Talk is cheap，Show me the code！
示例1、decode_video.c
|
int main(int argc, char **argv) { const char *filename, *outfilename; const AVCodec *codec; AVCodecContext *c= NULL; int frame_count; FILE *f; AVFrame *frame; uint8_t inbuf[INBUF_SIZE + AV_INPUT_BUFFER_PADDING_SIZE]; AVPacket avpkt; filename = argv[1]; outfilename = argv[2]; avcodec_register_all(); av_init_packet(&avpkt); codec = avcodec_find_decoder(AV_CODEC_ID_MPEG1VIDEO); c = avcodec_alloc_context3(codec); if (avcodec_open2(c, codec, NULL) < 0) { } frame = av_frame_alloc(); frame_count = 0; for (;;) { avpkt.size = fread(inbuf, 1, INBUF_SIZE, f); avpkt.data = inbuf; while (avpkt.size > 0) if (decode_write_frame(outfilename, c, frame, &frame_count, &avpkt, 0) < 0) exit(1); } avpkt.data = NULL; avpkt.size = 0; decode_write_frame(outfilename, c, frame, &frame_count, &avpkt, 1); fclose(f); avcodec_free_context(&c); av_frame_free(&frame); return 0; } static int decode_write_frame(const char *outfilename, AVCodecContext *avctx, AVFrame *frame, int *frame_count, AVPacket *pkt, int last) { len = avcodec_decode_video2(avctx, frame, &got_frame, pkt); return 0; } |
下面分析该例子涉及的几个数据结构：
1、AVPacket avpkt;
|
typedef struct AVPacket { AVBufferRef *buf; int64_t pts; int64_t dts; uint8_t *data; int size; int stream_index; int flags; AVPacketSideData *side_data; int side_data_elems; int64_t duration; int64_t pos; ///< byte position in stream, -1 if unknown } AVPacket; |
2、AVFrame *frame;
|
typedef struct AVFrame { uint8_t *data[AV_NUM_DATA_POINTERS]; int linesize[AV_NUM_DATA_POINTERS]; uint8_t **extended_data; int width, height; int nb_samples; int format; int key_frame; enum AVPictureType pict_type; AVRational sample_aspect_ratio; int64_t pts; int64_t pkt_dts; int coded_picture_number; int display_picture_number; int quality; void *opaque; int repeat_pict; int interlaced_frame; int top_field_first; int palette_has_changed; int64_t reordered_opaque; int sample_rate; uint64_t channel_layout; AVBufferRef *buf[AV_NUM_DATA_POINTERS]; AVBufferRef **extended_buf; int nb_extended_buf; AVFrameSideData **side_data; int nb_side_data; int flags; enum AVColorRange color_range; enum AVColorPrimaries color_primaries; enum AVColorTransferCharacteristic color_trc; enum AVColorSpace colorspace; enum AVChromaLocation chroma_location; int64_t best_effort_timestamp; int64_t pkt_pos; int64_t pkt_duration; AVDictionary *metadata; int decode_error_flags; int channels; int pkt_size; AVBufferRef *hw_frames_ctx; AVBufferRef *opaque_ref; } AVFrame; |
3、const AVCodec *codec;
|
codec = avcodec_find_decoder(AV_CODEC_ID_MPEG1VIDEO); AVCodec *avcodec_find_decoder(enum AVCodecID id) { return find_encdec(id, 0); } static AVCodec *find_encdec(enum AVCodecID id, int encoder) { AVCodec *p, *experimental = NULL; p = first_avcodec; id= remap_deprecated_codec_id(id); while (p) { if ((encoder ? av_codec_is_encoder(p) : av_codec_is_decoder(p)) && p->id == id) { if (p->capabilities & AV_CODEC_CAP_EXPERIMENTAL && !experimental) { experimental = p; } else return p; } p = p->next; } return experimental; } AVCodec ff_mpeg1video_decoder = { .name = "mpeg1video", .long_name = NULL_IF_CONFIG_SMALL("MPEG-1 video"), .type = AVMEDIA_TYPE_VIDEO, .id = AV_CODEC_ID_MPEG1VIDEO, .priv_data_size = sizeof(Mpeg1Context), .init = mpeg_decode_init, .close = mpeg_decode_end, .decode = mpeg_decode_frame, .capabilities = AV_CODEC_CAP_DRAW_HORIZ_BAND | AV_CODEC_CAP_DR1 | AV_CODEC_CAP_TRUNCATED | AV_CODEC_CAP_DELAY | AV_CODEC_CAP_SLICE_THREADS, .caps_internal = FF_CODEC_CAP_SKIP_FRAME_FILL_PARAM, .flush = flush, .max_lowres = 3, .update_thread_context = ONLY_IF_THREADS_ENABLED(mpeg_decode_update_thread_context) }; 这里顺便介绍一下： typedef struct Mpeg1Context { MpegEncContext mpeg_enc_ctx; int mpeg_enc_ctx_allocated; /* true if decoding context allocated */ int repeat_field; /* true if we must repeat the field */ AVPanScan pan_scan; /* some temporary storage for the panscan */ AVStereo3D stereo3d; int has_stereo3d; uint8_t *a53_caption; int a53_caption_size; uint8_t afd; int has_afd; int slice_count; AVRational save_aspect; int save_width, save_height, save_progressive_seq; AVRational frame_rate_ext; /* MPEG-2 specific framerate modificator */ int sync; /* Did we reach a sync point like a GOP/SEQ/KEYFrame? */ int tmpgexs; int first_slice; int extradata_decoded; } Mpeg1Context; 所以如果你要调用AVCodec ff_mpeg1video_decoder帮你干活，你首先要有一个Mpeg1Context，因为ff_mpeg1video_decoder的所有数据都来源于Mpeg1Context。而Mpeg1Context是在decode init的时候初始化的。 |
4、AVCodecContext *c= NULL;
|
c = avcodec_alloc_context3(codec); AVCodecContext *avcodec_alloc_context3(const AVCodec *codec) { AVCodecContext *avctx= av_malloc(sizeof(AVCodecContext)); if (!avctx) return NULL; if (init_context_defaults(avctx, codec) < 0) { av_free(avctx); return NULL; } return avctx; } static int init_context_defaults(AVCodecContext *s, const AVCodec *codec) { int flags=0; memset(s, 0, sizeof(AVCodecContext)); s->av_class = &av_codec_context_class; s->codec_type = codec ? codec->type : AVMEDIA_TYPE_UNKNOWN; if (codec) { s->codec = codec; s->codec_id = codec->id; } if(s->codec_type == AVMEDIA_TYPE_AUDIO) flags= AV_OPT_FLAG_AUDIO_PARAM; else if(s->codec_type == AVMEDIA_TYPE_VIDEO) flags= AV_OPT_FLAG_VIDEO_PARAM; else if(s->codec_type == AVMEDIA_TYPE_SUBTITLE) flags= AV_OPT_FLAG_SUBTITLE_PARAM; av_opt_set_defaults2(s, flags, flags); s->time_base = (AVRational){0,1}; s->framerate = (AVRational){ 0, 1 }; s->pkt_timebase = (AVRational){ 0, 1 }; s->get_buffer2 = avcodec_default_get_buffer2; s->get_format = avcodec_default_get_format; s->execute = avcodec_default_execute; s->execute2 = avcodec_default_execute2; s->sample_aspect_ratio = (AVRational){0,1}; s->pix_fmt = AV_PIX_FMT_NONE; s->sw_pix_fmt = AV_PIX_FMT_NONE; s->sample_fmt = AV_SAMPLE_FMT_NONE; s->reordered_opaque = AV_NOPTS_VALUE; if(codec && codec->priv_data_size){ if(!s->priv_data){ s->priv_data= av_mallocz(codec->priv_data_size); if (!s->priv_data) { return AVERROR(ENOMEM); } } if(codec->priv_class){ *(const AVClass**)s->priv_data = codec->priv_class; av_opt_set_defaults(s->priv_data); } } if (codec && codec->defaults) { int ret; const AVCodecDefault *d = codec->defaults; while (d->key) { ret = av_opt_set(s, d->key, d->value, 0); av_assert0(ret >= 0); d++; } } return 0; } |
5、avcodec_open2(c, codec, NULL)
|
初始化一些avcodeccontext的成员变量，最重要的是初始化解码器： ret = avctx->codec->init(avctx); //legacy decoder AVCodec ff_mpegvideo_decoder = { .name = "mpegvideo", .long_name = NULL_IF_CONFIG_SMALL("MPEG-1 video"), .type = AVMEDIA_TYPE_VIDEO, .id = AV_CODEC_ID_MPEG2VIDEO, .priv_data_size = sizeof(Mpeg1Context), .init = mpeg_decode_init, .close = mpeg_decode_end, .decode = mpeg_decode_frame, .capabilities = AV_CODEC_CAP_DRAW_HORIZ_BAND | AV_CODEC_CAP_DR1 | AV_CODEC_CAP_TRUNCATED | AV_CODEC_CAP_DELAY | AV_CODEC_CAP_SLICE_THREADS, .caps_internal = FF_CODEC_CAP_SKIP_FRAME_FILL_PARAM, .flush = flush, .max_lowres = 3, }; 这个太复杂，换一个H264的解码器吧，其实是一样的： AVCodec ff_h264_decoder = { .name = "h264", .long_name = NULL_IF_CONFIG_SMALL("H.264 / AVC / MPEG-4 AVC / MPEG-4 part 10"), .type = AVMEDIA_TYPE_VIDEO, .id = AV_CODEC_ID_H264, .priv_data_size = sizeof(H264Context), .init = ff_h264_decode_init, .close = h264_decode_end, .decode = h264_decode_frame, .capabilities = /*AV_CODEC_CAP_DRAW_HORIZ_BAND |*/ AV_CODEC_CAP_DR1 | AV_CODEC_CAP_DELAY | AV_CODEC_CAP_SLICE_THREADS | AV_CODEC_CAP_FRAME_THREADS, .caps_internal = FF_CODEC_CAP_INIT_THREADSAFE, .flush = flush_dpb, .init_thread_copy = ONLY_IF_THREADS_ENABLED(decode_init_thread_copy), .update_thread_context = ONLY_IF_THREADS_ENABLED(ff_h264_update_thread_context), .profiles = NULL_IF_CONFIG_SMALL(ff_h264_profiles), .priv_class = &h264_class, }; av_cold int ff_h264_decode_init(AVCodecContext *avctx) { H264Context *h = avctx->priv_data; int ret; ret = h264_init_context(avctx, h); if (ret < 0) return ret; ret = ff_thread_once(&h264_vlc_init, ff_h264_decode_init_vlc); if (ret != 0) { av_log(avctx, AV_LOG_ERROR, "pthread_once has failed."); return AVERROR_UNKNOWN; } if (avctx->ticks_per_frame == 1) { if(h->avctx->time_base.den < INT_MAX/2) { h->avctx->time_base.den *= 2; } else h->avctx->time_base.num /= 2; } avctx->ticks_per_frame = 2; if (avctx->extradata_size > 0 && avctx->extradata) { ret = ff_h264_decode_extradata(avctx->extradata, avctx->extradata_size, &h->ps, &h->is_avc, &h->nal_length_size, avctx->err_recognition, avctx); if (ret < 0) { h264_decode_end(avctx); return ret; } } if (h->ps.sps && h->ps.sps->bitstream_restriction_flag && h->avctx->has_b_frames < h->ps.sps->num_reorder_frames) { h->avctx->has_b_frames = h->ps.sps->num_reorder_frames; } avctx->internal->allocate_progress = 1; ff_h264_flush_change(h); if (h->enable_er < 0 && (avctx->active_thread_type & FF_THREAD_SLICE)) h->enable_er = 0; if (h->enable_er && (avctx->active_thread_type & FF_THREAD_SLICE)) { av_log(avctx, AV_LOG_WARNING, "Error resilience with slice threads is enabled. It is unsafe and unsupported and may crash. " "Use it at your own risk "); } return 0; } //初始化解码器的上下文，非常关键。之后解码所有的信息来源都是这里 static int h264_init_context(AVCodecContext *avctx, H264Context *h) { int i; h->avctx = avctx; h->cur_chroma_format_idc = -1; h->picture_structure = PICT_FRAME; h->workaround_bugs = avctx->workaround_bugs; h->flags = avctx->flags; h->poc.prev_poc_msb = 1 << 16; h->recovery_frame = -1; h->frame_recovered = 0; h->poc.prev_frame_num = -1; h->sei.frame_packing.frame_packing_arrangement_cancel_flag = -1; h->sei.unregistered.x264_build = -1; h->next_outputed_poc = INT_MIN; for (i = 0; i < MAX_DELAYED_PIC_COUNT; i++) h->last_pocs[i] = INT_MIN; ff_h264_sei_uninit(&h->sei); avctx->chroma_sample_location = AVCHROMA_LOC_LEFT; h->nb_slice_ctx = (avctx->active_thread_type & FF_THREAD_SLICE) ? avctx->thread_count : 1; h->slice_ctx = av_mallocz_array(h->nb_slice_ctx, sizeof(*h->slice_ctx)); if (!h->slice_ctx) { h->nb_slice_ctx = 0; return AVERROR(ENOMEM); } for (i = 0; i < H264_MAX_PICTURE_COUNT; i++) { h->DPB[i].f = av_frame_alloc(); if (!h->DPB[i].f) return AVERROR(ENOMEM); } h->cur_pic.f = av_frame_alloc(); if (!h->cur_pic.f) return AVERROR(ENOMEM); h->last_pic_for_ec.f = av_frame_alloc(); if (!h->last_pic_for_ec.f) return AVERROR(ENOMEM); for (i = 0; i < h->nb_slice_ctx; i++) h->slice_ctx[i].h264 = h; return 0; } |
6、解码：
|
ret = avctx->codec->decode(avctx, picture, got_picture_ptr, &tmp); static int h264_decode_frame(AVCodecContext *avctx, void *data, int *got_frame, AVPacket *avpkt) { const uint8_t *buf = avpkt->data; int buf_size = avpkt->size; H264Context *h = avctx->priv_data; AVFrame *pict = data; int buf_index; int ret; h->flags = avctx->flags; h->setup_finished = 0; h->nb_slice_ctx_queued = 0; ff_h264_unref_picture(h, &h->last_pic_for_ec); /* end of stream, output what is still in the buffers */ if (buf_size == 0) return send_next_delayed_frame(h, pict, got_frame, 0); if (h->is_avc && av_packet_get_side_data(avpkt, AV_PKT_DATA_NEW_EXTRADATA, NULL)) { int side_size; uint8_t *side = av_packet_get_side_data(avpkt, AV_PKT_DATA_NEW_EXTRADATA, &side_size); if (is_extra(side, side_size)) ff_h264_decode_extradata(side, side_size, &h->ps, &h->is_avc, &h->nal_length_size, avctx->err_recognition, avctx); } if(h->is_avc && buf_size >= 9 && buf[0]==1 && buf[2]==0 && (buf[4]&0xFC)==0xFC && (buf[5]&0x1F) && buf[8]==0x67){ if (is_extra(buf, buf_size)) return ff_h264_decode_extradata(buf, buf_size, &h->ps, &h->is_avc, &h->nal_length_size, avctx->err_recognition, avctx); } buf_index = decode_nal_units(h, buf, buf_size); if (buf_index < 0) return AVERROR_INVALIDDATA; if (!h->cur_pic_ptr && h->nal_unit_type == H264_NAL_END_SEQUENCE) { av_assert0(buf_index <= buf_size); return send_next_delayed_frame(h, pict, got_frame, buf_index); } if (!(avctx->flags2 & AV_CODEC_FLAG2_CHUNKS) && (!h->cur_pic_ptr || !h->has_slice)) { if (avctx->skip_frame >= AVDISCARD_NONREF || buf_size >= 4 && !memcmp("Q264", buf, 4)) return buf_size; av_log(avctx, AV_LOG_ERROR, "no frame! "); return AVERROR_INVALIDDATA; } if (!(avctx->flags2 & AV_CODEC_FLAG2_CHUNKS) || (h->mb_y >= h->mb_height && h->mb_height)) { if ((ret = ff_h264_field_end(h, &h->slice_ctx[0], 0)) < 0) return ret; /* Wait for second field. */ if (h->next_output_pic) { ret = finalize_frame(h, pict, h->next_output_pic, got_frame); if (ret < 0) return ret; } } av_assert0(pict->buf[0] || !*got_frame); ff_h264_unref_picture(h, &h->last_pic_for_ec); return get_consumed_bytes(buf_index, buf_size); } static int send_next_delayed_frame(H264Context *h, AVFrame *dst_frame, int *got_frame, int buf_index) { int ret, i, out_idx; H264Picture *out = h->delayed_pic[0]; h->cur_pic_ptr = NULL; h->first_field = 0; out_idx = 0; for (i = 1; h->delayed_pic[i] && !h->delayed_pic[i]->f->key_frame && !h->delayed_pic[i]->mmco_reset; i++) if (h->delayed_pic[i]->poc < out->poc) { out = h->delayed_pic[i]; out_idx = i; } for (i = out_idx; h->delayed_pic[i]; i++) h->delayed_pic[i] = h->delayed_pic[i + 1]; if (out) { out->reference &= ~DELAYED_PIC_REF; ret = finalize_frame(h, dst_frame, out, got_frame); if (ret < 0) return ret; } return buf_index; } static int finalize_frame(H264Context *h, AVFrame *dst, H264Picture *out, int *got_frame) { int ret; if (((h->avctx->flags & AV_CODEC_FLAG_OUTPUT_CORRUPT) || (h->avctx->flags2 & AV_CODEC_FLAG2_SHOW_ALL) || out->recovered)) { if (!h->avctx->hwaccel && (out->field_poc[0] == INT_MAX || out->field_poc[1] == INT_MAX) ) { int p; AVFrame *f = out->f; int field = out->field_poc[0] == INT_MAX; uint8_t *dst_data[4]; int linesizes[4]; const uint8_t *src_data[4]; av_log(h->avctx, AV_LOG_DEBUG, "Duplicating field %d to fill missing ", field); for (p = 0; p<4; p++) { dst_data[p] = f->data[p] + (field^1)*f->linesize[p]; src_data[p] = f->data[p] + field *f->linesize[p]; linesizes[p] = 2*f->linesize[p]; } av_image_copy(dst_data, linesizes, src_data, linesizes, f->format, f->width, f->height>>1); } ret = output_frame(h, dst, out); if (ret < 0) return ret; *got_frame = 1; if (CONFIG_MPEGVIDEO) { ff_print_debug_info2(h->avctx, dst, NULL, out->mb_type, out->qscale_table, out->motion_val, NULL, h->mb_width, h->mb_height, h->mb_stride, 1); } } return 0; } static int output_frame(H264Context *h, AVFrame *dst, H264Picture *srcp) { AVFrame *src = srcp->f; const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(src->format); int i; int ret; if (src->format == AV_PIX_FMT_VIDEOTOOLBOX && src->buf[0]->size == 1) return AVERROR_EXTERNAL; ret = av_frame_ref(dst, src); if (ret < 0) return ret; av_dict_set(&dst->metadata, "stereo_mode", ff_h264_sei_stereo_mode(&h->sei.frame_packing), 0); if (srcp->sei_recovery_frame_cnt == 0) dst->key_frame = 1; if (!srcp->crop) return 0; for (i = 0; i < desc->nb_components; i++) { int hshift = (i > 0) ? desc->log2_chroma_w : 0; int vshift = (i > 0) ? desc->log2_chroma_h : 0; int off = ((srcp->crop_left >> hshift) << h->pixel_shift) + (srcp->crop_top >> vshift) * dst->linesize[i]; dst->data[i] += off; } return 0; } |