *output_conv;
|
|
70
|
113
|
|
187
|
114 unsigned int shoort :1; /* C makes you speak Dutch */
|
|
|
115 unsigned int no_ascii_eol :1;
|
|
|
116 unsigned int no_ascii_cntl :1;
|
|
|
117 unsigned int seven :1;
|
|
|
118 unsigned int lock_shift :1;
|
|
|
119 unsigned int no_iso6429 :1;
|
|
|
120 unsigned int escape_quoted :1;
|
|
|
121 } iso2022;
|
|
70
|
122
|
|
|
123 struct
|
|
187
|
124 {
|
|
|
125 /* For a CCL coding system, these specify the CCL programs used for
|
|
|
126 decoding (input) and encoding (output). */
|
|
|
127 Lisp_Object decode, encode;
|
|
|
128 } ccl;
|
|
70
|
129 };
|
|
|
130
|
|
|
131 DECLARE_LRECORD (coding_system, struct Lisp_Coding_System);
|
|
|
132 #define XCODING_SYSTEM(x) XRECORD (x, coding_system, struct Lisp_Coding_System)
|
|
|
133 #define XSETCODING_SYSTEM(x, p) XSETRECORD (x, p, coding_system)
|
|
|
134 #define CODING_SYSTEMP(x) RECORDP (x, coding_system)
|
|
|
135 #define GC_CODING_SYSTEMP(x) GC_RECORDP (x, coding_system)
|
|
|
136 #define CHECK_CODING_SYSTEM(x) CHECK_RECORD (x, coding_system)
|
|
|
137 #define CONCHECK_CODING_SYSTEM(x) CONCHECK_RECORD (x, coding_system)
|
|
|
138
|
|
|
139 #define CODING_SYSTEM_NAME(codesys) ((codesys)->name)
|
|
|
140 #define CODING_SYSTEM_DOC_STRING(codesys) ((codesys)->doc_string)
|
|
|
141 #define CODING_SYSTEM_TYPE(codesys) ((codesys)->type)
|
|
|
142 #define CODING_SYSTEM_MNEMONIC(codesys) ((codesys)->mnemonic)
|
|
|
143 #define CODING_SYSTEM_POST_READ_CONVERSION(codesys) \
|
|
|
144 ((codesys)->post_read_conversion)
|
|
|
145 #define CODING_SYSTEM_PRE_WRITE_CONVERSION(codesys) \
|
|
|
146 ((codesys)->pre_write_conversion)
|
|
|
147 #define CODING_SYSTEM_EOL_TYPE(codesys) ((codesys)->eol_type)
|
|
|
148 #define CODING_SYSTEM_EOL_LF(codesys) ((codesys)->eol_lf)
|
|
|
149 #define CODING_SYSTEM_EOL_CRLF(codesys) ((codesys)->eol_crlf)
|
|
|
150 #define CODING_SYSTEM_EOL_CR(codesys) ((codesys)->eol_cr)
|
|
|
151 #define CODING_SYSTEM_ISO2022_INITIAL_CHARSET(codesys, g) \
|
|
|
152 ((codesys)->iso2022.initial_charset[g])
|
|
|
153 #define CODING_SYSTEM_ISO2022_FORCE_CHARSET_ON_OUTPUT(codesys, g) \
|
|
|
154 ((codesys)->iso2022.force_charset_on_output[g])
|
|
|
155 #define CODING_SYSTEM_ISO2022_SHORT(codesys) ((codesys)->iso2022.shoort)
|
|
|
156 #define CODING_SYSTEM_ISO2022_NO_ASCII_EOL(codesys) \
|
|
|
157 ((codesys)->iso2022.no_ascii_eol)
|
|
|
158 #define CODING_SYSTEM_ISO2022_NO_ASCII_CNTL(codesys) \
|
|
|
159 ((codesys)->iso2022.no_ascii_cntl)
|
|
|
160 #define CODING_SYSTEM_ISO2022_SEVEN(codesys) ((codesys)->iso2022.seven)
|
|
|
161 #define CODING_SYSTEM_ISO2022_LOCK_SHIFT(codesys) \
|
|
|
162 ((codesys)->iso2022.lock_shift)
|
|
|
163 #define CODING_SYSTEM_ISO2022_NO_ISO6429(codesys) \
|
|
|
164 ((codesys)->iso2022.no_iso6429)
|
|
|
165 #define CODING_SYSTEM_ISO2022_ESCAPE_QUOTED(codesys) \
|
|
|
166 ((codesys)->iso2022.escape_quoted)
|
|
|
167 #define CODING_SYSTEM_CCL_DECODE(codesys) ((codesys)->ccl.decode)
|
|
|
168 #define CODING_SYSTEM_CCL_ENCODE(codesys) ((codesys)->ccl.encode)
|
|
|
169
|
|
|
170 #define XCODING_SYSTEM_NAME(codesys) \
|
|
|
171 CODING_SYSTEM_NAME (XCODING_SYSTEM (codesys))
|
|
|
172 #define XCODING_SYSTEM_DOC_STRING(codesys) \
|
|
|
173 CODING_SYSTEM_DOC_STRING (XCODING_SYSTEM (codesys))
|
|
|
174 #define XCODING_SYSTEM_TYPE(codesys) \
|
|
|
175 CODING_SYSTEM_TYPE (XCODING_SYSTEM (codesys))
|
|
|
176 #define XCODING_SYSTEM_MNEMONIC(codesys) \
|
|
|
177 CODING_SYSTEM_MNEMONIC (XCODING_SYSTEM (codesys))
|
|
|
178 #define XCODING_SYSTEM_POST_READ_CONVERSION(codesys) \
|
|
|
179 CODING_SYSTEM_POST_READ_CONVERSION (XCODING_SYSTEM (codesys))
|
|
|
180 #define XCODING_SYSTEM_PRE_WRITE_CONVERSION(codesys) \
|
|
|
181 CODING_SYSTEM_PRE_WRITE_CONVERSION (XCODING_SYSTEM (codesys))
|
|
|
182 #define XCODING_SYSTEM_EOL_TYPE(codesys) \
|
|
|
183 CODING_SYSTEM_EOL_TYPE (XCODING_SYSTEM (codesys))
|
|
|
184 #define XCODING_SYSTEM_EOL_LF(codesys) \
|
|
|
185 CODING_SYSTEM_EOL_LF (XCODING_SYSTEM (codesys))
|
|
|
186 #define XCODING_SYSTEM_EOL_CRLF(codesys) \
|
|
|
187 CODING_SYSTEM_EOL_CRLF (XCODING_SYSTEM (codesys))
|
|
|
188 #define XCODING_SYSTEM_EOL_CR(codesys) \
|
|
|
189 CODING_SYSTEM_EOL_CR (XCODING_SYSTEM (codesys))
|
|
|
190 #define XCODING_SYSTEM_ISO2022_INITIAL_CHARSET(codesys, g) \
|
|
|
191 CODING_SYSTEM_ISO2022_INITIAL_CHARSET (XCODING_SYSTEM (codesys), g)
|
|
|
192 #define XCODING_SYSTEM_ISO2022_FORCE_CHARSET_ON_OUTPUT(codesys, g) \
|
|
|
193 CODING_SYSTEM_ISO2022_FORCE_CHARSET_ON_OUTPUT (XCODING_SYSTEM (codesys), g)
|
|
|
194 #define XCODING_SYSTEM_ISO2022_SHORT(codesys) \
|
|
|
195 CODING_SYSTEM_ISO2022_SHORT (XCODING_SYSTEM (codesys))
|
|
|
196 #define XCODING_SYSTEM_ISO2022_NO_ASCII_EOL(codesys) \
|
|
|
197 CODING_SYSTEM_ISO2022_NO_ASCII_EOL (XCODING_SYSTEM (codesys))
|
|
|
198 #define XCODING_SYSTEM_ISO2022_NO_ASCII_CNTL(codesys) \
|
|
|
199 CODING_SYSTEM_ISO2022_NO_ASCII_CNTL (XCODING_SYSTEM (codesys))
|
|
|
200 #define XCODING_SYSTEM_ISO2022_SEVEN(codesys) \
|
|
|
201 CODING_SYSTEM_ISO2022_SEVEN (XCODING_SYSTEM (codesys))
|
|
|
202 #define XCODING_SYSTEM_ISO2022_LOCK_SHIFT(codesys) \
|
|
|
203 CODING_SYSTEM_ISO2022_LOCK_SHIFT (XCODING_SYSTEM (codesys))
|
|
|
204 #define XCODING_SYSTEM_ISO2022_NO_ISO6429(codesys) \
|
|
|
205 CODING_SYSTEM_ISO2022_NO_ISO6429 (XCODING_SYSTEM (codesys))
|
|
|
206 #define XCODING_SYSTEM_ISO2022_ESCAPE_QUOTED(codesys) \
|
|
|
207 CODING_SYSTEM_ISO2022_ESCAPE_QUOTED (XCODING_SYSTEM (codesys))
|
|
|
208 #define XCODING_SYSTEM_CCL_DECODE(codesys) \
|
|
|
209 CODING_SYSTEM_CCL_DECODE (XCODING_SYSTEM (codesys))
|
|
|
210 #define XCODING_SYSTEM_CCL_ENCODE(codesys) \
|
|
|
211 CODING_SYSTEM_CCL_ENCODE (XCODING_SYSTEM (codesys))
|
|
|
212
|
|
110
|
213 extern Lisp_Object Qbuffer_file_coding_system, Qcoding_system_error;
|
|
70
|
214
|
|
|
215 extern Lisp_Object Vkeyboard_coding_system;
|
|
|
216 extern Lisp_Object Vterminal_coding_system;
|
|
120
|
217 extern Lisp_Object Vcoding_system_for_read;
|
|
|
218 extern Lisp_Object Vcoding_system_for_write;
|
|
70
|
219 extern Lisp_Object Vpathname_coding_system;
|
|
|
220
|
|
|
221 extern Lisp_Object Qescape_quoted;
|
|
|
222
|
|
|
223 /* Flags indicating current state while converting code. */
|
|
|
224
|
|
|
225 /* Used by everyone. */
|
|
|
226
|
|
|
227 #define CODING_STATE_END (1 << 0) /* If set, this is the last chunk of
|
|
|
228 data being processed. When this
|
|
|
229 is finished, output any necessary
|
|
|
230 terminating control characters,
|
|
|
231 escape sequences, etc. */
|
|
|
232 #define CODING_STATE_CR (1 << 1) /* If set, we just saw a CR. */
|
|
|
233
|
|
|
234
|
|
|
235 /* Used by Big 5 on output. */
|
|
|
236
|
|
|
237 #define CODING_STATE_BIG5_1 (1 << 2) /* If set, we just encountered
|
|
|
238 LEADING_BYTE_BIG5_1. */
|
|
|
239 #define CODING_STATE_BIG5_2 (1 << 3) /* If set, we just encountered
|
|
|
240 LEADING_BYTE_BIG5_2. */
|
|
|
241
|
|
|
242
|
|
|
243 /* Used by ISO2022 on input and output. */
|
|
|
244
|
|
|
245 #define CODING_STATE_R2L (1 << 4) /* If set, the current
|
|
|
246 directionality is right-to-left.
|
|
|
247 Otherwise, it's left-to-right. */
|
|
|
248
|
|
|
249
|
|
|
250 /* Used by ISO2022 on input. */
|
|
|
251
|
|
|
252 #define CODING_STATE_ESCAPE (1 << 5) /* If set, we're currently parsing
|
|
|
253 an escape sequence and the upper
|
|
|
254 16 bits should be looked at to
|
|
|
255 indicate what partial escape
|
|
|
256 sequence we've seen so far.
|
|
|
257 Otherwise, we're running
|
|
|
258 through actual text. */
|
|
|
259 #define CODING_STATE_SS2 (1 << 6) /* If set, G2 is invoked into GL, but
|
|
|
260 only for the next character. */
|
|
|
261 #define CODING_STATE_SS3 (1 << 7) /* If set, G3 is invoked into GL,
|
|
|
262 but only for the next character.
|
|
|
263 If both CODING_STATE_SS2 and
|
|
|
264 CODING_STATE_SS3 are set,
|
|
|
265 CODING_STATE_SS2 overrides; but
|
|
|
266 this probably indicates an error
|
|
|
267 in the text encoding. */
|
|
|
268 #define CODING_STATE_COMPOSITE (1 << 8) /* If set, we're currently processing
|
|
|
269 a composite character (i.e. a
|
|
|
270 character constructed by
|
|
|
271 overstriking two or more
|
|
|
272 characters). */
|
|
|
273
|
|
|
274
|
|
|
275 /* CODING_STATE_ISO2022_LOCK is the mask of flags that remain on until
|
|
|
276 explicitly turned off when in the ISO2022 encoder/decoder. Other flags are
|
|
|
277 turned off at the end of processing each character or escape sequence. */
|
|
|
278 # define CODING_STATE_ISO2022_LOCK \
|
|
|
279 (CODING_STATE_END | CODING_STATE_COMPOSITE | CODING_STATE_R2L)
|
|
|
280 #define CODING_STATE_BIG5_LOCK \
|
|
|
281 CODING_STATE_END
|
|
|
282
|
|
|
283 /* Flags indicating what we've seen so far when parsing an
|
|
|
284 ISO2022 escape sequence. */
|
|
|
285 enum iso_esc_flag
|
|
|
286 {
|
|
|
287 /* Partial sequences */
|
|
|
288 ISO_ESC_NOTHING, /* Nothing has been seen. */
|
|
|
289 ISO_ESC, /* We've seen ESC. */
|
|
|
290 ISO_ESC_2_4, /* We've seen ESC $. This indicates
|
|
|
291 that we're designating a multi-byte, rather
|
|
|
292 than a single-byte, character set. */
|
|
|
293 ISO_ESC_2_8, /* We've seen ESC 0x28, i.e. ESC (.
|
|
|
294 This means designate a 94-character
|
|
|
295 character set into G0. */
|
|
|
296 ISO_ESC_2_9, /* We've seen ESC 0x29 -- designate a
|
|
|
297 94-character character set into G1. */
|
|
|
298 ISO_ESC_2_10, /* We've seen ESC 0x2A. */
|
|
|
299 ISO_ESC_2_11, /* We've seen ESC 0x2B. */
|
|
|
300 ISO_ESC_2_12, /* We've seen ESC 0x2C -- designate a
|
|
|
301 96-character character set into G0.
|
|
|
302 (This is not ISO2022-standard.
|
|
|
303 The following 96-character
|
|
|
304 control sequences are standard,
|
|
|
305 though.) */
|
|
|
306 ISO_ESC_2_13, /* We've seen ESC 0x2D -- designate a
|
|
|
307 96-character character set into G1.
|
|
|
308 */
|
|
|
309 ISO_ESC_2_14, /* We've seen ESC 0x2E. */
|
|
|
310 ISO_ESC_2_15, /* We've seen ESC 0x2F. */
|
|
|
311 ISO_ESC_2_4_8, /* We've seen ESC $ 0x28 -- designate
|
|
|
312 a 94^N character set into G0. */
|
|
|
313 ISO_ESC_2_4_9, /* We've seen ESC $ 0x29. */
|
|
|
314 ISO_ESC_2_4_10, /* We've seen ESC $ 0x2A. */
|
|
|
315 ISO_ESC_2_4_11, /* We've seen ESC $ 0x2B. */
|
|
|
316 ISO_ESC_2_4_12, /* We've seen ESC $ 0x2C. */
|
|
|
317 ISO_ESC_2_4_13, /* We've seen ESC $ 0x2D. */
|
|
|
318 ISO_ESC_2_4_14, /* We've seen ESC $ 0x2E. */
|
|
|
319 ISO_ESC_2_4_15, /* We've seen ESC $ 0x2F. */
|
|
|
320 ISO_ESC_5_11, /* We've seen ESC [ or 0x9B. This
|
|
|
321 starts a directionality-control
|
|
|
322 sequence. The next character
|
|
|
323 must be 0, 1, 2, or ]. */
|
|
|
324 ISO_ESC_5_11_0, /* We've seen 0x9B 0. The next
|
|
|
325 character must be ]. */
|
|
|
326 ISO_ESC_5_11_1, /* We've seen 0x9B 1. The next
|
|
|
327 character must be ]. */
|
|
|
328 ISO_ESC_5_11_2, /* We've seen 0x9B 2. The next
|
|
|
329 character must be ]. */
|
|
|
330
|
|
|
331 /* Full sequences. */
|
|
|
332 ISO_ESC_START_COMPOSITE, /* Private usage for START COMPOSING */
|
|
|
333 ISO_ESC_END_COMPOSITE, /* Private usage for END COMPOSING */
|
|
|
334 ISO_ESC_SINGLE_SHIFT, /* We've seen a complete single-shift sequence. */
|
|
|
335 ISO_ESC_LOCKING_SHIFT,/* We've seen a complete locking-shift sequence. */
|
|
|
336 ISO_ESC_DESIGNATE, /* We've seen a complete designation sequence. */
|
|
|
337 ISO_ESC_DIRECTIONALITY,/* We've seen a complete ISO6429 directionality
|
|
|
338 sequence. */
|
|
|
339 ISO_ESC_LITERAL /* We've seen a literal character ala
|
|
|
340 escape-quoting. */
|
|
|
341 };
|
|
|
342
|
|
|
343 /* Macros to define code of control characters for ISO2022's functions. */
|
|
|
344 /* code */ /* function */
|
|
|
345 #define ISO_CODE_LF 0x0A /* line-feed */
|
|
|
346 #define ISO_CODE_CR 0x0D /* carriage-return */
|
|
|
347 #define ISO_CODE_SO 0x0E /* shift-out */
|
|
|
348 #define ISO_CODE_SI 0x0F /* shift-in */
|
|
|
349 #define ISO_CODE_ESC 0x1B /* escape */
|
|
|
350 #define ISO_CODE_DEL 0x7F /* delete */
|
|
|
351 #define ISO_CODE_SS2 0x8E /* single-shift-2 */
|
|
|
352 #define ISO_CODE_SS3 0x8F /* single-shift-3 */
|
|
|
353 #define ISO_CODE_CSI 0x9B /* control-sequence-introduce */
|
|
|
354
|
|
|
355 /* Macros to access an encoding stream or decoding stream */
|
|
|
356
|
|
|
357 #define CODING_STREAM_DECOMPOSE(str, flags, ch) \
|
|
|
358 do { \
|
|
|
359 flags = (str)->flags; \
|
|
|
360 ch = (str)->ch; \
|
|
|
361 } while (0)
|
|
|
362
|
|
|
363 #define CODING_STREAM_COMPOSE(str, flags, ch) \
|
|
|
364 do { \
|
|
|
365 (str)->flags = flags; \
|
|
|
366 (str)->ch = ch; \
|
|
|
367 } while (0)
|
|
|
368
|
|
|
369
|
|
|
370 /* For detecting the encoding of text */
|
|
|
371 enum coding_category_type
|
|
|
372 {
|
|
|
373 CODING_CATEGORY_SHIFT_JIS,
|
|
|
374 CODING_CATEGORY_ISO_7, /* ISO2022 system using only seven-bit bytes,
|
|
|
375 no locking shift */
|
|
|
376 CODING_CATEGORY_ISO_8_DESIGNATE, /* ISO2022 system using eight-bit bytes,
|
|
|
377 no locking shift, no single shift,
|
|
|
378 using designation to switch charsets */
|
|
|
379 CODING_CATEGORY_ISO_8_1, /* ISO2022 system using eight-bit bytes,
|
|
|
380 no locking shift, no designation sequences,
|
|
|
381 one-dimension characters in the upper half. */
|
|
|
382 CODING_CATEGORY_ISO_8_2, /* ISO2022 system using eight-bit bytes,
|
|
|
383 no locking shift, no designation sequences,
|
|
|
384 two-dimension characters in the upper half. */
|
|
|
385 CODING_CATEGORY_ISO_LOCK_SHIFT, /* ISO2022 system using locking shift */
|
|
|
386 CODING_CATEGORY_BIG5,
|
|
|
387 CODING_CATEGORY_NO_CONVERSION
|
|
|
388 };
|
|
|
389
|
|
|
390 #define CODING_CATEGORY_LAST CODING_CATEGORY_NO_CONVERSION
|
|
|
391
|
|
|
392 #define CODING_CATEGORY_SHIFT_JIS_MASK \
|
|
|
393 (1 << CODING_CATEGORY_SHIFT_JIS)
|
|
|
394 #define CODING_CATEGORY_ISO_7_MASK \
|
|
|
395 (1 << CODING_CATEGORY_ISO_7)
|
|
|
396 #define CODING_CATEGORY_ISO_8_DESIGNATE_MASK \
|
|
|
397 (1 << CODING_CATEGORY_ISO_8_DESIGNATE)
|
|
|
398 #define CODING_CATEGORY_ISO_8_1_MASK \
|
|
|
399 (1 << CODING_CATEGORY_ISO_8_1)
|
|
|
400 #define CODING_CATEGORY_ISO_8_2_MASK \
|
|
|
401 (1 << CODING_CATEGORY_ISO_8_2)
|
|
|
402 #define CODING_CATEGORY_ISO_LOCK_SHIFT_MASK \
|
|
|
403 (1 << CODING_CATEGORY_ISO_LOCK_SHIFT)
|
|
|
404 #define CODING_CATEGORY_BIG5_MASK \
|
|
|
405 (1 << CODING_CATEGORY_BIG5)
|
|
|
406 #define CODING_CATEGORY_NO_CONVERSION_MASK \
|
|
|
407 (1 << CODING_CATEGORY_NO_CONVERSION)
|
|
|
408 #define CODING_CATEGORY_NOT_FINISHED_MASK \
|
|
|
409 (1 << 30)
|
|
|
410
|
|
215
|
411 /* Convert shift-JIS code (sj1, sj2) into internal string
|
|
|
412 representation (c1, c2). (The leading byte is assumed.) */
|
|
|
413
|
|
|
414 #define DECODE_SJIS(sj1, sj2, c1, c2) \
|
|
|
415 do { \
|
|
|
416 int I1 = sj1, I2 = sj2; \
|
|
|
417 if (I2 >= 0x9f) \
|
|
|
418 c1 = (I1 << 1) - ((I1 >= 0xe0) ? 0xe0 : 0x60), \
|
|
|
419 c2 = I2 + 2; \
|
|
|
420 else \
|
|
|
421 c1 = (I1 << 1) - ((I1 >= 0xe0) ? 0xe1 : 0x61), \
|
|
|
422 c2 = I2 + ((I2 >= 0x7f) ? 0x60 : 0x61); \
|
|
|
423 } while (0)
|
|
213
|
424
|
|
215
|
425 /* Convert the internal string representation of a Shift-JIS character
|
|
|
426 (c1, c2) into Shift-JIS code (sj1, sj2). The leading byte is
|
|
|
427 assumed. */
|
|
213
|
428
|
|
215
|
429 #define ENCODE_SJIS(c1, c2, sj1, sj2) \
|
|
|
430 do { \
|
|
|
431 int I1 = c1, I2 = c2; \
|
|
|
432 if (I1 & 1) \
|
|
|
433 sj1 = (I1 >> 1) + ((I1 < 0xdf) ? 0x31 : 0x71), \
|
|
|
434 sj2 = I2 - ((I2 >= 0xe0) ? 0x60 : 0x61); \
|
|
|
435 else \
|
|
|
436 sj1 = (I1 >> 1) + ((I1 < 0xdf) ? 0x30 : 0x70), \
|
|
|
437 sj2 = I2 - 2; \
|
|
|
438 } while (0)
|
|
213
|
439
|
|
70
|
440 extern Lisp_Object make_decoding_input_stream (Lstream *stream,
|
|
|
441 Lisp_Object codesys);
|
|
|
442 extern Lisp_Object make_encoding_input_stream (Lstream *stream,
|
|
|
443 Lisp_Object codesys);
|
|
|
444 extern Lisp_Object make_decoding_output_stream (Lstream *stream,
|
|
|
445 Lisp_Object codesys);
|
|
|
446 extern Lisp_Object make_encoding_output_stream (Lstream *stream,
|
|
|
447 Lisp_Object codesys);
|
|
|
448 extern Lisp_Object decoding_stream_coding_system (Lstream *stream);
|
|
|
449 extern Lisp_Object encoding_stream_coding_system (Lstream *stream);
|
|
|
450 extern void set_decoding_stream_coding_system (Lstream *stream,
|
|
|
451 Lisp_Object codesys);
|
|
|
452 extern void set_encoding_stream_coding_system (Lstream *stream,
|
|
|
453 Lisp_Object codesys);
|
|
|
454 #endif /* _XEMACS_MULE_CODING_H_ */
|
