using LiteDB;
namespace ZB.MOM.WW.OtOpcUa.Configuration.LocalCache;
///
/// LiteDB-backed . One file per node (default
/// config_cache.db), one collection per snapshot. Corruption surfaces as
/// on construction or read — callers should
/// delete and re-fetch from the central DB (decision #80).
///
public sealed class LiteDbConfigCache : ILocalConfigCache, IDisposable
{
private const string CollectionName = "generations";
private readonly LiteDatabase _db;
private readonly ILiteCollection _col;
// PutAsync is a find-then-insert/update; without serialization, two concurrent puts for the
// same (ClusterId, GenerationId) can both observe `existing is null` and both Insert,
// producing duplicate rows (Configuration-005). Serialize writes through this semaphore so
// the read-modify-write block is atomic for a given instance. LiteDB itself only locks the
// page-level write, not the find-then-insert window.
private readonly SemaphoreSlim _writeGate = new(initialCount: 1, maxCount: 1);
/// Initializes a new instance of the class.
/// Path to the LiteDB database file.
public LiteDbConfigCache(string dbPath)
{
// LiteDB can be tolerant of header-only corruption at construction time (it may overwrite
// the header and "recover"), so we force a write + read probe to fail fast on real corruption.
try
{
_db = new LiteDatabase(new ConnectionString { Filename = dbPath, Upgrade = true });
_col = _db.GetCollection(CollectionName);
_col.EnsureIndex(s => s.ClusterId);
_col.EnsureIndex(s => s.GenerationId);
_ = _col.Count();
}
catch (Exception ex) when (ex is LiteException or InvalidDataException or IOException
or NotSupportedException or UnauthorizedAccessException
or ArgumentOutOfRangeException or FormatException)
{
_db?.Dispose();
throw new LocalConfigCacheCorruptException(
$"LiteDB cache at '{dbPath}' is corrupt or unreadable — delete the file and refetch from the central DB.",
ex);
}
}
/// Gets the most recent snapshot for the specified cluster.
/// The cluster ID.
/// Cancellation token.
public Task GetMostRecentAsync(string clusterId, CancellationToken ct = default)
{
ct.ThrowIfCancellationRequested();
var snapshot = _col
.Find(s => s.ClusterId == clusterId)
.OrderByDescending(s => s.GenerationId)
.FirstOrDefault();
return Task.FromResult(snapshot);
}
/// Stores a snapshot in the cache.
/// The snapshot to store.
/// Cancellation token.
public async Task PutAsync(GenerationSnapshot snapshot, CancellationToken ct = default)
{
ct.ThrowIfCancellationRequested();
// Serialize the find-then-insert/update so concurrent callers do not observe a stale
// `existing is null` and both Insert (Configuration-005). LiteDB's per-call lock is
// not enough — the read and the write are independent calls.
await _writeGate.WaitAsync(ct).ConfigureAwait(false);
try
{
// upsert by (ClusterId, GenerationId) — replace in place if already cached
var existing = _col
.Find(s => s.ClusterId == snapshot.ClusterId && s.GenerationId == snapshot.GenerationId)
.FirstOrDefault();
if (existing is null)
_col.Insert(snapshot);
else
{
snapshot.Id = existing.Id;
_col.Update(snapshot);
}
}
finally
{
_writeGate.Release();
}
}
/// Removes old generation snapshots, keeping only the latest ones.
/// The cluster ID.
/// Number of latest generations to keep.
/// Cancellation token.
public Task PruneOldGenerationsAsync(string clusterId, int keepLatest = 10, CancellationToken ct = default)
{
ct.ThrowIfCancellationRequested();
var doomed = _col
.Find(s => s.ClusterId == clusterId)
.OrderByDescending(s => s.GenerationId)
.Skip(keepLatest)
.Select(s => s.Id)
.ToList();
foreach (var id in doomed)
_col.Delete(id);
return Task.CompletedTask;
}
/// Releases all resources used by the cache.
public void Dispose()
{
_writeGate.Dispose();
_db.Dispose();
}
}
public sealed class LocalConfigCacheCorruptException(string message, Exception inner)
: Exception(message, inner);