FFmpeg
cafdec.c
Go to the documentation of this file.
1 /*
2  * Core Audio Format demuxer
3  * Copyright (c) 2007 Justin Ruggles
4  * Copyright (c) 2009 Peter Ross
5  *
6  * This file is part of FFmpeg.
7  *
8  * FFmpeg is free software; you can redistribute it and/or
9  * modify it under the terms of the GNU Lesser General Public
10  * License as published by the Free Software Foundation; either
11  * version 2.1 of the License, or (at your option) any later version.
12  *
13  * FFmpeg is distributed in the hope that it will be useful,
14  * but WITHOUT ANY WARRANTY; without even the implied warranty of
15  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
16  * Lesser General Public License for more details.
17  *
18  * You should have received a copy of the GNU Lesser General Public
19  * License along with FFmpeg; if not, write to the Free Software
20  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
21  */
22 
23 /**
24  * @file
25  * Core Audio Format demuxer
26  */
27 
28 #include <inttypes.h>
29 
30 #include "avformat.h"
31 #include "internal.h"
32 #include "isom.h"
33 #include "mov_chan.h"
34 #include "libavutil/intreadwrite.h"
35 #include "libavutil/intfloat.h"
36 #include "libavutil/dict.h"
37 #include "caf.h"
38 
39 typedef struct CafContext {
40  int bytes_per_packet; ///< bytes in a packet, or 0 if variable
41  int frames_per_packet; ///< frames in a packet, or 0 if variable
42  int64_t num_bytes; ///< total number of bytes in stream
43 
44  int64_t packet_cnt; ///< packet counter
45  int64_t frame_cnt; ///< frame counter
46 
47  int64_t data_start; ///< data start position, in bytes
48  int64_t data_size; ///< raw data size, in bytes
49 } CafContext;
50 
51 static int probe(const AVProbeData *p)
52 {
53  if (AV_RB32(p->buf) == MKBETAG('c','a','f','f') && AV_RB16(&p->buf[4]) == 1)
54  return AVPROBE_SCORE_MAX;
55  return 0;
56 }
57 
58 /** Read audio description chunk */
60 {
61  AVIOContext *pb = s->pb;
62  CafContext *caf = s->priv_data;
63  AVStream *st;
64  int flags;
65 
66  /* new audio stream */
67  st = avformat_new_stream(s, NULL);
68  if (!st)
69  return AVERROR(ENOMEM);
70 
71  /* parse format description */
74  st->codecpar->codec_tag = avio_rl32(pb);
75  flags = avio_rb32(pb);
76  caf->bytes_per_packet = avio_rb32(pb);
78  caf->frames_per_packet = avio_rb32(pb);
79  st->codecpar->channels = avio_rb32(pb);
81 
82  /* calculate bit rate for constant size packets */
83  if (caf->frames_per_packet > 0 && caf->bytes_per_packet > 0) {
84  st->codecpar->bit_rate = (uint64_t)st->codecpar->sample_rate * (uint64_t)caf->bytes_per_packet * 8
85  / (uint64_t)caf->frames_per_packet;
86  } else {
87  st->codecpar->bit_rate = 0;
88  }
89 
90  /* determine codec */
91  if (st->codecpar->codec_tag == MKTAG('l','p','c','m'))
93  else
95  return 0;
96 }
97 
98 /** Read magic cookie chunk */
99 static int read_kuki_chunk(AVFormatContext *s, int64_t size)
100 {
101  AVIOContext *pb = s->pb;
102  AVStream *st = s->streams[0];
103 
105  return -1;
106 
107  if (st->codecpar->codec_id == AV_CODEC_ID_AAC) {
108  /* The magic cookie format for AAC is an mp4 esds atom.
109  The lavc AAC decoder requires the data from the codec specific
110  description as extradata input. */
111  int strt, skip;
112 
113  strt = avio_tell(pb);
114  ff_mov_read_esds(s, pb);
115  skip = size - (avio_tell(pb) - strt);
116  if (skip < 0 || !st->codecpar->extradata ||
118  av_log(s, AV_LOG_ERROR, "invalid AAC magic cookie\n");
119  return AVERROR_INVALIDDATA;
120  }
121  avio_skip(pb, skip);
122  } else if (st->codecpar->codec_id == AV_CODEC_ID_ALAC) {
123 #define ALAC_PREAMBLE 12
124 #define ALAC_HEADER 36
125 #define ALAC_NEW_KUKI 24
126  uint8_t preamble[12];
127  if (size < ALAC_NEW_KUKI) {
128  av_log(s, AV_LOG_ERROR, "invalid ALAC magic cookie\n");
129  avio_skip(pb, size);
130  return AVERROR_INVALIDDATA;
131  }
132  if (avio_read(pb, preamble, ALAC_PREAMBLE) != ALAC_PREAMBLE) {
133  av_log(s, AV_LOG_ERROR, "failed to read preamble\n");
134  return AVERROR_INVALIDDATA;
135  }
136 
137  av_freep(&st->codecpar->extradata);
139  return AVERROR(ENOMEM);
140 
141  /* For the old style cookie, we skip 12 bytes, then read 36 bytes.
142  * The new style cookie only contains the last 24 bytes of what was
143  * 36 bytes in the old style cookie, so we fabricate the first 12 bytes
144  * in that case to maintain compatibility. */
145  if (!memcmp(&preamble[4], "frmaalac", 8)) {
146  if (size < ALAC_PREAMBLE + ALAC_HEADER) {
147  av_log(s, AV_LOG_ERROR, "invalid ALAC magic cookie\n");
148  av_freep(&st->codecpar->extradata);
149  return AVERROR_INVALIDDATA;
150  }
151  if (avio_read(pb, st->codecpar->extradata, ALAC_HEADER) != ALAC_HEADER) {
152  av_log(s, AV_LOG_ERROR, "failed to read kuki header\n");
153  av_freep(&st->codecpar->extradata);
154  return AVERROR_INVALIDDATA;
155  }
156  avio_skip(pb, size - ALAC_PREAMBLE - ALAC_HEADER);
157  } else {
158  AV_WB32(st->codecpar->extradata, 36);
159  memcpy(&st->codecpar->extradata[4], "alac", 4);
160  AV_WB32(&st->codecpar->extradata[8], 0);
161  memcpy(&st->codecpar->extradata[12], preamble, 12);
162  if (avio_read(pb, &st->codecpar->extradata[24], ALAC_NEW_KUKI - 12) != ALAC_NEW_KUKI - 12) {
163  av_log(s, AV_LOG_ERROR, "failed to read new kuki header\n");
164  av_freep(&st->codecpar->extradata);
165  return AVERROR_INVALIDDATA;
166  }
167  avio_skip(pb, size - ALAC_NEW_KUKI);
168  }
169  } else if (st->codecpar->codec_id == AV_CODEC_ID_OPUS) {
170  // The data layout for Opus is currently unknown, so we do not export
171  // extradata at all. Multichannel streams are not supported.
172  if (st->codecpar->channels > 2) {
173  avpriv_request_sample(s, "multichannel Opus in CAF");
174  return AVERROR_PATCHWELCOME;
175  }
176  avio_skip(pb, size);
177  } else {
178  av_freep(&st->codecpar->extradata);
179  if (ff_get_extradata(s, st->codecpar, pb, size) < 0)
180  return AVERROR(ENOMEM);
181  }
182 
183  return 0;
184 }
185 
186 /** Read packet table chunk */
187 static int read_pakt_chunk(AVFormatContext *s, int64_t size)
188 {
189  AVIOContext *pb = s->pb;
190  AVStream *st = s->streams[0];
191  CafContext *caf = s->priv_data;
192  int64_t pos = 0, ccount, num_packets;
193  int i;
194 
195  ccount = avio_tell(pb);
196 
197  num_packets = avio_rb64(pb);
198  if (num_packets < 0 || INT32_MAX / sizeof(AVIndexEntry) < num_packets)
199  return AVERROR_INVALIDDATA;
200 
201  st->nb_frames = avio_rb64(pb); /* valid frames */
202  st->nb_frames += avio_rb32(pb); /* priming frames */
203  st->nb_frames += avio_rb32(pb); /* remainder frames */
204 
205  st->duration = 0;
206  for (i = 0; i < num_packets; i++) {
207  av_add_index_entry(s->streams[0], pos, st->duration, 0, 0, AVINDEX_KEYFRAME);
210  }
211 
212  if (avio_tell(pb) - ccount > size) {
213  av_log(s, AV_LOG_ERROR, "error reading packet table\n");
214  return AVERROR_INVALIDDATA;
215  }
216  avio_skip(pb, ccount + size - avio_tell(pb));
217 
218  caf->num_bytes = pos;
219  return 0;
220 }
221 
222 /** Read information chunk */
223 static void read_info_chunk(AVFormatContext *s, int64_t size)
224 {
225  AVIOContext *pb = s->pb;
226  unsigned int i;
227  unsigned int nb_entries = avio_rb32(pb);
228  for (i = 0; i < nb_entries && !avio_feof(pb); i++) {
229  char key[32];
230  char value[1024];
231  avio_get_str(pb, INT_MAX, key, sizeof(key));
232  avio_get_str(pb, INT_MAX, value, sizeof(value));
233  av_dict_set(&s->metadata, key, value, 0);
234  }
235 }
236 
238 {
239  AVIOContext *pb = s->pb;
240  CafContext *caf = s->priv_data;
241  AVStream *st;
242  uint32_t tag = 0;
243  int found_data, ret;
244  int64_t size, pos;
245 
246  avio_skip(pb, 8); /* magic, version, file flags */
247 
248  /* audio description chunk */
249  if (avio_rb32(pb) != MKBETAG('d','e','s','c')) {
250  av_log(s, AV_LOG_ERROR, "desc chunk not present\n");
251  return AVERROR_INVALIDDATA;
252  }
253  size = avio_rb64(pb);
254  if (size != 32)
255  return AVERROR_INVALIDDATA;
256 
257  ret = read_desc_chunk(s);
258  if (ret)
259  return ret;
260  st = s->streams[0];
261 
262  /* parse each chunk */
263  found_data = 0;
264  while (!avio_feof(pb)) {
265 
266  /* stop at data chunk if seeking is not supported or
267  data chunk size is unknown */
268  if (found_data && (caf->data_size < 0 || !(pb->seekable & AVIO_SEEKABLE_NORMAL)))
269  break;
270 
271  tag = avio_rb32(pb);
272  size = avio_rb64(pb);
273  pos = avio_tell(pb);
274  if (avio_feof(pb))
275  break;
276 
277  switch (tag) {
278  case MKBETAG('d','a','t','a'):
279  avio_skip(pb, 4); /* edit count */
280  caf->data_start = avio_tell(pb);
281  caf->data_size = size < 0 ? -1 : size - 4;
282  if (caf->data_size > 0 && (pb->seekable & AVIO_SEEKABLE_NORMAL))
283  avio_skip(pb, caf->data_size);
284  found_data = 1;
285  break;
286 
287  case MKBETAG('c','h','a','n'):
288  if ((ret = ff_mov_read_chan(s, s->pb, st, size)) < 0)
289  return ret;
290  break;
291 
292  /* magic cookie chunk */
293  case MKBETAG('k','u','k','i'):
294  if (read_kuki_chunk(s, size))
295  return AVERROR_INVALIDDATA;
296  break;
297 
298  /* packet table chunk */
299  case MKBETAG('p','a','k','t'):
300  if (read_pakt_chunk(s, size))
301  return AVERROR_INVALIDDATA;
302  break;
303 
304  case MKBETAG('i','n','f','o'):
305  read_info_chunk(s, size);
306  break;
307 
308  default:
310  "skipping CAF chunk: %08"PRIX32" (%s), size %"PRId64"\n",
311  tag, av_fourcc2str(av_bswap32(tag)), size);
312  case MKBETAG('f','r','e','e'):
313  if (size < 0 && found_data)
314  goto found_data;
315  if (size < 0)
316  return AVERROR_INVALIDDATA;
317  break;
318  }
319 
320  if (size > 0) {
321  if (pos > INT64_MAX - size)
322  return AVERROR_INVALIDDATA;
323  avio_skip(pb, FFMAX(0, pos + size - avio_tell(pb)));
324  }
325  }
326 
327  if (!found_data)
328  return AVERROR_INVALIDDATA;
329 
330 found_data:
331  if (caf->bytes_per_packet > 0 && caf->frames_per_packet > 0) {
332  if (caf->data_size > 0)
333  st->nb_frames = (caf->data_size / caf->bytes_per_packet) * caf->frames_per_packet;
334  } else if (st->nb_index_entries && st->duration > 0) {
335  if (st->codecpar->sample_rate && caf->data_size / st->duration > INT64_MAX / st->codecpar->sample_rate / 8) {
336  av_log(s, AV_LOG_ERROR, "Overflow during bit rate calculation %d * 8 * %"PRId64"\n",
337  st->codecpar->sample_rate, caf->data_size / st->duration);
338  return AVERROR_INVALIDDATA;
339  }
340  st->codecpar->bit_rate = st->codecpar->sample_rate * 8LL *
341  (caf->data_size / st->duration);
342  } else {
343  av_log(s, AV_LOG_ERROR, "Missing packet table. It is required when "
344  "block size or frame size are variable.\n");
345  return AVERROR_INVALIDDATA;
346  }
347 
348  avpriv_set_pts_info(st, 64, 1, st->codecpar->sample_rate);
349  st->start_time = 0;
350 
351  /* position the stream at the start of data */
352  if (caf->data_size >= 0)
353  avio_seek(pb, caf->data_start, SEEK_SET);
354 
355  return 0;
356 }
357 
358 #define CAF_MAX_PKT_SIZE 4096
359 
361 {
362  AVIOContext *pb = s->pb;
363  AVStream *st = s->streams[0];
364  CafContext *caf = s->priv_data;
365  int res, pkt_size = 0, pkt_frames = 0;
366  int64_t left = CAF_MAX_PKT_SIZE;
367 
368  if (avio_feof(pb))
369  return AVERROR_EOF;
370 
371  /* don't read past end of data chunk */
372  if (caf->data_size > 0) {
373  left = (caf->data_start + caf->data_size) - avio_tell(pb);
374  if (!left)
375  return AVERROR_EOF;
376  if (left < 0)
377  return AVERROR(EIO);
378  }
379 
380  pkt_frames = caf->frames_per_packet;
381  pkt_size = caf->bytes_per_packet;
382 
383  if (pkt_size > 0 && pkt_frames == 1) {
384  pkt_size = (CAF_MAX_PKT_SIZE / pkt_size) * pkt_size;
385  pkt_size = FFMIN(pkt_size, left);
386  pkt_frames = pkt_size / caf->bytes_per_packet;
387  } else if (st->nb_index_entries) {
388  if (caf->packet_cnt < st->nb_index_entries - 1) {
389  pkt_size = st->index_entries[caf->packet_cnt + 1].pos - st->index_entries[caf->packet_cnt].pos;
390  pkt_frames = st->index_entries[caf->packet_cnt + 1].timestamp - st->index_entries[caf->packet_cnt].timestamp;
391  } else if (caf->packet_cnt == st->nb_index_entries - 1) {
392  pkt_size = caf->num_bytes - st->index_entries[caf->packet_cnt].pos;
393  pkt_frames = st->duration - st->index_entries[caf->packet_cnt].timestamp;
394  } else {
395  return AVERROR(EIO);
396  }
397  }
398 
399  if (pkt_size == 0 || pkt_frames == 0 || pkt_size > left)
400  return AVERROR(EIO);
401 
402  res = av_get_packet(pb, pkt, pkt_size);
403  if (res < 0)
404  return res;
405 
406  pkt->size = res;
407  pkt->stream_index = 0;
408  pkt->dts = pkt->pts = caf->frame_cnt;
409 
410  caf->packet_cnt++;
411  caf->frame_cnt += pkt_frames;
412 
413  return 0;
414 }
415 
416 static int read_seek(AVFormatContext *s, int stream_index,
417  int64_t timestamp, int flags)
418 {
419  AVStream *st = s->streams[0];
420  CafContext *caf = s->priv_data;
421  int64_t pos, packet_cnt, frame_cnt;
422 
423  timestamp = FFMAX(timestamp, 0);
424 
425  if (caf->frames_per_packet > 0 && caf->bytes_per_packet > 0) {
426  /* calculate new byte position based on target frame position */
427  pos = caf->bytes_per_packet * (timestamp / caf->frames_per_packet);
428  if (caf->data_size > 0)
429  pos = FFMIN(pos, caf->data_size);
430  packet_cnt = pos / caf->bytes_per_packet;
431  frame_cnt = caf->frames_per_packet * packet_cnt;
432  } else if (st->nb_index_entries) {
433  packet_cnt = av_index_search_timestamp(st, timestamp, flags);
434  frame_cnt = st->index_entries[packet_cnt].timestamp;
435  pos = st->index_entries[packet_cnt].pos;
436  } else {
437  return -1;
438  }
439 
440  if (avio_seek(s->pb, pos + caf->data_start, SEEK_SET) < 0)
441  return -1;
442 
443  caf->packet_cnt = packet_cnt;
444  caf->frame_cnt = frame_cnt;
445 
446  return 0;
447 }
448 
450  .name = "caf",
451  .long_name = NULL_IF_CONFIG_SMALL("Apple CAF (Core Audio Format)"),
452  .priv_data_size = sizeof(CafContext),
453  .read_probe = probe,
456  .read_seek = read_seek,
457  .codec_tag = (const AVCodecTag* const []){ ff_codec_caf_tags, 0 },
458 };
#define NULL
Definition: coverity.c:32
Bytestream IO Context.
Definition: avio.h:161
#define AVERROR_INVALIDDATA
Invalid data found when processing input.
Definition: error.h:59
static int read_packet(AVFormatContext *s, AVPacket *pkt)
Definition: cafdec.c:360
int av_add_index_entry(AVStream *st, int64_t pos, int64_t timestamp, int size, int distance, int flags)
Add an index entry into a sorted list.
Definition: utils.c:2039
enum AVCodecID ff_codec_get_id(const AVCodecTag *tags, unsigned int tag)
Definition: utils.c:3124
#define AV_LOG_WARNING
Something somehow does not look correct.
Definition: log.h:182
int bytes_per_packet
bytes in a packet, or 0 if variable
Definition: cafdec.c:40
void avpriv_set_pts_info(AVStream *s, int pts_wrap_bits, unsigned int pts_num, unsigned int pts_den)
Set the time base and wrapping info for a given stream.
Definition: utils.c:4882
int64_t pos
Definition: avformat.h:810
#define avpriv_request_sample(...)
enum AVCodecID codec_id
Specific type of the encoded data (the codec used).
Definition: avcodec.h:3953
int size
Definition: avcodec.h:1478
int64_t avio_seek(AVIOContext *s, int64_t offset, int whence)
fseek() equivalent for AVIOContext.
Definition: aviobuf.c:246
AVIndexEntry * index_entries
Only used if the format does not support seeking natively.
Definition: avformat.h:1110
CAF common code.
int64_t avio_skip(AVIOContext *s, int64_t offset)
Skip given number of bytes forward.
Definition: aviobuf.c:331
const char * key
static AVPacket pkt
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_WB24 unsigned int_TMPL AV_RB16
Definition: bytestream.h:87
#define CAF_MAX_PKT_SIZE
Definition: cafdec.c:358
static int read_seek(AVFormatContext *s, int stream_index, int64_t timestamp, int flags)
Definition: cafdec.c:416
static int read_header(AVFormatContext *s)
Definition: cafdec.c:237
Format I/O context.
Definition: avformat.h:1358
#define ALAC_PREAMBLE
Public dictionary API.
static av_always_inline double av_int2double(uint64_t i)
Reinterpret a 64-bit integer as a double.
Definition: intfloat.h:60
uint8_t
static int read_kuki_chunk(AVFormatContext *s, int64_t size)
Read magic cookie chunk.
Definition: cafdec.c:99
unsigned int avio_rb32(AVIOContext *s)
Definition: aviobuf.c:801
GLsizei GLboolean const GLfloat * value
Definition: opengl_enc.c:108
AVStream * avformat_new_stream(AVFormatContext *s, const AVCodec *c)
Add a new stream to a media file.
Definition: utils.c:4455
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_RB32
Definition: bytestream.h:87
AVStream ** streams
A list of all streams in the file.
Definition: avformat.h:1426
uint32_t tag
Definition: movenc.c:1496
#define AVERROR_EOF
End of file.
Definition: error.h:55
int av_get_packet(AVIOContext *s, AVPacket *pkt, int size)
Allocate and read the payload of a packet and initialize its fields with default values.
Definition: utils.c:310
ptrdiff_t size
Definition: opengl_enc.c:100
uint64_t avio_rb64(AVIOContext *s)
Definition: aviobuf.c:922
static av_always_inline int64_t avio_tell(AVIOContext *s)
ftell() equivalent for AVIOContext.
Definition: avio.h:557
#define av_log(a,...)
int avio_read(AVIOContext *s, unsigned char *buf, int size)
Read size bytes from AVIOContext into buf.
Definition: aviobuf.c:648
int64_t bit_rate
The average bitrate of the encoded data (in bits per second).
Definition: avcodec.h:3982
#define AVINDEX_KEYFRAME
Definition: avformat.h:817
#define i(width, name, range_min, range_max)
Definition: cbs_h2645.c:260
#define AV_LOG_ERROR
Something went wrong and cannot losslessly be recovered.
Definition: log.h:176
AVDictionary * metadata
Metadata that applies to the whole file.
Definition: avformat.h:1598
int av_index_search_timestamp(AVStream *st, int64_t timestamp, int flags)
Get the index for a specific timestamp.
Definition: utils.c:2148
int ff_mp4_read_descr_len(AVIOContext *pb)
Definition: isom.c:462
unsigned int avio_rl32(AVIOContext *s)
Definition: aviobuf.c:770
int64_t timestamp
Timestamp in AVStream.time_base units, preferably the time from which on correctly decoded frames are...
Definition: avformat.h:811
#define NULL_IF_CONFIG_SMALL(x)
Return NULL if CONFIG_SMALL is true, otherwise the argument without modification. ...
Definition: internal.h:186
#define av_fourcc2str(fourcc)
Definition: avutil.h:348
enum AVMediaType codec_type
General type of the encoded data.
Definition: avcodec.h:3949
int64_t num_bytes
total number of bytes in stream
Definition: cafdec.c:42
#define FFMAX(a, b)
Definition: common.h:94
unsigned char * buf
Buffer must have AVPROBE_PADDING_SIZE of extra allocated bytes filled with zero.
Definition: avformat.h:448
int block_align
Audio only.
Definition: avcodec.h:4070
int seekable
A combination of AVIO_SEEKABLE_ flags or 0 when the stream is not seekable.
Definition: avio.h:260
int ff_alloc_extradata(AVCodecParameters *par, int size)
Allocate extradata with additional AV_INPUT_BUFFER_PADDING_SIZE at end which is always set to 0...
Definition: utils.c:3287
#define FFMIN(a, b)
Definition: common.h:96
int64_t data_start
data start position, in bytes
Definition: cafdec.c:47
int64_t data_size
raw data size, in bytes
Definition: cafdec.c:48
AVInputFormat ff_caf_demuxer
Definition: cafdec.c:449
#define s(width, name)
Definition: cbs_vp9.c:257
#define ALAC_NEW_KUKI
int ff_mov_read_chan(AVFormatContext *s, AVIOContext *pb, AVStream *st, int64_t size)
Read &#39;chan&#39; tag from the input stream.
Definition: mov_chan.c:547
int ff_mov_read_esds(AVFormatContext *fc, AVIOContext *pb)
Definition: mov_esds.c:23
Stream structure.
Definition: avformat.h:881
#define AVERROR_PATCHWELCOME
Not yet implemented in FFmpeg, patches welcome.
Definition: error.h:62
#define AVIO_SEEKABLE_NORMAL
Seeking works like for a local file.
Definition: avio.h:40
#define av_bswap32
Definition: bswap.h:33
AVIOContext * pb
I/O context.
Definition: avformat.h:1400
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:206
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:70
int nb_index_entries
Definition: avformat.h:1112
#define AV_WB32(p, v)
Definition: intreadwrite.h:419
int frames_per_packet
frames in a packet, or 0 if variable
Definition: cafdec.c:41
static void read_info_chunk(AVFormatContext *s, int64_t size)
Read information chunk.
Definition: cafdec.c:223
static enum AVCodecID ff_mov_get_lpcm_codec_id(int bps, int flags)
Compute codec id for &#39;lpcm&#39; tag.
Definition: isom.h:370
This structure contains the data a format has to probe a file.
Definition: avformat.h:446
static int read_pakt_chunk(AVFormatContext *s, int64_t size)
Read packet table chunk.
Definition: cafdec.c:187
#define flags(name, subs,...)
Definition: cbs_av1.c:561
static int read_probe(const AVProbeData *pd)
Definition: jvdec.c:55
int64_t duration
Decoding: duration of the stream, in stream time base.
Definition: avformat.h:930
int sample_rate
Audio only.
Definition: avcodec.h:4063
#define AVPROBE_SCORE_MAX
maximum score
Definition: avformat.h:458
Main libavformat public API header.
int64_t start_time
Decoding: pts of the first frame of the stream in presentation order, in stream time base...
Definition: avformat.h:920
int ff_get_extradata(AVFormatContext *s, AVCodecParameters *par, AVIOContext *pb, int size)
Allocate extradata with additional AV_INPUT_BUFFER_PADDING_SIZE at end which is always set to 0 and f...
Definition: utils.c:3305
int64_t nb_frames
number of frames in this stream if known or 0
Definition: avformat.h:932
#define ALAC_HEADER
#define MKBETAG(a, b, c, d)
Definition: common.h:367
#define AV_INPUT_BUFFER_PADDING_SIZE
Required number of additionally allocated bytes at the end of the input bitstream for decoding...
Definition: avcodec.h:790
void * priv_data
Format private data.
Definition: avformat.h:1386
int bits_per_coded_sample
The number of bits per sample in the codedwords.
Definition: avcodec.h:3995
uint8_t * extradata
Extra binary data needed for initializing the decoder, codec-dependent.
Definition: avcodec.h:3967
int channels
Audio only.
Definition: avcodec.h:4059
int64_t dts
Decompression timestamp in AVStream->time_base units; the time at which the packet is decompressed...
Definition: avcodec.h:1476
static int probe(const AVProbeData *p)
Definition: cafdec.c:51
#define av_freep(p)
const char * name
A comma separated list of short names for the format.
Definition: avformat.h:654
AVCodecParameters * codecpar
Codec parameters associated with this stream.
Definition: avformat.h:1028
int avio_get_str(AVIOContext *pb, int maxlen, char *buf, int buflen)
Read a string from pb into buf.
Definition: aviobuf.c:880
int avio_feof(AVIOContext *s)
Similar to feof() but also returns nonzero on read errors.
Definition: aviobuf.c:358
uint32_t codec_tag
Additional information about the codec (corresponds to the AVI FOURCC).
Definition: avcodec.h:3957
static int read_desc_chunk(AVFormatContext *s)
Read audio description chunk.
Definition: cafdec.c:59
int stream_index
Definition: avcodec.h:1479
const AVCodecTag ff_codec_caf_tags[]
Known codec tags for CAF.
Definition: caf.c:34
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
#define MKTAG(a, b, c, d)
Definition: common.h:366
This structure stores compressed data.
Definition: avcodec.h:1454
int64_t packet_cnt
packet counter
Definition: cafdec.c:44
int64_t frame_cnt
frame counter
Definition: cafdec.c:45
int64_t pts
Presentation timestamp in AVStream->time_base units; the time at which the decompressed packet will b...
Definition: avcodec.h:1470