using MeetingAssistant.Recording;
using MeetingAssistant.Transcription;
using NAudio.Wave;

namespace MeetingAssistant.Tests;

public sealed class SpeakerAudioSampleCollectorTests
{
    [Fact]
    public void CollectorWaitsForConfiguredUninterruptedSpeechDuration()
    {
        var collector = new SpeakerAudioSampleCollector(
            TimeSpan.FromMinutes(2),
            maxSamplesPerSpeaker: 3,
            minimumUninterruptedSpeechDuration: TimeSpan.FromSeconds(30),
            maximumSegmentGap: TimeSpan.FromSeconds(1));
        collector.AppendAudio(CreateAudio(TimeSpan.FromSeconds(35)));

        collector.TryAdd(Segment(0, 12, "Guest01", "one two three four five."));
        collector.TryAdd(Segment(12, 24, "Guest01", "six seven eight nine ten."));

        Assert.Empty(collector.Snapshot());

        collector.TryAdd(Segment(24, 31, "Guest01", "eleven twelve thirteen fourteen fifteen."));

        var sample = Assert.Single(collector.Snapshot());
        Assert.Equal("Guest01", sample.Speaker);
        Assert.Equal(TimeSpan.Zero, sample.Segment.Start);
        Assert.Equal(TimeSpan.FromSeconds(31), sample.Segment.End);
        Assert.True(ReadDuration(sample.WavBytes) >= TimeSpan.FromSeconds(30));
    }

    [Fact]
    public void CollectorDoesNotCombineSpeechAcrossDifferentSpeakerInterruption()
    {
        var collector = new SpeakerAudioSampleCollector(
            TimeSpan.FromMinutes(2),
            maxSamplesPerSpeaker: 3,
            minimumUninterruptedSpeechDuration: TimeSpan.FromSeconds(30),
            maximumSegmentGap: TimeSpan.FromSeconds(1));
        collector.AppendAudio(CreateAudio(TimeSpan.FromSeconds(50)));

        collector.TryAdd(Segment(0, 20, "Guest01", "one two three four five."));
        collector.TryAdd(Segment(20, 22, "Guest02", "interrupting now."));
        collector.TryAdd(Segment(22, 35, "Guest01", "six seven eight nine ten."));

        Assert.DoesNotContain(collector.Snapshot(), sample => sample.Speaker == "Guest01");
    }

    private static TranscriptionSegment Segment(
        double start,
        double end,
        string speaker,
        string text)
    {
        return new TranscriptionSegment(
            TimeSpan.FromSeconds(start),
            TimeSpan.FromSeconds(end),
            speaker,
            text);
    }

    private static AudioChunk CreateAudio(TimeSpan duration)
    {
        const int sampleRate = 16000;
        const int channels = 1;
        var bytes = new byte[(int)(duration.TotalSeconds * sampleRate * channels * sizeof(short))];
        return new AudioChunk(bytes, sampleRate, channels);
    }

    private static TimeSpan ReadDuration(byte[] wavBytes)
    {
        using var reader = new WaveFileReader(new MemoryStream(wavBytes));
        return reader.TotalTime;
    }
}