ScadaBridge/src/ZB.MOM.WW.ScadaBridge.HealthMonitoring/SiteEventLogFailureCountReporter.cs

using Microsoft.Extensions.Hosting;
using Microsoft.Extensions.Logging;

namespace ZB.MOM.WW.ScadaBridge.HealthMonitoring;

/// <summary>
/// Site Event Logging — site-side hosted service that
/// periodically reads the cumulative event-log write-failure count and pushes
/// it into <see cref="ISiteHealthCollector"/> so the next
/// <see cref="ISiteHealthCollector.CollectReport"/> emits a fresh
/// <c>SiteEventLogWriteFailures</c> field on the site health report.
/// </summary>
/// <remarks>
/// <para>
/// <b>Why a Func&lt;long&gt; and not ISiteEventLogger directly.</b>
/// A direct <c>HealthMonitoring → SiteEventLogging</c> reference is avoided
/// to prevent an undesirable low-level coupling: <c>SiteEventLogging</c> is a
/// leaf component that should not pull in higher-level infrastructure. Note that
/// <c>HealthMonitoring → StoreAndForward → SiteEventLogging</c> already
/// exists as a transitive path (confirmed: <c>StoreAndForward.csproj</c> references
/// <c>SiteEventLogging.csproj</c>), so a direct reference would NOT introduce a
/// cycle — the delegate is purely a coupling-avoidance measure. The
/// <see cref="Func{TResult}"/> seam lets the caller (Host site wiring) capture
/// <c>ISiteEventLogger.FailedWriteCount</c> as a lambda at registration time; this
/// service reads only the numeric result. The delegate approach is a standard
/// pattern for counter bridges and keeps the registration path self-documenting.
/// </para>
/// <para>
/// <b>Cadence.</b> 30 s by default — the same cadence as
/// <c>SiteAuditBacklogReporter</c>, which is coarse enough to stay within
/// the health-report interval budget while keeping the central dashboard
/// current.
/// </para>
/// <para>
/// <b>Failure containment.</b> Any unexpected exception during the probe is
/// caught and logged; the next tick retries. Mirrors
/// <c>SiteAuditBacklogReporter</c>'s "exception logged, not propagated"
/// contract.
/// </para>
/// </remarks>
public sealed class SiteEventLogFailureCountReporter : IHostedService, IDisposable
{
    /// <summary>
    /// Default poll cadence. Matches <c>SiteAuditBacklogReporter.DefaultRefreshInterval</c>
    /// (30 s) — coarse enough to amortise the read across many reports, fine
    /// enough that the central dashboard never lags by more than one
    /// health-report interval.
    /// </summary>
    internal static readonly TimeSpan DefaultRefreshInterval = TimeSpan.FromSeconds(30);

    private readonly Func<long> _failedWriteCountProvider;
    private readonly ISiteHealthCollector _collector;
    private readonly ILogger<SiteEventLogFailureCountReporter> _logger;
    private readonly TimeSpan _refreshInterval;
    private CancellationTokenSource? _cts;
    private Task? _loop;

    /// <summary>Initializes a new instance of <see cref="SiteEventLogFailureCountReporter"/>.</summary>
    /// <param name="failedWriteCountProvider">
    /// A delegate that returns the current cumulative event-log write-failure count.
    /// Typically wired as <c>() => sp.GetRequiredService&lt;ISiteEventLogger&gt;().FailedWriteCount</c>
    /// in the Host site composition root.
    /// </param>
    /// <param name="collector">The site health collector that receives the failure-count snapshot.</param>
    /// <param name="logger">Logger instance.</param>
    /// <param name="refreshInterval">Poll interval override; defaults to <see cref="DefaultRefreshInterval"/> (30 s).</param>
    public SiteEventLogFailureCountReporter(
        Func<long> failedWriteCountProvider,
        ISiteHealthCollector collector,
        ILogger<SiteEventLogFailureCountReporter> logger,
        TimeSpan? refreshInterval = null)
    {
        _failedWriteCountProvider = failedWriteCountProvider
            ?? throw new ArgumentNullException(nameof(failedWriteCountProvider));
        _collector = collector ?? throw new ArgumentNullException(nameof(collector));
        _logger = logger ?? throw new ArgumentNullException(nameof(logger));
        _refreshInterval = refreshInterval ?? DefaultRefreshInterval;
    }

    /// <summary>Starts the background polling loop, running an immediate first probe before entering the timed cycle.</summary>
    /// <param name="ct">Cancellation token signalling host shutdown.</param>
    /// <returns>A task that represents the asynchronous operation.</returns>
    public Task StartAsync(CancellationToken ct)
    {
        // Linked CTS lets StopAsync's cancellation AND the host's shutdown
        // token both terminate the loop; either side firing aborts the
        // pending Task.Delay.
        var cts = CancellationTokenSource.CreateLinkedTokenSource(ct);
        _cts = cts;

        // Read Token on the caller's thread, not inside the lambda: the lambda runs
        // whenever the thread pool gets to it, so a Dispose landing first would make
        // the deferred _cts.Token read throw and fault the loop task the host awaits.
        var token = cts.Token;
        _loop = Task.Run(() => RunLoopAsync(token), CancellationToken.None);
        return Task.CompletedTask;
    }

    private async Task RunLoopAsync(CancellationToken ct)
    {
        // First tick runs immediately so the very first health report after
        // process start carries a real failure-count snapshot — without this
        // the dashboard would show 0 for the first 30 s after a deploy even
        // if failures had already accumulated.
        SafeProbe();

        while (!ct.IsCancellationRequested)
        {
            try
            {
                await Task.Delay(_refreshInterval, ct).ConfigureAwait(false);
            }
            catch (OperationCanceledException)
            {
                break;
            }

            SafeProbe();
        }
    }

    private void SafeProbe()
    {
        try
        {
            var count = _failedWriteCountProvider();
            _collector.SetSiteEventLogWriteFailures(count);
        }
        catch (Exception ex)
        {
            // Catch-all is deliberate: the hosted service must survive every
            // class of probe failure so the next tick gets a chance. Mirrors
            // SiteAuditBacklogReporter's "exception logged, not propagated" contract.
            _logger.LogWarning(ex, "SiteEventLogFailureCountReporter probe failed; next tick will retry.");
        }
    }

    /// <summary>Signals the polling loop to stop and waits for it to complete.</summary>
    /// <param name="ct">Cancellation token (not used; the internal CTS governs shutdown).</param>
    /// <returns>A task that represents the asynchronous operation.</returns>
    public Task StopAsync(CancellationToken ct)
    {
        try
        {
            _cts?.Cancel();
        }
        catch (ObjectDisposedException)
        {
            // Stop-after-Dispose is a legal ordering; Dispose already cancelled the
            // loop. Letting this escape would abort the host's shutdown sequence.
        }

        return _loop ?? Task.CompletedTask;
    }

    /// <summary>Releases the internal <see cref="CancellationTokenSource"/> used to stop the polling loop.</summary>
    public void Dispose()
    {
        // Cancel before disposing so the loop is always signalled even when the host
        // disposes the container without having driven StopAsync first, and so the
        // loop's pending Task.Delay(interval, token) sees an already-cancelled token
        // rather than registering against a dead source.
        try
        {
            _cts?.Cancel();
        }
        catch (ObjectDisposedException)
        {
            // Already disposed — Dispose is idempotent.
        }

        _cts?.Dispose();
    }
}