-
-
Notifications
You must be signed in to change notification settings - Fork 6
/
Copy pathtoml.c
2003 lines (1747 loc) · 46.8 KB
/
toml.c
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
#define _POSIX_C_SOURCE 200809L
#include <assert.h>
#include <ctype.h>
#include <errno.h>
#include <math.h>
#include <stdbool.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "toml.h"
#define ALIGN8(sz) (((sz) + 7) & ~7)
#define calloc(x, y) error - forbidden - use CALLOC instead
static void *CALLOC(size_t nmemb, size_t sz) {
int nb = ALIGN8(sz) * nmemb;
void *p = malloc(nb);
if (p) {
memset(p, 0, nb);
}
return p;
}
// some old platforms define strdup macro -- drop it.
#undef strdup
#define strdup(x) error - forbidden - use STRDUP instead
static char *STRDUP(const char *s) {
int len = strlen(s);
char *p = malloc(len + 1);
if (p) {
memcpy(p, s, len);
p[len] = 0;
}
return p;
}
// some old platforms define strndup macro -- drop it.
#undef strndup
#define strndup(x) error - forbidden - use STRNDUP instead
static char *STRNDUP(const char *s, size_t n) {
size_t len = strnlen(s, n);
char *p = malloc(len + 1);
if (p) {
memcpy(p, s, len);
p[len] = 0;
}
return p;
}
// Unparsed values.
typedef const char *toml_unparsed_t;
toml_unparsed_t toml_table_unparsed (const toml_table_t *table, const char *key);
toml_unparsed_t toml_array_unparsed (const toml_array_t *array, int idx);
int toml_value_string (toml_unparsed_t s, char **ret, int *len);
int toml_value_bool (toml_unparsed_t s, bool *ret);
int toml_value_int (toml_unparsed_t s, int64_t *ret);
int toml_value_double (toml_unparsed_t s, double *ret);
int toml_value_timestamp (toml_unparsed_t s, toml_timestamp_t *ret);
// Convert escape to UTF-8; return #bytes used in buf to encode the char, or -1
// on error.
// http://stackoverflow.com/questions/6240055/manually-converting-unicode-codepoints-into-utf-8-and-utf-16
int read_unicode_escape(int64_t code, char buf[6]) {
if (0xd800 <= code && code <= 0xdfff) /// UTF-16 surrogates
return -1;
if (0x10FFFF < code)
return -1;
if (code < 0)
return -1;
if (code <= 0x7F) { /// 0x00000000 - 0x0000007F: 0xxxxxxx
buf[0] = (unsigned char)code;
return 1;
}
if (code <= 0x000007FF) { /// 0x00000080 - 0x000007FF: 110xxxxx 10xxxxxx
buf[0] = (unsigned char)(0xc0 | (code >> 6));
buf[1] = (unsigned char)(0x80 | (code & 0x3f));
return 2;
}
if (code <= 0x0000FFFF) { /// 0x00000800 - 0x0000FFFF: 1110xxxx 10xxxxxx 10xxxxxx
buf[0] = (unsigned char)(0xe0 | (code >> 12));
buf[1] = (unsigned char)(0x80 | ((code >> 6) & 0x3f));
buf[2] = (unsigned char)(0x80 | (code & 0x3f));
return 3;
}
if (code <= 0x001FFFFF) { /// 0x00010000 - 0x001FFFFF: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
buf[0] = (unsigned char)(0xf0 | (code >> 18));
buf[1] = (unsigned char)(0x80 | ((code >> 12) & 0x3f));
buf[2] = (unsigned char)(0x80 | ((code >> 6) & 0x3f));
buf[3] = (unsigned char)(0x80 | (code & 0x3f));
return 4;
}
if (code <= 0x03FFFFFF) { /// 0x00200000 - 0x03FFFFFF: 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
buf[0] = (unsigned char)(0xf8 | (code >> 24));
buf[1] = (unsigned char)(0x80 | ((code >> 18) & 0x3f));
buf[2] = (unsigned char)(0x80 | ((code >> 12) & 0x3f));
buf[3] = (unsigned char)(0x80 | ((code >> 6) & 0x3f));
buf[4] = (unsigned char)(0x80 | (code & 0x3f));
return 5;
}
if (code <= 0x7FFFFFFF) { /// 0x04000000 - 0x7FFFFFFF: 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
buf[0] = (unsigned char)(0xfc | (code >> 30));
buf[1] = (unsigned char)(0x80 | ((code >> 24) & 0x3f));
buf[2] = (unsigned char)(0x80 | ((code >> 18) & 0x3f));
buf[3] = (unsigned char)(0x80 | ((code >> 12) & 0x3f));
buf[4] = (unsigned char)(0x80 | ((code >> 6) & 0x3f));
buf[5] = (unsigned char)(0x80 | (code & 0x3f));
return 6;
}
return -1;
}
static inline void xfree(const void *x) {
if (x)
free((void *)(intptr_t)x);
}
enum tokentype_t {
INVALID,
DOT,
COMMA,
EQUAL,
LBRACE,
RBRACE,
NEWLINE,
LBRACKET,
RBRACKET,
STRING,
};
typedef enum tokentype_t tokentype_t;
typedef struct token_t token_t;
struct token_t {
tokentype_t tok;
int lineno;
char *ptr; // points into context->start
int len;
int eof;
};
typedef struct context_t context_t;
struct context_t {
char *start;
char *stop;
char *errbuf;
int errbufsz;
token_t tok;
toml_table_t *root;
toml_table_t *curtab;
struct {
int top;
char *key[10];
int keylen[10];
token_t tok[10];
} tpath;
};
#define STRINGIFY(x) #x
#define TOSTRING(x) STRINGIFY(x)
#define FLINE __FILE__ ":" TOSTRING(__LINE__)
static int next_token(context_t *ctx, bool dotisspecial);
// Error reporting. Call when an error is detected. Always return -1.
static int e_outofmemory(context_t *ctx, const char *fline) {
snprintf(ctx->errbuf, ctx->errbufsz, "ERROR: out of memory (%s)", fline);
return -1;
}
static int e_internal(context_t *ctx, const char *fline) {
snprintf(ctx->errbuf, ctx->errbufsz, "internal error (%s)", fline);
return -1;
}
static int e_syntax(context_t *ctx, int lineno, const char *msg) {
snprintf(ctx->errbuf, ctx->errbufsz, "line %d: %s", lineno, msg);
return -1;
}
static int e_badkey(context_t *ctx, int lineno) {
snprintf(ctx->errbuf, ctx->errbufsz, "line %d: bad key", lineno);
return -1;
}
static int e_keyexists(context_t *ctx, int lineno) {
snprintf(ctx->errbuf, ctx->errbufsz, "line %d: key exists", lineno);
return -1;
}
static int e_forbid(context_t *ctx, int lineno, const char *msg) {
snprintf(ctx->errbuf, ctx->errbufsz, "line %d: %s", lineno, msg);
return -1;
}
static void *expand(void *p, int sz, int newsz) {
void *s = malloc(newsz);
if (!s)
return 0;
if (p) {
memcpy(s, p, sz);
free(p);
}
return s;
}
static void **expand_ptrarr(void **p, int n) {
void **s = malloc((n + 1) * sizeof(void *));
if (!s)
return 0;
s[n] = 0;
if (p) {
memcpy(s, p, n * sizeof(void *));
free(p);
}
return s;
}
static toml_arritem_t *expand_arritem(toml_arritem_t *p, int n) {
toml_arritem_t *pp = expand(p, n * sizeof(*p), (n + 1) * sizeof(*p));
if (!pp)
return 0;
memset(&pp[n], 0, sizeof(pp[n]));
return pp;
}
static uint8_t const u8_length[] = {1,1,1,1,1,1,1,1,0,0,0,0,2,2,3,4};
#define u8length(s) u8_length[(((uint8_t *)(s))[0] & 0xFF) >> 4];
static char *norm_lit_str(const char *src, int srclen, int *len, bool multiline, bool is_key, char *errbuf, int errbufsz) {
const char *sp = src;
const char *sq = src + srclen;
char *dst = 0; /// will write to dst[] and return it
int max = 0; /// max size of dst[]
int off = 0; /// cur offset in dst[]
for (;;) { /// scan forward on src
if (off >= max - 10) { /// have some slack for misc stuff
int newmax = max + 50;
char *x = expand(dst, max, newmax);
if (!x) {
xfree(dst);
snprintf(errbuf, errbufsz, "out of memory");
return 0;
}
dst = x;
max = newmax;
}
if (sp >= sq) /// finished?
break;
uint8_t l = u8length(sp);
if (l == 0) {
xfree(dst);
snprintf(errbuf, errbufsz, "invalid UTF-8 at byte pos %d", off);
return 0;
}
if (l > 1) {
for (int i = 0; i < l; i++) {
char ch = *sp++;
if ((ch & 0x80) != 0x80) {
xfree(dst);
snprintf(errbuf, errbufsz, "invalid UTF-8 at byte pos %d", off);
return 0;
}
dst[off++] = ch;
}
continue;
}
char ch = *sp++;
if (is_key && ch == '\n') {
xfree(dst);
snprintf(errbuf, errbufsz, "literal newlines not allowed in key");
return 0;
}
/// control characters other than tab is not allowed
if ((0 <= ch && ch <= 0x08) || (0x0a <= ch && ch <= 0x1f) || ch == 0x7f) {
if (!(multiline && (ch == '\r' || ch == '\n'))) {
xfree(dst);
snprintf(errbuf, errbufsz, "invalid char U+%04x", ch);
return 0;
}
}
dst[off++] = ch; /// a plain copy suffice
}
*len = off;
dst[off++] = 0;
return dst;
}
/* Convert src to raw unescaped utf-8 string.
* Returns NULL if error with errmsg in errbuf. */
static char *norm_basic_str(const char *src, int srclen, int *len, bool multiline, bool is_key, char *errbuf, int errbufsz) {
const char *sp = src;
const char *sq = src + srclen;
char *dst = 0; /// will write to dst[] and return it
int max = 0; /// max size of dst[]
int off = 0; /// cur offset in dst[]
///
/// scan forward on src
for (;;) {
if (off >= max - 10) { /// have some slack for misc stuff
int newmax = max + 50;
char *x = expand(dst, max, newmax);
if (!x) {
xfree(dst);
snprintf(errbuf, errbufsz, "out of memory");
return 0;
}
dst = x;
max = newmax;
}
if (sp >= sq) /// finished?
break;
uint8_t l = u8length(sp);
if (l == 0) {
xfree(dst);
snprintf(errbuf, errbufsz, "invalid UTF-8 at byte pos %d", off);
return 0;
}
if (l > 1) {
for (int i = 0; i < l; i++) {
char ch = *sp++;
if ((ch & 0x80) != 0x80) {
xfree(dst);
snprintf(errbuf, errbufsz, "invalid UTF-8 at byte pos %d", off);
return 0;
}
dst[off++] = ch;
}
continue;
}
char ch = *sp++;
if (is_key && ch == '\n') {
xfree(dst);
snprintf(errbuf, errbufsz, "literal newlines not allowed in key");
return 0;
}
if (ch != '\\') {
/// must be escaped: U+0000 to U+0008, U+000A to U+001F, U+007F
if ((ch >= 0 && ch <= 0x08) || (ch >= 0x0a && ch <= 0x1f) || ch == 0x7f) {
if (!(multiline && (ch == '\r' || ch == '\n'))) {
xfree(dst);
snprintf(errbuf, errbufsz, "invalid char U+%04x", ch);
return 0;
}
}
dst[off++] = ch; /// a plain copy suffice
continue;
}
if (sp >= sq) { /// ch was backslash. we expect the escape char.
snprintf(errbuf, errbufsz, "last backslash is invalid");
xfree(dst);
return 0;
}
if (multiline) { /// for multi-line, we want to kill line-ending-backslash.
if (sp[strspn(sp, " \t\r")] == '\n') { /// if there is only whitespace after the backslash ...
sp += strspn(sp, " \t\r\n"); /// skip all the following whitespaces
continue;
}
}
ch = *sp++; /// get the escaped char
switch (ch) {
case 'u':
case 'U': {
int64_t ucs = 0;
int nhex = (ch == 'u' ? 4 : 8);
for (int i = 0; i < nhex; i++) {
if (sp >= sq) {
snprintf(errbuf, errbufsz, "\\%c expects %d hex chars", ch, nhex);
xfree(dst);
return 0;
}
ch = *sp++;
int v = -1;
if ('0' <= ch && ch <= '9')
v = ch - '0';
else if ('A' <= ch && ch <= 'F')
v = ch - 'A' + 10;
else if ('a' <= ch && ch <= 'f')
v = (ch ^ 0x20) - 'A' + 10;
if (v == -1) {
snprintf(errbuf, errbufsz, "invalid hex chars for \\u or \\U");
xfree(dst);
return 0;
}
ucs = ucs * 16 + v;
}
int n = read_unicode_escape(ucs, &dst[off]);
if (n == -1) {
snprintf(errbuf, errbufsz, "illegal ucs code in \\u or \\U");
xfree(dst);
return 0;
}
off += n;
}; continue;
case 'b': ch = '\b'; break;
case 't': ch = '\t'; break;
case 'n': ch = '\n'; break;
case 'f': ch = '\f'; break;
case 'r': ch = '\r'; break;
case '"': ch = '"'; break;
case '\\': ch = '\\'; break;
default:
snprintf(errbuf, errbufsz, "illegal escape char \\%c", ch);
xfree(dst);
return 0;
}
dst[off++] = ch;
}
*len = off;
dst[off++] = 0; /// Cap with NUL and return it.
return dst;
}
// Normalize a key. Convert all special chars to raw unescaped utf-8 chars.
static char *normalize_key(context_t *ctx, token_t strtok, int *keylen) {
const char *sp = strtok.ptr;
const char *sq = strtok.ptr + strtok.len;
int lineno = strtok.lineno;
int ch = *sp;
char *ret;
// Quoted string
if (ch == '\'' || ch == '\"') {
/// if ''' or """, take 3 chars off front and back. Else, take 1 char off.
bool multiline = (sp[1] == ch && sp[2] == ch);
if (multiline)
sp += 3, sq -= 3;
else
sp++, sq--;
char ebuf[80];
if (ch == '\'')
ret = norm_lit_str(sp, sq - sp, keylen, multiline, true, ebuf, sizeof(ebuf));
else
ret = norm_basic_str(sp, sq - sp, keylen, multiline, true, ebuf, sizeof(ebuf));
if (!ret) {
e_syntax(ctx, lineno, ebuf);
return 0;
}
return ret;
}
*keylen = 0;
for (const char *c = sp; c != sq; c++) { /// Bare key: allow: [A-Za-z0-9_-]+
*keylen = *keylen + 1;
if (isalnum(*c) || *c == '_' || *c == '-')
continue;
e_badkey(ctx, lineno);
return 0;
}
if (!(ret = STRNDUP(sp, sq - sp))) { /// dup and return
e_outofmemory(ctx, FLINE);
return 0;
}
return ret;
}
/* Look up key in tab. Return 0 if not found, or
* 'v'alue, 'a'rray or 't'able depending on the element. */
static int check_key(toml_table_t *tab, const char *key, toml_keyval_t **ret_val, toml_array_t **ret_arr, toml_table_t **ret_tab) {
int i;
void *dummy;
if (!ret_tab)
ret_tab = (toml_table_t **)&dummy;
if (!ret_arr)
ret_arr = (toml_array_t **)&dummy;
if (!ret_val)
ret_val = (toml_keyval_t **)&dummy;
*ret_tab = 0;
*ret_arr = 0;
*ret_val = 0;
for (i = 0; i < tab->nkval; i++) {
if (strcmp(key, tab->kval[i]->key) == 0) {
*ret_val = tab->kval[i];
return 'v';
}
}
for (i = 0; i < tab->narr; i++) {
if (strcmp(key, tab->arr[i]->key) == 0) {
*ret_arr = tab->arr[i];
return 'a';
}
}
for (i = 0; i < tab->ntab; i++) {
if (strcmp(key, tab->tab[i]->key) == 0) {
*ret_tab = tab->tab[i];
return 't';
}
}
return 0;
}
static int key_kind(toml_table_t *tab, const char *key) {
return check_key(tab, key, 0, 0, 0);
}
/* Create a keyval in the table. */
static toml_keyval_t *create_keyval_in_table(context_t *ctx, toml_table_t *tab, token_t keytok) {
int keylen;
char *newkey = normalize_key(ctx, keytok, &keylen);
if (!newkey)
return 0;
toml_keyval_t *dest = 0;
if (key_kind(tab, newkey)) {
xfree(newkey);
e_keyexists(ctx, keytok.lineno);
return 0;
}
int n = tab->nkval;
toml_keyval_t **base;
if ((base = (toml_keyval_t **)expand_ptrarr((void **)tab->kval, n)) == 0) {
xfree(newkey);
e_outofmemory(ctx, FLINE);
return 0;
}
tab->kval = base;
if ((base[n] = (toml_keyval_t *)CALLOC(1, sizeof(*base[n]))) == 0) {
xfree(newkey);
e_outofmemory(ctx, FLINE);
return 0;
}
dest = tab->kval[tab->nkval++];
dest->key = newkey;
dest->keylen = keylen;
return dest;
}
// Create a table in the table.
static toml_table_t *create_keytable_in_table(context_t *ctx, toml_table_t *tab, token_t keytok) {
int keylen;
char *newkey = normalize_key(ctx, keytok, &keylen);
if (!newkey)
return 0;
toml_table_t *dest = 0;
if (check_key(tab, newkey, 0, 0, &dest)) {
xfree(newkey);
/// Special case: make explicit if table exists and was created
/// implicitly.
if (dest && dest->implicit) {
dest->implicit = false;
return dest;
}
e_keyexists(ctx, keytok.lineno);
return 0;
}
int n = tab->ntab;
toml_table_t **base;
if ((base = (toml_table_t **)expand_ptrarr((void **)tab->tab, n)) == 0) {
xfree(newkey);
e_outofmemory(ctx, FLINE);
return 0;
}
tab->tab = base;
if ((base[n] = (toml_table_t *)CALLOC(1, sizeof(*base[n]))) == 0) {
xfree(newkey);
e_outofmemory(ctx, FLINE);
return 0;
}
dest = tab->tab[tab->ntab++];
dest->key = newkey;
dest->keylen = keylen;
return dest;
}
// Create an array in the table.
static toml_array_t *create_keyarray_in_table(context_t *ctx, toml_table_t *tab, token_t keytok, char kind) {
int keylen;
char *newkey = normalize_key(ctx, keytok, &keylen);
if (!newkey)
return 0;
if (key_kind(tab, newkey)) {
xfree(newkey);
e_keyexists(ctx, keytok.lineno);
return 0;
}
int n = tab->narr;
toml_array_t **base;
if ((base = (toml_array_t **)expand_ptrarr((void **)tab->arr, n)) == 0) {
xfree(newkey);
e_outofmemory(ctx, FLINE);
return 0;
}
tab->arr = base;
if ((base[n] = (toml_array_t *)CALLOC(1, sizeof(*base[n]))) == 0) {
xfree(newkey);
e_outofmemory(ctx, FLINE);
return 0;
}
toml_array_t *dest = tab->arr[tab->narr++];
dest->keylen = keylen;
dest->key = newkey;
dest->kind = kind;
return dest;
}
static toml_arritem_t *create_value_in_array(context_t *ctx, toml_array_t *parent) {
const int n = parent->nitem;
toml_arritem_t *base = expand_arritem(parent->item, n);
if (!base) {
e_outofmemory(ctx, FLINE);
return 0;
}
parent->item = base;
parent->nitem++;
return &parent->item[n];
}
/* Create an array in an array */
static toml_array_t *create_array_in_array(context_t *ctx,
toml_array_t *parent) {
const int n = parent->nitem;
toml_arritem_t *base = expand_arritem(parent->item, n);
if (!base) {
e_outofmemory(ctx, FLINE);
return 0;
}
toml_array_t *ret = (toml_array_t *)CALLOC(1, sizeof(toml_array_t));
if (!ret) {
e_outofmemory(ctx, FLINE);
return 0;
}
base[n].arr = ret;
parent->item = base;
parent->nitem++;
return ret;
}
/* Create a table in an array */
static toml_table_t *create_table_in_array(context_t *ctx, toml_array_t *parent) {
int n = parent->nitem;
toml_arritem_t *base = expand_arritem(parent->item, n);
if (!base) {
e_outofmemory(ctx, FLINE);
return 0;
}
toml_table_t *ret = (toml_table_t *)CALLOC(1, sizeof(toml_table_t));
if (!ret) {
e_outofmemory(ctx, FLINE);
return 0;
}
base[n].tab = ret;
parent->item = base;
parent->nitem++;
return ret;
}
static int skip_newlines(context_t *ctx, bool isdotspecial) {
while (ctx->tok.tok == NEWLINE) {
if (next_token(ctx, isdotspecial))
return -1;
if (ctx->tok.eof)
break;
}
return 0;
}
static int parse_keyval(context_t *ctx, toml_table_t *tab);
static inline int eat_token(context_t *ctx, tokentype_t typ, bool isdotspecial, const char *fline) {
if (ctx->tok.tok != typ)
return e_internal(ctx, fline);
if (next_token(ctx, isdotspecial))
return -1;
return 0;
}
/* We are at '{ ... }'; parse the table. */
static int parse_inline_table(context_t *ctx, toml_table_t *tab) {
if (eat_token(ctx, LBRACE, 1, FLINE))
return -1;
for (;;) {
if (ctx->tok.tok == NEWLINE)
return e_syntax(ctx, ctx->tok.lineno, "newline not allowed in inline table");
if (ctx->tok.tok == RBRACE) // until closing brace
break;
if (ctx->tok.tok != STRING)
return e_syntax(ctx, ctx->tok.lineno, "expect a string");
if (parse_keyval(ctx, tab))
return -1;
if (ctx->tok.tok == NEWLINE)
return e_syntax(ctx, ctx->tok.lineno, "newline not allowed in inline table");
/* on comma, continue to scan for next keyval */
if (ctx->tok.tok == COMMA) {
if (eat_token(ctx, COMMA, 1, FLINE))
return -1;
continue;
}
break;
}
if (eat_token(ctx, RBRACE, 1, FLINE))
return -1;
tab->readonly = 1;
return 0;
}
static int valtype(const char *val) {
toml_timestamp_t ts;
if (*val == '\'' || *val == '"')
return 's';
if (toml_value_bool(val, false) == 0)
return 'b';
if (toml_value_int(val, 0) == 0)
return 'i';
if (toml_value_double(val, 0) == 0)
return 'd';
if (toml_value_timestamp(val, &ts) == 0) {
if (ts.year && ts.hour)
return 'T'; /// timestamp
if (ts.year)
return 'D'; /// date
return 't'; /// time
}
return 'u'; /// unknown
}
/* We are at '[...]' */
static int parse_array(context_t *ctx, toml_array_t *arr) {
if (eat_token(ctx, LBRACKET, 0, FLINE))
return -1;
for (;;) {
if (skip_newlines(ctx, 0))
return -1;
if (ctx->tok.tok == RBRACKET) /// until ]
break;
switch (ctx->tok.tok) {
case STRING: {
/// set array kind if this will be the first entry
if (arr->kind == 0)
arr->kind = 'v';
else if (arr->kind != 'v')
arr->kind = 'm';
char *val = ctx->tok.ptr;
int vlen = ctx->tok.len;
/// make a new value in array
toml_arritem_t *newval = create_value_in_array(ctx, arr);
if (!newval)
return e_outofmemory(ctx, FLINE);
if (!(newval->val = STRNDUP(val, vlen)))
return e_outofmemory(ctx, FLINE);
newval->valtype = valtype(newval->val);
/// set array type if this is the first entry
if (arr->nitem == 1)
arr->type = newval->valtype;
else if (arr->type != newval->valtype)
arr->type = 'm'; /// mixed
if (eat_token(ctx, ctx->tok.tok, 0, FLINE))
return -1;
break;
}
case LBRACKET: { /* [ [array], [array] ... ] */
/* set the array kind if this will be the first entry */
if (arr->kind == 0)
arr->kind = 'a';
else if (arr->kind != 'a')
arr->kind = 'm';
toml_array_t *subarr = create_array_in_array(ctx, arr);
if (!subarr)
return -1;
if (parse_array(ctx, subarr))
return -1;
break;
}
case LBRACE: { /* [ {table}, {table} ... ] */
/* set the array kind if this will be the first entry */
if (arr->kind == 0)
arr->kind = 't';
else if (arr->kind != 't')
arr->kind = 'm';
toml_table_t *subtab = create_table_in_array(ctx, arr);
if (!subtab)
return -1;
if (parse_inline_table(ctx, subtab))
return -1;
break;
}
default:
return e_syntax(ctx, ctx->tok.lineno, "syntax error");
}
if (skip_newlines(ctx, 0))
return -1;
/* on comma, continue to scan for next element */
if (ctx->tok.tok == COMMA) {
if (eat_token(ctx, COMMA, 0, FLINE))
return -1;
continue;
}
break;
}
if (eat_token(ctx, RBRACKET, 1, FLINE))
return -1;
return 0;
}
/* handle lines like these:
key = "value"
key = [ array ]
key = { table } */
static int parse_keyval(context_t *ctx, toml_table_t *tab) {
if (tab->readonly) {
return e_forbid(ctx, ctx->tok.lineno, "cannot insert new entry into existing table");
}
token_t key = ctx->tok;
if (eat_token(ctx, STRING, 1, FLINE))
return -1;
if (ctx->tok.tok == DOT) {
/* handle inline dotted key. e.g.
physical.color = "orange"
physical.shape = "round" */
toml_table_t *subtab = 0;
{
int keylen;
char *subtabstr = normalize_key(ctx, key, &keylen);
if (!subtabstr)
return -1;
subtab = toml_table_table(tab, subtabstr);
if (subtab)
subtab->keylen = keylen;
xfree(subtabstr);
}
if (!subtab) {
subtab = create_keytable_in_table(ctx, tab, key);
if (!subtab)
return -1;
}
if (next_token(ctx, true))
return -1;
if (parse_keyval(ctx, subtab))
return -1;
return 0;
}
if (ctx->tok.tok != EQUAL)
return e_syntax(ctx, ctx->tok.lineno, "missing =");
if (next_token(ctx, false))
return -1;
switch (ctx->tok.tok) {
case STRING: { // key = "value"
toml_keyval_t *keyval = create_keyval_in_table(ctx, tab, key);
if (!keyval)
return -1;
token_t val = ctx->tok;
assert(keyval->val == 0);
if (!(keyval->val = STRNDUP(val.ptr, val.len)))
return e_outofmemory(ctx, FLINE);
if (next_token(ctx, true))
return -1;
return 0;
}
case LBRACKET: { /* key = [ array ] */
toml_array_t *arr = create_keyarray_in_table(ctx, tab, key, 0);
if (!arr)
return -1;
if (parse_array(ctx, arr))
return -1;
return 0;
}
case LBRACE: { /* key = { table } */
toml_table_t *nxttab = create_keytable_in_table(ctx, tab, key);
if (!nxttab)
return -1;
if (parse_inline_table(ctx, nxttab))
return -1;
return 0;
}
default:
return e_syntax(ctx, ctx->tok.lineno, "syntax error");
}
return 0;
}
typedef struct tabpath_t tabpath_t;
struct tabpath_t {
int cnt;
token_t key[10];
};
/* at [x.y.z] or [[x.y.z]]
* Scan forward and fill tabpath until it enters ] or ]]
* There will be at least one entry on return. */
static int fill_tabpath(context_t *ctx) {
// clear tpath
for (int i = 0; i < ctx->tpath.top; i++) {
char **p = &ctx->tpath.key[i];
xfree(*p);
*p = 0;
}
ctx->tpath.top = 0;
for (;;) {
if (ctx->tpath.top >= 10)
return e_syntax(ctx, ctx->tok.lineno, "table path is too deep; max allowed is 10.");
if (ctx->tok.tok != STRING)
return e_syntax(ctx, ctx->tok.lineno, "invalid or missing key");
int keylen;
char *key = normalize_key(ctx, ctx->tok, &keylen);
if (!key)
return -1;
ctx->tpath.tok[ctx->tpath.top] = ctx->tok;
ctx->tpath.key[ctx->tpath.top] = key;
ctx->tpath.keylen[ctx->tpath.top] = keylen;
ctx->tpath.top++;
if (next_token(ctx, true))
return -1;
if (ctx->tok.tok == RBRACKET)
break;
if (ctx->tok.tok != DOT)
return e_syntax(ctx, ctx->tok.lineno, "invalid key");
if (next_token(ctx, true))
return -1;
}
if (ctx->tpath.top <= 0)
return e_syntax(ctx, ctx->tok.lineno, "empty table selector");
return 0;
}
/* Walk tabpath from the root, and create new tables on the way.
* Sets ctx->curtab to the final table. */
static int walk_tabpath(context_t *ctx) {
toml_table_t *curtab = ctx->root; /// start from root
for (int i = 0; i < ctx->tpath.top; i++) {
const char *key = ctx->tpath.key[i];
int keylen = ctx->tpath.keylen[i];
toml_keyval_t *nextval = 0;
toml_array_t *nextarr = 0;
toml_table_t *nexttab = 0;
switch (check_key(curtab, key, &nextval, &nextarr, &nexttab)) {
case 't': /// found a table. nexttab is where we will go next.