FFmpeg
4xm.c
Go to the documentation of this file.
1 /*
2  * 4X Technologies .4xm File Demuxer (no muxer)
3  * Copyright (c) 2003 The FFmpeg project
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 /**
23  * @file
24  * 4X Technologies file demuxer
25  * by Mike Melanson (melanson@pcisys.net)
26  * for more information on the .4xm file format, visit:
27  * http://www.pcisys.net/~melanson/codecs/
28  */
29 
30 #include "libavutil/intreadwrite.h"
31 #include "libavutil/intfloat.h"
32 #include "libavcodec/internal.h"
33 #include "avformat.h"
34 #include "internal.h"
35 
36 #define RIFF_TAG MKTAG('R', 'I', 'F', 'F')
37 #define FOURXMV_TAG MKTAG('4', 'X', 'M', 'V')
38 #define LIST_TAG MKTAG('L', 'I', 'S', 'T')
39 #define HEAD_TAG MKTAG('H', 'E', 'A', 'D')
40 #define TRK__TAG MKTAG('T', 'R', 'K', '_')
41 #define MOVI_TAG MKTAG('M', 'O', 'V', 'I')
42 #define VTRK_TAG MKTAG('V', 'T', 'R', 'K')
43 #define STRK_TAG MKTAG('S', 'T', 'R', 'K')
44 #define std__TAG MKTAG('s', 't', 'd', '_')
45 #define name_TAG MKTAG('n', 'a', 'm', 'e')
46 #define vtrk_TAG MKTAG('v', 't', 'r', 'k')
47 #define strk_TAG MKTAG('s', 't', 'r', 'k')
48 #define ifrm_TAG MKTAG('i', 'f', 'r', 'm')
49 #define pfrm_TAG MKTAG('p', 'f', 'r', 'm')
50 #define cfrm_TAG MKTAG('c', 'f', 'r', 'm')
51 #define ifr2_TAG MKTAG('i', 'f', 'r', '2')
52 #define pfr2_TAG MKTAG('p', 'f', 'r', '2')
53 #define cfr2_TAG MKTAG('c', 'f', 'r', '2')
54 #define snd__TAG MKTAG('s', 'n', 'd', '_')
55 
56 #define vtrk_SIZE 0x44
57 #define strk_SIZE 0x28
58 
59 #define GET_LIST_HEADER() \
60  fourcc_tag = avio_rl32(pb); \
61  size = avio_rl32(pb); \
62  if (fourcc_tag != LIST_TAG) { \
63  ret = AVERROR_INVALIDDATA; \
64  goto fail; \
65  } \
66  fourcc_tag = avio_rl32(pb);
67 
68 typedef struct AudioTrack {
70  int bits;
71  int channels;
73  int adpcm;
74  int64_t audio_pts;
75 } AudioTrack;
76 
77 typedef struct FourxmDemuxContext {
81 
82  int64_t video_pts;
85 
86 static int fourxm_probe(const AVProbeData *p)
87 {
88  if ((AV_RL32(&p->buf[0]) != RIFF_TAG) ||
89  (AV_RL32(&p->buf[8]) != FOURXMV_TAG))
90  return 0;
91 
92  return AVPROBE_SCORE_MAX;
93 }
94 
96  FourxmDemuxContext *fourxm, uint8_t *buf, int size,
97  int left)
98 {
99  AVStream *st;
100  /* check that there is enough data */
101  if (size != vtrk_SIZE || left < size + 8) {
102  return AVERROR_INVALIDDATA;
103  }
104 
105  /* allocate a new AVStream */
106  st = avformat_new_stream(s, NULL);
107  if (!st)
108  return AVERROR(ENOMEM);
109 
110  avpriv_set_pts_info(st, 60, fourxm->fps.den, fourxm->fps.num);
111 
112  fourxm->video_stream_index = st->index;
113 
116 
118  if (!st->codecpar->extradata)
119  return AVERROR(ENOMEM);
120  st->codecpar->extradata_size = 4;
121  AV_WL32(st->codecpar->extradata, AV_RL32(buf + 16));
122  st->codecpar->width = AV_RL32(buf + 36);
123  st->codecpar->height = AV_RL32(buf + 40);
124 
125  return 0;
126 }
127 
128 
130  FourxmDemuxContext *fourxm, uint8_t *buf, int size,
131  int left)
132 {
133  AVStream *st;
134  int track;
135  /* check that there is enough data */
136  if (size != strk_SIZE || left < size + 8)
137  return AVERROR_INVALIDDATA;
138 
139  track = AV_RL32(buf + 8);
140  if ((unsigned)track >= UINT_MAX / sizeof(AudioTrack) - 1 ||
141  track >= s->max_streams) {
142  av_log(s, AV_LOG_ERROR, "current_track too large\n");
143  return AVERROR_INVALIDDATA;
144  }
145 
146  if (track + 1 > fourxm->track_count) {
147  if (av_reallocp_array(&fourxm->tracks, track + 1, sizeof(AudioTrack)))
148  return AVERROR(ENOMEM);
149  memset(&fourxm->tracks[fourxm->track_count], 0,
150  sizeof(AudioTrack) * (track + 1 - fourxm->track_count));
151  fourxm->track_count = track + 1;
152  } else {
153  if (fourxm->tracks[track].bits)
154  return AVERROR_INVALIDDATA;
155  }
156  fourxm->tracks[track].adpcm = AV_RL32(buf + 12);
157  fourxm->tracks[track].channels = AV_RL32(buf + 36);
158  fourxm->tracks[track].sample_rate = AV_RL32(buf + 40);
159  fourxm->tracks[track].bits = AV_RL32(buf + 44);
160  fourxm->tracks[track].audio_pts = 0;
161 
162  if (fourxm->tracks[track].channels <= 0 ||
163  fourxm->tracks[track].channels > FF_SANE_NB_CHANNELS ||
164  fourxm->tracks[track].sample_rate <= 0 ||
165  fourxm->tracks[track].bits <= 0 ||
166  fourxm->tracks[track].bits > INT_MAX / FF_SANE_NB_CHANNELS) {
167  av_log(s, AV_LOG_ERROR, "audio header invalid\n");
168  return AVERROR_INVALIDDATA;
169  }
170  if (!fourxm->tracks[track].adpcm && fourxm->tracks[track].bits<8) {
171  av_log(s, AV_LOG_ERROR, "bits unspecified for non ADPCM\n");
172  return AVERROR_INVALIDDATA;
173  }
174 
175  if (fourxm->tracks[track].sample_rate > INT64_MAX / fourxm->tracks[track].bits / fourxm->tracks[track].channels) {
176  av_log(s, AV_LOG_ERROR, "Overflow during bit rate calculation %d * %d * %d\n",
177  fourxm->tracks[track].sample_rate, fourxm->tracks[track].bits, fourxm->tracks[track].channels);
178  return AVERROR_INVALIDDATA;
179  }
180 
181  /* allocate a new AVStream */
182  st = avformat_new_stream(s, NULL);
183  if (!st)
184  return AVERROR(ENOMEM);
185 
186  st->id = track;
187  avpriv_set_pts_info(st, 60, 1, fourxm->tracks[track].sample_rate);
188 
189  fourxm->tracks[track].stream_index = st->index;
190 
192  st->codecpar->codec_tag = 0;
193  st->codecpar->channels = fourxm->tracks[track].channels;
194  st->codecpar->sample_rate = fourxm->tracks[track].sample_rate;
195  st->codecpar->bits_per_coded_sample = fourxm->tracks[track].bits;
196  st->codecpar->bit_rate = (int64_t)st->codecpar->channels *
197  st->codecpar->sample_rate *
199  st->codecpar->block_align = st->codecpar->channels *
201 
202  if (fourxm->tracks[track].adpcm){
204  } else if (st->codecpar->bits_per_coded_sample == 8) {
206  } else
208 
209  return 0;
210 }
211 
213 {
214  AVIOContext *pb = s->pb;
215  unsigned int fourcc_tag;
216  unsigned int size;
217  int header_size;
218  FourxmDemuxContext *fourxm = s->priv_data;
219  unsigned char *header = NULL;
220  int i, ret;
221 
222  fourxm->track_count = 0;
223  fourxm->tracks = NULL;
224  fourxm->fps = (AVRational){1,1};
225  fourxm->video_stream_index = -1;
226 
227  /* skip the first 3 32-bit numbers */
228  avio_skip(pb, 12);
229 
230  /* check for LIST-HEAD */
231  GET_LIST_HEADER();
232  header_size = size - 4;
233  if (fourcc_tag != HEAD_TAG || header_size < 0)
234  return AVERROR_INVALIDDATA;
235 
236  /* allocate space for the header and load the whole thing */
237  header = av_malloc(header_size);
238  if (!header)
239  return AVERROR(ENOMEM);
240  if (avio_read(pb, header, header_size) != header_size) {
241  av_free(header);
242  return AVERROR(EIO);
243  }
244 
245  /* take the lazy approach and search for any and all vtrk and strk chunks */
246  for (i = 0; i < header_size - 8; i++) {
247  fourcc_tag = AV_RL32(&header[i]);
248  size = AV_RL32(&header[i + 4]);
249  if (size > header_size - i - 8 && (fourcc_tag == vtrk_TAG || fourcc_tag == strk_TAG)) {
250  av_log(s, AV_LOG_ERROR, "chunk larger than array %d>%d\n", size, header_size - i - 8);
252  goto fail;
253  }
254 
255  if (fourcc_tag == std__TAG) {
256  if (header_size - i < 16) {
257  av_log(s, AV_LOG_ERROR, "std TAG truncated\n");
259  goto fail;
260  }
261  fourxm->fps = av_d2q(av_int2float(AV_RL32(&header[i + 12])), 10000);
262  } else if (fourcc_tag == vtrk_TAG) {
263  if ((ret = parse_vtrk(s, fourxm, header + i, size,
264  header_size - i)) < 0)
265  goto fail;
266 
267  i += 8 + size;
268  } else if (fourcc_tag == strk_TAG) {
269  if ((ret = parse_strk(s, fourxm, header + i, size,
270  header_size - i)) < 0)
271  goto fail;
272 
273  i += 8 + size;
274  }
275  }
276 
277  /* skip over the LIST-MOVI chunk (which is where the stream should be */
278  GET_LIST_HEADER();
279  if (fourcc_tag != MOVI_TAG) {
281  goto fail;
282  }
283 
284  av_free(header);
285  /* initialize context members */
286  fourxm->video_pts = -1; /* first frame will push to 0 */
287 
288  return 0;
289 fail:
290  av_free(header);
291  return ret;
292 }
293 
295  AVPacket *pkt)
296 {
297  FourxmDemuxContext *fourxm = s->priv_data;
298  AVIOContext *pb = s->pb;
299  unsigned int fourcc_tag;
300  unsigned int size;
301  int ret = 0;
302  unsigned int track_number;
303  int packet_read = 0;
304  unsigned char header[8];
305  int64_t audio_frame_count;
306 
307  while (!packet_read) {
308  if ((ret = avio_read(s->pb, header, 8)) < 0)
309  return ret;
310  fourcc_tag = AV_RL32(&header[0]);
311  size = AV_RL32(&header[4]);
312  if (avio_feof(pb))
313  return AVERROR(EIO);
314  switch (fourcc_tag) {
315  case LIST_TAG:
316  /* this is a good time to bump the video pts */
317  fourxm->video_pts++;
318 
319  /* skip the LIST-* tag and move on to the next fourcc */
320  avio_rl32(pb);
321  break;
322 
323  case ifrm_TAG:
324  case pfrm_TAG:
325  case cfrm_TAG:
326  case ifr2_TAG:
327  case pfr2_TAG:
328  case cfr2_TAG:
329  /* allocate 8 more bytes than 'size' to account for fourcc
330  * and size */
331  if (size > INT_MAX - AV_INPUT_BUFFER_PADDING_SIZE - 8)
332  return AVERROR_INVALIDDATA;
333  if (fourxm->video_stream_index < 0)
334  return AVERROR_INVALIDDATA;
335  if ((ret = av_new_packet(pkt, size + 8)) < 0)
336  return ret;
338  pkt->pts = fourxm->video_pts;
339  pkt->pos = avio_tell(s->pb);
340  memcpy(pkt->data, header, 8);
341  ret = avio_read(s->pb, &pkt->data[8], size);
342 
343  if (ret < 0) {
345  } else {
346  packet_read = 1;
347  av_shrink_packet(pkt, ret + 8);
348  }
349  break;
350 
351  case snd__TAG:
352  track_number = avio_rl32(pb);
353  avio_skip(pb, 4);
354  size -= 8;
355 
356  if (track_number < fourxm->track_count &&
357  fourxm->tracks[track_number].channels > 0) {
358  ret = av_get_packet(s->pb, pkt, size);
359  if (ret < 0)
360  return ret;
361  pkt->stream_index =
362  fourxm->tracks[track_number].stream_index;
363  pkt->pts = fourxm->tracks[track_number].audio_pts;
364  packet_read = 1;
365 
366  /* pts accounting */
368  if (fourxm->tracks[track_number].adpcm)
369  audio_frame_count -= 2 * (fourxm->tracks[track_number].channels);
370  audio_frame_count /= fourxm->tracks[track_number].channels;
371  if (fourxm->tracks[track_number].adpcm) {
372  audio_frame_count *= 2;
373  } else
375  (fourxm->tracks[track_number].bits / 8);
376  fourxm->tracks[track_number].audio_pts += audio_frame_count;
377  } else {
378  avio_skip(pb, size);
379  }
380  break;
381 
382  default:
383  avio_skip(pb, size);
384  break;
385  }
386  }
387  return ret;
388 }
389 
391 {
392  FourxmDemuxContext *fourxm = s->priv_data;
393 
394  av_freep(&fourxm->tracks);
395 
396  return 0;
397 }
398 
400  .name = "4xm",
401  .long_name = NULL_IF_CONFIG_SMALL("4X Technologies"),
402  .priv_data_size = sizeof(FourxmDemuxContext),
403  .flags_internal = FF_FMT_INIT_CLEANUP,
408 };
AV_CODEC_ID_PCM_S16LE
@ AV_CODEC_ID_PCM_S16LE
Definition: codec_id.h:314
av_packet_unref
void av_packet_unref(AVPacket *pkt)
Wipe the packet.
Definition: avpacket.c:424
fourxm_read_packet
static int fourxm_read_packet(AVFormatContext *s, AVPacket *pkt)
Definition: 4xm.c:294
AVCodecParameters::extradata
uint8_t * extradata
Extra binary data needed for initializing the decoder, codec-dependent.
Definition: codec_par.h:74
FF_FMT_INIT_CLEANUP
#define FF_FMT_INIT_CLEANUP
For an AVInputFormat with this flag set read_close() needs to be called by the caller upon read_heade...
Definition: internal.h:49
AudioTrack::adpcm
int adpcm
Definition: 4xm.c:73
AudioTrack::audio_pts
int64_t audio_pts
Definition: 4xm.c:74
FourxmDemuxContext::tracks
AudioTrack * tracks
Definition: 4xm.c:80
FourxmDemuxContext::video_pts
int64_t video_pts
Definition: 4xm.c:82
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
avformat_new_stream
AVStream * avformat_new_stream(AVFormatContext *s, const AVCodec *c)
Add a new stream to a media file.
Definition: utils.c:768
AVCodecParameters::codec_type
enum AVMediaType codec_type
General type of the encoded data.
Definition: codec_par.h:56
AV_WL32
#define AV_WL32(p, v)
Definition: intreadwrite.h:426
internal.h
AVPacket::data
uint8_t * data
Definition: packet.h:373
ff_fourxm_demuxer
const AVInputFormat ff_fourxm_demuxer
Definition: 4xm.c:399
AVCodecParameters::codec_tag
uint32_t codec_tag
Additional information about the codec (corresponds to the AVI FOURCC).
Definition: codec_par.h:64
intfloat.h
AudioTrack::sample_rate
int sample_rate
Definition: 4xm.c:69
av_malloc
#define av_malloc(s)
Definition: tableprint_vlc.h:31
AVPROBE_SCORE_MAX
#define AVPROBE_SCORE_MAX
maximum score
Definition: avformat.h:459
AVCodecParameters::channels
int channels
Audio only.
Definition: codec_par.h:166
fourxm_probe
static int fourxm_probe(const AVProbeData *p)
Definition: 4xm.c:86
fail
#define fail()
Definition: checkasm.h:128
av_int2float
static av_always_inline float av_int2float(uint32_t i)
Reinterpret a 32-bit integer as a float.
Definition: intfloat.h:40
av_shrink_packet
void av_shrink_packet(AVPacket *pkt, int size)
Reduce packet size, correctly zeroing padding.
Definition: avpacket.c:114
fourxm_read_header
static int fourxm_read_header(AVFormatContext *s)
Definition: 4xm.c:212
read_close
static av_cold int read_close(AVFormatContext *ctx)
Definition: libcdio.c:141
avio_tell
static av_always_inline int64_t avio_tell(AVIOContext *s)
ftell() equivalent for AVIOContext.
Definition: avio.h:504
pfrm_TAG
#define pfrm_TAG
Definition: 4xm.c:49
AudioTrack::channels
int channels
Definition: 4xm.c:71
HEAD_TAG
#define HEAD_TAG
Definition: 4xm.c:39
AVRational::num
int num
Numerator.
Definition: rational.h:59
cfrm_TAG
#define cfrm_TAG
Definition: 4xm.c:50
pkt
AVPacket * pkt
Definition: movenc.c:59
AV_LOG_ERROR
#define AV_LOG_ERROR
Something went wrong and cannot losslessly be recovered.
Definition: log.h:180
AVInputFormat
Definition: avformat.h:650
FOURXMV_TAG
#define FOURXMV_TAG
Definition: 4xm.c:37
snd__TAG
#define snd__TAG
Definition: 4xm.c:54
MOVI_TAG
#define MOVI_TAG
Definition: 4xm.c:41
AV_CODEC_ID_4XM
@ AV_CODEC_ID_4XM
Definition: codec_id.h:84
intreadwrite.h
s
#define s(width, name)
Definition: cbs_vp9.c:257
av_new_packet
int av_new_packet(AVPacket *pkt, int size)
Allocate the payload of a packet and initialize its fields with default values.
Definition: avpacket.c:99
AVInputFormat::name
const char * name
A comma separated list of short names for the format.
Definition: avformat.h:655
AVProbeData::buf
unsigned char * buf
Buffer must have AVPROBE_PADDING_SIZE of extra allocated bytes filled with zero.
Definition: avformat.h:449
AVMEDIA_TYPE_AUDIO
@ AVMEDIA_TYPE_AUDIO
Definition: avutil.h:202
AVCodecParameters::width
int width
Video only.
Definition: codec_par.h:126
vtrk_SIZE
#define vtrk_SIZE
Definition: 4xm.c:56
strk_TAG
#define strk_TAG
Definition: 4xm.c:47
if
if(ret)
Definition: filter_design.txt:179
AVFormatContext
Format I/O context.
Definition: avformat.h:1200
AVStream::codecpar
AVCodecParameters * codecpar
Codec parameters associated with this stream.
Definition: avformat.h:1095
read_header
static int read_header(FFV1Context *f)
Definition: ffv1dec.c:527
NULL
#define NULL
Definition: coverity.c:32
read_probe
static int read_probe(const AVProbeData *pd)
Definition: jvdec.c:55
fourxm_read_close
static int fourxm_read_close(AVFormatContext *s)
Definition: 4xm.c:390
parse_strk
static int parse_strk(AVFormatContext *s, FourxmDemuxContext *fourxm, uint8_t *buf, int size, int left)
Definition: 4xm.c:129
AVRational
Rational number (pair of numerator and denominator).
Definition: rational.h:58
FourxmDemuxContext::fps
AVRational fps
Definition: 4xm.c:83
audio_frame_count
static int audio_frame_count
Definition: demuxing_decoding.c:57
strk_SIZE
#define strk_SIZE
Definition: 4xm.c:57
AVProbeData
This structure contains the data a format has to probe a file.
Definition: avformat.h:447
RIFF_TAG
#define RIFF_TAG
Definition: 4xm.c:36
FourxmDemuxContext::video_stream_index
int video_stream_index
Definition: 4xm.c:78
AVCodecParameters::sample_rate
int sample_rate
Audio only.
Definition: codec_par.h:170
AVCodecParameters::extradata_size
int extradata_size
Size of the extradata content in bytes.
Definition: codec_par.h:78
AudioTrack
Definition: 4xm.c:68
avio_rl32
unsigned int avio_rl32(AVIOContext *s)
Definition: aviobuf.c:759
AVIOContext
Bytestream IO Context.
Definition: avio.h:161
NULL_IF_CONFIG_SMALL
#define NULL_IF_CONFIG_SMALL(x)
Return NULL if CONFIG_SMALL is true, otherwise the argument without modification.
Definition: internal.h:117
size
int size
Definition: twinvq_data.h:10344
cfr2_TAG
#define cfr2_TAG
Definition: 4xm.c:53
vtrk_TAG
#define vtrk_TAG
Definition: 4xm.c:46
header
static const uint8_t header[24]
Definition: sdr2.c:67
av_reallocp_array
int av_reallocp_array(void *ptr, size_t nmemb, size_t size)
Allocate, reallocate, or free an array through a pointer to a pointer.
Definition: mem.c:232
parse_vtrk
static int parse_vtrk(AVFormatContext *s, FourxmDemuxContext *fourxm, uint8_t *buf, int size, int left)
Definition: 4xm.c:95
AudioTrack::stream_index
int stream_index
Definition: 4xm.c:72
GET_LIST_HEADER
#define GET_LIST_HEADER()
Definition: 4xm.c:59
i
#define i(width, name, range_min, range_max)
Definition: cbs_h2645.c:271
AVPacket::pts
int64_t pts
Presentation timestamp in AVStream->time_base units; the time at which the decompressed packet will b...
Definition: packet.h:366
AVCodecParameters::height
int height
Definition: codec_par.h:127
AVCodecParameters::block_align
int block_align
Audio only.
Definition: codec_par.h:177
av_d2q
AVRational av_d2q(double d, int max)
Convert a double precision floating point number to a rational.
Definition: rational.c:106
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:263
av_get_packet
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:197
FourxmDemuxContext
Definition: 4xm.c:77
AVStream::id
int id
Format-specific stream ID.
Definition: avformat.h:949
ret
ret
Definition: filter_design.txt:187
read_packet
static int read_packet(void *opaque, uint8_t *buf, int buf_size)
Definition: avio_reading.c:42
AVStream
Stream structure.
Definition: avformat.h:935
avformat.h
AudioTrack::bits
int bits
Definition: 4xm.c:70
FourxmDemuxContext::track_count
int track_count
Definition: 4xm.c:79
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
AV_RL32
uint64_t_TMPL AV_WL64 unsigned int_TMPL AV_RL32
Definition: bytestream.h:92
AVStream::index
int index
stream index in AVFormatContext
Definition: avformat.h:943
AVRational::den
int den
Denominator.
Definition: rational.h:60
avio_read
int avio_read(AVIOContext *s, unsigned char *buf, int size)
Read size bytes from AVIOContext into buf.
Definition: aviobuf.c:641
avpriv_set_pts_info
void avpriv_set_pts_info(AVStream *st, 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:1195
AVPacket::stream_index
int stream_index
Definition: packet.h:375
avio_skip
int64_t avio_skip(AVIOContext *s, int64_t offset)
Skip given number of bytes forward.
Definition: aviobuf.c:347
ifrm_TAG
#define ifrm_TAG
Definition: 4xm.c:48
AVMEDIA_TYPE_VIDEO
@ AVMEDIA_TYPE_VIDEO
Definition: avutil.h:201
AVCodecParameters::bits_per_coded_sample
int bits_per_coded_sample
The number of bits per sample in the codedwords.
Definition: codec_par.h:102
AV_CODEC_ID_PCM_U8
@ AV_CODEC_ID_PCM_U8
Definition: codec_id.h:319
av_free
#define av_free(p)
Definition: tableprint_vlc.h:34
AVCodecParameters::codec_id
enum AVCodecID codec_id
Specific type of the encoded data (the codec used).
Definition: codec_par.h:60
AVPacket
This structure stores compressed data.
Definition: packet.h:350
av_freep
#define av_freep(p)
Definition: tableprint_vlc.h:35
AVPacket::pos
int64_t pos
byte position in stream, -1 if unknown
Definition: packet.h:393
LIST_TAG
#define LIST_TAG
Definition: 4xm.c:38
AVCodecParameters::bit_rate
int64_t bit_rate
The average bitrate of the encoded data (in bits per second).
Definition: codec_par.h:89
av_log
#define av_log(a,...)
Definition: tableprint_vlc.h:28
AVERROR_INVALIDDATA
#define AVERROR_INVALIDDATA
Invalid data found when processing input.
Definition: error.h:61
AV_CODEC_ID_ADPCM_4XM
@ AV_CODEC_ID_ADPCM_4XM
Definition: codec_id.h:360
FF_SANE_NB_CHANNELS
#define FF_SANE_NB_CHANNELS
Definition: internal.h:101
std__TAG
#define std__TAG
Definition: 4xm.c:44
ifr2_TAG
#define ifr2_TAG
Definition: 4xm.c:51
pfr2_TAG
#define pfr2_TAG
Definition: 4xm.c:52
avio_feof
int avio_feof(AVIOContext *s)
Similar to feof() but also returns nonzero on read errors.
Definition: aviobuf.c:375