ScadaBridge/tests/ZB.MOM.WW.ScadaBridge.Commons.Tests/Observability/DataConnectionGaugeTests.cs

using System.Diagnostics.Metrics;
using ZB.MOM.WW.ScadaBridge.Commons.Observability;
using ZB.MOM.WW.ScadaBridge.Commons.Types.Enums;

namespace ZB.MOM.WW.ScadaBridge.Commons.Tests.Observability;

/// <summary>
/// Register row 54: the real per-site data-connection gauges. Before these existed the only
/// connection-ish series was <c>scadabridge_site_connection_up</c>, which counted open
/// central→site gRPC subscriber streams and sat at 0 on a healthy unwatched site — so there
/// was no metric that answered "are this site's devices actually connected?" at all.
/// </summary>
/// <remarks>
/// Every assertion here is a DELTA against a baseline taken inside the test, and every
/// connection name is unique to the test. That is deliberate: the registry behind these
/// gauges is a process-global static, so absolute assertions would inherit the register
/// row 32 flake that makes <c>QueueDepthGaugeTests</c> pass alone and fail under the full
/// concurrent suite. Each test also removes its own connections in a <c>finally</c> so it
/// leaves the shared registry exactly as it found it.
/// </remarks>
public sealed class DataConnectionGaugeTests
{
    private const string ConnectedGauge = "scadabridge.site.data_connections.connected";
    private const string TotalGauge = "scadabridge.site.data_connections.total";

    /// <summary>Verifies that the connected state raises both the connected and total gauges.</summary>
    [Fact]
    public void ConnectedState_RaisesConnectedAndTotal()
    {
        var name = UniqueName();
        var connectedBefore = ReadGauge(ConnectedGauge);
        var totalBefore = ReadGauge(TotalGauge);

        try
        {
            ScadaBridgeTelemetry.RecordDataConnectionState(name, ConnectionHealth.Connected);

            Assert.Equal(connectedBefore + 1, ReadGauge(ConnectedGauge));
            Assert.Equal(totalBefore + 1, ReadGauge(TotalGauge));
        }
        finally
        {
            ScadaBridgeTelemetry.RemoveDataConnection(name);
        }
    }

    /// <summary>Verifies that a non-connected state raises only the total gauge.</summary>
    /// <param name="state">The state.</param>
    [Theory]
    [InlineData(ConnectionHealth.Disconnected)]
    [InlineData(ConnectionHealth.Connecting)]
    [InlineData(ConnectionHealth.Error)]
    public void NonConnectedState_RaisesTotalOnly(ConnectionHealth state)
    {
        // The load-bearing shape of the pair: a device that is configured but not talking
        // must show up in the denominator and NOT in the numerator, because connected < total
        // is the whole alert condition. A gauge that only counted connected rows would read
        // identically for "one device down" and "device deleted".
        var name = UniqueName();
        var connectedBefore = ReadGauge(ConnectedGauge);
        var totalBefore = ReadGauge(TotalGauge);

        try
        {
            ScadaBridgeTelemetry.RecordDataConnectionState(name, state);

            Assert.Equal(connectedBefore, ReadGauge(ConnectedGauge));
            Assert.Equal(totalBefore + 1, ReadGauge(TotalGauge));
        }
        finally
        {
            ScadaBridgeTelemetry.RemoveDataConnection(name);
        }
    }

    /// <summary>Verifies that a transition from connected to disconnected drops the connected gauge but keeps the total.</summary>
    [Fact]
    public void TransitionFromConnectedToDisconnected_DropsConnectedButKeepsTotal()
    {
        // The DCL calls Record* once per state transition on the SAME name, so a transition
        // must overwrite rather than accumulate — otherwise a flapping connection would
        // inflate the total without bound.
        var name = UniqueName();
        var connectedBefore = ReadGauge(ConnectedGauge);
        var totalBefore = ReadGauge(TotalGauge);

        try
        {
            ScadaBridgeTelemetry.RecordDataConnectionState(name, ConnectionHealth.Connected);
            ScadaBridgeTelemetry.RecordDataConnectionState(name, ConnectionHealth.Disconnected);

            Assert.Equal(connectedBefore, ReadGauge(ConnectedGauge));
            Assert.Equal(totalBefore + 1, ReadGauge(TotalGauge));
        }
        finally
        {
            ScadaBridgeTelemetry.RemoveDataConnection(name);
        }
    }

    /// <summary>Verifies that removing a data connection drops it from both gauges.</summary>
    [Fact]
    public void RemoveDataConnection_DropsItFromBothGauges()
    {
        // An undeployed connection must leave the denominator. If it lingered as a
        // permanently not-connected row, connected < total would latch on forever and the
        // alert would be useless after the first undeploy.
        var name = UniqueName();
        var connectedBefore = ReadGauge(ConnectedGauge);
        var totalBefore = ReadGauge(TotalGauge);

        ScadaBridgeTelemetry.RecordDataConnectionState(name, ConnectionHealth.Connected);
        ScadaBridgeTelemetry.RemoveDataConnection(name);

        Assert.Equal(connectedBefore, ReadGauge(ConnectedGauge));
        Assert.Equal(totalBefore, ReadGauge(TotalGauge));
    }

    /// <summary>Verifies that removing a data connection is idempotent.</summary>
    [Fact]
    public void RemoveDataConnection_IsIdempotent()
    {
        var name = UniqueName();
        ScadaBridgeTelemetry.RecordDataConnectionState(name, ConnectionHealth.Connected);
        ScadaBridgeTelemetry.RemoveDataConnection(name);

        var ex = Record.Exception(() => ScadaBridgeTelemetry.RemoveDataConnection(name));

        Assert.Null(ex);
    }

    /// <summary>Verifies that a null or empty connection name is ignored.</summary>
    [Fact]
    public void NullOrEmptyConnectionName_IsIgnored()
    {
        // Guards the gauges against a malformed caller creating a phantom row that could
        // never be removed by name.
        var totalBefore = ReadGauge(TotalGauge);

        ScadaBridgeTelemetry.RecordDataConnectionState(string.Empty, ConnectionHealth.Connected);
        ScadaBridgeTelemetry.RecordDataConnectionState(null!, ConnectionHealth.Connected);

        Assert.Equal(totalBefore, ReadGauge(TotalGauge));
    }

    /// <summary>Verifies that the stream subscriber gauge is published under its renamed name.</summary>
    [Fact]
    public void StreamSubscriberGauge_IsPublishedUnderTheRenamedName()
    {
        // Register row 54's rename half. Pins the honest name so a future edit cannot
        // silently restore scadabridge.site.connection.up, whose meaning (open gRPC
        // subscriber streams) never matched what operators read it as.
        var names = PublishedInstrumentNames();

        Assert.Contains("scadabridge.site.stream.subscribers.active", names);
        Assert.DoesNotContain("scadabridge.site.connection.up", names);
    }

    private static string UniqueName() => $"conn-{Guid.NewGuid():N}";

    /// <summary>Forces one observation of the named gauge and returns its value.</summary>
    /// <param name="instrumentName">Instrument name to observe.</param>
    /// <returns>The observed value, or 0 if the instrument never reported.</returns>
    private static long ReadGauge(string instrumentName)
    {
        long observed = 0;
        using var listener = new MeterListener();
        listener.InstrumentPublished = (instrument, l) =>
        {
            if (instrument.Meter.Name == ScadaBridgeTelemetry.MeterName
                && instrument.Name == instrumentName)
            {
                l.EnableMeasurementEvents(instrument);
            }
        };
        listener.SetMeasurementEventCallback<long>((_, measurement, _, _) => observed = measurement);
        listener.Start();
        listener.RecordObservableInstruments();
        return observed;
    }

    /// <summary>Collects every instrument name published on the ScadaBridge meter.</summary>
    /// <returns>The published instrument names.</returns>
    private static IReadOnlyCollection<string> PublishedInstrumentNames()
    {
        var names = new List<string>();
        using var listener = new MeterListener();
        listener.InstrumentPublished = (instrument, _) =>
        {
            if (instrument.Meter.Name == ScadaBridgeTelemetry.MeterName)
            {
                names.Add(instrument.Name);
            }
        };
        listener.Start();
        return names;
    }
}