lmxopcua/tests/Server/ZB.MOM.WW.OtOpcUa.Runtime.Tests/OpcUa/OpcUaPublishActorBatchTests.cs

using Akka.Actor;
using Shouldly;
using Xunit;
using ZB.MOM.WW.OtOpcUa.Commons.OpcUa;
using ZB.MOM.WW.OtOpcUa.Runtime.OpcUa;
using ZB.MOM.WW.OtOpcUa.Runtime.Tests.Harness;

namespace ZB.MOM.WW.OtOpcUa.Runtime.Tests.OpcUa;

/// <summary>
///     Task 7 of the value-pipeline batching work: <see cref="OpcUaPublishActor.AttributeValueBatchUpdate"/>
///     must reach the sink as exactly ONE <see cref="IOpcUaAddressSpaceSink.WriteValues"/> call — that single
///     call is the whole point (the SDK-backed sink takes its lock once per batch instead of once per value),
///     so a handler that looped <c>WriteValue</c> would pass a "the values arrived" assertion while delivering
///     none of the win. Hence the fake counts per-item <c>WriteValue</c> calls separately and the assertions
///     require that count to be zero.
///     <para>The per-item <see cref="OpcUaPublishActor.AttributeValueUpdate"/> receive stays — VirtualTagHostActor
///     and the alarm paths still send it — so it is pinned here too.</para>
/// </summary>
public sealed class OpcUaPublishActorBatchTests : RuntimeActorTestBase
{
    /// <summary>A 3-item batch lands as one WriteValues call carrying all three items verbatim (field-exact,
    /// realm included), and never decomposes into per-item WriteValue calls.</summary>
    [Fact]
    public void Batch_message_reaches_sink_as_one_WriteValues_call()
    {
        var sink = new RecordingSink();
        var actor = Sys.ActorOf(OpcUaPublishActor.PropsForTests(sink: sink));

        var t0 = new DateTime(2026, 8, 15, 10, 0, 0, DateTimeKind.Utc);
        var items = new[]
        {
            new ValueWrite("Plant/Modbus/dev1/Speed", 42, OpcUaStatus.Good, t0, AddressSpaceRealm.Raw),
            new ValueWrite("AreaA/Line1/Eq1/Speed", 42, OpcUaStatus.Good, t0, AddressSpaceRealm.Uns),
            new ValueWrite("Plant/Modbus/dev1/Temp", 7.5d, OpcUaStatus.BadNoCommunication,
                t0.AddSeconds(1), AddressSpaceRealm.Raw),
        };

        actor.Tell(new OpcUaPublishActor.AttributeValueBatchUpdate(items));

        AwaitAssert(() => sink.Batches.Count.ShouldBe(1), PresenceBudget);

        var batch = sink.Batches[0];
        batch.Count.ShouldBe(3);
        batch[0].ShouldBe(items[0]);
        batch[1].ShouldBe(items[1]);
        batch[2].ShouldBe(items[2]);

        // The load-bearing half: one batched call, NOT three per-item calls.
        sink.SingleWrites.Count.ShouldBe(0);
    }

    /// <summary>A sink that throws out of WriteValues is swallowed and logged — the actor survives and keeps
    /// processing, rather than restarting and dropping traffic.
    /// <para>The survival assertion alone does NOT prove the catch exists: Akka's default supervision
    /// RESTARTS a throwing actor and the restart preserves the mailbox, so a follow-up message lands either
    /// way. The load-bearing assertions are therefore the two event filters — the exception must never reach
    /// supervision (no Error carrying it is ever logged), and the handler's own Warning must be logged so the
    /// fault is swallowed but not silent. Deleting the catch turns BOTH red.</para></summary>
    [Fact]
    public void Sink_throw_is_swallowed_and_logged()
    {
        var sink = new ThrowOnWriteValuesSink();
        var actor = Sys.ActorOf(OpcUaPublishActor.PropsForTests(sink: sink));

        var t0 = new DateTime(2026, 8, 15, 10, 0, 0, DateTimeKind.Utc);

        // Expect(0, …) counts matches at the END of the action, so everything that must have happened by
        // then goes INSIDE it — otherwise the absence assertion races the actor and passes vacuously.
        EventFilter.Exception<InvalidOperationException>().Expect(0, () =>
        {
            // The handler caught it AND said so: its own Warning, not supervision's Error.
            EventFilter.Warning(contains: "sink.WriteValues threw").ExpectOne(() =>
                actor.Tell(new OpcUaPublishActor.AttributeValueBatchUpdate(new[]
                {
                    new ValueWrite("Plant/Modbus/dev1/Speed", 1, OpcUaStatus.Good, t0, AddressSpaceRealm.Raw),
                })));

            // Survival: a follow-up on the untouched per-item path lands only if the actor is still pumping.
            actor.Tell(new OpcUaPublishActor.AttributeValueUpdate(
                "Plant/Modbus/dev1/Temp", 2, OpcUaStatus.Good, t0, AddressSpaceRealm.Raw));

            AwaitAssert(() => sink.SingleWrites.Count.ShouldBe(1), PresenceBudget);
        });

        sink.Threw.ShouldBeTrue();
    }

    /// <summary>A PARTIAL failure is metered honestly: a sink that applies 2 of 3 items and reports the
    /// aggregate as a <see cref="ValueWriteBatchException"/> must advance the write tally by the SUCCEEDED
    /// count, not by zero (the general catch's behaviour) and not by the whole batch. The invariant the
    /// batching work must not break is that the tally counts per ITEM — so a batch that half-failed reports
    /// exactly the half that landed.</summary>
    [Fact]
    public void Partial_failure_still_counts_the_items_that_landed()
    {
        var sink = new PartialFailureSink();
        // TestActorRef so the actor's own WriteCount tally is readable — the counter the handler advances is
        // the thing under test, and nothing else observes it.
        var actor = ActorOfAsTestActorRef<OpcUaPublishActor>(OpcUaPublishActor.PropsForTests(sink: sink));

        var t0 = new DateTime(2026, 8, 15, 10, 0, 0, DateTimeKind.Utc);
        actor.Tell(new OpcUaPublishActor.AttributeValueBatchUpdate(new[]
        {
            new ValueWrite("Plant/Modbus/dev1/Speed", 1, OpcUaStatus.Good, t0, AddressSpaceRealm.Raw),
            new ValueWrite("", 2, OpcUaStatus.Good, t0, AddressSpaceRealm.Raw),
            new ValueWrite("Plant/Modbus/dev1/Temp", 3, OpcUaStatus.Good, t0, AddressSpaceRealm.Raw),
        }));

        sink.Threw.ShouldBeTrue();
        actor.UnderlyingActor.WriteCount.ShouldBe(2,
            "the two items the sink DID apply must still be counted — not 0 (the general catch) and not 3");

        // The actor survived the partial failure and keeps pumping.
        actor.Tell(new OpcUaPublishActor.AttributeValueUpdate(
            "Plant/Modbus/dev1/Other", 4, OpcUaStatus.Good, t0, AddressSpaceRealm.Raw));
        sink.SingleWrites.Count.ShouldBe(1);
        actor.UnderlyingActor.WriteCount.ShouldBe(3);
    }

    /// <summary>The pre-existing single-item AttributeValueUpdate path is untouched by the batch addition.</summary>
    [Fact]
    public void Single_item_message_still_works()
    {
        var sink = new RecordingSink();
        var actor = Sys.ActorOf(OpcUaPublishActor.PropsForTests(sink: sink));

        var t0 = new DateTime(2026, 8, 15, 10, 0, 0, DateTimeKind.Utc);
        actor.Tell(new OpcUaPublishActor.AttributeValueUpdate(
            "AreaA/Line1/Eq1/Speed", 99, OpcUaStatus.Good, t0, AddressSpaceRealm.Uns));

        AwaitAssert(() => sink.SingleWrites.Count.ShouldBe(1), PresenceBudget);
        sink.SingleWrites[0].ShouldBe(new ValueWrite("AreaA/Line1/Eq1/Speed", 99, OpcUaStatus.Good, t0, AddressSpaceRealm.Uns));
        sink.Batches.Count.ShouldBe(0);
    }

    private void AwaitAssert(Action assertion, TimeSpan duration)
    {
        var deadline = DateTime.UtcNow + duration;
        Exception? last = null;
        while (DateTime.UtcNow < deadline)
        {
            try { assertion(); return; }
            catch (Exception ex) { last = ex; Thread.Sleep(25); }
        }
        if (last is not null) throw last;
    }

    /// <summary>Records batched and per-item value writes separately, so a handler that looped WriteValue
    /// instead of calling WriteValues once is distinguishable from one that batched.</summary>
    private class RecordingSink : IOpcUaAddressSpaceSink
    {
        private readonly object _gate = new();
        private readonly List<IReadOnlyList<ValueWrite>> _batches = new();
        private readonly List<ValueWrite> _singles = new();

        public IReadOnlyList<IReadOnlyList<ValueWrite>> Batches { get { lock (_gate) return _batches.ToArray(); } }
        public IReadOnlyList<ValueWrite> SingleWrites { get { lock (_gate) return _singles.ToArray(); } }

        public void WriteValue(string nodeId, object? value, uint statusCode, DateTime sourceTimestampUtc, AddressSpaceRealm realm = AddressSpaceRealm.Uns)
        {
            lock (_gate) _singles.Add(new ValueWrite(nodeId, value, statusCode, sourceTimestampUtc, realm));
        }

        // Overrides the interface's default WriteValues so the batch is observed as one call, not N.
        public virtual void WriteValues(IReadOnlyList<ValueWrite> values)
        {
            lock (_gate) _batches.Add(values.ToArray());
        }

        public void WriteAlarmQuality(string alarmNodeId, uint statusCode, DateTime sourceTimestampUtc, AddressSpaceRealm realm) { }
        public void WriteAlarmCondition(string alarmNodeId, AlarmConditionSnapshot state, DateTime occurredUtc, AddressSpaceRealm realm = AddressSpaceRealm.Uns) { }
        public void MaterialiseAlarmCondition(string alarmNodeId, string equipmentNodeId, string displayName, string alarmType, int severity, AddressSpaceRealm realm, bool isNative = false) { }
        public void EnsureFolder(string folderNodeId, string? parentNodeId, string displayName, AddressSpaceRealm realm = AddressSpaceRealm.Uns) { }
        public void EnsureVariable(string variableNodeId, string? parentFolderNodeId, string displayName, string dataType, bool writable, AddressSpaceRealm realm, string? historianTagname = null, bool isArray = false, uint? arrayLength = null, bool refuseArrayOnScalar = false) { }
        public void RebuildAddressSpace() { }
        public void RaiseNodesAddedModelChange(string affectedNodeId, AddressSpaceRealm realm = AddressSpaceRealm.Uns) { }
        public void WireAlarmNotifiers(string alarmNodeId, AddressSpaceRealm alarmRealm, IReadOnlyList<string> notifierFolderNodeIds, AddressSpaceRealm notifierFolderRealm) { }
        public void AddReference(string sourceNodeId, AddressSpaceRealm sourceRealm, string targetNodeId, AddressSpaceRealm targetRealm, string referenceType = "Organizes") { }
    }

    /// <summary>A sink whose batched write throws a PLAIN exception — drives the handler's GENERAL catch (an
    /// unrecognised sink failure, where nothing is known about what landed, so nothing is counted).</summary>
    private sealed class ThrowOnWriteValuesSink : RecordingSink
    {
        private int _threw;

        public bool Threw => Volatile.Read(ref _threw) != 0;

        public override void WriteValues(IReadOnlyList<ValueWrite> values)
        {
            Interlocked.Exchange(ref _threw, 1);
            throw new InvalidOperationException("simulated batched-write fault");
        }
    }

    /// <summary>A sink modelling the real SDK-backed one's PARTIAL failure: it applies every item with a
    /// non-empty NodeId, then reports the aggregate as a <see cref="ValueWriteBatchException"/>. Drives the
    /// handler's typed catch.</summary>
    private sealed class PartialFailureSink : RecordingSink
    {
        private int _threw;

        public bool Threw => Volatile.Read(ref _threw) != 0;

        public override void WriteValues(IReadOnlyList<ValueWrite> values)
        {
            var applied = values.Where(v => !string.IsNullOrEmpty(v.NodeId)).ToArray();
            var failedCount = values.Count - applied.Length;
            if (failedCount == 0)
            {
                base.WriteValues(values);
                return;
            }

            base.WriteValues(applied);
            Interlocked.Exchange(ref _threw, 1);
            throw new ValueWriteBatchException(
                firstFailedNodeId: values.First(v => string.IsNullOrEmpty(v.NodeId)).NodeId,
                failedCount: failedCount,
                succeededCount: applied.Length,
                firstFailure: new ArgumentException("empty NodeId"));
        }
    }
}