meeting-assistant/MeetingAssistant.Tests/SpeechRecognitionPipelineHostedServiceTests.cs

using MeetingAssistant;
using MeetingAssistant.LaunchProfiles;
using MeetingAssistant.Transcription;
using Microsoft.Extensions.Logging.Abstractions;

namespace MeetingAssistant.Tests;

public sealed class SpeechRecognitionPipelineHostedServiceTests
{
    [Fact]
    public async Task HostedServiceInitializesAndWarmsConfiguredPipelineWithoutBlockingStartup()
    {
        var pipeline = new CapturingSpeechRecognitionPipeline { BlockReadinessUntilCancelled = true };
        var service = new SpeechRecognitionPipelineHostedService(
            new CapturingSpeechRecognitionPipelineFactory(pipeline),
            NullLogger<SpeechRecognitionPipelineHostedService>.Instance);

        var startTask = service.StartAsync(CancellationToken.None);

        await startTask.WaitAsync(TimeSpan.FromSeconds(1));
        await pipeline.WaitForInitializeAsync();
        await pipeline.WaitForReadinessAsync();

        await service.StopAsync(CancellationToken.None);

        Assert.Equal(1, pipeline.InitializeCount);
        Assert.Equal(1, pipeline.ReadinessCount);
        Assert.True(pipeline.ReadinessCancellationWasObserved);
        Assert.True(pipeline.Disposed);
    }

    [Fact]
    public async Task HostedServiceWarmsConfiguredLaunchProfilePipelinesWithoutBlockingStartup()
    {
        var defaultPipeline = new CapturingSpeechRecognitionPipeline();
        var funAsrPipeline = new CapturingSpeechRecognitionPipeline { BlockReadinessUntilCancelled = true };
        var englishPipeline = new CapturingSpeechRecognitionPipeline();
        var service = new SpeechRecognitionPipelineHostedService(
            new CapturingSpeechRecognitionPipelineFactory(new Dictionary<string, ISpeechRecognitionPipeline>
            {
                [ConfigurationLaunchProfileOptionsProvider.DefaultProfileName] = defaultPipeline,
                ["funasr"] = funAsrPipeline,
                ["english"] = englishPipeline
            }),
            new FakeLaunchProfileOptionsProvider(
            [
                new LaunchProfile(
                    ConfigurationLaunchProfileOptionsProvider.DefaultProfileName,
                    new MeetingAssistantOptions
                    {
                        Recording = { TranscriptionProvider = "azure-speech" }
                    }),
                new LaunchProfile(
                    "funasr",
                    new MeetingAssistantOptions
                    {
                        Recording = { TranscriptionProvider = "funasr" }
                    }),
                new LaunchProfile(
                    "english",
                    new MeetingAssistantOptions
                    {
                        Recording = { TranscriptionProvider = "azure-speech" }
                    })
            ]),
            NullLogger<SpeechRecognitionPipelineHostedService>.Instance);

        var startTask = service.StartAsync(CancellationToken.None);

        await startTask.WaitAsync(TimeSpan.FromSeconds(1));
        await defaultPipeline.WaitForInitializeAsync();
        await defaultPipeline.WaitForReadinessAsync();
        await funAsrPipeline.WaitForInitializeAsync();
        await funAsrPipeline.WaitForReadinessAsync();

        await service.StopAsync(CancellationToken.None);

        Assert.Equal(1, defaultPipeline.InitializeCount);
        Assert.Equal(1, funAsrPipeline.InitializeCount);
        Assert.True(defaultPipeline.Disposed);
        Assert.True(funAsrPipeline.Disposed);
        Assert.True(funAsrPipeline.ReadinessCancellationWasObserved);
        Assert.Equal(0, englishPipeline.InitializeCount);
        Assert.False(englishPipeline.Disposed);
    }

    private sealed class CapturingSpeechRecognitionPipelineFactory : ISpeechRecognitionPipelineFactory
    {
        private readonly IReadOnlyDictionary<string, ISpeechRecognitionPipeline> pipelines;

        public CapturingSpeechRecognitionPipelineFactory(ISpeechRecognitionPipeline pipeline)
            : this(new Dictionary<string, ISpeechRecognitionPipeline>
            {
                [ConfigurationLaunchProfileOptionsProvider.DefaultProfileName] = pipeline
            })
        {
        }

        public CapturingSpeechRecognitionPipelineFactory(
            IReadOnlyDictionary<string, ISpeechRecognitionPipeline> pipelines)
        {
            this.pipelines = pipelines;
        }

        public ISpeechRecognitionPipeline Create()
        {
            return Create(ConfigurationLaunchProfileOptionsProvider.DefaultProfileName);
        }

        public ISpeechRecognitionPipeline Create(string? launchProfileName)
        {
            var profileName = string.IsNullOrWhiteSpace(launchProfileName)
                ? ConfigurationLaunchProfileOptionsProvider.DefaultProfileName
                : launchProfileName;
            return pipelines[profileName];
        }
    }

    private sealed class FakeLaunchProfileOptionsProvider : ILaunchProfileOptionsProvider
    {
        private readonly IReadOnlyList<LaunchProfile> profiles;

        public FakeLaunchProfileOptionsProvider(IReadOnlyList<LaunchProfile> profiles)
        {
            this.profiles = profiles;
        }

        public LaunchProfile GetRequiredProfile(string? name)
        {
            var profileName = string.IsNullOrWhiteSpace(name)
                ? ConfigurationLaunchProfileOptionsProvider.DefaultProfileName
                : name;
            return profiles.Single(profile => profile.Name.Equals(profileName, StringComparison.OrdinalIgnoreCase));
        }

        public IReadOnlyList<LaunchProfile> GetProfiles()
        {
            return profiles;
        }

        public IReadOnlyList<LaunchProfileHotkey> GetHotkeys()
        {
            return [];
        }
    }

    private sealed class CapturingSpeechRecognitionPipeline : ISpeechRecognitionPipeline
    {
        private readonly TaskCompletionSource initialized = new(TaskCreationOptions.RunContinuationsAsynchronously);
        private readonly TaskCompletionSource readinessChecked = new(TaskCreationOptions.RunContinuationsAsynchronously);

        public int InitializeCount { get; private set; }

        public int ReadinessCount { get; private set; }

        public bool BlockReadinessUntilCancelled { get; init; }

        public bool ReadinessCancellationWasObserved { get; private set; }

        public bool Disposed { get; private set; }

        public Task WaitForInitializeAsync()
        {
            return initialized.Task.WaitAsync(TimeSpan.FromSeconds(5));
        }

        public Task WaitForReadinessAsync()
        {
            return readinessChecked.Task.WaitAsync(TimeSpan.FromSeconds(5));
        }

        public Task InitializeAsync(CancellationToken cancellationToken)
        {
            return InitializeAsync(SpeechRecognitionPipelineOptions.Default, cancellationToken);
        }

        public Task InitializeAsync(
            SpeechRecognitionPipelineOptions options,
            CancellationToken cancellationToken)
        {
            InitializeCount++;
            initialized.TrySetResult();
            return Task.CompletedTask;
        }

        public async Task WaitUntilReadyAsync(CancellationToken cancellationToken)
        {
            ReadinessCount++;
            readinessChecked.TrySetResult();
            if (!BlockReadinessUntilCancelled)
            {
                return;
            }

            try
            {
                await Task.Delay(Timeout.InfiniteTimeSpan, cancellationToken);
            }
            catch (OperationCanceledException)
            {
                ReadinessCancellationWasObserved = true;
                throw;
            }
        }

        public ValueTask WriteAsync(MeetingAssistant.Recording.AudioChunk chunk, CancellationToken cancellationToken)
        {
            return ValueTask.CompletedTask;
        }

        public Task CompleteAsync(CancellationToken cancellationToken)
        {
            return Task.CompletedTask;
        }

        public async IAsyncEnumerable<TranscriptionSegment> ReadLiveTranscriptAsync(
            [System.Runtime.CompilerServices.EnumeratorCancellation] CancellationToken cancellationToken)
        {
            await Task.CompletedTask;
            yield break;
        }

        public Task<IReadOnlyList<TranscriptionSegment>> ReadFinishedTranscriptAsync(
            string audioPath,
            SpeechRecognitionPipelineOptions options,
            CancellationToken cancellationToken)
        {
            return Task.FromResult<IReadOnlyList<TranscriptionSegment>>([]);
        }

        public ValueTask DisposeAsync()
        {
            Disposed = true;
            return ValueTask.CompletedTask;
        }
    }
}