FFmpeg
mpeg4_unpack_bframes_bsf.c
Go to the documentation of this file.
1 /*
2  * Bitstream filter for unpacking DivX-style packed B-frames in MPEG-4 (divx_packed)
3  * Copyright (c) 2015 Andreas Cadhalpun <Andreas.Cadhalpun@googlemail.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 "avcodec.h"
23 #include "bsf.h"
24 #include "internal.h"
25 #include "mpeg4video.h"
26 
27 typedef struct UnpackBFramesBSFContext {
30 
31 /* determine the position of the packed marker in the userdata,
32  * the number of VOPs and the position of the second VOP */
33 static void scan_buffer(const uint8_t *buf, int buf_size,
34  int *pos_p, int *nb_vop, int *pos_vop2) {
35  uint32_t startcode;
36  const uint8_t *end = buf + buf_size, *pos = buf;
37 
38  while (pos < end) {
39  startcode = -1;
40  pos = avpriv_find_start_code(pos, end, &startcode);
41 
42  if (startcode == USER_DATA_STARTCODE && pos_p) {
43  /* check if the (DivX) userdata string ends with 'p' (packed) */
44  for (int i = 0; i < 255 && pos + i + 1 < end; i++) {
45  if (pos[i] == 'p' && pos[i + 1] == '\0') {
46  *pos_p = pos + i - buf;
47  break;
48  }
49  }
50  } else if (startcode == VOP_STARTCODE && nb_vop) {
51  *nb_vop += 1;
52  if (*nb_vop == 2 && pos_vop2) {
53  *pos_vop2 = pos - buf - 4; /* subtract 4 bytes startcode */
54  }
55  }
56  }
57 }
58 
60 {
62  int pos_p = -1, nb_vop = 0, pos_vop2 = -1, ret = 0;
63  AVPacket *in;
64 
66  if (ret < 0)
67  return ret;
68 
69  scan_buffer(in->data, in->size, &pos_p, &nb_vop, &pos_vop2);
70  av_log(ctx, AV_LOG_DEBUG, "Found %d VOP startcode(s) in this packet.\n", nb_vop);
71 
72  if (pos_vop2 >= 0) {
73  if (s->b_frame->data) {
75  "Missing one N-VOP packet, discarding one B-frame.\n");
76  av_packet_unref(s->b_frame);
77  }
78  /* store the packed B-frame in the BSFContext */
79  ret = av_packet_ref(s->b_frame, in);
80  if (ret < 0) {
81  goto fail;
82  }
83  s->b_frame->size -= pos_vop2;
84  s->b_frame->data += pos_vop2;
85  }
86 
87  if (nb_vop > 2) {
89  "Found %d VOP headers in one packet, only unpacking one.\n", nb_vop);
90  }
91 
92  if (nb_vop == 1 && s->b_frame->data) {
93  /* use frame from BSFContext */
94  av_packet_move_ref(out, s->b_frame);
95 
96  /* use properties from current input packet */
98  if (ret < 0) {
99  goto fail;
100  }
101 
102  if (in->size <= MAX_NVOP_SIZE) {
103  /* N-VOP */
104  av_log(ctx, AV_LOG_DEBUG, "Skipping N-VOP.\n");
105  } else {
106  /* copy packet into BSFContext */
107  av_packet_move_ref(s->b_frame, in);
108  }
109  } else if (nb_vop >= 2) {
110  /* use first frame of the packet */
112  out->size = pos_vop2;
113  } else if (pos_p >= 0) {
115  if (ret < 0)
116  goto fail;
117  av_log(ctx, AV_LOG_DEBUG, "Updating DivX userdata (remove trailing 'p').\n");
119  /* remove 'p' (packed) from the end of the (DivX) userdata string */
120  out->data[pos_p] = '\0';
121  } else {
122  /* copy packet */
124  }
125 
126 fail:
127  if (ret < 0)
129  av_packet_free(&in);
130 
131  return ret;
132 }
133 
135 {
137 
138  s->b_frame = av_packet_alloc();
139  if (!s->b_frame)
140  return AVERROR(ENOMEM);
141 
142  if (ctx->par_in->extradata) {
143  int pos_p_ext = -1;
144  scan_buffer(ctx->par_in->extradata, ctx->par_in->extradata_size, &pos_p_ext, NULL, NULL);
145  if (pos_p_ext >= 0) {
147  "Updating DivX userdata (remove trailing 'p') in extradata.\n");
148  ctx->par_out->extradata[pos_p_ext] = '\0';
149  }
150  }
151 
152  return 0;
153 }
154 
156 {
158  av_packet_unref(ctx->b_frame);
159 }
160 
162 {
164  av_packet_free(&ctx->b_frame);
165 }
166 
167 static const enum AVCodecID codec_ids[] = {
169 };
170 
172  .name = "mpeg4_unpack_bframes",
173  .priv_data_size = sizeof(UnpackBFramesBSFContext),
178  .codec_ids = codec_ids,
179 };
av_packet_unref
void av_packet_unref(AVPacket *pkt)
Wipe the packet.
Definition: avpacket.c:599
AV_LOG_WARNING
#define AV_LOG_WARNING
Something somehow does not look correct.
Definition: log.h:182
init
static av_cold int init(AVCodecContext *avctx)
Definition: avrndec.c:35
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
out
FILE * out
Definition: movenc.c:54
AVBitStreamFilter::name
const char * name
Definition: avcodec.h:5813
AV_CODEC_ID_MPEG4
@ AV_CODEC_ID_MPEG4
Definition: avcodec.h:230
end
static av_cold int end(AVCodecContext *avctx)
Definition: avrndec.c:90
internal.h
UnpackBFramesBSFContext::b_frame
AVPacket * b_frame
Definition: mpeg4_unpack_bframes_bsf.c:28
filter
filter_frame For filters that do not use the this method is called when a frame is pushed to the filter s input It can be called at any time except in a reentrant way If the input frame is enough to produce then the filter should push the output frames on the output link immediately As an exception to the previous rule if the input frame is enough to produce several output frames then the filter needs output only at least one per link The additional frames can be left buffered in the filter
Definition: filter_design.txt:228
avpriv_find_start_code
const uint8_t * avpriv_find_start_code(const uint8_t *p, const uint8_t *end, uint32_t *state)
ff_bsf_get_packet
int ff_bsf_get_packet(AVBSFContext *ctx, AVPacket **pkt)
Called by the bitstream filters to get the next packet for filtering.
Definition: bsf.c:217
av_packet_free
void av_packet_free(AVPacket **pkt)
Free the packet, if the packet is reference counted, it will be unreferenced first.
Definition: avpacket.c:62
AVBSFContext
The bitstream filter state.
Definition: avcodec.h:5763
UnpackBFramesBSFContext
Definition: mpeg4_unpack_bframes_bsf.c:27
bsf.h
fail
#define fail()
Definition: checkasm.h:120
buf
void * buf
Definition: avisynth_c.h:766
s
#define s(width, name)
Definition: cbs_vp9.c:257
codec_ids
static enum AVCodecID codec_ids[]
Definition: mpeg4_unpack_bframes_bsf.c:167
AV_LOG_DEBUG
#define AV_LOG_DEBUG
Stuff which is only useful for libav* developers.
Definition: log.h:197
ctx
AVFormatContext * ctx
Definition: movenc.c:48
mpeg4_unpack_bframes_filter
static int mpeg4_unpack_bframes_filter(AVBSFContext *ctx, AVPacket *out)
Definition: mpeg4_unpack_bframes_bsf.c:59
flush
static void flush(AVCodecContext *avctx)
Definition: aacdec_template.c:500
NULL
#define NULL
Definition: coverity.c:32
av_packet_ref
int av_packet_ref(AVPacket *dst, const AVPacket *src)
Setup a new reference to the data described by a given packet.
Definition: avpacket.c:608
av_packet_move_ref
void av_packet_move_ref(AVPacket *dst, AVPacket *src)
Move every field in src to dst and reset src.
Definition: avpacket.c:655
AVCodecID
AVCodecID
Identify the syntax and semantics of the bitstream.
Definition: avcodec.h:215
scan_buffer
static void scan_buffer(const uint8_t *buf, int buf_size, int *pos_p, int *nb_vop, int *pos_vop2)
Definition: mpeg4_unpack_bframes_bsf.c:33
av_packet_alloc
AVPacket * av_packet_alloc(void)
Allocate an AVPacket and set its fields to default values.
Definition: avpacket.c:51
in
uint8_t pi<< 24) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_U8, uint8_t,(*(const uint8_t *) pi - 0x80) *(1.0f/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_U8, uint8_t,(*(const uint8_t *) pi - 0x80) *(1.0/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S16, int16_t,(*(const int16_t *) pi >> 8)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S16, int16_t, *(const int16_t *) pi *(1.0f/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S16, int16_t, *(const int16_t *) pi *(1.0/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S32, int32_t,(*(const int32_t *) pi >> 24)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S32, int32_t, *(const int32_t *) pi *(1.0f/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S32, int32_t, *(const int32_t *) pi *(1.0/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_FLT, float, av_clip_uint8(lrintf(*(const float *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_FLT, float, av_clip_int16(lrintf(*(const float *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_FLT, float, av_clipl_int32(llrintf(*(const float *) pi *(1U<< 31)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_DBL, double, av_clip_uint8(lrint(*(const double *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_DBL, double, av_clip_int16(lrint(*(const double *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_DBL, double, av_clipl_int32(llrint(*(const double *) pi *(1U<< 31)))) #define SET_CONV_FUNC_GROUP(ofmt, ifmt) static void set_generic_function(AudioConvert *ac) { } void ff_audio_convert_free(AudioConvert **ac) { if(! *ac) return;ff_dither_free(&(*ac) ->dc);av_freep(ac);} AudioConvert *ff_audio_convert_alloc(AVAudioResampleContext *avr, enum AVSampleFormat out_fmt, enum AVSampleFormat in_fmt, int channels, int sample_rate, int apply_map) { AudioConvert *ac;int in_planar, out_planar;ac=av_mallocz(sizeof(*ac));if(!ac) return NULL;ac->avr=avr;ac->out_fmt=out_fmt;ac->in_fmt=in_fmt;ac->channels=channels;ac->apply_map=apply_map;if(avr->dither_method !=AV_RESAMPLE_DITHER_NONE &&av_get_packed_sample_fmt(out_fmt)==AV_SAMPLE_FMT_S16 &&av_get_bytes_per_sample(in_fmt) > 2) { ac->dc=ff_dither_alloc(avr, out_fmt, in_fmt, channels, sample_rate, apply_map);if(!ac->dc) { av_free(ac);return NULL;} return ac;} in_planar=ff_sample_fmt_is_planar(in_fmt, channels);out_planar=ff_sample_fmt_is_planar(out_fmt, channels);if(in_planar==out_planar) { ac->func_type=CONV_FUNC_TYPE_FLAT;ac->planes=in_planar ? ac->channels :1;} else if(in_planar) ac->func_type=CONV_FUNC_TYPE_INTERLEAVE;else ac->func_type=CONV_FUNC_TYPE_DEINTERLEAVE;set_generic_function(ac);if(ARCH_AARCH64) ff_audio_convert_init_aarch64(ac);if(ARCH_ARM) ff_audio_convert_init_arm(ac);if(ARCH_X86) ff_audio_convert_init_x86(ac);return ac;} int ff_audio_convert(AudioConvert *ac, AudioData *out, AudioData *in) { int use_generic=1;int len=in->nb_samples;int p;if(ac->dc) { av_log(ac->avr, AV_LOG_TRACE, "%d samples - audio_convert: %s to %s (dithered)\n", len, av_get_sample_fmt_name(ac->in_fmt), av_get_sample_fmt_name(ac->out_fmt));return ff_convert_dither(ac-> in
Definition: audio_convert.c:326
av_packet_copy_props
int av_packet_copy_props(AVPacket *dst, const AVPacket *src)
Copy only "properties" fields from src to dst.
Definition: avpacket.c:565
mpeg4_unpack_bframes_init
static int mpeg4_unpack_bframes_init(AVBSFContext *ctx)
Definition: mpeg4_unpack_bframes_bsf.c:134
AV_CODEC_ID_NONE
@ AV_CODEC_ID_NONE
Definition: avcodec.h:216
i
#define i(width, name, range_min, range_max)
Definition: cbs_h2645.c:259
uint8_t
uint8_t
Definition: audio_convert.c:194
USER_DATA_STARTCODE
#define USER_DATA_STARTCODE
Definition: mpeg4video.h:62
avcodec.h
AVBSFContext::priv_data
void * priv_data
Opaque filter-specific private data.
Definition: avcodec.h:5784
ret
ret
Definition: filter_design.txt:187
mpeg4_unpack_bframes_flush
static void mpeg4_unpack_bframes_flush(AVBSFContext *bsfc)
Definition: mpeg4_unpack_bframes_bsf.c:155
AVBitStreamFilter
Definition: avcodec.h:5812
mpeg4video.h
av_packet_make_writable
int av_packet_make_writable(AVPacket *pkt)
Create a writable reference for the data described by a given packet, avoiding data copy if possible.
Definition: avpacket.c:682
MAX_NVOP_SIZE
#define MAX_NVOP_SIZE
Definition: mpeg4video.h:72
ff_mpeg4_unpack_bframes_bsf
const AVBitStreamFilter ff_mpeg4_unpack_bframes_bsf
Definition: mpeg4_unpack_bframes_bsf.c:171
VOP_STARTCODE
#define VOP_STARTCODE
Definition: mpeg4video.h:65
AVPacket
This structure stores compressed data.
Definition: avcodec.h:1454
av_log
#define av_log(a,...)
Definition: tableprint_vlc.h:28
mpeg4_unpack_bframes_close
static void mpeg4_unpack_bframes_close(AVBSFContext *bsfc)
Definition: mpeg4_unpack_bframes_bsf.c:161
AVFormatContext::priv_data
void * priv_data
Format private data.
Definition: avformat.h:1370