isspam/borded_cpp/src/main2.cpp

#include <string>
#include <string_view>
#include <fstream>
#include <algorithm>
#include <iostream>
#include <numeric>
#include <execution>
#include <format>
#include <codecvt>
#include <ranges>

#ifdef __cpp_lib_print
#include <print>
#else
namespace std {
template <typename T, typename... Args>
inline void print(T format, Args &&... args) {
    auto f = std::vformat(format, std::make_format_args(args...));
    std::cout << f;
}

template <typename T, typename... Args>
inline void println(T format, Args &&... args) {
    auto f = std::vformat(format, std::make_format_args(args...));
    std::cout << f << std::endl;
}
}
#endif

constexpr std::array<std::wstring_view, 35> BAD_WORDS = {
    L"recovery",
    L"techie",
    L"http",
    L"https",
    L"digital",
    L"hack",
    L"::",
    L"//",
    L"com",
    L"@",
    L"crypto",
    L"bitcoin",
    L"wallet",
    L"hacker",
    L"welcome",
    L"whatsapp",
    L"email",
    L"cryptocurrency",
    L"stolen",
    L"freeze",
    L"quick",
    L"crucial",
    L"tracing",
    L"scammers",
    L"expers",
    L"hire",
    L"century",
    L"transaction",
    L"essential",
    L"managing",
    L"contact",
    L"contacting",
    L"understanding",
    L"assets",
    L"funds",
};

constexpr auto SHORTEST_BAD_WORD = std::ranges::fold_left(BAD_WORDS, std::numeric_limits<std::size_t>::max(),
                                                          [](std::size_t current, const std::wstring_view &word) {
                                                              return std::min(current, word.size());
                                                          }
    );
constexpr auto LONGEST_BAD_WORD = std::ranges::fold_left(BAD_WORDS, std::numeric_limits<std::size_t>::min(),
                                                         [](std::size_t current, const std::wstring_view &word) {
                                                             return std::max(current, word.size());
                                                         }
    );

std::size_t totalWordCount = 0;
std::size_t totalCapitalizedCount = 0;
std::size_t totalSentenceCount = 0;
std::size_t totalNumberCount = 0;
std::size_t totalForbiddenCount = 0;
std::size_t fileCount = 1;

std::size_t failCount = 0;

void check_word(std::wstring &word, std::size_t &forbiddenCount) {
    if (word.size() < SHORTEST_BAD_WORD || word.size() > LONGEST_BAD_WORD) {
        return;
    }
    std::ranges::transform(word, word.begin(), ::towlower);
    if (std::ranges::find(BAD_WORDS, word) != BAD_WORDS.end()) {
        forbiddenCount++;
    }
    // if (std::ranges::find_if(BAD_WORDS, [&word](const std::wstring_view &badWord) {
    //                              return word.contains(badWord);
    //                          }
    //         ) != BAD_WORDS.end()) {
    //     forbiddenCount++;
    // }
}

void parseFile(const std::string_view &filename) {
    std::wifstream file;

    // surpress warning of deprecation
#pragma warning(push)
#pragma warning(suppress : 4996)
    file.imbue(std::locale(std::locale(), new std::codecvt_utf8<wchar_t>));
#pragma warning(pop)

    file.open(std::string(filename));
    if (!file.is_open()) {
        std::println("File doesn't exist: {}", filename);
        return;
    }

    bool inWord = false;
    bool isDigit = false;
    wchar_t c;

    std::wstring word;
    while (file.get(c)) {
        if (c == '.') {
            totalSentenceCount++;
        }

        if (std::isspace(c)) {
            inWord = false;
            isDigit = false;

            if (!word.empty()) {
                check_word(word, totalForbiddenCount);
                word.clear();
            }
            continue;
        } else {
            if (!inWord) {
                totalWordCount++;
                if (std::isupper(c)) {
                    totalCapitalizedCount++;
                }
            }
            inWord = true;

            if (std::isdigit(c) && !isDigit) {
                totalNumberCount++;
                isDigit = true;
            }

            word.push_back(c);
        }
    };

    // std::cout << "File state: " << file.rdstate() << " EOF" << file.eof() << " Fail" << file.fail() << " Bad" << file.bad() << std::endl;

    if (!word.empty()) {
        check_word(word, totalForbiddenCount);
    }

    file.close();

    if (file.fail() && !file.eof()) {
        failCount++;
    }

}

int main(const int argc, char *argv[]) {
    if (argc < 2) {
        std::println("Usage: {} <file1> <file2> ... <fileN>", argv[0]);
        return 1;
    }

    std::for_each(std::execution::par_unseq, std::next(argv), argv + argc, parseFile);

    double capitalizedPercentage = (totalWordCount > 0)
                                       ? static_cast<double>(totalCapitalizedCount) / totalWordCount * 100.0
                                       : 0;
    double forbiddenPercentage = (totalWordCount > 0)
                                     ? static_cast<double>(totalForbiddenCount) / totalWordCount * 100.0
                                     : 0;
    double wordCountPerSentence = (totalSentenceCount > 0)
                                      ? static_cast<double>(totalWordCount) / totalSentenceCount
                                      : 0;

    std::println(
        "Word Count: {}\nCapitalized Count: {}\nSentence Count: {}\nNumber Count: {}\nForbidden Count: {}\nFile Count: {}\nFail Count: {}\nCapitalized Percentage: {}%\nForbidden Percentage: {}%\nWord Count Per Sentence: {}",
        totalWordCount, totalCapitalizedCount, totalSentenceCount, totalNumberCount, totalForbiddenCount, fileCount, failCount,
        capitalizedPercentage, forbiddenPercentage, wordCountPerSentence
        );

    return 0;
}