meeting-assistant/MeetingAssistant.Tests/VenvResemblyzerVoiceEncoderTests.cs

using MeetingAssistant;
using MeetingAssistant.Speakers;
using MeetingAssistant.Transcription;
using Microsoft.Extensions.Logging.Abstractions;
using Microsoft.Extensions.Options;
using System.Text.Json;

namespace MeetingAssistant.Tests;

public sealed class VenvResemblyzerVoiceEncoderTests
{
    [Fact]
    public async Task WarmUpAsyncProvisionsVersionedCpuOnlyEnvironmentWithoutDocker()
    {
        using var fixture = new EncoderFixture();

        await fixture.Encoder.WarmUpAsync(CancellationToken.None);

        Assert.DoesNotContain(
            fixture.Runner.Commands,
            command => command.FileName.Contains("docker", StringComparison.OrdinalIgnoreCase));
        Assert.Contains(
            fixture.Runner.Commands,
            command => command.FileName == "python-test"
                && command.Arguments.Take(2).SequenceEqual(["-m", "venv"]));
        Assert.Contains(
            fixture.Runner.Commands,
            command => command.Arguments.Contains("torch==2.14.0+cpu")
                && command.Arguments.Contains("https://download.pytorch.org/whl/cpu"));
        Assert.Contains(
            fixture.Runner.Commands,
            command => command.Arguments.Contains("webrtcvad-wheels==2.0.14"));
        Assert.Contains(
            fixture.Runner.Commands,
            command => command.Arguments.Contains("Resemblyzer==0.1.4")
                && command.Arguments.Contains("--no-deps"));
    }

    [Fact]
    public async Task WarmUpAsyncDoesNotMarkFailedEnvironmentReady()
    {
        using var fixture = new EncoderFixture(
            warmupExitCode: 21,
            warmupError: "incompatible environment");

        await Assert.ThrowsAsync<InvalidOperationException>(
            () => fixture.Encoder.WarmUpAsync(CancellationToken.None));

        Assert.Empty(Directory.EnumerateFiles(
            fixture.RuntimeFolder,
            ".ready",
            SearchOption.AllDirectories));
    }

    [Fact]
    public async Task EncodeAsyncRunsBatchWithManagedEnvironmentPython()
    {
        var first = new float[256];
        first[0] = 2;
        var second = new float[256];
        second[1] = 3;
        using var fixture = new EncoderFixture(VectorOutput([first, second]));

        var vectors = await fixture.Encoder.EncodeAsync([[1, 2, 3], [4, 5, 6]], CancellationToken.None);

        Assert.Equal(2, vectors.Count);
        Assert.Equal(1f, vectors[0][0], 5);
        Assert.Equal(1f, vectors[1][1], 5);
        var encodingCommand = Assert.Single(
            fixture.Runner.Commands,
            command => command.Arguments.Any(
                argument => argument.EndsWith("encode.py", StringComparison.Ordinal)));
        Assert.EndsWith(
            Path.Combine("Scripts", "python.exe"),
            encodingCommand.FileName,
            StringComparison.OrdinalIgnoreCase);
        Assert.Equal(2, encodingCommand.Arguments.Count);
        Assert.True(Path.IsPathFullyQualified(encodingCommand.Arguments[1]));
    }

    [Fact]
    public async Task EncodeAsyncRejectsWrongVectorDimension()
    {
        var vector = new float[255];
        vector[0] = 1;
        using var fixture = new EncoderFixture(VectorOutput([vector]));

        var error = await Assert.ThrowsAsync<InvalidDataException>(
            () => fixture.Encoder.EncodeAsync([[1]], CancellationToken.None));

        Assert.Contains("255 dimensions", error.Message);
    }

    [Fact]
    public async Task EncodeAsyncRejectsMalformedVectorJson()
    {
        using var fixture = new EncoderFixture(
            "__MEETING_ASSISTANT_RESEMBLYZER_JSON_START__\n[not-json]\n__MEETING_ASSISTANT_RESEMBLYZER_JSON_END__");

        await Assert.ThrowsAsync<InvalidDataException>(
            () => fixture.Encoder.EncodeAsync([[1]], CancellationToken.None));
    }

    [Fact]
    public async Task EncodeAsyncRejectsNonFiniteVector()
    {
        var values = string.Join(',', new[] { "NaN" }.Concat(Enumerable.Repeat("0", 255)));
        using var fixture = new EncoderFixture(
            $"__MEETING_ASSISTANT_RESEMBLYZER_JSON_START__\n[[{values}]]\n__MEETING_ASSISTANT_RESEMBLYZER_JSON_END__");

        await Assert.ThrowsAsync<InvalidDataException>(
            () => fixture.Encoder.EncodeAsync([[1]], CancellationToken.None));
    }

    [Fact]
    public async Task EncodeAsyncRejectsWrongResultCount()
    {
        var vector = new float[256];
        vector[0] = 1;
        using var fixture = new EncoderFixture(VectorOutput([vector, vector]));

        var error = await Assert.ThrowsAsync<InvalidDataException>(
            () => fixture.Encoder.EncodeAsync([[1]], CancellationToken.None));

        Assert.Contains("2 vectors for 1 WAV samples", error.Message);
    }

    [Fact]
    public async Task EncodeAsyncRejectsZeroMagnitudeVector()
    {
        using var fixture = new EncoderFixture(VectorOutput([new float[256]]));

        var error = await Assert.ThrowsAsync<InvalidDataException>(
            () => fixture.Encoder.EncodeAsync([[1]], CancellationToken.None));

        Assert.Contains("zero magnitude", error.Message);
    }

    [Fact]
    public async Task EncodeAsyncReportsFailedLocalCommand()
    {
        using var fixture = new EncoderFixture("", 17, "runtime failed");

        var error = await Assert.ThrowsAsync<InvalidOperationException>(
            () => fixture.Encoder.EncodeAsync([[1]], CancellationToken.None));

        Assert.Contains("exit code 17", error.Message);
        Assert.Contains("runtime failed", error.Message);
    }

    private static string VectorOutput(IReadOnlyList<float[]> vectors)
    {
        return $"""
            __MEETING_ASSISTANT_RESEMBLYZER_JSON_START__
            {JsonSerializer.Serialize(vectors)}
            __MEETING_ASSISTANT_RESEMBLYZER_JSON_END__
            """;
    }

    private sealed class EncoderFixture : IDisposable
    {
        public EncoderFixture(
            string encodingOutput = "",
            int encodingExitCode = 0,
            string encodingError = "",
            int warmupExitCode = 0,
            string warmupError = "")
        {
            RuntimeFolder = Path.Combine(
                Path.GetTempPath(),
                "meeting-assistant-tests",
                Guid.NewGuid().ToString("N"),
                "resemblyzer");
            Runner = new CapturingCommandRunner(
                encodingOutput,
                encodingExitCode,
                encodingError,
                warmupExitCode,
                warmupError);
            var options = new MeetingAssistantOptions();
            options.SpeakerIdentification.Resemblyzer.PythonCommand = "python-test";
            options.SpeakerIdentification.Resemblyzer.RuntimeFolder = RuntimeFolder;
            Encoder = new VenvResemblyzerVoiceEncoder(
                Runner,
                Options.Create(options),
                NullLogger<VenvResemblyzerVoiceEncoder>.Instance);
        }

        public CapturingCommandRunner Runner { get; }

        public VenvResemblyzerVoiceEncoder Encoder { get; }

        public string RuntimeFolder { get; }

        public void Dispose()
        {
            if (Directory.Exists(RuntimeFolder))
            {
                Directory.Delete(RuntimeFolder, recursive: true);
            }
        }
    }

    private sealed class CapturingCommandRunner : ICommandRunner
    {
        private readonly string encodingOutput;
        private readonly int encodingExitCode;
        private readonly string encodingError;
        private readonly int warmupExitCode;
        private readonly string warmupError;

        public CapturingCommandRunner(
            string encodingOutput = "",
            int encodingExitCode = 0,
            string encodingError = "",
            int warmupExitCode = 0,
            string warmupError = "")
        {
            this.encodingOutput = encodingOutput;
            this.encodingExitCode = encodingExitCode;
            this.encodingError = encodingError;
            this.warmupExitCode = warmupExitCode;
            this.warmupError = warmupError;
        }

        public List<CapturedCommand> Commands { get; } = [];

        public Task<CommandResult> RunAsync(
            string fileName,
            IReadOnlyList<string> arguments,
            CancellationToken cancellationToken,
            IReadOnlyDictionary<string, string>? environment = null)
        {
            Commands.Add(new CapturedCommand(fileName, arguments.ToList()));
            var isEncoding = arguments.Any(argument => argument.EndsWith("encode.py", StringComparison.Ordinal));
            if (isEncoding)
            {
                return Task.FromResult(new CommandResult(encodingExitCode, encodingOutput, encodingError));
            }

            var isWarmup = arguments.Any(argument => argument.Contains("VoiceEncoder", StringComparison.Ordinal));
            return Task.FromResult(isWarmup
                ? new CommandResult(warmupExitCode, string.Empty, warmupError)
                : new CommandResult(0, string.Empty, string.Empty));
        }
    }

    private sealed record CapturedCommand(string FileName, IReadOnlyList<string> Arguments);
}