ADOFAIRenderer/Util/Audio/Clip/PCMResampler.cs

using System;
using FFmpeg.AutoGen;

namespace ADOFAIRenderer.Util.Audio.Clip;

/// <summary>
/// Sample rate converter for interleaved 32-bit float PCM (libswresample).
/// Input and output have the same channel count; only the sample rate changes.
/// One instance keeps filter state between calls, so consecutive <see cref="Convert"/> calls form one continuous stream.
/// Reference: https://ffmpeg.org/doxygen/trunk/group__lswr.html
/// </summary>
internal sealed unsafe class PCMResampler : IDisposable
{
    /// <summary>Resampler context owned by this instance; null after <see cref="Dispose"/>.</summary>
    private SwrContext* _swr;

    /// <summary>True after <see cref="Flush"/> until <see cref="Reset"/>.</summary>
    private bool _flushed;

    /// <summary>Channel count of input and output (interleaved).</summary>
    public int Channels { get; }

    /// <summary>Input sample rate in Hz.</summary>
    public int InputRate { get; }

    /// <summary>Output sample rate in Hz.</summary>
    public int OutputRate { get; }

    /// <summary>Value of the SwrContext "filter_size" option (filter length per phase in taps at a 1:1 ratio).</summary>
    public int FilterSize { get; }

    /// <summary>Creates and initializes a float-to-float resampler with the default channel layout for <paramref name="channels"/>.</summary>
    /// <exception cref="ArgumentOutOfRangeException">A count or rate is not positive.</exception>
    /// <exception cref="InvalidOperationException">libswresample cannot allocate or initialize the context.</exception>
    public PCMResampler(int channels, int inputRate, int outputRate)
    {
        if (channels <= 0) throw new ArgumentOutOfRangeException(nameof(channels));
        if (inputRate <= 0) throw new ArgumentOutOfRangeException(nameof(inputRate));
        if (outputRate <= 0) throw new ArgumentOutOfRangeException(nameof(outputRate));

        Channels = channels;
        InputRate = inputRate;
        OutputRate = outputRate;

        AVChannelLayout layout;
        ffmpeg.av_channel_layout_default(&layout, channels);

        SwrContext* swr = null;
        var ret = ffmpeg.swr_alloc_set_opts2(
            &swr,
            &layout, AVSampleFormat.AV_SAMPLE_FMT_FLT, outputRate,
            &layout, AVSampleFormat.AV_SAMPLE_FMT_FLT, inputRate,
            0, null);
        ffmpeg.av_channel_layout_uninit(&layout);
        if (ret < 0 || swr == null)
            throw new InvalidOperationException($"swr_alloc_set_opts2 failed ({ret}).");
        _swr = swr;

        // Falls back to 32, the libswresample default of "filter_size", when the option cannot be read.
        // Reference: https://github.com/FFmpeg/FFmpeg/blob/master/libswresample/options.c (filter_size)
        long filterSize;
        FilterSize = ffmpeg.av_opt_get_int(_swr, "filter_size", 0, &filterSize) >= 0 ? (int)filterSize : 32;

        Reset();
    }

    /// <summary>Discards all buffered input and filter history. The next call starts a new stream.</summary>
    public void Reset()
    {
        // swr_init on an initialized context re-initializes it.
        // Reference: https://ffmpeg.org/doxygen/trunk/group__lswr.html (swr_init, swr_close)
        var ret = ffmpeg.swr_init(_swr);
        if (ret < 0)
            throw new InvalidOperationException($"swr_init failed ({ret}).");
        _flushed = false;
    }

    /// <summary>
    /// Feeds <paramref name="inputFrames"/> frames and writes up to <paramref name="outputCapacity"/> frames.
    /// Input that does not fit in the output is buffered inside the context and returned by later calls.
    /// <paramref name="inputFrames"/> may be 0 to take only buffered output.
    /// </summary>
    /// <returns>Frames written to <paramref name="output"/>.</returns>
    public int Convert(float* input, int inputFrames, float* output, int outputCapacity)
    {
        if (_flushed) throw new InvalidOperationException("Resampler was flushed. Call Reset first.");

        // swr_convert treats a null input array as a flush request, so a non-null pointer is passed even for 0 frames.
        float dummy = 0;
        var inPlane = (byte*)(input != null ? input : &dummy);
        var outPlane = (byte*)output;
        var ret = ffmpeg.swr_convert(_swr, &outPlane, outputCapacity, &inPlane, inputFrames);
        if (ret < 0)
            throw new InvalidOperationException($"swr_convert failed ({ret}).");
        return ret;
    }

    /// <summary>
    /// Ends the input stream and writes up to <paramref name="outputCapacity"/> remaining frames.
    /// Call repeatedly until it returns 0. <see cref="Convert"/> is not allowed afterwards until <see cref="Reset"/>.
    /// </summary>
    public int Flush(float* output, int outputCapacity)
    {
        _flushed = true;
        var outPlane = (byte*)output;
        var ret = ffmpeg.swr_convert(_swr, &outPlane, outputCapacity, null, 0);
        if (ret < 0)
            throw new InvalidOperationException($"swr_convert (flush) failed ({ret}).");
        return ret;
    }

    /// <summary>Frees the context. Safe to call more than once.</summary>
    public void Dispose()
    {
        if (_swr == null) return;
        var swr = _swr;
        ffmpeg.swr_free(&swr);
        _swr = null;
    }
}