FFmpeg
iamf_parse.c
Go to the documentation of this file.
1 /*
2  * Immersive Audio Model and Formats parsing
3  * Copyright (c) 2023 James Almer <jamrial@gmail.com>
4  *
5  * This file is part of FFmpeg.
6  *
7  * FFmpeg is free software; you can redistribute it and/or
8  * modify it under the terms of the GNU Lesser General Public
9  * License as published by the Free Software Foundation; either
10  * version 2.1 of the License, or (at your option) any later version.
11  *
12  * FFmpeg is distributed in the hope that it will be useful,
13  * but WITHOUT ANY WARRANTY; without even the implied warranty of
14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
15  * Lesser General Public License for more details.
16  *
17  * You should have received a copy of the GNU Lesser General Public
18  * License along with FFmpeg; if not, write to the Free Software
19  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
20  */
21 
22 #include "libavutil/avassert.h"
23 #include "libavutil/iamf.h"
24 #include "libavutil/intreadwrite.h"
25 #include "libavutil/log.h"
26 #include "libavutil/mem.h"
27 #include "libavcodec/get_bits.h"
28 #include "libavcodec/flac.h"
29 #include "libavcodec/leb.h"
30 #include "libavcodec/mpeg4audio.h"
31 #include "libavcodec/put_bits.h"
32 #include "avio_internal.h"
33 #include "iamf_parse.h"
34 #include "isom.h"
35 
36 static int opus_decoder_config(IAMFCodecConfig *codec_config,
37  AVIOContext *pb, int len)
38 {
39  int ret, left = len - avio_tell(pb);
40 
41  if (left < 11 || codec_config->audio_roll_distance >= 0)
42  return AVERROR_INVALIDDATA;
43 
44  codec_config->extradata = av_malloc(left + 8);
45  if (!codec_config->extradata)
46  return AVERROR(ENOMEM);
47 
48  AV_WB32A(codec_config->extradata, MKBETAG('O','p','u','s'));
49  AV_WB32A(codec_config->extradata + 4, MKBETAG('H','e','a','d'));
50  ret = ffio_read_size(pb, codec_config->extradata + 8, left);
51  if (ret < 0)
52  return ret;
53 
54  codec_config->extradata_size = left + 8;
55  codec_config->sample_rate = 48000;
56 
57  return 0;
58 }
59 
60 static int aac_decoder_config(IAMFCodecConfig *codec_config,
61  AVIOContext *pb, int len, void *logctx)
62 {
63  MPEG4AudioConfig cfg = { 0 };
64  int object_type_id, codec_id, stream_type;
65  int ret, tag, left;
66 
67  if (codec_config->audio_roll_distance >= 0)
68  return AVERROR_INVALIDDATA;
69 
70  ff_mp4_read_descr(logctx, pb, &tag);
72  return AVERROR_INVALIDDATA;
73 
74  object_type_id = avio_r8(pb);
75  if (object_type_id != 0x40)
76  return AVERROR_INVALIDDATA;
77 
78  stream_type = avio_r8(pb);
79  if (((stream_type >> 2) != 5) || ((stream_type >> 1) & 1))
80  return AVERROR_INVALIDDATA;
81 
82  avio_skip(pb, 3); // buffer size db
83  avio_skip(pb, 4); // rc_max_rate
84  avio_skip(pb, 4); // avg bitrate
85 
86  codec_id = ff_codec_get_id(ff_mp4_obj_type, object_type_id);
87  if (codec_id && codec_id != codec_config->codec_id)
88  return AVERROR_INVALIDDATA;
89 
90  left = ff_mp4_read_descr(logctx, pb, &tag);
91  if (tag != MP4DecSpecificDescrTag ||
92  !left || left > (len - avio_tell(pb)))
93  return AVERROR_INVALIDDATA;
94 
95  // We pad extradata here because avpriv_mpeg4audio_get_config2() needs it.
96  codec_config->extradata = av_malloc((size_t)left + AV_INPUT_BUFFER_PADDING_SIZE);
97  if (!codec_config->extradata)
98  return AVERROR(ENOMEM);
99 
100  ret = ffio_read_size(pb, codec_config->extradata, left);
101  if (ret < 0)
102  return ret;
103  codec_config->extradata_size = left;
104  memset(codec_config->extradata + codec_config->extradata_size, 0,
106 
107  ret = avpriv_mpeg4audio_get_config2(&cfg, codec_config->extradata,
108  codec_config->extradata_size, 1, logctx);
109  if (ret < 0)
110  return ret;
111 
112  codec_config->sample_rate = cfg.sample_rate;
113 
114  return 0;
115 }
116 
117 static int flac_decoder_config(IAMFCodecConfig *codec_config,
118  AVIOContext *pb, int len)
119 {
120  int ret, left;
121 
122  if (codec_config->audio_roll_distance)
123  return AVERROR_INVALIDDATA;
124 
125  avio_skip(pb, 4); // METADATA_BLOCK_HEADER
126 
127  left = len - avio_tell(pb);
129  return AVERROR_INVALIDDATA;
130 
131  codec_config->extradata = av_malloc(left);
132  if (!codec_config->extradata)
133  return AVERROR(ENOMEM);
134 
135  ret = ffio_read_size(pb, codec_config->extradata, left);
136  if (ret < 0)
137  return ret;
138 
139  codec_config->extradata_size = left;
140  codec_config->sample_rate = AV_RB24(codec_config->extradata + 10) >> 4;
141 
142  return 0;
143 }
144 
145 static int ipcm_decoder_config(IAMFCodecConfig *codec_config,
146  AVIOContext *pb, int len)
147 {
148  static const enum AVCodecID sample_fmt[2][3] = {
151  };
152  int sample_format = avio_r8(pb); // 0 = BE, 1 = LE
153  int sample_size = (avio_r8(pb) / 8 - 2); // 16, 24, 32
154  if (sample_format > 1 || sample_size > 2U || codec_config->audio_roll_distance)
155  return AVERROR_INVALIDDATA;
156 
157  codec_config->codec_id = sample_fmt[sample_format][sample_size];
158  codec_config->sample_rate = avio_rb32(pb);
159 
160  if (len - avio_tell(pb))
161  return AVERROR_INVALIDDATA;
162 
163  return 0;
164 }
165 
166 static int codec_config_obu(void *s, IAMFContext *c, AVIOContext *pb, int len)
167 {
168  IAMFCodecConfig **tmp, *codec_config = NULL;
169  FFIOContext b;
170  AVIOContext *pbc;
171  uint8_t *buf;
172  enum AVCodecID avcodec_id;
173  unsigned codec_config_id, nb_samples, codec_id;
174  int16_t audio_roll_distance;
175  int ret;
176 
177  buf = av_malloc(len);
178  if (!buf)
179  return AVERROR(ENOMEM);
180 
181  ret = ffio_read_size(pb, buf, len);
182  if (ret < 0)
183  goto fail;
184 
185  ffio_init_context(&b, buf, len, 0, NULL, NULL, NULL, NULL);
186  pbc = &b.pub;
187 
188  codec_config_id = ffio_read_leb(pbc);
189  codec_id = avio_rb32(pbc);
190  nb_samples = ffio_read_leb(pbc);
191  audio_roll_distance = avio_rb16(pbc);
192 
193  switch(codec_id) {
194  case MKBETAG('O','p','u','s'):
195  avcodec_id = AV_CODEC_ID_OPUS;
196  break;
197  case MKBETAG('m','p','4','a'):
198  avcodec_id = AV_CODEC_ID_AAC;
199  break;
200  case MKBETAG('f','L','a','C'):
201  avcodec_id = AV_CODEC_ID_FLAC;
202  break;
203  default:
204  avcodec_id = AV_CODEC_ID_NONE;
205  break;
206  }
207 
208  for (int i = 0; i < c->nb_codec_configs; i++)
209  if (c->codec_configs[i]->codec_config_id == codec_config_id) {
211  goto fail;
212  }
213 
214  tmp = av_realloc_array(c->codec_configs, c->nb_codec_configs + 1, sizeof(*c->codec_configs));
215  if (!tmp) {
216  ret = AVERROR(ENOMEM);
217  goto fail;
218  }
219  c->codec_configs = tmp;
220 
221  codec_config = av_mallocz(sizeof(*codec_config));
222  if (!codec_config) {
223  ret = AVERROR(ENOMEM);
224  goto fail;
225  }
226 
227  codec_config->codec_config_id = codec_config_id;
228  codec_config->codec_id = avcodec_id;
229  codec_config->nb_samples = nb_samples;
230  codec_config->audio_roll_distance = audio_roll_distance;
231 
232  switch(codec_id) {
233  case MKBETAG('O','p','u','s'):
234  ret = opus_decoder_config(codec_config, pbc, len);
235  break;
236  case MKBETAG('m','p','4','a'):
237  ret = aac_decoder_config(codec_config, pbc, len, s);
238  break;
239  case MKBETAG('f','L','a','C'):
240  ret = flac_decoder_config(codec_config, pbc, len);
241  break;
242  case MKBETAG('i','p','c','m'):
243  ret = ipcm_decoder_config(codec_config, pbc, len);
244  break;
245  default:
246  break;
247  }
248  if (ret < 0)
249  goto fail;
250 
251  if ((codec_config->nb_samples > INT_MAX) || codec_config->nb_samples <= 0 ||
252  (-codec_config->audio_roll_distance > INT_MAX / codec_config->nb_samples)) {
254  goto fail;
255  }
256 
257  c->codec_configs[c->nb_codec_configs++] = codec_config;
258 
259  len -= avio_tell(pbc);
260  if (len)
261  av_log(s, AV_LOG_WARNING, "Underread in codec_config_obu. %d bytes left at the end\n", len);
262 
263  ret = 0;
264 fail:
265  av_free(buf);
266  if (ret < 0) {
267  if (codec_config)
268  av_free(codec_config->extradata);
269  av_free(codec_config);
270  }
271  return ret;
272 }
273 
274 static int update_extradata(AVCodecParameters *codecpar)
275 {
276  GetBitContext gb;
277  PutBitContext pb;
278  int ret;
279 
280  switch(codecpar->codec_id) {
281  case AV_CODEC_ID_OPUS:
282  AV_WB8(codecpar->extradata + 9, codecpar->ch_layout.nb_channels);
283  AV_WL16A(codecpar->extradata + 10, AV_RB16A(codecpar->extradata + 10)); // Byte swap pre-skip
284  AV_WL32A(codecpar->extradata + 12, AV_RB32A(codecpar->extradata + 12)); // Byte swap sample rate
285  AV_WL16A(codecpar->extradata + 16, AV_RB16A(codecpar->extradata + 16)); // Byte swap Output Gain
286  break;
287  case AV_CODEC_ID_AAC: {
288  uint8_t buf[5];
289 
290  init_put_bits(&pb, buf, sizeof(buf));
291  ret = init_get_bits8(&gb, codecpar->extradata, codecpar->extradata_size);
292  if (ret < 0)
293  return ret;
294 
295  ret = get_bits(&gb, 5);
296  put_bits(&pb, 5, ret);
297  if (ret == AOT_ESCAPE) // violates section 3.11.2, but better check for it
298  put_bits(&pb, 6, get_bits(&gb, 6));
299  ret = get_bits(&gb, 4);
300  put_bits(&pb, 4, ret);
301  if (ret == 0x0f)
302  put_bits(&pb, 24, get_bits(&gb, 24));
303 
304  skip_bits(&gb, 4);
305  put_bits(&pb, 4, codecpar->ch_layout.nb_channels); // set channel config
306  ret = put_bits_left(&pb);
307  put_bits(&pb, ret, get_bits_long(&gb, ret));
308  flush_put_bits(&pb);
309 
310  memcpy(codecpar->extradata, buf, put_bytes_output(&pb));
311  break;
312  }
313  case AV_CODEC_ID_FLAC: {
314  uint8_t buf[13];
315 
316  init_put_bits(&pb, buf, sizeof(buf));
317  ret = init_get_bits8(&gb, codecpar->extradata, codecpar->extradata_size);
318  if (ret < 0)
319  return ret;
320 
321  put_bits32(&pb, get_bits_long(&gb, 32)); // min/max blocksize
322  put_bits64(&pb, 48, get_bits64(&gb, 48)); // min/max framesize
323  put_bits(&pb, 20, get_bits(&gb, 20)); // samplerate
324  skip_bits(&gb, 3);
325  put_bits(&pb, 3, codecpar->ch_layout.nb_channels - 1);
326  ret = put_bits_left(&pb);
327  put_bits(&pb, ret, get_bits(&gb, ret));
328  flush_put_bits(&pb);
329 
330  memcpy(codecpar->extradata, buf, sizeof(buf));
331  break;
332  }
333  }
334 
335  return 0;
336 }
337 
339  IAMFAudioElement *audio_element,
340  const IAMFCodecConfig *codec_config)
341 {
342  int nb_layers, k = 0;
343 
344  nb_layers = avio_r8(pb) >> 5; // get_bits(&gb, 3);
345  // skip_bits(&gb, 5); //reserved
346 
347  if (nb_layers > 6 || nb_layers == 0)
348  return AVERROR_INVALIDDATA;
349 
350  audio_element->layers = av_calloc(nb_layers, sizeof(*audio_element->layers));
351  if (!audio_element->layers)
352  return AVERROR(ENOMEM);
353 
354  audio_element->nb_layers = nb_layers;
355  for (int i = 0; i < nb_layers; i++) {
356  AVIAMFLayer *layer;
357  int loudspeaker_layout, output_gain_is_present_flag;
358  int substream_count, coupled_substream_count;
359  int ret, byte = avio_r8(pb);
360 
361  layer = av_iamf_audio_element_add_layer(audio_element->element);
362  if (!layer)
363  return AVERROR(ENOMEM);
364 
365  loudspeaker_layout = byte >> 4; // get_bits(&gb, 4);
366  output_gain_is_present_flag = (byte >> 3) & 1; //get_bits1(&gb);
367  if ((byte >> 2) & 1)
368  layer->flags |= AV_IAMF_LAYER_FLAG_RECON_GAIN;
369  substream_count = avio_r8(pb);
370  coupled_substream_count = avio_r8(pb);
371 
372  if (substream_count + k > audio_element->nb_substreams)
373  return AVERROR_INVALIDDATA;
374 
375  audio_element->layers[i].substream_count = substream_count;
376  audio_element->layers[i].coupled_substream_count = coupled_substream_count;
377  if (output_gain_is_present_flag) {
378  layer->output_gain_flags = avio_r8(pb) >> 2; // get_bits(&gb, 6);
379  layer->output_gain = av_make_q(sign_extend(avio_rb16(pb), 16), 1 << 8);
380  }
381 
382  if (loudspeaker_layout < 10)
383  av_channel_layout_copy(&layer->ch_layout, &ff_iamf_scalable_ch_layouts[loudspeaker_layout]);
384  else
386  .nb_channels = substream_count +
387  coupled_substream_count };
388 
389  for (int j = 0; j < substream_count; j++) {
390  IAMFSubStream *substream = &audio_element->substreams[k++];
391 
392  substream->codecpar->ch_layout = coupled_substream_count-- > 0 ? (AVChannelLayout)AV_CHANNEL_LAYOUT_STEREO :
394 
395  ret = update_extradata(substream->codecpar);
396  if (ret < 0)
397  return ret;
398  }
399 
400  }
401 
402  return 0;
403 }
404 
405 static int ambisonics_config(void *s, AVIOContext *pb,
406  IAMFAudioElement *audio_element,
407  const IAMFCodecConfig *codec_config)
408 {
409  AVIAMFLayer *layer;
410  unsigned ambisonics_mode;
411  int output_channel_count, substream_count, order;
412  int ret;
413 
414  ambisonics_mode = ffio_read_leb(pb);
415  if (ambisonics_mode > 1)
416  return AVERROR_INVALIDDATA;
417 
418  output_channel_count = avio_r8(pb); // C
419  substream_count = avio_r8(pb); // N
420  if (audio_element->nb_substreams != substream_count)
421  return AVERROR_INVALIDDATA;
422 
423  order = floor(sqrt(output_channel_count - 1));
424  /* incomplete order - some harmonics are missing */
425  if ((order + 1) * (order + 1) != output_channel_count)
426  return AVERROR_INVALIDDATA;
427 
428  audio_element->layers = av_mallocz(sizeof(*audio_element->layers));
429  if (!audio_element->layers)
430  return AVERROR(ENOMEM);
431 
432  audio_element->nb_layers = 1;
433  audio_element->layers->substream_count = substream_count;
434 
435  layer = av_iamf_audio_element_add_layer(audio_element->element);
436  if (!layer)
437  return AVERROR(ENOMEM);
438 
439  layer->ambisonics_mode = ambisonics_mode;
440  if (ambisonics_mode == 0) {
441  for (int i = 0; i < substream_count; i++) {
442  IAMFSubStream *substream = &audio_element->substreams[i];
443 
445 
446  ret = update_extradata(substream->codecpar);
447  if (ret < 0)
448  return ret;
449  }
450 
452  layer->ch_layout.nb_channels = output_channel_count;
453  layer->ch_layout.u.map = av_calloc(output_channel_count, sizeof(*layer->ch_layout.u.map));
454  if (!layer->ch_layout.u.map)
455  return AVERROR(ENOMEM);
456 
457  for (int i = 0; i < output_channel_count; i++)
458  layer->ch_layout.u.map[i].id = avio_r8(pb) + AV_CHAN_AMBISONIC_BASE;
459  } else {
460  int coupled_substream_count = avio_r8(pb); // M
461  int nb_demixing_matrix = substream_count + coupled_substream_count;
462  int demixing_matrix_size = nb_demixing_matrix * output_channel_count;
463 
464  audio_element->layers->coupled_substream_count = coupled_substream_count;
465 
466  layer->ch_layout = (AVChannelLayout){ .order = AV_CHANNEL_ORDER_AMBISONIC, .nb_channels = output_channel_count };
467  layer->demixing_matrix = av_malloc_array(demixing_matrix_size, sizeof(*layer->demixing_matrix));
468  if (!layer->demixing_matrix)
469  return AVERROR(ENOMEM);
470 
471  for (int i = 0; i < demixing_matrix_size; i++)
472  layer->demixing_matrix[i] = av_make_q(sign_extend(avio_rb16(pb), 16), 1 << 8);
473 
474  for (int i = 0; i < substream_count; i++) {
475  IAMFSubStream *substream = &audio_element->substreams[i];
476 
477  substream->codecpar->ch_layout = coupled_substream_count-- > 0 ? (AVChannelLayout)AV_CHANNEL_LAYOUT_STEREO :
479 
480 
481  ret = update_extradata(substream->codecpar);
482  if (ret < 0)
483  return ret;
484  }
485  }
486 
487  return 0;
488 }
489 
490 static int param_parse(void *s, IAMFContext *c, AVIOContext *pb,
491  unsigned int type,
492  const IAMFAudioElement *audio_element,
493  AVIAMFParamDefinition **out_param_definition)
494 {
496  AVIAMFParamDefinition *param;
497  unsigned int parameter_id, parameter_rate, mode;
498  unsigned int duration = 0, constant_subblock_duration = 0, nb_subblocks = 0;
499  size_t param_size;
500 
501  parameter_id = ffio_read_leb(pb);
502 
503  for (int i = 0; i < c->nb_param_definitions; i++)
504  if (c->param_definitions[i]->param->parameter_id == parameter_id) {
505  param_definition = c->param_definitions[i];
506  break;
507  }
508 
509  parameter_rate = ffio_read_leb(pb);
510  mode = avio_r8(pb) >> 7;
511 
512  if (mode == 0) {
513  duration = ffio_read_leb(pb);
514  if (!duration)
515  return AVERROR_INVALIDDATA;
516  constant_subblock_duration = ffio_read_leb(pb);
517  if (constant_subblock_duration == 0)
518  nb_subblocks = ffio_read_leb(pb);
519  else
520  nb_subblocks = duration / constant_subblock_duration;
521  }
522 
523  param = av_iamf_param_definition_alloc(type, nb_subblocks, &param_size);
524  if (!param)
525  return AVERROR(ENOMEM);
526 
527  for (int i = 0; i < nb_subblocks; i++) {
528  void *subblock = av_iamf_param_definition_get_subblock(param, i);
529  unsigned int subblock_duration = constant_subblock_duration;
530 
531  if (constant_subblock_duration == 0)
532  subblock_duration = ffio_read_leb(pb);
533 
534  switch (type) {
536  AVIAMFMixGain *mix = subblock;
537  mix->subblock_duration = subblock_duration;
538  break;
539  }
541  AVIAMFDemixingInfo *demix = subblock;
542  demix->subblock_duration = subblock_duration;
543  // DefaultDemixingInfoParameterData
544  av_assert0(audio_element);
545  demix->dmixp_mode = avio_r8(pb) >> 5;
546  audio_element->element->default_w = avio_r8(pb) >> 4;
547  break;
548  }
550  AVIAMFReconGain *recon = subblock;
551  recon->subblock_duration = subblock_duration;
552  break;
553  }
554  default:
555  av_free(param);
556  return AVERROR_INVALIDDATA;
557  }
558  }
559 
560  param->parameter_id = parameter_id;
561  param->parameter_rate = parameter_rate;
562  param->duration = duration;
563  param->constant_subblock_duration = constant_subblock_duration;
564  param->nb_subblocks = nb_subblocks;
565 
566  if (param_definition) {
567  if (param_definition->param_size != param_size || memcmp(param_definition->param, param, param_size)) {
568  av_log(s, AV_LOG_ERROR, "Incosistent parameters for parameter_id %u\n", parameter_id);
569  av_free(param);
570  return AVERROR_INVALIDDATA;
571  }
572  } else {
573  IAMFParamDefinition **tmp = av_realloc_array(c->param_definitions, c->nb_param_definitions + 1,
574  sizeof(*c->param_definitions));
575  if (!tmp) {
576  av_free(param);
577  return AVERROR(ENOMEM);
578  }
579  c->param_definitions = tmp;
580 
582  if (!param_definition) {
583  av_free(param);
584  return AVERROR(ENOMEM);
585  }
586  param_definition->param = param;
587  param_definition->mode = !mode;
588  param_definition->param_size = param_size;
589  param_definition->audio_element = audio_element;
590 
591  c->param_definitions[c->nb_param_definitions++] = param_definition;
592  }
593 
594  av_assert0(out_param_definition);
595  *out_param_definition = param;
596 
597  return 0;
598 }
599 
600 static int audio_element_obu(void *s, IAMFContext *c, AVIOContext *pb, int len)
601 {
602  const IAMFCodecConfig *codec_config;
603  AVIAMFAudioElement *element;
604  IAMFAudioElement **tmp, *audio_element = NULL;
605  FFIOContext b;
606  AVIOContext *pbc;
607  uint8_t *buf;
608  unsigned audio_element_id, nb_substreams, codec_config_id, num_parameters;
609  int audio_element_type, ret;
610 
611  buf = av_malloc(len);
612  if (!buf)
613  return AVERROR(ENOMEM);
614 
615  ret = ffio_read_size(pb, buf, len);
616  if (ret < 0)
617  goto fail;
618 
619  ffio_init_context(&b, buf, len, 0, NULL, NULL, NULL, NULL);
620  pbc = &b.pub;
621 
622  audio_element_id = ffio_read_leb(pbc);
623 
624  for (int i = 0; i < c->nb_audio_elements; i++)
625  if (c->audio_elements[i]->audio_element_id == audio_element_id) {
626  av_log(s, AV_LOG_ERROR, "Duplicate audio_element_id %d\n", audio_element_id);
628  goto fail;
629  }
630 
631  audio_element_type = avio_r8(pbc) >> 5;
632  if (audio_element_type > AV_IAMF_AUDIO_ELEMENT_TYPE_SCENE) {
633  av_log(s, AV_LOG_DEBUG, "Unknown audio_element_type referenced in an audio element. Ignoring\n");
634  ret = 0;
635  goto fail;
636  }
637 
638  codec_config_id = ffio_read_leb(pbc);
639 
640  codec_config = ff_iamf_get_codec_config(c, codec_config_id);
641  if (!codec_config) {
642  av_log(s, AV_LOG_ERROR, "Non existant codec config id %d referenced in an audio element\n", codec_config_id);
644  goto fail;
645  }
646 
647  if (codec_config->codec_id == AV_CODEC_ID_NONE) {
648  av_log(s, AV_LOG_DEBUG, "Unknown codec id referenced in an audio element. Ignoring\n");
649  ret = 0;
650  goto fail;
651  }
652 
653  tmp = av_realloc_array(c->audio_elements, c->nb_audio_elements + 1, sizeof(*c->audio_elements));
654  if (!tmp) {
655  ret = AVERROR(ENOMEM);
656  goto fail;
657  }
658  c->audio_elements = tmp;
659 
660  audio_element = av_mallocz(sizeof(*audio_element));
661  if (!audio_element) {
662  ret = AVERROR(ENOMEM);
663  goto fail;
664  }
665 
666  nb_substreams = ffio_read_leb(pbc);
667  audio_element->codec_config_id = codec_config_id;
668  audio_element->audio_element_id = audio_element_id;
669  audio_element->substreams = av_calloc(nb_substreams, sizeof(*audio_element->substreams));
670  if (!audio_element->substreams) {
671  ret = AVERROR(ENOMEM);
672  goto fail;
673  }
674  audio_element->nb_substreams = nb_substreams;
675 
676  element = audio_element->element = av_iamf_audio_element_alloc();
677  if (!element) {
678  ret = AVERROR(ENOMEM);
679  goto fail;
680  }
681  audio_element->celement = element;
682 
683  element->audio_element_type = audio_element_type;
684 
685  for (int i = 0; i < audio_element->nb_substreams; i++) {
686  IAMFSubStream *substream = &audio_element->substreams[i];
687 
688  substream->codecpar = avcodec_parameters_alloc();
689  if (!substream->codecpar) {
690  ret = AVERROR(ENOMEM);
691  goto fail;
692  }
693 
694  substream->audio_substream_id = ffio_read_leb(pbc);
695 
696  substream->codecpar->codec_type = AVMEDIA_TYPE_AUDIO;
697  substream->codecpar->codec_id = codec_config->codec_id;
698  substream->codecpar->frame_size = codec_config->nb_samples;
699  substream->codecpar->sample_rate = codec_config->sample_rate;
700  substream->codecpar->seek_preroll = -codec_config->audio_roll_distance * codec_config->nb_samples;
701 
702  switch(substream->codecpar->codec_id) {
703  case AV_CODEC_ID_AAC:
704  case AV_CODEC_ID_FLAC:
705  case AV_CODEC_ID_OPUS:
707  if (!substream->codecpar->extradata) {
708  ret = AVERROR(ENOMEM);
709  goto fail;
710  }
711  memcpy(substream->codecpar->extradata, codec_config->extradata, codec_config->extradata_size);
712  memset(substream->codecpar->extradata + codec_config->extradata_size, 0, AV_INPUT_BUFFER_PADDING_SIZE);
713  substream->codecpar->extradata_size = codec_config->extradata_size;
714  break;
715  }
716  }
717 
718  num_parameters = ffio_read_leb(pbc);
719  if (num_parameters && audio_element_type != 0) {
720  av_log(s, AV_LOG_ERROR, "Audio Element parameter count %u is invalid"
721  " for Scene representations\n", num_parameters);
723  goto fail;
724  }
725 
726  for (int i = 0; i < num_parameters; i++) {
727  unsigned type;
728 
729  type = ffio_read_leb(pbc);
733  ret = param_parse(s, c, pbc, type, audio_element, &element->demixing_info);
735  ret = param_parse(s, c, pbc, type, audio_element, &element->recon_gain_info);
736  else {
737  unsigned param_definition_size = ffio_read_leb(pbc);
738  avio_skip(pbc, param_definition_size);
739  }
740  if (ret < 0)
741  goto fail;
742  }
743 
744  if (audio_element_type == AV_IAMF_AUDIO_ELEMENT_TYPE_CHANNEL) {
745  ret = scalable_channel_layout_config(s, pbc, audio_element, codec_config);
746  if (ret < 0)
747  goto fail;
748  } else if (audio_element_type == AV_IAMF_AUDIO_ELEMENT_TYPE_SCENE) {
749  ret = ambisonics_config(s, pbc, audio_element, codec_config);
750  if (ret < 0)
751  goto fail;
752  } else {
753  av_assert0(0);
754  }
755 
756  c->audio_elements[c->nb_audio_elements++] = audio_element;
757 
758  len -= avio_tell(pbc);
759  if (len)
760  av_log(s, AV_LOG_WARNING, "Underread in audio_element_obu. %d bytes left at the end\n", len);
761 
762  ret = 0;
763 fail:
764  av_free(buf);
765  if (ret < 0)
766  ff_iamf_free_audio_element(&audio_element);
767  return ret;
768 }
769 
770 static int label_string(AVIOContext *pb, char **label)
771 {
772  uint8_t buf[128];
773 
774  avio_get_str(pb, sizeof(buf), buf, sizeof(buf));
775 
776  if (pb->error)
777  return pb->error;
778  if (pb->eof_reached)
779  return AVERROR_INVALIDDATA;
780  *label = av_strdup(buf);
781  if (!*label)
782  return AVERROR(ENOMEM);
783 
784  return 0;
785 }
786 
787 static int mix_presentation_obu(void *s, IAMFContext *c, AVIOContext *pb, int len)
788 {
790  IAMFMixPresentation **tmp, *mix_presentation = NULL;
791  FFIOContext b;
792  AVIOContext *pbc;
793  uint8_t *buf;
794  unsigned nb_submixes, mix_presentation_id;
795  int ret;
796 
797  buf = av_malloc(len);
798  if (!buf)
799  return AVERROR(ENOMEM);
800 
801  ret = ffio_read_size(pb, buf, len);
802  if (ret < 0)
803  goto fail;
804 
805  ffio_init_context(&b, buf, len, 0, NULL, NULL, NULL, NULL);
806  pbc = &b.pub;
807 
808  mix_presentation_id = ffio_read_leb(pbc);
809 
810  for (int i = 0; i < c->nb_mix_presentations; i++)
811  if (c->mix_presentations[i]->mix_presentation_id == mix_presentation_id) {
812  av_log(s, AV_LOG_ERROR, "Duplicate mix_presentation_id %d\n", mix_presentation_id);
814  goto fail;
815  }
816 
817  tmp = av_realloc_array(c->mix_presentations, c->nb_mix_presentations + 1, sizeof(*c->mix_presentations));
818  if (!tmp) {
819  ret = AVERROR(ENOMEM);
820  goto fail;
821  }
822  c->mix_presentations = tmp;
823 
824  mix_presentation = av_mallocz(sizeof(*mix_presentation));
825  if (!mix_presentation) {
826  ret = AVERROR(ENOMEM);
827  goto fail;
828  }
829 
830  mix_presentation->mix_presentation_id = mix_presentation_id;
831  mix = mix_presentation->mix = av_iamf_mix_presentation_alloc();
832  if (!mix) {
833  ret = AVERROR(ENOMEM);
834  goto fail;
835  }
836  mix_presentation->cmix = mix;
837 
838  mix_presentation->count_label = ffio_read_leb(pbc);
839  mix_presentation->language_label = av_calloc(mix_presentation->count_label,
840  sizeof(*mix_presentation->language_label));
841  if (!mix_presentation->language_label) {
842  mix_presentation->count_label = 0;
843  ret = AVERROR(ENOMEM);
844  goto fail;
845  }
846 
847  for (int i = 0; i < mix_presentation->count_label; i++) {
848  ret = label_string(pbc, &mix_presentation->language_label[i]);
849  if (ret < 0)
850  goto fail;
851  }
852 
853  for (int i = 0; i < mix_presentation->count_label; i++) {
854  char *annotation = NULL;
855  ret = label_string(pbc, &annotation);
856  if (ret < 0)
857  goto fail;
858  ret = av_dict_set(&mix->annotations, mix_presentation->language_label[i], annotation,
860  if (ret < 0)
861  goto fail;
862  }
863 
864  nb_submixes = ffio_read_leb(pbc);
865  for (int i = 0; i < nb_submixes; i++) {
866  AVIAMFSubmix *sub_mix;
867  unsigned nb_elements, nb_layouts;
868 
870  if (!sub_mix) {
871  ret = AVERROR(ENOMEM);
872  goto fail;
873  }
874 
875  nb_elements = ffio_read_leb(pbc);
876  for (int j = 0; j < nb_elements; j++) {
877  AVIAMFSubmixElement *submix_element;
878  IAMFAudioElement *audio_element = NULL;
879  unsigned int rendering_config_extension_size;
880 
881  submix_element = av_iamf_submix_add_element(sub_mix);
882  if (!submix_element) {
883  ret = AVERROR(ENOMEM);
884  goto fail;
885  }
886 
887  submix_element->audio_element_id = ffio_read_leb(pbc);
888 
889  for (int k = 0; k < c->nb_audio_elements; k++)
890  if (c->audio_elements[k]->audio_element_id == submix_element->audio_element_id) {
891  audio_element = c->audio_elements[k];
892  break;
893  }
894 
895  if (!audio_element) {
896  av_log(s, AV_LOG_ERROR, "Invalid Audio Element with id %u referenced by Mix Parameters %u\n",
897  submix_element->audio_element_id, mix_presentation_id);
899  goto fail;
900  }
901 
902  for (int k = 0; k < mix_presentation->count_label; k++) {
903  char *annotation = NULL;
904  ret = label_string(pbc, &annotation);
905  if (ret < 0)
906  goto fail;
907  ret = av_dict_set(&submix_element->annotations, mix_presentation->language_label[k], annotation,
909  if (ret < 0)
910  goto fail;
911  }
912 
913  submix_element->headphones_rendering_mode = avio_r8(pbc) >> 6;
914 
915  rendering_config_extension_size = ffio_read_leb(pbc);
916  avio_skip(pbc, rendering_config_extension_size);
917 
919  NULL,
920  &submix_element->element_mix_config);
921  if (ret < 0)
922  goto fail;
923  submix_element->default_mix_gain = av_make_q(sign_extend(avio_rb16(pbc), 16), 1 << 8);
924  }
925 
927  if (ret < 0)
928  goto fail;
929  sub_mix->default_mix_gain = av_make_q(sign_extend(avio_rb16(pbc), 16), 1 << 8);
930 
931  nb_layouts = ffio_read_leb(pbc);
932  for (int j = 0; j < nb_layouts; j++) {
933  AVIAMFSubmixLayout *submix_layout;
934  int info_type;
935  int byte = avio_r8(pbc);
936 
937  submix_layout = av_iamf_submix_add_layout(sub_mix);
938  if (!submix_layout) {
939  ret = AVERROR(ENOMEM);
940  goto fail;
941  }
942 
943  submix_layout->layout_type = byte >> 6;
946  av_log(s, AV_LOG_ERROR, "Invalid Layout type %u in a submix from Mix Presentation %u\n",
947  submix_layout->layout_type, mix_presentation_id);
949  goto fail;
950  }
951  if (submix_layout->layout_type == 2) {
952  int sound_system;
953  sound_system = (byte >> 2) & 0xF;
954  if (sound_system >= FF_ARRAY_ELEMS(ff_iamf_sound_system_map)) {
956  goto fail;
957  }
958  av_channel_layout_copy(&submix_layout->sound_system, &ff_iamf_sound_system_map[sound_system].layout);
959  } else
961 
962  info_type = avio_r8(pbc);
963  submix_layout->integrated_loudness = av_make_q(sign_extend(avio_rb16(pbc), 16), 1 << 8);
964  submix_layout->digital_peak = av_make_q(sign_extend(avio_rb16(pbc), 16), 1 << 8);
965 
966  if (info_type & 1)
967  submix_layout->true_peak = av_make_q(sign_extend(avio_rb16(pbc), 16), 1 << 8);
968  if (info_type & 2) {
969  unsigned int num_anchored_loudness = avio_r8(pbc);
970 
971  for (int k = 0; k < num_anchored_loudness; k++) {
972  unsigned int anchor_element = avio_r8(pbc);
973  AVRational anchored_loudness = av_make_q(sign_extend(avio_rb16(pbc), 16), 1 << 8);
974  if (anchor_element == IAMF_ANCHOR_ELEMENT_DIALOGUE)
975  submix_layout->dialogue_anchored_loudness = anchored_loudness;
976  else if (anchor_element <= IAMF_ANCHOR_ELEMENT_ALBUM)
977  submix_layout->album_anchored_loudness = anchored_loudness;
978  else
979  av_log(s, AV_LOG_DEBUG, "Unknown anchor_element. Ignoring\n");
980  }
981  }
982 
983  if (info_type & 0xFC) {
984  unsigned int info_type_size = ffio_read_leb(pbc);
985  avio_skip(pbc, info_type_size);
986  }
987  }
988  }
989 
990  c->mix_presentations[c->nb_mix_presentations++] = mix_presentation;
991 
992  len -= avio_tell(pbc);
993  if (len)
994  av_log(s, AV_LOG_WARNING, "Underread in mix_presentation_obu. %d bytes left at the end\n", len);
995 
996  ret = 0;
997 fail:
998  av_free(buf);
999  if (ret < 0)
1000  ff_iamf_free_mix_presentation(&mix_presentation);
1001  return ret;
1002 }
1003 
1004 int ff_iamf_parse_obu_header(const uint8_t *buf, int buf_size,
1005  unsigned *obu_size, int *start_pos, enum IAMF_OBU_Type *type,
1006  unsigned *skip_samples, unsigned *discard_padding)
1007 {
1008  GetBitContext gb;
1009  int ret, extension_flag, trimming, start;
1010  unsigned skip = 0, discard = 0;
1011  unsigned size;
1012 
1013  ret = init_get_bits8(&gb, buf, FFMIN(buf_size, MAX_IAMF_OBU_HEADER_SIZE));
1014  if (ret < 0)
1015  return ret;
1016 
1017  *type = get_bits(&gb, 5);
1018  /*redundant =*/ get_bits1(&gb);
1019  trimming = get_bits1(&gb);
1020  extension_flag = get_bits1(&gb);
1021 
1022  *obu_size = get_leb(&gb);
1023  if (*obu_size > INT_MAX)
1024  return AVERROR_INVALIDDATA;
1025 
1026  start = get_bits_count(&gb) / 8;
1027 
1028  if (trimming) {
1029  discard = get_leb(&gb); // num_samples_to_trim_at_end
1030  skip = get_leb(&gb); // num_samples_to_trim_at_start
1031  }
1032 
1033  if (skip_samples)
1034  *skip_samples = skip;
1035  if (discard_padding)
1036  *discard_padding = discard;
1037 
1038  if (extension_flag) {
1039  unsigned int extension_bytes;
1040  extension_bytes = get_leb(&gb);
1041  if (extension_bytes > INT_MAX / 8)
1042  return AVERROR_INVALIDDATA;
1043  skip_bits_long(&gb, extension_bytes * 8);
1044  }
1045 
1046  if (get_bits_left(&gb) < 0)
1047  return AVERROR_INVALIDDATA;
1048 
1049  size = *obu_size + start;
1050  if (size > INT_MAX)
1051  return AVERROR_INVALIDDATA;
1052 
1053  *obu_size -= get_bits_count(&gb) / 8 - start;
1054  *start_pos = size - *obu_size;
1055 
1056  return size;
1057 }
1058 
1060  int max_size, void *log_ctx)
1061 {
1063  int ret;
1064 
1065  while (1) {
1066  unsigned obu_size;
1067  enum IAMF_OBU_Type type;
1068  int start_pos, len, size;
1069 
1070  if ((ret = ffio_ensure_seekback(pb, FFMIN(MAX_IAMF_OBU_HEADER_SIZE, max_size))) < 0)
1071  return ret;
1072  size = avio_read(pb, header, FFMIN(MAX_IAMF_OBU_HEADER_SIZE, max_size));
1073  if (size < 0)
1074  return size;
1076 
1077  len = ff_iamf_parse_obu_header(header, size, &obu_size, &start_pos, &type, NULL, NULL);
1078  if (len < 0 || obu_size > max_size) {
1079  av_log(log_ctx, AV_LOG_ERROR, "Failed to read obu header\n");
1080  avio_seek(pb, -size, SEEK_CUR);
1081  return len;
1082  }
1083 
1085  avio_seek(pb, -size, SEEK_CUR);
1086  break;
1087  }
1088 
1089  avio_seek(pb, -(size - start_pos), SEEK_CUR);
1090  switch (type) {
1092  ret = codec_config_obu(log_ctx, c, pb, obu_size);
1093  break;
1095  ret = audio_element_obu(log_ctx, c, pb, obu_size);
1096  break;
1098  ret = mix_presentation_obu(log_ctx, c, pb, obu_size);
1099  break;
1100  default: {
1101  int64_t offset = avio_skip(pb, obu_size);
1102  if (offset < 0)
1103  ret = offset;
1104  break;
1105  }
1106  }
1107  if (ret < 0) {
1108  av_log(log_ctx, AV_LOG_ERROR, "Failed to read obu type %d\n", type);
1109  return ret;
1110  }
1111  max_size -= obu_size + start_pos;
1112  if (max_size < 0)
1113  return AVERROR_INVALIDDATA;
1114  if (!max_size)
1115  break;
1116  }
1117 
1118  return 0;
1119 }
update_extradata
static int update_extradata(AVCodecParameters *codecpar)
Definition: iamf_parse.c:274
AV_CODEC_ID_PCM_S16LE
@ AV_CODEC_ID_PCM_S16LE
Definition: codec_id.h:334
iamf.h
ff_iamf_free_mix_presentation
void ff_iamf_free_mix_presentation(IAMFMixPresentation **pmix_presentation)
Definition: iamf.c:85
skip_bits_long
static void skip_bits_long(GetBitContext *s, int n)
Skips the specified number of bits.
Definition: get_bits.h:278
AV_IAMF_SUBMIX_LAYOUT_TYPE_LOUDSPEAKERS
@ AV_IAMF_SUBMIX_LAYOUT_TYPE_LOUDSPEAKERS
The layout follows the loudspeaker sound system convention of ITU-2051-3.
Definition: iamf.h:498
AV_LOG_WARNING
#define AV_LOG_WARNING
Something somehow does not look correct.
Definition: log.h:215
AVCodecParameters::extradata
uint8_t * extradata
Extra binary data needed for initializing the decoder, codec-dependent.
Definition: codec_par.h:69
MP4DecConfigDescrTag
#define MP4DecConfigDescrTag
Definition: isom.h:383
ffio_init_context
void ffio_init_context(FFIOContext *s, unsigned char *buffer, int buffer_size, int write_flag, void *opaque, int(*read_packet)(void *opaque, uint8_t *buf, int buf_size), int(*write_packet)(void *opaque, const uint8_t *buf, int buf_size), int64_t(*seek)(void *opaque, int64_t offset, int whence))
Definition: aviobuf.c:50
mix
static int mix(int c0, int c1)
Definition: 4xm.c:716
get_bits_left
static int get_bits_left(GetBitContext *gb)
Definition: get_bits.h:695
AVERROR
Filter the word “frame” indicates either a video frame or a group of audio as stored in an AVFrame structure Format for each input and each output the list of supported formats For video that means pixel format For audio that means channel sample they are references to shared objects When the negotiation mechanism computes the intersection of the formats supported at each end of a all references to both lists are replaced with a reference to the intersection And when a single format is eventually chosen for a link amongst the remaining all references to the list are updated That means that if a filter requires that its input and output have the same format amongst a supported all it has to do is use a reference to the same list of formats query_formats can leave some formats unset and return AVERROR(EAGAIN) to cause the negotiation mechanism toagain later. That can be used by filters with complex requirements to use the format negotiated on one link to set the formats supported on another. Frame references ownership and permissions
put_bits32
static void av_unused put_bits32(PutBitContext *s, uint32_t value)
Write exactly 32 bits into a bitstream.
Definition: put_bits.h:291
AVCodecParameters::codec_type
enum AVMediaType codec_type
General type of the encoded data.
Definition: codec_par.h:51
AV_CHANNEL_LAYOUT_STEREO
#define AV_CHANNEL_LAYOUT_STEREO
Definition: channel_layout.h:393
put_bytes_output
static int put_bytes_output(const PutBitContext *s)
Definition: put_bits.h:89
IAMF_OBU_IA_SEQUENCE_HEADER
@ IAMF_OBU_IA_SEQUENCE_HEADER
Definition: iamf.h:63
ff_mp4_obj_type
const AVCodecTag ff_mp4_obj_type[]
Definition: isom.c:34
AVCodecParameters
This struct describes the properties of an encoded stream.
Definition: codec_par.h:47
AVIAMFAudioElement::default_w
unsigned int default_w
Default weight value as defined in section 3.6 of IAMF.
Definition: iamf.h:393
IAMFAudioElement::nb_substreams
unsigned int nb_substreams
Definition: iamf.h:99
av_iamf_param_definition_alloc
AVIAMFParamDefinition * av_iamf_param_definition_alloc(enum AVIAMFParamDefinitionType type, unsigned int nb_subblocks, size_t *out_size)
Allocates memory for AVIAMFParamDefinition, plus an array of.
Definition: iamf.c:159
get_bits_long
static unsigned int get_bits_long(GetBitContext *s, int n)
Read 0-32 bits.
Definition: get_bits.h:421
int64_t
long long int64_t
Definition: coverity.c:34
init_put_bits
static void init_put_bits(PutBitContext *s, uint8_t *buffer, int buffer_size)
Initialize the PutBitContext s.
Definition: put_bits.h:62
get_bits_count
static int get_bits_count(const GetBitContext *s)
Definition: get_bits.h:266
AVChannelLayout::map
AVChannelCustom * map
This member must be used when the channel order is AV_CHANNEL_ORDER_CUSTOM.
Definition: channel_layout.h:368
AV_RB32A
#define AV_RB32A(p)
Definition: intreadwrite.h:575
mode
Definition: swscale.c:52
put_bits
static void put_bits(Jpeg2000EncoderContext *s, int val, int n)
put n times val bit
Definition: j2kenc.c:223
tmp
static uint8_t tmp[11]
Definition: aes_ctr.c:28
ff_iamf_sound_system_map
const struct IAMFSoundSystemMap ff_iamf_sound_system_map[13]
Definition: iamf.c:48
put_bits64
static void put_bits64(PutBitContext *s, int n, uint64_t value)
Write up to 64 bits into a bitstream.
Definition: put_bits.h:334
AVCodecParameters::seek_preroll
int seek_preroll
Audio only.
Definition: codec_par.h:214
b
#define b
Definition: input.c:41
AVIOContext::error
int error
contains the error code or 0 if no error happened
Definition: avio.h:239
AVIAMFSubmixLayout::layout_type
enum AVIAMFSubmixLayoutType layout_type
Definition: iamf.h:517
AVIAMFParamDefinition
Parameters as defined in section 3.6.1 of IAMF.
Definition: iamf.h:193
AVIAMFSubmixElement::default_mix_gain
AVRational default_mix_gain
Default mix gain value to apply when there are no AVIAMFParamDefinition with element_mix_config's par...
Definition: iamf.h:469
AV_CODEC_ID_FLAC
@ AV_CODEC_ID_FLAC
Definition: codec_id.h:458
AVChannelLayout::order
enum AVChannelOrder order
Channel order used in this layout.
Definition: channel_layout.h:322
iamf_parse.h
ambisonics_config
static int ambisonics_config(void *s, AVIOContext *pb, IAMFAudioElement *audio_element, const IAMFCodecConfig *codec_config)
Definition: iamf_parse.c:405
AVChannelLayout::nb_channels
int nb_channels
Number of channels in this layout.
Definition: channel_layout.h:327
FFIOContext
Definition: avio_internal.h:28
flac_decoder_config
static int flac_decoder_config(IAMFCodecConfig *codec_config, AVIOContext *pb, int len)
Definition: iamf_parse.c:117
av_malloc
#define av_malloc(s)
Definition: tableprint_vlc.h:30
IAMFMixPresentation::cmix
const AVIAMFMixPresentation * cmix
Definition: iamf.h:108
MPEG4AudioConfig
Definition: mpeg4audio.h:29
AVIAMFSubmixLayout::digital_peak
AVRational digital_peak
The digital (sampled) peak value of the audio signal, as defined in ITU-1770-4.
Definition: iamf.h:535
skip_bits
static void skip_bits(GetBitContext *s, int n)
Definition: get_bits.h:381
get_bits
static unsigned int get_bits(GetBitContext *s, int n)
Read 1-25 bits.
Definition: get_bits.h:335
mpeg4audio.h
AVIAMFSubmixLayout::integrated_loudness
AVRational integrated_loudness
The program integrated loudness information, as defined in ITU-1770-4.
Definition: iamf.h:530
av_iamf_mix_presentation_add_submix
AVIAMFSubmix * av_iamf_mix_presentation_add_submix(AVIAMFMixPresentation *mix_presentation)
Allocate a submix and add it to a given AVIAMFMixPresentation.
IAMFCodecConfig::extradata
uint8_t * extradata
Definition: iamf.h:74
MP4DecSpecificDescrTag
#define MP4DecSpecificDescrTag
Definition: isom.h:384
AOT_ESCAPE
@ AOT_ESCAPE
Y Escape Value.
Definition: mpeg4audio.h:102
AV_CODEC_ID_PCM_S16BE
@ AV_CODEC_ID_PCM_S16BE
Definition: codec_id.h:335
IAMFParamDefinition
Definition: iamf.h:121
fail
#define fail()
Definition: checkasm.h:193
GetBitContext
Definition: get_bits.h:108
AVIAMFSubmixLayout
Submix layout as defined in section 3.7.6 of IAMF.
Definition: iamf.h:514
IAMF_ANCHOR_ELEMENT_ALBUM
@ IAMF_ANCHOR_ELEMENT_ALBUM
Definition: iamf.h:142
put_bits_left
static int put_bits_left(PutBitContext *s)
Definition: put_bits.h:125
avio_tell
static av_always_inline int64_t avio_tell(AVIOContext *s)
ftell() equivalent for AVIOContext.
Definition: avio.h:494
av_iamf_audio_element_alloc
AVIAMFAudioElement * av_iamf_audio_element_alloc(void)
Allocates a AVIAMFAudioElement, and initializes its fields with default values.
Definition: iamf.c:322
type
it s the only field you need to keep assuming you have a context There is some magic you don t need to care about around this just let it vf type
Definition: writing_filters.txt:86
IAMF_OBU_IA_PARAMETER_BLOCK
@ IAMF_OBU_IA_PARAMETER_BLOCK
Definition: iamf.h:41
AVIAMFAudioElement::audio_element_type
enum AVIAMFAudioElementType audio_element_type
Audio element type as defined in section 3.6 of IAMF.
Definition: iamf.h:388
opus_decoder_config
static int opus_decoder_config(IAMFCodecConfig *codec_config, AVIOContext *pb, int len)
Definition: iamf_parse.c:36
AVIAMFReconGain
Recon Gain Info Parameter Data as defined in section 3.8.3 of IAMF.
Definition: iamf.h:148
param_parse
static int param_parse(void *s, IAMFContext *c, AVIOContext *pb, unsigned int type, const IAMFAudioElement *audio_element, AVIAMFParamDefinition **out_param_definition)
Definition: iamf_parse.c:490
codec_config_obu
static int codec_config_obu(void *s, IAMFContext *c, AVIOContext *pb, int len)
Definition: iamf_parse.c:166
AV_DICT_DONT_STRDUP_VAL
#define AV_DICT_DONT_STRDUP_VAL
Take ownership of a value that's been allocated with av_malloc() or another memory allocation functio...
Definition: dict.h:79
IAMFAudioElement::element
AVIAMFAudioElement * element
element backs celement iff the AVIAMFAudioElement is owned by this structure.
Definition: iamf.h:95
AV_IAMF_PARAMETER_DEFINITION_RECON_GAIN
@ AV_IAMF_PARAMETER_DEFINITION_RECON_GAIN
Subblocks are of struct type AVIAMFReconGain.
Definition: iamf.h:181
AVIAMFSubmixElement::annotations
AVDictionary * annotations
A dictionary of strings describing the submix in different languages.
Definition: iamf.h:490
avassert.h
avio_rb32
unsigned int avio_rb32(AVIOContext *s)
Definition: aviobuf.c:761
AV_LOG_ERROR
#define AV_LOG_ERROR
Something went wrong and cannot losslessly be recovered.
Definition: log.h:209
FF_ARRAY_ELEMS
#define FF_ARRAY_ELEMS(a)
Definition: sinewin_tablegen.c:29
init_get_bits8
static int init_get_bits8(GetBitContext *s, const uint8_t *buffer, int byte_size)
Initialize GetBitContext.
Definition: get_bits.h:545
IAMFCodecConfig::sample_rate
int sample_rate
Definition: iamf.h:72
IAMF_OBU_IA_MIX_PRESENTATION
@ IAMF_OBU_IA_MIX_PRESENTATION
Definition: iamf.h:40
duration
int64_t duration
Definition: movenc.c:65
AVCodecParameters::frame_size
int frame_size
Audio only.
Definition: codec_par.h:195
av_iamf_submix_add_layout
AVIAMFSubmixLayout * av_iamf_submix_add_layout(AVIAMFSubmix *submix)
Allocate a submix layout and add it to a given AVIAMFSubmix.
avpriv_mpeg4audio_get_config2
int avpriv_mpeg4audio_get_config2(MPEG4AudioConfig *c, const uint8_t *buf, int size, int sync_extension, void *logctx)
Parse MPEG-4 systems extradata from a raw buffer to retrieve audio configuration.
Definition: mpeg4audio.c:165
intreadwrite.h
s
#define s(width, name)
Definition: cbs_vp9.c:198
IAMFSubStream::audio_substream_id
unsigned int audio_substream_id
Definition: iamf.h:83
IAMFLayer::substream_count
unsigned int substream_count
Definition: iamf.h:78
AVIAMFSubmixLayout::dialogue_anchored_loudness
AVRational dialogue_anchored_loudness
The Dialogue loudness information, as defined in ITU-1770-4.
Definition: iamf.h:543
av_realloc_array
void * av_realloc_array(void *ptr, size_t nmemb, size_t size)
Definition: mem.c:217
floor
static __device__ float floor(float a)
Definition: cuda_runtime.h:173
AVMEDIA_TYPE_AUDIO
@ AVMEDIA_TYPE_AUDIO
Definition: avutil.h:202
av_iamf_param_definition_get_subblock
static av_always_inline void * av_iamf_param_definition_get_subblock(const AVIAMFParamDefinition *par, unsigned int idx)
Get the subblock at the specified.
Definition: iamf.h:260
AVChannelLayout::u
union AVChannelLayout::@428 u
Details about which channels are present in this layout.
AV_CHANNEL_ORDER_UNSPEC
@ AV_CHANNEL_ORDER_UNSPEC
Only the channel count is specified, without any further information about the channel order.
Definition: channel_layout.h:119
av_assert0
#define av_assert0(cond)
assert() equivalent, that is always enabled.
Definition: avassert.h:40
AVIAMFSubmixElement::headphones_rendering_mode
enum AVIAMFHeadphonesMode headphones_rendering_mode
A value that indicates whether the referenced channel-based Audio Element shall be rendered to stereo...
Definition: iamf.h:478
ffio_read_leb
unsigned int ffio_read_leb(AVIOContext *s)
Read a unsigned integer coded as a variable number of up to eight little-endian bytes,...
Definition: aviobuf.c:927
AV_LOG_DEBUG
#define AV_LOG_DEBUG
Stuff which is only useful for libav* developers.
Definition: log.h:230
get_bits.h
AVIAMFLayer::ch_layout
AVChannelLayout ch_layout
Definition: iamf.h:297
IAMFAudioElement::nb_layers
unsigned int nb_layers
Definition: iamf.h:104
ff_iamfdec_read_descriptors
int ff_iamfdec_read_descriptors(IAMFContext *c, AVIOContext *pb, int max_size, void *log_ctx)
Definition: iamf_parse.c:1059
codec_id
enum AVCodecID codec_id
Definition: vaapi_decode.c:410
PutBitContext
Definition: put_bits.h:50
IAMFAudioElement::audio_element_id
unsigned int audio_element_id
Definition: iamf.h:96
AVIAMFDemixingInfo
Demixing Info Parameter Data as defined in section 3.8.2 of IAMF.
Definition: iamf.h:128
IAMFSoundSystemMap::layout
AVChannelLayout layout
Definition: iamf.h:163
AV_CHANNEL_ORDER_AMBISONIC
@ AV_CHANNEL_ORDER_AMBISONIC
The audio is represented as the decomposition of the sound field into spherical harmonics.
Definition: channel_layout.h:155
NULL
#define NULL
Definition: coverity.c:32
get_leb
static unsigned get_leb(GetBitContext *s)
Read a unsigned integer coded as a variable number of up to eight little-endian bytes,...
Definition: leb.h:35
isom.h
IAMF_OBU_IA_AUDIO_ELEMENT
@ IAMF_OBU_IA_AUDIO_ELEMENT
Definition: iamf.h:39
AVRational
Rational number (pair of numerator and denominator).
Definition: rational.h:58
AVIAMFParamDefinition::duration
unsigned int duration
The accumulated duration of all blocks in this parameter definition, in units of 1 / parameter_rate.
Definition: iamf.h:231
ff_iamf_get_codec_config
static IAMFCodecConfig * ff_iamf_get_codec_config(const IAMFContext *c, unsigned int codec_config_id)
Definition: iamf.h:170
get_bits1
static unsigned int get_bits1(GetBitContext *s)
Definition: get_bits.h:388
audio_element_obu
static int audio_element_obu(void *s, IAMFContext *c, AVIOContext *pb, int len)
Definition: iamf_parse.c:600
AVIAMFLayer
A layer defining a Channel Layout in the Audio Element.
Definition: iamf.h:294
IAMF_OBU_IA_CODEC_CONFIG
@ IAMF_OBU_IA_CODEC_CONFIG
Definition: iamf.h:38
IAMFSubStream
Definition: iamf.h:82
IAMFAudioElement::layers
IAMFLayer * layers
Definition: iamf.h:103
FLAC_STREAMINFO_SIZE
#define FLAC_STREAMINFO_SIZE
Definition: flac.h:32
AV_DICT_DONT_OVERWRITE
#define AV_DICT_DONT_OVERWRITE
Don't overwrite existing entries.
Definition: dict.h:81
AVCodecParameters::ch_layout
AVChannelLayout ch_layout
Audio only.
Definition: codec_par.h:180
IAMFAudioElement::celement
const AVIAMFAudioElement * celement
Definition: iamf.h:90
c
Undefined Behavior In the C some operations are like signed integer dereferencing freed accessing outside allocated Undefined Behavior must not occur in a C it is not safe even if the output of undefined operations is unused The unsafety may seem nit picking but Optimizing compilers have in fact optimized code on the assumption that no undefined Behavior occurs Optimizing code based on wrong assumptions can and has in some cases lead to effects beyond the output of computations The signed integer overflow problem in speed critical code Code which is highly optimized and works with signed integers sometimes has the problem that often the output of the computation does not c
Definition: undefined.txt:32
ff_mp4_read_descr
int ff_mp4_read_descr(void *logctx, AVIOContext *pb, int *tag)
Definition: isom.c:295
AVCodecParameters::sample_rate
int sample_rate
Audio only.
Definition: codec_par.h:184
ff_iamf_parse_obu_header
int ff_iamf_parse_obu_header(const uint8_t *buf, int buf_size, unsigned *obu_size, int *start_pos, enum IAMF_OBU_Type *type, unsigned *skip_samples, unsigned *discard_padding)
Definition: iamf_parse.c:1004
AVIAMFLayer::output_gain_flags
unsigned int output_gain_flags
Output gain channel flags as defined in section 3.6.2 of IAMF.
Definition: iamf.h:310
AVCodecID
AVCodecID
Identify the syntax and semantics of the bitstream.
Definition: codec_id.h:49
AVIAMFSubmixElement::audio_element_id
unsigned int audio_element_id
The id of the Audio Element this submix element references.
Definition: iamf.h:452
AVCodecParameters::extradata_size
int extradata_size
Size of the extradata content in bytes.
Definition: codec_par.h:73
AVIAMFSubmix
Submix layout as defined in section 3.7 of IAMF.
Definition: iamf.h:556
AV_CODEC_ID_AAC
@ AV_CODEC_ID_AAC
Definition: codec_id.h:448
IAMFAudioElement
Definition: iamf.h:89
AVIAMFReconGain::subblock_duration
unsigned int subblock_duration
Duration for the given subblock, in units of 1 / parameter_rate.
Definition: iamf.h:156
AVIOContext
Bytestream IO Context.
Definition: avio.h:160
IAMFCodecConfig::nb_samples
unsigned nb_samples
Definition: iamf.h:70
AV_CODEC_ID_PCM_S24LE
@ AV_CODEC_ID_PCM_S24LE
Definition: codec_id.h:346
AVIAMFDemixingInfo::subblock_duration
unsigned int subblock_duration
Duration for the given subblock, in units of 1 / parameter_rate.
Definition: iamf.h:136
ff_codec_get_id
enum AVCodecID ff_codec_get_id(const AVCodecTag *tags, unsigned int tag)
Definition: utils.c:133
IAMFCodecConfig
Definition: iamf.h:66
AVChannelLayout
An AVChannelLayout holds information about the channel layout of audio data.
Definition: channel_layout.h:317
IAMFCodecConfig::extradata_size
int extradata_size
Definition: iamf.h:73
avio_get_str
int avio_get_str(AVIOContext *pb, int maxlen, char *buf, int buflen)
Read a string from pb into buf.
Definition: aviobuf.c:866
size
int size
Definition: twinvq_data.h:10344
av_make_q
static AVRational av_make_q(int num, int den)
Create an AVRational.
Definition: rational.h:71
IAMFLayer::coupled_substream_count
unsigned int coupled_substream_count
Definition: iamf.h:79
AV_WL32A
#define AV_WL32A(p, v)
Definition: intreadwrite.h:571
MKBETAG
#define MKBETAG(a, b, c, d)
Definition: macros.h:56
AV_CODEC_ID_OPUS
@ AV_CODEC_ID_OPUS
Definition: codec_id.h:506
av_iamf_mix_presentation_alloc
AVIAMFMixPresentation * av_iamf_mix_presentation_alloc(void)
Allocates a AVIAMFMixPresentation, and initializes its fields with default values.
Definition: iamf.c:520
IAMFContext
Definition: iamf.h:128
header
static const uint8_t header[24]
Definition: sdr2.c:68
avio_r8
int avio_r8(AVIOContext *s)
Definition: aviobuf.c:603
IAMFAudioElement::substreams
IAMFSubStream * substreams
Definition: iamf.h:98
AVIAMFParamDefinition::constant_subblock_duration
unsigned int constant_subblock_duration
The duration of every subblock in the case where all subblocks, with the optional exception of the la...
Definition: iamf.h:238
av_iamf_submix_add_element
AVIAMFSubmixElement * av_iamf_submix_add_element(AVIAMFSubmix *submix)
Allocate a submix element and add it to a given AVIAMFSubmix.
AVIAMFAudioElement
Information on how to combine one or more audio streams, as defined in section 3.6 of IAMF.
Definition: iamf.h:356
ipcm_decoder_config
static int ipcm_decoder_config(IAMFCodecConfig *codec_config, AVIOContext *pb, int len)
Definition: iamf_parse.c:145
ffio_ensure_seekback
int ffio_ensure_seekback(AVIOContext *s, int64_t buf_size)
Ensures that the requested seekback buffer size will be available.
Definition: aviobuf.c:1023
offset
it s the only field you need to keep assuming you have a context There is some magic you don t need to care about around this just let it vf offset
Definition: writing_filters.txt:86
AVIAMFMixGain
Mix Gain Parameter Data as defined in section 3.8.1 of IAMF.
Definition: iamf.h:77
leb.h
AV_RB16A
#define AV_RB16A(p)
Definition: intreadwrite.h:561
avcodec_parameters_alloc
AVCodecParameters * avcodec_parameters_alloc(void)
Allocate a new AVCodecParameters and set its fields to default values (unknown/invalid/0).
Definition: codec_par.c:56
get_bits64
static uint64_t get_bits64(GetBitContext *s, int n)
Read 0-64 bits.
Definition: get_bits.h:453
log.h
AV_CODEC_ID_NONE
@ AV_CODEC_ID_NONE
Definition: codec_id.h:50
i
#define i(width, name, range_min, range_max)
Definition: cbs_h2645.c:256
AVIAMFParamDefinition::parameter_id
unsigned int parameter_id
Identifier for the paremeter substream.
Definition: iamf.h:218
avio_internal.h
AVIAMFLayer::demixing_matrix
AVRational * demixing_matrix
Demixing matrix as defined in section 3.6.3 of IAMF.
Definition: iamf.h:340
av_malloc_array
#define av_malloc_array(a, b)
Definition: tableprint_vlc.h:31
AVIAMFMixPresentation
Information on how to render and mix one or more AVIAMFAudioElement to generate the final audio outpu...
Definition: iamf.h:613
aac_decoder_config
static int aac_decoder_config(IAMFCodecConfig *codec_config, AVIOContext *pb, int len, void *logctx)
Definition: iamf_parse.c:60
FFMIN
#define FFMIN(a, b)
Definition: macros.h:49
param_definition
static int param_definition(const IAMFContext *iamf, const IAMFParamDefinition *param_def, AVIOContext *dyn_bc, void *log_ctx)
Definition: iamf_writer.c:586
AV_CODEC_ID_PCM_S32BE
@ AV_CODEC_ID_PCM_S32BE
Definition: codec_id.h:343
av_mallocz
void * av_mallocz(size_t size)
Allocate a memory block with alignment suitable for all memory accesses (including vectors if availab...
Definition: mem.c:256
len
int len
Definition: vorbis_enc_data.h:426
IAMFMixPresentation::count_label
unsigned int count_label
Definition: iamf.h:117
av_calloc
void * av_calloc(size_t nmemb, size_t size)
Definition: mem.c:264
AVIAMFParamDefinition::nb_subblocks
unsigned int nb_subblocks
Number of subblocks in the array.
Definition: iamf.h:208
AV_IAMF_AUDIO_ELEMENT_TYPE_SCENE
@ AV_IAMF_AUDIO_ELEMENT_TYPE_SCENE
Definition: iamf.h:346
AV_WB32A
#define AV_WB32A(p, v)
Definition: intreadwrite.h:578
AV_WB8
#define AV_WB8(p, d)
Definition: intreadwrite.h:392
tag
uint32_t tag
Definition: movenc.c:1879
ret
ret
Definition: filter_design.txt:187
avio_seek
int64_t avio_seek(AVIOContext *s, int64_t offset, int whence)
fseek() equivalent for AVIOContext.
Definition: aviobuf.c:231
ff_iamf_free_audio_element
void ff_iamf_free_audio_element(IAMFAudioElement **paudio_element)
Definition: iamf.c:70
avio_rb16
unsigned int avio_rb16(AVIOContext *s)
Definition: aviobuf.c:746
AV_INPUT_BUFFER_PADDING_SIZE
#define AV_INPUT_BUFFER_PADDING_SIZE
Definition: defs.h:40
left
Tag MUST be and< 10hcoeff half pel interpolation filter coefficients, hcoeff[0] are the 2 middle coefficients[1] are the next outer ones and so on, resulting in a filter like:...eff[2], hcoeff[1], hcoeff[0], hcoeff[0], hcoeff[1], hcoeff[2] ... the sign of the coefficients is not explicitly stored but alternates after each coeff and coeff[0] is positive, so ...,+,-,+,-,+,+,-,+,-,+,... hcoeff[0] is not explicitly stored but found by subtracting the sum of all stored coefficients with signs from 32 hcoeff[0]=32 - hcoeff[1] - hcoeff[2] - ... a good choice for hcoeff and htaps is htaps=6 hcoeff={40,-10, 2} an alternative which requires more computations at both encoder and decoder side and may or may not be better is htaps=8 hcoeff={42,-14, 6,-2}ref_frames minimum of the number of available reference frames and max_ref_frames for example the first frame after a key frame always has ref_frames=1spatial_decomposition_type wavelet type 0 is a 9/7 symmetric compact integer wavelet 1 is a 5/3 symmetric compact integer wavelet others are reserved stored as delta from last, last is reset to 0 if always_reset||keyframeqlog quality(logarithmic quantizer scale) stored as delta from last, last is reset to 0 if always_reset||keyframemv_scale stored as delta from last, last is reset to 0 if always_reset||keyframe FIXME check that everything works fine if this changes between framesqbias dequantization bias stored as delta from last, last is reset to 0 if always_reset||keyframeblock_max_depth maximum depth of the block tree stored as delta from last, last is reset to 0 if always_reset||keyframequant_table quantization tableHighlevel bitstream structure:==============================--------------------------------------------|Header|--------------------------------------------|------------------------------------|||Block0||||split?||||yes no||||......... intra?||||:Block01 :yes no||||:Block02 :....... ..........||||:Block03 ::y DC ::ref index:||||:Block04 ::cb DC ::motion x :||||......... :cr DC ::motion y :||||....... ..........|||------------------------------------||------------------------------------|||Block1|||...|--------------------------------------------|------------ ------------ ------------|||Y subbands||Cb subbands||Cr subbands||||--- ---||--- ---||--- ---|||||LL0||HL0||||LL0||HL0||||LL0||HL0|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||LH0||HH0||||LH0||HH0||||LH0||HH0|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||HL1||LH1||||HL1||LH1||||HL1||LH1|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||HH1||HL2||||HH1||HL2||||HH1||HL2|||||...||...||...|||------------ ------------ ------------|--------------------------------------------Decoding process:=================------------|||Subbands|------------||||------------|Intra DC||||LL0 subband prediction ------------|\ Dequantization ------------------- \||Reference frames|\ IDWT|------- -------|Motion \|||Frame 0||Frame 1||Compensation . OBMC v -------|------- -------|--------------. \------> Frame n output Frame Frame<----------------------------------/|...|------------------- Range Coder:============Binary Range Coder:------------------- The implemented range coder is an adapted version based upon "Range encoding: an algorithm for removing redundancy from a digitised message." by G. N. N. Martin. The symbols encoded by the Snow range coder are bits(0|1). The associated probabilities are not fix but change depending on the symbol mix seen so far. bit seen|new state ---------+----------------------------------------------- 0|256 - state_transition_table[256 - old_state];1|state_transition_table[old_state];state_transition_table={ 0, 0, 0, 0, 0, 0, 0, 0, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150, 151, 152, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 190, 191, 192, 194, 194, 195, 196, 197, 198, 199, 200, 201, 202, 202, 204, 205, 206, 207, 208, 209, 209, 210, 211, 212, 213, 215, 215, 216, 217, 218, 219, 220, 220, 222, 223, 224, 225, 226, 227, 227, 229, 229, 230, 231, 232, 234, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245, 246, 247, 248, 248, 0, 0, 0, 0, 0, 0, 0};FIXME Range Coding of integers:------------------------- FIXME Neighboring Blocks:===================left and top are set to the respective blocks unless they are outside of the image in which case they are set to the Null block top-left is set to the top left block unless it is outside of the image in which case it is set to the left block if this block has no larger parent block or it is at the left side of its parent block and the top right block is not outside of the image then the top right block is used for top-right else the top-left block is used Null block y, cb, cr are 128 level, ref, mx and my are 0 Motion Vector Prediction:=========================1. the motion vectors of all the neighboring blocks are scaled to compensate for the difference of reference frames scaled_mv=(mv *(256 *(current_reference+1)/(mv.reference+1))+128)> the median of the scaled left
Definition: snow.txt:386
U
#define U(x)
Definition: vpx_arith.h:37
IAMF_OBU_Type
IAMF_OBU_Type
Definition: iamf.h:37
label_string
static int label_string(AVIOContext *pb, char **label)
Definition: iamf_parse.c:770
IAMFMixPresentation
Definition: iamf.h:107
AV_CHANNEL_ORDER_CUSTOM
@ AV_CHANNEL_ORDER_CUSTOM
The channel order does not correspond to any other predefined order and is stored as an explicit map.
Definition: channel_layout.h:132
IAMFMixPresentation::language_label
char ** language_label
Definition: iamf.h:118
AVIAMFSubmix::default_mix_gain
AVRational default_mix_gain
Default mix gain value to apply when there are no AVIAMFParamDefinition with output_mix_config's para...
Definition: iamf.h:603
AVIAMFSubmixLayout::album_anchored_loudness
AVRational album_anchored_loudness
The Album loudness information, as defined in ITU-1770-4.
Definition: iamf.h:547
AVIAMFSubmixLayout::true_peak
AVRational true_peak
The true peak of the audio signal, as defined in ITU-1770-4.
Definition: iamf.h:539
mode
mode
Definition: ebur128.h:83
AVIAMFSubmixLayout::sound_system
AVChannelLayout sound_system
Channel layout matching one of Sound Systems A to J of ITU-2051-3, plus 7.1.2ch, 3....
Definition: iamf.h:525
IAMFCodecConfig::codec_id
enum AVCodecID codec_id
Definition: iamf.h:68
IAMFCodecConfig::codec_config_id
unsigned codec_config_id
Definition: iamf.h:67
avio_read
int avio_read(AVIOContext *s, unsigned char *buf, int size)
Read size bytes from AVIOContext into buf.
Definition: aviobuf.c:612
sign_extend
static av_const int sign_extend(int val, unsigned bits)
Definition: mathops.h:131
AVIOContext::eof_reached
int eof_reached
true if was unable to read due to error or eof
Definition: avio.h:238
IAMF_ANCHOR_ELEMENT_DIALOGUE
@ IAMF_ANCHOR_ELEMENT_DIALOGUE
Definition: iamf.h:141
AV_IAMF_PARAMETER_DEFINITION_MIX_GAIN
@ AV_IAMF_PARAMETER_DEFINITION_MIX_GAIN
Subblocks are of struct type AVIAMFMixGain.
Definition: iamf.h:173
MAX_IAMF_OBU_HEADER_SIZE
#define MAX_IAMF_OBU_HEADER_SIZE
Definition: iamf.h:34
avio_skip
int64_t avio_skip(AVIOContext *s, int64_t offset)
Skip given number of bytes forward.
Definition: aviobuf.c:318
mix_presentation_obu
static int mix_presentation_obu(void *s, IAMFContext *c, AVIOContext *pb, int len)
Definition: iamf_parse.c:787
av_iamf_audio_element_add_layer
AVIAMFLayer * av_iamf_audio_element_add_layer(AVIAMFAudioElement *audio_element)
Allocate a layer and add it to a given AVIAMFAudioElement.
av_channel_layout_copy
int av_channel_layout_copy(AVChannelLayout *dst, const AVChannelLayout *src)
Make a copy of a channel layout.
Definition: channel_layout.c:447
av_strdup
char * av_strdup(const char *s)
Duplicate a string.
Definition: mem.c:272
AV_CODEC_ID_PCM_S32LE
@ AV_CODEC_ID_PCM_S32LE
Definition: codec_id.h:342
AVIAMFAudioElement::demixing_info
AVIAMFParamDefinition * demixing_info
Demixing information used to reconstruct a scalable channel audio representation.
Definition: iamf.h:376
AVIAMFDemixingInfo::dmixp_mode
unsigned int dmixp_mode
Pre-defined combination of demixing parameters.
Definition: iamf.h:140
mem.h
AVIAMFSubmix::output_mix_config
AVIAMFParamDefinition * output_mix_config
Information required for post-processing the mixed audio signal to generate the audio signal for play...
Definition: iamf.h:595
AVIAMFLayer::ambisonics_mode
enum AVIAMFAmbisonicsMode ambisonics_mode
Ambisonics mode as defined in section 3.6.3 of IAMF.
Definition: iamf.h:328
sample_format
enum AVSampleFormat sample_format
Definition: mediacodecdec_common.c:101
flush_put_bits
static void flush_put_bits(PutBitContext *s)
Pad the end of the output stream with zeros.
Definition: put_bits.h:143
AV_CHANNEL_LAYOUT_BINAURAL
#define AV_CHANNEL_LAYOUT_BINAURAL
Definition: channel_layout.h:427
AV_CHANNEL_LAYOUT_MONO
#define AV_CHANNEL_LAYOUT_MONO
Definition: channel_layout.h:392
AV_IAMF_SUBMIX_LAYOUT_TYPE_BINAURAL
@ AV_IAMF_SUBMIX_LAYOUT_TYPE_BINAURAL
The layout is binaural.
Definition: iamf.h:505
AVIAMFLayer::flags
unsigned int flags
A bitmask which may contain a combination of AV_IAMF_LAYER_FLAG_* flags.
Definition: iamf.h:302
av_free
#define av_free(p)
Definition: tableprint_vlc.h:33
AVIAMFLayer::output_gain
AVRational output_gain
Output gain as defined in section 3.6.2 of IAMF.
Definition: iamf.h:316
AVCodecParameters::codec_id
enum AVCodecID codec_id
Specific type of the encoded data (the codec used).
Definition: codec_par.h:55
av_dict_set
int av_dict_set(AVDictionary **pm, const char *key, const char *value, int flags)
Set the given entry in *pm, overwriting an existing entry.
Definition: dict.c:88
AVIAMFSubmixElement::element_mix_config
AVIAMFParamDefinition * element_mix_config
Information required required for applying any processing to the referenced and rendered Audio Elemen...
Definition: iamf.h:461
AV_CHAN_AMBISONIC_BASE
@ AV_CHAN_AMBISONIC_BASE
Range of channels between AV_CHAN_AMBISONIC_BASE and AV_CHAN_AMBISONIC_END represent Ambisonic compon...
Definition: channel_layout.h:108
AVIAMFParamDefinition::parameter_rate
unsigned int parameter_rate
Sample rate for the paremeter substream.
Definition: iamf.h:222
ff_iamf_scalable_ch_layouts
const AVChannelLayout ff_iamf_scalable_ch_layouts[10]
Definition: iamf.c:27
AVIAMFSubmixElement
Submix element as defined in section 3.7 of IAMF.
Definition: iamf.h:446
AV_IAMF_AUDIO_ELEMENT_TYPE_CHANNEL
@ AV_IAMF_AUDIO_ELEMENT_TYPE_CHANNEL
Definition: iamf.h:345
IAMFAudioElement::codec_config_id
unsigned int codec_config_id
Definition: iamf.h:101
av_log
#define av_log(a,...)
Definition: tableprint_vlc.h:27
AVERROR_INVALIDDATA
#define AVERROR_INVALIDDATA
Invalid data found when processing input.
Definition: error.h:61
ffio_read_size
int ffio_read_size(AVIOContext *s, unsigned char *buf, int size)
Read size bytes from AVIOContext into buf.
Definition: aviobuf.c:662
AVIAMFAudioElement::recon_gain_info
AVIAMFParamDefinition * recon_gain_info
Recon gain information used to reconstruct a scalable channel audio representation.
Definition: iamf.h:383
IAMFMixPresentation::mix
AVIAMFMixPresentation * mix
mix backs cmix iff the AVIAMFMixPresentation is owned by this structure.
Definition: iamf.h:113
scalable_channel_layout_config
static int scalable_channel_layout_config(void *s, AVIOContext *pb, IAMFAudioElement *audio_element, const IAMFCodecConfig *codec_config)
Definition: iamf_parse.c:338
flac.h
AV_RB24
uint64_t_TMPL AV_WL64 unsigned int_TMPL AV_WL32 unsigned int_TMPL AV_WL24 unsigned int_TMPL AV_WL16 uint64_t_TMPL AV_WB64 unsigned int_TMPL AV_WB32 unsigned int_TMPL AV_RB24
Definition: bytestream.h:97
IAMFSubStream::codecpar
AVCodecParameters * codecpar
Definition: iamf.h:86
put_bits.h
IAMFCodecConfig::audio_roll_distance
int audio_roll_distance
Definition: iamf.h:71
IAMFMixPresentation::mix_presentation_id
unsigned int mix_presentation_id
Definition: iamf.h:114
AV_CODEC_ID_PCM_S24BE
@ AV_CODEC_ID_PCM_S24BE
Definition: codec_id.h:347
AVChannelCustom::id
enum AVChannel id
Definition: channel_layout.h:282
skip
static void BS_FUNC() skip(BSCTX *bc, unsigned int n)
Skip n bits in the buffer.
Definition: bitstream_template.h:375
AV_WL16A
#define AV_WL16A(p, v)
Definition: intreadwrite.h:557
AV_IAMF_PARAMETER_DEFINITION_DEMIXING
@ AV_IAMF_PARAMETER_DEFINITION_DEMIXING
Subblocks are of struct type AVIAMFDemixingInfo.
Definition: iamf.h:177
MPEG4AudioConfig::sample_rate
int sample_rate
Definition: mpeg4audio.h:32