【FFmpeg】详解FFmpeg解封装、解码流程

一个媒体文件通常包含视频数据、音频数据、字幕信息等，有的地方将这些不同的数据类别称为轨道，在FFmpeg中称为流stream。根据解封装器中已经获取的流信息，打开合适的解码器。
有几个流，就要打开几个解码器。例如：有音频流，要找到对应的音频解码器；有视频流，要找到对应的视频解码器。

3.1 获取视频、音频、字幕流在解封装上下文 AVFormatContext 的流列表 AVStream **streams 中的索引

int videoIndex = av_find_best_stream(formatContext, AVMEDIA_TYPE_VIDEO, -1, -1, NULL, 0);
int audioIndex = av_find_best_stream(formatContext, AVMEDIA_TYPE_AUDIO, -1, -1, NULL, 0);
int subtitleIndex = av_find_best_stream(formatContext, AVMEDIA_TYPE_SUBTITLE, -1, -1, NULL, 0);

3.2 使用已经获取的流信息创建对应的解码器及其上下文，以视频解码器为例

AVStream *videoStream = formatContext->streams[videoIndex];
AVCodec *videoDecode = avcodec_find_decoder(videoStream->codecpar->codec_id);
AVCodecContext *videoDecodeContext = avcodec_alloc_context3(videoDecode);
avcodec_parameters_to_context(videoDecodeContext, videoStream->codecpar);

3.3 初始化解码器上下文

avcodec_open2(*videoDecodeContext, videoDecode, NULL)

4、准备用于保存解码前后的内存空间

AVPacket 用于保存解码前的压缩数据，对于视频就是一帧图像的压缩数据，对于音频可能是压缩的好几帧数据。
AVPacket packet;
av_init_packet(&packet);
packet.data = NULL;
packet.size = 0;
AVFrame 用于保存解码后的原数据，例如对于视频流是YUV或RGB格式数据，对于音频流是PCM数据。
AVFrame *frame = av_frame_alloc();

5、获取压缩数据

使用 av_read_frame 从流中读取压缩数据到 AVPacket 中，准备解码，解码完成后，记得使用 av_packet_unref 来释放，否则会造成内存泄漏。

av_read_frame(formatContext, &packet);
av_packet_unref(&packet);

6、解码

终于看到解码了。以视频为例：走到这里，我们已经找到解码器并交给解码器上下文 AVCodecContext，压缩数据也保存到 AVPacket 中，只要将它们传入解码函数，就可以输出解码后的数据。
解码后的数据用 AVFrame 来保存。记得在解码之前，确保 AVPacket 中保存的是视频压缩数据。
if (packet.stream_index == videoIndex) {
avcodec_decode_video2(videoDecodeContext, frame, gotFrame, &packet);
}
注意：avcodec_decode_video2接口在新版本FFmpeg中已经不推荐使用，
新本版中将解码分成两步：avcodec_send_packet() 、avcodec_receive_frame()。
这样分开的好处是有两个，其一是，在一个压缩包 AVPacket 中，可能解压出多帧 AVFrame，对于这种情况要多调用几次 avcodec_receive_frame 直到返回空；
其二是，有些压缩包 AVPacket 不需要解压，比如在解码时指定了跳过不需要解码的帧 AVCodecContext.skip_frame，
这样满足一些特殊需求，例如，有的需求是丢弃双向帧B帧，有的需求是只保留关键帧。
AVCodecContext.skip_frame的取值如下：
enum AVDiscard{
AVDISCARD_NONE =-16, ///< discard nothing
AVDISCARD_DEFAULT = 0, ///< discard useless packets like 0 size packets in avi
AVDISCARD_NONREF = 8, ///< discard all non reference
AVDISCARD_BIDIR = 16, ///< discard all bidirectional frames
AVDISCARD_NONINTRA= 24, ///< discard all non intra frames
AVDISCARD_NONKEY = 32, ///< discard all frames except keyframes
AVDISCARD_ALL = 48, ///< discard all
};

7、处理解码后的数据

解码后是原数据在 frame->data 中，是显示、转换或者保存就由你来做主了。

8、参考代码

参考代码，参见FFmpeg源码中doc/examples/demuxing_decoding.c

#include <libavutil/imgutils.h>
#include <libavutil/samplefmt.h>
#include <libavutil/timestamp.h>
#include <libavformat/avformat.h>

static AVFormatContext *fmt_ctx = NULL;
static AVCodecContext *video_dec_ctx = NULL, *audio_dec_ctx;
static int width, height;
static enum AVPixelFormat pix_fmt;
static AVStream *video_stream = NULL, *audio_stream = NULL;
static const char *src_filename = NULL;
static const char *video_dst_filename = NULL;
static const char *audio_dst_filename = NULL;
static FILE *video_dst_file = NULL;
static FILE *audio_dst_file = NULL;

static uint8_t *video_dst_data[4] = {NULL};
static int      video_dst_linesize[4];
static int video_dst_bufsize;

static int video_stream_idx = -1, audio_stream_idx = -1;
static AVFrame *frame = NULL;
static AVPacket pkt;
static int video_frame_count = 0;
static int audio_frame_count = 0;

/* Enable or disable frame reference counting. You are not supposed to support
 * both paths in your application but pick the one most appropriate to your
 * needs. Look for the use of refcount in this example to see what are the
 * differences of API usage between them. */
static int refcount = 0;

static int decode_packet(int *got_frame, int cached)
{
    int ret = 0;
    int decoded = pkt.size;

    *got_frame = 0;

    if (pkt.stream_index == video_stream_idx) {
        /* decode video frame */
        ret = avcodec_decode_video2(video_dec_ctx, frame, got_frame, &pkt);
        if (ret < 0) {
            fprintf(stderr, "Error decoding video frame (%s)\n", av_err2str(ret));
            return ret;
        }

        if (*got_frame) {

            if (frame->width != width || frame->height != height ||
                frame->format != pix_fmt) {
                /* To handle this change, one could call av_image_alloc again and
                 * decode the following frames into another rawvideo file. */
                fprintf(stderr, "Error: Width, height and pixel format have to be "
                        "constant in a rawvideo file, but the width, height or "
                        "pixel format of the input video changed:\n"
                        "old: width = %d, height = %d, format = %s\n"
                        "new: width = %d, height = %d, format = %s\n",
                        width, height, av_get_pix_fmt_name(pix_fmt),
                        frame->width, frame->height,
                        av_get_pix_fmt_name(frame->format));
                return -1;
            }

            printf("video_frame%s n:%d coded_n:%d\n",
                   cached ? "(cached)" : "",
                   video_frame_count++, frame->coded_picture_number);

            /* copy decoded frame to destination buffer:
             * this is required since rawvideo expects non aligned data */
            av_image_copy(video_dst_data, video_dst_linesize,
                          (const uint8_t **)(frame->data), frame->linesize,
                          pix_fmt, width, height);

            /* write to rawvideo file */
            fwrite(video_dst_data[0], 1, video_dst_bufsize, video_dst_file);
        }
    } else if (pkt.stream_index == audio_stream_idx) {
        /* decode audio frame */
        ret = avcodec_decode_audio4(audio_dec_ctx, frame, got_frame, &pkt);
        if (ret < 0) {
            fprintf(stderr, "Error decoding audio frame (%s)\n", av_err2str(ret));
            return ret;
        }
        /* Some audio decoders decode only part of the packet, and have to be
         * called again with the remainder of the packet data.
         * Sample: fate-suite/lossless-audio/luckynight-partial.shn
         * Also, some decoders might over-read the packet. */
        decoded = FFMIN(ret, pkt.size);

        if (*got_frame) {
            size_t unpadded_linesize = frame->nb_samples * av_get_bytes_per_sample(frame->format);
            printf("audio_frame%s n:%d nb_samples:%d pts:%s\n",
                   cached ? "(cached)" : "",
                   audio_frame_count++, frame->nb_samples,
                   av_ts2timestr(frame->pts, &audio_dec_ctx->time_base));

            /* Write the raw audio data samples of the first plane. This works
             * fine for packed formats (e.g. AV_SAMPLE_FMT_S16). However,
             * most audio decoders output planar audio, which uses a separate
             * plane of audio samples for each channel (e.g. AV_SAMPLE_FMT_S16P).
             * In other words, this code will write only the first audio channel
             * in these cases.
             * You should use libswresample or libavfilter to convert the frame
             * to packed data. */
            fwrite(frame->extended_data[0], 1, unpadded_linesize, audio_dst_file);
        }
    }

    /* If we use frame reference counting, we own the data and need
     * to de-reference it when we don't use it anymore */
    if (*got_frame && refcount)
        av_frame_unref(frame);

    return decoded;
}

static int open_codec_context(int *stream_idx,
                              AVCodecContext **dec_ctx, AVFormatContext *fmt_ctx, enum AVMediaType type)
{
    int ret, stream_index;
    AVStream *st;
    AVCodec *dec = NULL;
    AVDictionary *opts = NULL;

    ret = av_find_best_stream(fmt_ctx, type, -1, -1, NULL, 0);
    if (ret < 0) {
        fprintf(stderr, "Could not find %s stream in input file '%s'\n",
                av_get_media_type_string(type), src_filename);
        return ret;
    } else {
        stream_index = ret;
        st = fmt_ctx->streams[stream_index];

        /* find decoder for the stream */
        dec = avcodec_find_decoder(st->codecpar->codec_id);
        if (!dec) {
            fprintf(stderr, "Failed to find %s codec\n",
                    av_get_media_type_string(type));
            return AVERROR(EINVAL);
        }

        /* Allocate a codec context for the decoder */
        *dec_ctx = avcodec_alloc_context3(dec);
        if (!*dec_ctx) {
            fprintf(stderr, "Failed to allocate the %s codec context\n",
                    av_get_media_type_string(type));
            return AVERROR(ENOMEM);
        }

        /* Copy codec parameters from input stream to output codec context */
        if ((ret = avcodec_parameters_to_context(*dec_ctx, st->codecpar)) < 0) {
            fprintf(stderr, "Failed to copy %s codec parameters to decoder context\n",
                    av_get_media_type_string(type));
            return ret;
        }

        /* Init the decoders, with or without reference counting */
        av_dict_set(&opts, "refcounted_frames", refcount ? "1" : "0", 0);
        if ((ret = avcodec_open2(*dec_ctx, dec, &opts)) < 0) {
            fprintf(stderr, "Failed to open %s codec\n",
                    av_get_media_type_string(type));
            return ret;
        }
        *stream_idx = stream_index;
    }

    return 0;
}

static int get_format_from_sample_fmt(const char **fmt,
                                      enum AVSampleFormat sample_fmt)
{
    int i;
    struct sample_fmt_entry {
        enum AVSampleFormat sample_fmt; const char *fmt_be, *fmt_le;
    } sample_fmt_entries[] = {
        { AV_SAMPLE_FMT_U8,  "u8",    "u8"    },
        { AV_SAMPLE_FMT_S16, "s16be", "s16le" },
        { AV_SAMPLE_FMT_S32, "s32be", "s32le" },
        { AV_SAMPLE_FMT_FLT, "f32be", "f32le" },
        { AV_SAMPLE_FMT_DBL, "f64be", "f64le" },
    };
    *fmt = NULL;

    for (i = 0; i < FF_ARRAY_ELEMS(sample_fmt_entries); i++) {
        struct sample_fmt_entry *entry = &sample_fmt_entries[i];
        if (sample_fmt == entry->sample_fmt) {
            *fmt = AV_NE(entry->fmt_be, entry->fmt_le);
            return 0;
        }
    }

    fprintf(stderr,
            "sample format %s is not supported as output format\n",
            av_get_sample_fmt_name(sample_fmt));
    return -1;
}

int main (int argc, char **argv)
{
    int ret = 0, got_frame;

    if (argc != 4 && argc != 5) {
        fprintf(stderr, "usage: %s [-refcount] input_file video_output_file audio_output_file\n"
                "API example program to show how to read frames from an input file.\n"
                "This program reads frames from a file, decodes them, and writes decoded\n"
                "video frames to a rawvideo file named video_output_file, and decoded\n"
                "audio frames to a rawaudio file named audio_output_file.\n\n"
                "If the -refcount option is specified, the program use the\n"
                "reference counting frame system which allows keeping a copy of\n"
                "the data for longer than one decode call.\n"
                "\n", argv[0]);
        exit(1);
    }
    if (argc == 5 && !strcmp(argv[1], "-refcount")) {
        refcount = 1;
        argv++;
    }
    src_filename = argv[1];
    video_dst_filename = argv[2];
    audio_dst_filename = argv[3];

    /* open input file, and allocate format context */
    if (avformat_open_input(&fmt_ctx, src_filename, NULL, NULL) < 0) {
        fprintf(stderr, "Could not open source file %s\n", src_filename);
        exit(1);
    }

    /* retrieve stream information */
    if (avformat_find_stream_info(fmt_ctx, NULL) < 0) {
        fprintf(stderr, "Could not find stream information\n");
        exit(1);
    }

    if (open_codec_context(&video_stream_idx, &video_dec_ctx, fmt_ctx, AVMEDIA_TYPE_VIDEO) >= 0) {
        video_stream = fmt_ctx->streams[video_stream_idx];

        video_dst_file = fopen(video_dst_filename, "wb");
        if (!video_dst_file) {
            fprintf(stderr, "Could not open destination file %s\n", video_dst_filename);
            ret = 1;
            goto end;
        }

        /* allocate image where the decoded image will be put */
        width = video_dec_ctx->width;
        height = video_dec_ctx->height;
        pix_fmt = video_dec_ctx->pix_fmt;
        ret = av_image_alloc(video_dst_data, video_dst_linesize,
                             width, height, pix_fmt, 1);
        if (ret < 0) {
            fprintf(stderr, "Could not allocate raw video buffer\n");
            goto end;
        }
        video_dst_bufsize = ret;
    }

    if (open_codec_context(&audio_stream_idx, &audio_dec_ctx, fmt_ctx, AVMEDIA_TYPE_AUDIO) >= 0) {
        audio_stream = fmt_ctx->streams[audio_stream_idx];
        audio_dst_file = fopen(audio_dst_filename, "wb");
        if (!audio_dst_file) {
            fprintf(stderr, "Could not open destination file %s\n", audio_dst_filename);
            ret = 1;
            goto end;
        }
    }

    /* dump input information to stderr */
    av_dump_format(fmt_ctx, 0, src_filename, 0);

    if (!audio_stream && !video_stream) {
        fprintf(stderr, "Could not find audio or video stream in the input, aborting\n");
        ret = 1;
        goto end;
    }

    frame = av_frame_alloc();
    if (!frame) {
        fprintf(stderr, "Could not allocate frame\n");
        ret = AVERROR(ENOMEM);
        goto end;
    }

    /* initialize packet, set data to NULL, let the demuxer fill it */
    av_init_packet(&pkt);
    pkt.data = NULL;
    pkt.size = 0;

    if (video_stream)
        printf("Demuxing video from file '%s' into '%s'\n", src_filename, video_dst_filename);
    if (audio_stream)
        printf("Demuxing audio from file '%s' into '%s'\n", src_filename, audio_dst_filename);

    /* read frames from the file */
    while (av_read_frame(fmt_ctx, &pkt) >= 0) {
        AVPacket orig_pkt = pkt;
        do {
            ret = decode_packet(&got_frame, 0);
            if (ret < 0)
                break;
            pkt.data += ret;
            pkt.size -= ret;
        } while (pkt.size > 0);
        av_packet_unref(&orig_pkt);
    }

    /* flush cached frames */
    pkt.data = NULL;
    pkt.size = 0;
    do {
        decode_packet(&got_frame, 1);
    } while (got_frame);

    printf("Demuxing succeeded.\n");

    if (video_stream) {
        printf("Play the output video file with the command:\n"
               "ffplay -f rawvideo -pix_fmt %s -video_size %dx%d %s\n",
               av_get_pix_fmt_name(pix_fmt), width, height,
               video_dst_filename);
    }

    if (audio_stream) {
        enum AVSampleFormat sfmt = audio_dec_ctx->sample_fmt;
        int n_channels = audio_dec_ctx->channels;
        const char *fmt;

        if (av_sample_fmt_is_planar(sfmt)) {
            const char *packed = av_get_sample_fmt_name(sfmt);
            printf("Warning: the sample format the decoder produced is planar "
                   "(%s). This example will output the first channel only.\n",
                   packed ? packed : "?");
            sfmt = av_get_packed_sample_fmt(sfmt);
            n_channels = 1;
        }

        if ((ret = get_format_from_sample_fmt(&fmt, sfmt)) < 0)
            goto end;

        printf("Play the output audio file with the command:\n"
               "ffplay -f %s -ac %d -ar %d %s\n",
               fmt, n_channels, audio_dec_ctx->sample_rate,
               audio_dst_filename);
    }

end:
    avcodec_free_context(&video_dec_ctx);
    avcodec_free_context(&audio_dec_ctx);
    avformat_close_input(&fmt_ctx);
    if (video_dst_file)
        fclose(video_dst_file);
    if (audio_dst_file)
        fclose(audio_dst_file);
    av_frame_free(&frame);
    av_free(video_dst_data[0]);

    return ret < 0;
}