forked from nlohmann/json
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathparser.hpp
More file actions
589 lines (510 loc) · 17.2 KB
/
parser.hpp
File metadata and controls
589 lines (510 loc) · 17.2 KB
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
#pragma once
#include <cassert> // assert
#include <cmath> // isfinite
#include <cstdint> // uint8_t
#include <functional> // function
#include <string> // string
#include <utility> // move
#include <nlohmann/detail/exceptions.hpp>
#include <nlohmann/detail/macro_scope.hpp>
#include <nlohmann/detail/input/input_adapters.hpp>
#include <nlohmann/detail/input/lexer.hpp>
#include <nlohmann/detail/value_t.hpp>
namespace nlohmann
{
namespace detail
{
////////////
// parser //
////////////
/*!
@brief syntax analysis
This class implements a recursive decent parser.
*/
template<typename BasicJsonType>
class parser
{
using number_integer_t = typename BasicJsonType::number_integer_t;
using number_unsigned_t = typename BasicJsonType::number_unsigned_t;
using number_float_t = typename BasicJsonType::number_float_t;
using lexer_t = lexer<BasicJsonType>;
using token_type = typename lexer_t::token_type;
public:
enum class parse_event_t : uint8_t
{
/// the parser read `{` and started to process a JSON object
object_start,
/// the parser read `}` and finished processing a JSON object
object_end,
/// the parser read `[` and started to process a JSON array
array_start,
/// the parser read `]` and finished processing a JSON array
array_end,
/// the parser read a key of a value in an object
key,
/// the parser finished reading a JSON value
value
};
using parser_callback_t =
std::function<bool(int depth, parse_event_t event, BasicJsonType& parsed)>;
/// a parser reading from an input adapter
explicit parser(detail::input_adapter_t adapter,
const parser_callback_t cb = nullptr,
const bool allow_exceptions_ = true)
: callback(cb), m_lexer(adapter), allow_exceptions(allow_exceptions_)
{}
/*!
@brief public parser interface
@param[in] strict whether to expect the last token to be EOF
@param[in,out] result parsed JSON value
@throw parse_error.101 in case of an unexpected token
@throw parse_error.102 if to_unicode fails or surrogate error
@throw parse_error.103 if to_unicode fails
*/
void parse(const bool strict, BasicJsonType& result)
{
// read first token
get_token();
parse_internal(true, result);
result.assert_invariant();
// in strict mode, input must be completely read
if (strict)
{
get_token();
expect(token_type::end_of_input);
}
// in case of an error, return discarded value
if (errored)
{
result = value_t::discarded;
return;
}
// set top-level value to null if it was discarded by the callback
// function
if (result.is_discarded())
{
result = nullptr;
}
}
/*!
@brief public accept interface
@param[in] strict whether to expect the last token to be EOF
@return whether the input is a proper JSON text
*/
bool accept(const bool strict = true)
{
// read first token
get_token();
if (not accept_internal())
{
return false;
}
// strict => last token must be EOF
return not strict or (get_token() == token_type::end_of_input);
}
private:
/*!
@brief the actual parser
@throw parse_error.101 in case of an unexpected token
@throw parse_error.102 if to_unicode fails or surrogate error
@throw parse_error.103 if to_unicode fails
*/
void parse_internal(bool keep, BasicJsonType& result)
{
// never parse after a parse error was detected
assert(not errored);
// start with a discarded value
if (not result.is_discarded())
{
result.m_value.destroy(result.m_type);
result.m_type = value_t::discarded;
}
switch (last_token)
{
case token_type::begin_object:
{
if (keep)
{
if (callback)
{
keep = callback(depth++, parse_event_t::object_start, result);
}
if (not callback or keep)
{
// explicitly set result to object to cope with {}
result.m_type = value_t::object;
result.m_value = value_t::object;
}
}
// read next token
get_token();
// closing } -> we are done
if (last_token == token_type::end_object)
{
if (keep and callback and not callback(--depth, parse_event_t::object_end, result))
{
result.m_value.destroy(result.m_type);
result.m_type = value_t::discarded;
}
break;
}
// parse values
std::string key;
BasicJsonType value;
while (true)
{
// store key
if (not expect(token_type::value_string))
{
return;
}
key = m_lexer.move_string();
bool keep_tag = false;
if (keep)
{
if (callback)
{
BasicJsonType k(key);
keep_tag = callback(depth, parse_event_t::key, k);
}
else
{
keep_tag = true;
}
}
// parse separator (:)
get_token();
if (not expect(token_type::name_separator))
{
return;
}
// parse and add value
get_token();
value.m_value.destroy(value.m_type);
value.m_type = value_t::discarded;
parse_internal(keep, value);
if (JSON_UNLIKELY(errored))
{
return;
}
if (keep and keep_tag and not value.is_discarded())
{
result.m_value.object->emplace(std::move(key), std::move(value));
}
// comma -> next value
get_token();
if (last_token == token_type::value_separator)
{
get_token();
continue;
}
// closing }
if (not expect(token_type::end_object))
{
return;
}
break;
}
if (keep and callback and not callback(--depth, parse_event_t::object_end, result))
{
result.m_value.destroy(result.m_type);
result.m_type = value_t::discarded;
}
break;
}
case token_type::begin_array:
{
if (keep)
{
if (callback)
{
keep = callback(depth++, parse_event_t::array_start, result);
}
if (not callback or keep)
{
// explicitly set result to array to cope with []
result.m_type = value_t::array;
result.m_value = value_t::array;
}
}
// read next token
get_token();
// closing ] -> we are done
if (last_token == token_type::end_array)
{
if (callback and not callback(--depth, parse_event_t::array_end, result))
{
result.m_value.destroy(result.m_type);
result.m_type = value_t::discarded;
}
break;
}
// parse values
BasicJsonType value;
while (true)
{
// parse value
value.m_value.destroy(value.m_type);
value.m_type = value_t::discarded;
parse_internal(keep, value);
if (JSON_UNLIKELY(errored))
{
return;
}
if (keep and not value.is_discarded())
{
result.m_value.array->push_back(std::move(value));
}
// comma -> next value
get_token();
if (last_token == token_type::value_separator)
{
get_token();
continue;
}
// closing ]
if (not expect(token_type::end_array))
{
return;
}
break;
}
if (keep and callback and not callback(--depth, parse_event_t::array_end, result))
{
result.m_value.destroy(result.m_type);
result.m_type = value_t::discarded;
}
break;
}
case token_type::literal_null:
{
result.m_type = value_t::null;
break;
}
case token_type::value_string:
{
result.m_type = value_t::string;
result.m_value = m_lexer.move_string();
break;
}
case token_type::literal_true:
{
result.m_type = value_t::boolean;
result.m_value = true;
break;
}
case token_type::literal_false:
{
result.m_type = value_t::boolean;
result.m_value = false;
break;
}
case token_type::value_unsigned:
{
result.m_type = value_t::number_unsigned;
result.m_value = m_lexer.get_number_unsigned();
break;
}
case token_type::value_integer:
{
result.m_type = value_t::number_integer;
result.m_value = m_lexer.get_number_integer();
break;
}
case token_type::value_float:
{
result.m_type = value_t::number_float;
result.m_value = m_lexer.get_number_float();
// throw in case of infinity or NAN
if (JSON_UNLIKELY(not std::isfinite(result.m_value.number_float)))
{
if (allow_exceptions)
{
JSON_THROW(out_of_range::create(406, "number overflow parsing '" +
m_lexer.get_token_string() + "'"));
}
expect(token_type::uninitialized);
}
break;
}
case token_type::parse_error:
{
// using "uninitialized" to avoid "expected" message
if (not expect(token_type::uninitialized))
{
return;
}
break; // LCOV_EXCL_LINE
}
default:
{
// the last token was unexpected; we expected a value
if (not expect(token_type::literal_or_value))
{
return;
}
break; // LCOV_EXCL_LINE
}
}
if (keep and callback and not callback(depth, parse_event_t::value, result))
{
result.m_type = value_t::discarded;
}
}
/*!
@brief the actual acceptor
@invariant 1. The last token is not yet processed. Therefore, the caller
of this function must make sure a token has been read.
2. When this function returns, the last token is processed.
That is, the last read character was already considered.
This invariant makes sure that no token needs to be "unput".
*/
bool accept_internal()
{
switch (last_token)
{
case token_type::begin_object:
{
// read next token
get_token();
// closing } -> we are done
if (last_token == token_type::end_object)
{
return true;
}
// parse values
while (true)
{
// parse key
if (last_token != token_type::value_string)
{
return false;
}
// parse separator (:)
get_token();
if (last_token != token_type::name_separator)
{
return false;
}
// parse value
get_token();
if (not accept_internal())
{
return false;
}
// comma -> next value
get_token();
if (last_token == token_type::value_separator)
{
get_token();
continue;
}
// closing }
return (last_token == token_type::end_object);
}
}
case token_type::begin_array:
{
// read next token
get_token();
// closing ] -> we are done
if (last_token == token_type::end_array)
{
return true;
}
// parse values
while (true)
{
// parse value
if (not accept_internal())
{
return false;
}
// comma -> next value
get_token();
if (last_token == token_type::value_separator)
{
get_token();
continue;
}
// closing ]
return (last_token == token_type::end_array);
}
}
case token_type::value_float:
{
// reject infinity or NAN
return std::isfinite(m_lexer.get_number_float());
}
case token_type::literal_false:
case token_type::literal_null:
case token_type::literal_true:
case token_type::value_integer:
case token_type::value_string:
case token_type::value_unsigned:
return true;
default: // the last token was unexpected
return false;
}
}
/// get next token from lexer
token_type get_token()
{
return (last_token = m_lexer.scan());
}
/*!
@throw parse_error.101 if expected token did not occur
*/
bool expect(token_type t)
{
if (JSON_UNLIKELY(t != last_token))
{
errored = true;
expected = t;
if (allow_exceptions)
{
throw_exception();
}
else
{
return false;
}
}
return true;
}
[[noreturn]] void throw_exception() const
{
std::string error_msg = "syntax error - ";
if (last_token == token_type::parse_error)
{
error_msg += std::string(m_lexer.get_error_message()) + "; last read: '" +
m_lexer.get_token_string() + "'";
}
else
{
error_msg += "unexpected " + std::string(lexer_t::token_type_name(last_token));
}
if (expected != token_type::uninitialized)
{
error_msg += "; expected " + std::string(lexer_t::token_type_name(expected));
}
JSON_THROW(parse_error::create(101, m_lexer.get_position(), error_msg));
}
private:
/// current level of recursion
int depth = 0;
/// callback function
const parser_callback_t callback = nullptr;
/// the type of the last read token
token_type last_token = token_type::uninitialized;
/// the lexer
lexer_t m_lexer;
/// whether a syntax error occurred
bool errored = false;
/// possible reason for the syntax error
token_type expected = token_type::uninitialized;
/// whether to throw exceptions in case of errors
const bool allow_exceptions = true;
};
}
}