using System;
using System.Collections.Generic;
using UnityEngine;
using UnityEditor;
#if UNITY_MATHEMATICS
using Unity.Mathematics;
using static Unity.Mathematics.math;
#endif

namespace NanoBrain {

    /// <summary>
    /// A neuron is a basic Nucleus
    /// </summary>
    [Serializable]
    public class Neuron : Nucleus {

        /// <summary>
        /// Create a new Neuron in a Cluster instance
        /// </summary>
        /// <param name="parent">The parent cluster in which the new Neuron should be created</param>
        /// <param name="name">The name of the new Neuron</param>
        public Neuron(Cluster parent, string name) {
            this.parent = parent;
            this.name = name;
            this.parent?.nuclei.Add(this);
        }
        /// <summary>
        /// Create a new Neuron in a Cluster Prefab
        /// </summary>
        /// <param name="prefab">The Cluster Preafb in which the new Neuron should be created</param>
        /// <param name="name">The name of the new Neuron</param>
        // public Neuron(ClusterPrefab prefab, string name) {
        //     this.clusterPrefab = prefab;
        //     this.name = name;
        //     if (this.clusterPrefab != null) {
        //         this.clusterPrefab.cluster.nuclei.Add(this);
        //         this.clusterPrefab.cluster.RefreshOutputs();
        //     }
        //     else
        //         Debug.LogError("No prefab when adding neuron to prefab");
        // }

        #region Serialization

        /// <summary>
        /// The bias
        /// </summary>
        /// The bias which a value which is always added to the combined value of the neuron
        /// It does not have a synapse and therefore no weight of source nucleus
        public Vector3 bias = Vector3.zero;

        #region Synapses

        [SerializeField]
        private List<Synapse> _synapses = new();
        /// <summary>
        /// The synapses of the nucleus
        /// </summary>
        public List<Synapse> synapses => _synapses;

        /// <summary>
        /// Add a new synapse to this nuclues
        /// </summary>
        /// <param name="sendingNucleus">The nucleus from which the signals may originate</param>
        /// <param name="weight">The weight applied to the input. Default value = 1</param>
        /// <returns>The created Synapse</returns>
        /// This will add a new input to this nucleus with the given weight.
        public Synapse AddSynapse(Neuron sendingNucleus, float weight = 1) {
            Synapse synapse = new(sendingNucleus, weight);
            this.synapses.Add(synapse);
            return synapse;
        }

        // public Synapse AddSynapse(ClusterPrefab clusterPrefab, string neuronName, float weight = 1) {

        //     }

        /// <summary>
        /// Find a synapse
        /// </summary>
        /// <param name="sender">The sender of the input to the Synapse</param>
        /// <returns>The found Synapse or null when the sender has no synapse to this nucleus.</returns>
        public Synapse GetSynapse(Nucleus sender) {
            foreach (Synapse synapse in this.synapses)
                if (synapse.neuron == sender)
                    return synapse;
            return null;
        }

        /// <summary>
        /// Remove a synapse from a Nucleus
        /// </summary>
        /// <param name="sendingNucleus">Remote the synapse connecting to this Nucleus</param>
        public void RemoveSynapse(Nucleus sendingNucleus) {
            this.synapses.RemoveAll(synapse => synapse.neuron == sendingNucleus);
        }

        #endregion Synapses

        /// <summary>
        /// Set the bias, recalculate the output and update all Nuclei receiving from this Nucleus
        /// </summary>
        /// <param name="inputValue"></param>
        public virtual void SetBias(Vector3 inputValue) {
            this.bias = inputValue;
            this.lastUpdate = Time.time;
            this.parent?.UpdateFromNucleus(this);
        }

        /// <summary>
        /// The type of combinators
        /// </summary>
        /// A combinator combines the weighted values of the synapses to a single value
        public enum CombinatorType {
            /// Add the weighted values together
            Sum,
            /// Multiply the weighted values
            Product,
        }
        /// <summary>
        /// The type of combinator used for this Neuron
        /// </summary>
        public CombinatorType combinator = CombinatorType.Sum;

        /// <summary>
        /// The type of 
        /// </summary>
        public enum ActivationType {
            Linear,
            Power,
            Sqrt,
            Reciprocal,
            Tanh,
            Binary,
            Normalized,
            Custom
        }
        /// <summary>
        /// The activation function
        /// </summary>
        [SerializeField]
        public ActivationType _activator;
        /// <summary>
        /// The activation funtion
        /// </summary>
        public ActivationType activator {
            get { return _activator; }
            set {
                _activator = value;
                this.curve = GenerateCurve();
            }
        }
        /// <summary>
        /// The curve representing the activation function
        /// </summary>
        public AnimationCurve curve;
        /// <summary>
        /// The maximum value of the curve
        /// </summary>
        public float curveMax = 1.0f;

        /// <summary>
        /// Generate the curve for the current activation function
        /// </summary>
        /// <returns>The curve </returns>
        public AnimationCurve GenerateCurve() {
            switch (this.activator) {
                case ActivationType.Linear:
                    this.curveMax = 1;
                    return Presets.Linear(1);
                case ActivationType.Power:
                    this.curveMax = 1;
                    return Presets.Power(2.0f, 1);
                case ActivationType.Sqrt:
                    this.curveMax = 1;
                    return Presets.Power(0.5f, 1);
                case ActivationType.Reciprocal:
                    this.curveMax = 1 / 0.01f * 1;
                    return Presets.Reciprocal(1);
                case ActivationType.Tanh:
                    this.curveMax = 1;
                    return Presets.Tanh(1);
                case ActivationType.Binary:
                    this.curveMax = 1;
                    return Presets.Binary();
                case ActivationType.Normalized:
                    this.curveMax = 1;
                    return Presets.Binary();
                default:
                    this.curveMax = 1;
                    return this.curve;
            }
        }

        /// <summary>
        /// The curve presets for the activation functions
        /// </summary>
        public static class Presets {
            /// <summary>
            /// The number of samples in the curve
            /// </summary>
            private const int samples = 32;
            /// <summary>
            /// Generate a curve for the linear activation function
            /// </summary>
            /// <param name="weight">The maximum value for the function</param>
            /// <returns>The curve preset</returns>
            public static AnimationCurve Linear(float weight) {
                return AnimationCurve.Linear(0f, 0f, 1000f, weight * 1000);
            }
            /// <summary>
            /// Generate a curve for the power activation function
            /// </summary>
            /// <param name="exponent">The exponent of the power function</param>
            /// <param name="weight">The maximum value for the function</param>
            /// <returns>The curve preset</returns>
            public static AnimationCurve Power(float exponent, float weight) {
                // build keyframes
                Keyframe[] keys = new Keyframe[samples];
                for (int i = 0; i < samples; i++) {
                    float t = i / (float)(samples - 1);
                    float v = Mathf.Pow(t, exponent) * weight;
                    keys[i] = new Keyframe(t, v);
                }

                AnimationCurve curve = new(keys);

                // set tangent modes for each key to Auto (smooth). Use Linear if you prefer straight segments.
                for (int i = 0; i < curve.length; i++) {
                    AnimationUtility.SetKeyLeftTangentMode(curve, i, AnimationUtility.TangentMode.Auto);
                    AnimationUtility.SetKeyRightTangentMode(curve, i, AnimationUtility.TangentMode.Auto);
                }

                return curve;
            }
            /// <summary>
            /// Generate a curve for the reciprocal activation function
            /// </summary>
            /// <param name="weight">The maximum value for the function</param>
            /// <returns>The curve preset</returns>
            public static AnimationCurve Reciprocal(float weight) {
                int samples = 128;
                float xMin = 0.001f;
                float xMax = 1;
                var keys = new Keyframe[samples];
                for (int i = 0; i < samples; i++) {
                    float t = i / (float)(samples - 1);
                    float x = Mathf.Lerp(xMin, xMax, t);
                    float y = 1f / x * weight;
                    keys[i] = new Keyframe(x, y);
                }
                var curve = new AnimationCurve(keys);
                for (int i = 0; i < curve.length; i++) {
                    AnimationUtility.SetKeyLeftTangentMode(curve, i, AnimationUtility.TangentMode.Linear);
                    AnimationUtility.SetKeyRightTangentMode(curve, i, AnimationUtility.TangentMode.Linear);
                }
                return curve;
            }
            /// <summary>
            /// Generate a curve for the tanh activation function
            /// </summary>
            /// <param name="weight">The maximum value for the function</param>
            /// <returns>The curve preset</returns>
            public static AnimationCurve Tanh(float weight) {
                //int samples = 128;
                float xMin = 0.001f;
                float xMax = 1;
                var keys = new Keyframe[samples];
                for (int i = 0; i < samples; i++) {
                    float t = i / (float)(samples - 1);
                    float x = Mathf.Lerp(xMin, xMax, t);
                    float y = MathF.Tanh(x * weight);
                    keys[i] = new Keyframe(x, y);
                }
                var curve = new AnimationCurve(keys);
                for (int i = 0; i < curve.length; i++) {
                    AnimationUtility.SetKeyLeftTangentMode(curve, i, AnimationUtility.TangentMode.Linear);
                    AnimationUtility.SetKeyRightTangentMode(curve, i, AnimationUtility.TangentMode.Linear);
                }
                return curve;

            }
            /// <summary>
            /// Generate a curve for the binary activation function
            /// </summary>
            /// <returns>The curve preset</returns>
            public static AnimationCurve Binary() {
                return AnimationCurve.Linear(0, 0, 1, 1);
            }
        }

        #endregion Serialization

#if UNITY_MATHEMATICS

        /// <summary>
        /// The output value of the neuron
        /// </summary>
        protected float3 _outputValue;
        /// <summary>
        /// The output value of the neuron
        /// </summary>
        public virtual float3 outputValue {
            get { return _outputValue; }
            set {
                _outputValue = value;
                if (this.isFiring)
                    WhenFiring?.Invoke();
            }
        }
        /// <summary>
        /// The magnitude of the neuron output
        /// </summary>
        public float outputMagnitude => length(_outputValue);
        /// <summary>
        /// The squared magnitude of the neuron output
        /// </summary>
        public float outputSqrMagnitude => lengthsq(_outputValue);

#else

        /// <summary>
        /// The output value of the neuron
        /// </summary>
        protected Vector3 _outputValue;
        /// <summary>
        /// The output value of the neuron
        /// </summary>
        public virtual Vector3 outputValue {
            get { return _outputValue; }
            set {
                _outputValue = value;
                if (this.isFiring)
                    WhenFiring?.Invoke();
            }
        }
        /// <summary>
        /// The magnitude of the neuron output
        /// </summary>
        public float outputMagnitude => _outputValue.magnitude;    
        /// <summary>
        /// The squared magnitude of the neuron output
        /// </summary>
        public float outputSqrMagnitude => _outputValue.sqrMagnitude;

#endif
        /// <summary>
        /// True if the neuron have a positive value with magnitude > 0.5
        /// </summary>
        public bool isFiring => this.outputMagnitude > 0.5f;
        /// <summary>
        /// An action which is called every time the neuron is updated and is firing
        /// </summary>
        public Action WhenFiring;

        /// <summary>
        /// When true, the value will not be reset after timeToSleep.
        /// </summary>
        public bool persistOutput = false;
        /// <summary>
        /// True when the neuron is not persisting and has not be updated for timeToSleep seconds
        /// </summary>
        public virtual bool isSleeping => !persistOutput && (Time.time - this.lastUpdate > this.timeToSleep);
        /// <summary>
        /// Check if the neuron is sleeping.
        /// </summary>
        /// This will reset the output value if it is sleeping
        public void SleepCheck() {
            if (this.isSleeping) {
#if UNITY_MATHEMATICS
                this._outputValue = new float3(0, 0, 0);
#else
                this._outputValue = new Vector3(0,0,0);
#endif
            }
        }

        /// <summary>
        /// The time at which the last update has been done
        /// </summary>
        public float lastUpdate = 0;
        /// <summary>
        /// Time in seconds after the last update the neuron can go to sleep
        /// </summary>
        public readonly float timeToSleep = 1f;

        /// \copydoc NanoBrain::Nucleus::ShallowCloneTo
        public override Nucleus ShallowCloneTo(Cluster parent) {
            Neuron clone = new(parent, this.name) {
                // prefabNucleus = this
            };
            CloneFields(clone);
            return clone;
        }

        // \copydoc NanoBrain::Nucleus::Clone
        // public override Nucleus Clone(ClusterPrefab prefab) {
        //     Neuron clone = new(prefab.cluster, this.name);
        //     CloneFields(clone);
        //     foreach (Synapse synapse in this.synapses) {
        //         Synapse clonedSynapse = clone.AddSynapse(synapse.neuron);
        //         clonedSynapse.weight = synapse.weight;
        //     }
        //     foreach (Nucleus receiver in this.receivers) {
        //         clone.AddReceiver(receiver);
        //     }
        //     return clone;
        // }

        /// <summary>
        /// Copy relevant fields of this neuron to the given neuron
        /// </summary>
        /// <param name="clone"></param>
        protected virtual void CloneFields(Neuron clone) {
            clone.bias = this.bias;
            clone.persistOutput = this.persistOutput;
            clone.combinator = this.combinator;
            clone.curve = this.curve;
            clone.activator = this.activator;
            clone.curveMax = this.curveMax;
        }

        /// <summary>
        /// Delete the give neuron
        /// </summary>
        /// <param name="nucleus">The neuron to delete</param>
        public static void Delete(Nucleus nucleus) {
            if (nucleus == null)
                return;
            if (nucleus is Neuron neuron) {
                foreach (Synapse synapse in neuron.synapses) {
                    if (synapse.neuron is Neuron synapse_nucleus) {
                        if (synapse_nucleus.receivers.Count > 1) {
                            // there is another nucleus feeding into this input nucleus
                            synapse_nucleus.receivers.RemoveAll(r => r == nucleus);
                        }
                        else {
                            // No other links, delete it.
                            Neuron.Delete(synapse_nucleus);
                        }
                    }
                }
                foreach (Nucleus receiver in neuron.receivers) {
                    if (receiver is not Neuron receiverNeuron)
                        continue;
                    if (receiver != null && receiverNeuron.synapses != null)
                        receiverNeuron.synapses.RemoveAll(s => s.neuron == nucleus);
                }
            }
            else if (nucleus is Cluster cluster) {
                // remove all receivers for this cluster
                foreach (Nucleus clusterNucleus in cluster.nuclei) {
                    if (clusterNucleus is Neuron output) {
                        foreach (Nucleus receiver in output.receivers) {
                            if (receiver is not Neuron receiverNeuron)
                                continue;
                            receiverNeuron.synapses.RemoveAll(s => s.neuron == output);
                        }
                    }
                }
            }

            if (nucleus.parent.prefab != null) {
                nucleus.parent.nuclei.RemoveAll(n => n == nucleus);
                nucleus.parent.RefreshOutputs();
            }
        }

        /// \copydoc NanoBrain::Nucleus::UpdateStateIsolated
        public override void UpdateStateIsolated() {
            var result = Combinator();
            this.outputValue = ApplyActivator(result);
            this.lastUpdate = Time.time;
        }

        // protected void CheckSleepingSynapses() {
        //     foreach (Synapse synapse in this.synapses)
        //         synapse.neuron.SleepCheck();
        // }

        #region Combinator

#if UNITY_MATHEMATICS

        /// <summary>
        /// The combinator which combines the values from all synapses
        /// </summary>
        protected Func<float3> Combinator => combinator switch {
            CombinatorType.Sum => CombinatorSum,
            CombinatorType.Product => CombinatorProduct,
            _ => CombinatorSum
        };

        /// <summary>
        /// Sum the synapse outputs together
        /// </summary>
        /// <returns>The sum of the synapse outputs</returns>
        public float3 CombinatorSum() {
            float3 sum = this.bias;
            foreach (Synapse synapse in this.synapses) {
                synapse.neuron.SleepCheck();
                sum += synapse.weight * synapse.neuron.outputValue;
            }
            return sum;
        }

        /// <summary>
        /// Multiply the synapse outputs together
        /// </summary>
        /// <returns>The mutliplcation of the synapse outputs</returns>
        public float3 CombinatorProduct() {
            float3 product = this.bias;
            foreach (Synapse synapse in this.synapses) {
                synapse.neuron.SleepCheck();
                product *= synapse.weight * synapse.neuron.outputValue;
            }
            return product;
        }

#else

        /// <summary>
        /// The combinator which combines the values from all synapses
        /// </summary>
        protected Func<Vector3> Combinator => combinator switch {
            CombinatorType.Sum => CombinatorSum,
            CombinatorType.Product => CombinatorProduct,
            _ => CombinatorSum
        };

        /// <summary>
        /// Sum the synapse outputs together
        /// </summary>
        /// <returns>The sum of the synapse outputs</returns>
        public Vector3 CombinatorSum() {
            Vector3 sum = this.bias;
            foreach (Synapse synapse in this.synapses)
                sum += synapse.weight * synapse.neuron.outputValue;
            return sum;
        }

        /// <summary>
        /// Multiply the synapse outputs together
        /// </summary>
        /// <returns>The mutliplcation of the synapse outputs</returns>
        public Vector3 CombinatorProduct() {
            Vector3 product = this.bias;
            foreach (Synapse synapse in this.synapses) {
                //product *= synapse.weight * synapse.neuron.outputValue;
                product = Vector3.Scale(product, synapse.weight * synapse.neuron.outputValue);
            }
            return product;
        }

#endif
        #endregion Combinator

        #region Activator

#if UNITY_MATHEMATICS

        /// <summary>
        /// Apply the activation function to the input
        /// </summary>
        /// <param name="inputValue"></param>
        /// <returns>The result of applying the activation function</returns>
        // This does not allocate memory and seems faster than a switch expression
        float3 ApplyActivator(float3 inputValue) {
            switch (activator) {
                case ActivationType.Linear: return ActivatorLinear(inputValue);
                case ActivationType.Sqrt: return ActivatorSqrt(inputValue);
                case ActivationType.Power: return ActivatorPower(inputValue);
                case ActivationType.Reciprocal: return ActivatorReciprocal(inputValue);
                case ActivationType.Tanh: return ActivatorTanh(inputValue);
                case ActivationType.Binary: return ActivatorBinary(inputValue);
                case ActivationType.Normalized: return ActivatorNormalized(inputValue);
                default: return ActivatorLinear(inputValue);
            }
        }

        /// <summary>
        /// Linear activation function
        /// </summary>
        /// <param name="input">Input value</param>
        /// <returns>The unchanged value</returns>
        protected float3 ActivatorLinear(float3 input) {
            return input;
        }

        /// <summary>
        /// Square root activation function
        /// </summary>
        /// <param name="input">Input value</param>
        /// <returns>The square root of the input</returns>
        protected float3 ActivatorSqrt(float3 input) {
            float3 result = normalize(input) * MathF.Sqrt(length(input));
            return result;
        }

        /// <summary>
        /// Power activation function
        /// </summary>
        /// <param name="input">Input value</param>
        /// <returns>The input to the power of 2</returns>
        protected float3 ActivatorPower(float3 input) {
            float3 result = normalize(input) * MathF.Pow(length(input), 2);
            return result;
        }

        /// <summary>
        /// Reciprocal activation function
        /// </summary>
        /// <param name="input">Input value</param>
        /// <returns>1/input value</returns>
        protected float3 ActivatorReciprocal(float3 input) {
            float magnitude = length(input);
            if (magnitude == 0)
                return new float3(0, 0, 0);

            float3 result = normalize(input) * (1 / magnitude);
            return result;
        }

        /// <summary>
        /// Tanh activation function
        /// </summary>
        /// <param name="input">Input value</param>
        /// <returns>Tanh(input value)</returns>
        protected float3 ActivatorTanh(float3 input) {
            float magnitude = length(input);
            float3 result = normalize(input) * MathF.Tanh(magnitude);
            return result;
        }
        /// <summary>
        /// Binary activation function
        /// </summary>
        /// <param name="input">Input value</param>
        /// <returns>An uniform vector with magnitude between 0 and 1</returns>
        protected float3 ActivatorBinary(float3 input) {
            float magnitude = length(input);
            float value = Mathf.Clamp01(magnitude);
            return float3(value, value, value);
        }

        /// <summary>
        /// Normalize activation function
        /// </summary>
        /// <param name="input">Input value</param>
        /// <returns>The normalized vector</returns>
        protected float3 ActivatorNormalized(float3 input) {
            if (lengthsq(input) == 0)
                return input;
            float3 result = normalize(input);
            return result;
        }

#else

        /// <summary>
        /// Apply the activation function to the input
        /// </summary>
        /// <param name="inputValue"></param>
        /// <returns>The result of applying the activation function</returns>
        // This does not allocate memory and seems faster than a switch expression
        Vector3 ApplyActivator(Vector3 inputValue) {
            switch (activator) {
                case ActivationType.Linear: return ActivatorLinear(inputValue);
                case ActivationType.Sqrt: return ActivatorSqrt(inputValue);
                case ActivationType.Power: return ActivatorPower(inputValue);
                case ActivationType.Reciprocal: return ActivatorReciprocal(inputValue);
                case ActivationType.Tanh: return ActivatorTanh(inputValue);
                case ActivationType.Binary: return ActivatorBinary(inputValue);
                case ActivationType.Normalized: return ActivatorNormalized(inputValue);
                default: return ActivatorLinear(inputValue);
            }
        }

        /// <summary>
        /// Linear activation function
        /// </summary>
        /// <param name="input">Input value</param>
        /// <returns>The unchanged value</returns>
        protected Vector3 ActivatorLinear(Vector3 input) {
            return input;
        }

        /// <summary>
        /// Square root activation function
        /// </summary>
        /// <param name="input">Input value</param>
        /// <returns>The square root of the input</returns>
        protected Vector3 ActivatorSqrt(Vector3 input) {
            Vector3 result = input.normalized * System.MathF.Sqrt(input.magnitude);
            return result;
        }

        /// <summary>
        /// Power activation function
        /// </summary>
        /// <param name="input">Input value</param>
        /// <returns>The input to the power of 2</returns>
        protected Vector3 ActivatorPower(Vector3 input) {
            Vector3 result = input.normalized * System.MathF.Pow(input.magnitude, 2);
            return result;
        }

        /// <summary>
        /// Reciprocal activation function
        /// </summary>
        /// <param name="input">Input value</param>
        /// <returns>1/input value</returns>
        protected Vector3 ActivatorReciprocal(Vector3 input) {
            float magnitude = input.magnitude;
            if (magnitude == 0)
                return new Vector3(0, 0, 0);

            Vector3 result = input.normalized * (1 / magnitude);
            return result;
        }

#endif

        #endregion Activator

        #region Receivers

        /// <summary>
        /// The nuclei which have a synapse to this neuron
        /// </summary>
        [SerializeReference]
        private List<Nucleus> _receivers = new();
        /// <summary>
        /// The nuclei which have a synapse to this neuron
        /// </summary>
        public virtual List<Nucleus> receivers {
            get { return _receivers; }
            set { _receivers = value; }
        }

        /// <summary>
        /// Add a new receiver to this neuron
        /// </summary>
        /// <param name="receiverToAdd">The receiver to add</param>
        /// <param name="weight">The weight to use for the synapse to his neuron</param>
        public virtual void AddReceiver(Nucleus receiverToAdd, float weight = 1) {
            if (receiverToAdd is not Neuron receiverNeuron)
                return;
            this._receivers.Add(receiverNeuron);
            receiverNeuron.AddSynapse(this, weight);
            //Debug.Log($"Add synapse {this.clusterPrefab.name}.{this.name} -> {receiverToAdd.name} --- [{this.receivers.Count}]");

        }

        /// <summary>
        /// Remove a receiver to this neuron
        /// </summary>
        /// <param name="receiverToRemove">The receiver to remove</param>
        public virtual void RemoveReceiver(Nucleus receiverToRemove) {
            if (receiverToRemove is not Neuron receiverNeuron)
                return;
            this._receivers.RemoveAll(receiver => receiver == receiverNeuron);
            receiverNeuron.synapses.RemoveAll(synapse => synapse.neuron == this);

            // Nucleus prefabReceiver = receiverToRemove.prefabNucleus;
            // if (this.prefabNucleus is Neuron prefabNeuron && prefabReceiver != null) {
            //     prefabNeuron.receivers.RemoveAll(receiver => receiver == prefabReceiver);
            //     prefabReceiver.synapses.RemoveAll(synapse => synapse.neuron == prefabNeuron);
            // }
        }


        #endregion Receivers

        /// <summary>
        /// Process an external stimulus
        /// </summary>
        /// <param name="inputValue">The value of the stimulus</param>
        public virtual void ProcessStimulus(Vector3 inputValue) {
            this.lastUpdate = Time.time;
            this.bias = inputValue;
            this.parent?.UpdateFromNucleus(this);
        }
    }

}