Вот способ выразить то, что я считаю вашим вариантом использования. Я использовал расширение кортежа c ++ 17.
Я использовал unordered_map
, чтобы определить, какие слова известны или неизвестны, и два multimap
с, чтобы определить частоту известных и неизвестных слов.
Надеюсь, это полезно.
#include <sstream>
#include <tuple>
#include <string>
#include <unordered_map>
#include <algorithm>
#include <iterator>
#include <map>
#include <iostream>
#include <iomanip>
#include <fstream>
// Set this to 1 to run a static test
#define TESTING 0
#if TESTING
using input_type = std::istringstream;
std::tuple<input_type, input_type> open_inputs() {
return {
std::istringstream("the big black cat sat on the grey mat"),
std::istringstream("the gold small cat lay on the purple mat")
};
}
#else
using input_type = std::ifstream;
std::tuple<input_type, input_type> open_inputs() {
return {
std::ifstream("left_file.txt"),
std::ifstream("right_file.txt"),
};
}
#endif
struct Counts {
int left_count = 0, right_count = 0;
int total() const {
return left_count + right_count;
}
bool is_known() const {
return left_count && right_count;
}
};
template<class F>
void for_each_word_in_file(std::istream &is, F f) {
std::for_each(std::istream_iterator<std::string>(is),
std::istream_iterator<std::string>(),
f);
}
int main() {
// open files
auto[left, right] = open_inputs();
auto known_words = std::unordered_map<std::string, Counts>();
// count words in each file
for_each_word_in_file(left, [&known_words](auto &&word) {
++known_words[word].left_count;
});
for_each_word_in_file(right, [&known_words](auto &&word) {
++known_words[word].right_count;
});
// map counts to words, in descending order, allowing multiple entries of the same count
std::multimap<int, std::string, std::greater<>> known_ordered, unknown_ordered;
// iterate all words seen, putting into appropriate map
for (auto&&[word, counts] : known_words) {
(counts.is_known() ? known_ordered : unknown_ordered)
.emplace(counts.total(), word);
}
// emit results
std::cout << "Known words by frequency\n";
for (auto&&[freq, word] : known_ordered) {
std::cout << std::setw(15) << word << " " << freq << '\n';
}
std::cout << "\nUmknown words by frequency\n";
for (auto&&[freq, word] : unknown_ordered) {
std::cout << std::setw(15) << word << " " << freq << '\n';
}
}