C++, I want to divide a text into individual strings. For example: "to bebe or not to be" will be {"to", "bebe", "or", "not", "be"}. I will put these individual strings into set tokens. Also, use this helper function to clean each string if it has any punctuations and then put the string into the set tokens.

// Helper Function

string cleanToken(string s) { // This for loop checks if there exists any alphabet in the string int found = 0; for (int i = 0, len = s.size(); i < len; i++) { if (isalpha(s[i])) { found = 1; break; } } // This for loop will remove any punctuation from the beginning until the first letter is encountered or return empty string if no alphabet is found for (int i = 0, len = s.size(); i < len; i++) { if (found != 1) { s = ""; } else if (ispunct(s[i])) { s.erase(i--, 1); len = s.size(); } else { break; } } // This for loop will remove any punctuation from the end until the first letter is encountered or return empty string if no alphabet is found for (int i = s.size() - 1; i > 0; i--) { if (found != 1) { s = ""; } else if (ispunct(s[i])) { s.erase(i); } else { break; } } transform(s.begin(), s.end(), s.begin(), ::tolower); // transform string to lowercase return s; }

set gatherTokens(string text) { set tokens;

// Todo:

return tokens; }