#include <string.h>

void *memcpy(void *s1, const void *s2, size_t n) {
    const char *f = s2;
    char       *t = s1;

    while (n-- > 0) *t++ = *f++;
    return s1;
}

void *memmove(void *s1, const void *s2, size_t n) {
    const char *f = s2;
    char       *t = s1;

    if (f < t) {
        f += n;
        t += n;
        while (n-- > 0) *--t = *--f;
    } else
        while (n-- > 0) *t++ = *f++;
    return s1;
}

void *memset(void *dest, int c, size_t n) {
    unsigned char *s = dest;
    size_t         k;

    /* Fill head and tail with minimal branching. Each
     * conditional ensures that all the subsequently used
     * offsets are well-defined and in the dest region. */

    if (!n)
        return dest;
    s[0] = c;
    s[n - 1] = c;
    if (n <= 2)
        return dest;
    s[1] = c;
    s[2] = c;
    s[n - 2] = c;
    s[n - 3] = c;
    if (n <= 6)
        return dest;
    s[3] = c;
    s[n - 4] = c;
    if (n <= 8)
        return dest;

    /* Advance pointer to align it at a 4-byte boundary,
     * and truncate n to a multiple of 4. The previous code
     * already took care of any head/tail that get cut off
     * by the alignment. */

    k = -(uintptr_t)s & 3;
    s += k;
    n -= k;
    n &= -4;

#ifdef __GNUC__
    typedef uint32_t __attribute__((__may_alias__)) u32;
    typedef uint64_t __attribute__((__may_alias__)) u64;

    u32 c32 = ((u32)-1) / 255 * (unsigned char)c;

    /* In preparation to copy 32 bytes at a time, aligned on
     * an 8-byte bounary, fill head/tail up to 28 bytes each.
     * As in the initial byte-based head/tail fill, each
     * conditional below ensures that the subsequent offsets
     * are valid (e.g. !(n<=24) implies n>=28). */

    *(u32 *)(s + 0) = c32;
    *(u32 *)(s + n - 4) = c32;
    if (n <= 8)
        return dest;
    *(u32 *)(s + 4) = c32;
    *(u32 *)(s + 8) = c32;
    *(u32 *)(s + n - 12) = c32;
    *(u32 *)(s + n - 8) = c32;
    if (n <= 24)
        return dest;
    *(u32 *)(s + 12) = c32;
    *(u32 *)(s + 16) = c32;
    *(u32 *)(s + 20) = c32;
    *(u32 *)(s + 24) = c32;
    *(u32 *)(s + n - 28) = c32;
    *(u32 *)(s + n - 24) = c32;
    *(u32 *)(s + n - 20) = c32;
    *(u32 *)(s + n - 16) = c32;

    /* Align to a multiple of 8 so we can fill 64 bits at a time,
     * and avoid writing the same bytes twice as much as is
     * practical without introducing additional branching. */

    k = 24 + ((uintptr_t)s & 4);
    s += k;
    n -= k;

    /* If this loop is reached, 28 tail bytes have already been
     * filled, so any remainder when n drops below 32 can be
     * safely ignored. */

    u64 c64 = c32 | ((u64)c32 << 32);
    for (; n >= 32; n -= 32, s += 32) {
        *(u64 *)(s + 0) = c64;
        *(u64 *)(s + 8) = c64;
        *(u64 *)(s + 16) = c64;
        *(u64 *)(s + 24) = c64;
    }
#else
    /* Pure C fallback with no aliasing violations. */
    for (; n; n--, s++) *s = c;
#endif

    return dest;
}

// int memcmp(const void *s1, const void *s2, size_t n) {
//     if (n != 0) {
//         const unsigned char *p1 = s1, *p2 = s2;
//
//         do {
//             if (*p1++ != *p2++)
//                 return (*--p1 - *--p2);
//         } while (--n != 0);
//     }
//     return (0);
// }

char *itoa(int value, char *str, int base) {
    char        *p = str;
    char        *p1, *p2;
    unsigned int uvalue = value;
    int          negative = 0;

    if (base < 2 || base > 36) {
        *str = '\0';
        return str;
    }

    if (value < 0 && base == 10) {
        negative = 1;
        uvalue = -value;
    }

    // Convert to string
    do {
        int digit = uvalue % base;
        *p++ = (digit < 10) ? '0' + digit : 'a' + (digit - 10);
        uvalue /= base;
    } while (uvalue);

    if (negative)
        *p++ = '-';

    *p = '\0';

    // Reverse string
    p1 = str;
    p2 = p - 1;
    while (p1 < p2) {
        char tmp = *p1;
        *p1++ = *p2;
        *p2-- = tmp;
    }

    return str;
}

// void *memset(void *dst, int c, size_t length) {
//     u8      *ptr = (u8 *)dst;
//     const u8 value = (u8)c;
//
//     while (length--) *(ptr++) = value;
//
//     return dst;
// }

// void *memcpy(void *dst, const void *src, size_t len) {
//     u8       *d = (u8 *)dst;
//     const u8 *s = (const u8 *)src;
//     for (size_t i = 0; i < len; i++) {
//         d[i] = s[i];
//     }
//     return dst;
// }

// void *memmove(void *dst, const void *src, size_t len) {
//     u8       *d = (u8 *)dst;
//     const u8 *s = (const u8 *)src;
//     if (d < s) {
//         for (size_t i = 0; i < len; i++) {
//             d[i] = s[i];
//         }
//     } else if (d > s) {
//         for (size_t i = len; i > 0; i--) {
//             d[i - 1] = s[i - 1];
//         }
//     }
//     return dst;
// }

int memcmp(const void *s1, const void *s2, size_t len) {
    const u8 *a = (const u8 *)s1;
    const u8 *b = (const u8 *)s2;
    for (size_t i = 0; i < len; i++) {
        if (a[i] != b[i]) {
            return (int)a[i] - (int)b[i];
        }
    }
    return 0;
}

size_t strlen(const char *s) {
    const char *p = s;
    while (*p) ++p;
    return (size_t)(p - s);
}

size_t strnlen(const char *s, size_t maxlen) {
    size_t len = 0;
    while (len < maxlen && s[len] != '\0') {
        len++;
    }
    return len;
}