jcs.org
qemu with hax to log dma reads & writes
jcs.org/2018/11/12/vfio
json: Reject invalid UTF-8 sequences
We reject bytes that can't occur in valid UTF-8 (\xC0..\xC1,
\xF5..\xFF in the lexer. That's insufficient; there's plenty of
invalid UTF-8 not containing these bytes, as demonstrated by
check-qjson:
* Malformed sequences
- Unexpected continuation bytes
- Missing continuation bytes after start bytes other than
\xC0..\xC1, \xF5..\xFD.
* Overlong sequences with start bytes other than \xC0..\xC1,
\xF5..\xFD.
* Invalid code points
Fixing this in the lexer would be bothersome. Fixing it in the parser
is straightforward, so do that.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-Id: <20180823164025.12553-23-armbru@redhat.com>
+122
-105
+1
include/qemu/unicode.h
+1
include/qemu/unicode.h
+14
-6
qobject/json-parser.c
+14
-6
qobject/json-parser.c
···
13
13
14
14
#include "qemu/osdep.h"
15
15
#include "qemu/cutils.h"
16
+
#include "qemu/unicode.h"
16
17
#include "qapi/error.h"
17
18
#include "qemu-common.h"
18
19
#include "qapi/qmp/qbool.h"
···
133
134
const char *ptr = token->str;
134
135
QString *str;
135
136
char quote;
137
+
int cp;
138
+
char *end;
139
+
ssize_t len;
140
+
char utf8_buf[5];
136
141
137
142
assert(*ptr == '"' || *ptr == '\'');
138
143
quote = *ptr++;
···
194
199
goto out;
195
200
}
196
201
} else {
197
-
char dummy[2];
198
-
199
-
dummy[0] = *ptr++;
200
-
dummy[1] = 0;
201
-
202
-
qstring_append(str, dummy);
202
+
cp = mod_utf8_codepoint(ptr, 6, &end);
203
+
if (cp <= 0) {
204
+
parse_error(ctxt, token, "invalid UTF-8 sequence in string");
205
+
goto out;
206
+
}
207
+
ptr = end;
208
+
len = mod_utf8_encode(utf8_buf, sizeof(utf8_buf), cp);
209
+
assert(len >= 0);
210
+
qstring_append(str, utf8_buf);
203
211
}
204
212
}
205
213
+45
-92
tests/check-qjson.c
+45
-92
tests/check-qjson.c
···
152
152
static void utf8_string(void)
153
153
{
154
154
/*
155
-
* FIXME Current behavior for invalid UTF-8 sequences is
156
-
* incorrect. This test expects current, incorrect results.
157
-
* They're all marked "bug:" below, and are to be replaced by
158
-
* correct ones as the bugs get fixed.
159
-
*
160
-
* The JSON parser rejects some, but not all invalid sequences.
161
-
*
162
155
* Problem: we can't easily deal with embedded U+0000. Parsing
163
156
* the JSON string "this \\u0000" is fun" yields "this \0 is fun",
164
157
* which gets misinterpreted as NUL-terminated "this ". We should
···
177
170
/* Expected unparse output, defaults to @json_in */
178
171
const char *json_out;
179
172
} test_cases[] = {
180
-
/*
181
-
* Bug markers used here:
182
-
* - bug: not rejected
183
-
* JSON parser fails to reject invalid sequence(s)
184
-
*/
185
-
186
173
/* 0 Control characters */
187
174
{
188
175
/*
···
330
317
{
331
318
/* first one beyond Unicode range: U+110000 */
332
319
"\xF4\x90\x80\x80",
333
-
"\xF4\x90\x80\x80",
320
+
NULL,
334
321
"\\uFFFD",
335
322
},
336
323
/* 3 Malformed sequences */
···
338
325
/* 3.1.1 First continuation byte */
339
326
{
340
327
"\x80",
341
-
"\x80", /* bug: not rejected */
328
+
NULL,
342
329
"\\uFFFD",
343
330
},
344
331
/* 3.1.2 Last continuation byte */
345
332
{
346
333
"\xBF",
347
-
"\xBF", /* bug: not rejected */
334
+
NULL,
348
335
"\\uFFFD",
349
336
},
350
337
/* 3.1.3 2 continuation bytes */
351
338
{
352
339
"\x80\xBF",
353
-
"\x80\xBF", /* bug: not rejected */
340
+
NULL,
354
341
"\\uFFFD\\uFFFD",
355
342
},
356
343
/* 3.1.4 3 continuation bytes */
357
344
{
358
345
"\x80\xBF\x80",
359
-
"\x80\xBF\x80", /* bug: not rejected */
346
+
NULL,
360
347
"\\uFFFD\\uFFFD\\uFFFD",
361
348
},
362
349
/* 3.1.5 4 continuation bytes */
363
350
{
364
351
"\x80\xBF\x80\xBF",
365
-
"\x80\xBF\x80\xBF", /* bug: not rejected */
352
+
NULL,
366
353
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD",
367
354
},
368
355
/* 3.1.6 5 continuation bytes */
369
356
{
370
357
"\x80\xBF\x80\xBF\x80",
371
-
"\x80\xBF\x80\xBF\x80", /* bug: not rejected */
358
+
NULL,
372
359
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD",
373
360
},
374
361
/* 3.1.7 6 continuation bytes */
375
362
{
376
363
"\x80\xBF\x80\xBF\x80\xBF",
377
-
"\x80\xBF\x80\xBF\x80\xBF", /* bug: not rejected */
364
+
NULL,
378
365
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD",
379
366
},
380
367
/* 3.1.8 7 continuation bytes */
381
368
{
382
369
"\x80\xBF\x80\xBF\x80\xBF\x80",
383
-
"\x80\xBF\x80\xBF\x80\xBF\x80", /* bug: not rejected */
370
+
NULL,
384
371
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD",
385
372
},
386
373
/* 3.1.9 Sequence of all 64 possible continuation bytes */
···
393
380
"\xA8\xA9\xAA\xAB\xAC\xAD\xAE\xAF"
394
381
"\xB0\xB1\xB2\xB3\xB4\xB5\xB6\xB7"
395
382
"\xB8\xB9\xBA\xBB\xBC\xBD\xBE\xBF",
396
-
/* bug: not rejected */
397
-
"\x80\x81\x82\x83\x84\x85\x86\x87"
398
-
"\x88\x89\x8A\x8B\x8C\x8D\x8E\x8F"
399
-
"\x90\x91\x92\x93\x94\x95\x96\x97"
400
-
"\x98\x99\x9A\x9B\x9C\x9D\x9E\x9F"
401
-
"\xA0\xA1\xA2\xA3\xA4\xA5\xA6\xA7"
402
-
"\xA8\xA9\xAA\xAB\xAC\xAD\xAE\xAF"
403
-
"\xB0\xB1\xB2\xB3\xB4\xB5\xB6\xB7"
404
-
"\xB8\xB9\xBA\xBB\xBC\xBD\xBE\xBF",
405
-
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
383
+
NULL,
406
384
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
407
385
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
408
386
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
···
410
388
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
411
389
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
412
390
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
391
+
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD",
413
392
},
414
393
/* 3.2 Lonely start characters */
415
394
/* 3.2.1 All 32 first bytes of 2-byte sequences, followed by space */
···
418
397
"\xC8 \xC9 \xCA \xCB \xCC \xCD \xCE \xCF "
419
398
"\xD0 \xD1 \xD2 \xD3 \xD4 \xD5 \xD6 \xD7 "
420
399
"\xD8 \xD9 \xDA \xDB \xDC \xDD \xDE \xDF ",
421
-
NULL, /* bug: accepted partly, see FIXME below */
400
+
NULL,
422
401
"\\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD "
423
402
"\\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD "
424
403
"\\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD "
···
428
407
{
429
408
"\xE0 \xE1 \xE2 \xE3 \xE4 \xE5 \xE6 \xE7 "
430
409
"\xE8 \xE9 \xEA \xEB \xEC \xED \xEE \xEF ",
431
-
/* bug: not rejected */
432
-
"\xE0 \xE1 \xE2 \xE3 \xE4 \xE5 \xE6 \xE7 "
433
-
"\xE8 \xE9 \xEA \xEB \xEC \xED \xEE \xEF ",
410
+
NULL,
434
411
"\\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD "
435
412
"\\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD ",
436
413
},
437
414
/* 3.2.3 All 8 first bytes of 4-byte sequences, followed by space */
438
415
{
439
416
"\xF0 \xF1 \xF2 \xF3 \xF4 \xF5 \xF6 \xF7 ",
440
-
NULL, /* bug: accepted partly, see FIXME below */
417
+
NULL,
441
418
"\\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD \\uFFFD ",
442
419
},
443
420
/* 3.2.4 All 4 first bytes of 5-byte sequences, followed by space */
···
462
439
/* 3.3.2 3-byte sequence with last byte missing (U+0000) */
463
440
{
464
441
"\xE0\x80",
465
-
"\xE0\x80", /* bug: not rejected */
442
+
NULL,
466
443
"\\uFFFD",
467
444
},
468
445
/* 3.3.3 4-byte sequence with last byte missing (U+0000) */
469
446
{
470
447
"\xF0\x80\x80",
471
-
"\xF0\x80\x80", /* bug: not rejected */
448
+
NULL,
472
449
"\\uFFFD",
473
450
},
474
451
/* 3.3.4 5-byte sequence with last byte missing (U+0000) */
···
486
463
/* 3.3.6 2-byte sequence with last byte missing (U+07FF) */
487
464
{
488
465
"\xDF",
489
-
"\xDF", /* bug: not rejected */
466
+
NULL,
490
467
"\\uFFFD",
491
468
},
492
469
/* 3.3.7 3-byte sequence with last byte missing (U+FFFF) */
493
470
{
494
471
"\xEF\xBF",
495
-
"\xEF\xBF", /* bug: not rejected */
472
+
NULL,
496
473
"\\uFFFD",
497
474
},
498
475
/* 3.3.8 4-byte sequence with last byte missing (U+1FFFFF) */
···
517
494
{
518
495
"\xC0\xE0\x80\xF0\x80\x80\xF8\x80\x80\x80\xFC\x80\x80\x80\x80"
519
496
"\xDF\xEF\xBF\xF7\xBF\xBF\xFB\xBF\xBF\xBF\xFD\xBF\xBF\xBF\xBF",
520
-
NULL, /* bug: accepted partly, see FIXME below */
497
+
NULL,
521
498
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
522
499
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD",
523
500
},
···
546
523
},
547
524
{
548
525
"\xE0\x80\xAF",
549
-
"\xE0\x80\xAF", /* bug: not rejected */
526
+
NULL,
550
527
"\\uFFFD",
551
528
},
552
529
{
553
530
"\xF0\x80\x80\xAF",
554
-
"\xF0\x80\x80\xAF", /* bug: not rejected */
531
+
NULL,
555
532
"\\uFFFD",
556
533
},
557
534
{
···
579
556
{
580
557
/* \U+07FF */
581
558
"\xE0\x9F\xBF",
582
-
"\xE0\x9F\xBF", /* bug: not rejected */
559
+
NULL,
583
560
"\\uFFFD",
584
561
},
585
562
{
···
590
567
* also 2.2.3
591
568
*/
592
569
"\xF0\x8F\xBF\xBC",
593
-
"\xF0\x8F\xBF\xBC", /* bug: not rejected */
570
+
NULL,
594
571
"\\uFFFD",
595
572
},
596
573
{
···
615
592
{
616
593
/* \U+0000 */
617
594
"\xE0\x80\x80",
618
-
"\xE0\x80\x80", /* bug: not rejected */
595
+
NULL,
619
596
"\\uFFFD",
620
597
},
621
598
{
622
599
/* \U+0000 */
623
600
"\xF0\x80\x80\x80",
624
-
"\xF0\x80\x80\x80", /* bug: not rejected */
601
+
NULL,
625
602
"\\uFFFD",
626
603
},
627
604
{
···
641
618
{
642
619
/* \U+D800 */
643
620
"\xED\xA0\x80",
644
-
"\xED\xA0\x80", /* bug: not rejected */
621
+
NULL,
645
622
"\\uFFFD",
646
623
},
647
624
{
648
625
/* \U+DB7F */
649
626
"\xED\xAD\xBF",
650
-
"\xED\xAD\xBF", /* bug: not rejected */
627
+
NULL,
651
628
"\\uFFFD",
652
629
},
653
630
{
654
631
/* \U+DB80 */
655
632
"\xED\xAE\x80",
656
-
"\xED\xAE\x80", /* bug: not rejected */
633
+
NULL,
657
634
"\\uFFFD",
658
635
},
659
636
{
660
637
/* \U+DBFF */
661
638
"\xED\xAF\xBF",
662
-
"\xED\xAF\xBF", /* bug: not rejected */
639
+
NULL,
663
640
"\\uFFFD",
664
641
},
665
642
{
666
643
/* \U+DC00 */
667
644
"\xED\xB0\x80",
668
-
"\xED\xB0\x80", /* bug: not rejected */
645
+
NULL,
669
646
"\\uFFFD",
670
647
},
671
648
{
672
649
/* \U+DF80 */
673
650
"\xED\xBE\x80",
674
-
"\xED\xBE\x80", /* bug: not rejected */
651
+
NULL,
675
652
"\\uFFFD",
676
653
},
677
654
{
678
655
/* \U+DFFF */
679
656
"\xED\xBF\xBF",
680
-
"\xED\xBF\xBF", /* bug: not rejected */
657
+
NULL,
681
658
"\\uFFFD",
682
659
},
683
660
/* 5.2 Paired UTF-16 surrogates */
684
661
{
685
662
/* \U+D800\U+DC00 */
686
663
"\xED\xA0\x80\xED\xB0\x80",
687
-
"\xED\xA0\x80\xED\xB0\x80", /* bug: not rejected */
664
+
NULL,
688
665
"\\uFFFD\\uFFFD",
689
666
},
690
667
{
691
668
/* \U+D800\U+DFFF */
692
669
"\xED\xA0\x80\xED\xBF\xBF",
693
-
"\xED\xA0\x80\xED\xBF\xBF", /* bug: not rejected */
670
+
NULL,
694
671
"\\uFFFD\\uFFFD",
695
672
},
696
673
{
697
674
/* \U+DB7F\U+DC00 */
698
675
"\xED\xAD\xBF\xED\xB0\x80",
699
-
"\xED\xAD\xBF\xED\xB0\x80", /* bug: not rejected */
676
+
NULL,
700
677
"\\uFFFD\\uFFFD",
701
678
},
702
679
{
703
680
/* \U+DB7F\U+DFFF */
704
681
"\xED\xAD\xBF\xED\xBF\xBF",
705
-
"\xED\xAD\xBF\xED\xBF\xBF", /* bug: not rejected */
682
+
NULL,
706
683
"\\uFFFD\\uFFFD",
707
684
},
708
685
{
709
686
/* \U+DB80\U+DC00 */
710
687
"\xED\xAE\x80\xED\xB0\x80",
711
-
"\xED\xAE\x80\xED\xB0\x80", /* bug: not rejected */
688
+
NULL,
712
689
"\\uFFFD\\uFFFD",
713
690
},
714
691
{
715
692
/* \U+DB80\U+DFFF */
716
693
"\xED\xAE\x80\xED\xBF\xBF",
717
-
"\xED\xAE\x80\xED\xBF\xBF", /* bug: not rejected */
694
+
NULL,
718
695
"\\uFFFD\\uFFFD",
719
696
},
720
697
{
721
698
/* \U+DBFF\U+DC00 */
722
699
"\xED\xAF\xBF\xED\xB0\x80",
723
-
"\xED\xAF\xBF\xED\xB0\x80", /* bug: not rejected */
700
+
NULL,
724
701
"\\uFFFD\\uFFFD",
725
702
},
726
703
{
727
704
/* \U+DBFF\U+DFFF */
728
705
"\xED\xAF\xBF\xED\xBF\xBF",
729
-
"\xED\xAF\xBF\xED\xBF\xBF", /* bug: not rejected */
706
+
NULL,
730
707
"\\uFFFD\\uFFFD",
731
708
},
732
709
/* 5.3 Other illegal code positions */
···
734
711
{
735
712
/* \U+FFFE */
736
713
"\xEF\xBF\xBE",
737
-
"\xEF\xBF\xBE", /* bug: not rejected */
714
+
NULL,
738
715
"\\uFFFD",
739
716
},
740
717
{
741
718
/* \U+FFFF */
742
719
"\xEF\xBF\xBF",
743
-
"\xEF\xBF\xBF", /* bug: not rejected */
720
+
NULL,
744
721
"\\uFFFD",
745
722
},
746
723
{
747
724
/* U+FDD0 */
748
725
"\xEF\xB7\x90",
749
-
"\xEF\xB7\x90", /* bug: not rejected */
726
+
NULL,
750
727
"\\uFFFD",
751
728
},
752
729
{
753
730
/* U+FDEF */
754
731
"\xEF\xB7\xAF",
755
-
"\xEF\xB7\xAF", /* bug: not rejected */
732
+
NULL,
756
733
"\\uFFFD",
757
734
},
758
735
/* Plane 1 .. 16 noncharacters */
···
774
751
"\xF3\xAF\xBF\xBE\xF3\xAF\xBF\xBF"
775
752
"\xF3\xBF\xBF\xBE\xF3\xBF\xBF\xBF"
776
753
"\xF4\x8F\xBF\xBE\xF4\x8F\xBF\xBF",
777
-
/* bug: not rejected */
778
-
"\xF0\x9F\xBF\xBE\xF0\x9F\xBF\xBF"
779
-
"\xF0\xAF\xBF\xBE\xF0\xAF\xBF\xBF"
780
-
"\xF0\xBF\xBF\xBE\xF0\xBF\xBF\xBF"
781
-
"\xF1\x8F\xBF\xBE\xF1\x8F\xBF\xBF"
782
-
"\xF1\x9F\xBF\xBE\xF1\x9F\xBF\xBF"
783
-
"\xF1\xAF\xBF\xBE\xF1\xAF\xBF\xBF"
784
-
"\xF1\xBF\xBF\xBE\xF1\xBF\xBF\xBF"
785
-
"\xF2\x8F\xBF\xBE\xF2\x8F\xBF\xBF"
786
-
"\xF2\x9F\xBF\xBE\xF2\x9F\xBF\xBF"
787
-
"\xF2\xAF\xBF\xBE\xF2\xAF\xBF\xBF"
788
-
"\xF2\xBF\xBF\xBE\xF2\xBF\xBF\xBF"
789
-
"\xF3\x8F\xBF\xBE\xF3\x8F\xBF\xBF"
790
-
"\xF3\x9F\xBF\xBE\xF3\x9F\xBF\xBF"
791
-
"\xF3\xAF\xBF\xBE\xF3\xAF\xBF\xBF"
792
-
"\xF3\xBF\xBF\xBE\xF3\xBF\xBF\xBF"
793
-
"\xF4\x8F\xBF\xBE\xF4\x8F\xBF\xBF",
754
+
NULL,
794
755
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
795
756
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
796
757
"\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD\\uFFFD"
···
829
790
}
830
791
in = strndup(tail, end - tail);
831
792
str = from_json_str(in, j, NULL);
832
-
/*
833
-
* FIXME JSON parser accepts invalid sequence
834
-
* starting with \xC2..\xF4
835
-
*/
836
-
if (*in >= '\xC2' && *in <= '\xF4') {
837
-
g_free(str);
838
-
str = NULL;
839
-
}
840
793
g_assert(!str);
841
794
g_free(in);
842
795
}
+62
-7
util/unicode.c
+62
-7
util/unicode.c
···
13
13
#include "qemu/osdep.h"
14
14
#include "qemu/unicode.h"
15
15
16
+
static bool is_valid_codepoint(int codepoint)
17
+
{
18
+
if (codepoint > 0x10FFFFu) {
19
+
return false; /* beyond Unicode range */
20
+
}
21
+
if ((codepoint >= 0xFDD0 && codepoint <= 0xFDEF)
22
+
|| (codepoint & 0xFFFE) == 0xFFFE) {
23
+
return false; /* noncharacter */
24
+
}
25
+
if (codepoint >= 0xD800 && codepoint <= 0xDFFF) {
26
+
return false; /* surrogate code point */
27
+
}
28
+
return true;
29
+
}
30
+
16
31
/**
17
32
* mod_utf8_codepoint:
18
33
* @s: string encoded in modified UTF-8
···
83
98
cp <<= 6;
84
99
cp |= byte & 0x3F;
85
100
}
86
-
if (cp > 0x10FFFF) {
87
-
cp = -1; /* beyond Unicode range */
88
-
} else if ((cp >= 0xFDD0 && cp <= 0xFDEF)
89
-
|| (cp & 0xFFFE) == 0xFFFE) {
90
-
cp = -1; /* noncharacter */
91
-
} else if (cp >= 0xD800 && cp <= 0xDFFF) {
92
-
cp = -1; /* surrogate code point */
101
+
if (!is_valid_codepoint(cp)) {
102
+
cp = -1;
93
103
} else if (cp < min_cp[len - 2] && !(cp == 0 && len == 2)) {
94
104
cp = -1; /* overlong, not \xC0\x80 */
95
105
}
···
99
109
*end = (char *)p;
100
110
return cp;
101
111
}
112
+
113
+
/**
114
+
* mod_utf8_encode:
115
+
* @buf: Destination buffer
116
+
* @bufsz: size of @buf, at least 5.
117
+
* @codepoint: Unicode codepoint to encode
118
+
*
119
+
* Convert Unicode codepoint @codepoint to modified UTF-8.
120
+
*
121
+
* Returns: the length of the UTF-8 sequence on success, -1 when
122
+
* @codepoint is invalid.
123
+
*/
124
+
ssize_t mod_utf8_encode(char buf[], size_t bufsz, int codepoint)
125
+
{
126
+
assert(bufsz >= 5);
127
+
128
+
if (!is_valid_codepoint(codepoint)) {
129
+
return -1;
130
+
}
131
+
132
+
if (codepoint > 0 && codepoint <= 0x7F) {
133
+
buf[0] = codepoint & 0x7F;
134
+
buf[1] = 0;
135
+
return 1;
136
+
}
137
+
if (codepoint <= 0x7FF) {
138
+
buf[0] = 0xC0 | ((codepoint >> 6) & 0x1F);
139
+
buf[1] = 0x80 | (codepoint & 0x3F);
140
+
buf[2] = 0;
141
+
return 2;
142
+
}
143
+
if (codepoint <= 0xFFFF) {
144
+
buf[0] = 0xE0 | ((codepoint >> 12) & 0x0F);
145
+
buf[1] = 0x80 | ((codepoint >> 6) & 0x3F);
146
+
buf[2] = 0x80 | (codepoint & 0x3F);
147
+
buf[3] = 0;
148
+
return 3;
149
+
}
150
+
buf[0] = 0xF0 | ((codepoint >> 18) & 0x07);
151
+
buf[1] = 0x80 | ((codepoint >> 12) & 0x3F);
152
+
buf[2] = 0x80 | ((codepoint >> 6) & 0x3F);
153
+
buf[3] = 0x80 | (codepoint & 0x3F);
154
+
buf[4] = 0;
155
+
return 4;
156
+
}