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.

Header

Mercurial (d8847129d134)

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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* vim: set ts=2 sw=2 et tw=78: */
/* This Source Code Form is subject to the terms of the Mozilla Public
 * License, v. 2.0. If a copy of the MPL was not distributed with this
 * file, You can obtain one at http://mozilla.org/MPL/2.0/. */

//#define __INCREMENTAL 1

#include "mozilla/DebugOnly.h"

#include "nsScanner.h"
#include "nsDebug.h"
#include "nsReadableUtils.h"
#include "nsIInputStream.h"
#include "nsIFile.h"
#include "nsNetUtil.h"
#include "nsUTF8Utils.h" // for LossyConvertEncoding
#include "nsCRT.h"
#include "nsParser.h"
#include "nsCharsetSource.h"

#include "mozilla/dom/EncodingUtils.h"

using mozilla::dom::EncodingUtils;

// We replace NUL characters with this character.
static char16_t sInvalid = UCS2_REPLACEMENT_CHAR;

nsReadEndCondition::nsReadEndCondition(const char16_t* aTerminateChars) :
  mChars(aTerminateChars), mFilter(char16_t(~0)) // All bits set
{
  // Build filter that will be used to filter out characters with
  // bits that none of the terminal chars have. This works very well
  // because terminal chars often have only the last 4-6 bits set and
  // normal ascii letters have bit 7 set. Other letters have even higher
  // bits set.
  
  // Calculate filter
  const char16_t *current = aTerminateChars;
  char16_t terminalChar = *current;
  while (terminalChar) {
    mFilter &= ~terminalChar;
    ++current;
    terminalChar = *current;
  }
}

/**
 *  Use this constructor if you want i/o to be based on 
 *  a single string you hand in during construction.
 *  This short cut was added for Javascript.
 *
 *  @update  gess 5/12/98
 *  @param   aMode represents the parser mode (nav, other)
 *  @return  
 */
nsScanner::nsScanner(const nsAString& anHTMLString)
{
  MOZ_COUNT_CTOR(nsScanner);

  mSlidingBuffer = nullptr;
  mCountRemaining = 0;
  mFirstNonWhitespacePosition = -1;
  if (AppendToBuffer(anHTMLString)) {
    mSlidingBuffer->BeginReading(mCurrentPosition);
  } else {
    /* XXX see hack below, re: bug 182067 */
    memset(&mCurrentPosition, 0, sizeof(mCurrentPosition));
    mEndPosition = mCurrentPosition;
  }
  mMarkPosition = mCurrentPosition;
  mIncremental = false;
  mUnicodeDecoder = 0;
  mCharsetSource = kCharsetUninitialized;
  mHasInvalidCharacter = false;
  mReplacementCharacter = char16_t(0x0);
}

/**
 *  Use this constructor if you want i/o to be based on strings 
 *  the scanner receives. If you pass a null filename, you
 *  can still provide data to the scanner via append.
 */
nsScanner::nsScanner(nsString& aFilename, bool aCreateStream)
  : mFilename(aFilename)
{
  MOZ_COUNT_CTOR(nsScanner);
  NS_ASSERTION(!aCreateStream, "This is always true.");

  mSlidingBuffer = nullptr;

  // XXX This is a big hack.  We need to initialize the iterators to something.
  // What matters is that mCurrentPosition == mEndPosition, so that our methods
  // believe that we are at EOF (see bug 182067).  We null out mCurrentPosition
  // so that we have some hope of catching null pointer dereferences associated
  // with this hack. --darin
  memset(&mCurrentPosition, 0, sizeof(mCurrentPosition));
  mMarkPosition = mCurrentPosition;
  mEndPosition = mCurrentPosition;

  mIncremental = true;
  mFirstNonWhitespacePosition = -1;
  mCountRemaining = 0;

  mUnicodeDecoder = 0;
  mCharsetSource = kCharsetUninitialized;
  mHasInvalidCharacter = false;
  mReplacementCharacter = char16_t(0x0);
  // XML defaults to UTF-8 and about:blank is UTF-8, too.
  SetDocumentCharset(NS_LITERAL_CSTRING("UTF-8"), kCharsetFromDocTypeDefault);
}

nsresult nsScanner::SetDocumentCharset(const nsACString& aCharset , int32_t aSource)
{
  if (aSource < mCharsetSource) // priority is lower than the current one
    return NS_OK;

  mCharsetSource = aSource;

  nsCString charsetName;
  mozilla::DebugOnly<bool> valid =
      EncodingUtils::FindEncodingForLabel(aCharset, charsetName);
  MOZ_ASSERT(valid, "Should never call with a bogus aCharset.");

  if (!mCharset.IsEmpty() && charsetName.Equals(mCharset)) {
    return NS_OK; // no difference, don't change it
  }

  // different, need to change it

  mCharset.Assign(charsetName);

  mUnicodeDecoder = EncodingUtils::DecoderForEncoding(mCharset);
  mUnicodeDecoder->SetInputErrorBehavior(nsIUnicodeDecoder::kOnError_Signal);

  return NS_OK;
}


/**
 *  default destructor
 *  
 *  @update  gess 3/25/98
 *  @param   
 *  @return  
 */
nsScanner::~nsScanner() {

  delete mSlidingBuffer;

  MOZ_COUNT_DTOR(nsScanner);
}

/**
 *  Resets current offset position of input stream to marked position. 
 *  This allows us to back up to this point if the need should arise, 
 *  such as when tokenization gets interrupted.
 *  NOTE: IT IS REALLY BAD FORM TO CALL RELEASE WITHOUT CALLING MARK FIRST!
 *
 *  @update  gess 5/12/98
 *  @param   
 *  @return  
 */
void nsScanner::RewindToMark(void){
  if (mSlidingBuffer) {
    mCountRemaining += (Distance(mMarkPosition, mCurrentPosition));
    mCurrentPosition = mMarkPosition;
  }
}


/**
 *  Records current offset position in input stream. This allows us
 *  to back up to this point if the need should arise, such as when
 *  tokenization gets interrupted.
 *
 *  @update  gess 7/29/98
 *  @param   
 *  @return  
 */
int32_t nsScanner::Mark() {
  int32_t distance = 0;
  if (mSlidingBuffer) {
    nsScannerIterator oldStart;
    mSlidingBuffer->BeginReading(oldStart);

    distance = Distance(oldStart, mCurrentPosition);

    mSlidingBuffer->DiscardPrefix(mCurrentPosition);
    mSlidingBuffer->BeginReading(mCurrentPosition);
    mMarkPosition = mCurrentPosition;
  }

  return distance;
}

/** 
 * Insert data to our underlying input buffer as
 * if it were read from an input stream.
 *
 * @update  harishd 01/12/99
 * @return  error code 
 */
bool nsScanner::UngetReadable(const nsAString& aBuffer) {
  if (!mSlidingBuffer) {
    return false;
  }

  mSlidingBuffer->UngetReadable(aBuffer,mCurrentPosition);
  mSlidingBuffer->BeginReading(mCurrentPosition); // Insertion invalidated our iterators
  mSlidingBuffer->EndReading(mEndPosition);
 
  uint32_t length = aBuffer.Length();
  mCountRemaining += length; // Ref. bug 117441
  return true;
}

/** 
 * Append data to our underlying input buffer as
 * if it were read from an input stream.
 *
 * @update  gess4/3/98
 * @return  error code 
 */
nsresult nsScanner::Append(const nsAString& aBuffer) {
  if (!AppendToBuffer(aBuffer))
    return NS_ERROR_OUT_OF_MEMORY;
  return NS_OK;
}

/**
 *  
 *  
 *  @update  gess 5/21/98
 *  @param   
 *  @return  
 */
nsresult nsScanner::Append(const char* aBuffer, uint32_t aLen,
                           nsIRequest *aRequest)
{
  nsresult res = NS_OK;
  if (mUnicodeDecoder) {
    int32_t unicharBufLen = 0;
    mUnicodeDecoder->GetMaxLength(aBuffer, aLen, &unicharBufLen);
    nsScannerString::Buffer* buffer = nsScannerString::AllocBuffer(unicharBufLen + 1);
    NS_ENSURE_TRUE(buffer,NS_ERROR_OUT_OF_MEMORY);
    char16_t *unichars = buffer->DataStart();

    int32_t totalChars = 0;
    int32_t unicharLength = unicharBufLen;
    int32_t errorPos = -1;

    do {
      int32_t srcLength = aLen;
      res = mUnicodeDecoder->Convert(aBuffer, &srcLength, unichars, &unicharLength);

      totalChars += unicharLength;
      // Continuation of failure case
      if(NS_FAILED(res)) {
        // if we failed, we consume one byte, replace it with the replacement
        // character and try the conversion again.

        // This is only needed because some decoders don't follow the
        // nsIUnicodeDecoder contract: they return a failure when *aDestLength
        // is 0 rather than the correct NS_OK_UDEC_MOREOUTPUT.  See bug 244177
        if ((unichars + unicharLength) >= buffer->DataEnd()) {
          NS_ERROR("Unexpected end of destination buffer");
          break;
        }

        if (mReplacementCharacter == 0x0 && errorPos == -1) {
          errorPos = totalChars;
        }
        unichars[unicharLength++] = mReplacementCharacter == 0x0 ?
                                    mUnicodeDecoder->GetCharacterForUnMapped() :
                                    mReplacementCharacter;

        unichars = unichars + unicharLength;
        unicharLength = unicharBufLen - (++totalChars);

        mUnicodeDecoder->Reset();

        if(((uint32_t) (srcLength + 1)) > aLen) {
          srcLength = aLen;
        }
        else {
          ++srcLength;
        }

        aBuffer += srcLength;
        aLen -= srcLength;
      }
    } while (NS_FAILED(res) && (aLen > 0));

    buffer->SetDataLength(totalChars);
    // Don't propagate return code of unicode decoder
    // since it doesn't reflect on our success or failure
    // - Ref. bug 87110
    res = NS_OK; 
    if (!AppendToBuffer(buffer, aRequest, errorPos))
      res = NS_ERROR_OUT_OF_MEMORY;
  }
  else {
    NS_WARNING("No decoder found.");
    res = NS_ERROR_FAILURE;
  }

  return res;
}

/**
 *  retrieve next char from scanners internal input stream
 *  
 *  @update  gess 3/25/98
 *  @param   
 *  @return  error code reflecting read status
 */
nsresult nsScanner::GetChar(char16_t& aChar) {
  if (!mSlidingBuffer || mCurrentPosition == mEndPosition) {
    aChar = 0;
    return kEOF;
  }

  aChar = *mCurrentPosition++;
  --mCountRemaining;

  return NS_OK;
}


/**
 *  peek ahead to consume next char from scanner's internal
 *  input buffer
 *  
 *  @update  gess 3/25/98
 *  @param   
 *  @return  
 */
nsresult nsScanner::Peek(char16_t& aChar, uint32_t aOffset) {
  aChar = 0;

  if (!mSlidingBuffer || mCurrentPosition == mEndPosition) {
    return kEOF;
  }

  if (aOffset > 0) {
    if (mCountRemaining <= aOffset)
      return kEOF;

    nsScannerIterator pos = mCurrentPosition;
    pos.advance(aOffset);
    aChar=*pos;
  }
  else {
    aChar=*mCurrentPosition;
  }

  return NS_OK;
}

nsresult nsScanner::Peek(nsAString& aStr, int32_t aNumChars, int32_t aOffset)
{
  if (!mSlidingBuffer || mCurrentPosition == mEndPosition) {
    return kEOF;
  }

  nsScannerIterator start, end;

  start = mCurrentPosition;

  if ((int32_t)mCountRemaining <= aOffset) {
    return kEOF;
  }

  if (aOffset > 0) {
    start.advance(aOffset);
  }

  if (mCountRemaining < uint32_t(aNumChars + aOffset)) {
    end = mEndPosition;
  }
  else {
    end = start;
    end.advance(aNumChars);
  }

  CopyUnicodeTo(start, end, aStr);

  return NS_OK;
}


/**
 *  Skip whitespace on scanner input stream
 *  
 *  @update  gess 3/25/98
 *  @param   
 *  @return  error status
 */
nsresult nsScanner::SkipWhitespace(int32_t& aNewlinesSkipped) {

  if (!mSlidingBuffer) {
    return kEOF;
  }

  char16_t theChar = 0;
  nsresult  result = Peek(theChar);
  
  if (NS_FAILED(result)) {
    return result;
  }
  
  nsScannerIterator current = mCurrentPosition;
  bool      done = false;
  bool      skipped = false;
  
  while (!done && current != mEndPosition) {
    switch(theChar) {
      case '\n':
      case '\r': ++aNewlinesSkipped;
      case ' ' :
      case '\t':
        {
          skipped = true;
          char16_t thePrevChar = theChar;
          theChar = (++current != mEndPosition) ? *current : '\0';
          if ((thePrevChar == '\r' && theChar == '\n') ||
              (thePrevChar == '\n' && theChar == '\r')) {
            theChar = (++current != mEndPosition) ? *current : '\0'; // CRLF == LFCR => LF
          }
        }
        break;
      default:
        done = true;
        break;
    }
  }

  if (skipped) {
    SetPosition(current);
    if (current == mEndPosition) {
      result = kEOF;
    }
  }

  return result;
}

/**
 *  Skip over chars as long as they equal given char
 *  
 *  @update  gess 3/25/98
 *  @param   
 *  @return  error code
 */
nsresult nsScanner::SkipOver(char16_t aSkipChar){

  if (!mSlidingBuffer) {
    return kEOF;
  }

  char16_t ch=0;
  nsresult   result=NS_OK;

  while(NS_OK==result) {
    result=Peek(ch);
    if(NS_OK == result) {
      if(ch!=aSkipChar) {
        break;
      }
      GetChar(ch);
    } 
    else break;
  } //while
  return result;

}

#if 0
void DoErrTest(nsString& aString) {
  int32_t pos=aString.FindChar(0);
  if(kNotFound<pos) {
    if(aString.Length()-1!=pos) {
    }
  }
}

void DoErrTest(nsCString& aString) {
  int32_t pos=aString.FindChar(0);
  if(kNotFound<pos) {
    if(aString.Length()-1!=pos) {
    }
  }
}
#endif

/**
 *  Consume characters until you run into space, a '<', a '>', or a '/'.
 *  
 *  @param   aString - receives new data from stream
 *  @return  error code
 */
nsresult nsScanner::ReadTagIdentifier(nsScannerSharedSubstring& aString) {

  if (!mSlidingBuffer) {
    return kEOF;
  }

  char16_t         theChar=0;
  nsresult          result=Peek(theChar);
  nsScannerIterator current, end;
  bool              found=false;  
  
  current = mCurrentPosition;
  end = mEndPosition;

  // Loop until we find an illegal character. Everything is then appended
  // later.
  while(current != end && !found) {
    theChar=*current;

    switch(theChar) {
      case '\n':
      case '\r':
      case ' ' :
      case '\t':
      case '\v':
      case '\f':
      case '<':
      case '>':
      case '/':
        found = true;
        break;

      case '\0':
        ReplaceCharacter(current, sInvalid);
        break;

      default:
        break;
    }

    if (!found) {
      ++current;
    }
  }

  // Don't bother appending nothing.
  if (current != mCurrentPosition) {
    AppendUnicodeTo(mCurrentPosition, current, aString);
  }

  SetPosition(current);  
  if (current == end) {
    result = kEOF;
  }

  //DoErrTest(aString);

  return result;
}

/**
 *  Consume characters until you run into a char that's not valid in an
 *  entity name
 *  
 *  @param   aString - receives new data from stream
 *  @return  error code
 */
nsresult nsScanner::ReadEntityIdentifier(nsString& aString) {

  if (!mSlidingBuffer) {
    return kEOF;
  }

  char16_t         theChar=0;
  nsresult          result=Peek(theChar);
  nsScannerIterator origin, current, end;
  bool              found=false;  

  origin = mCurrentPosition;
  current = mCurrentPosition;
  end = mEndPosition;

  while(current != end) {
 
    theChar=*current;
    if(theChar) {
      found=false;
      switch(theChar) {
        case '_':
        case '-':
        case '.':
          // Don't allow ':' in entity names.  See bug 23791
          found = true;
          break;
        default:
          found = ('a'<=theChar && theChar<='z') ||
                  ('A'<=theChar && theChar<='Z') ||
                  ('0'<=theChar && theChar<='9');
          break;
      }

      if(!found) {
        AppendUnicodeTo(mCurrentPosition, current, aString);
        break;
      }
    }
    ++current;
  }
  
  SetPosition(current);
  if (current == end) {
    AppendUnicodeTo(origin, current, aString);
    return kEOF;
  }

  //DoErrTest(aString);

  return result;
}

/**
 *  Consume digits 
 *  
 *  @param   aString - should contain digits
 *  @return  error code
 */
nsresult nsScanner::ReadNumber(nsString& aString,int32_t aBase) {

  if (!mSlidingBuffer) {
    return kEOF;
  }

  NS_ASSERTION(aBase == 10 || aBase == 16,"base value not supported");

  char16_t         theChar=0;
  nsresult          result=Peek(theChar);
  nsScannerIterator origin, current, end;

  origin = mCurrentPosition;
  current = origin;
  end = mEndPosition;

  bool done = false;
  while(current != end) {
    theChar=*current;
    if(theChar) {
      done = (theChar < '0' || theChar > '9') && 
             ((aBase == 16)? (theChar < 'A' || theChar > 'F') &&
                             (theChar < 'a' || theChar > 'f')
                             :true);
      if(done) {
        AppendUnicodeTo(origin, current, aString);
        break;
      }
    }
    ++current;
  }

  SetPosition(current);
  if (current == end) {
    AppendUnicodeTo(origin, current, aString);
    return kEOF;
  }

  //DoErrTest(aString);

  return result;
}

/**
 *  Consume characters until you find the terminal char
 *  
 *  @update  gess 3/25/98
 *  @param   aString receives new data from stream
 *  @param   addTerminal tells us whether to append terminal to aString
 *  @return  error code
 */
nsresult nsScanner::ReadWhitespace(nsScannerSharedSubstring& aString,
                                   int32_t& aNewlinesSkipped,
                                   bool& aHaveCR) {

  aHaveCR = false;

  if (!mSlidingBuffer) {
    return kEOF;
  }

  char16_t theChar = 0;
  nsresult  result = Peek(theChar);
  
  if (NS_FAILED(result)) {
    return result;
  }
  
  nsScannerIterator origin, current, end;
  bool done = false;  

  origin = mCurrentPosition;
  current = origin;
  end = mEndPosition;

  bool haveCR = false;

  while(!done && current != end) {
    switch(theChar) {
      case '\n':
      case '\r':
        {
          ++aNewlinesSkipped;
          char16_t thePrevChar = theChar;
          theChar = (++current != end) ? *current : '\0';
          if ((thePrevChar == '\r' && theChar == '\n') ||
              (thePrevChar == '\n' && theChar == '\r')) {
            theChar = (++current != end) ? *current : '\0'; // CRLF == LFCR => LF
            haveCR = true;
          } else if (thePrevChar == '\r') {
            // Lone CR becomes CRLF; callers should know to remove extra CRs
            AppendUnicodeTo(origin, current, aString);
            aString.writable().Append(char16_t('\n'));
            origin = current;
            haveCR = true;
          }
        }
        break;
      case ' ' :
      case '\t':
        theChar = (++current != end) ? *current : '\0';
        break;
      default:
        done = true;
        AppendUnicodeTo(origin, current, aString);
        break;
    }
  }

  SetPosition(current);
  if (current == end) {
    AppendUnicodeTo(origin, current, aString);
    result = kEOF;
  }

  aHaveCR = haveCR;
  return result;
}

//XXXbz callers of this have to manage their lone '\r' themselves if they want
//it to work.  Good thing they're all in view-source and it deals.
nsresult nsScanner::ReadWhitespace(nsScannerIterator& aStart, 
                                   nsScannerIterator& aEnd,
                                   int32_t& aNewlinesSkipped) {

  if (!mSlidingBuffer) {
    return kEOF;
  }

  char16_t theChar = 0;
  nsresult  result = Peek(theChar);
  
  if (NS_FAILED(result)) {
    return result;
  }
  
  nsScannerIterator origin, current, end;
  bool done = false;  

  origin = mCurrentPosition;
  current = origin;
  end = mEndPosition;

  while(!done && current != end) {
    switch(theChar) {
      case '\n':
      case '\r': ++aNewlinesSkipped;
      case ' ' :
      case '\t':
        {
          char16_t thePrevChar = theChar;
          theChar = (++current != end) ? *current : '\0';
          if ((thePrevChar == '\r' && theChar == '\n') ||
              (thePrevChar == '\n' && theChar == '\r')) {
            theChar = (++current != end) ? *current : '\0'; // CRLF == LFCR => LF
          }
        }
        break;
      default:
        done = true;
        aStart = origin;
        aEnd = current;
        break;
    }
  }

  SetPosition(current);
  if (current == end) {
    aStart = origin;
    aEnd = current;
    result = kEOF;
  }

  return result;
}

/**
 *  Consume characters until you encounter one contained in given
 *  input set.
 *  
 *  @update  gess 3/25/98
 *  @param   aString will contain the result of this method
 *  @param   aTerminalSet is an ordered string that contains
 *           the set of INVALID characters
 *  @return  error code
 */
nsresult nsScanner::ReadUntil(nsAString& aString,
                              const nsReadEndCondition& aEndCondition,
                              bool addTerminal)
{  
  if (!mSlidingBuffer) {
    return kEOF;
  }

  nsScannerIterator origin, current;
  const char16_t* setstart = aEndCondition.mChars;
  const char16_t* setcurrent;

  origin = mCurrentPosition;
  current = origin;

  char16_t         theChar=0;
  nsresult          result=Peek(theChar);

  if (NS_FAILED(result)) {
    return result;
  }
  
  while (current != mEndPosition) {
    theChar = *current;
    if (theChar == '\0') {
      ReplaceCharacter(current, sInvalid);
      theChar = sInvalid;
    }

    // Filter out completely wrong characters
    // Check if all bits are in the required area
    if(!(theChar & aEndCondition.mFilter)) {
      // They were. Do a thorough check.

      setcurrent = setstart;
      while (*setcurrent) {
        if (*setcurrent == theChar) {
          if(addTerminal)
            ++current;
          AppendUnicodeTo(origin, current, aString);
          SetPosition(current);

          //DoErrTest(aString);

          return NS_OK;
        }
        ++setcurrent;
      }
    }
    
    ++current;
  }

  // If we are here, we didn't find any terminator in the string and
  // current = mEndPosition
  SetPosition(current);
  AppendUnicodeTo(origin, current, aString);
  return kEOF;
}

nsresult nsScanner::ReadUntil(nsScannerSharedSubstring& aString,
                              const nsReadEndCondition& aEndCondition,
                              bool addTerminal)
{  
  if (!mSlidingBuffer) {
    return kEOF;
  }

  nsScannerIterator origin, current;
  const char16_t* setstart = aEndCondition.mChars;
  const char16_t* setcurrent;

  origin = mCurrentPosition;
  current = origin;

  char16_t         theChar=0;
  nsresult          result=Peek(theChar);

  if (NS_FAILED(result)) {
    return result;
  }
  
  while (current != mEndPosition) {
    theChar = *current;
    if (theChar == '\0') {
      ReplaceCharacter(current, sInvalid);
      theChar = sInvalid;
    }

    // Filter out completely wrong characters
    // Check if all bits are in the required area
    if(!(theChar & aEndCondition.mFilter)) {
      // They were. Do a thorough check.

      setcurrent = setstart;
      while (*setcurrent) {
        if (*setcurrent == theChar) {
          if(addTerminal)
            ++current;
          AppendUnicodeTo(origin, current, aString);
          SetPosition(current);

          //DoErrTest(aString);

          return NS_OK;
        }
        ++setcurrent;
      }
    }
    
    ++current;
  }

  // If we are here, we didn't find any terminator in the string and
  // current = mEndPosition
  SetPosition(current);
  AppendUnicodeTo(origin, current, aString);
  return kEOF;
}

nsresult nsScanner::ReadUntil(nsScannerIterator& aStart, 
                              nsScannerIterator& aEnd,
                              const nsReadEndCondition &aEndCondition,
                              bool addTerminal)
{
  if (!mSlidingBuffer) {
    return kEOF;
  }

  nsScannerIterator origin, current;
  const char16_t* setstart = aEndCondition.mChars;
  const char16_t* setcurrent;

  origin = mCurrentPosition;
  current = origin;

  char16_t         theChar=0;
  nsresult          result=Peek(theChar);
  
  if (NS_FAILED(result)) {
    aStart = aEnd = current;
    return result;
  }
  
  while (current != mEndPosition) {
    theChar = *current;
    if (theChar == '\0') {
      ReplaceCharacter(current, sInvalid);
      theChar = sInvalid;
    }

    // Filter out completely wrong characters
    // Check if all bits are in the required area
    if(!(theChar & aEndCondition.mFilter)) {
      // They were. Do a thorough check.
      setcurrent = setstart;
      while (*setcurrent) {
        if (*setcurrent == theChar) {
          if(addTerminal)
            ++current;
          aStart = origin;
          aEnd = current;
          SetPosition(current);

          return NS_OK;
        }
        ++setcurrent;
      }
    }

    ++current;
  }

  // If we are here, we didn't find any terminator in the string and
  // current = mEndPosition
  SetPosition(current);
  aStart = origin;
  aEnd = current;
  return kEOF;
}

/**
 *  Consumes chars until you see the given terminalChar
 *  
 *  @update  gess 3/25/98
 *  @param   
 *  @return  error code
 */
nsresult nsScanner::ReadUntil(nsAString& aString,
                              char16_t aTerminalChar,
                              bool addTerminal)
{
  if (!mSlidingBuffer) {
    return kEOF;
  }

  nsScannerIterator origin, current;

  origin = mCurrentPosition;
  current = origin;

  char16_t theChar;
  nsresult result = Peek(theChar);

  if (NS_FAILED(result)) {
    return result;
  }

  while (current != mEndPosition) {
    theChar = *current;
    if (theChar == '\0') {
      ReplaceCharacter(current, sInvalid);
      theChar = sInvalid;
    }

    if (aTerminalChar == theChar) {
      if(addTerminal)
        ++current;
      AppendUnicodeTo(origin, current, aString);
      SetPosition(current);
      return NS_OK;
    }
    ++current;
  }

  // If we are here, we didn't find any terminator in the string and
  // current = mEndPosition
  AppendUnicodeTo(origin, current, aString);
  SetPosition(current);
  return kEOF;

}

void nsScanner::BindSubstring(nsScannerSubstring& aSubstring, const nsScannerIterator& aStart, const nsScannerIterator& aEnd)
{
  aSubstring.Rebind(*mSlidingBuffer, aStart, aEnd);
}

void nsScanner::CurrentPosition(nsScannerIterator& aPosition)
{
  aPosition = mCurrentPosition;
}

void nsScanner::EndReading(nsScannerIterator& aPosition)
{
  aPosition = mEndPosition;
}
 
void nsScanner::SetPosition(nsScannerIterator& aPosition, bool aTerminate, bool aReverse)
{
  if (mSlidingBuffer) {
#ifdef DEBUG
    uint32_t origRemaining = mCountRemaining;
#endif

    if (aReverse) {
      mCountRemaining += (Distance(aPosition, mCurrentPosition));
    }
    else {
      mCountRemaining -= (Distance(mCurrentPosition, aPosition));
    }

    NS_ASSERTION((mCountRemaining >= origRemaining && aReverse) ||
                 (mCountRemaining <= origRemaining && !aReverse),
                 "Improper use of nsScanner::SetPosition. Make sure to set the"
                 " aReverse parameter correctly");

    mCurrentPosition = aPosition;
    if (aTerminate && (mCurrentPosition == mEndPosition)) {
      mMarkPosition = mCurrentPosition;
      mSlidingBuffer->DiscardPrefix(mCurrentPosition);
    }
  }
}

void nsScanner::ReplaceCharacter(nsScannerIterator& aPosition,
                                 char16_t aChar)
{
  if (mSlidingBuffer) {
    mSlidingBuffer->ReplaceCharacter(aPosition, aChar);
  }
}

bool nsScanner::AppendToBuffer(nsScannerString::Buffer* aBuf,
                                 nsIRequest *aRequest,
                                 int32_t aErrorPos)
{
  uint32_t countRemaining = mCountRemaining;
  if (!mSlidingBuffer) {
    mSlidingBuffer = new nsScannerString(aBuf);
    if (!mSlidingBuffer)
      return false;
    mSlidingBuffer->BeginReading(mCurrentPosition);
    mMarkPosition = mCurrentPosition;
    mSlidingBuffer->EndReading(mEndPosition);
    mCountRemaining = aBuf->DataLength();
  }
  else {
    mSlidingBuffer->AppendBuffer(aBuf);
    if (mCurrentPosition == mEndPosition) {
      mSlidingBuffer->BeginReading(mCurrentPosition);
    }
    mSlidingBuffer->EndReading(mEndPosition);
    mCountRemaining += aBuf->DataLength();
  }

  if (aErrorPos != -1 && !mHasInvalidCharacter) {
    mHasInvalidCharacter = true;
    mFirstInvalidPosition = mCurrentPosition;
    mFirstInvalidPosition.advance(countRemaining + aErrorPos);
  }

  if (mFirstNonWhitespacePosition == -1) {
    nsScannerIterator iter(mCurrentPosition);
    nsScannerIterator end(mEndPosition);

    while (iter != end) {
      if (!nsCRT::IsAsciiSpace(*iter)) {
        mFirstNonWhitespacePosition = Distance(mCurrentPosition, iter);

        break;
      }

      ++iter;
    }
  }
  return true;
}

/**
 *  call this to copy bytes out of the scanner that have not yet been consumed
 *  by the tokenization process.
 *  
 *  @update  gess 5/12/98
 *  @param   aCopyBuffer is where the scanner buffer will be copied to
 *  @return  nada
 */
void nsScanner::CopyUnusedData(nsString& aCopyBuffer) {
  if (!mSlidingBuffer) {
    aCopyBuffer.Truncate();
    return;
  }

  nsScannerIterator start, end;
  start = mCurrentPosition;
  end = mEndPosition;

  CopyUnicodeTo(start, end, aCopyBuffer);
}

/**
 *  Retrieve the name of the file that the scanner is reading from.
 *  In some cases, it's just a given name, because the scanner isn't
 *  really reading from a file.
 *  
 *  @update  gess 5/12/98
 *  @return  
 */
nsString& nsScanner::GetFilename(void) {
  return mFilename;
}

/**
 *  Conduct self test. Actually, selftesting for this class
 *  occurs in the parser selftest.
 *  
 *  @update  gess 3/25/98
 *  @param   
 *  @return  
 */

void nsScanner::SelfTest(void) {
#ifdef _DEBUG
#endif
}

void nsScanner::OverrideReplacementCharacter(char16_t aReplacementCharacter)
{
  mReplacementCharacter = aReplacementCharacter;

  if (mHasInvalidCharacter) {
    ReplaceCharacter(mFirstInvalidPosition, mReplacementCharacter);
  }
}