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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526
|
/* tld.c --- Declarations for TLD restriction checking.
Copyright (C) 2004-2025 Simon Josefsson.
Copyright (C) 2003-2025 Free Software Foundation, Inc.
Author: Thomas Jacob, Internet24.de
This file is part of GNU Libidn.
GNU Libidn is free software: you can redistribute it and/or
modify it under the terms of either:
* the GNU Lesser General Public License as published by the Free
Software Foundation; either version 3 of the License, or (at
your option) any later version.
or
* the GNU General Public License as published by the Free
Software Foundation; either version 2 of the License, or (at
your option) any later version.
or both in parallel, as here.
GNU Libidn 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
General Public License for more details.
You should have received copies of the GNU General Public License and
the GNU Lesser General Public License along with this program. If
not, see <https://www.gnu.org/licenses/>. */
#include <config.h>
/* Get stringprep_utf8_to_ucs4, stringprep_locale_to_utf8. */
#include <stringprep.h>
/* Get strcmp(). */
#include <string.h>
/* Get specifications. */
#include <tld.h>
/* Array of built-in domain restriction structures. See tlds.c. */
extern const Tld_table *_tld_tables[];
/**
* tld_get_table:
* @tld: TLD name (e.g. "com") as zero terminated ASCII byte string.
* @tables: Zero terminated array of #Tld_table info-structures for
* TLDs.
*
* Get the TLD table for a named TLD by searching through the given
* TLD table array.
*
* Return value: Return structure corresponding to TLD @tld by going
* thru @tables, or return %NULL if no such structure is found.
*/
const Tld_table *
tld_get_table (const char *tld, const Tld_table **tables)
{
const Tld_table **tldtable = NULL;
if (!tld || !tables)
return NULL;
for (tldtable = tables; *tldtable; tldtable++)
if (!strcmp ((*tldtable)->name, tld))
return *tldtable;
return NULL;
}
/**
* tld_default_table:
* @tld: TLD name (e.g. "com") as zero terminated ASCII byte string.
* @overrides: Additional zero terminated array of #Tld_table
* info-structures for TLDs, or %NULL to only use library default
* tables.
*
* Get the TLD table for a named TLD, using the internal defaults,
* possibly overridden by the (optional) supplied tables.
*
* Return value: Return structure corresponding to TLD @tld_str, first
* looking through @overrides then thru built-in list, or %NULL if
* no such structure found.
*/
const Tld_table *
tld_default_table (const char *tld, const Tld_table **overrides)
{
const Tld_table *tldtable = NULL;
if (!tld)
return NULL;
if (overrides)
tldtable = tld_get_table (tld, overrides);
if (!tldtable)
tldtable = tld_get_table (tld, _tld_tables);
return tldtable;
}
#define DOTP(c) ((c) == 0x002E || (c) == 0x3002 || \
(c) == 0xFF0E || (c) == 0xFF61)
/**
* tld_get_4:
* @in: Array of unicode code points to process. Does not need to be
* zero terminated.
* @inlen: Number of unicode code points.
* @out: Zero terminated ascii result string pointer.
*
* Isolate the top-level domain of @in and return it as an ASCII
* string in @out.
*
* Return value: Return %TLD_SUCCESS on success, or the corresponding
* #Tld_rc error code otherwise.
*/
int
tld_get_4 (const uint32_t *in, size_t inlen, char **out)
{
const uint32_t *ipos;
size_t olen;
*out = NULL;
if (!in || inlen == 0)
return TLD_NODATA;
ipos = &in[inlen - 1];
olen = 0;
/* Scan backwards for non(latin)letters. */
while (ipos >= in && ((*ipos >= 0x41 && *ipos <= 0x5A) ||
(*ipos >= 0x61 && *ipos <= 0x7A)))
ipos--, olen++;
if (olen > 0 && ipos >= in && DOTP (*ipos))
{
/* Found something that appears a TLD. */
char *out_s = malloc (sizeof (char) * (olen + 1));
char *opos = out_s;
if (!opos)
return TLD_MALLOC_ERROR;
ipos++;
/* Transcribe to lowercase ascii string. */
for (; ipos < &in[inlen]; ipos++, opos++)
*opos = *ipos > 0x5A ? *ipos : *ipos + 0x20;
*opos = 0;
*out = out_s;
return TLD_SUCCESS;
}
return TLD_NO_TLD;
}
/**
* tld_get_4z:
* @in: Zero terminated array of unicode code points to process.
* @out: Zero terminated ascii result string pointer.
*
* Isolate the top-level domain of @in and return it as an ASCII
* string in @out.
*
* Return value: Return %TLD_SUCCESS on success, or the corresponding
* #Tld_rc error code otherwise.
*/
int
tld_get_4z (const uint32_t *in, char **out)
{
const uint32_t *ipos = in;
if (!in)
return TLD_NODATA;
while (*ipos)
ipos++;
return tld_get_4 (in, ipos - in, out);
}
/**
* tld_get_z:
* @in: Zero terminated character array to process.
* @out: Zero terminated ascii result string pointer.
*
* Isolate the top-level domain of @in and return it as an ASCII
* string in @out. The input string @in may be UTF-8, ISO-8859-1 or
* any ASCII compatible character encoding.
*
* Return value: Return %TLD_SUCCESS on success, or the corresponding
* #Tld_rc error code otherwise.
*/
int
tld_get_z (const char *in, char **out)
{
uint32_t *iucs;
size_t i, ilen;
int rc;
ilen = strlen (in);
iucs = calloc (ilen, sizeof (*iucs));
if (!iucs)
return TLD_MALLOC_ERROR;
for (i = 0; i < ilen; i++)
iucs[i] = in[i];
rc = tld_get_4 (iucs, ilen, out);
free (iucs);
return rc;
}
/*
* tld_checkchar - verify that character is permitted
* @ch: 32 bit unicode character to check.
* @tld: A #Tld_table data structure to check @ch against.
*
* Verify if @ch is either in [a-z0-9-.] or mentioned as a valid
* character in @tld.
*
* Return value: Return the #Tld_rc value %TLD_SUCCESS if @ch is a
* valid character for the TLD @tld or if @tld is %NULL,
* %TLD_INVALID if @ch is invalid as defined by @tld.
*/
static int
_tld_checkchar (uint32_t ch, const Tld_table *tld)
{
const Tld_table_element *s, *e, *m;
if (!tld)
return TLD_SUCCESS;
/* Check for [-a-z0-9.]. */
if ((ch >= 0x61 && ch <= 0x7A) ||
(ch >= 0x30 && ch <= 0x39) || ch == 0x2D || DOTP (ch))
return TLD_SUCCESS;
s = tld->valid;
e = s + tld->nvalid;
while (s < e)
{
m = s + ((e - s) >> 1);
if (ch < m->start)
e = m;
else if (ch > m->end)
s = m + 1;
else
return TLD_SUCCESS;
}
return TLD_INVALID;
}
/**
* tld_check_4t:
* @in: Array of unicode code points to process. Does not need to be
* zero terminated.
* @inlen: Number of unicode code points.
* @errpos: Position of offending character is returned here.
* @tld: A #Tld_table data structure representing the restrictions for
* which the input should be tested.
*
* Test each of the code points in @in for whether or not
* they are allowed by the data structure in @tld, return
* the position of the first character for which this is not
* the case in @errpos.
*
* Return value: Returns the #Tld_rc value %TLD_SUCCESS if all code
* points are valid or when @tld is null, %TLD_INVALID if a
* character is not allowed, or additional error codes on general
* failure conditions.
*/
int
tld_check_4t (const uint32_t *in, size_t inlen, size_t *errpos,
const Tld_table *tld)
{
const uint32_t *ipos;
int rc;
if (!tld) /* No data for TLD so everything is valid. */
return TLD_SUCCESS;
ipos = in;
while (ipos < &in[inlen])
{
rc = _tld_checkchar (*ipos, tld);
if (rc != TLD_SUCCESS)
{
if (errpos)
*errpos = ipos - in;
return rc;
}
ipos++;
}
return TLD_SUCCESS;
}
/**
* tld_check_4tz:
* @in: Zero terminated array of unicode code points to process.
* @errpos: Position of offending character is returned here.
* @tld: A #Tld_table data structure representing the restrictions for
* which the input should be tested.
*
* Test each of the code points in @in for whether or not
* they are allowed by the data structure in @tld, return
* the position of the first character for which this is not
* the case in @errpos.
*
* Return value: Returns the #Tld_rc value %TLD_SUCCESS if all code
* points are valid or when @tld is null, %TLD_INVALID if a
* character is not allowed, or additional error codes on general
* failure conditions.
*/
int
tld_check_4tz (const uint32_t *in, size_t *errpos, const Tld_table *tld)
{
const uint32_t *ipos = in;
if (!ipos)
return TLD_NODATA;
while (*ipos)
ipos++;
return tld_check_4t (in, ipos - in, errpos, tld);
}
/**
* tld_check_4:
* @in: Array of unicode code points to process. Does not need to be
* zero terminated.
* @inlen: Number of unicode code points.
* @errpos: Position of offending character is returned here.
* @overrides: A #Tld_table array of additional domain restriction
* structures that complement and supersede the built-in information.
*
* Test each of the code points in @in for whether or not they are
* allowed by the information in @overrides or by the built-in TLD
* restriction data. When data for the same TLD is available both
* internally and in @overrides, the information in @overrides takes
* precedence. If several entries for a specific TLD are found, the
* first one is used. If @overrides is %NULL, only the built-in
* information is used. The position of the first offending character
* is returned in @errpos.
*
* Return value: Returns the #Tld_rc value %TLD_SUCCESS if all code
* points are valid or when @tld is null, %TLD_INVALID if a
* character is not allowed, or additional error codes on general
* failure conditions.
*/
int
tld_check_4 (const uint32_t *in, size_t inlen, size_t *errpos,
const Tld_table **overrides)
{
const Tld_table *tld;
char *domain;
int rc;
if (errpos)
*errpos = 0;
/* Get TLD name. */
rc = tld_get_4 (in, inlen, &domain);
if (rc != TLD_SUCCESS)
{
if (rc == TLD_NO_TLD) /* No TLD, say OK */
return TLD_SUCCESS;
else
return rc;
}
/* Retrieve appropriate data structure. */
tld = tld_default_table (domain, overrides);
free (domain);
return tld_check_4t (in, inlen, errpos, tld);
}
/**
* tld_check_4z:
* @in: Zero-terminated array of unicode code points to process.
* @errpos: Position of offending character is returned here.
* @overrides: A #Tld_table array of additional domain restriction
* structures that complement and supersede the built-in information.
*
* Test each of the code points in @in for whether or not they are
* allowed by the information in @overrides or by the built-in TLD
* restriction data. When data for the same TLD is available both
* internally and in @overrides, the information in @overrides takes
* precedence. If several entries for a specific TLD are found, the
* first one is used. If @overrides is %NULL, only the built-in
* information is used. The position of the first offending character
* is returned in @errpos.
*
* Return value: Returns the #Tld_rc value %TLD_SUCCESS if all code
* points are valid or when @tld is null, %TLD_INVALID if a
* character is not allowed, or additional error codes on general
* failure conditions.
*/
int
tld_check_4z (const uint32_t *in, size_t *errpos, const Tld_table **overrides)
{
const uint32_t *ipos = in;
if (!ipos)
return TLD_NODATA;
while (*ipos)
ipos++;
return tld_check_4 (in, ipos - in, errpos, overrides);
}
/**
* tld_check_8z:
* @in: Zero-terminated UTF8 string to process.
* @errpos: Position of offending character is returned here.
* @overrides: A #Tld_table array of additional domain restriction
* structures that complement and supersede the built-in information.
*
* Test each of the characters in @in for whether or not they are
* allowed by the information in @overrides or by the built-in TLD
* restriction data. When data for the same TLD is available both
* internally and in @overrides, the information in @overrides takes
* precedence. If several entries for a specific TLD are found, the
* first one is used. If @overrides is %NULL, only the built-in
* information is used. The position of the first offending character
* is returned in @errpos. Note that the error position refers to the
* decoded character offset rather than the byte position in the
* string.
*
* Return value: Returns the #Tld_rc value %TLD_SUCCESS if all
* characters are valid or when @tld is null, %TLD_INVALID if a
* character is not allowed, or additional error codes on general
* failure conditions.
*/
int
tld_check_8z (const char *in, size_t *errpos, const Tld_table **overrides)
{
uint32_t *iucs;
size_t ilen;
int rc;
if (!in)
return TLD_NODATA;
iucs = stringprep_utf8_to_ucs4 (in, -1, &ilen);
if (!iucs)
return TLD_MALLOC_ERROR;
rc = tld_check_4 (iucs, ilen, errpos, overrides);
free (iucs);
return rc;
}
/**
* tld_check_lz:
* @in: Zero-terminated string in the current locales encoding to process.
* @errpos: Position of offending character is returned here.
* @overrides: A #Tld_table array of additional domain restriction
* structures that complement and supersede the built-in information.
*
* Test each of the characters in @in for whether or not they are
* allowed by the information in @overrides or by the built-in TLD
* restriction data. When data for the same TLD is available both
* internally and in @overrides, the information in @overrides takes
* precedence. If several entries for a specific TLD are found, the
* first one is used. If @overrides is %NULL, only the built-in
* information is used. The position of the first offending character
* is returned in @errpos. Note that the error position refers to the
* decoded character offset rather than the byte position in the
* string.
*
* Return value: Returns the #Tld_rc value %TLD_SUCCESS if all
* characters are valid or when @tld is null, %TLD_INVALID if a
* character is not allowed, or additional error codes on general
* failure conditions.
*/
int
tld_check_lz (const char *in, size_t *errpos, const Tld_table **overrides)
{
char *utf8;
int rc;
if (!in)
return TLD_NODATA;
utf8 = stringprep_locale_to_utf8 (in);
if (!utf8)
return TLD_ICONV_ERROR;
rc = tld_check_8z (utf8, errpos, overrides);
free (utf8);
return rc;
}
/**
* Tld_rc:
* @TLD_SUCCESS: Successful operation. This value is guaranteed to
* always be zero, the remaining ones are only guaranteed to hold
* non-zero values, for logical comparison purposes.
* @TLD_INVALID: Invalid character found.
* @TLD_NODATA: No input data was provided.
* @TLD_MALLOC_ERROR: Error during memory allocation.
* @TLD_ICONV_ERROR: Character encoding conversion error.
* @TLD_NO_TLD: No top-level domain found in domain string.
* @TLD_NOTLD: Same as @TLD_NO_TLD, for compatibility
* with typo in earlier versions.
*
* Enumerated return codes of the TLD checking functions.
* The value 0 is guaranteed to always correspond to success.
*/
|