DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Mercurial (31ec81b5d7bb)

VCS Links

Line Code
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830
/*
***************************************************************************
* Copyright (C) 2008-2012, International Business Machines Corporation
* and others. All Rights Reserved.
***************************************************************************
*   file name:  uspoof.cpp
*   encoding:   US-ASCII
*   tab size:   8 (not used)
*   indentation:4
*
*   created on: 2008Feb13
*   created by: Andy Heninger
*
*   Unicode Spoof Detection
*/
#include "unicode/utypes.h"
#include "unicode/uspoof.h"
#include "unicode/unorm.h"
#include "unicode/ustring.h"
#include "unicode/utf16.h"
#include "cmemory.h"
#include "uspoof_impl.h"
#include "uassert.h"


#if !UCONFIG_NO_NORMALIZATION

U_NAMESPACE_USE


U_CAPI USpoofChecker * U_EXPORT2
uspoof_open(UErrorCode *status) {
    if (U_FAILURE(*status)) {
        return NULL;
    }
    SpoofImpl *si = new SpoofImpl(SpoofData::getDefault(*status), *status);
    if (U_FAILURE(*status)) {
        delete si;
        si = NULL;
    }
    return (USpoofChecker *)si;
}


U_CAPI USpoofChecker * U_EXPORT2
uspoof_openFromSerialized(const void *data, int32_t length, int32_t *pActualLength,
                          UErrorCode *status) {
    if (U_FAILURE(*status)) {
        return NULL;
    }
    SpoofData *sd = new SpoofData(data, length, *status);
    SpoofImpl *si = new SpoofImpl(sd, *status);
    if (U_FAILURE(*status)) {
        delete sd;
        delete si;
        return NULL;
    }
    if (sd == NULL || si == NULL) {
        *status = U_MEMORY_ALLOCATION_ERROR;
        delete sd;
        delete si;
        return NULL;
    }
        
    if (pActualLength != NULL) {
        *pActualLength = sd->fRawData->fLength;
    }
    return reinterpret_cast<USpoofChecker *>(si);
}


U_CAPI USpoofChecker * U_EXPORT2
uspoof_clone(const USpoofChecker *sc, UErrorCode *status) {
    const SpoofImpl *src = SpoofImpl::validateThis(sc, *status);
    if (src == NULL) {
        return NULL;
    }
    SpoofImpl *result = new SpoofImpl(*src, *status);   // copy constructor
    if (U_FAILURE(*status)) {
        delete result;
        result = NULL;
    }
    return (USpoofChecker *)result;
}


U_CAPI void U_EXPORT2
uspoof_close(USpoofChecker *sc) {
    UErrorCode status = U_ZERO_ERROR;
    SpoofImpl *This = SpoofImpl::validateThis(sc, status);
    delete This;
}


U_CAPI void U_EXPORT2
uspoof_setChecks(USpoofChecker *sc, int32_t checks, UErrorCode *status) {
    SpoofImpl *This = SpoofImpl::validateThis(sc, *status);
    if (This == NULL) {
        return;
    }

    // Verify that the requested checks are all ones (bits) that 
    //   are acceptable, known values.
    if (checks & ~USPOOF_ALL_CHECKS) {
        *status = U_ILLEGAL_ARGUMENT_ERROR; 
        return;
    }

    This->fChecks = checks;
}


U_CAPI int32_t U_EXPORT2
uspoof_getChecks(const USpoofChecker *sc, UErrorCode *status) {
    const SpoofImpl *This = SpoofImpl::validateThis(sc, *status);
    if (This == NULL) {
        return 0;
    }
    return This->fChecks;
}

U_CAPI void U_EXPORT2
uspoof_setAllowedLocales(USpoofChecker *sc, const char *localesList, UErrorCode *status) {
    SpoofImpl *This = SpoofImpl::validateThis(sc, *status);
    if (This == NULL) {
        return;
    }
    This->setAllowedLocales(localesList, *status);
}

U_CAPI const char * U_EXPORT2
uspoof_getAllowedLocales(USpoofChecker *sc, UErrorCode *status) {
    SpoofImpl *This = SpoofImpl::validateThis(sc, *status);
    if (This == NULL) {
        return NULL;
    }
    return This->getAllowedLocales(*status);
}


U_CAPI const USet * U_EXPORT2
uspoof_getAllowedChars(const USpoofChecker *sc, UErrorCode *status) {
    const UnicodeSet *result = uspoof_getAllowedUnicodeSet(sc, status);
    return reinterpret_cast<const USet *>(result);
}

U_CAPI const UnicodeSet * U_EXPORT2
uspoof_getAllowedUnicodeSet(const USpoofChecker *sc, UErrorCode *status) {
    const SpoofImpl *This = SpoofImpl::validateThis(sc, *status);
    if (This == NULL) {
        return NULL;
    }
    return This->fAllowedCharsSet;
}


U_CAPI void U_EXPORT2
uspoof_setAllowedChars(USpoofChecker *sc, const USet *chars, UErrorCode *status) {
    const UnicodeSet *set = reinterpret_cast<const UnicodeSet *>(chars);
    uspoof_setAllowedUnicodeSet(sc, set, status);
}


U_CAPI void U_EXPORT2
uspoof_setAllowedUnicodeSet(USpoofChecker *sc, const UnicodeSet *chars, UErrorCode *status) {
    SpoofImpl *This = SpoofImpl::validateThis(sc, *status);
    if (This == NULL) {
        return;
    }
    if (chars->isBogus()) {
        *status = U_ILLEGAL_ARGUMENT_ERROR;
        return;
    }
    UnicodeSet *clonedSet = static_cast<UnicodeSet *>(chars->clone());
    if (clonedSet == NULL || clonedSet->isBogus()) {
        *status = U_MEMORY_ALLOCATION_ERROR;
        return;
    }
    clonedSet->freeze();
    delete This->fAllowedCharsSet;
    This->fAllowedCharsSet = clonedSet;
    This->fChecks |= USPOOF_CHAR_LIMIT;
}


U_CAPI int32_t U_EXPORT2
uspoof_check(const USpoofChecker *sc,
             const UChar *text, int32_t length,
             int32_t *position,
             UErrorCode *status) {
             
    const SpoofImpl *This = SpoofImpl::validateThis(sc, *status);
    if (This == NULL) {
        return 0;
    }
    if (length < -1) {
        *status = U_ILLEGAL_ARGUMENT_ERROR;
        return 0;
    }
    if (length == -1) {
        // It's not worth the bother to handle nul terminated strings everywhere.
        //   Just get the length and be done with it.
        length = u_strlen(text);
    }

    int32_t result = 0;
    int32_t failPos = 0x7fffffff;   // TODO: do we have a #define for max int32?

    // A count of the number of non-Common or inherited scripts.
    // Needed for both the SINGLE_SCRIPT and the WHOLE/MIXED_SCIRPT_CONFUSABLE tests.
    // Share the computation when possible.  scriptCount == -1 means that we haven't
    // done it yet.
    int32_t scriptCount = -1;

    if ((This->fChecks) & USPOOF_SINGLE_SCRIPT) {
        scriptCount = This->scriptScan(text, length, failPos, *status);
        // printf("scriptCount (clipped to 2) = %d\n", scriptCount);
        if ( scriptCount >= 2) {
            // Note: scriptCount == 2 covers all cases of the number of scripts >= 2
            result |= USPOOF_SINGLE_SCRIPT;
        }
    }

    if (This->fChecks & USPOOF_CHAR_LIMIT) {
        int32_t i;
        UChar32 c;
        for (i=0; i<length ;) {
            U16_NEXT(text, i, length, c);
            if (!This->fAllowedCharsSet->contains(c)) {
                result |= USPOOF_CHAR_LIMIT;
                if (i < failPos) {
                    failPos = i;
                }
                break;
            }
        }
    }

    if (This->fChecks & 
        (USPOOF_WHOLE_SCRIPT_CONFUSABLE | USPOOF_MIXED_SCRIPT_CONFUSABLE | USPOOF_INVISIBLE)) {
        // These are the checks that need to be done on NFD input
        NFDBuffer   normalizedInput(text, length, *status);
        const UChar  *nfdText = normalizedInput.getBuffer();
        int32_t      nfdLength = normalizedInput.getLength();

        if (This->fChecks & USPOOF_INVISIBLE) {
           
            // scan for more than one occurence of the same non-spacing mark
            // in a sequence of non-spacing marks.
            int32_t     i;
            UChar32     c;
            UChar32     firstNonspacingMark = 0;
            UBool       haveMultipleMarks = FALSE;  
            UnicodeSet  marksSeenSoFar;   // Set of combining marks in a single combining sequence.
            
            for (i=0; i<nfdLength ;) {
                U16_NEXT(nfdText, i, nfdLength, c);
                if (u_charType(c) != U_NON_SPACING_MARK) {
                    firstNonspacingMark = 0;
                    if (haveMultipleMarks) {
                        marksSeenSoFar.clear();
                        haveMultipleMarks = FALSE;
                    }
                    continue;
                }
                if (firstNonspacingMark == 0) {
                    firstNonspacingMark = c;
                    continue;
                }
                if (!haveMultipleMarks) {
                    marksSeenSoFar.add(firstNonspacingMark);
                    haveMultipleMarks = TRUE;
                }
                if (marksSeenSoFar.contains(c)) {
                    // report the error, and stop scanning.
                    // No need to find more than the first failure.
                    result |= USPOOF_INVISIBLE;
                    failPos = i;
                    // TODO: Bug 8655: failPos is the position in the NFD buffer, but what we want
                    //       to give back to our caller is a position in the original input string.
                    if (failPos > length) {
                        failPos = length;
                    }
                    break;
                }
                marksSeenSoFar.add(c);
            }
        }
       
        
        if (This->fChecks & (USPOOF_WHOLE_SCRIPT_CONFUSABLE | USPOOF_MIXED_SCRIPT_CONFUSABLE)) {
            // The basic test is the same for both whole and mixed script confusables.
            // Compute the set of scripts that every input character has a confusable in.
            // For this computation an input character is always considered to be
            //    confusable with itself in its own script.
            // If the number of such scripts is two or more, and the input consisted of
            //   characters all from a single script, we have a whole script confusable.
            //   (The two scripts will be the original script and the one that is confusable)
            // If the number of such scripts >= one, and the original input contained characters from
            //   more than one script, we have a mixed script confusable.  (We can transform
            //   some of the characters, and end up with a visually similar string all in
            //   one script.)

            if (scriptCount == -1) {
                int32_t t;
                scriptCount = This->scriptScan(text, length, t, *status);
            }
            
            ScriptSet scripts;
            This->wholeScriptCheck(nfdText, nfdLength, &scripts, *status);
            int32_t confusableScriptCount = scripts.countMembers();
            //printf("confusableScriptCount = %d\n", confusableScriptCount);
            
            if ((This->fChecks & USPOOF_WHOLE_SCRIPT_CONFUSABLE) &&
                confusableScriptCount >= 2 &&
                scriptCount == 1) {
                result |= USPOOF_WHOLE_SCRIPT_CONFUSABLE;
            }
        
            if ((This->fChecks & USPOOF_MIXED_SCRIPT_CONFUSABLE) &&
                confusableScriptCount >= 1 &&
                scriptCount > 1) {
                result |= USPOOF_MIXED_SCRIPT_CONFUSABLE;
            }
        }
    }
    if (position != NULL && failPos != 0x7fffffff) {
        *position = failPos;
    }
    return result;
}


U_CAPI int32_t U_EXPORT2
uspoof_checkUTF8(const USpoofChecker *sc,
                 const char *text, int32_t length,
                 int32_t *position,
                 UErrorCode *status) {

    if (U_FAILURE(*status)) {
        return 0;
    }
    UChar stackBuf[USPOOF_STACK_BUFFER_SIZE];
    UChar* text16 = stackBuf;
    int32_t len16;
    
    u_strFromUTF8(text16, USPOOF_STACK_BUFFER_SIZE, &len16, text, length, status);
    if (U_FAILURE(*status) && *status != U_BUFFER_OVERFLOW_ERROR) {
        return 0;
    }
    if (*status == U_BUFFER_OVERFLOW_ERROR) {
        text16 = static_cast<UChar *>(uprv_malloc(len16 * sizeof(UChar) + 2));
        if (text16 == NULL) {
            *status = U_MEMORY_ALLOCATION_ERROR;
            return 0;
        }
        *status = U_ZERO_ERROR;
        u_strFromUTF8(text16, len16+1, NULL, text, length, status);
    }

    int32_t position16 = -1;
    int32_t result = uspoof_check(sc, text16, len16, &position16, status);
    if (U_FAILURE(*status)) {
        return 0;
    }

    if (position16 > 0) {
        // Translate a UTF-16 based error position back to a UTF-8 offset.
        // u_strToUTF8() in preflight mode is an easy way to do it.
        U_ASSERT(position16 <= len16);
        u_strToUTF8(NULL, 0, position, text16, position16, status);
        if (position > 0) {
            // position is the required buffer length from u_strToUTF8, which includes
            // space for a terminating NULL, which we don't want, hence the -1.
            *position -= 1;
        }
        *status = U_ZERO_ERROR;   // u_strToUTF8, above sets BUFFER_OVERFLOW_ERROR.
    }

    if (text16 != stackBuf) {
        uprv_free(text16);
    }
    return result;
    
}

/*  A convenience wrapper around the public uspoof_getSkeleton that handles
 *  allocating a larger buffer than provided if the original is too small.
 */
static UChar *getSkeleton(const USpoofChecker *sc, uint32_t type, const UChar *s, int32_t inputLength,
                         UChar *dest, int32_t destCapacity, int32_t *outputLength, UErrorCode *status) {
    int32_t requiredCapacity = 0;
    UChar *buf = dest;

    if (U_FAILURE(*status)) {
        return NULL;
    }
    requiredCapacity = uspoof_getSkeleton(sc, type, s, inputLength, dest, destCapacity, status);
    if (*status == U_BUFFER_OVERFLOW_ERROR) {
        buf = static_cast<UChar *>(uprv_malloc(requiredCapacity * sizeof(UChar)));
        if (buf == NULL) {
            *status = U_MEMORY_ALLOCATION_ERROR;
            return NULL;
        }
        *status = U_ZERO_ERROR;
        uspoof_getSkeleton(sc, type, s, inputLength, buf, requiredCapacity, status);
    }
    *outputLength = requiredCapacity;
    return buf;
}


U_CAPI int32_t U_EXPORT2
uspoof_areConfusable(const USpoofChecker *sc,
                     const UChar *s1, int32_t length1,
                     const UChar *s2, int32_t length2,
                     UErrorCode *status) {
    const SpoofImpl *This = SpoofImpl::validateThis(sc, *status);
    if (U_FAILURE(*status)) {
        return 0;
    }
    // 
    // See section 4 of UAX 39 for the algorithm for checking whether two strings are confusable,
    //   and for definitions of the types (single, whole, mixed-script) of confusables.
    
    // We only care about a few of the check flags.  Ignore the others.
    // If no tests relavant to this function have been specified, return an error.
    // TODO:  is this really the right thing to do?  It's probably an error on the caller's part,
    //        but logically we would just return 0 (no error).
    if ((This->fChecks & (USPOOF_SINGLE_SCRIPT_CONFUSABLE | USPOOF_MIXED_SCRIPT_CONFUSABLE | 
                          USPOOF_WHOLE_SCRIPT_CONFUSABLE)) == 0) {
        *status = U_INVALID_STATE_ERROR;
        return 0;
    }
    int32_t  flagsForSkeleton = This->fChecks & USPOOF_ANY_CASE;
    UChar    s1SkeletonBuf[USPOOF_STACK_BUFFER_SIZE];
    UChar   *s1Skeleton;
    int32_t  s1SkeletonLength = 0;

    UChar    s2SkeletonBuf[USPOOF_STACK_BUFFER_SIZE];
    UChar   *s2Skeleton;
    int32_t  s2SkeletonLength = 0;

    int32_t  result = 0;
    int32_t  t;
    int32_t  s1ScriptCount = This->scriptScan(s1, length1, t, *status);
    int32_t  s2ScriptCount = This->scriptScan(s2, length2, t, *status);

    if (This->fChecks & USPOOF_SINGLE_SCRIPT_CONFUSABLE) {
        // Do the Single Script compare.
        if (s1ScriptCount <= 1 && s2ScriptCount <= 1) {
            flagsForSkeleton |= USPOOF_SINGLE_SCRIPT_CONFUSABLE;
            s1Skeleton = getSkeleton(sc, flagsForSkeleton, s1, length1, s1SkeletonBuf, 
                                     sizeof(s1SkeletonBuf)/sizeof(UChar), &s1SkeletonLength, status);
            s2Skeleton = getSkeleton(sc, flagsForSkeleton, s2, length2, s2SkeletonBuf, 
                                     sizeof(s2SkeletonBuf)/sizeof(UChar), &s2SkeletonLength, status);
            if (s1SkeletonLength == s2SkeletonLength && u_strncmp(s1Skeleton, s2Skeleton, s1SkeletonLength) == 0) {
                result |= USPOOF_SINGLE_SCRIPT_CONFUSABLE;
            }
            if (s1Skeleton != s1SkeletonBuf) {
                uprv_free(s1Skeleton);
            }
            if (s2Skeleton != s2SkeletonBuf) {
                uprv_free(s2Skeleton);
            }
        }
    }

    if (result & USPOOF_SINGLE_SCRIPT_CONFUSABLE) {
         // If the two inputs are single script confusable they cannot also be
         // mixed or whole script confusable, according to the UAX39 definitions.
         // So we can skip those tests.
         return result;
    }

    // Optimization for whole script confusables test:  two identifiers are whole script confusable if
    // each is of a single script and they are mixed script confusable.
    UBool possiblyWholeScriptConfusables = 
        s1ScriptCount <= 1 && s2ScriptCount <= 1 && (This->fChecks & USPOOF_WHOLE_SCRIPT_CONFUSABLE);

    //
    // Mixed Script Check
    //
    if ((This->fChecks & USPOOF_MIXED_SCRIPT_CONFUSABLE) || possiblyWholeScriptConfusables ) {
        // For getSkeleton(), resetting the USPOOF_SINGLE_SCRIPT_CONFUSABLE flag will get us
        // the mixed script table skeleton, which is what we want.
        // The Any Case / Lower Case bit in the skelton flags was set at the top of the function.
        flagsForSkeleton &= ~USPOOF_SINGLE_SCRIPT_CONFUSABLE;
        s1Skeleton = getSkeleton(sc, flagsForSkeleton, s1, length1, s1SkeletonBuf, 
                                 sizeof(s1SkeletonBuf)/sizeof(UChar), &s1SkeletonLength, status);
        s2Skeleton = getSkeleton(sc, flagsForSkeleton, s2, length2, s2SkeletonBuf, 
                                 sizeof(s2SkeletonBuf)/sizeof(UChar), &s2SkeletonLength, status);
        if (s1SkeletonLength == s2SkeletonLength && u_strncmp(s1Skeleton, s2Skeleton, s1SkeletonLength) == 0) {
            result |= USPOOF_MIXED_SCRIPT_CONFUSABLE;
            if (possiblyWholeScriptConfusables) {
                result |= USPOOF_WHOLE_SCRIPT_CONFUSABLE;
            }
        }
        if (s1Skeleton != s1SkeletonBuf) {
            uprv_free(s1Skeleton);
        }
        if (s2Skeleton != s2SkeletonBuf) {
            uprv_free(s2Skeleton);
        }
    }

    return result;
}


// Convenience function for converting a UTF-8 input to a UChar * string, including
//          reallocating a buffer when required.  Parameters and their interpretation mostly
//          match u_strFromUTF8.

static UChar * convertFromUTF8(UChar *outBuf, int32_t outBufCapacity, int32_t *outputLength,
                               const char *in, int32_t inLength, UErrorCode *status) {
    if (U_FAILURE(*status)) {
        return NULL;
    }
    UChar *dest = outBuf;
    u_strFromUTF8(dest, outBufCapacity, outputLength, in, inLength, status);
    if (*status == U_BUFFER_OVERFLOW_ERROR) {
        dest = static_cast<UChar *>(uprv_malloc(*outputLength * sizeof(UChar)));
        if (dest == NULL) {
            *status = U_MEMORY_ALLOCATION_ERROR;
            return NULL;
        }
        *status = U_ZERO_ERROR;
        u_strFromUTF8(dest, *outputLength, NULL, in, inLength, status);
    }
    return dest;
}

    

U_CAPI int32_t U_EXPORT2
uspoof_areConfusableUTF8(const USpoofChecker *sc,
                         const char *s1, int32_t length1,
                         const char *s2, int32_t length2,
                         UErrorCode *status) {

    SpoofImpl::validateThis(sc, *status);
    if (U_FAILURE(*status)) {
        return 0;
    }

    UChar    s1Buf[USPOOF_STACK_BUFFER_SIZE];
    int32_t  lengthS1U;
    UChar   *s1U = convertFromUTF8(s1Buf, USPOOF_STACK_BUFFER_SIZE, &lengthS1U, s1, length1, status);

    UChar    s2Buf[USPOOF_STACK_BUFFER_SIZE];
    int32_t  lengthS2U;
    UChar   *s2U = convertFromUTF8(s2Buf, USPOOF_STACK_BUFFER_SIZE, &lengthS2U, s2, length2, status);

    int32_t results = uspoof_areConfusable(sc, s1U, lengthS1U, s2U, lengthS2U, status);
    
    if (s1U != s1Buf) {
        uprv_free(s1U);
    }
    if (s2U != s2Buf) {
        uprv_free(s2U);
    }
    return results;
}
 

U_CAPI int32_t U_EXPORT2
uspoof_areConfusableUnicodeString(const USpoofChecker *sc,
                                  const icu::UnicodeString &s1,
                                  const icu::UnicodeString &s2,
                                  UErrorCode *status) {

    const UChar *u1  = s1.getBuffer();
    int32_t  length1 = s1.length();
    const UChar *u2  = s2.getBuffer();
    int32_t  length2 = s2.length();

    int32_t results  = uspoof_areConfusable(sc, u1, length1, u2, length2, status);
    return results;
}




U_CAPI int32_t U_EXPORT2
uspoof_checkUnicodeString(const USpoofChecker *sc,
                          const icu::UnicodeString &text, 
                          int32_t *position,
                          UErrorCode *status) {
    int32_t result = uspoof_check(sc, text.getBuffer(), text.length(), position, status);
    return result;
}


U_CAPI int32_t U_EXPORT2
uspoof_getSkeleton(const USpoofChecker *sc,
                   uint32_t type,
                   const UChar *s,  int32_t length,
                   UChar *dest, int32_t destCapacity,
                   UErrorCode *status) {

    // TODO:  this function could be sped up a bit
    //        Skip the input normalization when not needed, work from callers data.
    //        Put the initial skeleton straight into the caller's destination buffer.
    //        It probably won't need normalization.
    //        But these would make the structure more complicated.  

    const SpoofImpl *This = SpoofImpl::validateThis(sc, *status);
    if (U_FAILURE(*status)) {
        return 0;
    }
    if (length<-1 || destCapacity<0 || (destCapacity==0 && dest!=NULL) ||
        (type & ~(USPOOF_SINGLE_SCRIPT_CONFUSABLE | USPOOF_ANY_CASE)) != 0) {
        *status = U_ILLEGAL_ARGUMENT_ERROR;
        return 0;
    }

   int32_t tableMask = 0;
   switch (type) {
      case 0:
        tableMask = USPOOF_ML_TABLE_FLAG;
        break;
      case USPOOF_SINGLE_SCRIPT_CONFUSABLE:
        tableMask = USPOOF_SL_TABLE_FLAG;
        break;
      case USPOOF_ANY_CASE:
        tableMask = USPOOF_MA_TABLE_FLAG;
        break;
      case USPOOF_SINGLE_SCRIPT_CONFUSABLE | USPOOF_ANY_CASE:
        tableMask = USPOOF_SA_TABLE_FLAG;
        break;
      default:
        *status = U_ILLEGAL_ARGUMENT_ERROR;
        return 0;
    }

    // NFD transform of the user supplied input
    
    UChar nfdStackBuf[USPOOF_STACK_BUFFER_SIZE];
    UChar *nfdInput = nfdStackBuf;
    int32_t normalizedLen = unorm_normalize(
        s, length, UNORM_NFD, 0, nfdInput, USPOOF_STACK_BUFFER_SIZE, status);
    if (*status == U_BUFFER_OVERFLOW_ERROR) {
        nfdInput = (UChar *)uprv_malloc((normalizedLen+1)*sizeof(UChar));
        if (nfdInput == NULL) {
            *status = U_MEMORY_ALLOCATION_ERROR;
            return 0;
        }
        *status = U_ZERO_ERROR;
        normalizedLen = unorm_normalize(s, length, UNORM_NFD, 0,
                                        nfdInput, normalizedLen+1, status);
    }
    if (U_FAILURE(*status)) {
        if (nfdInput != nfdStackBuf) {
            uprv_free(nfdInput);
        }
        return 0;
    }

    // buffer to hold the Unicode defined skeleton mappings for a single code point
    UChar buf[USPOOF_MAX_SKELETON_EXPANSION];

    // Apply the skeleton mapping to the NFD normalized input string
    // Accumulate the skeleton, possibly unnormalized, in a UnicodeString.
    int32_t inputIndex = 0;
    UnicodeString skelStr;
    while (inputIndex < normalizedLen) {
        UChar32 c;
        U16_NEXT(nfdInput, inputIndex, normalizedLen, c);
        int32_t replaceLen = This->confusableLookup(c, tableMask, buf);
        skelStr.append(buf, replaceLen);
    }

    if (nfdInput != nfdStackBuf) {
        uprv_free(nfdInput);
    }
    
    const UChar *result = skelStr.getBuffer();
    int32_t  resultLen  = skelStr.length();
    UChar   *normedResult = NULL;

    // Check the skeleton for NFD, normalize it if needed.
    // Unnormalized results should be very rare.
    if (!unorm_isNormalized(result, resultLen, UNORM_NFD, status)) {
        normalizedLen = unorm_normalize(result, resultLen, UNORM_NFD, 0, NULL, 0, status);
        normedResult = static_cast<UChar *>(uprv_malloc((normalizedLen+1)*sizeof(UChar)));
        if (normedResult == NULL) {
            *status = U_MEMORY_ALLOCATION_ERROR;
            return 0;
        }
        *status = U_ZERO_ERROR;
        unorm_normalize(result, resultLen, UNORM_NFD, 0, normedResult, normalizedLen+1, status);
        result = normedResult;
        resultLen = normalizedLen;
    }

    // Copy the skeleton to the caller's buffer
    if (U_SUCCESS(*status)) {
        if (destCapacity == 0 || resultLen > destCapacity) {
            *status = resultLen>destCapacity ? U_BUFFER_OVERFLOW_ERROR : U_STRING_NOT_TERMINATED_WARNING;
        } else {
            u_memcpy(dest, result, resultLen);
            if (destCapacity > resultLen) {
                dest[resultLen] = 0;
            } else {
                *status = U_STRING_NOT_TERMINATED_WARNING;
            }
        }
     }       
     uprv_free(normedResult);
     return resultLen;
}



U_I18N_API UnicodeString &  U_EXPORT2
uspoof_getSkeletonUnicodeString(const USpoofChecker *sc,
                                uint32_t type,
                                const UnicodeString &s,
                                UnicodeString &dest,
                                UErrorCode *status) {
    if (U_FAILURE(*status)) {
        return dest;
    }
    dest.remove();
    
    const UChar *str = s.getBuffer();
    int32_t      strLen = s.length();
    UChar        smallBuf[USPOOF_STACK_BUFFER_SIZE];
    UChar       *buf = smallBuf;
    int32_t outputSize = uspoof_getSkeleton(sc, type, str, strLen, smallBuf, USPOOF_STACK_BUFFER_SIZE, status);
    if (*status == U_BUFFER_OVERFLOW_ERROR) {
        buf = static_cast<UChar *>(uprv_malloc((outputSize+1)*sizeof(UChar)));
        if (buf == NULL) {
            *status = U_MEMORY_ALLOCATION_ERROR;
            return dest;
        }
        *status = U_ZERO_ERROR;
        uspoof_getSkeleton(sc, type, str, strLen, buf, outputSize+1, status);
    }
    if (U_SUCCESS(*status)) {
        dest.setTo(buf, outputSize);
    }

    if (buf != smallBuf) {
        uprv_free(buf);
    }
    return dest;
}


U_CAPI int32_t U_EXPORT2
uspoof_getSkeletonUTF8(const USpoofChecker *sc,
                       uint32_t type,
                       const char *s,  int32_t length,
                       char *dest, int32_t destCapacity,
                       UErrorCode *status) {
    // Lacking a UTF-8 normalization API, just converting the input to
    // UTF-16 seems as good an approach as any.  In typical use, input will
    // be an identifier, which is to say not too long for stack buffers.
    if (U_FAILURE(*status)) {
        return 0;
    }
    // Buffers for the UChar form of the input and skeleton strings.
    UChar    smallInBuf[USPOOF_STACK_BUFFER_SIZE];
    UChar   *inBuf = smallInBuf;
    UChar    smallOutBuf[USPOOF_STACK_BUFFER_SIZE];
    UChar   *outBuf = smallOutBuf;

    int32_t  lengthInUChars = 0;
    int32_t  skelLengthInUChars = 0;
    int32_t  skelLengthInUTF8 = 0;
    
    u_strFromUTF8(inBuf, USPOOF_STACK_BUFFER_SIZE, &lengthInUChars,
                  s, length, status);
    if (*status == U_BUFFER_OVERFLOW_ERROR) {
        inBuf = static_cast<UChar *>(uprv_malloc((lengthInUChars+1)*sizeof(UChar)));
        if (inBuf == NULL) {
            *status = U_MEMORY_ALLOCATION_ERROR;
            goto cleanup;
        }
        *status = U_ZERO_ERROR;
        u_strFromUTF8(inBuf, lengthInUChars+1, &lengthInUChars,
                      s, length, status);
    }
    
    skelLengthInUChars = uspoof_getSkeleton(sc, type, inBuf, lengthInUChars,
                                         outBuf, USPOOF_STACK_BUFFER_SIZE, status);
    if (*status == U_BUFFER_OVERFLOW_ERROR) {
        outBuf = static_cast<UChar *>(uprv_malloc((skelLengthInUChars+1)*sizeof(UChar)));
        if (outBuf == NULL) {
            *status = U_MEMORY_ALLOCATION_ERROR;
            goto cleanup;
        }
        *status = U_ZERO_ERROR;
        skelLengthInUChars = uspoof_getSkeleton(sc, type, inBuf, lengthInUChars,
                                         outBuf, skelLengthInUChars+1, status);
    }

    u_strToUTF8(dest, destCapacity, &skelLengthInUTF8,
                outBuf, skelLengthInUChars, status);

  cleanup:
    if (inBuf != smallInBuf) {
        uprv_free(inBuf);
    }
    if (outBuf != smallOutBuf) {
        uprv_free(outBuf);
    }
    return skelLengthInUTF8;
}


U_CAPI int32_t U_EXPORT2
uspoof_serialize(USpoofChecker *sc,void *buf, int32_t capacity, UErrorCode *status) {
    SpoofImpl *This = SpoofImpl::validateThis(sc, *status);
    if (This == NULL) {
        U_ASSERT(U_FAILURE(*status));
        return 0;
    }
    int32_t dataSize = This->fSpoofData->fRawData->fLength;
    if (capacity < dataSize) {
        *status = U_BUFFER_OVERFLOW_ERROR;
        return dataSize;
    }
    uprv_memcpy(buf, This->fSpoofData->fRawData, dataSize);
    return dataSize;
}

#endif