/* jaccard-set-linear: Program to calculate Jaccard similarity using sets and two iterators.
   James S. Plank
   CS494/CS594 - Advanced Algorithms and Programming
   October, 2017
 */

#include <string>
#include <stdint.h>
#include <sys/time.h>
#include <fstream>
#include <vector>
#include <list>
#include <cmath>
#include <algorithm>
#include <map>
#include <set>
#include <iostream>
#include <cstdio>
#include <cstdlib>

using namespace std;

void usage(const string s)
{
    fprintf(stderr, "usage: jaccard-set-linear files\n");
    if (s != "") fprintf(stderr, "%s\n", s.c_str()); 
    exit(1);
}

int main(int argc, char **argv)
{
  vector < set <string> > sets;
  set <string>::iterator liti, litj;
  ifstream f;
  string s;
  int i, j;
  double Intersection;
  double Total;
  double Union;

  if (argc == 1) usage("");

  /* Read the data sets into set. */

  sets.resize(argc-1);
  for (i = 1; i < argc; i++) {
    f.clear();
    f.open(argv[i]);
    if (f.fail()) { perror(argv[i]); exit(1); }
    while (getline(f, s)) sets[i-1].insert(s);
    f.close();
  }

  /* For each pair of sets, calculate the Jaccard similarity directly. */

  for (i = 0; i < sets.size(); i++) {
    for (j = 0; j < sets.size(); j++) {
      Total = sets[i].size() + sets[j].size();
      Intersection = 0;
      liti = sets[i].begin(); 
      litj = sets[j].begin(); 
      while (liti != sets[i].end() && litj != sets[j].end()) {
        if (*liti == *litj) {
          Intersection++;
          liti++;
          litj++;
        } else if (*liti < *litj) {
          liti++;
        } else {
          litj++;
        }
      }
      Union = Total - Intersection;
      printf("%-30s %-30s %.6lf\n", argv[i+1], argv[j+1], Intersection / Union);
    }
  }
  exit(1);
}