lmxopcua/tests/Server/ZB.MOM.WW.OtOpcUa.OpcUaServer.Tests/NodeManagerBatchWriteTests.cs

using Microsoft.Extensions.Logging.Abstractions;
using Opc.Ua;
using Shouldly;
using Xunit;
using ZB.MOM.WW.OtOpcUa.Commons.OpcUa;

namespace ZB.MOM.WW.OtOpcUa.OpcUaServer.Tests;

/// <summary>
///     Value-pipeline batching (Task 6) — <see cref="OtOpcUaNodeManager.WriteValues"/> applies a batch under
///     one acquisition of the manager-wide SDK <c>Lock</c> per 512-item chunk instead of one per value (the
///     per-value take was the steady-state throughput ceiling on the publish path; the chunk cap keeps the
///     first poll cycle's force-raise-everything batch from stalling every SDK service thread).
///     <para>These tests pin the <b>observable</b> contract rather than the locking: every item lands with
///     its own Value / StatusCode / Timestamp, an item for an undeclared NodeId is lazily created exactly
///     as <see cref="OtOpcUaNodeManager.WriteValue"/> does, and an empty batch does nothing at all.
///     A non-Good status is included so the #519 verbatim-sub-code passthrough is proven on the batched
///     path too — a batch that re-projected status through a 3-state enum would collapse it to a bare
///     <c>Bad</c>.</para>
///     <para>Boots a real <see cref="OtOpcUaSdkServer"/> through <see cref="OpcUaApplicationHost"/> — the
///     same harness <see cref="NodeManagerArrayTests"/> uses — so the assertions read the real SDK node
///     state an OPC UA client would receive.</para>
/// </summary>
public sealed class NodeManagerBatchWriteTests : IDisposable
{
    private static CancellationToken Ct => TestContext.Current.CancellationToken;

    private readonly string _pkiRoot = Path.Combine(
        Path.GetTempPath(),
        $"otopcua-batchwrite-{Guid.NewGuid():N}");

    /// <summary>Every item of a multi-item batch lands on its own node with its own value, status code
    /// (including a non-Good sub-code) and source timestamp — no item is dropped, and none overwrites
    /// another's state.</summary>
    [Fact]
    public async Task WriteValues_lands_every_value()
    {
        var (host, server) = await BootAsync();
        try
        {
            var nm = server.NodeManager!;

            foreach (var name in new[] { "a", "b", "c" })
            {
                nm.EnsureVariable($"eq-1/{name}", parentFolderNodeId: null, displayName: name, dataType: "Double",
                    writable: false, realm: AddressSpaceRealm.Uns);
            }

            var t1 = new DateTime(2026, 8, 15, 10, 0, 0, DateTimeKind.Utc);
            var t2 = new DateTime(2026, 8, 15, 10, 0, 1, DateTimeKind.Utc);
            var t3 = new DateTime(2026, 8, 15, 10, 0, 2, DateTimeKind.Utc);

            nm.WriteValues(new List<ValueWrite>
            {
                new("eq-1/a", 1.5d, OpcUaStatus.Good, t1, AddressSpaceRealm.Uns),
                new("eq-1/b", null, OpcUaStatus.BadNoCommunication, t2, AddressSpaceRealm.Uns),
                new("eq-1/c", 3.5d, 0x80740000u /* BadTypeMismatch */, t3, AddressSpaceRealm.Uns),
            });

            var a = nm.TryGetVariable("eq-1/a");
            a.ShouldNotBeNull();
            a!.Value.ShouldBe(1.5d);
            a.StatusCode.ShouldBe((StatusCode)StatusCodes.Good);
            a.Timestamp.ShouldBe(t1);

            var b = nm.TryGetVariable("eq-1/b");
            b.ShouldNotBeNull();
            b!.Value.ShouldBeNull();
            b.StatusCode.ShouldBe((StatusCode)StatusCodes.BadNoCommunication);
            b.StatusCode.ShouldNotBe((StatusCode)StatusCodes.Bad,
                "the batched path must hand the status sub-code to the SDK verbatim (#519)");
            b.Timestamp.ShouldBe(t2);

            var c = nm.TryGetVariable("eq-1/c");
            c.ShouldNotBeNull();
            c!.Value.ShouldBe(3.5d);
            c.StatusCode.ShouldBe((StatusCode)StatusCodes.BadTypeMismatch);
            c.Timestamp.ShouldBe(t3);
        }
        finally
        {
            await host.DisposeAsync();
        }
    }

    /// <summary>A batch item naming a NodeId that was never declared lazily creates the variable, exactly
    /// as the single-value <see cref="OtOpcUaNodeManager.WriteValue"/> create-on-first-write path does —
    /// and it does so PER REALM. Both items here carry the SAME <c>s=</c> id and differ only by realm, so a
    /// key that ignored the realm would create one node and have the second item overwrite the first. The
    /// assertion is therefore two nodes with DISTINCT namespace indices, not merely "both reads returned
    /// something" (which a realm-blind map satisfies, since the shared key resolves for either lookup).</summary>
    [Fact]
    public async Task WriteValues_creates_missing_variables()
    {
        var (host, server) = await BootAsync();
        try
        {
            var nm = server.NodeManager!;

            const string SharedId = "Shared/lazy/id";
            nm.TryGetVariable(SharedId, AddressSpaceRealm.Uns).ShouldBeNull();
            nm.TryGetVariable(SharedId, AddressSpaceRealm.Raw).ShouldBeNull();

            var ts = new DateTime(2026, 8, 15, 11, 0, 0, DateTimeKind.Utc);
            nm.WriteValues(new List<ValueWrite>
            {
                new(SharedId, 42, OpcUaStatus.Good, ts, AddressSpaceRealm.Uns),
                new(SharedId, 7, OpcUaStatus.Good, ts, AddressSpaceRealm.Raw),
            });

            var uns = nm.TryGetVariable(SharedId, AddressSpaceRealm.Uns);
            uns.ShouldNotBeNull();
            uns!.Value.ShouldBe(42);
            uns.StatusCode.ShouldBe((StatusCode)StatusCodes.Good);
            uns.Timestamp.ShouldBe(ts);

            var raw = nm.TryGetVariable(SharedId, AddressSpaceRealm.Raw);
            raw.ShouldNotBeNull();
            raw!.Value.ShouldBe(7);

            // Two DISTINCT nodes, one per namespace — the realm-blind failure mode collapses these to one.
            raw.NodeId.NamespaceIndex.ShouldNotBe(uns.NodeId.NamespaceIndex);
            raw.NodeId.NamespaceIndex.ShouldBe(nm.NamespaceIndexForRealm(AddressSpaceRealm.Raw));
            uns.NodeId.NamespaceIndex.ShouldBe(nm.NamespaceIndexForRealm(AddressSpaceRealm.Uns));
        }
        finally
        {
            await host.DisposeAsync();
        }
    }

    /// <summary>A bad item does NOT drop the tail of the batch. Item 2's NodeId is empty; items 1 and 3 must
    /// still land, and the aggregate surfaces as a <see cref="ValueWriteBatchException"/> naming the offender
    /// and the failed/succeeded split.
    /// <para>This is the durability-critical half: the poll engine updates its last-value cache BEFORE
    /// raising, so an item dropped here is never re-raised until that tag's value changes again — the node
    /// would serve a stale value indefinitely, with nothing in the log naming it.</para></summary>
    [Fact]
    public async Task A_failing_item_neither_drops_the_tail_nor_hides_which_node_failed()
    {
        var (host, server) = await BootAsync();
        try
        {
            var nm = server.NodeManager!;
            var ts = new DateTime(2026, 8, 15, 12, 0, 0, DateTimeKind.Utc);

            var ex = Should.Throw<ValueWriteBatchException>(() => nm.WriteValues(new List<ValueWrite>
            {
                new("eq-iso/first", 1, OpcUaStatus.Good, ts, AddressSpaceRealm.Uns),
                new(string.Empty, 2, OpcUaStatus.Good, ts, AddressSpaceRealm.Uns),
                new("eq-iso/third", 3, OpcUaStatus.Good, ts, AddressSpaceRealm.Uns),
            }));

            ex.FailedCount.ShouldBe(1);
            ex.SucceededCount.ShouldBe(2);
            ex.FirstFailedNodeId.ShouldBe(string.Empty);

            // The load-bearing half: BOTH good items applied — including the one AFTER the failure.
            var first = nm.TryGetVariable("eq-iso/first");
            first.ShouldNotBeNull();
            first!.Value.ShouldBe(1);

            var third = nm.TryGetVariable("eq-iso/third");
            third.ShouldNotBeNull("the item after the failing one must not be dropped");
            third!.Value.ShouldBe(3);
        }
        finally
        {
            await host.DisposeAsync();
        }
    }

    /// <summary>A batch larger than <c>MaxWritesPerLockAcquisition</c> (512) spans several lock acquisitions;
    /// chunking must be invisible in the outcome — every item still lands exactly once, with its own value.
    /// Chunk boundaries are the natural off-by-one hazard, so the size is deliberately not a multiple of 512.
    /// </summary>
    [Fact]
    public async Task A_batch_spanning_several_chunks_lands_every_item()
    {
        var (host, server) = await BootAsync();
        try
        {
            var nm = server.NodeManager!;
            var ts = new DateTime(2026, 8, 15, 13, 0, 0, DateTimeKind.Utc);

            const int Count = 1300; // > 2 chunks of 512, and not a multiple of it
            var items = new List<ValueWrite>(Count);
            for (var i = 0; i < Count; i++)
            {
                items.Add(new ValueWrite($"eq-chunk/{i}", i, OpcUaStatus.Good, ts, AddressSpaceRealm.Uns));
            }

            nm.WriteValues(items);

            nm.VariableCount.ShouldBe(Count);
            foreach (var probe in new[] { 0, 511, 512, 1023, 1024, Count - 1 })
            {
                var v = nm.TryGetVariable($"eq-chunk/{probe}");
                v.ShouldNotBeNull($"item {probe} (a chunk boundary) must have landed");
                v!.Value.ShouldBe(probe);
            }
        }
        finally
        {
            await host.DisposeAsync();
        }
    }

    /// <summary>An empty batch neither throws nor touches the address space.</summary>
    [Fact]
    public async Task Empty_batch_is_a_no_op()
    {
        var (host, server) = await BootAsync();
        try
        {
            var nm = server.NodeManager!;

            var before = nm.VariableCount;
            Should.NotThrow(() => nm.WriteValues([]));
            nm.VariableCount.ShouldBe(before);
        }
        finally
        {
            await host.DisposeAsync();
        }
    }

    private async Task<(OpcUaApplicationHost Host, OtOpcUaSdkServer Server)> BootAsync()
    {
        var applicationUri = $"urn:OtOpcUa.BatchWriteTest:{Guid.NewGuid():N}";
        var started = await OpcUaHostStart.StartAsync(
            port => new OpcUaApplicationHost(
                new OpcUaApplicationHostOptions
                {
                    ApplicationName = "OtOpcUa.BatchWriteTest",
                    ApplicationUri = applicationUri,
                    OpcUaPort = port,
                    PublicHostname = "localhost",
                    PkiStoreRoot = _pkiRoot,
                },
                NullLogger<OpcUaApplicationHost>.Instance),
            () => new OtOpcUaSdkServer(), Ct);
        var host = started.Host;
        var server = started.Server;
        return (host, server);
    }

    /// <summary>Cleans up the PKI root directory.</summary>
    public void Dispose()
    {
        if (Directory.Exists(_pkiRoot))
        {
            try { Directory.Delete(_pkiRoot, recursive: true); }
            catch { /* best-effort cleanup */ }
        }
    }
}