FFmpegsample 分析：demux_decode_audio.c

FFmpegsample 分析：demux_decode_audio.c

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

static AVFormatContext *fmt_ctx = NULL;
static AVCodecContext *audio_dec_ctx = NULL;
static AVStream *audio_stream = NULL;
static const char *src_filename = NULL;
static const char *audio_dst_filename = NULL;
static FILE *audio_dst_file = NULL;

static int audio_stream_idx = -1;
static AVFrame *frame = NULL;
static AVPacket pkt;
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 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 */
        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;
}

static void decode(AVCodecContext *dec_ctx, AVPacket *pkt, AVFrame *frame,
                   FILE *outfile)
{
    int i, ch;
    int ret, data_size;

    /* send the packet with the compressed data to the decoder */
    ret = avcodec_send_packet(dec_ctx, pkt);
    if (ret < 0) {
        fprintf(stderr, "Error submitting the packet to the decoder\n");
        exit(1);
    }

    /* read all the output frames (in general there may be any number of them */
    while (ret >= 0) {
        ret = avcodec_receive_frame(dec_ctx, frame);
        if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
            return;
        else if (ret < 0) {
            fprintf(stderr, "Error during decoding\n");
            exit(1);
        }
        data_size = av_get_bytes_per_sample(dec_ctx->sample_fmt);
        if (data_size < 0) {
            /* This should not occur, checking just for paranoia */
            fprintf(stderr, "Failed to calculate data size\n");
            exit(1);
        }
        for (i = 0; i < frame->nb_samples; i++)
            for (ch = 0; ch < dec_ctx->channels; ch++)
                fwrite(frame->data[ch] + data_size*i, 1, data_size, outfile);
    }
}

void print_usage(void)
{
    fprintf(stderr, "usage: demuxer_decode_audio input_file audio_output_file\n");
    exit(1);
}

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

    if (argc != 3) {
       print_usage();
    }
   
    src_filename = argv[1];
    audio_dst_filename = argv[2];

    /* 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(&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) {
        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 (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) {
        decode(audio_dec_ctx, &pkt, frame, audio_dst_file);
    }

    /* flush cached frames */
    pkt.data = NULL;
    pkt.size = 0;
    decode(audio_dec_ctx, &pkt, frame, audio_dst_file);

    printf("Demuxing decode succeeded.\n");

    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);
        }

        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(&audio_dec_ctx);
    avformat_close_input(&fmt_ctx);
    if (audio_dst_file)
        fclose(audio_dst_file);
    av_frame_free(&frame);

    return ret < 0;
}

编译

gcc -o demuxer_decode_audio demuxer_decode_audio.c  `pkg-config --cflags --libs libavformat libavutil libavcodec`