isspam/borded_cpp/src/main3.cpp

#include <string>
#include <string_view>
#include <fstream>
#include <algorithm>
#include <iostream>
#include <execution>
#include <format>
#include <cstdio>
#include <fcntl.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <aio.h>
#include <condition_variable>
#include <unordered_set>
#include <sys/signal.h>

#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::string_view, 35> BAD_WORDS = {
    "recovery",
    "techie",
    "http",
    "https",
    "digital",
    "hack",
    "::",
    "//",
    "com",
    "@",
    "crypto",
    "bitcoin",
    "wallet",
    "hacker",
    "welcome",
    "whatsapp",
    "email",
    "cryptocurrency",
    "stolen",
    "freeze",
    "quick",
    "crucial",
    "tracing",
    "scammers",
    "expers",
    "hire",
    "century",
    "transaction",
    "essential",
    "managing",
    "contact",
    "contacting",
    "understanding",
    "assets",
    "funds",
};
const std::unordered_set<std::string_view> BAD_WORDS_SET(BAD_WORDS.begin(), BAD_WORDS.end());
static constexpr unsigned int crc_table[256] = {
    0x00000000,
    0x77073096,
    0xee0e612c,
    0x990951ba,
    0x076dc419,
    0x706af48f,
    0xe963a535,
    0x9e6495a3,
    0x0edb8832,
    0x79dcb8a4,
    0xe0d5e91e,
    0x97d2d988,
    0x09b64c2b,
    0x7eb17cbd,
    0xe7b82d07,
    0x90bf1d91,
    0x1db71064,
    0x6ab020f2,
    0xf3b97148,
    0x84be41de,
    0x1adad47d,
    0x6ddde4eb,
    0xf4d4b551,
    0x83d385c7,
    0x136c9856,
    0x646ba8c0,
    0xfd62f97a,
    0x8a65c9ec,
    0x14015c4f,
    0x63066cd9,
    0xfa0f3d63,
    0x8d080df5,
    0x3b6e20c8,
    0x4c69105e,
    0xd56041e4,
    0xa2677172,
    0x3c03e4d1,
    0x4b04d447,
    0xd20d85fd,
    0xa50ab56b,
    0x35b5a8fa,
    0x42b2986c,
    0xdbbbc9d6,
    0xacbcf940,
    0x32d86ce3,
    0x45df5c75,
    0xdcd60dcf,
    0xabd13d59,
    0x26d930ac,
    0x51de003a,
    0xc8d75180,
    0xbfd06116,
    0x21b4f4b5,
    0x56b3c423,
    0xcfba9599,
    0xb8bda50f,
    0x2802b89e,
    0x5f058808,
    0xc60cd9b2,
    0xb10be924,
    0x2f6f7c87,
    0x58684c11,
    0xc1611dab,
    0xb6662d3d,
    0x76dc4190,
    0x01db7106,
    0x98d220bc,
    0xefd5102a,
    0x71b18589,
    0x06b6b51f,
    0x9fbfe4a5,
    0xe8b8d433,
    0x7807c9a2,
    0x0f00f934,
    0x9609a88e,
    0xe10e9818,
    0x7f6a0dbb,
    0x086d3d2d,
    0x91646c97,
    0xe6635c01,
    0x6b6b51f4,
    0x1c6c6162,
    0x856530d8,
    0xf262004e,
    0x6c0695ed,
    0x1b01a57b,
    0x8208f4c1,
    0xf50fc457,
    0x65b0d9c6,
    0x12b7e950,
    0x8bbeb8ea,
    0xfcb9887c,
    0x62dd1ddf,
    0x15da2d49,
    0x8cd37cf3,
    0xfbd44c65,
    0x4db26158,
    0x3ab551ce,
    0xa3bc0074,
    0xd4bb30e2,
    0x4adfa541,
    0x3dd895d7,
    0xa4d1c46d,
    0xd3d6f4fb,
    0x4369e96a,
    0x346ed9fc,
    0xad678846,
    0xda60b8d0,
    0x44042d73,
    0x33031de5,
    0xaa0a4c5f,
    0xdd0d7cc9,
    0x5005713c,
    0x270241aa,
    0xbe0b1010,
    0xc90c2086,
    0x5768b525,
    0x206f85b3,
    0xb966d409,
    0xce61e49f,
    0x5edef90e,
    0x29d9c998,
    0xb0d09822,
    0xc7d7a8b4,
    0x59b33d17,
    0x2eb40d81,
    0xb7bd5c3b,
    0xc0ba6cad,
    0xedb88320,
    0x9abfb3b6,
    0x03b6e20c,
    0x74b1d29a,
    0xead54739,
    0x9dd277af,
    0x04db2615,
    0x73dc1683,
    0xe3630b12,
    0x94643b84,
    0x0d6d6a3e,
    0x7a6a5aa8,
    0xe40ecf0b,
    0x9309ff9d,
    0x0a00ae27,
    0x7d079eb1,
    0xf00f9344,
    0x8708a3d2,
    0x1e01f268,
    0x6906c2fe,
    0xf762575d,
    0x806567cb,
    0x196c3671,
    0x6e6b06e7,
    0xfed41b76,
    0x89d32be0,
    0x10da7a5a,
    0x67dd4acc,
    0xf9b9df6f,
    0x8ebeeff9,
    0x17b7be43,
    0x60b08ed5,
    0xd6d6a3e8,
    0xa1d1937e,
    0x38d8c2c4,
    0x4fdff252,
    0xd1bb67f1,
    0xa6bc5767,
    0x3fb506dd,
    0x48b2364b,
    0xd80d2bda,
    0xaf0a1b4c,
    0x36034af6,
    0x41047a60,
    0xdf60efc3,
    0xa867df55,
    0x316e8eef,
    0x4669be79,
    0xcb61b38c,
    0xbc66831a,
    0x256fd2a0,
    0x5268e236,
    0xcc0c7795,
    0xbb0b4703,
    0x220216b9,
    0x5505262f,
    0xc5ba3bbe,
    0xb2bd0b28,
    0x2bb45a92,
    0x5cb36a04,
    0xc2d7ffa7,
    0xb5d0cf31,
    0x2cd99e8b,
    0x5bdeae1d,
    0x9b64c2b0,
    0xec63f226,
    0x756aa39c,
    0x026d930a,
    0x9c0906a9,
    0xeb0e363f,
    0x72076785,
    0x05005713,
    0x95bf4a82,
    0xe2b87a14,
    0x7bb12bae,
    0x0cb61b38,
    0x92d28e9b,
    0xe5d5be0d,
    0x7cdcefb7,
    0x0bdbdf21,
    0x86d3d2d4,
    0xf1d4e242,
    0x68ddb3f8,
    0x1fda836e,
    0x81be16cd,
    0xf6b9265b,
    0x6fb077e1,
    0x18b74777,
    0x88085ae6,
    0xff0f6a70,
    0x66063bca,
    0x11010b5c,
    0x8f659eff,
    0xf862ae69,
    0x616bffd3,
    0x166ccf45,
    0xa00ae278,
    0xd70dd2ee,
    0x4e048354,
    0x3903b3c2,
    0xa7672661,
    0xd06016f7,
    0x4969474d,
    0x3e6e77db,
    0xaed16a4a,
    0xd9d65adc,
    0x40df0b66,
    0x37d83bf0,
    0xa9bcae53,
    0xdebb9ec5,
    0x47b2cf7f,
    0x30b5ffe9,
    0xbdbdf21c,
    0xcabac28a,
    0x53b39330,
    0x24b4a3a6,
    0xbad03605,
    0xcdd70693,
    0x54de5729,
    0x23d967bf,
    0xb3667a2e,
    0xc4614ab8,
    0x5d681b02,
    0x2a6f2b94,
    0xb40bbe37,
    0xc30c8ea1,
    0x5a05df1b,
    0x2d02ef8d
};

constexpr uint32_t crc32(std::string_view str) {
    uint32_t crc = 0xffffffff;
    for (auto c : str)
        crc = (crc >> 8) ^ crc_table[(crc ^ c) & 0xff];
    return crc ^ 0xffffffff;
}

constexpr uint32_t crc32(char const *str, const size_t size) {
    uint32_t crc = 0xffffffff;
    for (size_t i = 0; i < size; ++i)
        crc = (crc >> 8) ^ crc_table[(crc ^ str[i]) & 0xff];
    return crc ^ 0xffffffff;
}

constexpr std::array<uint32_t, 35> BAD_WORDS_HASH = {
    crc32("recovery"),
    crc32("techie"),
    crc32("http"),
    crc32("https"),
    crc32("digital"),
    crc32("hack"),
    crc32("::"),
    crc32("//"),
    crc32("com"),
    crc32("@"),
    crc32("crypto"),
    crc32("bitcoin"),
    crc32("wallet"),
    crc32("hacker"),
    crc32("welcome"),
    crc32("whatsapp"),
    crc32("email"),
    crc32("cryptocurrency"),
    crc32("stolen"),
    crc32("freeze"),
    crc32("quick"),
    crc32("crucial"),
    crc32("tracing"),
    crc32("scammers"),
    crc32("expers"),
    crc32("hire"),
    crc32("century"),
    crc32("transaction"),
    crc32("essential"),
    crc32("managing"),
    crc32("contact"),
    crc32("contacting"),
    crc32("understanding"),
    crc32("assets"),
    crc32("funds")
};
const std::unordered_set BAD_WORDS_STR(BAD_WORDS.begin(), BAD_WORDS.end());

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

int totalWordCount = 0;
int totalCapitalizedCount = 0;
int totalSentenceCount = 0;
int totalNumberCount = 0;
int totalForbiddenCount = 0;
int fileCount = 1;

int failCount = 0;


int done = 0;


struct info {
    std::string_view name;
    aiocb *cb;
    const std::chrono::time_point<std::chrono::steady_clock> start = std::chrono::steady_clock::now();
};

constexpr void check_word_simple(const char *word, const ssize_t size) {
    if (size < SHORTEST_BAD_WORD || size > LONGEST_BAD_WORD) {
        return;
    }
    // if (BAD_WORDS_SET.contains(word)) {
    //     totalForbiddenCount++;
    // }

    const auto hs = crc32(word, size);

    for (int i = 0; i < BAD_WORDS_HASH.size(); ++i) {
        if (BAD_WORDS_HASH[i] == hs) {
            totalForbiddenCount++;
            return;
        }
    }
}

void read_str(char *str, ssize_t size) {
    int mark = -1;

    int fileWords = 0;
    for (int pos = 0; pos <= size; ++pos) {
        char *c = str + pos;

        if (*c == '.') {
            totalSentenceCount++;
        }

        if (*c == ' ' || *c == '\n' || *c == '\r' || *c == '\t') {
            if (mark != -1) {
                check_word_simple(str + mark, pos - mark);
                mark = -1;
            }
        } else if (mark == -1) {
            ++fileWords;
            if (*c >= 'A' && *c <= 'Z') {
                totalCapitalizedCount++;
            }

            mark = pos;
        } else if (*c >= '0' && *c <= '9') {
            totalNumberCount++;
            for (; pos <= size; ++pos) {
                c = str + pos;
                if (*c == '.') {
                    totalSentenceCount++;
                }
                if (*c == ' ' || *c == '\n' || *c == '\r' || *c == '\t') {
                    break;
                }
            }
            mark = -1;
        }

    }

    if (mark != -1) {
        check_word_simple(str + mark, size - mark);
    }

    totalWordCount += fileWords;
}


void aio_completion_handler(sigval_t sigval) {

        fileCount++;
        info *data = (info *)sigval.sival_ptr;
        auto req = data->cb;
        // auto req = (struct aiocb *)sigval.sival_ptr;
        /* Did the request complete? */
        auto error = aio_error(req);
        if (error == 0) {

            /* Request completed successfully, get the return status */
            // const auto start{std::chrono::steady_clock::now()};
            // const std::chrono::duration<double> start_seconds{start - (data->start)};
            // std::println("File started {} in {}", data->name, start_seconds.count());
            read_str((char *)req->aio_buf, aio_return(req));
            // const auto finish{std::chrono::steady_clock::now()};
            // const std::chrono::duration<double> elapsed_seconds{finish - (data->start)};
            // std::println("File read {} in {}", data->name, elapsed_seconds.count());
        } else {
            std::println("Error at aio_error ({}): ", error);
            failCount++;
        }
        --done;

}

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

    done = argc - 1;

    // lio_listio
    auto aiocb_list = (struct aiocb *)malloc(sizeof(struct aiocb) * (argc - 1));
    auto aiocb_list_ptr = (struct aiocb **)malloc(sizeof(struct aiocb *) * (argc - 1));

    // char *memchnk = (char *)malloc(5 * 1024 * 1024 * (argc - 1));

    for (std::size_t i = 0; i < argc - 1; i++) {
        aiocb_list[i].aio_fildes = open(argv[i + 1], O_RDONLY);
        aiocb_list[i].aio_offset = 0;
        // 5mb
        aiocb_list[i].aio_buf = malloc(5 * 1024 * 1024);
        aiocb_list[i].aio_nbytes = (5 * 1024 * 1024);;

        aiocb_list[i].aio_sigevent.sigev_notify = SIGEV_THREAD;
        aiocb_list[i].aio_sigevent.sigev_notify_function = aio_completion_handler;
        aiocb_list[i].aio_sigevent.sigev_notify_attributes = nullptr;
        // aiocb_list[i].aio_sigevent.sigev_value.sival_ptr = &aiocb_list[i];
        aiocb_list[i].aio_sigevent.sigev_value.sival_ptr = new info{
            argv[i + 1],
            &aiocb_list[i]};

        // aiocb_list[i].aio_reqprio = SIGRTMIN;

        aiocb_list_ptr[i] = &aiocb_list[i];
    }

    lio_listio(LIO_WAIT, aiocb_list_ptr, argc - 1, nullptr);

    while (done > 0) {
        std::this_thread::sleep_for(std::chrono::milliseconds(1));
    }

    std::println("Done reading files, {} done", done);

    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
        );

    for (std::size_t i = 0; i < argc - 1; i++) {
        close(aiocb_list[i].aio_fildes);
        free((void *)aiocb_list[i].aio_buf);
    }

    free(aiocb_list);
    free(aiocb_list_ptr);
    // free(memchnk);

    if (failCount > 0) {
        return 1;
    }
}