aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/llvm16/lib/Support/ConvertUTF.cpp
blob: bc04c5ab5113563fb82d7b3b168985369b611f4b (plain) (blame)
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
/*===--- ConvertUTF.c - Universal Character Names conversions ---------------===
 *
 * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 * See https://llvm.org/LICENSE.txt for license information.
 * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===------------------------------------------------------------------------=*/
/*
 * Copyright © 1991-2015 Unicode, Inc. All rights reserved.
 * Distributed under the Terms of Use in
 * http://www.unicode.org/copyright.html.
 *
 * Permission is hereby granted, free of charge, to any person obtaining
 * a copy of the Unicode data files and any associated documentation
 * (the "Data Files") or Unicode software and any associated documentation
 * (the "Software") to deal in the Data Files or Software
 * without restriction, including without limitation the rights to use,
 * copy, modify, merge, publish, distribute, and/or sell copies of
 * the Data Files or Software, and to permit persons to whom the Data Files
 * or Software are furnished to do so, provided that
 * (a) this copyright and permission notice appear with all copies
 * of the Data Files or Software,
 * (b) this copyright and permission notice appear in associated
 * documentation, and
 * (c) there is clear notice in each modified Data File or in the Software
 * as well as in the documentation associated with the Data File(s) or
 * Software that the data or software has been modified.
 *
 * THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF
 * ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE
 * WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT OF THIRD PARTY RIGHTS.
 * IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS INCLUDED IN THIS
 * NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL
 * DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE,
 * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
 * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
 * PERFORMANCE OF THE DATA FILES OR SOFTWARE.
 *
 * Except as contained in this notice, the name of a copyright holder
 * shall not be used in advertising or otherwise to promote the sale,
 * use or other dealings in these Data Files or Software without prior
 * written authorization of the copyright holder.
 */

/* ---------------------------------------------------------------------

    Conversions between UTF32, UTF-16, and UTF-8. Source code file.
    Author: Mark E. Davis, 1994.
    Rev History: Rick McGowan, fixes & updates May 2001.
    Sept 2001: fixed const & error conditions per
        mods suggested by S. Parent & A. Lillich.
    June 2002: Tim Dodd added detection and handling of incomplete
        source sequences, enhanced error detection, added casts
        to eliminate compiler warnings.
    July 2003: slight mods to back out aggressive FFFE detection.
    Jan 2004: updated switches in from-UTF8 conversions.
    Oct 2004: updated to use UNI_MAX_LEGAL_UTF32 in UTF-32 conversions.

    See the header file "ConvertUTF.h" for complete documentation.

------------------------------------------------------------------------ */

#include "llvm/Support/ConvertUTF.h"
#ifdef CVTUTF_DEBUG
#include <stdio.h>
#endif
#include <assert.h>

/*
 * This code extensively uses fall-through switches.
 * Keep the compiler from warning about that.
 */
#if defined(__clang__) && defined(__has_warning)
# if __has_warning("-Wimplicit-fallthrough")
#  define ConvertUTF_DISABLE_WARNINGS \
    _Pragma("clang diagnostic push")  \
    _Pragma("clang diagnostic ignored \"-Wimplicit-fallthrough\"")
#  define ConvertUTF_RESTORE_WARNINGS \
    _Pragma("clang diagnostic pop")
# endif
#elif defined(__GNUC__) && __GNUC__ > 6
# define ConvertUTF_DISABLE_WARNINGS \
   _Pragma("GCC diagnostic push")    \
   _Pragma("GCC diagnostic ignored \"-Wimplicit-fallthrough\"")
# define ConvertUTF_RESTORE_WARNINGS \
   _Pragma("GCC diagnostic pop")
#endif
#ifndef ConvertUTF_DISABLE_WARNINGS
# define ConvertUTF_DISABLE_WARNINGS
#endif
#ifndef ConvertUTF_RESTORE_WARNINGS
# define ConvertUTF_RESTORE_WARNINGS
#endif

ConvertUTF_DISABLE_WARNINGS

namespace llvm {

static const int halfShift  = 10; /* used for shifting by 10 bits */

static const UTF32 halfBase = 0x0010000UL;
static const UTF32 halfMask = 0x3FFUL;

#define UNI_SUR_HIGH_START  (UTF32)0xD800
#define UNI_SUR_HIGH_END    (UTF32)0xDBFF
#define UNI_SUR_LOW_START   (UTF32)0xDC00
#define UNI_SUR_LOW_END     (UTF32)0xDFFF

/* --------------------------------------------------------------------- */

/*
 * Index into the table below with the first byte of a UTF-8 sequence to
 * get the number of trailing bytes that are supposed to follow it.
 * Note that *legal* UTF-8 values can't have 4 or 5-bytes. The table is
 * left as-is for anyone who may want to do such conversion, which was
 * allowed in earlier algorithms.
 */
static const char trailingBytesForUTF8[256] = {
    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5
};

/*
 * Magic values subtracted from a buffer value during UTF8 conversion.
 * This table contains as many values as there might be trailing bytes
 * in a UTF-8 sequence.
 */
static const UTF32 offsetsFromUTF8[6] = { 0x00000000UL, 0x00003080UL, 0x000E2080UL,
                     0x03C82080UL, 0xFA082080UL, 0x82082080UL };

/*
 * Once the bits are split out into bytes of UTF-8, this is a mask OR-ed
 * into the first byte, depending on how many bytes follow.  There are
 * as many entries in this table as there are UTF-8 sequence types.
 * (I.e., one byte sequence, two byte... etc.). Remember that sequencs
 * for *legal* UTF-8 will be 4 or fewer bytes total.
 */
static const UTF8 firstByteMark[7] = { 0x00, 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC };

/* --------------------------------------------------------------------- */

/* The interface converts a whole buffer to avoid function-call overhead.
 * Constants have been gathered. Loops & conditionals have been removed as
 * much as possible for efficiency, in favor of drop-through switches.
 * (See "Note A" at the bottom of the file for equivalent code.)
 * If your compiler supports it, the "isLegalUTF8" call can be turned
 * into an inline function.
 */


/* --------------------------------------------------------------------- */

ConversionResult ConvertUTF32toUTF16 (
        const UTF32** sourceStart, const UTF32* sourceEnd,
        UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags) {
    ConversionResult result = conversionOK;
    const UTF32* source = *sourceStart;
    UTF16* target = *targetStart;
    while (source < sourceEnd) {
        UTF32 ch;
        if (target >= targetEnd) {
            result = targetExhausted; break;
        }
        ch = *source++;
        if (ch <= UNI_MAX_BMP) { /* Target is a character <= 0xFFFF */
            /* UTF-16 surrogate values are illegal in UTF-32; 0xffff or 0xfffe are both reserved values */
            if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_LOW_END) {
                if (flags == strictConversion) {
                    --source; /* return to the illegal value itself */
                    result = sourceIllegal;
                    break;
                } else {
                    *target++ = UNI_REPLACEMENT_CHAR;
                }
            } else {
                *target++ = (UTF16)ch; /* normal case */
            }
        } else if (ch > UNI_MAX_LEGAL_UTF32) {
            if (flags == strictConversion) {
                result = sourceIllegal;
            } else {
                *target++ = UNI_REPLACEMENT_CHAR;
            }
        } else {
            /* target is a character in range 0xFFFF - 0x10FFFF. */
            if (target + 1 >= targetEnd) {
                --source; /* Back up source pointer! */
                result = targetExhausted; break;
            }
            ch -= halfBase;
            *target++ = (UTF16)((ch >> halfShift) + UNI_SUR_HIGH_START);
            *target++ = (UTF16)((ch & halfMask) + UNI_SUR_LOW_START);
        }
    }
    *sourceStart = source;
    *targetStart = target;
    return result;
}

/* --------------------------------------------------------------------- */

ConversionResult ConvertUTF16toUTF32 (
        const UTF16** sourceStart, const UTF16* sourceEnd,
        UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags) {
    ConversionResult result = conversionOK;
    const UTF16* source = *sourceStart;
    UTF32* target = *targetStart;
    UTF32 ch, ch2;
    while (source < sourceEnd) {
        const UTF16* oldSource = source; /*  In case we have to back up because of target overflow. */
        ch = *source++;
        /* If we have a surrogate pair, convert to UTF32 first. */
        if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_HIGH_END) {
            /* If the 16 bits following the high surrogate are in the source buffer... */
            if (source < sourceEnd) {
                ch2 = *source;
                /* If it's a low surrogate, convert to UTF32. */
                if (ch2 >= UNI_SUR_LOW_START && ch2 <= UNI_SUR_LOW_END) {
                    ch = ((ch - UNI_SUR_HIGH_START) << halfShift)
                        + (ch2 - UNI_SUR_LOW_START) + halfBase;
                    ++source;
                } else if (flags == strictConversion) { /* it's an unpaired high surrogate */
                    --source; /* return to the illegal value itself */
                    result = sourceIllegal;
                    break;
                }
            } else { /* We don't have the 16 bits following the high surrogate. */
                --source; /* return to the high surrogate */
                result = sourceExhausted;
                break;
            }
        } else if (flags == strictConversion) {
            /* UTF-16 surrogate values are illegal in UTF-32 */
            if (ch >= UNI_SUR_LOW_START && ch <= UNI_SUR_LOW_END) {
                --source; /* return to the illegal value itself */
                result = sourceIllegal;
                break;
            }
        }
        if (target >= targetEnd) {
            source = oldSource; /* Back up source pointer! */
            result = targetExhausted; break;
        }
        *target++ = ch;
    }
    *sourceStart = source;
    *targetStart = target;
#ifdef CVTUTF_DEBUG
if (result == sourceIllegal) {
    fprintf(stderr, "ConvertUTF16toUTF32 illegal seq 0x%04x,%04x\n", ch, ch2);
    fflush(stderr);
}
#endif
    return result;
}
ConversionResult ConvertUTF16toUTF8 (
        const UTF16** sourceStart, const UTF16* sourceEnd,
        UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags) {
    ConversionResult result = conversionOK;
    const UTF16* source = *sourceStart;
    UTF8* target = *targetStart;
    while (source < sourceEnd) {
        UTF32 ch;
        unsigned short bytesToWrite = 0;
        const UTF32 byteMask = 0xBF;
        const UTF32 byteMark = 0x80;
        const UTF16* oldSource = source; /* In case we have to back up because of target overflow. */
        ch = *source++;
        /* If we have a surrogate pair, convert to UTF32 first. */
        if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_HIGH_END) {
            /* If the 16 bits following the high surrogate are in the source buffer... */
            if (source < sourceEnd) {
                UTF32 ch2 = *source;
                /* If it's a low surrogate, convert to UTF32. */
                if (ch2 >= UNI_SUR_LOW_START && ch2 <= UNI_SUR_LOW_END) {
                    ch = ((ch - UNI_SUR_HIGH_START) << halfShift)
                        + (ch2 - UNI_SUR_LOW_START) + halfBase;
                    ++source;
                } else if (flags == strictConversion) { /* it's an unpaired high surrogate */
                    --source; /* return to the illegal value itself */
                    result = sourceIllegal;
                    break;
                }
            } else { /* We don't have the 16 bits following the high surrogate. */
                --source; /* return to the high surrogate */
                result = sourceExhausted;
                break;
            }
        } else if (flags == strictConversion) {
            /* UTF-16 surrogate values are illegal in UTF-32 */
            if (ch >= UNI_SUR_LOW_START && ch <= UNI_SUR_LOW_END) {
                --source; /* return to the illegal value itself */
                result = sourceIllegal;
                break;
            }
        }
        /* Figure out how many bytes the result will require */
        if (ch < (UTF32)0x80) {      bytesToWrite = 1;
        } else if (ch < (UTF32)0x800) {     bytesToWrite = 2;
        } else if (ch < (UTF32)0x10000) {   bytesToWrite = 3;
        } else if (ch < (UTF32)0x110000) {  bytesToWrite = 4;
        } else {                            bytesToWrite = 3;
                                            ch = UNI_REPLACEMENT_CHAR;
        }

        target += bytesToWrite;
        if (target > targetEnd) {
            source = oldSource; /* Back up source pointer! */
            target -= bytesToWrite; result = targetExhausted; break;
        }
        switch (bytesToWrite) { /* note: everything falls through. */
            case 4: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
            case 3: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
            case 2: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
            case 1: *--target =  (UTF8)(ch | firstByteMark[bytesToWrite]);
        }
        target += bytesToWrite;
    }
    *sourceStart = source;
    *targetStart = target;
    return result;
}

/* --------------------------------------------------------------------- */

ConversionResult ConvertUTF32toUTF8 (
        const UTF32** sourceStart, const UTF32* sourceEnd,
        UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags) {
    ConversionResult result = conversionOK;
    const UTF32* source = *sourceStart;
    UTF8* target = *targetStart;
    while (source < sourceEnd) {
        UTF32 ch;
        unsigned short bytesToWrite = 0;
        const UTF32 byteMask = 0xBF;
        const UTF32 byteMark = 0x80;
        ch = *source++;
        if (flags == strictConversion ) {
            /* UTF-16 surrogate values are illegal in UTF-32 */
            if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_LOW_END) {
                --source; /* return to the illegal value itself */
                result = sourceIllegal;
                break;
            }
        }
        /*
         * Figure out how many bytes the result will require. Turn any
         * illegally large UTF32 things (> Plane 17) into replacement chars.
         */
        if (ch < (UTF32)0x80) {      bytesToWrite = 1;
        } else if (ch < (UTF32)0x800) {     bytesToWrite = 2;
        } else if (ch < (UTF32)0x10000) {   bytesToWrite = 3;
        } else if (ch <= UNI_MAX_LEGAL_UTF32) {  bytesToWrite = 4;
        } else {                            bytesToWrite = 3;
                                            ch = UNI_REPLACEMENT_CHAR;
                                            result = sourceIllegal;
        }

        target += bytesToWrite;
        if (target > targetEnd) {
            --source; /* Back up source pointer! */
            target -= bytesToWrite; result = targetExhausted; break;
        }
        switch (bytesToWrite) { /* note: everything falls through. */
            case 4: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
            case 3: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
            case 2: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
            case 1: *--target = (UTF8) (ch | firstByteMark[bytesToWrite]);
        }
        target += bytesToWrite;
    }
    *sourceStart = source;
    *targetStart = target;
    return result;
}

/* --------------------------------------------------------------------- */

/*
 * Utility routine to tell whether a sequence of bytes is legal UTF-8.
 * This must be called with the length pre-determined by the first byte.
 * If not calling this from ConvertUTF8to*, then the length can be set by:
 *  length = trailingBytesForUTF8[*source]+1;
 * and the sequence is illegal right away if there aren't that many bytes
 * available.
 * If presented with a length > 4, this returns false.  The Unicode
 * definition of UTF-8 goes up to 4-byte sequences.
 */

static Boolean isLegalUTF8(const UTF8 *source, int length) {
    UTF8 a;
    const UTF8 *srcptr = source+length;
    switch (length) {
    default: return false;
        /* Everything else falls through when "true"... */
    case 4: if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return false;
    case 3: if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return false;
    case 2: if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return false;

        switch (*source) {
            /* no fall-through in this inner switch */
            case 0xE0: if (a < 0xA0) return false; break;
            case 0xED: if (a > 0x9F) return false; break;
            case 0xF0: if (a < 0x90) return false; break;
            case 0xF4: if (a > 0x8F) return false; break;
            default:   if (a < 0x80) return false;
        }

    case 1: if (*source >= 0x80 && *source < 0xC2) return false;
    }
    if (*source > 0xF4) return false;
    return true;
}

/* --------------------------------------------------------------------- */

/*
 * Exported function to return whether a UTF-8 sequence is legal or not.
 * This is not used here; it's just exported.
 */
Boolean isLegalUTF8Sequence(const UTF8 *source, const UTF8 *sourceEnd) {
    int length = trailingBytesForUTF8[*source]+1;
    if (length > sourceEnd - source) {
        return false;
    }
    return isLegalUTF8(source, length);
}

/*
 * Exported function to return the size of the first utf-8 code unit sequence,
 * Or 0 if the sequence is not valid;
 */
unsigned getUTF8SequenceSize(const UTF8 *source, const UTF8 *sourceEnd) {
  int length = trailingBytesForUTF8[*source] + 1;
  return (length <= sourceEnd - source && isLegalUTF8(source, length)) ? length
                                                                       : 0;
}

/* --------------------------------------------------------------------- */

static unsigned
findMaximalSubpartOfIllFormedUTF8Sequence(const UTF8 *source,
                                          const UTF8 *sourceEnd) {
  UTF8 b1, b2, b3;

  assert(!isLegalUTF8Sequence(source, sourceEnd));

  /*
   * Unicode 6.3.0, D93b:
   *
   *   Maximal subpart of an ill-formed subsequence: The longest code unit
   *   subsequence starting at an unconvertible offset that is either:
   *   a. the initial subsequence of a well-formed code unit sequence, or
   *   b. a subsequence of length one.
   */

  if (source == sourceEnd)
    return 0;

  /*
   * Perform case analysis.  See Unicode 6.3.0, Table 3-7. Well-Formed UTF-8
   * Byte Sequences.
   */

  b1 = *source;
  ++source;
  if (b1 >= 0xC2 && b1 <= 0xDF) {
    /*
     * First byte is valid, but we know that this code unit sequence is
     * invalid, so the maximal subpart has to end after the first byte.
     */
    return 1;
  }

  if (source == sourceEnd)
    return 1;

  b2 = *source;
  ++source;

  if (b1 == 0xE0) {
    return (b2 >= 0xA0 && b2 <= 0xBF) ? 2 : 1;
  }
  if (b1 >= 0xE1 && b1 <= 0xEC) {
    return (b2 >= 0x80 && b2 <= 0xBF) ? 2 : 1;
  }
  if (b1 == 0xED) {
    return (b2 >= 0x80 && b2 <= 0x9F) ? 2 : 1;
  }
  if (b1 >= 0xEE && b1 <= 0xEF) {
    return (b2 >= 0x80 && b2 <= 0xBF) ? 2 : 1;
  }
  if (b1 == 0xF0) {
    if (b2 >= 0x90 && b2 <= 0xBF) {
      if (source == sourceEnd)
        return 2;

      b3 = *source;
      return (b3 >= 0x80 && b3 <= 0xBF) ? 3 : 2;
    }
    return 1;
  }
  if (b1 >= 0xF1 && b1 <= 0xF3) {
    if (b2 >= 0x80 && b2 <= 0xBF) {
      if (source == sourceEnd)
        return 2;

      b3 = *source;
      return (b3 >= 0x80 && b3 <= 0xBF) ? 3 : 2;
    }
    return 1;
  }
  if (b1 == 0xF4) {
    if (b2 >= 0x80 && b2 <= 0x8F) {
      if (source == sourceEnd)
        return 2;

      b3 = *source;
      return (b3 >= 0x80 && b3 <= 0xBF) ? 3 : 2;
    }
    return 1;
  }

  assert((b1 >= 0x80 && b1 <= 0xC1) || b1 >= 0xF5);
  /*
   * There are no valid sequences that start with these bytes.  Maximal subpart
   * is defined to have length 1 in these cases.
   */
  return 1;
}

/* --------------------------------------------------------------------- */

/*
 * Exported function to return the total number of bytes in a codepoint
 * represented in UTF-8, given the value of the first byte.
 */
unsigned getNumBytesForUTF8(UTF8 first) {
  return trailingBytesForUTF8[first] + 1;
}

/* --------------------------------------------------------------------- */

/*
 * Exported function to return whether a UTF-8 string is legal or not.
 * This is not used here; it's just exported.
 */
Boolean isLegalUTF8String(const UTF8 **source, const UTF8 *sourceEnd) {
    while (*source != sourceEnd) {
        int length = trailingBytesForUTF8[**source] + 1;
        if (length > sourceEnd - *source || !isLegalUTF8(*source, length))
            return false;
        *source += length;
    }
    return true;
}

/* --------------------------------------------------------------------- */

ConversionResult ConvertUTF8toUTF16 (
        const UTF8** sourceStart, const UTF8* sourceEnd,
        UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags) {
    ConversionResult result = conversionOK;
    const UTF8* source = *sourceStart;
    UTF16* target = *targetStart;
    while (source < sourceEnd) {
        UTF32 ch = 0;
        unsigned short extraBytesToRead = trailingBytesForUTF8[*source];
        if (extraBytesToRead >= sourceEnd - source) {
            result = sourceExhausted; break;
        }
        /* Do this check whether lenient or strict */
        if (!isLegalUTF8(source, extraBytesToRead+1)) {
            result = sourceIllegal;
            break;
        }
        /*
         * The cases all fall through. See "Note A" below.
         */
        switch (extraBytesToRead) {
            case 5: ch += *source++; ch <<= 6; /* remember, illegal UTF-8 */
            case 4: ch += *source++; ch <<= 6; /* remember, illegal UTF-8 */
            case 3: ch += *source++; ch <<= 6;
            case 2: ch += *source++; ch <<= 6;
            case 1: ch += *source++; ch <<= 6;
            case 0: ch += *source++;
        }
        ch -= offsetsFromUTF8[extraBytesToRead];

        if (target >= targetEnd) {
            source -= (extraBytesToRead+1); /* Back up source pointer! */
            result = targetExhausted; break;
        }
        if (ch <= UNI_MAX_BMP) { /* Target is a character <= 0xFFFF */
            /* UTF-16 surrogate values are illegal in UTF-32 */
            if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_LOW_END) {
                if (flags == strictConversion) {
                    source -= (extraBytesToRead+1); /* return to the illegal value itself */
                    result = sourceIllegal;
                    break;
                } else {
                    *target++ = UNI_REPLACEMENT_CHAR;
                }
            } else {
                *target++ = (UTF16)ch; /* normal case */
            }
        } else if (ch > UNI_MAX_UTF16) {
            if (flags == strictConversion) {
                result = sourceIllegal;
                source -= (extraBytesToRead+1); /* return to the start */
                break; /* Bail out; shouldn't continue */
            } else {
                *target++ = UNI_REPLACEMENT_CHAR;
            }
        } else {
            /* target is a character in range 0xFFFF - 0x10FFFF. */
            if (target + 1 >= targetEnd) {
                source -= (extraBytesToRead+1); /* Back up source pointer! */
                result = targetExhausted; break;
            }
            ch -= halfBase;
            *target++ = (UTF16)((ch >> halfShift) + UNI_SUR_HIGH_START);
            *target++ = (UTF16)((ch & halfMask) + UNI_SUR_LOW_START);
        }
    }
    *sourceStart = source;
    *targetStart = target;
    return result;
}

/* --------------------------------------------------------------------- */

static ConversionResult ConvertUTF8toUTF32Impl(
        const UTF8** sourceStart, const UTF8* sourceEnd,
        UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags,
        Boolean InputIsPartial) {
    ConversionResult result = conversionOK;
    const UTF8* source = *sourceStart;
    UTF32* target = *targetStart;
    while (source < sourceEnd) {
        UTF32 ch = 0;
        unsigned short extraBytesToRead = trailingBytesForUTF8[*source];
        if (extraBytesToRead >= sourceEnd - source) {
            if (flags == strictConversion || InputIsPartial) {
                result = sourceExhausted;
                break;
            } else {
                result = sourceIllegal;

                /*
                 * Replace the maximal subpart of ill-formed sequence with
                 * replacement character.
                 */
                source += findMaximalSubpartOfIllFormedUTF8Sequence(source,
                                                                    sourceEnd);
                *target++ = UNI_REPLACEMENT_CHAR;
                continue;
            }
        }
        if (target >= targetEnd) {
            result = targetExhausted; break;
        }

        /* Do this check whether lenient or strict */
        if (!isLegalUTF8(source, extraBytesToRead+1)) {
            result = sourceIllegal;
            if (flags == strictConversion) {
                /* Abort conversion. */
                break;
            } else {
                /*
                 * Replace the maximal subpart of ill-formed sequence with
                 * replacement character.
                 */
                source += findMaximalSubpartOfIllFormedUTF8Sequence(source,
                                                                    sourceEnd);
                *target++ = UNI_REPLACEMENT_CHAR;
                continue;
            }
        }
        /*
         * The cases all fall through. See "Note A" below.
         */
        switch (extraBytesToRead) {
            case 5: ch += *source++; ch <<= 6;
            case 4: ch += *source++; ch <<= 6;
            case 3: ch += *source++; ch <<= 6;
            case 2: ch += *source++; ch <<= 6;
            case 1: ch += *source++; ch <<= 6;
            case 0: ch += *source++;
        }
        ch -= offsetsFromUTF8[extraBytesToRead];

        if (ch <= UNI_MAX_LEGAL_UTF32) {
            /*
             * UTF-16 surrogate values are illegal in UTF-32, and anything
             * over Plane 17 (> 0x10FFFF) is illegal.
             */
            if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_LOW_END) {
                if (flags == strictConversion) {
                    source -= (extraBytesToRead+1); /* return to the illegal value itself */
                    result = sourceIllegal;
                    break;
                } else {
                    *target++ = UNI_REPLACEMENT_CHAR;
                }
            } else {
                *target++ = ch;
            }
        } else { /* i.e., ch > UNI_MAX_LEGAL_UTF32 */
            result = sourceIllegal;
            *target++ = UNI_REPLACEMENT_CHAR;
        }
    }
    *sourceStart = source;
    *targetStart = target;
    return result;
}

ConversionResult ConvertUTF8toUTF32Partial(const UTF8 **sourceStart,
                                           const UTF8 *sourceEnd,
                                           UTF32 **targetStart,
                                           UTF32 *targetEnd,
                                           ConversionFlags flags) {
  return ConvertUTF8toUTF32Impl(sourceStart, sourceEnd, targetStart, targetEnd,
                                flags, /*InputIsPartial=*/true);
}

ConversionResult ConvertUTF8toUTF32(const UTF8 **sourceStart,
                                    const UTF8 *sourceEnd, UTF32 **targetStart,
                                    UTF32 *targetEnd, ConversionFlags flags) {
  return ConvertUTF8toUTF32Impl(sourceStart, sourceEnd, targetStart, targetEnd,
                                flags, /*InputIsPartial=*/false);
}

/* ---------------------------------------------------------------------

    Note A.
    The fall-through switches in UTF-8 reading code save a
    temp variable, some decrements & conditionals.  The switches
    are equivalent to the following loop:
        {
            int tmpBytesToRead = extraBytesToRead+1;
            do {
                ch += *source++;
                --tmpBytesToRead;
                if (tmpBytesToRead) ch <<= 6;
            } while (tmpBytesToRead > 0);
        }
    In UTF-8 writing code, the switches on "bytesToWrite" are
    similarly unrolled loops.

   --------------------------------------------------------------------- */

} // namespace llvm

ConvertUTF_RESTORE_WARNINGS