converters.h
7.86 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
/*
* Copyright (C) 1999-2002, 2004-2011, 2016 Free Software Foundation, Inc.
* This file is part of the GNU LIBICONV Library.
*
* The GNU LIBICONV Library is free software; you can redistribute it
* and/or modify it under the terms of the GNU Library General Public
* License as published by the Free Software Foundation; either version 2
* of the License, or (at your option) any later version.
*
* The GNU LIBICONV Library is distributed in the hope that it will be
* useful, but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Library General Public License for more details.
*
* You should have received a copy of the GNU Library General Public
* License along with the GNU LIBICONV Library; see the file COPYING.LIB.
* If not, see <http://www.gnu.org/licenses/>.
*/
/* This file defines all the converters. */
/* Our own notion of wide character, as UCS-4, according to ISO-10646-1. */
typedef unsigned int ucs4_t;
/* State used by a conversion. 0 denotes the initial state. */
typedef unsigned int state_t;
/* iconv_t is an opaque type. This is the real iconv_t type. */
typedef struct conv_struct * conv_t;
/*
* Data type for conversion multibyte -> unicode
*/
struct mbtowc_funcs {
int (*xxx_mbtowc) (conv_t conv, ucs4_t *pwc, unsigned char const *s, size_t n);
/*
* int xxx_mbtowc (conv_t conv, ucs4_t *pwc, unsigned char const *s, size_t n)
* converts the byte sequence starting at s to a wide character. Up to n bytes
* are available at s. n is >= 1.
* Result is number of bytes consumed (if a wide character was read),
* or -1 if invalid, or -2 if n too small,
* or RET_SHIFT_ILSEQ(number of bytes consumed) if invalid input after a shift
* sequence was read,
* or RET_TOOFEW(number of bytes consumed) if only a shift sequence was read.
*/
int (*xxx_flushwc) (conv_t conv, ucs4_t *pwc);
/*
* int xxx_flushwc (conv_t conv, ucs4_t *pwc)
* returns to the initial state and stores the pending wide character, if any.
* Result is 1 (if a wide character was read) or 0 if none was pending.
*/
};
/* Return code if invalid input after a shift sequence of n bytes was read.
(xxx_mbtowc) */
#define RET_SHIFT_ILSEQ(n) (-1-2*(n))
/* Return code if invalid. (xxx_mbtowc) */
#define RET_ILSEQ RET_SHIFT_ILSEQ(0)
/* Return code if only a shift sequence of n bytes was read. (xxx_mbtowc) */
#define RET_TOOFEW(n) (-2-2*(n))
/* Retrieve the n from the encoded RET_... value. */
#define DECODE_SHIFT_ILSEQ(r) ((unsigned int)(RET_SHIFT_ILSEQ(0) - (r)) / 2)
#define DECODE_TOOFEW(r) ((unsigned int)(RET_TOOFEW(0) - (r)) / 2)
/* Maximum value of n that may be used as argument to RET_SHIFT_ILSEQ or RET_TOOFEW. */
#define RET_COUNT_MAX ((INT_MAX / 2) - 1)
/*
* Data type for conversion unicode -> multibyte
*/
struct wctomb_funcs {
int (*xxx_wctomb) (conv_t conv, unsigned char *r, ucs4_t wc, size_t n);
/*
* int xxx_wctomb (conv_t conv, unsigned char *r, ucs4_t wc, size_t n)
* converts the wide character wc to the character set xxx, and stores the
* result beginning at r. Up to n bytes may be written at r. n is >= 1.
* Result is number of bytes written, or -1 if invalid, or -2 if n too small.
*/
int (*xxx_reset) (conv_t conv, unsigned char *r, size_t n);
/*
* int xxx_reset (conv_t conv, unsigned char *r, size_t n)
* stores a shift sequences returning to the initial state beginning at r.
* Up to n bytes may be written at r. n is >= 0.
* Result is number of bytes written, or -2 if n too small.
*/
};
/* Return code if invalid. (xxx_wctomb) */
#define RET_ILUNI -1
/* Return code if output buffer is too small. (xxx_wctomb, xxx_reset) */
#define RET_TOOSMALL -2
/*
* Contents of a conversion descriptor.
*/
struct conv_struct {
struct loop_funcs lfuncs;
/* Input (conversion multibyte -> unicode) */
int iindex;
struct mbtowc_funcs ifuncs;
state_t istate;
/* Output (conversion unicode -> multibyte) */
int oindex;
struct wctomb_funcs ofuncs;
int oflags;
state_t ostate;
/* Operation flags */
int transliterate;
int discard_ilseq;
#ifndef LIBICONV_PLUG
struct iconv_fallbacks fallbacks;
struct iconv_hooks hooks;
#endif
};
/*
* Include all the converters.
*/
#include "ascii.h"
/* General multi-byte encodings */
#include "utf8.h"
#include "ucs2.h"
#include "ucs2be.h"
#include "ucs2le.h"
#include "ucs4.h"
#include "ucs4be.h"
#include "ucs4le.h"
#include "utf16.h"
#include "utf16be.h"
#include "utf16le.h"
#include "utf32.h"
#include "utf32be.h"
#include "utf32le.h"
#include "utf7.h"
#include "ucs2internal.h"
#include "ucs2swapped.h"
#include "ucs4internal.h"
#include "ucs4swapped.h"
#include "c99.h"
#include "java.h"
/* 8-bit encodings */
#include "iso8859_1.h"
#include "iso8859_2.h"
#include "iso8859_3.h"
#include "iso8859_4.h"
#include "iso8859_5.h"
#include "iso8859_6.h"
#include "iso8859_7.h"
#include "iso8859_8.h"
#include "iso8859_9.h"
#include "iso8859_10.h"
#include "iso8859_11.h"
#include "iso8859_13.h"
#include "iso8859_14.h"
#include "iso8859_15.h"
#include "iso8859_16.h"
#include "koi8_r.h"
#include "koi8_u.h"
#include "koi8_ru.h"
#include "cp1250.h"
#include "cp1251.h"
#include "cp1252.h"
#include "cp1253.h"
#include "cp1254.h"
#include "cp1255.h"
#include "cp1256.h"
#include "cp1257.h"
#include "cp1258.h"
#include "cp850.h"
#include "cp862.h"
#include "cp866.h"
#include "cp1131.h"
#include "mac_roman.h"
#include "mac_centraleurope.h"
#include "mac_iceland.h"
#include "mac_croatian.h"
#include "mac_romania.h"
#include "mac_cyrillic.h"
#include "mac_ukraine.h"
#include "mac_greek.h"
#include "mac_turkish.h"
#include "mac_hebrew.h"
#include "mac_arabic.h"
#include "mac_thai.h"
#include "hp_roman8.h"
#include "nextstep.h"
#include "armscii_8.h"
#include "georgian_academy.h"
#include "georgian_ps.h"
#include "koi8_t.h"
#include "pt154.h"
#include "rk1048.h"
#include "mulelao.h"
#include "cp1133.h"
#include "tis620.h"
#include "cp874.h"
#include "viscii.h"
#include "tcvn.h"
/* CJK character sets [CCS = coded character set] [CJKV.INF chapter 3] */
typedef struct {
unsigned short indx; /* index into big table */
unsigned short used; /* bitmask of used entries */
} Summary16;
#include "iso646_jp.h"
#include "jisx0201.h"
#include "jisx0208.h"
#include "jisx0212.h"
#include "iso646_cn.h"
#include "gb2312.h"
#include "isoir165.h"
/*#include "gb12345.h"*/
#include "gbk.h"
#include "cns11643.h"
#include "big5.h"
#include "ksc5601.h"
#include "johab_hangul.h"
/* CJK encodings [CES = character encoding scheme] [CJKV.INF chapter 4] */
#include "euc_jp.h"
#include "sjis.h"
#include "cp932.h"
#include "iso2022_jp.h"
#include "iso2022_jp1.h"
#include "iso2022_jp2.h"
#include "iso2022_jpms.h"
#include "euc_cn.h"
#include "ces_gbk.h"
#include "cp936.h"
#include "gb18030.h"
#include "iso2022_cn.h"
#include "iso2022_cnext.h"
#include "hz.h"
#include "euc_tw.h"
#include "ces_big5.h"
#include "cp950.h"
#include "big5hkscs1999.h"
#include "big5hkscs2001.h"
#include "big5hkscs2004.h"
#include "big5hkscs2008.h"
#include "euc_kr.h"
#include "cp949.h"
#include "johab.h"
#include "iso2022_kr.h"
/* Encodings used by system dependent locales. */
#ifdef USE_AIX
#include "cp856.h"
#include "cp922.h"
#include "cp943.h"
#include "cp1046.h"
#include "cp1124.h"
#include "cp1129.h"
#include "cp1161.h"
#include "cp1162.h"
#include "cp1163.h"
#endif
#ifdef USE_OSF1
#include "dec_kanji.h"
#include "dec_hanyu.h"
#endif
#ifdef USE_DOS
#include "cp437.h"
#include "cp737.h"
#include "cp775.h"
#include "cp852.h"
#include "cp853.h"
#include "cp855.h"
#include "cp857.h"
#include "cp858.h"
#include "cp860.h"
#include "cp861.h"
#include "cp863.h"
#include "cp864.h"
#include "cp865.h"
#include "cp869.h"
#include "cp1125.h"
#endif
#ifdef USE_EXTRA
#include "euc_jisx0213.h"
#include "shift_jisx0213.h"
#include "iso2022_jp3.h"
#include "big5_2003.h"
#include "tds565.h"
#include "atarist.h"
#include "riscos1.h"
#endif