Move AudioDecoder and related stuff to the api/ directory

BUG=webrtc:5805, webrtc:6725

Review-Url: https://codereview.webrtc.org/2668523004
Cr-Commit-Position: refs/heads/master@{#16534}
This commit is contained in:
kwiberg
2017-02-10 08:15:44 -08:00
committed by Commit bot
parent 84a3759825
commit 087bd34d23
78 changed files with 535 additions and 380 deletions

View File

@ -0,0 +1,39 @@
# Copyright (c) 2017 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.
import("../../webrtc.gni")
if (is_android) {
import("//build/config/android/config.gni")
import("//build/config/android/rules.gni")
}
rtc_source_set("audio_codecs_api") {
sources = [
"audio_decoder.cc",
"audio_decoder.h",
"audio_decoder_factory.h",
"audio_format.cc",
"audio_format.h",
]
deps = [
"../..:webrtc_common",
"../../base:rtc_base_approved",
]
}
rtc_static_library("builtin_audio_decoder_factory") {
sources = [
"builtin_audio_decoder_factory.cc",
"builtin_audio_decoder_factory.h",
]
deps = [
":audio_codecs_api",
"../../base:rtc_base_approved",
"../../modules/audio_coding:builtin_audio_decoder_factory_internal",
]
}

View File

@ -0,0 +1,169 @@
/*
* 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 "webrtc/api/audio_codecs/audio_decoder.h"
#include <assert.h>
#include <memory>
#include <utility>
#include "webrtc/base/array_view.h"
#include "webrtc/base/checks.h"
#include "webrtc/base/sanitizer.h"
#include "webrtc/base/trace_event.h"
namespace webrtc {
namespace {
class OldStyleEncodedFrame final : public AudioDecoder::EncodedAudioFrame {
public:
OldStyleEncodedFrame(AudioDecoder* decoder, rtc::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);
}
rtc::Optional<DecodeResult> Decode(
rtc::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 ? rtc::Optional<DecodeResult>()
: rtc::Optional<DecodeResult>(
{static_cast<size_t>(ret), speech_type});
}
private:
AudioDecoder* const decoder_;
const rtc::Buffer payload_;
};
} // namespace
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(
rtc::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");
rtc::MsanCheckInitialized(rtc::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");
rtc::MsanCheckInitialized(rtc::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;
}
int AudioDecoder::IncomingPacket(const uint8_t* payload,
size_t payload_len,
uint16_t rtp_sequence_number,
uint32_t rtp_timestamp,
uint32_t arrival_timestamp) {
return 0;
}
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:
assert(false);
return kSpeech;
}
}
} // namespace webrtc

View File

@ -0,0 +1,177 @@
/*
* 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.
*/
#ifndef WEBRTC_API_AUDIO_CODECS_AUDIO_DECODER_H_
#define WEBRTC_API_AUDIO_CODECS_AUDIO_DECODER_H_
#include <memory>
#include <vector>
#include "webrtc/base/array_view.h"
#include "webrtc/base/buffer.h"
#include "webrtc/base/constructormagic.h"
#include "webrtc/base/optional.h"
#include "webrtc/typedefs.h"
namespace webrtc {
class AudioDecoder {
public:
enum SpeechType {
kSpeech = 1,
kComfortNoise = 2,
};
// Used by PacketDuration below. Save the value -1 for errors.
enum { kNotImplemented = -2 };
AudioDecoder() = default;
virtual ~AudioDecoder() = default;
class EncodedAudioFrame {
public:
struct DecodeResult {
size_t num_decoded_samples;
SpeechType speech_type;
};
virtual ~EncodedAudioFrame() = default;
// Returns the duration in samples-per-channel of this audio frame.
// If no duration can be ascertained, returns zero.
virtual size_t Duration() const = 0;
// Decodes this frame of audio and writes the result in |decoded|.
// |decoded| must be large enough to store as many samples as indicated by a
// call to Duration() . On success, returns an rtc::Optional containing the
// total number of samples across all channels, as well as whether the
// decoder produced comfort noise or speech. On failure, returns an empty
// rtc::Optional. Decode may be called at most once per frame object.
virtual rtc::Optional<DecodeResult> Decode(
rtc::ArrayView<int16_t> decoded) const = 0;
};
struct ParseResult {
ParseResult();
ParseResult(uint32_t timestamp,
int priority,
std::unique_ptr<EncodedAudioFrame> frame);
ParseResult(ParseResult&& b);
~ParseResult();
ParseResult& operator=(ParseResult&& b);
// The timestamp of the frame is in samples per channel.
uint32_t timestamp;
// The relative priority of the frame compared to other frames of the same
// payload and the same timeframe. A higher value means a lower priority.
// The highest priority is zero - negative values are not allowed.
int priority;
std::unique_ptr<EncodedAudioFrame> frame;
};
// Let the decoder parse this payload and prepare zero or more decodable
// frames. Each frame must be between 10 ms and 120 ms long. The caller must
// ensure that the AudioDecoder object outlives any frame objects returned by
// this call. The decoder is free to swap or move the data from the |payload|
// buffer. |timestamp| is the input timestamp, in samples, corresponding to
// the start of the payload.
virtual std::vector<ParseResult> ParsePayload(rtc::Buffer&& payload,
uint32_t timestamp);
// Decodes |encode_len| bytes from |encoded| and writes the result in
// |decoded|. The maximum bytes allowed to be written into |decoded| is
// |max_decoded_bytes|. Returns the total number of samples across all
// channels. If the decoder produced comfort noise, |speech_type|
// is set to kComfortNoise, otherwise it is kSpeech. The desired output
// sample rate is provided in |sample_rate_hz|, which must be valid for the
// codec at hand.
int Decode(const uint8_t* encoded,
size_t encoded_len,
int sample_rate_hz,
size_t max_decoded_bytes,
int16_t* decoded,
SpeechType* speech_type);
// Same as Decode(), but interfaces to the decoders redundant decode function.
// The default implementation simply calls the regular Decode() method.
int DecodeRedundant(const uint8_t* encoded,
size_t encoded_len,
int sample_rate_hz,
size_t max_decoded_bytes,
int16_t* decoded,
SpeechType* speech_type);
// Indicates if the decoder implements the DecodePlc method.
virtual bool HasDecodePlc() const;
// Calls the packet-loss concealment of the decoder to update the state after
// one or several lost packets. The caller has to make sure that the
// memory allocated in |decoded| should accommodate |num_frames| frames.
virtual size_t DecodePlc(size_t num_frames, int16_t* decoded);
// Resets the decoder state (empty buffers etc.).
virtual void Reset() = 0;
// Notifies the decoder of an incoming packet to NetEQ.
virtual int IncomingPacket(const uint8_t* payload,
size_t payload_len,
uint16_t rtp_sequence_number,
uint32_t rtp_timestamp,
uint32_t arrival_timestamp);
// Returns the last error code from the decoder.
virtual int ErrorCode();
// Returns the duration in samples-per-channel of the payload in |encoded|
// which is |encoded_len| bytes long. Returns kNotImplemented if no duration
// estimate is available, or -1 in case of an error.
virtual int PacketDuration(const uint8_t* encoded, size_t encoded_len) const;
// Returns the duration in samples-per-channel of the redandant payload in
// |encoded| which is |encoded_len| bytes long. Returns kNotImplemented if no
// duration estimate is available, or -1 in case of an error.
virtual int PacketDurationRedundant(const uint8_t* encoded,
size_t encoded_len) const;
// Detects whether a packet has forward error correction. The packet is
// comprised of the samples in |encoded| which is |encoded_len| bytes long.
// Returns true if the packet has FEC and false otherwise.
virtual bool PacketHasFec(const uint8_t* encoded, size_t encoded_len) const;
// Returns the actual sample rate of the decoder's output. This value may not
// change during the lifetime of the decoder.
virtual int SampleRateHz() const = 0;
// The number of channels in the decoder's output. This value may not change
// during the lifetime of the decoder.
virtual size_t Channels() const = 0;
protected:
static SpeechType ConvertSpeechType(int16_t type);
virtual int DecodeInternal(const uint8_t* encoded,
size_t encoded_len,
int sample_rate_hz,
int16_t* decoded,
SpeechType* speech_type) = 0;
virtual int DecodeRedundantInternal(const uint8_t* encoded,
size_t encoded_len,
int sample_rate_hz,
int16_t* decoded,
SpeechType* speech_type);
private:
RTC_DISALLOW_COPY_AND_ASSIGN(AudioDecoder);
};
} // namespace webrtc
#endif // WEBRTC_API_AUDIO_CODECS_AUDIO_DECODER_H_

View File

@ -0,0 +1,37 @@
/*
* Copyright (c) 2016 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.
*/
#ifndef WEBRTC_API_AUDIO_CODECS_AUDIO_DECODER_FACTORY_H_
#define WEBRTC_API_AUDIO_CODECS_AUDIO_DECODER_FACTORY_H_
#include <memory>
#include <vector>
#include "webrtc/api/audio_codecs/audio_decoder.h"
#include "webrtc/api/audio_codecs/audio_format.h"
#include "webrtc/base/refcount.h"
namespace webrtc {
// A factory that creates AudioDecoders.
// NOTE: This class is still under development and may change without notice.
class AudioDecoderFactory : public rtc::RefCountInterface {
public:
virtual std::vector<AudioCodecSpec> GetSupportedDecoders() = 0;
virtual bool IsSupportedDecoder(const SdpAudioFormat& format) = 0;
virtual std::unique_ptr<AudioDecoder> MakeAudioDecoder(
const SdpAudioFormat& format) = 0;
};
} // namespace webrtc
#endif // WEBRTC_API_AUDIO_CODECS_AUDIO_DECODER_FACTORY_H_

View File

@ -0,0 +1,85 @@
/*
* Copyright (c) 2016 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 "webrtc/api/audio_codecs/audio_format.h"
#include "webrtc/common_types.h"
namespace webrtc {
SdpAudioFormat::SdpAudioFormat(const SdpAudioFormat&) = default;
SdpAudioFormat::SdpAudioFormat(SdpAudioFormat&&) = default;
SdpAudioFormat::SdpAudioFormat(const char* name,
int clockrate_hz,
int num_channels)
: name(name), clockrate_hz(clockrate_hz), num_channels(num_channels) {}
SdpAudioFormat::SdpAudioFormat(const std::string& name,
int clockrate_hz,
int num_channels)
: name(name), clockrate_hz(clockrate_hz), num_channels(num_channels) {}
SdpAudioFormat::SdpAudioFormat(const char* name,
int clockrate_hz,
int num_channels,
const Parameters& param)
: name(name),
clockrate_hz(clockrate_hz),
num_channels(num_channels),
parameters(param) {}
SdpAudioFormat::SdpAudioFormat(const std::string& name,
int clockrate_hz,
int num_channels,
const Parameters& param)
: name(name),
clockrate_hz(clockrate_hz),
num_channels(num_channels),
parameters(param) {}
SdpAudioFormat::~SdpAudioFormat() = default;
SdpAudioFormat& SdpAudioFormat::operator=(const SdpAudioFormat&) = default;
SdpAudioFormat& SdpAudioFormat::operator=(SdpAudioFormat&&) = default;
bool operator==(const SdpAudioFormat& a, const SdpAudioFormat& b) {
return STR_CASE_CMP(a.name.c_str(), b.name.c_str()) == 0 &&
a.clockrate_hz == b.clockrate_hz && a.num_channels == b.num_channels &&
a.parameters == b.parameters;
}
void swap(SdpAudioFormat& a, SdpAudioFormat& b) {
using std::swap;
swap(a.name, b.name);
swap(a.clockrate_hz, b.clockrate_hz);
swap(a.num_channels, b.num_channels);
swap(a.parameters, b.parameters);
}
std::ostream& operator<<(std::ostream& os, const SdpAudioFormat& saf) {
os << "{name: " << saf.name;
os << ", clockrate_hz: " << saf.clockrate_hz;
os << ", num_channels: " << saf.num_channels;
os << ", parameters: {";
const char* sep = "";
for (const auto& kv : saf.parameters) {
os << sep << kv.first << ": " << kv.second;
sep = ", ";
}
os << "}}";
return os;
}
AudioCodecSpec::AudioCodecSpec(const SdpAudioFormat& format) : format(format) {}
AudioCodecSpec::AudioCodecSpec(SdpAudioFormat&& format)
: format(std::move(format)) {}
} // namespace webrtc

View File

@ -0,0 +1,81 @@
/*
* Copyright (c) 2016 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.
*/
#ifndef WEBRTC_API_AUDIO_CODECS_AUDIO_FORMAT_H_
#define WEBRTC_API_AUDIO_CODECS_AUDIO_FORMAT_H_
#include <map>
#include <ostream>
#include <string>
#include <utility>
namespace webrtc {
// SDP specification for a single audio codec.
// NOTE: This class is still under development and may change without notice.
struct SdpAudioFormat {
using Parameters = std::map<std::string, std::string>;
SdpAudioFormat(const SdpAudioFormat&);
SdpAudioFormat(SdpAudioFormat&&);
SdpAudioFormat(const char* name, int clockrate_hz, int num_channels);
SdpAudioFormat(const std::string& name, int clockrate_hz, int num_channels);
SdpAudioFormat(const char* name,
int clockrate_hz,
int num_channels,
const Parameters& param);
SdpAudioFormat(const std::string& name,
int clockrate_hz,
int num_channels,
const Parameters& param);
~SdpAudioFormat();
SdpAudioFormat& operator=(const SdpAudioFormat&);
SdpAudioFormat& operator=(SdpAudioFormat&&);
friend bool operator==(const SdpAudioFormat& a, const SdpAudioFormat& b);
friend bool operator!=(const SdpAudioFormat& a, const SdpAudioFormat& b) {
return !(a == b);
}
std::string name;
int clockrate_hz;
int num_channels;
Parameters parameters;
};
void swap(SdpAudioFormat& a, SdpAudioFormat& b);
std::ostream& operator<<(std::ostream& os, const SdpAudioFormat& saf);
// To avoid API breakage, and make the code clearer, AudioCodecSpec should not
// be directly initializable with any flags indicating optional support. If it
// were, these initializers would break any time a new flag was added. It's also
// more difficult to understand:
// AudioCodecSpec spec{{"format", 8000, 1}, true, false, false, true, true};
// than
// AudioCodecSpec spec({"format", 8000, 1});
// spec.allow_comfort_noise = true;
// spec.future_flag_b = true;
// spec.future_flag_c = true;
struct AudioCodecSpec {
explicit AudioCodecSpec(const SdpAudioFormat& format);
explicit AudioCodecSpec(SdpAudioFormat&& format);
~AudioCodecSpec() = default;
SdpAudioFormat format;
bool allow_comfort_noise = true; // This codec can be used with an external
// comfort noise generator.
bool supports_network_adaption = false; // This codec can adapt to varying
// network conditions.
};
} // namespace webrtc
#endif // WEBRTC_API_AUDIO_CODECS_AUDIO_FORMAT_H_

View File

@ -0,0 +1,21 @@
/*
* Copyright (c) 2017 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 "webrtc/api/audio_codecs/builtin_audio_decoder_factory.h"
#include "webrtc/modules/audio_coding/codecs/builtin_audio_decoder_factory_internal.h"
namespace webrtc {
rtc::scoped_refptr<AudioDecoderFactory> CreateBuiltinAudioDecoderFactory() {
return CreateBuiltinAudioDecoderFactoryInternal();
}
} // namespace webrtc

View File

@ -0,0 +1,25 @@
/*
* Copyright (c) 2016 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.
*/
#ifndef WEBRTC_API_AUDIO_CODECS_BUILTIN_AUDIO_DECODER_FACTORY_H_
#define WEBRTC_API_AUDIO_CODECS_BUILTIN_AUDIO_DECODER_FACTORY_H_
#include "webrtc/api/audio_codecs/audio_decoder_factory.h"
#include "webrtc/base/scoped_ref_ptr.h"
namespace webrtc {
// Creates a new factory that can create the built-in types of audio decoders.
// NOTE: This function is still under development and may change without notice.
rtc::scoped_refptr<AudioDecoderFactory> CreateBuiltinAudioDecoderFactory();
} // namespace webrtc
#endif // WEBRTC_API_AUDIO_CODECS_BUILTIN_AUDIO_DECODER_FACTORY_H_