ScadaBridge/tests/ZB.MOM.WW.ScadaBridge.AuditLog.Tests/Site/SqliteAuditWriterBacklogStatsTests.cs

using Microsoft.Extensions.Logging.Abstractions;
using Microsoft.Extensions.Options;
using ZB.MOM.WW.ScadaBridge.AuditLog.Site;
using ZB.MOM.WW.ScadaBridge.AuditLog.Tests.TestSupport;
using ZB.MOM.WW.Audit;
using ZB.MOM.WW.ScadaBridge.Commons.Types.Audit;
using ZB.MOM.WW.ScadaBridge.Commons.Types.Enums;

namespace ZB.MOM.WW.ScadaBridge.AuditLog.Tests.Site;

/// <summary>
/// Bundle E (M6-T6) tests for <see cref="SqliteAuditWriter.GetBacklogStatsAsync"/>.
/// Exercises the health-metric surface that <c>SiteAuditBacklogReporter</c>
/// polls every 30 s and pushes onto the site health report as
/// <c>SiteAuditBacklog</c>.
/// </summary>
public class SqliteAuditWriterBacklogStatsTests : IDisposable
{
    private readonly string _dbPath;

    public SqliteAuditWriterBacklogStatsTests()
    {
        // OnDiskBytes assertions only make sense against a real file — the
        // shared-cache in-memory mode returns 0 for the file size, so this
        // suite is opinionated about file-backed storage. Tests in
        // SqliteAuditWriterWriteTests use in-memory for performance reasons.
        _dbPath = Path.Combine(Path.GetTempPath(),
            $"audit-backlog-stats-{Guid.NewGuid():N}.db");
    }

    public void Dispose()
    {
        if (File.Exists(_dbPath))
        {
            try { File.Delete(_dbPath); } catch { /* test cleanup best-effort */ }
        }
    }

    private SqliteAuditWriter CreateWriter()
    {
        var options = new SqliteAuditWriterOptions { DatabasePath = _dbPath };
        return new SqliteAuditWriter(
            Options.Create(options),
            NullLogger<SqliteAuditWriter>.Instance,
            new FakeNodeIdentityProvider());
    }

    private static AuditEvent NewEvent(DateTime? occurredAtUtc = null) => ScadaBridgeAuditEventFactory.Create(
        eventId: Guid.NewGuid(),
        occurredAtUtc: occurredAtUtc ?? DateTime.UtcNow,
        channel: AuditChannel.ApiOutbound,
        kind: AuditKind.ApiCall,
        status: AuditStatus.Delivered);

    [Fact]
    public async Task EmptyDb_Returns_Zero_Null_AndZeroBytes()
    {
        // No file exists yet — the writer ctor creates one but no rows are
        // inserted; the snapshot should report a clean queue. OnDiskBytes is
        // allowed to be zero (fresh ftruncate) OR small (page header) — the
        // contract only requires non-negative; we assert >= 0 and exercise
        // the pending fields strictly.
        await using var writer = CreateWriter();

        var snapshot = await writer.GetBacklogStatsAsync();

        Assert.Equal(0, snapshot.PendingCount);
        Assert.Null(snapshot.OldestPendingUtc);
        Assert.True(snapshot.OnDiskBytes >= 0,
            $"OnDiskBytes must be non-negative, got {snapshot.OnDiskBytes}");
    }

    [Fact]
    public async Task Pending_5_Returns_5()
    {
        await using var writer = CreateWriter();

        for (var i = 0; i < 5; i++)
        {
            await writer.WriteAsync(NewEvent());
        }

        var snapshot = await writer.GetBacklogStatsAsync();

        Assert.Equal(5, snapshot.PendingCount);
    }

    [Fact]
    public async Task OldestPending_Is_Earliest_OccurredAtUtc()
    {
        await using var writer = CreateWriter();

        var t1 = new DateTime(2026, 5, 20, 10, 0, 0, DateTimeKind.Utc);
        var t2 = new DateTime(2026, 5, 20, 10, 1, 0, DateTimeKind.Utc);
        var t3 = new DateTime(2026, 5, 20, 10, 2, 0, DateTimeKind.Utc);

        // Insert out of order so the snapshot is not "the last write" by
        // accident — the OldestPendingUtc must come from a column-min, not
        // an insertion-order proxy.
        await writer.WriteAsync(NewEvent(t2));
        await writer.WriteAsync(NewEvent(t1));
        await writer.WriteAsync(NewEvent(t3));

        var snapshot = await writer.GetBacklogStatsAsync();

        Assert.Equal(3, snapshot.PendingCount);
        Assert.NotNull(snapshot.OldestPendingUtc);
        // The DB round-trips OccurredAtUtc through the "o" format which
        // preserves Kind=Utc — assert tick-equality.
        Assert.Equal(t1, snapshot.OldestPendingUtc!.Value);
    }

    [Fact]
    public async Task GetBacklogStatsAsync_DoesNotBlockOnConcurrentWriteLoad()
    {
        // AuditLog-005: GetBacklogStatsAsync previously took _writeLock, the
        // same lock that serialises every batch INSERT in FlushBatch. Under a
        // backlog growing to hundreds of thousands of rows a COUNT(*)+MIN
        // index scan could park the hot-path writer for hundreds of ms. The
        // fix adds a dedicated read-only connection in WAL mode so the probe
        // never contends with the writer.
        //
        // This test demonstrates the lock decoupling by saturating the writer
        // with a burst of concurrent writes and asserting that a probe issued
        // while those writes are in flight returns inside a tight time bound.
        // Without the fix the probe would be queued behind FlushBatch under
        // the same _writeLock; with the fix it reads through _readConnection
        // and is not gated by the writer.
        await using var writer = CreateWriter();

        // Seed a baseline so MIN(OccurredAtUtc) has a row to find — the
        // important assertion is timing, but a non-empty result also confirms
        // the read connection sees the writer's commits via WAL.
        for (var i = 0; i < 100; i++)
        {
            await writer.WriteAsync(NewEvent());
        }

        // Kick off a sustained write burst on a background task. The writes
        // are fire-and-forget — we only need the writer to be busy enough
        // that any reuse of _writeLock by the probe would be observable.
        var burst = Task.Run(async () =>
        {
            for (var i = 0; i < 2_000; i++)
            {
                await writer.WriteAsync(NewEvent()).ConfigureAwait(false);
            }
        });

        // Race the probe against the write burst. The probe must return
        // promptly even though the writer is actively flushing batches.
        var sw = System.Diagnostics.Stopwatch.StartNew();
        var snapshot = await writer.GetBacklogStatsAsync();
        sw.Stop();

        // Drain the burst before disposing so we don't observe a flake when
        // pending writes race with dispose.
        await burst;

        Assert.True(sw.ElapsedMilliseconds < 1_000,
            $"GetBacklogStatsAsync must not block on the writer's _writeLock; took {sw.ElapsedMilliseconds} ms");
        Assert.True(snapshot.PendingCount >= 100,
            $"backlog probe should see at least the seeded rows; got {snapshot.PendingCount}");
    }

    [Fact]
    public async Task OnDiskBytes_ReturnsFileSize()
    {
        await using var writer = CreateWriter();

        // Insert enough rows to grow the file past the empty schema baseline.
        for (var i = 0; i < 100; i++)
        {
            await writer.WriteAsync(NewEvent());
        }

        var snapshot = await writer.GetBacklogStatsAsync();

        // The exact size depends on SQLite page allocation, but a file-backed
        // db with 100 inserted rows MUST be larger than the empty schema
        // (a few pages, ~4 KB). The implementation should return the
        // FileInfo.Length value verbatim.
        Assert.True(File.Exists(_dbPath), $"DB file should exist at {_dbPath}");
        var expected = new FileInfo(_dbPath).Length;
        Assert.Equal(expected, snapshot.OnDiskBytes);
        Assert.True(snapshot.OnDiskBytes > 0,
            $"after 100 inserts OnDiskBytes must be > 0, got {snapshot.OnDiskBytes}");
    }
}