1 /* Header for coding system handler.
2 Copyright (C) 1995, 1997 Electrotechnical Laboratory, JAPAN.
3 Licensed to the Free Software Foundation.
5 This file is part of GNU Emacs.
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)
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.
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. */
26 #include "../src/ccl.h"
29 /*** EMACS' INTERNAL FORMAT (emacs-mule) section ***/
31 /* All code (1-byte) of Emacs' internal format is classified into one
32 of the followings. See also `charset.h'. */
33 enum emacs_code_class_type
35 EMACS_control_code
, /* Control codes in the range
36 0x00..0x1F and 0x7F except for the
37 following two codes. */
38 EMACS_linefeed_code
, /* 0x0A (linefeed) to denote
40 EMACS_carriage_return_code
, /* 0x0D (carriage-return) to be used
41 in selective display mode. */
42 EMACS_ascii_code
, /* ASCII characters. */
43 EMACS_leading_code_composition
, /* Leading code of a composite
45 EMACS_leading_code_2
, /* Base leading code of official
47 EMACS_leading_code_3
, /* Base leading code of private TYPE9N
48 or official TYPE9Nx9N character. */
49 EMACS_leading_code_4
, /* Base leading code of private
50 TYPE9Nx9N character. */
51 EMACS_invalid_code
/* Invalid code, i.e. a base leading
52 code not yet assigned to any
53 charset, or a code of the range
57 extern enum emacs_code_class_type emacs_code_class
[256];
59 /*** ISO2022 section ***/
61 /* Macros to define code of control characters for ISO2022's functions. */
62 /* code */ /* function */
63 #define ISO_CODE_LF 0x0A /* line-feed */
64 #define ISO_CODE_CR 0x0D /* carriage-return */
65 #define ISO_CODE_SO 0x0E /* shift-out */
66 #define ISO_CODE_SI 0x0F /* shift-in */
67 #define ISO_CODE_SS2_7 0x19 /* single-shift-2 for 7-bit code */
68 #define ISO_CODE_ESC 0x1B /* escape */
69 #define ISO_CODE_SS2 0x8E /* single-shift-2 */
70 #define ISO_CODE_SS3 0x8F /* single-shift-3 */
71 #define ISO_CODE_CSI 0x9B /* control-sequence-introduce */
73 /* All code (1-byte) of ISO2022 is classified into one of the
75 enum iso_code_class_type
77 ISO_control_code
, /* Control codes in the range
78 0x00..0x1F, 0x7F, and 0x80..0x9F,
79 except for the following seven
81 ISO_carriage_return
, /* ISO_CODE_CR (0x0D) */
82 ISO_shift_out
, /* ISO_CODE_SO (0x0E) */
83 ISO_shift_in
, /* ISO_CODE_SI (0x0F) */
84 ISO_single_shift_2_7
, /* ISO_CODE_SS2_7 (0x19) */
85 ISO_escape
, /* ISO_CODE_SO (0x1B) */
86 ISO_single_shift_2
, /* ISO_CODE_SS2 (0x8E) */
87 ISO_single_shift_3
, /* ISO_CODE_SS3 (0x8F) */
88 ISO_control_sequence_introducer
, /* ISO_CODE_CSI (0x9B) */
89 ISO_0x20_or_0x7F
, /* Codes of the values 0x20 or 0x7F. */
90 ISO_graphic_plane_0
, /* Graphic codes in the range 0x21..0x7E. */
91 ISO_0xA0_or_0xFF
, /* Codes of the values 0xA0 or 0xFF. */
92 ISO_graphic_plane_1
/* Graphic codes in the range 0xA1..0xFE. */
95 /** The macros CODING_FLAG_ISO_XXX defines a flag bit of the `flags'
96 element in the structure `coding_system'. This information is used
97 while encoding a text to ISO2022. **/
99 /* If set, produce short-form designation sequence (e.g. ESC $ A)
100 instead of long-form sequence (e.g. ESC $ ( A). */
101 #define CODING_FLAG_ISO_SHORT_FORM 0x0001
103 /* If set, reset graphic planes and registers at end-of-line to the
105 #define CODING_FLAG_ISO_RESET_AT_EOL 0x0002
107 /* If set, reset graphic planes and registers before any control
108 characters to the initial state. */
109 #define CODING_FLAG_ISO_RESET_AT_CNTL 0x0004
111 /* If set, encode by 7-bit environment. */
112 #define CODING_FLAG_ISO_SEVEN_BITS 0x0008
114 /* If set, use locking-shift function. */
115 #define CODING_FLAG_ISO_LOCKING_SHIFT 0x0010
117 /* If set, use single-shift function. Overwrite
118 CODING_FLAG_ISO_LOCKING_SHIFT. */
119 #define CODING_FLAG_ISO_SINGLE_SHIFT 0x0020
121 /* If set, designate JISX0201-Roman instead of ASCII. */
122 #define CODING_FLAG_ISO_USE_ROMAN 0x0040
124 /* If set, designate JISX0208-1978 instead of JISX0208-1983. */
125 #define CODING_FLAG_ISO_USE_OLDJIS 0x0080
127 /* If set, do not produce ISO6429's direction specifying sequence. */
128 #define CODING_FLAG_ISO_NO_DIRECTION 0x0100
130 /* If set, assume designation states are reset at beginning of line on
132 #define CODING_FLAG_ISO_INIT_AT_BOL 0x0200
134 /* If set, designation sequence should be placed at beginning of line
136 #define CODING_FLAG_ISO_DESIGNATE_AT_BOL 0x0400
138 /* If set, do not encode unexpected charactes on output. */
139 #define CODING_FLAG_ISO_SAFE 0x0800
141 /* A character to be produced on output if encoding of the original
142 character is prohibited by CODING_FLAG_ISO_SAFE. */
143 #define CODING_INHIBIT_CHARACTER_SUBSTITUTION 077 /* `?' */
145 /* Structure of the field `spec.iso2022' in the structure `coding_system'. */
148 /* The current graphic register invoked to each graphic plane. */
149 int current_invocation
[2];
151 /* The current charset designated to each graphic register. */
152 int current_designation
[4];
154 /* A charset initially designated to each graphic register. */
155 int initial_designation
[4];
157 /* A graphic register to which each charset should be designated. */
158 unsigned char requested_designation
[MAX_CHARSET
+ 1];
160 /* Set to 1 temporarily only when graphic register 2 or 3 is invoked
161 by single-shift while encoding. */
164 /* Set to 1 temporarily only when processing at beginning of line. */
168 /* Macros to access each field in the structure `spec.iso2022'. */
169 #define CODING_SPEC_ISO_INVOCATION(coding, plane) \
170 coding->spec.iso2022.current_invocation[plane]
171 #define CODING_SPEC_ISO_DESIGNATION(coding, reg) \
172 coding->spec.iso2022.current_designation[reg]
173 #define CODING_SPEC_ISO_INITIAL_DESIGNATION(coding, reg) \
174 coding->spec.iso2022.initial_designation[reg]
175 #define CODING_SPEC_ISO_REQUESTED_DESIGNATION(coding, charset) \
176 coding->spec.iso2022.requested_designation[charset]
177 #define CODING_SPEC_ISO_SINGLE_SHIFTING(coding) \
178 coding->spec.iso2022.single_shifting
179 #define CODING_SPEC_ISO_BOL(coding) \
180 coding->spec.iso2022.bol
182 /* A value which may appear in
183 coding->spec.iso2022.requested_designation indicating that the
184 corresponding charset does not request any graphic register to be
186 #define CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION 4
188 /* Return a charset which is currently designated to the graphic plane
189 PLANE in the coding-system CODING. */
190 #define CODING_SPEC_ISO_PLANE_CHARSET(coding, plane) \
191 ((CODING_SPEC_ISO_INVOCATION (coding, plane) < 0) \
193 : CODING_SPEC_ISO_DESIGNATION (coding, \
194 CODING_SPEC_ISO_INVOCATION (coding, plane)))
196 /*** BIG5 section ***/
198 /* Macros to denote each type of BIG5 coding system. */
199 #define CODING_FLAG_BIG5_HKU 0x00 /* BIG5-HKU is one of variants of
200 BIG5 developed by Hong Kong
202 #define CODING_FLAG_BIG5_ETEN 0x01 /* BIG5_ETen is one of variants
203 of BIG5 developed by the
204 company ETen in Taiwan. */
206 /*** GENERAL section ***/
208 /* Types of coding system. */
211 coding_type_no_conversion
, /* A coding system which requires no
212 conversion for reading and writing
213 including end-of-line format. */
214 coding_type_emacs_mule
, /* A coding system used in Emacs'
215 buffer and string. Requires no
216 conversion for reading and writing
217 except for end-of-line format. */
218 coding_type_undecided
, /* A coding system which requires
219 automatic detection of a real
221 coding_type_sjis
, /* SJIS coding system for Japanese. */
222 coding_type_iso2022
, /* Any coding system of ISO2022
224 coding_type_big5
, /* BIG5 coding system for Chinese. */
225 coding_type_ccl
/* The coding system of which decoder
226 and encoder are written in CCL. */
229 /* Formats of end-of-line. */
230 #define CODING_EOL_LF 0 /* Line-feed only, same as Emacs'
232 #define CODING_EOL_CRLF 1 /* Sequence of carriage-return and
234 #define CODING_EOL_CR 2 /* Carriage-return only. */
235 #define CODING_EOL_UNDECIDED 3 /* This value is used to denote the
236 eol-type is not yet decided. */
238 /* Character composition status while encoding/decoding. */
239 #define COMPOSING_NO 0 /* not composing */
240 #define COMPOSING_WITH_RULE_HEAD 1 /* 1st char of with-rule composing follow */
241 #define COMPOSING_NO_RULE_HEAD 2 /* 1st char of no-rule composing follow */
242 #define COMPOSING_WITH_RULE_TAIL 3 /* Nth char of with-rule composing follow */
243 #define COMPOSING_NO_RULE_TAIL 4 /* Nth char of no-rule composing follow */
244 #define COMPOSING_WITH_RULE_RULE 5 /* composition rule follow */
246 /* 1 iff composing. */
247 #define COMPOSING_P(composing) (composing)
248 /* 1 iff 1st char of composing element follows. */
249 #define COMPOSING_HEAD_P(composing) \
250 ((composing) && (composing) <= COMPOSING_NO_RULE_HEAD)
251 /* 1 iff composing with embeded composition rule. */
252 #define COMPOSING_WITH_RULE_P(composing) ((composing) & 1)
256 /* Type of the coding system. */
257 enum coding_type type
;
259 /* If the coding system requires specific code to be attached at the
260 tail of converted text, this value should be set to `1'. */
261 int require_flushing
;
263 /* Flag bits of the coding system. The meaning of each bit depends
264 on the type of the coding system. */
267 /* Type of end-of-line format (LF, CRLF, or CR) of the coding system. */
270 /* Non-zero means that the current source text is the last block of the
271 whole text to be converted. */
274 /* Non-zero means that characters are being composed currently while
275 decoding or encoding. See macros COMPOSING_XXXX above for the
276 meaing of each non-zero value. */
279 /* 0 (left-to-right) or 1 (right-to-left): the direction of the text
280 being processed currently. */
283 /* Non-zero means that the current source text is in a buffer which
284 enables selective display. */
287 /* Detailed information specific to each type of coding system. */
290 struct iso2022_spec iso2022
;
291 struct ccl_spec ccl
; /* Defined in ccl.h. */
294 /* Backward pointer to the Lisp symbol of the coding system. */
297 /* Lisp function (symbol) to be called after decoding to do
298 additional conversion. */
299 Lisp_Object post_read_conversion
;
301 /* Lisp function (symbol) to be called before encoding to do
302 additional conversion. */
303 Lisp_Object pre_write_conversion
;
305 /* Character unification tables to look up, or nil. */
306 Lisp_Object character_unification_table_for_decode
;
307 Lisp_Object character_unification_table_for_encode
;
309 /* Carryover yielded by decoding/encoding incomplete source. No
310 coding-system yields more than 7-byte of carryover. This does
311 not include a text which is not processed because of short of
315 /* Actual data length in the above array. */
319 /* Return 1 if coding system CODING never requires any code conversion. */
320 #define CODING_REQUIRE_NO_CONVERSION(coding) \
321 (((coding)->type == coding_type_no_conversion \
322 || (coding)->type == coding_type_emacs_mule) \
323 && (coding)->eol_type == CODING_EOL_LF)
325 /* Return 1 if coding system CODING may not require code conversion. */
326 #define CODING_MAY_REQUIRE_NO_CONVERSION(coding) \
327 (((coding)->type == coding_type_no_conversion \
328 || (coding)->type == coding_type_emacs_mule \
329 || (coding)->type == coding_type_undecided) \
330 && ((coding)->eol_type == CODING_EOL_LF \
331 || (coding)->eol_type == CODING_EOL_UNDECIDED))
333 /* Index for each coding category in `coding_category_table' */
334 #define CODING_CATEGORY_IDX_EMACS_MULE 0
335 #define CODING_CATEGORY_IDX_SJIS 1
336 #define CODING_CATEGORY_IDX_ISO_7 2
337 #define CODING_CATEGORY_IDX_ISO_8_1 3
338 #define CODING_CATEGORY_IDX_ISO_8_2 4
339 #define CODING_CATEGORY_IDX_ISO_7_ELSE 5
340 #define CODING_CATEGORY_IDX_ISO_8_ELSE 6
341 #define CODING_CATEGORY_IDX_BIG5 7
342 #define CODING_CATEGORY_IDX_BINARY 8
343 #define CODING_CATEGORY_IDX_MAX 9
345 /* Definitions of flag bits returned by the function
346 detect_coding_mask (). */
347 #define CODING_CATEGORY_MASK_EMACS_MULE (1 << CODING_CATEGORY_IDX_EMACS_MULE)
348 #define CODING_CATEGORY_MASK_SJIS (1 << CODING_CATEGORY_IDX_SJIS)
349 #define CODING_CATEGORY_MASK_ISO_7 (1 << CODING_CATEGORY_IDX_ISO_7)
350 #define CODING_CATEGORY_MASK_ISO_8_1 (1 << CODING_CATEGORY_IDX_ISO_8_1)
351 #define CODING_CATEGORY_MASK_ISO_8_2 (1 << CODING_CATEGORY_IDX_ISO_8_2)
352 #define CODING_CATEGORY_MASK_ISO_7_ELSE (1 << CODING_CATEGORY_IDX_ISO_7_ELSE)
353 #define CODING_CATEGORY_MASK_ISO_8_ELSE (1 << CODING_CATEGORY_IDX_ISO_8_ELSE)
354 #define CODING_CATEGORY_MASK_BIG5 (1 << CODING_CATEGORY_IDX_BIG5)
355 #define CODING_CATEGORY_MASK_BINARY (1 << CODING_CATEGORY_IDX_BINARY)
357 /* This value is returned if detect_coding_mask () find nothing other
358 than ASCII characters. */
359 #define CODING_CATEGORY_MASK_ANY \
360 ( CODING_CATEGORY_MASK_EMACS_MULE \
361 | CODING_CATEGORY_MASK_SJIS \
362 | CODING_CATEGORY_MASK_ISO_7 \
363 | CODING_CATEGORY_MASK_ISO_8_1 \
364 | CODING_CATEGORY_MASK_ISO_8_2 \
365 | CODING_CATEGORY_MASK_ISO_7_ELSE \
366 | CODING_CATEGORY_MASK_ISO_8_ELSE \
367 | CODING_CATEGORY_MASK_BIG5)
369 /* Macros to decode or encode a character of JISX0208 in SJIS. S1 and
370 S2 are the 1st and 2nd position-codes of JISX0208 in SJIS coding
371 system. C1 and C2 are the 1st and 2nd position codes of Emacs'
374 #define DECODE_SJIS(s1, s2, c1, c2) \
377 c1 = s1 * 2 - (s1 >= 0xE0 ? 0x160 : 0xE0), \
380 c1 = s1 * 2 - ((s1 >= 0xE0) ? 0x161 : 0xE1), \
381 c2 = s2 - ((s2 >= 0x7F) ? 0x20 : 0x1F); \
384 #define ENCODE_SJIS(c1, c2, s1, s2) \
387 s1 = c1 / 2 + ((c1 < 0x5F) ? 0x71 : 0xB1), \
388 s2 = c2 + ((c2 >= 0x60) ? 0x20 : 0x1F); \
390 s1 = c1 / 2 + ((c1 < 0x5F) ? 0x70 : 0xB0), \
394 /* Extern declarations. */
395 extern int decode_coding (), encode_coding ();
396 extern int decoding_buffer_size (), encoding_buffer_size ();
397 extern int conversion_buffer_size
;
398 extern char *conversion_buffer
, *get_conversion_buffer ();
399 extern Lisp_Object
Fcheck_coding_system ();
400 extern Lisp_Object Qcoding_system
, Qeol_type
, Qcoding_category_index
;
401 extern Lisp_Object Qemacs_mule
;
402 extern Lisp_Object Qbuffer_file_coding_system
;
403 extern Lisp_Object Vcoding_category_list
;
405 /* Mnemonic character to indicate each type of end-of-line. */
406 extern int eol_mnemonic_unix
, eol_mnemonic_dos
, eol_mnemonic_mac
;
407 /* Mnemonic character to indicate type of end-of-line is not yet decided. */
408 extern int eol_mnemonic_undecided
;
410 /* Table of coding-systems currently assigned to each coding-category. */
411 extern Lisp_Object coding_category_table
[CODING_CATEGORY_IDX_MAX
];
412 /* Table of names of symbol for each coding-category. */
413 extern char *coding_category_name
[CODING_CATEGORY_IDX_MAX
];
416 extern Lisp_Object Qfile_coding_system
;
417 extern Lisp_Object Qcall_process
, Qcall_process_region
, Qprocess_argument
;
418 extern Lisp_Object Qstart_process
, Qopen_network_stream
;
420 /* Coding-system for reading files and receiving data from process. */
421 extern Lisp_Object Vcoding_system_for_read
;
422 /* Coding-system for writing files and sending data to process. */
423 extern Lisp_Object Vcoding_system_for_write
;
424 /* Coding-system actually used in the latest I/O. */
425 extern Lisp_Object Vlast_coding_system_used
;
427 /* Coding-system to be used for encoding terminal output. This
428 structure contains information of a coding-system specified by the
429 function `set-terminal-coding-system'. */
430 extern struct coding_system terminal_coding
;
432 /* Coding system to be used to encode text for terminal display when
433 terminal coding system is nil. */
434 extern struct coding_system safe_terminal_coding
;
436 /* Coding-system of what is sent from terminal keyboard. This
437 structure contains information of a coding-system specified by the
438 function `set-keyboard-coding-system'. */
439 extern struct coding_system keyboard_coding
;
441 /* Default coding systems used for process I/O. */
442 extern Lisp_Object Vdefault_process_coding_system
;
446 #endif /* _CODING_H */