file_dublicates.cpp

//This program needs to be compiled at least with -std=c++17
//Cause of <filesystem>, which provides cross-platform directories access

#include <iostream>
#include <filesystem>
#include <fstream>
#include <unordered_map>
#include <algorithm>

int main(int argc, const char* argv[])
{
    struct file_amount
    {
        std::string filename;
        unsigned amount;
    };

    if (argc < 1)
    {
        std::cout << "Specify the directory to search files" << std::endl;
        return 0;
    }

    std::string path = argv[0];
    std::hash<std::string> hash_func;

    //key is the hash of the file contents, vector contains amount of files with that contents
    std::unordered_map<size_t, file_amount> occasions;
    for (const auto& file: std::filesystem::recursive_directory_iterator(path))
    {
        //open in binary to read bytes
        std::ifstream fin(file.path().string(), std::ios::binary);

        //the same thing as vector<char>, just stores bytes from file
        std::string bytes(std::istreambuf_iterator<char>{fin}, std::istreambuf_iterator<char>{});
        std::size_t file_hash = hash_func(std::move(bytes));

        fin.close();

        if (occasions.find(file_hash) != occasions.end())
            ++occasions[file_hash].amount;
        else
            occasions[file_hash] = {file.path().string(), 1};
    }

    file_amount max_copies = std::max_element(occasions.begin(), occasions.end(), [](const auto& a, const auto& b) {
        return a.second.amount < b.second.amount;
    })->second;

    std::cout << "File with maximum copies found: " << max_copies.filename << std::endl
              << "Found " << max_copies.amount << "copies" << std::endl;
    return 0;
}