summaryrefslogtreecommitdiffstats
path: root/RedfishPkg/Library/JsonLib/load.c
blob: 1a3b4a6e6ab4cc57a3b51a09ea2cb732efbef111 (plain)
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
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
/*
 * Copyright (c) 2009-2016 Petri Lehtinen <petri@digip.org>
 *
 * Jansson is free software; you can redistribute it and/or modify
 * it under the terms of the MIT license. See LICENSE for details.

 (C) Copyright 2020 Hewlett Packard Enterprise Development LP<BR>
 Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved.

    SPDX-License-Identifier: BSD-2-Clause-Patent AND MIT
 */

#ifndef _GNU_SOURCE
#define _GNU_SOURCE
#endif

#include "jansson_private.h"

#include <assert.h>
#include <errno.h>
#include <limits.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#ifdef HAVE_UNISTD_H
  #include <unistd.h>
#endif

#include "jansson.h"
#include "strbuffer.h"
#include "utf.h"

#define STREAM_STATE_OK     0
#define STREAM_STATE_EOF    -1
#define STREAM_STATE_ERROR  -2

#define TOKEN_INVALID  -1
#define TOKEN_EOF      0
#define TOKEN_STRING   256
#define TOKEN_INTEGER  257
#define TOKEN_REAL     258
#define TOKEN_TRUE     259
#define TOKEN_FALSE    260
#define TOKEN_NULL     261

/* Locale independent versions of isxxx() functions */
#define l_isupper(c)  ('A' <= (c) && (c) <= 'Z')
#define l_islower(c)  ('a' <= (c) && (c) <= 'z')
#define l_isalpha(c)  (l_isupper(c) || l_islower(c))
#define l_isdigit(c)  ('0' <= (c) && (c) <= '9')
#define l_isxdigit(c)                                                                    \
    (l_isdigit(c) || ('A' <= (c) && (c) <= 'F') || ('a' <= (c) && (c) <= 'f'))

/* Read one byte from stream, convert to unsigned char, then int, and
   return. return EOF on end of file. This corresponds to the
   behaviour of fgetc(). */
typedef int (*get_func)(
  void  *data
  );

typedef struct {
  get_func    get;
  void        *data;
  char        buffer[5];
  size_t      buffer_pos;
  int         state;
  int         line;
  int         column, last_column;
  size_t      position;
} stream_t;

typedef struct {
  stream_t       stream;
  strbuffer_t    saved_text;
  size_t         flags;
  size_t         depth;
  int            token;
  union {
    struct {
      char      *val;
      size_t    len;
    } string;
    json_int_t    integer;
    double        real;
  } value;
} lex_t;

#define stream_to_lex(stream)  container_of(stream, lex_t, stream)

/*** error reporting ***/

static void
error_set (
  json_error_t          *error,
  const lex_t           *lex,
  enum json_error_code  code,
  const char            *msg,
  ...
  )
{
  va_list  ap;
  char     msg_text[JSON_ERROR_TEXT_LENGTH];
  char     msg_with_context[JSON_ERROR_TEXT_LENGTH];

  int         line = -1, col = -1;
  size_t      pos     = 0;
  const char  *result = msg_text;

  if (!error) {
    return;
  }

  va_start (ap, msg);
  vsnprintf (msg_text, JSON_ERROR_TEXT_LENGTH, msg, ap);
  msg_text[JSON_ERROR_TEXT_LENGTH - 1] = '\0';
  va_end (ap);

  if (lex) {
    const char  *saved_text = strbuffer_value (&lex->saved_text);

    line = lex->stream.line;
    col  = lex->stream.column;
    pos  = lex->stream.position;

    if (saved_text && saved_text[0]) {
      if (lex->saved_text.length <= 20) {
        snprintf (
          msg_with_context,
          JSON_ERROR_TEXT_LENGTH,
          "%s near '%s'",
          msg_text,
          saved_text
          );
        msg_with_context[JSON_ERROR_TEXT_LENGTH - 1] = '\0';
        result                                       = msg_with_context;
      }
    } else {
      if (code == json_error_invalid_syntax) {
        /* More specific error code for premature end of file. */
        code = json_error_premature_end_of_input;
      }

      if (lex->stream.state == STREAM_STATE_ERROR) {
        /* No context for UTF-8 decoding errors */
        result = msg_text;
      } else {
        snprintf (
          msg_with_context,
          JSON_ERROR_TEXT_LENGTH,
          "%s near end of file",
          msg_text
          );
        msg_with_context[JSON_ERROR_TEXT_LENGTH - 1] = '\0';
        result                                       = msg_with_context;
      }
    }
  }

  jsonp_error_set (error, line, col, pos, code, "%s", result);
}

/*** lexical analyzer ***/

static void
stream_init (
  stream_t  *stream,
  get_func  get,
  void      *data
  )
{
  stream->get        = get;
  stream->data       = data;
  stream->buffer[0]  = '\0';
  stream->buffer_pos = 0;

  stream->state    = STREAM_STATE_OK;
  stream->line     = 1;
  stream->column   = 0;
  stream->position = 0;
}

static int
stream_get (
  stream_t      *stream,
  json_error_t  *error
  )
{
  int  c;

  if (stream->state != STREAM_STATE_OK) {
    return stream->state;
  }

  if (!stream->buffer[stream->buffer_pos]) {
    c = stream->get (stream->data);
    if (c == EOF) {
      stream->state = STREAM_STATE_EOF;
      return STREAM_STATE_EOF;
    }

    stream->buffer[0]  = c;
    stream->buffer_pos = 0;

    if ((0x80 <= c) && (c <= 0xFF)) {
      /* multi-byte UTF-8 sequence */
      size_t  i, count;

      count = utf8_check_first (c);
      if (!count) {
        goto out;
      }

      assert (count >= 2);

      for (i = 1; i < count; i++) {
        stream->buffer[i] = stream->get (stream->data);
      }

      if (!utf8_check_full (stream->buffer, count, NULL)) {
        goto out;
      }

      stream->buffer[count] = '\0';
    } else {
      stream->buffer[1] = '\0';
    }
  }

  c = stream->buffer[stream->buffer_pos++];

  stream->position++;
  if (c == '\n') {
    stream->line++;
    stream->last_column = stream->column;
    stream->column      = 0;
  } else if (utf8_check_first (c)) {
    /* track the Unicode character column, so increment only if
       this is the first character of a UTF-8 sequence */
    stream->column++;
  }

  return c;

out:
  stream->state = STREAM_STATE_ERROR;
  error_set (
    error,
    stream_to_lex (stream),
    json_error_invalid_utf8,
    "unable to decode byte 0x%x",
    c
    );
  return STREAM_STATE_ERROR;
}

static void
stream_unget (
  stream_t  *stream,
  int       c
  )
{
  if ((c == STREAM_STATE_EOF) || (c == STREAM_STATE_ERROR)) {
    return;
  }

  stream->position--;
  if (c == '\n') {
    stream->line--;
    stream->column = stream->last_column;
  } else if (utf8_check_first (c)) {
    stream->column--;
  }

  assert (stream->buffer_pos > 0);
  stream->buffer_pos--;
  assert (stream->buffer[stream->buffer_pos] == c);
}

static int
lex_get (
  lex_t         *lex,
  json_error_t  *error
  )
{
  return stream_get (&lex->stream, error);
}

static void
lex_save (
  lex_t  *lex,
  int    c
  )
{
  strbuffer_append_byte (&lex->saved_text, c);
}

static int
lex_get_save (
  lex_t         *lex,
  json_error_t  *error
  )
{
  int  c = stream_get (&lex->stream, error);

  if ((c != STREAM_STATE_EOF) && (c != STREAM_STATE_ERROR)) {
    lex_save (lex, c);
  }

  return c;
}

static void
lex_unget (
  lex_t  *lex,
  int    c
  )
{
  stream_unget (&lex->stream, c);
}

static void
lex_unget_unsave (
  lex_t  *lex,
  int    c
  )
{
  if ((c != STREAM_STATE_EOF) && (c != STREAM_STATE_ERROR)) {
    /* Since we treat warnings as errors, when assertions are turned
     * off the "d" variable would be set but never used. Which is
     * treated as an error by GCC.
     */
 #ifndef NDEBUG
    char  d;
 #endif
    stream_unget (&lex->stream, c);
 #ifndef NDEBUG
    d =
 #endif
    strbuffer_pop (&lex->saved_text);
    assert (c == d);
  }
}

static void
lex_save_cached (
  lex_t  *lex
  )
{
  while (lex->stream.buffer[lex->stream.buffer_pos] != '\0') {
    lex_save (lex, lex->stream.buffer[lex->stream.buffer_pos]);
    lex->stream.buffer_pos++;
    lex->stream.position++;
  }
}

static void
lex_free_string (
  lex_t  *lex
  )
{
  jsonp_free (lex->value.string.val);
  lex->value.string.val = NULL;
  lex->value.string.len = 0;
}

/* assumes that str points to 'u' plus at least 4 valid hex digits */
static int32_t
decode_unicode_escape (
  const char  *str
  )
{
  int      i;
  int32_t  value = 0;

  assert (str[0] == 'u');

  for (i = 1; i <= 4; i++) {
    char  c = str[i];
    value <<= 4;
    if (l_isdigit (c)) {
      value += c - '0';
    } else if (l_islower (c)) {
      value += c - 'a' + 10;
    } else if (l_isupper (c)) {
      value += c - 'A' + 10;
    } else {
      return -1;
    }
  }

  return value;
}

static void
lex_scan_string (
  lex_t         *lex,
  json_error_t  *error
  )
{
  int         c;
  const char  *p;
  char        *t;
  int         i;

  lex->value.string.val = NULL;
  lex->token            = TOKEN_INVALID;

  c = lex_get_save (lex, error);

  while (c != '"') {
    if (c == STREAM_STATE_ERROR) {
      goto out;
    } else if (c == STREAM_STATE_EOF) {
      error_set (
        error,
        lex,
        json_error_premature_end_of_input,
        "premature end of input"
        );
      goto out;
    } else if ((0 <= c) && (c <= 0x1F)) {
      /* control character */
      lex_unget_unsave (lex, c);
      if (c == '\n') {
        error_set (error, lex, json_error_invalid_syntax, "unexpected newline");
      } else {
        error_set (
          error,
          lex,
          json_error_invalid_syntax,
          "control character 0x%x",
          c
          );
      }

      goto out;
    } else if (c == '\\') {
      c = lex_get_save (lex, error);
      if (c == 'u') {
        c = lex_get_save (lex, error);
        for (i = 0; i < 4; i++) {
          if (!l_isxdigit (c)) {
            error_set (
              error,
              lex,
              json_error_invalid_syntax,
              "invalid escape"
              );
            goto out;
          }

          c = lex_get_save (lex, error);
        }
      } else if ((c == '"') || (c == '\\') || (c == '/') || (c == 'b') || (c == 'f') ||
                 (c == 'n') || (c == 'r') || (c == 't'))
      {
        c = lex_get_save (lex, error);
      } else {
        error_set (error, lex, json_error_invalid_syntax, "invalid escape");
        goto out;
      }
    } else {
      c = lex_get_save (lex, error);
    }
  }

  /* the actual value is at most of the same length as the source
     string, because:
       - shortcut escapes (e.g. "\t") (length 2) are converted to 1 byte
       - a single \uXXXX escape (length 6) is converted to at most 3 bytes
       - two \uXXXX escapes (length 12) forming an UTF-16 surrogate pair
         are converted to 4 bytes
  */
  t = jsonp_malloc (lex->saved_text.length + 1);
  if (!t) {
    /* this is not very nice, since TOKEN_INVALID is returned */
    goto out;
  }

  lex->value.string.val = t;

  /* + 1 to skip the " */
  p = strbuffer_value (&lex->saved_text) + 1;

  while (*p != '"') {
    if (*p == '\\') {
      p++;
      if (*p == 'u') {
        size_t   length;
        int32_t  value;

        value = decode_unicode_escape (p);
        if (value < 0) {
          error_set (
            error,
            lex,
            json_error_invalid_syntax,
            "invalid Unicode escape '%.6s'",
            p - 1
            );
          goto out;
        }

        p += 5;

        if ((0xD800 <= value) && (value <= 0xDBFF)) {
          /* surrogate pair */
          if ((*p == '\\') && (*(p + 1) == 'u')) {
            int32_t  value2 = decode_unicode_escape (++p);
            if (value2 < 0) {
              error_set (
                error,
                lex,
                json_error_invalid_syntax,
                "invalid Unicode escape '%.6s'",
                p - 1
                );
              goto out;
            }

            p += 5;

            if ((0xDC00 <= value2) && (value2 <= 0xDFFF)) {
              /* valid second surrogate */
              value =
                ((value - 0xD800) << 10) + (value2 - 0xDC00) + 0x10000;
            } else {
              /* invalid second surrogate */
              error_set (
                error,
                lex,
                json_error_invalid_syntax,
                "invalid Unicode '\\u%04X\\u%04X'",
                value,
                value2
                );
              goto out;
            }
          } else {
            /* no second surrogate */
            error_set (
              error,
              lex,
              json_error_invalid_syntax,
              "invalid Unicode '\\u%04X'",
              value
              );
            goto out;
          }
        } else if ((0xDC00 <= value) && (value <= 0xDFFF)) {
          error_set (
            error,
            lex,
            json_error_invalid_syntax,
            "invalid Unicode '\\u%04X'",
            value
            );
          goto out;
        }

        if (utf8_encode (value, t, &length)) {
          assert (0);
        }

        t += length;
      } else {
        switch (*p) {
          case '"':
          case '\\':
          case '/':
            *t = *p;
            break;
          case 'b':
            *t = '\b';
            break;
          case 'f':
            *t = '\f';
            break;
          case 'n':
            *t = '\n';
            break;
          case 'r':
            *t = '\r';
            break;
          case 't':
            *t = '\t';
            break;
          default:
            assert (0);
        }

        t++;
        p++;
      }
    } else {
      *(t++) = *(p++);
    }
  }

  *t                    = '\0';
  lex->value.string.len = t - lex->value.string.val;
  lex->token            = TOKEN_STRING;
  return;

out:
  lex_free_string (lex);
}

#ifndef JANSSON_USING_CMAKE /* disabled if using cmake */
  #if JSON_INTEGER_IS_LONG_LONG
    #ifdef _MSC_VER /* Microsoft Visual Studio */
#define json_strtoint  _strtoi64
    #else
#define json_strtoint  strtoll
    #endif
  #else
#define json_strtoint  strtol
  #endif
#endif

static int
lex_scan_number (
  lex_t         *lex,
  int           c,
  json_error_t  *error
  )
{
  const char  *saved_text;
  char        *end;
  double      doubleval;

  lex->token = TOKEN_INVALID;

  if (c == '-') {
    c = lex_get_save (lex, error);
  }

  if (c == '0') {
    c = lex_get_save (lex, error);
    if (l_isdigit (c)) {
      lex_unget_unsave (lex, c);
      goto out;
    }
  } else if (l_isdigit (c)) {
    do {
      c = lex_get_save (lex, error);
    } while (l_isdigit (c));
  } else {
    lex_unget_unsave (lex, c);
    goto out;
  }

  if (!(lex->flags & JSON_DECODE_INT_AS_REAL) && (c != '.') && (c != 'E') && (c != 'e')) {
    json_int_t  intval;

    lex_unget_unsave (lex, c);

    saved_text = strbuffer_value (&lex->saved_text);

    errno  = 0;
    intval = json_strtoint (saved_text, &end, 10);
    if (errno == ERANGE) {
      if (intval < 0) {
        error_set (
          error,
          lex,
          json_error_numeric_overflow,
          "too big negative integer"
          );
      } else {
        error_set (error, lex, json_error_numeric_overflow, "too big integer");
      }

      goto out;
    }

    assert (end == saved_text + lex->saved_text.length);

    lex->token         = TOKEN_INTEGER;
    lex->value.integer = intval;
    return 0;
  }

  if (c == '.') {
    c = lex_get (lex, error);
    if (!l_isdigit (c)) {
      lex_unget (lex, c);
      goto out;
    }

    lex_save (lex, c);

    do {
      c = lex_get_save (lex, error);
    } while (l_isdigit (c));
  }

  if ((c == 'E') || (c == 'e')) {
    c = lex_get_save (lex, error);
    if ((c == '+') || (c == '-')) {
      c = lex_get_save (lex, error);
    }

    if (!l_isdigit (c)) {
      lex_unget_unsave (lex, c);
      goto out;
    }

    do {
      c = lex_get_save (lex, error);
    } while (l_isdigit (c));
  }

  lex_unget_unsave (lex, c);

  if (jsonp_strtod (&lex->saved_text, &doubleval)) {
    error_set (error, lex, json_error_numeric_overflow, "real number overflow");
    goto out;
  }

  lex->token         = TOKEN_INTEGER;
  lex->value.integer = doubleval;
  return 0;

out:
  return -1;
}

static int
lex_scan (
  lex_t         *lex,
  json_error_t  *error
  )
{
  int  c;

  strbuffer_clear (&lex->saved_text);

  if (lex->token == TOKEN_STRING) {
    lex_free_string (lex);
  }

  do {
    c = lex_get (lex, error);
  } while (c == ' ' || c == '\t' || c == '\n' || c == '\r');

  if (c == STREAM_STATE_EOF) {
    lex->token = TOKEN_EOF;
    goto out;
  }

  if (c == STREAM_STATE_ERROR) {
    lex->token = TOKEN_INVALID;
    goto out;
  }

  lex_save (lex, c);

  if ((c == '{') || (c == '}') || (c == '[') || (c == ']') || (c == ':') || (c == ',')) {
    lex->token = c;
  } else if (c == '"') {
    lex_scan_string (lex, error);
  } else if (l_isdigit (c) || (c == '-')) {
    if (lex_scan_number (lex, c, error)) {
      goto out;
    }
  } else if (l_isalpha (c)) {
    /* eat up the whole identifier for clearer error messages */
    const char  *saved_text;

    do {
      c = lex_get_save (lex, error);
    } while (l_isalpha (c));

    lex_unget_unsave (lex, c);

    saved_text = strbuffer_value (&lex->saved_text);

    if (strcmp (saved_text, "true") == 0) {
      lex->token = TOKEN_TRUE;
    } else if (strcmp (saved_text, "false") == 0) {
      lex->token = TOKEN_FALSE;
    } else if (strcmp (saved_text, "null") == 0) {
      lex->token = TOKEN_NULL;
    } else {
      lex->token = TOKEN_INVALID;
    }
  } else {
    /* save the rest of the input UTF-8 sequence to get an error
       message of valid UTF-8 */
    lex_save_cached (lex);
    lex->token = TOKEN_INVALID;
  }

out:
  return lex->token;
}

static char *
lex_steal_string (
  lex_t   *lex,
  size_t  *out_len
  )
{
  char  *result = NULL;

  if (lex->token == TOKEN_STRING) {
    result                = lex->value.string.val;
    *out_len              = lex->value.string.len;
    lex->value.string.val = NULL;
    lex->value.string.len = 0;
  }

  return result;
}

static int
lex_init (
  lex_t     *lex,
  get_func  get,
  size_t    flags,
  void      *data
  )
{
  stream_init (&lex->stream, get, data);
  if (strbuffer_init (&lex->saved_text)) {
    return -1;
  }

  lex->flags = flags;
  lex->token = TOKEN_INVALID;
  return 0;
}

static void
lex_close (
  lex_t  *lex
  )
{
  if (lex->token == TOKEN_STRING) {
    lex_free_string (lex);
  }

  strbuffer_close (&lex->saved_text);
}

/*** parser ***/

static json_t *
parse_value (
  lex_t         *lex,
  size_t        flags,
  json_error_t  *error
  );

static json_t *
parse_object (
  lex_t         *lex,
  size_t        flags,
  json_error_t  *error
  )
{
  json_t  *object = json_object ();

  if (!object) {
    return NULL;
  }

  lex_scan (lex, error);
  if (lex->token == '}') {
    return object;
  }

  while (1) {
    char    *key;
    size_t  len;
    json_t  *value;

    if (lex->token != TOKEN_STRING) {
      error_set (error, lex, json_error_invalid_syntax, "string or '}' expected");
      goto error;
    }

    key = lex_steal_string (lex, &len);
    if (!key) {
      return NULL;
    }

    if (memchr (key, '\0', len)) {
      jsonp_free (key);
      error_set (
        error,
        lex,
        json_error_null_byte_in_key,
        "NUL byte in object key not supported"
        );
      goto error;
    }

    if (flags & JSON_REJECT_DUPLICATES) {
      if (json_object_get (object, key)) {
        jsonp_free (key);
        error_set (error, lex, json_error_duplicate_key, "duplicate object key");
        goto error;
      }
    }

    lex_scan (lex, error);
    if (lex->token != ':') {
      jsonp_free (key);
      error_set (error, lex, json_error_invalid_syntax, "':' expected");
      goto error;
    }

    lex_scan (lex, error);
    value = parse_value (lex, flags, error);
    if (!value) {
      jsonp_free (key);
      goto error;
    }

    if (json_object_set_new_nocheck (object, key, value)) {
      jsonp_free (key);
      goto error;
    }

    jsonp_free (key);

    lex_scan (lex, error);
    if (lex->token != ',') {
      break;
    }

    lex_scan (lex, error);
  }

  if (lex->token != '}') {
    error_set (error, lex, json_error_invalid_syntax, "'}' expected");
    goto error;
  }

  return object;

error:
  json_decref (object);
  return NULL;
}

static json_t *
parse_array (
  lex_t         *lex,
  size_t        flags,
  json_error_t  *error
  )
{
  json_t  *array = json_array ();

  if (!array) {
    return NULL;
  }

  lex_scan (lex, error);
  if (lex->token == ']') {
    return array;
  }

  while (lex->token) {
    json_t  *elem = parse_value (lex, flags, error);
    if (!elem) {
      goto error;
    }

    if (json_array_append_new (array, elem)) {
      goto error;
    }

    lex_scan (lex, error);
    if (lex->token != ',') {
      break;
    }

    lex_scan (lex, error);
  }

  if (lex->token != ']') {
    error_set (error, lex, json_error_invalid_syntax, "']' expected");
    goto error;
  }

  return array;

error:
  json_decref (array);
  return NULL;
}

static json_t *
parse_value (
  lex_t         *lex,
  size_t        flags,
  json_error_t  *error
  )
{
  json_t  *json;

  lex->depth++;
  if (lex->depth > JSON_PARSER_MAX_DEPTH) {
    error_set (error, lex, json_error_stack_overflow, "maximum parsing depth reached");
    return NULL;
  }

  switch (lex->token) {
    case TOKEN_STRING:
    {
      const char  *value = lex->value.string.val;
      size_t      len    = lex->value.string.len;

      if (!(flags & JSON_ALLOW_NUL)) {
        if (memchr (value, '\0', len)) {
          error_set (
            error,
            lex,
            json_error_null_character,
            "\\u0000 is not allowed without JSON_ALLOW_NUL"
            );
          return NULL;
        }
      }

      json                  = jsonp_stringn_nocheck_own (value, len);
      lex->value.string.val = NULL;
      lex->value.string.len = 0;
      break;
    }

    case TOKEN_INTEGER:
    {
      json = json_integer (lex->value.integer);
      break;
    }

    case TOKEN_REAL:
    {
      json = json_real (lex->value.real);
      break;
    }

    case TOKEN_TRUE:
      json = json_true ();
      break;

    case TOKEN_FALSE:
      json = json_false ();
      break;

    case TOKEN_NULL:
      json = json_null ();
      break;

    case '{':
      json = parse_object (lex, flags, error);
      break;

    case '[':
      json = parse_array (lex, flags, error);
      break;

    case TOKEN_INVALID:
      error_set (error, lex, json_error_invalid_syntax, "invalid token");
      return NULL;

    default:
      error_set (error, lex, json_error_invalid_syntax, "unexpected token");
      return NULL;
  }

  if (!json) {
    return NULL;
  }

  lex->depth--;
  return json;
}

static json_t *
parse_json (
  lex_t         *lex,
  size_t        flags,
  json_error_t  *error
  )
{
  json_t  *result;

  lex->depth = 0;

  lex_scan (lex, error);
  if (!(flags & JSON_DECODE_ANY)) {
    if ((lex->token != '[') && (lex->token != '{')) {
      error_set (error, lex, json_error_invalid_syntax, "'[' or '{' expected");
      return NULL;
    }
  }

  result = parse_value (lex, flags, error);
  if (!result) {
    return NULL;
  }

  if (!(flags & JSON_DISABLE_EOF_CHECK)) {
    lex_scan (lex, error);
    if (lex->token != TOKEN_EOF) {
      error_set (
        error,
        lex,
        json_error_end_of_input_expected,
        "end of file expected"
        );
      json_decref (result);
      return NULL;
    }
  }

  if (error) {
    /* Save the position even though there was no error */
    error->position = (int)lex->stream.position;
  }

  return result;
}

typedef struct {
  const char    *data;
  size_t        pos;
} string_data_t;

static int
string_get (
  void  *data
  )
{
  char           c;
  string_data_t  *stream = (string_data_t *)data;

  c = stream->data[stream->pos];
  if (c == '\0') {
    return EOF;
  } else {
    stream->pos++;
    return (unsigned char)c;
  }
}

json_t *
json_loads (
  const char    *string,
  size_t        flags,
  json_error_t  *error
  )
{
  lex_t          lex;
  json_t         *result;
  string_data_t  stream_data;

  jsonp_error_init (error, "<string>");

  if (string == NULL) {
    error_set (error, NULL, json_error_invalid_argument, "wrong arguments");
    return NULL;
  }

  stream_data.data = string;
  stream_data.pos  = 0;

  if (lex_init (&lex, string_get, flags, (void *)&stream_data)) {
    return NULL;
  }

  result = parse_json (&lex, flags, error);

  lex_close (&lex);
  return result;
}

typedef struct {
  const char    *data;
  size_t        len;
  size_t        pos;
} buffer_data_t;

static int
buffer_get (
  void  *data
  )
{
  char           c;
  buffer_data_t  *stream = data;

  if (stream->pos >= stream->len) {
    return EOF;
  }

  c = stream->data[stream->pos];
  stream->pos++;
  return (unsigned char)c;
}

json_t *
json_loadb (
  const char    *buffer,
  size_t        buflen,
  size_t        flags,
  json_error_t  *error
  )
{
  lex_t          lex;
  json_t         *result;
  buffer_data_t  stream_data;

  jsonp_error_init (error, "<buffer>");

  if (buffer == NULL) {
    error_set (error, NULL, json_error_invalid_argument, "wrong arguments");
    return NULL;
  }

  stream_data.data = buffer;
  stream_data.pos  = 0;
  stream_data.len  = buflen;

  if (lex_init (&lex, buffer_get, flags, (void *)&stream_data)) {
    return NULL;
  }

  result = parse_json (&lex, flags, error);

  lex_close (&lex);
  return result;
}

json_t *
json_loadf (
  FILE          *input,
  size_t        flags,
  json_error_t  *error
  )
{
  lex_t       lex;
  const char  *source;
  json_t      *result;

 #ifdef HAVE_UNISTD_H
  if (input == stdin) {
    source = "<stdin>";
  } else
 #endif
  source = "<stream>";

  jsonp_error_init (error, source);

  if (input == NULL) {
    error_set (error, NULL, json_error_invalid_argument, "wrong arguments");
    return NULL;
  }

  if (lex_init (&lex, (get_func)fgetc, flags, input)) {
    return NULL;
  }

  result = parse_json (&lex, flags, error);

  lex_close (&lex);
  return result;
}

static int
fd_get_func (
  int  *fd
  )
{
 #ifdef HAVE_UNISTD_H
  uint8_t  c;
  if (read (*fd, &c, 1) == 1) {
    return c;
  }

 #endif
  return EOF;
}

json_t *
json_loadfd (
  int           input,
  size_t        flags,
  json_error_t  *error
  )
{
  lex_t       lex;
  const char  *source;
  json_t      *result;

 #ifdef HAVE_UNISTD_H
  if (input == STDIN_FILENO) {
    source = "<stdin>";
  } else
 #endif
  source = "<stream>";

  jsonp_error_init (error, source);

  if (input < 0) {
    error_set (error, NULL, json_error_invalid_argument, "wrong arguments");
    return NULL;
  }

  if (lex_init (&lex, (get_func)fd_get_func, flags, &input)) {
    return NULL;
  }

  result = parse_json (&lex, flags, error);

  lex_close (&lex);
  return result;
}

json_t *
json_load_file (
  const char    *path,
  size_t        flags,
  json_error_t  *error
  )
{
  json_t  *result;
  FILE    *fp;

  jsonp_error_init (error, path);

  if (path == NULL) {
    error_set (error, NULL, json_error_invalid_argument, "wrong arguments");
    return NULL;
  }

  fp = fopen (path, "rb");
  if (!fp) {
    error_set (
      error,
      NULL,
      json_error_cannot_open_file,
      "unable to open %s: %s",
      path,
      strerror (errno)
      );
    return NULL;
  }

  result = json_loadf (fp, flags, error);

  fclose (fp);
  return result;
}

#define MAX_BUF_LEN  1024

typedef struct {
  char                    data[MAX_BUF_LEN];
  size_t                  len;
  size_t                  pos;
  json_load_callback_t    callback;
  void                    *arg;
} callback_data_t;

static int
callback_get (
  void  *data
  )
{
  char             c;
  callback_data_t  *stream = data;

  if (stream->pos >= stream->len) {
    stream->pos = 0;
    stream->len = stream->callback (stream->data, MAX_BUF_LEN, stream->arg);
    if ((stream->len == 0) || (stream->len == (size_t)-1)) {
      return EOF;
    }
  }

  c = stream->data[stream->pos];
  stream->pos++;
  return (unsigned char)c;
}

json_t *
json_load_callback (
  json_load_callback_t  callback,
  void                  *arg,
  size_t                flags,
  json_error_t          *error
  )
{
  lex_t   lex;
  json_t  *result;

  callback_data_t  stream_data;

  memset (&stream_data, 0, sizeof (stream_data));
  stream_data.callback = callback;
  stream_data.arg      = arg;

  jsonp_error_init (error, "<callback>");

  if (callback == NULL) {
    error_set (error, NULL, json_error_invalid_argument, "wrong arguments");
    return NULL;
  }

  if (lex_init (&lex, (get_func)callback_get, flags, &stream_data)) {
    return NULL;
  }

  result = parse_json (&lex, flags, error);

  lex_close (&lex);
  return result;
}