summaryrefslogtreecommitdiff
path: root/include/lib/modernjson/detail/input/parser.hpp
blob: d205bbb079efd20007f3775539050bc1c4859db5 (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
#pragma once

#include <cassert> // assert
#include <cmath> // isfinite
#include <cstdint> // uint8_t
#include <functional> // function
#include <string> // string
#include <utility> // move

#include <lib/modernjson/detail/exceptions.hpp>
#include <lib/modernjson/detail/macro_scope.hpp>
#include <lib/modernjson/detail/meta/is_sax.hpp>
#include <lib/modernjson/detail/input/input_adapters.hpp>
#include <lib/modernjson/detail/input/json_sax.hpp>
#include <lib/modernjson/detail/input/lexer.hpp>
#include <lib/modernjson/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 string_t = typename BasicJsonType::string_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(std::move(adapter)), allow_exceptions(allow_exceptions_)
    {
        // read first token
        get_token();
    }

    /*!
    @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)
    {
        if (callback)
        {
            json_sax_dom_callback_parser<BasicJsonType> sdp(result, callback, allow_exceptions);
            sax_parse_internal(&sdp);
            result.assert_invariant();

            // in strict mode, input must be completely read
            if (strict and (get_token() != token_type::end_of_input))
            {
                sdp.parse_error(m_lexer.get_position(),
                                m_lexer.get_token_string(),
                                parse_error::create(101, m_lexer.get_position(),
                                                    exception_message(token_type::end_of_input, "value")));
            }

            // in case of an error, return discarded value
            if (sdp.is_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;
            }
        }
        else
        {
            json_sax_dom_parser<BasicJsonType> sdp(result, allow_exceptions);
            sax_parse_internal(&sdp);
            result.assert_invariant();

            // in strict mode, input must be completely read
            if (strict and (get_token() != token_type::end_of_input))
            {
                sdp.parse_error(m_lexer.get_position(),
                                m_lexer.get_token_string(),
                                parse_error::create(101, m_lexer.get_position(),
                                                    exception_message(token_type::end_of_input, "value")));
            }

            // in case of an error, return discarded value
            if (sdp.is_errored())
            {
                result = value_t::discarded;
                return;
            }
        }
    }

    /*!
    @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)
    {
        json_sax_acceptor<BasicJsonType> sax_acceptor;
        return sax_parse(&sax_acceptor, strict);
    }

    template <typename SAX>
    bool sax_parse(SAX* sax, const bool strict = true)
    {
        (void)detail::is_sax_static_asserts<SAX, BasicJsonType> {};
        const bool result = sax_parse_internal(sax);

        // strict mode: next byte must be EOF
        if (result and strict and (get_token() != token_type::end_of_input))
        {
            return sax->parse_error(m_lexer.get_position(),
                                    m_lexer.get_token_string(),
                                    parse_error::create(101, m_lexer.get_position(),
                                            exception_message(token_type::end_of_input, "value")));
        }

        return result;
    }

  private:
    template <typename SAX>
    bool sax_parse_internal(SAX* sax)
    {
        // stack to remember the hierarchy of structured values we are parsing
        // true = array; false = object
        std::vector<bool> states;
        // value to avoid a goto (see comment where set to true)
        bool skip_to_state_evaluation = false;

        while (true)
        {
            if (not skip_to_state_evaluation)
            {
                // invariant: get_token() was called before each iteration
                switch (last_token)
                {
                    case token_type::begin_object:
                    {
                        if (JSON_UNLIKELY(not sax->start_object(std::size_t(-1))))
                        {
                            return false;
                        }

                        // closing } -> we are done
                        if (get_token() == token_type::end_object)
                        {
                            if (JSON_UNLIKELY(not sax->end_object()))
                            {
                                return false;
                            }
                            break;
                        }

                        // parse key
                        if (JSON_UNLIKELY(last_token != token_type::value_string))
                        {
                            return sax->parse_error(m_lexer.get_position(),
                                                    m_lexer.get_token_string(),
                                                    parse_error::create(101, m_lexer.get_position(),
                                                            exception_message(token_type::value_string, "object key")));
                        }
                        if (JSON_UNLIKELY(not sax->key(m_lexer.get_string())))
                        {
                            return false;
                        }

                        // parse separator (:)
                        if (JSON_UNLIKELY(get_token() != token_type::name_separator))
                        {
                            return sax->parse_error(m_lexer.get_position(),
                                                    m_lexer.get_token_string(),
                                                    parse_error::create(101, m_lexer.get_position(),
                                                            exception_message(token_type::name_separator, "object separator")));
                        }

                        // remember we are now inside an object
                        states.push_back(false);

                        // parse values
                        get_token();
                        continue;
                    }

                    case token_type::begin_array:
                    {
                        if (JSON_UNLIKELY(not sax->start_array(std::size_t(-1))))
                        {
                            return false;
                        }

                        // closing ] -> we are done
                        if (get_token() == token_type::end_array)
                        {
                            if (JSON_UNLIKELY(not sax->end_array()))
                            {
                                return false;
                            }
                            break;
                        }

                        // remember we are now inside an array
                        states.push_back(true);

                        // parse values (no need to call get_token)
                        continue;
                    }

                    case token_type::value_float:
                    {
                        const auto res = m_lexer.get_number_float();

                        if (JSON_UNLIKELY(not std::isfinite(res)))
                        {
                            return sax->parse_error(m_lexer.get_position(),
                                                    m_lexer.get_token_string(),
                                                    out_of_range::create(406, "number overflow parsing '" + m_lexer.get_token_string() + "'"));
                        }
                        else
                        {
                            if (JSON_UNLIKELY(not sax->number_float(res, m_lexer.get_string())))
                            {
                                return false;
                            }
                            break;
                        }
                    }

                    case token_type::literal_false:
                    {
                        if (JSON_UNLIKELY(not sax->boolean(false)))
                        {
                            return false;
                        }
                        break;
                    }

                    case token_type::literal_null:
                    {
                        if (JSON_UNLIKELY(not sax->null()))
                        {
                            return false;
                        }
                        break;
                    }

                    case token_type::literal_true:
                    {
                        if (JSON_UNLIKELY(not sax->boolean(true)))
                        {
                            return false;
                        }
                        break;
                    }

                    case token_type::value_integer:
                    {
                        if (JSON_UNLIKELY(not sax->number_integer(m_lexer.get_number_integer())))
                        {
                            return false;
                        }
                        break;
                    }

                    case token_type::value_string:
                    {
                        if (JSON_UNLIKELY(not sax->string(m_lexer.get_string())))
                        {
                            return false;
                        }
                        break;
                    }

                    case token_type::value_unsigned:
                    {
                        if (JSON_UNLIKELY(not sax->number_unsigned(m_lexer.get_number_unsigned())))
                        {
                            return false;
                        }
                        break;
                    }

                    case token_type::parse_error:
                    {
                        // using "uninitialized" to avoid "expected" message
                        return sax->parse_error(m_lexer.get_position(),
                                                m_lexer.get_token_string(),
                                                parse_error::create(101, m_lexer.get_position(),
                                                        exception_message(token_type::uninitialized, "value")));
                    }

                    default: // the last token was unexpected
                    {
                        return sax->parse_error(m_lexer.get_position(),
                                                m_lexer.get_token_string(),
                                                parse_error::create(101, m_lexer.get_position(),
                                                        exception_message(token_type::literal_or_value, "value")));
                    }
                }
            }
            else
            {
                skip_to_state_evaluation = false;
            }

            // we reached this line after we successfully parsed a value
            if (states.empty())
            {
                // empty stack: we reached the end of the hierarchy: done
                return true;
            }
            else
            {
                if (states.back())  // array
                {
                    // comma -> next value
                    if (get_token() == token_type::value_separator)
                    {
                        // parse a new value
                        get_token();
                        continue;
                    }

                    // closing ]
                    if (JSON_LIKELY(last_token == token_type::end_array))
                    {
                        if (JSON_UNLIKELY(not sax->end_array()))
                        {
                            return false;
                        }

                        // We are done with this array. Before we can parse a
                        // new value, we need to evaluate the new state first.
                        // By setting skip_to_state_evaluation to false, we
                        // are effectively jumping to the beginning of this if.
                        assert(not states.empty());
                        states.pop_back();
                        skip_to_state_evaluation = true;
                        continue;
                    }
                    else
                    {
                        return sax->parse_error(m_lexer.get_position(),
                                                m_lexer.get_token_string(),
                                                parse_error::create(101, m_lexer.get_position(),
                                                        exception_message(token_type::end_array, "array")));
                    }
                }
                else  // object
                {
                    // comma -> next value
                    if (get_token() == token_type::value_separator)
                    {
                        // parse key
                        if (JSON_UNLIKELY(get_token() != token_type::value_string))
                        {
                            return sax->parse_error(m_lexer.get_position(),
                                                    m_lexer.get_token_string(),
                                                    parse_error::create(101, m_lexer.get_position(),
                                                            exception_message(token_type::value_string, "object key")));
                        }
                        else
                        {
                            if (JSON_UNLIKELY(not sax->key(m_lexer.get_string())))
                            {
                                return false;
                            }
                        }

                        // parse separator (:)
                        if (JSON_UNLIKELY(get_token() != token_type::name_separator))
                        {
                            return sax->parse_error(m_lexer.get_position(),
                                                    m_lexer.get_token_string(),
                                                    parse_error::create(101, m_lexer.get_position(),
                                                            exception_message(token_type::name_separator, "object separator")));
                        }

                        // parse values
                        get_token();
                        continue;
                    }

                    // closing }
                    if (JSON_LIKELY(last_token == token_type::end_object))
                    {
                        if (JSON_UNLIKELY(not sax->end_object()))
                        {
                            return false;
                        }

                        // We are done with this object. Before we can parse a
                        // new value, we need to evaluate the new state first.
                        // By setting skip_to_state_evaluation to false, we
                        // are effectively jumping to the beginning of this if.
                        assert(not states.empty());
                        states.pop_back();
                        skip_to_state_evaluation = true;
                        continue;
                    }
                    else
                    {
                        return sax->parse_error(m_lexer.get_position(),
                                                m_lexer.get_token_string(),
                                                parse_error::create(101, m_lexer.get_position(),
                                                        exception_message(token_type::end_object, "object")));
                    }
                }
            }
        }
    }

    /// get next token from lexer
    token_type get_token()
    {
        return (last_token = m_lexer.scan());
    }

    std::string exception_message(const token_type expected, const std::string& context)
    {
        std::string error_msg = "syntax error ";

        if (not context.empty())
        {
            error_msg += "while parsing " + context + " ";
        }

        error_msg += "- ";

        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));
        }

        return error_msg;
    }

  private:
    /// 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 to throw exceptions in case of errors
    const bool allow_exceptions = true;
};
}  // namespace detail
}  // namespace nlohmann