#include <vector>
#include <queue>
#include <memory>
#include <thread>
#include <mutex>
#include <condition_variable>
#include <future>
#include <functional>
#include <stdexcept>

typedef std::thread worker_t;

class ThreadPool {
public:
    ThreadPool(size_t threads);
#if (__GNUC__ <= 4) || (__GNUC_MINOR__ < 8)
    //
    // By default thread pools run at a lower priority
    //
    template<class T, class F, class... Args>
    std::future<T> enqueue(F&& f, Args&&... args);
#else
    template<class F, class... Args>
    auto enqueue(F&& f, Args&&... args)
        -> std::future<typename std::result_of<F(Args...)>::type>;
#endif
    ~ThreadPool();

private:
    // need to keep track of threads so we can join them
    std::vector< worker_t > workers;

    // the task queue
    std::queue< std::function<void()> > tasks;

    // synchronization
    std::mutex queue_mutex;
    std::condition_variable condition;
    bool stop;
};

// the constructor just launches some amount of workers
inline ThreadPool::ThreadPool(size_t threads) : stop(false)
{
    for(size_t i = 0;i<threads;++i)
    {
        workers.emplace_back(
            [this]
            {
                while(true)
                {
                    std::unique_lock<std::mutex> lock(this->queue_mutex);
                    while(!this->stop && this->tasks.empty())
                        this->condition.wait(lock);
                    if(this->stop && this->tasks.empty())
                        return;
                    std::function<void()> task(this->tasks.front());
                    this->tasks.pop();
                    lock.unlock();
                    task();
                }
            }
        );
    }
}

#if (__GNUC__ <= 4) || (__GNUC_MINOR__ < 8)
template<class T, class F, class... Args>
// coverity[pass_by_value]
inline std::future<T>
ThreadPool::enqueue(F&& f, Args&&... args)
{
    //typedef typename std::result_of<F(Args...)>::type return_type;
    
    // don't allow enqueueing after stopping the pool
    if(stop)
        throw std::runtime_error("enqueue on stopped ThreadPool");

    auto task = std::make_shared< std::packaged_task<T()> >(
            std::bind(std::forward<F>(f), std::forward<Args>(args)...)
        );
        
    std::future<T> res = task->get_future();
    {
        std::unique_lock<std::mutex> lock(queue_mutex);
        tasks.push([task](){ (*task)(); });
    }
    condition.notify_one();
    return res;
}
#else
// add new work item to the pool
template<class F, class... Args>
auto ThreadPool::enqueue(F&& f, Args&&... args)
    -> std::future<typename std::result_of<F(Args...)>::type>
{
    typedef typename std::result_of<F(Args...)>::type return_type;
    
    // don't allow enqueueing after stopping the pool
    if(stop)
        throw std::runtime_error("enqueue on stopped ThreadPool");

    auto task = std::make_shared< std::packaged_task<return_type()> >(
            std::bind(std::forward<F>(f), std::forward<Args>(args)...)
        );
        
    std::future<return_type> res = task->get_future();
    {
        std::unique_lock<std::mutex> lock(queue_mutex);
        tasks.push([task](){ (*task)(); });
    }
    condition.notify_one();
    return res;
}
#endif

// the destructor joins all threads
inline ThreadPool::~ThreadPool()
{
    {
        std::unique_lock<std::mutex> lock(queue_mutex);
        stop = true;
    }
    condition.notify_all();
    for(size_t i = 0;i<workers.size();++i)
    {
        workers[i].join();
    }
}

#include <iostream>

int
main(int argc, char *argv[])
{
    // create thread pool with 4 worker threads
    ThreadPool pool(4);

    // enqueue and store future
    auto result = pool.enqueue<int>([](int answer) { return answer; }, 42);

    // get result from future
    std::cout << result.get() << std::endl;

}