lmxopcua/src/ZB.MOM.WW.OtOpcUa.Driver.S7/S7Driver.cs

using S7.Net;
using ZB.MOM.WW.OtOpcUa.Core.Abstractions;

namespace ZB.MOM.WW.OtOpcUa.Driver.S7;

/// <summary>
///     Siemens S7 native driver — speaks S7comm over ISO-on-TCP (port 102) via the S7netplus
///     library. First implementation of <see cref="IDriver"/> for an in-process .NET Standard
///     PLC protocol that is NOT Modbus, validating that the v2 driver-capability interfaces
///     generalize beyond Modbus + Galaxy.
/// </summary>
/// <remarks>
///     <para>
///         PR 62 ships the scaffold: <see cref="IDriver"/> only (Initialize / Reinitialize /
///         Shutdown / GetHealth). <see cref="ITagDiscovery"/>, <see cref="IReadable"/>,
///         <see cref="IWritable"/>, <see cref="ISubscribable"/>, <see cref="IHostConnectivityProbe"/>
///         land in PRs 63-65 once the address parser (PR 63) is in place.
///     </para>
///     <para>
///         <b>Single-connection policy</b>: S7netplus documented pattern is one
///         <c>Plc</c> instance per PLC, serialized with a <see cref="SemaphoreSlim"/>.
///         Parallelising reads against a single S7 CPU doesn't help — the CPU scans the
///         communication mailbox at most once per cycle (2-10 ms) and queues concurrent
///         requests wire-side anyway. Multiple client-side connections just waste the CPU's
///         8-64 connection-resource budget.
///     </para>
/// </remarks>
public sealed class S7Driver(S7DriverOptions options, string driverInstanceId)
    : IDriver, ITagDiscovery, IReadable, IWritable, ISubscribable, IHostConnectivityProbe, IDisposable, IAsyncDisposable
{
    // ---- ISubscribable + IHostConnectivityProbe state ----

    private readonly System.Collections.Concurrent.ConcurrentDictionary<long, SubscriptionState> _subscriptions = new();
    private long _nextSubscriptionId;
    private readonly object _probeLock = new();
    private HostState _hostState = HostState.Unknown;
    private DateTime _hostStateChangedUtc = DateTime.UtcNow;
    private CancellationTokenSource? _probeCts;

    public event EventHandler<DataChangeEventArgs>? OnDataChange;
    public event EventHandler<HostStatusChangedEventArgs>? OnHostStatusChanged;

    /// <summary>OPC UA StatusCode used when the tag name isn't in the driver's tag map.</summary>
    private const uint StatusBadNodeIdUnknown = 0x80340000u;
    /// <summary>OPC UA StatusCode used when the tag's data type isn't implemented yet.</summary>
    private const uint StatusBadNotSupported = 0x803D0000u;
    /// <summary>OPC UA StatusCode used when the tag is declared read-only.</summary>
    private const uint StatusBadNotWritable = 0x803B0000u;
    /// <summary>OPC UA StatusCode used when write fails validation (e.g. out-of-range value).</summary>
    private const uint StatusBadInternalError = 0x80020000u;
    /// <summary>OPC UA StatusCode used for socket / timeout / protocol-layer faults.</summary>
    private const uint StatusBadCommunicationError = 0x80050000u;
    /// <summary>OPC UA StatusCode used when S7 returns <c>ErrorCode.WrongCPU</c> / PUT/GET disabled.</summary>
    private const uint StatusBadDeviceFailure = 0x80550000u;

    private readonly Dictionary<string, S7TagDefinition> _tagsByName = new(StringComparer.OrdinalIgnoreCase);
    private readonly Dictionary<string, S7ParsedAddress> _parsedByName = new(StringComparer.OrdinalIgnoreCase);

    private readonly S7DriverOptions _options = options;
    private readonly SemaphoreSlim _gate = new(1, 1);

    /// <summary>
    ///     Per-connection gate. Internal so PRs 63-65 (read/write/subscribe) can serialize on
    ///     the same semaphore without exposing it publicly. Single-connection-per-PLC is a
    ///     hard requirement of S7netplus — see class remarks.
    /// </summary>
    internal SemaphoreSlim Gate => _gate;

    /// <summary>
    ///     Active S7.Net PLC connection. Null until <see cref="InitializeAsync"/> returns; null
    ///     after <see cref="ShutdownAsync"/>. Read-only outside this class; PR 64's Read/Write
    ///     will take the <see cref="_gate"/> before touching it.
    /// </summary>
    internal Plc? Plc { get; private set; }

    private DriverHealth _health = new(DriverState.Unknown, null, null);
    private bool _disposed;

    public string DriverInstanceId => driverInstanceId;
    public string DriverType => "S7";

    public async Task InitializeAsync(string driverConfigJson, CancellationToken cancellationToken)
    {
        _health = new DriverHealth(DriverState.Initializing, null, null);
        try
        {
            var plc = new Plc(_options.CpuType, _options.Host, _options.Rack, _options.Slot);
            // S7netplus writes timeouts into the underlying TcpClient via Plc.WriteTimeout /
            // Plc.ReadTimeout (milliseconds). Set before OpenAsync so the handshake itself
            // honours the bound.
            plc.WriteTimeout = (int)_options.Timeout.TotalMilliseconds;
            plc.ReadTimeout = (int)_options.Timeout.TotalMilliseconds;

            using var cts = CancellationTokenSource.CreateLinkedTokenSource(cancellationToken);
            cts.CancelAfter(_options.Timeout);
            await plc.OpenAsync(cts.Token).ConfigureAwait(false);

            Plc = plc;

            // Parse every tag's address once at init so config typos fail fast here instead
            // of surfacing as BadInternalError on every Read against the bad tag. The parser
            // also rejects bit-offset > 7, DB 0, unknown area letters, etc.
            _tagsByName.Clear();
            _parsedByName.Clear();
            foreach (var t in _options.Tags)
            {
                var parsed = S7AddressParser.Parse(t.Address); // throws FormatException
                _tagsByName[t.Name] = t;
                _parsedByName[t.Name] = parsed;
            }

            _health = new DriverHealth(DriverState.Healthy, DateTime.UtcNow, null);

            // Kick off the probe loop once the connection is up. Initial HostState stays
            // Unknown until the first probe tick succeeds — avoids broadcasting a premature
            // Running transition before any PDU round-trip has happened.
            if (_options.Probe.Enabled)
            {
                _probeCts = new CancellationTokenSource();
                _ = Task.Run(() => ProbeLoopAsync(_probeCts.Token), _probeCts.Token);
            }
        }
        catch (Exception ex)
        {
            // Clean up a partially-constructed Plc so a retry from the caller doesn't leak
            // the TcpClient. S7netplus's Close() is best-effort and idempotent.
            try { Plc?.Close(); } catch { }
            Plc = null;
            _health = new DriverHealth(DriverState.Faulted, null, ex.Message);
            throw;
        }
    }

    public async Task ReinitializeAsync(string driverConfigJson, CancellationToken cancellationToken)
    {
        await ShutdownAsync(cancellationToken).ConfigureAwait(false);
        await InitializeAsync(driverConfigJson, cancellationToken).ConfigureAwait(false);
    }

    public Task ShutdownAsync(CancellationToken cancellationToken)
    {
        try { _probeCts?.Cancel(); } catch { }
        _probeCts?.Dispose();
        _probeCts = null;

        foreach (var state in _subscriptions.Values)
        {
            try { state.Cts.Cancel(); } catch { }
            state.Cts.Dispose();
        }
        _subscriptions.Clear();

        try { Plc?.Close(); } catch { /* best-effort — tearing down anyway */ }
        Plc = null;
        _health = new DriverHealth(DriverState.Unknown, _health.LastSuccessfulRead, null);
        return Task.CompletedTask;
    }

    public DriverHealth GetHealth() => _health;

    /// <summary>
    ///     Approximate memory footprint. The Plc instance + one 240-960 byte PDU buffer is
    ///     under 4 KB; return 0 because the <see cref="IDriver"/> contract asks for a
    ///     driver-attributable growth number and S7.Net doesn't expose one.
    /// </summary>
    public long GetMemoryFootprint() => 0;

    public Task FlushOptionalCachesAsync(CancellationToken cancellationToken) => Task.CompletedTask;

    // ---- IReadable ----

    public async Task<IReadOnlyList<DataValueSnapshot>> ReadAsync(
        IReadOnlyList<string> fullReferences, CancellationToken cancellationToken)
    {
        var plc = RequirePlc();
        var now = DateTime.UtcNow;
        var results = new DataValueSnapshot[fullReferences.Count];

        await _gate.WaitAsync(cancellationToken).ConfigureAwait(false);
        try
        {
            for (var i = 0; i < fullReferences.Count; i++)
            {
                var name = fullReferences[i];
                if (!_tagsByName.TryGetValue(name, out var tag))
                {
                    results[i] = new DataValueSnapshot(null, StatusBadNodeIdUnknown, null, now);
                    continue;
                }
                try
                {
                    var value = await ReadOneAsync(plc, tag, cancellationToken).ConfigureAwait(false);
                    results[i] = new DataValueSnapshot(value, 0u, now, now);
                    _health = new DriverHealth(DriverState.Healthy, now, null);
                }
                catch (NotSupportedException)
                {
                    results[i] = new DataValueSnapshot(null, StatusBadNotSupported, null, now);
                }
                catch (global::S7.Net.PlcException pex)
                {
                    // S7.Net's PlcException carries an ErrorCode; PUT/GET-disabled on
                    // S7-1200/1500 surfaces here. Map to BadDeviceFailure so operators see a
                    // device-config problem (toggle PUT/GET in TIA Portal) rather than a
                    // transient fault — per driver-specs.md §5.
                    results[i] = new DataValueSnapshot(null, StatusBadDeviceFailure, null, now);
                    _health = new DriverHealth(DriverState.Degraded, _health.LastSuccessfulRead, pex.Message);
                }
                catch (Exception ex)
                {
                    results[i] = new DataValueSnapshot(null, StatusBadCommunicationError, null, now);
                    _health = new DriverHealth(DriverState.Degraded, _health.LastSuccessfulRead, ex.Message);
                }
            }
        }
        finally { _gate.Release(); }
        return results;
    }

    private async Task<object> ReadOneAsync(global::S7.Net.Plc plc, S7TagDefinition tag, CancellationToken ct)
    {
        var addr = _parsedByName[tag.Name];
        // S7.Net's string-based ReadAsync returns object where the boxed .NET type depends on
        // the size suffix: DBX=bool, DBB=byte, DBW=ushort, DBD=uint. Our S7DataType enum
        // specifies the SEMANTIC type (Int16 vs UInt16 vs Float32 etc.); the reinterpret below
        // converts the raw unsigned boxed value into the requested type without issuing an
        // extra PLC round-trip.
        var raw = await plc.ReadAsync(tag.Address, ct).ConfigureAwait(false)
            ?? throw new System.IO.InvalidDataException($"S7.Net returned null for '{tag.Address}'");

        return (tag.DataType, addr.Size, raw) switch
        {
            (S7DataType.Bool, S7Size.Bit, bool b) => b,
            (S7DataType.Byte, S7Size.Byte, byte by) => by,
            (S7DataType.UInt16, S7Size.Word, ushort u16) => u16,
            (S7DataType.Int16, S7Size.Word, ushort u16) => unchecked((short)u16),
            (S7DataType.UInt32, S7Size.DWord, uint u32) => u32,
            (S7DataType.Int32, S7Size.DWord, uint u32) => unchecked((int)u32),
            (S7DataType.Float32, S7Size.DWord, uint u32) => BitConverter.UInt32BitsToSingle(u32),

            (S7DataType.Int64, _, _)   => throw new NotSupportedException("S7 Int64 reads land in a follow-up PR"),
            (S7DataType.UInt64, _, _)  => throw new NotSupportedException("S7 UInt64 reads land in a follow-up PR"),
            (S7DataType.Float64, _, _) => throw new NotSupportedException("S7 Float64 (LReal) reads land in a follow-up PR"),
            (S7DataType.String, _, _)  => throw new NotSupportedException("S7 STRING reads land in a follow-up PR"),
            (S7DataType.DateTime, _, _) => throw new NotSupportedException("S7 DateTime reads land in a follow-up PR"),

            _ => throw new System.IO.InvalidDataException(
                $"S7 Read type-mismatch: tag '{tag.Name}' declared {tag.DataType} but address '{tag.Address}' " +
                $"parsed as Size={addr.Size}; S7.Net returned {raw.GetType().Name}"),
        };
    }

    // ---- IWritable ----

    public async Task<IReadOnlyList<WriteResult>> WriteAsync(
        IReadOnlyList<WriteRequest> writes, CancellationToken cancellationToken)
    {
        var plc = RequirePlc();
        var results = new WriteResult[writes.Count];

        await _gate.WaitAsync(cancellationToken).ConfigureAwait(false);
        try
        {
            for (var i = 0; i < writes.Count; i++)
            {
                var w = writes[i];
                if (!_tagsByName.TryGetValue(w.FullReference, out var tag))
                {
                    results[i] = new WriteResult(StatusBadNodeIdUnknown);
                    continue;
                }
                if (!tag.Writable)
                {
                    results[i] = new WriteResult(StatusBadNotWritable);
                    continue;
                }
                try
                {
                    await WriteOneAsync(plc, tag, w.Value, cancellationToken).ConfigureAwait(false);
                    results[i] = new WriteResult(0u);
                }
                catch (NotSupportedException)
                {
                    results[i] = new WriteResult(StatusBadNotSupported);
                }
                catch (global::S7.Net.PlcException)
                {
                    results[i] = new WriteResult(StatusBadDeviceFailure);
                }
                catch (Exception)
                {
                    results[i] = new WriteResult(StatusBadInternalError);
                }
            }
        }
        finally { _gate.Release(); }
        return results;
    }

    private async Task WriteOneAsync(global::S7.Net.Plc plc, S7TagDefinition tag, object? value, CancellationToken ct)
    {
        // S7.Net's Plc.WriteAsync(string address, object value) expects the boxed value to
        // match the address's size-suffix type: DBX=bool, DBB=byte, DBW=ushort, DBD=uint.
        // Our S7DataType lets the caller pass short/int/float; convert to the unsigned
        // wire representation before handing off.
        var boxed = tag.DataType switch
        {
            S7DataType.Bool    => (object)Convert.ToBoolean(value),
            S7DataType.Byte    => (object)Convert.ToByte(value),
            S7DataType.UInt16  => (object)Convert.ToUInt16(value),
            S7DataType.Int16   => (object)unchecked((ushort)Convert.ToInt16(value)),
            S7DataType.UInt32  => (object)Convert.ToUInt32(value),
            S7DataType.Int32   => (object)unchecked((uint)Convert.ToInt32(value)),
            S7DataType.Float32 => (object)BitConverter.SingleToUInt32Bits(Convert.ToSingle(value)),

            S7DataType.Int64   => throw new NotSupportedException("S7 Int64 writes land in a follow-up PR"),
            S7DataType.UInt64  => throw new NotSupportedException("S7 UInt64 writes land in a follow-up PR"),
            S7DataType.Float64 => throw new NotSupportedException("S7 Float64 (LReal) writes land in a follow-up PR"),
            S7DataType.String  => throw new NotSupportedException("S7 STRING writes land in a follow-up PR"),
            S7DataType.DateTime => throw new NotSupportedException("S7 DateTime writes land in a follow-up PR"),
            _ => throw new InvalidOperationException($"Unknown S7DataType {tag.DataType}"),
        };
        await plc.WriteAsync(tag.Address, boxed, ct).ConfigureAwait(false);
    }

    private global::S7.Net.Plc RequirePlc() =>
        Plc ?? throw new InvalidOperationException("S7Driver not initialized");

    // ---- ITagDiscovery ----

    public Task DiscoverAsync(IAddressSpaceBuilder builder, CancellationToken cancellationToken)
    {
        ArgumentNullException.ThrowIfNull(builder);
        var folder = builder.Folder("S7", "S7");
        foreach (var t in _options.Tags)
        {
            folder.Variable(t.Name, t.Name, new DriverAttributeInfo(
                FullName: t.Name,
                DriverDataType: MapDataType(t.DataType),
                IsArray: false,
                ArrayDim: null,
                SecurityClass: t.Writable ? SecurityClassification.Operate : SecurityClassification.ViewOnly,
                IsHistorized: false,
                IsAlarm: false,
                WriteIdempotent: t.WriteIdempotent));
        }
        return Task.CompletedTask;
    }

    private static DriverDataType MapDataType(S7DataType t) => t switch
    {
        S7DataType.Bool => DriverDataType.Boolean,
        S7DataType.Byte => DriverDataType.Int32,      // no 8-bit in DriverDataType yet
        S7DataType.Int16 or S7DataType.UInt16 or S7DataType.Int32 or S7DataType.UInt32 => DriverDataType.Int32,
        S7DataType.Int64 or S7DataType.UInt64 => DriverDataType.Int32, // widens; lossy for >2^31-1
        S7DataType.Float32 => DriverDataType.Float32,
        S7DataType.Float64 => DriverDataType.Float64,
        S7DataType.String => DriverDataType.String,
        S7DataType.DateTime => DriverDataType.DateTime,
        _ => DriverDataType.Int32,
    };

    // ---- ISubscribable (polling overlay) ----

    public Task<ISubscriptionHandle> SubscribeAsync(
        IReadOnlyList<string> fullReferences, TimeSpan publishingInterval, CancellationToken cancellationToken)
    {
        var id = Interlocked.Increment(ref _nextSubscriptionId);
        var cts = new CancellationTokenSource();
        // Floor at 100 ms — S7 CPUs scan 2-10 ms but the comms mailbox is processed at most
        // once per scan; sub-100 ms polling just queues wire-side with worse latency.
        var interval = publishingInterval < TimeSpan.FromMilliseconds(100)
            ? TimeSpan.FromMilliseconds(100)
            : publishingInterval;
        var handle = new S7SubscriptionHandle(id);
        var state = new SubscriptionState(handle, [.. fullReferences], interval, cts);
        _subscriptions[id] = state;
        _ = Task.Run(() => PollLoopAsync(state, cts.Token), cts.Token);
        return Task.FromResult<ISubscriptionHandle>(handle);
    }

    public Task UnsubscribeAsync(ISubscriptionHandle handle, CancellationToken cancellationToken)
    {
        if (handle is S7SubscriptionHandle h && _subscriptions.TryRemove(h.Id, out var state))
        {
            state.Cts.Cancel();
            state.Cts.Dispose();
        }
        return Task.CompletedTask;
    }

    private async Task PollLoopAsync(SubscriptionState state, CancellationToken ct)
    {
        // Initial-data push per OPC UA Part 4 convention.
        try { await PollOnceAsync(state, forceRaise: true, ct).ConfigureAwait(false); }
        catch (OperationCanceledException) { return; }
        catch { /* first-read error — polling continues */ }

        while (!ct.IsCancellationRequested)
        {
            try { await Task.Delay(state.Interval, ct).ConfigureAwait(false); }
            catch (OperationCanceledException) { return; }

            try { await PollOnceAsync(state, forceRaise: false, ct).ConfigureAwait(false); }
            catch (OperationCanceledException) { return; }
            catch { /* transient polling error — loop continues, health surface reflects it */ }
        }
    }

    private async Task PollOnceAsync(SubscriptionState state, bool forceRaise, CancellationToken ct)
    {
        var snapshots = await ReadAsync(state.TagReferences, ct).ConfigureAwait(false);
        for (var i = 0; i < state.TagReferences.Count; i++)
        {
            var tagRef = state.TagReferences[i];
            var current = snapshots[i];
            var lastSeen = state.LastValues.TryGetValue(tagRef, out var prev) ? prev : default;

            if (forceRaise || !Equals(lastSeen?.Value, current.Value) || lastSeen?.StatusCode != current.StatusCode)
            {
                state.LastValues[tagRef] = current;
                OnDataChange?.Invoke(this, new DataChangeEventArgs(state.Handle, tagRef, current));
            }
        }
    }

    private sealed record SubscriptionState(
        S7SubscriptionHandle Handle,
        IReadOnlyList<string> TagReferences,
        TimeSpan Interval,
        CancellationTokenSource Cts)
    {
        public System.Collections.Concurrent.ConcurrentDictionary<string, DataValueSnapshot> LastValues { get; }
            = new(StringComparer.OrdinalIgnoreCase);
    }

    private sealed record S7SubscriptionHandle(long Id) : ISubscriptionHandle
    {
        public string DiagnosticId => $"s7-sub-{Id}";
    }

    // ---- IHostConnectivityProbe ----

    /// <summary>
    ///     Host identifier surfaced in <see cref="GetHostStatuses"/>. <c>host:port</c> format
    ///     matches the Modbus driver's convention so the Admin UI dashboard renders both
    ///     family's rows uniformly.
    /// </summary>
    public string HostName => $"{_options.Host}:{_options.Port}";

    public IReadOnlyList<HostConnectivityStatus> GetHostStatuses()
    {
        lock (_probeLock)
            return [new HostConnectivityStatus(HostName, _hostState, _hostStateChangedUtc)];
    }

    private async Task ProbeLoopAsync(CancellationToken ct)
    {
        while (!ct.IsCancellationRequested)
        {
            var success = false;
            try
            {
                // Probe via S7.Net's low-cost GetCpuStatus — returns the CPU state (Run/Stop)
                // and is intentionally light on the comms mailbox. Single-word Plc.ReadAsync
                // would also work but GetCpuStatus doubles as a "PLC actually up" check.
                using var probeCts = CancellationTokenSource.CreateLinkedTokenSource(ct);
                probeCts.CancelAfter(_options.Probe.Timeout);

                var plc = Plc;
                if (plc is null) throw new InvalidOperationException("Plc dropped during probe");

                await _gate.WaitAsync(probeCts.Token).ConfigureAwait(false);
                try
                {
                    _ = await plc.ReadStatusAsync(probeCts.Token).ConfigureAwait(false);
                    success = true;
                }
                finally { _gate.Release(); }
            }
            catch (OperationCanceledException) when (ct.IsCancellationRequested) { return; }
            catch { /* transport/timeout/exception — treated as Stopped below */ }

            TransitionTo(success ? HostState.Running : HostState.Stopped);

            try { await Task.Delay(_options.Probe.Interval, ct).ConfigureAwait(false); }
            catch (OperationCanceledException) { return; }
        }
    }

    private void TransitionTo(HostState newState)
    {
        HostState old;
        lock (_probeLock)
        {
            old = _hostState;
            if (old == newState) return;
            _hostState = newState;
            _hostStateChangedUtc = DateTime.UtcNow;
        }
        OnHostStatusChanged?.Invoke(this, new HostStatusChangedEventArgs(HostName, old, newState));
    }

    public void Dispose() => DisposeAsync().AsTask().GetAwaiter().GetResult();

    public async ValueTask DisposeAsync()
    {
        if (_disposed) return;
        _disposed = true;
        try { await ShutdownAsync(CancellationToken.None).ConfigureAwait(false); }
        catch { /* disposal is best-effort */ }
        _gate.Dispose();
    }
}