ffmpeg API基础

本文会简单介绍一下ffmpeg demuxer、decoder的调用流程。本系列文章基于ffmpeg4.2版本，以ffplay.c调用的ffmpeg API为切入点进行讲解。

一、Demuxer部分

ffmpeg打开媒体文件（本地/网络）的过程开始于avformat_open_input，该函数定义在avformat.h中：

/**
 * 打开输入流并读取头信息。未打开编解码器。
 * 必须使用avformat_close_input()来关闭已经打开的流。
 *
 * @param ps Pointer to user-supplied AVFormatContext (allocated by avformat_alloc_context).
 *           May be a pointer to NULL, in which case an AVFormatContext is allocated by this
 *           function and written into ps.
 *           Note that a user-supplied AVFormatContext will be freed on failure.
 * @param url URL of the stream to open.
 * @param fmt If non-NULL, this parameter forces a specific input format.
 *            Otherwise the format is autodetected.
 * @param options  A dictionary filled with AVFormatContext and demuxer-private options.
 *                 On return this parameter will be destroyed and replaced with a dict containing
 *                 options that were not found. May be NULL.
 *
 * @return 0 on success, a negative AVERROR on failure.
 *
 * @note If you want to use custom IO, preallocate the format context and set its pb field.
 */
int avformat_open_input(AVFormatContext **ps, const char *url, ff_const59 AVInputFormat *fmt, AVDictionary **options);

该函数通常是最耗时的API，它主要完成如下2件事：
(1)打开url并完成输入输出结构体AVFormatContext 的初始化（可能拿到duration，codec id等信息）；
(2)对AVInputFormat结构体中各个函数指针的赋值。
函数调用流程图如下：

avformat_open_input()

该函数在libavformat/utils.c中：

int avformat_open_input(AVFormatContext **ps, const char *filename,
                        AVInputFormat *fmt, AVDictionary **options)
{
    AVFormatContext *s = *ps;
    int i, ret = 0;
    AVDictionary *tmp = NULL;
    ID3v2ExtraMeta *id3v2_extra_meta = NULL;

    if (!s && !(s = avformat_alloc_context()))
        return AVERROR(ENOMEM);
    if (!s->av_class) {
        av_log(NULL, AV_LOG_ERROR, "Input context has not been properly allocated by avformat_alloc_context() and is not NULL either\n");
        return AVERROR(EINVAL);
    }
    if (fmt)
        s->iformat = fmt;

    if (options)
        av_dict_copy(&tmp, *options, 0);

    if (s->pb) // must be before any goto fail
        s->flags |= AVFMT_FLAG_CUSTOM_IO;

    if ((ret = av_opt_set_dict(s, &tmp)) < 0)
        goto fail;

    av_strlcpy(s->filename, filename ? filename : "", sizeof(s->filename));
    if ((ret = init_input(s, filename, &tmp)) < 0)
        goto fail;
    s->probe_score = ret;

    if (!s->protocol_whitelist && s->pb && s->pb->protocol_whitelist) {
        s->protocol_whitelist = av_strdup(s->pb->protocol_whitelist);
        if (!s->protocol_whitelist) {
            ret = AVERROR(ENOMEM);
            goto fail;
        }
    }

    if (!s->protocol_blacklist && s->pb && s->pb->protocol_blacklist) {
        s->protocol_blacklist = av_strdup(s->pb->protocol_blacklist);
        if (!s->protocol_blacklist) {
            ret = AVERROR(ENOMEM);
            goto fail;
        }
    }

    if (s->format_whitelist && av_match_list(s->iformat->name, s->format_whitelist, ',') <= 0) {
        av_log(s, AV_LOG_ERROR, "Format not on whitelist \'%s\'\n", s->format_whitelist);
        ret = AVERROR(EINVAL);
        goto fail;
    }

    avio_skip(s->pb, s->skip_initial_bytes);

    /* Check filename in case an image number is expected. */
    if (s->iformat->flags & AVFMT_NEEDNUMBER) {
        if (!av_filename_number_test(filename)) {
            ret = AVERROR(EINVAL);
            goto fail;
        }
    }

    s->duration = s->start_time = AV_NOPTS_VALUE;

    /* Allocate private data. */
    if (s->iformat->priv_data_size > 0) {
        if (!(s->priv_data = av_mallocz(s->iformat->priv_data_size))) {
            ret = AVERROR(ENOMEM);
            goto fail;
        }
        if (s->iformat->priv_class) {
            *(const AVClass **) s->priv_data = s->iformat->priv_class;
            av_opt_set_defaults(s->priv_data);
            if ((ret = av_opt_set_dict(s->priv_data, &tmp)) < 0)
                goto fail;
        }
    }

    /* e.g. AVFMT_NOFILE formats will not have a AVIOContext */
    if (s->pb)
        ff_id3v2_read_dict(s->pb, &s->internal->id3v2_meta, ID3v2_DEFAULT_MAGIC, &id3v2_extra_meta);


    if (!(s->flags&AVFMT_FLAG_PRIV_OPT) && s->iformat->read_header)
        if ((ret = s->iformat->read_header(s)) < 0)
            goto fail;
    ... ...

avformat_open_input()源代码比较长，一部分是一些容错代码，比如说如果发现传入的AVFormatContext指针没有初始化过，就调用avformat_alloc_context()初始化该结构体；还有一部分是针对一些格式做的特殊处理，比如id3v2信息的处理等等。有关上述两种信息不再详细分析，在这里只选择它关键的两个函数进行分析：
init_input()：绝大部分初始化工作都是在这里做的。
s->iformat->read_header()：读取多媒体数据文件头，根据视音频流创建相应的AVStream。

1、read_probe

    /**
     * Tell if a given file has a chance of being parsed as this format.
     * The buffer provided is guaranteed to be AVPROBE_PADDING_SIZE bytes
     * big so you do not have to check for that unless you need more.
     */
    int (*read_probe)(AVProbeData *);

从avformat_open_input开始大致的调用流程如下如所示：

ffmpeg demuxer的probe机制是以循环遍历链表的形式执行每种格式的read_probe，read_probe()会返回一个分数，分数越高代表跟对应的demuxer type越匹配，相关代码如下：

	// 以链表的形式循环遍历执行各个封装格式的read_probe
    while ((fmt1 = av_iformat_next(fmt1))) {
        if (!is_opened == !(fmt1->flags & AVFMT_NOFILE) && strcmp(fmt1->name, "image2"))
            continue;
        score = 0;
        if (fmt1->read_probe) {
            score = fmt1->read_probe(&lpd);
            if (score)
                av_log(NULL, AV_LOG_TRACE, "Probing %s score:%d size:%d\n", fmt1->name, score, lpd.buf_size);
            if (fmt1->extensions && av_match_ext(lpd.filename, fmt1->extensions)) {
                switch (nodat) {
                case NO_ID3:
                    score = FFMAX(score, 1);
                    break;
                case ID3_GREATER_PROBE:
                case ID3_ALMOST_GREATER_PROBE:
                    score = FFMAX(score, AVPROBE_SCORE_EXTENSION / 2 - 1);
                    break;
                case ID3_GREATER_MAX_PROBE:
                    score = FFMAX(score, AVPROBE_SCORE_EXTENSION);
                    break;
                }
            }
        } else if (fmt1->extensions) {
            if (av_match_ext(lpd.filename, fmt1->extensions))
                score = AVPROBE_SCORE_EXTENSION;
        }
        if (av_match_name(lpd.mime_type, fmt1->mime_type)) {
            if (AVPROBE_SCORE_MIME > score) {
                av_log(NULL, AV_LOG_DEBUG, "Probing %s score:%d increased to %d due to MIME type\n", fmt1->name, score, AVPROBE_SCORE_MIME);
                score = AVPROBE_SCORE_MIME;
            }
        }
        if (score > score_max) {
            score_max = score;
            fmt       = fmt1;
        } else if (score == score_max)
            fmt = NULL;
    }
    if (nodat == ID3_GREATER_PROBE)
        score_max = FFMIN(AVPROBE_SCORE_EXTENSION / 2 - 1, score_max);
    *score_ret = score_max;

    return fmt;
}

这里的fmt就是AVInputFormat结构体。
AVInputFormat中包含read_probe()是用于获得匹配函数的函数指针，不同的封装格式包含不同的实现函数。例如，MP4封装格式的AVInputFormat模块定义（位于libavformat\mov.c）如下所示：

AVInputFormat ff_mov_demuxer = {
    .name           = "mov,mp4,m4a,3gp,3g2,mj2",
    .long_name      = NULL_IF_CONFIG_SMALL("QuickTime / MOV"),
    .priv_class     = &mov_class,
    .priv_data_size = sizeof(MOVContext),
    .extensions     = "mov,mp4,m4a,3gp,3g2,mj2",
    .read_probe     = mov_probe,
    .read_header    = mov_read_header,
    .read_packet    = mov_read_packet,
    .read_close     = mov_read_close,
    .read_seek      = mov_read_seek,
    .flags          = AVFMT_NO_BYTE_SEEK,
};

2、read_header

    /**
     * Read the format header and initialize the AVFormatContext
     * structure. Return 0 if OK. 'avformat_new_stream' should be
     * called to create new streams.
     */
    int (*read_header)(struct AVFormatContext *);

在调用完init_input()完成基本的初始化并且推测得到相应的AVInputFormat之后，avformat_open_input()会调用AVInputFormat的read_header()方法读取媒体文件的文件头并且完成相关的初始化工作。read_header()是一个位于AVInputFormat结构体中的一个函数指针，对于不同的封装格式，会调用不同的read_header()的实现函数。

3、read_packet

4、read_seek

二、Decoder部分

未完待续…

参考文献：https://blog.csdn.net/leixiaohua1020/article/details/44064715（雷神）