ffmpeg_sample解读_resampling_audio

---

title: ffmpeg_sample解读_resampling_audio
date: 2020-10-28 10:15:02
tags: [读书笔记]
typora-copy-images-to: ./imgs
typora-root-url: ./imgs

---

总结

* 音频重采样,创建一系列音频帧,然后进行重采样,设定格式和频率.保存到另一个文件中
* 也就是改变一段音频的相关参数,采样率,采样通道,采样格式等

流程图

graph TB
sa[swr_alloc]
-->aosi[av_opt_set_int]
-->aossf[av_opt_set_sample_fmt]
-->si[swr_init]
-->agclnc[av_get_channel_layout_nb_channels]
-->asaaas[av_samples_alloc_array_and_samples]
-->fs[fill_samples]
-->arr[av_rescale_rnd]
-->sc[swr_convert]
-->asgbs[av_samples_get_buffer_size]
-->fwrite[fwrite]
-->release[release]

image-20201113151823237

代码

/**
 * @example resampling_audio.c
 * libswresample API use example.
 */

#include <libavutil/opt.h>
#include <libavutil/channel_layout.h>
#include <libavutil/samplefmt.h>
#include <libswresample/swresample.h>
/**
 * 这里是一个格式转换
 * @param fmt
 * @param sample_fmt
 * @return
 */
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 not supported as output format\n",
            av_get_sample_fmt_name(sample_fmt));
    return AVERROR(EINVAL);
}

/**
 * Fill dst buffer with nb_samples, generated starting from t.
 * 随机产生音频的数据
 */
static void fill_samples(double *dst, int nb_samples, int nb_channels, int sample_rate, double *t)
{
    int i, j;
    double tincr = 1.0 / sample_rate, *dstp = dst;
    const double c = 2 * M_PI * 440.0;

    //产生双声道 440hz的数据  nb _samples 应该就是采样数  channels 是2
    /* generate sin tone with 440Hz frequency and duplicated channels */
    for (i = 0; i < nb_samples; i++) {
        *dstp = sin(c * *t);
        for (j = 1; j < nb_channels; j++)
            dstp[j] = dstp[0];
        dstp += nb_channels;
        *t += tincr;
    }
}

/**
 * 音频重采样,创建一系列音频帧,然后进行重采样,设定格式和频率.保存到另一个文件中
 * 也就是改变一段音频的相关参数,采样率,采样通道,采样格式等
 * @param argc
 * @param argv
 * @return
 */
int resampling_audio_main(int argc, char **argv)
{
                            //立体声                           //布局环绕声
    int64_t src_ch_layout = AV_CH_LAYOUT_STEREO, dst_ch_layout = AV_CH_LAYOUT_SURROUND;
    int src_rate = 48000, dst_rate = 44100; //输入输出的采样率
    uint8_t **src_data = NULL, **dst_data = NULL;
    int src_nb_channels = 0, dst_nb_channels = 0;
    int src_linesize, dst_linesize;
    int src_nb_samples = 1024, dst_nb_samples, max_dst_nb_samples;
                        //采样格式      双精度                     16位
    enum AVSampleFormat src_sample_fmt = AV_SAMPLE_FMT_DBL, dst_sample_fmt = AV_SAMPLE_FMT_S16;
    const char *dst_filename = NULL;
    FILE *dst_file;
    int dst_bufsize;
    const char *fmt;
    struct SwrContext *swr_ctx;
    double t;
    int ret;

    if (argc != 2) {
        fprintf(stderr, "Usage: %s output_file\n"
                "API example program to show how to resample an audio stream with libswresample.\n"
                "This program generates a series of audio frames, resamples them to a specified "
                "output format and rate and saves them to an output file named output_file.\n",
            argv[0]);
        exit(1);
    }
    dst_filename = argv[1];
//打开输入文件.写出模式
    dst_file = fopen(dst_filename, "wb");
    if (!dst_file) {
        fprintf(stderr, "Could not open destination file %s\n", dst_filename);
        exit(1);
    }

    /* create resampler context */
    //重采样上下文分配空间 重采样就是用来进行音频转换的
    swr_ctx = swr_alloc();
    if (!swr_ctx) {
        fprintf(stderr, "Could not allocate resampler context\n");
        ret = AVERROR(ENOMEM);
        goto end;
    }

    /* set options */ //创建输入和输入音频的参数
    av_opt_set_int(swr_ctx, "in_channel_layout",    src_ch_layout, 0);
    av_opt_set_int(swr_ctx, "in_sample_rate",       src_rate, 0);
    av_opt_set_sample_fmt(swr_ctx, "in_sample_fmt", src_sample_fmt, 0);

    av_opt_set_int(swr_ctx, "out_channel_layout",    dst_ch_layout, 0);
    av_opt_set_int(swr_ctx, "out_sample_rate",       dst_rate, 0);
    av_opt_set_sample_fmt(swr_ctx, "out_sample_fmt", dst_sample_fmt, 0);

    /* initialize the resampling context */
    //初始化重采样
    if ((ret = swr_init(swr_ctx)) < 0) {
        fprintf(stderr, "Failed to initialize the resampling context\n");
        goto end;
    }

    /* allocate source and destination samples buffers */
//  源通道布局的 通道数
    src_nb_channels = av_get_channel_layout_nb_channels(src_ch_layout);
    //利用 通道数,采样格式,采样数.分配数据指针数组,和数据长度
    ret = av_samples_alloc_array_and_samples(&src_data, &src_linesize, src_nb_channels,
                                             src_nb_samples, src_sample_fmt, 0);
    if (ret < 0) {
        fprintf(stderr, "Could not allocate source samples\n");
        goto end;
    }

    /* compute the number of converted samples: buffering is avoided
     * ensuring that the output buffer will contain at least all the
     * converted input samples */
    max_dst_nb_samples = dst_nb_samples =
            //a * bq / cq  计算转换后的样本数,也就是输出文件的样本数
        av_rescale_rnd(src_nb_samples, dst_rate, src_rate, AV_ROUND_UP);

    /* buffer is going to be directly written to a rawaudio file, no alignment */
    //目标布局的通道数
    dst_nb_channels = av_get_channel_layout_nb_channels(dst_ch_layout);
    //为目标数据(dst_data)分配指针数组,和上边的源类似
    ret = av_samples_alloc_array_and_samples(&dst_data, &dst_linesize, dst_nb_channels,
                                             dst_nb_samples, dst_sample_fmt, 0);
    if (ret < 0) {
        fprintf(stderr, "Could not allocate destination samples\n");
        goto end;
    }

    t = 0;
    do {// 这里根据t来处理循环. t又累加1/采样率 因此这里是转换10s的数据
        /* generate synthetic audio */
        //随机产生音频数据,天到 src_dat[0]的数组中,src_data 这是一个二维数组
        fill_samples((double *)src_data[0], src_nb_samples, src_nb_channels, src_rate, &t);

        /* compute destination number of samples */
        //a * b / c   计算目标采样数,同时加入了输入样板到输入样本间的延迟,得到输出的采样数目
        dst_nb_samples = av_rescale_rnd(swr_get_delay(swr_ctx, src_rate) +
                                        src_nb_samples, dst_rate, src_rate, AV_ROUND_UP);
        if (dst_nb_samples > max_dst_nb_samples) {
            //计算的样本数有误,需要重新获取数据指针
            av_freep(&dst_data[0]);
            //重新分配输出数据的指针数组,这里更新了 dst_linesize 的数据
            ret = av_samples_alloc(dst_data, &dst_linesize, dst_nb_channels,
                                   dst_nb_samples, dst_sample_fmt, 1);
            if (ret < 0)
                break;
            max_dst_nb_samples = dst_nb_samples;
        }

        /* convert to destination format */
        //把原始数据转换为输出数据,根据样本数目来转换
        ret = swr_convert(swr_ctx, dst_data, dst_nb_samples, (const uint8_t **)src_data, src_nb_samples);
        if (ret < 0) {
            fprintf(stderr, "Error while converting\n");
            goto end;
        }
        //根据格式获取指定大小,也就是dst_buffer 实际写入的数据
        dst_bufsize = av_samples_get_buffer_size(&dst_linesize, dst_nb_channels,
                                                 ret, dst_sample_fmt, 1);
        if (dst_bufsize < 0) {
            fprintf(stderr, "Could not get sample buffer size\n");
            goto end;
        }
        printf("t:%f in:%d out:%d\n", t, src_nb_samples, ret);
        //把数据写到输出文件中
        fwrite(dst_data[0], 1, dst_bufsize, dst_file);
    } while (t < 10);
    //获取输出文件的格式
    if ((ret = get_format_from_sample_fmt(&fmt, dst_sample_fmt)) < 0)
        goto end;
    fprintf(stderr, "Resampling succeeded. Play the output file with the command:\n"
            "ffplay -f %s -channel_layout %"PRId64" -channels %d -ar %d %s\n",
            fmt, dst_ch_layout, dst_nb_channels, dst_rate, dst_filename);

end:
    fclose(dst_file);

    if (src_data)
        av_freep(&src_data[0]);
    av_freep(&src_data);

    if (dst_data)
        av_freep(&dst_data[0]);
    av_freep(&dst_data);

    swr_free(&swr_ctx);
    return ret < 0;
}