FFMPEG演示教程——ResamplingAudio

概述

本示例基于ffmpeg的resampling_audio.c示例，增加了Plane模式的支持以及将程序接口化。Plane格式的介绍可以参照博文：音频格式解析：交错模式 vs Plane模式。

基于下文中代码，可实现AV_SAMPLE_FMT_S16转AV_SAMPLE_FMT_S16P，当然稍作修改，也可实现AV_SAMPLE_FMT_S16转AV_SAMPLE_FMT_FLTP。

非Plane模式转码后的数据保存在程序当前路径下的channel_all.pcm文件中，Plane模式则将每个通道单独保存：channel_x.pcm。

代码

#include <libavutil/opt.h>
#include <libavutil/channel_layout.h>
#include <libavutil/samplefmt.h>
#include <libswresample/swresample.h>

#define DEBUG_ON 1

typedef struct _convertParam {
    int64_t src_ch_layout;
    int src_rate;
    enum AVSampleFormat src_sample_fmt;

    int64_t dst_ch_layout;
    int dst_rate;
    enum AVSampleFormat dst_sample_fmt;

    struct SwrContext *swr_ctx;
} ConvertParam;

int audio_convert_init(ConvertParam *param);
void audio_convert_deinit(ConvertParam *param);
int audio_convert_process(ConvertParam *param,
    int src_nb_samples, uint8_t **src_data,
    int *result_nb_samples, uint8_t ***result_data);


/**
 * Fill dst buffer with nb_samples, generated starting from t.
 */
static void fill_samples_S16(int16_t *dst, int nb_samples, int nb_channels, int sample_rate, double *t)
{
    int i, j;
    double tincr = 1.0 / sample_rate;
    int16_t *dstp = dst;
    const double c = 2 * M_PI * 440.0;

    /* generate sin tone with 440Hz frequency and duplicated channels */
    for (i = 0; i < nb_samples; i++) {
        *dstp = (int16_t)(sin(c * *t) * 10000);
        for (j = 1; j < nb_channels; j++)
            dstp[j] = dstp[0];
        dstp += nb_channels;
        *t += tincr;
    }
}

//double
static void fill_samples_DBL(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;

    /* 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;
    }
}

static int check_param(ConvertParam *param)
{
    if (!param)
        return -1;

    if (!param->src_ch_layout ||
        !param->src_rate ||
        (param->src_sample_fmt == AV_SAMPLE_FMT_NONE) ||
        (param->src_sample_fmt == AV_SAMPLE_FMT_NB))
        return -1;

    if (!param->dst_ch_layout ||
        !param->dst_rate ||
        (param->dst_sample_fmt == AV_SAMPLE_FMT_NONE) ||
        (param->dst_sample_fmt == AV_SAMPLE_FMT_NB))
        return -1;

    return 0;
}

int audio_convert_init(ConvertParam *param)
{
    int64_t src_ch_layout, dst_ch_layout;
    int src_rate, dst_rate;
    enum AVSampleFormat src_sample_fmt, dst_sample_fmt;
    struct SwrContext *swr_ctx;
    int ret = 0;

    if (check_param(param) < 0) {
        printf("ERROR: Invalid param!\n");
        return -1;
    }

    src_ch_layout = param->src_ch_layout;
    dst_ch_layout = param->dst_ch_layout;
    src_rate = param->src_rate;
    dst_rate = param->dst_rate;
    src_sample_fmt = param->src_sample_fmt;
    dst_sample_fmt = param->dst_sample_fmt;

    /* create resampler context */
    swr_ctx = swr_alloc();
    if (!swr_ctx) {
        fprintf(stderr, "Could not allocate resampler context\n");
        return -1;
    }

    /* set options */
    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 */
    if ((ret = swr_init(swr_ctx)) < 0) {
        fprintf(stderr, "Failed to initialize the resampling context\n");
        swr_free(&swr_ctx);
        return -1;
    }

    param->swr_ctx = swr_ctx;
    return 0;
}

void audio_convert_deinit(ConvertParam *param)
{
    if (param->swr_ctx) {
        swr_free(&param->swr_ctx);
        param->swr_ctx = NULL;
    }
}

int audio_convert_process(ConvertParam *param,
    int src_nb_samples, uint8_t **src_data,
    int *result_nb_samples, uint8_t ***result_data)
{
    int dst_linesize, dst_nb_channels;
    int dst_nb_samples, max_dst_nb_samples;
    int ret;
    int src_rate, dst_rate;
    enum AVSampleFormat dst_sample_fmt;
    int64_t dst_ch_layout;
    struct SwrContext *swr_ctx;
    uint8_t **dst_data;
    int dst_bufsize = 0;

    if (!param->swr_ctx) {
        printf("ERROR: audio convert not be inited.\n");
        return -1;
    }

    swr_ctx = param->swr_ctx;
    dst_sample_fmt = param->dst_sample_fmt;
    dst_ch_layout = param->dst_ch_layout;
    src_rate = param->src_rate;
    dst_rate = param->dst_rate;

    /* 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 =
        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 */
    dst_nb_channels = av_get_channel_layout_nb_channels(dst_ch_layout);
    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");
        return -1;
    }

    /* compute destination number of samples */
    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) {
        av_freep(&dst_data[0]);
        ret = av_samples_alloc(dst_data, &dst_linesize, dst_nb_channels,
                               dst_nb_samples, dst_sample_fmt, 1);
        if (ret < 0) {
            fprintf(stderr, "Could not reallocate destination samples\n");
            return -1;
        }
        max_dst_nb_samples = dst_nb_samples;
    }

    /* convert to destination format */
    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");
        av_freep(&dst_data[0]);
        return -1;
    }

    dst_bufsize = av_samples_get_buffer_size(&dst_linesize, dst_nb_channels,
                                                 ret, dst_sample_fmt, 1);
    if (dst_bufsize < 0)
        printf("WARNING: Could not get sample buffer size\n");

    *result_nb_samples = dst_nb_samples;
    *result_data = dst_data;
    return dst_bufsize;
}

int main(int argc, char **argv)
{
    int ret = 0;
    ConvertParam param;
    int src_nb_samples = 1024;
    int dst_nb_samples = 0;
    int src_nb_channels;
    int dst_nb_channels;
    uint8_t **src_data = NULL;
    uint8_t **dst_data = NULL;
    double t = 0;
    int i = 0;
#if DEBUG_ON
    FILE *debug_file[8] = {NULL};
#endif

    memset(&param, 0, sizeof(param));
    param.src_ch_layout = AV_CH_LAYOUT_STEREO;
    param.src_rate = 48000;
    param.src_sample_fmt = AV_SAMPLE_FMT_S16;

    param.dst_ch_layout = AV_CH_LAYOUT_STEREO;
    param.dst_rate = 48000;
    param.dst_sample_fmt = AV_SAMPLE_FMT_S16P;

#if DEBUG_ON
    dst_nb_channels = av_get_channel_layout_nb_channels(param.dst_sample_fmt);

    if ((param.dst_sample_fmt >= AV_SAMPLE_FMT_U8P) &&
        (param.dst_sample_fmt <= AV_SAMPLE_FMT_S64P) &&
        dst_nb_channels > 1) {
        for (i = 0; i < dst_nb_channels; i++) {
            char f_name[64] = {0};
            sprintf(f_name, "channel_%d.pcm", i);
            debug_file[i] = fopen(f_name, "wb");
            if (!debug_file[i])
                printf("WARNING: Could not open debug file %s\n", f_name);
        }
    } else {
        debug_file[0] = fopen("channel_all.pcm", "wb");
        if (!debug_file[0])
            printf("WARNING: Could not open debug file channel_all.pcm\n");
    }
#endif

    ret = audio_convert_init(&param);
    if (ret < 0)
        return -1;

    src_nb_channels = av_get_channel_layout_nb_channels(param.src_ch_layout);
    ret = av_samples_alloc_array_and_samples(&src_data, NULL, src_nb_channels,
                                             src_nb_samples, param.src_sample_fmt, 0);
    if (ret < 0) {
        fprintf(stderr, "Could not allocate source samples\n");
        return -1;
    }

    do {
        fill_samples_S16((int16_t *)src_data[0], src_nb_samples, src_nb_channels, param.src_rate, &t);
        ret = audio_convert_process(&param, src_nb_samples, src_data, &dst_nb_samples, &dst_data);
        if (ret < 0)
            break;

        printf("### FLC-DBG: convert %d frames to %d frames\n", src_nb_samples, dst_nb_samples);

#if DEBUG_ON
        if ((param.dst_sample_fmt >= AV_SAMPLE_FMT_U8P) &&
            (param.dst_sample_fmt <= AV_SAMPLE_FMT_S64P)) {
            for (i = 0; i < dst_nb_channels; i++) {
                if (debug_file[i])
                    fwrite(dst_data[i], 1, ret / dst_nb_channels, debug_file[i]);
            }
        } else if (debug_file[0])
            fwrite(dst_data[0], 1, ret, debug_file[0]);
#endif

        av_freep(&dst_data);
    } while(t < 10);

    av_freep(&src_data);
    audio_convert_deinit(&param);

    return 0;
}