lmxopcua/tests/Drivers/ZB.MOM.WW.OtOpcUa.Driver.AbLegacy.Tests/AbLegacyLifecycleConcurrencyTests.cs

using Shouldly;
using Xunit;
using ZB.MOM.WW.OtOpcUa.Core.Abstractions;
using ZB.MOM.WW.OtOpcUa.Driver.AbLegacy.PlcFamilies;

namespace ZB.MOM.WW.OtOpcUa.Driver.AbLegacy.Tests;

/// <summary>
///     Review 07 H13 + the Lane A runtime contract: the device and tag tables are build-and-swapped (never cleared
///     in place under a reader), <c>Dispose</c> may run concurrently with a still-running <c>ShutdownAsync</c>, and
///     an abandoned <c>InitializeAsync</c> that overlaps the next <c>ShutdownAsync</c> must not resurrect state.
/// </summary>
[Trait("Category", "Unit")]
public sealed class AbLegacyLifecycleConcurrencyTests
{
    private const string Host = "ab://10.0.0.5/1,0";

    /// <summary>A probe tag whose read parks until released, ignoring cancellation (a wedged device call).</summary>
    private sealed class ParkingProbeTag(AbLegacyTagCreateParams p, Task release) : FakeAbLegacyTag(p)
    {
        public readonly TaskCompletionSource Entered = new(TaskCreationOptions.RunContinuationsAsynchronously);

        public override async Task ReadAsync(CancellationToken ct)
        {
            Entered.TrySetResult();
            await release.ConfigureAwait(false);
            await base.ReadAsync(ct).ConfigureAwait(false);
        }
    }

    private static async Task WaitUntilAsync(Func<bool> condition, string what)
    {
        var deadline = DateTime.UtcNow.AddSeconds(10);
        while (!condition())
        {
            if (DateTime.UtcNow > deadline) throw new TimeoutException(what);
            await Task.Delay(10);
        }
    }

    /// <summary>
    ///     Re-initialising in a loop while other threads read the tables never throws "Collection was modified":
    ///     the readers see either the old or the new table, never one being cleared.
    /// </summary>
    [Fact]
    public async Task Reinit_under_concurrent_readers_never_throws()
    {
        var factory = new FakeAbLegacyTagFactory { Customise = p => new FakeAbLegacyTag(p) { Value = 1 } };
        var drv = new AbLegacyDriver(new AbLegacyDriverOptions
        {
            Devices = [new AbLegacyDeviceOptions(Host), new AbLegacyDeviceOptions("ab://10.0.0.6/1,0")],
            RawTags = AbLegacyRawTags.Entries(
                new AbLegacyTagDefinition("X", Host, "N7:0", AbLegacyDataType.Int),
                new AbLegacyTagDefinition("Y", "ab://10.0.0.6/1,0", "N7:1", AbLegacyDataType.Int)),
            Probe = new AbLegacyProbeOptions { Enabled = false },
        }, "drv-swap", factory);
        await drv.InitializeAsync("{}", CancellationToken.None);

        using var stop = new CancellationTokenSource();
        var failures = new System.Collections.Concurrent.ConcurrentQueue<Exception>();
        var reads = 0;
        var readers = Enumerable.Range(0, 3).Select(n => Task.Run(async () =>
        {
            while (!stop.IsCancellationRequested)
            {
                try
                {
                    _ = drv.GetHostStatuses();
                    _ = drv.ResolveHost("X");
                    _ = await drv.ReadAsync(["X", "Y"], CancellationToken.None);
                    Interlocked.Increment(ref reads);
                }
                catch (Exception ex) { failures.Enqueue(ex); }
            }
        })).ToArray();

        // Keep re-initialising until the readers have demonstrably overlapped many swaps.
        var deadline = DateTime.UtcNow.AddSeconds(10);
        for (var i = 0; i < 100 || Volatile.Read(ref reads) < 200; i++)
        {
            if (DateTime.UtcNow > deadline) break;
            await drv.InitializeAsync("{}", CancellationToken.None);
        }
        stop.Cancel();
        await Task.WhenAll(readers);

        failures.ShouldBeEmpty();
        reads.ShouldBeGreaterThan(0); // positive control: the readers really ran against the swapping tables
        await drv.ShutdownAsync(CancellationToken.None);
    }

    /// <summary>A re-init publishes a NEW device state; the old one is retired, not mutated in place.</summary>
    [Fact]
    public async Task Reinit_publishes_a_new_table_and_retires_the_old_state()
    {
        var factory = new FakeAbLegacyTagFactory { Customise = p => new FakeAbLegacyTag(p) { Value = 1 } };
        var drv = new AbLegacyDriver(new AbLegacyDriverOptions
        {
            Devices = [new AbLegacyDeviceOptions(Host)],
            RawTags = AbLegacyRawTags.Entries(new AbLegacyTagDefinition("X", Host, "N7:0", AbLegacyDataType.Int)),
            Probe = new AbLegacyProbeOptions { Enabled = false },
        }, "drv-swap", factory);
        await drv.InitializeAsync("{}", CancellationToken.None);
        (await drv.ReadAsync(["X"], CancellationToken.None))[0].StatusCode.ShouldBe(AbLegacyStatusMapper.Good);
        var old = drv.GetDeviceState(Host)!;
        var oldTag = factory.Tags["N7:0"];

        await drv.InitializeAsync("{}", CancellationToken.None);

        var fresh = drv.GetDeviceState(Host)!;
        fresh.ShouldNotBeSameAs(old);
        old.IsRetired.ShouldBeTrue();
        oldTag.Disposed.ShouldBeTrue();
        (await drv.ReadAsync(["X"], CancellationToken.None))[0].StatusCode.ShouldBe(AbLegacyStatusMapper.Good);
        await drv.ShutdownAsync(CancellationToken.None);
    }

    /// <summary>
    ///     A runtime created by a read that was already in flight when shutdown retired its device state is disposed
    ///     instead of being cached on the retired state (where nothing would ever release it).
    /// </summary>
    [Fact]
    public async Task Runtime_created_after_retirement_is_disposed_not_cached()
    {
        var release = new TaskCompletionSource(TaskCreationOptions.RunContinuationsAsynchronously);
        var entered = new TaskCompletionSource(TaskCreationOptions.RunContinuationsAsynchronously);
        FakeAbLegacyTag? created = null;
        var factory = new FakeAbLegacyTagFactory
        {
            Customise = p => created = new InitParkingTag(p, entered, release.Task) { Value = 1 },
        };
        var drv = new AbLegacyDriver(new AbLegacyDriverOptions
        {
            Devices = [new AbLegacyDeviceOptions(Host)],
            RawTags = AbLegacyRawTags.Entries(new AbLegacyTagDefinition("X", Host, "N7:0", AbLegacyDataType.Int)),
            Probe = new AbLegacyProbeOptions { Enabled = false },
        }, "drv-late", factory);
        await drv.InitializeAsync("{}", CancellationToken.None);
        var state = drv.GetDeviceState(Host)!;

        var read = drv.ReadAsync(["X"], CancellationToken.None);
        await entered.Task;
        await drv.ShutdownAsync(CancellationToken.None);
        release.SetResult();
        _ = await read;

        created.ShouldNotBeNull();
        created!.Disposed.ShouldBeTrue();
        state.Runtimes.ShouldBeEmpty();
        drv.GetHealth().State.ShouldBe(DriverState.Unknown); // the late read did not overwrite shutdown's health
    }

    private sealed class InitParkingTag(AbLegacyTagCreateParams p, TaskCompletionSource entered, Task release)
        : FakeAbLegacyTag(p)
    {
        public override async Task InitializeAsync(CancellationToken ct)
        {
            entered.TrySetResult();
            await release.ConfigureAwait(false);
            await base.InitializeAsync(ct).ConfigureAwait(false);
        }
    }

    /// <summary>
    ///     Lane A's final stop calls ShutdownAsync and then DisposeAsync/Dispose; under the 5 s bound Dispose can run
    ///     while ShutdownAsync is still joining a wedged probe loop. Both complete without throwing and every runtime
    ///     is released.
    /// </summary>
    [Fact]
    public async Task Dispose_concurrent_with_running_shutdown_is_safe()
    {
        var release = new TaskCompletionSource(TaskCreationOptions.RunContinuationsAsynchronously);
        ParkingProbeTag? probe = null;
        var factory = new FakeAbLegacyTagFactory
        {
            Customise = p => p.TagName == "S:0"
                ? probe = new ParkingProbeTag(p, release.Task)
                : new FakeAbLegacyTag(p) { Value = 1 },
        };
        var drv = new AbLegacyDriver(new AbLegacyDriverOptions
        {
            Devices = [new AbLegacyDeviceOptions(Host)],
            RawTags = AbLegacyRawTags.Entries(new AbLegacyTagDefinition("X", Host, "N7:0", AbLegacyDataType.Int)),
            Probe = new AbLegacyProbeOptions { Enabled = true, Interval = TimeSpan.FromMilliseconds(20) },
        }, "drv-dispose", factory);
        await drv.InitializeAsync("{}", CancellationToken.None);
        (await drv.ReadAsync(["X"], CancellationToken.None))[0].StatusCode.ShouldBe(AbLegacyStatusMapper.Good);
        await WaitUntilAsync(() => probe is not null, "probe never created");
        await probe!.Entered.Task;

        var shutdown = drv.ShutdownAsync(CancellationToken.None); // parks joining the wedged probe loop
        await Task.Delay(50);
        shutdown.IsCompleted.ShouldBeFalse();

        Should.NotThrow(() => drv.Dispose());
        await Should.NotThrowAsync(async () => await drv.DisposeAsync());
        release.SetResult();
        await shutdown;

        factory.Tags["N7:0"].Disposed.ShouldBeTrue();
        probe.Disposed.ShouldBeTrue();
        drv.DeviceCount.ShouldBe(0);
    }

    /// <summary>
    ///     An InitializeAsync the runtime abandoned (it is parked releasing a wedged prior probe loop) overlaps the next
    ///     ShutdownAsync. When it resumes it must NOT publish its tables or start probe loops — that state would sit
    ///     behind a driver the runtime believes is stopped. A later Initialize publishes normally (positive control).
    /// </summary>
    [Fact]
    public async Task Abandoned_initialize_overlapping_shutdown_does_not_resurrect_state()
    {
        var release = new TaskCompletionSource(TaskCreationOptions.RunContinuationsAsynchronously);
        var probes = new System.Collections.Concurrent.ConcurrentQueue<FakeAbLegacyTag>();
        ParkingProbeTag? first = null;
        var factory = new FakeAbLegacyTagFactory
        {
            Customise = p =>
            {
                FakeAbLegacyTag t = first is null ? first = new ParkingProbeTag(p, release.Task) : new FakeAbLegacyTag(p);
                probes.Enqueue(t);
                return t;
            },
        };
        var drv = new AbLegacyDriver(new AbLegacyDriverOptions
        {
            Devices = [new AbLegacyDeviceOptions(Host, AbLegacyPlcFamily.Slc500)],
            Probe = new AbLegacyProbeOptions { Enabled = true, Interval = TimeSpan.FromMilliseconds(20) },
        }, "drv-abandon", factory);
        await drv.InitializeAsync("{}", CancellationToken.None);
        await WaitUntilAsync(() => first is not null, "probe never created");
        await first!.Entered.Task;

        var abandoned = drv.InitializeAsync("{}", CancellationToken.None); // parks joining the wedged loop
        await Task.Delay(50);
        abandoned.IsCompleted.ShouldBeFalse();
        await drv.ShutdownAsync(CancellationToken.None);

        release.SetResult();
        await Should.ThrowAsync<OperationCanceledException>(() => abandoned);
        var createdAfter = probes.Count;
        await Task.Delay(150); // several probe intervals

        drv.DeviceCount.ShouldBe(0);
        drv.GetHealth().State.ShouldBe(DriverState.Unknown);
        probes.Count.ShouldBe(createdAfter);

        // Positive control: a fresh Initialize after the stop publishes and probes as normal.
        await drv.InitializeAsync("{}", CancellationToken.None);
        drv.DeviceCount.ShouldBe(1);
        drv.GetHealth().State.ShouldBe(DriverState.Healthy);
        await WaitUntilAsync(() => probes.Count > createdAfter, "fresh init never probed");
        await drv.ShutdownAsync(CancellationToken.None);
    }
}