#include <iostream>
#include <cstdlib>
#include <array>
#include "utf8.h"
#include "context.hpp"
#include "utf8/checked.h"

static
context_model process_input()
{
    std::array<char, 4096> buffer;
    std::ptrdiff_t left_over{ 0 };
    context_model context;

    while (!std::cin.eof())
    {
        std::cin.read(buffer.data() + left_over, buffer.size() - left_over);

        std::array<char, 4096>::iterator octet_iterator = std::begin(buffer);
        std::array<char, 4096>::iterator start_iterator = octet_iterator;
        std::array<char, 4096>::iterator end_iterator = octet_iterator + std::cin.gcount() + left_over;

        try
        {
            while (start_iterator != end_iterator)
            {
                utf8::utfchar32_t character = utf8::next(start_iterator, end_iterator);

                context.add(character);
                octet_iterator = start_iterator;
            }
            left_over = 0;
        }
        catch (const utf8::not_enough_room&)
        {
            std::copy(octet_iterator, end_iterator, std::begin(buffer));
            left_over = std::distance(octet_iterator, end_iterator);
        }
    }
    return context;
}

/*
 * Reads a UTF-8 file from stdin, analyzes it and prints context information.
 */
int main(int argc, char **argv)
{
    context_model context = process_input();

    std::size_t i{ 0 };
    for (auto [context_characters, occurrence]: context)
    {
        ++i;
        std::cout << i << ". " << context_characters << ": ";

        for (auto [character, count]: occurrence)
        {
            std::string character_bytes;
            utf8::append(character, character_bytes);

            std::cout << character_bytes << " - " << count << "; ";
        }
        std::cout  << std::endl;
    }

    return EXIT_SUCCESS;
}