Splitting a string based on a regular expression

main.cpp

// based on code taken from
// http://en.cppreference.com/w/cpp/regex/regex_iterator#Example,
// last access 10/22/2016
#include <regex>
#include <iostream>

using namespace std;

int main() {
    // some words to pick apart
    vector<string> words = {"Harry", "hairy", "hare", "the"};

    // a case-insensitive regular expression that matches anything that is NOT a vowel
    regex words_regex("[^aeiouy]+", regex_constants::ECMAScript | regex_constants::icase );

    // for every word
    for (auto word : words) {

        // separate it based on the regex
        auto words_begin =
                sregex_iterator(word.begin(), word.end(), words_regex);
        auto words_end = sregex_iterator();

        // print the word
        cout << word << ", ";

        // compute how many parts (tokens) the word was broken into
        int num_tokens = std::distance(words_begin, words_end);

        cout << num_tokens << " token";
        // pluralization
        cout << (num_tokens != 1 ? "s: " : ": ");

        // print out the parts (tokens)
        for (auto i = words_begin; i != words_end; ++i) {
            smatch match = *i;
            string match_str = match.str();
            cout << match_str << ' ';
        } // end
        cout << endl;
    }
}