is_blank.cpp

// Best real time: 0.80 s
#include <fstream>
#include <iostream>
#include <string>
#include <vector>
#include <clocale>
#include "utf8.h"

using namespace std;

bool is_blank(const std::string& line) {
    auto it = line.begin();
    auto end = line.end();
    while (it != end) {
        auto c = utf8::next(it, end);
        if (!std::iswspace(c)) return false;
    }
    return true;
}

int main() {
    std::setlocale(LC_ALL, "en_US.UTF8");

    const char* test_file_path = "biggest.txt";
    // Open the test file (contains UTF-8 encoded text)
    ifstream fs8(test_file_path);
    if (!fs8.is_open()) {
        cout << "Could not open " << test_file_path << endl;
        return 0;
    }

    unsigned int line_count = 1;
    unsigned int k = 0;
    string line;
    // Play with all the lines in the file
    while (std::getline(fs8, line)) {
        if (!utf8::is_valid(line.begin(), line.end())) {
            cout << "Invalid UTF-8 encoding detected at line " << line_count << endl;
            cout << "\t" << line;
            return -1;
        }

        if (is_blank(line)) {
            k++;
        }

        line_count++;
    }

    cout << k << endl;
    return 0;
}