// replace #include <boost/tr1/regex.hpp> with 
//         #include <regex> 
#include <boost/tr1/regex.hpp> 

#include <algorithm> 
#include <cstdlib> 
#include <fstream> 
#include <iostream> 
#include <string> 
#include <map> 
#include <unordered_map> 
#include <utility> 

using std::cout; 
using std::cerr; 
using std::endl; 

using std::ifstream; 
using std::stringstream; 

using std::pair; 
using std::string; 
using std::map; 
using std::unordered_map; 
using std::vector; 

using std::advance; 
using std::find_if; 

// replace std::tr1 with std:: 
using std::tr1::regex; 
using std::tr1::sregex_iterator; 

using str2Int= unordered_map<string,size_t>; 
using intAndWords= pair<size_t,vector<string>>; 
using int2Words= map<size_t,vector<string>>; 

// count the frequency of each word 
str2Int wordCount(const string& text){ 
  regex wordReg(R"(\w+)"); 
  sregex_iterator wordItBegin(text.begin(),text.end(),wordReg); 
  const sregex_iterator wordItEnd; 
  str2Int allWords; 
  for (; wordItBegin != wordItEnd;++wordItBegin){ 
    ++allWords[wordItBegin->str()]; 
  } 
  return allWords; 
} 

// get to all frequencies the appropriate words 
int2Words frequencyOfWords(str2Int& wordCount){ 
  int2Words freq2Words; 
  for ( auto wordIt: wordCount ){ 
    auto freqWord= wordIt.second; 
    if ( freq2Words.find(freqWord) == freq2Words.end() ){ 
      freq2Words.insert( intAndWords(freqWord,{wordIt.first} )); 
    } 
    else { 
      freq2Words[freqWord].push_back(wordIt.first); 
    } 
  } 
  return freq2Words; 
} 

int main(int argc, char* argv[]){ 

  cout << endl; 

  // get the filename 
  std::string myFile; 
  if ( argc == 2 ){ 
    myFile= {argv[1]}; 
  } 
  else{ 
    cerr << "Filename missing !" << endl; 
    exit(EXIT_FAILURE); 
  } 

  // open the file 
  ifstream file(myFile, std::ios::in); 
  if ( !file ){ 
    cerr << "Can't open file "+ myFile + "!" << endl; 
    exit(EXIT_FAILURE); 
  } 

  // read the file 
  stringstream buffer; 
  buffer << file.rdbuf(); 
  string text(buffer.str()); 

  // get the frequency of each word 
  auto allWords= wordCount(text); 

  cout << "The first 20 (key, value)-pairs: " << endl; 
  auto end= allWords.begin(); 
  advance(end,20); 
  for (auto pair= allWords.begin(); pair != end; ++pair){ 
    cout << "(" << pair->first <<  ": " << pair->second << ")"; 
  } 
  cout << "\n\n"; 

  cout << "allWords[Web]: " << allWords["Web"] << endl; 
  cout << "allWords[The]: " << allWords["The"] << "\n\n"; 

  cout << "Number of unique words: "; 
  cout << allWords.size() << "\n\n"; 

  size_t sumWords=0; 
  for ( auto wordIt: allWords) sumWords+= wordIt.second; 
  cout << "Total number of words: " << sumWords <<"\n\n"; 

  auto allFreq= frequencyOfWords(allWords); 

  std::cout << "Number of different frequencies: " << allFreq.size() << "\n\n"; 

  cout << "All frequencies: "; 
  for ( auto freqIt: allFreq) cout << freqIt.first << " "; 
  cout << "\n\n"; 

  cout << "The most frequently occurring word(s): " << endl; 
  auto atTheEnd= allFreq.rbegin(); 
  cout << atTheEnd->first << " :"; 
  for ( auto word: atTheEnd->second) cout << word << " "; 
  cout << "\n\n"; 

  cout << "All word which appears more then 1000 times:" << endl; 
  auto biggerIt= find_if(allFreq.begin(),allFreq.end(), 
                         [](intAndWords iAndW){return iAndW.first > 1000;}); 
  if ( biggerIt == allFreq.end()){ 
    cerr << "No word appears more then 1000 times !" << endl; 
    exit(EXIT_FAILURE); 
  } 
  else{ 
    for ( auto allFreqIt= biggerIt; allFreqIt != allFreq.end(); ++allFreqIt){ 
      cout << allFreqIt->first << " :"; 
      for ( auto word: allFreqIt->second) cout << word << " "; 
      cout << endl; 
    } 
  } 
  cout << endl; 
}