485 lines
9.3 KiB
Go
485 lines
9.3 KiB
Go
//go:build !disable_format_aac && !disable_codec_libfdk_aac
|
|
// +build !disable_format_aac,!disable_codec_libfdk_aac
|
|
|
|
package aac
|
|
|
|
import (
|
|
"bytes"
|
|
"errors"
|
|
"fmt"
|
|
"git.gammaspectra.live/S.O.N.G/Kirika/audio"
|
|
"git.gammaspectra.live/S.O.N.G/Kirika/cgo"
|
|
"git.gammaspectra.live/S.O.N.G/go-fdkaac/fdkaac"
|
|
aac_adts "github.com/edgeware/mp4ff/aac"
|
|
"github.com/edgeware/mp4ff/mp4"
|
|
"io"
|
|
"time"
|
|
"unsafe"
|
|
)
|
|
|
|
type Format struct {
|
|
}
|
|
|
|
func NewFormat() Format {
|
|
return Format{}
|
|
}
|
|
|
|
func (f Format) Name() string {
|
|
return "aac"
|
|
}
|
|
|
|
func (f Format) Description() string {
|
|
return "libfdk-aac (S.O.N.G/go-fdkaac)"
|
|
}
|
|
|
|
func decodeFrame(decoder *fdkaac.AacDecoder, r io.Reader) ([]float32, error) {
|
|
pcm, err := tryDecodeFrame(decoder)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
if pcm != nil {
|
|
return pcm, err
|
|
}
|
|
|
|
header, _, err := aac_adts.DecodeADTSHeader(r)
|
|
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
data := make([]byte, header.PayloadLength)
|
|
|
|
if _, err = io.ReadFull(r, data); err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
var n int
|
|
fullData := append(header.Encode(), data...)
|
|
if n, err = decoder.Fill(fullData); n != 0 {
|
|
return nil, errors.New("buffer under read")
|
|
}
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
return decodeFrame(decoder, r)
|
|
}
|
|
|
|
func tryDecodeFrame(decoder *fdkaac.AacDecoder) ([]float32, error) {
|
|
pcm, err := decoder.Decode()
|
|
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
if pcm != nil {
|
|
return cgo.Int32ToFloat32(cgo.BytesToInt32(pcm, 16), 16), nil
|
|
}
|
|
|
|
return nil, nil
|
|
}
|
|
|
|
func decodeFrameMP4(decoder *fdkaac.AacDecoder, demuxer *mp4Decoder) (result []float32, err error) {
|
|
pcm, err := tryDecodeFrame(decoder)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
if pcm != nil {
|
|
return pcm, err
|
|
}
|
|
|
|
samples := demuxer.Read()
|
|
if samples == nil {
|
|
return nil, io.EOF
|
|
}
|
|
var n int
|
|
for _, sample := range samples {
|
|
if n, err = decoder.Fill(sample); n != 0 {
|
|
return nil, errors.New("buffer under read")
|
|
}
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
pcm, err = tryDecodeFrame(decoder)
|
|
if pcm != nil {
|
|
result = append(result, pcm...)
|
|
}
|
|
}
|
|
|
|
return result, nil
|
|
}
|
|
|
|
func (f Format) Open(r io.ReadSeekCloser) (audio.Source, error) {
|
|
decoder := fdkaac.NewAacDecoder()
|
|
|
|
mp4Demuxer, err := tryDecodeMP4(r)
|
|
if err != nil { //try ADTS
|
|
r.Seek(0, io.SeekStart)
|
|
err = decoder.InitAdts()
|
|
if err != nil {
|
|
return audio.Source{}, err
|
|
}
|
|
|
|
buf, err := decodeFrame(decoder, r)
|
|
|
|
if err != nil {
|
|
decoder.Close()
|
|
return audio.Source{}, err
|
|
}
|
|
|
|
newChannel := make(chan []float32)
|
|
|
|
go func() {
|
|
defer close(newChannel)
|
|
defer decoder.Close()
|
|
|
|
if len(buf) > 0 {
|
|
newChannel <- buf
|
|
}
|
|
|
|
for {
|
|
buf, err = decodeFrame(decoder, r)
|
|
|
|
if err != nil {
|
|
return
|
|
}
|
|
|
|
if len(buf) > 0 {
|
|
newChannel <- buf
|
|
}
|
|
}
|
|
}()
|
|
|
|
return audio.Source{
|
|
Channels: decoder.NumChannels(),
|
|
SampleRate: decoder.SampleRate(),
|
|
Blocks: newChannel,
|
|
}, nil
|
|
} else {
|
|
return audio.Source{}, fmt.Errorf("unsupported format mp4")
|
|
err = decoder.InitRaw(mp4Demuxer.cookie)
|
|
if err != nil {
|
|
return audio.Source{}, err
|
|
}
|
|
|
|
buf, err := decodeFrameMP4(decoder, mp4Demuxer)
|
|
|
|
if err != nil {
|
|
decoder.Close()
|
|
return audio.Source{}, err
|
|
}
|
|
|
|
newChannel := make(chan []float32)
|
|
|
|
go func() {
|
|
defer close(newChannel)
|
|
defer decoder.Close()
|
|
|
|
if len(buf) > 0 {
|
|
newChannel <- buf
|
|
}
|
|
|
|
for {
|
|
buf, err = decodeFrameMP4(decoder, mp4Demuxer)
|
|
|
|
if err != nil {
|
|
return
|
|
}
|
|
|
|
if len(buf) > 0 {
|
|
newChannel <- buf
|
|
}
|
|
}
|
|
}()
|
|
|
|
return audio.Source{
|
|
Channels: decoder.NumChannels(),
|
|
SampleRate: decoder.SampleRate(),
|
|
Blocks: newChannel,
|
|
}, nil
|
|
}
|
|
|
|
}
|
|
|
|
func (f Format) Encode(source audio.Source, writer io.WriteCloser, options map[string]interface{}) error {
|
|
var bitrate = 128
|
|
var isHEv2 bool
|
|
var format = "adts"
|
|
|
|
if options != nil {
|
|
var val interface{}
|
|
var ok bool
|
|
var intVal int
|
|
var strVal string
|
|
if val, ok = options["bitrate"]; ok {
|
|
if strVal, ok = val.(string); ok {
|
|
switch strVal {
|
|
case "320k":
|
|
bitrate = 320
|
|
case "256k":
|
|
bitrate = 256
|
|
case "192k":
|
|
bitrate = 192
|
|
case "128k":
|
|
bitrate = 128
|
|
|
|
default:
|
|
return fmt.Errorf("unknown setting bitrate=%s", strVal)
|
|
}
|
|
} else if intVal, ok = val.(int); ok {
|
|
bitrate = intVal
|
|
}
|
|
}
|
|
if val, ok = options["mode"]; ok {
|
|
if strVal, ok = val.(string); ok {
|
|
switch strVal {
|
|
case "lc":
|
|
isHEv2 = false
|
|
case "hev2":
|
|
isHEv2 = true
|
|
|
|
default:
|
|
return fmt.Errorf("unknown setting mode=%s", strVal)
|
|
}
|
|
}
|
|
}
|
|
if val, ok = options["format"]; ok {
|
|
if strVal, ok = val.(string); ok {
|
|
format = strVal
|
|
}
|
|
}
|
|
}
|
|
|
|
muxingMode := fdkaac.MuxingModeADTS
|
|
|
|
if format == "adts" {
|
|
muxingMode = fdkaac.MuxingModeADTS
|
|
} else if format == "mp4" {
|
|
muxingMode = fdkaac.MuxingModeRAW
|
|
} else if format == "adif" {
|
|
muxingMode = fdkaac.MuxingModeADIF
|
|
} else {
|
|
return fmt.Errorf("unsupported format %s", format)
|
|
}
|
|
|
|
encoder := fdkaac.NewAacEncoder()
|
|
if isHEv2 {
|
|
err := encoder.InitHEv2(source.Channels, source.SampleRate, bitrate*1024, muxingMode)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
} else {
|
|
err := encoder.InitLc(source.Channels, source.SampleRate, bitrate*1024, muxingMode)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
}
|
|
defer encoder.Close()
|
|
|
|
frameSize := encoder.FrameSize() * encoder.Channels()
|
|
|
|
if format == "mp4" {
|
|
init := mp4.CreateEmptyInit()
|
|
init.AddEmptyTrack(uint32(source.SampleRate), "audio", "en")
|
|
trackId := init.Moov.Mvhd.NextTrackID - 1
|
|
trak := init.Moov.Trak
|
|
|
|
objType := aac_adts.AAClc
|
|
if isHEv2 {
|
|
objType = aac_adts.HEAACv2
|
|
}
|
|
|
|
{
|
|
stsd := trak.Mdia.Minf.Stbl.Stsd
|
|
asc := &aac_adts.AudioSpecificConfig{
|
|
ObjectType: byte(objType),
|
|
ChannelConfiguration: byte(source.Channels),
|
|
SamplingFrequency: source.SampleRate,
|
|
ExtensionFrequency: 0,
|
|
SBRPresentFlag: false,
|
|
PSPresentFlag: false,
|
|
}
|
|
switch objType {
|
|
case aac_adts.HEAACv1:
|
|
asc.ExtensionFrequency = 2 * source.SampleRate
|
|
asc.SBRPresentFlag = true
|
|
case aac_adts.HEAACv2:
|
|
asc.ExtensionFrequency = 2 * source.SampleRate
|
|
asc.SBRPresentFlag = true
|
|
asc.ChannelConfiguration = 1
|
|
asc.PSPresentFlag = true
|
|
}
|
|
|
|
buf := &bytes.Buffer{}
|
|
err := asc.Encode(buf)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
ascBytes := buf.Bytes()
|
|
esds := mp4.CreateEsdsBox(ascBytes)
|
|
mp4a := mp4.CreateAudioSampleEntryBox("mp4a",
|
|
uint16(asc.ChannelConfiguration),
|
|
16, uint16(source.SampleRate), esds)
|
|
stsd.AddChild(mp4a)
|
|
}
|
|
|
|
init.Encode(writer)
|
|
|
|
var seqNumber uint32
|
|
var packetsWritten uint64
|
|
var outputBuffer [][]byte
|
|
|
|
segmentDuration := time.Millisecond * 100
|
|
|
|
outputSegment := func() {
|
|
seg := mp4.NewMediaSegment()
|
|
frag, _ := mp4.CreateFragment(seqNumber, trackId)
|
|
seg.AddFragment(frag)
|
|
|
|
for _, b := range outputBuffer {
|
|
frag.AddFullSampleToTrack(mp4.FullSample{
|
|
Sample: mp4.Sample{
|
|
Dur: uint32(frameSize),
|
|
Size: uint32(len(b)),
|
|
},
|
|
DecodeTime: uint64(frameSize) * packetsWritten,
|
|
Data: b,
|
|
}, trackId)
|
|
packetsWritten++
|
|
}
|
|
|
|
seg.Encode(writer)
|
|
seqNumber++
|
|
outputBuffer = nil
|
|
}
|
|
|
|
outputPacket := func(packet []byte) {
|
|
outputBuffer = append(outputBuffer, packet)
|
|
|
|
if time.Duration(float64(time.Second)*(float64(frameSize*len(outputBuffer))/float64(source.SampleRate))) >= segmentDuration {
|
|
outputSegment()
|
|
}
|
|
}
|
|
|
|
var buffer []int16
|
|
for block := range source.Blocks {
|
|
|
|
buffer = append(buffer, cgo.Float32ToInt16(block)...)
|
|
|
|
for len(buffer) >= frameSize {
|
|
sl := buffer[:frameSize]
|
|
buf, err := encoder.Encode(unsafe.Slice((*byte)(unsafe.Pointer(&sl[0])), len(sl)*2))
|
|
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
if len(buf) > 0 {
|
|
outputPacket(buf)
|
|
}
|
|
|
|
buffer = buffer[frameSize:]
|
|
}
|
|
}
|
|
|
|
if len(buffer) > 0 {
|
|
//pad
|
|
buffer = append(buffer, make([]int16, frameSize-len(buffer))...)
|
|
buf, err := encoder.Encode(unsafe.Slice((*byte)(unsafe.Pointer(&buffer[0])), len(buffer)*2))
|
|
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
if len(buf) > 0 {
|
|
outputPacket(buf)
|
|
}
|
|
}
|
|
|
|
//Do flush
|
|
for {
|
|
buf, err := encoder.Flush()
|
|
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
if len(buf) > 0 {
|
|
outputPacket(buf)
|
|
} else {
|
|
break
|
|
}
|
|
}
|
|
|
|
if len(outputBuffer) > 0 {
|
|
outputSegment()
|
|
}
|
|
} else {
|
|
|
|
var buffer []int16
|
|
for block := range source.Blocks {
|
|
|
|
buffer = append(buffer, cgo.Float32ToInt16(block)...)
|
|
|
|
for len(buffer) >= frameSize {
|
|
sl := buffer[:frameSize]
|
|
buf, err := encoder.Encode(unsafe.Slice((*byte)(unsafe.Pointer(&sl[0])), len(sl)*2))
|
|
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
if len(buf) > 0 {
|
|
_, err = writer.Write(buf)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
}
|
|
|
|
buffer = buffer[frameSize:]
|
|
}
|
|
}
|
|
|
|
if len(buffer) > 0 {
|
|
//pad
|
|
buffer = append(buffer, make([]int16, frameSize-len(buffer))...)
|
|
buf, err := encoder.Encode(unsafe.Slice((*byte)(unsafe.Pointer(&buffer[0])), len(buffer)*2))
|
|
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
if len(buf) > 0 {
|
|
_, err = writer.Write(buf)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
}
|
|
}
|
|
|
|
//Do flush
|
|
for {
|
|
buf, err := encoder.Flush()
|
|
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
if len(buf) > 0 {
|
|
_, err = writer.Write(buf)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
} else {
|
|
break
|
|
}
|
|
}
|
|
}
|
|
|
|
return nil
|
|
}
|
|
|
|
func (f Format) Identify(peek []byte, extension string) bool {
|
|
return extension == "aac" || extension == "adts"
|
|
}
|