1
0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-11-21 10:55:51 +02:00

avcodec: add ATRAC Advanced Lossless decoders

Only lossy part is decoded for now.

Signed-off-by: Paul B Mahol <onemda@gmail.com>
This commit is contained in:
Paul B Mahol 2017-01-25 13:33:52 +01:00
parent d96ebc5ef8
commit 280a40dd27
10 changed files with 223 additions and 42 deletions

View File

@ -193,8 +193,11 @@ OBJS-$(CONFIG_ASV2_DECODER) += asvdec.o asv.o mpeg12data.o
OBJS-$(CONFIG_ASV2_ENCODER) += asvenc.o asv.o mpeg12data.o
OBJS-$(CONFIG_ATRAC1_DECODER) += atrac1.o atrac.o
OBJS-$(CONFIG_ATRAC3_DECODER) += atrac3.o atrac.o
OBJS-$(CONFIG_ATRAC3AL_DECODER) += atrac3.o atrac.o
OBJS-$(CONFIG_ATRAC3P_DECODER) += atrac3plusdec.o atrac3plus.o \
atrac3plusdsp.o atrac.o
OBJS-$(CONFIG_ATRAC3PAL_DECODER) += atrac3plusdec.o atrac3plus.o \
atrac3plusdsp.o atrac.o
OBJS-$(CONFIG_AURA_DECODER) += cyuv.o
OBJS-$(CONFIG_AURA2_DECODER) += aura.o
OBJS-$(CONFIG_AVRN_DECODER) += avrndec.o mjpegdec.o

View File

@ -403,7 +403,9 @@ void avcodec_register_all(void)
REGISTER_DECODER(APE, ape);
REGISTER_DECODER(ATRAC1, atrac1);
REGISTER_DECODER(ATRAC3, atrac3);
REGISTER_DECODER(ATRAC3AL, atrac3al);
REGISTER_DECODER(ATRAC3P, atrac3p);
REGISTER_DECODER(ATRAC3PAL, atrac3pal);
REGISTER_DECODER(BINKAUDIO_DCT, binkaudio_dct);
REGISTER_DECODER(BINKAUDIO_RDFT, binkaudio_rdft);
REGISTER_DECODER(BMV_AUDIO, bmv_audio);

View File

@ -751,6 +751,40 @@ static int decode_frame(AVCodecContext *avctx, const uint8_t *databuf,
return 0;
}
static int al_decode_frame(AVCodecContext *avctx, const uint8_t *databuf,
int size, float **out_samples)
{
ATRAC3Context *q = avctx->priv_data;
int ret, i;
/* Set the bitstream reader at the start of a channel sound unit. */
init_get_bits(&q->gb, databuf, size * 8);
/* single channels */
/* Decode the channel sound units. */
for (i = 0; i < avctx->channels; i++) {
ret = decode_channel_sound_unit(q, &q->gb, &q->units[i],
out_samples[i], i, q->coding_mode);
if (ret != 0)
return ret;
while (i < avctx->channels && get_bits_left(&q->gb) > 6 && show_bits(&q->gb, 6) != 0x28) {
skip_bits(&q->gb, 1);
}
}
/* Apply the iQMF synthesis filter. */
for (i = 0; i < avctx->channels; i++) {
float *p1 = out_samples[i];
float *p2 = p1 + 256;
float *p3 = p2 + 256;
float *p4 = p3 + 256;
ff_atrac_iqmf(p1, p2, 256, p1, q->units[i].delay_buf1, q->temp_buf);
ff_atrac_iqmf(p4, p3, 256, p3, q->units[i].delay_buf2, q->temp_buf);
ff_atrac_iqmf(p1, p3, 512, p1, q->units[i].delay_buf3, q->temp_buf);
}
return 0;
}
static int atrac3_decode_frame(AVCodecContext *avctx, void *data,
int *got_frame_ptr, AVPacket *avpkt)
{
@ -791,6 +825,28 @@ static int atrac3_decode_frame(AVCodecContext *avctx, void *data,
return avctx->block_align;
}
static int atrac3al_decode_frame(AVCodecContext *avctx, void *data,
int *got_frame_ptr, AVPacket *avpkt)
{
AVFrame *frame = data;
int ret;
frame->nb_samples = SAMPLES_PER_FRAME;
if ((ret = ff_get_buffer(avctx, frame, 0)) < 0)
return ret;
ret = al_decode_frame(avctx, avpkt->data, avpkt->size,
(float **)frame->extended_data);
if (ret) {
av_log(avctx, AV_LOG_ERROR, "Frame decoding error!\n");
return ret;
}
*got_frame_ptr = 1;
return avpkt->size;
}
static av_cold void atrac3_init_static_data(void)
{
int i;
@ -827,7 +883,12 @@ static av_cold int atrac3_decode_init(AVCodecContext *avctx)
static_init_done = 1;
/* Take care of the codec-specific extradata. */
if (avctx->extradata_size == 14) {
if (avctx->codec_id == AV_CODEC_ID_ATRAC3AL) {
version = 4;
samples_per_frame = SAMPLES_PER_FRAME * avctx->channels;
delay = 0x88E;
q->coding_mode = SINGLE;
} else if (avctx->extradata_size == 14) {
/* Parse the extradata, WAV format */
av_log(avctx, AV_LOG_DEBUG, "[0-1] %d\n",
bytestream_get_le16(&edata_ptr)); // Unknown value always 1
@ -959,3 +1020,17 @@ AVCodec ff_atrac3_decoder = {
.sample_fmts = (const enum AVSampleFormat[]) { AV_SAMPLE_FMT_FLTP,
AV_SAMPLE_FMT_NONE },
};
AVCodec ff_atrac3al_decoder = {
.name = "atrac3al",
.long_name = NULL_IF_CONFIG_SMALL("ATRAC3 AL (Adaptive TRansform Acoustic Coding 3 Advanced Lossless)"),
.type = AVMEDIA_TYPE_AUDIO,
.id = AV_CODEC_ID_ATRAC3AL,
.priv_data_size = sizeof(ATRAC3Context),
.init = atrac3_decode_init,
.close = atrac3_decode_close,
.decode = atrac3al_decode_frame,
.capabilities = AV_CODEC_CAP_SUBFRAMES | AV_CODEC_CAP_DR1,
.sample_fmts = (const enum AVSampleFormat[]) { AV_SAMPLE_FMT_FLTP,
AV_SAMPLE_FMT_NONE },
};

View File

@ -384,7 +384,7 @@ static int atrac3p_decode_frame(AVCodecContext *avctx, void *data,
*got_frame_ptr = 1;
return FFMIN(avctx->block_align, avpkt->size);
return avctx->codec_id == AV_CODEC_ID_ATRAC3P ? FFMIN(avctx->block_align, avpkt->size) : avpkt->size;
}
AVCodec ff_atrac3p_decoder = {
@ -398,3 +398,15 @@ AVCodec ff_atrac3p_decoder = {
.close = atrac3p_decode_close,
.decode = atrac3p_decode_frame,
};
AVCodec ff_atrac3pal_decoder = {
.name = "atrac3plusal",
.long_name = NULL_IF_CONFIG_SMALL("ATRAC3+ AL (Adaptive TRansform Acoustic Coding 3+ Advanced Lossless)"),
.type = AVMEDIA_TYPE_AUDIO,
.id = AV_CODEC_ID_ATRAC3PAL,
.capabilities = AV_CODEC_CAP_DR1,
.priv_data_size = sizeof(ATRAC3PContext),
.init = atrac3p_decode_init,
.close = atrac3p_decode_close,
.decode = atrac3p_decode_frame,
};

View File

@ -603,6 +603,8 @@ enum AVCodecID {
AV_CODEC_ID_XMA1,
AV_CODEC_ID_XMA2,
AV_CODEC_ID_DST,
AV_CODEC_ID_ATRAC3AL,
AV_CODEC_ID_ATRAC3PAL,
/* subtitle codecs */
AV_CODEC_ID_FIRST_SUBTITLE = 0x17000, ///< A dummy ID pointing at the start of subtitle codecs.

View File

@ -2476,6 +2476,20 @@ static const AVCodecDescriptor codec_descriptors[] = {
.long_name = NULL_IF_CONFIG_SMALL("ATRAC3+ (Adaptive TRansform Acoustic Coding 3+)"),
.props = AV_CODEC_PROP_LOSSY,
},
{
.id = AV_CODEC_ID_ATRAC3PAL,
.type = AVMEDIA_TYPE_AUDIO,
.name = "atrac3pal",
.long_name = NULL_IF_CONFIG_SMALL("ATRAC3+ AL (Adaptive TRansform Acoustic Coding 3+ Advanced Lossless)"),
.props = AV_CODEC_PROP_LOSSLESS,
},
{
.id = AV_CODEC_ID_ATRAC3AL,
.type = AVMEDIA_TYPE_AUDIO,
.name = "atrac3al",
.long_name = NULL_IF_CONFIG_SMALL("ATRAC3 AL (Adaptive TRansform Acoustic Coding 3 Advanced Lossless)"),
.props = AV_CODEC_PROP_LOSSLESS,
},
{
.id = AV_CODEC_ID_EAC3,
.type = AVMEDIA_TYPE_AUDIO,

View File

@ -28,7 +28,7 @@
#include "libavutil/version.h"
#define LIBAVCODEC_VERSION_MAJOR 57
#define LIBAVCODEC_VERSION_MINOR 77
#define LIBAVCODEC_VERSION_MINOR 78
#define LIBAVCODEC_VERSION_MICRO 100
#define LIBAVCODEC_VERSION_INT AV_VERSION_INT(LIBAVCODEC_VERSION_MAJOR, \

View File

@ -26,10 +26,12 @@
const uint16_t ff_oma_srate_tab[8] = { 320, 441, 480, 882, 960, 0 };
const AVCodecTag ff_oma_codec_tags[] = {
{ AV_CODEC_ID_ATRAC3, OMA_CODECID_ATRAC3 },
{ AV_CODEC_ID_ATRAC3P, OMA_CODECID_ATRAC3P },
{ AV_CODEC_ID_MP3, OMA_CODECID_MP3 },
{ AV_CODEC_ID_PCM_S16BE, OMA_CODECID_LPCM },
{ AV_CODEC_ID_ATRAC3, OMA_CODECID_ATRAC3 },
{ AV_CODEC_ID_ATRAC3P, OMA_CODECID_ATRAC3P },
{ AV_CODEC_ID_MP3, OMA_CODECID_MP3 },
{ AV_CODEC_ID_PCM_S16BE, OMA_CODECID_LPCM },
{ AV_CODEC_ID_ATRAC3PAL, OMA_CODECID_ATRAC3PAL },
{ AV_CODEC_ID_ATRAC3AL, OMA_CODECID_ATRAC3AL },
{ 0 },
};

View File

@ -35,6 +35,8 @@ enum {
OMA_CODECID_MP3 = 3,
OMA_CODECID_LPCM = 4,
OMA_CODECID_WMA = 5,
OMA_CODECID_ATRAC3PAL = 33,
OMA_CODECID_ATRAC3AL = 34,
};
extern const uint16_t ff_oma_srate_tab[8];

View File

@ -75,6 +75,8 @@ typedef struct OMAContext {
uint8_t e_val[8];
uint8_t iv[8];
struct AVDES *av_des;
int (*read_packet)(AVFormatContext *s, AVPacket *pkt);
} OMAContext;
static void hex_log(AVFormatContext *s, int level,
@ -302,6 +304,82 @@ static int decrypt_init(AVFormatContext *s, ID3v2ExtraMeta *em, uint8_t *header)
return 0;
}
static int read_packet(AVFormatContext *s, AVPacket *pkt)
{
OMAContext *oc = s->priv_data;
AVStream *st = s->streams[0];
int packet_size = st->codecpar->block_align;
int byte_rate = st->codecpar->bit_rate >> 3;
int64_t pos = avio_tell(s->pb);
int ret = av_get_packet(s->pb, pkt, packet_size);
if (ret < packet_size)
pkt->flags |= AV_PKT_FLAG_CORRUPT;
if (ret < 0)
return ret;
if (!ret)
return AVERROR_EOF;
pkt->stream_index = 0;
if (pos >= oc->content_start && byte_rate > 0) {
pkt->pts =
pkt->dts = av_rescale(pos - oc->content_start, st->time_base.den,
byte_rate * (int64_t)st->time_base.num);
}
if (oc->encrypted) {
/* previous unencrypted block saved in IV for
* the next packet (CBC mode) */
if (ret == packet_size)
av_des_crypt(oc->av_des, pkt->data, pkt->data,
(packet_size >> 3), oc->iv, 1);
else
memset(oc->iv, 0, 8);
}
return ret;
}
static int aal_read_packet(AVFormatContext *s, AVPacket *pkt)
{
int64_t pos = avio_tell(s->pb);
int ret, type, pts;
int packet_size;
unsigned tag;
if (avio_feof(s->pb))
return AVERROR_EOF;
tag = avio_rb24(s->pb);
if (tag == 0)
return AVERROR_EOF;
else if (tag != MKBETAG(0,'B','L','K'))
return AVERROR_INVALIDDATA;
type = avio_r8(s->pb);
packet_size = avio_rb16(s->pb);
avio_skip(s->pb, 2);
pts = avio_rb32(s->pb);
avio_skip(s->pb, 12);
ret = av_get_packet(s->pb, pkt, packet_size);
if (ret < packet_size)
pkt->flags |= AV_PKT_FLAG_CORRUPT;
if (ret < 0)
return ret;
if (!ret)
return AVERROR_EOF;
pkt->stream_index = 0;
pkt->pos = pos;
pkt->pts = pts * 2048LL;
pkt->duration = 2048;
return ret;
}
static int oma_read_header(AVFormatContext *s)
{
int ret, framesize, jsflag, samplerate;
@ -347,6 +425,8 @@ static int oma_read_header(AVFormatContext *s)
st->codecpar->codec_id = ff_codec_get_id(ff_oma_codec_tags,
st->codecpar->codec_tag);
oc->read_packet = read_packet;
switch (buf[32]) {
case OMA_CODECID_ATRAC3:
samplerate = ff_oma_srate_tab[(codec_params >> 13) & 7] * 100;
@ -417,6 +497,22 @@ static int oma_read_header(AVFormatContext *s)
av_get_bits_per_sample(st->codecpar->codec_id);
avpriv_set_pts_info(st, 64, 1, st->codecpar->sample_rate);
break;
case OMA_CODECID_ATRAC3AL:
st->codecpar->channels = 2;
st->codecpar->channel_layout = AV_CH_LAYOUT_STEREO;
st->codecpar->sample_rate = 44100;
avpriv_set_pts_info(st, 64, 1, 44100);
oc->read_packet = aal_read_packet;
framesize = 4096;
break;
case OMA_CODECID_ATRAC3PAL:
st->codecpar->channel_layout = AV_CH_LAYOUT_STEREO;
st->codecpar->channels = 2;
st->codecpar->sample_rate = 44100;
avpriv_set_pts_info(st, 64, 1, 44100);
oc->read_packet = aal_read_packet;
framesize = 4096;
break;
default:
av_log(s, AV_LOG_ERROR, "Unsupported codec %d!\n", buf[32]);
return AVERROR(ENOSYS);
@ -427,43 +523,10 @@ static int oma_read_header(AVFormatContext *s)
return 0;
}
static int oma_read_packet(AVFormatContext *s, AVPacket *pkt)
{
OMAContext *oc = s->priv_data;
AVStream *st = s->streams[0];
int packet_size = st->codecpar->block_align;
int byte_rate = st->codecpar->bit_rate >> 3;
int64_t pos = avio_tell(s->pb);
int ret = av_get_packet(s->pb, pkt, packet_size);
if (ret < packet_size)
pkt->flags |= AV_PKT_FLAG_CORRUPT;
if (ret < 0)
return ret;
if (!ret)
return AVERROR_EOF;
pkt->stream_index = 0;
if (pos >= oc->content_start && byte_rate > 0) {
pkt->pts =
pkt->dts = av_rescale(pos - oc->content_start, st->time_base.den,
byte_rate * (int64_t)st->time_base.num);
}
if (oc->encrypted) {
/* previous unencrypted block saved in IV for
* the next packet (CBC mode) */
if (ret == packet_size)
av_des_crypt(oc->av_des, pkt->data, pkt->data,
(packet_size >> 3), oc->iv, 1);
else
memset(oc->iv, 0, 8);
}
return ret;
return oc->read_packet(s, pkt);
}
static int oma_read_probe(AVProbeData *p)
@ -491,8 +554,14 @@ static int oma_read_seek(struct AVFormatContext *s,
int stream_index, int64_t timestamp, int flags)
{
OMAContext *oc = s->priv_data;
int64_t err = ff_pcm_read_seek(s, stream_index, timestamp, flags);
AVStream *st = s->streams[0];
int64_t err;
if (st->codecpar->codec_id == AV_CODEC_ID_ATRAC3PAL ||
st->codecpar->codec_id == AV_CODEC_ID_ATRAC3AL)
return -1;
err = ff_pcm_read_seek(s, stream_index, timestamp, flags);
if (!oc->encrypted)
return err;