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 "demux.h"
35 #include "internal.h"
36 
37 #define RIFF_TAG MKTAG('R', 'I', 'F', 'F')
38 #define FOURXMV_TAG MKTAG('4', 'X', 'M', 'V')
39 #define LIST_TAG MKTAG('L', 'I', 'S', 'T')
40 #define HEAD_TAG MKTAG('H', 'E', 'A', 'D')
41 #define TRK__TAG MKTAG('T', 'R', 'K', '_')
42 #define MOVI_TAG MKTAG('M', 'O', 'V', 'I')
43 #define VTRK_TAG MKTAG('V', 'T', 'R', 'K')
44 #define STRK_TAG MKTAG('S', 'T', 'R', 'K')
45 #define std__TAG MKTAG('s', 't', 'd', '_')
46 #define name_TAG MKTAG('n', 'a', 'm', 'e')
47 #define vtrk_TAG MKTAG('v', 't', 'r', 'k')
48 #define strk_TAG MKTAG('s', 't', 'r', 'k')
49 #define ifrm_TAG MKTAG('i', 'f', 'r', 'm')
50 #define pfrm_TAG MKTAG('p', 'f', 'r', 'm')
51 #define cfrm_TAG MKTAG('c', 'f', 'r', 'm')
52 #define ifr2_TAG MKTAG('i', 'f', 'r', '2')
53 #define pfr2_TAG MKTAG('p', 'f', 'r', '2')
54 #define cfr2_TAG MKTAG('c', 'f', 'r', '2')
55 #define snd__TAG MKTAG('s', 'n', 'd', '_')
56 
57 #define vtrk_SIZE 0x44
58 #define strk_SIZE 0x28
59 
60 #define GET_LIST_HEADER() \
61  fourcc_tag = avio_rl32(pb); \
62  size = avio_rl32(pb); \
63  if (fourcc_tag != LIST_TAG) { \
64  ret = AVERROR_INVALIDDATA; \
65  goto fail; \
66  } \
67  fourcc_tag = avio_rl32(pb);
68 
69 typedef struct AudioTrack {
71  int bits;
72  int channels;
74  int adpcm;
76 } AudioTrack;
77 
78 typedef struct FourxmDemuxContext {
82 
86 
87 static int fourxm_probe(const AVProbeData *p)
88 {
89  if ((AV_RL32(&p->buf[0]) != RIFF_TAG) ||
90  (AV_RL32(&p->buf[8]) != FOURXMV_TAG))
91  return 0;
92 
93  return AVPROBE_SCORE_MAX;
94 }
95 
97  FourxmDemuxContext *fourxm, uint8_t *buf, int size,
98  int left)
99 {
100  AVStream *st;
101  /* check that there is enough data */
102  if (size != vtrk_SIZE || left < size + 8) {
103  return AVERROR_INVALIDDATA;
104  }
105 
106  /* allocate a new AVStream */
107  st = avformat_new_stream(s, NULL);
108  if (!st)
109  return AVERROR(ENOMEM);
110 
111  avpriv_set_pts_info(st, 60, fourxm->fps.den, fourxm->fps.num);
112 
113  fourxm->video_stream_index = st->index;
114 
117 
119  if (!st->codecpar->extradata)
120  return AVERROR(ENOMEM);
121  st->codecpar->extradata_size = 4;
122  AV_WL32(st->codecpar->extradata, AV_RL32(buf + 16));
123  st->codecpar->width = AV_RL32(buf + 36);
124  st->codecpar->height = AV_RL32(buf + 40);
125 
126  return 0;
127 }
128 
129 
131  FourxmDemuxContext *fourxm, uint8_t *buf, int size,
132  int left)
133 {
134  AVStream *st;
135  int track;
136  /* check that there is enough data */
137  if (size != strk_SIZE || left < size + 8)
138  return AVERROR_INVALIDDATA;
139 
140  track = AV_RL32(buf + 8);
141  if ((unsigned)track >= UINT_MAX / sizeof(AudioTrack) - 1 ||
142  track >= s->max_streams) {
143  av_log(s, AV_LOG_ERROR, "current_track too large\n");
144  return AVERROR_INVALIDDATA;
145  }
146 
147  if (track + 1 > fourxm->track_count) {
148  if (av_reallocp_array(&fourxm->tracks, track + 1, sizeof(AudioTrack)))
149  return AVERROR(ENOMEM);
150  memset(&fourxm->tracks[fourxm->track_count], 0,
151  sizeof(AudioTrack) * (track + 1 - fourxm->track_count));
152  fourxm->track_count = track + 1;
153  } else {
154  if (fourxm->tracks[track].bits)
155  return AVERROR_INVALIDDATA;
156  }
157  fourxm->tracks[track].adpcm = AV_RL32(buf + 12);
158  fourxm->tracks[track].channels = AV_RL32(buf + 36);
159  fourxm->tracks[track].sample_rate = AV_RL32(buf + 40);
160  fourxm->tracks[track].bits = AV_RL32(buf + 44);
161  fourxm->tracks[track].audio_pts = 0;
162 
163  if (fourxm->tracks[track].channels <= 0 ||
164  fourxm->tracks[track].channels > FF_SANE_NB_CHANNELS ||
165  fourxm->tracks[track].sample_rate <= 0 ||
166  fourxm->tracks[track].bits <= 0 ||
167  fourxm->tracks[track].bits > INT_MAX / FF_SANE_NB_CHANNELS) {
168  av_log(s, AV_LOG_ERROR, "audio header invalid\n");
169  return AVERROR_INVALIDDATA;
170  }
171  if (!fourxm->tracks[track].adpcm && fourxm->tracks[track].bits<8) {
172  av_log(s, AV_LOG_ERROR, "bits unspecified for non ADPCM\n");
173  return AVERROR_INVALIDDATA;
174  }
175 
176  if (fourxm->tracks[track].sample_rate > INT64_MAX / fourxm->tracks[track].bits / fourxm->tracks[track].channels) {
177  av_log(s, AV_LOG_ERROR, "Overflow during bit rate calculation %d * %d * %d\n",
178  fourxm->tracks[track].sample_rate, fourxm->tracks[track].bits, fourxm->tracks[track].channels);
179  return AVERROR_INVALIDDATA;
180  }
181 
182  /* allocate a new AVStream */
183  st = avformat_new_stream(s, NULL);
184  if (!st)
185  return AVERROR(ENOMEM);
186 
187  st->id = track;
188  avpriv_set_pts_info(st, 60, 1, fourxm->tracks[track].sample_rate);
189 
190  fourxm->tracks[track].stream_index = st->index;
191 
193  st->codecpar->codec_tag = 0;
194  st->codecpar->ch_layout.nb_channels = fourxm->tracks[track].channels;
195  st->codecpar->sample_rate = fourxm->tracks[track].sample_rate;
196  st->codecpar->bits_per_coded_sample = fourxm->tracks[track].bits;
198  st->codecpar->sample_rate *
202 
203  if (fourxm->tracks[track].adpcm){
205  } else if (st->codecpar->bits_per_coded_sample == 8) {
207  } else
209 
210  return 0;
211 }
212 
214 {
215  AVIOContext *pb = s->pb;
216  unsigned int fourcc_tag;
217  unsigned int size;
218  int header_size;
219  FourxmDemuxContext *fourxm = s->priv_data;
220  unsigned char *header = NULL;
221  int i, ret;
222 
223  fourxm->track_count = 0;
224  fourxm->tracks = NULL;
225  fourxm->fps = (AVRational){1,1};
226  fourxm->video_stream_index = -1;
227 
228  /* skip the first 3 32-bit numbers */
229  avio_skip(pb, 12);
230 
231  /* check for LIST-HEAD */
232  GET_LIST_HEADER();
233  header_size = size - 4;
234  if (fourcc_tag != HEAD_TAG || header_size < 0)
235  return AVERROR_INVALIDDATA;
236 
237  /* allocate space for the header and load the whole thing */
238  header = av_malloc(header_size);
239  if (!header)
240  return AVERROR(ENOMEM);
241  if (avio_read(pb, header, header_size) != header_size) {
242  av_free(header);
243  return AVERROR(EIO);
244  }
245 
246  /* take the lazy approach and search for any and all vtrk and strk chunks */
247  for (i = 0; i < header_size - 8; i++) {
248  fourcc_tag = AV_RL32(&header[i]);
249  size = AV_RL32(&header[i + 4]);
250  if (size > header_size - i - 8 && (fourcc_tag == vtrk_TAG || fourcc_tag == strk_TAG)) {
251  av_log(s, AV_LOG_ERROR, "chunk larger than array %d>%d\n", size, header_size - i - 8);
253  goto fail;
254  }
255 
256  if (fourcc_tag == std__TAG) {
257  if (header_size - i < 16) {
258  av_log(s, AV_LOG_ERROR, "std TAG truncated\n");
260  goto fail;
261  }
262  fourxm->fps = av_d2q(av_int2float(AV_RL32(&header[i + 12])), 10000);
263  } else if (fourcc_tag == vtrk_TAG) {
264  if ((ret = parse_vtrk(s, fourxm, header + i, size,
265  header_size - i)) < 0)
266  goto fail;
267 
268  i += 8 + size;
269  } else if (fourcc_tag == strk_TAG) {
270  if ((ret = parse_strk(s, fourxm, header + i, size,
271  header_size - i)) < 0)
272  goto fail;
273 
274  i += 8 + size;
275  }
276  }
277 
278  /* skip over the LIST-MOVI chunk (which is where the stream should be */
279  GET_LIST_HEADER();
280  if (fourcc_tag != MOVI_TAG) {
282  goto fail;
283  }
284 
285  av_free(header);
286  /* initialize context members */
287  fourxm->video_pts = -1; /* first frame will push to 0 */
288 
289  return 0;
290 fail:
291  av_free(header);
292  return ret;
293 }
294 
296  AVPacket *pkt)
297 {
298  FourxmDemuxContext *fourxm = s->priv_data;
299  AVIOContext *pb = s->pb;
300  unsigned int fourcc_tag;
301  unsigned int size;
302  int ret = 0;
303  unsigned int track_number;
304  int packet_read = 0;
305  unsigned char header[8];
307 
308  while (!packet_read) {
309  if ((ret = avio_read(s->pb, header, 8)) < 0)
310  return ret;
311  fourcc_tag = AV_RL32(&header[0]);
312  size = AV_RL32(&header[4]);
313  if (avio_feof(pb))
314  return AVERROR(EIO);
315  switch (fourcc_tag) {
316  case LIST_TAG:
317  /* this is a good time to bump the video pts */
318  fourxm->video_pts++;
319 
320  /* skip the LIST-* tag and move on to the next fourcc */
321  avio_rl32(pb);
322  break;
323 
324  case ifrm_TAG:
325  case pfrm_TAG:
326  case cfrm_TAG:
327  case ifr2_TAG:
328  case pfr2_TAG:
329  case cfr2_TAG:
330  /* allocate 8 more bytes than 'size' to account for fourcc
331  * and size */
332  if (size > INT_MAX - AV_INPUT_BUFFER_PADDING_SIZE - 8)
333  return AVERROR_INVALIDDATA;
334  if (fourxm->video_stream_index < 0)
335  return AVERROR_INVALIDDATA;
336  if ((ret = av_new_packet(pkt, size + 8)) < 0)
337  return ret;
339  pkt->pts = fourxm->video_pts;
340  pkt->pos = avio_tell(s->pb);
341  memcpy(pkt->data, header, 8);
342  ret = avio_read(s->pb, &pkt->data[8], size);
343 
344  if (ret < 0) {
346  } else {
347  packet_read = 1;
348  av_shrink_packet(pkt, ret + 8);
349  }
350  break;
351 
352  case snd__TAG:
353  track_number = avio_rl32(pb);
354  avio_skip(pb, 4);
355  size -= 8;
356 
357  if (track_number < fourxm->track_count &&
358  fourxm->tracks[track_number].channels > 0) {
359  ret = av_get_packet(s->pb, pkt, size);
360  if (ret < 0)
361  return ret;
362  pkt->stream_index =
363  fourxm->tracks[track_number].stream_index;
364  pkt->pts = fourxm->tracks[track_number].audio_pts;
365  packet_read = 1;
366 
367  /* pts accounting */
369  if (fourxm->tracks[track_number].adpcm)
370  audio_frame_count -= 2 * (fourxm->tracks[track_number].channels);
371  audio_frame_count /= fourxm->tracks[track_number].channels;
372  if (fourxm->tracks[track_number].adpcm) {
373  audio_frame_count *= 2;
374  } else
376  (fourxm->tracks[track_number].bits / 8);
377  fourxm->tracks[track_number].audio_pts += audio_frame_count;
378  } else {
379  avio_skip(pb, size);
380  }
381  break;
382 
383  default:
384  avio_skip(pb, size);
385  break;
386  }
387  }
388  return ret;
389 }
390 
392 {
393  FourxmDemuxContext *fourxm = s->priv_data;
394 
395  av_freep(&fourxm->tracks);
396 
397  return 0;
398 }
399 
401  .p.name = "4xm",
402  .p.long_name = NULL_IF_CONFIG_SMALL("4X Technologies"),
403  .priv_data_size = sizeof(FourxmDemuxContext),
404  .flags_internal = FF_INFMT_FLAG_INIT_CLEANUP,
409 };
AV_CODEC_ID_PCM_S16LE
@ AV_CODEC_ID_PCM_S16LE
Definition: codec_id.h:328
av_packet_unref
void av_packet_unref(AVPacket *pkt)
Wipe the packet.
Definition: avpacket.c:427
fourxm_read_packet
static int fourxm_read_packet(AVFormatContext *s, AVPacket *pkt)
Definition: 4xm.c:295
AVCodecParameters::extradata
uint8_t * extradata
Extra binary data needed for initializing the decoder, codec-dependent.
Definition: codec_par.h:69
AudioTrack::adpcm
int adpcm
Definition: 4xm.c:74
AudioTrack::audio_pts
int64_t audio_pts
Definition: 4xm.c:75
FourxmDemuxContext::tracks
AudioTrack * tracks
Definition: 4xm.c:81
FourxmDemuxContext::video_pts
int64_t video_pts
Definition: 4xm.c:83
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
AVCodecParameters::codec_type
enum AVMediaType codec_type
General type of the encoded data.
Definition: codec_par.h:51
AV_WL32
#define AV_WL32(p, v)
Definition: intreadwrite.h:424
avformat_new_stream
AVStream * avformat_new_stream(AVFormatContext *s, const struct AVCodec *c)
Add a new stream to a media file.
int64_t
long long int64_t
Definition: coverity.c:34
internal.h
AVPacket::data
uint8_t * data
Definition: packet.h:522
AVCodecParameters::codec_tag
uint32_t codec_tag
Additional information about the codec (corresponds to the AVI FOURCC).
Definition: codec_par.h:59
AVChannelLayout::nb_channels
int nb_channels
Number of channels in this layout.
Definition: channel_layout.h:313
intfloat.h
AudioTrack::sample_rate
int sample_rate
Definition: 4xm.c:70
av_malloc
#define av_malloc(s)
Definition: tableprint_vlc.h:30
AVPROBE_SCORE_MAX
#define AVPROBE_SCORE_MAX
maximum score
Definition: avformat.h:463
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: avformat.c:853
fourxm_probe
static int fourxm_probe(const AVProbeData *p)
Definition: 4xm.c:87
fail
#define fail()
Definition: checkasm.h:179
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:113
fourxm_read_header
static int fourxm_read_header(AVFormatContext *s)
Definition: 4xm.c:213
read_close
static av_cold int read_close(AVFormatContext *ctx)
Definition: libcdio.c:143
avio_tell
static av_always_inline int64_t avio_tell(AVIOContext *s)
ftell() equivalent for AVIOContext.
Definition: avio.h:494
pfrm_TAG
#define pfrm_TAG
Definition: 4xm.c:50
AudioTrack::channels
int channels
Definition: 4xm.c:72
HEAD_TAG
#define HEAD_TAG
Definition: 4xm.c:40
AVRational::num
int num
Numerator.
Definition: rational.h:59
cfrm_TAG
#define cfrm_TAG
Definition: 4xm.c:51
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
read_packet
static int read_packet(void *opaque, uint8_t *buf, int buf_size)
Definition: avio_read_callback.c:41
FOURXMV_TAG
#define FOURXMV_TAG
Definition: 4xm.c:38
snd__TAG
#define snd__TAG
Definition: 4xm.c:55
MOVI_TAG
#define MOVI_TAG
Definition: 4xm.c:42
AV_CODEC_ID_4XM
@ AV_CODEC_ID_4XM
Definition: codec_id.h:86
intreadwrite.h
s
#define s(width, name)
Definition: cbs_vp9.c:198
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:98
AVInputFormat::name
const char * name
A comma separated list of short names for the format.
Definition: avformat.h:553
AVProbeData::buf
unsigned char * buf
Buffer must have AVPROBE_PADDING_SIZE of extra allocated bytes filled with zero.
Definition: avformat.h:453
AVMEDIA_TYPE_AUDIO
@ AVMEDIA_TYPE_AUDIO
Definition: avutil.h:202
AVCodecParameters::width
int width
Video only.
Definition: codec_par.h:134
audio_frame_count
static int audio_frame_count
Definition: demux_decode.c:57
vtrk_SIZE
#define vtrk_SIZE
Definition: 4xm.c:57
strk_TAG
#define strk_TAG
Definition: 4xm.c:48
if
if(ret)
Definition: filter_design.txt:179
FF_INFMT_FLAG_INIT_CLEANUP
#define FF_INFMT_FLAG_INIT_CLEANUP
For an FFInputFormat with this flag set read_close() needs to be called by the caller upon read_heade...
Definition: demux.h:35
AVFormatContext
Format I/O context.
Definition: avformat.h:1255
AVStream::codecpar
AVCodecParameters * codecpar
Codec parameters associated with this stream.
Definition: avformat.h:766
read_header
static int read_header(FFV1Context *f)
Definition: ffv1dec.c:550
NULL
#define NULL
Definition: coverity.c:32
fourxm_read_close
static int fourxm_read_close(AVFormatContext *s)
Definition: 4xm.c:391
parse_strk
static int parse_strk(AVFormatContext *s, FourxmDemuxContext *fourxm, uint8_t *buf, int size, int left)
Definition: 4xm.c:130
AVRational
Rational number (pair of numerator and denominator).
Definition: rational.h:58
FourxmDemuxContext::fps
AVRational fps
Definition: 4xm.c:84
strk_SIZE
#define strk_SIZE
Definition: 4xm.c:58
AVProbeData
This structure contains the data a format has to probe a file.
Definition: avformat.h:451
RIFF_TAG
#define RIFF_TAG
Definition: 4xm.c:37
AVCodecParameters::ch_layout
AVChannelLayout ch_layout
Audio only.
Definition: codec_par.h:180
FourxmDemuxContext::video_stream_index
int video_stream_index
Definition: 4xm.c:79
AVCodecParameters::sample_rate
int sample_rate
Audio only.
Definition: codec_par.h:184
AVCodecParameters::extradata_size
int extradata_size
Size of the extradata content in bytes.
Definition: codec_par.h:73
AudioTrack
Definition: 4xm.c:69
avio_rl32
unsigned int avio_rl32(AVIOContext *s)
Definition: aviobuf.c:729
AVIOContext
Bytestream IO Context.
Definition: avio.h:160
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:106
size
int size
Definition: twinvq_data.h:10344
cfr2_TAG
#define cfr2_TAG
Definition: 4xm.c:54
vtrk_TAG
#define vtrk_TAG
Definition: 4xm.c:47
ff_fourxm_demuxer
const FFInputFormat ff_fourxm_demuxer
Definition: 4xm.c:400
FFInputFormat::p
AVInputFormat p
The public AVInputFormat.
Definition: demux.h:41
header
static const uint8_t header[24]
Definition: sdr2.c:68
av_reallocp_array
int av_reallocp_array(void *ptr, size_t nmemb, size_t size)
Allocate, reallocate an array through a pointer to a pointer.
Definition: mem.c:223
parse_vtrk
static int parse_vtrk(AVFormatContext *s, FourxmDemuxContext *fourxm, uint8_t *buf, int size, int left)
Definition: 4xm.c:96
AudioTrack::stream_index
int stream_index
Definition: 4xm.c:73
GET_LIST_HEADER
#define GET_LIST_HEADER()
Definition: 4xm.c:60
i
#define i(width, name, range_min, range_max)
Definition: cbs_h2645.c:255
AVPacket::pts
int64_t pts
Presentation timestamp in AVStream->time_base units; the time at which the decompressed packet will b...
Definition: packet.h:515
AVCodecParameters::height
int height
Definition: codec_par.h:135
AVCodecParameters::block_align
int block_align
Audio only.
Definition: codec_par.h:191
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:254
demux.h
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:103
FourxmDemuxContext
Definition: 4xm.c:78
AVStream::id
int id
Format-specific stream ID.
Definition: avformat.h:755
ret
ret
Definition: filter_design.txt:187
AVStream
Stream structure.
Definition: avformat.h:743
avformat.h
AudioTrack::bits
int bits
Definition: 4xm.c:71
FourxmDemuxContext::track_count
int track_count
Definition: 4xm.c:80
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:749
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:611
AVPacket::stream_index
int stream_index
Definition: packet.h:524
avio_skip
int64_t avio_skip(AVIOContext *s, int64_t offset)
Skip given number of bytes forward.
Definition: aviobuf.c:317
ifrm_TAG
#define ifrm_TAG
Definition: 4xm.c:49
AVMEDIA_TYPE_VIDEO
@ AVMEDIA_TYPE_VIDEO
Definition: avutil.h:201
read_probe
static int read_probe(const AVProbeData *p)
Definition: cdg.c:30
AVCodecParameters::bits_per_coded_sample
int bits_per_coded_sample
The number of bits per sample in the codedwords.
Definition: codec_par.h:110
AV_CODEC_ID_PCM_U8
@ AV_CODEC_ID_PCM_U8
Definition: codec_id.h:333
av_free
#define av_free(p)
Definition: tableprint_vlc.h:33
AVCodecParameters::codec_id
enum AVCodecID codec_id
Specific type of the encoded data (the codec used).
Definition: codec_par.h:55
AVPacket
This structure stores compressed data.
Definition: packet.h:499
av_freep
#define av_freep(p)
Definition: tableprint_vlc.h:34
AVPacket::pos
int64_t pos
byte position in stream, -1 if unknown
Definition: packet.h:542
FFInputFormat
Definition: demux.h:37
LIST_TAG
#define LIST_TAG
Definition: 4xm.c:39
AVCodecParameters::bit_rate
int64_t bit_rate
The average bitrate of the encoded data (in bits per second).
Definition: codec_par.h:97
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
AV_CODEC_ID_ADPCM_4XM
@ AV_CODEC_ID_ADPCM_4XM
Definition: codec_id.h:374
FF_SANE_NB_CHANNELS
#define FF_SANE_NB_CHANNELS
Definition: internal.h:37
std__TAG
#define std__TAG
Definition: 4xm.c:45
ifr2_TAG
#define ifr2_TAG
Definition: 4xm.c:52
pfr2_TAG
#define pfr2_TAG
Definition: 4xm.c:53
avio_feof
int avio_feof(AVIOContext *s)
Similar to feof() but also returns nonzero on read errors.
Definition: aviobuf.c:345