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
|
/*
* Copyright (c) 2012 The WebRTC project authors. All Rights Reserved.
*
* Use of this source code is governed by a BSD-style license
* that can be found in the LICENSE file in the root of the source
* tree. An additional intellectual property rights grant can be found
* in the file PATENTS. All contributing project authors may
* be found in the AUTHORS file in the root of the source tree.
*/
#include "api/audio_codecs/audio_decoder.h"
#include <cstddef>
#include <cstdint>
#include <memory>
#include <optional>
#include <utility>
#include <vector>
#include "api/array_view.h"
#include "rtc_base/buffer.h"
#include "rtc_base/checks.h"
#include "rtc_base/sanitizer.h"
#include "rtc_base/trace_event.h"
namespace webrtc {
namespace {
// TODO(peah): Rationale
static_assert(AudioDecoder::kMaxNumberOfChannels <= 255, "");
class OldStyleEncodedFrame final : public AudioDecoder::EncodedAudioFrame {
public:
OldStyleEncodedFrame(AudioDecoder* decoder, Buffer&& payload)
: decoder_(decoder), payload_(std::move(payload)) {}
size_t Duration() const override {
const int ret = decoder_->PacketDuration(payload_.data(), payload_.size());
return ret < 0 ? 0 : static_cast<size_t>(ret);
}
std::optional<DecodeResult> Decode(
ArrayView<int16_t> decoded) const override {
auto speech_type = AudioDecoder::kSpeech;
const int ret = decoder_->Decode(
payload_.data(), payload_.size(), decoder_->SampleRateHz(),
decoded.size() * sizeof(int16_t), decoded.data(), &speech_type);
return ret < 0 ? std::nullopt
: std::optional<DecodeResult>(
{static_cast<size_t>(ret), speech_type});
}
private:
AudioDecoder* const decoder_;
const Buffer payload_;
};
} // namespace
bool AudioDecoder::EncodedAudioFrame::IsDtxPacket() const {
return false;
}
AudioDecoder::ParseResult::ParseResult() = default;
AudioDecoder::ParseResult::ParseResult(ParseResult&& b) = default;
AudioDecoder::ParseResult::ParseResult(uint32_t timestamp,
int priority,
std::unique_ptr<EncodedAudioFrame> frame)
: timestamp(timestamp), priority(priority), frame(std::move(frame)) {
RTC_DCHECK_GE(priority, 0);
}
AudioDecoder::ParseResult::~ParseResult() = default;
AudioDecoder::ParseResult& AudioDecoder::ParseResult::operator=(
ParseResult&& b) = default;
std::vector<AudioDecoder::ParseResult> AudioDecoder::ParsePayload(
Buffer&& payload,
uint32_t timestamp) {
std::vector<ParseResult> results;
std::unique_ptr<EncodedAudioFrame> frame(
new OldStyleEncodedFrame(this, std::move(payload)));
results.emplace_back(timestamp, 0, std::move(frame));
return results;
}
int AudioDecoder::Decode(const uint8_t* encoded,
size_t encoded_len,
int sample_rate_hz,
size_t max_decoded_bytes,
int16_t* decoded,
SpeechType* speech_type) {
TRACE_EVENT0("webrtc", "AudioDecoder::Decode");
MsanCheckInitialized(MakeArrayView(encoded, encoded_len));
int duration = PacketDuration(encoded, encoded_len);
if (duration >= 0 &&
duration * Channels() * sizeof(int16_t) > max_decoded_bytes) {
return -1;
}
return DecodeInternal(encoded, encoded_len, sample_rate_hz, decoded,
speech_type);
}
int AudioDecoder::DecodeRedundant(const uint8_t* encoded,
size_t encoded_len,
int sample_rate_hz,
size_t max_decoded_bytes,
int16_t* decoded,
SpeechType* speech_type) {
TRACE_EVENT0("webrtc", "AudioDecoder::DecodeRedundant");
MsanCheckInitialized(MakeArrayView(encoded, encoded_len));
int duration = PacketDurationRedundant(encoded, encoded_len);
if (duration >= 0 &&
duration * Channels() * sizeof(int16_t) > max_decoded_bytes) {
return -1;
}
return DecodeRedundantInternal(encoded, encoded_len, sample_rate_hz, decoded,
speech_type);
}
int AudioDecoder::DecodeRedundantInternal(const uint8_t* encoded,
size_t encoded_len,
int sample_rate_hz,
int16_t* decoded,
SpeechType* speech_type) {
return DecodeInternal(encoded, encoded_len, sample_rate_hz, decoded,
speech_type);
}
bool AudioDecoder::HasDecodePlc() const {
return false;
}
size_t AudioDecoder::DecodePlc(size_t /* num_frames */,
int16_t* /* decoded */) {
return 0;
}
// TODO(bugs.webrtc.org/9676): Remove default implementation.
void AudioDecoder::GeneratePlc(size_t /*requested_samples_per_channel*/,
BufferT<int16_t>* /*concealment_audio*/) {}
int AudioDecoder::ErrorCode() {
return 0;
}
int AudioDecoder::PacketDuration(const uint8_t* /* encoded */,
size_t /* encoded_len */) const {
return kNotImplemented;
}
int AudioDecoder::PacketDurationRedundant(const uint8_t* /* encoded */,
size_t /* encoded_len */) const {
return kNotImplemented;
}
bool AudioDecoder::PacketHasFec(const uint8_t* /* encoded */,
size_t /* encoded_len */) const {
return false;
}
AudioDecoder::SpeechType AudioDecoder::ConvertSpeechType(int16_t type) {
switch (type) {
case 0: // TODO(hlundin): Both iSAC and Opus return 0 for speech.
case 1:
return kSpeech;
case 2:
return kComfortNoise;
default:
RTC_DCHECK_NOTREACHED();
return kSpeech;
}
}
constexpr int AudioDecoder::kMaxNumberOfChannels;
} // namespace webrtc
|
