summaryrefslogtreecommitdiffstats
path: root/src/3rdparty/v8/src/json-parser.h
blob: d22cd0da3aa1a97b46ab80f1cc66f25dc28aded0 (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
// Copyright 2011 the V8 project authors. All rights reserved.
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
//
//     * Redistributions of source code must retain the above copyright
//       notice, this list of conditions and the following disclaimer.
//     * Redistributions in binary form must reproduce the above
//       copyright notice, this list of conditions and the following
//       disclaimer in the documentation and/or other materials provided
//       with the distribution.
//     * Neither the name of Google Inc. nor the names of its
//       contributors may be used to endorse or promote products derived
//       from this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

#ifndef V8_JSON_PARSER_H_
#define V8_JSON_PARSER_H_

#include "v8.h"

#include "char-predicates-inl.h"
#include "v8conversions.h"
#include "messages.h"
#include "spaces-inl.h"
#include "token.h"

namespace v8 {
namespace internal {

// A simple json parser.
template <bool seq_ascii>
class JsonParser BASE_EMBEDDED {
 public:
  static Handle<Object> Parse(Handle<String> source) {
    return JsonParser().ParseJson(source);
  }

  static const int kEndOfString = -1;

 private:
  // Parse a string containing a single JSON value.
  Handle<Object> ParseJson(Handle<String> source);

  inline void Advance() {
    position_++;
    if (position_ >= source_length_) {
      c0_ = kEndOfString;
    } else if (seq_ascii) {
      c0_ = seq_source_->SeqAsciiStringGet(position_);
    } else {
      c0_ = source_->Get(position_);
    }
  }

  // The JSON lexical grammar is specified in the ECMAScript 5 standard,
  // section 15.12.1.1. The only allowed whitespace characters between tokens
  // are tab, carriage-return, newline and space.

  inline void AdvanceSkipWhitespace() {
    do {
      Advance();
    } while (c0_ == '\t' || c0_ == '\r' || c0_ == '\n' || c0_ == ' ');
  }

  inline void SkipWhitespace() {
    while (c0_ == '\t' || c0_ == '\r' || c0_ == '\n' || c0_ == ' ') {
      Advance();
    }
  }

  inline uc32 AdvanceGetChar() {
    Advance();
    return c0_;
  }

  // Checks that current charater is c.
  // If so, then consume c and skip whitespace.
  inline bool MatchSkipWhiteSpace(uc32 c) {
    if (c0_ == c) {
      AdvanceSkipWhitespace();
      return true;
    }
    return false;
  }

  // A JSON string (production JSONString) is subset of valid JavaScript string
  // literals. The string must only be double-quoted (not single-quoted), and
  // the only allowed backslash-escapes are ", /, \, b, f, n, r, t and
  // four-digit hex escapes (uXXXX). Any other use of backslashes is invalid.
  Handle<String> ParseJsonString() {
    return ScanJsonString<false>();
  }
  Handle<String> ParseJsonSymbol() {
    return ScanJsonString<true>();
  }
  template <bool is_symbol>
  Handle<String> ScanJsonString();
  // Creates a new string and copies prefix[start..end] into the beginning
  // of it. Then scans the rest of the string, adding characters after the
  // prefix. Called by ScanJsonString when reaching a '\' or non-ASCII char.
  template <typename StringType, typename SinkChar>
  Handle<String> SlowScanJsonString(Handle<String> prefix, int start, int end);

  // A JSON number (production JSONNumber) is a subset of the valid JavaScript
  // decimal number literals.
  // It includes an optional minus sign, must have at least one
  // digit before and after a decimal point, may not have prefixed zeros (unless
  // the integer part is zero), and may include an exponent part (e.g., "e-10").
  // Hexadecimal and octal numbers are not allowed.
  Handle<Object> ParseJsonNumber();

  // Parse a single JSON value from input (grammar production JSONValue).
  // A JSON value is either a (double-quoted) string literal, a number literal,
  // one of "true", "false", or "null", or an object or array literal.
  Handle<Object> ParseJsonValue();

  // Parse a JSON object literal (grammar production JSONObject).
  // An object literal is a squiggly-braced and comma separated sequence
  // (possibly empty) of key/value pairs, where the key is a JSON string
  // literal, the value is a JSON value, and the two are separated by a colon.
  // A JSON array doesn't allow numbers and identifiers as keys, like a
  // JavaScript array.
  Handle<Object> ParseJsonObject();

  // Parses a JSON array literal (grammar production JSONArray). An array
  // literal is a square-bracketed and comma separated sequence (possibly empty)
  // of JSON values.
  // A JSON array doesn't allow leaving out values from the sequence, nor does
  // it allow a terminal comma, like a JavaScript array does.
  Handle<Object> ParseJsonArray();


  // Mark that a parsing error has happened at the current token, and
  // return a null handle. Primarily for readability.
  inline Handle<Object> ReportUnexpectedCharacter() {
    return Handle<Object>::null();
  }

  inline Isolate* isolate() { return isolate_; }

  static const int kInitialSpecialStringLength = 1024;


 private:
  Handle<String> source_;
  int source_length_;
  Handle<SeqAsciiString> seq_source_;

  Isolate* isolate_;
  uc32 c0_;
  int position_;
};

template <bool seq_ascii>
Handle<Object> JsonParser<seq_ascii>::ParseJson(Handle<String> source) {
  isolate_ = source->map()->GetHeap()->isolate();
  FlattenString(source);
  source_ = source;
  source_length_ = source_->length();

  // Optimized fast case where we only have ASCII characters.
  if (seq_ascii) {
    seq_source_ = Handle<SeqAsciiString>::cast(source_);
  }

  // Set initial position right before the string.
  position_ = -1;
  // Advance to the first character (possibly EOS)
  AdvanceSkipWhitespace();
  Handle<Object> result = ParseJsonValue();
  if (result.is_null() || c0_ != kEndOfString) {
    // Parse failed. Current character is the unexpected token.

    const char* message;
    Factory* factory = isolate()->factory();
    Handle<JSArray> array;

    switch (c0_) {
      case kEndOfString:
        message = "unexpected_eos";
        array = factory->NewJSArray(0);
        break;
      case '-':
      case '0':
      case '1':
      case '2':
      case '3':
      case '4':
      case '5':
      case '6':
      case '7':
      case '8':
      case '9':
        message = "unexpected_token_number";
        array = factory->NewJSArray(0);
        break;
      case '"':
        message = "unexpected_token_string";
        array = factory->NewJSArray(0);
        break;
      default:
        message = "unexpected_token";
        Handle<Object> name = LookupSingleCharacterStringFromCode(c0_);
        Handle<FixedArray> element = factory->NewFixedArray(1);
        element->set(0, *name);
        array = factory->NewJSArrayWithElements(element);
        break;
    }

    MessageLocation location(factory->NewScript(source),
                             position_,
                             position_ + 1);
    Handle<Object> result = factory->NewSyntaxError(message, array);
    isolate()->Throw(*result, &location);
    return Handle<Object>::null();
  }
  return result;
}


// Parse any JSON value.
template <bool seq_ascii>
Handle<Object> JsonParser<seq_ascii>::ParseJsonValue() {
  switch (c0_) {
    case '"':
      return ParseJsonString();
    case '-':
    case '0':
    case '1':
    case '2':
    case '3':
    case '4':
    case '5':
    case '6':
    case '7':
    case '8':
    case '9':
      return ParseJsonNumber();
    case 'f':
      if (AdvanceGetChar() == 'a' && AdvanceGetChar() == 'l' &&
          AdvanceGetChar() == 's' && AdvanceGetChar() == 'e') {
        AdvanceSkipWhitespace();
        return isolate()->factory()->false_value();
      } else {
        return ReportUnexpectedCharacter();
      }
    case 't':
      if (AdvanceGetChar() == 'r' && AdvanceGetChar() == 'u' &&
          AdvanceGetChar() == 'e') {
        AdvanceSkipWhitespace();
        return isolate()->factory()->true_value();
      } else {
        return ReportUnexpectedCharacter();
      }
    case 'n':
      if (AdvanceGetChar() == 'u' && AdvanceGetChar() == 'l' &&
          AdvanceGetChar() == 'l') {
        AdvanceSkipWhitespace();
        return isolate()->factory()->null_value();
      } else {
        return ReportUnexpectedCharacter();
      }
    case '{':
      return ParseJsonObject();
    case '[':
      return ParseJsonArray();
    default:
      return ReportUnexpectedCharacter();
  }
}


// Parse a JSON object. Position must be right at '{'.
template <bool seq_ascii>
Handle<Object> JsonParser<seq_ascii>::ParseJsonObject() {
  Handle<JSFunction> object_constructor(
      isolate()->global_context()->object_function());
  Handle<JSObject> json_object =
      isolate()->factory()->NewJSObject(object_constructor);
  ASSERT_EQ(c0_, '{');

  AdvanceSkipWhitespace();
  if (c0_ != '}') {
    do {
      if (c0_ != '"') return ReportUnexpectedCharacter();
      Handle<String> key = ParseJsonSymbol();
      if (key.is_null() || c0_ != ':') return ReportUnexpectedCharacter();
      AdvanceSkipWhitespace();
      Handle<Object> value = ParseJsonValue();
      if (value.is_null()) return ReportUnexpectedCharacter();

      uint32_t index;
      if (key->AsArrayIndex(&index)) {
        JSObject::SetOwnElement(json_object, index, value, kNonStrictMode);
      } else if (key->Equals(isolate()->heap()->Proto_symbol())) {
        SetPrototype(json_object, value);
      } else {
        JSObject::SetLocalPropertyIgnoreAttributes(
            json_object, key, value, NONE);
      }
    } while (MatchSkipWhiteSpace(','));
    if (c0_ != '}') {
      return ReportUnexpectedCharacter();
    }
  }
  AdvanceSkipWhitespace();
  return json_object;
}

// Parse a JSON array. Position must be right at '['.
template <bool seq_ascii>
Handle<Object> JsonParser<seq_ascii>::ParseJsonArray() {
  ZoneScope zone_scope(isolate(), DELETE_ON_EXIT);
  ZoneList<Handle<Object> > elements(4);
  ASSERT_EQ(c0_, '[');

  AdvanceSkipWhitespace();
  if (c0_ != ']') {
    do {
      Handle<Object> element = ParseJsonValue();
      if (element.is_null()) return ReportUnexpectedCharacter();
      elements.Add(element);
    } while (MatchSkipWhiteSpace(','));
    if (c0_ != ']') {
      return ReportUnexpectedCharacter();
    }
  }
  AdvanceSkipWhitespace();
  // Allocate a fixed array with all the elements.
  Handle<FixedArray> fast_elements =
      isolate()->factory()->NewFixedArray(elements.length());
  for (int i = 0, n = elements.length(); i < n; i++) {
    fast_elements->set(i, *elements[i]);
  }
  return isolate()->factory()->NewJSArrayWithElements(fast_elements);
}


template <bool seq_ascii>
Handle<Object> JsonParser<seq_ascii>::ParseJsonNumber() {
  bool negative = false;
  int beg_pos = position_;
  if (c0_ == '-') {
    Advance();
    negative = true;
  }
  if (c0_ == '0') {
    Advance();
    // Prefix zero is only allowed if it's the only digit before
    // a decimal point or exponent.
    if ('0' <= c0_ && c0_ <= '9') return ReportUnexpectedCharacter();
  } else {
    int i = 0;
    int digits = 0;
    if (c0_ < '1' || c0_ > '9') return ReportUnexpectedCharacter();
    do {
      i = i * 10 + c0_ - '0';
      digits++;
      Advance();
    } while (c0_ >= '0' && c0_ <= '9');
    if (c0_ != '.' && c0_ != 'e' && c0_ != 'E' && digits < 10) {
      SkipWhitespace();
      return Handle<Smi>(Smi::FromInt((negative ? -i : i)), isolate());
    }
  }
  if (c0_ == '.') {
    Advance();
    if (c0_ < '0' || c0_ > '9') return ReportUnexpectedCharacter();
    do {
      Advance();
    } while (c0_ >= '0' && c0_ <= '9');
  }
  if (AsciiAlphaToLower(c0_) == 'e') {
    Advance();
    if (c0_ == '-' || c0_ == '+') Advance();
    if (c0_ < '0' || c0_ > '9') return ReportUnexpectedCharacter();
    do {
      Advance();
    } while (c0_ >= '0' && c0_ <= '9');
  }
  int length = position_ - beg_pos;
  double number;
  if (seq_ascii) {
    Vector<const char> chars(seq_source_->GetChars() +  beg_pos, length);
    number = StringToDouble(isolate()->unicode_cache(),
                             chars,
                             NO_FLAGS,  // Hex, octal or trailing junk.
                             OS::nan_value());
  } else {
    Vector<char> buffer = Vector<char>::New(length);
    String::WriteToFlat(*source_, buffer.start(), beg_pos, position_);
    Vector<const char> result =
        Vector<const char>(reinterpret_cast<const char*>(buffer.start()),
        length);
    number = StringToDouble(isolate()->unicode_cache(),
                             result,
                             NO_FLAGS,  // Hex, octal or trailing junk.
                             0.0);
    buffer.Dispose();
  }
  SkipWhitespace();
  return isolate()->factory()->NewNumber(number);
}


template <typename StringType>
inline void SeqStringSet(Handle<StringType> seq_str, int i, uc32 c);

template <>
inline void SeqStringSet(Handle<SeqTwoByteString> seq_str, int i, uc32 c) {
  seq_str->SeqTwoByteStringSet(i, c);
}

template <>
inline void SeqStringSet(Handle<SeqAsciiString> seq_str, int i, uc32 c) {
  seq_str->SeqAsciiStringSet(i, c);
}

template <typename StringType>
inline Handle<StringType> NewRawString(Factory* factory, int length);

template <>
inline Handle<SeqTwoByteString> NewRawString(Factory* factory, int length) {
  return factory->NewRawTwoByteString(length, NOT_TENURED);
}

template <>
inline Handle<SeqAsciiString> NewRawString(Factory* factory, int length) {
  return factory->NewRawAsciiString(length, NOT_TENURED);
}


// Scans the rest of a JSON string starting from position_ and writes
// prefix[start..end] along with the scanned characters into a
// sequential string of type StringType.
template <bool seq_ascii>
template <typename StringType, typename SinkChar>
Handle<String> JsonParser<seq_ascii>::SlowScanJsonString(
    Handle<String> prefix, int start, int end) {
  int count = end - start;
  int max_length = count + source_length_ - position_;
  int length = Min(max_length, Max(kInitialSpecialStringLength, 2 * count));
  Handle<StringType> seq_str = NewRawString<StringType>(isolate()->factory(),
                                                        length);
  // Copy prefix into seq_str.
  SinkChar* dest = seq_str->GetChars();
  String::WriteToFlat(*prefix, dest, start, end);

  while (c0_ != '"') {
    // Check for control character (0x00-0x1f) or unterminated string (<0).
    if (c0_ < 0x20) return Handle<String>::null();
    if (count >= length) {
      // We need to create a longer sequential string for the result.
      return SlowScanJsonString<StringType, SinkChar>(seq_str, 0, count);
    }
    if (c0_ != '\\') {
      // If the sink can contain UC16 characters, or source_ contains only
      // ASCII characters, there's no need to test whether we can store the
      // character. Otherwise check whether the UC16 source character can fit
      // in the ASCII sink.
      if (sizeof(SinkChar) == kUC16Size ||
          seq_ascii ||
          c0_ <= kMaxAsciiCharCode) {
        SeqStringSet(seq_str, count++, c0_);
        Advance();
      } else {
        // StringType is SeqAsciiString and we just read a non-ASCII char.
        return SlowScanJsonString<SeqTwoByteString, uc16>(seq_str, 0, count);
      }
    } else {
      Advance();  // Advance past the \.
      switch (c0_) {
        case '"':
        case '\\':
        case '/':
          SeqStringSet(seq_str, count++, c0_);
          break;
        case 'b':
          SeqStringSet(seq_str, count++, '\x08');
          break;
        case 'f':
          SeqStringSet(seq_str, count++, '\x0c');
          break;
        case 'n':
          SeqStringSet(seq_str, count++, '\x0a');
          break;
        case 'r':
          SeqStringSet(seq_str, count++, '\x0d');
          break;
        case 't':
          SeqStringSet(seq_str, count++, '\x09');
          break;
        case 'u': {
          uc32 value = 0;
          for (int i = 0; i < 4; i++) {
            Advance();
            int digit = HexValue(c0_);
            if (digit < 0) {
              return Handle<String>::null();
            }
            value = value * 16 + digit;
          }
          if (sizeof(SinkChar) == kUC16Size || value <= kMaxAsciiCharCode) {
            SeqStringSet(seq_str, count++, value);
            break;
          } else {
            // StringType is SeqAsciiString and we just read a non-ASCII char.
            position_ -= 6;  // Rewind position_ to \ in \uxxxx.
            Advance();
            return SlowScanJsonString<SeqTwoByteString, uc16>(seq_str,
                                                              0,
                                                              count);
          }
        }
        default:
          return Handle<String>::null();
      }
      Advance();
    }
  }
  // Shrink seq_string length to count.
  if (isolate()->heap()->InNewSpace(*seq_str)) {
    isolate()->heap()->new_space()->
        template ShrinkStringAtAllocationBoundary<StringType>(
            *seq_str, count);
  } else {
    int string_size = StringType::SizeFor(count);
    int allocated_string_size = StringType::SizeFor(length);
    int delta = allocated_string_size - string_size;
    Address start_filler_object = seq_str->address() + string_size;
    seq_str->set_length(count);
    isolate()->heap()->CreateFillerObjectAt(start_filler_object, delta);
  }
  ASSERT_EQ('"', c0_);
  // Advance past the last '"'.
  AdvanceSkipWhitespace();
  return seq_str;
}


template <bool seq_ascii>
template <bool is_symbol>
Handle<String> JsonParser<seq_ascii>::ScanJsonString() {
  ASSERT_EQ('"', c0_);
  Advance();
  if (c0_ == '"') {
    AdvanceSkipWhitespace();
    return Handle<String>(isolate()->heap()->empty_string());
  }
  int beg_pos = position_;
  // Fast case for ASCII only without escape characters.
  do {
    // Check for control character (0x00-0x1f) or unterminated string (<0).
    if (c0_ < 0x20) return Handle<String>::null();
    if (c0_ != '\\') {
      if (seq_ascii || c0_ <= kMaxAsciiCharCode) {
        Advance();
      } else {
        return SlowScanJsonString<SeqTwoByteString, uc16>(source_,
                                                          beg_pos,
                                                          position_);
      }
    } else {
      return SlowScanJsonString<SeqAsciiString, char>(source_,
                                                      beg_pos,
                                                      position_);
    }
  } while (c0_ != '"');
  int length = position_ - beg_pos;
  Handle<String> result;
  if (seq_ascii && is_symbol) {
    result = isolate()->factory()->LookupAsciiSymbol(seq_source_,
                                                     beg_pos,
                                                     length);
  } else {
    result = isolate()->factory()->NewRawAsciiString(length);
    char* dest = SeqAsciiString::cast(*result)->GetChars();
    String::WriteToFlat(*source_, dest, beg_pos, position_);
  }
  ASSERT_EQ('"', c0_);
  // Advance past the last '"'.
  AdvanceSkipWhitespace();
  return result;
}

} }  // namespace v8::internal

#endif  // V8_JSON_PARSER_H_