1 |
/* Header for multibyte character handler. |
/* Header for charset handler. |
2 |
Copyright (C) 1995, 1997, 1998 Electrotechnical Laboratory, JAPAN. |
Copyright (C) 1995, 1997, 1998 Electrotechnical Laboratory, JAPAN. |
3 |
Licensed to the Free Software Foundation. |
Licensed to the Free Software Foundation. |
4 |
Copyright (C) 2001 Free Software Foundation, Inc. |
Copyright (C) 2001 Free Software Foundation, Inc. |
5 |
|
Copyright (C) 2001, 2002 |
6 |
|
National Institute of Advanced Industrial Science and Technology (AIST) |
7 |
|
Registration Number H13PRO009 |
8 |
|
|
9 |
This file is part of GNU Emacs. |
This file is part of GNU Emacs. |
10 |
|
|
26 |
#ifndef EMACS_CHARSET_H |
#ifndef EMACS_CHARSET_H |
27 |
#define EMACS_CHARSET_H |
#define EMACS_CHARSET_H |
28 |
|
|
29 |
/* #define BYTE_COMBINING_DEBUG */ |
/* Index to arguments of Fdefine_charset_internal. */ |
30 |
|
|
31 |
/*** GENERAL NOTE on CHARACTER SET (CHARSET) *** |
enum define_charset_arg_index |
32 |
|
{ |
33 |
|
charset_arg_name, |
34 |
|
charset_arg_dimension, |
35 |
|
charset_arg_code_space, |
36 |
|
charset_arg_iso_final, |
37 |
|
charset_arg_iso_revision, |
38 |
|
charset_arg_emacs_mule_id, |
39 |
|
charset_arg_ascii_compatible_p, |
40 |
|
charset_arg_supplementary_p, |
41 |
|
charset_arg_invalid_code, |
42 |
|
charset_arg_code_offset, |
43 |
|
charset_arg_map, |
44 |
|
charset_arg_parents, |
45 |
|
charset_arg_unify_map, |
46 |
|
charset_arg_plist, |
47 |
|
charset_arg_max |
48 |
|
}; |
49 |
|
|
50 |
|
|
51 |
|
/* Indices to charset attributes vector. */ |
52 |
|
|
53 |
|
enum charset_attr_index |
54 |
|
{ |
55 |
|
/* ID number of the charset. */ |
56 |
|
charset_id, |
57 |
|
|
58 |
|
/* Name of the charset (symbol). */ |
59 |
|
charset_name, |
60 |
|
|
61 |
|
/* Property list of the charset. */ |
62 |
|
charset_plist, |
63 |
|
|
64 |
|
/* If the method of the charset is `MAP_DEFERRED', the value is a |
65 |
|
mappint vector or a file name that contains mapping vector. |
66 |
|
Otherwise, nil. */ |
67 |
|
charset_map, |
68 |
|
|
69 |
|
/* If the method of the charset is `MAP', the value is a vector |
70 |
|
that maps code points of the charset to characters. The vector |
71 |
|
is indexed by a character index. A character index is |
72 |
|
calculated from a code point and the code-space table of the |
73 |
|
charset. */ |
74 |
|
charset_decoder, |
75 |
|
|
76 |
|
/* If the method of the charset is `MAP', the value is a |
77 |
|
char-table that maps characters of the charset to code |
78 |
|
points. */ |
79 |
|
charset_encoder, |
80 |
|
|
81 |
|
/* If the method of the charset is `INHERIT', the value is a list |
82 |
|
of the form (PARENT-CHARSET-ID . CODE-OFFSET). */ |
83 |
|
charset_parents, |
84 |
|
|
85 |
|
/* */ |
86 |
|
charset_unify_map, |
87 |
|
|
88 |
|
/* */ |
89 |
|
charset_deunifier, |
90 |
|
|
91 |
|
/* The length of charset attribute vector. */ |
92 |
|
charset_attr_max |
93 |
|
}; |
94 |
|
|
95 |
|
/* Methods for converting code points and characters of charsets. */ |
96 |
|
|
97 |
|
enum charset_method |
98 |
|
{ |
99 |
|
/* For a charset of this method, a character code is calculated |
100 |
|
from a character index (which is calculated from a code point) |
101 |
|
simply by adding an offset value. */ |
102 |
|
CHARSET_METHOD_OFFSET, |
103 |
|
|
104 |
|
/* For a charset of this method, a decoder vector and an encoder |
105 |
|
char-table is used for code point <-> character code |
106 |
|
conversion. */ |
107 |
|
CHARSET_METHOD_MAP, |
108 |
|
|
109 |
|
/* Same as above but decoder and encoder are loaded from a file on |
110 |
|
demand. Once loaded, the method is changed to |
111 |
|
CHARSET_METHOD_MAP. */ |
112 |
|
CHARSET_METHOD_MAP_DEFERRED, |
113 |
|
|
114 |
|
/* A charset of this method inherits characters from the other |
115 |
|
charsets. */ |
116 |
|
CHARSET_METHOD_INHERIT, |
117 |
|
}; |
118 |
|
|
119 |
|
struct charset |
120 |
|
{ |
121 |
|
int id; |
122 |
|
|
123 |
|
int hash_index; |
124 |
|
|
125 |
|
/* Dimension of the charset: 1, 2, 3, or 4. */ |
126 |
|
int dimension; |
127 |
|
|
128 |
|
/* Minimum byte code in each dimension. */ |
129 |
|
int code_space[16]; |
130 |
|
|
131 |
|
/* 1 if there's no gap in code-points. */ |
132 |
|
int code_linear_p; |
133 |
|
|
134 |
|
/* If the charset is treated as 94-chars in ISO-2022, the value is 0. |
135 |
|
If the charset is treated as 96-chars in ISO-2022, the value is 1. */ |
136 |
|
int iso_chars_96; |
137 |
|
|
138 |
|
/* ISO final character code for the charset: 48..127. |
139 |
|
It may be 0 if the charset doesn't conform to ISO-2022. */ |
140 |
|
int iso_final; |
141 |
|
|
142 |
|
int iso_revision; |
143 |
|
|
144 |
|
/* If the charset is identical to what supported by Emacs 21 and the |
145 |
|
priors, the identification number of the charset used in those |
146 |
|
version. Otherwise, -1. */ |
147 |
|
int emacs_mule_id; |
148 |
|
|
149 |
|
/* Nonzero iff the charset is compatible with ASCII. */ |
150 |
|
int ascii_compatible_p; |
151 |
|
|
152 |
|
/* Nonzero iff the charset is supplementary. */ |
153 |
|
int supplementary_p; |
154 |
|
|
155 |
|
/* Nonzero iff all the code points are representable by Lisp_Int. */ |
156 |
|
int compact_codes_p; |
157 |
|
|
158 |
|
/* The method for encoding/decoding characters of the charset. */ |
159 |
|
enum charset_method method; |
160 |
|
|
161 |
|
/* Mininum and Maximum code points of the charset. */ |
162 |
|
unsigned min_code, max_code; |
163 |
|
|
164 |
|
/* Mininum and Maximum character codes of the charset. If the |
165 |
|
charset is compatible with ASCII, min_char is a minimum non-ASCII |
166 |
|
character of the charset. */ |
167 |
|
int min_char, max_char; |
168 |
|
|
169 |
|
/* The code returned by ENCODE_CHAR if a character is not encodable |
170 |
|
by the charset. */ |
171 |
|
unsigned invalid_code; |
172 |
|
|
173 |
|
/* If the method of the charset is CHARSET_METHOD_MAP, this is a |
174 |
|
table of bits used to quickly and roughly guess if a character |
175 |
|
belongs to the charset. |
176 |
|
|
177 |
|
The first 64 elements are 512 bits for characters less than |
178 |
|
0x10000. Each bit corresponds to 128-character block. The last |
179 |
|
126 elements are 1008 bits for the greater characters |
180 |
|
(0x10000..0x3FFFFF). Each bit corresponds to 4096-character |
181 |
|
block. |
182 |
|
|
183 |
|
If a bit is 1, at least one character in the corresponds block is |
184 |
|
in this charset. */ |
185 |
|
unsigned char fast_map[190]; |
186 |
|
|
187 |
|
/* Offset value to calculate a character code from code-point, and |
188 |
|
visa versa. */ |
189 |
|
int code_offset; |
190 |
|
|
191 |
|
int unified_p; |
192 |
|
}; |
193 |
|
|
194 |
|
/* Hash table of charset symbols vs. the correponding attribute |
195 |
|
vectors. */ |
196 |
|
extern Lisp_Object Vcharset_hash_table; |
197 |
|
|
198 |
|
/* Table of struct charset. */ |
199 |
|
extern struct charset *charset_table; |
200 |
|
extern int charset_table_used; |
201 |
|
|
202 |
|
#define CHARSET_FROM_ID(id) (charset_table + (id)) |
203 |
|
|
204 |
|
extern Lisp_Object Vcharset_list; |
205 |
|
extern Lisp_Object Viso_2022_charset_list; |
206 |
|
extern Lisp_Object Vemacs_mule_charset_list; |
207 |
|
|
208 |
|
extern struct charset *emacs_mule_charset[256]; |
209 |
|
|
210 |
|
|
211 |
|
/* Macros to access information about charset. */ |
212 |
|
|
213 |
|
/* Return the attribute vector of charset whose symbol is SYMBOL. */ |
214 |
|
#define CHARSET_SYMBOL_ATTRIBUTES(symbol) \ |
215 |
|
Fgethash ((symbol), Vcharset_hash_table, Qnil) |
216 |
|
|
217 |
|
#define CHARSET_ATTR_ID(attrs) AREF ((attrs), charset_id) |
218 |
|
#define CHARSET_ATTR_NAME(attrs) AREF ((attrs), charset_name) |
219 |
|
#define CHARSET_ATTR_PLIST(attrs) AREF ((attrs), charset_plist) |
220 |
|
#define CHARSET_ATTR_MAP(attrs) AREF ((attrs), charset_map) |
221 |
|
#define CHARSET_ATTR_DECODER(attrs) AREF ((attrs), charset_decoder) |
222 |
|
#define CHARSET_ATTR_ENCODER(attrs) AREF ((attrs), charset_encoder) |
223 |
|
#define CHARSET_ATTR_PARENTS(attrs) AREF ((attrs), charset_parents) |
224 |
|
#define CHARSET_ATTR_UNIFY_MAP(attrs) AREF ((attrs), charset_unify_map) |
225 |
|
#define CHARSET_ATTR_DEUNIFIER(attrs) AREF ((attrs), charset_deunifier) |
226 |
|
|
227 |
|
#define CHARSET_SYMBOL_ID(symbol) \ |
228 |
|
CHARSET_ATTR_ID (CHARSET_SYMBOL_ATTRIBUTES (symbol)) |
229 |
|
|
230 |
|
/* Return an index to Vcharset_hash_table of the charset whose symbol |
231 |
|
is SYMBOL. */ |
232 |
|
#define CHARSET_SYMBOL_HASH_INDEX(symbol) \ |
233 |
|
hash_lookup (XHASH_TABLE (Vcharset_hash_table), symbol, NULL) |
234 |
|
|
235 |
|
/* Return the attribute vector of CHARSET. */ |
236 |
|
#define CHARSET_ATTRIBUTES(charset) \ |
237 |
|
(HASH_VALUE (XHASH_TABLE (Vcharset_hash_table), (charset)->hash_index)) |
238 |
|
|
239 |
|
#define CHARSET_ID(charset) ((charset)->id) |
240 |
|
#define CHARSET_HASH_INDEX(charset) ((charset)->hash_index) |
241 |
|
#define CHARSET_DIMENSION(charset) ((charset)->dimension) |
242 |
|
#define CHARSET_CODE_SPACE(charset) ((charset)->code_space) |
243 |
|
#define CHARSET_CODE_LINEAR_P(charset) ((charset)->code_linear_p) |
244 |
|
#define CHARSET_ISO_CHARS_96(charset) ((charset)->iso_chars_96) |
245 |
|
#define CHARSET_ISO_FINAL(charset) ((charset)->iso_final) |
246 |
|
#define CHARSET_ISO_PLANE(charset) ((charset)->iso_plane) |
247 |
|
#define CHARSET_ISO_REVISION(charset) ((charset)->iso_revision) |
248 |
|
#define CHARSET_EMACS_MULE_ID(charset) ((charset)->emacs_mule_id) |
249 |
|
#define CHARSET_ASCII_COMPATIBLE_P(charset) ((charset)->ascii_compatible_p) |
250 |
|
#define CHARSET_COMPACT_CODES_P(charset) ((charset)->compact_codes_p) |
251 |
|
#define CHARSET_METHOD(charset) ((charset)->method) |
252 |
|
#define CHARSET_MIN_CODE(charset) ((charset)->min_code) |
253 |
|
#define CHARSET_MAX_CODE(charset) ((charset)->max_code) |
254 |
|
#define CHARSET_INVALID_CODE(charset) ((charset)->invalid_code) |
255 |
|
#define CHARSET_MIN_CHAR(charset) ((charset)->min_char) |
256 |
|
#define CHARSET_MAX_CHAR(charset) ((charset)->max_char) |
257 |
|
#define CHARSET_CODE_OFFSET(charset) ((charset)->code_offset) |
258 |
|
#define CHARSET_UNIFIED_P(charset) ((charset)->unified_p) |
259 |
|
|
260 |
|
#define CHARSET_NAME(charset) \ |
261 |
|
(CHARSET_ATTR_NAME (CHARSET_ATTRIBUTES (charset))) |
262 |
|
#define CHARSET_MAP(charset) \ |
263 |
|
(CHARSET_ATTR_MAP (CHARSET_ATTRIBUTES (charset))) |
264 |
|
#define CHARSET_DECODER(charset) \ |
265 |
|
(CHARSET_ATTR_DECODER (CHARSET_ATTRIBUTES (charset))) |
266 |
|
#define CHARSET_ENCODER(charset) \ |
267 |
|
(CHARSET_ATTR_ENCODER (CHARSET_ATTRIBUTES (charset))) |
268 |
|
#define CHARSET_PARENTS(charset) \ |
269 |
|
(CHARSET_ATTR_PARENTS (CHARSET_ATTRIBUTES (charset))) |
270 |
|
#define CHARSET_UNIFY_MAP(charset) \ |
271 |
|
(CHARSET_ATTR_UNIFY_MAP (CHARSET_ATTRIBUTES (charset))) |
272 |
|
#define CHARSET_DEUNIFIER(charset) \ |
273 |
|
(CHARSET_ATTR_DEUNIFIER (CHARSET_ATTRIBUTES (charset))) |
274 |
|
|
|
A character set ("charset" hereafter) is a meaningful collection |
|
|
(i.e. language, culture, functionality, etc) of characters. Emacs |
|
|
handles multiple charsets at once. Each charset corresponds to one |
|
|
of the ISO charsets. Emacs identifies a charset by a unique |
|
|
identification number, whereas ISO identifies a charset by a triplet |
|
|
of DIMENSION, CHARS and FINAL-CHAR. So, hereafter, just saying |
|
|
"charset" means an identification number (integer value). |
|
|
|
|
|
The value range of charsets is 0x00, 0x81..0xFE. There are four |
|
|
kinds of charset depending on DIMENSION (1 or 2) and CHARS (94 or |
|
|
96). For instance, a charset of DIMENSION2_CHARS94 contains 94x94 |
|
|
characters. |
|
|
|
|
|
Within Emacs Lisp, a charset is treated as a symbol which has a |
|
|
property `charset'. The property value is a vector containing |
|
|
various information about the charset. For readability of C code, |
|
|
we use the following convention for C variable names: |
|
|
charset_symbol: Emacs Lisp symbol of a charset |
|
|
charset_id: Emacs Lisp integer of an identification number of a charset |
|
|
charset: C integer of an identification number of a charset |
|
|
|
|
|
Each charset (except for ascii) is assigned a base leading-code |
|
|
(range 0x80..0x9E). In addition, a charset of greater than 0xA0 |
|
|
(whose base leading-code is 0x9A..0x9D) is assigned an extended |
|
|
leading-code (range 0xA0..0xFE). In this case, each base |
|
|
leading-code specifies the allowable range of extended leading-code |
|
|
as shown in the table below. A leading-code is used to represent a |
|
|
character in Emacs' buffer and string. |
|
|
|
|
|
We call a charset which has extended leading-code a "private |
|
|
charset" because those are mainly for a charset which is not yet |
|
|
registered by ISO. On the contrary, we call a charset which does |
|
|
not have extended leading-code an "official charset". |
|
|
|
|
|
--------------------------------------------------------------------------- |
|
|
charset dimension base leading-code extended leading-code |
|
|
--------------------------------------------------------------------------- |
|
|
0x00 official dim1 -- none -- -- none -- |
|
|
(ASCII) |
|
|
0x01..0x7F --never used-- |
|
|
0x80 official dim1 -- none -- -- none -- |
|
|
(eight-bit-graphic) |
|
|
0x81..0x8F official dim1 same as charset -- none -- |
|
|
0x90..0x99 official dim2 same as charset -- none -- |
|
|
0x9A..0x9D --never used-- |
|
|
0x9E official dim1 same as charset -- none -- |
|
|
(eight-bit-control) |
|
|
0x9F --never used-- |
|
|
0xA0..0xDF private dim1 0x9A same as charset |
|
|
of 1-column width |
|
|
0xE0..0xEF private dim1 0x9B same as charset |
|
|
of 2-column width |
|
|
0xF0..0xF4 private dim2 0x9C same as charset |
|
|
of 1-column width |
|
|
0xF5..0xFE private dim2 0x9D same as charset |
|
|
of 2-column width |
|
|
0xFF --never used-- |
|
|
--------------------------------------------------------------------------- |
|
|
|
|
|
*/ |
|
|
|
|
|
/* Definition of special leading-codes. */ |
|
|
/* Leading-code followed by extended leading-code. */ |
|
|
#define LEADING_CODE_PRIVATE_11 0x9A /* for private DIMENSION1 of 1-column */ |
|
|
#define LEADING_CODE_PRIVATE_12 0x9B /* for private DIMENSION1 of 2-column */ |
|
|
#define LEADING_CODE_PRIVATE_21 0x9C /* for private DIMENSION2 of 1-column */ |
|
|
#define LEADING_CODE_PRIVATE_22 0x9D /* for private DIMENSION2 of 2-column */ |
|
|
|
|
|
#define LEADING_CODE_8_BIT_CONTROL 0x9E /* for `eight-bit-control' */ |
|
|
|
|
|
/* Extended leading-code. */ |
|
|
/* Start of each extended leading-codes. */ |
|
|
#define LEADING_CODE_EXT_11 0xA0 /* follows LEADING_CODE_PRIVATE_11 */ |
|
|
#define LEADING_CODE_EXT_12 0xE0 /* follows LEADING_CODE_PRIVATE_12 */ |
|
|
#define LEADING_CODE_EXT_21 0xF0 /* follows LEADING_CODE_PRIVATE_21 */ |
|
|
#define LEADING_CODE_EXT_22 0xF5 /* follows LEADING_CODE_PRIVATE_22 */ |
|
|
/* Maximum value of extended leading-codes. */ |
|
|
#define LEADING_CODE_EXT_MAX 0xFE |
|
|
|
|
|
/* Definition of minimum/maximum charset of each DIMENSION. */ |
|
|
#define MIN_CHARSET_OFFICIAL_DIMENSION1 0x80 |
|
|
#define MAX_CHARSET_OFFICIAL_DIMENSION1 0x8F |
|
|
#define MIN_CHARSET_OFFICIAL_DIMENSION2 0x90 |
|
|
#define MAX_CHARSET_OFFICIAL_DIMENSION2 0x99 |
|
|
#define MIN_CHARSET_PRIVATE_DIMENSION1 LEADING_CODE_EXT_11 |
|
|
#define MIN_CHARSET_PRIVATE_DIMENSION2 LEADING_CODE_EXT_21 |
|
|
|
|
|
/* Maximum value of overall charset identification number. */ |
|
|
#define MAX_CHARSET 0xFE |
|
|
|
|
|
/* Definition of special charsets. */ |
|
|
#define CHARSET_ASCII 0 /* 0x00..0x7F */ |
|
|
#define CHARSET_8_BIT_CONTROL 0x9E /* 0x80..0x9F */ |
|
|
#define CHARSET_8_BIT_GRAPHIC 0x80 /* 0xA0..0xFF */ |
|
|
|
|
|
extern int charset_latin_iso8859_1; /* ISO8859-1 (Latin-1) */ |
|
|
extern int charset_jisx0208_1978; /* JISX0208.1978 (Japanese Kanji old set) */ |
|
|
extern int charset_jisx0208; /* JISX0208.1983 (Japanese Kanji) */ |
|
|
extern int charset_katakana_jisx0201; /* JISX0201.Kana (Japanese Katakana) */ |
|
|
extern int charset_latin_jisx0201; /* JISX0201.Roman (Japanese Roman) */ |
|
|
extern int charset_big5_1; /* Big5 Level 1 (Chinese Traditional) */ |
|
|
extern int charset_big5_2; /* Big5 Level 2 (Chinese Traditional) */ |
|
|
|
|
|
/* Check if CH is an ASCII character or a base leading-code. |
|
|
Nowadays, any byte can be the first byte of a character in a |
|
|
multibyte buffer/string. So this macro name is not appropriate. */ |
|
|
#define CHAR_HEAD_P(ch) ((unsigned char) (ch) < 0xA0) |
|
|
|
|
|
/*** GENERAL NOTE on CHARACTER REPRESENTATION *** |
|
|
|
|
|
Firstly, the term "character" or "char" is used for a multilingual |
|
|
character (of course, including ASCII characters), not for a byte in |
|
|
computer memory. We use the term "code" or "byte" for the latter |
|
|
case. |
|
|
|
|
|
A character is identified by charset and one or two POSITION-CODEs. |
|
|
POSITION-CODE is the position of the character in the charset. A |
|
|
character of DIMENSION1 charset has one POSITION-CODE: POSITION-CODE-1. |
|
|
A character of DIMENSION2 charset has two POSITION-CODE: |
|
|
POSITION-CODE-1 and POSITION-CODE-2. The code range of |
|
|
POSITION-CODE is 0x20..0x7F. |
|
|
|
|
|
Emacs has two kinds of representation of a character: multi-byte |
|
|
form (for buffers and strings) and single-word form (for character |
|
|
objects in Emacs Lisp). The latter is called "character code" |
|
|
hereafter. Both representations encode the information of charset |
|
|
and POSITION-CODE but in a different way (for instance, the MSB of |
|
|
POSITION-CODE is set in multi-byte form). |
|
|
|
|
|
For details of the multi-byte form, see the section "2. Emacs |
|
|
internal format handlers" of `coding.c'. |
|
|
|
|
|
Emacs uses 19 bits for a character code. The bits are divided into |
|
|
3 fields: FIELD1(5bits):FIELD2(7bits):FIELD3(7bits). |
|
|
|
|
|
A character code of DIMENSION1 character uses FIELD2 to hold charset |
|
|
and FIELD3 to hold POSITION-CODE-1. A character code of DIMENSION2 |
|
|
character uses FIELD1 to hold charset, FIELD2 and FIELD3 to hold |
|
|
POSITION-CODE-1 and POSITION-CODE-2 respectively. |
|
|
|
|
|
More precisely... |
|
|
|
|
|
FIELD2 of DIMENSION1 character (except for ascii, eight-bit-control, |
|
|
and eight-bit-graphic) is "charset - 0x70". This is to make all |
|
|
character codes except for ASCII and 8-bit codes greater than 256. |
|
|
So, the range of FIELD2 of DIMENSION1 character is 0, 1, or |
|
|
0x11..0x7F. |
|
|
|
|
|
FIELD1 of DIMENSION2 character is "charset - 0x8F" for official |
|
|
charset and "charset - 0xE0" for private charset. So, the range of |
|
|
FIELD1 of DIMENSION2 character is 0x01..0x1E. |
|
|
|
|
|
----------------------------------------------------------------------------- |
|
|
charset FIELD1 (5-bit) FIELD2 (7-bit) FIELD3 (7-bit) |
|
|
----------------------------------------------------------------------------- |
|
|
ascii 0 0 0x00..0x7F |
|
|
eight-bit-control 0 1 0x00..0x1F |
|
|
eight-bit-graphic 0 1 0x20..0x7F |
|
|
DIMENSION1 0 charset - 0x70 POSITION-CODE-1 |
|
|
DIMENSION2(o) charset - 0x8F POSITION-CODE-1 POSITION-CODE-2 |
|
|
DIMENSION2(p) charset - 0xE0 POSITION-CODE-1 POSITION-CODE-2 |
|
|
----------------------------------------------------------------------------- |
|
|
"(o)": official, "(p)": private |
|
|
----------------------------------------------------------------------------- |
|
|
*/ |
|
|
|
|
|
/* Masks of each field of character code. */ |
|
|
#define CHAR_FIELD1_MASK (0x1F << 14) |
|
|
#define CHAR_FIELD2_MASK (0x7F << 7) |
|
|
#define CHAR_FIELD3_MASK 0x7F |
|
|
|
|
|
/* Macros to access each field of character C. */ |
|
|
#define CHAR_FIELD1(c) (((c) & CHAR_FIELD1_MASK) >> 14) |
|
|
#define CHAR_FIELD2(c) (((c) & CHAR_FIELD2_MASK) >> 7) |
|
|
#define CHAR_FIELD3(c) ((c) & CHAR_FIELD3_MASK) |
|
|
|
|
|
/* Minimum character code of character of each DIMENSION. */ |
|
|
#define MIN_CHAR_OFFICIAL_DIMENSION1 \ |
|
|
((0x81 - 0x70) << 7) |
|
|
#define MIN_CHAR_PRIVATE_DIMENSION1 \ |
|
|
((MIN_CHARSET_PRIVATE_DIMENSION1 - 0x70) << 7) |
|
|
#define MIN_CHAR_OFFICIAL_DIMENSION2 \ |
|
|
((MIN_CHARSET_OFFICIAL_DIMENSION2 - 0x8F) << 14) |
|
|
#define MIN_CHAR_PRIVATE_DIMENSION2 \ |
|
|
((MIN_CHARSET_PRIVATE_DIMENSION2 - 0xE0) << 14) |
|
|
/* Maximum character code currently used plus 1. */ |
|
|
#define MAX_CHAR (0x1F << 14) |
|
|
|
|
|
/* 1 if C is a single byte character, else 0. */ |
|
|
#define SINGLE_BYTE_CHAR_P(c) ((unsigned) (c) < 0x100) |
|
|
|
|
|
/* 1 if BYTE is an ASCII character in itself, in multibyte mode. */ |
|
|
#define ASCII_BYTE_P(byte) ((byte) < 0x80) |
|
|
|
|
|
/* A char-table containing information on each character set. |
|
|
|
|
|
Unlike ordinary char-tables, this doesn't contain any nested tables. |
|
|
Only the top level elements are used. Each element is a vector of |
|
|
the following information: |
|
|
CHARSET-ID, BYTES, DIMENSION, CHARS, WIDTH, DIRECTION, |
|
|
LEADING-CODE-BASE, LEADING-CODE-EXT, |
|
|
ISO-FINAL-CHAR, ISO-GRAPHIC-PLANE, |
|
|
REVERSE-CHARSET, SHORT-NAME, LONG-NAME, DESCRIPTION, |
|
|
PLIST. |
|
|
|
|
|
CHARSET-ID (integer) is the identification number of the charset. |
|
|
|
|
|
BYTES (integer) is the length of the multi-byte form of a character |
|
|
in the charset: one of 1, 2, 3, and 4. |
|
|
|
|
|
DIMENSION (integer) is the number of bytes to represent a character: 1 or 2. |
|
|
|
|
|
CHARS (integer) is the number of characters in a dimension: 94 or 96. |
|
|
|
|
|
WIDTH (integer) is the number of columns a character in the charset |
|
|
occupies on the screen: one of 0, 1, and 2.. |
|
|
|
|
|
DIRECTION (integer) is the rendering direction of characters in the |
|
|
charset when rendering. If 0, render from left to right, else |
|
|
render from right to left. |
|
|
|
|
|
LEADING-CODE-BASE (integer) is the base leading-code for the |
|
|
charset. |
|
|
|
|
|
LEADING-CODE-EXT (integer) is the extended leading-code for the |
|
|
charset. All charsets of less than 0xA0 have the value 0. |
|
|
|
|
|
ISO-FINAL-CHAR (character) is the final character of the |
|
|
corresponding ISO 2022 charset. It is -1 for such a character |
|
|
that is used only internally (e.g. `eight-bit-control'). |
|
|
|
|
|
ISO-GRAPHIC-PLANE (integer) is the graphic plane to be invoked |
|
|
while encoding to variants of ISO 2022 coding system, one of the |
|
|
following: 0/graphic-plane-left(GL), 1/graphic-plane-right(GR). It |
|
|
is -1 for such a character that is used only internally |
|
|
(e.g. `eight-bit-control'). |
|
|
|
|
|
REVERSE-CHARSET (integer) is the charset which differs only in |
|
|
LEFT-TO-RIGHT value from the charset. If there's no such a |
|
|
charset, the value is -1. |
|
|
|
|
|
SHORT-NAME (string) is the short name to refer to the charset. |
|
|
|
|
|
LONG-NAME (string) is the long name to refer to the charset. |
|
|
|
|
|
DESCRIPTION (string) is the description string of the charset. |
|
|
|
|
|
PLIST (property list) may contain any type of information a user |
|
|
wants to put and get by functions `put-charset-property' and |
|
|
`get-charset-property' respectively. */ |
|
|
extern Lisp_Object Vcharset_table; |
|
|
|
|
|
/* Macros to access various information of CHARSET in Vcharset_table. |
|
|
We provide these macros for efficiency. No range check of CHARSET. */ |
|
|
|
|
|
/* Return entry of CHARSET (C integer) in Vcharset_table. */ |
|
|
#define CHARSET_TABLE_ENTRY(charset) \ |
|
|
XCHAR_TABLE (Vcharset_table)->contents[((charset) == CHARSET_ASCII \ |
|
|
? 0 : (charset) + 128)] |
|
|
|
|
|
/* Return information INFO-IDX of CHARSET. */ |
|
|
#define CHARSET_TABLE_INFO(charset, info_idx) \ |
|
|
XVECTOR (CHARSET_TABLE_ENTRY (charset))->contents[info_idx] |
|
|
|
|
|
#define CHARSET_ID_IDX (0) |
|
|
#define CHARSET_BYTES_IDX (1) |
|
|
#define CHARSET_DIMENSION_IDX (2) |
|
|
#define CHARSET_CHARS_IDX (3) |
|
|
#define CHARSET_WIDTH_IDX (4) |
|
|
#define CHARSET_DIRECTION_IDX (5) |
|
|
#define CHARSET_LEADING_CODE_BASE_IDX (6) |
|
|
#define CHARSET_LEADING_CODE_EXT_IDX (7) |
|
|
#define CHARSET_ISO_FINAL_CHAR_IDX (8) |
|
|
#define CHARSET_ISO_GRAPHIC_PLANE_IDX (9) |
|
|
#define CHARSET_REVERSE_CHARSET_IDX (10) |
|
|
#define CHARSET_SHORT_NAME_IDX (11) |
|
|
#define CHARSET_LONG_NAME_IDX (12) |
|
|
#define CHARSET_DESCRIPTION_IDX (13) |
|
|
#define CHARSET_PLIST_IDX (14) |
|
|
/* Size of a vector of each entry of Vcharset_table. */ |
|
|
#define CHARSET_MAX_IDX (15) |
|
|
|
|
|
/* And several more macros to be used frequently. */ |
|
|
#define CHARSET_BYTES(charset) \ |
|
|
XFASTINT (CHARSET_TABLE_INFO (charset, CHARSET_BYTES_IDX)) |
|
|
#define CHARSET_DIMENSION(charset) \ |
|
|
XFASTINT (CHARSET_TABLE_INFO (charset, CHARSET_DIMENSION_IDX)) |
|
|
#define CHARSET_CHARS(charset) \ |
|
|
XFASTINT (CHARSET_TABLE_INFO (charset, CHARSET_CHARS_IDX)) |
|
|
#define CHARSET_WIDTH(charset) \ |
|
|
XFASTINT (CHARSET_TABLE_INFO (charset, CHARSET_WIDTH_IDX)) |
|
|
#define CHARSET_DIRECTION(charset) \ |
|
|
XFASTINT (CHARSET_TABLE_INFO (charset, CHARSET_DIRECTION_IDX)) |
|
|
#define CHARSET_LEADING_CODE_BASE(charset) \ |
|
|
XFASTINT (CHARSET_TABLE_INFO (charset, CHARSET_LEADING_CODE_BASE_IDX)) |
|
|
#define CHARSET_LEADING_CODE_EXT(charset) \ |
|
|
XFASTINT (CHARSET_TABLE_INFO (charset, CHARSET_LEADING_CODE_EXT_IDX)) |
|
|
#define CHARSET_ISO_FINAL_CHAR(charset) \ |
|
|
XINT (CHARSET_TABLE_INFO (charset, CHARSET_ISO_FINAL_CHAR_IDX)) |
|
|
#define CHARSET_ISO_GRAPHIC_PLANE(charset) \ |
|
|
XINT (CHARSET_TABLE_INFO (charset, CHARSET_ISO_GRAPHIC_PLANE_IDX)) |
|
|
#define CHARSET_REVERSE_CHARSET(charset) \ |
|
|
XINT (CHARSET_TABLE_INFO (charset, CHARSET_REVERSE_CHARSET_IDX)) |
|
|
|
|
|
/* Macros to specify direction of a charset. */ |
|
|
#define CHARSET_DIRECTION_LEFT_TO_RIGHT 0 |
|
|
#define CHARSET_DIRECTION_RIGHT_TO_LEFT 1 |
|
|
|
|
|
/* A vector of charset symbol indexed by charset-id. This is used |
|
|
only for returning charset symbol from C functions. */ |
|
|
extern Lisp_Object Vcharset_symbol_table; |
|
|
|
|
|
/* Return symbol of CHARSET. */ |
|
|
#define CHARSET_SYMBOL(charset) \ |
|
|
XVECTOR (Vcharset_symbol_table)->contents[charset] |
|
|
|
|
|
/* 1 if CHARSET is in valid value range, else 0. */ |
|
|
#define CHARSET_VALID_P(charset) \ |
|
|
((charset) == 0 \ |
|
|
|| ((charset) > 0x80 && (charset) <= MAX_CHARSET_OFFICIAL_DIMENSION2) \ |
|
|
|| ((charset) >= MIN_CHARSET_PRIVATE_DIMENSION1 \ |
|
|
&& (charset) <= MAX_CHARSET) \ |
|
|
|| ((charset) == CHARSET_8_BIT_CONTROL) \ |
|
|
|| ((charset) == CHARSET_8_BIT_GRAPHIC)) |
|
|
|
|
|
/* 1 if CHARSET is already defined, else 0. */ |
|
|
#define CHARSET_DEFINED_P(charset) \ |
|
|
(((charset) >= 0) && ((charset) <= MAX_CHARSET) \ |
|
|
&& !NILP (CHARSET_TABLE_ENTRY (charset))) |
|
|
|
|
|
/* Since the information CHARSET-BYTES and CHARSET-WIDTH of |
|
|
Vcharset_table can be retrieved only by the first byte of |
|
|
multi-byte form (an ASCII code or a base leading-code), we provide |
|
|
here tables to be used by macros BYTES_BY_CHAR_HEAD and |
|
|
WIDTH_BY_CHAR_HEAD for faster information retrieval. */ |
|
|
extern int bytes_by_char_head[256]; |
|
|
extern int width_by_char_head[256]; |
|
|
|
|
|
#define BYTES_BY_CHAR_HEAD(char_head) \ |
|
|
(ASCII_BYTE_P (char_head) ? 1 : bytes_by_char_head[char_head]) |
|
|
#define WIDTH_BY_CHAR_HEAD(char_head) \ |
|
|
(ASCII_BYTE_P (char_head) ? 1 : width_by_char_head[char_head]) |
|
|
|
|
|
/* Charset of the character C. */ |
|
|
#define CHAR_CHARSET(c) \ |
|
|
(SINGLE_BYTE_CHAR_P (c) \ |
|
|
? (ASCII_BYTE_P (c) \ |
|
|
? CHARSET_ASCII \ |
|
|
: (c) < 0xA0 ? CHARSET_8_BIT_CONTROL : CHARSET_8_BIT_GRAPHIC) \ |
|
|
: ((c) < MIN_CHAR_OFFICIAL_DIMENSION2 \ |
|
|
? CHAR_FIELD2 (c) + 0x70 \ |
|
|
: ((c) < MIN_CHAR_PRIVATE_DIMENSION2 \ |
|
|
? CHAR_FIELD1 (c) + 0x8F \ |
|
|
: CHAR_FIELD1 (c) + 0xE0))) |
|
275 |
|
|
276 |
/* Check if two characters C1 and C2 belong to the same charset. */ |
/* Nonzero iff OBJ is a valid charset symbol. */ |
277 |
#define SAME_CHARSET_P(c1, c2) \ |
#define CHARSETP(obj) (CHARSET_SYMBOL_HASH_INDEX (obj) >= 0) |
|
(c1 < MIN_CHAR_OFFICIAL_DIMENSION2 \ |
|
|
? (c1 & CHAR_FIELD2_MASK) == (c2 & CHAR_FIELD2_MASK) \ |
|
|
: (c1 & CHAR_FIELD1_MASK) == (c2 & CHAR_FIELD1_MASK)) |
|
|
|
|
|
/* Return a character of which charset is CHARSET and position-codes |
|
|
are C1 and C2. DIMENSION1 character ignores C2. */ |
|
|
#define MAKE_CHAR(charset, c1, c2) \ |
|
|
((charset) == CHARSET_ASCII \ |
|
|
? (c1) & 0x7F \ |
|
|
: (((charset) == CHARSET_8_BIT_CONTROL \ |
|
|
|| (charset) == CHARSET_8_BIT_GRAPHIC) \ |
|
|
? ((c1) & 0x7F) | 0x80 \ |
|
|
: ((CHARSET_DEFINED_P (charset) \ |
|
|
? CHARSET_DIMENSION (charset) == 1 \ |
|
|
: (charset) < MIN_CHARSET_PRIVATE_DIMENSION2) \ |
|
|
? (((charset) - 0x70) << 7) | ((c1) <= 0 ? 0 : ((c1) & 0x7F)) \ |
|
|
: ((((charset) \ |
|
|
- ((charset) < MIN_CHARSET_PRIVATE_DIMENSION2 ? 0x8F : 0xE0)) \ |
|
|
<< 14) \ |
|
|
| ((c2) <= 0 ? 0 : ((c2) & 0x7F)) \ |
|
|
| ((c1) <= 0 ? 0 : (((c1) & 0x7F) << 7)))))) |
|
|
|
|
|
|
|
|
/* If GENERICP is nonzero, return nonzero iff C is a valid normal or |
|
|
generic character. If GENERICP is zero, return nonzero iff C is a |
|
|
valid normal character. */ |
|
|
#define CHAR_VALID_P(c, genericp) \ |
|
|
((c) >= 0 \ |
|
|
&& (SINGLE_BYTE_CHAR_P (c) || char_valid_p (c, genericp))) |
|
|
|
|
|
/* This default value is used when nonascii-translation-table or |
|
|
nonascii-insert-offset fail to convert unibyte character to a valid |
|
|
multibyte character. This makes a Latin-1 character. */ |
|
|
|
|
|
#define DEFAULT_NONASCII_INSERT_OFFSET 0x800 |
|
|
|
|
|
/* Parse multibyte string STR of length LENGTH and set BYTES to the |
|
|
byte length of a character at STR. */ |
|
|
|
|
|
#ifdef BYTE_COMBINING_DEBUG |
|
278 |
|
|
279 |
#define PARSE_MULTIBYTE_SEQ(str, length, bytes) \ |
/* Check if X is a valid charset symbol. If not, signal an error. */ |
280 |
|
#define CHECK_CHARSET(x) \ |
281 |
do { \ |
do { \ |
282 |
int i = 1; \ |
if (! SYMBOLP (x) || CHARSET_SYMBOL_HASH_INDEX (x) < 0) \ |
283 |
while (i < (length) && ! CHAR_HEAD_P ((str)[i])) i++; \ |
x = wrong_type_argument (Qcharsetp, (x)); \ |
|
(bytes) = BYTES_BY_CHAR_HEAD ((str)[0]); \ |
|
|
if ((bytes) > i) \ |
|
|
abort (); \ |
|
284 |
} while (0) |
} while (0) |
285 |
|
|
|
#else /* not BYTE_COMBINING_DEBUG */ |
|
|
|
|
|
#define PARSE_MULTIBYTE_SEQ(str, length, bytes) \ |
|
|
(bytes) = BYTES_BY_CHAR_HEAD ((str)[0]) |
|
|
|
|
|
#endif /* not BYTE_COMBINING_DEBUG */ |
|
|
|
|
|
/* Return 1 iff the byte sequence at unibyte string STR (LENGTH bytes) |
|
|
is valid as a multibyte form. If valid, by a side effect, BYTES is |
|
|
set to the byte length of the multibyte form. */ |
|
|
|
|
|
#define UNIBYTE_STR_AS_MULTIBYTE_P(str, length, bytes) \ |
|
|
(((str)[0] < 0x80 || (str)[0] >= 0xA0) \ |
|
|
? ((bytes) = 1) \ |
|
|
: (((bytes) = BYTES_BY_CHAR_HEAD ((str)[0])), \ |
|
|
((bytes) > 1 && (bytes) <= (length) \ |
|
|
&& (str)[0] != LEADING_CODE_8_BIT_CONTROL \ |
|
|
&& !CHAR_HEAD_P ((str)[1]) \ |
|
|
&& ((bytes) == 2 \ |
|
|
|| (!CHAR_HEAD_P ((str)[2]) \ |
|
|
&& ((bytes) == 3 \ |
|
|
|| !CHAR_HEAD_P ((str)[3]))))))) |
|
|
|
|
|
/* Return 1 iff the byte sequence at multibyte string STR is valid as |
|
|
a unibyte form. By a side effect, BYTES is set to the byte length |
|
|
of one character at STR. */ |
|
|
|
|
|
#define MULTIBYTE_STR_AS_UNIBYTE_P(str, bytes) \ |
|
|
((bytes) = BYTES_BY_CHAR_HEAD ((str)[0]), \ |
|
|
(str)[0] != LEADING_CODE_8_BIT_CONTROL) |
|
|
|
|
|
/* The charset of character C is stored in CHARSET, and the |
|
|
position-codes of C are stored in C1 and C2. |
|
|
We store -1 in C2 if the dimension of the charset is 1. */ |
|
|
|
|
|
#define SPLIT_CHAR(c, charset, c1, c2) \ |
|
|
(SINGLE_BYTE_CHAR_P (c) \ |
|
|
? ((charset \ |
|
|
= (ASCII_BYTE_P (c) \ |
|
|
? CHARSET_ASCII \ |
|
|
: ((c) < 0xA0 ? CHARSET_8_BIT_CONTROL : CHARSET_8_BIT_GRAPHIC))), \ |
|
|
c1 = (c), c2 = -1) \ |
|
|
: ((c) & CHAR_FIELD1_MASK \ |
|
|
? (charset = (CHAR_FIELD1 (c) \ |
|
|
+ ((c) < MIN_CHAR_PRIVATE_DIMENSION2 ? 0x8F : 0xE0)), \ |
|
|
c1 = CHAR_FIELD2 (c), \ |
|
|
c2 = CHAR_FIELD3 (c)) \ |
|
|
: (charset = CHAR_FIELD2 (c) + 0x70, \ |
|
|
c1 = CHAR_FIELD3 (c), \ |
|
|
c2 = -1))) |
|
|
|
|
|
/* Return 1 iff character C has valid printable glyph. */ |
|
|
#define CHAR_PRINTABLE_P(c) (ASCII_BYTE_P (c) || char_printable_p (c)) |
|
|
|
|
|
/* The charset of the character at STR is stored in CHARSET, and the |
|
|
position-codes are stored in C1 and C2. |
|
|
We store -1 in C2 if the character is just 2 bytes. */ |
|
|
|
|
|
#define SPLIT_STRING(str, len, charset, c1, c2) \ |
|
|
((BYTES_BY_CHAR_HEAD ((unsigned char) *(str)) < 2 \ |
|
|
|| BYTES_BY_CHAR_HEAD ((unsigned char) *(str)) > len \ |
|
|
|| split_string (str, len, &charset, &c1, &c2) < 0) \ |
|
|
? c1 = *(str), charset = CHARSET_ASCII \ |
|
|
: charset) |
|
|
|
|
|
/* Mapping table from ISO2022's charset (specified by DIMENSION, |
|
|
CHARS, and FINAL_CHAR) to Emacs' charset. Should be accessed by |
|
|
macro ISO_CHARSET_TABLE (DIMENSION, CHARS, FINAL_CHAR). */ |
|
|
extern int iso_charset_table[2][2][128]; |
|
286 |
|
|
287 |
#define ISO_CHARSET_TABLE(dimension, chars, final_char) \ |
/* Check if X is a valid charset symbol. If valid, set ID to the id |
288 |
iso_charset_table[XINT (dimension) - 1][XINT (chars) > 94][XINT (final_char)] |
number of the charset. Otherwise, signal an error. */ |
289 |
|
#define CHECK_CHARSET_GET_ID(x, id) \ |
290 |
|
do { \ |
291 |
|
int idx; \ |
292 |
|
\ |
293 |
|
if (! SYMBOLP (x) || (idx = CHARSET_SYMBOL_HASH_INDEX (x)) < 0) \ |
294 |
|
x = wrong_type_argument (Qcharsetp, (x)); \ |
295 |
|
id = AREF (HASH_VALUE (XHASH_TABLE (Vcharset_hash_table), idx), \ |
296 |
|
charset_id); \ |
297 |
|
} while (0) |
298 |
|
|
|
#define BASE_LEADING_CODE_P(c) (BYTES_BY_CHAR_HEAD ((unsigned char) (c)) > 1) |
|
299 |
|
|
300 |
/* Return how many bytes C will occupy in a multibyte buffer. */ |
/* Check if X is a valid charset symbol. If valid, set ATTR to the |
301 |
#define CHAR_BYTES(c) \ |
attr vector of the charset. Otherwise, signal an error. */ |
302 |
(SINGLE_BYTE_CHAR_P (c) \ |
#define CHECK_CHARSET_GET_ATTR(x, attr) \ |
303 |
? ((ASCII_BYTE_P (c) || (c) >= 0xA0) ? 1 : 2) \ |
do { \ |
304 |
: char_bytes (c)) |
if (!SYMBOLP (x) || NILP (attr = CHARSET_SYMBOL_ATTRIBUTES (x))) \ |
305 |
|
x = wrong_type_argument (Qcharsetp, (x)); \ |
|
/* The following two macros CHAR_STRING and STRING_CHAR are the main |
|
|
entry points to convert between Emacs's two types of character |
|
|
representations: multi-byte form and single-word form (character |
|
|
code). */ |
|
|
|
|
|
/* Store multi-byte form of the character C in STR. The caller should |
|
|
allocate at least MAX_MULTIBYTE_LENGTH bytes area at STR in |
|
|
advance. Returns the length of the multi-byte form. If C is an |
|
|
invalid character code, signal an error. */ |
|
|
|
|
|
#define CHAR_STRING(c, str) \ |
|
|
(SINGLE_BYTE_CHAR_P (c) \ |
|
|
? ((ASCII_BYTE_P (c) || c >= 0xA0) \ |
|
|
? (*(str) = (unsigned char)(c), 1) \ |
|
|
: (*(str) = LEADING_CODE_8_BIT_CONTROL, *((str)+ 1) = c + 0x20, 2)) \ |
|
|
: char_to_string (c, (unsigned char *) str)) |
|
|
|
|
|
/* Like CHAR_STRING but don't signal an error if C is invalid. |
|
|
Value is -1 in this case. */ |
|
|
|
|
|
#define CHAR_STRING_NO_SIGNAL(c, str) \ |
|
|
(SINGLE_BYTE_CHAR_P (c) \ |
|
|
? ((ASCII_BYTE_P (c) || c >= 0xA0) \ |
|
|
? (*(str) = (unsigned char)(c), 1) \ |
|
|
: (*(str) = LEADING_CODE_8_BIT_CONTROL, *((str)+ 1) = c + 0x20, 2)) \ |
|
|
: char_to_string_1 (c, (unsigned char *) str)) |
|
|
|
|
|
/* Return a character code of the character of which multi-byte form |
|
|
is at STR and the length is LEN. If STR doesn't contain valid |
|
|
multi-byte form, only the first byte in STR is returned. */ |
|
|
|
|
|
#define STRING_CHAR(str, len) \ |
|
|
(BYTES_BY_CHAR_HEAD ((unsigned char) *(str)) == 1 \ |
|
|
? (unsigned char) *(str) \ |
|
|
: string_to_char (str, len, 0)) |
|
|
|
|
|
/* This is like STRING_CHAR but the third arg ACTUAL_LEN is set to the |
|
|
length of the multi-byte form. Just to know the length, use |
|
|
MULTIBYTE_FORM_LENGTH. */ |
|
|
|
|
|
#define STRING_CHAR_AND_LENGTH(str, len, actual_len) \ |
|
|
(BYTES_BY_CHAR_HEAD ((unsigned char) *(str)) == 1 \ |
|
|
? ((actual_len) = 1), (unsigned char) *(str) \ |
|
|
: string_to_char (str, len, &(actual_len))) |
|
|
|
|
|
/* Fetch the "next" character from Lisp string STRING at byte position |
|
|
BYTEIDX, character position CHARIDX. Store it into OUTPUT. |
|
|
|
|
|
All the args must be side-effect-free. |
|
|
BYTEIDX and CHARIDX must be lvalues; |
|
|
we increment them past the character fetched. */ |
|
|
|
|
|
#define FETCH_STRING_CHAR_ADVANCE(OUTPUT, STRING, CHARIDX, BYTEIDX) \ |
|
|
if (1) \ |
|
|
{ \ |
|
|
CHARIDX++; \ |
|
|
if (STRING_MULTIBYTE (STRING)) \ |
|
|
{ \ |
|
|
unsigned char *ptr = &XSTRING (STRING)->data[BYTEIDX]; \ |
|
|
int space_left = XSTRING (STRING)->size_byte - BYTEIDX; \ |
|
|
int actual_len; \ |
|
|
\ |
|
|
OUTPUT = STRING_CHAR_AND_LENGTH (ptr, space_left, actual_len); \ |
|
|
BYTEIDX += actual_len; \ |
|
|
} \ |
|
|
else \ |
|
|
OUTPUT = XSTRING (STRING)->data[BYTEIDX++]; \ |
|
|
} \ |
|
|
else |
|
|
|
|
|
/* Like FETCH_STRING_CHAR_ADVANCE but assume STRING is multibyte. */ |
|
|
|
|
|
#define FETCH_STRING_CHAR_ADVANCE_NO_CHECK(OUTPUT, STRING, CHARIDX, BYTEIDX) \ |
|
|
if (1) \ |
|
|
{ \ |
|
|
unsigned char *fetch_string_char_ptr = &XSTRING (STRING)->data[BYTEIDX]; \ |
|
|
int fetch_string_char_space_left = XSTRING (STRING)->size_byte - BYTEIDX; \ |
|
|
int actual_len; \ |
|
|
\ |
|
|
OUTPUT \ |
|
|
= STRING_CHAR_AND_LENGTH (fetch_string_char_ptr, \ |
|
|
fetch_string_char_space_left, actual_len); \ |
|
|
\ |
|
|
BYTEIDX += actual_len; \ |
|
|
CHARIDX++; \ |
|
|
} \ |
|
|
else |
|
|
|
|
|
/* Like FETCH_STRING_CHAR_ADVANCE but fetch character from the current |
|
|
buffer. */ |
|
|
|
|
|
#define FETCH_CHAR_ADVANCE(OUTPUT, CHARIDX, BYTEIDX) \ |
|
|
if (1) \ |
|
|
{ \ |
|
|
CHARIDX++; \ |
|
|
if (!NILP (current_buffer->enable_multibyte_characters)) \ |
|
|
{ \ |
|
|
unsigned char *ptr = BYTE_POS_ADDR (BYTEIDX); \ |
|
|
int space_left = ((CHARIDX < GPT ? GPT_BYTE : Z_BYTE) - BYTEIDX); \ |
|
|
int actual_len; \ |
|
|
\ |
|
|
OUTPUT= STRING_CHAR_AND_LENGTH (ptr, space_left, actual_len); \ |
|
|
BYTEIDX += actual_len; \ |
|
|
} \ |
|
|
else \ |
|
|
{ \ |
|
|
OUTPUT = *(BYTE_POS_ADDR (BYTEIDX)); \ |
|
|
BYTEIDX++; \ |
|
|
} \ |
|
|
} \ |
|
|
else |
|
|
|
|
|
/* Return the length of the multi-byte form at string STR of length LEN. */ |
|
|
|
|
|
#define MULTIBYTE_FORM_LENGTH(str, len) \ |
|
|
(BYTES_BY_CHAR_HEAD (*(unsigned char *)(str)) == 1 \ |
|
|
? 1 \ |
|
|
: multibyte_form_length (str, len)) |
|
|
|
|
|
#ifdef emacs |
|
|
|
|
|
/* Increase the buffer byte position POS_BYTE of the current buffer to |
|
|
the next character boundary. This macro relies on the fact that |
|
|
*GPT_ADDR and *Z_ADDR are always accessible and the values are |
|
|
'\0'. No range checking of POS. */ |
|
|
|
|
|
#ifdef BYTE_COMBINING_DEBUG |
|
|
|
|
|
#define INC_POS(pos_byte) \ |
|
|
do { \ |
|
|
unsigned char *p = BYTE_POS_ADDR (pos_byte); \ |
|
|
if (BASE_LEADING_CODE_P (*p)) \ |
|
|
{ \ |
|
|
int len, bytes; \ |
|
|
len = Z_BYTE - pos_byte; \ |
|
|
PARSE_MULTIBYTE_SEQ (p, len, bytes); \ |
|
|
pos_byte += bytes; \ |
|
|
} \ |
|
|
else \ |
|
|
pos_byte++; \ |
|
306 |
} while (0) |
} while (0) |
307 |
|
|
|
#else /* not BYTE_COMBINING_DEBUG */ |
|
308 |
|
|
309 |
#define INC_POS(pos_byte) \ |
#define CHECK_CHARSET_GET_CHARSET(x, charset) \ |
310 |
do { \ |
do { \ |
311 |
unsigned char *p = BYTE_POS_ADDR (pos_byte); \ |
int id; \ |
312 |
pos_byte += BYTES_BY_CHAR_HEAD (*p); \ |
CHECK_CHARSET_GET_ID (x, id); \ |
313 |
|
charset = CHARSET_FROM_ID (id); \ |
314 |
} while (0) |
} while (0) |
315 |
|
|
|
#endif /* not BYTE_COMBINING_DEBUG */ |
|
316 |
|
|
317 |
/* Decrease the buffer byte position POS_BYTE of the current buffer to |
/* Lookup Vcharset_order_list and return the first charset that |
318 |
the previous character boundary. No range checking of POS. */ |
contains the character C. */ |
319 |
#define DEC_POS(pos_byte) \ |
#define CHAR_CHARSET(c) \ |
320 |
do { \ |
char_charset ((c), Qnil, NULL) |
321 |
unsigned char *p, *p_min; \ |
|
322 |
\ |
#if 0 |
323 |
pos_byte--; \ |
/* Char-table of charset-sets. Each element is a bool vector indexed |
324 |
if (pos_byte < GPT_BYTE) \ |
by a charset ID. */ |
325 |
p = BEG_ADDR + pos_byte - 1, p_min = BEG_ADDR; \ |
extern Lisp_Object Vchar_charset_set; |
326 |
else \ |
|
327 |
p = BEG_ADDR + GAP_SIZE + pos_byte - 1, p_min = GAP_END_ADDR; \ |
/* Charset-bag of character C. */ |
328 |
if (p > p_min && !CHAR_HEAD_P (*p)) \ |
#define CHAR_CHARSET_SET(c) \ |
329 |
{ \ |
CHAR_TABLE_REF (Vchar_charset_set, c) |
|
unsigned char *pend = p--; \ |
|
|
int len, bytes; \ |
|
|
while (p > p_min && !CHAR_HEAD_P (*p)) p--; \ |
|
|
len = pend + 1 - p; \ |
|
|
PARSE_MULTIBYTE_SEQ (p, len, bytes); \ |
|
|
if (bytes == len) \ |
|
|
pos_byte -= len - 1; \ |
|
|
} \ |
|
|
} while (0) |
|
330 |
|
|
331 |
/* Increment both CHARPOS and BYTEPOS, each in the appropriate way. */ |
/* Check if two characters C1 and C2 belong to the same charset. */ |
332 |
|
#define SAME_CHARSET_P(c1, c2) \ |
333 |
|
intersection_p (CHAR_CHARSET_SET (c1), CHAR_CHARSET_SET (c2)) |
334 |
|
|
335 |
#define INC_BOTH(charpos, bytepos) \ |
#endif |
|
do \ |
|
|
{ \ |
|
|
(charpos)++; \ |
|
|
if (NILP (current_buffer->enable_multibyte_characters)) \ |
|
|
(bytepos)++; \ |
|
|
else \ |
|
|
INC_POS ((bytepos)); \ |
|
|
} \ |
|
|
while (0) |
|
|
|
|
|
/* Decrement both CHARPOS and BYTEPOS, each in the appropriate way. */ |
|
|
|
|
|
#define DEC_BOTH(charpos, bytepos) \ |
|
|
do \ |
|
|
{ \ |
|
|
(charpos)--; \ |
|
|
if (NILP (current_buffer->enable_multibyte_characters)) \ |
|
|
(bytepos)--; \ |
|
|
else \ |
|
|
DEC_POS ((bytepos)); \ |
|
|
} \ |
|
|
while (0) |
|
|
|
|
|
/* Increase the buffer byte position POS_BYTE of the current buffer to |
|
|
the next character boundary. This macro relies on the fact that |
|
|
*GPT_ADDR and *Z_ADDR are always accessible and the values are |
|
|
'\0'. No range checking of POS_BYTE. */ |
|
336 |
|
|
|
#ifdef BYTE_COMBINING_DEBUG |
|
337 |
|
|
338 |
#define BUF_INC_POS(buf, pos_byte) \ |
/* Return a character correponding to the code-point CODE of CHARSET. |
339 |
do { \ |
Try some optimization before calling decode_char. */ |
|
unsigned char *p = BUF_BYTE_ADDRESS (buf, pos_byte); \ |
|
|
if (BASE_LEADING_CODE_P (*p)) \ |
|
|
{ \ |
|
|
int len, bytes; \ |
|
|
len = BUF_Z_BYTE (buf) - pos_byte; \ |
|
|
PARSE_MULTIBYTE_SEQ (p, len, bytes); \ |
|
|
pos_byte += bytes; \ |
|
|
} \ |
|
|
else \ |
|
|
pos_byte++; \ |
|
|
} while (0) |
|
340 |
|
|
341 |
#else /* not BYTE_COMBINING_DEBUG */ |
#define DECODE_CHAR(charset, code) \ |
342 |
|
((ASCII_BYTE_P (code) && (charset)->ascii_compatible_p) \ |
343 |
|
? (code) \ |
344 |
|
: ((code) < (charset)->min_code || (code) > (charset)->max_code) \ |
345 |
|
? -1 \ |
346 |
|
: (charset)->unified_p \ |
347 |
|
? decode_char ((charset), (code)) \ |
348 |
|
: (charset)->method == CHARSET_METHOD_OFFSET \ |
349 |
|
? ((charset)->code_linear_p \ |
350 |
|
? (code) - (charset)->min_code + (charset)->code_offset \ |
351 |
|
: decode_char ((charset), (code))) \ |
352 |
|
: (charset)->method == CHARSET_METHOD_MAP \ |
353 |
|
? ((charset)->code_linear_p \ |
354 |
|
? XINT (AREF (CHARSET_DECODER (charset), \ |
355 |
|
(code) - (charset)->min_code)) \ |
356 |
|
: decode_char ((charset), (code))) \ |
357 |
|
: decode_char ((charset), (code))) |
358 |
|
|
359 |
|
|
360 |
|
/* Return a code point of CHAR in CHARSET. |
361 |
|
Try some optimization before calling encode_char. */ |
362 |
|
|
363 |
|
#define ENCODE_CHAR(charset, c) \ |
364 |
|
((ASCII_CHAR_P (c) && (charset)->ascii_compatible_p) \ |
365 |
|
? (c) \ |
366 |
|
: (charset)->unified_p \ |
367 |
|
? encode_char ((charset), (c)) \ |
368 |
|
: ((c) < (charset)->min_char || (c) > (charset)->max_char) \ |
369 |
|
? (charset)->invalid_code \ |
370 |
|
: (charset)->method == CHARSET_METHOD_OFFSET \ |
371 |
|
? ((charset)->code_linear_p \ |
372 |
|
? (c) - (charset)->code_offset + (charset)->min_code \ |
373 |
|
: encode_char ((charset), (c))) \ |
374 |
|
: (charset)->method == CHARSET_METHOD_MAP \ |
375 |
|
? ((charset)->compact_codes_p \ |
376 |
|
? XFASTINT (CHAR_TABLE_REF (CHARSET_ENCODER (charset), (c))) \ |
377 |
|
: encode_char ((charset), (c))) \ |
378 |
|
: encode_char ((charset), (c))) |
379 |
|
|
380 |
|
|
381 |
|
/* Set to 1 when a charset map is loaded to warn that a buffer text |
382 |
|
and a string data may be relocated. */ |
383 |
|
extern int charset_map_loaded; |
384 |
|
|
385 |
|
|
386 |
|
/* Set CHARSET to the charset highest priority of C, CODE to the |
387 |
|
code-point of C in CHARSET. */ |
388 |
|
#define SPLIT_CHAR(c, charset, code) \ |
389 |
|
((charset) = char_charset ((c), Qnil, &(code))) |
390 |
|
|
391 |
|
|
392 |
|
#define ISO_MAX_DIMENSION 3 |
393 |
|
#define ISO_MAX_CHARS 2 |
394 |
|
#define ISO_MAX_FINAL 0x80 /* only 0x30..0xFF are used */ |
395 |
|
|
396 |
#define BUF_INC_POS(buf, pos_byte) \ |
/* Mapping table from ISO2022's charset (specified by DIMENSION, |
397 |
do { \ |
CHARS, and FINAL_CHAR) to Emacs' charset ID. Should be accessed by |
398 |
unsigned char *p = BUF_BYTE_ADDRESS (buf, pos_byte); \ |
macro ISO_CHARSET_TABLE (DIMENSION, CHARS, FINAL_CHAR). */ |
399 |
pos_byte += BYTES_BY_CHAR_HEAD (*p); \ |
extern int iso_charset_table[ISO_MAX_DIMENSION][ISO_MAX_CHARS][ISO_MAX_FINAL]; |
|
} while (0) |
|
400 |
|
|
401 |
#endif /* not BYTE_COMBINING_DEBUG */ |
/* A charset of type iso2022 who has DIMENSION, CHARS, and FINAL |
402 |
|
(final character). */ |
403 |
|
#define ISO_CHARSET_TABLE(dimension, chars_96, final) \ |
404 |
|
iso_charset_table[(dimension) - 1][(chars_96)][(final)] |
405 |
|
|
406 |
|
/* Nonzero iff the charset who has FAST_MAP may contain C. */ |
407 |
|
#define CHARSET_FAST_MAP_REF(c, fast_map) \ |
408 |
|
((c) < 0x10000 \ |
409 |
|
? fast_map[(c) >> 10] & (1 << (((c) >> 7) & 7)) \ |
410 |
|
: fast_map[((c) >> 15) + 62] & (1 << (((c) >> 12) & 7))) |
411 |
|
|
412 |
/* Decrease the buffer byte position POS_BYTE of the current buffer to |
#define CHARSET_FAST_MAP_SET(c, fast_map) \ |
413 |
the previous character boundary. No range checking of POS_BYTE. */ |
do { \ |
414 |
#define BUF_DEC_POS(buf, pos_byte) \ |
if ((c) < 0x10000) \ |
415 |
do { \ |
(fast_map)[(c) >> 10] |= 1 << (((c) >> 7) & 7); \ |
416 |
unsigned char *p, *p_min; \ |
else \ |
417 |
pos_byte--; \ |
(fast_map)[((c) >> 15) + 62] |= 1 << (((c) >> 12) & 7); \ |
|
if (pos_byte < BUF_GPT_BYTE (buf)) \ |
|
|
{ \ |
|
|
p = BUF_BEG_ADDR (buf) + pos_byte - 1; \ |
|
|
p_min = BUF_BEG_ADDR (buf); \ |
|
|
} \ |
|
|
else \ |
|
|
{ \ |
|
|
p = BUF_BEG_ADDR (buf) + BUF_GAP_SIZE (buf) + pos_byte - 1; \ |
|
|
p_min = BUF_GAP_END_ADDR (buf); \ |
|
|
} \ |
|
|
if (p > p_min && !CHAR_HEAD_P (*p)) \ |
|
|
{ \ |
|
|
unsigned char *pend = p--; \ |
|
|
int len, bytes; \ |
|
|
while (p > p_min && !CHAR_HEAD_P (*p)) p--; \ |
|
|
len = pend + 1 - p; \ |
|
|
PARSE_MULTIBYTE_SEQ (p, len, bytes); \ |
|
|
if (bytes == len) \ |
|
|
pos_byte -= len - 1; \ |
|
|
} \ |
|
418 |
} while (0) |
} while (0) |
419 |
|
|
|
#endif /* emacs */ |
|
|
|
|
|
/* This is the maximum byte length of multi-byte sequence. */ |
|
|
#define MAX_MULTIBYTE_LENGTH 4 |
|
420 |
|
|
|
extern void invalid_character P_ ((int)); |
|
421 |
|
|
422 |
extern int translate_char P_ ((Lisp_Object, int, int, int, int)); |
/* 1 iff CHARSET may contain the character C. */ |
423 |
extern int split_string P_ ((const unsigned char *, int, int *, |
#define CHAR_CHARSET_P(c, charset) \ |
424 |
unsigned char *, unsigned char *)); |
((ASCII_CHAR_P (c) && (charset)->ascii_compatible_p) \ |
425 |
extern int char_to_string P_ ((int, unsigned char *)); |
|| (CHARSET_UNIFIED_P (charset) \ |
426 |
extern int char_to_string_1 P_ ((int, unsigned char *)); |
? encode_char ((charset), (c)) != (charset)->invalid_code \ |
427 |
extern int string_to_char P_ ((const unsigned char *, int, int *)); |
: (CHARSET_FAST_MAP_REF ((c), (charset)->fast_map) \ |
428 |
extern int char_printable_p P_ ((int c)); |
&& ((charset)->method == CHARSET_METHOD_OFFSET \ |
429 |
extern int multibyte_form_length P_ ((const unsigned char *, int)); |
? (c) >= (charset)->min_char && (c) <= (charset)->max_char \ |
430 |
extern void parse_str_as_multibyte P_ ((unsigned char *, int, int *, int *)); |
: ((charset)->method == CHARSET_METHOD_MAP \ |
431 |
extern int str_as_multibyte P_ ((unsigned char *, int, int, int *)); |
&& (charset)->compact_codes_p) \ |
432 |
extern int parse_str_to_multibyte P_ ((unsigned char *, int)); |
? (XFASTINT (CHAR_TABLE_REF (CHARSET_ENCODER (charset), (c))) \ |
433 |
extern int str_to_multibyte P_ ((unsigned char *, int, int)); |
!= (charset)->invalid_code) \ |
434 |
extern int str_as_unibyte P_ ((unsigned char *, int)); |
: encode_char ((charset), (c)) != (charset)->invalid_code)))) |
435 |
extern int get_charset_id P_ ((Lisp_Object)); |
|
436 |
extern int find_charset_in_text P_ ((unsigned char *, int, int, int *, |
|
437 |
Lisp_Object)); |
extern Lisp_Object Qcharsetp; |
438 |
extern int strwidth P_ ((unsigned char *, int)); |
|
439 |
extern int c_string_width P_ ((unsigned char *, int, int, int *, int *)); |
extern Lisp_Object Qascii, Qunicode; |
440 |
extern int lisp_string_width P_ ((Lisp_Object, int, int *, int *)); |
extern int charset_ascii, charset_8_bit_control, charset_8_bit_graphic; |
441 |
extern int char_bytes P_ ((int)); |
extern int charset_iso_8859_1; |
442 |
extern int char_valid_p P_ ((int, int)); |
extern int charset_primary; |
443 |
|
|
444 |
extern Lisp_Object Vtranslation_table_vector; |
extern struct charset *char_charset P_ ((int, Lisp_Object, unsigned *)); |
445 |
|
extern Lisp_Object charset_attributes P_ ((int)); |
446 |
/* Return a translation table of id number ID. */ |
|
447 |
#define GET_TRANSLATION_TABLE(id) \ |
extern int decode_char P_ ((struct charset *, unsigned)); |
448 |
(XCDR(XVECTOR(Vtranslation_table_vector)->contents[(id)])) |
extern unsigned encode_char P_ ((struct charset *, int)); |
449 |
|
extern int string_xstring_p P_ ((Lisp_Object)); |
|
/* A char-table for characters which may invoke auto-filling. */ |
|
|
extern Lisp_Object Vauto_fill_chars; |
|
|
|
|
|
/* Copy LEN bytes from FROM to TO. This macro should be used only |
|
|
when a caller knows that LEN is short and the obvious copy loop is |
|
|
faster than calling bcopy which has some overhead. Copying a |
|
|
multibyte sequence of a multibyte character is the typical case. */ |
|
450 |
|
|
451 |
#define BCOPY_SHORT(from, to, len) \ |
EXFUN (Funify_charset, 2); |
|
do { \ |
|
|
int i = len; \ |
|
|
unsigned char *from_p = from, *to_p = to; \ |
|
|
while (i--) *to_p++ = *from_p++; \ |
|
|
} while (0) |
|
452 |
|
|
453 |
#endif /* EMACS_CHARSET_H */ |
#endif /* EMACS_CHARSET_H */ |