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