FFmpeg源码分析:音频采样格式相关API

FFmpeg针对音频采样格式的获取与处理,封装有专门工具类。音频采样格式枚举类型与相关API,位于libavutil模块的samplefmt.h,包括获取采样格式名字、获取采样格式类型、获取每个采样所占字节、获取采样数所需缓冲区大小、填充采样数组、分配采样缓冲区、拷贝采样数据、填充采样数据为静音。

1、AVSampleFormat

AVSampleFormat是音频采样格式的枚举类型,按照符号类型分为有符号与无符号,按照存储位数分为8位、16位、32位、64位,按照数值类型分为int、short、float、double,按照存储结构分为packed和planar。具体如下:

enum AVSampleFormat {
    AV_SAMPLE_FMT_NONE = -1,
    AV_SAMPLE_FMT_U8,          ///< unsigned 8 bits
    AV_SAMPLE_FMT_S16,         ///< signed 16 bits
    AV_SAMPLE_FMT_S32,         ///< signed 32 bits
    AV_SAMPLE_FMT_FLT,         ///< float
    AV_SAMPLE_FMT_DBL,         ///< double

    AV_SAMPLE_FMT_U8P,         ///< unsigned 8 bits, planar
    AV_SAMPLE_FMT_S16P,        ///< signed 16 bits, planar
    AV_SAMPLE_FMT_S32P,        ///< signed 32 bits, planar
    AV_SAMPLE_FMT_FLTP,        ///< float, planar
    AV_SAMPLE_FMT_DBLP,        ///< double, planar
    AV_SAMPLE_FMT_S64,         ///< signed 64 bits
    AV_SAMPLE_FMT_S64P,        ///< signed 64 bits, planar

    AV_SAMPLE_FMT_NB           ///< Number of sample formats. DO NOT USE if linking dynamically
};

2、av_get_sample_fmt_name

获取采样格式名字,返回对应AVSampleFormat枚举的name。在samplefmt.c有对应的SampleFmtInfo,包括name、bits、planar、altform等字段:

static const SampleFmtInfo sample_fmt_info[AV_SAMPLE_FMT_NB] = {
    [AV_SAMPLE_FMT_U8]   = { .name =   "u8", .bits =  8, .planar = 0, .altform = AV_SAMPLE_FMT_U8P  },
    [AV_SAMPLE_FMT_S16]  = { .name =  "s16", .bits = 16, .planar = 0, .altform = AV_SAMPLE_FMT_S16P },
    [AV_SAMPLE_FMT_S32]  = { .name =  "s32", .bits = 32, .planar = 0, .altform = AV_SAMPLE_FMT_S32P },
    [AV_SAMPLE_FMT_S64]  = { .name =  "s64", .bits = 64, .planar = 0, .altform = AV_SAMPLE_FMT_S64P },
    [AV_SAMPLE_FMT_FLT]  = { .name =  "flt", .bits = 32, .planar = 0, .altform = AV_SAMPLE_FMT_FLTP },
    [AV_SAMPLE_FMT_DBL]  = { .name =  "dbl", .bits = 64, .planar = 0, .altform = AV_SAMPLE_FMT_DBLP },
    [AV_SAMPLE_FMT_U8P]  = { .name =  "u8p", .bits =  8, .planar = 1, .altform = AV_SAMPLE_FMT_U8   },
    [AV_SAMPLE_FMT_S16P] = { .name = "s16p", .bits = 16, .planar = 1, .altform = AV_SAMPLE_FMT_S16  },
    [AV_SAMPLE_FMT_S32P] = { .name = "s32p", .bits = 32, .planar = 1, .altform = AV_SAMPLE_FMT_S32  },
    [AV_SAMPLE_FMT_S64P] = { .name = "s64p", .bits = 64, .planar = 1, .altform = AV_SAMPLE_FMT_S64  },
    [AV_SAMPLE_FMT_FLTP] = { .name = "fltp", .bits = 32, .planar = 1, .altform = AV_SAMPLE_FMT_FLT  },
    [AV_SAMPLE_FMT_DBLP] = { .name = "dblp", .bits = 64, .planar = 1, .altform = AV_SAMPLE_FMT_DBL  },
};

3、av_get_sample_fmt

获取采样格式类型,返回对应AVSampleFormat枚举的类型。

4、av_get_alt_sample_fmt

返回planar或packed可选的采样格式类型,如果出错则返回AV_SAMPLE_FMT_NONE。

5、av_get_packed_sample_fmt

获取交错存储的采样格式,返回AVSampleFormat枚举的类型。

6、av_get_planar_sample_fmt

获取平面存储的采样格式,返回AVSampleFormat枚举的类型。

7、av_get_bytes_per_sample

根据采样格式,获取每个采样所占的字节数。

8、av_sample_fmt_is_planar

判断采样格式是否为平面存储。

9、av_samples_get_buffer_size

获取采样数所需要的缓冲区大小,代码实现位于samplefmt.c,具体如下:

int av_samples_get_buffer_size(int *linesize, int nb_channels, int nb_samples,
                               enum AVSampleFormat sample_fmt, int align)
{
    int line_size;
    int sample_size = av_get_bytes_per_sample(sample_fmt);
    int planar      = av_sample_fmt_is_planar(sample_fmt);

    // 检查参数是否合法
    if (!sample_size || nb_samples <= 0 || nb_channels <= 0)
        return AVERROR(EINVAL);

    // 如果没有指定,自动选择是否对齐
    if (!align) {
        if (nb_samples > INT_MAX - 31)
            return AVERROR(EINVAL);
        align = 1;
        nb_samples = FFALIGN(nb_samples, 32);
    }

    // 检查integer是否溢出
    if (nb_channels > INT_MAX / align ||
        (int64_t)nb_channels * nb_samples > (INT_MAX - (align * nb_channels)) / sample_size)
        return AVERROR(EINVAL);

    line_size = planar ? FFALIGN(nb_samples * sample_size,               align) :
                         FFALIGN(nb_samples * sample_size * nb_channels, align);
    if (linesize)
        *linesize = line_size;

    return planar ? line_size * nb_channels : line_size;
}

10、av_samples_fill_arrays

根据采样数填充数组,对于planar平面存储,每个声道的缓冲区设置指针头;对于packed交错存储,整个缓冲区只设置一个指针头:

/**
 * Fill plane data pointers and linesize for samples with sample
 * format sample_fmt.
 *
 * The audio_data array is filled with the pointers to the samples data planes:
 * for planar, set the start point of each channel's data within the buffer,
 * for packed, set the start point of the entire buffer only.
 *
 * The value pointed to by linesize is set to the aligned size of each
 * channel's data buffer for planar layout, or to the aligned size of the
 * buffer for all channels for packed layout.
 *
 * The buffer in buf must be big enough to contain all the samples
 * (use av_samples_get_buffer_size() to compute its minimum size),
 * otherwise the audio_data pointers will point to invalid data.
 *
 * @see enum AVSampleFormat
 * The documentation for AVSampleFormat describes the data layout.
 *
 * @param[out] audio_data  array to be filled with the pointer for each channel
 * @param[out] linesize    calculated linesize, may be NULL
 * @param buf              the pointer to a buffer containing the samples
 * @param nb_channels      the number of channels
 * @param nb_samples       the number of samples in a single channel
 * @param sample_fmt       the sample format
 * @param align            buffer size alignment (0 = default, 1 = no alignment)
 * @return                 >=0 on success or a negative error code on failure
 * @todo return minimum size in bytes required for the buffer in case
 * of success at the next bump
 */
int av_samples_fill_arrays(uint8_t **audio_data, int *linesize,
                           const uint8_t *buf,
                           int nb_channels, int nb_samples,
                           enum AVSampleFormat sample_fmt, int align);

11、av_samples_alloc

为指定nb_samples的采样数分配采样缓冲区。

12、av_samples_copy

把采样数据从源地址拷贝到目的地址。

13、av_samples_set_silence

把采样数据填充为静音,如果是AV_SAMPLE_FMT_U8或AV_SAMPLE_FMT_U8P类型,就填充0x80,否则统一填充0x00。代码如下:

int av_samples_set_silence(uint8_t **audio_data, int offset, int nb_samples,
                           int nb_channels, enum AVSampleFormat sample_fmt)
{
    int planar      = av_sample_fmt_is_planar(sample_fmt);
    int planes      = planar ? nb_channels : 1;
    int block_align = av_get_bytes_per_sample(sample_fmt) * (planar ? 1 : nb_channels);
    int data_size   = nb_samples * block_align;
    int fill_char   = (sample_fmt == AV_SAMPLE_FMT_U8 ||
                     sample_fmt == AV_SAMPLE_FMT_U8P) ? 0x80 : 0x00;
    int i;

    offset *= block_align;

    for (i = 0; i < planes; i++)
        memset(audio_data[i] + offset, fill_char, data_size);

    return 0;
}

猜你喜欢

转载自blog.csdn.net/u011686167/article/details/121917453