1 /* Coding system handler (conversion, detection, etc).
2 Copyright (C) 1995, 1997, 1998 Electrotechnical Laboratory, JAPAN.
3 Licensed to the Free Software Foundation.
4 Copyright (C) 2001, 2002 Free Software Foundation, Inc.
6 National Institute of Advanced Industrial Science and Technology (AIST)
7 Registration Number H13PRO009
9 This file is part of GNU Emacs.
11 GNU Emacs is free software; you can redistribute it and/or modify
12 it under the terms of the GNU General Public License as published by
13 the Free Software Foundation; either version 2, or (at your option)
16 GNU Emacs is distributed in the hope that it will be useful,
17 but WITHOUT ANY WARRANTY; without even the implied warranty of
18 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
19 GNU General Public License for more details.
21 You should have received a copy of the GNU General Public License
22 along with GNU Emacs; see the file COPYING. If not, write to
23 the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
24 Boston, MA 02111-1307, USA. */
26 /*** TABLE OF CONTENTS ***
30 2. Emacs' internal format (emacs-utf-8) handlers
33 5. Charset-base coding systems handlers
34 6. emacs-mule (old Emacs' internal format) handlers
36 8. Shift-JIS and BIG5 handlers
38 10. C library functions
39 11. Emacs Lisp library functions
44 /*** 0. General comments ***
49 A coding system is an object for an encoding mechanism that contains
50 information about how to convert byte sequences to character
51 sequences and vice versa. When we say "decode", it means converting
52 a byte sequence of a specific coding system into a character
53 sequence that is represented by Emacs' internal coding system
54 `emacs-utf-8', and when we say "encode", it means converting a
55 character sequence of emacs-utf-8 to a byte sequence of a specific
58 In Emacs Lisp, a coding system is represented by a Lisp symbol. In
59 C level, a coding system is represented by a vector of attributes
60 stored in the hash table Vcharset_hash_table. The conversion from
61 coding system symbol to attributes vector is done by looking up
62 Vcharset_hash_table by the symbol.
64 Coding systems are classified into the following types depending on
65 the encoding mechanism. Here's a brief description of the types.
71 o Charset-base coding system
73 A coding system defined by one or more (coded) character sets.
74 Decoding and encoding are done by a code converter defined for each
77 o Old Emacs internal format (emacs-mule)
79 The coding system adopted by old versions of Emacs (20 and 21).
81 o ISO2022-base coding system
83 The most famous coding system for multiple character sets. X's
84 Compound Text, various EUCs (Extended Unix Code), and coding systems
85 used in the Internet communication such as ISO-2022-JP are all
88 o SJIS (or Shift-JIS or MS-Kanji-Code)
90 A coding system to encode character sets: ASCII, JISX0201, and
91 JISX0208. Widely used for PC's in Japan. Details are described in
96 A coding system to encode character sets: ASCII and Big5. Widely
97 used for Chinese (mainly in Taiwan and Hong Kong). Details are
98 described in section 8. In this file, when we write "big5" (all
99 lowercase), we mean the coding system, and when we write "Big5"
100 (capitalized), we mean the character set.
104 If a user wants to decode/encode text encoded in a coding system
105 not listed above, he can supply a decoder and an encoder for it in
106 CCL (Code Conversion Language) programs. Emacs executes the CCL
107 program while decoding/encoding.
111 A coding system for text containing raw eight-bit data. Emacs
112 treats each byte of source text as a character (except for
113 end-of-line conversion).
117 Like raw text, but don't do end-of-line conversion.
122 How text end-of-line is encoded depends on operating system. For
123 instance, Unix's format is just one byte of LF (line-feed) code,
124 whereas DOS's format is two-byte sequence of `carriage-return' and
125 `line-feed' codes. MacOS's format is usually one byte of
128 Since text character encoding and end-of-line encoding are
129 independent, any coding system described above can take any format
130 of end-of-line (except for no-conversion).
134 Before using a coding system for code conversion (i.e. decoding and
135 encoding), we setup a structure of type `struct coding_system'.
136 This structure keeps various information about a specific code
137 conversion (e.g. the location of source and destination data).
144 /*** GENERAL NOTES on `detect_coding_XXX ()' functions ***
146 These functions check if a byte sequence specified as a source in
147 CODING conforms to the format of XXX, and update the members of
150 Return 1 if the byte sequence conforms to XXX, otherwise return 0.
152 Below is the template of these functions. */
156 detect_coding_XXX (coding
, detect_info
)
157 struct coding_system
*coding
;
158 struct coding_detection_info
*detect_info
;
160 unsigned char *src
= coding
->source
;
161 unsigned char *src_end
= coding
->source
+ coding
->src_bytes
;
162 int multibytep
= coding
->src_multibyte
;
163 int consumed_chars
= 0;
169 /* Get one byte from the source. If the souce is exausted, jump
170 to no_more_source:. */
173 if (! __C_conforms_to_XXX___ (c
))
175 if (! __C_strongly_suggests_XXX__ (c
))
176 found
= CATEGORY_MASK_XXX
;
178 /* The byte sequence is invalid for XXX. */
179 detect_info
->rejected
|= CATEGORY_MASK_XXX
;
183 /* The source exausted successfully. */
184 detect_info
->found
|= found
;
189 /*** GENERAL NOTES on `decode_coding_XXX ()' functions ***
191 These functions decode a byte sequence specified as a source by
192 CODING. The resulting multibyte text goes to a place pointed to by
193 CODING->charbuf, the length of which should not exceed
194 CODING->charbuf_size;
196 These functions set the information of original and decoded texts in
197 CODING->consumed, CODING->consumed_char, and CODING->charbuf_used.
198 They also set CODING->result to one of CODING_RESULT_XXX indicating
199 how the decoding is finished.
201 Below is the template of these functions. */
205 decode_coding_XXXX (coding
)
206 struct coding_system
*coding
;
208 unsigned char *src
= coding
->source
+ coding
->consumed
;
209 unsigned char *src_end
= coding
->source
+ coding
->src_bytes
;
210 /* SRC_BASE remembers the start position in source in each loop.
211 The loop will be exited when there's not enough source code, or
212 when there's no room in CHARBUF for a decoded character. */
213 unsigned char *src_base
;
214 /* A buffer to produce decoded characters. */
215 int *charbuf
= coding
->charbuf
+ coding
->charbuf_used
;
216 int *charbuf_end
= coding
->charbuf
+ coding
->charbuf_size
;
217 int multibytep
= coding
->src_multibyte
;
222 if (charbuf
< charbuf_end
)
223 /* No more room to produce a decoded character. */
230 if (src_base
< src_end
231 && coding
->mode
& CODING_MODE_LAST_BLOCK
)
232 /* If the source ends by partial bytes to construct a character,
233 treat them as eight-bit raw data. */
234 while (src_base
< src_end
&& charbuf
< charbuf_end
)
235 *charbuf
++ = *src_base
++;
236 /* Remember how many bytes and characters we consumed. If the
237 source is multibyte, the bytes and chars are not identical. */
238 coding
->consumed
= coding
->consumed_char
= src_base
- coding
->source
;
239 /* Remember how many characters we produced. */
240 coding
->charbuf_used
= charbuf
- coding
->charbuf
;
244 /*** GENERAL NOTES on `encode_coding_XXX ()' functions ***
246 These functions encode SRC_BYTES length text at SOURCE of Emacs'
247 internal multibyte format by CODING. The resulting byte sequence
248 goes to a place pointed to by DESTINATION, the length of which
249 should not exceed DST_BYTES.
251 These functions set the information of original and encoded texts in
252 the members produced, produced_char, consumed, and consumed_char of
253 the structure *CODING. They also set the member result to one of
254 CODING_RESULT_XXX indicating how the encoding finished.
256 DST_BYTES zero means that source area and destination area are
257 overlapped, which means that we can produce a encoded text until it
258 reaches at the head of not-yet-encoded source text.
260 Below is a template of these functions. */
263 encode_coding_XXX (coding
)
264 struct coding_system
*coding
;
266 int multibytep
= coding
->dst_multibyte
;
267 int *charbuf
= coding
->charbuf
;
268 int *charbuf_end
= charbuf
->charbuf
+ coding
->charbuf_used
;
269 unsigned char *dst
= coding
->destination
+ coding
->produced
;
270 unsigned char *dst_end
= coding
->destination
+ coding
->dst_bytes
;
271 unsigned char *adjusted_dst_end
= dst_end
- _MAX_BYTES_PRODUCED_IN_LOOP_
;
272 int produced_chars
= 0;
274 for (; charbuf
< charbuf_end
&& dst
< adjusted_dst_end
; charbuf
++)
277 /* Encode C into DST, and increment DST. */
279 label_no_more_destination
:
280 /* How many chars and bytes we produced. */
281 coding
->produced_char
+= produced_chars
;
282 coding
->produced
= dst
- coding
->destination
;
287 /*** 1. Preamble ***/
294 #include "character.h"
297 #include "composite.h"
301 Lisp_Object Vcoding_system_hash_table
;
303 Lisp_Object Qcoding_system
, Qcoding_aliases
, Qeol_type
;
304 Lisp_Object Qunix
, Qdos
;
305 extern Lisp_Object Qmac
; /* frame.c */
306 Lisp_Object Qbuffer_file_coding_system
;
307 Lisp_Object Qpost_read_conversion
, Qpre_write_conversion
;
308 Lisp_Object Qdefault_char
;
309 Lisp_Object Qno_conversion
, Qundecided
;
310 Lisp_Object Qcharset
, Qiso_2022
, Qutf_8
, Qutf_16
, Qshift_jis
, Qbig5
;
311 Lisp_Object Qbig
, Qlittle
;
312 Lisp_Object Qcoding_system_history
;
313 Lisp_Object Qvalid_codes
;
314 Lisp_Object QCcategory
, QCmnemonic
, QCdefalut_char
;
315 Lisp_Object QCdecode_translation_table
, QCencode_translation_table
;
316 Lisp_Object QCpost_read_conversion
, QCpre_write_conversion
;
318 extern Lisp_Object Qinsert_file_contents
, Qwrite_region
;
319 Lisp_Object Qcall_process
, Qcall_process_region
, Qprocess_argument
;
320 Lisp_Object Qstart_process
, Qopen_network_stream
;
321 Lisp_Object Qtarget_idx
;
323 Lisp_Object Qinsufficient_source
, Qinconsistent_eol
, Qinvalid_source
;
324 Lisp_Object Qinterrupted
, Qinsufficient_memory
;
326 int coding_system_require_warning
;
328 Lisp_Object Vselect_safe_coding_system_function
;
330 /* Mnemonic string for each format of end-of-line. */
331 Lisp_Object eol_mnemonic_unix
, eol_mnemonic_dos
, eol_mnemonic_mac
;
332 /* Mnemonic string to indicate format of end-of-line is not yet
334 Lisp_Object eol_mnemonic_undecided
;
338 Lisp_Object Vcoding_system_list
, Vcoding_system_alist
;
340 Lisp_Object Qcoding_system_p
, Qcoding_system_error
;
342 /* Coding system emacs-mule and raw-text are for converting only
343 end-of-line format. */
344 Lisp_Object Qemacs_mule
, Qraw_text
;
345 Lisp_Object Qutf_8_emacs
;
347 /* Coding-systems are handed between Emacs Lisp programs and C internal
348 routines by the following three variables. */
349 /* Coding-system for reading files and receiving data from process. */
350 Lisp_Object Vcoding_system_for_read
;
351 /* Coding-system for writing files and sending data to process. */
352 Lisp_Object Vcoding_system_for_write
;
353 /* Coding-system actually used in the latest I/O. */
354 Lisp_Object Vlast_coding_system_used
;
355 /* Set to non-nil when an error is detected while code conversion. */
356 Lisp_Object Vlast_code_conversion_error
;
357 /* A vector of length 256 which contains information about special
358 Latin codes (especially for dealing with Microsoft codes). */
359 Lisp_Object Vlatin_extra_code_table
;
361 /* Flag to inhibit code conversion of end-of-line format. */
362 int inhibit_eol_conversion
;
364 /* Flag to inhibit ISO2022 escape sequence detection. */
365 int inhibit_iso_escape_detection
;
367 /* Flag to make buffer-file-coding-system inherit from process-coding. */
368 int inherit_process_coding_system
;
370 /* Coding system to be used to encode text for terminal display. */
371 struct coding_system terminal_coding
;
373 /* Coding system to be used to encode text for terminal display when
374 terminal coding system is nil. */
375 struct coding_system safe_terminal_coding
;
377 /* Coding system of what is sent from terminal keyboard. */
378 struct coding_system keyboard_coding
;
380 Lisp_Object Vfile_coding_system_alist
;
381 Lisp_Object Vprocess_coding_system_alist
;
382 Lisp_Object Vnetwork_coding_system_alist
;
384 Lisp_Object Vlocale_coding_system
;
388 /* Flag to tell if we look up translation table on character code
390 Lisp_Object Venable_character_translation
;
391 /* Standard translation table to look up on decoding (reading). */
392 Lisp_Object Vstandard_translation_table_for_decode
;
393 /* Standard translation table to look up on encoding (writing). */
394 Lisp_Object Vstandard_translation_table_for_encode
;
396 Lisp_Object Qtranslation_table
;
397 Lisp_Object Qtranslation_table_id
;
398 Lisp_Object Qtranslation_table_for_decode
;
399 Lisp_Object Qtranslation_table_for_encode
;
401 /* Alist of charsets vs revision number. */
402 static Lisp_Object Vcharset_revision_table
;
404 /* Default coding systems used for process I/O. */
405 Lisp_Object Vdefault_process_coding_system
;
407 /* Char table for translating Quail and self-inserting input. */
408 Lisp_Object Vtranslation_table_for_input
;
410 /* Two special coding systems. */
411 Lisp_Object Vsjis_coding_system
;
412 Lisp_Object Vbig5_coding_system
;
414 /* ISO2022 section */
416 #define CODING_ISO_INITIAL(coding, reg) \
417 (XINT (AREF (AREF (CODING_ID_ATTRS ((coding)->id), \
418 coding_attr_iso_initial), \
422 #define CODING_ISO_REQUEST(coding, charset_id) \
423 ((charset_id <= (coding)->max_charset_id \
424 ? (coding)->safe_charsets[charset_id] \
428 #define CODING_ISO_FLAGS(coding) \
429 ((coding)->spec.iso_2022.flags)
430 #define CODING_ISO_DESIGNATION(coding, reg) \
431 ((coding)->spec.iso_2022.current_designation[reg])
432 #define CODING_ISO_INVOCATION(coding, plane) \
433 ((coding)->spec.iso_2022.current_invocation[plane])
434 #define CODING_ISO_SINGLE_SHIFTING(coding) \
435 ((coding)->spec.iso_2022.single_shifting)
436 #define CODING_ISO_BOL(coding) \
437 ((coding)->spec.iso_2022.bol)
438 #define CODING_ISO_INVOKED_CHARSET(coding, plane) \
439 CODING_ISO_DESIGNATION ((coding), CODING_ISO_INVOCATION ((coding), (plane)))
441 /* Control characters of ISO2022. */
442 /* code */ /* function */
443 #define ISO_CODE_LF 0x0A /* line-feed */
444 #define ISO_CODE_CR 0x0D /* carriage-return */
445 #define ISO_CODE_SO 0x0E /* shift-out */
446 #define ISO_CODE_SI 0x0F /* shift-in */
447 #define ISO_CODE_SS2_7 0x19 /* single-shift-2 for 7-bit code */
448 #define ISO_CODE_ESC 0x1B /* escape */
449 #define ISO_CODE_SS2 0x8E /* single-shift-2 */
450 #define ISO_CODE_SS3 0x8F /* single-shift-3 */
451 #define ISO_CODE_CSI 0x9B /* control-sequence-introducer */
453 /* All code (1-byte) of ISO2022 is classified into one of the
455 enum iso_code_class_type
457 ISO_control_0
, /* Control codes in the range
458 0x00..0x1F and 0x7F, except for the
459 following 5 codes. */
460 ISO_shift_out
, /* ISO_CODE_SO (0x0E) */
461 ISO_shift_in
, /* ISO_CODE_SI (0x0F) */
462 ISO_single_shift_2_7
, /* ISO_CODE_SS2_7 (0x19) */
463 ISO_escape
, /* ISO_CODE_SO (0x1B) */
464 ISO_control_1
, /* Control codes in the range
465 0x80..0x9F, except for the
466 following 3 codes. */
467 ISO_single_shift_2
, /* ISO_CODE_SS2 (0x8E) */
468 ISO_single_shift_3
, /* ISO_CODE_SS3 (0x8F) */
469 ISO_control_sequence_introducer
, /* ISO_CODE_CSI (0x9B) */
470 ISO_0x20_or_0x7F
, /* Codes of the values 0x20 or 0x7F. */
471 ISO_graphic_plane_0
, /* Graphic codes in the range 0x21..0x7E. */
472 ISO_0xA0_or_0xFF
, /* Codes of the values 0xA0 or 0xFF. */
473 ISO_graphic_plane_1
/* Graphic codes in the range 0xA1..0xFE. */
476 /** The macros CODING_ISO_FLAG_XXX defines a flag bit of the
477 `iso-flags' attribute of an iso2022 coding system. */
479 /* If set, produce long-form designation sequence (e.g. ESC $ ( A)
480 instead of the correct short-form sequence (e.g. ESC $ A). */
481 #define CODING_ISO_FLAG_LONG_FORM 0x0001
483 /* If set, reset graphic planes and registers at end-of-line to the
485 #define CODING_ISO_FLAG_RESET_AT_EOL 0x0002
487 /* If set, reset graphic planes and registers before any control
488 characters to the initial state. */
489 #define CODING_ISO_FLAG_RESET_AT_CNTL 0x0004
491 /* If set, encode by 7-bit environment. */
492 #define CODING_ISO_FLAG_SEVEN_BITS 0x0008
494 /* If set, use locking-shift function. */
495 #define CODING_ISO_FLAG_LOCKING_SHIFT 0x0010
497 /* If set, use single-shift function. Overwrite
498 CODING_ISO_FLAG_LOCKING_SHIFT. */
499 #define CODING_ISO_FLAG_SINGLE_SHIFT 0x0020
501 /* If set, use designation escape sequence. */
502 #define CODING_ISO_FLAG_DESIGNATION 0x0040
504 /* If set, produce revision number sequence. */
505 #define CODING_ISO_FLAG_REVISION 0x0080
507 /* If set, produce ISO6429's direction specifying sequence. */
508 #define CODING_ISO_FLAG_DIRECTION 0x0100
510 /* If set, assume designation states are reset at beginning of line on
512 #define CODING_ISO_FLAG_INIT_AT_BOL 0x0200
514 /* If set, designation sequence should be placed at beginning of line
516 #define CODING_ISO_FLAG_DESIGNATE_AT_BOL 0x0400
518 /* If set, do not encode unsafe charactes on output. */
519 #define CODING_ISO_FLAG_SAFE 0x0800
521 /* If set, extra latin codes (128..159) are accepted as a valid code
523 #define CODING_ISO_FLAG_LATIN_EXTRA 0x1000
525 #define CODING_ISO_FLAG_COMPOSITION 0x2000
527 #define CODING_ISO_FLAG_EUC_TW_SHIFT 0x4000
529 #define CODING_ISO_FLAG_USE_ROMAN 0x8000
531 #define CODING_ISO_FLAG_USE_OLDJIS 0x10000
533 #define CODING_ISO_FLAG_FULL_SUPPORT 0x100000
535 /* A character to be produced on output if encoding of the original
536 character is prohibited by CODING_ISO_FLAG_SAFE. */
537 #define CODING_INHIBIT_CHARACTER_SUBSTITUTION '?'
541 #define CODING_UTF_16_BOM(coding) \
542 ((coding)->spec.utf_16.bom)
544 #define CODING_UTF_16_ENDIAN(coding) \
545 ((coding)->spec.utf_16.endian)
547 #define CODING_UTF_16_SURROGATE(coding) \
548 ((coding)->spec.utf_16.surrogate)
552 #define CODING_CCL_DECODER(coding) \
553 AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_decoder)
554 #define CODING_CCL_ENCODER(coding) \
555 AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_encoder)
556 #define CODING_CCL_VALIDS(coding) \
557 (SDATA (AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_valids)))
559 /* Index for each coding category in `coding_categories' */
563 coding_category_iso_7
,
564 coding_category_iso_7_tight
,
565 coding_category_iso_8_1
,
566 coding_category_iso_8_2
,
567 coding_category_iso_7_else
,
568 coding_category_iso_8_else
,
569 coding_category_utf_8
,
570 coding_category_utf_16_auto
,
571 coding_category_utf_16_be
,
572 coding_category_utf_16_le
,
573 coding_category_utf_16_be_nosig
,
574 coding_category_utf_16_le_nosig
,
575 coding_category_charset
,
576 coding_category_sjis
,
577 coding_category_big5
,
579 coding_category_emacs_mule
,
580 /* All above are targets of code detection. */
581 coding_category_raw_text
,
582 coding_category_undecided
,
586 /* Definitions of flag bits used in detect_coding_XXXX. */
587 #define CATEGORY_MASK_ISO_7 (1 << coding_category_iso_7)
588 #define CATEGORY_MASK_ISO_7_TIGHT (1 << coding_category_iso_7_tight)
589 #define CATEGORY_MASK_ISO_8_1 (1 << coding_category_iso_8_1)
590 #define CATEGORY_MASK_ISO_8_2 (1 << coding_category_iso_8_2)
591 #define CATEGORY_MASK_ISO_7_ELSE (1 << coding_category_iso_7_else)
592 #define CATEGORY_MASK_ISO_8_ELSE (1 << coding_category_iso_8_else)
593 #define CATEGORY_MASK_UTF_8 (1 << coding_category_utf_8)
594 #define CATEGORY_MASK_UTF_16_AUTO (1 << coding_category_utf_16_auto)
595 #define CATEGORY_MASK_UTF_16_BE (1 << coding_category_utf_16_be)
596 #define CATEGORY_MASK_UTF_16_LE (1 << coding_category_utf_16_le)
597 #define CATEGORY_MASK_UTF_16_BE_NOSIG (1 << coding_category_utf_16_be_nosig)
598 #define CATEGORY_MASK_UTF_16_LE_NOSIG (1 << coding_category_utf_16_le_nosig)
599 #define CATEGORY_MASK_CHARSET (1 << coding_category_charset)
600 #define CATEGORY_MASK_SJIS (1 << coding_category_sjis)
601 #define CATEGORY_MASK_BIG5 (1 << coding_category_big5)
602 #define CATEGORY_MASK_CCL (1 << coding_category_ccl)
603 #define CATEGORY_MASK_EMACS_MULE (1 << coding_category_emacs_mule)
604 #define CATEGORY_MASK_RAW_TEXT (1 << coding_category_raw_text)
606 /* This value is returned if detect_coding_mask () find nothing other
607 than ASCII characters. */
608 #define CATEGORY_MASK_ANY \
609 (CATEGORY_MASK_ISO_7 \
610 | CATEGORY_MASK_ISO_7_TIGHT \
611 | CATEGORY_MASK_ISO_8_1 \
612 | CATEGORY_MASK_ISO_8_2 \
613 | CATEGORY_MASK_ISO_7_ELSE \
614 | CATEGORY_MASK_ISO_8_ELSE \
615 | CATEGORY_MASK_UTF_8 \
616 | CATEGORY_MASK_UTF_16_BE \
617 | CATEGORY_MASK_UTF_16_LE \
618 | CATEGORY_MASK_UTF_16_BE_NOSIG \
619 | CATEGORY_MASK_UTF_16_LE_NOSIG \
620 | CATEGORY_MASK_CHARSET \
621 | CATEGORY_MASK_SJIS \
622 | CATEGORY_MASK_BIG5 \
623 | CATEGORY_MASK_CCL \
624 | CATEGORY_MASK_EMACS_MULE)
627 #define CATEGORY_MASK_ISO_7BIT \
628 (CATEGORY_MASK_ISO_7 | CATEGORY_MASK_ISO_7_TIGHT)
630 #define CATEGORY_MASK_ISO_8BIT \
631 (CATEGORY_MASK_ISO_8_1 | CATEGORY_MASK_ISO_8_2)
633 #define CATEGORY_MASK_ISO_ELSE \
634 (CATEGORY_MASK_ISO_7_ELSE | CATEGORY_MASK_ISO_8_ELSE)
636 #define CATEGORY_MASK_ISO_ESCAPE \
637 (CATEGORY_MASK_ISO_7 \
638 | CATEGORY_MASK_ISO_7_TIGHT \
639 | CATEGORY_MASK_ISO_7_ELSE \
640 | CATEGORY_MASK_ISO_8_ELSE)
642 #define CATEGORY_MASK_ISO \
643 ( CATEGORY_MASK_ISO_7BIT \
644 | CATEGORY_MASK_ISO_8BIT \
645 | CATEGORY_MASK_ISO_ELSE)
647 #define CATEGORY_MASK_UTF_16 \
648 (CATEGORY_MASK_UTF_16_BE \
649 | CATEGORY_MASK_UTF_16_LE \
650 | CATEGORY_MASK_UTF_16_BE_NOSIG \
651 | CATEGORY_MASK_UTF_16_LE_NOSIG)
654 /* List of symbols `coding-category-xxx' ordered by priority. This
655 variable is exposed to Emacs Lisp. */
656 static Lisp_Object Vcoding_category_list
;
658 /* Table of coding categories (Lisp symbols). This variable is for
660 static Lisp_Object Vcoding_category_table
;
662 /* Table of coding-categories ordered by priority. */
663 static enum coding_category coding_priorities
[coding_category_max
];
665 /* Nth element is a coding context for the coding system bound to the
666 Nth coding category. */
667 static struct coding_system coding_categories
[coding_category_max
];
669 /*** Commonly used macros and functions ***/
672 #define min(a, b) ((a) < (b) ? (a) : (b))
675 #define max(a, b) ((a) > (b) ? (a) : (b))
678 #define CODING_GET_INFO(coding, attrs, charset_list) \
680 (attrs) = CODING_ID_ATTRS ((coding)->id); \
681 (charset_list) = CODING_ATTR_CHARSET_LIST (attrs); \
685 /* Safely get one byte from the source text pointed by SRC which ends
686 at SRC_END, and set C to that byte. If there are not enough bytes
687 in the source, it jumps to `no_more_source'. If multibytep is
688 nonzero, and a multibyte character is found at SRC, set C to the
689 negative value of the character code. The caller should declare
690 and set these variables appropriately in advance:
691 src, src_end, multibytep */
693 #define ONE_MORE_BYTE(c) \
695 if (src == src_end) \
697 if (src_base < src) \
698 record_conversion_result \
699 (coding, CODING_RESULT_INSUFFICIENT_SRC); \
700 goto no_more_source; \
703 if (multibytep && (c & 0x80)) \
705 if ((c & 0xFE) == 0xC0) \
706 c = ((c & 1) << 6) | *src++; \
709 c = - string_char (--src, &src, NULL); \
710 record_conversion_result \
711 (coding, CODING_RESULT_INVALID_SRC); \
718 #define ONE_MORE_BYTE_NO_CHECK(c) \
721 if (multibytep && (c & 0x80)) \
723 if ((c & 0xFE) == 0xC0) \
724 c = ((c & 1) << 6) | *src++; \
727 c = - string_char (--src, &src, NULL); \
728 record_conversion_result \
729 (coding, CODING_RESULT_INVALID_SRC); \
736 /* Store a byte C in the place pointed by DST and increment DST to the
737 next free point, and increment PRODUCED_CHARS. The caller should
738 assure that C is 0..127, and declare and set the variable `dst'
739 appropriately in advance.
743 #define EMIT_ONE_ASCII_BYTE(c) \
750 /* Like EMIT_ONE_ASCII_BYTE byt store two bytes; C1 and C2. */
752 #define EMIT_TWO_ASCII_BYTES(c1, c2) \
754 produced_chars += 2; \
755 *dst++ = (c1), *dst++ = (c2); \
759 /* Store a byte C in the place pointed by DST and increment DST to the
760 next free point, and increment PRODUCED_CHARS. If MULTIBYTEP is
761 nonzero, store in an appropriate multibyte from. The caller should
762 declare and set the variables `dst' and `multibytep' appropriately
765 #define EMIT_ONE_BYTE(c) \
772 ch = BYTE8_TO_CHAR (ch); \
773 CHAR_STRING_ADVANCE (ch, dst); \
780 /* Like EMIT_ONE_BYTE, but emit two bytes; C1 and C2. */
782 #define EMIT_TWO_BYTES(c1, c2) \
784 produced_chars += 2; \
791 ch = BYTE8_TO_CHAR (ch); \
792 CHAR_STRING_ADVANCE (ch, dst); \
795 ch = BYTE8_TO_CHAR (ch); \
796 CHAR_STRING_ADVANCE (ch, dst); \
806 #define EMIT_THREE_BYTES(c1, c2, c3) \
808 EMIT_ONE_BYTE (c1); \
809 EMIT_TWO_BYTES (c2, c3); \
813 #define EMIT_FOUR_BYTES(c1, c2, c3, c4) \
815 EMIT_TWO_BYTES (c1, c2); \
816 EMIT_TWO_BYTES (c3, c4); \
820 /* Prototypes for static functions. */
821 static void record_conversion_result
P_ ((struct coding_system
*coding
,
822 enum coding_result_code result
));
823 static int detect_coding_utf_8
P_ ((struct coding_system
*,
824 struct coding_detection_info
*info
));
825 static void decode_coding_utf_8
P_ ((struct coding_system
*));
826 static int encode_coding_utf_8
P_ ((struct coding_system
*));
828 static int detect_coding_utf_16
P_ ((struct coding_system
*,
829 struct coding_detection_info
*info
));
830 static void decode_coding_utf_16
P_ ((struct coding_system
*));
831 static int encode_coding_utf_16
P_ ((struct coding_system
*));
833 static int detect_coding_iso_2022
P_ ((struct coding_system
*,
834 struct coding_detection_info
*info
));
835 static void decode_coding_iso_2022
P_ ((struct coding_system
*));
836 static int encode_coding_iso_2022
P_ ((struct coding_system
*));
838 static int detect_coding_emacs_mule
P_ ((struct coding_system
*,
839 struct coding_detection_info
*info
));
840 static void decode_coding_emacs_mule
P_ ((struct coding_system
*));
841 static int encode_coding_emacs_mule
P_ ((struct coding_system
*));
843 static int detect_coding_sjis
P_ ((struct coding_system
*,
844 struct coding_detection_info
*info
));
845 static void decode_coding_sjis
P_ ((struct coding_system
*));
846 static int encode_coding_sjis
P_ ((struct coding_system
*));
848 static int detect_coding_big5
P_ ((struct coding_system
*,
849 struct coding_detection_info
*info
));
850 static void decode_coding_big5
P_ ((struct coding_system
*));
851 static int encode_coding_big5
P_ ((struct coding_system
*));
853 static int detect_coding_ccl
P_ ((struct coding_system
*,
854 struct coding_detection_info
*info
));
855 static void decode_coding_ccl
P_ ((struct coding_system
*));
856 static int encode_coding_ccl
P_ ((struct coding_system
*));
858 static void decode_coding_raw_text
P_ ((struct coding_system
*));
859 static int encode_coding_raw_text
P_ ((struct coding_system
*));
861 static void coding_set_source
P_ ((struct coding_system
*));
862 static void coding_set_destination
P_ ((struct coding_system
*));
863 static void coding_alloc_by_realloc
P_ ((struct coding_system
*, EMACS_INT
));
864 static void coding_alloc_by_making_gap
P_ ((struct coding_system
*,
866 static unsigned char *alloc_destination
P_ ((struct coding_system
*,
867 EMACS_INT
, unsigned char *));
868 static void setup_iso_safe_charsets
P_ ((Lisp_Object
));
869 static unsigned char *encode_designation_at_bol
P_ ((struct coding_system
*,
872 static int detect_eol
P_ ((const unsigned char *,
873 EMACS_INT
, enum coding_category
));
874 static Lisp_Object adjust_coding_eol_type
P_ ((struct coding_system
*, int));
875 static void decode_eol
P_ ((struct coding_system
*));
876 static Lisp_Object get_translation_table
P_ ((Lisp_Object
, int, int *));
877 static Lisp_Object get_translation
P_ ((Lisp_Object
, int *, int *,
879 static int produce_chars
P_ ((struct coding_system
*, Lisp_Object
, int));
880 static INLINE
void produce_composition
P_ ((struct coding_system
*, int *,
882 static INLINE
void produce_charset
P_ ((struct coding_system
*, int *,
884 static void produce_annotation
P_ ((struct coding_system
*, EMACS_INT
));
885 static int decode_coding
P_ ((struct coding_system
*));
886 static INLINE
int *handle_composition_annotation
P_ ((EMACS_INT
, EMACS_INT
,
887 struct coding_system
*,
888 int *, EMACS_INT
*));
889 static INLINE
int *handle_charset_annotation
P_ ((EMACS_INT
, EMACS_INT
,
890 struct coding_system
*,
891 int *, EMACS_INT
*));
892 static void consume_chars
P_ ((struct coding_system
*, Lisp_Object
, int));
893 static int encode_coding
P_ ((struct coding_system
*));
894 static Lisp_Object make_conversion_work_buffer
P_ ((int));
895 static Lisp_Object code_conversion_restore
P_ ((Lisp_Object
));
896 static INLINE
int char_encodable_p
P_ ((int, Lisp_Object
));
897 static Lisp_Object make_subsidiaries
P_ ((Lisp_Object
));
900 record_conversion_result (struct coding_system
*coding
,
901 enum coding_result_code result
)
903 coding
->result
= result
;
906 case CODING_RESULT_INSUFFICIENT_SRC
:
907 Vlast_code_conversion_error
= Qinsufficient_source
;
909 case CODING_RESULT_INCONSISTENT_EOL
:
910 Vlast_code_conversion_error
= Qinconsistent_eol
;
912 case CODING_RESULT_INVALID_SRC
:
913 Vlast_code_conversion_error
= Qinvalid_source
;
915 case CODING_RESULT_INTERRUPT
:
916 Vlast_code_conversion_error
= Qinterrupted
;
918 case CODING_RESULT_INSUFFICIENT_MEM
:
919 Vlast_code_conversion_error
= Qinsufficient_memory
;
924 #define CODING_DECODE_CHAR(coding, src, src_base, src_end, charset, code, c) \
926 charset_map_loaded = 0; \
927 c = DECODE_CHAR (charset, code); \
928 if (charset_map_loaded) \
930 const unsigned char *orig = coding->source; \
933 coding_set_source (coding); \
934 offset = coding->source - orig; \
936 src_base += offset; \
942 #define ASSURE_DESTINATION(bytes) \
944 if (dst + (bytes) >= dst_end) \
946 int more_bytes = charbuf_end - charbuf + (bytes); \
948 dst = alloc_destination (coding, more_bytes, dst); \
949 dst_end = coding->destination + coding->dst_bytes; \
956 coding_set_source (coding
)
957 struct coding_system
*coding
;
959 if (BUFFERP (coding
->src_object
))
961 struct buffer
*buf
= XBUFFER (coding
->src_object
);
963 if (coding
->src_pos
< 0)
964 coding
->source
= BUF_GAP_END_ADDR (buf
) + coding
->src_pos_byte
;
966 coding
->source
= BUF_BYTE_ADDRESS (buf
, coding
->src_pos_byte
);
968 else if (STRINGP (coding
->src_object
))
970 coding
->source
= SDATA (coding
->src_object
) + coding
->src_pos_byte
;
973 /* Otherwise, the source is C string and is never relocated
974 automatically. Thus we don't have to update anything. */
979 coding_set_destination (coding
)
980 struct coding_system
*coding
;
982 if (BUFFERP (coding
->dst_object
))
984 if (coding
->src_pos
< 0)
986 coding
->destination
= BEG_ADDR
+ coding
->dst_pos_byte
- 1;
987 coding
->dst_bytes
= (GAP_END_ADDR
988 - (coding
->src_bytes
- coding
->consumed
)
989 - coding
->destination
);
993 /* We are sure that coding->dst_pos_byte is before the gap
995 coding
->destination
= (BUF_BEG_ADDR (XBUFFER (coding
->dst_object
))
996 + coding
->dst_pos_byte
- 1);
997 coding
->dst_bytes
= (BUF_GAP_END_ADDR (XBUFFER (coding
->dst_object
))
998 - coding
->destination
);
1002 /* Otherwise, the destination is C string and is never relocated
1003 automatically. Thus we don't have to update anything. */
1009 coding_alloc_by_realloc (coding
, bytes
)
1010 struct coding_system
*coding
;
1013 coding
->destination
= (unsigned char *) xrealloc (coding
->destination
,
1014 coding
->dst_bytes
+ bytes
);
1015 coding
->dst_bytes
+= bytes
;
1019 coding_alloc_by_making_gap (coding
, bytes
)
1020 struct coding_system
*coding
;
1023 if (BUFFERP (coding
->dst_object
)
1024 && EQ (coding
->src_object
, coding
->dst_object
))
1026 EMACS_INT add
= coding
->src_bytes
- coding
->consumed
;
1028 GAP_SIZE
-= add
; ZV
+= add
; Z
+= add
; ZV_BYTE
+= add
; Z_BYTE
+= add
;
1030 GAP_SIZE
+= add
; ZV
-= add
; Z
-= add
; ZV_BYTE
-= add
; Z_BYTE
-= add
;
1034 Lisp_Object this_buffer
;
1036 this_buffer
= Fcurrent_buffer ();
1037 set_buffer_internal (XBUFFER (coding
->dst_object
));
1039 set_buffer_internal (XBUFFER (this_buffer
));
1044 static unsigned char *
1045 alloc_destination (coding
, nbytes
, dst
)
1046 struct coding_system
*coding
;
1050 EMACS_INT offset
= dst
- coding
->destination
;
1052 if (BUFFERP (coding
->dst_object
))
1053 coding_alloc_by_making_gap (coding
, nbytes
);
1055 coding_alloc_by_realloc (coding
, nbytes
);
1056 record_conversion_result (coding
, CODING_RESULT_SUCCESS
);
1057 coding_set_destination (coding
);
1058 dst
= coding
->destination
+ offset
;
1062 /** Macros for annotations. */
1064 /* Maximum length of annotation data (sum of annotations for
1065 composition and charset). */
1066 #define MAX_ANNOTATION_LENGTH (4 + (MAX_COMPOSITION_COMPONENTS * 2) - 1 + 4)
1068 /* An annotation data is stored in the array coding->charbuf in this
1070 [ -LENGTH ANNOTATION_MASK NCHARS ... ]
1071 LENGTH is the number of elements in the annotation.
1072 ANNOTATION_MASK is one of CODING_ANNOTATE_XXX_MASK.
1073 NCHARS is the number of characters in the text annotated.
1075 The format of the following elements depend on ANNOTATION_MASK.
1077 In the case of CODING_ANNOTATE_COMPOSITION_MASK, these elements
1079 ... METHOD [ COMPOSITION-COMPONENTS ... ]
1080 METHOD is one of enum composition_method.
1081 Optionnal COMPOSITION-COMPONENTS are characters and composition
1084 In the case of CODING_ANNOTATE_CHARSET_MASK, one element CHARSET-ID
1087 #define ADD_ANNOTATION_DATA(buf, len, mask, nchars) \
1089 *(buf)++ = -(len); \
1090 *(buf)++ = (mask); \
1091 *(buf)++ = (nchars); \
1092 coding->annotated = 1; \
1095 #define ADD_COMPOSITION_DATA(buf, nchars, method) \
1097 ADD_ANNOTATION_DATA (buf, 4, CODING_ANNOTATE_COMPOSITION_MASK, nchars); \
1102 #define ADD_CHARSET_DATA(buf, nchars, id) \
1104 ADD_ANNOTATION_DATA (buf, 4, CODING_ANNOTATE_CHARSET_MASK, nchars); \
1109 /*** 2. Emacs' internal format (emacs-utf-8) ***/
1116 /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
1117 Check if a text is encoded in UTF-8. If it is, return 1, else
1120 #define UTF_8_1_OCTET_P(c) ((c) < 0x80)
1121 #define UTF_8_EXTRA_OCTET_P(c) (((c) & 0xC0) == 0x80)
1122 #define UTF_8_2_OCTET_LEADING_P(c) (((c) & 0xE0) == 0xC0)
1123 #define UTF_8_3_OCTET_LEADING_P(c) (((c) & 0xF0) == 0xE0)
1124 #define UTF_8_4_OCTET_LEADING_P(c) (((c) & 0xF8) == 0xF0)
1125 #define UTF_8_5_OCTET_LEADING_P(c) (((c) & 0xFC) == 0xF8)
1128 detect_coding_utf_8 (coding
, detect_info
)
1129 struct coding_system
*coding
;
1130 struct coding_detection_info
*detect_info
;
1132 const unsigned char *src
= coding
->source
, *src_base
;
1133 const unsigned char *src_end
= coding
->source
+ coding
->src_bytes
;
1134 int multibytep
= coding
->src_multibyte
;
1135 int consumed_chars
= 0;
1138 detect_info
->checked
|= CATEGORY_MASK_UTF_8
;
1139 /* A coding system of this category is always ASCII compatible. */
1140 src
+= coding
->head_ascii
;
1144 int c
, c1
, c2
, c3
, c4
;
1148 if (c
< 0 || UTF_8_1_OCTET_P (c
))
1151 if (c1
< 0 || ! UTF_8_EXTRA_OCTET_P (c1
))
1153 if (UTF_8_2_OCTET_LEADING_P (c
))
1155 found
= CATEGORY_MASK_UTF_8
;
1159 if (c2
< 0 || ! UTF_8_EXTRA_OCTET_P (c2
))
1161 if (UTF_8_3_OCTET_LEADING_P (c
))
1163 found
= CATEGORY_MASK_UTF_8
;
1167 if (c3
< 0 || ! UTF_8_EXTRA_OCTET_P (c3
))
1169 if (UTF_8_4_OCTET_LEADING_P (c
))
1171 found
= CATEGORY_MASK_UTF_8
;
1175 if (c4
< 0 || ! UTF_8_EXTRA_OCTET_P (c4
))
1177 if (UTF_8_5_OCTET_LEADING_P (c
))
1179 found
= CATEGORY_MASK_UTF_8
;
1184 detect_info
->rejected
|= CATEGORY_MASK_UTF_8
;
1188 if (src_base
< src
&& coding
->mode
& CODING_MODE_LAST_BLOCK
)
1190 detect_info
->rejected
|= CATEGORY_MASK_UTF_8
;
1193 detect_info
->found
|= found
;
1199 decode_coding_utf_8 (coding
)
1200 struct coding_system
*coding
;
1202 const unsigned char *src
= coding
->source
+ coding
->consumed
;
1203 const unsigned char *src_end
= coding
->source
+ coding
->src_bytes
;
1204 const unsigned char *src_base
;
1205 int *charbuf
= coding
->charbuf
+ coding
->charbuf_used
;
1206 int *charbuf_end
= coding
->charbuf
+ coding
->charbuf_size
;
1207 int consumed_chars
= 0, consumed_chars_base
;
1208 int multibytep
= coding
->src_multibyte
;
1209 Lisp_Object attr
, charset_list
;
1211 CODING_GET_INFO (coding
, attr
, charset_list
);
1215 int c
, c1
, c2
, c3
, c4
, c5
;
1218 consumed_chars_base
= consumed_chars
;
1220 if (charbuf
>= charbuf_end
)
1228 else if (UTF_8_1_OCTET_P(c1
))
1235 if (c2
< 0 || ! UTF_8_EXTRA_OCTET_P (c2
))
1237 if (UTF_8_2_OCTET_LEADING_P (c1
))
1239 c
= ((c1
& 0x1F) << 6) | (c2
& 0x3F);
1240 /* Reject overlong sequences here and below. Encoders
1241 producing them are incorrect, they can be misleading,
1242 and they mess up read/write invariance. */
1249 if (c3
< 0 || ! UTF_8_EXTRA_OCTET_P (c3
))
1251 if (UTF_8_3_OCTET_LEADING_P (c1
))
1253 c
= (((c1
& 0xF) << 12)
1254 | ((c2
& 0x3F) << 6) | (c3
& 0x3F));
1256 || (c
>= 0xd800 && c
< 0xe000)) /* surrogates (invalid) */
1262 if (c4
< 0 || ! UTF_8_EXTRA_OCTET_P (c4
))
1264 if (UTF_8_4_OCTET_LEADING_P (c1
))
1266 c
= (((c1
& 0x7) << 18) | ((c2
& 0x3F) << 12)
1267 | ((c3
& 0x3F) << 6) | (c4
& 0x3F));
1274 if (c5
< 0 || ! UTF_8_EXTRA_OCTET_P (c5
))
1276 if (UTF_8_5_OCTET_LEADING_P (c1
))
1278 c
= (((c1
& 0x3) << 24) | ((c2
& 0x3F) << 18)
1279 | ((c3
& 0x3F) << 12) | ((c4
& 0x3F) << 6)
1281 if ((c
> MAX_CHAR
) || (c
< 0x200000))
1296 consumed_chars
= consumed_chars_base
;
1298 *charbuf
++ = ASCII_BYTE_P (c
) ? c
: BYTE8_TO_CHAR (c
);
1303 coding
->consumed_char
+= consumed_chars_base
;
1304 coding
->consumed
= src_base
- coding
->source
;
1305 coding
->charbuf_used
= charbuf
- coding
->charbuf
;
1310 encode_coding_utf_8 (coding
)
1311 struct coding_system
*coding
;
1313 int multibytep
= coding
->dst_multibyte
;
1314 int *charbuf
= coding
->charbuf
;
1315 int *charbuf_end
= charbuf
+ coding
->charbuf_used
;
1316 unsigned char *dst
= coding
->destination
+ coding
->produced
;
1317 unsigned char *dst_end
= coding
->destination
+ coding
->dst_bytes
;
1318 int produced_chars
= 0;
1323 int safe_room
= MAX_MULTIBYTE_LENGTH
* 2;
1325 while (charbuf
< charbuf_end
)
1327 unsigned char str
[MAX_MULTIBYTE_LENGTH
], *p
, *pend
= str
;
1329 ASSURE_DESTINATION (safe_room
);
1331 if (CHAR_BYTE8_P (c
))
1333 c
= CHAR_TO_BYTE8 (c
);
1338 CHAR_STRING_ADVANCE (c
, pend
);
1339 for (p
= str
; p
< pend
; p
++)
1346 int safe_room
= MAX_MULTIBYTE_LENGTH
;
1348 while (charbuf
< charbuf_end
)
1350 ASSURE_DESTINATION (safe_room
);
1352 if (CHAR_BYTE8_P (c
))
1353 *dst
++ = CHAR_TO_BYTE8 (c
);
1355 dst
+= CHAR_STRING (c
, dst
);
1359 record_conversion_result (coding
, CODING_RESULT_SUCCESS
);
1360 coding
->produced_char
+= produced_chars
;
1361 coding
->produced
= dst
- coding
->destination
;
1366 /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
1367 Check if a text is encoded in one of UTF-16 based coding systems.
1368 If it is, return 1, else return 0. */
1370 #define UTF_16_HIGH_SURROGATE_P(val) \
1371 (((val) & 0xFC00) == 0xD800)
1373 #define UTF_16_LOW_SURROGATE_P(val) \
1374 (((val) & 0xFC00) == 0xDC00)
1376 #define UTF_16_INVALID_P(val) \
1377 (((val) == 0xFFFE) \
1378 || ((val) == 0xFFFF) \
1379 || UTF_16_LOW_SURROGATE_P (val))
1383 detect_coding_utf_16 (coding
, detect_info
)
1384 struct coding_system
*coding
;
1385 struct coding_detection_info
*detect_info
;
1387 const unsigned char *src
= coding
->source
, *src_base
= src
;
1388 const unsigned char *src_end
= coding
->source
+ coding
->src_bytes
;
1389 int multibytep
= coding
->src_multibyte
;
1390 int consumed_chars
= 0;
1393 detect_info
->checked
|= CATEGORY_MASK_UTF_16
;
1394 if (coding
->mode
& CODING_MODE_LAST_BLOCK
1395 && (coding
->src_chars
& 1))
1397 detect_info
->rejected
|= CATEGORY_MASK_UTF_16
;
1403 if ((c1
== 0xFF) && (c2
== 0xFE))
1405 detect_info
->found
|= (CATEGORY_MASK_UTF_16_LE
1406 | CATEGORY_MASK_UTF_16_AUTO
);
1407 detect_info
->rejected
|= (CATEGORY_MASK_UTF_16_BE
1408 | CATEGORY_MASK_UTF_16_BE_NOSIG
1409 | CATEGORY_MASK_UTF_16_LE_NOSIG
);
1411 else if ((c1
== 0xFE) && (c2
== 0xFF))
1413 detect_info
->found
|= (CATEGORY_MASK_UTF_16_BE
1414 | CATEGORY_MASK_UTF_16_AUTO
);
1415 detect_info
->rejected
|= (CATEGORY_MASK_UTF_16_LE
1416 | CATEGORY_MASK_UTF_16_BE_NOSIG
1417 | CATEGORY_MASK_UTF_16_LE_NOSIG
);
1419 else if (c1
>= 0 && c2
>= 0)
1421 detect_info
->rejected
1422 |= (CATEGORY_MASK_UTF_16_BE
| CATEGORY_MASK_UTF_16_LE
);
1429 decode_coding_utf_16 (coding
)
1430 struct coding_system
*coding
;
1432 const unsigned char *src
= coding
->source
+ coding
->consumed
;
1433 const unsigned char *src_end
= coding
->source
+ coding
->src_bytes
;
1434 const unsigned char *src_base
;
1435 int *charbuf
= coding
->charbuf
+ coding
->charbuf_used
;
1436 int *charbuf_end
= coding
->charbuf
+ coding
->charbuf_size
;
1437 int consumed_chars
= 0, consumed_chars_base
;
1438 int multibytep
= coding
->src_multibyte
;
1439 enum utf_16_bom_type bom
= CODING_UTF_16_BOM (coding
);
1440 enum utf_16_endian_type endian
= CODING_UTF_16_ENDIAN (coding
);
1441 int surrogate
= CODING_UTF_16_SURROGATE (coding
);
1442 Lisp_Object attr
, charset_list
;
1444 CODING_GET_INFO (coding
, attr
, charset_list
);
1446 if (bom
== utf_16_with_bom
)
1455 if (endian
== utf_16_big_endian
1456 ? c
!= 0xFEFF : c
!= 0xFFFE)
1458 /* The first two bytes are not BOM. Treat them as bytes
1459 for a normal character. */
1463 CODING_UTF_16_BOM (coding
) = utf_16_without_bom
;
1465 else if (bom
== utf_16_detect_bom
)
1467 /* We have already tried to detect BOM and failed in
1469 CODING_UTF_16_BOM (coding
) = utf_16_without_bom
;
1477 consumed_chars_base
= consumed_chars
;
1479 if (charbuf
+ 2 >= charbuf_end
)
1491 *charbuf
++ = ASCII_BYTE_P (c1
) ? c1
: BYTE8_TO_CHAR (c1
);
1495 c
= (endian
== utf_16_big_endian
1496 ? ((c1
<< 8) | c2
) : ((c2
<< 8) | c1
));
1499 if (! UTF_16_LOW_SURROGATE_P (c
))
1501 if (endian
== utf_16_big_endian
)
1502 c1
= surrogate
>> 8, c2
= surrogate
& 0xFF;
1504 c1
= surrogate
& 0xFF, c2
= surrogate
>> 8;
1508 if (UTF_16_HIGH_SURROGATE_P (c
))
1509 CODING_UTF_16_SURROGATE (coding
) = surrogate
= c
;
1515 c
= ((surrogate
- 0xD800) << 10) | (c
- 0xDC00);
1516 CODING_UTF_16_SURROGATE (coding
) = surrogate
= 0;
1517 *charbuf
++ = 0x10000 + c
;
1522 if (UTF_16_HIGH_SURROGATE_P (c
))
1523 CODING_UTF_16_SURROGATE (coding
) = surrogate
= c
;
1530 coding
->consumed_char
+= consumed_chars_base
;
1531 coding
->consumed
= src_base
- coding
->source
;
1532 coding
->charbuf_used
= charbuf
- coding
->charbuf
;
1536 encode_coding_utf_16 (coding
)
1537 struct coding_system
*coding
;
1539 int multibytep
= coding
->dst_multibyte
;
1540 int *charbuf
= coding
->charbuf
;
1541 int *charbuf_end
= charbuf
+ coding
->charbuf_used
;
1542 unsigned char *dst
= coding
->destination
+ coding
->produced
;
1543 unsigned char *dst_end
= coding
->destination
+ coding
->dst_bytes
;
1545 enum utf_16_bom_type bom
= CODING_UTF_16_BOM (coding
);
1546 int big_endian
= CODING_UTF_16_ENDIAN (coding
) == utf_16_big_endian
;
1547 int produced_chars
= 0;
1548 Lisp_Object attrs
, charset_list
;
1551 CODING_GET_INFO (coding
, attrs
, charset_list
);
1553 if (bom
!= utf_16_without_bom
)
1555 ASSURE_DESTINATION (safe_room
);
1557 EMIT_TWO_BYTES (0xFE, 0xFF);
1559 EMIT_TWO_BYTES (0xFF, 0xFE);
1560 CODING_UTF_16_BOM (coding
) = utf_16_without_bom
;
1563 while (charbuf
< charbuf_end
)
1565 ASSURE_DESTINATION (safe_room
);
1567 if (c
>= MAX_UNICODE_CHAR
)
1568 c
= coding
->default_char
;
1573 EMIT_TWO_BYTES (c
>> 8, c
& 0xFF);
1575 EMIT_TWO_BYTES (c
& 0xFF, c
>> 8);
1582 c1
= (c
>> 10) + 0xD800;
1583 c2
= (c
& 0x3FF) + 0xDC00;
1585 EMIT_FOUR_BYTES (c1
>> 8, c1
& 0xFF, c2
>> 8, c2
& 0xFF);
1587 EMIT_FOUR_BYTES (c1
& 0xFF, c1
>> 8, c2
& 0xFF, c2
>> 8);
1590 record_conversion_result (coding
, CODING_RESULT_SUCCESS
);
1591 coding
->produced
= dst
- coding
->destination
;
1592 coding
->produced_char
+= produced_chars
;
1597 /*** 6. Old Emacs' internal format (emacs-mule) ***/
1599 /* Emacs' internal format for representation of multiple character
1600 sets is a kind of multi-byte encoding, i.e. characters are
1601 represented by variable-length sequences of one-byte codes.
1603 ASCII characters and control characters (e.g. `tab', `newline') are
1604 represented by one-byte sequences which are their ASCII codes, in
1605 the range 0x00 through 0x7F.
1607 8-bit characters of the range 0x80..0x9F are represented by
1608 two-byte sequences of LEADING_CODE_8_BIT_CONTROL and (their 8-bit
1611 8-bit characters of the range 0xA0..0xFF are represented by
1612 one-byte sequences which are their 8-bit code.
1614 The other characters are represented by a sequence of `base
1615 leading-code', optional `extended leading-code', and one or two
1616 `position-code's. The length of the sequence is determined by the
1617 base leading-code. Leading-code takes the range 0x81 through 0x9D,
1618 whereas extended leading-code and position-code take the range 0xA0
1619 through 0xFF. See `charset.h' for more details about leading-code
1622 --- CODE RANGE of Emacs' internal format ---
1626 eight-bit-control LEADING_CODE_8_BIT_CONTROL + 0xA0..0xBF
1627 eight-bit-graphic 0xA0..0xBF
1628 ELSE 0x81..0x9D + [0xA0..0xFF]+
1629 ---------------------------------------------
1631 As this is the internal character representation, the format is
1632 usually not used externally (i.e. in a file or in a data sent to a
1633 process). But, it is possible to have a text externally in this
1634 format (i.e. by encoding by the coding system `emacs-mule').
1636 In that case, a sequence of one-byte codes has a slightly different
1639 At first, all characters in eight-bit-control are represented by
1640 one-byte sequences which are their 8-bit code.
1642 Next, character composition data are represented by the byte
1643 sequence of the form: 0x80 METHOD BYTES CHARS COMPONENT ...,
1645 METHOD is 0xF0 plus one of composition method (enum
1646 composition_method),
1648 BYTES is 0xA0 plus a byte length of this composition data,
1650 CHARS is 0x20 plus a number of characters composed by this
1653 COMPONENTs are characters of multibye form or composition
1654 rules encoded by two-byte of ASCII codes.
1656 In addition, for backward compatibility, the following formats are
1657 also recognized as composition data on decoding.
1660 0x80 0xFF MSEQ RULE MSEQ RULE ... MSEQ
1663 MSEQ is a multibyte form but in these special format:
1664 ASCII: 0xA0 ASCII_CODE+0x80,
1665 other: LEADING_CODE+0x20 FOLLOWING-BYTE ...,
1666 RULE is a one byte code of the range 0xA0..0xF0 that
1667 represents a composition rule.
1670 char emacs_mule_bytes
[256];
1673 emacs_mule_char (coding
, src
, nbytes
, nchars
, id
)
1674 struct coding_system
*coding
;
1675 const unsigned char *src
;
1676 int *nbytes
, *nchars
, *id
;
1678 const unsigned char *src_end
= coding
->source
+ coding
->src_bytes
;
1679 const unsigned char *src_base
= src
;
1680 int multibytep
= coding
->src_multibyte
;
1681 struct charset
*charset
;
1684 int consumed_chars
= 0;
1690 charset
= emacs_mule_charset
[0];
1694 switch (emacs_mule_bytes
[c
])
1697 if (! (charset
= emacs_mule_charset
[c
]))
1706 if (c
== EMACS_MULE_LEADING_CODE_PRIVATE_11
1707 || c
== EMACS_MULE_LEADING_CODE_PRIVATE_12
)
1710 if (c
< 0xA0 || ! (charset
= emacs_mule_charset
[c
]))
1719 if (! (charset
= emacs_mule_charset
[c
]))
1724 code
= (c
& 0x7F) << 8;
1734 if (c
< 0 || ! (charset
= emacs_mule_charset
[c
]))
1739 code
= (c
& 0x7F) << 8;
1748 charset
= CHARSET_FROM_ID (ASCII_BYTE_P (code
)
1749 ? charset_ascii
: charset_eight_bit
);
1755 c
= DECODE_CHAR (charset
, code
);
1759 *nbytes
= src
- src_base
;
1760 *nchars
= consumed_chars
;
1773 /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
1774 Check if a text is encoded in `emacs-mule'. If it is, return 1,
1778 detect_coding_emacs_mule (coding
, detect_info
)
1779 struct coding_system
*coding
;
1780 struct coding_detection_info
*detect_info
;
1782 const unsigned char *src
= coding
->source
, *src_base
;
1783 const unsigned char *src_end
= coding
->source
+ coding
->src_bytes
;
1784 int multibytep
= coding
->src_multibyte
;
1785 int consumed_chars
= 0;
1789 detect_info
->checked
|= CATEGORY_MASK_EMACS_MULE
;
1790 /* A coding system of this category is always ASCII compatible. */
1791 src
+= coding
->head_ascii
;
1801 /* Perhaps the start of composite character. We simple skip
1802 it because analyzing it is too heavy for detecting. But,
1803 at least, we check that the composite character
1804 constitues of more than 4 bytes. */
1805 const unsigned char *src_base
;
1815 if (src
- src_base
<= 4)
1817 found
= CATEGORY_MASK_EMACS_MULE
;
1825 && (c
== ISO_CODE_ESC
|| c
== ISO_CODE_SI
|| c
== ISO_CODE_SO
))
1830 int more_bytes
= emacs_mule_bytes
[*src_base
] - 1;
1832 while (more_bytes
> 0)
1837 src
--; /* Unread the last byte. */
1842 if (more_bytes
!= 0)
1844 found
= CATEGORY_MASK_EMACS_MULE
;
1847 detect_info
->rejected
|= CATEGORY_MASK_EMACS_MULE
;
1851 if (src_base
< src
&& coding
->mode
& CODING_MODE_LAST_BLOCK
)
1853 detect_info
->rejected
|= CATEGORY_MASK_EMACS_MULE
;
1856 detect_info
->found
|= found
;
1861 /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */
1863 /* Decode a character represented as a component of composition
1864 sequence of Emacs 20/21 style at SRC. Set C to that character and
1865 update SRC to the head of next character (or an encoded composition
1866 rule). If SRC doesn't points a composition component, set C to -1.
1867 If SRC points an invalid byte sequence, global exit by a return
1870 #define DECODE_EMACS_MULE_COMPOSITION_CHAR(buf) \
1874 int nbytes, nchars; \
1876 if (src == src_end) \
1878 c = emacs_mule_char (coding, src, &nbytes, &nchars, NULL);\
1883 goto invalid_code; \
1887 consumed_chars += nchars; \
1892 /* Decode a composition rule represented as a component of composition
1893 sequence of Emacs 20 style at SRC. Store the decoded rule in *BUF,
1894 and increment BUF. If SRC points an invalid byte sequence, set C
1897 #define DECODE_EMACS_MULE_COMPOSITION_RULE_20(buf) \
1899 int c, gref, nref; \
1901 if (src >= src_end) \
1902 goto invalid_code; \
1903 ONE_MORE_BYTE_NO_CHECK (c); \
1905 if (c < 0 || c >= 81) \
1906 goto invalid_code; \
1908 gref = c / 9, nref = c % 9; \
1909 *buf++ = COMPOSITION_ENCODE_RULE (gref, nref); \
1913 /* Decode a composition rule represented as a component of composition
1914 sequence of Emacs 21 style at SRC. Store the decoded rule in *BUF,
1915 and increment BUF. If SRC points an invalid byte sequence, set C
1918 #define DECODE_EMACS_MULE_COMPOSITION_RULE_21(buf) \
1922 if (src + 1>= src_end) \
1923 goto invalid_code; \
1924 ONE_MORE_BYTE_NO_CHECK (gref); \
1926 ONE_MORE_BYTE_NO_CHECK (nref); \
1928 if (gref < 0 || gref >= 81 \
1929 || nref < 0 || nref >= 81) \
1930 goto invalid_code; \
1931 *buf++ = COMPOSITION_ENCODE_RULE (gref, nref); \
1935 #define DECODE_EMACS_MULE_21_COMPOSITION(c) \
1937 /* Emacs 21 style format. The first three bytes at SRC are \
1938 (METHOD - 0xF2), (BYTES - 0xA0), (CHARS - 0xA0), where BYTES is \
1939 the byte length of this composition information, CHARS is the \
1940 number of characters composed by this composition. */ \
1941 enum composition_method method = c - 0xF2; \
1942 int *charbuf_base = charbuf; \
1943 int consumed_chars_limit; \
1944 int nbytes, nchars; \
1946 ONE_MORE_BYTE (c); \
1948 goto invalid_code; \
1949 nbytes = c - 0xA0; \
1951 goto invalid_code; \
1952 ONE_MORE_BYTE (c); \
1954 goto invalid_code; \
1955 nchars = c - 0xA0; \
1956 ADD_COMPOSITION_DATA (charbuf, nchars, method); \
1957 consumed_chars_limit = consumed_chars_base + nbytes; \
1958 if (method != COMPOSITION_RELATIVE) \
1961 while (consumed_chars < consumed_chars_limit) \
1963 if (i % 2 && method != COMPOSITION_WITH_ALTCHARS) \
1964 DECODE_EMACS_MULE_COMPOSITION_RULE_21 (charbuf); \
1966 DECODE_EMACS_MULE_COMPOSITION_CHAR (charbuf); \
1969 if (consumed_chars < consumed_chars_limit) \
1970 goto invalid_code; \
1971 charbuf_base[0] -= i; \
1976 #define DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION(c) \
1978 /* Emacs 20 style format for relative composition. */ \
1979 /* Store multibyte form of characters to be composed. */ \
1980 enum composition_method method = COMPOSITION_RELATIVE; \
1981 int components[MAX_COMPOSITION_COMPONENTS * 2 - 1]; \
1982 int *buf = components; \
1986 ONE_MORE_BYTE (c); /* skip 0x80 */ \
1987 for (i = 0; i < MAX_COMPOSITION_COMPONENTS; i++) \
1988 DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \
1990 goto invalid_code; \
1991 ADD_COMPOSITION_DATA (charbuf, i, method); \
1992 for (j = 0; j < i; j++) \
1993 *charbuf++ = components[j]; \
1997 #define DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION(c) \
1999 /* Emacs 20 style format for rule-base composition. */ \
2000 /* Store multibyte form of characters to be composed. */ \
2001 enum composition_method method = COMPOSITION_WITH_RULE; \
2002 int components[MAX_COMPOSITION_COMPONENTS * 2 - 1]; \
2003 int *buf = components; \
2006 DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \
2007 for (i = 0; i < MAX_COMPOSITION_COMPONENTS; i++) \
2009 DECODE_EMACS_MULE_COMPOSITION_RULE_20 (buf); \
2010 DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \
2012 if (i < 1 || (buf - components) % 2 == 0) \
2013 goto invalid_code; \
2014 if (charbuf + i + (i / 2) + 1 < charbuf_end) \
2015 goto no_more_source; \
2016 ADD_COMPOSITION_DATA (buf, i, method); \
2017 for (j = 0; j < i; j++) \
2018 *charbuf++ = components[j]; \
2019 for (j = 0; j < i; j += 2) \
2020 *charbuf++ = components[j]; \
2025 decode_coding_emacs_mule (coding
)
2026 struct coding_system
*coding
;
2028 const unsigned char *src
= coding
->source
+ coding
->consumed
;
2029 const unsigned char *src_end
= coding
->source
+ coding
->src_bytes
;
2030 const unsigned char *src_base
;
2031 int *charbuf
= coding
->charbuf
+ coding
->charbuf_used
;
2033 = coding
->charbuf
+ coding
->charbuf_size
- MAX_ANNOTATION_LENGTH
;
2034 int consumed_chars
= 0, consumed_chars_base
;
2035 int multibytep
= coding
->src_multibyte
;
2036 Lisp_Object attrs
, charset_list
;
2037 int char_offset
= coding
->produced_char
;
2038 int last_offset
= char_offset
;
2039 int last_id
= charset_ascii
;
2041 CODING_GET_INFO (coding
, attrs
, charset_list
);
2048 consumed_chars_base
= consumed_chars
;
2050 if (charbuf
>= charbuf_end
)
2069 if (c
- 0xF2 >= COMPOSITION_RELATIVE
2070 && c
- 0xF2 <= COMPOSITION_WITH_RULE_ALTCHARS
)
2071 DECODE_EMACS_MULE_21_COMPOSITION (c
);
2073 DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION (c
);
2075 DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION (c
);
2079 else if (c
< 0xA0 && emacs_mule_bytes
[c
] > 1)
2085 consumed_chars
= consumed_chars_base
;
2086 c
= emacs_mule_char (coding
, src
, &nbytes
, &nchars
, &id
);
2095 if (last_id
!= charset_ascii
)
2096 ADD_CHARSET_DATA (charbuf
, char_offset
- last_offset
, last_id
);
2098 last_offset
= char_offset
;
2102 consumed_chars
+= nchars
;
2109 consumed_chars
= consumed_chars_base
;
2111 *charbuf
++ = ASCII_BYTE_P (c
) ? c
: BYTE8_TO_CHAR (c
);
2117 if (last_id
!= charset_ascii
)
2118 ADD_CHARSET_DATA (charbuf
, char_offset
- last_offset
, last_id
);
2119 coding
->consumed_char
+= consumed_chars_base
;
2120 coding
->consumed
= src_base
- coding
->source
;
2121 coding
->charbuf_used
= charbuf
- coding
->charbuf
;
2125 #define EMACS_MULE_LEADING_CODES(id, codes) \
2128 codes[0] = id, codes[1] = 0; \
2129 else if (id < 0xE0) \
2130 codes[0] = 0x9A, codes[1] = id; \
2131 else if (id < 0xF0) \
2132 codes[0] = 0x9B, codes[1] = id; \
2133 else if (id < 0xF5) \
2134 codes[0] = 0x9C, codes[1] = id; \
2136 codes[0] = 0x9D, codes[1] = id; \
2141 encode_coding_emacs_mule (coding
)
2142 struct coding_system
*coding
;
2144 int multibytep
= coding
->dst_multibyte
;
2145 int *charbuf
= coding
->charbuf
;
2146 int *charbuf_end
= charbuf
+ coding
->charbuf_used
;
2147 unsigned char *dst
= coding
->destination
+ coding
->produced
;
2148 unsigned char *dst_end
= coding
->destination
+ coding
->dst_bytes
;
2150 int produced_chars
= 0;
2151 Lisp_Object attrs
, charset_list
;
2153 int preferred_charset_id
= -1;
2155 CODING_GET_INFO (coding
, attrs
, charset_list
);
2156 if (! EQ (charset_list
, Vemacs_mule_charset_list
))
2158 CODING_ATTR_CHARSET_LIST (attrs
)
2159 = charset_list
= Vemacs_mule_charset_list
;
2162 while (charbuf
< charbuf_end
)
2164 ASSURE_DESTINATION (safe_room
);
2169 /* Handle an annotation. */
2172 case CODING_ANNOTATE_COMPOSITION_MASK
:
2173 /* Not yet implemented. */
2175 case CODING_ANNOTATE_CHARSET_MASK
:
2176 preferred_charset_id
= charbuf
[3];
2177 if (preferred_charset_id
>= 0
2178 && NILP (Fmemq (make_number (preferred_charset_id
),
2180 preferred_charset_id
= -1;
2189 if (ASCII_CHAR_P (c
))
2190 EMIT_ONE_ASCII_BYTE (c
);
2191 else if (CHAR_BYTE8_P (c
))
2193 c
= CHAR_TO_BYTE8 (c
);
2198 struct charset
*charset
;
2202 unsigned char leading_codes
[2];
2204 if (preferred_charset_id
>= 0)
2206 charset
= CHARSET_FROM_ID (preferred_charset_id
);
2207 if (! CHAR_CHARSET_P (c
, charset
))
2208 charset
= char_charset (c
, charset_list
, NULL
);
2211 charset
= char_charset (c
, charset_list
, &code
);
2214 c
= coding
->default_char
;
2215 if (ASCII_CHAR_P (c
))
2217 EMIT_ONE_ASCII_BYTE (c
);
2220 charset
= char_charset (c
, charset_list
, &code
);
2222 dimension
= CHARSET_DIMENSION (charset
);
2223 emacs_mule_id
= CHARSET_EMACS_MULE_ID (charset
);
2224 EMACS_MULE_LEADING_CODES (emacs_mule_id
, leading_codes
);
2225 EMIT_ONE_BYTE (leading_codes
[0]);
2226 if (leading_codes
[1])
2227 EMIT_ONE_BYTE (leading_codes
[1]);
2229 EMIT_ONE_BYTE (code
| 0x80);
2233 EMIT_ONE_BYTE (code
>> 8);
2234 EMIT_ONE_BYTE (code
& 0xFF);
2238 record_conversion_result (coding
, CODING_RESULT_SUCCESS
);
2239 coding
->produced_char
+= produced_chars
;
2240 coding
->produced
= dst
- coding
->destination
;
2245 /*** 7. ISO2022 handlers ***/
2247 /* The following note describes the coding system ISO2022 briefly.
2248 Since the intention of this note is to help understand the
2249 functions in this file, some parts are NOT ACCURATE or are OVERLY
2250 SIMPLIFIED. For thorough understanding, please refer to the
2251 original document of ISO2022. This is equivalent to the standard
2252 ECMA-35, obtainable from <URL:http://www.ecma.ch/> (*).
2254 ISO2022 provides many mechanisms to encode several character sets
2255 in 7-bit and 8-bit environments. For 7-bit environments, all text
2256 is encoded using bytes less than 128. This may make the encoded
2257 text a little bit longer, but the text passes more easily through
2258 several types of gateway, some of which strip off the MSB (Most
2261 There are two kinds of character sets: control character sets and
2262 graphic character sets. The former contain control characters such
2263 as `newline' and `escape' to provide control functions (control
2264 functions are also provided by escape sequences). The latter
2265 contain graphic characters such as 'A' and '-'. Emacs recognizes
2266 two control character sets and many graphic character sets.
2268 Graphic character sets are classified into one of the following
2269 four classes, according to the number of bytes (DIMENSION) and
2270 number of characters in one dimension (CHARS) of the set:
2271 - DIMENSION1_CHARS94
2272 - DIMENSION1_CHARS96
2273 - DIMENSION2_CHARS94
2274 - DIMENSION2_CHARS96
2276 In addition, each character set is assigned an identification tag,
2277 unique for each set, called the "final character" (denoted as <F>
2278 hereafter). The <F> of each character set is decided by ECMA(*)
2279 when it is registered in ISO. The code range of <F> is 0x30..0x7F
2280 (0x30..0x3F are for private use only).
2282 Note (*): ECMA = European Computer Manufacturers Association
2284 Here are examples of graphic character sets [NAME(<F>)]:
2285 o DIMENSION1_CHARS94 -- ASCII('B'), right-half-of-JISX0201('I'), ...
2286 o DIMENSION1_CHARS96 -- right-half-of-ISO8859-1('A'), ...
2287 o DIMENSION2_CHARS94 -- GB2312('A'), JISX0208('B'), ...
2288 o DIMENSION2_CHARS96 -- none for the moment
2290 A code area (1 byte=8 bits) is divided into 4 areas, C0, GL, C1, and GR.
2291 C0 [0x00..0x1F] -- control character plane 0
2292 GL [0x20..0x7F] -- graphic character plane 0
2293 C1 [0x80..0x9F] -- control character plane 1
2294 GR [0xA0..0xFF] -- graphic character plane 1
2296 A control character set is directly designated and invoked to C0 or
2297 C1 by an escape sequence. The most common case is that:
2298 - ISO646's control character set is designated/invoked to C0, and
2299 - ISO6429's control character set is designated/invoked to C1,
2300 and usually these designations/invocations are omitted in encoded
2301 text. In a 7-bit environment, only C0 can be used, and a control
2302 character for C1 is encoded by an appropriate escape sequence to
2303 fit into the environment. All control characters for C1 are
2304 defined to have corresponding escape sequences.
2306 A graphic character set is at first designated to one of four
2307 graphic registers (G0 through G3), then these graphic registers are
2308 invoked to GL or GR. These designations and invocations can be
2309 done independently. The most common case is that G0 is invoked to
2310 GL, G1 is invoked to GR, and ASCII is designated to G0. Usually
2311 these invocations and designations are omitted in encoded text.
2312 In a 7-bit environment, only GL can be used.
2314 When a graphic character set of CHARS94 is invoked to GL, codes
2315 0x20 and 0x7F of the GL area work as control characters SPACE and
2316 DEL respectively, and codes 0xA0 and 0xFF of the GR area should not
2319 There are two ways of invocation: locking-shift and single-shift.
2320 With locking-shift, the invocation lasts until the next different
2321 invocation, whereas with single-shift, the invocation affects the
2322 following character only and doesn't affect the locking-shift
2323 state. Invocations are done by the following control characters or
2326 ----------------------------------------------------------------------
2327 abbrev function cntrl escape seq description
2328 ----------------------------------------------------------------------
2329 SI/LS0 (shift-in) 0x0F none invoke G0 into GL
2330 SO/LS1 (shift-out) 0x0E none invoke G1 into GL
2331 LS2 (locking-shift-2) none ESC 'n' invoke G2 into GL
2332 LS3 (locking-shift-3) none ESC 'o' invoke G3 into GL
2333 LS1R (locking-shift-1 right) none ESC '~' invoke G1 into GR (*)
2334 LS2R (locking-shift-2 right) none ESC '}' invoke G2 into GR (*)
2335 LS3R (locking-shift 3 right) none ESC '|' invoke G3 into GR (*)
2336 SS2 (single-shift-2) 0x8E ESC 'N' invoke G2 for one char
2337 SS3 (single-shift-3) 0x8F ESC 'O' invoke G3 for one char
2338 ----------------------------------------------------------------------
2339 (*) These are not used by any known coding system.
2341 Control characters for these functions are defined by macros
2342 ISO_CODE_XXX in `coding.h'.
2344 Designations are done by the following escape sequences:
2345 ----------------------------------------------------------------------
2346 escape sequence description
2347 ----------------------------------------------------------------------
2348 ESC '(' <F> designate DIMENSION1_CHARS94<F> to G0
2349 ESC ')' <F> designate DIMENSION1_CHARS94<F> to G1
2350 ESC '*' <F> designate DIMENSION1_CHARS94<F> to G2
2351 ESC '+' <F> designate DIMENSION1_CHARS94<F> to G3
2352 ESC ',' <F> designate DIMENSION1_CHARS96<F> to G0 (*)
2353 ESC '-' <F> designate DIMENSION1_CHARS96<F> to G1
2354 ESC '.' <F> designate DIMENSION1_CHARS96<F> to G2
2355 ESC '/' <F> designate DIMENSION1_CHARS96<F> to G3
2356 ESC '$' '(' <F> designate DIMENSION2_CHARS94<F> to G0 (**)
2357 ESC '$' ')' <F> designate DIMENSION2_CHARS94<F> to G1
2358 ESC '$' '*' <F> designate DIMENSION2_CHARS94<F> to G2
2359 ESC '$' '+' <F> designate DIMENSION2_CHARS94<F> to G3
2360 ESC '$' ',' <F> designate DIMENSION2_CHARS96<F> to G0 (*)
2361 ESC '$' '-' <F> designate DIMENSION2_CHARS96<F> to G1
2362 ESC '$' '.' <F> designate DIMENSION2_CHARS96<F> to G2
2363 ESC '$' '/' <F> designate DIMENSION2_CHARS96<F> to G3
2364 ----------------------------------------------------------------------
2366 In this list, "DIMENSION1_CHARS94<F>" means a graphic character set
2367 of dimension 1, chars 94, and final character <F>, etc...
2369 Note (*): Although these designations are not allowed in ISO2022,
2370 Emacs accepts them on decoding, and produces them on encoding
2371 CHARS96 character sets in a coding system which is characterized as
2372 7-bit environment, non-locking-shift, and non-single-shift.
2374 Note (**): If <F> is '@', 'A', or 'B', the intermediate character
2375 '(' must be omitted. We refer to this as "short-form" hereafter.
2377 Now you may notice that there are a lot of ways of encoding the
2378 same multilingual text in ISO2022. Actually, there exist many
2379 coding systems such as Compound Text (used in X11's inter client
2380 communication, ISO-2022-JP (used in Japanese Internet), ISO-2022-KR
2381 (used in Korean Internet), EUC (Extended UNIX Code, used in Asian
2382 localized platforms), and all of these are variants of ISO2022.
2384 In addition to the above, Emacs handles two more kinds of escape
2385 sequences: ISO6429's direction specification and Emacs' private
2386 sequence for specifying character composition.
2388 ISO6429's direction specification takes the following form:
2389 o CSI ']' -- end of the current direction
2390 o CSI '0' ']' -- end of the current direction
2391 o CSI '1' ']' -- start of left-to-right text
2392 o CSI '2' ']' -- start of right-to-left text
2393 The control character CSI (0x9B: control sequence introducer) is
2394 abbreviated to the escape sequence ESC '[' in a 7-bit environment.
2396 Character composition specification takes the following form:
2397 o ESC '0' -- start relative composition
2398 o ESC '1' -- end composition
2399 o ESC '2' -- start rule-base composition (*)
2400 o ESC '3' -- start relative composition with alternate chars (**)
2401 o ESC '4' -- start rule-base composition with alternate chars (**)
2402 Since these are not standard escape sequences of any ISO standard,
2403 the use of them with these meanings is restricted to Emacs only.
2405 (*) This form is used only in Emacs 20.7 and older versions,
2406 but newer versions can safely decode it.
2407 (**) This form is used only in Emacs 21.1 and newer versions,
2408 and older versions can't decode it.
2410 Here's a list of example usages of these composition escape
2411 sequences (categorized by `enum composition_method').
2413 COMPOSITION_RELATIVE:
2414 ESC 0 CHAR [ CHAR ] ESC 1
2415 COMPOSITION_WITH_RULE:
2416 ESC 2 CHAR [ RULE CHAR ] ESC 1
2417 COMPOSITION_WITH_ALTCHARS:
2418 ESC 3 ALTCHAR [ ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1
2419 COMPOSITION_WITH_RULE_ALTCHARS:
2420 ESC 4 ALTCHAR [ RULE ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 */
2422 enum iso_code_class_type iso_code_class
[256];
2424 #define SAFE_CHARSET_P(coding, id) \
2425 ((id) <= (coding)->max_charset_id \
2426 && (coding)->safe_charsets[id] >= 0)
2429 #define SHIFT_OUT_OK(category) \
2430 (CODING_ISO_INITIAL (&coding_categories[category], 1) >= 0)
2433 setup_iso_safe_charsets (attrs
)
2436 Lisp_Object charset_list
, safe_charsets
;
2437 Lisp_Object request
;
2438 Lisp_Object reg_usage
;
2441 int flags
= XINT (AREF (attrs
, coding_attr_iso_flags
));
2444 charset_list
= CODING_ATTR_CHARSET_LIST (attrs
);
2445 if ((flags
& CODING_ISO_FLAG_FULL_SUPPORT
)
2446 && ! EQ (charset_list
, Viso_2022_charset_list
))
2448 CODING_ATTR_CHARSET_LIST (attrs
)
2449 = charset_list
= Viso_2022_charset_list
;
2450 ASET (attrs
, coding_attr_safe_charsets
, Qnil
);
2453 if (STRINGP (AREF (attrs
, coding_attr_safe_charsets
)))
2457 for (tail
= charset_list
; CONSP (tail
); tail
= XCDR (tail
))
2459 int id
= XINT (XCAR (tail
));
2460 if (max_charset_id
< id
)
2461 max_charset_id
= id
;
2464 safe_charsets
= Fmake_string (make_number (max_charset_id
+ 1),
2466 request
= AREF (attrs
, coding_attr_iso_request
);
2467 reg_usage
= AREF (attrs
, coding_attr_iso_usage
);
2468 reg94
= XINT (XCAR (reg_usage
));
2469 reg96
= XINT (XCDR (reg_usage
));
2471 for (tail
= charset_list
; CONSP (tail
); tail
= XCDR (tail
))
2475 struct charset
*charset
;
2478 charset
= CHARSET_FROM_ID (XINT (id
));
2479 reg
= Fcdr (Fassq (id
, request
));
2481 SSET (safe_charsets
, XINT (id
), XINT (reg
));
2482 else if (charset
->iso_chars_96
)
2485 SSET (safe_charsets
, XINT (id
), reg96
);
2490 SSET (safe_charsets
, XINT (id
), reg94
);
2493 ASET (attrs
, coding_attr_safe_charsets
, safe_charsets
);
2497 /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
2498 Check if a text is encoded in one of ISO-2022 based codig systems.
2499 If it is, return 1, else return 0. */
2502 detect_coding_iso_2022 (coding
, detect_info
)
2503 struct coding_system
*coding
;
2504 struct coding_detection_info
*detect_info
;
2506 const unsigned char *src
= coding
->source
, *src_base
= src
;
2507 const unsigned char *src_end
= coding
->source
+ coding
->src_bytes
;
2508 int multibytep
= coding
->src_multibyte
;
2509 int single_shifting
= 0;
2512 int consumed_chars
= 0;
2517 detect_info
->checked
|= CATEGORY_MASK_ISO
;
2519 for (i
= coding_category_iso_7
; i
<= coding_category_iso_8_else
; i
++)
2521 struct coding_system
*this = &(coding_categories
[i
]);
2522 Lisp_Object attrs
, val
;
2524 attrs
= CODING_ID_ATTRS (this->id
);
2525 if (CODING_ISO_FLAGS (this) & CODING_ISO_FLAG_FULL_SUPPORT
2526 && ! EQ (CODING_ATTR_SAFE_CHARSETS (attrs
), Viso_2022_charset_list
))
2527 setup_iso_safe_charsets (attrs
);
2528 val
= CODING_ATTR_SAFE_CHARSETS (attrs
);
2529 this->max_charset_id
= SCHARS (val
) - 1;
2530 this->safe_charsets
= (char *) SDATA (val
);
2533 /* A coding system of this category is always ASCII compatible. */
2534 src
+= coding
->head_ascii
;
2536 while (rejected
!= CATEGORY_MASK_ISO
)
2543 if (inhibit_iso_escape_detection
)
2545 single_shifting
= 0;
2547 if (c
>= '(' && c
<= '/')
2549 /* Designation sequence for a charset of dimension 1. */
2551 if (c1
< ' ' || c1
>= 0x80
2552 || (id
= iso_charset_table
[0][c
>= ','][c1
]) < 0)
2553 /* Invalid designation sequence. Just ignore. */
2558 /* Designation sequence for a charset of dimension 2. */
2560 if (c
>= '@' && c
<= 'B')
2561 /* Designation for JISX0208.1978, GB2312, or JISX0208. */
2562 id
= iso_charset_table
[1][0][c
];
2563 else if (c
>= '(' && c
<= '/')
2566 if (c1
< ' ' || c1
>= 0x80
2567 || (id
= iso_charset_table
[1][c
>= ','][c1
]) < 0)
2568 /* Invalid designation sequence. Just ignore. */
2572 /* Invalid designation sequence. Just ignore it. */
2575 else if (c
== 'N' || c
== 'O')
2577 /* ESC <Fe> for SS2 or SS3. */
2578 single_shifting
= 1;
2579 rejected
|= CATEGORY_MASK_ISO_7BIT
| CATEGORY_MASK_ISO_8BIT
;
2582 else if (c
>= '0' && c
<= '4')
2584 /* ESC <Fp> for start/end composition. */
2585 found
|= CATEGORY_MASK_ISO
;
2590 /* Invalid escape sequence. Just ignore it. */
2594 /* We found a valid designation sequence for CHARSET. */
2595 rejected
|= CATEGORY_MASK_ISO_8BIT
;
2596 if (SAFE_CHARSET_P (&coding_categories
[coding_category_iso_7
],
2598 found
|= CATEGORY_MASK_ISO_7
;
2600 rejected
|= CATEGORY_MASK_ISO_7
;
2601 if (SAFE_CHARSET_P (&coding_categories
[coding_category_iso_7_tight
],
2603 found
|= CATEGORY_MASK_ISO_7_TIGHT
;
2605 rejected
|= CATEGORY_MASK_ISO_7_TIGHT
;
2606 if (SAFE_CHARSET_P (&coding_categories
[coding_category_iso_7_else
],
2608 found
|= CATEGORY_MASK_ISO_7_ELSE
;
2610 rejected
|= CATEGORY_MASK_ISO_7_ELSE
;
2611 if (SAFE_CHARSET_P (&coding_categories
[coding_category_iso_8_else
],
2613 found
|= CATEGORY_MASK_ISO_8_ELSE
;
2615 rejected
|= CATEGORY_MASK_ISO_8_ELSE
;
2620 /* Locking shift out/in. */
2621 if (inhibit_iso_escape_detection
)
2623 single_shifting
= 0;
2624 rejected
|= CATEGORY_MASK_ISO_7BIT
| CATEGORY_MASK_ISO_8BIT
;
2625 found
|= CATEGORY_MASK_ISO_ELSE
;
2629 /* Control sequence introducer. */
2630 single_shifting
= 0;
2631 rejected
|= CATEGORY_MASK_ISO_7BIT
| CATEGORY_MASK_ISO_7_ELSE
;
2632 found
|= CATEGORY_MASK_ISO_8_ELSE
;
2633 goto check_extra_latin
;
2638 if (inhibit_iso_escape_detection
)
2640 single_shifting
= 0;
2641 rejected
|= CATEGORY_MASK_ISO_7BIT
;
2642 if (CODING_ISO_FLAGS (&coding_categories
[coding_category_iso_8_1
])
2643 & CODING_ISO_FLAG_SINGLE_SHIFT
)
2644 found
|= CATEGORY_MASK_ISO_8_1
, single_shifting
= 1;
2645 if (CODING_ISO_FLAGS (&coding_categories
[coding_category_iso_8_2
])
2646 & CODING_ISO_FLAG_SINGLE_SHIFT
)
2647 found
|= CATEGORY_MASK_ISO_8_2
, single_shifting
= 1;
2648 if (single_shifting
)
2650 goto check_extra_latin
;
2657 single_shifting
= 0;
2662 rejected
|= CATEGORY_MASK_ISO_7BIT
| CATEGORY_MASK_ISO_7_ELSE
;
2663 found
|= CATEGORY_MASK_ISO_8_1
;
2664 /* Check the length of succeeding codes of the range
2665 0xA0..0FF. If the byte length is even, we include
2666 CATEGORY_MASK_ISO_8_2 in `found'. We can check this
2667 only when we are not single shifting. */
2668 if (! single_shifting
2669 && ! (rejected
& CATEGORY_MASK_ISO_8_2
))
2672 while (src
< src_end
)
2680 if (i
& 1 && src
< src_end
)
2681 rejected
|= CATEGORY_MASK_ISO_8_2
;
2683 found
|= CATEGORY_MASK_ISO_8_2
;
2688 single_shifting
= 0;
2689 if (! VECTORP (Vlatin_extra_code_table
)
2690 || NILP (XVECTOR (Vlatin_extra_code_table
)->contents
[c
]))
2692 rejected
= CATEGORY_MASK_ISO
;
2695 if (CODING_ISO_FLAGS (&coding_categories
[coding_category_iso_8_1
])
2696 & CODING_ISO_FLAG_LATIN_EXTRA
)
2697 found
|= CATEGORY_MASK_ISO_8_1
;
2699 rejected
|= CATEGORY_MASK_ISO_8_1
;
2700 rejected
|= CATEGORY_MASK_ISO_8_2
;
2703 detect_info
->rejected
|= CATEGORY_MASK_ISO
;
2707 detect_info
->rejected
|= rejected
;
2708 detect_info
->found
|= (found
& ~rejected
);
2713 /* Set designation state into CODING. Set CHARS_96 to -1 if the
2714 escape sequence should be kept. */
2715 #define DECODE_DESIGNATION(reg, dim, chars_96, final) \
2719 if (final < '0' || final >= 128 \
2720 || ((id = ISO_CHARSET_TABLE (dim, chars_96, final)) < 0) \
2721 || !SAFE_CHARSET_P (coding, id)) \
2723 CODING_ISO_DESIGNATION (coding, reg) = -2; \
2727 prev = CODING_ISO_DESIGNATION (coding, reg); \
2728 if (id == charset_jisx0201_roman) \
2730 if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \
2731 id = charset_ascii; \
2733 else if (id == charset_jisx0208_1978) \
2735 if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \
2736 id = charset_jisx0208; \
2738 CODING_ISO_DESIGNATION (coding, reg) = id; \
2739 /* If there was an invalid designation to REG previously, and this \
2740 designation is ASCII to REG, we should keep this designation \
2742 if (prev == -2 && id == charset_ascii) \
2747 #define MAYBE_FINISH_COMPOSITION() \
2750 if (composition_state == COMPOSING_NO) \
2752 /* It is assured that we have enough room for producing \
2753 characters stored in the table `components'. */ \
2754 if (charbuf + component_idx > charbuf_end) \
2755 goto no_more_source; \
2756 composition_state = COMPOSING_NO; \
2757 if (method == COMPOSITION_RELATIVE \
2758 || method == COMPOSITION_WITH_ALTCHARS) \
2760 for (i = 0; i < component_idx; i++) \
2761 *charbuf++ = components[i]; \
2762 char_offset += component_idx; \
2766 for (i = 0; i < component_idx; i += 2) \
2767 *charbuf++ = components[i]; \
2768 char_offset += (component_idx / 2) + 1; \
2773 /* Handle composition start sequence ESC 0, ESC 2, ESC 3, or ESC 4.
2774 ESC 0 : relative composition : ESC 0 CHAR ... ESC 1
2775 ESC 2 : rulebase composition : ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1
2776 ESC 3 : altchar composition : ESC 3 CHAR ... ESC 0 CHAR ... ESC 1
2777 ESC 4 : alt&rule composition : ESC 4 CHAR RULE ... CHAR ESC 0 CHAR ... ESC 1
2780 #define DECODE_COMPOSITION_START(c1) \
2783 && composition_state == COMPOSING_COMPONENT_RULE) \
2785 component_len = component_idx; \
2786 composition_state = COMPOSING_CHAR; \
2790 const unsigned char *p; \
2792 MAYBE_FINISH_COMPOSITION (); \
2793 if (charbuf + MAX_COMPOSITION_COMPONENTS > charbuf_end) \
2794 goto no_more_source; \
2795 for (p = src; p < src_end - 1; p++) \
2796 if (*p == ISO_CODE_ESC && p[1] == '1') \
2798 if (p == src_end - 1) \
2800 if (coding->mode & CODING_MODE_LAST_BLOCK) \
2801 goto invalid_code; \
2802 goto no_more_source; \
2805 /* This is surely the start of a composition. */ \
2806 method = (c1 == '0' ? COMPOSITION_RELATIVE \
2807 : c1 == '2' ? COMPOSITION_WITH_RULE \
2808 : c1 == '3' ? COMPOSITION_WITH_ALTCHARS \
2809 : COMPOSITION_WITH_RULE_ALTCHARS); \
2810 composition_state = (c1 <= '2' ? COMPOSING_CHAR \
2811 : COMPOSING_COMPONENT_CHAR); \
2812 component_idx = component_len = 0; \
2817 /* Handle compositoin end sequence ESC 1. */
2819 #define DECODE_COMPOSITION_END() \
2821 int nchars = (component_len > 0 ? component_idx - component_len \
2822 : method == COMPOSITION_RELATIVE ? component_idx \
2823 : (component_idx + 1) / 2); \
2825 int *saved_charbuf = charbuf; \
2827 ADD_COMPOSITION_DATA (charbuf, nchars, method); \
2828 if (method != COMPOSITION_RELATIVE) \
2830 if (component_len == 0) \
2831 for (i = 0; i < component_idx; i++) \
2832 *charbuf++ = components[i]; \
2834 for (i = 0; i < component_len; i++) \
2835 *charbuf++ = components[i]; \
2836 *saved_charbuf = saved_charbuf - charbuf; \
2838 if (method == COMPOSITION_WITH_RULE) \
2839 for (i = 0; i < component_idx; i += 2, char_offset++) \
2840 *charbuf++ = components[i]; \
2842 for (i = component_len; i < component_idx; i++, char_offset++) \
2843 *charbuf++ = components[i]; \
2844 coding->annotated = 1; \
2845 composition_state = COMPOSING_NO; \
2849 /* Decode a composition rule from the byte C1 (and maybe one more byte
2850 from SRC) and store one encoded composition rule in
2851 coding->cmp_data. */
2853 #define DECODE_COMPOSITION_RULE(c1) \
2856 if (c1 < 81) /* old format (before ver.21) */ \
2858 int gref = (c1) / 9; \
2859 int nref = (c1) % 9; \
2860 if (gref == 4) gref = 10; \
2861 if (nref == 4) nref = 10; \
2862 c1 = COMPOSITION_ENCODE_RULE (gref, nref); \
2864 else if (c1 < 93) /* new format (after ver.21) */ \
2866 ONE_MORE_BYTE (c2); \
2867 c1 = COMPOSITION_ENCODE_RULE (c1 - 81, c2 - 32); \
2874 /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */
2877 decode_coding_iso_2022 (coding
)
2878 struct coding_system
*coding
;
2880 const unsigned char *src
= coding
->source
+ coding
->consumed
;
2881 const unsigned char *src_end
= coding
->source
+ coding
->src_bytes
;
2882 const unsigned char *src_base
;
2883 int *charbuf
= coding
->charbuf
+ coding
->charbuf_used
;
2885 = coding
->charbuf
+ coding
->charbuf_size
- 4 - MAX_ANNOTATION_LENGTH
;
2886 int consumed_chars
= 0, consumed_chars_base
;
2887 int multibytep
= coding
->src_multibyte
;
2888 /* Charsets invoked to graphic plane 0 and 1 respectively. */
2889 int charset_id_0
= CODING_ISO_INVOKED_CHARSET (coding
, 0);
2890 int charset_id_1
= CODING_ISO_INVOKED_CHARSET (coding
, 1);
2891 int charset_id_2
, charset_id_3
;
2892 struct charset
*charset
;
2894 /* For handling composition sequence. */
2895 #define COMPOSING_NO 0
2896 #define COMPOSING_CHAR 1
2897 #define COMPOSING_RULE 2
2898 #define COMPOSING_COMPONENT_CHAR 3
2899 #define COMPOSING_COMPONENT_RULE 4
2901 int composition_state
= COMPOSING_NO
;
2902 enum composition_method method
;
2903 int components
[MAX_COMPOSITION_COMPONENTS
* 2 + 1];
2906 Lisp_Object attrs
, charset_list
;
2907 int char_offset
= coding
->produced_char
;
2908 int last_offset
= char_offset
;
2909 int last_id
= charset_ascii
;
2911 CODING_GET_INFO (coding
, attrs
, charset_list
);
2912 setup_iso_safe_charsets (attrs
);
2919 consumed_chars_base
= consumed_chars
;
2921 if (charbuf
>= charbuf_end
)
2928 /* We produce at most one character. */
2929 switch (iso_code_class
[c1
])
2931 case ISO_0x20_or_0x7F
:
2932 if (composition_state
!= COMPOSING_NO
)
2934 if (composition_state
== COMPOSING_RULE
2935 || composition_state
== COMPOSING_COMPONENT_RULE
)
2937 DECODE_COMPOSITION_RULE (c1
);
2938 components
[component_idx
++] = c1
;
2939 composition_state
--;
2943 if (charset_id_0
< 0
2944 || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_0
)))
2945 /* This is SPACE or DEL. */
2946 charset
= CHARSET_FROM_ID (charset_ascii
);
2948 charset
= CHARSET_FROM_ID (charset_id_0
);
2951 case ISO_graphic_plane_0
:
2952 if (composition_state
!= COMPOSING_NO
)
2954 if (composition_state
== COMPOSING_RULE
2955 || composition_state
== COMPOSING_COMPONENT_RULE
)
2957 DECODE_COMPOSITION_RULE (c1
);
2958 components
[component_idx
++] = c1
;
2959 composition_state
--;
2963 if (charset_id_0
< 0)
2964 charset
= CHARSET_FROM_ID (charset_ascii
);
2966 charset
= CHARSET_FROM_ID (charset_id_0
);
2969 case ISO_0xA0_or_0xFF
:
2970 if (charset_id_1
< 0
2971 || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_1
))
2972 || CODING_ISO_FLAGS (coding
) & CODING_ISO_FLAG_SEVEN_BITS
)
2974 /* This is a graphic character, we fall down ... */
2976 case ISO_graphic_plane_1
:
2977 if (charset_id_1
< 0)
2979 charset
= CHARSET_FROM_ID (charset_id_1
);
2983 MAYBE_FINISH_COMPOSITION ();
2984 charset
= CHARSET_FROM_ID (charset_ascii
);
2988 MAYBE_FINISH_COMPOSITION ();
2992 if (! (CODING_ISO_FLAGS (coding
) & CODING_ISO_FLAG_LOCKING_SHIFT
)
2993 || CODING_ISO_DESIGNATION (coding
, 1) < 0)
2995 CODING_ISO_INVOCATION (coding
, 0) = 1;
2996 charset_id_0
= CODING_ISO_INVOKED_CHARSET (coding
, 0);
3000 if (! (CODING_ISO_FLAGS (coding
) & CODING_ISO_FLAG_LOCKING_SHIFT
))
3002 CODING_ISO_INVOCATION (coding
, 0) = 0;
3003 charset_id_0
= CODING_ISO_INVOKED_CHARSET (coding
, 0);
3006 case ISO_single_shift_2_7
:
3007 case ISO_single_shift_2
:
3008 if (! (CODING_ISO_FLAGS (coding
) & CODING_ISO_FLAG_SINGLE_SHIFT
))
3010 /* SS2 is handled as an escape sequence of ESC 'N' */
3012 goto label_escape_sequence
;
3014 case ISO_single_shift_3
:
3015 if (! (CODING_ISO_FLAGS (coding
) & CODING_ISO_FLAG_SINGLE_SHIFT
))
3017 /* SS2 is handled as an escape sequence of ESC 'O' */
3019 goto label_escape_sequence
;
3021 case ISO_control_sequence_introducer
:
3022 /* CSI is handled as an escape sequence of ESC '[' ... */
3024 goto label_escape_sequence
;
3028 label_escape_sequence
:
3029 /* Escape sequences handled here are invocation,
3030 designation, direction specification, and character
3031 composition specification. */
3034 case '&': /* revision of following character set */
3036 if (!(c1
>= '@' && c1
<= '~'))
3039 if (c1
!= ISO_CODE_ESC
)
3042 goto label_escape_sequence
;
3044 case '$': /* designation of 2-byte character set */
3045 if (! (CODING_ISO_FLAGS (coding
) & CODING_ISO_FLAG_DESIGNATION
))
3051 if (c1
>= '@' && c1
<= 'B')
3052 { /* designation of JISX0208.1978, GB2312.1980,
3054 reg
= 0, chars96
= 0;
3056 else if (c1
>= 0x28 && c1
<= 0x2B)
3057 { /* designation of DIMENSION2_CHARS94 character set */
3058 reg
= c1
- 0x28, chars96
= 0;
3061 else if (c1
>= 0x2C && c1
<= 0x2F)
3062 { /* designation of DIMENSION2_CHARS96 character set */
3063 reg
= c1
- 0x2C, chars96
= 1;
3068 DECODE_DESIGNATION (reg
, 2, chars96
, c1
);
3069 /* We must update these variables now. */
3071 charset_id_0
= CODING_ISO_INVOKED_CHARSET (coding
, 0);
3073 charset_id_1
= CODING_ISO_INVOKED_CHARSET (coding
, 1);
3079 case 'n': /* invocation of locking-shift-2 */
3080 if (! (CODING_ISO_FLAGS (coding
) & CODING_ISO_FLAG_LOCKING_SHIFT
)
3081 || CODING_ISO_DESIGNATION (coding
, 2) < 0)
3083 CODING_ISO_INVOCATION (coding
, 0) = 2;
3084 charset_id_0
= CODING_ISO_INVOKED_CHARSET (coding
, 0);
3087 case 'o': /* invocation of locking-shift-3 */
3088 if (! (CODING_ISO_FLAGS (coding
) & CODING_ISO_FLAG_LOCKING_SHIFT
)
3089 || CODING_ISO_DESIGNATION (coding
, 3) < 0)
3091 CODING_ISO_INVOCATION (coding
, 0) = 3;
3092 charset_id_0
= CODING_ISO_INVOKED_CHARSET (coding
, 0);
3095 case 'N': /* invocation of single-shift-2 */
3096 if (! (CODING_ISO_FLAGS (coding
) & CODING_ISO_FLAG_SINGLE_SHIFT
)
3097 || CODING_ISO_DESIGNATION (coding
, 2) < 0)
3099 charset_id_2
= CODING_ISO_DESIGNATION (coding
, 2);
3100 if (charset_id_2
< 0)
3101 charset
= CHARSET_FROM_ID (charset_ascii
);
3103 charset
= CHARSET_FROM_ID (charset_id_2
);
3105 if (c1
< 0x20 || (c1
>= 0x80 && c1
< 0xA0))
3109 case 'O': /* invocation of single-shift-3 */
3110 if (! (CODING_ISO_FLAGS (coding
) & CODING_ISO_FLAG_SINGLE_SHIFT
)
3111 || CODING_ISO_DESIGNATION (coding
, 3) < 0)
3113 charset_id_3
= CODING_ISO_DESIGNATION (coding
, 3);
3114 if (charset_id_3
< 0)
3115 charset
= CHARSET_FROM_ID (charset_ascii
);
3117 charset
= CHARSET_FROM_ID (charset_id_3
);
3119 if (c1
< 0x20 || (c1
>= 0x80 && c1
< 0xA0))
3123 case '0': case '2': case '3': case '4': /* start composition */
3124 if (! (coding
->common_flags
& CODING_ANNOTATE_COMPOSITION_MASK
))
3126 DECODE_COMPOSITION_START (c1
);
3129 case '1': /* end composition */
3130 if (composition_state
== COMPOSING_NO
)
3132 DECODE_COMPOSITION_END ();
3135 case '[': /* specification of direction */
3136 if (! CODING_ISO_FLAGS (coding
) & CODING_ISO_FLAG_DIRECTION
)
3138 /* For the moment, nested direction is not supported.
3139 So, `coding->mode & CODING_MODE_DIRECTION' zero means
3140 left-to-right, and nozero means right-to-left. */
3144 case ']': /* end of the current direction */
3145 coding
->mode
&= ~CODING_MODE_DIRECTION
;
3147 case '0': /* end of the current direction */
3148 case '1': /* start of left-to-right direction */
3151 coding
->mode
&= ~CODING_MODE_DIRECTION
;
3156 case '2': /* start of right-to-left direction */
3159 coding
->mode
|= CODING_MODE_DIRECTION
;
3173 /* CTEXT extended segment:
3174 ESC % / [0-4] M L --ENCODING-NAME-- \002 --BYTES--
3175 We keep these bytes as is for the moment.
3176 They may be decoded by post-read-conversion. */
3180 ONE_MORE_BYTE (dim
);
3183 size
= ((M
- 128) * 128) + (L
- 128);
3184 if (charbuf
+ 8 + size
> charbuf_end
)
3186 *charbuf
++ = ISO_CODE_ESC
;
3190 *charbuf
++ = BYTE8_TO_CHAR (M
);
3191 *charbuf
++ = BYTE8_TO_CHAR (L
);
3195 *charbuf
++ = ASCII_BYTE_P (c1
) ? c1
: BYTE8_TO_CHAR (c1
);
3200 /* XFree86 extension for embedding UTF-8 in CTEXT:
3201 ESC % G --UTF-8-BYTES-- ESC % @
3202 We keep these bytes as is for the moment.
3203 They may be decoded by post-read-conversion. */
3206 if (p
+ 6 > charbuf_end
)
3208 *p
++ = ISO_CODE_ESC
;
3211 while (p
< charbuf_end
)
3214 if (c1
== ISO_CODE_ESC
3215 && src
+ 1 < src_end
3222 *p
++ = ASCII_BYTE_P (c1
) ? c1
: BYTE8_TO_CHAR (c1
);
3224 if (p
+ 3 > charbuf_end
)
3226 *p
++ = ISO_CODE_ESC
;
3237 if (! (CODING_ISO_FLAGS (coding
) & CODING_ISO_FLAG_DESIGNATION
))
3242 if (c1
>= 0x28 && c1
<= 0x2B)
3243 { /* designation of DIMENSION1_CHARS94 character set */
3244 reg
= c1
- 0x28, chars96
= 0;
3247 else if (c1
>= 0x2C && c1
<= 0x2F)
3248 { /* designation of DIMENSION1_CHARS96 character set */
3249 reg
= c1
- 0x2C, chars96
= 1;
3254 DECODE_DESIGNATION (reg
, 1, chars96
, c1
);
3255 /* We must update these variables now. */
3257 charset_id_0
= CODING_ISO_INVOKED_CHARSET (coding
, 0);
3259 charset_id_1
= CODING_ISO_INVOKED_CHARSET (coding
, 1);
3267 if (charset
->id
!= charset_ascii
3268 && last_id
!= charset
->id
)
3270 if (last_id
!= charset_ascii
)
3271 ADD_CHARSET_DATA (charbuf
, char_offset
- last_offset
, last_id
);
3272 last_id
= charset
->id
;
3273 last_offset
= char_offset
;
3276 /* Now we know CHARSET and 1st position code C1 of a character.
3277 Produce a decoded character while getting 2nd position code
3280 if (CHARSET_DIMENSION (charset
) > 1)
3283 if (c2
< 0x20 || (c2
>= 0x80 && c2
< 0xA0))
3284 /* C2 is not in a valid range. */
3286 c1
= (c1
<< 8) | (c2
& 0x7F);
3287 if (CHARSET_DIMENSION (charset
) > 2)
3290 if (c2
< 0x20 || (c2
>= 0x80 && c2
< 0xA0))
3291 /* C2 is not in a valid range. */
3293 c1
= (c1
<< 8) | (c2
& 0x7F);
3297 CODING_DECODE_CHAR (coding
, src
, src_base
, src_end
, charset
, c1
, c
);
3300 MAYBE_FINISH_COMPOSITION ();
3301 for (; src_base
< src
; src_base
++, char_offset
++)
3303 if (ASCII_BYTE_P (*src_base
))
3304 *charbuf
++ = *src_base
;
3306 *charbuf
++ = BYTE8_TO_CHAR (*src_base
);
3309 else if (composition_state
== COMPOSING_NO
)
3316 components
[component_idx
++] = c
;
3317 if (method
== COMPOSITION_WITH_RULE
3318 || (method
== COMPOSITION_WITH_RULE_ALTCHARS
3319 && composition_state
== COMPOSING_COMPONENT_CHAR
))
3320 composition_state
++;
3325 MAYBE_FINISH_COMPOSITION ();
3327 consumed_chars
= consumed_chars_base
;
3329 *charbuf
++ = c
< 0 ? -c
: ASCII_BYTE_P (c
) ? c
: BYTE8_TO_CHAR (c
);
3339 if (last_id
!= charset_ascii
)
3340 ADD_CHARSET_DATA (charbuf
, char_offset
- last_offset
, last_id
);
3341 coding
->consumed_char
+= consumed_chars_base
;
3342 coding
->consumed
= src_base
- coding
->source
;
3343 coding
->charbuf_used
= charbuf
- coding
->charbuf
;
3347 /* ISO2022 encoding stuff. */
3350 It is not enough to say just "ISO2022" on encoding, we have to
3351 specify more details. In Emacs, each coding system of ISO2022
3352 variant has the following specifications:
3353 1. Initial designation to G0 thru G3.
3354 2. Allows short-form designation?
3355 3. ASCII should be designated to G0 before control characters?
3356 4. ASCII should be designated to G0 at end of line?
3357 5. 7-bit environment or 8-bit environment?
3358 6. Use locking-shift?
3359 7. Use Single-shift?
3360 And the following two are only for Japanese:
3361 8. Use ASCII in place of JIS0201-1976-Roman?
3362 9. Use JISX0208-1983 in place of JISX0208-1978?
3363 These specifications are encoded in CODING_ISO_FLAGS (coding) as flag bits
3364 defined by macros CODING_ISO_FLAG_XXX. See `coding.h' for more
3368 /* Produce codes (escape sequence) for designating CHARSET to graphic
3369 register REG at DST, and increment DST. If <final-char> of CHARSET is
3370 '@', 'A', or 'B' and the coding system CODING allows, produce
3371 designation sequence of short-form. */
3373 #define ENCODE_DESIGNATION(charset, reg, coding) \
3375 unsigned char final_char = CHARSET_ISO_FINAL (charset); \
3376 char *intermediate_char_94 = "()*+"; \
3377 char *intermediate_char_96 = ",-./"; \
3378 int revision = -1; \
3381 if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_REVISION) \
3382 revision = CHARSET_ISO_REVISION (charset); \
3384 if (revision >= 0) \
3386 EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '&'); \
3387 EMIT_ONE_BYTE ('@' + revision); \
3389 EMIT_ONE_ASCII_BYTE (ISO_CODE_ESC); \
3390 if (CHARSET_DIMENSION (charset) == 1) \
3392 if (! CHARSET_ISO_CHARS_96 (charset)) \
3393 c = intermediate_char_94[reg]; \
3395 c = intermediate_char_96[reg]; \
3396 EMIT_ONE_ASCII_BYTE (c); \
3400 EMIT_ONE_ASCII_BYTE ('$'); \
3401 if (! CHARSET_ISO_CHARS_96 (charset)) \
3403 if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LONG_FORM \
3405 || final_char < '@' || final_char > 'B') \
3406 EMIT_ONE_ASCII_BYTE (intermediate_char_94[reg]); \
3409 EMIT_ONE_ASCII_BYTE (intermediate_char_96[reg]); \
3411 EMIT_ONE_ASCII_BYTE (final_char); \
3413 CODING_ISO_DESIGNATION (coding, reg) = CHARSET_ID (charset); \
3417 /* The following two macros produce codes (control character or escape
3418 sequence) for ISO2022 single-shift functions (single-shift-2 and
3421 #define ENCODE_SINGLE_SHIFT_2 \
3423 if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \
3424 EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'N'); \
3426 EMIT_ONE_BYTE (ISO_CODE_SS2); \
3427 CODING_ISO_SINGLE_SHIFTING (coding) = 1; \
3431 #define ENCODE_SINGLE_SHIFT_3 \
3433 if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \
3434 EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'O'); \
3436 EMIT_ONE_BYTE (ISO_CODE_SS3); \
3437 CODING_ISO_SINGLE_SHIFTING (coding) = 1; \
3441 /* The following four macros produce codes (control character or
3442 escape sequence) for ISO2022 locking-shift functions (shift-in,
3443 shift-out, locking-shift-2, and locking-shift-3). */
3445 #define ENCODE_SHIFT_IN \
3447 EMIT_ONE_ASCII_BYTE (ISO_CODE_SI); \
3448 CODING_ISO_INVOCATION (coding, 0) = 0; \
3452 #define ENCODE_SHIFT_OUT \
3454 EMIT_ONE_ASCII_BYTE (ISO_CODE_SO); \
3455 CODING_ISO_INVOCATION (coding, 0) = 1; \
3459 #define ENCODE_LOCKING_SHIFT_2 \
3461 EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \
3462 CODING_ISO_INVOCATION (coding, 0) = 2; \
3466 #define ENCODE_LOCKING_SHIFT_3 \
3468 EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \
3469 CODING_ISO_INVOCATION (coding, 0) = 3; \
3473 /* Produce codes for a DIMENSION1 character whose character set is
3474 CHARSET and whose position-code is C1. Designation and invocation
3475 sequences are also produced in advance if necessary. */
3477 #define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \
3479 int id = CHARSET_ID (charset); \
3481 if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \
3482 && id == charset_ascii) \
3484 id = charset_jisx0201_roman; \
3485 charset = CHARSET_FROM_ID (id); \
3488 if (CODING_ISO_SINGLE_SHIFTING (coding)) \
3490 if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \
3491 EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \
3493 EMIT_ONE_BYTE (c1 | 0x80); \
3494 CODING_ISO_SINGLE_SHIFTING (coding) = 0; \
3497 else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \
3499 EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \
3502 else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \
3504 EMIT_ONE_BYTE (c1 | 0x80); \
3508 /* Since CHARSET is not yet invoked to any graphic planes, we \
3509 must invoke it, or, at first, designate it to some graphic \
3510 register. Then repeat the loop to actually produce the \
3512 dst = encode_invocation_designation (charset, coding, dst, \
3517 /* Produce codes for a DIMENSION2 character whose character set is
3518 CHARSET and whose position-codes are C1 and C2. Designation and
3519 invocation codes are also produced in advance if necessary. */
3521 #define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \
3523 int id = CHARSET_ID (charset); \
3525 if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \
3526 && id == charset_jisx0208) \
3528 id = charset_jisx0208_1978; \
3529 charset = CHARSET_FROM_ID (id); \
3532 if (CODING_ISO_SINGLE_SHIFTING (coding)) \
3534 if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \
3535 EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \
3537 EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \
3538 CODING_ISO_SINGLE_SHIFTING (coding) = 0; \
3541 else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \
3543 EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \
3546 else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \
3548 EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \
3552 /* Since CHARSET is not yet invoked to any graphic planes, we \
3553 must invoke it, or, at first, designate it to some graphic \
3554 register. Then repeat the loop to actually produce the \
3556 dst = encode_invocation_designation (charset, coding, dst, \
3561 #define ENCODE_ISO_CHARACTER(charset, c) \
3563 int code = ENCODE_CHAR ((charset),(c)); \
3565 if (CHARSET_DIMENSION (charset) == 1) \
3566 ENCODE_ISO_CHARACTER_DIMENSION1 ((charset), code); \
3568 ENCODE_ISO_CHARACTER_DIMENSION2 ((charset), code >> 8, code & 0xFF); \
3572 /* Produce designation and invocation codes at a place pointed by DST
3573 to use CHARSET. The element `spec.iso_2022' of *CODING is updated.
3577 encode_invocation_designation (charset
, coding
, dst
, p_nchars
)
3578 struct charset
*charset
;
3579 struct coding_system
*coding
;
3583 int multibytep
= coding
->dst_multibyte
;
3584 int produced_chars
= *p_nchars
;
3585 int reg
; /* graphic register number */
3586 int id
= CHARSET_ID (charset
);
3588 /* At first, check designations. */
3589 for (reg
= 0; reg
< 4; reg
++)
3590 if (id
== CODING_ISO_DESIGNATION (coding
, reg
))
3595 /* CHARSET is not yet designated to any graphic registers. */
3596 /* At first check the requested designation. */
3597 reg
= CODING_ISO_REQUEST (coding
, id
);
3599 /* Since CHARSET requests no special designation, designate it
3600 to graphic register 0. */
3603 ENCODE_DESIGNATION (charset
, reg
, coding
);
3606 if (CODING_ISO_INVOCATION (coding
, 0) != reg
3607 && CODING_ISO_INVOCATION (coding
, 1) != reg
)
3609 /* Since the graphic register REG is not invoked to any graphic
3610 planes, invoke it to graphic plane 0. */
3613 case 0: /* graphic register 0 */
3617 case 1: /* graphic register 1 */
3621 case 2: /* graphic register 2 */
3622 if (CODING_ISO_FLAGS (coding
) & CODING_ISO_FLAG_SINGLE_SHIFT
)
3623 ENCODE_SINGLE_SHIFT_2
;
3625 ENCODE_LOCKING_SHIFT_2
;
3628 case 3: /* graphic register 3 */
3629 if (CODING_ISO_FLAGS (coding
) & CODING_ISO_FLAG_SINGLE_SHIFT
)
3630 ENCODE_SINGLE_SHIFT_3
;
3632 ENCODE_LOCKING_SHIFT_3
;
3637 *p_nchars
= produced_chars
;
3641 /* The following three macros produce codes for indicating direction
3643 #define ENCODE_CONTROL_SEQUENCE_INTRODUCER \
3645 if (CODING_ISO_FLAGS (coding) == CODING_ISO_FLAG_SEVEN_BITS) \
3646 EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '['); \
3648 EMIT_ONE_BYTE (ISO_CODE_CSI); \
3652 #define ENCODE_DIRECTION_R2L() \
3654 ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \
3655 EMIT_TWO_ASCII_BYTES ('2', ']'); \
3659 #define ENCODE_DIRECTION_L2R() \
3661 ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \
3662 EMIT_TWO_ASCII_BYTES ('0', ']'); \
3666 /* Produce codes for designation and invocation to reset the graphic
3667 planes and registers to initial state. */
3668 #define ENCODE_RESET_PLANE_AND_REGISTER() \
3671 struct charset *charset; \
3673 if (CODING_ISO_INVOCATION (coding, 0) != 0) \
3675 for (reg = 0; reg < 4; reg++) \
3676 if (CODING_ISO_INITIAL (coding, reg) >= 0 \
3677 && (CODING_ISO_DESIGNATION (coding, reg) \
3678 != CODING_ISO_INITIAL (coding, reg))) \
3680 charset = CHARSET_FROM_ID (CODING_ISO_INITIAL (coding, reg)); \
3681 ENCODE_DESIGNATION (charset, reg, coding); \
3686 /* Produce designation sequences of charsets in the line started from
3687 SRC to a place pointed by DST, and return updated DST.
3689 If the current block ends before any end-of-line, we may fail to
3690 find all the necessary designations. */
3692 static unsigned char *
3693 encode_designation_at_bol (coding
, charbuf
, charbuf_end
, dst
)
3694 struct coding_system
*coding
;
3695 int *charbuf
, *charbuf_end
;
3698 struct charset
*charset
;
3699 /* Table of charsets to be designated to each graphic register. */
3701 int c
, found
= 0, reg
;
3702 int produced_chars
= 0;
3703 int multibytep
= coding
->dst_multibyte
;
3705 Lisp_Object charset_list
;
3707 attrs
= CODING_ID_ATTRS (coding
->id
);
3708 charset_list
= CODING_ATTR_CHARSET_LIST (attrs
);
3709 if (EQ (charset_list
, Qiso_2022
))
3710 charset_list
= Viso_2022_charset_list
;
3712 for (reg
= 0; reg
< 4; reg
++)
3722 charset
= char_charset (c
, charset_list
, NULL
);
3723 id
= CHARSET_ID (charset
);
3724 reg
= CODING_ISO_REQUEST (coding
, id
);
3725 if (reg
>= 0 && r
[reg
] < 0)
3734 for (reg
= 0; reg
< 4; reg
++)
3736 && CODING_ISO_DESIGNATION (coding
, reg
) != r
[reg
])
3737 ENCODE_DESIGNATION (CHARSET_FROM_ID (r
[reg
]), reg
, coding
);
3743 /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */
3746 encode_coding_iso_2022 (coding
)
3747 struct coding_system
*coding
;
3749 int multibytep
= coding
->dst_multibyte
;
3750 int *charbuf
= coding
->charbuf
;
3751 int *charbuf_end
= charbuf
+ coding
->charbuf_used
;
3752 unsigned char *dst
= coding
->destination
+ coding
->produced
;
3753 unsigned char *dst_end
= coding
->destination
+ coding
->dst_bytes
;
3756 = (CODING_ISO_FLAGS (coding
) & CODING_ISO_FLAG_DESIGNATE_AT_BOL
3757 && CODING_ISO_BOL (coding
));
3758 int produced_chars
= 0;
3759 Lisp_Object attrs
, eol_type
, charset_list
;
3760 int ascii_compatible
;
3762 int preferred_charset_id
= -1;
3764 CODING_GET_INFO (coding
, attrs
, charset_list
);
3765 eol_type
= CODING_ID_EOL_TYPE (coding
->id
);
3766 if (VECTORP (eol_type
))
3769 setup_iso_safe_charsets (attrs
);
3770 /* Charset list may have been changed. */
3771 charset_list
= CODING_ATTR_CHARSET_LIST (attrs
); \
3772 coding
->safe_charsets
= (char *) SDATA (CODING_ATTR_SAFE_CHARSETS(attrs
));
3774 ascii_compatible
= ! NILP (CODING_ATTR_ASCII_COMPAT (attrs
));
3776 while (charbuf
< charbuf_end
)
3778 ASSURE_DESTINATION (safe_room
);
3780 if (bol_designation
)
3782 unsigned char *dst_prev
= dst
;
3784 /* We have to produce designation sequences if any now. */
3785 dst
= encode_designation_at_bol (coding
, charbuf
, charbuf_end
, dst
);
3786 bol_designation
= 0;
3787 /* We are sure that designation sequences are all ASCII bytes. */
3788 produced_chars
+= dst
- dst_prev
;
3795 /* Handle an annotation. */
3798 case CODING_ANNOTATE_COMPOSITION_MASK
:
3799 /* Not yet implemented. */
3801 case CODING_ANNOTATE_CHARSET_MASK
:
3802 preferred_charset_id
= charbuf
[2];
3803 if (preferred_charset_id
>= 0
3804 && NILP (Fmemq (make_number (preferred_charset_id
),
3806 preferred_charset_id
= -1;
3815 /* Now encode the character C. */
3816 if (c
< 0x20 || c
== 0x7F)
3819 || (c
== '\r' && EQ (eol_type
, Qmac
)))
3821 if (CODING_ISO_FLAGS (coding
) & CODING_ISO_FLAG_RESET_AT_EOL
)
3822 ENCODE_RESET_PLANE_AND_REGISTER ();
3823 if (CODING_ISO_FLAGS (coding
) & CODING_ISO_FLAG_INIT_AT_BOL
)
3827 for (i
= 0; i
< 4; i
++)
3828 CODING_ISO_DESIGNATION (coding
, i
)
3829 = CODING_ISO_INITIAL (coding
, i
);
3832 = CODING_ISO_FLAGS (coding
) & CODING_ISO_FLAG_DESIGNATE_AT_BOL
;
3834 else if (CODING_ISO_FLAGS (coding
) & CODING_ISO_FLAG_RESET_AT_CNTL
)
3835 ENCODE_RESET_PLANE_AND_REGISTER ();
3836 EMIT_ONE_ASCII_BYTE (c
);
3838 else if (ASCII_CHAR_P (c
))
3840 if (ascii_compatible
)
3841 EMIT_ONE_ASCII_BYTE (c
);
3844 struct charset
*charset
= CHARSET_FROM_ID (charset_ascii
);
3845 ENCODE_ISO_CHARACTER (charset
, c
);
3848 else if (CHAR_BYTE8_P (c
))
3850 c
= CHAR_TO_BYTE8 (c
);
3855 struct charset
*charset
;
3857 if (preferred_charset_id
>= 0)
3859 charset
= CHARSET_FROM_ID (preferred_charset_id
);
3860 if (! CHAR_CHARSET_P (c
, charset
))
3861 charset
= char_charset (c
, charset_list
, NULL
);
3864 charset
= char_charset (c
, charset_list
, NULL
);
3867 if (coding
->mode
& CODING_MODE_SAFE_ENCODING
)
3869 c
= CODING_INHIBIT_CHARACTER_SUBSTITUTION
;
3870 charset
= CHARSET_FROM_ID (charset_ascii
);
3874 c
= coding
->default_char
;
3875 charset
= char_charset (c
, charset_list
, NULL
);
3878 ENCODE_ISO_CHARACTER (charset
, c
);
3882 if (coding
->mode
& CODING_MODE_LAST_BLOCK
3883 && CODING_ISO_FLAGS (coding
) & CODING_ISO_FLAG_RESET_AT_EOL
)
3885 ASSURE_DESTINATION (safe_room
);
3886 ENCODE_RESET_PLANE_AND_REGISTER ();
3888 record_conversion_result (coding
, CODING_RESULT_SUCCESS
);
3889 CODING_ISO_BOL (coding
) = bol_designation
;
3890 coding
->produced_char
+= produced_chars
;
3891 coding
->produced
= dst
- coding
->destination
;
3896 /*** 8,9. SJIS and BIG5 handlers ***/
3898 /* Although SJIS and BIG5 are not ISO's coding system, they are used
3899 quite widely. So, for the moment, Emacs supports them in the bare
3900 C code. But, in the future, they may be supported only by CCL. */
3902 /* SJIS is a coding system encoding three character sets: ASCII, right
3903 half of JISX0201-Kana, and JISX0208. An ASCII character is encoded
3904 as is. A character of charset katakana-jisx0201 is encoded by
3905 "position-code + 0x80". A character of charset japanese-jisx0208
3906 is encoded in 2-byte but two position-codes are divided and shifted
3907 so that it fit in the range below.
3909 --- CODE RANGE of SJIS ---
3910 (character set) (range)
3912 KATAKANA-JISX0201 0xA0 .. 0xDF
3913 JISX0208 (1st byte) 0x81 .. 0x9F and 0xE0 .. 0xEF
3914 (2nd byte) 0x40 .. 0x7E and 0x80 .. 0xFC
3915 -------------------------------
3919 /* BIG5 is a coding system encoding two character sets: ASCII and
3920 Big5. An ASCII character is encoded as is. Big5 is a two-byte
3921 character set and is encoded in two-byte.
3923 --- CODE RANGE of BIG5 ---
3924 (character set) (range)
3926 Big5 (1st byte) 0xA1 .. 0xFE
3927 (2nd byte) 0x40 .. 0x7E and 0xA1 .. 0xFE
3928 --------------------------
3932 /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
3933 Check if a text is encoded in SJIS. If it is, return
3934 CATEGORY_MASK_SJIS, else return 0. */
3937 detect_coding_sjis (coding
, detect_info
)
3938 struct coding_system
*coding
;
3939 struct coding_detection_info
*detect_info
;
3941 const unsigned char *src
= coding
->source
, *src_base
;
3942 const unsigned char *src_end
= coding
->source
+ coding
->src_bytes
;
3943 int multibytep
= coding
->src_multibyte
;
3944 int consumed_chars
= 0;
3948 detect_info
->checked
|= CATEGORY_MASK_SJIS
;
3949 /* A coding system of this category is always ASCII compatible. */
3950 src
+= coding
->head_ascii
;
3958 if ((c
>= 0x81 && c
<= 0x9F) || (c
>= 0xE0 && c
<= 0xEF))
3961 if (c
< 0x40 || c
== 0x7F || c
> 0xFC)
3963 found
= CATEGORY_MASK_SJIS
;
3965 else if (c
>= 0xA0 && c
< 0xE0)
3966 found
= CATEGORY_MASK_SJIS
;
3970 detect_info
->rejected
|= CATEGORY_MASK_SJIS
;
3974 if (src_base
< src
&& coding
->mode
& CODING_MODE_LAST_BLOCK
)
3976 detect_info
->rejected
|= CATEGORY_MASK_SJIS
;
3979 detect_info
->found
|= found
;
3983 /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
3984 Check if a text is encoded in BIG5. If it is, return
3985 CATEGORY_MASK_BIG5, else return 0. */
3988 detect_coding_big5 (coding
, detect_info
)
3989 struct coding_system
*coding
;
3990 struct coding_detection_info
*detect_info
;
3992 const unsigned char *src
= coding
->source
, *src_base
;
3993 const unsigned char *src_end
= coding
->source
+ coding
->src_bytes
;
3994 int multibytep
= coding
->src_multibyte
;
3995 int consumed_chars
= 0;
3999 detect_info
->checked
|= CATEGORY_MASK_BIG5
;
4000 /* A coding system of this category is always ASCII compatible. */
4001 src
+= coding
->head_ascii
;
4012 if (c
< 0x40 || (c
>= 0x7F && c
<= 0xA0))
4014 found
= CATEGORY_MASK_BIG5
;
4019 detect_info
->rejected
|= CATEGORY_MASK_BIG5
;
4023 if (src_base
< src
&& coding
->mode
& CODING_MODE_LAST_BLOCK
)
4025 detect_info
->rejected
|= CATEGORY_MASK_BIG5
;
4028 detect_info
->found
|= found
;
4032 /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions".
4033 If SJIS_P is 1, decode SJIS text, else decode BIG5 test. */
4036 decode_coding_sjis (coding
)
4037 struct coding_system
*coding
;
4039 const unsigned char *src
= coding
->source
+ coding
->consumed
;
4040 const unsigned char *src_end
= coding
->source
+ coding
->src_bytes
;
4041 const unsigned char *src_base
;
4042 int *charbuf
= coding
->charbuf
+ coding
->charbuf_used
;
4044 = coding
->charbuf
+ coding
->charbuf_size
- MAX_ANNOTATION_LENGTH
;
4045 int consumed_chars
= 0, consumed_chars_base
;
4046 int multibytep
= coding
->src_multibyte
;
4047 struct charset
*charset_roman
, *charset_kanji
, *charset_kana
;
4048 struct charset
*charset_kanji2
;
4049 Lisp_Object attrs
, charset_list
, val
;
4050 int char_offset
= coding
->produced_char
;
4051 int last_offset
= char_offset
;
4052 int last_id
= charset_ascii
;
4054 CODING_GET_INFO (coding
, attrs
, charset_list
);
4057 charset_roman
= CHARSET_FROM_ID (XINT (XCAR (val
))), val
= XCDR (val
);
4058 charset_kana
= CHARSET_FROM_ID (XINT (XCAR (val
))), val
= XCDR (val
);
4059 charset_kanji
= CHARSET_FROM_ID (XINT (XCAR (val
))), val
= XCDR (val
);
4060 charset_kanji2
= NILP (val
) ? NULL
: CHARSET_FROM_ID (XINT (XCAR (val
)));
4065 struct charset
*charset
;
4068 consumed_chars_base
= consumed_chars
;
4070 if (charbuf
>= charbuf_end
)
4077 charset
= charset_roman
;
4078 else if (c
== 0x80 || c
== 0xA0)
4080 else if (c
>= 0xA1 && c
<= 0xDF)
4082 /* SJIS -> JISX0201-Kana */
4084 charset
= charset_kana
;
4088 /* SJIS -> JISX0208 */
4090 if (c1
< 0x40 || c1
== 0x7F || c1
> 0xFC)
4094 charset
= charset_kanji
;
4096 else if (c
<= 0xFC && charset_kanji2
)
4098 /* SJIS -> JISX0213-2 */
4100 if (c1
< 0x40 || c1
== 0x7F || c1
> 0xFC)
4104 charset
= charset_kanji2
;
4108 if (charset
->id
!= charset_ascii
4109 && last_id
!= charset
->id
)
4111 if (last_id
!= charset_ascii
)
4112 ADD_CHARSET_DATA (charbuf
, char_offset
- last_offset
, last_id
);
4113 last_id
= charset
->id
;
4114 last_offset
= char_offset
;
4116 CODING_DECODE_CHAR (coding
, src
, src_base
, src_end
, charset
, c
, c
);
4123 consumed_chars
= consumed_chars_base
;
4125 *charbuf
++ = c
< 0 ? -c
: BYTE8_TO_CHAR (c
);
4131 if (last_id
!= charset_ascii
)
4132 ADD_CHARSET_DATA (charbuf
, char_offset
- last_offset
, last_id
);
4133 coding
->consumed_char
+= consumed_chars_base
;
4134 coding
->consumed
= src_base
- coding
->source
;
4135 coding
->charbuf_used
= charbuf
- coding
->charbuf
;
4139 decode_coding_big5 (coding
)
4140 struct coding_system
*coding
;
4142 const unsigned char *src
= coding
->source
+ coding
->consumed
;
4143 const unsigned char *src_end
= coding
->source
+ coding
->src_bytes
;
4144 const unsigned char *src_base
;
4145 int *charbuf
= coding
->charbuf
+ coding
->charbuf_used
;
4147 = coding
->charbuf
+ coding
->charbuf_size
- MAX_ANNOTATION_LENGTH
;
4148 int consumed_chars
= 0, consumed_chars_base
;
4149 int multibytep
= coding
->src_multibyte
;
4150 struct charset
*charset_roman
, *charset_big5
;
4151 Lisp_Object attrs
, charset_list
, val
;
4152 int char_offset
= coding
->produced_char
;
4153 int last_offset
= char_offset
;
4154 int last_id
= charset_ascii
;
4156 CODING_GET_INFO (coding
, attrs
, charset_list
);
4158 charset_roman
= CHARSET_FROM_ID (XINT (XCAR (val
))), val
= XCDR (val
);
4159 charset_big5
= CHARSET_FROM_ID (XINT (XCAR (val
)));
4164 struct charset
*charset
;
4167 consumed_chars_base
= consumed_chars
;
4169 if (charbuf
>= charbuf_end
)
4177 charset
= charset_roman
;
4181 if (c
< 0xA1 || c
> 0xFE)
4184 if (c1
< 0x40 || (c1
> 0x7E && c1
< 0xA1) || c1
> 0xFE)
4187 charset
= charset_big5
;
4189 if (charset
->id
!= charset_ascii
4190 && last_id
!= charset
->id
)
4192 if (last_id
!= charset_ascii
)
4193 ADD_CHARSET_DATA (charbuf
, char_offset
- last_offset
, last_id
);
4194 last_id
= charset
->id
;
4195 last_offset
= char_offset
;
4197 CODING_DECODE_CHAR (coding
, src
, src_base
, src_end
, charset
, c
, c
);
4204 consumed_chars
= consumed_chars_base
;
4206 *charbuf
++ = c
< 0 ? -c
: BYTE8_TO_CHAR (c
);
4212 if (last_id
!= charset_ascii
)
4213 ADD_CHARSET_DATA (charbuf
, char_offset
- last_offset
, last_id
);
4214 coding
->consumed_char
+= consumed_chars_base
;
4215 coding
->consumed
= src_base
- coding
->source
;
4216 coding
->charbuf_used
= charbuf
- coding
->charbuf
;
4219 /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions".
4220 This function can encode charsets `ascii', `katakana-jisx0201',
4221 `japanese-jisx0208', `chinese-big5-1', and `chinese-big5-2'. We
4222 are sure that all these charsets are registered as official charset
4223 (i.e. do not have extended leading-codes). Characters of other
4224 charsets are produced without any encoding. If SJIS_P is 1, encode
4225 SJIS text, else encode BIG5 text. */
4228 encode_coding_sjis (coding
)
4229 struct coding_system
*coding
;
4231 int multibytep
= coding
->dst_multibyte
;
4232 int *charbuf
= coding
->charbuf
;
4233 int *charbuf_end
= charbuf
+ coding
->charbuf_used
;
4234 unsigned char *dst
= coding
->destination
+ coding
->produced
;
4235 unsigned char *dst_end
= coding
->destination
+ coding
->dst_bytes
;
4237 int produced_chars
= 0;
4238 Lisp_Object attrs
, charset_list
, val
;
4239 int ascii_compatible
;
4240 struct charset
*charset_roman
, *charset_kanji
, *charset_kana
;
4241 struct charset
*charset_kanji2
;
4244 CODING_GET_INFO (coding
, attrs
, charset_list
);
4246 charset_roman
= CHARSET_FROM_ID (XINT (XCAR (val
))), val
= XCDR (val
);
4247 charset_kana
= CHARSET_FROM_ID (XINT (XCAR (val
))), val
= XCDR (val
);
4248 charset_kanji
= CHARSET_FROM_ID (XINT (XCAR (val
))), val
= XCDR (val
);
4249 charset_kanji2
= NILP (val
) ? NULL
: CHARSET_FROM_ID (XINT (XCAR (val
)));
4251 ascii_compatible
= ! NILP (CODING_ATTR_ASCII_COMPAT (attrs
));
4253 while (charbuf
< charbuf_end
)
4255 ASSURE_DESTINATION (safe_room
);
4257 /* Now encode the character C. */
4258 if (ASCII_CHAR_P (c
) && ascii_compatible
)
4259 EMIT_ONE_ASCII_BYTE (c
);
4260 else if (CHAR_BYTE8_P (c
))
4262 c
= CHAR_TO_BYTE8 (c
);
4268 struct charset
*charset
= char_charset (c
, charset_list
, &code
);
4272 if (coding
->mode
& CODING_MODE_SAFE_ENCODING
)
4274 code
= CODING_INHIBIT_CHARACTER_SUBSTITUTION
;
4275 charset
= CHARSET_FROM_ID (charset_ascii
);
4279 c
= coding
->default_char
;
4280 charset
= char_charset (c
, charset_list
, &code
);
4283 if (code
== CHARSET_INVALID_CODE (charset
))
4285 if (charset
== charset_kanji
)
4289 c1
= code
>> 8, c2
= code
& 0xFF;
4290 EMIT_TWO_BYTES (c1
, c2
);
4292 else if (charset
== charset_kana
)
4293 EMIT_ONE_BYTE (code
| 0x80);
4294 else if (charset_kanji2
&& charset
== charset_kanji2
)
4299 if (c1
== 0x21 || (c1
>= 0x23 && c1
< 0x25)
4300 || (c1
>= 0x2C && c1
<= 0x2F) || c1
>= 0x6E)
4302 JIS_TO_SJIS2 (code
);
4303 c1
= code
>> 8, c2
= code
& 0xFF;
4304 EMIT_TWO_BYTES (c1
, c2
);
4307 EMIT_ONE_ASCII_BYTE (code
& 0x7F);
4310 EMIT_ONE_ASCII_BYTE (code
& 0x7F);
4313 record_conversion_result (coding
, CODING_RESULT_SUCCESS
);
4314 coding
->produced_char
+= produced_chars
;
4315 coding
->produced
= dst
- coding
->destination
;
4320 encode_coding_big5 (coding
)
4321 struct coding_system
*coding
;
4323 int multibytep
= coding
->dst_multibyte
;
4324 int *charbuf
= coding
->charbuf
;
4325 int *charbuf_end
= charbuf
+ coding
->charbuf_used
;
4326 unsigned char *dst
= coding
->destination
+ coding
->produced
;
4327 unsigned char *dst_end
= coding
->destination
+ coding
->dst_bytes
;
4329 int produced_chars
= 0;
4330 Lisp_Object attrs
, charset_list
, val
;
4331 int ascii_compatible
;
4332 struct charset
*charset_roman
, *charset_big5
;
4335 CODING_GET_INFO (coding
, attrs
, charset_list
);
4337 charset_roman
= CHARSET_FROM_ID (XINT (XCAR (val
))), val
= XCDR (val
);
4338 charset_big5
= CHARSET_FROM_ID (XINT (XCAR (val
)));
4339 ascii_compatible
= ! NILP (CODING_ATTR_ASCII_COMPAT (attrs
));
4341 while (charbuf
< charbuf_end
)
4343 ASSURE_DESTINATION (safe_room
);
4345 /* Now encode the character C. */
4346 if (ASCII_CHAR_P (c
) && ascii_compatible
)
4347 EMIT_ONE_ASCII_BYTE (c
);
4348 else if (CHAR_BYTE8_P (c
))
4350 c
= CHAR_TO_BYTE8 (c
);
4356 struct charset
*charset
= char_charset (c
, charset_list
, &code
);
4360 if (coding
->mode
& CODING_MODE_SAFE_ENCODING
)
4362 code
= CODING_INHIBIT_CHARACTER_SUBSTITUTION
;
4363 charset
= CHARSET_FROM_ID (charset_ascii
);
4367 c
= coding
->default_char
;
4368 charset
= char_charset (c
, charset_list
, &code
);
4371 if (code
== CHARSET_INVALID_CODE (charset
))
4373 if (charset
== charset_big5
)
4377 c1
= code
>> 8, c2
= code
& 0xFF;
4378 EMIT_TWO_BYTES (c1
, c2
);
4381 EMIT_ONE_ASCII_BYTE (code
& 0x7F);
4384 record_conversion_result (coding
, CODING_RESULT_SUCCESS
);
4385 coding
->produced_char
+= produced_chars
;
4386 coding
->produced
= dst
- coding
->destination
;
4391 /*** 10. CCL handlers ***/
4393 /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
4394 Check if a text is encoded in a coding system of which
4395 encoder/decoder are written in CCL program. If it is, return
4396 CATEGORY_MASK_CCL, else return 0. */
4399 detect_coding_ccl (coding
, detect_info
)
4400 struct coding_system
*coding
;
4401 struct coding_detection_info
*detect_info
;
4403 const unsigned char *src
= coding
->source
, *src_base
;
4404 const unsigned char *src_end
= coding
->source
+ coding
->src_bytes
;
4405 int multibytep
= coding
->src_multibyte
;
4406 int consumed_chars
= 0;
4408 unsigned char *valids
;
4409 int head_ascii
= coding
->head_ascii
;
4412 detect_info
->checked
|= CATEGORY_MASK_CCL
;
4414 coding
= &coding_categories
[coding_category_ccl
];
4415 valids
= CODING_CCL_VALIDS (coding
);
4416 attrs
= CODING_ID_ATTRS (coding
->id
);
4417 if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs
)))
4426 if (c
< 0 || ! valids
[c
])
4428 if ((valids
[c
] > 1))
4429 found
= CATEGORY_MASK_CCL
;
4431 detect_info
->rejected
|= CATEGORY_MASK_CCL
;
4435 detect_info
->found
|= found
;
4440 decode_coding_ccl (coding
)
4441 struct coding_system
*coding
;
4443 const unsigned char *src
= coding
->source
+ coding
->consumed
;
4444 const unsigned char *src_end
= coding
->source
+ coding
->src_bytes
;
4445 int *charbuf
= coding
->charbuf
+ coding
->charbuf_used
;
4446 int *charbuf_end
= coding
->charbuf
+ coding
->charbuf_size
;
4447 int consumed_chars
= 0;
4448 int multibytep
= coding
->src_multibyte
;
4449 struct ccl_program ccl
;
4450 int source_charbuf
[1024];
4451 int source_byteidx
[1024];
4452 Lisp_Object attrs
, charset_list
;
4454 CODING_GET_INFO (coding
, attrs
, charset_list
);
4455 setup_ccl_program (&ccl
, CODING_CCL_DECODER (coding
));
4457 while (src
< src_end
)
4459 const unsigned char *p
= src
;
4460 int *source
, *source_end
;
4464 while (i
< 1024 && p
< src_end
)
4466 source_byteidx
[i
] = p
- src
;
4467 source_charbuf
[i
++] = STRING_CHAR_ADVANCE (p
);
4470 while (i
< 1024 && p
< src_end
)
4471 source_charbuf
[i
++] = *p
++;
4473 if (p
== src_end
&& coding
->mode
& CODING_MODE_LAST_BLOCK
)
4476 source
= source_charbuf
;
4477 source_end
= source
+ i
;
4478 while (source
< source_end
)
4480 ccl_driver (&ccl
, source
, charbuf
,
4481 source_end
- source
, charbuf_end
- charbuf
,
4483 source
+= ccl
.consumed
;
4484 charbuf
+= ccl
.produced
;
4485 if (ccl
.status
!= CCL_STAT_SUSPEND_BY_DST
)
4488 if (source
< source_end
)
4489 src
+= source_byteidx
[source
- source_charbuf
];
4492 consumed_chars
+= source
- source_charbuf
;
4494 if (ccl
.status
!= CCL_STAT_SUSPEND_BY_SRC
4495 && ccl
.status
!= CODING_RESULT_INSUFFICIENT_SRC
)
4501 case CCL_STAT_SUSPEND_BY_SRC
:
4502 record_conversion_result (coding
, CODING_RESULT_INSUFFICIENT_SRC
);
4504 case CCL_STAT_SUSPEND_BY_DST
:
4507 case CCL_STAT_INVALID_CMD
:
4508 record_conversion_result (coding
, CODING_RESULT_INTERRUPT
);
4511 record_conversion_result (coding
, CODING_RESULT_SUCCESS
);
4514 coding
->consumed_char
+= consumed_chars
;
4515 coding
->consumed
= src
- coding
->source
;
4516 coding
->charbuf_used
= charbuf
- coding
->charbuf
;
4520 encode_coding_ccl (coding
)
4521 struct coding_system
*coding
;
4523 struct ccl_program ccl
;
4524 int multibytep
= coding
->dst_multibyte
;
4525 int *charbuf
= coding
->charbuf
;
4526 int *charbuf_end
= charbuf
+ coding
->charbuf_used
;
4527 unsigned char *dst
= coding
->destination
+ coding
->produced
;
4528 unsigned char *dst_end
= coding
->destination
+ coding
->dst_bytes
;
4529 unsigned char *adjusted_dst_end
= dst_end
- 1;
4530 int destination_charbuf
[1024];
4531 int i
, produced_chars
= 0;
4532 Lisp_Object attrs
, charset_list
;
4534 CODING_GET_INFO (coding
, attrs
, charset_list
);
4535 setup_ccl_program (&ccl
, CODING_CCL_ENCODER (coding
));
4537 ccl
.last_block
= coding
->mode
& CODING_MODE_LAST_BLOCK
;
4538 ccl
.dst_multibyte
= coding
->dst_multibyte
;
4540 while (charbuf
< charbuf_end
&& dst
< adjusted_dst_end
)
4542 int dst_bytes
= dst_end
- dst
;
4543 if (dst_bytes
> 1024)
4546 ccl_driver (&ccl
, charbuf
, destination_charbuf
,
4547 charbuf_end
- charbuf
, dst_bytes
, charset_list
);
4548 charbuf
+= ccl
.consumed
;
4550 for (i
= 0; i
< ccl
.produced
; i
++)
4551 EMIT_ONE_BYTE (destination_charbuf
[i
] & 0xFF);
4554 for (i
= 0; i
< ccl
.produced
; i
++)
4555 *dst
++ = destination_charbuf
[i
] & 0xFF;
4556 produced_chars
+= ccl
.produced
;
4562 case CCL_STAT_SUSPEND_BY_SRC
:
4563 record_conversion_result (coding
, CODING_RESULT_INSUFFICIENT_SRC
);
4565 case CCL_STAT_SUSPEND_BY_DST
:
4566 record_conversion_result (coding
, CODING_RESULT_INSUFFICIENT_DST
);
4569 case CCL_STAT_INVALID_CMD
:
4570 record_conversion_result (coding
, CODING_RESULT_INTERRUPT
);
4573 record_conversion_result (coding
, CODING_RESULT_SUCCESS
);
4577 coding
->produced_char
+= produced_chars
;
4578 coding
->produced
= dst
- coding
->destination
;
4584 /*** 10, 11. no-conversion handlers ***/
4586 /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */
4589 decode_coding_raw_text (coding
)
4590 struct coding_system
*coding
;
4592 coding
->chars_at_source
= 1;
4593 coding
->consumed_char
= 0;
4594 coding
->consumed
= 0;
4595 record_conversion_result (coding
, CODING_RESULT_SUCCESS
);
4599 encode_coding_raw_text (coding
)
4600 struct coding_system
*coding
;
4602 int multibytep
= coding
->dst_multibyte
;
4603 int *charbuf
= coding
->charbuf
;
4604 int *charbuf_end
= coding
->charbuf
+ coding
->charbuf_used
;
4605 unsigned char *dst
= coding
->destination
+ coding
->produced
;
4606 unsigned char *dst_end
= coding
->destination
+ coding
->dst_bytes
;
4607 int produced_chars
= 0;
4612 int safe_room
= MAX_MULTIBYTE_LENGTH
* 2;
4614 if (coding
->src_multibyte
)
4615 while (charbuf
< charbuf_end
)
4617 ASSURE_DESTINATION (safe_room
);
4619 if (ASCII_CHAR_P (c
))
4620 EMIT_ONE_ASCII_BYTE (c
);
4621 else if (CHAR_BYTE8_P (c
))
4623 c
= CHAR_TO_BYTE8 (c
);
4628 unsigned char str
[MAX_MULTIBYTE_LENGTH
], *p0
= str
, *p1
= str
;
4630 CHAR_STRING_ADVANCE (c
, p1
);
4633 EMIT_ONE_BYTE (*p0
);
4639 while (charbuf
< charbuf_end
)
4641 ASSURE_DESTINATION (safe_room
);
4648 if (coding
->src_multibyte
)
4650 int safe_room
= MAX_MULTIBYTE_LENGTH
;
4652 while (charbuf
< charbuf_end
)
4654 ASSURE_DESTINATION (safe_room
);
4656 if (ASCII_CHAR_P (c
))
4658 else if (CHAR_BYTE8_P (c
))
4659 *dst
++ = CHAR_TO_BYTE8 (c
);
4661 CHAR_STRING_ADVANCE (c
, dst
);
4667 ASSURE_DESTINATION (charbuf_end
- charbuf
);
4668 while (charbuf
< charbuf_end
&& dst
< dst_end
)
4669 *dst
++ = *charbuf
++;
4670 produced_chars
= dst
- (coding
->destination
+ coding
->dst_bytes
);
4673 record_conversion_result (coding
, CODING_RESULT_SUCCESS
);
4674 coding
->produced_char
+= produced_chars
;
4675 coding
->produced
= dst
- coding
->destination
;
4679 /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
4680 Check if a text is encoded in a charset-based coding system. If it
4681 is, return 1, else return 0. */
4684 detect_coding_charset (coding
, detect_info
)
4685 struct coding_system
*coding
;
4686 struct coding_detection_info
*detect_info
;
4688 const unsigned char *src
= coding
->source
, *src_base
;
4689 const unsigned char *src_end
= coding
->source
+ coding
->src_bytes
;
4690 int multibytep
= coding
->src_multibyte
;
4691 int consumed_chars
= 0;
4692 Lisp_Object attrs
, valids
;
4695 detect_info
->checked
|= CATEGORY_MASK_CHARSET
;
4697 coding
= &coding_categories
[coding_category_charset
];
4698 attrs
= CODING_ID_ATTRS (coding
->id
);
4699 valids
= AREF (attrs
, coding_attr_charset_valids
);
4701 if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs
)))
4702 src
+= coding
->head_ascii
;
4712 if (NILP (AREF (valids
, c
)))
4715 found
= CATEGORY_MASK_CHARSET
;
4717 detect_info
->rejected
|= CATEGORY_MASK_CHARSET
;
4721 detect_info
->found
|= found
;
4726 decode_coding_charset (coding
)
4727 struct coding_system
*coding
;
4729 const unsigned char *src
= coding
->source
+ coding
->consumed
;
4730 const unsigned char *src_end
= coding
->source
+ coding
->src_bytes
;
4731 const unsigned char *src_base
;
4732 int *charbuf
= coding
->charbuf
+ coding
->charbuf_used
;
4734 = coding
->charbuf
+ coding
->charbuf_size
- MAX_ANNOTATION_LENGTH
;
4735 int consumed_chars
= 0, consumed_chars_base
;
4736 int multibytep
= coding
->src_multibyte
;
4737 Lisp_Object attrs
, charset_list
, valids
;
4738 int char_offset
= coding
->produced_char
;
4739 int last_offset
= char_offset
;
4740 int last_id
= charset_ascii
;
4742 CODING_GET_INFO (coding
, attrs
, charset_list
);
4743 valids
= AREF (attrs
, coding_attr_charset_valids
);
4749 struct charset
*charset
;
4755 consumed_chars_base
= consumed_chars
;
4757 if (charbuf
>= charbuf_end
)
4765 val
= AREF (valids
, c
);
4770 charset
= CHARSET_FROM_ID (XFASTINT (val
));
4771 dim
= CHARSET_DIMENSION (charset
);
4775 code
= (code
<< 8) | c
;
4778 CODING_DECODE_CHAR (coding
, src
, src_base
, src_end
,
4783 /* VAL is a list of charset IDs. It is assured that the
4784 list is sorted by charset dimensions (smaller one
4788 charset
= CHARSET_FROM_ID (XFASTINT (XCAR (val
)));
4789 dim
= CHARSET_DIMENSION (charset
);
4793 code
= (code
<< 8) | c
;
4796 CODING_DECODE_CHAR (coding
, src
, src_base
,
4797 src_end
, charset
, code
, c
);
4805 if (charset
->id
!= charset_ascii
4806 && last_id
!= charset
->id
)
4808 if (last_id
!= charset_ascii
)
4809 ADD_CHARSET_DATA (charbuf
, char_offset
- last_offset
, last_id
);
4810 last_id
= charset
->id
;
4811 last_offset
= char_offset
;
4820 consumed_chars
= consumed_chars_base
;
4822 *charbuf
++ = c
< 0 ? -c
: ASCII_BYTE_P (c
) ? c
: BYTE8_TO_CHAR (c
);
4828 if (last_id
!= charset_ascii
)
4829 ADD_CHARSET_DATA (charbuf
, char_offset
- last_offset
, last_id
);
4830 coding
->consumed_char
+= consumed_chars_base
;
4831 coding
->consumed
= src_base
- coding
->source
;
4832 coding
->charbuf_used
= charbuf
- coding
->charbuf
;
4836 encode_coding_charset (coding
)
4837 struct coding_system
*coding
;
4839 int multibytep
= coding
->dst_multibyte
;
4840 int *charbuf
= coding
->charbuf
;
4841 int *charbuf_end
= charbuf
+ coding
->charbuf_used
;
4842 unsigned char *dst
= coding
->destination
+ coding
->produced
;
4843 unsigned char *dst_end
= coding
->destination
+ coding
->dst_bytes
;
4844 int safe_room
= MAX_MULTIBYTE_LENGTH
;
4845 int produced_chars
= 0;
4846 Lisp_Object attrs
, charset_list
;
4847 int ascii_compatible
;
4850 CODING_GET_INFO (coding
, attrs
, charset_list
);
4851 ascii_compatible
= ! NILP (CODING_ATTR_ASCII_COMPAT (attrs
));
4853 while (charbuf
< charbuf_end
)
4855 struct charset
*charset
;
4858 ASSURE_DESTINATION (safe_room
);
4860 if (ascii_compatible
&& ASCII_CHAR_P (c
))
4861 EMIT_ONE_ASCII_BYTE (c
);
4862 else if (CHAR_BYTE8_P (c
))
4864 c
= CHAR_TO_BYTE8 (c
);
4869 charset
= char_charset (c
, charset_list
, &code
);
4872 if (CHARSET_DIMENSION (charset
) == 1)
4873 EMIT_ONE_BYTE (code
);
4874 else if (CHARSET_DIMENSION (charset
) == 2)
4875 EMIT_TWO_BYTES (code
>> 8, code
& 0xFF);
4876 else if (CHARSET_DIMENSION (charset
) == 3)
4877 EMIT_THREE_BYTES (code
>> 16, (code
>> 8) & 0xFF, code
& 0xFF);
4879 EMIT_FOUR_BYTES (code
>> 24, (code
>> 16) & 0xFF,
4880 (code
>> 8) & 0xFF, code
& 0xFF);
4884 if (coding
->mode
& CODING_MODE_SAFE_ENCODING
)
4885 c
= CODING_INHIBIT_CHARACTER_SUBSTITUTION
;
4887 c
= coding
->default_char
;
4893 record_conversion_result (coding
, CODING_RESULT_SUCCESS
);
4894 coding
->produced_char
+= produced_chars
;
4895 coding
->produced
= dst
- coding
->destination
;
4900 /*** 7. C library functions ***/
4902 /* Setup coding context CODING from information about CODING_SYSTEM.
4903 If CODING_SYSTEM is nil, `no-conversion' is assumed. If
4904 CODING_SYSTEM is invalid, signal an error. */
4907 setup_coding_system (coding_system
, coding
)
4908 Lisp_Object coding_system
;
4909 struct coding_system
*coding
;
4912 Lisp_Object eol_type
;
4913 Lisp_Object coding_type
;
4916 if (NILP (coding_system
))
4917 coding_system
= Qundecided
;
4919 CHECK_CODING_SYSTEM_GET_ID (coding_system
, coding
->id
);
4921 attrs
= CODING_ID_ATTRS (coding
->id
);
4922 eol_type
= CODING_ID_EOL_TYPE (coding
->id
);
4925 coding
->head_ascii
= -1;
4926 coding
->common_flags
4927 = (VECTORP (eol_type
) ? CODING_REQUIRE_DETECTION_MASK
: 0);
4928 if (! NILP (CODING_ATTR_POST_READ (attrs
)))
4929 coding
->common_flags
|= CODING_REQUIRE_DECODING_MASK
;
4930 if (! NILP (CODING_ATTR_PRE_WRITE (attrs
)))
4931 coding
->common_flags
|= CODING_REQUIRE_ENCODING_MASK
;
4932 if (! NILP (CODING_ATTR_FOR_UNIBYTE (attrs
)))
4933 coding
->common_flags
|= CODING_FOR_UNIBYTE_MASK
;
4935 val
= CODING_ATTR_SAFE_CHARSETS (attrs
);
4936 coding
->max_charset_id
= SCHARS (val
) - 1;
4937 coding
->safe_charsets
= (char *) SDATA (val
);
4938 coding
->default_char
= XINT (CODING_ATTR_DEFAULT_CHAR (attrs
));
4940 coding_type
= CODING_ATTR_TYPE (attrs
);
4941 if (EQ (coding_type
, Qundecided
))
4943 coding
->detector
= NULL
;
4944 coding
->decoder
= decode_coding_raw_text
;
4945 coding
->encoder
= encode_coding_raw_text
;
4946 coding
->common_flags
|= CODING_REQUIRE_DETECTION_MASK
;
4948 else if (EQ (coding_type
, Qiso_2022
))
4951 int flags
= XINT (AREF (attrs
, coding_attr_iso_flags
));
4953 /* Invoke graphic register 0 to plane 0. */
4954 CODING_ISO_INVOCATION (coding
, 0) = 0;
4955 /* Invoke graphic register 1 to plane 1 if we can use 8-bit. */
4956 CODING_ISO_INVOCATION (coding
, 1)
4957 = (flags
& CODING_ISO_FLAG_SEVEN_BITS
? -1 : 1);
4958 /* Setup the initial status of designation. */
4959 for (i
= 0; i
< 4; i
++)
4960 CODING_ISO_DESIGNATION (coding
, i
) = CODING_ISO_INITIAL (coding
, i
);
4961 /* Not single shifting initially. */
4962 CODING_ISO_SINGLE_SHIFTING (coding
) = 0;
4963 /* Beginning of buffer should also be regarded as bol. */
4964 CODING_ISO_BOL (coding
) = 1;
4965 coding
->detector
= detect_coding_iso_2022
;
4966 coding
->decoder
= decode_coding_iso_2022
;
4967 coding
->encoder
= encode_coding_iso_2022
;
4968 if (flags
& CODING_ISO_FLAG_SAFE
)
4969 coding
->mode
|= CODING_MODE_SAFE_ENCODING
;
4970 coding
->common_flags
4971 |= (CODING_REQUIRE_DECODING_MASK
| CODING_REQUIRE_ENCODING_MASK
4972 | CODING_REQUIRE_FLUSHING_MASK
);
4973 if (flags
& CODING_ISO_FLAG_COMPOSITION
)
4974 coding
->common_flags
|= CODING_ANNOTATE_COMPOSITION_MASK
;
4975 if (flags
& CODING_ISO_FLAG_DESIGNATION
)
4976 coding
->common_flags
|= CODING_ANNOTATE_CHARSET_MASK
;
4977 if (flags
& CODING_ISO_FLAG_FULL_SUPPORT
)
4979 setup_iso_safe_charsets (attrs
);
4980 val
= CODING_ATTR_SAFE_CHARSETS (attrs
);
4981 coding
->max_charset_id
= SCHARS (val
) - 1;
4982 coding
->safe_charsets
= (char *) SDATA (val
);
4984 CODING_ISO_FLAGS (coding
) = flags
;
4986 else if (EQ (coding_type
, Qcharset
))
4988 coding
->detector
= detect_coding_charset
;
4989 coding
->decoder
= decode_coding_charset
;
4990 coding
->encoder
= encode_coding_charset
;
4991 coding
->common_flags
4992 |= (CODING_REQUIRE_DECODING_MASK
| CODING_REQUIRE_ENCODING_MASK
);
4994 else if (EQ (coding_type
, Qutf_8
))
4996 coding
->detector
= detect_coding_utf_8
;
4997 coding
->decoder
= decode_coding_utf_8
;
4998 coding
->encoder
= encode_coding_utf_8
;
4999 coding
->common_flags
5000 |= (CODING_REQUIRE_DECODING_MASK
| CODING_REQUIRE_ENCODING_MASK
);
5002 else if (EQ (coding_type
, Qutf_16
))
5004 val
= AREF (attrs
, coding_attr_utf_16_bom
);
5005 CODING_UTF_16_BOM (coding
) = (CONSP (val
) ? utf_16_detect_bom
5006 : EQ (val
, Qt
) ? utf_16_with_bom
5007 : utf_16_without_bom
);
5008 val
= AREF (attrs
, coding_attr_utf_16_endian
);
5009 CODING_UTF_16_ENDIAN (coding
) = (EQ (val
, Qbig
) ? utf_16_big_endian
5010 : utf_16_little_endian
);
5011 CODING_UTF_16_SURROGATE (coding
) = 0;
5012 coding
->detector
= detect_coding_utf_16
;
5013 coding
->decoder
= decode_coding_utf_16
;
5014 coding
->encoder
= encode_coding_utf_16
;
5015 coding
->common_flags
5016 |= (CODING_REQUIRE_DECODING_MASK
| CODING_REQUIRE_ENCODING_MASK
);
5017 if (CODING_UTF_16_BOM (coding
) == utf_16_detect_bom
)
5018 coding
->common_flags
|= CODING_REQUIRE_DETECTION_MASK
;
5020 else if (EQ (coding_type
, Qccl
))
5022 coding
->detector
= detect_coding_ccl
;
5023 coding
->decoder
= decode_coding_ccl
;
5024 coding
->encoder
= encode_coding_ccl
;
5025 coding
->common_flags
5026 |= (CODING_REQUIRE_DECODING_MASK
| CODING_REQUIRE_ENCODING_MASK
5027 | CODING_REQUIRE_FLUSHING_MASK
);
5029 else if (EQ (coding_type
, Qemacs_mule
))
5031 coding
->detector
= detect_coding_emacs_mule
;
5032 coding
->decoder
= decode_coding_emacs_mule
;
5033 coding
->encoder
= encode_coding_emacs_mule
;
5034 coding
->common_flags
5035 |= (CODING_REQUIRE_DECODING_MASK
| CODING_REQUIRE_ENCODING_MASK
);
5036 if (! NILP (AREF (attrs
, coding_attr_emacs_mule_full
))
5037 && ! EQ (CODING_ATTR_CHARSET_LIST (attrs
), Vemacs_mule_charset_list
))
5039 Lisp_Object tail
, safe_charsets
;
5040 int max_charset_id
= 0;
5042 for (tail
= Vemacs_mule_charset_list
; CONSP (tail
);
5044 if (max_charset_id
< XFASTINT (XCAR (tail
)))
5045 max_charset_id
= XFASTINT (XCAR (tail
));
5046 safe_charsets
= Fmake_string (make_number (max_charset_id
+ 1),
5048 for (tail
= Vemacs_mule_charset_list
; CONSP (tail
);
5050 SSET (safe_charsets
, XFASTINT (XCAR (tail
)), 0);
5051 coding
->max_charset_id
= max_charset_id
;
5052 coding
->safe_charsets
= (char *) SDATA (safe_charsets
);
5055 else if (EQ (coding_type
, Qshift_jis
))
5057 coding
->detector
= detect_coding_sjis
;
5058 coding
->decoder
= decode_coding_sjis
;
5059 coding
->encoder
= encode_coding_sjis
;
5060 coding
->common_flags
5061 |= (CODING_REQUIRE_DECODING_MASK
| CODING_REQUIRE_ENCODING_MASK
);
5063 else if (EQ (coding_type
, Qbig5
))
5065 coding
->detector
= detect_coding_big5
;
5066 coding
->decoder
= decode_coding_big5
;
5067 coding
->encoder
= encode_coding_big5
;
5068 coding
->common_flags
5069 |= (CODING_REQUIRE_DECODING_MASK
| CODING_REQUIRE_ENCODING_MASK
);
5071 else /* EQ (coding_type, Qraw_text) */
5073 coding
->detector
= NULL
;
5074 coding
->decoder
= decode_coding_raw_text
;
5075 coding
->encoder
= encode_coding_raw_text
;
5076 if (! EQ (eol_type
, Qunix
))
5078 coding
->common_flags
|= CODING_REQUIRE_DECODING_MASK
;
5079 if (! VECTORP (eol_type
))
5080 coding
->common_flags
|= CODING_REQUIRE_ENCODING_MASK
;
5088 /* Return raw-text or one of its subsidiaries that has the same
5089 eol_type as CODING-SYSTEM. */
5092 raw_text_coding_system (coding_system
)
5093 Lisp_Object coding_system
;
5095 Lisp_Object spec
, attrs
;
5096 Lisp_Object eol_type
, raw_text_eol_type
;
5098 if (NILP (coding_system
))
5100 spec
= CODING_SYSTEM_SPEC (coding_system
);
5101 attrs
= AREF (spec
, 0);
5103 if (EQ (CODING_ATTR_TYPE (attrs
), Qraw_text
))
5104 return coding_system
;
5106 eol_type
= AREF (spec
, 2);
5107 if (VECTORP (eol_type
))
5109 spec
= CODING_SYSTEM_SPEC (Qraw_text
);
5110 raw_text_eol_type
= AREF (spec
, 2);
5111 return (EQ (eol_type
, Qunix
) ? AREF (raw_text_eol_type
, 0)
5112 : EQ (eol_type
, Qdos
) ? AREF (raw_text_eol_type
, 1)
5113 : AREF (raw_text_eol_type
, 2));
5117 /* If CODING_SYSTEM doesn't specify end-of-line format but PARENT
5118 does, return one of the subsidiary that has the same eol-spec as
5119 PARENT. Otherwise, return CODING_SYSTEM. */
5122 coding_inherit_eol_type (coding_system
, parent
)
5123 Lisp_Object coding_system
, parent
;
5125 Lisp_Object spec
, eol_type
;
5127 if (NILP (coding_system
))
5128 coding_system
= Qraw_text
;
5129 spec
= CODING_SYSTEM_SPEC (coding_system
);
5130 eol_type
= AREF (spec
, 2);
5131 if (VECTORP (eol_type
)
5134 Lisp_Object parent_spec
;
5135 Lisp_Object parent_eol_type
;
5138 = CODING_SYSTEM_SPEC (buffer_defaults
.buffer_file_coding_system
);
5139 parent_eol_type
= AREF (parent_spec
, 2);
5140 if (EQ (parent_eol_type
, Qunix
))
5141 coding_system
= AREF (eol_type
, 0);
5142 else if (EQ (parent_eol_type
, Qdos
))
5143 coding_system
= AREF (eol_type
, 1);
5144 else if (EQ (parent_eol_type
, Qmac
))
5145 coding_system
= AREF (eol_type
, 2);
5147 return coding_system
;
5150 /* Emacs has a mechanism to automatically detect a coding system if it
5151 is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But,
5152 it's impossible to distinguish some coding systems accurately
5153 because they use the same range of codes. So, at first, coding
5154 systems are categorized into 7, those are:
5156 o coding-category-emacs-mule
5158 The category for a coding system which has the same code range
5159 as Emacs' internal format. Assigned the coding-system (Lisp
5160 symbol) `emacs-mule' by default.
5162 o coding-category-sjis
5164 The category for a coding system which has the same code range
5165 as SJIS. Assigned the coding-system (Lisp
5166 symbol) `japanese-shift-jis' by default.
5168 o coding-category-iso-7
5170 The category for a coding system which has the same code range
5171 as ISO2022 of 7-bit environment. This doesn't use any locking
5172 shift and single shift functions. This can encode/decode all
5173 charsets. Assigned the coding-system (Lisp symbol)
5174 `iso-2022-7bit' by default.
5176 o coding-category-iso-7-tight
5178 Same as coding-category-iso-7 except that this can
5179 encode/decode only the specified charsets.
5181 o coding-category-iso-8-1
5183 The category for a coding system which has the same code range
5184 as ISO2022 of 8-bit environment and graphic plane 1 used only
5185 for DIMENSION1 charset. This doesn't use any locking shift
5186 and single shift functions. Assigned the coding-system (Lisp
5187 symbol) `iso-latin-1' by default.
5189 o coding-category-iso-8-2
5191 The category for a coding system which has the same code range
5192 as ISO2022 of 8-bit environment and graphic plane 1 used only
5193 for DIMENSION2 charset. This doesn't use any locking shift
5194 and single shift functions. Assigned the coding-system (Lisp
5195 symbol) `japanese-iso-8bit' by default.
5197 o coding-category-iso-7-else
5199 The category for a coding system which has the same code range
5200 as ISO2022 of 7-bit environemnt but uses locking shift or
5201 single shift functions. Assigned the coding-system (Lisp
5202 symbol) `iso-2022-7bit-lock' by default.
5204 o coding-category-iso-8-else
5206 The category for a coding system which has the same code range
5207 as ISO2022 of 8-bit environemnt but uses locking shift or
5208 single shift functions. Assigned the coding-system (Lisp
5209 symbol) `iso-2022-8bit-ss2' by default.
5211 o coding-category-big5
5213 The category for a coding system which has the same code range
5214 as BIG5. Assigned the coding-system (Lisp symbol)
5215 `cn-big5' by default.
5217 o coding-category-utf-8
5219 The category for a coding system which has the same code range
5220 as UTF-8 (cf. RFC3629). Assigned the coding-system (Lisp
5221 symbol) `utf-8' by default.
5223 o coding-category-utf-16-be
5225 The category for a coding system in which a text has an
5226 Unicode signature (cf. Unicode Standard) in the order of BIG
5227 endian at the head. Assigned the coding-system (Lisp symbol)
5228 `utf-16-be' by default.
5230 o coding-category-utf-16-le
5232 The category for a coding system in which a text has an
5233 Unicode signature (cf. Unicode Standard) in the order of
5234 LITTLE endian at the head. Assigned the coding-system (Lisp
5235 symbol) `utf-16-le' by default.
5237 o coding-category-ccl
5239 The category for a coding system of which encoder/decoder is
5240 written in CCL programs. The default value is nil, i.e., no
5241 coding system is assigned.
5243 o coding-category-binary
5245 The category for a coding system not categorized in any of the
5246 above. Assigned the coding-system (Lisp symbol)
5247 `no-conversion' by default.
5249 Each of them is a Lisp symbol and the value is an actual
5250 `coding-system's (this is also a Lisp symbol) assigned by a user.
5251 What Emacs does actually is to detect a category of coding system.
5252 Then, it uses a `coding-system' assigned to it. If Emacs can't
5253 decide only one possible category, it selects a category of the
5254 highest priority. Priorities of categories are also specified by a
5255 user in a Lisp variable `coding-category-list'.
5259 #define EOL_SEEN_NONE 0
5260 #define EOL_SEEN_LF 1
5261 #define EOL_SEEN_CR 2
5262 #define EOL_SEEN_CRLF 4
5264 /* Detect how end-of-line of a text of length SRC_BYTES pointed by
5265 SOURCE is encoded. If CATEGORY is one of
5266 coding_category_utf_16_XXXX, assume that CR and LF are encoded by
5267 two-byte, else they are encoded by one-byte.
5269 Return one of EOL_SEEN_XXX. */
5271 #define MAX_EOL_CHECK_COUNT 3
5274 detect_eol (source
, src_bytes
, category
)
5275 const unsigned char *source
;
5276 EMACS_INT src_bytes
;
5277 enum coding_category category
;
5279 const unsigned char *src
= source
, *src_end
= src
+ src_bytes
;
5282 int eol_seen
= EOL_SEEN_NONE
;
5284 if ((1 << category
) & CATEGORY_MASK_UTF_16
)
5288 msb
= category
== (coding_category_utf_16_le
5289 | coding_category_utf_16_le_nosig
);
5292 while (src
+ 1 < src_end
)
5295 if (src
[msb
] == 0 && (c
== '\n' || c
== '\r'))
5300 this_eol
= EOL_SEEN_LF
;
5301 else if (src
+ 3 >= src_end
5302 || src
[msb
+ 2] != 0
5303 || src
[lsb
+ 2] != '\n')
5304 this_eol
= EOL_SEEN_CR
;
5306 this_eol
= EOL_SEEN_CRLF
;
5308 if (eol_seen
== EOL_SEEN_NONE
)
5309 /* This is the first end-of-line. */
5310 eol_seen
= this_eol
;
5311 else if (eol_seen
!= this_eol
)
5313 /* The found type is different from what found before. */
5314 eol_seen
= EOL_SEEN_LF
;
5317 if (++total
== MAX_EOL_CHECK_COUNT
)
5325 while (src
< src_end
)
5328 if (c
== '\n' || c
== '\r')
5333 this_eol
= EOL_SEEN_LF
;
5334 else if (src
>= src_end
|| *src
!= '\n')
5335 this_eol
= EOL_SEEN_CR
;
5337 this_eol
= EOL_SEEN_CRLF
, src
++;
5339 if (eol_seen
== EOL_SEEN_NONE
)
5340 /* This is the first end-of-line. */
5341 eol_seen
= this_eol
;
5342 else if (eol_seen
!= this_eol
)
5344 /* The found type is different from what found before. */
5345 eol_seen
= EOL_SEEN_LF
;
5348 if (++total
== MAX_EOL_CHECK_COUNT
)
5358 adjust_coding_eol_type (coding
, eol_seen
)
5359 struct coding_system
*coding
;
5362 Lisp_Object eol_type
;
5364 eol_type
= CODING_ID_EOL_TYPE (coding
->id
);
5365 if (eol_seen
& EOL_SEEN_LF
)
5367 coding
->id
= CODING_SYSTEM_ID (AREF (eol_type
, 0));
5370 else if (eol_seen
& EOL_SEEN_CRLF
)
5372 coding
->id
= CODING_SYSTEM_ID (AREF (eol_type
, 1));
5375 else if (eol_seen
& EOL_SEEN_CR
)
5377 coding
->id
= CODING_SYSTEM_ID (AREF (eol_type
, 2));
5383 /* Detect how a text specified in CODING is encoded. If a coding
5384 system is detected, update fields of CODING by the detected coding
5388 detect_coding (coding
)
5389 struct coding_system
*coding
;
5391 const unsigned char *src
, *src_end
;
5393 coding
->consumed
= coding
->consumed_char
= 0;
5394 coding
->produced
= coding
->produced_char
= 0;
5395 coding_set_source (coding
);
5397 src_end
= coding
->source
+ coding
->src_bytes
;
5399 /* If we have not yet decided the text encoding type, detect it
5401 if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding
->id
)), Qundecided
))
5404 struct coding_detection_info detect_info
;
5406 detect_info
.checked
= detect_info
.found
= detect_info
.rejected
= 0;
5407 for (i
= 0, src
= coding
->source
; src
< src_end
; i
++, src
++)
5413 && (c
== ISO_CODE_ESC
|| c
== ISO_CODE_SI
|| c
== ISO_CODE_SO
)
5414 && ! inhibit_iso_escape_detection
5415 && ! detect_info
.checked
)
5417 coding
->head_ascii
= src
- (coding
->source
+ coding
->consumed
);
5418 if (detect_coding_iso_2022 (coding
, &detect_info
))
5420 /* We have scanned the whole data. */
5421 if (! (detect_info
.rejected
& CATEGORY_MASK_ISO_7_ELSE
))
5422 /* We didn't find an 8-bit code. */
5428 coding
->head_ascii
= src
- (coding
->source
+ coding
->consumed
);
5430 if (coding
->head_ascii
< coding
->src_bytes
5431 || detect_info
.found
)
5433 enum coding_category category
;
5434 struct coding_system
*this;
5436 if (coding
->head_ascii
== coding
->src_bytes
)
5437 /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */
5438 for (i
= 0; i
< coding_category_raw_text
; i
++)
5440 category
= coding_priorities
[i
];
5441 this = coding_categories
+ category
;
5442 if (detect_info
.found
& (1 << category
))
5446 for (i
= 0; i
< coding_category_raw_text
; i
++)
5448 category
= coding_priorities
[i
];
5449 this = coding_categories
+ category
;
5452 /* No coding system of this category is defined. */
5453 detect_info
.rejected
|= (1 << category
);
5455 else if (category
>= coding_category_raw_text
)
5457 else if (detect_info
.checked
& (1 << category
))
5459 if (detect_info
.found
& (1 << category
))
5462 else if ((*(this->detector
)) (coding
, &detect_info
)
5463 && detect_info
.found
& (1 << category
))
5465 if (category
== coding_category_utf_16_auto
)
5467 if (detect_info
.found
& CATEGORY_MASK_UTF_16_LE
)
5468 category
= coding_category_utf_16_le
;
5470 category
= coding_category_utf_16_be
;
5476 if (i
< coding_category_raw_text
)
5477 setup_coding_system (CODING_ID_NAME (this->id
), coding
);
5478 else if (detect_info
.rejected
== CATEGORY_MASK_ANY
)
5479 setup_coding_system (Qraw_text
, coding
);
5480 else if (detect_info
.rejected
)
5481 for (i
= 0; i
< coding_category_raw_text
; i
++)
5482 if (! (detect_info
.rejected
& (1 << coding_priorities
[i
])))
5484 this = coding_categories
+ coding_priorities
[i
];
5485 setup_coding_system (CODING_ID_NAME (this->id
), coding
);
5490 else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding
->id
)))
5491 == coding_category_utf_16_auto
)
5493 Lisp_Object coding_systems
;
5494 struct coding_detection_info detect_info
;
5497 = AREF (CODING_ID_ATTRS (coding
->id
), coding_attr_utf_16_bom
);
5498 detect_info
.found
= detect_info
.rejected
= 0;
5499 if (CONSP (coding_systems
)
5500 && detect_coding_utf_16 (coding
, &detect_info
))
5502 if (detect_info
.found
& CATEGORY_MASK_UTF_16_LE
)
5503 setup_coding_system (XCAR (coding_systems
), coding
);
5504 else if (detect_info
.found
& CATEGORY_MASK_UTF_16_BE
)
5505 setup_coding_system (XCDR (coding_systems
), coding
);
5513 struct coding_system
*coding
;
5515 Lisp_Object eol_type
;
5516 unsigned char *p
, *pbeg
, *pend
;
5518 eol_type
= CODING_ID_EOL_TYPE (coding
->id
);
5519 if (EQ (eol_type
, Qunix
))
5522 if (NILP (coding
->dst_object
))
5523 pbeg
= coding
->destination
;
5525 pbeg
= BYTE_POS_ADDR (coding
->dst_pos_byte
);
5526 pend
= pbeg
+ coding
->produced
;
5528 if (VECTORP (eol_type
))
5530 int eol_seen
= EOL_SEEN_NONE
;
5532 for (p
= pbeg
; p
< pend
; p
++)
5535 eol_seen
|= EOL_SEEN_LF
;
5536 else if (*p
== '\r')
5538 if (p
+ 1 < pend
&& *(p
+ 1) == '\n')
5540 eol_seen
|= EOL_SEEN_CRLF
;
5544 eol_seen
|= EOL_SEEN_CR
;
5547 if (eol_seen
!= EOL_SEEN_NONE
5548 && eol_seen
!= EOL_SEEN_LF
5549 && eol_seen
!= EOL_SEEN_CRLF
5550 && eol_seen
!= EOL_SEEN_CR
)
5551 eol_seen
= EOL_SEEN_LF
;
5552 if (eol_seen
!= EOL_SEEN_NONE
)
5553 eol_type
= adjust_coding_eol_type (coding
, eol_seen
);
5556 if (EQ (eol_type
, Qmac
))
5558 for (p
= pbeg
; p
< pend
; p
++)
5562 else if (EQ (eol_type
, Qdos
))
5566 if (NILP (coding
->dst_object
))
5568 for (p
= pend
- 2; p
>= pbeg
; p
--)
5571 safe_bcopy ((char *) (p
+ 1), (char *) p
, pend
-- - p
- 1);
5577 for (p
= pend
- 2; p
>= pbeg
; p
--)
5580 int pos_byte
= coding
->dst_pos_byte
+ (p
- pbeg
);
5581 int pos
= BYTE_TO_CHAR (pos_byte
);
5583 del_range_2 (pos
, pos_byte
, pos
+ 1, pos_byte
+ 1, 0);
5587 coding
->produced
-= n
;
5588 coding
->produced_char
-= n
;
5593 /* Return a translation table (or list of them) from coding system
5594 attribute vector ATTRS for encoding (ENCODEP is nonzero) or
5595 decoding (ENCODEP is zero). */
5598 get_translation_table (attrs
, encodep
, max_lookup
)
5600 int encodep
, *max_lookup
;
5602 Lisp_Object standard
, translation_table
;
5606 translation_table
= CODING_ATTR_ENCODE_TBL (attrs
),
5607 standard
= Vstandard_translation_table_for_encode
;
5609 translation_table
= CODING_ATTR_DECODE_TBL (attrs
),
5610 standard
= Vstandard_translation_table_for_decode
;
5611 if (NILP (translation_table
))
5612 translation_table
= standard
;
5615 if (SYMBOLP (translation_table
))
5616 translation_table
= Fget (translation_table
, Qtranslation_table
);
5617 else if (CONSP (translation_table
))
5619 translation_table
= Fcopy_sequence (translation_table
);
5620 for (val
= translation_table
; CONSP (val
); val
= XCDR (val
))
5621 if (SYMBOLP (XCAR (val
)))
5622 XSETCAR (val
, Fget (XCAR (val
), Qtranslation_table
));
5624 if (CHAR_TABLE_P (standard
))
5626 if (CONSP (translation_table
))
5627 translation_table
= nconc2 (translation_table
,
5628 Fcons (standard
, Qnil
));
5630 translation_table
= Fcons (translation_table
,
5631 Fcons (standard
, Qnil
));
5638 if (CHAR_TABLE_P (translation_table
)
5639 && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (translation_table
)) > 1)
5641 val
= XCHAR_TABLE (translation_table
)->extras
[1];
5642 if (NATNUMP (val
) && *max_lookup
< XFASTINT (val
))
5643 *max_lookup
= XFASTINT (val
);
5645 else if (CONSP (translation_table
))
5647 Lisp_Object tail
, val
;
5649 for (tail
= translation_table
; CONSP (tail
); tail
= XCDR (tail
))
5650 if (CHAR_TABLE_P (XCAR (tail
))
5651 && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (XCAR (tail
))) > 1)
5653 val
= XCHAR_TABLE (XCAR (tail
))->extras
[1];
5654 if (NATNUMP (val
) && *max_lookup
< XFASTINT (val
))
5655 *max_lookup
= XFASTINT (val
);
5659 return translation_table
;
5662 #define LOOKUP_TRANSLATION_TABLE(table, c, trans) \
5665 if (CHAR_TABLE_P (table)) \
5667 trans = CHAR_TABLE_REF (table, c); \
5668 if (CHARACTERP (trans)) \
5669 c = XFASTINT (trans), trans = Qnil; \
5671 else if (CONSP (table)) \
5675 for (tail = table; CONSP (tail); tail = XCDR (tail)) \
5676 if (CHAR_TABLE_P (XCAR (tail))) \
5678 trans = CHAR_TABLE_REF (XCAR (tail), c); \
5679 if (CHARACTERP (trans)) \
5680 c = XFASTINT (trans), trans = Qnil; \
5681 else if (! NILP (trans)) \
5689 get_translation (val
, buf
, buf_end
, last_block
, from_nchars
, to_nchars
)
5693 int *from_nchars
, *to_nchars
;
5695 /* VAL is TO or (([FROM-CHAR ...] . TO) ...) where TO is TO-CHAR or
5699 Lisp_Object from
, tail
;
5702 for (tail
= val
; CONSP (tail
); tail
= XCDR (tail
))
5707 for (i
= 0; i
< len
; i
++)
5709 if (buf
+ i
== buf_end
)
5715 if (XINT (AREF (from
, i
)) != buf
[i
])
5729 *buf
= XINT (AREF (val
, 0)), *to_nchars
= ASIZE (val
);
5737 produce_chars (coding
, translation_table
, last_block
)
5738 struct coding_system
*coding
;
5739 Lisp_Object translation_table
;
5742 unsigned char *dst
= coding
->destination
+ coding
->produced
;
5743 unsigned char *dst_end
= coding
->destination
+ coding
->dst_bytes
;
5745 int produced_chars
= 0;
5748 if (! coding
->chars_at_source
)
5750 /* Characters are in coding->charbuf. */
5751 int *buf
= coding
->charbuf
;
5752 int *buf_end
= buf
+ coding
->charbuf_used
;
5754 if (BUFFERP (coding
->src_object
)
5755 && EQ (coding
->src_object
, coding
->dst_object
))
5756 dst_end
= ((unsigned char *) coding
->source
) + coding
->consumed
;
5758 while (buf
< buf_end
)
5764 int from_nchars
= 1, to_nchars
= 1;
5765 Lisp_Object trans
= Qnil
;
5767 LOOKUP_TRANSLATION_TABLE (translation_table
, c
, trans
);
5770 trans
= get_translation (trans
, buf
, buf_end
, last_block
,
5771 &from_nchars
, &to_nchars
);
5777 if (dst
+ MAX_MULTIBYTE_LENGTH
* to_nchars
> dst_end
)
5779 dst
= alloc_destination (coding
,
5781 + MAX_MULTIBYTE_LENGTH
* to_nchars
,
5783 dst_end
= coding
->destination
+ coding
->dst_bytes
;
5786 for (i
= 0; i
< to_nchars
; i
++)
5789 c
= XINT (AREF (trans
, i
));
5790 if (coding
->dst_multibyte
5791 || ! CHAR_BYTE8_P (c
))
5792 CHAR_STRING_ADVANCE (c
, dst
);
5794 *dst
++ = CHAR_TO_BYTE8 (c
);
5796 produced_chars
+= to_nchars
;
5798 while (--from_nchars
> 0)
5802 /* This is an annotation datum. (-C) is the length. */
5805 carryover
= buf_end
- buf
;
5809 const unsigned char *src
= coding
->source
;
5810 const unsigned char *src_end
= src
+ coding
->src_bytes
;
5811 Lisp_Object eol_type
;
5813 eol_type
= CODING_ID_EOL_TYPE (coding
->id
);
5815 if (coding
->src_multibyte
!= coding
->dst_multibyte
)
5817 if (coding
->src_multibyte
)
5824 const unsigned char *src_base
= src
;
5830 if (EQ (eol_type
, Qdos
))
5834 record_conversion_result
5835 (coding
, CODING_RESULT_INSUFFICIENT_SRC
);
5836 goto no_more_source
;
5841 else if (EQ (eol_type
, Qmac
))
5846 coding
->consumed
= src
- coding
->source
;
5848 if (EQ (coding
->src_object
, coding
->dst_object
))
5849 dst_end
= (unsigned char *) src
;
5852 dst
= alloc_destination (coding
, src_end
- src
+ 1,
5854 dst_end
= coding
->destination
+ coding
->dst_bytes
;
5855 coding_set_source (coding
);
5856 src
= coding
->source
+ coding
->consumed
;
5857 src_end
= coding
->source
+ coding
->src_bytes
;
5867 while (src
< src_end
)
5874 if (EQ (eol_type
, Qdos
))
5880 else if (EQ (eol_type
, Qmac
))
5883 if (dst
>= dst_end
- 1)
5885 coding
->consumed
= src
- coding
->source
;
5887 if (EQ (coding
->src_object
, coding
->dst_object
))
5888 dst_end
= (unsigned char *) src
;
5889 if (dst
>= dst_end
- 1)
5891 dst
= alloc_destination (coding
, src_end
- src
+ 2,
5893 dst_end
= coding
->destination
+ coding
->dst_bytes
;
5894 coding_set_source (coding
);
5895 src
= coding
->source
+ coding
->consumed
;
5896 src_end
= coding
->source
+ coding
->src_bytes
;
5904 if (!EQ (coding
->src_object
, coding
->dst_object
))
5906 int require
= coding
->src_bytes
- coding
->dst_bytes
;
5910 EMACS_INT offset
= src
- coding
->source
;
5912 dst
= alloc_destination (coding
, require
, dst
);
5913 coding_set_source (coding
);
5914 src
= coding
->source
+ offset
;
5915 src_end
= coding
->source
+ coding
->src_bytes
;
5918 produced_chars
= coding
->src_chars
;
5919 while (src
< src_end
)
5925 if (EQ (eol_type
, Qdos
))
5932 else if (EQ (eol_type
, Qmac
))
5938 coding
->consumed
= coding
->src_bytes
;
5939 coding
->consumed_char
= coding
->src_chars
;
5942 produced
= dst
- (coding
->destination
+ coding
->produced
);
5943 if (BUFFERP (coding
->dst_object
))
5944 insert_from_gap (produced_chars
, produced
);
5945 coding
->produced
+= produced
;
5946 coding
->produced_char
+= produced_chars
;
5950 /* Compose text in CODING->object according to the annotation data at
5951 CHARBUF. CHARBUF is an array:
5952 [ -LENGTH ANNOTATION_MASK FROM TO METHOD COMP_LEN [ COMPONENTS... ] ]
5956 produce_composition (coding
, charbuf
, pos
)
5957 struct coding_system
*coding
;
5963 enum composition_method method
;
5964 Lisp_Object components
;
5967 to
= pos
+ charbuf
[2];
5970 method
= (enum composition_method
) (charbuf
[3]);
5972 if (method
== COMPOSITION_RELATIVE
)
5974 else if (method
>= COMPOSITION_WITH_RULE
5975 && method
<= COMPOSITION_WITH_RULE_ALTCHARS
)
5977 Lisp_Object args
[MAX_COMPOSITION_COMPONENTS
* 2 - 1];
5982 for (i
= 0; i
< len
; i
++)
5984 args
[i
] = make_number (charbuf
[i
]);
5988 components
= (method
== COMPOSITION_WITH_ALTCHARS
5989 ? Fstring (len
, args
) : Fvector (len
, args
));
5993 compose_text (pos
, to
, components
, Qnil
, coding
->dst_object
);
5997 /* Put `charset' property on text in CODING->object according to
5998 the annotation data at CHARBUF. CHARBUF is an array:
5999 [ -LENGTH ANNOTATION_MASK NCHARS CHARSET-ID ]
6003 produce_charset (coding
, charbuf
, pos
)
6004 struct coding_system
*coding
;
6008 EMACS_INT from
= pos
- charbuf
[2];
6009 struct charset
*charset
= CHARSET_FROM_ID (charbuf
[3]);
6011 Fput_text_property (make_number (from
), make_number (pos
),
6012 Qcharset
, CHARSET_NAME (charset
),
6013 coding
->dst_object
);
6017 #define CHARBUF_SIZE 0x4000
6019 #define ALLOC_CONVERSION_WORK_AREA(coding) \
6021 int size = CHARBUF_SIZE;; \
6023 coding->charbuf = NULL; \
6024 while (size > 1024) \
6026 coding->charbuf = (int *) alloca (sizeof (int) * size); \
6027 if (coding->charbuf) \
6031 if (! coding->charbuf) \
6033 record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_MEM); \
6034 return coding->result; \
6036 coding->charbuf_size = size; \
6041 produce_annotation (coding
, pos
)
6042 struct coding_system
*coding
;
6045 int *charbuf
= coding
->charbuf
;
6046 int *charbuf_end
= charbuf
+ coding
->charbuf_used
;
6048 if (NILP (coding
->dst_object
))
6051 while (charbuf
< charbuf_end
)
6057 int len
= -*charbuf
;
6060 case CODING_ANNOTATE_COMPOSITION_MASK
:
6061 produce_composition (coding
, charbuf
, pos
);
6063 case CODING_ANNOTATE_CHARSET_MASK
:
6064 produce_charset (coding
, charbuf
, pos
);
6074 /* Decode the data at CODING->src_object into CODING->dst_object.
6075 CODING->src_object is a buffer, a string, or nil.
6076 CODING->dst_object is a buffer.
6078 If CODING->src_object is a buffer, it must be the current buffer.
6079 In this case, if CODING->src_pos is positive, it is a position of
6080 the source text in the buffer, otherwise, the source text is in the
6081 gap area of the buffer, and CODING->src_pos specifies the offset of
6082 the text from GPT (which must be the same as PT). If this is the
6083 same buffer as CODING->dst_object, CODING->src_pos must be
6086 If CODING->src_object is a string, CODING->src_pos in an index to
6089 If CODING->src_object is nil, CODING->source must already point to
6090 the non-relocatable memory area. In this case, CODING->src_pos is
6091 an offset from CODING->source.
6093 The decoded data is inserted at the current point of the buffer
6098 decode_coding (coding
)
6099 struct coding_system
*coding
;
6102 Lisp_Object undo_list
;
6103 Lisp_Object translation_table
;
6107 if (BUFFERP (coding
->src_object
)
6108 && coding
->src_pos
> 0
6109 && coding
->src_pos
< GPT
6110 && coding
->src_pos
+ coding
->src_chars
> GPT
)
6111 move_gap_both (coding
->src_pos
, coding
->src_pos_byte
);
6114 if (BUFFERP (coding
->dst_object
))
6116 if (current_buffer
!= XBUFFER (coding
->dst_object
))
6117 set_buffer_internal (XBUFFER (coding
->dst_object
));
6119 move_gap_both (PT
, PT_BYTE
);
6120 undo_list
= current_buffer
->undo_list
;
6121 current_buffer
->undo_list
= Qt
;
6124 coding
->consumed
= coding
->consumed_char
= 0;
6125 coding
->produced
= coding
->produced_char
= 0;
6126 coding
->chars_at_source
= 0;
6127 record_conversion_result (coding
, CODING_RESULT_SUCCESS
);
6130 ALLOC_CONVERSION_WORK_AREA (coding
);
6132 attrs
= CODING_ID_ATTRS (coding
->id
);
6133 translation_table
= get_translation_table (attrs
, 0, NULL
);
6138 EMACS_INT pos
= coding
->dst_pos
+ coding
->produced_char
;
6140 coding_set_source (coding
);
6141 coding
->annotated
= 0;
6142 coding
->charbuf_used
= carryover
;
6143 (*(coding
->decoder
)) (coding
);
6144 coding_set_destination (coding
);
6145 carryover
= produce_chars (coding
, translation_table
, 0);
6146 if (coding
->annotated
)
6147 produce_annotation (coding
, pos
);
6148 for (i
= 0; i
< carryover
; i
++)
6150 = coding
->charbuf
[coding
->charbuf_used
- carryover
+ i
];
6152 while (coding
->consumed
< coding
->src_bytes
6153 && ! coding
->result
);
6157 coding_set_destination (coding
);
6158 coding
->charbuf_used
= carryover
;
6159 produce_chars (coding
, translation_table
, 1);
6162 coding
->carryover_bytes
= 0;
6163 if (coding
->consumed
< coding
->src_bytes
)
6165 int nbytes
= coding
->src_bytes
- coding
->consumed
;
6166 const unsigned char *src
;
6168 coding_set_source (coding
);
6169 coding_set_destination (coding
);
6170 src
= coding
->source
+ coding
->consumed
;
6172 if (coding
->mode
& CODING_MODE_LAST_BLOCK
)
6174 /* Flush out unprocessed data as binary chars. We are sure
6175 that the number of data is less than the size of
6177 coding
->charbuf_used
= 0;
6178 while (nbytes
-- > 0)
6182 coding
->charbuf
[coding
->charbuf_used
++] = (c
& 0x80 ? - c
: c
);
6184 produce_chars (coding
, Qnil
, 1);
6188 /* Record unprocessed bytes in coding->carryover. We are
6189 sure that the number of data is less than the size of
6190 coding->carryover. */
6191 unsigned char *p
= coding
->carryover
;
6193 coding
->carryover_bytes
= nbytes
;
6194 while (nbytes
-- > 0)
6197 coding
->consumed
= coding
->src_bytes
;
6200 if (BUFFERP (coding
->dst_object
))
6202 current_buffer
->undo_list
= undo_list
;
6203 record_insert (coding
->dst_pos
, coding
->produced_char
);
6205 if (! EQ (CODING_ID_EOL_TYPE (coding
->id
), Qunix
))
6206 decode_eol (coding
);
6207 return coding
->result
;
6211 /* Extract an annotation datum from a composition starting at POS and
6212 ending before LIMIT of CODING->src_object (buffer or string), store
6213 the data in BUF, set *STOP to a starting position of the next
6214 composition (if any) or to LIMIT, and return the address of the
6215 next element of BUF.
6217 If such an annotation is not found, set *STOP to a starting
6218 position of a composition after POS (if any) or to LIMIT, and
6222 handle_composition_annotation (pos
, limit
, coding
, buf
, stop
)
6223 EMACS_INT pos
, limit
;
6224 struct coding_system
*coding
;
6228 EMACS_INT start
, end
;
6231 if (! find_composition (pos
, limit
, &start
, &end
, &prop
, coding
->src_object
)
6234 else if (start
> pos
)
6240 /* We found a composition. Store the corresponding
6241 annotation data in BUF. */
6243 enum composition_method method
= COMPOSITION_METHOD (prop
);
6244 int nchars
= COMPOSITION_LENGTH (prop
);
6246 ADD_COMPOSITION_DATA (buf
, nchars
, method
);
6247 if (method
!= COMPOSITION_RELATIVE
)
6249 Lisp_Object components
;
6252 components
= COMPOSITION_COMPONENTS (prop
);
6253 if (VECTORP (components
))
6255 len
= XVECTOR (components
)->size
;
6256 for (i
= 0; i
< len
; i
++)
6257 *buf
++ = XINT (AREF (components
, i
));
6259 else if (STRINGP (components
))
6261 len
= SCHARS (components
);
6265 FETCH_STRING_CHAR_ADVANCE (*buf
, components
, i
, i_byte
);
6269 else if (INTEGERP (components
))
6272 *buf
++ = XINT (components
);
6274 else if (CONSP (components
))
6276 for (len
= 0; CONSP (components
);
6277 len
++, components
= XCDR (components
))
6278 *buf
++ = XINT (XCAR (components
));
6286 if (find_composition (end
, limit
, &start
, &end
, &prop
,
6297 /* Extract an annotation datum from a text property `charset' at POS of
6298 CODING->src_object (buffer of string), store the data in BUF, set
6299 *STOP to the position where the value of `charset' property changes
6300 (limiting by LIMIT), and return the address of the next element of
6303 If the property value is nil, set *STOP to the position where the
6304 property value is non-nil (limiting by LIMIT), and return BUF. */
6307 handle_charset_annotation (pos
, limit
, coding
, buf
, stop
)
6308 EMACS_INT pos
, limit
;
6309 struct coding_system
*coding
;
6313 Lisp_Object val
, next
;
6316 val
= Fget_text_property (make_number (pos
), Qcharset
, coding
->src_object
);
6317 if (! NILP (val
) && CHARSETP (val
))
6318 id
= XINT (CHARSET_SYMBOL_ID (val
));
6321 ADD_CHARSET_DATA (buf
, 0, id
);
6322 next
= Fnext_single_property_change (make_number (pos
), Qcharset
,
6324 make_number (limit
));
6325 *stop
= XINT (next
);
6331 consume_chars (coding
, translation_table
, max_lookup
)
6332 struct coding_system
*coding
;
6333 Lisp_Object translation_table
;
6336 int *buf
= coding
->charbuf
;
6337 int *buf_end
= coding
->charbuf
+ coding
->charbuf_size
;
6338 const unsigned char *src
= coding
->source
+ coding
->consumed
;
6339 const unsigned char *src_end
= coding
->source
+ coding
->src_bytes
;
6340 EMACS_INT pos
= coding
->src_pos
+ coding
->consumed_char
;
6341 EMACS_INT end_pos
= coding
->src_pos
+ coding
->src_chars
;
6342 int multibytep
= coding
->src_multibyte
;
6343 Lisp_Object eol_type
;
6345 EMACS_INT stop
, stop_composition
, stop_charset
;
6346 int *lookup_buf
= NULL
;
6348 if (! NILP (translation_table
))
6349 lookup_buf
= alloca (sizeof (int) * max_lookup
);
6351 eol_type
= CODING_ID_EOL_TYPE (coding
->id
);
6352 if (VECTORP (eol_type
))
6355 /* Note: composition handling is not yet implemented. */
6356 coding
->common_flags
&= ~CODING_ANNOTATE_COMPOSITION_MASK
;
6358 if (NILP (coding
->src_object
))
6359 stop
= stop_composition
= stop_charset
= end_pos
;
6362 if (coding
->common_flags
& CODING_ANNOTATE_COMPOSITION_MASK
)
6363 stop
= stop_composition
= pos
;
6365 stop
= stop_composition
= end_pos
;
6366 if (coding
->common_flags
& CODING_ANNOTATE_CHARSET_MASK
)
6367 stop
= stop_charset
= pos
;
6369 stop_charset
= end_pos
;
6372 /* Compensate for CRLF and conversion. */
6373 buf_end
-= 1 + MAX_ANNOTATION_LENGTH
;
6374 while (buf
< buf_end
)
6382 if (pos
== stop_composition
)
6383 buf
= handle_composition_annotation (pos
, end_pos
, coding
,
6384 buf
, &stop_composition
);
6385 if (pos
== stop_charset
)
6386 buf
= handle_charset_annotation (pos
, end_pos
, coding
,
6387 buf
, &stop_charset
);
6388 stop
= (stop_composition
< stop_charset
6389 ? stop_composition
: stop_charset
);
6396 if (coding
->encoder
== encode_coding_raw_text
)
6398 else if ((bytes
= MULTIBYTE_LENGTH (src
, src_end
)) > 0)
6399 c
= STRING_CHAR_ADVANCE (src
), pos
+= bytes
;
6401 c
= BYTE8_TO_CHAR (*src
), src
++, pos
++;
6404 c
= STRING_CHAR_ADVANCE (src
), pos
++;
6405 if ((c
== '\r') && (coding
->mode
& CODING_MODE_SELECTIVE_DISPLAY
))
6407 if (! EQ (eol_type
, Qunix
))
6411 if (EQ (eol_type
, Qdos
))
6419 LOOKUP_TRANSLATION_TABLE (translation_table
, c
, trans
);
6424 int from_nchars
= 1, to_nchars
= 1;
6425 int *lookup_buf_end
;
6426 const unsigned char *p
= src
;
6430 for (i
= 1; i
< max_lookup
&& p
< src_end
; i
++)
6431 lookup_buf
[i
] = STRING_CHAR_ADVANCE (p
);
6432 lookup_buf_end
= lookup_buf
+ i
;
6433 trans
= get_translation (trans
, lookup_buf
, lookup_buf_end
, 1,
6434 &from_nchars
, &to_nchars
);
6436 || buf
+ to_nchars
> buf_end
)
6438 *buf
++ = *lookup_buf
;
6439 for (i
= 1; i
< to_nchars
; i
++)
6440 *buf
++ = XINT (AREF (trans
, i
));
6441 for (i
= 1; i
< from_nchars
; i
++, pos
++)
6442 src
+= MULTIBYTE_LENGTH_NO_CHECK (src
);
6446 coding
->consumed
= src
- coding
->source
;
6447 coding
->consumed_char
= pos
- coding
->src_pos
;
6448 coding
->charbuf_used
= buf
- coding
->charbuf
;
6449 coding
->chars_at_source
= 0;
6453 /* Encode the text at CODING->src_object into CODING->dst_object.
6454 CODING->src_object is a buffer or a string.
6455 CODING->dst_object is a buffer or nil.
6457 If CODING->src_object is a buffer, it must be the current buffer.
6458 In this case, if CODING->src_pos is positive, it is a position of
6459 the source text in the buffer, otherwise. the source text is in the
6460 gap area of the buffer, and coding->src_pos specifies the offset of
6461 the text from GPT (which must be the same as PT). If this is the
6462 same buffer as CODING->dst_object, CODING->src_pos must be
6463 negative and CODING should not have `pre-write-conversion'.
6465 If CODING->src_object is a string, CODING should not have
6466 `pre-write-conversion'.
6468 If CODING->dst_object is a buffer, the encoded data is inserted at
6469 the current point of that buffer.
6471 If CODING->dst_object is nil, the encoded data is placed at the
6472 memory area specified by CODING->destination. */
6475 encode_coding (coding
)
6476 struct coding_system
*coding
;
6479 Lisp_Object translation_table
;
6482 attrs
= CODING_ID_ATTRS (coding
->id
);
6483 if (coding
->encoder
== encode_coding_raw_text
)
6484 translation_table
= Qnil
, max_lookup
= 0;
6486 translation_table
= get_translation_table (attrs
, 1, &max_lookup
);
6488 if (BUFFERP (coding
->dst_object
))
6490 set_buffer_internal (XBUFFER (coding
->dst_object
));
6491 coding
->dst_multibyte
6492 = ! NILP (current_buffer
->enable_multibyte_characters
);
6495 coding
->consumed
= coding
->consumed_char
= 0;
6496 coding
->produced
= coding
->produced_char
= 0;
6497 record_conversion_result (coding
, CODING_RESULT_SUCCESS
);
6500 ALLOC_CONVERSION_WORK_AREA (coding
);
6503 coding_set_source (coding
);
6504 consume_chars (coding
, translation_table
, max_lookup
);
6505 coding_set_destination (coding
);
6506 (*(coding
->encoder
)) (coding
);
6507 } while (coding
->consumed_char
< coding
->src_chars
);
6509 if (BUFFERP (coding
->dst_object
))
6510 insert_from_gap (coding
->produced_char
, coding
->produced
);
6512 return (coding
->result
);
6516 /* Name (or base name) of work buffer for code conversion. */
6517 static Lisp_Object Vcode_conversion_workbuf_name
;
6519 /* A working buffer used by the top level conversion. Once it is
6520 created, it is never destroyed. It has the name
6521 Vcode_conversion_workbuf_name. The other working buffers are
6522 destroyed after the use is finished, and their names are modified
6523 versions of Vcode_conversion_workbuf_name. */
6524 static Lisp_Object Vcode_conversion_reused_workbuf
;
6526 /* 1 iff Vcode_conversion_reused_workbuf is already in use. */
6527 static int reused_workbuf_in_use
;
6530 /* Return a working buffer of code convesion. MULTIBYTE specifies the
6531 multibyteness of returning buffer. */
6534 make_conversion_work_buffer (multibyte
)
6537 Lisp_Object name
, workbuf
;
6538 struct buffer
*current
;
6540 if (reused_workbuf_in_use
++)
6542 name
= Fgenerate_new_buffer_name (Vcode_conversion_workbuf_name
, Qnil
);
6543 workbuf
= Fget_buffer_create (name
);
6547 name
= Vcode_conversion_workbuf_name
;
6548 workbuf
= Fget_buffer_create (name
);
6549 if (NILP (Vcode_conversion_reused_workbuf
))
6550 Vcode_conversion_reused_workbuf
= workbuf
;
6552 current
= current_buffer
;
6553 set_buffer_internal (XBUFFER (workbuf
));
6555 current_buffer
->undo_list
= Qt
;
6556 current_buffer
->enable_multibyte_characters
= multibyte
? Qt
: Qnil
;
6557 set_buffer_internal (current
);
6563 code_conversion_restore (arg
)
6566 Lisp_Object current
, workbuf
;
6568 current
= XCAR (arg
);
6569 workbuf
= XCDR (arg
);
6570 if (! NILP (workbuf
))
6572 if (EQ (workbuf
, Vcode_conversion_reused_workbuf
))
6573 reused_workbuf_in_use
= 0;
6574 else if (! NILP (Fbuffer_live_p (workbuf
)))
6575 Fkill_buffer (workbuf
);
6577 set_buffer_internal (XBUFFER (current
));
6582 code_conversion_save (with_work_buf
, multibyte
)
6583 int with_work_buf
, multibyte
;
6585 Lisp_Object workbuf
= Qnil
;
6588 workbuf
= make_conversion_work_buffer (multibyte
);
6589 record_unwind_protect (code_conversion_restore
,
6590 Fcons (Fcurrent_buffer (), workbuf
));
6595 decode_coding_gap (coding
, chars
, bytes
)
6596 struct coding_system
*coding
;
6597 EMACS_INT chars
, bytes
;
6599 int count
= specpdl_ptr
- specpdl
;
6602 code_conversion_save (0, 0);
6604 coding
->src_object
= Fcurrent_buffer ();
6605 coding
->src_chars
= chars
;
6606 coding
->src_bytes
= bytes
;
6607 coding
->src_pos
= -chars
;
6608 coding
->src_pos_byte
= -bytes
;
6609 coding
->src_multibyte
= chars
< bytes
;
6610 coding
->dst_object
= coding
->src_object
;
6611 coding
->dst_pos
= PT
;
6612 coding
->dst_pos_byte
= PT_BYTE
;
6613 coding
->dst_multibyte
= ! NILP (current_buffer
->enable_multibyte_characters
);
6614 coding
->mode
|= CODING_MODE_LAST_BLOCK
;
6616 if (CODING_REQUIRE_DETECTION (coding
))
6617 detect_coding (coding
);
6619 decode_coding (coding
);
6621 attrs
= CODING_ID_ATTRS (coding
->id
);
6622 if (! NILP (CODING_ATTR_POST_READ (attrs
)))
6624 EMACS_INT prev_Z
= Z
, prev_Z_BYTE
= Z_BYTE
;
6627 TEMP_SET_PT_BOTH (coding
->dst_pos
, coding
->dst_pos_byte
);
6628 val
= call1 (CODING_ATTR_POST_READ (attrs
),
6629 make_number (coding
->produced_char
));
6631 coding
->produced_char
+= Z
- prev_Z
;
6632 coding
->produced
+= Z_BYTE
- prev_Z_BYTE
;
6635 unbind_to (count
, Qnil
);
6636 return coding
->result
;
6640 encode_coding_gap (coding
, chars
, bytes
)
6641 struct coding_system
*coding
;
6642 EMACS_INT chars
, bytes
;
6644 int count
= specpdl_ptr
- specpdl
;
6646 code_conversion_save (0, 0);
6648 coding
->src_object
= Fcurrent_buffer ();
6649 coding
->src_chars
= chars
;
6650 coding
->src_bytes
= bytes
;
6651 coding
->src_pos
= -chars
;
6652 coding
->src_pos_byte
= -bytes
;
6653 coding
->src_multibyte
= chars
< bytes
;
6654 coding
->dst_object
= coding
->src_object
;
6655 coding
->dst_pos
= PT
;
6656 coding
->dst_pos_byte
= PT_BYTE
;
6658 encode_coding (coding
);
6660 unbind_to (count
, Qnil
);
6661 return coding
->result
;
6665 /* Decode the text in the range FROM/FROM_BYTE and TO/TO_BYTE in
6666 SRC_OBJECT into DST_OBJECT by coding context CODING.
6668 SRC_OBJECT is a buffer, a string, or Qnil.
6670 If it is a buffer, the text is at point of the buffer. FROM and TO
6671 are positions in the buffer.
6673 If it is a string, the text is at the beginning of the string.
6674 FROM and TO are indices to the string.
6676 If it is nil, the text is at coding->source. FROM and TO are
6677 indices to coding->source.
6679 DST_OBJECT is a buffer, Qt, or Qnil.
6681 If it is a buffer, the decoded text is inserted at point of the
6682 buffer. If the buffer is the same as SRC_OBJECT, the source text
6685 If it is Qt, a string is made from the decoded text, and
6686 set in CODING->dst_object.
6688 If it is Qnil, the decoded text is stored at CODING->destination.
6689 The caller must allocate CODING->dst_bytes bytes at
6690 CODING->destination by xmalloc. If the decoded text is longer than
6691 CODING->dst_bytes, CODING->destination is relocated by xrealloc.
6695 decode_coding_object (coding
, src_object
, from
, from_byte
, to
, to_byte
,
6697 struct coding_system
*coding
;
6698 Lisp_Object src_object
;
6699 EMACS_INT from
, from_byte
, to
, to_byte
;
6700 Lisp_Object dst_object
;
6702 int count
= specpdl_ptr
- specpdl
;
6703 unsigned char *destination
;
6704 EMACS_INT dst_bytes
;
6705 EMACS_INT chars
= to
- from
;
6706 EMACS_INT bytes
= to_byte
- from_byte
;
6709 int saved_pt
= -1, saved_pt_byte
;
6711 buffer
= Fcurrent_buffer ();
6713 if (NILP (dst_object
))
6715 destination
= coding
->destination
;
6716 dst_bytes
= coding
->dst_bytes
;
6719 coding
->src_object
= src_object
;
6720 coding
->src_chars
= chars
;
6721 coding
->src_bytes
= bytes
;
6722 coding
->src_multibyte
= chars
< bytes
;
6724 if (STRINGP (src_object
))
6726 coding
->src_pos
= from
;
6727 coding
->src_pos_byte
= from_byte
;
6729 else if (BUFFERP (src_object
))
6731 set_buffer_internal (XBUFFER (src_object
));
6733 move_gap_both (from
, from_byte
);
6734 if (EQ (src_object
, dst_object
))
6736 saved_pt
= PT
, saved_pt_byte
= PT_BYTE
;
6737 TEMP_SET_PT_BOTH (from
, from_byte
);
6738 del_range_both (from
, from_byte
, to
, to_byte
, 1);
6739 coding
->src_pos
= -chars
;
6740 coding
->src_pos_byte
= -bytes
;
6744 coding
->src_pos
= from
;
6745 coding
->src_pos_byte
= from_byte
;
6749 if (CODING_REQUIRE_DETECTION (coding
))
6750 detect_coding (coding
);
6751 attrs
= CODING_ID_ATTRS (coding
->id
);
6753 if (EQ (dst_object
, Qt
)
6754 || (! NILP (CODING_ATTR_POST_READ (attrs
))
6755 && NILP (dst_object
)))
6757 coding
->dst_object
= code_conversion_save (1, 1);
6758 coding
->dst_pos
= BEG
;
6759 coding
->dst_pos_byte
= BEG_BYTE
;
6760 coding
->dst_multibyte
= 1;
6762 else if (BUFFERP (dst_object
))
6764 code_conversion_save (0, 0);
6765 coding
->dst_object
= dst_object
;
6766 coding
->dst_pos
= BUF_PT (XBUFFER (dst_object
));
6767 coding
->dst_pos_byte
= BUF_PT_BYTE (XBUFFER (dst_object
));
6768 coding
->dst_multibyte
6769 = ! NILP (XBUFFER (dst_object
)->enable_multibyte_characters
);
6773 code_conversion_save (0, 0);
6774 coding
->dst_object
= Qnil
;
6775 coding
->dst_multibyte
= 1;
6778 decode_coding (coding
);
6780 if (BUFFERP (coding
->dst_object
))
6781 set_buffer_internal (XBUFFER (coding
->dst_object
));
6783 if (! NILP (CODING_ATTR_POST_READ (attrs
)))
6785 struct gcpro gcpro1
, gcpro2
;
6786 EMACS_INT prev_Z
= Z
, prev_Z_BYTE
= Z_BYTE
;
6789 TEMP_SET_PT_BOTH (coding
->dst_pos
, coding
->dst_pos_byte
);
6790 GCPRO2 (coding
->src_object
, coding
->dst_object
);
6791 val
= call1 (CODING_ATTR_POST_READ (attrs
),
6792 make_number (coding
->produced_char
));
6795 coding
->produced_char
+= Z
- prev_Z
;
6796 coding
->produced
+= Z_BYTE
- prev_Z_BYTE
;
6799 if (EQ (dst_object
, Qt
))
6801 coding
->dst_object
= Fbuffer_string ();
6803 else if (NILP (dst_object
) && BUFFERP (coding
->dst_object
))
6805 set_buffer_internal (XBUFFER (coding
->dst_object
));
6806 if (dst_bytes
< coding
->produced
)
6809 = (unsigned char *) xrealloc (destination
, coding
->produced
);
6812 record_conversion_result (coding
,
6813 CODING_RESULT_INSUFFICIENT_DST
);
6814 unbind_to (count
, Qnil
);
6817 if (BEGV
< GPT
&& GPT
< BEGV
+ coding
->produced_char
)
6818 move_gap_both (BEGV
, BEGV_BYTE
);
6819 bcopy (BEGV_ADDR
, destination
, coding
->produced
);
6820 coding
->destination
= destination
;
6826 /* This is the case of:
6827 (BUFFERP (src_object) && EQ (src_object, dst_object))
6828 As we have moved PT while replacing the original buffer
6829 contents, we must recover it now. */
6830 set_buffer_internal (XBUFFER (src_object
));
6831 if (saved_pt
< from
)
6832 TEMP_SET_PT_BOTH (saved_pt
, saved_pt_byte
);
6833 else if (saved_pt
< from
+ chars
)
6834 TEMP_SET_PT_BOTH (from
, from_byte
);
6835 else if (! NILP (current_buffer
->enable_multibyte_characters
))
6836 TEMP_SET_PT_BOTH (saved_pt
+ (coding
->produced_char
- chars
),
6837 saved_pt_byte
+ (coding
->produced
- bytes
));
6839 TEMP_SET_PT_BOTH (saved_pt
+ (coding
->produced
- bytes
),
6840 saved_pt_byte
+ (coding
->produced
- bytes
));
6843 unbind_to (count
, coding
->dst_object
);
6848 encode_coding_object (coding
, src_object
, from
, from_byte
, to
, to_byte
,
6850 struct coding_system
*coding
;
6851 Lisp_Object src_object
;
6852 EMACS_INT from
, from_byte
, to
, to_byte
;
6853 Lisp_Object dst_object
;
6855 int count
= specpdl_ptr
- specpdl
;
6856 EMACS_INT chars
= to
- from
;
6857 EMACS_INT bytes
= to_byte
- from_byte
;
6860 int saved_pt
= -1, saved_pt_byte
;
6862 buffer
= Fcurrent_buffer ();
6864 coding
->src_object
= src_object
;
6865 coding
->src_chars
= chars
;
6866 coding
->src_bytes
= bytes
;
6867 coding
->src_multibyte
= chars
< bytes
;
6869 attrs
= CODING_ID_ATTRS (coding
->id
);
6871 if (! NILP (CODING_ATTR_PRE_WRITE (attrs
)))
6873 coding
->src_object
= code_conversion_save (1, coding
->src_multibyte
);
6874 set_buffer_internal (XBUFFER (coding
->src_object
));
6875 if (STRINGP (src_object
))
6876 insert_from_string (src_object
, from
, from_byte
, chars
, bytes
, 0);
6877 else if (BUFFERP (src_object
))
6878 insert_from_buffer (XBUFFER (src_object
), from
, chars
, 0);
6880 insert_1_both (coding
->source
+ from
, chars
, bytes
, 0, 0, 0);
6882 if (EQ (src_object
, dst_object
))
6884 set_buffer_internal (XBUFFER (src_object
));
6885 saved_pt
= PT
, saved_pt_byte
= PT_BYTE
;
6886 del_range_both (from
, from_byte
, to
, to_byte
, 1);
6887 set_buffer_internal (XBUFFER (coding
->src_object
));
6890 call2 (CODING_ATTR_PRE_WRITE (attrs
),
6891 make_number (BEG
), make_number (Z
));
6892 coding
->src_object
= Fcurrent_buffer ();
6894 move_gap_both (BEG
, BEG_BYTE
);
6895 coding
->src_chars
= Z
- BEG
;
6896 coding
->src_bytes
= Z_BYTE
- BEG_BYTE
;
6897 coding
->src_pos
= BEG
;
6898 coding
->src_pos_byte
= BEG_BYTE
;
6899 coding
->src_multibyte
= Z
< Z_BYTE
;
6901 else if (STRINGP (src_object
))
6903 code_conversion_save (0, 0);
6904 coding
->src_pos
= from
;
6905 coding
->src_pos_byte
= from_byte
;
6907 else if (BUFFERP (src_object
))
6909 code_conversion_save (0, 0);
6910 set_buffer_internal (XBUFFER (src_object
));
6911 if (EQ (src_object
, dst_object
))
6913 saved_pt
= PT
, saved_pt_byte
= PT_BYTE
;
6914 coding
->src_object
= del_range_1 (from
, to
, 1, 1);
6915 coding
->src_pos
= 0;
6916 coding
->src_pos_byte
= 0;
6920 if (from
< GPT
&& to
>= GPT
)
6921 move_gap_both (from
, from_byte
);
6922 coding
->src_pos
= from
;
6923 coding
->src_pos_byte
= from_byte
;
6927 code_conversion_save (0, 0);
6929 if (BUFFERP (dst_object
))
6931 coding
->dst_object
= dst_object
;
6932 if (EQ (src_object
, dst_object
))
6934 coding
->dst_pos
= from
;
6935 coding
->dst_pos_byte
= from_byte
;
6939 coding
->dst_pos
= BUF_PT (XBUFFER (dst_object
));
6940 coding
->dst_pos_byte
= BUF_PT_BYTE (XBUFFER (dst_object
));
6942 coding
->dst_multibyte
6943 = ! NILP (XBUFFER (dst_object
)->enable_multibyte_characters
);
6945 else if (EQ (dst_object
, Qt
))
6947 coding
->dst_object
= Qnil
;
6948 coding
->dst_bytes
= coding
->src_chars
;
6949 if (coding
->dst_bytes
== 0)
6950 coding
->dst_bytes
= 1;
6951 coding
->destination
= (unsigned char *) xmalloc (coding
->dst_bytes
);
6952 coding
->dst_multibyte
= 0;
6956 coding
->dst_object
= Qnil
;
6957 coding
->dst_multibyte
= 0;
6960 encode_coding (coding
);
6962 if (EQ (dst_object
, Qt
))
6964 if (BUFFERP (coding
->dst_object
))
6965 coding
->dst_object
= Fbuffer_string ();
6969 = make_unibyte_string ((char *) coding
->destination
,
6971 xfree (coding
->destination
);
6977 /* This is the case of:
6978 (BUFFERP (src_object) && EQ (src_object, dst_object))
6979 As we have moved PT while replacing the original buffer
6980 contents, we must recover it now. */
6981 set_buffer_internal (XBUFFER (src_object
));
6982 if (saved_pt
< from
)
6983 TEMP_SET_PT_BOTH (saved_pt
, saved_pt_byte
);
6984 else if (saved_pt
< from
+ chars
)
6985 TEMP_SET_PT_BOTH (from
, from_byte
);
6986 else if (! NILP (current_buffer
->enable_multibyte_characters
))
6987 TEMP_SET_PT_BOTH (saved_pt
+ (coding
->produced_char
- chars
),
6988 saved_pt_byte
+ (coding
->produced
- bytes
));
6990 TEMP_SET_PT_BOTH (saved_pt
+ (coding
->produced
- bytes
),
6991 saved_pt_byte
+ (coding
->produced
- bytes
));
6994 unbind_to (count
, Qnil
);
6999 preferred_coding_system ()
7001 int id
= coding_categories
[coding_priorities
[0]].id
;
7003 return CODING_ID_NAME (id
);
7008 /*** 8. Emacs Lisp library functions ***/
7010 DEFUN ("coding-system-p", Fcoding_system_p
, Scoding_system_p
, 1, 1, 0,
7011 doc
: /* Return t if OBJECT is nil or a coding-system.
7012 See the documentation of `define-coding-system' for information
7013 about coding-system objects. */)
7017 return ((NILP (obj
) || CODING_SYSTEM_P (obj
)) ? Qt
: Qnil
);
7020 DEFUN ("read-non-nil-coding-system", Fread_non_nil_coding_system
,
7021 Sread_non_nil_coding_system
, 1, 1, 0,
7022 doc
: /* Read a coding system from the minibuffer, prompting with string PROMPT. */)
7029 val
= Fcompleting_read (prompt
, Vcoding_system_alist
, Qnil
,
7030 Qt
, Qnil
, Qcoding_system_history
, Qnil
, Qnil
);
7032 while (SCHARS (val
) == 0);
7033 return (Fintern (val
, Qnil
));
7036 DEFUN ("read-coding-system", Fread_coding_system
, Sread_coding_system
, 1, 2, 0,
7037 doc
: /* Read a coding system from the minibuffer, prompting with string PROMPT.
7038 If the user enters null input, return second argument DEFAULT-CODING-SYSTEM. */)
7039 (prompt
, default_coding_system
)
7040 Lisp_Object prompt
, default_coding_system
;
7043 if (SYMBOLP (default_coding_system
))
7044 XSETSTRING (default_coding_system
, XPNTR (SYMBOL_NAME (default_coding_system
)));
7045 val
= Fcompleting_read (prompt
, Vcoding_system_alist
, Qnil
,
7046 Qt
, Qnil
, Qcoding_system_history
,
7047 default_coding_system
, Qnil
);
7048 return (SCHARS (val
) == 0 ? Qnil
: Fintern (val
, Qnil
));
7051 DEFUN ("check-coding-system", Fcheck_coding_system
, Scheck_coding_system
,
7053 doc
: /* Check validity of CODING-SYSTEM.
7054 If valid, return CODING-SYSTEM, else signal a `coding-system-error' error.
7055 It is valid if it is nil or a symbol defined as a coding system by the
7056 function `define-coding-system'. */)
7058 Lisp_Object coding_system
;
7060 CHECK_SYMBOL (coding_system
);
7061 if (!NILP (Fcoding_system_p (coding_system
)))
7062 return coding_system
;
7064 Fsignal (Qcoding_system_error
, Fcons (coding_system
, Qnil
));
7068 /* Detect how the bytes at SRC of length SRC_BYTES are encoded. If
7069 HIGHEST is nonzero, return the coding system of the highest
7070 priority among the detected coding systems. Otherwize return a
7071 list of detected coding systems sorted by their priorities. If
7072 MULTIBYTEP is nonzero, it is assumed that the bytes are in correct
7073 multibyte form but contains only ASCII and eight-bit chars.
7074 Otherwise, the bytes are raw bytes.
7076 CODING-SYSTEM controls the detection as below:
7078 If it is nil, detect both text-format and eol-format. If the
7079 text-format part of CODING-SYSTEM is already specified
7080 (e.g. `iso-latin-1'), detect only eol-format. If the eol-format
7081 part of CODING-SYSTEM is already specified (e.g. `undecided-unix'),
7082 detect only text-format. */
7085 detect_coding_system (src
, src_chars
, src_bytes
, highest
, multibytep
,
7087 const unsigned char *src
;
7088 int src_chars
, src_bytes
, highest
;
7090 Lisp_Object coding_system
;
7092 const unsigned char *src_end
= src
+ src_bytes
;
7093 Lisp_Object attrs
, eol_type
;
7095 struct coding_system coding
;
7097 struct coding_detection_info detect_info
;
7098 enum coding_category base_category
;
7100 if (NILP (coding_system
))
7101 coding_system
= Qundecided
;
7102 setup_coding_system (coding_system
, &coding
);
7103 attrs
= CODING_ID_ATTRS (coding
.id
);
7104 eol_type
= CODING_ID_EOL_TYPE (coding
.id
);
7105 coding_system
= CODING_ATTR_BASE_NAME (attrs
);
7107 coding
.source
= src
;
7108 coding
.src_chars
= src_chars
;
7109 coding
.src_bytes
= src_bytes
;
7110 coding
.src_multibyte
= multibytep
;
7111 coding
.consumed
= 0;
7112 coding
.mode
|= CODING_MODE_LAST_BLOCK
;
7114 detect_info
.checked
= detect_info
.found
= detect_info
.rejected
= 0;
7116 /* At first, detect text-format if necessary. */
7117 base_category
= XINT (CODING_ATTR_CATEGORY (attrs
));
7118 if (base_category
== coding_category_undecided
)
7120 enum coding_category category
;
7121 struct coding_system
*this;
7124 /* Skip all ASCII bytes except for a few ISO2022 controls. */
7125 for (i
= 0; src
< src_end
; i
++, src
++)
7131 && (c
== ISO_CODE_ESC
|| c
== ISO_CODE_SI
|| c
== ISO_CODE_SO
)
7132 && inhibit_iso_escape_detection
)
7134 coding
.head_ascii
= src
- coding
.source
;
7135 if (detect_coding_iso_2022 (&coding
, &detect_info
))
7137 /* We have scanned the whole data. */
7138 if (! (detect_info
.rejected
& CATEGORY_MASK_ISO_7_ELSE
))
7139 /* We didn't find an 8-bit code. */
7145 coding
.head_ascii
= src
- coding
.source
;
7148 || detect_info
.found
)
7151 /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */
7152 for (i
= 0; i
< coding_category_raw_text
; i
++)
7154 category
= coding_priorities
[i
];
7155 if (detect_info
.found
& (1 << category
))
7159 for (i
= 0; i
< coding_category_raw_text
; i
++)
7161 category
= coding_priorities
[i
];
7162 this = coding_categories
+ category
;
7166 /* No coding system of this category is defined. */
7167 detect_info
.rejected
|= (1 << category
);
7169 else if (category
>= coding_category_raw_text
)
7171 else if (detect_info
.checked
& (1 << category
))
7174 && (detect_info
.found
& (1 << category
)))
7179 if ((*(this->detector
)) (&coding
, &detect_info
)
7181 && (detect_info
.found
& (1 << category
)))
7183 if (category
== coding_category_utf_16_auto
)
7185 if (detect_info
.found
& CATEGORY_MASK_UTF_16_LE
)
7186 category
= coding_category_utf_16_le
;
7188 category
= coding_category_utf_16_be
;
7196 if (detect_info
.rejected
== CATEGORY_MASK_ANY
)
7198 detect_info
.found
= CATEGORY_MASK_RAW_TEXT
;
7199 id
= coding_categories
[coding_category_raw_text
].id
;
7200 val
= Fcons (make_number (id
), Qnil
);
7202 else if (! detect_info
.rejected
&& ! detect_info
.found
)
7204 detect_info
.found
= CATEGORY_MASK_ANY
;
7205 id
= coding_categories
[coding_category_undecided
].id
;
7206 val
= Fcons (make_number (id
), Qnil
);
7210 if (detect_info
.found
)
7212 detect_info
.found
= 1 << category
;
7213 val
= Fcons (make_number (this->id
), Qnil
);
7216 for (i
= 0; i
< coding_category_raw_text
; i
++)
7217 if (! (detect_info
.rejected
& (1 << coding_priorities
[i
])))
7219 detect_info
.found
= 1 << coding_priorities
[i
];
7220 id
= coding_categories
[coding_priorities
[i
]].id
;
7221 val
= Fcons (make_number (id
), Qnil
);
7227 int mask
= detect_info
.rejected
| detect_info
.found
;
7231 for (i
= coding_category_raw_text
- 1; i
>= 0; i
--)
7233 category
= coding_priorities
[i
];
7234 if (! (mask
& (1 << category
)))
7236 found
|= 1 << category
;
7237 id
= coding_categories
[category
].id
;
7238 val
= Fcons (make_number (id
), val
);
7241 for (i
= coding_category_raw_text
- 1; i
>= 0; i
--)
7243 category
= coding_priorities
[i
];
7244 if (detect_info
.found
& (1 << category
))
7246 id
= coding_categories
[category
].id
;
7247 val
= Fcons (make_number (id
), val
);
7250 detect_info
.found
|= found
;
7253 else if (base_category
== coding_category_utf_16_auto
)
7255 if (detect_coding_utf_16 (&coding
, &detect_info
))
7257 struct coding_system
*this;
7259 if (detect_info
.found
& CATEGORY_MASK_UTF_16_LE
)
7260 this = coding_categories
+ coding_category_utf_16_le
;
7261 else if (detect_info
.found
& CATEGORY_MASK_UTF_16_BE
)
7262 this = coding_categories
+ coding_category_utf_16_be
;
7263 else if (detect_info
.rejected
& CATEGORY_MASK_UTF_16_LE_NOSIG
)
7264 this = coding_categories
+ coding_category_utf_16_be_nosig
;
7266 this = coding_categories
+ coding_category_utf_16_le_nosig
;
7267 val
= Fcons (make_number (this->id
), Qnil
);
7272 detect_info
.found
= 1 << XINT (CODING_ATTR_CATEGORY (attrs
));
7273 val
= Fcons (make_number (coding
.id
), Qnil
);
7276 /* Then, detect eol-format if necessary. */
7278 int normal_eol
= -1, utf_16_be_eol
= -1, utf_16_le_eol
;
7281 if (VECTORP (eol_type
))
7283 if (detect_info
.found
& ~CATEGORY_MASK_UTF_16
)
7284 normal_eol
= detect_eol (coding
.source
, src_bytes
,
7285 coding_category_raw_text
);
7286 if (detect_info
.found
& (CATEGORY_MASK_UTF_16_BE
7287 | CATEGORY_MASK_UTF_16_BE_NOSIG
))
7288 utf_16_be_eol
= detect_eol (coding
.source
, src_bytes
,
7289 coding_category_utf_16_be
);
7290 if (detect_info
.found
& (CATEGORY_MASK_UTF_16_LE
7291 | CATEGORY_MASK_UTF_16_LE_NOSIG
))
7292 utf_16_le_eol
= detect_eol (coding
.source
, src_bytes
,
7293 coding_category_utf_16_le
);
7297 if (EQ (eol_type
, Qunix
))
7298 normal_eol
= utf_16_be_eol
= utf_16_le_eol
= EOL_SEEN_LF
;
7299 else if (EQ (eol_type
, Qdos
))
7300 normal_eol
= utf_16_be_eol
= utf_16_le_eol
= EOL_SEEN_CRLF
;
7302 normal_eol
= utf_16_be_eol
= utf_16_le_eol
= EOL_SEEN_CR
;
7305 for (tail
= val
; CONSP (tail
); tail
= XCDR (tail
))
7307 enum coding_category category
;
7310 id
= XINT (XCAR (tail
));
7311 attrs
= CODING_ID_ATTRS (id
);
7312 category
= XINT (CODING_ATTR_CATEGORY (attrs
));
7313 eol_type
= CODING_ID_EOL_TYPE (id
);
7314 if (VECTORP (eol_type
))
7316 if (category
== coding_category_utf_16_be
7317 || category
== coding_category_utf_16_be_nosig
)
7318 this_eol
= utf_16_be_eol
;
7319 else if (category
== coding_category_utf_16_le
7320 || category
== coding_category_utf_16_le_nosig
)
7321 this_eol
= utf_16_le_eol
;
7323 this_eol
= normal_eol
;
7325 if (this_eol
== EOL_SEEN_LF
)
7326 XSETCAR (tail
, AREF (eol_type
, 0));
7327 else if (this_eol
== EOL_SEEN_CRLF
)
7328 XSETCAR (tail
, AREF (eol_type
, 1));
7329 else if (this_eol
== EOL_SEEN_CR
)
7330 XSETCAR (tail
, AREF (eol_type
, 2));
7332 XSETCAR (tail
, CODING_ID_NAME (id
));
7335 XSETCAR (tail
, CODING_ID_NAME (id
));
7339 return (highest
? XCAR (val
) : val
);
7343 DEFUN ("detect-coding-region", Fdetect_coding_region
, Sdetect_coding_region
,
7345 doc
: /* Detect coding system of the text in the region between START and END.
7346 Return a list of possible coding systems ordered by priority.
7348 If only ASCII characters are found, it returns a list of single element
7349 `undecided' or its subsidiary coding system according to a detected
7352 If optional argument HIGHEST is non-nil, return the coding system of
7353 highest priority. */)
7354 (start
, end
, highest
)
7355 Lisp_Object start
, end
, highest
;
7358 int from_byte
, to_byte
;
7360 CHECK_NUMBER_COERCE_MARKER (start
);
7361 CHECK_NUMBER_COERCE_MARKER (end
);
7363 validate_region (&start
, &end
);
7364 from
= XINT (start
), to
= XINT (end
);
7365 from_byte
= CHAR_TO_BYTE (from
);
7366 to_byte
= CHAR_TO_BYTE (to
);
7368 if (from
< GPT
&& to
>= GPT
)
7369 move_gap_both (to
, to_byte
);
7371 return detect_coding_system (BYTE_POS_ADDR (from_byte
),
7372 to
- from
, to_byte
- from_byte
,
7374 !NILP (current_buffer
7375 ->enable_multibyte_characters
),
7379 DEFUN ("detect-coding-string", Fdetect_coding_string
, Sdetect_coding_string
,
7381 doc
: /* Detect coding system of the text in STRING.
7382 Return a list of possible coding systems ordered by priority.
7384 If only ASCII characters are found, it returns a list of single element
7385 `undecided' or its subsidiary coding system according to a detected
7388 If optional argument HIGHEST is non-nil, return the coding system of
7389 highest priority. */)
7391 Lisp_Object string
, highest
;
7393 CHECK_STRING (string
);
7395 return detect_coding_system (SDATA (string
),
7396 SCHARS (string
), SBYTES (string
),
7397 !NILP (highest
), STRING_MULTIBYTE (string
),
7403 char_encodable_p (c
, attrs
)
7408 struct charset
*charset
;
7409 Lisp_Object translation_table
;
7411 translation_table
= CODING_ATTR_TRANS_TBL (attrs
);
7412 if (! NILP (translation_table
))
7413 c
= translate_char (translation_table
, c
);
7414 for (tail
= CODING_ATTR_CHARSET_LIST (attrs
);
7415 CONSP (tail
); tail
= XCDR (tail
))
7417 charset
= CHARSET_FROM_ID (XINT (XCAR (tail
)));
7418 if (CHAR_CHARSET_P (c
, charset
))
7421 return (! NILP (tail
));
7425 /* Return a list of coding systems that safely encode the text between
7426 START and END. If EXCLUDE is non-nil, it is a list of coding
7427 systems not to check. The returned list doesn't contain any such
7428 coding systems. In any case, if the text contains only ASCII or is
7429 unibyte, return t. */
7431 DEFUN ("find-coding-systems-region-internal",
7432 Ffind_coding_systems_region_internal
,
7433 Sfind_coding_systems_region_internal
, 2, 3, 0,
7434 doc
: /* Internal use only. */)
7435 (start
, end
, exclude
)
7436 Lisp_Object start
, end
, exclude
;
7438 Lisp_Object coding_attrs_list
, safe_codings
;
7439 EMACS_INT start_byte
, end_byte
;
7440 const unsigned char *p
, *pbeg
, *pend
;
7442 Lisp_Object tail
, elt
;
7444 if (STRINGP (start
))
7446 if (!STRING_MULTIBYTE (start
)
7447 || SCHARS (start
) == SBYTES (start
))
7450 end_byte
= SBYTES (start
);
7454 CHECK_NUMBER_COERCE_MARKER (start
);
7455 CHECK_NUMBER_COERCE_MARKER (end
);
7456 if (XINT (start
) < BEG
|| XINT (end
) > Z
|| XINT (start
) > XINT (end
))
7457 args_out_of_range (start
, end
);
7458 if (NILP (current_buffer
->enable_multibyte_characters
))
7460 start_byte
= CHAR_TO_BYTE (XINT (start
));
7461 end_byte
= CHAR_TO_BYTE (XINT (end
));
7462 if (XINT (end
) - XINT (start
) == end_byte
- start_byte
)
7465 if (XINT (start
) < GPT
&& XINT (end
) > GPT
)
7467 if ((GPT
- XINT (start
)) < (XINT (end
) - GPT
))
7468 move_gap_both (XINT (start
), start_byte
);
7470 move_gap_both (XINT (end
), end_byte
);
7474 coding_attrs_list
= Qnil
;
7475 for (tail
= Vcoding_system_list
; CONSP (tail
); tail
= XCDR (tail
))
7477 || NILP (Fmemq (XCAR (tail
), exclude
)))
7481 attrs
= AREF (CODING_SYSTEM_SPEC (XCAR (tail
)), 0);
7482 if (EQ (XCAR (tail
), CODING_ATTR_BASE_NAME (attrs
))
7483 && ! EQ (CODING_ATTR_TYPE (attrs
), Qundecided
))
7485 ASET (attrs
, coding_attr_trans_tbl
,
7486 get_translation_table (attrs
, 1, NULL
));
7487 coding_attrs_list
= Fcons (attrs
, coding_attrs_list
);
7491 if (STRINGP (start
))
7492 p
= pbeg
= SDATA (start
);
7494 p
= pbeg
= BYTE_POS_ADDR (start_byte
);
7495 pend
= p
+ (end_byte
- start_byte
);
7497 while (p
< pend
&& ASCII_BYTE_P (*p
)) p
++;
7498 while (p
< pend
&& ASCII_BYTE_P (*(pend
- 1))) pend
--;
7502 if (ASCII_BYTE_P (*p
))
7506 c
= STRING_CHAR_ADVANCE (p
);
7508 charset_map_loaded
= 0;
7509 for (tail
= coding_attrs_list
; CONSP (tail
);)
7514 else if (char_encodable_p (c
, elt
))
7516 else if (CONSP (XCDR (tail
)))
7518 XSETCAR (tail
, XCAR (XCDR (tail
)));
7519 XSETCDR (tail
, XCDR (XCDR (tail
)));
7523 XSETCAR (tail
, Qnil
);
7527 if (charset_map_loaded
)
7529 EMACS_INT p_offset
= p
- pbeg
, pend_offset
= pend
- pbeg
;
7531 if (STRINGP (start
))
7532 pbeg
= SDATA (start
);
7534 pbeg
= BYTE_POS_ADDR (start_byte
);
7535 p
= pbeg
+ p_offset
;
7536 pend
= pbeg
+ pend_offset
;
7541 safe_codings
= list2 (Qraw_text
, Qno_conversion
);
7542 for (tail
= coding_attrs_list
; CONSP (tail
); tail
= XCDR (tail
))
7543 if (! NILP (XCAR (tail
)))
7544 safe_codings
= Fcons (CODING_ATTR_BASE_NAME (XCAR (tail
)), safe_codings
);
7546 return safe_codings
;
7550 DEFUN ("unencodable-char-position", Funencodable_char_position
,
7551 Sunencodable_char_position
, 3, 5, 0,
7553 Return position of first un-encodable character in a region.
7554 START and END specfiy the region and CODING-SYSTEM specifies the
7555 encoding to check. Return nil if CODING-SYSTEM does encode the region.
7557 If optional 4th argument COUNT is non-nil, it specifies at most how
7558 many un-encodable characters to search. In this case, the value is a
7561 If optional 5th argument STRING is non-nil, it is a string to search
7562 for un-encodable characters. In that case, START and END are indexes
7564 (start
, end
, coding_system
, count
, string
)
7565 Lisp_Object start
, end
, coding_system
, count
, string
;
7568 struct coding_system coding
;
7569 Lisp_Object attrs
, charset_list
, translation_table
;
7570 Lisp_Object positions
;
7572 const unsigned char *p
, *stop
, *pend
;
7573 int ascii_compatible
;
7575 setup_coding_system (Fcheck_coding_system (coding_system
), &coding
);
7576 attrs
= CODING_ID_ATTRS (coding
.id
);
7577 if (EQ (CODING_ATTR_TYPE (attrs
), Qraw_text
))
7579 ascii_compatible
= ! NILP (CODING_ATTR_ASCII_COMPAT (attrs
));
7580 charset_list
= CODING_ATTR_CHARSET_LIST (attrs
);
7581 translation_table
= get_translation_table (attrs
, 1, NULL
);
7585 validate_region (&start
, &end
);
7586 from
= XINT (start
);
7588 if (NILP (current_buffer
->enable_multibyte_characters
)
7589 || (ascii_compatible
7590 && (to
- from
) == (CHAR_TO_BYTE (to
) - (CHAR_TO_BYTE (from
)))))
7592 p
= CHAR_POS_ADDR (from
);
7593 pend
= CHAR_POS_ADDR (to
);
7594 if (from
< GPT
&& to
>= GPT
)
7601 CHECK_STRING (string
);
7602 CHECK_NATNUM (start
);
7604 from
= XINT (start
);
7607 || to
> SCHARS (string
))
7608 args_out_of_range_3 (string
, start
, end
);
7609 if (! STRING_MULTIBYTE (string
))
7611 p
= SDATA (string
) + string_char_to_byte (string
, from
);
7612 stop
= pend
= SDATA (string
) + string_char_to_byte (string
, to
);
7613 if (ascii_compatible
&& (to
- from
) == (pend
- p
))
7621 CHECK_NATNUM (count
);
7630 if (ascii_compatible
)
7631 while (p
< stop
&& ASCII_BYTE_P (*p
))
7641 c
= STRING_CHAR_ADVANCE (p
);
7642 if (! (ASCII_CHAR_P (c
) && ascii_compatible
)
7643 && ! char_charset (translate_char (translation_table
, c
),
7644 charset_list
, NULL
))
7646 positions
= Fcons (make_number (from
), positions
);
7655 return (NILP (count
) ? Fcar (positions
) : Fnreverse (positions
));
7659 DEFUN ("check-coding-systems-region", Fcheck_coding_systems_region
,
7660 Scheck_coding_systems_region
, 3, 3, 0,
7661 doc
: /* Check if the region is encodable by coding systems.
7663 START and END are buffer positions specifying the region.
7664 CODING-SYSTEM-LIST is a list of coding systems to check.
7666 The value is an alist ((CODING-SYSTEM POS0 POS1 ...) ...), where
7667 CODING-SYSTEM is a member of CODING-SYSTEM-LIst and can't encode the
7668 whole region, POS0, POS1, ... are buffer positions where non-encodable
7669 characters are found.
7671 If all coding systems in CODING-SYSTEM-LIST can encode the region, the
7674 START may be a string. In that case, check if the string is
7675 encodable, and the value contains indices to the string instead of
7676 buffer positions. END is ignored. */)
7677 (start
, end
, coding_system_list
)
7678 Lisp_Object start
, end
, coding_system_list
;
7681 EMACS_INT start_byte
, end_byte
;
7683 const unsigned char *p
, *pbeg
, *pend
;
7685 Lisp_Object tail
, elt
, attrs
;
7687 if (STRINGP (start
))
7689 if (!STRING_MULTIBYTE (start
)
7690 && SCHARS (start
) != SBYTES (start
))
7693 end_byte
= SBYTES (start
);
7698 CHECK_NUMBER_COERCE_MARKER (start
);
7699 CHECK_NUMBER_COERCE_MARKER (end
);
7700 if (XINT (start
) < BEG
|| XINT (end
) > Z
|| XINT (start
) > XINT (end
))
7701 args_out_of_range (start
, end
);
7702 if (NILP (current_buffer
->enable_multibyte_characters
))
7704 start_byte
= CHAR_TO_BYTE (XINT (start
));
7705 end_byte
= CHAR_TO_BYTE (XINT (end
));
7706 if (XINT (end
) - XINT (start
) == end_byte
- start_byte
)
7709 if (XINT (start
) < GPT
&& XINT (end
) > GPT
)
7711 if ((GPT
- XINT (start
)) < (XINT (end
) - GPT
))
7712 move_gap_both (XINT (start
), start_byte
);
7714 move_gap_both (XINT (end
), end_byte
);
7720 for (tail
= coding_system_list
; CONSP (tail
); tail
= XCDR (tail
))
7723 attrs
= AREF (CODING_SYSTEM_SPEC (elt
), 0);
7724 ASET (attrs
, coding_attr_trans_tbl
,
7725 get_translation_table (attrs
, 1, NULL
));
7726 list
= Fcons (Fcons (elt
, Fcons (attrs
, Qnil
)), list
);
7729 if (STRINGP (start
))
7730 p
= pbeg
= SDATA (start
);
7732 p
= pbeg
= BYTE_POS_ADDR (start_byte
);
7733 pend
= p
+ (end_byte
- start_byte
);
7735 while (p
< pend
&& ASCII_BYTE_P (*p
)) p
++, pos
++;
7736 while (p
< pend
&& ASCII_BYTE_P (*(pend
- 1))) pend
--;
7740 if (ASCII_BYTE_P (*p
))
7744 c
= STRING_CHAR_ADVANCE (p
);
7746 charset_map_loaded
= 0;
7747 for (tail
= list
; CONSP (tail
); tail
= XCDR (tail
))
7749 elt
= XCDR (XCAR (tail
));
7750 if (! char_encodable_p (c
, XCAR (elt
)))
7751 XSETCDR (elt
, Fcons (make_number (pos
), XCDR (elt
)));
7753 if (charset_map_loaded
)
7755 EMACS_INT p_offset
= p
- pbeg
, pend_offset
= pend
- pbeg
;
7757 if (STRINGP (start
))
7758 pbeg
= SDATA (start
);
7760 pbeg
= BYTE_POS_ADDR (start_byte
);
7761 p
= pbeg
+ p_offset
;
7762 pend
= pbeg
+ pend_offset
;
7770 for (; CONSP (tail
); tail
= XCDR (tail
))
7773 if (CONSP (XCDR (XCDR (elt
))))
7774 list
= Fcons (Fcons (XCAR (elt
), Fnreverse (XCDR (XCDR (elt
)))),
7783 code_convert_region (start
, end
, coding_system
, dst_object
, encodep
, norecord
)
7784 Lisp_Object start
, end
, coding_system
, dst_object
;
7785 int encodep
, norecord
;
7787 struct coding_system coding
;
7788 EMACS_INT from
, from_byte
, to
, to_byte
;
7789 Lisp_Object src_object
;
7791 CHECK_NUMBER_COERCE_MARKER (start
);
7792 CHECK_NUMBER_COERCE_MARKER (end
);
7793 if (NILP (coding_system
))
7794 coding_system
= Qno_conversion
;
7796 CHECK_CODING_SYSTEM (coding_system
);
7797 src_object
= Fcurrent_buffer ();
7798 if (NILP (dst_object
))
7799 dst_object
= src_object
;
7800 else if (! EQ (dst_object
, Qt
))
7801 CHECK_BUFFER (dst_object
);
7803 validate_region (&start
, &end
);
7804 from
= XFASTINT (start
);
7805 from_byte
= CHAR_TO_BYTE (from
);
7806 to
= XFASTINT (end
);
7807 to_byte
= CHAR_TO_BYTE (to
);
7809 setup_coding_system (coding_system
, &coding
);
7810 coding
.mode
|= CODING_MODE_LAST_BLOCK
;
7813 encode_coding_object (&coding
, src_object
, from
, from_byte
, to
, to_byte
,
7816 decode_coding_object (&coding
, src_object
, from
, from_byte
, to
, to_byte
,
7819 Vlast_coding_system_used
= CODING_ID_NAME (coding
.id
);
7821 return (BUFFERP (dst_object
)
7822 ? make_number (coding
.produced_char
)
7823 : coding
.dst_object
);
7827 DEFUN ("decode-coding-region", Fdecode_coding_region
, Sdecode_coding_region
,
7828 3, 4, "r\nzCoding system: ",
7829 doc
: /* Decode the current region from the specified coding system.
7830 When called from a program, takes four arguments:
7831 START, END, CODING-SYSTEM, and DESTINATION.
7832 START and END are buffer positions.
7834 Optional 4th arguments DESTINATION specifies where the decoded text goes.
7835 If nil, the region between START and END is replace by the decoded text.
7836 If buffer, the decoded text is inserted in the buffer.
7837 If t, the decoded text is returned.
7839 This function sets `last-coding-system-used' to the precise coding system
7840 used (which may be different from CODING-SYSTEM if CODING-SYSTEM is
7841 not fully specified.)
7842 It returns the length of the decoded text. */)
7843 (start
, end
, coding_system
, destination
)
7844 Lisp_Object start
, end
, coding_system
, destination
;
7846 return code_convert_region (start
, end
, coding_system
, destination
, 0, 0);
7849 DEFUN ("encode-coding-region", Fencode_coding_region
, Sencode_coding_region
,
7850 3, 4, "r\nzCoding system: ",
7851 doc
: /* Encode the current region by specified coding system.
7852 When called from a program, takes three arguments:
7853 START, END, and CODING-SYSTEM. START and END are buffer positions.
7855 Optional 4th arguments DESTINATION specifies where the encoded text goes.
7856 If nil, the region between START and END is replace by the encoded text.
7857 If buffer, the encoded text is inserted in the buffer.
7858 If t, the encoded text is returned.
7860 This function sets `last-coding-system-used' to the precise coding system
7861 used (which may be different from CODING-SYSTEM if CODING-SYSTEM is
7862 not fully specified.)
7863 It returns the length of the encoded text. */)
7864 (start
, end
, coding_system
, destination
)
7865 Lisp_Object start
, end
, coding_system
, destination
;
7867 return code_convert_region (start
, end
, coding_system
, destination
, 1, 0);
7871 code_convert_string (string
, coding_system
, dst_object
,
7872 encodep
, nocopy
, norecord
)
7873 Lisp_Object string
, coding_system
, dst_object
;
7874 int encodep
, nocopy
, norecord
;
7876 struct coding_system coding
;
7877 EMACS_INT chars
, bytes
;
7879 CHECK_STRING (string
);
7880 if (NILP (coding_system
))
7883 Vlast_coding_system_used
= Qno_conversion
;
7884 if (NILP (dst_object
))
7885 return (nocopy
? Fcopy_sequence (string
) : string
);
7888 if (NILP (coding_system
))
7889 coding_system
= Qno_conversion
;
7891 CHECK_CODING_SYSTEM (coding_system
);
7892 if (NILP (dst_object
))
7894 else if (! EQ (dst_object
, Qt
))
7895 CHECK_BUFFER (dst_object
);
7897 setup_coding_system (coding_system
, &coding
);
7898 coding
.mode
|= CODING_MODE_LAST_BLOCK
;
7899 chars
= SCHARS (string
);
7900 bytes
= SBYTES (string
);
7902 encode_coding_object (&coding
, string
, 0, 0, chars
, bytes
, dst_object
);
7904 decode_coding_object (&coding
, string
, 0, 0, chars
, bytes
, dst_object
);
7906 Vlast_coding_system_used
= CODING_ID_NAME (coding
.id
);
7908 return (BUFFERP (dst_object
)
7909 ? make_number (coding
.produced_char
)
7910 : coding
.dst_object
);
7914 /* Encode or decode STRING according to CODING_SYSTEM.
7915 Do not set Vlast_coding_system_used.
7917 This function is called only from macros DECODE_FILE and
7918 ENCODE_FILE, thus we ignore character composition. */
7921 code_convert_string_norecord (string
, coding_system
, encodep
)
7922 Lisp_Object string
, coding_system
;
7925 return code_convert_string (string
, coding_system
, Qt
, encodep
, 0, 1);
7929 DEFUN ("decode-coding-string", Fdecode_coding_string
, Sdecode_coding_string
,
7931 doc
: /* Decode STRING which is encoded in CODING-SYSTEM, and return the result.
7933 Optional third arg NOCOPY non-nil means it is OK to return STRING itself
7934 if the decoding operation is trivial.
7936 Optional fourth arg BUFFER non-nil meant that the decoded text is
7937 inserted in BUFFER instead of returned as a string. In this case,
7938 the return value is BUFFER.
7940 This function sets `last-coding-system-used' to the precise coding system
7941 used (which may be different from CODING-SYSTEM if CODING-SYSTEM is
7942 not fully specified. */)
7943 (string
, coding_system
, nocopy
, buffer
)
7944 Lisp_Object string
, coding_system
, nocopy
, buffer
;
7946 return code_convert_string (string
, coding_system
, buffer
,
7947 0, ! NILP (nocopy
), 0);
7950 DEFUN ("encode-coding-string", Fencode_coding_string
, Sencode_coding_string
,
7952 doc
: /* Encode STRING to CODING-SYSTEM, and return the result.
7954 Optional third arg NOCOPY non-nil means it is OK to return STRING
7955 itself if the encoding operation is trivial.
7957 Optional fourth arg BUFFER non-nil meant that the encoded text is
7958 inserted in BUFFER instead of returned as a string. In this case,
7959 the return value is BUFFER.
7961 This function sets `last-coding-system-used' to the precise coding system
7962 used (which may be different from CODING-SYSTEM if CODING-SYSTEM is
7963 not fully specified.) */)
7964 (string
, coding_system
, nocopy
, buffer
)
7965 Lisp_Object string
, coding_system
, nocopy
, buffer
;
7967 return code_convert_string (string
, coding_system
, buffer
,
7968 1, ! NILP (nocopy
), 1);
7972 DEFUN ("decode-sjis-char", Fdecode_sjis_char
, Sdecode_sjis_char
, 1, 1, 0,
7973 doc
: /* Decode a Japanese character which has CODE in shift_jis encoding.
7974 Return the corresponding character. */)
7978 Lisp_Object spec
, attrs
, val
;
7979 struct charset
*charset_roman
, *charset_kanji
, *charset_kana
, *charset
;
7982 CHECK_NATNUM (code
);
7983 c
= XFASTINT (code
);
7984 CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system
, spec
);
7985 attrs
= AREF (spec
, 0);
7987 if (ASCII_BYTE_P (c
)
7988 && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs
)))
7991 val
= CODING_ATTR_CHARSET_LIST (attrs
);
7992 charset_roman
= CHARSET_FROM_ID (XINT (XCAR (val
))), val
= XCDR (val
);
7993 charset_kana
= CHARSET_FROM_ID (XINT (XCAR (val
))), val
= XCDR (val
);
7994 charset_kanji
= CHARSET_FROM_ID (XINT (XCAR (val
)));
7997 charset
= charset_roman
;
7998 else if (c
>= 0xA0 && c
< 0xDF)
8000 charset
= charset_kana
;
8005 int s1
= c
>> 8, s2
= c
& 0xFF;
8007 if (s1
< 0x81 || (s1
> 0x9F && s1
< 0xE0) || s1
> 0xEF
8008 || s2
< 0x40 || s2
== 0x7F || s2
> 0xFC)
8009 error ("Invalid code: %d", code
);
8011 charset
= charset_kanji
;
8013 c
= DECODE_CHAR (charset
, c
);
8015 error ("Invalid code: %d", code
);
8016 return make_number (c
);
8020 DEFUN ("encode-sjis-char", Fencode_sjis_char
, Sencode_sjis_char
, 1, 1, 0,
8021 doc
: /* Encode a Japanese character CHAR to shift_jis encoding.
8022 Return the corresponding code in SJIS. */)
8026 Lisp_Object spec
, attrs
, charset_list
;
8028 struct charset
*charset
;
8031 CHECK_CHARACTER (ch
);
8033 CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system
, spec
);
8034 attrs
= AREF (spec
, 0);
8036 if (ASCII_CHAR_P (c
)
8037 && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs
)))
8040 charset_list
= CODING_ATTR_CHARSET_LIST (attrs
);
8041 charset
= char_charset (c
, charset_list
, &code
);
8042 if (code
== CHARSET_INVALID_CODE (charset
))
8043 error ("Can't encode by shift_jis encoding: %d", c
);
8046 return make_number (code
);
8049 DEFUN ("decode-big5-char", Fdecode_big5_char
, Sdecode_big5_char
, 1, 1, 0,
8050 doc
: /* Decode a Big5 character which has CODE in BIG5 coding system.
8051 Return the corresponding character. */)
8055 Lisp_Object spec
, attrs
, val
;
8056 struct charset
*charset_roman
, *charset_big5
, *charset
;
8059 CHECK_NATNUM (code
);
8060 c
= XFASTINT (code
);
8061 CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system
, spec
);
8062 attrs
= AREF (spec
, 0);
8064 if (ASCII_BYTE_P (c
)
8065 && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs
)))
8068 val
= CODING_ATTR_CHARSET_LIST (attrs
);
8069 charset_roman
= CHARSET_FROM_ID (XINT (XCAR (val
))), val
= XCDR (val
);
8070 charset_big5
= CHARSET_FROM_ID (XINT (XCAR (val
)));
8073 charset
= charset_roman
;
8076 int b1
= c
>> 8, b2
= c
& 0x7F;
8077 if (b1
< 0xA1 || b1
> 0xFE
8078 || b2
< 0x40 || (b2
> 0x7E && b2
< 0xA1) || b2
> 0xFE)
8079 error ("Invalid code: %d", code
);
8080 charset
= charset_big5
;
8082 c
= DECODE_CHAR (charset
, (unsigned )c
);
8084 error ("Invalid code: %d", code
);
8085 return make_number (c
);
8088 DEFUN ("encode-big5-char", Fencode_big5_char
, Sencode_big5_char
, 1, 1, 0,
8089 doc
: /* Encode the Big5 character CHAR to BIG5 coding system.
8090 Return the corresponding character code in Big5. */)
8094 Lisp_Object spec
, attrs
, charset_list
;
8095 struct charset
*charset
;
8099 CHECK_CHARACTER (ch
);
8101 CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system
, spec
);
8102 attrs
= AREF (spec
, 0);
8103 if (ASCII_CHAR_P (c
)
8104 && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs
)))
8107 charset_list
= CODING_ATTR_CHARSET_LIST (attrs
);
8108 charset
= char_charset (c
, charset_list
, &code
);
8109 if (code
== CHARSET_INVALID_CODE (charset
))
8110 error ("Can't encode by Big5 encoding: %d", c
);
8112 return make_number (code
);
8116 DEFUN ("set-terminal-coding-system-internal",
8117 Fset_terminal_coding_system_internal
,
8118 Sset_terminal_coding_system_internal
, 1, 1, 0,
8119 doc
: /* Internal use only. */)
8121 Lisp_Object coding_system
;
8123 CHECK_SYMBOL (coding_system
);
8124 setup_coding_system (Fcheck_coding_system (coding_system
),
8127 /* We had better not send unsafe characters to terminal. */
8128 terminal_coding
.mode
|= CODING_MODE_SAFE_ENCODING
;
8129 /* Characer composition should be disabled. */
8130 terminal_coding
.common_flags
&= ~CODING_ANNOTATE_COMPOSITION_MASK
;
8131 terminal_coding
.src_multibyte
= 1;
8132 terminal_coding
.dst_multibyte
= 0;
8136 DEFUN ("set-safe-terminal-coding-system-internal",
8137 Fset_safe_terminal_coding_system_internal
,
8138 Sset_safe_terminal_coding_system_internal
, 1, 1, 0,
8139 doc
: /* Internal use only. */)
8141 Lisp_Object coding_system
;
8143 CHECK_SYMBOL (coding_system
);
8144 setup_coding_system (Fcheck_coding_system (coding_system
),
8145 &safe_terminal_coding
);
8146 /* Characer composition should be disabled. */
8147 safe_terminal_coding
.common_flags
&= ~CODING_ANNOTATE_COMPOSITION_MASK
;
8148 safe_terminal_coding
.src_multibyte
= 1;
8149 safe_terminal_coding
.dst_multibyte
= 0;
8153 DEFUN ("terminal-coding-system",
8154 Fterminal_coding_system
, Sterminal_coding_system
, 0, 0, 0,
8155 doc
: /* Return coding system specified for terminal output. */)
8158 Lisp_Object coding_system
;
8160 coding_system
= CODING_ID_NAME (terminal_coding
.id
);
8161 /* For backward compatibility, return nil if it is `undecided'. */
8162 return (coding_system
!= Qundecided
? coding_system
: Qnil
);
8165 DEFUN ("set-keyboard-coding-system-internal",
8166 Fset_keyboard_coding_system_internal
,
8167 Sset_keyboard_coding_system_internal
, 1, 1, 0,
8168 doc
: /* Internal use only. */)
8170 Lisp_Object coding_system
;
8172 CHECK_SYMBOL (coding_system
);
8173 setup_coding_system (Fcheck_coding_system (coding_system
),
8175 /* Characer composition should be disabled. */
8176 keyboard_coding
.common_flags
&= ~CODING_ANNOTATE_COMPOSITION_MASK
;
8180 DEFUN ("keyboard-coding-system",
8181 Fkeyboard_coding_system
, Skeyboard_coding_system
, 0, 0, 0,
8182 doc
: /* Return coding system specified for decoding keyboard input. */)
8185 return CODING_ID_NAME (keyboard_coding
.id
);
8189 DEFUN ("find-operation-coding-system", Ffind_operation_coding_system
,
8190 Sfind_operation_coding_system
, 1, MANY
, 0,
8191 doc
: /* Choose a coding system for an operation based on the target name.
8192 The value names a pair of coding systems: (DECODING-SYSTEM . ENCODING-SYSTEM).
8193 DECODING-SYSTEM is the coding system to use for decoding
8194 \(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system
8195 for encoding (in case OPERATION does encoding).
8197 The first argument OPERATION specifies an I/O primitive:
8198 For file I/O, `insert-file-contents' or `write-region'.
8199 For process I/O, `call-process', `call-process-region', or `start-process'.
8200 For network I/O, `open-network-stream'.
8202 The remaining arguments should be the same arguments that were passed
8203 to the primitive. Depending on which primitive, one of those arguments
8204 is selected as the TARGET. For example, if OPERATION does file I/O,
8205 whichever argument specifies the file name is TARGET.
8207 TARGET has a meaning which depends on OPERATION:
8208 For file I/O, TARGET is a file name.
8209 For process I/O, TARGET is a process name.
8210 For network I/O, TARGET is a service name or a port number
8212 This function looks up what specified for TARGET in,
8213 `file-coding-system-alist', `process-coding-system-alist',
8214 or `network-coding-system-alist' depending on OPERATION.
8215 They may specify a coding system, a cons of coding systems,
8216 or a function symbol to call.
8217 In the last case, we call the function with one argument,
8218 which is a list of all the arguments given to this function.
8220 usage: (find-operation-coding-system OPERATION ARGUMENTS ...) */)
8225 Lisp_Object operation
, target_idx
, target
, val
;
8226 register Lisp_Object chain
;
8229 error ("Too few arguments");
8230 operation
= args
[0];
8231 if (!SYMBOLP (operation
)
8232 || !INTEGERP (target_idx
= Fget (operation
, Qtarget_idx
)))
8233 error ("Invalid first arguement");
8234 if (nargs
< 1 + XINT (target_idx
))
8235 error ("Too few arguments for operation: %s",
8236 SDATA (SYMBOL_NAME (operation
)));
8237 target
= args
[XINT (target_idx
) + 1];
8238 if (!(STRINGP (target
)
8239 || (EQ (operation
, Qopen_network_stream
) && INTEGERP (target
))))
8240 error ("Invalid %dth argument", XINT (target_idx
) + 1);
8242 chain
= ((EQ (operation
, Qinsert_file_contents
)
8243 || EQ (operation
, Qwrite_region
))
8244 ? Vfile_coding_system_alist
8245 : (EQ (operation
, Qopen_network_stream
)
8246 ? Vnetwork_coding_system_alist
8247 : Vprocess_coding_system_alist
));
8251 for (; CONSP (chain
); chain
= XCDR (chain
))
8257 && ((STRINGP (target
)
8258 && STRINGP (XCAR (elt
))
8259 && fast_string_match (XCAR (elt
), target
) >= 0)
8260 || (INTEGERP (target
) && EQ (target
, XCAR (elt
)))))
8263 /* Here, if VAL is both a valid coding system and a valid
8264 function symbol, we return VAL as a coding system. */
8267 if (! SYMBOLP (val
))
8269 if (! NILP (Fcoding_system_p (val
)))
8270 return Fcons (val
, val
);
8271 if (! NILP (Ffboundp (val
)))
8273 val
= call1 (val
, Flist (nargs
, args
));
8276 if (SYMBOLP (val
) && ! NILP (Fcoding_system_p (val
)))
8277 return Fcons (val
, val
);
8285 DEFUN ("set-coding-system-priority", Fset_coding_system_priority
,
8286 Sset_coding_system_priority
, 0, MANY
, 0,
8287 doc
: /* Assign higher priority to the coding systems given as arguments.
8288 If multiple coding systems belongs to the same category,
8289 all but the first one are ignored.
8291 usage: (set-coding-system-priority ...) */)
8297 int changed
[coding_category_max
];
8298 enum coding_category priorities
[coding_category_max
];
8300 bzero (changed
, sizeof changed
);
8302 for (i
= j
= 0; i
< nargs
; i
++)
8304 enum coding_category category
;
8305 Lisp_Object spec
, attrs
;
8307 CHECK_CODING_SYSTEM_GET_SPEC (args
[i
], spec
);
8308 attrs
= AREF (spec
, 0);
8309 category
= XINT (CODING_ATTR_CATEGORY (attrs
));
8310 if (changed
[category
])
8311 /* Ignore this coding system because a coding system of the
8312 same category already had a higher priority. */
8314 changed
[category
] = 1;
8315 priorities
[j
++] = category
;
8316 if (coding_categories
[category
].id
>= 0
8317 && ! EQ (args
[i
], CODING_ID_NAME (coding_categories
[category
].id
)))
8318 setup_coding_system (args
[i
], &coding_categories
[category
]);
8319 Fset (AREF (Vcoding_category_table
, category
), args
[i
]);
8322 /* Now we have decided top J priorities. Reflect the order of the
8323 original priorities to the remaining priorities. */
8325 for (i
= j
, j
= 0; i
< coding_category_max
; i
++, j
++)
8327 while (j
< coding_category_max
8328 && changed
[coding_priorities
[j
]])
8330 if (j
== coding_category_max
)
8332 priorities
[i
] = coding_priorities
[j
];
8335 bcopy (priorities
, coding_priorities
, sizeof priorities
);
8337 /* Update `coding-category-list'. */
8338 Vcoding_category_list
= Qnil
;
8339 for (i
= coding_category_max
- 1; i
>= 0; i
--)
8340 Vcoding_category_list
8341 = Fcons (AREF (Vcoding_category_table
, priorities
[i
]),
8342 Vcoding_category_list
);
8347 DEFUN ("coding-system-priority-list", Fcoding_system_priority_list
,
8348 Scoding_system_priority_list
, 0, 1, 0,
8349 doc
: /* Return a list of coding systems ordered by their priorities.
8350 HIGHESTP non-nil means just return the highest priority one. */)
8352 Lisp_Object highestp
;
8357 for (i
= 0, val
= Qnil
; i
< coding_category_max
; i
++)
8359 enum coding_category category
= coding_priorities
[i
];
8360 int id
= coding_categories
[category
].id
;
8365 attrs
= CODING_ID_ATTRS (id
);
8366 if (! NILP (highestp
))
8367 return CODING_ATTR_BASE_NAME (attrs
);
8368 val
= Fcons (CODING_ATTR_BASE_NAME (attrs
), val
);
8370 return Fnreverse (val
);
8373 static char *suffixes
[] = { "-unix", "-dos", "-mac" };
8376 make_subsidiaries (base
)
8379 Lisp_Object subsidiaries
;
8380 int base_name_len
= SBYTES (SYMBOL_NAME (base
));
8381 char *buf
= (char *) alloca (base_name_len
+ 6);
8384 bcopy (SDATA (SYMBOL_NAME (base
)), buf
, base_name_len
);
8385 subsidiaries
= Fmake_vector (make_number (3), Qnil
);
8386 for (i
= 0; i
< 3; i
++)
8388 bcopy (suffixes
[i
], buf
+ base_name_len
, strlen (suffixes
[i
]) + 1);
8389 ASET (subsidiaries
, i
, intern (buf
));
8391 return subsidiaries
;
8395 DEFUN ("define-coding-system-internal", Fdefine_coding_system_internal
,
8396 Sdefine_coding_system_internal
, coding_arg_max
, MANY
, 0,
8397 doc
: /* For internal use only.
8398 usage: (define-coding-system-internal ...) */)
8404 Lisp_Object spec_vec
; /* [ ATTRS ALIASE EOL_TYPE ] */
8405 Lisp_Object attrs
; /* Vector of attributes. */
8406 Lisp_Object eol_type
;
8407 Lisp_Object aliases
;
8408 Lisp_Object coding_type
, charset_list
, safe_charsets
;
8409 enum coding_category category
;
8410 Lisp_Object tail
, val
;
8411 int max_charset_id
= 0;
8414 if (nargs
< coding_arg_max
)
8417 attrs
= Fmake_vector (make_number (coding_attr_last_index
), Qnil
);
8419 name
= args
[coding_arg_name
];
8420 CHECK_SYMBOL (name
);
8421 CODING_ATTR_BASE_NAME (attrs
) = name
;
8423 val
= args
[coding_arg_mnemonic
];
8424 if (! STRINGP (val
))
8425 CHECK_CHARACTER (val
);
8426 CODING_ATTR_MNEMONIC (attrs
) = val
;
8428 coding_type
= args
[coding_arg_coding_type
];
8429 CHECK_SYMBOL (coding_type
);
8430 CODING_ATTR_TYPE (attrs
) = coding_type
;
8432 charset_list
= args
[coding_arg_charset_list
];
8433 if (SYMBOLP (charset_list
))
8435 if (EQ (charset_list
, Qiso_2022
))
8437 if (! EQ (coding_type
, Qiso_2022
))
8438 error ("Invalid charset-list");
8439 charset_list
= Viso_2022_charset_list
;
8441 else if (EQ (charset_list
, Qemacs_mule
))
8443 if (! EQ (coding_type
, Qemacs_mule
))
8444 error ("Invalid charset-list");
8445 charset_list
= Vemacs_mule_charset_list
;
8447 for (tail
= charset_list
; CONSP (tail
); tail
= XCDR (tail
))
8448 if (max_charset_id
< XFASTINT (XCAR (tail
)))
8449 max_charset_id
= XFASTINT (XCAR (tail
));
8453 charset_list
= Fcopy_sequence (charset_list
);
8454 for (tail
= charset_list
; !NILP (tail
); tail
= Fcdr (tail
))
8456 struct charset
*charset
;
8459 CHECK_CHARSET_GET_CHARSET (val
, charset
);
8460 if (EQ (coding_type
, Qiso_2022
)
8461 ? CHARSET_ISO_FINAL (charset
) < 0
8462 : EQ (coding_type
, Qemacs_mule
)
8463 ? CHARSET_EMACS_MULE_ID (charset
) < 0
8465 error ("Can't handle charset `%s'",
8466 SDATA (SYMBOL_NAME (CHARSET_NAME (charset
))));
8468 XSETCAR (tail
, make_number (charset
->id
));
8469 if (max_charset_id
< charset
->id
)
8470 max_charset_id
= charset
->id
;
8473 CODING_ATTR_CHARSET_LIST (attrs
) = charset_list
;
8475 safe_charsets
= Fmake_string (make_number (max_charset_id
+ 1),
8477 for (tail
= charset_list
; CONSP (tail
); tail
= XCDR (tail
))
8478 SSET (safe_charsets
, XFASTINT (XCAR (tail
)), 0);
8479 CODING_ATTR_SAFE_CHARSETS (attrs
) = safe_charsets
;
8481 CODING_ATTR_ASCII_COMPAT (attrs
) = args
[coding_arg_ascii_compatible_p
];
8483 val
= args
[coding_arg_decode_translation_table
];
8484 if (! CHAR_TABLE_P (val
) && ! CONSP (val
))
8486 CODING_ATTR_DECODE_TBL (attrs
) = val
;
8488 val
= args
[coding_arg_encode_translation_table
];
8489 if (! CHAR_TABLE_P (val
) && ! CONSP (val
))
8491 CODING_ATTR_ENCODE_TBL (attrs
) = val
;
8493 val
= args
[coding_arg_post_read_conversion
];
8495 CODING_ATTR_POST_READ (attrs
) = val
;
8497 val
= args
[coding_arg_pre_write_conversion
];
8499 CODING_ATTR_PRE_WRITE (attrs
) = val
;
8501 val
= args
[coding_arg_default_char
];
8503 CODING_ATTR_DEFAULT_CHAR (attrs
) = make_number (' ');
8506 CHECK_CHARACTER (val
);
8507 CODING_ATTR_DEFAULT_CHAR (attrs
) = val
;
8510 val
= args
[coding_arg_for_unibyte
];
8511 CODING_ATTR_FOR_UNIBYTE (attrs
) = NILP (val
) ? Qnil
: Qt
;
8513 val
= args
[coding_arg_plist
];
8515 CODING_ATTR_PLIST (attrs
) = val
;
8517 if (EQ (coding_type
, Qcharset
))
8519 /* Generate a lisp vector of 256 elements. Each element is nil,
8520 integer, or a list of charset IDs.
8522 If Nth element is nil, the byte code N is invalid in this
8525 If Nth element is a number NUM, N is the first byte of a
8526 charset whose ID is NUM.
8528 If Nth element is a list of charset IDs, N is the first byte
8529 of one of them. The list is sorted by dimensions of the
8530 charsets. A charset of smaller dimension comes firtst. */
8531 val
= Fmake_vector (make_number (256), Qnil
);
8533 for (tail
= charset_list
; CONSP (tail
); tail
= XCDR (tail
))
8535 struct charset
*charset
= CHARSET_FROM_ID (XFASTINT (XCAR (tail
)));
8536 int dim
= CHARSET_DIMENSION (charset
);
8537 int idx
= (dim
- 1) * 4;
8539 if (CHARSET_ASCII_COMPATIBLE_P (charset
))
8540 CODING_ATTR_ASCII_COMPAT (attrs
) = Qt
;
8542 for (i
= charset
->code_space
[idx
];
8543 i
<= charset
->code_space
[idx
+ 1]; i
++)
8545 Lisp_Object tmp
, tmp2
;
8548 tmp
= AREF (val
, i
);
8551 else if (NUMBERP (tmp
))
8553 dim2
= CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (tmp
)));
8555 tmp
= Fcons (XCAR (tail
), Fcons (tmp
, Qnil
));
8557 tmp
= Fcons (tmp
, Fcons (XCAR (tail
), Qnil
));
8561 for (tmp2
= tmp
; CONSP (tmp2
); tmp2
= XCDR (tmp2
))
8563 dim2
= CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (XCAR (tmp2
))));
8568 tmp
= nconc2 (tmp
, Fcons (XCAR (tail
), Qnil
));
8571 XSETCDR (tmp2
, Fcons (XCAR (tmp2
), XCDR (tmp2
)));
8572 XSETCAR (tmp2
, XCAR (tail
));
8578 ASET (attrs
, coding_attr_charset_valids
, val
);
8579 category
= coding_category_charset
;
8581 else if (EQ (coding_type
, Qccl
))
8585 if (nargs
< coding_arg_ccl_max
)
8588 val
= args
[coding_arg_ccl_decoder
];
8589 CHECK_CCL_PROGRAM (val
);
8591 val
= Fcopy_sequence (val
);
8592 ASET (attrs
, coding_attr_ccl_decoder
, val
);
8594 val
= args
[coding_arg_ccl_encoder
];
8595 CHECK_CCL_PROGRAM (val
);
8597 val
= Fcopy_sequence (val
);
8598 ASET (attrs
, coding_attr_ccl_encoder
, val
);
8600 val
= args
[coding_arg_ccl_valids
];
8601 valids
= Fmake_string (make_number (256), make_number (0));
8602 for (tail
= val
; !NILP (tail
); tail
= Fcdr (tail
))
8609 from
= to
= XINT (val
);
8610 if (from
< 0 || from
> 255)
8611 args_out_of_range_3 (val
, make_number (0), make_number (255));
8616 CHECK_NATNUM_CAR (val
);
8617 CHECK_NATNUM_CDR (val
);
8618 from
= XINT (XCAR (val
));
8620 args_out_of_range_3 (XCAR (val
),
8621 make_number (0), make_number (255));
8622 to
= XINT (XCDR (val
));
8623 if (to
< from
|| to
> 255)
8624 args_out_of_range_3 (XCDR (val
),
8625 XCAR (val
), make_number (255));
8627 for (i
= from
; i
<= to
; i
++)
8628 SSET (valids
, i
, 1);
8630 ASET (attrs
, coding_attr_ccl_valids
, valids
);
8632 category
= coding_category_ccl
;
8634 else if (EQ (coding_type
, Qutf_16
))
8636 Lisp_Object bom
, endian
;
8638 CODING_ATTR_ASCII_COMPAT (attrs
) = Qnil
;
8640 if (nargs
< coding_arg_utf16_max
)
8643 bom
= args
[coding_arg_utf16_bom
];
8644 if (! NILP (bom
) && ! EQ (bom
, Qt
))
8648 CHECK_CODING_SYSTEM (val
);
8650 CHECK_CODING_SYSTEM (val
);
8652 ASET (attrs
, coding_attr_utf_16_bom
, bom
);
8654 endian
= args
[coding_arg_utf16_endian
];
8655 CHECK_SYMBOL (endian
);
8658 else if (! EQ (endian
, Qbig
) && ! EQ (endian
, Qlittle
))
8659 error ("Invalid endian: %s", SDATA (SYMBOL_NAME (endian
)));
8660 ASET (attrs
, coding_attr_utf_16_endian
, endian
);
8662 category
= (CONSP (bom
)
8663 ? coding_category_utf_16_auto
8665 ? (EQ (endian
, Qbig
)
8666 ? coding_category_utf_16_be_nosig
8667 : coding_category_utf_16_le_nosig
)
8668 : (EQ (endian
, Qbig
)
8669 ? coding_category_utf_16_be
8670 : coding_category_utf_16_le
));
8672 else if (EQ (coding_type
, Qiso_2022
))
8674 Lisp_Object initial
, reg_usage
, request
, flags
;
8677 if (nargs
< coding_arg_iso2022_max
)
8680 initial
= Fcopy_sequence (args
[coding_arg_iso2022_initial
]);
8681 CHECK_VECTOR (initial
);
8682 for (i
= 0; i
< 4; i
++)
8684 val
= Faref (initial
, make_number (i
));
8687 struct charset
*charset
;
8689 CHECK_CHARSET_GET_CHARSET (val
, charset
);
8690 ASET (initial
, i
, make_number (CHARSET_ID (charset
)));
8691 if (i
== 0 && CHARSET_ASCII_COMPATIBLE_P (charset
))
8692 CODING_ATTR_ASCII_COMPAT (attrs
) = Qt
;
8695 ASET (initial
, i
, make_number (-1));
8698 reg_usage
= args
[coding_arg_iso2022_reg_usage
];
8699 CHECK_CONS (reg_usage
);
8700 CHECK_NUMBER_CAR (reg_usage
);
8701 CHECK_NUMBER_CDR (reg_usage
);
8703 request
= Fcopy_sequence (args
[coding_arg_iso2022_request
]);
8704 for (tail
= request
; ! NILP (tail
); tail
= Fcdr (tail
))
8712 CHECK_CHARSET_GET_ID (tmp
, id
);
8713 CHECK_NATNUM_CDR (val
);
8714 if (XINT (XCDR (val
)) >= 4)
8715 error ("Invalid graphic register number: %d", XINT (XCDR (val
)));
8716 XSETCAR (val
, make_number (id
));
8719 flags
= args
[coding_arg_iso2022_flags
];
8720 CHECK_NATNUM (flags
);
8722 if (EQ (args
[coding_arg_charset_list
], Qiso_2022
))
8723 flags
= make_number (i
| CODING_ISO_FLAG_FULL_SUPPORT
);
8725 ASET (attrs
, coding_attr_iso_initial
, initial
);
8726 ASET (attrs
, coding_attr_iso_usage
, reg_usage
);
8727 ASET (attrs
, coding_attr_iso_request
, request
);
8728 ASET (attrs
, coding_attr_iso_flags
, flags
);
8729 setup_iso_safe_charsets (attrs
);
8731 if (i
& CODING_ISO_FLAG_SEVEN_BITS
)
8732 category
= ((i
& (CODING_ISO_FLAG_LOCKING_SHIFT
8733 | CODING_ISO_FLAG_SINGLE_SHIFT
))
8734 ? coding_category_iso_7_else
8735 : EQ (args
[coding_arg_charset_list
], Qiso_2022
)
8736 ? coding_category_iso_7
8737 : coding_category_iso_7_tight
);
8740 int id
= XINT (AREF (initial
, 1));
8742 category
= (((i
& CODING_ISO_FLAG_LOCKING_SHIFT
)
8743 || EQ (args
[coding_arg_charset_list
], Qiso_2022
)
8745 ? coding_category_iso_8_else
8746 : (CHARSET_DIMENSION (CHARSET_FROM_ID (id
)) == 1)
8747 ? coding_category_iso_8_1
8748 : coding_category_iso_8_2
);
8750 if (category
!= coding_category_iso_8_1
8751 && category
!= coding_category_iso_8_2
)
8752 CODING_ATTR_ASCII_COMPAT (attrs
) = Qnil
;
8754 else if (EQ (coding_type
, Qemacs_mule
))
8756 if (EQ (args
[coding_arg_charset_list
], Qemacs_mule
))
8757 ASET (attrs
, coding_attr_emacs_mule_full
, Qt
);
8758 CODING_ATTR_ASCII_COMPAT (attrs
) = Qt
;
8759 category
= coding_category_emacs_mule
;
8761 else if (EQ (coding_type
, Qshift_jis
))
8764 struct charset
*charset
;
8766 if (XINT (Flength (charset_list
)) != 3
8767 && XINT (Flength (charset_list
)) != 4)
8768 error ("There should be three or four charsets");
8770 charset
= CHARSET_FROM_ID (XINT (XCAR (charset_list
)));
8771 if (CHARSET_DIMENSION (charset
) != 1)
8772 error ("Dimension of charset %s is not one",
8773 SDATA (SYMBOL_NAME (CHARSET_NAME (charset
))));
8774 if (CHARSET_ASCII_COMPATIBLE_P (charset
))
8775 CODING_ATTR_ASCII_COMPAT (attrs
) = Qt
;
8777 charset_list
= XCDR (charset_list
);
8778 charset
= CHARSET_FROM_ID (XINT (XCAR (charset_list
)));
8779 if (CHARSET_DIMENSION (charset
) != 1)
8780 error ("Dimension of charset %s is not one",
8781 SDATA (SYMBOL_NAME (CHARSET_NAME (charset
))));
8783 charset_list
= XCDR (charset_list
);
8784 charset
= CHARSET_FROM_ID (XINT (XCAR (charset_list
)));
8785 if (CHARSET_DIMENSION (charset
) != 2)
8786 error ("Dimension of charset %s is not two",
8787 SDATA (SYMBOL_NAME (CHARSET_NAME (charset
))));
8789 charset_list
= XCDR (charset_list
);
8790 if (! NILP (charset_list
))
8792 charset
= CHARSET_FROM_ID (XINT (XCAR (charset_list
)));
8793 if (CHARSET_DIMENSION (charset
) != 2)
8794 error ("Dimension of charset %s is not two",
8795 SDATA (SYMBOL_NAME (CHARSET_NAME (charset
))));
8798 category
= coding_category_sjis
;
8799 Vsjis_coding_system
= name
;
8801 else if (EQ (coding_type
, Qbig5
))
8803 struct charset
*charset
;
8805 if (XINT (Flength (charset_list
)) != 2)
8806 error ("There should be just two charsets");
8808 charset
= CHARSET_FROM_ID (XINT (XCAR (charset_list
)));
8809 if (CHARSET_DIMENSION (charset
) != 1)
8810 error ("Dimension of charset %s is not one",
8811 SDATA (SYMBOL_NAME (CHARSET_NAME (charset
))));
8812 if (CHARSET_ASCII_COMPATIBLE_P (charset
))
8813 CODING_ATTR_ASCII_COMPAT (attrs
) = Qt
;
8815 charset_list
= XCDR (charset_list
);
8816 charset
= CHARSET_FROM_ID (XINT (XCAR (charset_list
)));
8817 if (CHARSET_DIMENSION (charset
) != 2)
8818 error ("Dimension of charset %s is not two",
8819 SDATA (SYMBOL_NAME (CHARSET_NAME (charset
))));
8821 category
= coding_category_big5
;
8822 Vbig5_coding_system
= name
;
8824 else if (EQ (coding_type
, Qraw_text
))
8826 category
= coding_category_raw_text
;
8827 CODING_ATTR_ASCII_COMPAT (attrs
) = Qt
;
8829 else if (EQ (coding_type
, Qutf_8
))
8831 category
= coding_category_utf_8
;
8832 CODING_ATTR_ASCII_COMPAT (attrs
) = Qt
;
8834 else if (EQ (coding_type
, Qundecided
))
8835 category
= coding_category_undecided
;
8837 error ("Invalid coding system type: %s",
8838 SDATA (SYMBOL_NAME (coding_type
)));
8840 CODING_ATTR_CATEGORY (attrs
) = make_number (category
);
8841 CODING_ATTR_PLIST (attrs
)
8842 = Fcons (QCcategory
, Fcons (AREF (Vcoding_category_table
, category
),
8843 CODING_ATTR_PLIST (attrs
)));
8845 eol_type
= args
[coding_arg_eol_type
];
8846 if (! NILP (eol_type
)
8847 && ! EQ (eol_type
, Qunix
)
8848 && ! EQ (eol_type
, Qdos
)
8849 && ! EQ (eol_type
, Qmac
))
8850 error ("Invalid eol-type");
8852 aliases
= Fcons (name
, Qnil
);
8854 if (NILP (eol_type
))
8856 eol_type
= make_subsidiaries (name
);
8857 for (i
= 0; i
< 3; i
++)
8859 Lisp_Object this_spec
, this_name
, this_aliases
, this_eol_type
;
8861 this_name
= AREF (eol_type
, i
);
8862 this_aliases
= Fcons (this_name
, Qnil
);
8863 this_eol_type
= (i
== 0 ? Qunix
: i
== 1 ? Qdos
: Qmac
);
8864 this_spec
= Fmake_vector (make_number (3), attrs
);
8865 ASET (this_spec
, 1, this_aliases
);
8866 ASET (this_spec
, 2, this_eol_type
);
8867 Fputhash (this_name
, this_spec
, Vcoding_system_hash_table
);
8868 Vcoding_system_list
= Fcons (this_name
, Vcoding_system_list
);
8869 Vcoding_system_alist
= Fcons (Fcons (Fsymbol_name (this_name
), Qnil
),
8870 Vcoding_system_alist
);
8874 spec_vec
= Fmake_vector (make_number (3), attrs
);
8875 ASET (spec_vec
, 1, aliases
);
8876 ASET (spec_vec
, 2, eol_type
);
8878 Fputhash (name
, spec_vec
, Vcoding_system_hash_table
);
8879 Vcoding_system_list
= Fcons (name
, Vcoding_system_list
);
8880 Vcoding_system_alist
= Fcons (Fcons (Fsymbol_name (name
), Qnil
),
8881 Vcoding_system_alist
);
8884 int id
= coding_categories
[category
].id
;
8886 if (id
< 0 || EQ (name
, CODING_ID_NAME (id
)))
8887 setup_coding_system (name
, &coding_categories
[category
]);
8893 return Fsignal (Qwrong_number_of_arguments
,
8894 Fcons (intern ("define-coding-system-internal"),
8895 make_number (nargs
)));
8899 DEFUN ("coding-system-put", Fcoding_system_put
, Scoding_system_put
,
8901 doc
: /* Change value in CODING-SYSTEM's property list PROP to VAL. */)
8902 (coding_system
, prop
, val
)
8903 Lisp_Object coding_system
, prop
, val
;
8905 Lisp_Object spec
, attrs
;
8907 CHECK_CODING_SYSTEM_GET_SPEC (coding_system
, spec
);
8908 attrs
= AREF (spec
, 0);
8909 if (EQ (prop
, QCmnemonic
))
8911 if (! STRINGP (val
))
8912 CHECK_CHARACTER (val
);
8913 CODING_ATTR_MNEMONIC (attrs
) = val
;
8915 else if (EQ (prop
, QCdefalut_char
))
8918 val
= make_number (' ');
8920 CHECK_CHARACTER (val
);
8921 CODING_ATTR_DEFAULT_CHAR (attrs
) = val
;
8923 else if (EQ (prop
, QCdecode_translation_table
))
8925 if (! CHAR_TABLE_P (val
) && ! CONSP (val
))
8927 CODING_ATTR_DECODE_TBL (attrs
) = val
;
8929 else if (EQ (prop
, QCencode_translation_table
))
8931 if (! CHAR_TABLE_P (val
) && ! CONSP (val
))
8933 CODING_ATTR_ENCODE_TBL (attrs
) = val
;
8935 else if (EQ (prop
, QCpost_read_conversion
))
8938 CODING_ATTR_POST_READ (attrs
) = val
;
8940 else if (EQ (prop
, QCpre_write_conversion
))
8943 CODING_ATTR_PRE_WRITE (attrs
) = val
;
8946 CODING_ATTR_PLIST (attrs
)
8947 = Fplist_put (CODING_ATTR_PLIST (attrs
), prop
, val
);
8952 DEFUN ("define-coding-system-alias", Fdefine_coding_system_alias
,
8953 Sdefine_coding_system_alias
, 2, 2, 0,
8954 doc
: /* Define ALIAS as an alias for CODING-SYSTEM. */)
8955 (alias
, coding_system
)
8956 Lisp_Object alias
, coding_system
;
8958 Lisp_Object spec
, aliases
, eol_type
;
8960 CHECK_SYMBOL (alias
);
8961 CHECK_CODING_SYSTEM_GET_SPEC (coding_system
, spec
);
8962 aliases
= AREF (spec
, 1);
8963 /* ALISES should be a list of length more than zero, and the first
8964 element is a base coding system. Append ALIAS at the tail of the
8966 while (!NILP (XCDR (aliases
)))
8967 aliases
= XCDR (aliases
);
8968 XSETCDR (aliases
, Fcons (alias
, Qnil
));
8970 eol_type
= AREF (spec
, 2);
8971 if (VECTORP (eol_type
))
8973 Lisp_Object subsidiaries
;
8976 subsidiaries
= make_subsidiaries (alias
);
8977 for (i
= 0; i
< 3; i
++)
8978 Fdefine_coding_system_alias (AREF (subsidiaries
, i
),
8979 AREF (eol_type
, i
));
8982 Fputhash (alias
, spec
, Vcoding_system_hash_table
);
8983 Vcoding_system_list
= Fcons (alias
, Vcoding_system_list
);
8984 Vcoding_system_alist
= Fcons (Fcons (Fsymbol_name (alias
), Qnil
),
8985 Vcoding_system_alist
);
8990 DEFUN ("coding-system-base", Fcoding_system_base
, Scoding_system_base
,
8992 doc
: /* Return the base of CODING-SYSTEM.
8993 Any alias or subsidiary coding system is not a base coding system. */)
8995 Lisp_Object coding_system
;
8997 Lisp_Object spec
, attrs
;
8999 if (NILP (coding_system
))
9000 return (Qno_conversion
);
9001 CHECK_CODING_SYSTEM_GET_SPEC (coding_system
, spec
);
9002 attrs
= AREF (spec
, 0);
9003 return CODING_ATTR_BASE_NAME (attrs
);
9006 DEFUN ("coding-system-plist", Fcoding_system_plist
, Scoding_system_plist
,
9008 doc
: "Return the property list of CODING-SYSTEM.")
9010 Lisp_Object coding_system
;
9012 Lisp_Object spec
, attrs
;
9014 if (NILP (coding_system
))
9015 coding_system
= Qno_conversion
;
9016 CHECK_CODING_SYSTEM_GET_SPEC (coding_system
, spec
);
9017 attrs
= AREF (spec
, 0);
9018 return CODING_ATTR_PLIST (attrs
);
9022 DEFUN ("coding-system-aliases", Fcoding_system_aliases
, Scoding_system_aliases
,
9024 doc
: /* Return the list of aliases of CODING-SYSTEM. */)
9026 Lisp_Object coding_system
;
9030 if (NILP (coding_system
))
9031 coding_system
= Qno_conversion
;
9032 CHECK_CODING_SYSTEM_GET_SPEC (coding_system
, spec
);
9033 return AREF (spec
, 1);
9036 DEFUN ("coding-system-eol-type", Fcoding_system_eol_type
,
9037 Scoding_system_eol_type
, 1, 1, 0,
9038 doc
: /* Return eol-type of CODING-SYSTEM.
9039 An eol-type is integer 0, 1, 2, or a vector of coding systems.
9041 Integer values 0, 1, and 2 indicate a format of end-of-line; LF, CRLF,
9042 and CR respectively.
9044 A vector value indicates that a format of end-of-line should be
9045 detected automatically. Nth element of the vector is the subsidiary
9046 coding system whose eol-type is N. */)
9048 Lisp_Object coding_system
;
9050 Lisp_Object spec
, eol_type
;
9053 if (NILP (coding_system
))
9054 coding_system
= Qno_conversion
;
9055 if (! CODING_SYSTEM_P (coding_system
))
9057 spec
= CODING_SYSTEM_SPEC (coding_system
);
9058 eol_type
= AREF (spec
, 2);
9059 if (VECTORP (eol_type
))
9060 return Fcopy_sequence (eol_type
);
9061 n
= EQ (eol_type
, Qunix
) ? 0 : EQ (eol_type
, Qdos
) ? 1 : 2;
9062 return make_number (n
);
9068 /*** 9. Post-amble ***/
9075 for (i
= 0; i
< coding_category_max
; i
++)
9077 coding_categories
[i
].id
= -1;
9078 coding_priorities
[i
] = i
;
9081 /* ISO2022 specific initialize routine. */
9082 for (i
= 0; i
< 0x20; i
++)
9083 iso_code_class
[i
] = ISO_control_0
;
9084 for (i
= 0x21; i
< 0x7F; i
++)
9085 iso_code_class
[i
] = ISO_graphic_plane_0
;
9086 for (i
= 0x80; i
< 0xA0; i
++)
9087 iso_code_class
[i
] = ISO_control_1
;
9088 for (i
= 0xA1; i
< 0xFF; i
++)
9089 iso_code_class
[i
] = ISO_graphic_plane_1
;
9090 iso_code_class
[0x20] = iso_code_class
[0x7F] = ISO_0x20_or_0x7F
;
9091 iso_code_class
[0xA0] = iso_code_class
[0xFF] = ISO_0xA0_or_0xFF
;
9092 iso_code_class
[ISO_CODE_SO
] = ISO_shift_out
;
9093 iso_code_class
[ISO_CODE_SI
] = ISO_shift_in
;
9094 iso_code_class
[ISO_CODE_SS2_7
] = ISO_single_shift_2_7
;
9095 iso_code_class
[ISO_CODE_ESC
] = ISO_escape
;
9096 iso_code_class
[ISO_CODE_SS2
] = ISO_single_shift_2
;
9097 iso_code_class
[ISO_CODE_SS3
] = ISO_single_shift_3
;
9098 iso_code_class
[ISO_CODE_CSI
] = ISO_control_sequence_introducer
;
9100 for (i
= 0; i
< 256; i
++)
9102 emacs_mule_bytes
[i
] = 1;
9104 emacs_mule_bytes
[EMACS_MULE_LEADING_CODE_PRIVATE_11
] = 3;
9105 emacs_mule_bytes
[EMACS_MULE_LEADING_CODE_PRIVATE_12
] = 3;
9106 emacs_mule_bytes
[EMACS_MULE_LEADING_CODE_PRIVATE_21
] = 4;
9107 emacs_mule_bytes
[EMACS_MULE_LEADING_CODE_PRIVATE_22
] = 4;
9115 staticpro (&Vcoding_system_hash_table
);
9117 Lisp_Object args
[2];
9120 Vcoding_system_hash_table
= Fmake_hash_table (2, args
);
9123 staticpro (&Vsjis_coding_system
);
9124 Vsjis_coding_system
= Qnil
;
9126 staticpro (&Vbig5_coding_system
);
9127 Vbig5_coding_system
= Qnil
;
9129 staticpro (&Vcode_conversion_reused_workbuf
);
9130 Vcode_conversion_reused_workbuf
= Qnil
;
9132 staticpro (&Vcode_conversion_workbuf_name
);
9133 Vcode_conversion_workbuf_name
= build_string (" *code-conversion-work*");
9135 reused_workbuf_in_use
= 0;
9137 DEFSYM (Qcharset
, "charset");
9138 DEFSYM (Qtarget_idx
, "target-idx");
9139 DEFSYM (Qcoding_system_history
, "coding-system-history");
9140 Fset (Qcoding_system_history
, Qnil
);
9142 /* Target FILENAME is the first argument. */
9143 Fput (Qinsert_file_contents
, Qtarget_idx
, make_number (0));
9144 /* Target FILENAME is the third argument. */
9145 Fput (Qwrite_region
, Qtarget_idx
, make_number (2));
9147 DEFSYM (Qcall_process
, "call-process");
9148 /* Target PROGRAM is the first argument. */
9149 Fput (Qcall_process
, Qtarget_idx
, make_number (0));
9151 DEFSYM (Qcall_process_region
, "call-process-region");
9152 /* Target PROGRAM is the third argument. */
9153 Fput (Qcall_process_region
, Qtarget_idx
, make_number (2));
9155 DEFSYM (Qstart_process
, "start-process");
9156 /* Target PROGRAM is the third argument. */
9157 Fput (Qstart_process
, Qtarget_idx
, make_number (2));
9159 DEFSYM (Qopen_network_stream
, "open-network-stream");
9160 /* Target SERVICE is the fourth argument. */
9161 Fput (Qopen_network_stream
, Qtarget_idx
, make_number (3));
9163 DEFSYM (Qcoding_system
, "coding-system");
9164 DEFSYM (Qcoding_aliases
, "coding-aliases");
9166 DEFSYM (Qeol_type
, "eol-type");
9167 DEFSYM (Qunix
, "unix");
9168 DEFSYM (Qdos
, "dos");
9170 DEFSYM (Qbuffer_file_coding_system
, "buffer-file-coding-system");
9171 DEFSYM (Qpost_read_conversion
, "post-read-conversion");
9172 DEFSYM (Qpre_write_conversion
, "pre-write-conversion");
9173 DEFSYM (Qdefault_char
, "default-char");
9174 DEFSYM (Qundecided
, "undecided");
9175 DEFSYM (Qno_conversion
, "no-conversion");
9176 DEFSYM (Qraw_text
, "raw-text");
9178 DEFSYM (Qiso_2022
, "iso-2022");
9180 DEFSYM (Qutf_8
, "utf-8");
9181 DEFSYM (Qutf_8_emacs
, "utf-8-emacs");
9183 DEFSYM (Qutf_16
, "utf-16");
9184 DEFSYM (Qbig
, "big");
9185 DEFSYM (Qlittle
, "little");
9187 DEFSYM (Qshift_jis
, "shift-jis");
9188 DEFSYM (Qbig5
, "big5");
9190 DEFSYM (Qcoding_system_p
, "coding-system-p");
9192 DEFSYM (Qcoding_system_error
, "coding-system-error");
9193 Fput (Qcoding_system_error
, Qerror_conditions
,
9194 Fcons (Qcoding_system_error
, Fcons (Qerror
, Qnil
)));
9195 Fput (Qcoding_system_error
, Qerror_message
,
9196 build_string ("Invalid coding system"));
9198 /* Intern this now in case it isn't already done.
9199 Setting this variable twice is harmless.
9200 But don't staticpro it here--that is done in alloc.c. */
9201 Qchar_table_extra_slots
= intern ("char-table-extra-slots");
9203 DEFSYM (Qtranslation_table
, "translation-table");
9204 Fput (Qtranslation_table
, Qchar_table_extra_slots
, make_number (2));
9205 DEFSYM (Qtranslation_table_id
, "translation-table-id");
9206 DEFSYM (Qtranslation_table_for_decode
, "translation-table-for-decode");
9207 DEFSYM (Qtranslation_table_for_encode
, "translation-table-for-encode");
9209 DEFSYM (Qvalid_codes
, "valid-codes");
9211 DEFSYM (Qemacs_mule
, "emacs-mule");
9213 DEFSYM (QCcategory
, ":category");
9214 DEFSYM (QCmnemonic
, ":mnemonic");
9215 DEFSYM (QCdefalut_char
, ":default-char");
9216 DEFSYM (QCdecode_translation_table
, ":decode-translation-table");
9217 DEFSYM (QCencode_translation_table
, ":encode-translation-table");
9218 DEFSYM (QCpost_read_conversion
, ":post-read-conversion");
9219 DEFSYM (QCpre_write_conversion
, ":pre-write-conversion");
9221 Vcoding_category_table
9222 = Fmake_vector (make_number (coding_category_max
), Qnil
);
9223 staticpro (&Vcoding_category_table
);
9224 /* Followings are target of code detection. */
9225 ASET (Vcoding_category_table
, coding_category_iso_7
,
9226 intern ("coding-category-iso-7"));
9227 ASET (Vcoding_category_table
, coding_category_iso_7_tight
,
9228 intern ("coding-category-iso-7-tight"));
9229 ASET (Vcoding_category_table
, coding_category_iso_8_1
,
9230 intern ("coding-category-iso-8-1"));
9231 ASET (Vcoding_category_table
, coding_category_iso_8_2
,
9232 intern ("coding-category-iso-8-2"));
9233 ASET (Vcoding_category_table
, coding_category_iso_7_else
,
9234 intern ("coding-category-iso-7-else"));
9235 ASET (Vcoding_category_table
, coding_category_iso_8_else
,
9236 intern ("coding-category-iso-8-else"));
9237 ASET (Vcoding_category_table
, coding_category_utf_8
,
9238 intern ("coding-category-utf-8"));
9239 ASET (Vcoding_category_table
, coding_category_utf_16_be
,
9240 intern ("coding-category-utf-16-be"));
9241 ASET (Vcoding_category_table
, coding_category_utf_16_auto
,
9242 intern ("coding-category-utf-16-auto"));
9243 ASET (Vcoding_category_table
, coding_category_utf_16_le
,
9244 intern ("coding-category-utf-16-le"));
9245 ASET (Vcoding_category_table
, coding_category_utf_16_be_nosig
,
9246 intern ("coding-category-utf-16-be-nosig"));
9247 ASET (Vcoding_category_table
, coding_category_utf_16_le_nosig
,
9248 intern ("coding-category-utf-16-le-nosig"));
9249 ASET (Vcoding_category_table
, coding_category_charset
,
9250 intern ("coding-category-charset"));
9251 ASET (Vcoding_category_table
, coding_category_sjis
,
9252 intern ("coding-category-sjis"));
9253 ASET (Vcoding_category_table
, coding_category_big5
,
9254 intern ("coding-category-big5"));
9255 ASET (Vcoding_category_table
, coding_category_ccl
,
9256 intern ("coding-category-ccl"));
9257 ASET (Vcoding_category_table
, coding_category_emacs_mule
,
9258 intern ("coding-category-emacs-mule"));
9259 /* Followings are NOT target of code detection. */
9260 ASET (Vcoding_category_table
, coding_category_raw_text
,
9261 intern ("coding-category-raw-text"));
9262 ASET (Vcoding_category_table
, coding_category_undecided
,
9263 intern ("coding-category-undecided"));
9265 DEFSYM (Qinsufficient_source
, "insufficient-source");
9266 DEFSYM (Qinconsistent_eol
, "inconsistent-eol");
9267 DEFSYM (Qinvalid_source
, "invalid-source");
9268 DEFSYM (Qinterrupted
, "interrupted");
9269 DEFSYM (Qinsufficient_memory
, "insufficient-memory");
9271 defsubr (&Scoding_system_p
);
9272 defsubr (&Sread_coding_system
);
9273 defsubr (&Sread_non_nil_coding_system
);
9274 defsubr (&Scheck_coding_system
);
9275 defsubr (&Sdetect_coding_region
);
9276 defsubr (&Sdetect_coding_string
);
9277 defsubr (&Sfind_coding_systems_region_internal
);
9278 defsubr (&Sunencodable_char_position
);
9279 defsubr (&Scheck_coding_systems_region
);
9280 defsubr (&Sdecode_coding_region
);
9281 defsubr (&Sencode_coding_region
);
9282 defsubr (&Sdecode_coding_string
);
9283 defsubr (&Sencode_coding_string
);
9284 defsubr (&Sdecode_sjis_char
);
9285 defsubr (&Sencode_sjis_char
);
9286 defsubr (&Sdecode_big5_char
);
9287 defsubr (&Sencode_big5_char
);
9288 defsubr (&Sset_terminal_coding_system_internal
);
9289 defsubr (&Sset_safe_terminal_coding_system_internal
);
9290 defsubr (&Sterminal_coding_system
);
9291 defsubr (&Sset_keyboard_coding_system_internal
);
9292 defsubr (&Skeyboard_coding_system
);
9293 defsubr (&Sfind_operation_coding_system
);
9294 defsubr (&Sset_coding_system_priority
);
9295 defsubr (&Sdefine_coding_system_internal
);
9296 defsubr (&Sdefine_coding_system_alias
);
9297 defsubr (&Scoding_system_put
);
9298 defsubr (&Scoding_system_base
);
9299 defsubr (&Scoding_system_plist
);
9300 defsubr (&Scoding_system_aliases
);
9301 defsubr (&Scoding_system_eol_type
);
9302 defsubr (&Scoding_system_priority_list
);
9304 DEFVAR_LISP ("coding-system-list", &Vcoding_system_list
,
9305 doc
: /* List of coding systems.
9307 Do not alter the value of this variable manually. This variable should be
9308 updated by the functions `define-coding-system' and
9309 `define-coding-system-alias'. */);
9310 Vcoding_system_list
= Qnil
;
9312 DEFVAR_LISP ("coding-system-alist", &Vcoding_system_alist
,
9313 doc
: /* Alist of coding system names.
9314 Each element is one element list of coding system name.
9315 This variable is given to `completing-read' as TABLE argument.
9317 Do not alter the value of this variable manually. This variable should be
9318 updated by the functions `make-coding-system' and
9319 `define-coding-system-alias'. */);
9320 Vcoding_system_alist
= Qnil
;
9322 DEFVAR_LISP ("coding-category-list", &Vcoding_category_list
,
9323 doc
: /* List of coding-categories (symbols) ordered by priority.
9325 On detecting a coding system, Emacs tries code detection algorithms
9326 associated with each coding-category one by one in this order. When
9327 one algorithm agrees with a byte sequence of source text, the coding
9328 system bound to the corresponding coding-category is selected. */);
9332 Vcoding_category_list
= Qnil
;
9333 for (i
= coding_category_max
- 1; i
>= 0; i
--)
9334 Vcoding_category_list
9335 = Fcons (XVECTOR (Vcoding_category_table
)->contents
[i
],
9336 Vcoding_category_list
);
9339 DEFVAR_LISP ("coding-system-for-read", &Vcoding_system_for_read
,
9340 doc
: /* Specify the coding system for read operations.
9341 It is useful to bind this variable with `let', but do not set it globally.
9342 If the value is a coding system, it is used for decoding on read operation.
9343 If not, an appropriate element is used from one of the coding system alists:
9344 There are three such tables, `file-coding-system-alist',
9345 `process-coding-system-alist', and `network-coding-system-alist'. */);
9346 Vcoding_system_for_read
= Qnil
;
9348 DEFVAR_LISP ("coding-system-for-write", &Vcoding_system_for_write
,
9349 doc
: /* Specify the coding system for write operations.
9350 Programs bind this variable with `let', but you should not set it globally.
9351 If the value is a coding system, it is used for encoding of output,
9352 when writing it to a file and when sending it to a file or subprocess.
9354 If this does not specify a coding system, an appropriate element
9355 is used from one of the coding system alists:
9356 There are three such tables, `file-coding-system-alist',
9357 `process-coding-system-alist', and `network-coding-system-alist'.
9358 For output to files, if the above procedure does not specify a coding system,
9359 the value of `buffer-file-coding-system' is used. */);
9360 Vcoding_system_for_write
= Qnil
;
9362 DEFVAR_LISP ("last-coding-system-used", &Vlast_coding_system_used
,
9364 Coding system used in the latest file or process I/O. */);
9365 Vlast_coding_system_used
= Qnil
;
9367 DEFVAR_LISP ("last-code-conversion-error", &Vlast_code_conversion_error
,
9369 Error status of the last code conversion.
9371 When an error was detected in the last code conversion, this variable
9372 is set to one of the following symbols.
9373 `insufficient-source'
9377 `insufficient-memory'
9378 When no error was detected, the value doesn't change. So, to check
9379 the error status of a code conversion by this variable, you must
9380 explicitly set this variable to nil before performing code
9382 Vlast_code_conversion_error
= Qnil
;
9384 DEFVAR_BOOL ("inhibit-eol-conversion", &inhibit_eol_conversion
,
9386 *Non-nil means always inhibit code conversion of end-of-line format.
9387 See info node `Coding Systems' and info node `Text and Binary' concerning
9388 such conversion. */);
9389 inhibit_eol_conversion
= 0;
9391 DEFVAR_BOOL ("inherit-process-coding-system", &inherit_process_coding_system
,
9393 Non-nil means process buffer inherits coding system of process output.
9394 Bind it to t if the process output is to be treated as if it were a file
9395 read from some filesystem. */);
9396 inherit_process_coding_system
= 0;
9398 DEFVAR_LISP ("file-coding-system-alist", &Vfile_coding_system_alist
,
9400 Alist to decide a coding system to use for a file I/O operation.
9401 The format is ((PATTERN . VAL) ...),
9402 where PATTERN is a regular expression matching a file name,
9403 VAL is a coding system, a cons of coding systems, or a function symbol.
9404 If VAL is a coding system, it is used for both decoding and encoding
9406 If VAL is a cons of coding systems, the car part is used for decoding,
9407 and the cdr part is used for encoding.
9408 If VAL is a function symbol, the function must return a coding system
9409 or a cons of coding systems which are used as above. The function gets
9410 the arguments with which `find-operation-coding-systems' was called.
9412 See also the function `find-operation-coding-system'
9413 and the variable `auto-coding-alist'. */);
9414 Vfile_coding_system_alist
= Qnil
;
9416 DEFVAR_LISP ("process-coding-system-alist", &Vprocess_coding_system_alist
,
9418 Alist to decide a coding system to use for a process I/O operation.
9419 The format is ((PATTERN . VAL) ...),
9420 where PATTERN is a regular expression matching a program name,
9421 VAL is a coding system, a cons of coding systems, or a function symbol.
9422 If VAL is a coding system, it is used for both decoding what received
9423 from the program and encoding what sent to the program.
9424 If VAL is a cons of coding systems, the car part is used for decoding,
9425 and the cdr part is used for encoding.
9426 If VAL is a function symbol, the function must return a coding system
9427 or a cons of coding systems which are used as above.
9429 See also the function `find-operation-coding-system'. */);
9430 Vprocess_coding_system_alist
= Qnil
;
9432 DEFVAR_LISP ("network-coding-system-alist", &Vnetwork_coding_system_alist
,
9434 Alist to decide a coding system to use for a network I/O operation.
9435 The format is ((PATTERN . VAL) ...),
9436 where PATTERN is a regular expression matching a network service name
9437 or is a port number to connect to,
9438 VAL is a coding system, a cons of coding systems, or a function symbol.
9439 If VAL is a coding system, it is used for both decoding what received
9440 from the network stream and encoding what sent to the network stream.
9441 If VAL is a cons of coding systems, the car part is used for decoding,
9442 and the cdr part is used for encoding.
9443 If VAL is a function symbol, the function must return a coding system
9444 or a cons of coding systems which are used as above.
9446 See also the function `find-operation-coding-system'. */);
9447 Vnetwork_coding_system_alist
= Qnil
;
9449 DEFVAR_LISP ("locale-coding-system", &Vlocale_coding_system
,
9450 doc
: /* Coding system to use with system messages.
9451 Also used for decoding keyboard input on X Window system. */);
9452 Vlocale_coding_system
= Qnil
;
9454 /* The eol mnemonics are reset in startup.el system-dependently. */
9455 DEFVAR_LISP ("eol-mnemonic-unix", &eol_mnemonic_unix
,
9457 *String displayed in mode line for UNIX-like (LF) end-of-line format. */);
9458 eol_mnemonic_unix
= build_string (":");
9460 DEFVAR_LISP ("eol-mnemonic-dos", &eol_mnemonic_dos
,
9462 *String displayed in mode line for DOS-like (CRLF) end-of-line format. */);
9463 eol_mnemonic_dos
= build_string ("\\");
9465 DEFVAR_LISP ("eol-mnemonic-mac", &eol_mnemonic_mac
,
9467 *String displayed in mode line for MAC-like (CR) end-of-line format. */);
9468 eol_mnemonic_mac
= build_string ("/");
9470 DEFVAR_LISP ("eol-mnemonic-undecided", &eol_mnemonic_undecided
,
9472 *String displayed in mode line when end-of-line format is not yet determined. */);
9473 eol_mnemonic_undecided
= build_string (":");
9475 DEFVAR_LISP ("enable-character-translation", &Venable_character_translation
,
9477 *Non-nil enables character translation while encoding and decoding. */);
9478 Venable_character_translation
= Qt
;
9480 DEFVAR_LISP ("standard-translation-table-for-decode",
9481 &Vstandard_translation_table_for_decode
,
9482 doc
: /* Table for translating characters while decoding. */);
9483 Vstandard_translation_table_for_decode
= Qnil
;
9485 DEFVAR_LISP ("standard-translation-table-for-encode",
9486 &Vstandard_translation_table_for_encode
,
9487 doc
: /* Table for translating characters while encoding. */);
9488 Vstandard_translation_table_for_encode
= Qnil
;
9490 DEFVAR_LISP ("charset-revision-table", &Vcharset_revision_table
,
9491 doc
: /* Alist of charsets vs revision numbers.
9492 While encoding, if a charset (car part of an element) is found,
9493 designate it with the escape sequence identifying revision (cdr part
9494 of the element). */);
9495 Vcharset_revision_table
= Qnil
;
9497 DEFVAR_LISP ("default-process-coding-system",
9498 &Vdefault_process_coding_system
,
9499 doc
: /* Cons of coding systems used for process I/O by default.
9500 The car part is used for decoding a process output,
9501 the cdr part is used for encoding a text to be sent to a process. */);
9502 Vdefault_process_coding_system
= Qnil
;
9504 DEFVAR_LISP ("latin-extra-code-table", &Vlatin_extra_code_table
,
9506 Table of extra Latin codes in the range 128..159 (inclusive).
9507 This is a vector of length 256.
9508 If Nth element is non-nil, the existence of code N in a file
9509 \(or output of subprocess) doesn't prevent it to be detected as
9510 a coding system of ISO 2022 variant which has a flag
9511 `accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file
9512 or reading output of a subprocess.
9513 Only 128th through 159th elements has a meaning. */);
9514 Vlatin_extra_code_table
= Fmake_vector (make_number (256), Qnil
);
9516 DEFVAR_LISP ("select-safe-coding-system-function",
9517 &Vselect_safe_coding_system_function
,
9519 Function to call to select safe coding system for encoding a text.
9521 If set, this function is called to force a user to select a proper
9522 coding system which can encode the text in the case that a default
9523 coding system used in each operation can't encode the text.
9525 The default value is `select-safe-coding-system' (which see). */);
9526 Vselect_safe_coding_system_function
= Qnil
;
9528 DEFVAR_BOOL ("coding-system-require-warning",
9529 &coding_system_require_warning
,
9530 doc
: /* Internal use only.
9531 If non-nil, on writing a file, `select-safe-coding-system-function' is
9532 called even if `coding-system-for-write' is non-nil. The command
9533 `universal-coding-system-argument' binds this variable to t temporarily. */);
9534 coding_system_require_warning
= 0;
9537 DEFVAR_BOOL ("inhibit-iso-escape-detection",
9538 &inhibit_iso_escape_detection
,
9540 If non-nil, Emacs ignores ISO2022's escape sequence on code detection.
9542 By default, on reading a file, Emacs tries to detect how the text is
9543 encoded. This code detection is sensitive to escape sequences. If
9544 the sequence is valid as ISO2022, the code is determined as one of
9545 the ISO2022 encodings, and the file is decoded by the corresponding
9546 coding system (e.g. `iso-2022-7bit').
9548 However, there may be a case that you want to read escape sequences in
9549 a file as is. In such a case, you can set this variable to non-nil.
9550 Then, as the code detection ignores any escape sequences, no file is
9551 detected as encoded in some ISO2022 encoding. The result is that all
9552 escape sequences become visible in a buffer.
9554 The default value is nil, and it is strongly recommended not to change
9555 it. That is because many Emacs Lisp source files that contain
9556 non-ASCII characters are encoded by the coding system `iso-2022-7bit'
9557 in Emacs's distribution, and they won't be decoded correctly on
9558 reading if you suppress escape sequence detection.
9560 The other way to read escape sequences in a file without decoding is
9561 to explicitly specify some coding system that doesn't use ISO2022's
9562 escape sequence (e.g `latin-1') on reading by \\[universal-coding-system-argument]. */);
9563 inhibit_iso_escape_detection
= 0;
9565 DEFVAR_LISP ("translation-table-for-input", &Vtranslation_table_for_input
,
9566 doc
: /* Char table for translating self-inserting characters.
9567 This is applied to the result of input methods, not their input. See also
9568 `keyboard-translate-table'. */);
9569 Vtranslation_table_for_input
= Qnil
;
9572 Lisp_Object args
[coding_arg_max
];
9573 Lisp_Object plist
[16];
9576 for (i
= 0; i
< coding_arg_max
; i
++)
9579 plist
[0] = intern (":name");
9580 plist
[1] = args
[coding_arg_name
] = Qno_conversion
;
9581 plist
[2] = intern (":mnemonic");
9582 plist
[3] = args
[coding_arg_mnemonic
] = make_number ('=');
9583 plist
[4] = intern (":coding-type");
9584 plist
[5] = args
[coding_arg_coding_type
] = Qraw_text
;
9585 plist
[6] = intern (":ascii-compatible-p");
9586 plist
[7] = args
[coding_arg_ascii_compatible_p
] = Qt
;
9587 plist
[8] = intern (":default-char");
9588 plist
[9] = args
[coding_arg_default_char
] = make_number (0);
9589 plist
[10] = intern (":for-unibyte");
9590 plist
[11] = args
[coding_arg_for_unibyte
] = Qt
;
9591 plist
[12] = intern (":docstring");
9592 plist
[13] = build_string ("Do no conversion.\n\
9594 When you visit a file with this coding, the file is read into a\n\
9595 unibyte buffer as is, thus each byte of a file is treated as a\n\
9597 plist
[14] = intern (":eol-type");
9598 plist
[15] = args
[coding_arg_eol_type
] = Qunix
;
9599 args
[coding_arg_plist
] = Flist (16, plist
);
9600 Fdefine_coding_system_internal (coding_arg_max
, args
);
9602 plist
[1] = args
[coding_arg_name
] = Qundecided
;
9603 plist
[3] = args
[coding_arg_mnemonic
] = make_number ('-');
9604 plist
[5] = args
[coding_arg_coding_type
] = Qundecided
;
9605 /* This is already set.
9606 /*plist[7] = args[coding_arg_ascii_compatible_p] = Qt;*/
9607 plist
[8] = intern (":charset-list");
9608 plist
[9] = args
[coding_arg_charset_list
] = Fcons (Qascii
, Qnil
);
9609 plist
[11] = args
[coding_arg_for_unibyte
] = Qnil
;
9610 plist
[13] = build_string ("No conversion on encoding, automatic conversion on decoding.");
9611 plist
[15] = args
[coding_arg_eol_type
] = Qnil
;
9612 args
[coding_arg_plist
] = Flist (16, plist
);
9613 Fdefine_coding_system_internal (coding_arg_max
, args
);
9616 setup_coding_system (Qno_conversion
, &keyboard_coding
);
9617 setup_coding_system (Qundecided
, &terminal_coding
);
9618 setup_coding_system (Qno_conversion
, &safe_terminal_coding
);
9623 for (i
= 0; i
< coding_category_max
; i
++)
9624 Fset (AREF (Vcoding_category_table
, i
), Qno_conversion
);
9629 emacs_strerror (error_number
)
9634 synchronize_system_messages_locale ();
9635 str
= strerror (error_number
);
9637 if (! NILP (Vlocale_coding_system
))
9639 Lisp_Object dec
= code_convert_string_norecord (build_string (str
),
9640 Vlocale_coding_system
,
9642 str
= (char *) SDATA (dec
);
9650 /* arch-tag: 3a3a2b01-5ff6-4071-9afe-f5b808d9229d
9651 (do not change this comment) */