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
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
|
// Copyright 2016 Daniel Parker
// Distributed under the Boost license, Version 1.0.
// (See accompanying file LICENSE_1_0.txt or copy at http://www.boost.org/LICENSE_1_0.txt)
// See https://github.com/danielaparker/unicode_traits for latest version
/*
* Includes code derived from Unicode, Inc decomposition code in ConvertUTF.h and ConvertUTF.c
* http://www.unicode.org/
*
* "Unicode, Inc. hereby grants the right to freely use the information
* supplied in this file in the creation of products supporting the
* Unicode Standard."
*/
#ifndef JSONCONS_UNICODE_TRAITS_HPP
#define JSONCONS_UNICODE_TRAITS_HPP
#include <cstring>
#include <string>
#include <iterator>
#include <type_traits>
#include <system_error>
#include <limits>
#include <jsoncons/config/compiler_support.hpp>
#include <jsoncons/more_type_traits.hpp>
namespace jsoncons { namespace unicode_traits {
enum class encoding_kind {undetected,utf8,utf16le,utf16be,utf32le,utf32be};
inline
std::string to_string(encoding_kind encoding)
{
switch (encoding)
{
case encoding_kind::utf8:
return "utf8";
case encoding_kind::utf16le:
return "utf16le";
case encoding_kind::utf16be:
return "utf16be";
case encoding_kind::utf32le:
return "utf32le";
case encoding_kind::utf32be:
return "utf32be";
default:
return "undetected";
}
}
template <class Byte>
struct detect_encoding_result
{
const Byte* ptr;
encoding_kind encoding;
};
template <class CharT>
typename std::enable_if<type_traits::is_char8<CharT>::value,detect_encoding_result<CharT>>::type
detect_encoding_from_bom(const CharT* data, std::size_t length)
{
const uint8_t bom_utf8[] = {0xef,0xbb,0xbf};
const uint8_t bom_utf16le[] = {0xff,0xfe};
const uint8_t bom_utf16be[] = {0xfe,0xff};
const uint8_t bom_utf32le[] = {0xff,0xfe,0x00,0x00};
const uint8_t bom_utf32be[] = {0x00,0x00,0xfe,0xff};
if (length >= 4 && !memcmp(data,bom_utf32le,4))
{
return detect_encoding_result<CharT>{data+4,encoding_kind::utf32le};
}
else if (length >= 4 && !memcmp(data,bom_utf32be,4))
{
return detect_encoding_result<CharT>{data+4,encoding_kind::utf32be};
}
else if (length >= 2 && !memcmp(data,bom_utf16le,2))
{
return detect_encoding_result<CharT>{data+2,encoding_kind::utf16le};
}
else if (length >= 2 && !memcmp(data,bom_utf16be,2))
{
return detect_encoding_result<CharT>{data+2,encoding_kind::utf16be};
}
else if (length >= 3 && !memcmp(data,bom_utf8,3))
{
return detect_encoding_result<CharT>{data+3,encoding_kind::utf8};
}
else
{
return detect_encoding_result<CharT>{data,encoding_kind::undetected};
}
}
template <class CharT>
typename std::enable_if<type_traits::is_char16<CharT>::value || type_traits::is_char32<CharT>::value,detect_encoding_result<CharT>>::type
detect_encoding_from_bom(const CharT* data, std::size_t)
{
return detect_encoding_result<CharT>{data,encoding_kind::undetected};
}
template <class CharT>
typename std::enable_if<type_traits::is_char8<CharT>::value,detect_encoding_result<CharT>>::type
detect_json_encoding(const CharT* data, std::size_t length)
{
detect_encoding_result<CharT> r = detect_encoding_from_bom(data,length);
if (r.encoding != encoding_kind::undetected)
{
return r;
}
else if (length < 4)
{
return detect_encoding_result<CharT>{data,encoding_kind::utf8};
}
else if (*data == 0 && *(data+1) == 0 && *(data+2) == 0)
{
return detect_encoding_result<CharT>{data,encoding_kind::utf32be};
}
else if (*data == 0 && *(data+2) == 0)
{
return detect_encoding_result<CharT>{data,encoding_kind::utf16be};
}
else if (*(data+1) == 0 && *(data+2) == 0 && *(data+3) == 0)
{
return detect_encoding_result<CharT>{data,encoding_kind::utf32le};
}
else if (*(data+1) == 0 && *(data+3) == 0)
{
return detect_encoding_result<CharT>{data,encoding_kind::utf16le};
}
else
{
return detect_encoding_result<CharT>{data,encoding_kind::utf8};
}
}
template <class CharT>
typename std::enable_if<type_traits::is_char16<CharT>::value || type_traits::is_char32<CharT>::value,detect_encoding_result<CharT>>::type
detect_json_encoding(const CharT* data, std::size_t)
{
return detect_encoding_result<CharT>{data,encoding_kind::undetected};
}
/*
* 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. Source: ConvertUTF.c
*/
const uint32_t offsets_from_utf8[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. Source: ConvertUTF.c
*/
const uint8_t first_byte_mark[7] = { 0x00, 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC };
/*
* 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. Source: ConvertUTF.c
*/
const uint8_t trailing_bytes_for_utf8[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
};
// Some fundamental constants. Source: ConvertUTF.h
const uint32_t replacement_char = 0x0000FFFD;
const uint32_t max_bmp = 0x0000FFFF;
const uint32_t max_utf16 = 0x0010FFFF;
const uint32_t max_utf32 = 0x7FFFFFFF;
const uint32_t max_legal_utf32 = 0x0010FFFF;
const int half_shift = 10; // used for shifting by 10 bits
const uint32_t half_base = 0x0010000UL;
const uint32_t half_mask = 0x3FFUL;
const uint16_t sur_high_start = 0xD800;
const uint16_t sur_high_end = 0xDBFF;
const uint16_t sur_low_start = 0xDC00;
const uint16_t sur_low_end = 0xDFFF;
inline
static bool is_continuation_byte(unsigned char ch)
{
return (ch & 0xC0) == 0x80;
}
inline
bool is_high_surrogate(uint32_t ch) noexcept
{
return (ch >= sur_high_start && ch <= sur_high_end);
}
inline
bool is_low_surrogate(uint32_t ch) noexcept
{
return (ch >= sur_low_start && ch <= sur_low_end);
}
inline
bool is_surrogate(uint32_t ch) noexcept
{
return (ch >= sur_high_start && ch <= sur_low_end);
}
enum class conv_flags
{
strict = 0,
lenient
};
// conv_errc
enum class conv_errc
{
success = 0,
over_long_utf8_sequence = 1, // over long utf8 sequence
expected_continuation_byte, // expected continuation byte
unpaired_high_surrogate, // unpaired high surrogate UTF-16
illegal_surrogate_value, // UTF-16 surrogate values are illegal in UTF-32
source_exhausted, // partial character in source, but hit end
source_illegal // source sequence is illegal/malformed
};
class Unicode_traits_error_category_impl_
: public std::error_category
{
public:
virtual const char* name() const noexcept
{
return "unicode_traits conversion error";
}
virtual std::string message(int ev) const
{
switch (static_cast<conv_errc>(ev))
{
case conv_errc::over_long_utf8_sequence:
return "Over long utf8 sequence";
case conv_errc::expected_continuation_byte:
return "Expected continuation byte";
case conv_errc::unpaired_high_surrogate:
return "Unpaired high surrogate UTF-16";
case conv_errc::illegal_surrogate_value:
return "UTF-16 surrogate values are illegal in UTF-32";
case conv_errc::source_exhausted:
return "Partial character in source, but hit end";
case conv_errc::source_illegal:
return "Source sequence is illegal/malformed";
default:
return "";
break;
}
}
};
inline
const std::error_category& unicode_traits_error_category()
{
static Unicode_traits_error_category_impl_ instance;
return instance;
}
inline
std::error_code make_error_code(conv_errc result)
{
return std::error_code(static_cast<int>(result),unicode_traits_error_category());
}
} // unicode_traits
} // jsoncons
namespace std {
template<>
struct is_error_code_enum<jsoncons::unicode_traits::conv_errc> : public true_type
{
};
}
namespace jsoncons { namespace unicode_traits {
// utf8
template <class CharT>
typename std::enable_if<type_traits::is_char8<CharT>::value, conv_errc>::type
is_legal_utf8(const CharT* first, std::size_t length)
{
uint8_t a;
const CharT* srcptr = first+length;
switch (length) {
default:
return conv_errc::over_long_utf8_sequence;
case 4:
if (((a = (*--srcptr))& 0xC0) != 0x80)
return conv_errc::expected_continuation_byte;
JSONCONS_FALLTHROUGH;
case 3:
if (((a = (*--srcptr))& 0xC0) != 0x80)
return conv_errc::expected_continuation_byte;
JSONCONS_FALLTHROUGH;
case 2:
if (((a = (*--srcptr))& 0xC0) != 0x80)
return conv_errc::expected_continuation_byte;
switch (static_cast<uint8_t>(*first))
{
// no fall-through in this inner switch
case 0xE0: if (a < 0xA0) return conv_errc::source_illegal; break;
case 0xED: if (a > 0x9F) return conv_errc::source_illegal; break;
case 0xF0: if (a < 0x90) return conv_errc::source_illegal; break;
case 0xF4: if (a > 0x8F) return conv_errc::source_illegal; break;
default: if (a < 0x80) return conv_errc::source_illegal;
}
JSONCONS_FALLTHROUGH;
case 1:
if (static_cast<uint8_t>(*first) >= 0x80 && static_cast<uint8_t>(*first) < 0xC2)
return conv_errc::source_illegal;
break;
}
if (static_cast<uint8_t>(*first) > 0xF4)
return conv_errc::source_illegal;
return conv_errc();
}
template <class...> using void_t = void;
template <class, class, class = void>
struct is_output_iterator : std::false_type {};
template <class I, class E>
struct is_output_iterator<I, E, void_t<
typename std::iterator_traits<I>::iterator_category,
decltype(*std::declval<I>() = std::declval<E>())>> : std::true_type {};
// is_same_size fixes issue with vs2013
// primary template
template<class T1, class T2, class Enable = void>
struct is_same_size : std::false_type
{
};
// specialization for non void types
template<class T1, class T2>
struct is_same_size<T1, T2, typename std::enable_if<!std::is_void<T1>::value && !std::is_void<T2>::value>::type>
{
static constexpr bool value = (sizeof(T1) == sizeof(T2));
};
// convert
template <class CharT>
struct convert_result
{
const CharT* ptr;
conv_errc ec;
};
// to_codepoint
template <class CharT,class CodepointT>
typename std::enable_if<type_traits::is_char8<CharT>::value && type_traits::is_char32<CodepointT>::value,
convert_result<CharT>>::type
to_codepoint(const CharT* first, const CharT* last,
CodepointT& ch,
conv_flags flags = conv_flags::strict) noexcept
{
ch = 0;
if (first >= last)
{
return convert_result<CharT>{first, conv_errc::source_exhausted};
}
conv_errc result = conv_errc();
unsigned short extra_bytes_to_read = trailing_bytes_for_utf8[static_cast<uint8_t>(*first)];
if (extra_bytes_to_read >= last - first)
{
result = conv_errc::source_exhausted;
return convert_result<CharT>{first, result};
}
// Do this check whether lenient or strict
if ((result=is_legal_utf8(first, extra_bytes_to_read+1)) != conv_errc())
{
return convert_result<CharT>{first, result};
}
// The cases all fall through. See "Note A" below.
switch (extra_bytes_to_read)
{
case 5:
ch += static_cast<uint8_t>(*first++);
ch <<= 6;
JSONCONS_FALLTHROUGH;
case 4:
ch += static_cast<uint8_t>(*first++);
ch <<= 6;
JSONCONS_FALLTHROUGH;
case 3:
ch += static_cast<uint8_t>(*first++);
ch <<= 6;
JSONCONS_FALLTHROUGH;
case 2:
ch += static_cast<uint8_t>(*first++);
ch <<= 6;
JSONCONS_FALLTHROUGH;
case 1:
ch += static_cast<uint8_t>(*first++);
ch <<= 6;
JSONCONS_FALLTHROUGH;
case 0:
ch += static_cast<uint8_t>(*first++);
break;
}
ch -= offsets_from_utf8[extra_bytes_to_read];
if (ch <= max_legal_utf32) {
/*
* UTF-16 surrogate values are illegal in UTF-32, and anything
* over Plane 17 (> 0x10FFFF) is illegal.
*/
if (is_surrogate(ch) )
{
if (flags == conv_flags::strict)
{
first -= (extra_bytes_to_read+1); // return to the illegal value itself
result = conv_errc::source_illegal;
return convert_result<CharT>{first, result};
}
else
{
ch = replacement_char;
}
}
}
else // i.e., ch > max_legal_utf32
{
result = conv_errc::source_illegal;
ch = replacement_char;
}
return convert_result<CharT>{first,result} ;
}
template <class CharT,class CodepointT>
typename std::enable_if<type_traits::is_char16<CharT>::value && type_traits::is_char32<CodepointT>::value,
convert_result<CharT>>::type
to_codepoint(const CharT* first, const CharT* last,
CodepointT& ch,
conv_flags flags = conv_flags::strict) noexcept
{
ch = 0;
if (first >= last)
{
return convert_result<CharT>{first, conv_errc::source_exhausted};
}
conv_errc result = conv_errc();
ch = *first++;
// If we have a surrogate pair, convert to UTF32 first.
if (is_high_surrogate(ch))
{
// If the 16 bits following the high surrogate are in the first buffer...
if (first < last)
{
uint32_t ch2 = *first;
// If ptr's a low surrogate, convert to UTF32.
if (ch2 >= sur_low_start && ch2 <= sur_low_end )
{
ch = ((ch - sur_high_start) << half_shift)
+ (ch2 - sur_low_start) + half_base;
++first;
}
else if (flags == conv_flags::strict) // ptr's an unpaired high surrogate
{
--first; /* return to the illegal value itself */
result = conv_errc::source_illegal;
return convert_result<CharT>{first, result};
}
}
else
{ /* We don't have the 16 bits following the high surrogate. */
--first; /* return to the high surrogate */
result = conv_errc::source_exhausted;
return convert_result<CharT>{first, result};
}
} else if (flags == conv_flags::strict) {
/* UTF-16 surrogate values are illegal in UTF-32 */
if (is_low_surrogate(ch) )
{
--first; /* return to the illegal value itself */
result = conv_errc::source_illegal;
return convert_result<CharT>{first, result};
}
}
return convert_result<CharT>{first,result} ;
}
template <class CharT,class CodepointT>
typename std::enable_if<type_traits::is_char32<CharT>::value && type_traits::is_char32<CodepointT>::value,
convert_result<CharT>>::type
to_codepoint(const CharT* first, const CharT* last,
CodepointT& ch,
conv_flags flags = conv_flags::strict) noexcept
{
ch = 0;
if (first >= last)
{
return convert_result<CharT>{first, conv_errc::source_exhausted};
}
conv_errc result = conv_errc();
ch = *first++;
if (flags == conv_flags::strict )
{
/* UTF-16 surrogate values are illegal in UTF-32 */
if (is_surrogate(ch))
{
--first; /* return to the illegal value itself */
result = conv_errc::illegal_surrogate_value;
return convert_result<CharT>{first,result} ;
}
}
if (!(ch <= max_legal_utf32))
{
ch = replacement_char;
result = conv_errc::source_illegal;
}
return convert_result<CharT>{first,result} ;
}
// convert
template <class CharT,class Container>
typename std::enable_if<type_traits::is_char8<CharT>::value
&& type_traits::is_back_insertable<Container>::value
&& type_traits::is_char8<typename Container::value_type>::value,
convert_result<CharT>>::type
convert(const CharT* data, std::size_t length, Container& target, conv_flags flags=conv_flags::strict)
{
(void)flags;
conv_errc result = conv_errc();
const CharT* last = data + length;
while (data != last)
{
std::size_t len = trailing_bytes_for_utf8[static_cast<uint8_t>(*data)] + 1;
if (len > (std::size_t)(last - data))
{
return convert_result<CharT>{data, conv_errc::source_exhausted};
}
if ((result=is_legal_utf8(data, len)) != conv_errc())
{
return convert_result<CharT>{data,result};
}
switch (len) {
case 4: target.push_back(static_cast<uint8_t>(*data++));
JSONCONS_FALLTHROUGH;
case 3: target.push_back(static_cast<uint8_t>(*data++));
JSONCONS_FALLTHROUGH;
case 2: target.push_back(static_cast<uint8_t>(*data++));
JSONCONS_FALLTHROUGH;
case 1: target.push_back(static_cast<uint8_t>(*data++));
}
}
return convert_result<CharT>{data,result} ;
}
template <class CharT,class Container>
typename std::enable_if<type_traits::is_char8<CharT>::value
&& type_traits::is_back_insertable<Container>::value
&& type_traits::is_char16<typename Container::value_type>::value,
convert_result<CharT>>::type
convert(const CharT* data, std::size_t length,
Container& target,
conv_flags flags = conv_flags::strict)
{
conv_errc result = conv_errc();
const CharT* last = data + length;
while (data != last)
{
unsigned short extra_bytes_to_read = trailing_bytes_for_utf8[static_cast<uint8_t>(*data)];
if (extra_bytes_to_read >= last - data)
{
result = conv_errc::source_exhausted;
break;
}
/* Do this check whether lenient or strict */
if ((result=is_legal_utf8(data, extra_bytes_to_read+1)) != conv_errc())
{
break;
}
/*
* The cases all fall through. See "Note A" below.
*/
uint32_t ch = 0;
switch (extra_bytes_to_read) {
case 5: ch += static_cast<uint8_t>(*data++); ch <<= 6; /* remember, illegal UTF-8 */
JSONCONS_FALLTHROUGH;
case 4: ch += static_cast<uint8_t>(*data++); ch <<= 6; /* remember, illegal UTF-8 */
JSONCONS_FALLTHROUGH;
case 3: ch += static_cast<uint8_t>(*data++); ch <<= 6;
JSONCONS_FALLTHROUGH;
case 2: ch += static_cast<uint8_t>(*data++); ch <<= 6;
JSONCONS_FALLTHROUGH;
case 1: ch += static_cast<uint8_t>(*data++); ch <<= 6;
JSONCONS_FALLTHROUGH;
case 0: ch += static_cast<uint8_t>(*data++);
break;
}
ch -= offsets_from_utf8[extra_bytes_to_read];
if (ch <= max_bmp) { /* Target is a character <= 0xFFFF */
/* UTF-16 surrogate values are illegal in UTF-32 */
if (is_surrogate(ch) )
{
if (flags == conv_flags::strict) {
data -= (extra_bytes_to_read+1); /* return to the illegal value itself */
result = conv_errc::source_illegal;
break;
} else {
target.push_back(replacement_char);
}
} else {
target.push_back((uint16_t)ch); /* normal case */
}
} else if (ch > max_utf16) {
if (flags == conv_flags::strict) {
result = conv_errc::source_illegal;
data -= (extra_bytes_to_read+1); /* return to the start */
break; /* Bail out; shouldn't continue */
} else {
target.push_back(replacement_char);
}
} else {
/* target is a character in range 0xFFFF - 0x10FFFF. */
ch -= half_base;
target.push_back((uint16_t)((ch >> half_shift) + sur_high_start));
target.push_back((uint16_t)((ch & half_mask) + sur_low_start));
}
}
return convert_result<CharT>{data,result} ;
}
template <class CharT,class Container>
typename std::enable_if<type_traits::is_char8<CharT>::value
&& type_traits::is_back_insertable<Container>::value
&& type_traits::is_char32<typename Container::value_type>::value,
convert_result<CharT>>::type
convert(const CharT* data, std::size_t length,
Container& target,
conv_flags flags = conv_flags::strict)
{
conv_errc result = conv_errc();
const CharT* last = data + length;
while (data < last)
{
uint32_t ch = 0;
unsigned short extra_bytes_to_read = trailing_bytes_for_utf8[static_cast<uint8_t>(*data)];
if (extra_bytes_to_read >= last - data)
{
result = conv_errc::source_exhausted;
break;
}
/* Do this check whether lenient or strict */
if ((result=is_legal_utf8(data, extra_bytes_to_read+1)) != conv_errc())
{
break;
}
/*
* The cases all fall through. See "Note A" below.
*/
switch (extra_bytes_to_read)
{
case 5:
ch += static_cast<uint8_t>(*data++);
ch <<= 6;
JSONCONS_FALLTHROUGH;
case 4:
ch += static_cast<uint8_t>(*data++);
ch <<= 6;
JSONCONS_FALLTHROUGH;
case 3:
ch += static_cast<uint8_t>(*data++);
ch <<= 6;
JSONCONS_FALLTHROUGH;
case 2:
ch += static_cast<uint8_t>(*data++);
ch <<= 6;
JSONCONS_FALLTHROUGH;
case 1:
ch += static_cast<uint8_t>(*data++);
ch <<= 6;
JSONCONS_FALLTHROUGH;
case 0:
ch += static_cast<uint8_t>(*data++);
break;
}
ch -= offsets_from_utf8[extra_bytes_to_read];
if (ch <= max_legal_utf32) {
/*
* UTF-16 surrogate values are illegal in UTF-32, and anything
* over Plane 17 (> 0x10FFFF) is illegal.
*/
if (is_surrogate(ch) )
{
if (flags == conv_flags::strict) {
data -= (extra_bytes_to_read+1); /* return to the illegal value itself */
result = conv_errc::source_illegal;
break;
} else {
target.push_back(replacement_char);
}
} else {
target.push_back(ch);
}
} else { /* i.e., ch > max_legal_utf32 */
result = conv_errc::source_illegal;
target.push_back(replacement_char);
}
}
return convert_result<CharT>{data,result} ;
}
// utf16
template <class CharT,class Container>
typename std::enable_if<type_traits::is_char16<CharT>::value
&& type_traits::is_back_insertable<Container>::value
&& type_traits::is_char8<typename Container::value_type>::value,
convert_result<CharT>>::type
convert(const CharT* data, std::size_t length,
Container& target,
conv_flags flags = conv_flags::strict) {
conv_errc result = conv_errc();
const CharT* last = data + length;
while (data < last) {
unsigned short bytes_to_write = 0;
const uint32_t byteMask = 0xBF;
const uint32_t byteMark = 0x80;
uint32_t ch = *data++;
/* If we have a surrogate pair, convert to uint32_t data. */
if (is_high_surrogate(ch))
{
/* If the 16 bits following the high surrogate are in the data buffer... */
if (data < last) {
uint32_t ch2 = *data;
/* If ptr's a low surrogate, convert to uint32_t. */
if (ch2 >= sur_low_start && ch2 <= sur_low_end) {
ch = ((ch - sur_high_start) << half_shift)
+ (ch2 - sur_low_start) + half_base;
++data;
} else if (flags == conv_flags::strict) { /* ptr's an unpaired high surrogate */
--data; /* return to the illegal value itself */
result = conv_errc::unpaired_high_surrogate;
break;
}
} else { /* We don't have the 16 bits following the high surrogate. */
--data; /* return to the high surrogate */
result = conv_errc::source_exhausted;
break;
}
} else if (flags == conv_flags::strict) {
/* UTF-16 surrogate values are illegal in UTF-32 */
if (is_low_surrogate(ch))
{
--data; /* return to the illegal value itself */
result = conv_errc::source_illegal;
break;
}
}
/* Figure out how many bytes the result will require */
if (ch < (uint32_t)0x80) {
bytes_to_write = 1;
} else if (ch < (uint32_t)0x800) {
bytes_to_write = 2;
} else if (ch < (uint32_t)0x10000) {
bytes_to_write = 3;
} else if (ch < (uint32_t)0x110000) {
bytes_to_write = 4;
} else {
bytes_to_write = 3;
ch = replacement_char;
}
uint8_t byte1 = 0;
uint8_t byte2 = 0;
uint8_t byte3 = 0;
uint8_t byte4 = 0;
switch (bytes_to_write) { // note: everything falls through
case 4: byte4 = (uint8_t)((ch | byteMark) & byteMask); ch >>= 6;
JSONCONS_FALLTHROUGH;
case 3: byte3 = (uint8_t)((ch | byteMark) & byteMask); ch >>= 6;
JSONCONS_FALLTHROUGH;
case 2: byte2 = (uint8_t)((ch | byteMark) & byteMask); ch >>= 6;
JSONCONS_FALLTHROUGH;
case 1: byte1 = (uint8_t)(ch | first_byte_mark[bytes_to_write]);
break;
}
switch (bytes_to_write)
{
case 4:
target.push_back(byte1);
target.push_back(byte2);
target.push_back(byte3);
target.push_back(byte4);
break;
case 3:
target.push_back(byte1);
target.push_back(byte2);
target.push_back(byte3);
break;
case 2:
target.push_back(byte1);
target.push_back(byte2);
break;
case 1:
target.push_back(byte1);
break;
}
}
return convert_result<CharT>{data,result} ;
}
template <class CharT,class Container>
typename std::enable_if<type_traits::is_char16<CharT>::value
&& type_traits::is_back_insertable<Container>::value
&& type_traits::is_char16<typename Container::value_type>::value,
convert_result<CharT>>::type
convert(const CharT* data, std::size_t length,
Container& target,
conv_flags flags = conv_flags::strict)
{
conv_errc result = conv_errc();
const CharT* last = data + length;
while (data != last)
{
uint32_t ch = *data++;
/* If we have a surrogate pair, convert to uint32_t data. */
if (is_high_surrogate(ch))
{
/* If the 16 bits following the high surrogate are in the data buffer... */
if (data < last) {
uint32_t ch2 = *data;
/* If ptr's a low surrogate, */
if (ch2 >= sur_low_start && ch2 <= sur_low_end) {
target.push_back((uint16_t)ch);
target.push_back((uint16_t)ch2);
++data;
} else if (flags == conv_flags::strict) { /* ptr's an unpaired high surrogate */
--data; /* return to the illegal value itself */
result = conv_errc::unpaired_high_surrogate;
break;
}
} else { /* We don't have the 16 bits following the high surrogate. */
--data; /* return to the high surrogate */
result = conv_errc::source_exhausted;
break;
}
} else if (is_low_surrogate(ch))
{
// illegal leading low surrogate
if (flags == conv_flags::strict) {
--data; /* return to the illegal value itself */
result = conv_errc::source_illegal;
break;
}
else
{
target.push_back((uint16_t)ch);
}
}
else
{
target.push_back((uint16_t)ch);
}
}
return convert_result<CharT>{data,result} ;
}
template <class CharT,class Container>
typename std::enable_if<type_traits::is_char16<CharT>::value
&& type_traits::is_back_insertable<Container>::value
&& type_traits::is_char32<typename Container::value_type>::value,
convert_result<CharT>>::type
convert(const CharT* data, std::size_t length,
Container& target,
conv_flags flags = conv_flags::strict)
{
conv_errc result = conv_errc();
const CharT* last = data + length;
while (data != last)
{
uint32_t ch = *data++;
/* If we have a surrogate pair, convert to UTF32 data. */
if (is_high_surrogate(ch))
{
/* If the 16 bits following the high surrogate are in the data buffer... */
if (data < last) {
uint32_t ch2 = *data;
/* If ptr's a low surrogate, convert to UTF32. */
if (ch2 >= sur_low_start && ch2 <= sur_low_end )
{
ch = ((ch - sur_high_start) << half_shift)
+ (ch2 - sur_low_start) + half_base;
++data;
} else if (flags == conv_flags::strict) { /* ptr's an unpaired high surrogate */
--data; /* return to the illegal value itself */
result = conv_errc::source_illegal;
break;
}
} else { /* We don't have the 16 bits following the high surrogate. */
--data; /* return to the high surrogate */
result = conv_errc::source_exhausted;
break;
}
} else if (flags == conv_flags::strict) {
/* UTF-16 surrogate values are illegal in UTF-32 */
if (is_low_surrogate(ch) )
{
--data; /* return to the illegal value itself */
result = conv_errc::source_illegal;
break;
}
}
target.push_back(ch);
}
return convert_result<CharT>{data,result} ;
}
// utf32
template <class CharT,class Container>
typename std::enable_if<type_traits::is_char32<CharT>::value
&& type_traits::is_back_insertable<Container>::value
&& type_traits::is_char8<typename Container::value_type>::value,
convert_result<CharT>>::type
convert(const CharT* data, std::size_t length,
Container& target,
conv_flags flags = conv_flags::strict)
{
conv_errc result = conv_errc();
const CharT* last = data + length;
while (data < last)
{
unsigned short bytes_to_write = 0;
const uint32_t byteMask = 0xBF;
const uint32_t byteMark = 0x80;
uint32_t ch = *data++;
if (flags == conv_flags::strict )
{
/* UTF-16 surrogate values are illegal in UTF-32 */
if (is_surrogate(ch))
{
--data; /* return to the illegal value itself */
result = conv_errc::illegal_surrogate_value;
break;
}
}
/*
* Figure out how many bytes the result will require. Turn any
* illegally large UTF32 things (> Plane 17) into replacement chars.
*/
if (ch < (uint32_t)0x80) { bytes_to_write = 1;
} else if (ch < (uint32_t)0x800) { bytes_to_write = 2;
} else if (ch < (uint32_t)0x10000) { bytes_to_write = 3;
} else if (ch <= max_legal_utf32) { bytes_to_write = 4;
} else {
bytes_to_write = 3;
ch = replacement_char;
result = conv_errc::source_illegal;
}
uint8_t byte1 = 0;
uint8_t byte2 = 0;
uint8_t byte3 = 0;
uint8_t byte4 = 0;
switch (bytes_to_write) {
case 4:
byte4 = (uint8_t)((ch | byteMark) & byteMask); ch >>= 6;
JSONCONS_FALLTHROUGH;
case 3:
byte3 = (uint8_t)((ch | byteMark) & byteMask); ch >>= 6;
JSONCONS_FALLTHROUGH;
case 2:
byte2 = (uint8_t)((ch | byteMark) & byteMask); ch >>= 6;
JSONCONS_FALLTHROUGH;
case 1:
byte1 = (uint8_t) (ch | first_byte_mark[bytes_to_write]);
break;
}
switch (bytes_to_write)
{
case 4:
target.push_back(byte1);
target.push_back(byte2);
target.push_back(byte3);
target.push_back(byte4);
break;
case 3:
target.push_back(byte1);
target.push_back(byte2);
target.push_back(byte3);
break;
case 2:
target.push_back(byte1);
target.push_back(byte2);
break;
case 1:
target.push_back(byte1);
break;
}
}
return convert_result<CharT>{data,result} ;
}
template <class CharT,class Container>
typename std::enable_if<type_traits::is_char32<CharT>::value
&& type_traits::is_back_insertable<Container>::value
&& type_traits::is_char16<typename Container::value_type>::value,
convert_result<CharT>>::type
convert(const CharT* data, std::size_t length,
Container& target,
conv_flags flags = conv_flags::strict)
{
conv_errc result = conv_errc();
const CharT* last = data + length;
while (data != last)
{
uint32_t ch = *data++;
if (ch <= max_bmp) { /* Target is a character <= 0xFFFF */
/* UTF-16 surrogate values are illegal in UTF-32; 0xffff or 0xfffe are both reserved values */
if (is_surrogate(ch) )
{
if (flags == conv_flags::strict) {
--data; /* return to the illegal value itself */
result = conv_errc::source_illegal;
break;
} else {
target.push_back(replacement_char);
}
} else {
target.push_back((uint16_t)ch); /* normal case */
}
} else if (ch > max_legal_utf32) {
if (flags == conv_flags::strict) {
result = conv_errc::source_illegal;
} else {
target.push_back(replacement_char);
}
} else {
/* target is a character in range 0xFFFF - 0x10FFFF. */
ch -= half_base;
target.push_back((uint16_t)((ch >> half_shift) + sur_high_start));
target.push_back((uint16_t)((ch & half_mask) + sur_low_start));
}
}
return convert_result<CharT>{data,result} ;
}
template <class CharT,class Container>
typename std::enable_if<type_traits::is_char32<CharT>::value
&& type_traits::is_back_insertable<Container>::value
&& type_traits::is_char32<typename Container::value_type>::value,
convert_result<CharT>>::type
convert(const CharT* data, std::size_t length,
Container& target,
conv_flags flags = conv_flags::strict)
{
conv_errc result = conv_errc();
const CharT* last = data + length;
while (data != last)
{
uint32_t ch = *data++;
if (flags == conv_flags::strict )
{
/* UTF-16 surrogate values are illegal in UTF-32 */
if (is_surrogate(ch))
{
--data; /* return to the illegal value itself */
result = conv_errc::illegal_surrogate_value;
break;
}
}
if (ch <= max_legal_utf32)
{
target.push_back(ch);
}
else
{
target.push_back(replacement_char);
result = conv_errc::source_illegal;
}
}
return convert_result<CharT>{data,result} ;
}
// validate
template <class CharT>
typename std::enable_if<type_traits::is_char8<CharT>::value,
convert_result<CharT>>::type
validate(const CharT* data, std::size_t length) noexcept
{
conv_errc result = conv_errc();
const CharT* last = data + length;
while (data != last)
{
std::size_t len = static_cast<std::size_t>(trailing_bytes_for_utf8[static_cast<uint8_t>(*data)]) + 1;
if (len > (std::size_t)(last - data))
{
return convert_result<CharT>{data, conv_errc::source_exhausted};
}
if ((result=is_legal_utf8(data, len)) != conv_errc())
{
return convert_result<CharT>{data,result} ;
}
data += len;
}
return convert_result<CharT>{data,result} ;
}
// utf16
template <class CharT>
typename std::enable_if<type_traits::is_char16<CharT>::value,
convert_result<CharT>>::type
validate(const CharT* data, std::size_t length) noexcept
{
conv_errc result = conv_errc();
const CharT* last = data + length;
while (data != last)
{
uint32_t ch = *data++;
/* If we have a surrogate pair, validate to uint32_t data. */
if (is_high_surrogate(ch))
{
/* If the 16 bits following the high surrogate are in the data buffer... */
if (data < last) {
uint32_t ch2 = *data;
/* If ptr's a low surrogate, */
if (ch2 >= sur_low_start && ch2 <= sur_low_end) {
++data;
} else {
--data; /* return to the illegal value itself */
result = conv_errc::unpaired_high_surrogate;
break;
}
}
else // We don't have the 16 bits following the high surrogate.
{
--data; /* return to the high surrogate */
result = conv_errc::source_exhausted;
break;
}
}
else if (is_low_surrogate(ch))
{
/* UTF-16 surrogate values are illegal in UTF-32 */
--data; /* return to the illegal value itself */
result = conv_errc::source_illegal;
break;
}
}
return convert_result<CharT>{data,result} ;
}
// utf32
template <class CharT>
typename std::enable_if<type_traits::is_char32<CharT>::value,
convert_result<CharT>>::type
validate(const CharT* data, std::size_t length) noexcept
{
conv_errc result = conv_errc();
const CharT* last = data + length;
while (data != last)
{
uint32_t ch = *data++;
/* UTF-16 surrogate values are illegal in UTF-32 */
if (is_surrogate(ch))
{
--data; /* return to the illegal value itself */
result = conv_errc::illegal_surrogate_value;
break;
}
if (!(ch <= max_legal_utf32))
{
result = conv_errc::source_illegal;
}
}
return convert_result<CharT>{data, result} ;
}
enum class encoding {u8,u16le,u16be,u32le,u32be,undetected};
template <class Iterator>
struct determine_encoding_result
{
Iterator it;
encoding ec;
};
template <class Iterator>
typename std::enable_if<std::is_integral<typename std::iterator_traits<Iterator>::value_type>::value && sizeof(typename std::iterator_traits<Iterator>::value_type) == sizeof(uint8_t),
determine_encoding_result<Iterator>>::type
detect_encoding(Iterator first, Iterator last) noexcept
{
Iterator it1 = first;
if (std::distance(first,last) < 4)
{
if (std::distance(first,last) == 3)
{
Iterator it2 = ++first;
Iterator it3 = ++first;
if (static_cast<uint8_t>(*it1) == 0xEF && static_cast<uint8_t>(*it2) == 0xBB && static_cast<uint8_t>(*it3) == 0xBF)
{
return determine_encoding_result<Iterator>{last,encoding::u8};
}
}
return determine_encoding_result<Iterator>{it1,encoding::undetected};
}
else
{
Iterator it2 = ++first;
Iterator it3 = ++first;
Iterator it4 = ++first;
uint32_t bom = static_cast<uint8_t>(*it1) | (static_cast<uint8_t>(*it2) << 8) | (static_cast<uint8_t>(*it3) << 16) | (static_cast<uint8_t>(*it4) << 24);
if (bom == 0xFFFE0000)
{
return determine_encoding_result<Iterator>{it4++,encoding::u32be};
}
else if (bom == 0x0000FEFF)
{
return determine_encoding_result<Iterator>{first,encoding::u32le};
}
else if ((bom & 0xFFFF) == 0xFFFE)
{
return determine_encoding_result<Iterator>{it3,encoding::u16be};
}
else if ((bom & 0xFFFF) == 0xFEFF)
{
return determine_encoding_result<Iterator>{it3,encoding::u16le};
}
else if ((bom & 0xFFFFFF) == 0xBFBBEF)
{
return determine_encoding_result<Iterator>{it4,encoding::u8};
}
else
{
uint32_t pattern = (static_cast<uint8_t>(*it1) ? 1 : 0) | (static_cast<uint8_t>(*it2) ? 2 : 0) | (static_cast<uint8_t>(*it3) ? 4 : 0) | (static_cast<uint8_t>(*it4) ? 8 : 0);
switch (pattern) {
case 0x08:
return determine_encoding_result<Iterator>{it1,encoding::u32be};
case 0x0A:
return determine_encoding_result<Iterator>{it1,encoding::u16be};
case 0x01:
return determine_encoding_result<Iterator>{it1,encoding::u32le};
case 0x05:
return determine_encoding_result<Iterator>{it1,encoding::u16le};
case 0x0F:
return determine_encoding_result<Iterator>{it1,encoding::u8};
default:
return determine_encoding_result<Iterator>{it1,encoding::undetected};
}
}
}
}
// count_codepoints
template <class CharT>
typename std::enable_if<type_traits::is_char8<CharT>::value || type_traits::is_char16<CharT>::value || type_traits::is_char32<CharT>::value, std::size_t>::type
count_codepoints(const CharT* data, std::size_t length,
conv_flags flags = conv_flags::strict) noexcept
{
conv_errc ec = conv_errc();
std::size_t count = 0;
const CharT* ptr = data;
const CharT* last = data + length;
for (; ptr < last; ++count)
{
uint32_t cp = 0;
auto r = to_codepoint(ptr, last, cp, flags);
if (r.ec != conv_errc())
{
ec = r.ec;
break;
}
ptr = r.ptr;
}
return ec == conv_errc() && ptr == last ? count : 0;
}
} // unicode_traits
} // jsoncons
#endif
|