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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364
|
/* Conversion module for UTF-16.
Copyright (C) 1999-2014 Free Software Foundation, Inc.
This file is part of the GNU C Library.
Contributed by Ulrich Drepper <drepper@cygnus.com>, 1999.
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
The GNU C 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
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with the GNU C Library; if not, see
<http://www.gnu.org/licenses/>. */
#include <byteswap.h>
#include <dlfcn.h>
#include <gconv.h>
#include <stddef.h>
#include <stdint.h>
#include <stdlib.h>
#include <string.h>
/* This is the Byte Order Mark character (BOM). */
#define BOM 0xfeff
/* And in the other byte order. */
#define BOM_OE 0xfffe
/* Definitions used in the body of the `gconv' function. */
#define FROM_LOOP from_utf16_loop
#define TO_LOOP to_utf16_loop
#define DEFINE_INIT 0
#define DEFINE_FINI 0
#define MIN_NEEDED_FROM 2
#define MAX_NEEDED_FROM 4
#define MIN_NEEDED_TO 4
#define FROM_DIRECTION (dir == from_utf16)
#define PREPARE_LOOP \
enum direction dir = ((struct utf16_data *) step->__data)->dir; \
enum variant var = ((struct utf16_data *) step->__data)->var; \
if (__builtin_expect (data->__invocation_counter == 0, 0)) \
{ \
if (var == UTF_16) \
{ \
if (FROM_DIRECTION) \
{ \
/* We have to find out which byte order the file is \
encoded in. */ \
if (inptr + 2 > inend) \
return (inptr == inend \
? __GCONV_EMPTY_INPUT : __GCONV_INCOMPLETE_INPUT); \
\
if (get16u (inptr) == BOM) \
/* Simply ignore the BOM character. */ \
*inptrp = inptr += 2; \
else if (get16u (inptr) == BOM_OE) \
{ \
data->__flags |= __GCONV_SWAP; \
*inptrp = inptr += 2; \
} \
} \
else if (!FROM_DIRECTION && !data->__internal_use) \
{ \
/* Emit the Byte Order Mark. */ \
if (__builtin_expect (outbuf + 2 > outend, 0)) \
return __GCONV_FULL_OUTPUT; \
\
put16u (outbuf, BOM); \
outbuf += 2; \
} \
} \
else if ((var == UTF_16LE && BYTE_ORDER == BIG_ENDIAN) \
|| (var == UTF_16BE && BYTE_ORDER == LITTLE_ENDIAN)) \
data->__flags |= __GCONV_SWAP; \
} \
const int swap = data->__flags & __GCONV_SWAP;
#define EXTRA_LOOP_ARGS , swap
/* Direction of the transformation. */
enum direction
{
illegal_dir,
to_utf16,
from_utf16
};
enum variant
{
illegal_var,
UTF_16,
UTF_16LE,
UTF_16BE
};
struct utf16_data
{
enum direction dir;
enum variant var;
};
extern int gconv_init (struct __gconv_step *step);
int
gconv_init (struct __gconv_step *step)
{
/* Determine which direction. */
struct utf16_data *new_data;
enum direction dir = illegal_dir;
enum variant var = illegal_var;
int result;
if (__strcasecmp (step->__from_name, "UTF-16//") == 0)
{
dir = from_utf16;
var = UTF_16;
}
else if (__strcasecmp (step->__to_name, "UTF-16//") == 0)
{
dir = to_utf16;
var = UTF_16;
}
else if (__strcasecmp (step->__from_name, "UTF-16BE//") == 0)
{
dir = from_utf16;
var = UTF_16BE;
}
else if (__strcasecmp (step->__to_name, "UTF-16BE//") == 0)
{
dir = to_utf16;
var = UTF_16BE;
}
else if (__strcasecmp (step->__from_name, "UTF-16LE//") == 0)
{
dir = from_utf16;
var = UTF_16LE;
}
else if (__strcasecmp (step->__to_name, "UTF-16LE//") == 0)
{
dir = to_utf16;
var = UTF_16LE;
}
result = __GCONV_NOCONV;
if (__builtin_expect (dir, to_utf16) != illegal_dir)
{
new_data = (struct utf16_data *) malloc (sizeof (struct utf16_data));
result = __GCONV_NOMEM;
if (new_data != NULL)
{
new_data->dir = dir;
new_data->var = var;
step->__data = new_data;
if (dir == from_utf16)
{
step->__min_needed_from = MIN_NEEDED_FROM;
step->__max_needed_from = MAX_NEEDED_FROM;
step->__min_needed_to = MIN_NEEDED_TO;
step->__max_needed_to = MIN_NEEDED_TO;
}
else
{
step->__min_needed_from = MIN_NEEDED_TO;
step->__max_needed_from = MIN_NEEDED_TO;
step->__min_needed_to = MIN_NEEDED_FROM;
step->__max_needed_to = MAX_NEEDED_FROM;
}
step->__stateful = 0;
result = __GCONV_OK;
}
}
return result;
}
extern void gconv_end (struct __gconv_step *data);
void
gconv_end (struct __gconv_step *data)
{
free (data->__data);
}
/* Convert from the internal (UCS4-like) format to UTF-16. */
#define MIN_NEEDED_INPUT MIN_NEEDED_TO
#define MIN_NEEDED_OUTPUT MIN_NEEDED_FROM
#define MAX_NEEDED_OUTPUT MAX_NEEDED_FROM
#define LOOPFCT TO_LOOP
#define BODY \
{ \
uint32_t c = get32 (inptr); \
\
if (__builtin_expect (c >= 0xd800 && c < 0xe000, 0)) \
{ \
/* Surrogate characters in UCS-4 input are not valid. \
We must catch this. If we let surrogates pass through, \
attackers could make a security hole exploit by \
synthesizing any desired plane 1-16 character. */ \
result = __GCONV_ILLEGAL_INPUT; \
if (! ignore_errors_p ()) \
break; \
inptr += 4; \
++*irreversible; \
continue; \
} \
\
if (swap) \
{ \
if (__builtin_expect (c >= 0x10000, 0)) \
{ \
if (__builtin_expect (c >= 0x110000, 0)) \
{ \
STANDARD_TO_LOOP_ERR_HANDLER (4); \
} \
\
/* Generate a surrogate character. */ \
if (__builtin_expect (outptr + 4 > outend, 0)) \
{ \
/* Overflow in the output buffer. */ \
result = __GCONV_FULL_OUTPUT; \
break; \
} \
\
put16 (outptr, bswap_16 (0xd7c0 + (c >> 10))); \
outptr += 2; \
put16 (outptr, bswap_16 (0xdc00 + (c & 0x3ff))); \
} \
else \
put16 (outptr, bswap_16 (c)); \
} \
else \
{ \
if (__builtin_expect (c >= 0x10000, 0)) \
{ \
if (__builtin_expect (c >= 0x110000, 0)) \
{ \
STANDARD_TO_LOOP_ERR_HANDLER (4); \
} \
\
/* Generate a surrogate character. */ \
if (__builtin_expect (outptr + 4 > outend, 0)) \
{ \
/* Overflow in the output buffer. */ \
result = __GCONV_FULL_OUTPUT; \
break; \
} \
\
put16 (outptr, 0xd7c0 + (c >> 10)); \
outptr += 2; \
put16 (outptr, 0xdc00 + (c & 0x3ff)); \
} \
else \
put16 (outptr, c); \
} \
outptr += 2; \
inptr += 4; \
}
#define LOOP_NEED_FLAGS
#define EXTRA_LOOP_DECLS \
, int swap
#include <iconv/loop.c>
/* Convert from UTF-16 to the internal (UCS4-like) format. */
#define MIN_NEEDED_INPUT MIN_NEEDED_FROM
#define MAX_NEEDED_INPUT MAX_NEEDED_FROM
#define MIN_NEEDED_OUTPUT MIN_NEEDED_TO
#define LOOPFCT FROM_LOOP
#define BODY \
{ \
uint16_t u1 = get16 (inptr); \
\
if (swap) \
{ \
u1 = bswap_16 (u1); \
\
if (__builtin_expect (u1 < 0xd800, 1) || u1 > 0xdfff) \
{ \
/* No surrogate. */ \
put32 (outptr, u1); \
inptr += 2; \
} \
else \
{ \
uint16_t u2; \
\
/* It's a surrogate character. At least the first word says \
it is. */ \
if (__builtin_expect (inptr + 4 > inend, 0)) \
{ \
/* We don't have enough input for another complete input \
character. */ \
result = __GCONV_INCOMPLETE_INPUT; \
break; \
} \
\
inptr += 2; \
u2 = bswap_16 (get16 (inptr)); \
if (__builtin_expect (u2 < 0xdc00, 0) \
|| __builtin_expect (u2 > 0xdfff, 0)) \
{ \
/* This is no valid second word for a surrogate. */ \
inptr -= 2; \
STANDARD_FROM_LOOP_ERR_HANDLER (2); \
} \
\
put32 (outptr, ((u1 - 0xd7c0) << 10) + (u2 - 0xdc00)); \
inptr += 2; \
} \
} \
else \
{ \
if (__builtin_expect (u1 < 0xd800, 1) || u1 > 0xdfff) \
{ \
/* No surrogate. */ \
put32 (outptr, u1); \
inptr += 2; \
} \
else \
{ \
/* It's a surrogate character. At least the first word says \
it is. */ \
if (__builtin_expect (inptr + 4 > inend, 0)) \
{ \
/* We don't have enough input for another complete input \
character. */ \
result = __GCONV_INCOMPLETE_INPUT; \
break; \
} \
\
inptr += 2; \
uint16_t u2 = get16 (inptr); \
if (__builtin_expect (u2 < 0xdc00, 0) \
|| __builtin_expect (u2 > 0xdfff, 0)) \
{ \
/* This is no valid second word for a surrogate. */ \
inptr -= 2; \
STANDARD_FROM_LOOP_ERR_HANDLER (2); \
} \
\
put32 (outptr, ((u1 - 0xd7c0) << 10) + (u2 - 0xdc00)); \
inptr += 2; \
} \
} \
outptr += 4; \
}
#define LOOP_NEED_FLAGS
#define EXTRA_LOOP_DECLS \
, int swap
#include <iconv/loop.c>
/* Now define the toplevel functions. */
#include <iconv/skeleton.c>
|