FFmpeg
h264_mp4toannexb_bsf.c
Go to the documentation of this file.
1 /*
2  * H.264 MP4 to Annex B byte stream format filter
3  * Copyright (c) 2007 Benoit Fouet <benoit.fouet@free.fr>
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 <string.h>
23 
24 #include "libavutil/intreadwrite.h"
25 #include "libavutil/mem.h"
26 
27 #include "avcodec.h"
28 #include "bsf.h"
29 #include "h264.h"
30 
31 typedef struct H264BSFContext {
40 
42  const uint8_t *sps_pps, uint32_t sps_pps_size,
43  const uint8_t *in, uint32_t in_size, int ps)
44 {
45  uint32_t offset = out->size;
46  uint8_t start_code_size = offset == 0 || ps ? 4 : 3;
47  int err;
48 
49  err = av_grow_packet(out, sps_pps_size + in_size + start_code_size);
50  if (err < 0)
51  return err;
52 
53  if (sps_pps)
54  memcpy(out->data + offset, sps_pps, sps_pps_size);
55  memcpy(out->data + sps_pps_size + start_code_size + offset, in, in_size);
56  if (start_code_size == 4) {
57  AV_WB32(out->data + offset + sps_pps_size, 1);
58  } else {
59  (out->data + offset + sps_pps_size)[0] =
60  (out->data + offset + sps_pps_size)[1] = 0;
61  (out->data + offset + sps_pps_size)[2] = 1;
62  }
63 
64  return 0;
65 }
66 
67 static int h264_extradata_to_annexb(AVBSFContext *ctx, const int padding)
68 {
69  H264BSFContext *s = ctx->priv_data;
70  uint16_t unit_size;
71  uint64_t total_size = 0;
72  uint8_t *out = NULL, unit_nb, sps_done = 0,
73  sps_seen = 0, pps_seen = 0;
74  const uint8_t *extradata = ctx->par_in->extradata + 4;
75  static const uint8_t nalu_header[4] = { 0, 0, 0, 1 };
76  int length_size = (*extradata++ & 0x3) + 1; // retrieve length coded size
77 
78  s->sps_offset = s->pps_offset = -1;
79 
80  /* retrieve sps and pps unit(s) */
81  unit_nb = *extradata++ & 0x1f; /* number of sps unit(s) */
82  if (!unit_nb) {
83  goto pps;
84  } else {
85  s->sps_offset = 0;
86  sps_seen = 1;
87  }
88 
89  while (unit_nb--) {
90  int err;
91 
92  unit_size = AV_RB16(extradata);
93  total_size += unit_size + 4;
94  if (total_size > INT_MAX - padding) {
95  av_log(ctx, AV_LOG_ERROR,
96  "Too big extradata size, corrupted stream or invalid MP4/AVCC bitstream\n");
97  av_free(out);
98  return AVERROR(EINVAL);
99  }
100  if (extradata + 2 + unit_size > ctx->par_in->extradata + ctx->par_in->extradata_size) {
101  av_log(ctx, AV_LOG_ERROR, "Packet header is not contained in global extradata, "
102  "corrupted stream or invalid MP4/AVCC bitstream\n");
103  av_free(out);
104  return AVERROR(EINVAL);
105  }
106  if ((err = av_reallocp(&out, total_size + padding)) < 0)
107  return err;
108  memcpy(out + total_size - unit_size - 4, nalu_header, 4);
109  memcpy(out + total_size - unit_size, extradata + 2, unit_size);
110  extradata += 2 + unit_size;
111 pps:
112  if (!unit_nb && !sps_done++) {
113  unit_nb = *extradata++; /* number of pps unit(s) */
114  if (unit_nb) {
115  s->pps_offset = total_size;
116  pps_seen = 1;
117  }
118  }
119  }
120 
121  if (out)
122  memset(out + total_size, 0, padding);
123 
124  if (!sps_seen)
125  av_log(ctx, AV_LOG_WARNING,
126  "Warning: SPS NALU missing or invalid. "
127  "The resulting stream may not play.\n");
128 
129  if (!pps_seen)
130  av_log(ctx, AV_LOG_WARNING,
131  "Warning: PPS NALU missing or invalid. "
132  "The resulting stream may not play.\n");
133 
134  av_freep(&ctx->par_out->extradata);
135  ctx->par_out->extradata = out;
136  ctx->par_out->extradata_size = total_size;
137 
138  return length_size;
139 }
140 
142 {
143  H264BSFContext *s = ctx->priv_data;
144  int extra_size = ctx->par_in->extradata_size;
145  int ret;
146 
147  /* retrieve sps and pps NAL units from extradata */
148  if (!extra_size ||
149  (extra_size >= 3 && AV_RB24(ctx->par_in->extradata) == 1) ||
150  (extra_size >= 4 && AV_RB32(ctx->par_in->extradata) == 1)) {
151  av_log(ctx, AV_LOG_VERBOSE,
152  "The input looks like it is Annex B already\n");
153  } else if (extra_size >= 6) {
155  if (ret < 0)
156  return ret;
157 
158  s->length_size = ret;
159  s->new_idr = 1;
160  s->idr_sps_seen = 0;
161  s->idr_pps_seen = 0;
162  s->extradata_parsed = 1;
163  } else {
164  av_log(ctx, AV_LOG_ERROR, "Invalid extradata size: %d\n", extra_size);
165  return AVERROR_INVALIDDATA;
166  }
167 
168  return 0;
169 }
170 
172 {
173  H264BSFContext *s = ctx->priv_data;
174 
175  AVPacket *in;
176  uint8_t unit_type;
177  int32_t nal_size;
178  uint32_t cumul_size = 0;
179  const uint8_t *buf;
180  const uint8_t *buf_end;
181  int buf_size;
182  int ret = 0, i;
183 
184  ret = ff_bsf_get_packet(ctx, &in);
185  if (ret < 0)
186  return ret;
187 
188  /* nothing to filter */
189  if (!s->extradata_parsed) {
190  av_packet_move_ref(out, in);
191  av_packet_free(&in);
192  return 0;
193  }
194 
195  buf = in->data;
196  buf_size = in->size;
197  buf_end = in->data + in->size;
198 
199  do {
200  ret= AVERROR(EINVAL);
201  if (buf + s->length_size > buf_end)
202  goto fail;
203 
204  for (nal_size = 0, i = 0; i<s->length_size; i++)
205  nal_size = (nal_size << 8) | buf[i];
206 
207  buf += s->length_size;
208  unit_type = *buf & 0x1f;
209 
210  if (nal_size > buf_end - buf || nal_size < 0)
211  goto fail;
212 
213  if (unit_type == H264_NAL_SPS)
214  s->idr_sps_seen = s->new_idr = 1;
215  else if (unit_type == H264_NAL_PPS) {
216  s->idr_pps_seen = s->new_idr = 1;
217  /* if SPS has not been seen yet, prepend the AVCC one to PPS */
218  if (!s->idr_sps_seen) {
219  if (s->sps_offset == -1)
220  av_log(ctx, AV_LOG_WARNING, "SPS not present in the stream, nor in AVCC, stream may be unreadable\n");
221  else {
222  if ((ret = alloc_and_copy(out,
223  ctx->par_out->extradata + s->sps_offset,
224  s->pps_offset != -1 ? s->pps_offset : ctx->par_out->extradata_size - s->sps_offset,
225  buf, nal_size, 1)) < 0)
226  goto fail;
227  s->idr_sps_seen = 1;
228  goto next_nal;
229  }
230  }
231  }
232 
233  /* if this is a new IDR picture following an IDR picture, reset the idr flag.
234  * Just check first_mb_in_slice to be 0 as this is the simplest solution.
235  * This could be checking idr_pic_id instead, but would complexify the parsing. */
236  if (!s->new_idr && unit_type == H264_NAL_IDR_SLICE && (buf[1] & 0x80))
237  s->new_idr = 1;
238 
239  /* prepend only to the first type 5 NAL unit of an IDR picture, if no sps/pps are already present */
240  if (s->new_idr && unit_type == H264_NAL_IDR_SLICE && !s->idr_sps_seen && !s->idr_pps_seen) {
241  if ((ret=alloc_and_copy(out,
243  buf, nal_size, 1)) < 0)
244  goto fail;
245  s->new_idr = 0;
246  /* if only SPS has been seen, also insert PPS */
247  } else if (s->new_idr && unit_type == H264_NAL_IDR_SLICE && s->idr_sps_seen && !s->idr_pps_seen) {
248  if (s->pps_offset == -1) {
249  av_log(ctx, AV_LOG_WARNING, "PPS not present in the stream, nor in AVCC, stream may be unreadable\n");
250  if ((ret = alloc_and_copy(out, NULL, 0, buf, nal_size, 0)) < 0)
251  goto fail;
252  } else if ((ret = alloc_and_copy(out,
254  buf, nal_size, 1)) < 0)
255  goto fail;
256  } else {
257  if ((ret=alloc_and_copy(out, NULL, 0, buf, nal_size, unit_type == H264_NAL_SPS || unit_type == H264_NAL_PPS)) < 0)
258  goto fail;
259  if (!s->new_idr && unit_type == H264_NAL_SLICE) {
260  s->new_idr = 1;
261  s->idr_sps_seen = 0;
262  s->idr_pps_seen = 0;
263  }
264  }
265 
266 next_nal:
267  buf += nal_size;
268  cumul_size += nal_size + s->length_size;
269  } while (cumul_size < buf_size);
270 
271  ret = av_packet_copy_props(out, in);
272  if (ret < 0)
273  goto fail;
274 
275 fail:
276  if (ret < 0)
277  av_packet_unref(out);
278  av_packet_free(&in);
279 
280  return ret;
281 }
282 
284 {
285  H264BSFContext *s = ctx->priv_data;
286 
287  s->idr_sps_seen = 0;
288  s->idr_pps_seen = 0;
289  s->new_idr = s->extradata_parsed;
290 }
291 
292 static const enum AVCodecID codec_ids[] = {
294 };
295 
297  .name = "h264_mp4toannexb",
298  .priv_data_size = sizeof(H264BSFContext),
302  .codec_ids = codec_ids,
303 };
#define NULL
Definition: coverity.c:32
#define AVERROR_INVALIDDATA
Invalid data found when processing input.
Definition: error.h:59
AVCodecParameters * par_out
Parameters of the output stream.
Definition: avcodec.h:5793
static void flush(AVCodecContext *avctx)
#define AV_LOG_WARNING
Something somehow does not look correct.
Definition: log.h:182
Memory handling functions.
static av_cold int init(AVCodecContext *avctx)
Definition: avrndec.c:35
The bitstream filter state.
Definition: avcodec.h:5759
int size
Definition: avcodec.h:1478
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
static int h264_mp4toannexb_init(AVBSFContext *ctx)
void * priv_data
Opaque filter-specific private data.
Definition: avcodec.h:5780
void av_packet_free(AVPacket **pkt)
Free the packet, if the packet is reference counted, it will be unreferenced first.
Definition: avpacket.c:62
uint8_t
it s the only field you need to keep assuming you have a context There is some magic you don t need to care about around this just let it vf offset
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
const char * name
Definition: avcodec.h:5809
uint8_t * data
Definition: avcodec.h:1477
void av_packet_move_ref(AVPacket *dst, AVPacket *src)
Move every field in src to dst and reset src.
Definition: avpacket.c:655
static int h264_extradata_to_annexb(AVBSFContext *ctx, const int padding)
#define AV_LOG_VERBOSE
Detailed information.
Definition: log.h:192
#define av_log(a,...)
H.264 common definitions.
#define i(width, name, range_min, range_max)
Definition: cbs_h2645.c:260
AVCodecID
Identify the syntax and semantics of the bitstream.
Definition: avcodec.h:215
#define AV_LOG_ERROR
Something went wrong and cannot losslessly be recovered.
Definition: log.h:176
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
static void h264_mp4toannexb_flush(AVBSFContext *ctx)
#define fail()
Definition: checkasm.h:120
int extradata_size
Size of the extradata content in bytes.
Definition: avcodec.h:3971
int av_packet_copy_props(AVPacket *dst, const AVPacket *src)
Copy only "properties" fields from src to dst.
Definition: avpacket.c:565
int32_t
AVFormatContext * ctx
Definition: movenc.c:48
#define s(width, name)
Definition: cbs_vp9.c:257
static int alloc_and_copy(AVPacket *out, const uint8_t *sps_pps, uint32_t sps_pps_size, const uint8_t *in, uint32_t in_size, int ps)
static int h264_mp4toannexb_filter(AVBSFContext *ctx, AVPacket *out)
int av_reallocp(void *ptr, size_t size)
Allocate, reallocate, or free a block of memory through a pointer to a pointer.
Definition: mem.c:163
Libavcodec external API header.
uint64_t_TMPL AV_WL64 unsigned int_TMPL AV_WL32 unsigned int_TMPL AV_WL24 unsigned int_TMPL AV_WL16 uint64_t_TMPL AV_WB64 unsigned int_TMPL AV_WB32 unsigned int_TMPL AV_RB24
Definition: bytestream.h:87
void av_packet_unref(AVPacket *pkt)
Wipe the packet.
Definition: avpacket.c:599
void * buf
Definition: avisynth_c.h:766
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
static int FUNC() pps(CodedBitstreamContext *ctx, RWContext *rw, H264RawPPS *current)
#define AV_WB32(p, v)
Definition: intreadwrite.h:419
static enum AVCodecID codec_ids[]
int ff_bsf_get_packet(AVBSFContext *ctx, AVPacket **pkt)
Called by the bitstream filters to get the next packet for filtering.
Definition: bsf.c:216
int av_grow_packet(AVPacket *pkt, int grow_by)
Increase packet size, correctly zeroing padding.
Definition: avpacket.c:109
#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
const AVBitStreamFilter ff_h264_mp4toannexb_bsf
#define av_free(p)
uint8_t * extradata
Extra binary data needed for initializing the decoder, codec-dependent.
Definition: avcodec.h:3967
FILE * out
Definition: movenc.c:54
#define av_freep(p)
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
This structure stores compressed data.
Definition: avcodec.h:1454
AVCodecParameters * par_in
Parameters of the input stream.
Definition: avcodec.h:5787