/* indexvec.cpp - Matt Mahoney, mmahoney@cs.fit.edu

This program reads text from standard input and prints an alphabetically
sorted list of words and the number of times each word occurs.  A
word is defined as a sequence of one or more letters and no other
characters.  For purposes of counting, differences in case are
ignored.  For instance, "Don't" is 2 words, "don" and "t".  The output
is in two columns with the count first.  For instance, if input.txt is:

  Don, don't do
  that.

Then the command:

  indexmap <input.txt

prints the following:

  1 do
  2 don
  1 t
  1 that
*/

#include <iostream>
#include <cctype>
#include <string>
#include <vector>
#include <algorithm>
using namespace std;

int main() {

  // Read the input, parsing into lowercase words.
  // Store the words in a vector, wordlist, in lower case format.
  char c;
  string word;
  vector<string> wordlist;
  while (cin.get(c)) {
    if (isalpha(c))
      word += char(tolower(c));
    else if (word != "") {
      wordlist.push_back(word);
      word = "";
    }
  }

  // Sort wordlist, bringing identical words together
  sort(wordlist.begin(), wordlist.end());

  // Print the unique words in wordlist along with their repeat counts.
  int count=1;  // How many times the current word has been seen.
  for (int i=0; i<int(wordlist.size()); ++i) {
    if (i==int(wordlist.size())-1 || wordlist[i]!=wordlist[i+1]) {
      cout << count << " " << wordlist[i] << "\n";  // Last repeat?
      count=1;
    }
    else
      ++count;
  }
  return 0;
}