| Message ID | 20230212005240.3167630-1-marth64@proxyid.net |
|---|---|
| State | New |
| Headers | show |
| Series | [FFmpeg-devel] ffprobe/eac3/mlp/dca: add detection of spatial audio extensions | expand |
| Context | Check | Description |
|---|---|---|
| andriy/make_x86 | success | Make finished |
| andriy/make_fate_x86 | success | Make fate finished |
On Sun, Feb 12, 2023 at 1:53 AM Marth64 <marth64@proxyid.net> wrote: > diff --git a/libavcodec/dca_syncwords.h b/libavcodec/dca_syncwords.h > index 4d2cd5f56d..200702f89e 100644 > --- a/libavcodec/dca_syncwords.h > +++ b/libavcodec/dca_syncwords.h > @@ -33,4 +33,7 @@ > #define DCA_SYNCWORD_SUBSTREAM_CORE 0x02B09261U > #define DCA_SYNCWORD_REV1AUX 0x9A1105A0U > > +#define DCA_SYNCWORD_XLL_X 0x00020008U > +#define DCA_SYNCWORD_XLL_X_IMAX 0x00F14000U > + > #endif /* AVCODEC_DCA_SYNCWORDS_H */ > diff --git a/libavcodec/dca_xll.c b/libavcodec/dca_xll.c > index fe2c766d98..efbbae67f8 100644 > --- a/libavcodec/dca_xll.c > +++ b/libavcodec/dca_xll.c > @@ -19,6 +19,7 @@ > */ > > #include "libavutil/channel_layout.h" > +#include "avcodec.h" > #include "dcadec.h" > #include "dcadata.h" > #include "dcamath.h" > @@ -1043,6 +1044,7 @@ static int parse_band_data(DCAXllDecoder *s) > static int parse_frame(DCAXllDecoder *s, const uint8_t *data, int size, DCAExssAsset *asset) > { > int ret; > + int extradata_peek_pos; > > if ((ret = init_get_bits8(&s->gb, data, size)) < 0) > return ret; > @@ -1054,10 +1056,23 @@ static int parse_frame(DCAXllDecoder *s, const uint8_t *data, int size, DCAExssA > return ret; > if ((ret = parse_band_data(s)) < 0) > return ret; > + > + extradata_peek_pos = (get_bits_count(&s->gb) + 31) & ~31; > + if (s->frame_size * 8 > extradata_peek_pos) { > + unsigned int extradata_syncword = show_bits_long(&s->gb, 32); > + > + if (extradata_syncword == DCA_SYNCWORD_XLL_X) { > + s->x_syncword_present = 1; > + } else if (extradata_syncword == DCA_SYNCWORD_XLL_X_IMAX) { > + s->x_imax_syncword_present = 1; > + } > + } > + I was testing this, and the DTS detections were not very reliable for me. This is what I came up with instead: #define DCA_SYNCWORD_XLL_X 0x02000850U #define DCA_SYNCWORD_XLL_X_IMAX 0xF14000D0U if (s->frame_size * 8 > FFALIGN(get_bits_count(&s->gb), 32)) { unsigned int extradata_syncword; // align to dword skip_bits_long(&s->gb, -get_bits_count(&s->gb) & 31); // get sync code extradata_syncword = show_bits_long(&s->gb, 32); if (extradata_syncword == DCA_SYNCWORD_XLL_X) { s->x_syncword_present = 1; } else if ((extradata_syncword >> 1) == (DCA_SYNCWORD_XLL_X_IMAX >> 1)) { s->x_imax_syncword_present = 1; } } I don't have many DTS:X discs, but this worked on them, the old code did not. Aligning to DWORD for a new section is a typical DTS thing to do, which then also resulted in the syncwords to shift a bit, and actually include more digits. The IMAX case is a bit weird, there seems to be an extra bit in there thats not stable, so shifting it out improves the detection (or it could be masked out, but same difference). - Hendrik
Hi Hendrik, Thank you for taking the time to help me test this. I will verify this as well on my corpus of 15 or so titles and commit/sign if it passes there too. Will update within 24. Respectfully, Marth64 On Thu, Feb 16, 2023 at 06:37 Hendrik Leppkes <h.leppkes@gmail.com> wrote: > On Sun, Feb 12, 2023 at 1:53 AM Marth64 <marth64@proxyid.net> wrote: > > diff --git a/libavcodec/dca_syncwords.h b/libavcodec/dca_syncwords.h > > index 4d2cd5f56d..200702f89e 100644 > > --- a/libavcodec/dca_syncwords.h > > +++ b/libavcodec/dca_syncwords.h > > @@ -33,4 +33,7 @@ > > #define DCA_SYNCWORD_SUBSTREAM_CORE 0x02B09261U > > #define DCA_SYNCWORD_REV1AUX 0x9A1105A0U > > > > +#define DCA_SYNCWORD_XLL_X 0x00020008U > > +#define DCA_SYNCWORD_XLL_X_IMAX 0x00F14000U > > + > > #endif /* AVCODEC_DCA_SYNCWORDS_H */ > > diff --git a/libavcodec/dca_xll.c b/libavcodec/dca_xll.c > > index fe2c766d98..efbbae67f8 100644 > > --- a/libavcodec/dca_xll.c > > +++ b/libavcodec/dca_xll.c > > @@ -19,6 +19,7 @@ > > */ > > > > #include "libavutil/channel_layout.h" > > +#include "avcodec.h" > > #include "dcadec.h" > > #include "dcadata.h" > > #include "dcamath.h" > > @@ -1043,6 +1044,7 @@ static int parse_band_data(DCAXllDecoder *s) > > static int parse_frame(DCAXllDecoder *s, const uint8_t *data, int size, > DCAExssAsset *asset) > > { > > int ret; > > + int extradata_peek_pos; > > > > if ((ret = init_get_bits8(&s->gb, data, size)) < 0) > > return ret; > > @@ -1054,10 +1056,23 @@ static int parse_frame(DCAXllDecoder *s, const > uint8_t *data, int size, DCAExssA > > return ret; > > if ((ret = parse_band_data(s)) < 0) > > return ret; > > + > > + extradata_peek_pos = (get_bits_count(&s->gb) + 31) & ~31; > > + if (s->frame_size * 8 > extradata_peek_pos) { > > + unsigned int extradata_syncword = show_bits_long(&s->gb, 32); > > + > > + if (extradata_syncword == DCA_SYNCWORD_XLL_X) { > > + s->x_syncword_present = 1; > > + } else if (extradata_syncword == DCA_SYNCWORD_XLL_X_IMAX) { > > + s->x_imax_syncword_present = 1; > > + } > > + } > > + > > > I was testing this, and the DTS detections were not very reliable for > me. This is what I came up with instead: > > #define DCA_SYNCWORD_XLL_X 0x02000850U > #define DCA_SYNCWORD_XLL_X_IMAX 0xF14000D0U > > > if (s->frame_size * 8 > FFALIGN(get_bits_count(&s->gb), 32)) { > unsigned int extradata_syncword; > > // align to dword > skip_bits_long(&s->gb, -get_bits_count(&s->gb) & 31); > > // get sync code > extradata_syncword = show_bits_long(&s->gb, 32); > > if (extradata_syncword == DCA_SYNCWORD_XLL_X) { > s->x_syncword_present = 1; > } else if ((extradata_syncword >> 1) == > (DCA_SYNCWORD_XLL_X_IMAX >> 1)) { > s->x_imax_syncword_present = 1; > } > } > > I don't have many DTS:X discs, but this worked on them, the old code did > not. > Aligning to DWORD for a new section is a typical DTS thing to do, > which then also resulted in the syncwords to shift a bit, and actually > include more digits. > > The IMAX case is a bit weird, there seems to be an extra bit in there > thats not stable, so shifting it out improves the detection (or it > could be masked out, but same difference). > > - Hendrik > _______________________________________________ > ffmpeg-devel mailing list > ffmpeg-devel@ffmpeg.org > https://ffmpeg.org/mailman/listinfo/ffmpeg-devel > > To unsubscribe, visit link above, or email > ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe". >
diff --git a/libavcodec/ac3dec.c b/libavcodec/ac3dec.c index 0b120e6140..d7070645e6 100644 --- a/libavcodec/ac3dec.c +++ b/libavcodec/ac3dec.c @@ -43,6 +43,7 @@ #include "ac3dec.h" #include "ac3dec_data.h" #include "ac3defs.h" +#include "avcodec.h" #include "decode.h" #include "kbdwin.h" @@ -1714,6 +1715,9 @@ skip: if (!err) { avctx->sample_rate = s->sample_rate; avctx->bit_rate = s->bit_rate + s->prev_bit_rate; + + if (s->eac3_extension_type_a == 1) + avctx->profile = FF_PROFILE_EAC3_DDP_ATMOS; } if (!avctx->sample_rate) { diff --git a/libavcodec/ac3dec.h b/libavcodec/ac3dec.h index 138b462abb..0829f4b40d 100644 --- a/libavcodec/ac3dec.h +++ b/libavcodec/ac3dec.h @@ -102,6 +102,7 @@ typedef struct AC3DecodeContext { int eac3; ///< indicates if current frame is E-AC-3 int eac3_frame_dependent_found; ///< bitstream has E-AC-3 dependent frame(s) int eac3_subsbtreamid_found; ///< bitstream has E-AC-3 additional substream(s) + int eac3_extension_type_a; ///< bitstream has E-AC-3 extension type A enabled frame(s) int dolby_surround_mode; ///< dolby surround mode (dsurmod) int dolby_surround_ex_mode; ///< dolby surround ex mode (dsurexmod) int dolby_headphone_mode; ///< dolby headphone mode (dheadphonmod) diff --git a/libavcodec/avcodec.h b/libavcodec/avcodec.h index 755e543fac..2d3a7a4625 100644 --- a/libavcodec/avcodec.h +++ b/libavcodec/avcodec.h @@ -1616,12 +1616,18 @@ typedef struct AVCodecContext { #define FF_PROFILE_DNXHR_HQX 4 #define FF_PROFILE_DNXHR_444 5 -#define FF_PROFILE_DTS 20 -#define FF_PROFILE_DTS_ES 30 -#define FF_PROFILE_DTS_96_24 40 -#define FF_PROFILE_DTS_HD_HRA 50 -#define FF_PROFILE_DTS_HD_MA 60 -#define FF_PROFILE_DTS_EXPRESS 70 +#define FF_PROFILE_DTS 20 +#define FF_PROFILE_DTS_ES 30 +#define FF_PROFILE_DTS_96_24 40 +#define FF_PROFILE_DTS_HD_HRA 50 +#define FF_PROFILE_DTS_HD_MA 60 +#define FF_PROFILE_DTS_HD_MA_X 61 +#define FF_PROFILE_DTS_HD_MA_X_IMAX 62 +#define FF_PROFILE_DTS_EXPRESS 70 + +#define FF_PROFILE_EAC3_DDP_ATMOS 30 + +#define FF_PROFILE_TRUEHD_ATMOS 30 #define FF_PROFILE_MPEG2_422 0 #define FF_PROFILE_MPEG2_HIGH 1 diff --git a/libavcodec/codec_desc.c b/libavcodec/codec_desc.c index 57d0f98211..f33bbcd124 100644 --- a/libavcodec/codec_desc.c +++ b/libavcodec/codec_desc.c @@ -2931,6 +2931,7 @@ static const AVCodecDescriptor codec_descriptors[] = { .name = "eac3", .long_name = NULL_IF_CONFIG_SMALL("ATSC A/52B (AC-3, E-AC-3)"), .props = AV_CODEC_PROP_INTRA_ONLY | AV_CODEC_PROP_LOSSY, + .profiles = NULL_IF_CONFIG_SMALL(ff_eac3_profiles), }, { .id = AV_CODEC_ID_SIPR, @@ -2959,6 +2960,7 @@ static const AVCodecDescriptor codec_descriptors[] = { .name = "truehd", .long_name = NULL_IF_CONFIG_SMALL("TrueHD"), .props = AV_CODEC_PROP_LOSSLESS, + .profiles = NULL_IF_CONFIG_SMALL(ff_truehd_profiles), }, { .id = AV_CODEC_ID_MP4ALS, diff --git a/libavcodec/dca_syncwords.h b/libavcodec/dca_syncwords.h index 4d2cd5f56d..200702f89e 100644 --- a/libavcodec/dca_syncwords.h +++ b/libavcodec/dca_syncwords.h @@ -33,4 +33,7 @@ #define DCA_SYNCWORD_SUBSTREAM_CORE 0x02B09261U #define DCA_SYNCWORD_REV1AUX 0x9A1105A0U +#define DCA_SYNCWORD_XLL_X 0x00020008U +#define DCA_SYNCWORD_XLL_X_IMAX 0x00F14000U + #endif /* AVCODEC_DCA_SYNCWORDS_H */ diff --git a/libavcodec/dca_xll.c b/libavcodec/dca_xll.c index fe2c766d98..efbbae67f8 100644 --- a/libavcodec/dca_xll.c +++ b/libavcodec/dca_xll.c @@ -19,6 +19,7 @@ */ #include "libavutil/channel_layout.h" +#include "avcodec.h" #include "dcadec.h" #include "dcadata.h" #include "dcamath.h" @@ -1043,6 +1044,7 @@ static int parse_band_data(DCAXllDecoder *s) static int parse_frame(DCAXllDecoder *s, const uint8_t *data, int size, DCAExssAsset *asset) { int ret; + int extradata_peek_pos; if ((ret = init_get_bits8(&s->gb, data, size)) < 0) return ret; @@ -1054,10 +1056,23 @@ static int parse_frame(DCAXllDecoder *s, const uint8_t *data, int size, DCAExssA return ret; if ((ret = parse_band_data(s)) < 0) return ret; + + extradata_peek_pos = (get_bits_count(&s->gb) + 31) & ~31; + if (s->frame_size * 8 > extradata_peek_pos) { + unsigned int extradata_syncword = show_bits_long(&s->gb, 32); + + if (extradata_syncword == DCA_SYNCWORD_XLL_X) { + s->x_syncword_present = 1; + } else if (extradata_syncword == DCA_SYNCWORD_XLL_X_IMAX) { + s->x_imax_syncword_present = 1; + } + } + if (ff_dca_seek_bits(&s->gb, s->frame_size * 8)) { av_log(s->avctx, AV_LOG_ERROR, "Read past end of XLL frame\n"); return AVERROR_INVALIDDATA; } + return ret; } @@ -1428,8 +1443,15 @@ int ff_dca_xll_filter_frame(DCAXllDecoder *s, AVFrame *frame) return AVERROR(EINVAL); } + if (s->x_imax_syncword_present) { + avctx->profile = FF_PROFILE_DTS_HD_MA_X_IMAX; + } else if (s->x_syncword_present) { + avctx->profile = FF_PROFILE_DTS_HD_MA_X; + } else { + avctx->profile = FF_PROFILE_DTS_HD_MA; + } + avctx->bits_per_raw_sample = p->storage_bit_res; - avctx->profile = FF_PROFILE_DTS_HD_MA; avctx->bit_rate = 0; frame->nb_samples = nsamples = s->nframesamples << (s->nfreqbands - 1); diff --git a/libavcodec/dca_xll.h b/libavcodec/dca_xll.h index d7c1a13ec8..a22bbb8d77 100644 --- a/libavcodec/dca_xll.h +++ b/libavcodec/dca_xll.h @@ -135,6 +135,9 @@ typedef struct DCAXllDecoder { DCADSPContext *dcadsp; + int x_syncword_present; ///< Syncword for extension data at end of frame (DTS:X) is present + int x_imax_syncword_present; ///< Syncword for extension data at end of frame (DTS:X IMAX) is present + int output_mask; int32_t *output_samples[DCA_SPEAKER_COUNT]; } DCAXllDecoder; diff --git a/libavcodec/eac3dec.c b/libavcodec/eac3dec.c index deca51dd3d..5c71751a0c 100644 --- a/libavcodec/eac3dec.c +++ b/libavcodec/eac3dec.c @@ -464,7 +464,16 @@ static int ff_eac3_parse_header(AC3DecodeContext *s) if (get_bits1(gbc)) { int addbsil = get_bits(gbc, 6); for (i = 0; i < addbsil + 1; i++) { - skip_bits(gbc, 8); // skip additional bit stream info + if (i == 0) { + /* In this 8 bit chunk, the LSB is equal to flag_ec3_extension_type_a + which can be used to detect Atmos presence */ + skip_bits(gbc, 7); + if (get_bits1(gbc)) { + s->eac3_extension_type_a = 1; + } + } else { + skip_bits(gbc, 8); // skip additional bit stream info + } } } diff --git a/libavcodec/mlpdec.c b/libavcodec/mlpdec.c index 0ee1f0982c..e95357e35a 100644 --- a/libavcodec/mlpdec.c +++ b/libavcodec/mlpdec.c @@ -28,20 +28,21 @@ #include <stdint.h> -#include "avcodec.h" #include "libavutil/internal.h" #include "libavutil/intreadwrite.h" #include "libavutil/channel_layout.h" #include "libavutil/mem_internal.h" #include "libavutil/thread.h" #include "libavutil/opt.h" +#include "avcodec.h" #include "codec_internal.h" +#include "config.h" #include "decode.h" #include "get_bits.h" #include "mlp_parse.h" #include "mlpdsp.h" #include "mlp.h" -#include "config.h" +#include "profiles.h" /** number of bits used for VLC lookup - longest Huffman code is 9 */ #if ARCH_ARM @@ -392,6 +393,15 @@ static int read_major_sync(MLPDecodeContext *m, GetBitContext *gb) m->num_substreams = mh.num_substreams; m->substream_info = mh.substream_info; + /* If there is a 4th substream and the MSB of substream_info is set, + * there is a 16-channel spatial presentation (Atmos in TrueHD). + */ + if (m->avctx->codec_id == AV_CODEC_ID_TRUEHD + && m->num_substreams == 4 + && m->substream_info >> 7 == 1) { + m->avctx->profile = FF_PROFILE_TRUEHD_ATMOS; + } + /* limit to decoding 3 substreams, as the 4th is used by Dolby Atmos for non-audio data */ m->max_decoded_substream = FFMIN(m->num_substreams - 1, 2); @@ -1452,5 +1462,6 @@ const FFCodec ff_truehd_decoder = { FF_CODEC_DECODE_CB(read_access_unit), .flush = mlp_decode_flush, .p.capabilities = AV_CODEC_CAP_DR1 | AV_CODEC_CAP_CHANNEL_CONF, + .p.profiles = NULL_IF_CONFIG_SMALL(ff_truehd_profiles), }; #endif /* CONFIG_TRUEHD_DECODER */ diff --git a/libavcodec/profiles.c b/libavcodec/profiles.c index 7af7fbeb13..52066185b1 100644 --- a/libavcodec/profiles.c +++ b/libavcodec/profiles.c @@ -36,15 +36,27 @@ const AVProfile ff_aac_profiles[] = { }; const AVProfile ff_dca_profiles[] = { - { FF_PROFILE_DTS, "DTS" }, - { FF_PROFILE_DTS_ES, "DTS-ES" }, - { FF_PROFILE_DTS_96_24, "DTS 96/24" }, - { FF_PROFILE_DTS_HD_HRA, "DTS-HD HRA" }, - { FF_PROFILE_DTS_HD_MA, "DTS-HD MA" }, - { FF_PROFILE_DTS_EXPRESS, "DTS Express" }, + { FF_PROFILE_DTS, "DTS" }, + { FF_PROFILE_DTS_ES, "DTS-ES" }, + { FF_PROFILE_DTS_96_24, "DTS 96/24" }, + { FF_PROFILE_DTS_HD_HRA, "DTS-HD HRA" }, + { FF_PROFILE_DTS_HD_MA, "DTS-HD MA" }, + { FF_PROFILE_DTS_HD_MA_X, "DTS-HD MA + DTS:X" }, + { FF_PROFILE_DTS_HD_MA_X_IMAX, "DTS-HD MA + DTS:X IMAX" }, + { FF_PROFILE_DTS_EXPRESS, "DTS Express" }, { FF_PROFILE_UNKNOWN }, }; +const AVProfile ff_eac3_profiles[] = { + { FF_PROFILE_EAC3_DDP_ATMOS, "Dolby Digital Plus + Dolby Atmos"}, + { FF_PROFILE_UNKNOWN }, +}; + +const AVProfile ff_truehd_profiles[] = { + { FF_PROFILE_TRUEHD_ATMOS, "Dolby TrueHD + Dolby Atmos"}, + { FF_PROFILE_UNKNOWN }, +}; + const AVProfile ff_dnxhd_profiles[] = { { FF_PROFILE_DNXHD, "DNXHD"}, { FF_PROFILE_DNXHR_LB, "DNXHR LB"}, diff --git a/libavcodec/profiles.h b/libavcodec/profiles.h index 41a19aa9ad..1d523992fc 100644 --- a/libavcodec/profiles.h +++ b/libavcodec/profiles.h @@ -58,6 +58,8 @@ extern const AVProfile ff_aac_profiles[]; extern const AVProfile ff_dca_profiles[]; +extern const AVProfile ff_eac3_profiles[]; +extern const AVProfile ff_truehd_profiles[]; extern const AVProfile ff_dnxhd_profiles[]; extern const AVProfile ff_h264_profiles[]; extern const AVProfile ff_hevc_profiles[];
Signed-off-by: Marth64 <marth64@proxyid.net> --- - Signed the commit libavcodec/ac3dec.c | 4 ++++ libavcodec/ac3dec.h | 1 + libavcodec/avcodec.h | 18 ++++++++++++------ libavcodec/codec_desc.c | 2 ++ libavcodec/dca_syncwords.h | 3 +++ libavcodec/dca_xll.c | 24 +++++++++++++++++++++++- libavcodec/dca_xll.h | 3 +++ libavcodec/eac3dec.c | 11 ++++++++++- libavcodec/mlpdec.c | 15 +++++++++++++-- libavcodec/profiles.c | 24 ++++++++++++++++++------ libavcodec/profiles.h | 2 ++ 11 files changed, 91 insertions(+), 16 deletions(-)