word-freq.cpp

#include <iostream>
#include <fstream>
#include <sstream>
#include <regex>
#include <string>
#include <unordered_map>
#include <vector>
using namespace std;


bool comparator (pair<string, int> p1, pair<string, int> p2) {
    return p1.second > p2.second; 
}



int main () {
    ifstream f;
    f.open ("sherlock.txt");
    stringstream buffer;
    buffer << f.rdbuf();
    f.close();

    string s = buffer.str();

    std::regex word("[^A-Za-z]+");
    std::sregex_token_iterator iter(
        s.begin(), s.end(), word, -1);
    std::sregex_token_iterator end;

    std::map<std::string, int> counter;

    for ( ; iter != end; ++iter) {
        string word = *iter;
        transform(
            word.begin(), word.end(), word.begin(),
            [](unsigned char c){ return tolower(c); });
        counter[word] += 1;
    }

    vector<pair<string, int>> pairs;

    for (auto pair : counter) {
        pairs.push_back(pair);
    }

    sort(pairs.begin(), pairs.end(), comparator);

    for (auto pair: vector<pair<string, int>>(pairs.begin(), pairs.begin() + 20)) {
       cout << pair.first << " " << pair.second << endl; 
    }

  return 0;
}