大家都知道，ffmpeg是一個強大的轉碼程式，但是ffmpeg功能實在太多了，以至於我們讀ffmpeg.c都覺得特別頭疼！其實你我都只是想看看mp4轉ts，或avi轉mkv怎麼做的~

好吧，其實ffmpeg的原始碼裡有sample code，是簡化版的轉碼程式，讀起來就容易多了！
具體位置：ffmpeg/doc/examples/transcoding.c。

我把這個程式碼拉出來，修改了一下，單獨編譯成一個程式。也很好用。
為了讓更多的朋友瞭解，我決定博此一文，說說這個轉碼程式！

1 原始碼+詳細註釋

#include <libavcodec/avcodec.h>
 

#include <libavformat/avformat.h>
#include <libavfilter/avfiltergraph.h>
#include <libavfilter/buffersink.h>
#include <libavfilter/buffersrc.h>
#include <libavutil/opt.h>
#include <libavutil/pixdesc.h>

static AVFormatContext *ifmt_ctx;//DEMUX,比如把輸入的input.mp4拆分為audio和video的ES資料
 

static AVFormatContext *ofmt_ctx;//MUX，比如把編碼好的audio/video ES資料打包成output.ts
typedef struct FilteringContext {
    AVFilterContext *buffersink_ctx;
    AVFilterContext *buffersrc_ctx;
    AVFilterGraph *filter_graph;
} FilteringContext;
static FilteringContext *filter_ctx;

//開啟並解析要轉碼的原始檔(如input.mp4)，並分配相應的decoder
 

//比如，原始檔是input.mp4(H264+AAC),那麼就有2個stream，分配2個decoder，H264 decoder & AAC decoder
static int open_input_file(const char *filename)
{
    int ret;
    unsigned int i;

    ifmt_ctx = NULL;
    if ((ret = avformat_open_input(&ifmt_ctx, filename, NULL, NULL)) < 0) {
        printf("Cannot open input file\n");
        return ret;
    }

    if ((ret = avformat_find_stream_info(ifmt_ctx, NULL)) < 0) {
        printf("Cannot find stream information\n");
        return ret;
    }

    //一般有2個streams,一個video, 一個audio
    for (i = 0; i < ifmt_ctx->nb_streams; i++) {
        AVStream *stream;
        AVCodecContext *codec_ctx;
        stream = ifmt_ctx->streams[i];
        codec_ctx = stream->codec;
        /* Reencode video & audio and remux subtitles etc. */
        if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO
                || codec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
            /* Open decoder */
            //為stream尋找一個合適的decoder，for example, video stream use H264 decoder, audio stream use AAC decoder
            ret = avcodec_open2(codec_ctx,
                    avcodec_find_decoder(codec_ctx->codec_id), NULL);
            if (ret < 0) {
                printf("Failed to open decoder for stream #%u\n", i);
                return ret;
            }
        }
    }

    av_dump_format(ifmt_ctx, 0, filename, 0);
    return 0;
}

//開啟輸出檔案，如我們的目標是轉碼成TS檔案，output.ts
//分配相應的encoder, 本例，encoder的codec與decoder的一樣。也就是, output.ts的codec還是和input.mp4一樣(H264+AAC)
static int open_output_file(const char *filename)
{
    AVStream *out_stream;
    AVStream *in_stream;
    AVCodecContext *dec_ctx, *enc_ctx;
    AVCodec *encoder;
    int ret;
    unsigned int i;

    ofmt_ctx = NULL;
    avformat_alloc_output_context2(&ofmt_ctx, NULL, NULL, filename);
    if (!ofmt_ctx) {
        printf("Could not create output context\n");
        return AVERROR_UNKNOWN;
    }


    for (i = 0; i < ifmt_ctx->nb_streams; i++) {
        out_stream = avformat_new_stream(ofmt_ctx, NULL);
        if (!out_stream) {
            printf("Failed allocating output stream\n");
            return AVERROR_UNKNOWN;
        }

        in_stream = ifmt_ctx->streams[i];
        dec_ctx = in_stream->codec;
        enc_ctx = out_stream->codec;

        if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO
                || dec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
            // in this example, we choose transcoding to same codec 
            //假設輸入input.mp4(H264+AAC), 那輸出還是H264+AAC, 只不過容器變成ts, 輸出名字output.ts
            encoder = avcodec_find_encoder(dec_ctx->codec_id);
            if (!encoder) {
                av_log(NULL, AV_LOG_FATAL, "Necessary encoder not found\n");
                return AVERROR_INVALIDDATA;
            }

            /* In this example, we transcode to same properties (picture size,
             * sample rate etc.). These properties can be changed for output
             * streams easily using filters */
            if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
                enc_ctx->height = dec_ctx->height;
                enc_ctx->width = dec_ctx->width;
                enc_ctx->sample_aspect_ratio = dec_ctx->sample_aspect_ratio;
                /* take first format from list of supported formats */
                enc_ctx->pix_fmt = encoder->pix_fmts[0];
                /* video time_base can be set to whatever is handy and supported by encoder */
                enc_ctx->time_base = dec_ctx->time_base;
            } else {
                enc_ctx->sample_rate = dec_ctx->sample_rate;
                enc_ctx->channel_layout = dec_ctx->channel_layout;
                enc_ctx->channels = av_get_channel_layout_nb_channels(enc_ctx->channel_layout);
                /* take first format from list of supported formats */
                enc_ctx->sample_fmt = encoder->sample_fmts[0];
                enc_ctx->time_base = (AVRational){1, enc_ctx->sample_rate};
            }

            /* Third parameter can be used to pass settings to encoder */
            ret = avcodec_open2(enc_ctx, encoder, NULL);
            if (ret < 0) {
                printf("Cannot open video encoder for stream #%u\n", i);
                return ret;
            }
        } else if (dec_ctx->codec_type == AVMEDIA_TYPE_UNKNOWN) {
            av_log(NULL, AV_LOG_FATAL, "Elementary stream #%d is of unknown type, cannot proceed\n", i);
            return AVERROR_INVALIDDATA;
        } else {
            /* if this stream must be remuxed */
            ret = avcodec_copy_context(ofmt_ctx->streams[i]->codec,
                    ifmt_ctx->streams[i]->codec);
            if (ret < 0) {
                printf("Copying stream context failed\n");
                return ret;
            }
        }

        if (ofmt_ctx->oformat->flags & AVFMT_GLOBALHEADER)
            enc_ctx->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;

    }
    av_dump_format(ofmt_ctx, 0, filename, 1);

    if (!(ofmt_ctx->oformat->flags & AVFMT_NOFILE)) {
        ret = avio_open(&ofmt_ctx->pb, filename, AVIO_FLAG_WRITE);
        if (ret < 0) {
            printf("Could not open output file '%s'", filename);
            return ret;
        }
    }

    /* init muxer, write output file header */
    ret = avformat_write_header(ofmt_ctx, NULL);
    if (ret < 0) {
        printf("Error occurred when opening output file\n");
        return ret;
    }

    return 0;
}

//filter不要怕，請看http://blog.csdn.net/newchenxf/article/details/51364105
//其實對本例，你可以忽略其細節，就把filter當作FIFO，輸入就是buffersrc，輸出就是buffersink，buffer無非在這走了個過場而已。
//不過不用filter，直接把buffer從decoder送給encoder，也是可以的。只不過缺點是，這buffer就不能改了，不像用filter，你還可以處理buffer
static int init_filter(FilteringContext* fctx, AVCodecContext *dec_ctx,
        AVCodecContext *enc_ctx, const char *filter_spec)
{
    char args[512];
    int ret = 0;
    AVFilter *buffersrc = NULL;
    AVFilter *buffersink = NULL;
    AVFilterContext *buffersrc_ctx = NULL;
    AVFilterContext *buffersink_ctx = NULL;
    AVFilterInOut *outputs = avfilter_inout_alloc();
    AVFilterInOut *inputs  = avfilter_inout_alloc();
    AVFilterGraph *filter_graph = avfilter_graph_alloc();

    if (!outputs || !inputs || !filter_graph) {
        ret = AVERROR(ENOMEM);
        goto end;
    }

    if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
        buffersrc = avfilter_get_by_name("buffer");
        buffersink = avfilter_get_by_name("buffersink");
        if (!buffersrc || !buffersink) {
            printf("filtering source or sink element not found\n");
            ret = AVERROR_UNKNOWN;
            goto end;
        }

        snprintf(args, sizeof(args),
                "video_size=%dx%d:pix_fmt=%d:time_base=%d/%d:pixel_aspect=%d/%d",
                dec_ctx->width, dec_ctx->height, dec_ctx->pix_fmt,
                dec_ctx->time_base.num, dec_ctx->time_base.den,
                dec_ctx->sample_aspect_ratio.num,
                dec_ctx->sample_aspect_ratio.den);

        ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in",
                args, NULL, filter_graph);
        if (ret < 0) {
            printf("Cannot create buffer source\n");
            goto end;
        }

        ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out",
                NULL, NULL, filter_graph);
        if (ret < 0) {
            printf("Cannot create buffer sink\n");
            goto end;
        }

        ret = av_opt_set_bin(buffersink_ctx, "pix_fmts",
                (uint8_t*)&enc_ctx->pix_fmt, sizeof(enc_ctx->pix_fmt),
                AV_OPT_SEARCH_CHILDREN);
        if (ret < 0) {
            printf("Cannot set output pixel format\n");
            goto end;
        }
    } else if (dec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
        buffersrc = avfilter_get_by_name("abuffer");
        buffersink = avfilter_get_by_name("abuffersink");
        if (!buffersrc || !buffersink) {
            printf("filtering source or sink element not found\n");
            ret = AVERROR_UNKNOWN;
            goto end;
        }

        if (!dec_ctx->channel_layout)
            dec_ctx->channel_layout =
                av_get_default_channel_layout(dec_ctx->channels);
        snprintf(args, sizeof(args),
                "time_base=%d/%d:sample_rate=%d:sample_fmt=%s:channel_layout=0x%"PRIx64,
                dec_ctx->time_base.num, dec_ctx->time_base.den, dec_ctx->sample_rate,
                av_get_sample_fmt_name(dec_ctx->sample_fmt),
                dec_ctx->channel_layout);
        ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in",
                args, NULL, filter_graph);
        if (ret < 0) {
            printf("Cannot create audio buffer source\n");
            goto end;
        }

        ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out",
                NULL, NULL, filter_graph);
        if (ret < 0) {
            printf("Cannot create audio buffer sink\n");
            goto end;
        }

        ret = av_opt_set_bin(buffersink_ctx, "sample_fmts",
                (uint8_t*)&enc_ctx->sample_fmt, sizeof(enc_ctx->sample_fmt),
                AV_OPT_SEARCH_CHILDREN);
        if (ret < 0) {
            printf("Cannot set output sample format\n");
            goto end;
        }

        ret = av_opt_set_bin(buffersink_ctx, "channel_layouts",
                (uint8_t*)&enc_ctx->channel_layout,
                sizeof(enc_ctx->channel_layout), AV_OPT_SEARCH_CHILDREN);
        if (ret < 0) {
            printf("Cannot set output channel layout\n");
            goto end;
        }

        ret = av_opt_set_bin(buffersink_ctx, "sample_rates",
                (uint8_t*)&enc_ctx->sample_rate, sizeof(enc_ctx->sample_rate),
                AV_OPT_SEARCH_CHILDREN);
        if (ret < 0) {
            printf("Cannot set output sample rate\n");
            goto end;
        }
    } else {
        ret = AVERROR_UNKNOWN;
        goto end;
    }

    /* Endpoints for the filter graph. */
    outputs->name       = av_strdup("in");
    outputs->filter_ctx = buffersrc_ctx;
    outputs->pad_idx    = 0;
    outputs->next       = NULL;

    inputs->name       = av_strdup("out");
    inputs->filter_ctx = buffersink_ctx;
    inputs->pad_idx    = 0;
    inputs->next       = NULL;

    if (!outputs->name || !inputs->name) {
        ret = AVERROR(ENOMEM);
        goto end;
    }

    if ((ret = avfilter_graph_parse_ptr(filter_graph, filter_spec,
                    &inputs, &outputs, NULL)) < 0)
        goto end;

    if ((ret = avfilter_graph_config(filter_graph, NULL)) < 0)
        goto end;

    /* Fill FilteringContext */
    fctx->buffersrc_ctx = buffersrc_ctx;
    fctx->buffersink_ctx = buffersink_ctx;
    fctx->filter_graph = filter_graph;

end:
    avfilter_inout_free(&inputs);
    avfilter_inout_free(&outputs);

    return ret;
}

static int init_filters(void)
{
    const char *filter_spec;
    unsigned int i;
    int ret;
    filter_ctx = av_malloc_array(ifmt_ctx->nb_streams, sizeof(*filter_ctx));
    if (!filter_ctx)
        return AVERROR(ENOMEM);

    for (i = 0; i < ifmt_ctx->nb_streams; i++) {
        filter_ctx[i].buffersrc_ctx  = NULL;
        filter_ctx[i].buffersink_ctx = NULL;
        filter_ctx[i].filter_graph   = NULL;
        if (!(ifmt_ctx->streams[i]->codec->codec_type == AVMEDIA_TYPE_AUDIO
                || ifmt_ctx->streams[i]->codec->codec_type == AVMEDIA_TYPE_VIDEO))
            continue;


        if (ifmt_ctx->streams[i]->codec->codec_type == AVMEDIA_TYPE_VIDEO)
            filter_spec = "null"; /* passthrough (dummy) filter for video */
        else
            filter_spec = "anull"; /* passthrough (dummy) filter for audio */
        ret = init_filter(&filter_ctx[i], ifmt_ctx->streams[i]->codec,
                ofmt_ctx->streams[i]->codec, filter_spec);
        if (ret)
            return ret;
    }
    return 0;
}

static void dumptimebase(const char* flag, int stream_index, AVRational timebase) {
    printf("%s[%d]: timebase: %d/%d \n", flag, stream_index, timebase.num, timebase.den);
}

static int encode_write_frame(AVFrame *filt_frame, unsigned int stream_index, int *got_frame) {
    int ret;
    int got_frame_local;
    AVPacket enc_pkt;
    //函式指標，看要encode video or audio
    int (*enc_func)(AVCodecContext *, AVPacket *, const AVFrame *, int *) =
        (ifmt_ctx->streams[stream_index]->codec->codec_type ==
         AVMEDIA_TYPE_VIDEO) ? avcodec_encode_video2 : avcodec_encode_audio2;

    if (!got_frame)
        got_frame = &got_frame_local;

    printf("Encoding frame\n");
    /* encode filtered frame */
    enc_pkt.data = NULL;
    enc_pkt.size = 0;
    av_init_packet(&enc_pkt);
    ret = enc_func(ofmt_ctx->streams[stream_index]->codec, &enc_pkt,
            filt_frame, got_frame);
    av_frame_free(&filt_frame);
    if (ret < 0)
        return ret;
    if (!(*got_frame))
        return 0;

    // 編碼完成，準備做muxing，做之前，又得把time_base，從encoder，轉到輸出的time_base
    enc_pkt.stream_index = stream_index;
    printf("stream[%d]: finish encoding, enc_pkt.pts = %lld\n", stream_index, enc_pkt.pts);
    dumptimebase("output streams", stream_index, ofmt_ctx->streams[stream_index]->time_base);
    dumptimebase("output streams codec ", stream_index, ofmt_ctx->streams[stream_index]->codec->time_base);
    av_packet_rescale_ts(&enc_pkt,
                         ofmt_ctx->streams[stream_index]->codec->time_base,
                         ofmt_ctx->streams[stream_index]->time_base);

    printf("stream[%d], after scale, now enc_pkt.pts = %lld\n", stream_index, enc_pkt.pts);

    printf("Muxing frame\n");
    /* mux encoded frame */
    ret = av_interleaved_write_frame(ofmt_ctx, &enc_pkt);
    return ret;
}

static int filter_encode_write_frame(AVFrame *frame, unsigned int stream_index)
{
    int ret;
    AVFrame *filt_frame;

    printf("Pushing decoded frame to filters\n");
    // push the decoded frame into the filtergraph
    //其實你如果不知道filter，也不怕，就把它當作一個FIFO，buffersrc是FIFO的輸入，buffersinkFIFO的輸出
    //這裡做的，無非就是先把buffer送到FIFO，待會要encode時，再從FIFO拿資料，其實很簡單的
    ret = av_buffersrc_add_frame_flags(filter_ctx[stream_index].buffersrc_ctx,
            frame, 0);
    if (ret < 0) {
        printf("Error while feeding the filtergraph\n");
        return ret;
    }

    /* pull filtered frames from the filtergraph */
    while (1) {
        filt_frame = av_frame_alloc();
        if (!filt_frame) {
            ret = AVERROR(ENOMEM);
            break;
        }
        printf("Pulling filtered frame from filters\n");
        //如上文所說，就當作從FIFO拿出資料
        ret = av_buffersink_get_frame(filter_ctx[stream_index].buffersink_ctx,
                filt_frame);
        if (ret < 0) {
            /* if no more frames for output - returns AVERROR(EAGAIN)
             * if flushed and no more frames for output - returns AVERROR_EOF
             * rewrite retcode to 0 to show it as normal procedure completion
             */
            if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
                ret = 0;
            av_frame_free(&filt_frame);
            break;
        }

        filt_frame->pict_type = AV_PICTURE_TYPE_NONE;
        //好了，FIFO走了個過場，真的要開始編碼了
        ret = encode_write_frame(filt_frame, stream_index, NULL);
        if (ret < 0)
            break;
    }

    return ret;
}

static int flush_encoder(unsigned int stream_index)
{
    int ret;
    int got_frame;

    if (!(ofmt_ctx->streams[stream_index]->codec->codec->capabilities &
                AV_CODEC_CAP_DELAY))
        return 0;

    while (1) {
        av_log(NULL, AV_LOG_INFO, "Flushing stream #%u encoder\n", stream_index);
        ret = encode_write_frame(NULL, stream_index, &got_frame);
        if (ret < 0)
            break;
        if (!got_frame)
            return 0;
    }
    return ret;
}


int main(int argc, char **argv)
{
    int ret;
    AVPacket packet = { .data = NULL, .size = 0 };
    AVFrame *frame = NULL;
    enum AVMediaType type;
    unsigned int stream_index;
    unsigned int i;
    int got_frame;
    int (*dec_func)(AVCodecContext *, AVFrame *, int *, const AVPacket *);

    if (argc != 3) {
        printf("Usage: %s <input file> <output file>\n", argv[0]);
        return 1;
    }
    //任何ffmpeg程式，都得av_register_all()，哈哈!
    av_register_all();
    avfilter_register_all();

    if ((ret = open_input_file(argv[1])) < 0)
        goto end;
    if ((ret = open_output_file(argv[2])) < 0)
        goto end;
    if ((ret = init_filters()) < 0)
        goto end;

    /* read all packets */
    while (1) {
        //從輸入檔案讀取一幀ES資料，要麼是音訊，要麼是視訊
        if ((ret = av_read_frame(ifmt_ctx, &packet)) < 0)
            break;
        //stream_index表示這一幀是屬於哪個流(要麼是視訊流，要麼是音訊流, 一般視訊流，stream_index=0,音訊流stream_index=1
        stream_index = packet.stream_index;
        type = ifmt_ctx->streams[packet.stream_index]->codec->codec_type;
        //printf("Demuxer gave frame of stream_index %u\n", stream_index);

        if (filter_ctx[stream_index].filter_graph) {
            printf("Going to reencode&filter the frame\n");
            //先分配一個空幀，準備儲存解碼的資料
            frame = av_frame_alloc();
            if (!frame) {
                ret = AVERROR(ENOMEM);
                break;
            }
            //packet的pts的time_base是基於編碼格式的，比如TS碼流，就是"1/90000"，要解碼了，所以要scale到decoder，decoder的time_base一般="1/FPS"
            printf("stream[%d]:  before scale, packet pts %lld\n", stream_index, packet.pts);
            av_packet_rescale_ts(&packet,
                                 ifmt_ctx->streams[stream_index]->time_base,
                                 ifmt_ctx->streams[stream_index]->codec->time_base);
            dumptimebase("streams", stream_index, ifmt_ctx->streams[stream_index]->time_base);
            dumptimebase("streams codec", stream_index, ifmt_ctx->streams[stream_index]->codec->time_base);
            printf("stream[%d]:  after scale, packet pts %lld\n", stream_index, packet.pts);

            //函式指標，根據情況，解碼音訊或者視訊
            dec_func = (type == AVMEDIA_TYPE_VIDEO) ? avcodec_decode_video2 :
                avcodec_decode_audio4;
            ret = dec_func(ifmt_ctx->streams[stream_index]->codec, frame,
                    &got_frame, &packet);
            if (ret < 0) {
                av_frame_free(&frame);
                printf("Decoding failed\n");
                break;
            }

            //解碼成功!準備開始編碼咯
            if (got_frame) {
                //其實，這時候解碼出來的frame，pts一般=AV_NOPTS_VALUE，即64位的最小值-9223372036854775808(0x8000000000000000)
                printf("stream_index %d: decode a frame:  frame->pts %lld, %lld \n", stream_index, frame->pts, AV_NOPTS_VALUE);
                //所以，就呼叫av_frame_get_best_effort_timestamp，這個函式獲得的，就是上面packet.pts
                //av_frame_get_best_effort_timestamp是由巨集定義的，搜尋ffmpeg原始碼是搜尋不到的。
                //巨集定義在ffmpeg-2.7.1\libavutil\internal.h
                //type av_##name##_get_##field(const str *s) { return s->field; } \  void av_##name##_set_##field(str *s, type v) { s->field = v; }
                //set函式,就在上面做decode的時候呼叫的，所以get才能獲得packet.pts
                frame->pts = av_frame_get_best_effort_timestamp(frame);
                printf("stream index %d: av_frame_get_best_effort_timestamp,  frame->pts %lld\n", stream_index, frame->pts);

                //準備編碼並寫入輸出檔案
                ret = filter_encode_write_frame(frame, stream_index);
                av_frame_free(&frame);
                if (ret < 0)
                    goto end;
            } else {
                printf("didn't got frame? \n");
                av_frame_free(&frame);
            }
        } else {
            /* remux this frame without reencoding */
            av_packet_rescale_ts(&packet,
                                 ifmt_ctx->streams[stream_index]->time_base,
                                 ofmt_ctx->streams[stream_index]->time_base);

            ret = av_interleaved_write_frame(ofmt_ctx, &packet);
            if (ret < 0)
                goto end;
        }
        av_packet_unref(&packet);
    }

    /* flush filters and encoders */
    for (i = 0; i < ifmt_ctx->nb_streams; i++) {
        /* flush filter */
        if (!filter_ctx[i].filter_graph)
            continue;
        ret = filter_encode_write_frame(NULL, i);
        if (ret < 0) {
            printf("Flushing filter failed\n");
            goto end;
        }

        /* flush encoder */
        ret = flush_encoder(i);
        if (ret < 0) {
            printf("Flushing encoder failed\n");
            goto end;
        }
    }
    //寫輸出檔案的尾巴
    av_write_trailer(ofmt_ctx);

end:
    av_packet_unref(&packet);
    av_frame_free(&frame);
    for (i = 0; i < ifmt_ctx->nb_streams; i++) {
        avcodec_close(ifmt_ctx->streams[i]->codec);
        if (ofmt_ctx && ofmt_ctx->nb_streams > i && ofmt_ctx->streams[i] && ofmt_ctx->streams[i]->codec)
            avcodec_close(ofmt_ctx->streams[i]->codec);
        if (filter_ctx && filter_ctx[i].filter_graph)
            avfilter_graph_free(&filter_ctx[i].filter_graph);
    }
    av_free(filter_ctx);
    avformat_close_input(&ifmt_ctx);
    if (ofmt_ctx && !(ofmt_ctx->oformat->flags & AVFMT_NOFILE))
        avio_closep(&ofmt_ctx->pb);
    avformat_free_context(ofmt_ctx);

    if (ret < 0)
        printf("Error occurred: %s\n", av_err2str(ret));

    return ret ? 1 : 0;
}

2 詳細解析

看了程式碼，可能你還意猶未盡。
那麼，我先來說說程式碼的流程。

既然是轉碼，那整理流程就是，先把一個原始檔，比如input.mp4，拆包（DEMUX），獲得編碼過的資料packet，然後把packet送給decoder解碼，獲得audio/video的原始資料frame，再把frame送給encoder編碼，又變成編碼過的資料packet，然後把packet打包(MUX)成另一種格式，比如output.ts。

程式流程圖就不說了，程式碼量那麼少，一看就知道。

3 關於PTS

本例最難懂的就是PTS的計算。

time_base

time_base稱為時間基準，在不同的階段(結構體)，每個time_base具體的值不一樣，ffmpeg提供函式av_packet_rescale_ts()在各個time_base中進行切換。
time_base主要在2個結構體最常用，一個是AVStream。

//libavformat/avformat.h
typedef struct AVStream {
    AVCodecContext *codec;

    /**
     * This is the fundamental unit of time (in seconds) in terms
     * of which frame timestamps are represented.
     *
     * decoding: set by libavformat
     * encoding: May be set by the caller before avformat_write_header() to
     *           provide a hint to the muxer about the desired timebase. In
     *           avformat_write_header(), the muxer will overwrite this field
     *           with the timebase that will actually be used for the timestamps
     *           written into the file (which may or may not be related to the
     *           user-provided one, depending on the format).
     */
    AVRational time_base;
    //......
}

一個是AVCodecContext

//libavcodec/avcodec.h
typedef struct AVCodecContext {
    const AVClass *av_class;
    enum AVMediaType codec_type; /* see AVMEDIA_TYPE_xxx */
    const struct AVCodec  *codec;

    /**
     * This is the fundamental unit of time (in seconds) in terms
     * of which frame timestamps are represented. For fixed-fps content,
     * timebase should be 1/framerate and timestamp increments should be
     * identically 1.
     * This often, but not always is the inverse of the frame rate or field rate
     * for video. 1/time_base is not the average frame rate if the frame rate is not
     * constant.
     *
     * Like containers, elementary streams also can store timestamps, 1/time_base
     * is the unit in which these timestamps are specified.
     * As example of such codec time base see ISO/IEC 14496-2:2001(E)
     * vop_time_increment_resolution and fixed_vop_rate
     * (fixed_vop_rate == 0 implies that it is different from the framerate)
     *
     * - encoding: MUST be set by user.
     * - decoding: the use of this field for decoding is deprecated.
     *             Use framerate instead.
     */
    AVRational time_base;

AVRational 本身很簡單，定義是

typedef struct AVRational{
    int num; ///< numerator
    int den; ///< denominator
} AVRational;

什麼意思呢？
以video為例子。
在AVStream的階段，也就是還沒解碼之前的原始資料，假設是mp4檔案，FPS = 15，那麼
time_base={1， 15}，那麼
懂第一幀到開始，每一ES packet的PTS就是1， 2， 3，。。。。
為何呢？
簡單啊，比如第一幀，packet.pts=1，實際的packet.pts = 1/15 = 0.0666s
同理第二幀，packet.pts=2，實際的packet.pts = 2/15 = 0.1333s
到第15幀，packet.pts=15，實際的packet.pts = 15/15 = 1s
也符合我們的預想嘛！