summaryrefslogtreecommitdiff
path: root/chromium/components/cbor/reader.cc
blob: 9c748d4486921c8481835940c77de7f1ee0f7c04 (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
// Copyright 2017 The Chromium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.

#include "components/cbor/reader.h"

#include <math.h>

#include <utility>

#include "base/check_op.h"
#include "base/notreached.h"
#include "base/numerics/checked_math.h"
#include "base/numerics/safe_conversions.h"
#include "base/stl_util.h"
#include "base/strings/string_util.h"
#include "components/cbor/constants.h"

namespace cbor {

namespace constants {
const char kUnsupportedMajorType[] = "Unsupported major type.";
}

namespace {

Value::Type GetMajorType(uint8_t initial_data_byte) {
  return static_cast<Value::Type>(
      (initial_data_byte & constants::kMajorTypeMask) >>
      constants::kMajorTypeBitShift);
}

uint8_t GetAdditionalInfo(uint8_t initial_data_byte) {
  return initial_data_byte & constants::kAdditionalInformationMask;
}

// Error messages that correspond to each of the error codes. There is 1
// exception: we declare |kUnsupportedMajorType| in constants.h in the
// `constants` namespace, because we use it in several files.
const char kNoError[] = "Successfully deserialized to a CBOR value.";
const char kUnknownAdditionalInfo[] =
    "Unknown additional info format in the first byte.";
const char kIncompleteCBORData[] =
    "Prematurely terminated CBOR data byte array.";
const char kIncorrectMapKeyType[] =
    "Specified map key type is not supported by the current implementation.";
const char kTooMuchNesting[] = "Too much nesting.";
const char kInvalidUTF8[] =
    "String encodings other than UTF-8 are not allowed.";
const char kExtraneousData[] = "Trailing data bytes are not allowed.";
const char kMapKeyOutOfOrder[] =
    "Map keys must be strictly monotonically increasing based on byte length "
    "and then by byte-wise lexical order.";
const char kNonMinimalCBOREncoding[] =
    "Unsigned integers must be encoded with minimum number of bytes.";
const char kUnsupportedSimpleValue[] =
    "Unsupported or unassigned simple value.";
const char kUnsupportedFloatingPointValue[] =
    "Floating point numbers are not supported.";
const char kOutOfRangeIntegerValue[] =
    "Integer values must be between INT64_MIN and INT64_MAX.";
const char kUnknownError[] = "An unknown error occured.";

}  // namespace

Reader::Config::Config() = default;
Reader::Config::~Config() = default;

Reader::Reader(base::span<const uint8_t> data)
    : rest_(data), error_code_(DecoderError::CBOR_NO_ERROR) {}
Reader::~Reader() {}

// static
base::Optional<Value> Reader::Read(base::span<uint8_t const> data,
                                   DecoderError* error_code_out,
                                   int max_nesting_level) {
  Config config;
  config.error_code_out = error_code_out;
  config.max_nesting_level = max_nesting_level;

  return Read(data, config);
}

// static
base::Optional<Value> Reader::Read(base::span<uint8_t const> data,
                                   size_t* num_bytes_consumed,
                                   DecoderError* error_code_out,
                                   int max_nesting_level) {
  DCHECK(num_bytes_consumed);

  Config config;
  config.num_bytes_consumed = num_bytes_consumed;
  config.error_code_out = error_code_out;
  config.max_nesting_level = max_nesting_level;

  return Read(data, config);
}

// static
base::Optional<Value> Reader::Read(base::span<uint8_t const> data,
                                   const Config& config) {
  Reader reader(data);
  base::Optional<Value> value =
      reader.DecodeCompleteDataItem(config, config.max_nesting_level);

  auto error = reader.GetErrorCode();
  const bool success = value.has_value();
  DCHECK_EQ(success, error == DecoderError::CBOR_NO_ERROR);

  if (config.num_bytes_consumed) {
    *config.num_bytes_consumed =
        success ? data.size() - reader.num_bytes_remaining() : 0;
  } else if (success && reader.num_bytes_remaining() > 0) {
    error = DecoderError::EXTRANEOUS_DATA;
    value.reset();
  }

  if (config.error_code_out) {
    *config.error_code_out = error;
  }

  return value;
}

base::Optional<Value> Reader::DecodeCompleteDataItem(const Config& config,
                                                     int max_nesting_level) {
  if (max_nesting_level < 0 || max_nesting_level > kCBORMaxDepth) {
    error_code_ = DecoderError::TOO_MUCH_NESTING;
    return base::nullopt;
  }

  base::Optional<DataItemHeader> header = DecodeDataItemHeader();
  if (!header.has_value()) {
    return base::nullopt;
  }

  switch (header->type) {
    case Value::Type::UNSIGNED:
      return DecodeValueToUnsigned(header->value);
    case Value::Type::NEGATIVE:
      return DecodeValueToNegative(header->value);
    case Value::Type::BYTE_STRING:
      return ReadByteStringContent(*header);
    case Value::Type::STRING:
      return ReadStringContent(*header, config);
    case Value::Type::ARRAY:
      return ReadArrayContent(*header, config, max_nesting_level);
    case Value::Type::MAP:
      return ReadMapContent(*header, config, max_nesting_level);
    case Value::Type::SIMPLE_VALUE:
      return DecodeToSimpleValue(*header);
    case Value::Type::TAG:  // We explicitly don't support TAG.
    case Value::Type::NONE:
    case Value::Type::INVALID_UTF8:
      break;
  }

  error_code_ = DecoderError::UNSUPPORTED_MAJOR_TYPE;
  return base::nullopt;
}

base::Optional<Reader::DataItemHeader> Reader::DecodeDataItemHeader() {
  const base::Optional<uint8_t> initial_byte = ReadByte();
  if (!initial_byte) {
    return base::nullopt;
  }

  const auto major_type = GetMajorType(initial_byte.value());
  const uint8_t additional_info = GetAdditionalInfo(initial_byte.value());

  base::Optional<uint64_t> value = ReadVariadicLengthInteger(additional_info);
  return value ? base::make_optional(
                     DataItemHeader{major_type, additional_info, value.value()})
               : base::nullopt;
}

base::Optional<uint64_t> Reader::ReadVariadicLengthInteger(
    uint8_t additional_info) {
  uint8_t additional_bytes = 0;
  if (additional_info < 24) {
    return base::make_optional(additional_info);
  } else if (additional_info == 24) {
    additional_bytes = 1;
  } else if (additional_info == 25) {
    additional_bytes = 2;
  } else if (additional_info == 26) {
    additional_bytes = 4;
  } else if (additional_info == 27) {
    additional_bytes = 8;
  } else {
    error_code_ = DecoderError::UNKNOWN_ADDITIONAL_INFO;
    return base::nullopt;
  }

  const base::Optional<base::span<const uint8_t>> bytes =
      ReadBytes(additional_bytes);
  if (!bytes) {
    return base::nullopt;
  }

  uint64_t int_data = 0;
  for (const uint8_t b : bytes.value()) {
    int_data <<= 8;
    int_data |= b;
  }

  return IsEncodingMinimal(additional_bytes, int_data)
             ? base::make_optional(int_data)
             : base::nullopt;
}

base::Optional<Value> Reader::DecodeValueToNegative(uint64_t value) {
  auto negative_value = -base::CheckedNumeric<int64_t>(value) - 1;
  if (!negative_value.IsValid()) {
    error_code_ = DecoderError::OUT_OF_RANGE_INTEGER_VALUE;
    return base::nullopt;
  }
  return Value(negative_value.ValueOrDie());
}

base::Optional<Value> Reader::DecodeValueToUnsigned(uint64_t value) {
  auto unsigned_value = base::CheckedNumeric<int64_t>(value);
  if (!unsigned_value.IsValid()) {
    error_code_ = DecoderError::OUT_OF_RANGE_INTEGER_VALUE;
    return base::nullopt;
  }
  return Value(unsigned_value.ValueOrDie());
}

base::Optional<Value> Reader::DecodeToSimpleValue(
    const DataItemHeader& header) {
  // ReadVariadicLengthInteger provides this bound.
  CHECK_LE(header.additional_info, 27);
  // Floating point numbers are not supported.
  if (header.additional_info > 24) {
    error_code_ = DecoderError::UNSUPPORTED_FLOATING_POINT_VALUE;
    return base::nullopt;
  }

  // Since |header.additional_info| <= 24, ReadVariadicLengthInteger also
  // provides this bound for |header.value|.
  CHECK_LE(header.value, 255u);
  // |SimpleValue| is an enum class and so the underlying type is specified to
  // be |int|. So this cast is safe.
  Value::SimpleValue possibly_unsupported_simple_value =
      static_cast<Value::SimpleValue>(static_cast<int>(header.value));
  switch (possibly_unsupported_simple_value) {
    case Value::SimpleValue::FALSE_VALUE:
    case Value::SimpleValue::TRUE_VALUE:
    case Value::SimpleValue::NULL_VALUE:
    case Value::SimpleValue::UNDEFINED:
      return Value(possibly_unsupported_simple_value);
  }

  error_code_ = DecoderError::UNSUPPORTED_SIMPLE_VALUE;
  return base::nullopt;
}

base::Optional<Value> Reader::ReadStringContent(
    const Reader::DataItemHeader& header,
    const Config& config) {
  uint64_t num_bytes = header.value;
  const base::Optional<base::span<const uint8_t>> bytes = ReadBytes(num_bytes);
  if (!bytes) {
    return base::nullopt;
  }

  std::string cbor_string(bytes->begin(), bytes->end());
  if (base::IsStringUTF8(cbor_string)) {
    return Value(std::move(cbor_string));
  }

  if (config.allow_invalid_utf8) {
    return Value(*bytes, Value::Type::INVALID_UTF8);
  }

  error_code_ = DecoderError::INVALID_UTF8;
  return base::nullopt;
}

base::Optional<Value> Reader::ReadByteStringContent(
    const Reader::DataItemHeader& header) {
  uint64_t num_bytes = header.value;
  const base::Optional<base::span<const uint8_t>> bytes = ReadBytes(num_bytes);
  if (!bytes) {
    return base::nullopt;
  }

  std::vector<uint8_t> cbor_byte_string(bytes->begin(), bytes->end());
  return Value(std::move(cbor_byte_string));
}

base::Optional<Value> Reader::ReadArrayContent(
    const Reader::DataItemHeader& header,
    const Config& config,
    int max_nesting_level) {
  const uint64_t length = header.value;

  Value::ArrayValue cbor_array;
  for (uint64_t i = 0; i < length; ++i) {
    base::Optional<Value> cbor_element =
        DecodeCompleteDataItem(config, max_nesting_level - 1);
    if (!cbor_element.has_value()) {
      return base::nullopt;
    }
    cbor_array.push_back(std::move(cbor_element.value()));
  }
  return Value(std::move(cbor_array));
}

base::Optional<Value> Reader::ReadMapContent(
    const Reader::DataItemHeader& header,
    const Config& config,
    int max_nesting_level) {
  const uint64_t length = header.value;

  Value::MapValue cbor_map;
  for (uint64_t i = 0; i < length; ++i) {
    base::Optional<Value> key =
        DecodeCompleteDataItem(config, max_nesting_level - 1);
    base::Optional<Value> value =
        DecodeCompleteDataItem(config, max_nesting_level - 1);
    if (!key.has_value() || !value.has_value()) {
      return base::nullopt;
    }

    switch (key.value().type()) {
      case Value::Type::UNSIGNED:
      case Value::Type::NEGATIVE:
      case Value::Type::STRING:
      case Value::Type::BYTE_STRING:
        break;
      case Value::Type::INVALID_UTF8:
        error_code_ = DecoderError::INVALID_UTF8;
        return base::nullopt;
      default:
        error_code_ = DecoderError::INCORRECT_MAP_KEY_TYPE;
        return base::nullopt;
    }
    if (!IsKeyInOrder(key.value(), &cbor_map)) {
      return base::nullopt;
    }

    cbor_map.insert_or_assign(std::move(key.value()), std::move(value.value()));
  }
  return Value(std::move(cbor_map));
}

base::Optional<uint8_t> Reader::ReadByte() {
  const base::Optional<base::span<const uint8_t>> bytes = ReadBytes(1);
  return bytes ? base::make_optional(bytes.value()[0]) : base::nullopt;
}

base::Optional<base::span<const uint8_t>> Reader::ReadBytes(
    uint64_t num_bytes) {
  if (base::strict_cast<uint64_t>(rest_.size()) < num_bytes) {
    error_code_ = DecoderError::INCOMPLETE_CBOR_DATA;
    return base::nullopt;
  }
  const base::span<const uint8_t> ret = rest_.first(num_bytes);
  rest_ = rest_.subspan(num_bytes);
  return ret;
}

bool Reader::IsEncodingMinimal(uint8_t additional_bytes, uint64_t uint_data) {
  if ((additional_bytes == 1 && uint_data < 24) ||
      uint_data <= (1ULL << 8 * (additional_bytes >> 1)) - 1) {
    error_code_ = DecoderError::NON_MINIMAL_CBOR_ENCODING;
    return false;
  }
  return true;
}

bool Reader::IsKeyInOrder(const Value& new_key, Value::MapValue* map) {
  if (map->empty()) {
    return true;
  }

  const auto& max_current_key = map->rbegin()->first;
  const auto less = map->key_comp();
  if (!less(max_current_key, new_key)) {
    error_code_ = DecoderError::OUT_OF_ORDER_KEY;
    return false;
  }
  return true;
}

// static
const char* Reader::ErrorCodeToString(DecoderError error) {
  switch (error) {
    case DecoderError::CBOR_NO_ERROR:
      return kNoError;
    case DecoderError::UNSUPPORTED_MAJOR_TYPE:
      return constants::kUnsupportedMajorType;
    case DecoderError::UNKNOWN_ADDITIONAL_INFO:
      return kUnknownAdditionalInfo;
    case DecoderError::INCOMPLETE_CBOR_DATA:
      return kIncompleteCBORData;
    case DecoderError::INCORRECT_MAP_KEY_TYPE:
      return kIncorrectMapKeyType;
    case DecoderError::TOO_MUCH_NESTING:
      return kTooMuchNesting;
    case DecoderError::INVALID_UTF8:
      return kInvalidUTF8;
    case DecoderError::EXTRANEOUS_DATA:
      return kExtraneousData;
    case DecoderError::OUT_OF_ORDER_KEY:
      return kMapKeyOutOfOrder;
    case DecoderError::NON_MINIMAL_CBOR_ENCODING:
      return kNonMinimalCBOREncoding;
    case DecoderError::UNSUPPORTED_SIMPLE_VALUE:
      return kUnsupportedSimpleValue;
    case DecoderError::UNSUPPORTED_FLOATING_POINT_VALUE:
      return kUnsupportedFloatingPointValue;
    case DecoderError::OUT_OF_RANGE_INTEGER_VALUE:
      return kOutOfRangeIntegerValue;
    case DecoderError::UNKNOWN_ERROR:
      return kUnknownError;
    default:
      NOTREACHED();
      return "Unknown error code.";
  }
}

}  // namespace cbor