/usr/include/webrtc_audio_processing/webrtc/modules/interface/module_common_types.h is in libwebrtc-audio-processing-dev 0.3-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 | /*
* 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 MODULE_COMMON_TYPES_H
#define MODULE_COMMON_TYPES_H
#include <assert.h>
#include <string.h> // memcpy
#include <algorithm>
#include <limits>
#include "webrtc/base/constructormagic.h"
#include "webrtc/common_types.h"
#ifndef WEBRTC_AUDIO_PROCESSING_ONLY_BUILD
#include "webrtc/common_video/rotation.h"
#endif
#include "webrtc/typedefs.h"
namespace webrtc {
struct RTPAudioHeader {
uint8_t numEnergy; // number of valid entries in arrOfEnergy
uint8_t arrOfEnergy[kRtpCsrcSize]; // one energy byte (0-9) per channel
bool isCNG; // is this CNG
uint8_t channel; // number of channels 2 = stereo
};
const int16_t kNoPictureId = -1;
const int16_t kMaxOneBytePictureId = 0x7F; // 7 bits
const int16_t kMaxTwoBytePictureId = 0x7FFF; // 15 bits
const int16_t kNoTl0PicIdx = -1;
const uint8_t kNoTemporalIdx = 0xFF;
const uint8_t kNoSpatialIdx = 0xFF;
const uint8_t kNoGofIdx = 0xFF;
const size_t kMaxVp9RefPics = 3;
const size_t kMaxVp9FramesInGof = 0xFF; // 8 bits
const size_t kMaxVp9NumberOfSpatialLayers = 8;
const int kNoKeyIdx = -1;
struct RTPVideoHeaderVP8 {
void InitRTPVideoHeaderVP8() {
nonReference = false;
pictureId = kNoPictureId;
tl0PicIdx = kNoTl0PicIdx;
temporalIdx = kNoTemporalIdx;
layerSync = false;
keyIdx = kNoKeyIdx;
partitionId = 0;
beginningOfPartition = false;
}
bool nonReference; // Frame is discardable.
int16_t pictureId; // Picture ID index, 15 bits;
// kNoPictureId if PictureID does not exist.
int16_t tl0PicIdx; // TL0PIC_IDX, 8 bits;
// kNoTl0PicIdx means no value provided.
uint8_t temporalIdx; // Temporal layer index, or kNoTemporalIdx.
bool layerSync; // This frame is a layer sync frame.
// Disabled if temporalIdx == kNoTemporalIdx.
int keyIdx; // 5 bits; kNoKeyIdx means not used.
int partitionId; // VP8 partition ID
bool beginningOfPartition; // True if this packet is the first
// in a VP8 partition. Otherwise false
};
enum TemporalStructureMode {
kTemporalStructureMode1, // 1 temporal layer structure - i.e., IPPP...
kTemporalStructureMode2, // 2 temporal layers 0-1-0-1...
kTemporalStructureMode3 // 3 temporal layers 0-2-1-2-0-2-1-2...
};
struct GofInfoVP9 {
void SetGofInfoVP9(TemporalStructureMode tm) {
switch (tm) {
case kTemporalStructureMode1:
num_frames_in_gof = 1;
temporal_idx[0] = 0;
temporal_up_switch[0] = false;
num_ref_pics[0] = 1;
pid_diff[0][0] = 1;
break;
case kTemporalStructureMode2:
num_frames_in_gof = 2;
temporal_idx[0] = 0;
temporal_up_switch[0] = false;
num_ref_pics[0] = 1;
pid_diff[0][0] = 2;
temporal_idx[1] = 1;
temporal_up_switch[1] = true;
num_ref_pics[1] = 1;
pid_diff[1][0] = 1;
break;
case kTemporalStructureMode3:
num_frames_in_gof = 4;
temporal_idx[0] = 0;
temporal_up_switch[0] = false;
num_ref_pics[0] = 1;
pid_diff[0][0] = 4;
temporal_idx[1] = 2;
temporal_up_switch[1] = true;
num_ref_pics[1] = 1;
pid_diff[1][0] = 1;
temporal_idx[2] = 1;
temporal_up_switch[2] = true;
num_ref_pics[2] = 1;
pid_diff[2][0] = 2;
temporal_idx[3] = 2;
temporal_up_switch[3] = false;
num_ref_pics[3] = 2;
pid_diff[3][0] = 1;
pid_diff[3][1] = 2;
break;
default:
assert(false);
}
}
void CopyGofInfoVP9(const GofInfoVP9& src) {
num_frames_in_gof = src.num_frames_in_gof;
for (size_t i = 0; i < num_frames_in_gof; ++i) {
temporal_idx[i] = src.temporal_idx[i];
temporal_up_switch[i] = src.temporal_up_switch[i];
num_ref_pics[i] = src.num_ref_pics[i];
for (size_t r = 0; r < num_ref_pics[i]; ++r) {
pid_diff[i][r] = src.pid_diff[i][r];
}
}
}
size_t num_frames_in_gof;
uint8_t temporal_idx[kMaxVp9FramesInGof];
bool temporal_up_switch[kMaxVp9FramesInGof];
size_t num_ref_pics[kMaxVp9FramesInGof];
int16_t pid_diff[kMaxVp9FramesInGof][kMaxVp9RefPics];
};
struct RTPVideoHeaderVP9 {
void InitRTPVideoHeaderVP9() {
inter_pic_predicted = false;
flexible_mode = false;
beginning_of_frame = false;
end_of_frame = false;
ss_data_available = false;
picture_id = kNoPictureId;
max_picture_id = kMaxTwoBytePictureId;
tl0_pic_idx = kNoTl0PicIdx;
temporal_idx = kNoTemporalIdx;
spatial_idx = kNoSpatialIdx;
temporal_up_switch = false;
inter_layer_predicted = false;
gof_idx = kNoGofIdx;
num_ref_pics = 0;
num_spatial_layers = 1;
}
bool inter_pic_predicted; // This layer frame is dependent on previously
// coded frame(s).
bool flexible_mode; // This frame is in flexible mode.
bool beginning_of_frame; // True if this packet is the first in a VP9 layer
// frame.
bool end_of_frame; // True if this packet is the last in a VP9 layer frame.
bool ss_data_available; // True if SS data is available in this payload
// descriptor.
int16_t picture_id; // PictureID index, 15 bits;
// kNoPictureId if PictureID does not exist.
int16_t max_picture_id; // Maximum picture ID index; either 0x7F or 0x7FFF;
int16_t tl0_pic_idx; // TL0PIC_IDX, 8 bits;
// kNoTl0PicIdx means no value provided.
uint8_t temporal_idx; // Temporal layer index, or kNoTemporalIdx.
uint8_t spatial_idx; // Spatial layer index, or kNoSpatialIdx.
bool temporal_up_switch; // True if upswitch to higher frame rate is possible
// starting from this frame.
bool inter_layer_predicted; // Frame is dependent on directly lower spatial
// layer frame.
uint8_t gof_idx; // Index to predefined temporal frame info in SS data.
size_t num_ref_pics; // Number of reference pictures used by this layer
// frame.
int16_t pid_diff[kMaxVp9RefPics]; // P_DIFF signaled to derive the PictureID
// of the reference pictures.
int16_t ref_picture_id[kMaxVp9RefPics]; // PictureID of reference pictures.
// SS data.
size_t num_spatial_layers; // Always populated.
bool spatial_layer_resolution_present;
uint16_t width[kMaxVp9NumberOfSpatialLayers];
uint16_t height[kMaxVp9NumberOfSpatialLayers];
GofInfoVP9 gof;
};
// The packetization types that we support: single, aggregated, and fragmented.
enum H264PacketizationTypes {
kH264SingleNalu, // This packet contains a single NAL unit.
kH264StapA, // This packet contains STAP-A (single time
// aggregation) packets. If this packet has an
// associated NAL unit type, it'll be for the
// first such aggregated packet.
kH264FuA, // This packet contains a FU-A (fragmentation
// unit) packet, meaning it is a part of a frame
// that was too large to fit into a single packet.
};
struct RTPVideoHeaderH264 {
uint8_t nalu_type; // The NAL unit type. If this is a header for a
// fragmented packet, it's the NAL unit type of
// the original data. If this is the header for an
// aggregated packet, it's the NAL unit type of
// the first NAL unit in the packet.
H264PacketizationTypes packetization_type;
};
union RTPVideoTypeHeader {
RTPVideoHeaderVP8 VP8;
RTPVideoHeaderVP9 VP9;
RTPVideoHeaderH264 H264;
};
enum RtpVideoCodecTypes {
kRtpVideoNone,
kRtpVideoGeneric,
kRtpVideoVp8,
kRtpVideoVp9,
kRtpVideoH264
};
#ifndef WEBRTC_AUDIO_PROCESSING_ONLY_BUILD
// Since RTPVideoHeader is used as a member of a union, it can't have a
// non-trivial default constructor.
struct RTPVideoHeader {
uint16_t width; // size
uint16_t height;
VideoRotation rotation;
bool isFirstPacket; // first packet in frame
uint8_t simulcastIdx; // Index if the simulcast encoder creating
// this frame, 0 if not using simulcast.
RtpVideoCodecTypes codec;
RTPVideoTypeHeader codecHeader;
};
#endif
union RTPTypeHeader {
RTPAudioHeader Audio;
#ifndef WEBRTC_AUDIO_PROCESSING_ONLY_BUILD
RTPVideoHeader Video;
#endif
};
struct WebRtcRTPHeader {
RTPHeader header;
FrameType frameType;
RTPTypeHeader type;
// NTP time of the capture time in local timebase in milliseconds.
int64_t ntp_time_ms;
};
class RTPFragmentationHeader {
public:
RTPFragmentationHeader()
: fragmentationVectorSize(0),
fragmentationOffset(NULL),
fragmentationLength(NULL),
fragmentationTimeDiff(NULL),
fragmentationPlType(NULL) {};
~RTPFragmentationHeader() {
delete[] fragmentationOffset;
delete[] fragmentationLength;
delete[] fragmentationTimeDiff;
delete[] fragmentationPlType;
}
void CopyFrom(const RTPFragmentationHeader& src) {
if (this == &src) {
return;
}
if (src.fragmentationVectorSize != fragmentationVectorSize) {
// new size of vectors
// delete old
delete[] fragmentationOffset;
fragmentationOffset = NULL;
delete[] fragmentationLength;
fragmentationLength = NULL;
delete[] fragmentationTimeDiff;
fragmentationTimeDiff = NULL;
delete[] fragmentationPlType;
fragmentationPlType = NULL;
if (src.fragmentationVectorSize > 0) {
// allocate new
if (src.fragmentationOffset) {
fragmentationOffset = new size_t[src.fragmentationVectorSize];
}
if (src.fragmentationLength) {
fragmentationLength = new size_t[src.fragmentationVectorSize];
}
if (src.fragmentationTimeDiff) {
fragmentationTimeDiff = new uint16_t[src.fragmentationVectorSize];
}
if (src.fragmentationPlType) {
fragmentationPlType = new uint8_t[src.fragmentationVectorSize];
}
}
// set new size
fragmentationVectorSize = src.fragmentationVectorSize;
}
if (src.fragmentationVectorSize > 0) {
// copy values
if (src.fragmentationOffset) {
memcpy(fragmentationOffset, src.fragmentationOffset,
src.fragmentationVectorSize * sizeof(size_t));
}
if (src.fragmentationLength) {
memcpy(fragmentationLength, src.fragmentationLength,
src.fragmentationVectorSize * sizeof(size_t));
}
if (src.fragmentationTimeDiff) {
memcpy(fragmentationTimeDiff, src.fragmentationTimeDiff,
src.fragmentationVectorSize * sizeof(uint16_t));
}
if (src.fragmentationPlType) {
memcpy(fragmentationPlType, src.fragmentationPlType,
src.fragmentationVectorSize * sizeof(uint8_t));
}
}
}
void VerifyAndAllocateFragmentationHeader(const size_t size) {
assert(size <= std::numeric_limits<uint16_t>::max());
const uint16_t size16 = static_cast<uint16_t>(size);
if (fragmentationVectorSize < size16) {
uint16_t oldVectorSize = fragmentationVectorSize;
{
// offset
size_t* oldOffsets = fragmentationOffset;
fragmentationOffset = new size_t[size16];
memset(fragmentationOffset + oldVectorSize, 0,
sizeof(size_t) * (size16 - oldVectorSize));
// copy old values
memcpy(fragmentationOffset, oldOffsets,
sizeof(size_t) * oldVectorSize);
delete[] oldOffsets;
}
// length
{
size_t* oldLengths = fragmentationLength;
fragmentationLength = new size_t[size16];
memset(fragmentationLength + oldVectorSize, 0,
sizeof(size_t) * (size16 - oldVectorSize));
memcpy(fragmentationLength, oldLengths,
sizeof(size_t) * oldVectorSize);
delete[] oldLengths;
}
// time diff
{
uint16_t* oldTimeDiffs = fragmentationTimeDiff;
fragmentationTimeDiff = new uint16_t[size16];
memset(fragmentationTimeDiff + oldVectorSize, 0,
sizeof(uint16_t) * (size16 - oldVectorSize));
memcpy(fragmentationTimeDiff, oldTimeDiffs,
sizeof(uint16_t) * oldVectorSize);
delete[] oldTimeDiffs;
}
// payload type
{
uint8_t* oldTimePlTypes = fragmentationPlType;
fragmentationPlType = new uint8_t[size16];
memset(fragmentationPlType + oldVectorSize, 0,
sizeof(uint8_t) * (size16 - oldVectorSize));
memcpy(fragmentationPlType, oldTimePlTypes,
sizeof(uint8_t) * oldVectorSize);
delete[] oldTimePlTypes;
}
fragmentationVectorSize = size16;
}
}
uint16_t fragmentationVectorSize; // Number of fragmentations
size_t* fragmentationOffset; // Offset of pointer to data for each
// fragmentation
size_t* fragmentationLength; // Data size for each fragmentation
uint16_t* fragmentationTimeDiff; // Timestamp difference relative "now" for
// each fragmentation
uint8_t* fragmentationPlType; // Payload type of each fragmentation
private:
RTC_DISALLOW_COPY_AND_ASSIGN(RTPFragmentationHeader);
};
struct RTCPVoIPMetric {
// RFC 3611 4.7
uint8_t lossRate;
uint8_t discardRate;
uint8_t burstDensity;
uint8_t gapDensity;
uint16_t burstDuration;
uint16_t gapDuration;
uint16_t roundTripDelay;
uint16_t endSystemDelay;
uint8_t signalLevel;
uint8_t noiseLevel;
uint8_t RERL;
uint8_t Gmin;
uint8_t Rfactor;
uint8_t extRfactor;
uint8_t MOSLQ;
uint8_t MOSCQ;
uint8_t RXconfig;
uint16_t JBnominal;
uint16_t JBmax;
uint16_t JBabsMax;
};
// Types for the FEC packet masks. The type |kFecMaskRandom| is based on a
// random loss model. The type |kFecMaskBursty| is based on a bursty/consecutive
// loss model. The packet masks are defined in
// modules/rtp_rtcp/fec_private_tables_random(bursty).h
enum FecMaskType {
kFecMaskRandom,
kFecMaskBursty,
};
// Struct containing forward error correction settings.
struct FecProtectionParams {
int fec_rate;
bool use_uep_protection;
int max_fec_frames;
FecMaskType fec_mask_type;
};
// Interface used by the CallStats class to distribute call statistics.
// Callbacks will be triggered as soon as the class has been registered to a
// CallStats object using RegisterStatsObserver.
class CallStatsObserver {
public:
virtual void OnRttUpdate(int64_t avg_rtt_ms, int64_t max_rtt_ms) = 0;
virtual ~CallStatsObserver() {}
};
struct VideoContentMetrics {
VideoContentMetrics()
: motion_magnitude(0.0f),
spatial_pred_err(0.0f),
spatial_pred_err_h(0.0f),
spatial_pred_err_v(0.0f) {}
void Reset() {
motion_magnitude = 0.0f;
spatial_pred_err = 0.0f;
spatial_pred_err_h = 0.0f;
spatial_pred_err_v = 0.0f;
}
float motion_magnitude;
float spatial_pred_err;
float spatial_pred_err_h;
float spatial_pred_err_v;
};
/* This class holds up to 60 ms of super-wideband (32 kHz) stereo audio. It
* allows for adding and subtracting frames while keeping track of the resulting
* states.
*
* Notes
* - The total number of samples in |data_| is
* samples_per_channel_ * num_channels_
*
* - Stereo data is interleaved starting with the left channel.
*
* - The +operator assume that you would never add exactly opposite frames when
* deciding the resulting state. To do this use the -operator.
*/
class AudioFrame {
public:
// Stereo, 32 kHz, 60 ms (2 * 32 * 60)
static const size_t kMaxDataSizeSamples = 3840;
enum VADActivity {
kVadActive = 0,
kVadPassive = 1,
kVadUnknown = 2
};
enum SpeechType {
kNormalSpeech = 0,
kPLC = 1,
kCNG = 2,
kPLCCNG = 3,
kUndefined = 4
};
AudioFrame();
virtual ~AudioFrame() {}
// Resets all members to their default state (except does not modify the
// contents of |data_|).
void Reset();
// |interleaved_| is not changed by this method.
void UpdateFrame(int id, uint32_t timestamp, const int16_t* data,
size_t samples_per_channel, int sample_rate_hz,
SpeechType speech_type, VADActivity vad_activity,
int num_channels = 1, uint32_t energy = -1);
AudioFrame& Append(const AudioFrame& rhs);
void CopyFrom(const AudioFrame& src);
void Mute();
AudioFrame& operator>>=(const int rhs);
AudioFrame& operator+=(const AudioFrame& rhs);
AudioFrame& operator-=(const AudioFrame& rhs);
int id_;
// RTP timestamp of the first sample in the AudioFrame.
uint32_t timestamp_;
// Time since the first frame in milliseconds.
// -1 represents an uninitialized value.
int64_t elapsed_time_ms_;
// NTP time of the estimated capture time in local timebase in milliseconds.
// -1 represents an uninitialized value.
int64_t ntp_time_ms_;
int16_t data_[kMaxDataSizeSamples];
size_t samples_per_channel_;
int sample_rate_hz_;
int num_channels_;
SpeechType speech_type_;
VADActivity vad_activity_;
// Note that there is no guarantee that |energy_| is correct. Any user of this
// member must verify that the value is correct.
// TODO(henrike) Remove |energy_|.
// See https://code.google.com/p/webrtc/issues/detail?id=3315.
uint32_t energy_;
bool interleaved_;
private:
RTC_DISALLOW_COPY_AND_ASSIGN(AudioFrame);
};
inline AudioFrame::AudioFrame()
: data_() {
Reset();
}
inline void AudioFrame::Reset() {
id_ = -1;
// TODO(wu): Zero is a valid value for |timestamp_|. We should initialize
// to an invalid value, or add a new member to indicate invalidity.
timestamp_ = 0;
elapsed_time_ms_ = -1;
ntp_time_ms_ = -1;
samples_per_channel_ = 0;
sample_rate_hz_ = 0;
num_channels_ = 0;
speech_type_ = kUndefined;
vad_activity_ = kVadUnknown;
energy_ = 0xffffffff;
interleaved_ = true;
}
inline void AudioFrame::UpdateFrame(int id,
uint32_t timestamp,
const int16_t* data,
size_t samples_per_channel,
int sample_rate_hz,
SpeechType speech_type,
VADActivity vad_activity,
int num_channels,
uint32_t energy) {
id_ = id;
timestamp_ = timestamp;
samples_per_channel_ = samples_per_channel;
sample_rate_hz_ = sample_rate_hz;
speech_type_ = speech_type;
vad_activity_ = vad_activity;
num_channels_ = num_channels;
energy_ = energy;
assert(num_channels >= 0);
const size_t length = samples_per_channel * num_channels;
assert(length <= kMaxDataSizeSamples);
if (data != NULL) {
memcpy(data_, data, sizeof(int16_t) * length);
} else {
memset(data_, 0, sizeof(int16_t) * length);
}
}
inline void AudioFrame::CopyFrom(const AudioFrame& src) {
if (this == &src) return;
id_ = src.id_;
timestamp_ = src.timestamp_;
elapsed_time_ms_ = src.elapsed_time_ms_;
ntp_time_ms_ = src.ntp_time_ms_;
samples_per_channel_ = src.samples_per_channel_;
sample_rate_hz_ = src.sample_rate_hz_;
speech_type_ = src.speech_type_;
vad_activity_ = src.vad_activity_;
num_channels_ = src.num_channels_;
energy_ = src.energy_;
interleaved_ = src.interleaved_;
assert(num_channels_ >= 0);
const size_t length = samples_per_channel_ * num_channels_;
assert(length <= kMaxDataSizeSamples);
memcpy(data_, src.data_, sizeof(int16_t) * length);
}
inline void AudioFrame::Mute() {
memset(data_, 0, samples_per_channel_ * num_channels_ * sizeof(int16_t));
}
inline AudioFrame& AudioFrame::operator>>=(const int rhs) {
assert((num_channels_ > 0) && (num_channels_ < 3));
if ((num_channels_ > 2) || (num_channels_ < 1)) return *this;
for (size_t i = 0; i < samples_per_channel_ * num_channels_; i++) {
data_[i] = static_cast<int16_t>(data_[i] >> rhs);
}
return *this;
}
inline AudioFrame& AudioFrame::Append(const AudioFrame& rhs) {
// Sanity check
assert((num_channels_ > 0) && (num_channels_ < 3));
assert(interleaved_ == rhs.interleaved_);
if ((num_channels_ > 2) || (num_channels_ < 1)) return *this;
if (num_channels_ != rhs.num_channels_) return *this;
if ((vad_activity_ == kVadActive) || rhs.vad_activity_ == kVadActive) {
vad_activity_ = kVadActive;
} else if (vad_activity_ == kVadUnknown || rhs.vad_activity_ == kVadUnknown) {
vad_activity_ = kVadUnknown;
}
if (speech_type_ != rhs.speech_type_) {
speech_type_ = kUndefined;
}
size_t offset = samples_per_channel_ * num_channels_;
for (size_t i = 0; i < rhs.samples_per_channel_ * rhs.num_channels_; i++) {
data_[offset + i] = rhs.data_[i];
}
samples_per_channel_ += rhs.samples_per_channel_;
return *this;
}
namespace {
inline int16_t ClampToInt16(int32_t input) {
if (input < -0x00008000) {
return -0x8000;
} else if (input > 0x00007FFF) {
return 0x7FFF;
} else {
return static_cast<int16_t>(input);
}
}
}
inline AudioFrame& AudioFrame::operator+=(const AudioFrame& rhs) {
// Sanity check
assert((num_channels_ > 0) && (num_channels_ < 3));
assert(interleaved_ == rhs.interleaved_);
if ((num_channels_ > 2) || (num_channels_ < 1)) return *this;
if (num_channels_ != rhs.num_channels_) return *this;
bool noPrevData = false;
if (samples_per_channel_ != rhs.samples_per_channel_) {
if (samples_per_channel_ == 0) {
// special case we have no data to start with
samples_per_channel_ = rhs.samples_per_channel_;
noPrevData = true;
} else {
return *this;
}
}
if ((vad_activity_ == kVadActive) || rhs.vad_activity_ == kVadActive) {
vad_activity_ = kVadActive;
} else if (vad_activity_ == kVadUnknown || rhs.vad_activity_ == kVadUnknown) {
vad_activity_ = kVadUnknown;
}
if (speech_type_ != rhs.speech_type_) speech_type_ = kUndefined;
if (noPrevData) {
memcpy(data_, rhs.data_,
sizeof(int16_t) * rhs.samples_per_channel_ * num_channels_);
} else {
// IMPROVEMENT this can be done very fast in assembly
for (size_t i = 0; i < samples_per_channel_ * num_channels_; i++) {
int32_t wrap_guard =
static_cast<int32_t>(data_[i]) + static_cast<int32_t>(rhs.data_[i]);
data_[i] = ClampToInt16(wrap_guard);
}
}
energy_ = 0xffffffff;
return *this;
}
inline AudioFrame& AudioFrame::operator-=(const AudioFrame& rhs) {
// Sanity check
assert((num_channels_ > 0) && (num_channels_ < 3));
assert(interleaved_ == rhs.interleaved_);
if ((num_channels_ > 2) || (num_channels_ < 1)) return *this;
if ((samples_per_channel_ != rhs.samples_per_channel_) ||
(num_channels_ != rhs.num_channels_)) {
return *this;
}
if ((vad_activity_ != kVadPassive) || rhs.vad_activity_ != kVadPassive) {
vad_activity_ = kVadUnknown;
}
speech_type_ = kUndefined;
for (size_t i = 0; i < samples_per_channel_ * num_channels_; i++) {
int32_t wrap_guard =
static_cast<int32_t>(data_[i]) - static_cast<int32_t>(rhs.data_[i]);
data_[i] = ClampToInt16(wrap_guard);
}
energy_ = 0xffffffff;
return *this;
}
inline bool IsNewerSequenceNumber(uint16_t sequence_number,
uint16_t prev_sequence_number) {
// Distinguish between elements that are exactly 0x8000 apart.
// If s1>s2 and |s1-s2| = 0x8000: IsNewer(s1,s2)=true, IsNewer(s2,s1)=false
// rather than having IsNewer(s1,s2) = IsNewer(s2,s1) = false.
if (static_cast<uint16_t>(sequence_number - prev_sequence_number) == 0x8000) {
return sequence_number > prev_sequence_number;
}
return sequence_number != prev_sequence_number &&
static_cast<uint16_t>(sequence_number - prev_sequence_number) < 0x8000;
}
inline bool IsNewerTimestamp(uint32_t timestamp, uint32_t prev_timestamp) {
// Distinguish between elements that are exactly 0x80000000 apart.
// If t1>t2 and |t1-t2| = 0x80000000: IsNewer(t1,t2)=true,
// IsNewer(t2,t1)=false
// rather than having IsNewer(t1,t2) = IsNewer(t2,t1) = false.
if (static_cast<uint32_t>(timestamp - prev_timestamp) == 0x80000000) {
return timestamp > prev_timestamp;
}
return timestamp != prev_timestamp &&
static_cast<uint32_t>(timestamp - prev_timestamp) < 0x80000000;
}
inline uint16_t LatestSequenceNumber(uint16_t sequence_number1,
uint16_t sequence_number2) {
return IsNewerSequenceNumber(sequence_number1, sequence_number2)
? sequence_number1
: sequence_number2;
}
inline uint32_t LatestTimestamp(uint32_t timestamp1, uint32_t timestamp2) {
return IsNewerTimestamp(timestamp1, timestamp2) ? timestamp1 : timestamp2;
}
// Utility class to unwrap a sequence number to a larger type, for easier
// handling large ranges. Note that sequence numbers will never be unwrapped
// to a negative value.
class SequenceNumberUnwrapper {
public:
SequenceNumberUnwrapper() : last_seq_(-1) {}
// Get the unwrapped sequence, but don't update the internal state.
int64_t UnwrapWithoutUpdate(uint16_t sequence_number) {
if (last_seq_ == -1)
return sequence_number;
uint16_t cropped_last = static_cast<uint16_t>(last_seq_);
int64_t delta = sequence_number - cropped_last;
if (IsNewerSequenceNumber(sequence_number, cropped_last)) {
if (delta < 0)
delta += (1 << 16); // Wrap forwards.
} else if (delta > 0 && (last_seq_ + delta - (1 << 16)) >= 0) {
// If sequence_number is older but delta is positive, this is a backwards
// wrap-around. However, don't wrap backwards past 0 (unwrapped).
delta -= (1 << 16);
}
return last_seq_ + delta;
}
// Only update the internal state to the specified last (unwrapped) sequence.
void UpdateLast(int64_t last_sequence) { last_seq_ = last_sequence; }
// Unwrap the sequence number and update the internal state.
int64_t Unwrap(uint16_t sequence_number) {
int64_t unwrapped = UnwrapWithoutUpdate(sequence_number);
UpdateLast(unwrapped);
return unwrapped;
}
private:
int64_t last_seq_;
};
} // namespace webrtc
#endif // MODULE_COMMON_TYPES_H
|