This file is indexed.

/usr/include/firefox/nsUTF8Utils.h is in firefox-dev 11.0+build1-0ubuntu4.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  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
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* ***** BEGIN LICENSE BLOCK *****
 * Version: MPL 1.1/GPL 2.0/LGPL 2.1
 *
 * The contents of this file are subject to the Mozilla Public License Version
 * 1.1 (the "License"); you may not use this file except in compliance with
 * the License. You may obtain a copy of the License at
 * http://www.mozilla.org/MPL/
 *
 * Software distributed under the License is distributed on an "AS IS" basis,
 * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
 * for the specific language governing rights and limitations under the
 * License.
 *
 * The Original Code is mozilla.org code.
 *
 * The Initial Developer of the Original Code is
 * Netscape Communications Corporation.
 * Portions created by the Initial Developer are Copyright (C) 2001
 * the Initial Developer. All Rights Reserved.
 *
 * Contributor(s):
 *   Peter Annema <jaggernaut@netscape.com> (original author)
 *
 * Alternatively, the contents of this file may be used under the terms of
 * either of the GNU General Public License Version 2 or later (the "GPL"),
 * or the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
 * in which case the provisions of the GPL or the LGPL are applicable instead
 * of those above. If you wish to allow use of your version of this file only
 * under the terms of either the GPL or the LGPL, and not to allow others to
 * use your version of this file under the terms of the MPL, indicate your
 * decision by deleting the provisions above and replace them with the notice
 * and other provisions required by the GPL or the LGPL. If you do not delete
 * the provisions above, a recipient may use your version of this file under
 * the terms of any one of the MPL, the GPL or the LGPL.
 *
 * ***** END LICENSE BLOCK ***** */
#ifndef nsUTF8Utils_h_
#define nsUTF8Utils_h_

// This file may be used in two ways: if MOZILLA_INTERNAL_API is defined, this
// file will provide signatures for the Mozilla abstract string types. It will
// use XPCOM assertion/debugging macros, etc.

#include "nscore.h"
#include "mozilla/SSE.h"

#include "nsCharTraits.h"

class UTF8traits
  {
    public:
      static bool isASCII(char c) { return (c & 0x80) == 0x00; }
      static bool isInSeq(char c) { return (c & 0xC0) == 0x80; }
      static bool is2byte(char c) { return (c & 0xE0) == 0xC0; }
      static bool is3byte(char c) { return (c & 0xF0) == 0xE0; }
      static bool is4byte(char c) { return (c & 0xF8) == 0xF0; }
      static bool is5byte(char c) { return (c & 0xFC) == 0xF8; }
      static bool is6byte(char c) { return (c & 0xFE) == 0xFC; }
  };

/**
 * Extract the next UCS-4 character from the buffer and return it.  The
 * pointer passed in is advanced to the start of the next character in the
 * buffer.  If non-null, the parameters err and overlong are filled in to
 * indicate that the character was represented by an overlong sequence, or
 * that an error occurred.
 */

class UTF8CharEnumerator
{
public:
  static PRUint32 NextChar(const char **buffer, const char *end,
                           bool *err)
  {
    NS_ASSERTION(buffer && *buffer, "null buffer!");

    const char *p = *buffer;
    *err = false;

    if (p >= end)
      {
        *err = true;

        return 0;
      }

    char c = *p++;

    if ( UTF8traits::isASCII(c) )
      {
        *buffer = p;
        return c;
      }

    PRUint32 ucs4;
    PRUint32 minUcs4;
    PRInt32 state = 0;

    if (!CalcState(c, ucs4, minUcs4, state)) {
        NS_ERROR("Not a UTF-8 string. This code should only be used for converting from known UTF-8 strings.");
        *err = true;

        return 0;
    }

    while ( state-- )
      {
        if (p == end)
          {
            *err = true;

            return 0;
          }

        c = *p++;

        if (!AddByte(c, state, ucs4))
          {
            *err = true;

            return 0;
          }
      }

      if ( ucs4 < minUcs4 )
        {
          // Overlong sequence
          ucs4 = UCS2_REPLACEMENT_CHAR;
        }
      else if ( ucs4 >= 0xD800 &&
                (ucs4 <= 0xDFFF || ucs4 >= UCS_END))
        {
          // Surrogates and code points outside the Unicode range.
          ucs4 = UCS2_REPLACEMENT_CHAR;
        }

    *buffer = p;
    return ucs4;
  }

private:
  static bool CalcState(char c, PRUint32& ucs4, PRUint32& minUcs4,
                          PRInt32& state)
  {
    if ( UTF8traits::is2byte(c) )
      {
        ucs4 = (PRUint32(c) << 6) & 0x000007C0L;
        state = 1;
        minUcs4 = 0x00000080;
      }
    else if ( UTF8traits::is3byte(c) )
      {
        ucs4 = (PRUint32(c) << 12) & 0x0000F000L;
        state = 2;
        minUcs4 = 0x00000800;
      }
    else if ( UTF8traits::is4byte(c) )
      {
        ucs4 = (PRUint32(c) << 18) & 0x001F0000L;
        state = 3;
        minUcs4 = 0x00010000;
      }
    else if ( UTF8traits::is5byte(c) )
      {
        ucs4 = (PRUint32(c) << 24) & 0x03000000L;
        state = 4;
        minUcs4 = 0x00200000;
      }
    else if ( UTF8traits::is6byte(c) )
      {
        ucs4 = (PRUint32(c) << 30) & 0x40000000L;
        state = 5;
        minUcs4 = 0x04000000;
      }
    else
      {
        return false;
      }

    return true;
  }

  static bool AddByte(char c, PRInt32 state, PRUint32& ucs4)
  {
    if ( UTF8traits::isInSeq(c) )
      {
        PRInt32 shift = state * 6;
        ucs4 |= (PRUint32(c) & 0x3F) << shift;
        return true;
      }

    return false;
  }
};


/**
 * Extract the next UCS-4 character from the buffer and return it.  The
 * pointer passed in is advanced to the start of the next character in the
 * buffer.  If non-null, the err parameter is filled in if an error occurs.
 */


class UTF16CharEnumerator
{
public:
  static PRUint32 NextChar(const PRUnichar **buffer, const PRUnichar *end,
                           bool *err = nsnull)
  {
    NS_ASSERTION(buffer && *buffer, "null buffer!");

    const PRUnichar *p = *buffer;

    if (p >= end)
      {
        NS_ERROR("No input to work with");
        if (err)
          *err = true;

        return 0;
      }

    PRUnichar c = *p++;

    if (!IS_SURROGATE(c)) // U+0000 - U+D7FF,U+E000 - U+FFFF
      {
        if (err)
          *err = false;
        *buffer = p;
        return c;
      }
    else if (NS_IS_HIGH_SURROGATE(c)) // U+D800 - U+DBFF
      {
        if (p == end)
          {
            // Found a high surrogate the end of the buffer. Flag this
            // as an error and return the Unicode replacement
            // character 0xFFFD.

            NS_WARNING("Unexpected end of buffer after high surrogate");

            if (err)
              *err = true;
            *buffer = p;
            return 0xFFFD;
          }

        // D800- DBFF - High Surrogate
        PRUnichar h = c;

        c = *p++;

        if (NS_IS_LOW_SURROGATE(c))
          {
            // DC00- DFFF - Low Surrogate
            // N = (H - D800) *400 + 10000 + (L - DC00)
            PRUint32 ucs4 = SURROGATE_TO_UCS4(h, c);
            if (err)
              *err = false;
            *buffer = p;
            return ucs4;
          }
        else
          {
            // Found a high surrogate followed by something other than
            // a low surrogate. Flag this as an error and return the
            // Unicode replacement character 0xFFFD.  Note that the
            // pointer to the next character points to the second 16-bit
            // value, not beyond it, as per Unicode 5.0.0 Chapter 3 C10,
            // only the first code unit of an illegal sequence must be
            // treated as an illegally terminated code unit sequence
            // (also Chapter 3 D91, "isolated [not paired and ill-formed]
            // UTF-16 code units in the range D800..DFFF are ill-formed").
            NS_WARNING("got a High Surrogate but no low surrogate");

            if (err)
              *err = true;
            *buffer = p - 1;
            return 0xFFFD;
          }
      }
    else // U+DC00 - U+DFFF
      {
        // DC00- DFFF - Low Surrogate

        // Found a low surrogate w/o a preceding high surrogate. Flag
        // this as an error and return the Unicode replacement
        // character 0xFFFD.

        NS_WARNING("got a low Surrogate but no high surrogate");
        if (err)
          *err = true;
        *buffer = p;
        return 0xFFFD;
      }

    if (err)
      *err = true;
    return 0;
  }
};


/**
 * A character sink (see |copy_string| in nsAlgorithm.h) for converting
 * UTF-8 to UTF-16
 */
class ConvertUTF8toUTF16
  {
    public:
      typedef char      value_type;
      typedef PRUnichar buffer_type;

    ConvertUTF8toUTF16( buffer_type* aBuffer )
        : mStart(aBuffer), mBuffer(aBuffer), mErrorEncountered(false) {}

    size_t Length() const { return mBuffer - mStart; }

    bool ErrorEncountered() const { return mErrorEncountered; }

    void NS_ALWAYS_INLINE write( const value_type* start, PRUint32 N )
      {
        if ( mErrorEncountered )
          return;

        // algorithm assumes utf8 units won't
        // be spread across fragments
        const value_type* p = start;
        const value_type* end = start + N;
        buffer_type* out = mBuffer;
        for ( ; p != end /* && *p */; )
          {
            bool err;
            PRUint32 ucs4 = UTF8CharEnumerator::NextChar(&p, end, &err);

            if ( err )
              {
                mErrorEncountered = true;
                mBuffer = out;
                return;
              }

            if ( ucs4 >= PLANE1_BASE )
              {
                *out++ = (buffer_type)H_SURROGATE(ucs4);
                *out++ = (buffer_type)L_SURROGATE(ucs4);
              }
            else
              {
                *out++ = ucs4;
              }
          }
        mBuffer = out;
      }

    void write_terminator()
      {
        *mBuffer = buffer_type(0);
      }

    private:
      buffer_type* const mStart;
      buffer_type* mBuffer;
      bool mErrorEncountered;
  };

/**
 * A character sink (see |copy_string| in nsAlgorithm.h) for computing
 * the length of the UTF-16 string equivalent to a UTF-8 string.
 */
class CalculateUTF8Length
  {
    public:
      typedef char value_type;

    CalculateUTF8Length() : mLength(0), mErrorEncountered(false) { }

    size_t Length() const { return mLength; }

    void NS_ALWAYS_INLINE write( const value_type* start, PRUint32 N )
      {
          // ignore any further requests
        if ( mErrorEncountered )
            return;

        // algorithm assumes utf8 units won't
        // be spread across fragments
        const value_type* p = start;
        const value_type* end = start + N;
        for ( ; p < end /* && *p */; ++mLength )
          {
            if ( UTF8traits::isASCII(*p) )
                p += 1;
            else if ( UTF8traits::is2byte(*p) )
                p += 2;
            else if ( UTF8traits::is3byte(*p) )
                p += 3;
            else if ( UTF8traits::is4byte(*p) ) {
                // Because a UTF-8 sequence of 4 bytes represents a codepoint
                // greater than 0xFFFF, it will become a surrogate pair in the
                // UTF-16 string, so add 1 more to mLength.
                // This doesn't happen with is5byte and is6byte because they
                // are illegal UTF-8 sequences (greater than 0x10FFFF) so get
                // converted to a single replacement character.

                // However, there is one case when a 4 byte UTF-8 sequence will
                // only generate 2 UTF-16 bytes. If we have a properly encoded
                // sequence, but with an invalid value (too small or too big),
                // that will result in a replacement character being written
                // This replacement character is encoded as just 1 single
                // UTF-16 character, which is 2 bytes.

                // The below code therefore only adds 1 to mLength if the UTF8
                // data will produce a decoded character which is greater than
                // or equal to 0x010000 and less than 0x0110000.

                // A 4byte UTF8 character is encoded as
                // 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
                // Bit 1-3 on the first byte, and bit 5-6 on the second byte,
                // map to bit 17-21 in the final result. If these bits are
                // between 0x01 and 0x11, that means that the final result is
                // between 0x010000 and 0x110000. The below code reads these
                // bits out and assigns them to c, but shifted up 4 bits to
                // avoid having to shift twice.

                // It doesn't matter what to do in the case where p + 4 > end
                // since no UTF16 characters will be written in that case by
                // ConvertUTF8toUTF16. Likewise it doesn't matter what we do if
                // any of the surrogate bits are wrong since no UTF16
                // characters will be written in that case either.

                if (p + 4 <= end) {
                  PRUint32 c = ((PRUint32)(p[0] & 0x07)) << 6 |
                               ((PRUint32)(p[1] & 0x30));
                  if (c >= 0x010 && c < 0x110)
                    ++mLength;
                }

                p += 4;
            }
            else if ( UTF8traits::is5byte(*p) )
                p += 5;
            else if ( UTF8traits::is6byte(*p) )
                p += 6;
            else // error
              {
                ++mLength; // to account for the decrement below
                break;
              }
          }
        if ( p != end )
          {
            NS_ERROR("Not a UTF-8 string. This code should only be used for converting from known UTF-8 strings.");
            --mLength; // The last multi-byte char wasn't complete, discard it.
            mErrorEncountered = true;
          }
      }

    private:
      size_t mLength;
      bool mErrorEncountered;
  };

/**
 * A character sink (see |copy_string| in nsAlgorithm.h) for
 * converting UTF-16 to UTF-8. Treats invalid UTF-16 data as 0xFFFD
 * (0xEFBFBD in UTF-8).
 */
class ConvertUTF16toUTF8
  {
    public:
      typedef PRUnichar value_type;
      typedef char      buffer_type;

    // The error handling here is more lenient than that in
    // |ConvertUTF8toUTF16|, but it's that way for backwards
    // compatibility.

    ConvertUTF16toUTF8( buffer_type* aBuffer )
        : mStart(aBuffer), mBuffer(aBuffer) {}

    size_t Size() const { return mBuffer - mStart; }

    void NS_ALWAYS_INLINE write( const value_type* start, PRUint32 N )
      {
        buffer_type *out = mBuffer; // gcc isn't smart enough to do this!

        for (const value_type *p = start, *end = start + N; p < end; ++p )
          {
            value_type c = *p;
            if (! (c & 0xFF80)) // U+0000 - U+007F
              {
                *out++ = (char)c;
              }
            else if (! (c & 0xF800)) // U+0100 - U+07FF
              {
                *out++ = 0xC0 | (char)(c >> 6);
                *out++ = 0x80 | (char)(0x003F & c);
              }
            else if (!IS_SURROGATE(c)) // U+0800 - U+D7FF,U+E000 - U+FFFF
              {
                *out++ = 0xE0 | (char)(c >> 12);
                *out++ = 0x80 | (char)(0x003F & (c >> 6));
                *out++ = 0x80 | (char)(0x003F & c );
              }
            else if (NS_IS_HIGH_SURROGATE(c)) // U+D800 - U+DBFF
              {
                // D800- DBFF - High Surrogate
                value_type h = c;

                ++p;
                if (p == end)
                  {
                    // Treat broken characters as the Unicode
                    // replacement character 0xFFFD (0xEFBFBD in
                    // UTF-8)
                    *out++ = '\xEF';
                    *out++ = '\xBF';
                    *out++ = '\xBD';

                    NS_WARNING("String ending in half a surrogate pair!");

                    break;
                  }
                c = *p;

                if (NS_IS_LOW_SURROGATE(c))
                  {
                    // DC00- DFFF - Low Surrogate
                    // N = (H - D800) *400 + 10000 + ( L - DC00 )
                    PRUint32 ucs4 = SURROGATE_TO_UCS4(h, c);

                    // 0001 0000-001F FFFF
                    *out++ = 0xF0 | (char)(ucs4 >> 18);
                    *out++ = 0x80 | (char)(0x003F & (ucs4 >> 12));
                    *out++ = 0x80 | (char)(0x003F & (ucs4 >> 6));
                    *out++ = 0x80 | (char)(0x003F & ucs4);
                  }
                else
                  {
                    // Treat broken characters as the Unicode
                    // replacement character 0xFFFD (0xEFBFBD in
                    // UTF-8)
                    *out++ = '\xEF';
                    *out++ = '\xBF';
                    *out++ = '\xBD';

                    // The pointer to the next character points to the second
                    // 16-bit value, not beyond it, as per Unicode 5.0.0
                    // Chapter 3 C10, only the first code unit of an illegal
                    // sequence must be treated as an illegally terminated
                    // code unit sequence (also Chapter 3 D91, "isolated [not
                    // paired and ill-formed] UTF-16 code units in the range
                    // D800..DFFF are ill-formed").
                    p--;

                    NS_WARNING("got a High Surrogate but no low surrogate");
                  }
              }
            else // U+DC00 - U+DFFF
              {
                // Treat broken characters as the Unicode replacement
                // character 0xFFFD (0xEFBFBD in UTF-8)
                *out++ = '\xEF';
                *out++ = '\xBF';
                *out++ = '\xBD';

                // DC00- DFFF - Low Surrogate
                NS_WARNING("got a low Surrogate but no high surrogate");
              }
          }

        mBuffer = out;
      }

    void write_terminator()
      {
        *mBuffer = buffer_type(0);
      }

    private:
      buffer_type* const mStart;
      buffer_type* mBuffer;
  };

/**
 * A character sink (see |copy_string| in nsAlgorithm.h) for computing
 * the number of bytes a UTF-16 would occupy in UTF-8. Treats invalid
 * UTF-16 data as 0xFFFD (0xEFBFBD in UTF-8).
 */
class CalculateUTF8Size
  {
    public:
      typedef PRUnichar value_type;

    CalculateUTF8Size()
      : mSize(0) { }

    size_t Size() const { return mSize; }

    void NS_ALWAYS_INLINE write( const value_type* start, PRUint32 N )
      {
        // Assume UCS2 surrogate pairs won't be spread across fragments.
        for (const value_type *p = start, *end = start + N; p < end; ++p )
          {
            value_type c = *p;
            if (! (c & 0xFF80)) // U+0000 - U+007F
              mSize += 1;
            else if (! (c & 0xF800)) // U+0100 - U+07FF
              mSize += 2;
            else if (0xD800 != (0xF800 & c)) // U+0800 - U+D7FF,U+E000 - U+FFFF
              mSize += 3;
            else if (0xD800 == (0xFC00 & c)) // U+D800 - U+DBFF
              {
                ++p;
                if (p == end)
                  {
                    // Treat broken characters as the Unicode
                    // replacement character 0xFFFD (0xEFBFBD in
                    // UTF-8)
                    mSize += 3;

                    NS_WARNING("String ending in half a surrogate pair!");

                    break;
                  }
                c = *p;

                if (0xDC00 == (0xFC00 & c))
                  mSize += 4;
                else
                  {
                    // Treat broken characters as the Unicode
                    // replacement character 0xFFFD (0xEFBFBD in
                    // UTF-8)
                    mSize += 3;

                    // The next code unit is the second 16-bit value, not
                    // the one beyond it, as per Unicode 5.0.0 Chapter 3 C10,
                    // only the first code unit of an illegal sequence must
                    // be treated as an illegally terminated code unit
                    // sequence (also Chapter 3 D91, "isolated [not paired and
                    // ill-formed] UTF-16 code units in the range D800..DFFF
                    // are ill-formed").
                    p--;

                    NS_WARNING("got a high Surrogate but no low surrogate");
                  }
              }
            else // U+DC00 - U+DFFF
              {
                // Treat broken characters as the Unicode replacement
                // character 0xFFFD (0xEFBFBD in UTF-8)
                mSize += 3;

                NS_WARNING("got a low Surrogate but no high surrogate");
              }
          }
      }

    private:
      size_t mSize;
  };

#ifdef MOZILLA_INTERNAL_API
/**
 * A character sink that performs a |reinterpret_cast|-style conversion
 * from char to PRUnichar.
 */
class LossyConvertEncoding8to16
  {
    public:
      typedef char      value_type;
      typedef char      input_type;
      typedef PRUnichar output_type;

    public:
      LossyConvertEncoding8to16( PRUnichar* aDestination ) :
        mDestination(aDestination) { }

      void
      write( const char* aSource, PRUint32 aSourceLength )
        {
#ifdef MOZILLA_MAY_SUPPORT_SSE2
          if (mozilla::supports_sse2())
            {
              write_sse2(aSource, aSourceLength);
              return;
            }
#endif
          const char* done_writing = aSource + aSourceLength;
          while ( aSource < done_writing )
            *mDestination++ = (PRUnichar)(unsigned char)(*aSource++);
        }

      void
      write_sse2( const char* aSource, PRUint32 aSourceLength );

      void
      write_terminator()
        {
          *mDestination = (PRUnichar)(0);
        }

    private:
      PRUnichar* mDestination;
  };

/**
 * A character sink that performs a |reinterpret_cast|-style conversion
 * from PRUnichar to char.
 */
class LossyConvertEncoding16to8
  {
    public:
      typedef PRUnichar value_type;
      typedef PRUnichar input_type;
      typedef char      output_type;

      LossyConvertEncoding16to8( char* aDestination ) : mDestination(aDestination) { }

      void
      write( const PRUnichar* aSource, PRUint32 aSourceLength)
        {
#ifdef MOZILLA_MAY_SUPPORT_SSE2
          if (mozilla::supports_sse2())
            {
              write_sse2(aSource, aSourceLength);
              return;
            }
#endif
            const PRUnichar* done_writing = aSource + aSourceLength;
            while ( aSource < done_writing )
              *mDestination++ = (char)(*aSource++);
        }

#ifdef MOZILLA_MAY_SUPPORT_SSE2
      void
      write_sse2( const PRUnichar* aSource, PRUint32 aSourceLength );
#endif

      void
      write_terminator()
        {
          *mDestination = '\0';
        }

    private:
      char *mDestination;
  };
#endif // MOZILLA_INTERNAL_API

#endif /* !defined(nsUTF8Utils_h_) */