lmxopcua/tests/ZB.MOM.WW.OtOpcUa.Historian.Aveva.Tests/HistorianClusterEndpointPickerTests.cs

using System;
using System.Collections.Generic;
using System.Linq;
using System.Threading;
using System.Threading.Tasks;
using Shouldly;
using Xunit;
using ZB.MOM.WW.OtOpcUa.Host.Configuration;

namespace ZB.MOM.WW.OtOpcUa.Historian.Aveva.Tests
{
    /// <summary>
    ///     Exhaustive coverage of the cluster endpoint picker: config parsing, healthy-list ordering,
    ///     cooldown behavior with an injected clock, and thread-safety under concurrent writers.
    /// </summary>
    public class HistorianClusterEndpointPickerTests
    {
        // ---------- Construction / config parsing ----------

        [Fact]
        public void SingleServerName_FallbackWhenServerNamesEmpty()
        {
            var picker = new HistorianClusterEndpointPicker(Config(serverName: "host-a"));
            picker.NodeCount.ShouldBe(1);
            picker.GetHealthyNodes().ShouldBe(new[] { "host-a" });
        }

        [Fact]
        public void ServerNames_TakesPrecedenceOverLegacyServerName()
        {
            var picker = new HistorianClusterEndpointPicker(
                Config(serverName: "legacy", serverNames: new[] { "host-a", "host-b" }));
            picker.NodeCount.ShouldBe(2);
            picker.GetHealthyNodes().ShouldBe(new[] { "host-a", "host-b" });
        }

        [Fact]
        public void ServerNames_OrderedAsConfigured()
        {
            var picker = new HistorianClusterEndpointPicker(
                Config(serverNames: new[] { "c", "a", "b" }));
            picker.GetHealthyNodes().ShouldBe(new[] { "c", "a", "b" });
        }

        [Fact]
        public void ServerNames_WhitespaceTrimmedAndEmptyDropped()
        {
            var picker = new HistorianClusterEndpointPicker(
                Config(serverNames: new[] { "  host-a  ", "", "   ", "host-b" }));
            picker.GetHealthyNodes().ShouldBe(new[] { "host-a", "host-b" });
        }

        [Fact]
        public void ServerNames_CaseInsensitiveDeduplication()
        {
            var picker = new HistorianClusterEndpointPicker(
                Config(serverNames: new[] { "Host-A", "HOST-A", "host-a" }));
            picker.NodeCount.ShouldBe(1);
        }

        [Fact]
        public void EmptyConfig_ProducesEmptyPool()
        {
            var picker = new HistorianClusterEndpointPicker(
                Config(serverName: "", serverNames: Array.Empty<string>()));
            picker.NodeCount.ShouldBe(0);
            picker.GetHealthyNodes().ShouldBeEmpty();
        }

        // ---------- MarkFailed / cooldown window ----------

        [Fact]
        public void MarkFailed_RemovesNodeFromHealthyList()
        {
            var clock = new FakeClock();
            var picker = new HistorianClusterEndpointPicker(
                Config(serverNames: new[] { "a", "b" }, cooldownSeconds: 60), clock.Now);

            picker.MarkFailed("a", "boom");

            picker.GetHealthyNodes().ShouldBe(new[] { "b" });
            picker.HealthyNodeCount.ShouldBe(1);
        }

        [Fact]
        public void MarkFailed_RecordsErrorAndTimestamp()
        {
            var clock = new FakeClock { UtcNow = new DateTime(2026, 4, 13, 10, 0, 0, DateTimeKind.Utc) };
            var picker = new HistorianClusterEndpointPicker(
                Config(serverNames: new[] { "a", "b" }), clock.Now);

            picker.MarkFailed("a", "connection refused");

            var states = picker.SnapshotNodeStates();
            var a = states.First(s => s.Name == "a");
            a.IsHealthy.ShouldBeFalse();
            a.FailureCount.ShouldBe(1);
            a.LastError.ShouldBe("connection refused");
            a.LastFailureTime.ShouldBe(clock.UtcNow);
        }

        [Fact]
        public void MarkFailed_CooldownExpiryRestoresNode()
        {
            var clock = new FakeClock { UtcNow = new DateTime(2026, 4, 13, 10, 0, 0, DateTimeKind.Utc) };
            var picker = new HistorianClusterEndpointPicker(
                Config(serverNames: new[] { "a", "b" }, cooldownSeconds: 60), clock.Now);

            picker.MarkFailed("a", "boom");
            picker.GetHealthyNodes().ShouldBe(new[] { "b" });

            // Advance clock just before expiry — still in cooldown
            clock.UtcNow = clock.UtcNow.AddSeconds(59);
            picker.GetHealthyNodes().ShouldBe(new[] { "b" });

            // Advance past cooldown — node returns to pool
            clock.UtcNow = clock.UtcNow.AddSeconds(2);
            picker.GetHealthyNodes().ShouldBe(new[] { "a", "b" });
        }

        [Fact]
        public void ZeroCooldown_NeverBenchesNode()
        {
            var clock = new FakeClock();
            var picker = new HistorianClusterEndpointPicker(
                Config(serverNames: new[] { "a", "b" }, cooldownSeconds: 0), clock.Now);

            picker.MarkFailed("a", "boom");

            // Zero cooldown → node remains eligible immediately
            picker.GetHealthyNodes().ShouldBe(new[] { "a", "b" });
            var state = picker.SnapshotNodeStates().First(s => s.Name == "a");
            state.FailureCount.ShouldBe(1);
            state.LastError.ShouldBe("boom");
        }

        [Fact]
        public void AllNodesFailed_HealthyListIsEmpty()
        {
            var clock = new FakeClock();
            var picker = new HistorianClusterEndpointPicker(
                Config(serverNames: new[] { "a", "b" }, cooldownSeconds: 60), clock.Now);

            picker.MarkFailed("a", "boom");
            picker.MarkFailed("b", "boom");

            picker.GetHealthyNodes().ShouldBeEmpty();
            picker.HealthyNodeCount.ShouldBe(0);
        }

        [Fact]
        public void MarkFailed_AccumulatesFailureCount()
        {
            var clock = new FakeClock();
            var picker = new HistorianClusterEndpointPicker(
                Config(serverNames: new[] { "a" }, cooldownSeconds: 10), clock.Now);

            picker.MarkFailed("a", "error 1");
            clock.UtcNow = clock.UtcNow.AddSeconds(20); // recover
            picker.MarkFailed("a", "error 2");

            picker.SnapshotNodeStates().First().FailureCount.ShouldBe(2);
            picker.SnapshotNodeStates().First().LastError.ShouldBe("error 2");
        }

        // ---------- MarkHealthy ----------

        [Fact]
        public void MarkHealthy_ClearsCooldownImmediately()
        {
            var clock = new FakeClock();
            var picker = new HistorianClusterEndpointPicker(
                Config(serverNames: new[] { "a", "b" }, cooldownSeconds: 3600), clock.Now);

            picker.MarkFailed("a", "boom");
            picker.GetHealthyNodes().ShouldBe(new[] { "b" });

            picker.MarkHealthy("a");
            picker.GetHealthyNodes().ShouldBe(new[] { "a", "b" });
        }

        [Fact]
        public void MarkHealthy_PreservesCumulativeFailureCount()
        {
            var clock = new FakeClock();
            var picker = new HistorianClusterEndpointPicker(
                Config(serverNames: new[] { "a" }), clock.Now);

            picker.MarkFailed("a", "boom");
            picker.MarkHealthy("a");

            var state = picker.SnapshotNodeStates().First();
            state.IsHealthy.ShouldBeTrue();
            state.FailureCount.ShouldBe(1); // history preserved
        }

        // ---------- Unknown node handling ----------

        [Fact]
        public void MarkFailed_UnknownNode_IsIgnored()
        {
            var clock = new FakeClock();
            var picker = new HistorianClusterEndpointPicker(
                Config(serverNames: new[] { "a" }), clock.Now);

            Should.NotThrow(() => picker.MarkFailed("not-configured", "boom"));
            picker.GetHealthyNodes().ShouldBe(new[] { "a" });
        }

        [Fact]
        public void MarkHealthy_UnknownNode_IsIgnored()
        {
            var picker = new HistorianClusterEndpointPicker(
                Config(serverNames: new[] { "a" }));
            Should.NotThrow(() => picker.MarkHealthy("not-configured"));
        }

        // ---------- SnapshotNodeStates ----------

        [Fact]
        public void SnapshotNodeStates_ReflectsConfigurationOrder()
        {
            var picker = new HistorianClusterEndpointPicker(
                Config(serverNames: new[] { "z", "m", "a" }));
            picker.SnapshotNodeStates().Select(s => s.Name).ShouldBe(new[] { "z", "m", "a" });
        }

        [Fact]
        public void SnapshotNodeStates_HealthyEntriesHaveNoCooldown()
        {
            var picker = new HistorianClusterEndpointPicker(
                Config(serverNames: new[] { "a" }));
            var state = picker.SnapshotNodeStates().First();
            state.IsHealthy.ShouldBeTrue();
            state.CooldownUntil.ShouldBeNull();
            state.LastError.ShouldBeNull();
            state.LastFailureTime.ShouldBeNull();
        }

        // ---------- Thread safety smoke test ----------

        [Fact]
        public void ConcurrentMarkAndQuery_DoesNotCorrupt()
        {
            var clock = new FakeClock();
            var picker = new HistorianClusterEndpointPicker(
                Config(serverNames: new[] { "a", "b", "c", "d" }, cooldownSeconds: 5), clock.Now);

            var tasks = new List<Task>();
            for (var i = 0; i < 8; i++)
            {
                tasks.Add(Task.Run(() =>
                {
                    for (var j = 0; j < 1000; j++)
                    {
                        picker.MarkFailed("a", "boom");
                        picker.MarkHealthy("a");
                        _ = picker.GetHealthyNodes();
                        _ = picker.SnapshotNodeStates();
                    }
                }));
            }

            Task.WaitAll(tasks.ToArray());
            // Just verify we can still read state after the storm.
            picker.NodeCount.ShouldBe(4);
            picker.GetHealthyNodes().Count.ShouldBeInRange(3, 4);
        }

        // ---------- Helpers ----------

        private static HistorianConfiguration Config(
            string serverName = "localhost",
            string[]? serverNames = null,
            int cooldownSeconds = 60)
        {
            return new HistorianConfiguration
            {
                ServerName = serverName,
                ServerNames = (serverNames ?? Array.Empty<string>()).ToList(),
                FailureCooldownSeconds = cooldownSeconds
            };
        }

        private sealed class FakeClock
        {
            public DateTime UtcNow { get; set; } = new DateTime(2026, 1, 1, 0, 0, 0, DateTimeKind.Utc);
            public DateTime Now() => UtcNow;
        }
    }
}