summaryrefslogtreecommitdiffstats
path: root/src/xplist.c
blob: fc8fd61b41728fa5737566f29f66c4656c8c00b7 (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
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
/*
 * xplist.c
 * XML plist implementation
 *
 * Copyright (c) 2010-2017 Nikias Bassen All Rights Reserved.
 * Copyright (c) 2010-2015 Martin Szulecki All Rights Reserved.
 * Copyright (c) 2008 Jonathan Beck All Rights Reserved.
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
 */

#ifdef HAVE_CONFIG_H
#include <config.h>
#endif

#ifdef HAVE_STRPTIME
#define _XOPEN_SOURCE 600
#endif

#include <string.h>
#include <assert.h>
#include <stdlib.h>
#include <stdio.h>
#include <time.h>

#include <inttypes.h>
#include <math.h>
#include <limits.h>

#include <node.h>
#include <node_list.h>

#include "plist.h"
#include "base64.h"
#include "strbuf.h"
#include "time64.h"

#define XPLIST_KEY	"key"
#define XPLIST_KEY_LEN 3
#define XPLIST_FALSE	"false"
#define XPLIST_FALSE_LEN 5
#define XPLIST_TRUE	"true"
#define XPLIST_TRUE_LEN 4
#define XPLIST_INT	"integer"
#define XPLIST_INT_LEN 7
#define XPLIST_REAL	"real"
#define XPLIST_REAL_LEN 4
#define XPLIST_DATE	"date"
#define XPLIST_DATE_LEN 4
#define XPLIST_DATA	"data"
#define XPLIST_DATA_LEN 4
#define XPLIST_STRING	"string"
#define XPLIST_STRING_LEN 6
#define XPLIST_ARRAY	"array"
#define XPLIST_ARRAY_LEN 5
#define XPLIST_DICT	"dict"
#define XPLIST_DICT_LEN 4

#define MAC_EPOCH 978307200

#define MAX_DATA_BYTES_PER_LINE(__i) (((76 - (__i << 3)) >> 2) * 3)

static const char XML_PLIST_PROLOG[] = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n\
<!DOCTYPE plist PUBLIC \"-//Apple//DTD PLIST 1.0//EN\" \"http://www.apple.com/DTDs/PropertyList-1.0.dtd\">\n\
<plist version=\"1.0\">\n";
static const char XML_PLIST_EPILOG[] = "</plist>\n";

#ifdef DEBUG
static int plist_xml_debug = 0;
#define PLIST_XML_ERR(...) if (plist_xml_debug) { fprintf(stderr, "libplist[xmlparser] ERROR: " __VA_ARGS__); }
#else
#define PLIST_XML_ERR(...)
#endif

void plist_xml_init(void)
{
    /* init XML stuff */
#ifdef DEBUG
    char *env_debug = getenv("PLIST_XML_DEBUG");
    if (env_debug && !strcmp(env_debug, "1")) {
        plist_xml_debug = 1;
    }
#endif
}

void plist_xml_deinit(void)
{
    /* deinit XML stuff */
}

static size_t dtostr(char *buf, size_t bufsize, double realval)
{
    double f = realval;
    double ip = 0.0;
    int64_t v;
    size_t len;
    size_t p;
    double CORR = 0.0000005;

    f = modf(f, &ip);
    v = (int64_t)ip;
    if (f < 0) {
        if (((int)((f - CORR) * -10.0f)) >= 10) {
            v--;
            f = 0;
        }
    } else {
        if (((int)((f + CORR) * 10.0f)) >= 10) {
            v++;
            f = 0;
        }
    }
    len = snprintf(buf, bufsize, "%s%"PRIi64, ((f < 0) && (ip >= 0)) ? "-" : "", v);
    if (len >= bufsize) {
        return 0;
    }

    if (f < 0) {
        f *= -1;
    }
    f += CORR;

    p = len;
    buf[p++] = '.';

    while (p < bufsize && (p <= len+6)) {
        f = modf(f*10, &ip);
        v = (int)ip;
        buf[p++] = (v + 0x30);
    }
    buf[p] = '\0';
    return p;
}

static void node_to_xml(node_t* node, bytearray_t **outbuf, uint32_t depth)
{
    plist_data_t node_data = NULL;

    char isStruct = FALSE;
    char tagOpen = FALSE;

    const char *tag = NULL;
    size_t tag_len = 0;
    char *val = NULL;
    size_t val_len = 0;

    uint32_t i = 0;

    if (!node)
        return;

    node_data = plist_get_data(node);

    switch (node_data->type)
    {
    case PLIST_BOOLEAN:
    {
        if (node_data->boolval) {
            tag = XPLIST_TRUE;
            tag_len = XPLIST_TRUE_LEN;
        } else {
            tag = XPLIST_FALSE;
            tag_len = XPLIST_FALSE_LEN;
        }
    }
    break;

    case PLIST_UINT:
        tag = XPLIST_INT;
        tag_len = XPLIST_INT_LEN;
        val = (char*)malloc(64);
        if (node_data->length == 16) {
            val_len = snprintf(val, 64, "%"PRIu64, node_data->intval);
        } else {
            val_len = snprintf(val, 64, "%"PRIi64, node_data->intval);
        }
        break;

    case PLIST_REAL:
        tag = XPLIST_REAL;
        tag_len = XPLIST_REAL_LEN;
        val = (char*)malloc(64);
        val_len = dtostr(val, 64, node_data->realval);
        break;

    case PLIST_STRING:
        tag = XPLIST_STRING;
        tag_len = XPLIST_STRING_LEN;
        /* contents processed directly below */
        break;

    case PLIST_KEY:
        tag = XPLIST_KEY;
        tag_len = XPLIST_KEY_LEN;
        /* contents processed directly below */
        break;

    case PLIST_DATA:
        tag = XPLIST_DATA;
        tag_len = XPLIST_DATA_LEN;
        /* contents processed directly below */
        break;
    case PLIST_ARRAY:
        tag = XPLIST_ARRAY;
        tag_len = XPLIST_ARRAY_LEN;
        isStruct = (node->children) ? TRUE : FALSE;
        break;
    case PLIST_DICT:
        tag = XPLIST_DICT;
        tag_len = XPLIST_DICT_LEN;
        isStruct = (node->children) ? TRUE : FALSE;
        break;
    case PLIST_DATE:
        tag = XPLIST_DATE;
        tag_len = XPLIST_DATE_LEN;
        {
            Time64_T timev = (Time64_T)node_data->realval + MAC_EPOCH;
            struct TM _btime;
            struct TM *btime = gmtime64_r(&timev, &_btime);
            if (btime) {
                val = (char*)malloc(24);
                memset(val, 0, 24);
                struct tm _tmcopy;
                copy_TM64_to_tm(btime, &_tmcopy);
                val_len = strftime(val, 24, "%Y-%m-%dT%H:%M:%SZ", &_tmcopy);
                if (val_len <= 0) {
                    free (val);
                    val = NULL;
                }
            }
        }
        break;
    case PLIST_UID:
        tag = XPLIST_DICT;
        tag_len = XPLIST_DICT_LEN;
        val = (char*)malloc(64);
        if (node_data->length == 16) {
            val_len = snprintf(val, 64, "%"PRIu64, node_data->intval);
        } else {
            val_len = snprintf(val, 64, "%"PRIi64, node_data->intval);
        }
        break;
    default:
        break;
    }

    for (i = 0; i < depth; i++) {
        str_buf_append(*outbuf, "\t", 1);
    }

    /* append tag */
    str_buf_append(*outbuf, "<", 1);
    str_buf_append(*outbuf, tag, tag_len);
    if (node_data->type == PLIST_STRING || node_data->type == PLIST_KEY) {
        size_t j;
        size_t len;
        off_t start = 0;
        off_t cur = 0;

        str_buf_append(*outbuf, ">", 1);
        tagOpen = TRUE;

        /* make sure we convert the following predefined xml entities */
        /* < = &lt; > = &gt; & = &amp; */
        len = node_data->length;
        for (j = 0; j < len; j++) {
            switch (node_data->strval[j]) {
            case '<':
                str_buf_append(*outbuf, node_data->strval + start, cur - start);
                str_buf_append(*outbuf, "&lt;", 4);
                start = cur+1;
                break;
            case '>':
                str_buf_append(*outbuf, node_data->strval + start, cur - start);
                str_buf_append(*outbuf, "&gt;", 4);
                start = cur+1;
                break;
            case '&':
                str_buf_append(*outbuf, node_data->strval + start, cur - start);
                str_buf_append(*outbuf, "&amp;", 5);
                start = cur+1;
                break;
            default:
                break;
            }
            cur++;
        }
        str_buf_append(*outbuf, node_data->strval + start, cur - start);
    } else if (node_data->type == PLIST_DATA) {
        str_buf_append(*outbuf, ">", 1);
        tagOpen = TRUE;
        str_buf_append(*outbuf, "\n", 1);
        if (node_data->length > 0) {
            uint32_t j = 0;
            uint32_t indent = (depth > 8) ? 8 : depth;
            uint32_t maxread = MAX_DATA_BYTES_PER_LINE(indent);
            size_t count = 0;
            size_t amount = (node_data->length / 3 * 4) + 4 + (((node_data->length / maxread) + 1) * (indent+1));
            if ((*outbuf)->len + amount > (*outbuf)->capacity) {
                str_buf_grow(*outbuf, amount);
            }
            while (j < node_data->length) {
                for (i = 0; i < indent; i++) {
                    str_buf_append(*outbuf, "\t", 1);
                }
                count = (node_data->length-j < maxread) ? node_data->length-j : maxread;
                assert((*outbuf)->len + count < (*outbuf)->capacity);
                (*outbuf)->len += base64encode((char*)(*outbuf)->data + (*outbuf)->len, node_data->buff + j, count);
                str_buf_append(*outbuf, "\n", 1);
                j+=count;
            }
        }
        for (i = 0; i < depth; i++) {
            str_buf_append(*outbuf, "\t", 1);
        }
    } else if (node_data->type == PLIST_UID) {
        /* special case for UID nodes: create a DICT */
        str_buf_append(*outbuf, ">", 1);
        tagOpen = TRUE;
        str_buf_append(*outbuf, "\n", 1);

        /* add CF$UID key */
        for (i = 0; i < depth+1; i++) {
            str_buf_append(*outbuf, "\t", 1);
        }
        str_buf_append(*outbuf, "<key>CF$UID</key>", 17);
        str_buf_append(*outbuf, "\n", 1);

        /* add UID value */
        for (i = 0; i < depth+1; i++) {
            str_buf_append(*outbuf, "\t", 1);
        }
        str_buf_append(*outbuf, "<integer>", 9);
        str_buf_append(*outbuf, val, val_len);
        str_buf_append(*outbuf, "</integer>", 10);
        str_buf_append(*outbuf, "\n", 1);

        for (i = 0; i < depth; i++) {
            str_buf_append(*outbuf, "\t", 1);
        }
    } else if (val) {
        str_buf_append(*outbuf, ">", 1);
        tagOpen = TRUE;
        str_buf_append(*outbuf, val, val_len);
    } else if (isStruct) {
        tagOpen = TRUE;
        str_buf_append(*outbuf, ">", 1);
    } else {
        tagOpen = FALSE;
        str_buf_append(*outbuf, "/>", 2);
    }
    free(val);

    if (isStruct) {
        /* add newline for structured types */
        str_buf_append(*outbuf, "\n", 1);

        /* add child nodes */
        if (node_data->type == PLIST_DICT && node->children) {
            assert((node->children->count % 2) == 0);
        }
        node_t *ch;
        for (ch = node_first_child(node); ch; ch = node_next_sibling(ch)) {
            node_to_xml(ch, outbuf, depth+1);
        }

        /* fix indent for structured types */
        for (i = 0; i < depth; i++) {
            str_buf_append(*outbuf, "\t", 1);
        }
    }

    if (tagOpen) {
        /* add closing tag */
        str_buf_append(*outbuf, "</", 2);
        str_buf_append(*outbuf, tag, tag_len);
        str_buf_append(*outbuf, ">", 1);
    }
    str_buf_append(*outbuf, "\n", 1);

    return;
}

static void parse_date(const char *strval, struct TM *btime)
{
    if (!btime) return;
    memset(btime, 0, sizeof(struct tm));
    if (!strval) return;
#ifdef HAVE_STRPTIME
    strptime((char*)strval, "%Y-%m-%dT%H:%M:%SZ", btime);
#else
#ifdef USE_TM64
    #define PLIST_SSCANF_FORMAT "%lld-%d-%dT%d:%d:%dZ"
#else
    #define PLIST_SSCANF_FORMAT "%d-%d-%dT%d:%d:%dZ"
#endif
    sscanf(strval, PLIST_SSCANF_FORMAT, &btime->tm_year, &btime->tm_mon, &btime->tm_mday, &btime->tm_hour, &btime->tm_min, &btime->tm_sec);
    btime->tm_year-=1900;
    btime->tm_mon--;
#endif
    btime->tm_isdst=0;
}

#define PO10i_LIMIT (INT64_MAX/10)

/* based on https://stackoverflow.com/a/4143288 */
static int num_digits_i(int64_t i)
{
    int n;
    int64_t po10;
    n=1;
    if (i < 0) {
        i = -i;
        n++;
    }
    po10=10;
    while (i>=po10) {
        n++;
        if (po10 > PO10i_LIMIT) break;
        po10*=10;
    }
    return n;
}

#define PO10u_LIMIT (UINT64_MAX/10)

/* based on https://stackoverflow.com/a/4143288 */
static int num_digits_u(uint64_t i)
{
    int n;
    uint64_t po10;
    n=1;
    po10=10;
    while (i>=po10) {
        n++;
        if (po10 > PO10u_LIMIT) break;
        po10*=10;
    }
    return n;
}

static void node_estimate_size(node_t *node, uint64_t *size, uint32_t depth)
{
    plist_data_t data;
    if (!node) {
        return;
    }
    data = plist_get_data(node);
    if (node->children) {
        node_t *ch;
        for (ch = node_first_child(node); ch; ch = node_next_sibling(ch)) {
            node_estimate_size(ch, size, depth + 1);
        }
        switch (data->type) {
        case PLIST_DICT:
            *size += (XPLIST_DICT_LEN << 1) + 7;
            break;
        case PLIST_ARRAY:
            *size += (XPLIST_ARRAY_LEN << 1) + 7;
            break;
        default:
            break;
	}
        *size += (depth << 1);
    } else {
        uint32_t indent = (depth > 8) ? 8 : depth;
        switch (data->type) {
        case PLIST_DATA: {
            uint32_t req_lines = (data->length / MAX_DATA_BYTES_PER_LINE(indent)) + 1;
            uint32_t b64len = data->length + (data->length / 3);
            b64len += b64len % 4;
            *size += b64len;
            *size += (XPLIST_DATA_LEN << 1) + 5 + (indent+1) * (req_lines+1) + 1;
        }   break;
        case PLIST_STRING:
            *size += data->length;
            *size += (XPLIST_STRING_LEN << 1) + 6;
            break;
        case PLIST_KEY:
            *size += data->length;
            *size += (XPLIST_KEY_LEN << 1) + 6;
            break;
        case PLIST_UINT:
            if (data->length == 16) {
                *size += num_digits_u(data->intval);
            } else {
                *size += num_digits_i((int64_t)data->intval);
            }
            *size += (XPLIST_INT_LEN << 1) + 6;
            break;
        case PLIST_REAL:
            *size += num_digits_i((int64_t)data->realval) + 7;
            *size += (XPLIST_REAL_LEN << 1) + 6;
            break;
        case PLIST_DATE:
            *size += 20; /* YYYY-MM-DDThh:mm:ssZ */
            *size += (XPLIST_DATE_LEN << 1) + 6;
            break;
        case PLIST_BOOLEAN:
            *size += ((data->boolval) ? XPLIST_TRUE_LEN : XPLIST_FALSE_LEN) + 4;
            break;
        case PLIST_DICT:
            *size += XPLIST_DICT_LEN + 4; /* <dict/> */
            break;
        case PLIST_ARRAY:
            *size += XPLIST_ARRAY_LEN + 4; /* <array/> */
            break;
        case PLIST_UID:
            *size += num_digits_i((int64_t)data->intval);
            *size += (XPLIST_DICT_LEN << 1) + 7;
            *size += indent + ((indent+1) << 1);
            *size += 18; /* <key>CF$UID</key> */
            *size += (XPLIST_INT_LEN << 1) + 6;
            break;
        default:
            break;
        }
        *size += indent;
    }
}

PLIST_API void plist_to_xml(plist_t plist, char **plist_xml, uint32_t * length)
{
    uint64_t size = 0;
    node_estimate_size(plist, &size, 0);
    size += sizeof(XML_PLIST_PROLOG) + sizeof(XML_PLIST_EPILOG) - 1;

    strbuf_t *outbuf = str_buf_new(size);

    str_buf_append(outbuf, XML_PLIST_PROLOG, sizeof(XML_PLIST_PROLOG)-1);

    node_to_xml(plist, &outbuf, 0);

    str_buf_append(outbuf, XML_PLIST_EPILOG, sizeof(XML_PLIST_EPILOG));

    *plist_xml = outbuf->data;
    *length = outbuf->len - 1;

    outbuf->data = NULL;
    str_buf_free(outbuf);
}

struct _parse_ctx {
    const char *pos;
    const char *end;
    int err;
};
typedef struct _parse_ctx* parse_ctx;

static void parse_skip_ws(parse_ctx ctx)
{
    while (ctx->pos < ctx->end && ((*(ctx->pos) == ' ') || (*(ctx->pos) == '\t') || (*(ctx->pos) == '\r') || (*(ctx->pos) == '\n'))) {
        ctx->pos++;
    }
}

static void find_char(parse_ctx ctx, char c, int skip_quotes)
{
    while (ctx->pos < ctx->end && (*(ctx->pos) != c)) {
        if (skip_quotes && (c != '"') && (*(ctx->pos) == '"')) {
            ctx->pos++;
            find_char(ctx, '"', 0);
            if (ctx->pos >= ctx->end) {
                PLIST_XML_ERR("EOF while looking for matching double quote\n");
                return;
            }
            if (*(ctx->pos) != '"') {
                PLIST_XML_ERR("Unmatched double quote\n");
                return;
            }
        }
        ctx->pos++;
    }
}

static void find_str(parse_ctx ctx, const char *str, size_t len, int skip_quotes)
{
    while (ctx->pos < (ctx->end - len)) {
        if (!strncmp(ctx->pos, str, len)) {
            break;
        }
        if (skip_quotes && (*(ctx->pos) == '"')) {
            ctx->pos++;
            find_char(ctx, '"', 0);
            if (ctx->pos >= ctx->end) {
                PLIST_XML_ERR("EOF while looking for matching double quote\n");
                return;
            }
            if (*(ctx->pos) != '"') {
                PLIST_XML_ERR("Unmatched double quote\n");
                return;
            }
        }
        ctx->pos++;
    }
}

static void find_next(parse_ctx ctx, const char *nextchars, int numchars, int skip_quotes)
{
    int i = 0;
    while (ctx->pos < ctx->end) {
        if (skip_quotes && (*(ctx->pos) == '"')) {
            ctx->pos++;
            find_char(ctx, '"', 0);
            if (ctx->pos >= ctx->end) {
                PLIST_XML_ERR("EOF while looking for matching double quote\n");
                return;
            }
            if (*(ctx->pos) != '"') {
                PLIST_XML_ERR("Unmatched double quote\n");
                return;
            }
        }
        for (i = 0; i < numchars; i++) {
            if (*(ctx->pos) == nextchars[i]) {
                return;
            }
        }
        ctx->pos++;
    }
}

typedef struct {
    const char *begin;
    size_t length;
    int is_cdata;
    void *next;
} text_part_t;

static text_part_t* text_part_init(text_part_t* part, const char *begin, size_t length, int is_cdata)
{
    part->begin = begin;
    part->length = length;
    part->is_cdata = is_cdata;
    part->next = NULL;
    return part;
}

static void text_parts_free(text_part_t *tp)
{
    while (tp) {
        text_part_t *tmp = tp;
        tp = tp->next;
        free(tmp);
    }
}

static text_part_t* text_part_append(text_part_t* parts, const char *begin, size_t length, int is_cdata)
{
    text_part_t* newpart = malloc(sizeof(text_part_t));
    assert(newpart);
    parts->next = text_part_init(newpart, begin, length, is_cdata);
    return newpart;
}

static text_part_t* get_text_parts(parse_ctx ctx, const char* tag, size_t tag_len, int skip_ws, text_part_t *parts)
{
    const char *p = NULL;
    const char *q = NULL;
    text_part_t *last = NULL;

    if (skip_ws) {
        parse_skip_ws(ctx);
    }
    do {
        p = ctx->pos;
        find_char(ctx, '<', 0);
        if (ctx->pos >= ctx->end || *ctx->pos != '<') {
            PLIST_XML_ERR("EOF while looking for closing tag\n");
            ctx->err++;
            return NULL;
        }
        q = ctx->pos;
        ctx->pos++;
        if (ctx->pos >= ctx->end) {
            PLIST_XML_ERR("EOF while parsing '%s'\n", p);
            ctx->err++;
            return NULL;
        }
        if (*ctx->pos == '!') {
            ctx->pos++;
            if (ctx->pos >= ctx->end-1) {
                PLIST_XML_ERR("EOF while parsing <! special tag\n");
                ctx->err++;
                return NULL;
            }
            if (*ctx->pos == '-' && *(ctx->pos+1) == '-') {
                if (last) {
                    last = text_part_append(last, p, q-p, 0);
                } else if (parts) {
                    last = text_part_init(parts, p, q-p, 0);
                }
                ctx->pos += 2;
                find_str(ctx, "-->", 3, 0);
                if (ctx->pos > ctx->end-3 || strncmp(ctx->pos, "-->", 3) != 0) {
                    PLIST_XML_ERR("EOF while looking for end of comment\n");
                    ctx->err++;
                    return NULL;
                }
                ctx->pos += 3;
            } else if (*ctx->pos == '[') {
                ctx->pos++;
                if (ctx->pos >= ctx->end - 8) {
                    PLIST_XML_ERR("EOF while parsing <[ tag\n");
                    ctx->err++;
                    return NULL;
                }
                if (strncmp(ctx->pos, "CDATA[", 6) == 0) {
                    if (q-p > 0) {
                        if (last) {
                            last = text_part_append(last, p, q-p, 0);
                        } else if (parts) {
                            last = text_part_init(parts, p, q-p, 0);
                        }
                    }
                    ctx->pos+=6;
                    p = ctx->pos;
                    find_str(ctx, "]]>", 3, 0);
                    if (ctx->pos > ctx->end-3 || strncmp(ctx->pos, "]]>", 3) != 0) {
                        PLIST_XML_ERR("EOF while looking for end of CDATA block\n");
                        ctx->err++;
                        return NULL;
                    }
                    q = ctx->pos;
                    if (last) {
                        last = text_part_append(last, p, q-p, 1);
                    } else if (parts) {
                        last = text_part_init(parts, p, q-p, 1);
                    }
                    ctx->pos += 3;
                } else {
                    p = ctx->pos;
                    find_next(ctx, " \r\n\t>", 5, 1);
                    PLIST_XML_ERR("Invalid special tag <[%.*s> encountered inside <%s> tag\n", (int)(ctx->pos - p), p, tag);
                    ctx->err++;
                    return NULL;
                }
            } else {
                p = ctx->pos;
                find_next(ctx, " \r\n\t>", 5, 1);
                PLIST_XML_ERR("Invalid special tag <!%.*s> encountered inside <%s> tag\n", (int)(ctx->pos - p), p, tag);
                ctx->err++;
                return NULL;
            }
        } else if (*ctx->pos == '/') {
            break;
        } else {
            p = ctx->pos;
            find_next(ctx, " \r\n\t>", 5, 1);
            PLIST_XML_ERR("Invalid tag <%.*s> encountered inside <%s> tag\n", (int)(ctx->pos - p), p, tag);
            ctx->err++;
            return NULL;
        }
    } while (1);
    ctx->pos++;
    if (ctx->pos >= ctx->end-tag_len || strncmp(ctx->pos, tag, tag_len)) {
        PLIST_XML_ERR("EOF or end tag mismatch\n");
        ctx->err++;
        return NULL;
    }
    ctx->pos+=tag_len;
    parse_skip_ws(ctx);
    if (ctx->pos >= ctx->end) {
        PLIST_XML_ERR("EOF while parsing closing tag\n");
        ctx->err++;
        return NULL;
    } else if (*ctx->pos != '>') {
        PLIST_XML_ERR("Invalid closing tag; expected '>', found '%c'\n", *ctx->pos);
        ctx->err++;
        return NULL;
    }
    ctx->pos++;

    if (q-p > 0) {
        if (last) {
            last = text_part_append(last, p, q-p, 0);
        } else if (parts) {
            last = text_part_init(parts, p, q-p, 0);
        }
    }
    return parts;
}

static int unescape_entities(char *str, size_t *length)
{
    size_t i = 0;
    size_t len = *length;
    while (len > 0 && i < len-1) {
        if (str[i] == '&') {
            char *entp = str + i + 1;
            while (i < len && str[i] != ';') {
                i++;
            }
            if (i >= len) {
                PLIST_XML_ERR("Invalid entity sequence encountered (missing terminating ';')\n");
                return -1;
            }
            if (str+i >= entp+1) {
                int entlen = str+i - entp;
                int bytelen = 1;
                if (!strncmp(entp, "amp", 3)) {
                    /* the '&' is already there */
                } else if (!strncmp(entp, "apos", 4)) {
                    *(entp-1) = '\'';
                } else if (!strncmp(entp, "quot", 4)) {
                    *(entp-1) = '"';
                } else if (!strncmp(entp, "lt", 2)) {
                    *(entp-1) = '<';
                } else if (!strncmp(entp, "gt", 2)) {
                    *(entp-1) = '>';
                } else if (*entp == '#') {
                    /* numerical  character reference */
                    uint64_t val = 0;
                    char* ep = NULL;
                    if (entlen > 8) {
                        PLIST_XML_ERR("Invalid numerical character reference encountered, sequence too long: &%.*s;\n", entlen, entp);
                        return -1;
                    }
                    if (*(entp+1) == 'x' || *(entp+1) == 'X') {
                        if (entlen < 3) {
                            PLIST_XML_ERR("Invalid numerical character reference encountered, sequence too short: &%.*s;\n", entlen, entp);
                            return -1;
                        }
                        val = strtoull(entp+2, &ep, 16);
                    } else {
                        if (entlen < 2) {
                            PLIST_XML_ERR("Invalid numerical character reference encountered, sequence too short: &%.*s;\n", entlen, entp);
                            return -1;
                        }
                        val = strtoull(entp+1, &ep, 10);
                    }
                    if (val == 0 || val > 0x10FFFF || ep-entp != entlen) {
                        PLIST_XML_ERR("Invalid numerical character reference found: &%.*s;\n", entlen, entp);
                        return -1;
                    }
                    /* convert to UTF8 */
                    if (val >= 0x10000) {
                        /* four bytes */
                        *(entp-1) = (char)(0xF0 + ((val >> 18) & 0x7));
                        *(entp+0) = (char)(0x80 + ((val >> 12) & 0x3F));
                        *(entp+1) = (char)(0x80 + ((val >> 6) & 0x3F));
                        *(entp+2) = (char)(0x80 + (val & 0x3F));
                        entp+=3;
                        bytelen = 4;
                    } else if (val >= 0x800) {
                        /* three bytes */
                        *(entp-1) = (char)(0xE0 + ((val >> 12) & 0xF));
                        *(entp+0) = (char)(0x80 + ((val >> 6) & 0x3F));
                        *(entp+1) = (char)(0x80 + (val & 0x3F));
                        entp+=2;
                        bytelen = 3;
                    } else if (val >= 0x80) {
                        /* two bytes */
                        *(entp-1) = (char)(0xC0 + ((val >> 6) & 0x1F));
                        *(entp+0) = (char)(0x80 + (val & 0x3F));
                        entp++;
                        bytelen = 2;
                    } else {
                        /* one byte */
                        *(entp-1) = (char)(val & 0x7F);
                    }
                } else {
                    PLIST_XML_ERR("Invalid entity encountered: &%.*s;\n", entlen, entp);
                    return -1;
                }
                memmove(entp, str+i+1, len - i);
                i -= entlen+1 - bytelen;
                len -= entlen+2 - bytelen;
                continue;
            } else {
                PLIST_XML_ERR("Invalid empty entity sequence &;\n");
                return -1;
            }
        }
        i++;
    }
    *length = len;
    return 0;
}

static char* text_parts_get_content(text_part_t *tp, int unesc_entities, size_t *length, int *requires_free)
{
    char *str = NULL;
    size_t total_length = 0;

    if (!tp) {
        return NULL;
    }
    char *p;
    if (requires_free && !tp->next) {
        if (tp->is_cdata || !unesc_entities) {
            *requires_free = 0;
            if (length) {
                *length = tp->length;
            }
            return (char*)tp->begin;
        }
    }
    text_part_t *tmp = tp;
    while (tp && tp->begin) {
        total_length += tp->length;
        tp = tp->next;
    }
    str = malloc(total_length + 1);
    assert(str);
    p = str;
    tp = tmp;
    while (tp && tp->begin) {
        size_t len = tp->length;
        strncpy(p, tp->begin, len);
        p[len] = '\0';
        if (!tp->is_cdata && unesc_entities) {
            if (unescape_entities(p, &len) < 0) {
                free(str);
                return NULL;
            }
        }
        p += len;
        tp = tp->next;
    }
    *p = '\0';
    if (length) {
        *length = p - str;
    }
    if (requires_free) {
        *requires_free = 1;
    }
    return str;
}

static void node_from_xml(parse_ctx ctx, plist_t *plist)
{
    char *tag = NULL;
    char *keyname = NULL;
    plist_t subnode = NULL;
    const char *p = NULL;
    plist_t parent = NULL;
    int has_content = 0;

    struct node_path_item {
        const char *type;
        void *prev;
    };
    struct node_path_item* node_path = NULL;

    while (ctx->pos < ctx->end && !ctx->err) {
        parse_skip_ws(ctx);
        if (ctx->pos >= ctx->end) {
            break;
        }
        if (*ctx->pos != '<') {
            p = ctx->pos;
            find_next(ctx, " \t\r\n", 4, 0);
            PLIST_XML_ERR("Expected: opening tag, found: %.*s\n", (int)(ctx->pos - p), p);
            ctx->err++;
            goto err_out;
        }
        ctx->pos++;
        if (ctx->pos >= ctx->end) {
            PLIST_XML_ERR("EOF while parsing tag\n");
            ctx->err++;
            goto err_out;
        }

        if (*(ctx->pos) == '?') {
            find_str(ctx, "?>", 2, 1);
            if (ctx->pos > ctx->end-2) {
                PLIST_XML_ERR("EOF while looking for <? tag closing marker\n");
                ctx->err++;
                goto err_out;
            }
            if (strncmp(ctx->pos, "?>", 2)) {
                PLIST_XML_ERR("Couldn't find <? tag closing marker\n");
                ctx->err++;
                goto err_out;
            }
            ctx->pos += 2;
            continue;
        } else if (*(ctx->pos) == '!') {
            /* comment or DTD */
            if (((ctx->end - ctx->pos) > 3) && !strncmp(ctx->pos, "!--", 3)) {
                ctx->pos += 3;
                find_str(ctx,"-->", 3, 0);
                if (ctx->pos > ctx->end-3 || strncmp(ctx->pos, "-->", 3)) {
                    PLIST_XML_ERR("Couldn't find end of comment\n");
                    ctx->err++;
                    goto err_out;
                }
                ctx->pos+=3;
            } else if (((ctx->end - ctx->pos) > 8) && !strncmp(ctx->pos, "!DOCTYPE", 8)) {
                int embedded_dtd = 0;
                ctx->pos+=8;
                while (ctx->pos < ctx->end) {
                    find_next(ctx, " \t\r\n[>", 6, 1);
                    if (ctx->pos >= ctx->end) {
                        PLIST_XML_ERR("EOF while parsing !DOCTYPE\n");
                        ctx->err++;
                        goto err_out;
                    }
                    if (*ctx->pos == '[') {
                        embedded_dtd = 1;
                        break;
                    } else if (*ctx->pos == '>') {
                        /* end of DOCTYPE found already */
                        ctx->pos++;
                        break;
                    } else {
                        parse_skip_ws(ctx);
                    }
                }
                if (embedded_dtd) {
                    find_str(ctx, "]>", 2, 1);
                    if (ctx->pos > ctx->end-2 || strncmp(ctx->pos, "]>", 2)) {
                        PLIST_XML_ERR("Couldn't find end of DOCTYPE\n");
                        ctx->err++;
                        goto err_out;
                    }
                    ctx->pos += 2;
                }
            } else {
                p = ctx->pos;
                find_next(ctx, " \r\n\t>", 5, 1);
                PLIST_XML_ERR("Invalid or incomplete special tag <%.*s> encountered\n", (int)(ctx->pos - p), p);
                ctx->err++;
                goto err_out;
            }
            continue;
        } else {
            int is_empty = 0;
            int closing_tag = 0;
            p = ctx->pos;
            find_next(ctx," \r\n\t<>", 6, 0);
            if (ctx->pos >= ctx->end) {
                PLIST_XML_ERR("Unexpected EOF while parsing XML\n");
                ctx->err++;
                goto err_out;
            }
            int taglen = ctx->pos - p;
            tag = malloc(taglen + 1);
            strncpy(tag, p, taglen);
            tag[taglen] = '\0';
            if (*ctx->pos != '>') {
                find_next(ctx, "<>", 2, 1);
            }
            if (ctx->pos >= ctx->end) {
                PLIST_XML_ERR("Unexpected EOF while parsing XML\n");
                ctx->err++;
                goto err_out;
            }
            if (*ctx->pos != '>') {
                PLIST_XML_ERR("Missing '>' for tag <%s\n", tag);
                ctx->err++;
                goto err_out;
            }
            if (*(ctx->pos-1) == '/') {
                int idx = ctx->pos - p - 1;
                if (idx < taglen)
                    tag[idx] = '\0';
                is_empty = 1;
            }
            ctx->pos++;
            if (!strcmp(tag, "plist")) {
                free(tag);
                tag = NULL;
                has_content = 0;

                if (!node_path && *plist) {
                    /* we don't allow another top-level <plist> */
                    break;
                }
                if (is_empty) {
                    PLIST_XML_ERR("Empty plist tag\n");
                    ctx->err++;
                    goto err_out;
                }

                struct node_path_item *path_item = malloc(sizeof(struct node_path_item));
                if (!path_item) {
                    PLIST_XML_ERR("out of memory when allocating node path item\n");
                    ctx->err++;
                    goto err_out;
                }
                path_item->type = "plist";
                path_item->prev = node_path;
                node_path = path_item;

                continue;
            } else if (!strcmp(tag, "/plist")) {
                if (!has_content) {
                    PLIST_XML_ERR("encountered empty plist tag\n");
                    ctx->err++;
                    goto err_out;
                }
                if (!node_path) {
                    PLIST_XML_ERR("node path is empty while trying to match closing tag with opening tag\n");
                    ctx->err++;
                    goto err_out;
                }
                if (strcmp(node_path->type, tag+1) != 0) {
                    PLIST_XML_ERR("mismatching closing tag <%s> found for opening tag <%s>\n", tag, node_path->type);
                    ctx->err++;
                    goto err_out;
                }
                struct node_path_item *path_item = node_path;
                node_path = node_path->prev;
                free(path_item);

                free(tag);
                tag = NULL;

                continue;
            }

            plist_data_t data = plist_new_plist_data();
            subnode = plist_new_node(data);
            has_content = 1;

            if (!strcmp(tag, XPLIST_DICT)) {
                data->type = PLIST_DICT;
            } else if (!strcmp(tag, XPLIST_ARRAY)) {
                data->type = PLIST_ARRAY;
            } else if (!strcmp(tag, XPLIST_INT)) {
                if (!is_empty) {
                    text_part_t first_part = { NULL, 0, 0, NULL };
                    text_part_t *tp = get_text_parts(ctx, tag, taglen, 1, &first_part);
                    if (!tp) {
                        PLIST_XML_ERR("Could not parse text content for '%s' node\n", tag);
                        text_parts_free(first_part.next);
                        ctx->err++;
                        goto err_out;
                    }
                    if (tp->begin) {
                        int requires_free = 0;
                        char *str_content = text_parts_get_content(tp, 0, NULL, &requires_free);
                        if (!str_content) {
                            PLIST_XML_ERR("Could not get text content for '%s' node\n", tag);
                            text_parts_free(first_part.next);
                            ctx->err++;
                            goto err_out;
                        }
                        char *str = str_content;
                        int is_negative = 0;
                        if ((str[0] == '-') || (str[0] == '+')) {
                            if (str[0] == '-') {
                                is_negative = 1;
                            }
                            str++;
                        }
                        data->intval = strtoull((char*)str, NULL, 0);
                        if (is_negative || (data->intval <= INT64_MAX)) {
                            uint64_t v = data->intval;
                            if (is_negative) {
                                v = -v;
                            }
                            data->intval = v;
                            data->length = 8;
                        } else {
                            data->length = 16;
                        }
                        if (requires_free) {
                            free(str_content);
                        }
                    } else {
                        is_empty = 1;
                    }
                    text_parts_free(tp->next);
                }
                if (is_empty) {
                    data->intval = 0;
                    data->length = 8;
                }
                data->type = PLIST_UINT;
            } else if (!strcmp(tag, XPLIST_REAL)) {
                if (!is_empty) {
                    text_part_t first_part = { NULL, 0, 0, NULL };
                    text_part_t *tp = get_text_parts(ctx, tag, taglen, 1, &first_part);
                    if (!tp) {
                        PLIST_XML_ERR("Could not parse text content for '%s' node\n", tag);
                        text_parts_free(first_part.next);
                        ctx->err++;
                        goto err_out;
                    }
                    if (tp->begin) {
                        int requires_free = 0;
                        char *str_content = text_parts_get_content(tp, 0, NULL, &requires_free);
                        if (!str_content) {
                            PLIST_XML_ERR("Could not get text content for '%s' node\n", tag);
                            text_parts_free(first_part.next);
                            ctx->err++;
                            goto err_out;
                        }
                        data->realval = atof(str_content);
                        if (requires_free) {
                            free(str_content);
                        }
                    }
                    text_parts_free(tp->next);
                }
                data->type = PLIST_REAL;
                data->length = 8;
            } else if (!strcmp(tag, XPLIST_TRUE)) {
                if (!is_empty) {
                    get_text_parts(ctx, tag, taglen, 1, NULL);
                }
                data->type = PLIST_BOOLEAN;
                data->boolval = 1;
                data->length = 1;
            } else if (!strcmp(tag, XPLIST_FALSE)) {
                if (!is_empty) {
                    get_text_parts(ctx, tag, taglen, 1, NULL);
                }
                data->type = PLIST_BOOLEAN;
                data->boolval = 0;
                data->length = 1;
            } else if (!strcmp(tag, XPLIST_STRING) || !strcmp(tag, XPLIST_KEY)) {
                if (!is_empty) {
                    text_part_t first_part = { NULL, 0, 0, NULL };
                    text_part_t *tp = get_text_parts(ctx, tag, taglen, 0, &first_part);
                    char *str = NULL;
                    size_t length = 0;
                    if (!tp) {
                        PLIST_XML_ERR("Could not parse text content for '%s' node\n", tag);
                        text_parts_free(first_part.next);
                        ctx->err++;
                        goto err_out;
                    }
                    str = text_parts_get_content(tp, 1, &length, NULL);
                    text_parts_free(first_part.next);
                    if (!str) {
                        PLIST_XML_ERR("Could not get text content for '%s' node\n", tag);
                        ctx->err++;
                        goto err_out;
                    }
                    if (!strcmp(tag, "key") && !keyname && parent && (plist_get_node_type(parent) == PLIST_DICT)) {
                        keyname = str;
                        free(tag);
                        tag = NULL;
                        plist_free(subnode);
                        subnode = NULL;
                        continue;
                    } else {
                        data->strval = str;
                        data->length = length;
                    }
                } else {
                    data->strval = strdup("");
                    data->length = 0;
                }
                data->type = PLIST_STRING;
            } else if (!strcmp(tag, XPLIST_DATA)) {
                if (!is_empty) {
                    text_part_t first_part = { NULL, 0, 0, NULL };
                    text_part_t *tp = get_text_parts(ctx, tag, taglen, 1, &first_part);
                    if (!tp) {
                        PLIST_XML_ERR("Could not parse text content for '%s' node\n", tag);
                        text_parts_free(first_part.next);
                        ctx->err++;
                        goto err_out;
                    }
                    if (tp->begin) {
                        int requires_free = 0;
                        char *str_content = text_parts_get_content(tp, 0, NULL, &requires_free);
                        if (!str_content) {
                            PLIST_XML_ERR("Could not get text content for '%s' node\n", tag);
                            text_parts_free(first_part.next);
                            ctx->err++;
                            goto err_out;
                        }
                        size_t size = tp->length;
                        if (size > 0) {
                            data->buff = base64decode(str_content, &size);
                            data->length = size;
                        }

                        if (requires_free) {
                            free(str_content);
                        }
                    }
                    text_parts_free(tp->next);
                }
                data->type = PLIST_DATA;
            } else if (!strcmp(tag, XPLIST_DATE)) {
                if (!is_empty) {
                    text_part_t first_part = { NULL, 0, 0, NULL };
                    text_part_t *tp = get_text_parts(ctx, tag, taglen, 1, &first_part);
                    if (!tp) {
                        PLIST_XML_ERR("Could not parse text content for '%s' node\n", tag);
                        text_parts_free(first_part.next);
                        ctx->err++;
                        goto err_out;
                    }
                    Time64_T timev = 0;
                    if (tp->begin) {
                        int requires_free = 0;
                        size_t length = 0;
                        char *str_content = text_parts_get_content(tp, 0, &length, &requires_free);
                        if (!str_content) {
                            PLIST_XML_ERR("Could not get text content for '%s' node\n", tag);
                            text_parts_free(first_part.next);
                            ctx->err++;
                            goto err_out;
                        }

                        if ((length >= 11) && (length < 32)) {
                            /* we need to copy here and 0-terminate because sscanf will read the entire string (whole rest of XML data) which can be huge */
                            char strval[32];
                            struct TM btime;
                            strncpy(strval, str_content, length);
                            strval[tp->length] = '\0';
                            parse_date(strval, &btime);
                            timev = timegm64(&btime);
                        } else {
                            PLIST_XML_ERR("Invalid text content in date node\n");
                        }
                        if (requires_free) {
                            free(str_content);
                        }
                    }
                    text_parts_free(tp->next);
                    data->realval = (double)(timev - MAC_EPOCH);
                }
                data->length = sizeof(double);
                data->type = PLIST_DATE;
            } else if (tag[0] == '/') {
                 closing_tag = 1;
            } else {
                PLIST_XML_ERR("Unexpected tag <%s%s> encountered\n", tag, (is_empty) ? "/" : "");
                ctx->pos = ctx->end;
                ctx->err++;
                goto err_out;
            }
            if (subnode && !closing_tag) {
                if (!*plist) {
                    /* first node, make this node the parent node */
                    *plist = subnode;
                    if (data->type != PLIST_DICT && data->type != PLIST_ARRAY) {
                        /* if the first node is not a structered node, we're done */
                        subnode = NULL;
                        goto err_out;
                    }
                    parent = subnode;
                } else if (parent) {
                    switch (plist_get_node_type(parent)) {
                    case PLIST_DICT:
                        if (!keyname) {
                            PLIST_XML_ERR("missing key name while adding dict item\n");
                            ctx->err++;
                            goto err_out;
                        }
                        plist_dict_set_item(parent, keyname, subnode);
                        break;
                    case PLIST_ARRAY:
                        plist_array_append_item(parent, subnode);
                        break;
                    default:
                        /* should not happen */
                        PLIST_XML_ERR("parent is not a structured node\n");
                        ctx->err++;
                        goto err_out;
                    }
                }
                if (!is_empty && (data->type == PLIST_DICT || data->type == PLIST_ARRAY)) {
                    struct node_path_item *path_item = malloc(sizeof(struct node_path_item));
                    if (!path_item) {
                        PLIST_XML_ERR("out of memory when allocating node path item\n");
                        ctx->err++;
                        goto err_out;
                    }
                    path_item->type = (data->type == PLIST_DICT) ? XPLIST_DICT : XPLIST_ARRAY;
                    path_item->prev = node_path;
                    node_path = path_item;

                    parent = subnode;
                }
                subnode = NULL;
            } else if (closing_tag) {
                if (!node_path) {
                    PLIST_XML_ERR("node path is empty while trying to match closing tag with opening tag\n");
                    ctx->err++;
                    goto err_out;
                }
                if (strcmp(node_path->type, tag+1) != 0) {
                    PLIST_XML_ERR("unexpected %s found (for opening %s)\n", tag, node_path->type);
                    ctx->err++;
                    goto err_out;
                }
                struct node_path_item *path_item = node_path;
                node_path = node_path->prev;
                free(path_item);

                parent = ((node_t*)parent)->parent;
                if (!parent) {
                    goto err_out;
                }
            }

            free(tag);
            tag = NULL;
            free(keyname);
            keyname = NULL;
            plist_free(subnode);
            subnode = NULL;
        }
    }

    if (node_path) {
        PLIST_XML_ERR("EOF encountered while </%s> was expected\n", node_path->type);
        ctx->err++;
    }

err_out:
    free(tag);
    free(keyname);
    plist_free(subnode);

    /* clean up node_path if required */
    while (node_path) {
        struct node_path_item *path_item = node_path;
        node_path = path_item->prev;
        free(path_item);
    }

    if (ctx->err) {
        plist_free(*plist);
        *plist = NULL;
    }
}

PLIST_API void plist_from_xml(const char *plist_xml, uint32_t length, plist_t * plist)
{
    if (!plist_xml || (length == 0)) {
        *plist = NULL;
        return;
    }

    struct _parse_ctx ctx = { plist_xml, plist_xml + length, 0 };

    node_from_xml(&ctx, plist);
}