// RELU: Rectified Linear Unit
// Activation function that returns max(0, x)

using System.Runtime.CompilerServices;
using System.Runtime.Intrinsics;
using System.Runtime.Intrinsics.X86;

namespace QuanTAlib;

/// <summary>
/// RELU: Rectified Linear Unit
/// Applies max(0, x) transformation to input values.
/// </summary>
/// <remarks>
/// Key properties:
/// - Zero for negative inputs, passthrough for positive
/// - Commonly used as activation function in neural networks
/// - Computationally efficient: simple comparison
/// - Non-linear, allowing networks to learn complex patterns
/// </remarks>
[SkipLocalsInit]
public sealed class Relu : AbstractBase
{
    private record struct State(double LastValid);
    private State _state, _p_state;
    private readonly ITValuePublisher? _source;
    private readonly TValuePublishedHandler? _handler;
    private bool _disposed;

    public override bool IsHot => true;  // No warmup needed

    public Relu()
    {
        Name = "ReLU";
        WarmupPeriod = 0;
    }

    /// <summary>
    /// Initializes a new ReLU indicator chained to a source publisher.
    /// </summary>
    /// <param name="source">Source indicator for chaining</param>
    public Relu(ITValuePublisher source) : this()
    {
        _source = source;
        _handler = HandleUpdate;
        _source.Pub += _handler;
    }

    protected override void Dispose(bool disposing)
    {
        if (!_disposed)
        {
            if (disposing && _source != null && _handler != null)
            {
                _source.Pub -= _handler;
            }
            _disposed = true;
        }
        base.Dispose(disposing);
    }

    [MethodImpl(MethodImplOptions.AggressiveInlining)]
    private void HandleUpdate(object? sender, in TValueEventArgs e) => Update(e.Value, e.IsNew);

    [MethodImpl(MethodImplOptions.AggressiveInlining)]
    public override TValue Update(TValue input, bool isNew = true)
    {
        if (isNew)
        {
            _p_state = _state;
        }
        else
        {
            _state = _p_state;
        }

        double value = input.Value;
        double result;

        if (double.IsFinite(value))
        {
            result = Math.Max(0.0, value);
            _state = new State(result);
        }
        else
        {
            result = _state.LastValid;
        }

        Last = new TValue(input.Time, result);
        PubEvent(Last, isNew);
        return Last;
    }

    public override TSeries Update(TSeries source)
    {
        if (source.Count == 0)
        {
            return new TSeries([], []);
        }

        int len = source.Count;
        var t = new List<long>(len);
        var v = new List<double>(len);
        System.Runtime.InteropServices.CollectionsMarshal.SetCount(t, len);
        System.Runtime.InteropServices.CollectionsMarshal.SetCount(v, len);

        var tSpan = System.Runtime.InteropServices.CollectionsMarshal.AsSpan(t);
        var vSpan = System.Runtime.InteropServices.CollectionsMarshal.AsSpan(v);

        // Use vectorized Calculate for batch processing
        Batch(source.Values, vSpan);
        source.Times.CopyTo(tSpan);

        // Restore state from last value
        if (len > 0 && double.IsFinite(vSpan[len - 1]))
        {
            _state = new State(vSpan[len - 1]);
            _p_state = _state;
        }

        Last = new TValue(tSpan[len - 1], vSpan[len - 1]);
        return new TSeries(t, v);
    }

    public override void Prime(ReadOnlySpan<double> source, TimeSpan? step = null)
    {
        TimeSpan interval = step ?? TimeSpan.FromSeconds(1);
        DateTime time = DateTime.UtcNow - (interval * source.Length);

        for (int i = 0; i < source.Length; i++)
        {
            Update(new TValue(time, source[i]), true);
            time += interval;
        }
    }

    public static TSeries Batch(TSeries source)
    {
        var indicator = new Relu();
        return indicator.Update(source);
    }

    /// <summary>
    /// Calculates ReLU over a span of values with SIMD optimization.
    /// </summary>
    public static void Batch(ReadOnlySpan<double> source, Span<double> output)
    {
        if (source.Length == 0)
        {
            throw new ArgumentException("Source cannot be empty", nameof(source));
        }

        if (output.Length < source.Length)
        {
            throw new ArgumentException("Output length must be >= source length", nameof(output));
        }

        double lastValid = 0.0;
        int i = 0;

        // SIMD path for AVX2
        if (Avx2.IsSupported && source.Length >= Vector256<double>.Count)
        {
            Vector256<double> zero = Vector256<double>.Zero;
            int simdLength = source.Length - (source.Length % Vector256<double>.Count);

            for (; i < simdLength; i += Vector256<double>.Count)
            {
                Vector256<double> vec = Vector256.LoadUnsafe(ref System.Runtime.InteropServices.MemoryMarshal.GetReference(source.Slice(i)));

                // Create mask for finite values (NaN and Infinity comparisons return false)
                // A value is finite if it equals itself AND is not +/- infinity
                Vector256<double> isFiniteMask = Avx.And(
                    Avx.Compare(vec, vec, FloatComparisonMode.OrderedEqualNonSignaling),
                    Avx.And(
                        Avx.Compare(vec, Vector256.Create(double.PositiveInfinity), FloatComparisonMode.OrderedNotEqualNonSignaling),
                        Avx.Compare(vec, Vector256.Create(double.NegativeInfinity), FloatComparisonMode.OrderedNotEqualNonSignaling)
                    )
                );

                // ReLU: max(0, x) for finite values
                Vector256<double> relu = Avx.Max(zero, vec);

                // Blend: finite lanes get relu result, non-finite lanes get lastValid
                Vector256<double> lastValidVec = Vector256.Create(lastValid);
                Vector256<double> result = Avx.BlendVariable(lastValidVec, relu, isFiniteMask);

                result.StoreUnsafe(ref System.Runtime.InteropServices.MemoryMarshal.GetReference(output.Slice(i)));

                // Update lastValid from the last finite element in this vector
                for (int j = Vector256<double>.Count - 1; j >= 0; j--)
                {
                    double elem = vec.GetElement(j);
                    if (double.IsFinite(elem))
                    {
                        lastValid = result.GetElement(j);
                        break;
                    }
                }
            }
        }

        // Scalar fallback for remaining elements
        for (; i < source.Length; i++)
        {
            double val = source[i];
            if (double.IsFinite(val))
            {
                double result = Math.Max(0.0, val);
                lastValid = result;
                output[i] = result;
            }
            else
            {
                output[i] = lastValid;
            }
        }
    }

    public static (TSeries Results, Relu Indicator) Calculate(TSeries source)
    {
        var indicator = new Relu();
        TSeries results = indicator.Update(source);
        return (results, indicator);
    }

    public override void Reset()
    {
        _state = default;
        _p_state = default;
        Last = default;
    }
}