#pragma once
/**
 * @file object_pool.h
 * @brief 高性能对象池 + 写时复制
 *
 * 对象池：预分配 chunk，free-list 回收，O(1) acquire/release。
 * 写时复制：引用计数共享，修改时深拷贝，避免不必要的大对象拷贝。
 *
 * @ingroup foundation
 */

#include <vector>
#include <memory>
#include <atomic>
#include <mutex>
#include <cstddef>
#include <type_traits>
#include <functional>

namespace vde::core {

// ═══════════════════════════════════════════════════════════
//  ObjectPool — 单线程对象池
// ═══════════════════════════════════════════════════════════

/**
 * @brief 高性能对象池（单线程）
 *
 * 预分配 chunk 减少 malloc 调用，free-list 实现 O(1) 回收。
 *
 * @tparam T 池化对象类型（需有默认构造函数）
 * @tparam ChunkSize 每次扩容时分配的 chunk 大小
 *
 * @ingroup foundation
 */
template <typename T, size_t ChunkSize = 256>
class ObjectPool {
    static_assert(std::is_default_constructible_v<T>,
                  "T must be default constructible");

public:
    ObjectPool() { expand(); }
    ~ObjectPool() {
        for (auto* chunk : chunks_) {
            ::operator delete(chunk);
        }
    }

    /// 禁止拷贝
    ObjectPool(const ObjectPool&) = delete;
    ObjectPool& operator=(const ObjectPool&) = delete;

    /**
     * @brief 获取一个对象（复用或新建）
     * @return 对象指针
     */
    [[nodiscard]] T* acquire();

    /**
     * @brief 归还对象到池中
     * @param ptr 之前由 acquire() 返回的指针
     */
    void release(T* ptr);

    /// 统计
    [[nodiscard]] size_t total_allocated() const { return total_allocated_; }
    [[nodiscard]] size_t total_reused() const { return total_reused_; }
    [[nodiscard]] size_t pool_size() const { return chunks_.size() * ChunkSize; }
    [[nodiscard]] size_t free_count() const { return free_count_; }
    [[nodiscard]] double reuse_rate() const;

private:
    struct Node {
        Node* next = nullptr;
        T data;
    };

    std::vector<Node*> chunks_;   ///< 分配的 chunk
    Node* free_list_ = nullptr;    ///< 空闲列表头
    size_t free_count_ = 0;
    size_t total_allocated_ = 0;
    size_t total_reused_ = 0;

    void expand();
};

template <typename T, size_t ChunkSize>
T* ObjectPool<T, ChunkSize>::acquire() {
    if (free_list_ == nullptr) {
        expand();
    }

    total_allocated_++;
    if (free_list_ != chunks_.back()) {
        total_reused_++;
    }

    Node* node = free_list_;
    free_list_ = node->next;
    free_count_--;

    // Reset the object to default state
    node->data = T{};
    return &node->data;
}

template <typename T, size_t ChunkSize>
void ObjectPool<T, ChunkSize>::release(T* ptr) {
    if (!ptr) return;

    // Recover the Node pointer from the data pointer
    Node* node = reinterpret_cast<Node*>(
        reinterpret_cast<char*>(ptr) - offsetof(Node, data));

    node->next = free_list_;
    free_list_ = node;
    free_count_++;
}

template <typename T, size_t ChunkSize>
void ObjectPool<T, ChunkSize>::expand() {
    auto* chunk = static_cast<Node*>(::operator new(ChunkSize * sizeof(Node)));
    chunks_.push_back(chunk);

    // Build free list from the new chunk
    for (size_t i = 0; i < ChunkSize; ++i) {
        chunk[i].next = free_list_;
        free_list_ = &chunk[i];
    }
    free_count_ += ChunkSize;
}

template <typename T, size_t ChunkSize>
double ObjectPool<T, ChunkSize>::reuse_rate() const {
    if (total_allocated_ == 0) return 0.0;
    return static_cast<double>(total_reused_) / total_allocated_;
}

// ═══════════════════════════════════════════════════════════
//  ThreadSafeObjectPool — 线程安全对象池
// ═══════════════════════════════════════════════════════════

/**
 * @brief 线程安全对象池
 *
 * 每线程独立 pool + global fallback，无锁竞争。
 *
 * @tparam T 池化对象类型
 * @tparam ChunkSize 每个线程 local pool 的 chunk 大小
 */
template <typename T, size_t ChunkSize = 256>
class ThreadSafeObjectPool {
public:
    [[nodiscard]] T* acquire();
    void release(T* ptr);

    [[nodiscard]] size_t total_allocated() const { return global_allocated_.load(); }

private:
    // Per-thread pool (thread_local)
    static thread_local ObjectPool<T, ChunkSize> local_pool_;

    // Fallback when local pool is empty
    ObjectPool<T, ChunkSize> global_pool_;
    std::mutex global_mutex_;
    std::atomic<size_t> global_allocated_{0};
};

template <typename T, size_t ChunkSize>
thread_local ObjectPool<T, ChunkSize> ThreadSafeObjectPool<T, ChunkSize>::local_pool_{};

template <typename T, size_t ChunkSize>
T* ThreadSafeObjectPool<T, ChunkSize>::acquire() {
    // Try local pool first (no lock)
    if (local_pool_.free_count() > 0) {
        return local_pool_.acquire();
    }

    // Fall back to global pool
    std::lock_guard<std::mutex> lock(global_mutex_);
    if (global_pool_.free_count() > 0) {
        global_allocated_++;
        return global_pool_.acquire();
    }

    // Both empty — expand global
    global_allocated_++;
    return global_pool_.acquire();
}

template <typename T, size_t ChunkSize>
void ThreadSafeObjectPool<T, ChunkSize>::release(T* ptr) {
    // Return to local pool
    local_pool_.release(ptr);
}

// ═══════════════════════════════════════════════════════════
//  CowPtr — Copy-on-Write 智能指针
// ═══════════════════════════════════════════════════════════

/**
 * @brief 写时复制 (Copy-on-Write) 智能指针
 *
 * 类似 shared_ptr，但修改时自动深拷贝（detach）。
 * 用于大对象如 NurbsSurface、HalfedgeMesh 的共享。
 *
 * @tparam T 被包装类型
 */
template <typename T>
class CowPtr {
public:
    CowPtr() = default;

    explicit CowPtr(T value)
        : data_(std::make_shared<T>(std::move(value))) {}

    CowPtr(const CowPtr& other) = default;
    CowPtr& operator=(const CowPtr& other) = default;
    CowPtr(CowPtr&&) = default;
    CowPtr& operator=(CowPtr&&) = default;

    /// 只读访问
    [[nodiscard]] const T& read() const {
        ensure_valid();
        return *data_;
    }

    /// 可写访问（如有共享则深拷贝）
    [[nodiscard]] T& write() {
        ensure_valid();
        detach();
        return *data_;
    }

    /// 只读解引用
    [[nodiscard]] const T& operator*() const { return read(); }
    [[nodiscard]] const T* operator->() const { return &read(); }

    /// 引用计数
    [[nodiscard]] long use_count() const {
        return data_ ? data_.use_count() : 0;
    }

    /// 是否唯一持有
    [[nodiscard]] bool unique() const {
        return data_ && data_.use_count() == 1;
    }

    /// 浅拷贝（共享数据）
    [[nodiscard]] CowPtr shallow_copy() const {
        return CowPtr(*this);
    }

    /// 深拷贝（显式复制数据）
    [[nodiscard]] CowPtr deep_copy() const {
        if (!data_) return CowPtr();
        return CowPtr(T(*data_));
    }

private:
    std::shared_ptr<T> data_;

    void ensure_valid() const {
        if (!data_) {
            const_cast<CowPtr*>(this)->data_ = std::make_shared<T>();
        }
    }

    /// 如果数据被共享，则深拷贝
    void detach() {
        if (data_ && data_.use_count() > 1) {
            data_ = std::make_shared<T>(*data_);
        }
    }
};

} // namespace vde::core