1 /* 2 *************************************************************************** 3 * Copyright (C) 2008-2013, International Business Machines Corporation 4 * and others. All Rights Reserved. 5 *************************************************************************** 6 * file name: uspoof.h 7 * encoding: US-ASCII 8 * tab size: 8 (not used) 9 * indentation:4 10 * 11 * created on: 2008Feb13 12 * created by: Andy Heninger 13 * 14 * Unicode Spoof Detection 15 */ 16 17 #ifndef USPOOF_H 18 #define USPOOF_H 19 20 #include "unicode/utypes.h" 21 #include "unicode/uset.h" 22 #include "unicode/parseerr.h" 23 #include "unicode/localpointer.h" 24 25 #if !UCONFIG_NO_NORMALIZATION 26 27 28 #if U_SHOW_CPLUSPLUS_API 29 #include "unicode/unistr.h" 30 #include "unicode/uniset.h" 31 #endif 32 33 34 /** 35 * \file 36 * \brief Unicode Security and Spoofing Detection, C API. 37 * 38 * These functions are intended to check strings, typically 39 * identifiers of some type, such as URLs, for the presence of 40 * characters that are likely to be visually confusing - 41 * for cases where the displayed form of an identifier may 42 * not be what it appears to be. 43 * 44 * Unicode Technical Report #36, http://unicode.org/reports/tr36, and 45 * Unicode Technical Standard #39, http://unicode.org/reports/tr39 46 * "Unicode security considerations", give more background on 47 * security an spoofing issues with Unicode identifiers. 48 * The tests and checks provided by this module implement the recommendations 49 * from those Unicode documents. 50 * 51 * The tests available on identifiers fall into two general categories: 52 * -# Single identifier tests. Check whether an identifier is 53 * potentially confusable with any other string, or is suspicious 54 * for other reasons. 55 * -# Two identifier tests. Check whether two specific identifiers are confusable. 56 * This does not consider whether either of strings is potentially 57 * confusable with any string other than the exact one specified. 58 * 59 * The steps to perform confusability testing are 60 * -# Open a USpoofChecker. 61 * -# Configure the USPoofChecker for the desired set of tests. The tests that will 62 * be performed are specified by a set of USpoofChecks flags. 63 * -# Perform the checks using the pre-configured USpoofChecker. The results indicate 64 * which (if any) of the selected tests have identified possible problems with the identifier. 65 * Results are reported as a set of USpoofChecks flags; this mirrors the form in which 66 * the set of tests to perform was originally specified to the USpoofChecker. 67 * 68 * A USpoofChecker may be used repeatedly to perform checks on any number of identifiers. 69 * 70 * Thread Safety: The test functions for checking a single identifier, or for testing 71 * whether two identifiers are possible confusable, are thread safe. 72 * They may called concurrently, from multiple threads, using the same USpoofChecker instance. 73 * 74 * More generally, the standard ICU thread safety rules apply: functions that take a 75 * const USpoofChecker parameter are thread safe. Those that take a non-const 76 * USpoofChecier are not thread safe. 77 * 78 * 79 * Descriptions of the available checks. 80 * 81 * When testing whether pairs of identifiers are confusable, with the uspoof_areConfusable() 82 * family of functions, the relevant tests are 83 * 84 * -# USPOOF_SINGLE_SCRIPT_CONFUSABLE: All of the characters from the two identifiers are 85 * from a single script, and the two identifiers are visually confusable. 86 * -# USPOOF_MIXED_SCRIPT_CONFUSABLE: At least one of the identifiers contains characters 87 * from more than one script, and the two identifiers are visually confusable. 88 * -# USPOOF_WHOLE_SCRIPT_CONFUSABLE: Each of the two identifiers is of a single script, but 89 * the two identifiers are from different scripts, and they are visually confusable. 90 * 91 * The safest approach is to enable all three of these checks as a group. 92 * 93 * USPOOF_ANY_CASE is a modifier for the above tests. If the identifiers being checked can 94 * be of mixed case and are used in a case-sensitive manner, this option should be specified. 95 * 96 * If the identifiers being checked are used in a case-insensitive manner, and if they are 97 * displayed to users in lower-case form only, the USPOOF_ANY_CASE option should not be 98 * specified. Confusabality issues involving upper case letters will not be reported. 99 * 100 * When performing tests on a single identifier, with the uspoof_check() family of functions, 101 * the relevant tests are: 102 * 103 * -# USPOOF_MIXED_SCRIPT_CONFUSABLE: the identifier contains characters from multiple 104 * scripts, and there exists an identifier of a single script that is visually confusable. 105 * -# USPOOF_WHOLE_SCRIPT_CONFUSABLE: the identifier consists of characters from a single 106 * script, and there exists a visually confusable identifier. 107 * The visually confusable identifier also consists of characters from a single script. 108 * but not the same script as the identifier being checked. 109 * -# USPOOF_ANY_CASE: modifies the mixed script and whole script confusables tests. If 110 * specified, the checks will consider confusable characters of any case. If this flag is not 111 * set, the test is performed assuming case folded identifiers. 112 * -# USPOOF_SINGLE_SCRIPT: check that the identifier contains only characters from a 113 * single script. (Characters from the 'common' and 'inherited' scripts are ignored.) 114 * This is not a test for confusable identifiers 115 * -# USPOOF_INVISIBLE: check an identifier for the presence of invisible characters, 116 * such as zero-width spaces, or character sequences that are 117 * likely not to display, such as multiple occurrences of the same 118 * non-spacing mark. This check does not test the input string as a whole 119 * for conformance to any particular syntax for identifiers. 120 * -# USPOOF_CHAR_LIMIT: check that an identifier contains only characters from a specified set 121 * of acceptable characters. See uspoof_setAllowedChars() and 122 * uspoof_setAllowedLocales(). 123 * 124 * Note on Scripts: 125 * Characters from the Unicode Scripts "Common" and "Inherited" are ignored when considering 126 * the script of an identifier. Common characters include digits and symbols that 127 * are normally used with text from more than one script. 128 * 129 * Identifier Skeletons: A skeleton is a transformation of an identifier, such that 130 * all identifiers that are confusable with each other have the same skeleton. 131 * Using skeletons, it is possible to build a dictionary data structure for 132 * a set of identifiers, and then quickly test whether a new identifier is 133 * confusable with an identifier already in the set. The uspoof_getSkeleton() 134 * family of functions will produce the skeleton from an identifier. 135 * 136 * Note that skeletons are not guaranteed to be stable between versions 137 * of Unicode or ICU, so an applications should not rely on creating a permanent, 138 * or difficult to update, database of skeletons. Instabilities result from 139 * identifying new pairs or sequences of characters that are visually 140 * confusable, and thus must be mapped to the same skeleton character(s). 141 * 142 */ 143 144 struct USpoofChecker; 145 typedef struct USpoofChecker USpoofChecker; /**< typedef for C of USpoofChecker */ 146 147 /** 148 * Enum for the kinds of checks that USpoofChecker can perform. 149 * These enum values are used both to select the set of checks that 150 * will be performed, and to report results from the check function. 151 * 152 * @stable ICU 4.2 153 */ 154 typedef enum USpoofChecks { 155 /** Single script confusable test. 156 * When testing whether two identifiers are confusable, report that they are if 157 * both are from the same script and they are visually confusable. 158 * Note: this test is not applicable to a check of a single identifier. 159 */ 160 USPOOF_SINGLE_SCRIPT_CONFUSABLE = 1, 161 162 /** Mixed script confusable test. 163 * When checking a single identifier, report a problem if 164 * the identifier contains multiple scripts, and 165 * is confusable with some other identifier in a single script 166 * When testing whether two identifiers are confusable, report that they are if 167 * the two IDs are visually confusable, 168 * and at least one contains characters from more than one script. 169 */ 170 USPOOF_MIXED_SCRIPT_CONFUSABLE = 2, 171 172 /** Whole script confusable test. 173 * When checking a single identifier, report a problem if 174 * The identifier is of a single script, and 175 * there exists a confusable identifier in another script. 176 * When testing whether two identifiers are confusable, report that they are if 177 * each is of a single script, 178 * the scripts of the two identifiers are different, and 179 * the identifiers are visually confusable. 180 */ 181 USPOOF_WHOLE_SCRIPT_CONFUSABLE = 4, 182 183 /** Any Case Modifier for confusable identifier tests. 184 If specified, consider all characters, of any case, when looking for confusables. 185 If USPOOF_ANY_CASE is not specified, identifiers being checked are assumed to have been 186 case folded. Upper case confusable characters will not be checked. 187 Selects between Lower Case Confusable and 188 Any Case Confusable. */ 189 USPOOF_ANY_CASE = 8, 190 191 /** 192 * Check that an identifier is no looser than the specified RestrictionLevel. 193 * The default if uspoof_setRestrctionLevel() is not called is HIGHLY_RESTRICTIVE. 194 * 195 * If USPOOF_AUX_INFO is enabled the actual restriction level of the 196 * identifier being tested will also be returned by uspoof_check(). 197 * 198 * @see URestrictionLevel 199 * @see uspoof_setRestrictionLevel 200 * @see USPOOF_AUX_INFO 201 * 202 * @stable ICU 51 203 */ 204 USPOOF_RESTRICTION_LEVEL = 16, 205 206 #ifndef U_HIDE_DEPRECATED_API 207 /** Check that an identifier contains only characters from a 208 * single script (plus chars from the common and inherited scripts.) 209 * Applies to checks of a single identifier check only. 210 * @deprecated ICU 51 Use RESTRICTION_LEVEL instead. 211 */ 212 USPOOF_SINGLE_SCRIPT = USPOOF_RESTRICTION_LEVEL, 213 #endif /* U_HIDE_DEPRECATED_API */ 214 215 /** Check an identifier for the presence of invisible characters, 216 * such as zero-width spaces, or character sequences that are 217 * likely not to display, such as multiple occurrences of the same 218 * non-spacing mark. This check does not test the input string as a whole 219 * for conformance to any particular syntax for identifiers. 220 */ 221 USPOOF_INVISIBLE = 32, 222 223 /** Check that an identifier contains only characters from a specified set 224 * of acceptable characters. See uspoof_setAllowedChars() and 225 * uspoof_setAllowedLocales(). 226 */ 227 USPOOF_CHAR_LIMIT = 64, 228 229 #ifndef U_HIDE_DRAFT_API 230 /** 231 * Check that an identifier does not include decimal digits from 232 * more than one numbering system. 233 * 234 * @draft ICU 51 235 */ 236 USPOOF_MIXED_NUMBERS = 128, 237 #endif /* U_HIDE_DRAFT_API */ 238 239 /** 240 * Enable all spoof checks. 241 * 242 * @stable ICU 4.6 243 */ 244 USPOOF_ALL_CHECKS = 0xFFFF, 245 246 #ifndef U_HIDE_DRAFT_API 247 /** 248 * Enable the return of auxillary (non-error) information in the 249 * upper bits of the check results value. 250 * 251 * If this "check" is not enabled, the results of uspoof_check() will be zero when an 252 * identifier passes all of the enabled checks. 253 * 254 * If this "check" is enabled, (uspoof_check() & USPOOF_ALL_CHECKS) will be zero 255 * when an identifier passes all checks. 256 * 257 * @draft ICU 51 258 */ 259 USPOOF_AUX_INFO = 0x40000000 260 #endif /* U_HIDE_DRAFT_API */ 261 262 } USpoofChecks; 263 264 265 #ifndef U_HIDE_DRAFT_API 266 /** 267 * Constants from UAX #39 for use in setRestrictionLevel(), and 268 * for returned identifier restriction levels in check results. 269 * @draft ICU 51 270 */ 271 typedef enum URestrictionLevel { 272 /** 273 * Only ASCII characters: U+0000..U+007F 274 * 275 * @draft ICU 51 276 */ 277 USPOOF_ASCII = 0x10000000, 278 /** 279 * All characters in each identifier must be from a single script, or from the combinations: Latin + Han + 280 * Hiragana + Katakana; Latin + Han + Bopomofo; or Latin + Han + Hangul. Note that this level will satisfy the 281 * vast majority of Latin-script users; also that TR36 has ASCII instead of Latin. 282 * 283 * @draft ICU 51 284 */ 285 USPOOF_HIGHLY_RESTRICTIVE = 0x20000000, 286 /** 287 * Allow Latin with other scripts except Cyrillic, Greek, Cherokee Otherwise, the same as Highly Restrictive 288 * 289 * @draft ICU 51 290 */ 291 USPOOF_MODERATELY_RESTRICTIVE = 0x30000000, 292 /** 293 * Allow arbitrary mixtures of scripts. Otherwise, the same as Moderately Restrictive. 294 * 295 * @draft ICU 51 296 */ 297 USPOOF_MINIMALLY_RESTRICTIVE = 0x40000000, 298 /** 299 * Any valid identifiers, including characters outside of the Identifier Profile. 300 * 301 * @draft ICU 51 302 */ 303 USPOOF_UNRESTRICTIVE = 0x50000000 304 } URestrictionLevel; 305 #endif /* U_HIDE_DRAFT_API */ 306 307 /** 308 * Create a Unicode Spoof Checker, configured to perform all 309 * checks except for USPOOF_LOCALE_LIMIT and USPOOF_CHAR_LIMIT. 310 * Note that additional checks may be added in the future, 311 * resulting in the changes to the default checking behavior. 312 * 313 * @param status The error code, set if this function encounters a problem. 314 * @return the newly created Spoof Checker 315 * @stable ICU 4.2 316 */ 317 U_STABLE USpoofChecker * U_EXPORT2 318 uspoof_open(UErrorCode *status); 319 320 321 /** 322 * Open a Spoof checker from its serialized from, stored in 32-bit-aligned memory. 323 * Inverse of uspoof_serialize(). 324 * The memory containing the serialized data must remain valid and unchanged 325 * as long as the spoof checker, or any cloned copies of the spoof checker, 326 * are in use. Ownership of the memory remains with the caller. 327 * The spoof checker (and any clones) must be closed prior to deleting the 328 * serialized data. 329 * 330 * @param data a pointer to 32-bit-aligned memory containing the serialized form of spoof data 331 * @param length the number of bytes available at data; 332 * can be more than necessary 333 * @param pActualLength receives the actual number of bytes at data taken up by the data; 334 * can be NULL 335 * @param pErrorCode ICU error code 336 * @return the spoof checker. 337 * 338 * @see uspoof_open 339 * @see uspoof_serialize 340 * @stable ICU 4.2 341 */ 342 U_STABLE USpoofChecker * U_EXPORT2 343 uspoof_openFromSerialized(const void *data, int32_t length, int32_t *pActualLength, 344 UErrorCode *pErrorCode); 345 346 /** 347 * Open a Spoof Checker from the source form of the spoof data. 348 * The Three inputs correspond to the Unicode data files confusables.txt 349 * confusablesWholeScript.txt and xidmdifications.txt as described in 350 * Unicode UAX #39. The syntax of the source data is as described in UAX #39 for 351 * these files, and the content of these files is acceptable input. 352 * 353 * The character encoding of the (char *) input text is UTF-8. 354 * 355 * @param confusables a pointer to the confusable characters definitions, 356 * as found in file confusables.txt from unicode.org. 357 * @param confusablesLen The length of the confusables text, or -1 if the 358 * input string is zero terminated. 359 * @param confusablesWholeScript 360 * a pointer to the whole script confusables definitions, 361 * as found in the file confusablesWholeScript.txt from unicode.org. 362 * @param confusablesWholeScriptLen The length of the whole script confusables text, or 363 * -1 if the input string is zero terminated. 364 * @param errType In the event of an error in the input, indicates 365 * which of the input files contains the error. 366 * The value is one of USPOOF_SINGLE_SCRIPT_CONFUSABLE or 367 * USPOOF_WHOLE_SCRIPT_CONFUSABLE, or 368 * zero if no errors are found. 369 * @param pe In the event of an error in the input, receives the position 370 * in the input text (line, offset) of the error. 371 * @param status an in/out ICU UErrorCode. Among the possible errors is 372 * U_PARSE_ERROR, which is used to report syntax errors 373 * in the input. 374 * @return A spoof checker that uses the rules from the input files. 375 * @stable ICU 4.2 376 */ 377 U_STABLE USpoofChecker * U_EXPORT2 378 uspoof_openFromSource(const char *confusables, int32_t confusablesLen, 379 const char *confusablesWholeScript, int32_t confusablesWholeScriptLen, 380 int32_t *errType, UParseError *pe, UErrorCode *status); 381 382 383 /** 384 * Close a Spoof Checker, freeing any memory that was being held by 385 * its implementation. 386 * @stable ICU 4.2 387 */ 388 U_STABLE void U_EXPORT2 389 uspoof_close(USpoofChecker *sc); 390 391 #if U_SHOW_CPLUSPLUS_API 392 393 U_NAMESPACE_BEGIN 394 395 /** 396 * \class LocalUSpoofCheckerPointer 397 * "Smart pointer" class, closes a USpoofChecker via uspoof_close(). 398 * For most methods see the LocalPointerBase base class. 399 * 400 * @see LocalPointerBase 401 * @see LocalPointer 402 * @stable ICU 4.4 403 */ 404 U_DEFINE_LOCAL_OPEN_POINTER(LocalUSpoofCheckerPointer, USpoofChecker, uspoof_close); 405 406 U_NAMESPACE_END 407 408 #endif 409 410 /** 411 * Clone a Spoof Checker. The clone will be set to perform the same checks 412 * as the original source. 413 * 414 * @param sc The source USpoofChecker 415 * @param status The error code, set if this function encounters a problem. 416 * @return 417 * @stable ICU 4.2 418 */ 419 U_STABLE USpoofChecker * U_EXPORT2 420 uspoof_clone(const USpoofChecker *sc, UErrorCode *status); 421 422 423 /** 424 * Specify the set of checks that will be performed by the check 425 * functions of this Spoof Checker. 426 * 427 * @param sc The USpoofChecker 428 * @param checks The set of checks that this spoof checker will perform. 429 * The value is a bit set, obtained by OR-ing together 430 * values from enum USpoofChecks. 431 * @param status The error code, set if this function encounters a problem. 432 * @stable ICU 4.2 433 * 434 */ 435 U_STABLE void U_EXPORT2 436 uspoof_setChecks(USpoofChecker *sc, int32_t checks, UErrorCode *status); 437 438 /** 439 * Get the set of checks that this Spoof Checker has been configured to perform. 440 * 441 * @param sc The USpoofChecker 442 * @param status The error code, set if this function encounters a problem. 443 * @return The set of checks that this spoof checker will perform. 444 * The value is a bit set, obtained by OR-ing together 445 * values from enum USpoofChecks. 446 * @stable ICU 4.2 447 * 448 */ 449 U_STABLE int32_t U_EXPORT2 450 uspoof_getChecks(const USpoofChecker *sc, UErrorCode *status); 451 452 #ifndef U_HIDE_DRAFT_API 453 /** 454 * Set the loosest restriction level allowed. The default if this function 455 * is not called is HIGHLY_RESTRICTIVE. 456 * Calling this function also enables the RESTRICTION_LEVEL check. 457 * @param restrictionLevel The loosest restriction level allowed. 458 * @see URestrictionLevel 459 * @draft ICU 51 460 */ 461 U_DRAFT void U_EXPORT2 462 uspoof_setRestrictionLevel(USpoofChecker *sc, URestrictionLevel restrictionLevel); 463 464 465 /** 466 * Get the Restriction Level that will be tested if the checks include RESTRICTION_LEVEL. 467 * 468 * @return The restriction level 469 * @see URestrictionLevel 470 * @draft ICU 51 471 */ 472 U_DRAFT URestrictionLevel U_EXPORT2 473 uspoof_getRestrictionLevel(const USpoofChecker *sc); 474 #endif /* U_HIDE_DRAFT_API */ 475 476 /** 477 * Limit characters that are acceptable in identifiers being checked to those 478 * normally used with the languages associated with the specified locales. 479 * Any previously specified list of locales is replaced by the new settings. 480 * 481 * A set of languages is determined from the locale(s), and 482 * from those a set of acceptable Unicode scripts is determined. 483 * Characters from this set of scripts, along with characters from 484 * the "common" and "inherited" Unicode Script categories 485 * will be permitted. 486 * 487 * Supplying an empty string removes all restrictions; 488 * characters from any script will be allowed. 489 * 490 * The USPOOF_CHAR_LIMIT test is automatically enabled for this 491 * USpoofChecker when calling this function with a non-empty list 492 * of locales. 493 * 494 * The Unicode Set of characters that will be allowed is accessible 495 * via the uspoof_getAllowedChars() function. uspoof_setAllowedLocales() 496 * will <i>replace</i> any previously applied set of allowed characters. 497 * 498 * Adjustments, such as additions or deletions of certain classes of characters, 499 * can be made to the result of uspoof_setAllowedLocales() by 500 * fetching the resulting set with uspoof_getAllowedChars(), 501 * manipulating it with the Unicode Set API, then resetting the 502 * spoof detectors limits with uspoof_setAllowedChars() 503 * 504 * @param sc The USpoofChecker 505 * @param localesList A list list of locales, from which the language 506 * and associated script are extracted. The locales 507 * are comma-separated if there is more than one. 508 * White space may not appear within an individual locale, 509 * but is ignored otherwise. 510 * The locales are syntactically like those from the 511 * HTTP Accept-Language header. 512 * If the localesList is empty, no restrictions will be placed on 513 * the allowed characters. 514 * 515 * @param status The error code, set if this function encounters a problem. 516 * @stable ICU 4.2 517 */ 518 U_STABLE void U_EXPORT2 519 uspoof_setAllowedLocales(USpoofChecker *sc, const char *localesList, UErrorCode *status); 520 521 /** 522 * Get a list of locales for the scripts that are acceptable in strings 523 * to be checked. If no limitations on scripts have been specified, 524 * an empty string will be returned. 525 * 526 * uspoof_setAllowedChars() will reset the list of allowed to be empty. 527 * 528 * The format of the returned list is the same as that supplied to 529 * uspoof_setAllowedLocales(), but returned list may not be identical 530 * to the originally specified string; the string may be reformatted, 531 * and information other than languages from 532 * the originally specified locales may be omitted. 533 * 534 * @param sc The USpoofChecker 535 * @param status The error code, set if this function encounters a problem. 536 * @return A string containing a list of locales corresponding 537 * to the acceptable scripts, formatted like an 538 * HTTP Accept Language value. 539 * 540 * @stable ICU 4.2 541 */ 542 U_STABLE const char * U_EXPORT2 543 uspoof_getAllowedLocales(USpoofChecker *sc, UErrorCode *status); 544 545 546 /** 547 * Limit the acceptable characters to those specified by a Unicode Set. 548 * Any previously specified character limit is 549 * is replaced by the new settings. This includes limits on 550 * characters that were set with the uspoof_setAllowedLocales() function. 551 * 552 * The USPOOF_CHAR_LIMIT test is automatically enabled for this 553 * USpoofChecker by this function. 554 * 555 * @param sc The USpoofChecker 556 * @param chars A Unicode Set containing the list of 557 * characters that are permitted. Ownership of the set 558 * remains with the caller. The incoming set is cloned by 559 * this function, so there are no restrictions on modifying 560 * or deleting the USet after calling this function. 561 * @param status The error code, set if this function encounters a problem. 562 * @stable ICU 4.2 563 */ 564 U_STABLE void U_EXPORT2 565 uspoof_setAllowedChars(USpoofChecker *sc, const USet *chars, UErrorCode *status); 566 567 568 /** 569 * Get a USet for the characters permitted in an identifier. 570 * This corresponds to the limits imposed by the Set Allowed Characters 571 * functions. Limitations imposed by other checks will not be 572 * reflected in the set returned by this function. 573 * 574 * The returned set will be frozen, meaning that it cannot be modified 575 * by the caller. 576 * 577 * Ownership of the returned set remains with the Spoof Detector. The 578 * returned set will become invalid if the spoof detector is closed, 579 * or if a new set of allowed characters is specified. 580 * 581 * 582 * @param sc The USpoofChecker 583 * @param status The error code, set if this function encounters a problem. 584 * @return A USet containing the characters that are permitted by 585 * the USPOOF_CHAR_LIMIT test. 586 * @stable ICU 4.2 587 */ 588 U_STABLE const USet * U_EXPORT2 589 uspoof_getAllowedChars(const USpoofChecker *sc, UErrorCode *status); 590 591 592 #if U_SHOW_CPLUSPLUS_API 593 /** 594 * Limit the acceptable characters to those specified by a Unicode Set. 595 * Any previously specified character limit is 596 * is replaced by the new settings. This includes limits on 597 * characters that were set with the uspoof_setAllowedLocales() function. 598 * 599 * The USPOOF_CHAR_LIMIT test is automatically enabled for this 600 * USoofChecker by this function. 601 * 602 * @param sc The USpoofChecker 603 * @param chars A Unicode Set containing the list of 604 * characters that are permitted. Ownership of the set 605 * remains with the caller. The incoming set is cloned by 606 * this function, so there are no restrictions on modifying 607 * or deleting the UnicodeSet after calling this function. 608 * @param status The error code, set if this function encounters a problem. 609 * @stable ICU 4.2 610 */ 611 U_STABLE void U_EXPORT2 612 uspoof_setAllowedUnicodeSet(USpoofChecker *sc, const icu::UnicodeSet *chars, UErrorCode *status); 613 614 615 /** 616 * Get a UnicodeSet for the characters permitted in an identifier. 617 * This corresponds to the limits imposed by the Set Allowed Characters / 618 * UnicodeSet functions. Limitations imposed by other checks will not be 619 * reflected in the set returned by this function. 620 * 621 * The returned set will be frozen, meaning that it cannot be modified 622 * by the caller. 623 * 624 * Ownership of the returned set remains with the Spoof Detector. The 625 * returned set will become invalid if the spoof detector is closed, 626 * or if a new set of allowed characters is specified. 627 * 628 * 629 * @param sc The USpoofChecker 630 * @param status The error code, set if this function encounters a problem. 631 * @return A UnicodeSet containing the characters that are permitted by 632 * the USPOOF_CHAR_LIMIT test. 633 * @stable ICU 4.2 634 */ 635 U_STABLE const icu::UnicodeSet * U_EXPORT2 636 uspoof_getAllowedUnicodeSet(const USpoofChecker *sc, UErrorCode *status); 637 #endif 638 639 640 /** 641 * Check the specified string for possible security issues. 642 * The text to be checked will typically be an identifier of some sort. 643 * The set of checks to be performed is specified with uspoof_setChecks(). 644 * 645 * @param sc The USpoofChecker 646 * @param id The identifier to be checked for possible security issues, 647 * in UTF-16 format. 648 * @param length the length of the string to be checked, expressed in 649 * 16 bit UTF-16 code units, or -1 if the string is 650 * zero terminated. 651 * @param position An out parameter. 652 * Originally, the index of the first string position that failed a check. 653 * Now, always returns zero. 654 * This parameter may be null. 655 * @param status The error code, set if an error occurred while attempting to 656 * perform the check. 657 * Spoofing or security issues detected with the input string are 658 * not reported here, but through the function's return value. 659 * @return An integer value with bits set for any potential security 660 * or spoofing issues detected. The bits are defined by 661 * enum USpoofChecks. (returned_value & USPOOF_ALL_CHECKS) 662 * will be zero if the input string passes all of the 663 * enabled checks. 664 * @stable ICU 4.2 665 */ 666 U_STABLE int32_t U_EXPORT2 667 uspoof_check(const USpoofChecker *sc, 668 const UChar *id, int32_t length, 669 int32_t *position, 670 UErrorCode *status); 671 672 673 /** 674 * Check the specified string for possible security issues. 675 * The text to be checked will typically be an identifier of some sort. 676 * The set of checks to be performed is specified with uspoof_setChecks(). 677 * 678 * @param sc The USpoofChecker 679 * @param id A identifier to be checked for possible security issues, in UTF8 format. 680 * @param length the length of the string to be checked, or -1 if the string is 681 * zero terminated. 682 * @param position An out parameter. 683 * Originally, the index of the first string position that failed a check. 684 * Now, always returns zero. 685 * This parameter may be null. 686 * @deprecated ICU 51 687 * @param status The error code, set if an error occurred while attempting to 688 * perform the check. 689 * Spoofing or security issues detected with the input string are 690 * not reported here, but through the function's return value. 691 * If the input contains invalid UTF-8 sequences, 692 * a status of U_INVALID_CHAR_FOUND will be returned. 693 * @return An integer value with bits set for any potential security 694 * or spoofing issues detected. The bits are defined by 695 * enum USpoofChecks. (returned_value & USPOOF_ALL_CHECKS) 696 * will be zero if the input string passes all of the 697 * enabled checks. 698 * @stable ICU 4.2 699 */ 700 U_STABLE int32_t U_EXPORT2 701 uspoof_checkUTF8(const USpoofChecker *sc, 702 const char *id, int32_t length, 703 int32_t *position, 704 UErrorCode *status); 705 706 707 #if U_SHOW_CPLUSPLUS_API 708 /** 709 * Check the specified string for possible security issues. 710 * The text to be checked will typically be an identifier of some sort. 711 * The set of checks to be performed is specified with uspoof_setChecks(). 712 * 713 * @param sc The USpoofChecker 714 * @param id A identifier to be checked for possible security issues. 715 * @param position An out parameter. 716 * Originally, the index of the first string position that failed a check. 717 * Now, always returns zero. 718 * This parameter may be null. 719 * @deprecated ICU 51 720 * @param status The error code, set if an error occurred while attempting to 721 * perform the check. 722 * Spoofing or security issues detected with the input string are 723 * not reported here, but through the function's return value. 724 * @return An integer value with bits set for any potential security 725 * or spoofing issues detected. The bits are defined by 726 * enum USpoofChecks. (returned_value & USPOOF_ALL_CHECKS) 727 * will be zero if the input string passes all of the 728 * enabled checks. 729 * @stable ICU 4.2 730 */ 731 U_STABLE int32_t U_EXPORT2 732 uspoof_checkUnicodeString(const USpoofChecker *sc, 733 const icu::UnicodeString &id, 734 int32_t *position, 735 UErrorCode *status); 736 737 #endif 738 739 740 /** 741 * Check the whether two specified strings are visually confusable. 742 * The types of confusability to be tested - single script, mixed script, 743 * or whole script - are determined by the check options set for the 744 * USpoofChecker. 745 * 746 * The tests to be performed are controlled by the flags 747 * USPOOF_SINGLE_SCRIPT_CONFUSABLE 748 * USPOOF_MIXED_SCRIPT_CONFUSABLE 749 * USPOOF_WHOLE_SCRIPT_CONFUSABLE 750 * At least one of these tests must be selected. 751 * 752 * USPOOF_ANY_CASE is a modifier for the tests. Select it if the identifiers 753 * may be of mixed case. 754 * If identifiers are case folded for comparison and 755 * display to the user, do not select the USPOOF_ANY_CASE option. 756 * 757 * 758 * @param sc The USpoofChecker 759 * @param id1 The first of the two identifiers to be compared for 760 * confusability. The strings are in UTF-16 format. 761 * @param length1 the length of the first identifer, expressed in 762 * 16 bit UTF-16 code units, or -1 if the string is 763 * nul terminated. 764 * @param id2 The second of the two identifiers to be compared for 765 * confusability. The identifiers are in UTF-16 format. 766 * @param length2 The length of the second identifiers, expressed in 767 * 16 bit UTF-16 code units, or -1 if the string is 768 * nul terminated. 769 * @param status The error code, set if an error occurred while attempting to 770 * perform the check. 771 * Confusability of the identifiers is not reported here, 772 * but through this function's return value. 773 * @return An integer value with bit(s) set corresponding to 774 * the type of confusability found, as defined by 775 * enum USpoofChecks. Zero is returned if the identifiers 776 * are not confusable. 777 * @stable ICU 4.2 778 */ 779 U_STABLE int32_t U_EXPORT2 780 uspoof_areConfusable(const USpoofChecker *sc, 781 const UChar *id1, int32_t length1, 782 const UChar *id2, int32_t length2, 783 UErrorCode *status); 784 785 786 787 /** 788 * Check the whether two specified strings are visually confusable. 789 * The types of confusability to be tested - single script, mixed script, 790 * or whole script - are determined by the check options set for the 791 * USpoofChecker. 792 * 793 * @param sc The USpoofChecker 794 * @param id1 The first of the two identifiers to be compared for 795 * confusability. The strings are in UTF-8 format. 796 * @param length1 the length of the first identifiers, in bytes, or -1 797 * if the string is nul terminated. 798 * @param id2 The second of the two identifiers to be compared for 799 * confusability. The strings are in UTF-8 format. 800 * @param length2 The length of the second string in bytes, or -1 801 * if the string is nul terminated. 802 * @param status The error code, set if an error occurred while attempting to 803 * perform the check. 804 * Confusability of the strings is not reported here, 805 * but through this function's return value. 806 * @return An integer value with bit(s) set corresponding to 807 * the type of confusability found, as defined by 808 * enum USpoofChecks. Zero is returned if the strings 809 * are not confusable. 810 * @stable ICU 4.2 811 */ 812 U_STABLE int32_t U_EXPORT2 813 uspoof_areConfusableUTF8(const USpoofChecker *sc, 814 const char *id1, int32_t length1, 815 const char *id2, int32_t length2, 816 UErrorCode *status); 817 818 819 820 821 #if U_SHOW_CPLUSPLUS_API 822 /** 823 * Check the whether two specified strings are visually confusable. 824 * The types of confusability to be tested - single script, mixed script, 825 * or whole script - are determined by the check options set for the 826 * USpoofChecker. 827 * 828 * @param sc The USpoofChecker 829 * @param s1 The first of the two identifiers to be compared for 830 * confusability. The strings are in UTF-8 format. 831 * @param s2 The second of the two identifiers to be compared for 832 * confusability. The strings are in UTF-8 format. 833 * @param status The error code, set if an error occurred while attempting to 834 * perform the check. 835 * Confusability of the identifiers is not reported here, 836 * but through this function's return value. 837 * @return An integer value with bit(s) set corresponding to 838 * the type of confusability found, as defined by 839 * enum USpoofChecks. Zero is returned if the identifiers 840 * are not confusable. 841 * @stable ICU 4.2 842 */ 843 U_STABLE int32_t U_EXPORT2 844 uspoof_areConfusableUnicodeString(const USpoofChecker *sc, 845 const icu::UnicodeString &s1, 846 const icu::UnicodeString &s2, 847 UErrorCode *status); 848 #endif 849 850 851 /** 852 * Get the "skeleton" for an identifier. 853 * Skeletons are a transformation of the input identifier; 854 * Two identifiers are confusable if their skeletons are identical. 855 * See Unicode UAX #39 for additional information. 856 * 857 * Using skeletons directly makes it possible to quickly check 858 * whether an identifier is confusable with any of some large 859 * set of existing identifiers, by creating an efficiently 860 * searchable collection of the skeletons. 861 * 862 * @param sc The USpoofChecker 863 * @param type The type of skeleton, corresponding to which 864 * of the Unicode confusable data tables to use. 865 * The default is Mixed-Script, Lowercase. 866 * Allowed options are USPOOF_SINGLE_SCRIPT_CONFUSABLE and 867 * USPOOF_ANY_CASE_CONFUSABLE. The two flags may be ORed. 868 * @param id The input identifier whose skeleton will be computed. 869 * @param length The length of the input identifier, expressed in 16 bit 870 * UTF-16 code units, or -1 if the string is zero terminated. 871 * @param dest The output buffer, to receive the skeleton string. 872 * @param destCapacity The length of the output buffer, in 16 bit units. 873 * The destCapacity may be zero, in which case the function will 874 * return the actual length of the skeleton. 875 * @param status The error code, set if an error occurred while attempting to 876 * perform the check. 877 * @return The length of the skeleton string. The returned length 878 * is always that of the complete skeleton, even when the 879 * supplied buffer is too small (or of zero length) 880 * 881 * @stable ICU 4.2 882 */ 883 U_STABLE int32_t U_EXPORT2 884 uspoof_getSkeleton(const USpoofChecker *sc, 885 uint32_t type, 886 const UChar *id, int32_t length, 887 UChar *dest, int32_t destCapacity, 888 UErrorCode *status); 889 890 /** 891 * Get the "skeleton" for an identifier. 892 * Skeletons are a transformation of the input identifier; 893 * Two identifiers are confusable if their skeletons are identical. 894 * See Unicode UAX #39 for additional information. 895 * 896 * Using skeletons directly makes it possible to quickly check 897 * whether an identifier is confusable with any of some large 898 * set of existing identifiers, by creating an efficiently 899 * searchable collection of the skeletons. 900 * 901 * @param sc The USpoofChecker 902 * @param type The type of skeleton, corresponding to which 903 * of the Unicode confusable data tables to use. 904 * The default is Mixed-Script, Lowercase. 905 * Allowed options are USPOOF_SINGLE_SCRIPT_CONFUSABLE and 906 * USPOOF_ANY_CASE. The two flags may be ORed. 907 * @param id The UTF-8 format identifier whose skeleton will be computed. 908 * @param length The length of the input string, in bytes, 909 * or -1 if the string is zero terminated. 910 * @param dest The output buffer, to receive the skeleton string. 911 * @param destCapacity The length of the output buffer, in bytes. 912 * The destCapacity may be zero, in which case the function will 913 * return the actual length of the skeleton. 914 * @param status The error code, set if an error occurred while attempting to 915 * perform the check. Possible Errors include U_INVALID_CHAR_FOUND 916 * for invalid UTF-8 sequences, and 917 * U_BUFFER_OVERFLOW_ERROR if the destination buffer is too small 918 * to hold the complete skeleton. 919 * @return The length of the skeleton string, in bytes. The returned length 920 * is always that of the complete skeleton, even when the 921 * supplied buffer is too small (or of zero length) 922 * 923 * @stable ICU 4.2 924 */ 925 U_STABLE int32_t U_EXPORT2 926 uspoof_getSkeletonUTF8(const USpoofChecker *sc, 927 uint32_t type, 928 const char *id, int32_t length, 929 char *dest, int32_t destCapacity, 930 UErrorCode *status); 931 932 #if U_SHOW_CPLUSPLUS_API 933 /** 934 * Get the "skeleton" for an identifier. 935 * Skeletons are a transformation of the input identifier; 936 * Two identifiers are confusable if their skeletons are identical. 937 * See Unicode UAX #39 for additional information. 938 * 939 * Using skeletons directly makes it possible to quickly check 940 * whether an identifier is confusable with any of some large 941 * set of existing identifiers, by creating an efficiently 942 * searchable collection of the skeletons. 943 * 944 * @param sc The USpoofChecker. 945 * @param type The type of skeleton, corresponding to which 946 * of the Unicode confusable data tables to use. 947 * The default is Mixed-Script, Lowercase. 948 * Allowed options are USPOOF_SINGLE_SCRIPT_CONFUSABLE and 949 * USPOOF_ANY_CASE_CONFUSABLE. The two flags may be ORed. 950 * @param id The input identifier whose skeleton will be computed. 951 * @param dest The output identifier, to receive the skeleton string. 952 * @param status The error code, set if an error occurred while attempting to 953 * perform the check. 954 * @return A reference to the destination (skeleton) string. 955 * 956 * @stable ICU 4.2 957 */ 958 U_I18N_API icu::UnicodeString & U_EXPORT2 959 uspoof_getSkeletonUnicodeString(const USpoofChecker *sc, 960 uint32_t type, 961 const icu::UnicodeString &id, 962 icu::UnicodeString &dest, 963 UErrorCode *status); 964 #endif /* U_SHOW_CPLUSPLUS_API */ 965 966 967 #ifndef U_HIDE_DRAFT_API 968 /** 969 * Get the set of Candidate Characters for Inclusion in Identifiers, as defined 970 * in Unicode UAX #31, http://www.unicode.org/reports/tr31/#Table_Candidate_Characters_for_Inclusion_in_Identifiers 971 * 972 * The returned set is frozen. Ownership of the set remains with the ICU library; it must not 973 * be deleted by the caller. 974 * 975 * @param status The error code, set if a problem occurs while creating the set. 976 * 977 * @draft ICU 51 978 */ 979 U_DRAFT const USet * U_EXPORT2 980 uspoof_getInclusionSet(UErrorCode *status); 981 982 /** 983 * Get the set of characters from Recommended Scripts for Inclusion in Identifiers, as defined 984 * in Unicode UAX #31, http://www.unicode.org/reports/tr31/#Table_Recommended_Scripts 985 * 986 * The returned set is frozen. Ownership of the set remains with the ICU library; it must not 987 * be deleted by the caller. 988 * 989 * @param status The error code, set if a problem occurs while creating the set. 990 * 991 * @draft ICU 51 992 */ 993 U_DRAFT const USet * U_EXPORT2 994 uspoof_getRecommendedSet(UErrorCode *status); 995 996 #if U_SHOW_CPLUSPLUS_API 997 998 /** 999 * Get the set of Candidate Characters for Inclusion in Identifiers, as defined 1000 * in Unicode UAX #31, http://www.unicode.org/reports/tr31/#Table_Candidate_Characters_for_Inclusion_in_Identifiers 1001 * 1002 * The returned set is frozen. Ownership of the set remains with the ICU library; it must not 1003 * be deleted by the caller. 1004 * 1005 * @param status The error code, set if a problem occurs while creating the set. 1006 * 1007 * @draft ICU 51 1008 */ 1009 U_DRAFT const icu::UnicodeSet * U_EXPORT2 1010 uspoof_getInclusionUnicodeSet(UErrorCode *status); 1011 1012 /** 1013 * Get the set of characters from Recommended Scripts for Inclusion in Identifiers, as defined 1014 * in Unicode UAX #31, http://www.unicode.org/reports/tr31/#Table_Recommended_Scripts 1015 * 1016 * The returned set is frozen. Ownership of the set remains with the ICU library; it must not 1017 * be deleted by the caller. 1018 * 1019 * @param status The error code, set if a problem occurs while creating the set. 1020 * 1021 * @draft ICU 51 1022 */ 1023 U_DRAFT const icu::UnicodeSet * U_EXPORT2 1024 uspoof_getRecommendedUnicodeSet(UErrorCode *status); 1025 1026 #endif /* U_SHOW_CPLUSPLUS_API */ 1027 #endif /* U_HIDE_DRAFT_API */ 1028 1029 /** 1030 * Serialize the data for a spoof detector into a chunk of memory. 1031 * The flattened spoof detection tables can later be used to efficiently 1032 * instantiate a new Spoof Detector. 1033 * 1034 * The serialized spoof checker includes only the data compiled from the 1035 * Unicode data tables by uspoof_openFromSource(); it does not include 1036 * include any other state or configuration that may have been set. 1037 * 1038 * @param sc the Spoof Detector whose data is to be serialized. 1039 * @param data a pointer to 32-bit-aligned memory to be filled with the data, 1040 * can be NULL if capacity==0 1041 * @param capacity the number of bytes available at data, 1042 * or 0 for preflighting 1043 * @param status an in/out ICU UErrorCode; possible errors include: 1044 * - U_BUFFER_OVERFLOW_ERROR if the data storage block is too small for serialization 1045 * - U_ILLEGAL_ARGUMENT_ERROR the data or capacity parameters are bad 1046 * @return the number of bytes written or needed for the spoof data 1047 * 1048 * @see utrie2_openFromSerialized() 1049 * @stable ICU 4.2 1050 */ 1051 U_STABLE int32_t U_EXPORT2 1052 uspoof_serialize(USpoofChecker *sc, 1053 void *data, int32_t capacity, 1054 UErrorCode *status); 1055 1056 1057 #endif 1058 1059 #endif /* USPOOF_H */ 1060