ffmpeg学习之音频解码数据

音频数据经过解码后会被保存为，pcm数据格式。而对应的处理流程如下所示。

avcodec_find_encoder() 

/**
 * 查找具有匹配编解码器ID的已注册编码器.
 *
 * @param id AVCodecID of the requested encoder
 * @return An encoder if one was found, NULL otherwise.
 */
const AVCodec *avcodec_find_encoder(enum AVCodecID id);

avcodec_find_encoder_by_name() 

/**
 * 查找具有指定名称的已注册编码器.
 *
 * @param name name of the requested encoder
 * @return An encoder if one was found, NULL otherwise.
 */
const AVCodec *avcodec_find_encoder_by_name(const char *name);

avcodec_alloc_context3(） 

/**
分配AVCodecContext并将其字段设置为默认值。该应使用avcodec_free_context（）释放结果结构。
 *
 * @param codec if non-NULL, allocate private data and initialize defaults
 *              for the given codec. It is illegal to then call avcodec_open2()
 *              with a different codec.
 *              If NULL, then the codec-specific defaults won't be initialized,
 *              which may result in suboptimal default settings (this is
 *              important mainly for encoders, e.g. libx264).
 *
 * @return An AVCodecContext filled with default values or NULL on failure.
 */
AVCodecContext *avcodec_alloc_context3(const AVCodec *codec);

 设置对应音频编码的数据类型

    codec_ctx->sample_fmt = AV_SAMPLE_FMT_S16;          //输入音频的采样大小
    codec_ctx->channel_layout = AV_CH_LAYOUT_STEREO;    //输入音频的channel layout
    codec_ctx->channels = 2;                            //输入音频 channel 个数
    codec_ctx->sample_rate = 44100;                     //输入音频的采样率
    codec_ctx->bit_rate = 0; //AAC_LC: 128K, AAC HE: 64K, AAC HE V2: 32K
    codec_ctx->profile = FF_PROFILE_AAC_HE_V2; //阅读 ffmpeg 代码

设置编码的frame的相关参数

//set parameters
    frame->nb_samples     = 512;                //单通道一个音频帧的采样数
    frame->format         = AV_SAMPLE_FMT_S16;  //每个采样的大小
    frame->channel_layout = AV_CH_LAYOUT_STEREO; //channel layout

整个代码:

#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
 extern "C"{
    
    
    #include <libavcodec/avcodec.h>
    #include <libavutil/channel_layout.h>
    #include <libavutil/common.h>
    #include <libavutil/frame.h>
    #include <libavutil/samplefmt.h>
 }

   

 
/* check that a given sample format is supported by the encoder */
static int check_sample_fmt(const AVCodec *codec, enum AVSampleFormat sample_fmt)
{
    const enum AVSampleFormat *p = codec->sample_fmts;
 
    while (*p != AV_SAMPLE_FMT_NONE) {
        if (*p == sample_fmt)
            return 1;
        p++;
    }
    return 0;
}
 
/* just pick the highest supported samplerate */
static int select_sample_rate(const AVCodec *codec)
{
    const int *p;
    int best_samplerate = 0;
 
    if (!codec->supported_samplerates)
        return 44100;
 
    p = codec->supported_samplerates;
    while (*p) {
        if (!best_samplerate || abs(44100 - *p) < abs(44100 - best_samplerate))
            best_samplerate = *p;
        p++;
    }
    return best_samplerate;
}
 
/* select layout with the highest channel count */
static int select_channel_layout(const AVCodec *codec, AVChannelLayout *dst){

    const AVChannelLayout *p, *best_ch_layout;
    int best_nb_channels   = 0;
 
    if (!codec->ch_layouts){
        AVChannelLayout src = (AVChannelLayout)AV_CHANNEL_LAYOUT_STEREO;
        return av_channel_layout_copy(dst,&src);
    }
      
 
    p = codec->ch_layouts;
    while (p->nb_channels) {
        int nb_channels = p->nb_channels;
 
        if (nb_channels > best_nb_channels) {
            best_ch_layout   = p;
            best_nb_channels = nb_channels;
        }
        p++;
    }
    return av_channel_layout_copy(dst, best_ch_layout);
}
 
static void encode(AVCodecContext *ctx, AVFrame *frame, AVPacket *pkt,
                   FILE *output)
{
    int ret;
 
    /* send the frame for encoding */
    ret = avcodec_send_frame(ctx, frame);
    if (ret < 0) {
        fprintf(stderr, "Error sending the frame to the encoder\n");
        exit(1);
    }
 
    /* read all the available output packets (in general there may be any
     * number of them */
    while (ret >= 0) {
        ret = avcodec_receive_packet(ctx, pkt);
        if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
            return;
        else if (ret < 0) {
            fprintf(stderr, "Error encoding audio frame\n");
            exit(1);
        }
 
        fwrite(pkt->data, 1, pkt->size, output);
        av_packet_unref(pkt);
    }
}
 
int main(int argc, char **argv)
{
    // 对应文件的编码数据
    const char *filename;

    // 编码器
    const AVCodec *codec;

    // 编码器上下文
    AVCodecContext *c= NULL;

    // 保存未曾解码的数据
    AVFrame *frame;
    // 对应的保存数据
    AVPacket *pkt;
    int i, j, k, ret;
    FILE *f;
    uint16_t *samples;
    float t, tincr;
 
    if (argc <= 1) {
        fprintf(stderr, "Usage: %s <output file>\n", argv[0]);
        return 0;
    }
    // 获得输出文件
    filename = argv[1];
 
    // 找到对应的编码器
    codec = avcodec_find_encoder(AV_CODEC_ID_MP2);
    if (!codec) {
        fprintf(stderr, "Codec not found\n");
        exit(1);
    }
    // 使用默认值设置编码器的内容数据
    c = avcodec_alloc_context3(codec);
    if (!c) {
        fprintf(stderr, "Could not allocate audio codec context\n");
        exit(1);
    }
 
    // 设置编码器的相关信息
    // 设置编码器的比特率
    c->bit_rate = 64000;
 
    // /采样的数据类型
    c->sample_fmt = AV_SAMPLE_FMT_S16;
    if (!check_sample_fmt(codec, c->sample_fmt)) {
        fprintf(stderr, "Encoder does not support sample format %s",
                av_get_sample_fmt_name(c->sample_fmt));
        exit(1);
    }
 
    // 对应的采样频率
    c->sample_rate    = select_sample_rate(codec);
    // 设置对应布局
    ret = select_channel_layout(codec, &c->ch_layout);
    if (ret < 0)
        exit(1);
 
    // 打开对应的编码器
    if (avcodec_open2(c, codec, NULL) < 0) {
        fprintf(stderr, "Could not open codec\n");
        exit(1);
    }
 
    f = fopen(filename, "wb");
    if (!f) {
        fprintf(stderr, "Could not open %s\n", filename);
        exit(1);
    }
 
    /* packet for holding encoded output */
    pkt = av_packet_alloc();
    if (!pkt) {
        fprintf(stderr, "could not allocate the packet\n");
        exit(1);
    }
 
    /* frame containing input raw audio */
    frame = av_frame_alloc();
    if (!frame) {
        fprintf(stderr, "Could not allocate audio frame\n");
        exit(1);
    }
    // 设置单通道数据采样大小
    frame->nb_samples     = c->frame_size;
    // 数据采样的大小
    frame->format         = c->sample_fmt;
    // 设置对用的通道大小
    ret = av_channel_layout_copy(&frame->ch_layout, &c->ch_layout);
    if (ret < 0)
        exit(1);
 
    /* 设置对应数据的缓冲区 */
    ret = av_frame_get_buffer(frame, 0);
    if (ret < 0) {
        fprintf(stderr, "Could not allocate audio data buffers\n");
        exit(1);
    }
 
    /* encode a single tone sound */
    t = 0;
    tincr = 2 * M_PI * 440.0 / c->sample_rate;
    for (i = 0; i < 200; i++) {
        /* make sure the frame is writable -- makes a copy if the encoder
         * kept a reference internally */
        ret = av_frame_make_writable(frame);
        if (ret < 0)
            exit(1);
        samples = (uint16_t*)frame->data[0];
 
        for (j = 0; j < c->frame_size; j++) {
            samples[2*j] = (int)(sin(t) * 10000);
 
            for (k = 1; k < c->ch_layout.nb_channels; k++)
                samples[2*j + k] = samples[2*j];
            t += tincr;
        }
        encode(c, frame, pkt, f);
    }
 
    /* flush the encoder */
    encode(c, NULL, pkt, f);
 
    fclose(f);
 
    av_frame_free(&frame);
    av_packet_free(&pkt);
    avcodec_free_context(&c);
 
    return 0;
}