-
Notifications
You must be signed in to change notification settings - Fork 0
/
jsonfuncs.c
2994 lines (2538 loc) · 75.1 KB
/
jsonfuncs.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
/*-------------------------------------------------------------------------
*
* jsonfuncs.c
* Functions to process JSON data types.
*
* Portions Copyright (c) 1996-2014, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
* IDENTIFICATION
* src/backend/utils/adt/jsonfuncs.c
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include <limits.h>
#include "access/htup_details.h"
#include "catalog/pg_type.h"
#include "fmgr.h"
#include "funcapi.h"
#include "lib/stringinfo.h"
#include "mb/pg_wchar.h"
#include "miscadmin.h"
#include "utils/array.h"
#include "utils/builtins.h"
#include "utils/hsearch.h"
#include "utils/json.h"
#include "utils/jsonapi.h"
#include "jsonbc.h"
#include "utils/lsyscache.h"
#include "utils/memutils.h"
#include "utils/typcache.h"
/* semantic action functions for json_object_keys */
static void okeys_object_field_start(void *state, char *fname, bool isnull);
static void okeys_array_start(void *state);
static void okeys_scalar(void *state, char *token, JsonTokenType tokentype);
/* semantic action functions for json_get* functions */
static void get_object_start(void *state);
static void get_object_end(void *state);
static void get_object_field_start(void *state, char *fname, bool isnull);
static void get_object_field_end(void *state, char *fname, bool isnull);
static void get_array_start(void *state);
static void get_array_end(void *state);
static void get_array_element_start(void *state, bool isnull);
static void get_array_element_end(void *state, bool isnull);
static void get_scalar(void *state, char *token, JsonTokenType tokentype);
/* common worker function for json getter functions */
static Datum get_path_all(FunctionCallInfo fcinfo, bool as_text);
static text *get_worker(text *json, char **tpath, int *ipath, int npath,
bool normalize_results);
static Datum get_jsonbc_path_all(FunctionCallInfo fcinfo, bool as_text);
/* semantic action functions for json_array_length */
static void alen_object_start(void *state);
static void alen_scalar(void *state, char *token, JsonTokenType tokentype);
static void alen_array_element_start(void *state, bool isnull);
/* common workers for json{b}_each* functions */
static Datum each_worker(FunctionCallInfo fcinfo, bool as_text);
static Datum each_worker_jsonb(FunctionCallInfo fcinfo, const char *funcname,
bool as_text);
/* semantic action functions for json_each */
static void each_object_field_start(void *state, char *fname, bool isnull);
static void each_object_field_end(void *state, char *fname, bool isnull);
static void each_array_start(void *state);
static void each_scalar(void *state, char *token, JsonTokenType tokentype);
/* common workers for json{b}_array_elements_* functions */
static Datum elements_worker(FunctionCallInfo fcinfo, const char *funcname,
bool as_text);
static Datum elements_worker_jsonb(FunctionCallInfo fcinfo, const char *funcname,
bool as_text);
/* semantic action functions for json_array_elements */
static void elements_object_start(void *state);
static void elements_array_element_start(void *state, bool isnull);
static void elements_array_element_end(void *state, bool isnull);
static void elements_scalar(void *state, char *token, JsonTokenType tokentype);
/* turn a json object into a hash table */
static HTAB *get_json_object_as_hash(text *json, const char *funcname);
/* common worker for populate_record and to_record */
static Datum populate_record_worker(FunctionCallInfo fcinfo, const char *funcname,
bool have_record_arg);
/* semantic action functions for get_json_object_as_hash */
static void hash_object_field_start(void *state, char *fname, bool isnull);
static void hash_object_field_end(void *state, char *fname, bool isnull);
static void hash_array_start(void *state);
static void hash_scalar(void *state, char *token, JsonTokenType tokentype);
/* semantic action functions for populate_recordset */
static void populate_recordset_object_field_start(void *state, char *fname, bool isnull);
static void populate_recordset_object_field_end(void *state, char *fname, bool isnull);
static void populate_recordset_scalar(void *state, char *token, JsonTokenType tokentype);
static void populate_recordset_object_start(void *state);
static void populate_recordset_object_end(void *state);
static void populate_recordset_array_start(void *state);
static void populate_recordset_array_element_start(void *state, bool isnull);
/* worker function for populate_recordset and to_recordset */
static Datum populate_recordset_worker(FunctionCallInfo fcinfo, const char *funcname,
bool have_record_arg);
/* Worker that takes care of common setup for us */
static JsonbcValue *findJsonbcValueFromContainerLen(JsonbcContainer *container,
uint32 flags,
char *key,
uint32 keylen);
/* state for json_object_keys */
typedef struct OkeysState
{
JsonLexContext *lex;
char **result;
int result_size;
int result_count;
int sent_count;
} OkeysState;
/* state for json_get* functions */
typedef struct GetState
{
JsonLexContext *lex;
text *tresult;
char *result_start;
bool normalize_results;
bool next_scalar;
int npath; /* length of each path-related array */
char **path_names; /* field name(s) being sought */
int *path_indexes; /* array index(es) being sought */
bool *pathok; /* is path matched to current depth? */
int *array_cur_index; /* current element index at each path level */
} GetState;
/* state for json_array_length */
typedef struct AlenState
{
JsonLexContext *lex;
int count;
} AlenState;
/* state for json_each */
typedef struct EachState
{
JsonLexContext *lex;
Tuplestorestate *tuple_store;
TupleDesc ret_tdesc;
MemoryContext tmp_cxt;
char *result_start;
bool normalize_results;
bool next_scalar;
char *normalized_scalar;
} EachState;
/* state for json_array_elements */
typedef struct ElementsState
{
JsonLexContext *lex;
const char *function_name;
Tuplestorestate *tuple_store;
TupleDesc ret_tdesc;
MemoryContext tmp_cxt;
char *result_start;
bool normalize_results;
bool next_scalar;
char *normalized_scalar;
} ElementsState;
/* state for get_json_object_as_hash */
typedef struct JhashState
{
JsonLexContext *lex;
const char *function_name;
HTAB *hash;
char *saved_scalar;
char *save_json_start;
} JHashState;
/* hashtable element */
typedef struct JsonHashEntry
{
char fname[NAMEDATALEN]; /* hash key (MUST BE FIRST) */
char *val;
char *json;
bool isnull;
} JsonHashEntry;
/* these two are stolen from hstore / record_out, used in populate_record* */
typedef struct ColumnIOData
{
Oid column_type;
Oid typiofunc;
Oid typioparam;
FmgrInfo proc;
} ColumnIOData;
typedef struct RecordIOData
{
Oid record_type;
int32 record_typmod;
int ncolumns;
ColumnIOData columns[1]; /* VARIABLE LENGTH ARRAY */
} RecordIOData;
/* state for populate_recordset */
typedef struct PopulateRecordsetState
{
JsonLexContext *lex;
const char *function_name;
HTAB *json_hash;
char *saved_scalar;
char *save_json_start;
Tuplestorestate *tuple_store;
TupleDesc ret_tdesc;
HeapTupleHeader rec;
RecordIOData *my_extra;
MemoryContext fn_mcxt; /* used to stash IO funcs */
} PopulateRecordsetState;
/* Turn a jsonb object into a record */
static void make_row_from_rec_and_jsonb(Jsonbc *element,
PopulateRecordsetState *state);
/*
* SQL function json_object_keys
*
* Returns the set of keys for the object argument.
*
* This SRF operates in value-per-call mode. It processes the
* object during the first call, and the keys are simply stashed
* in an array, whose size is expanded as necessary. This is probably
* safe enough for a list of keys of a single object, since they are
* limited in size to NAMEDATALEN and the number of keys is unlikely to
* be so huge that it has major memory implications.
*/
Datum
jsonbc_object_keys(PG_FUNCTION_ARGS)
{
FuncCallContext *funcctx;
OkeysState *state;
int i;
if (SRF_IS_FIRSTCALL())
{
MemoryContext oldcontext;
Jsonbc *jb = PG_GETARG_JSONB(0);
bool skipNested = false;
JsonbcIterator *it;
JsonbcValue v;
int r;
if (JB_ROOT_IS_SCALAR(jb))
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("cannot call %s on a scalar",
"jsonbc_object_keys")));
else if (JB_ROOT_IS_ARRAY(jb))
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("cannot call %s on an array",
"jsonbc_object_keys")));
funcctx = SRF_FIRSTCALL_INIT();
oldcontext = MemoryContextSwitchTo(funcctx->multi_call_memory_ctx);
state = palloc(sizeof(OkeysState));
state->result_size = JB_ROOT_COUNT(jb);
state->result_count = 0;
state->sent_count = 0;
state->result = palloc(state->result_size * sizeof(char *));
it = JsonbcIteratorInit(&jb->root);
while ((r = JsonbcIteratorNext(&it, &v, skipNested)) != WJB_DONE)
{
skipNested = true;
if (r == WJB_KEY)
{
char *cstr;
cstr = palloc(v.val.string.len + 1 * sizeof(char));
memcpy(cstr, v.val.string.val, v.val.string.len);
cstr[v.val.string.len] = '\0';
state->result[state->result_count++] = cstr;
}
}
MemoryContextSwitchTo(oldcontext);
funcctx->user_fctx = (void *) state;
}
funcctx = SRF_PERCALL_SETUP();
state = (OkeysState *) funcctx->user_fctx;
if (state->sent_count < state->result_count)
{
char *nxt = state->result[state->sent_count++];
SRF_RETURN_NEXT(funcctx, CStringGetTextDatum(nxt));
}
/* cleanup to reduce or eliminate memory leaks */
for (i = 0; i < state->result_count; i++)
pfree(state->result[i]);
pfree(state->result);
pfree(state);
SRF_RETURN_DONE(funcctx);
}
Datum
json_object_keys(PG_FUNCTION_ARGS)
{
FuncCallContext *funcctx;
OkeysState *state;
int i;
if (SRF_IS_FIRSTCALL())
{
text *json = PG_GETARG_TEXT_P(0);
JsonLexContext *lex = makeJsonLexContext(json, true);
JsonSemAction *sem;
MemoryContext oldcontext;
funcctx = SRF_FIRSTCALL_INIT();
oldcontext = MemoryContextSwitchTo(funcctx->multi_call_memory_ctx);
state = palloc(sizeof(OkeysState));
sem = palloc0(sizeof(JsonSemAction));
state->lex = lex;
state->result_size = 256;
state->result_count = 0;
state->sent_count = 0;
state->result = palloc(256 * sizeof(char *));
sem->semstate = (void *) state;
sem->array_start = okeys_array_start;
sem->scalar = okeys_scalar;
sem->object_field_start = okeys_object_field_start;
/* remainder are all NULL, courtesy of palloc0 above */
pg_parse_json(lex, sem);
/* keys are now in state->result */
pfree(lex->strval->data);
pfree(lex->strval);
pfree(lex);
pfree(sem);
MemoryContextSwitchTo(oldcontext);
funcctx->user_fctx = (void *) state;
}
funcctx = SRF_PERCALL_SETUP();
state = (OkeysState *) funcctx->user_fctx;
if (state->sent_count < state->result_count)
{
char *nxt = state->result[state->sent_count++];
SRF_RETURN_NEXT(funcctx, CStringGetTextDatum(nxt));
}
/* cleanup to reduce or eliminate memory leaks */
for (i = 0; i < state->result_count; i++)
pfree(state->result[i]);
pfree(state->result);
pfree(state);
SRF_RETURN_DONE(funcctx);
}
static void
okeys_object_field_start(void *state, char *fname, bool isnull)
{
OkeysState *_state = (OkeysState *) state;
/* only collecting keys for the top level object */
if (_state->lex->lex_level != 1)
return;
/* enlarge result array if necessary */
if (_state->result_count >= _state->result_size)
{
_state->result_size *= 2;
_state->result = (char **)
repalloc(_state->result, sizeof(char *) * _state->result_size);
}
/* save a copy of the field name */
_state->result[_state->result_count++] = pstrdup(fname);
}
static void
okeys_array_start(void *state)
{
OkeysState *_state = (OkeysState *) state;
/* top level must be a json object */
if (_state->lex->lex_level == 0)
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("cannot call %s on an array",
"json_object_keys")));
}
static void
okeys_scalar(void *state, char *token, JsonTokenType tokentype)
{
OkeysState *_state = (OkeysState *) state;
/* top level must be a json object */
if (_state->lex->lex_level == 0)
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("cannot call %s on a scalar",
"json_object_keys")));
}
/*
* json and jsonb getter functions
* these implement the -> ->> #> and #>> operators
* and the json{b?}_extract_path*(json, text, ...) functions
*/
Datum
json_object_field(PG_FUNCTION_ARGS)
{
text *json = PG_GETARG_TEXT_P(0);
text *fname = PG_GETARG_TEXT_PP(1);
char *fnamestr = text_to_cstring(fname);
text *result;
result = get_worker(json, &fnamestr, NULL, 1, false);
if (result != NULL)
PG_RETURN_TEXT_P(result);
else
PG_RETURN_NULL();
}
Datum
jsonbc_object_field(PG_FUNCTION_ARGS)
{
Jsonbc *jb = PG_GETARG_JSONB(0);
text *key = PG_GETARG_TEXT_PP(1);
JsonbcValue *v;
if (!JB_ROOT_IS_OBJECT(jb))
PG_RETURN_NULL();
v = findJsonbcValueFromContainerLen(&jb->root, JB_FOBJECT,
VARDATA_ANY(key),
VARSIZE_ANY_EXHDR(key));
if (v != NULL)
PG_RETURN_JSONB(JsonbcValueToJsonbc(v));
PG_RETURN_NULL();
}
Datum
json_object_field_text(PG_FUNCTION_ARGS)
{
text *json = PG_GETARG_TEXT_P(0);
text *fname = PG_GETARG_TEXT_PP(1);
char *fnamestr = text_to_cstring(fname);
text *result;
result = get_worker(json, &fnamestr, NULL, 1, true);
if (result != NULL)
PG_RETURN_TEXT_P(result);
else
PG_RETURN_NULL();
}
Datum
jsonbc_object_field_text(PG_FUNCTION_ARGS)
{
Jsonbc *jb = PG_GETARG_JSONB(0);
text *key = PG_GETARG_TEXT_PP(1);
JsonbcValue *v;
if (!JB_ROOT_IS_OBJECT(jb))
PG_RETURN_NULL();
v = findJsonbcValueFromContainerLen(&jb->root, JB_FOBJECT,
VARDATA_ANY(key),
VARSIZE_ANY_EXHDR(key));
if (v != NULL)
{
text *result = NULL;
switch (v->type)
{
case jbvNull:
break;
case jbvBool:
result = cstring_to_text(v->val.boolean ? "true" : "false");
break;
case jbvString:
result = cstring_to_text_with_len(v->val.string.val, v->val.string.len);
break;
case jbvNumeric:
result = cstring_to_text(DatumGetCString(DirectFunctionCall1(numeric_out,
PointerGetDatum(v->val.numeric))));
break;
case jbvBinary:
{
StringInfo jtext = makeStringInfo();
(void) JsonbcToCString(jtext, v->val.binary.data, -1);
result = cstring_to_text_with_len(jtext->data, jtext->len);
}
break;
default:
elog(ERROR, "unrecognized jsonb type: %d", (int) v->type);
}
if (result)
PG_RETURN_TEXT_P(result);
}
PG_RETURN_NULL();
}
Datum
json_array_element(PG_FUNCTION_ARGS)
{
text *json = PG_GETARG_TEXT_P(0);
int element = PG_GETARG_INT32(1);
text *result;
result = get_worker(json, NULL, &element, 1, false);
if (result != NULL)
PG_RETURN_TEXT_P(result);
else
PG_RETURN_NULL();
}
Datum
jsonbc_array_element(PG_FUNCTION_ARGS)
{
Jsonbc *jb = PG_GETARG_JSONB(0);
int element = PG_GETARG_INT32(1);
JsonbcValue *v;
if (!JB_ROOT_IS_ARRAY(jb))
PG_RETURN_NULL();
v = getIthJsonbcValueFromContainer(&jb->root, element);
if (v != NULL)
PG_RETURN_JSONB(JsonbcValueToJsonbc(v));
PG_RETURN_NULL();
}
Datum
json_array_element_text(PG_FUNCTION_ARGS)
{
text *json = PG_GETARG_TEXT_P(0);
int element = PG_GETARG_INT32(1);
text *result;
result = get_worker(json, NULL, &element, 1, true);
if (result != NULL)
PG_RETURN_TEXT_P(result);
else
PG_RETURN_NULL();
}
Datum
jsonbc_array_element_text(PG_FUNCTION_ARGS)
{
Jsonbc *jb = PG_GETARG_JSONB(0);
int element = PG_GETARG_INT32(1);
JsonbcValue *v;
if (!JB_ROOT_IS_ARRAY(jb))
PG_RETURN_NULL();
v = getIthJsonbcValueFromContainer(&jb->root, element);
if (v != NULL)
{
text *result = NULL;
switch (v->type)
{
case jbvNull:
break;
case jbvBool:
result = cstring_to_text(v->val.boolean ? "true" : "false");
break;
case jbvString:
result = cstring_to_text_with_len(v->val.string.val, v->val.string.len);
break;
case jbvNumeric:
result = cstring_to_text(DatumGetCString(DirectFunctionCall1(numeric_out,
PointerGetDatum(v->val.numeric))));
break;
case jbvBinary:
{
StringInfo jtext = makeStringInfo();
(void) JsonbcToCString(jtext, v->val.binary.data, -1);
result = cstring_to_text_with_len(jtext->data, jtext->len);
}
break;
default:
elog(ERROR, "unrecognized jsonb type: %d", (int) v->type);
}
if (result)
PG_RETURN_TEXT_P(result);
}
PG_RETURN_NULL();
}
Datum
json_extract_path(PG_FUNCTION_ARGS)
{
return get_path_all(fcinfo, false);
}
Datum
json_extract_path_text(PG_FUNCTION_ARGS)
{
return get_path_all(fcinfo, true);
}
/*
* common routine for extract_path functions
*/
static Datum
get_path_all(FunctionCallInfo fcinfo, bool as_text)
{
text *json = PG_GETARG_TEXT_P(0);
ArrayType *path = PG_GETARG_ARRAYTYPE_P(1);
text *result;
Datum *pathtext;
bool *pathnulls;
int npath;
char **tpath;
int *ipath;
int i;
/*
* If the array contains any null elements, return NULL, on the grounds
* that you'd have gotten NULL if any RHS value were NULL in a nested
* series of applications of the -> operator. (Note: because we also
* return NULL for error cases such as no-such-field, this is true
* regardless of the contents of the rest of the array.)
*/
if (array_contains_nulls(path))
PG_RETURN_NULL();
deconstruct_array(path, TEXTOID, -1, false, 'i',
&pathtext, &pathnulls, &npath);
tpath = palloc(npath * sizeof(char *));
ipath = palloc(npath * sizeof(int));
for (i = 0; i < npath; i++)
{
Assert(!pathnulls[i]);
tpath[i] = TextDatumGetCString(pathtext[i]);
/*
* we have no idea at this stage what structure the document is so
* just convert anything in the path that we can to an integer and set
* all the other integers to -1 which will never match.
*/
if (*tpath[i] != '\0')
{
long ind;
char *endptr;
errno = 0;
ind = strtol(tpath[i], &endptr, 10);
if (*endptr == '\0' && errno == 0 && ind <= INT_MAX && ind >= 0)
ipath[i] = (int) ind;
else
ipath[i] = -1;
}
else
ipath[i] = -1;
}
result = get_worker(json, tpath, ipath, npath, as_text);
if (result != NULL)
PG_RETURN_TEXT_P(result);
else
PG_RETURN_NULL();
}
/*
* get_worker
*
* common worker for all the json getter functions
*
* json: JSON object (in text form)
* tpath[]: field name(s) to extract
* ipath[]: array index(es) (zero-based) to extract
* npath: length of tpath[] and/or ipath[]
* normalize_results: true to de-escape string and null scalars
*
* tpath can be NULL, or any one tpath[] entry can be NULL, if an object
* field is not to be matched at that nesting level. Similarly, ipath can
* be NULL, or any one ipath[] entry can be -1, if an array element is not
* to be matched at that nesting level.
*/
static text *
get_worker(text *json,
char **tpath,
int *ipath,
int npath,
bool normalize_results)
{
JsonLexContext *lex = makeJsonLexContext(json, true);
JsonSemAction *sem = palloc0(sizeof(JsonSemAction));
GetState *state = palloc0(sizeof(GetState));
Assert(npath >= 0);
state->lex = lex;
/* is it "_as_text" variant? */
state->normalize_results = normalize_results;
state->npath = npath;
state->path_names = tpath;
state->path_indexes = ipath;
state->pathok = palloc0(sizeof(bool) * npath);
state->array_cur_index = palloc(sizeof(int) * npath);
if (npath > 0)
state->pathok[0] = true;
sem->semstate = (void *) state;
/*
* Not all variants need all the semantic routines. Only set the ones that
* are actually needed for maximum efficiency.
*/
sem->scalar = get_scalar;
if (npath == 0)
{
sem->object_start = get_object_start;
sem->object_end = get_object_end;
sem->array_start = get_array_start;
sem->array_end = get_array_end;
}
if (tpath != NULL)
{
sem->object_field_start = get_object_field_start;
sem->object_field_end = get_object_field_end;
}
if (ipath != NULL)
{
sem->array_start = get_array_start;
sem->array_element_start = get_array_element_start;
sem->array_element_end = get_array_element_end;
}
pg_parse_json(lex, sem);
return state->tresult;
}
static void
get_object_start(void *state)
{
GetState *_state = (GetState *) state;
int lex_level = _state->lex->lex_level;
if (lex_level == 0 && _state->npath == 0)
{
/*
* Special case: we should match the entire object. We only need this
* at outermost level because at nested levels the match will have
* been started by the outer field or array element callback.
*/
_state->result_start = _state->lex->token_start;
}
}
static void
get_object_end(void *state)
{
GetState *_state = (GetState *) state;
int lex_level = _state->lex->lex_level;
if (lex_level == 0 && _state->npath == 0)
{
/* Special case: return the entire object */
char *start = _state->result_start;
int len = _state->lex->prev_token_terminator - start;
_state->tresult = cstring_to_text_with_len(start, len);
}
}
static void
get_object_field_start(void *state, char *fname, bool isnull)
{
GetState *_state = (GetState *) state;
bool get_next = false;
int lex_level = _state->lex->lex_level;
if (lex_level <= _state->npath &&
_state->pathok[lex_level - 1] &&
_state->path_names != NULL &&
_state->path_names[lex_level - 1] != NULL &&
strcmp(fname, _state->path_names[lex_level - 1]) == 0)
{
if (lex_level < _state->npath)
{
/* if not at end of path just mark path ok */
_state->pathok[lex_level] = true;
}
else
{
/* end of path, so we want this value */
get_next = true;
}
}
if (get_next)
{
/* this object overrides any previous matching object */
_state->tresult = NULL;
_state->result_start = NULL;
if (_state->normalize_results &&
_state->lex->token_type == JSON_TOKEN_STRING)
{
/* for as_text variants, tell get_scalar to set it for us */
_state->next_scalar = true;
}
else
{
/* for non-as_text variants, just note the json starting point */
_state->result_start = _state->lex->token_start;
}
}
}
static void
get_object_field_end(void *state, char *fname, bool isnull)
{
GetState *_state = (GetState *) state;
bool get_last = false;
int lex_level = _state->lex->lex_level;
/* same tests as in get_object_field_start */
if (lex_level <= _state->npath &&
_state->pathok[lex_level - 1] &&
_state->path_names != NULL &&
_state->path_names[lex_level - 1] != NULL &&
strcmp(fname, _state->path_names[lex_level - 1]) == 0)
{
if (lex_level < _state->npath)
{
/* done with this field so reset pathok */
_state->pathok[lex_level] = false;
}
else
{
/* end of path, so we want this value */
get_last = true;
}
}
/* for as_text scalar case, our work is already done */
if (get_last && _state->result_start != NULL)
{
/*
* make a text object from the string from the prevously noted json
* start up to the end of the previous token (the lexer is by now
* ahead of us on whatever came after what we're interested in).
*/
if (isnull && _state->normalize_results)
_state->tresult = (text *) NULL;
else
{
char *start = _state->result_start;
int len = _state->lex->prev_token_terminator - start;
_state->tresult = cstring_to_text_with_len(start, len);
}
/* this should be unnecessary but let's do it for cleanliness: */
_state->result_start = NULL;
}
}
static void
get_array_start(void *state)
{
GetState *_state = (GetState *) state;
int lex_level = _state->lex->lex_level;
if (lex_level < _state->npath)
{
/* Initialize counting of elements in this array */
_state->array_cur_index[lex_level] = -1;
}
else if (lex_level == 0 && _state->npath == 0)
{
/*
* Special case: we should match the entire array. We only need this
* at outermost level because at nested levels the match will have
* been started by the outer field or array element callback.
*/
_state->result_start = _state->lex->token_start;
}
}
static void
get_array_end(void *state)
{
GetState *_state = (GetState *) state;
int lex_level = _state->lex->lex_level;
if (lex_level == 0 && _state->npath == 0)
{
/* Special case: return the entire array */
char *start = _state->result_start;
int len = _state->lex->prev_token_terminator - start;
_state->tresult = cstring_to_text_with_len(start, len);
}
}
static void
get_array_element_start(void *state, bool isnull)
{
GetState *_state = (GetState *) state;
bool get_next = false;
int lex_level = _state->lex->lex_level;
/* Update array element counter */
if (lex_level <= _state->npath)
_state->array_cur_index[lex_level - 1]++;
if (lex_level <= _state->npath &&
_state->pathok[lex_level - 1] &&
_state->path_indexes != NULL &&
_state->array_cur_index[lex_level - 1] == _state->path_indexes[lex_level - 1])
{
if (lex_level < _state->npath)
{
/* if not at end of path just mark path ok */
_state->pathok[lex_level] = true;
}
else
{
/* end of path, so we want this value */
get_next = true;
}
}
/* same logic as for objects */
if (get_next)
{
_state->tresult = NULL;
_state->result_start = NULL;
if (_state->normalize_results &&
_state->lex->token_type == JSON_TOKEN_STRING)
{
_state->next_scalar = true;
}
else
{
_state->result_start = _state->lex->token_start;
}
}
}
static void
get_array_element_end(void *state, bool isnull)
{