#include <iostream>
#include <set>
#include <vector>
#include <algorithm> // transform
#include <cctype>
/*
Tokenize text into words.
- Keeps only letters and digits
- Splits on punctuation and spaces
*/
std::set<std::string> tokenize(const std::string &text) {
std::set<std::string> words;
std::string word;
for (char c : text) {
if (std::isalnum(c)) {
word += std::tolower(c);
} else if (!word.empty()) {
words.insert(word);
word.clear();
}
}
if (!word.empty()) words.insert(word);
return words;
}
/*
// Find keyword matches across THREE OR MORE texts
// -------------------------------------------------------------
This function receives a vector of sets.
It returns the intersection of ALL sets.
*/
std::set<std::string> findMatchesMultiple(
const std::vector<std::set<std::string>> &allSets)
{
if (allSets.empty()) return {};
// Start with the first set
std::set<std::string> result = allSets[0];
// Intersect with each remaining set
for (size_t i = 1; i < allSets.size(); i++) {
std::set<std::string> temp;
for (const std::string &w : result) {
if (allSets[i].count(w)) {
temp.insert(w);
}
}
result = std::move(temp);
}
return result;
}
int main() {
// -------------------------------------------------------------
// Three text blocks to compare
// -------------------------------------------------------------
std::string text1 =
"Machine learning allows computers to learn from data. "
"It is widely used in modern applications.";
std::string text2 =
"Data science uses machine learning techniques. "
"Applications rely on data-driven models.";
std::string text3 =
"Modern applications of machine learning include data analysis, "
"automation, and intelligent systems.";
// -------------------------------------------------------------
// Tokenize all texts
// -------------------------------------------------------------
std::set<std::string> words1 = tokenize(text1);
std::set<std::string> words2 = tokenize(text2);
std::set<std::string> words3 = tokenize(text3);
// Put them into a vector for multi-text comparison
std::vector<std::set<std::string>> allSets = { words1, words2, words3 };
// -------------------------------------------------------------
// Find keyword matches across ALL texts
// -------------------------------------------------------------
std::set<std::string> matches = findMatchesMultiple(allSets);
// -------------------------------------------------------------
// Output results
// -------------------------------------------------------------
std::cout << "Matched Keywords Across ALL Texts:\n";
for (const std::string &w : matches)
std::cout << w << " ";
}
/*
run:
Matched Keywords Across ALL Texts:
applications data learning machine
*/
