// Derived from the "RSA Data Security, Inc. MD5 Message-Digest Algorithm":
// src: https://github.com/freebsd/freebsd-src/blob/release/14.2.0/sys/kern/md5c.c

#include <bit>
#include <cstdint>
#include <cstring>

#include "md5.h"

#if defined(_MSC_VER)
#define bswap_u16 _byteswap_ushort
#define bswap_u32 _byteswap_ulong
#define bswap_u64 _byteswap_uint64
#else
#define bswap_u16 __builtin_bswap16
#define bswap_u32 __builtin_bswap32
#define bswap_u64 __builtin_bswap64
#endif

template <typename T>
void Encode(uint8_t* output, const T input)
    requires(std::is_integral_v<T> && (sizeof(T) == 1 || sizeof(T) == 2 || sizeof(T) == 4 || sizeof(T) == 8))
{
    if constexpr (std::endian::native == std::endian::little || sizeof(T) == 1) {
        memcpy(output, &input, sizeof(T));
        // ReSharper disable once CppDFAUnreachableCode
    } else if constexpr (sizeof(T) == 2) {
        *reinterpret_cast<uint16_t*>(output) = bswap_u16(input);
    } else if constexpr (sizeof(T) == 4) {
        *reinterpret_cast<uint32_t*>(output) = bswap_u32(input);
    } else if constexpr (sizeof(T) == 8) {
        *reinterpret_cast<uint64_t*>(output) = bswap_u64(input);
    }
}

template <typename T>
void Decode(T* output, const uint8_t* input)
    requires(std::is_integral_v<T> && (sizeof(T) == 1 || sizeof(T) == 2 || sizeof(T) == 4 || sizeof(T) == 8))
{
    if constexpr (std::endian::native == std::endian::little) {
        memcpy(output, input, sizeof(T));
        // ReSharper disable once CppDFAUnreachableCode
    } else if constexpr (sizeof(T) == 2) {
        *output = bswap_u16(*reinterpret_cast<const uint16_t*>(input));
    } else if constexpr (sizeof(T) == 4) {
        *output = bswap_u32(*reinterpret_cast<const uint32_t*>(input));
    } else if constexpr (sizeof(T) == 8) {
        *output = bswap_u64(*reinterpret_cast<const uint64_t*>(input));
    }
}

inline void Encode(unsigned char* output, const uint32_t* input, const unsigned int len) {
    if constexpr (std::endian::native == std::endian::little) {
        memcpy(output, input, len);
    } else {
        // ReSharper disable once CppDFAUnreachableCode
        for (unsigned int i = 0; i < len; i += 4, output += 4) {
            Encode(output, input[i]);
        }
    }
}

inline void Decode(uint32_t* output, const unsigned char* input, const unsigned int len) {
    // ReSharper disable once CppDFAUnreachableCode
    if constexpr (std::endian::native == std::endian::little) {
        memcpy(output, input, len);
    } else {
        for (unsigned int i = 0; i < len; i += 4, ++output) {
            Decode(output, &input[i]);
        }
    }
}

void MD5Transform(uint32_t state[4], const unsigned char block[64]);

static unsigned char PADDING[64] = {0x80};

/* F, G, H and I are basic MD5 functions. */
#define F(x, y, z) (((x) & (y)) | ((~x) & (z)))
#define G(x, y, z) (((x) & (z)) | ((y) & (~z)))
#define H(x, y, z) ((x) ^ (y) ^ (z))
#define I(x, y, z) ((y) ^ ((x) | (~z)))

/* ROTATE_LEFT rotates x left n bits. */
#define ROTATE_LEFT(x, n) (((x) << (n)) | ((x) >> (32 - (n))))

/*
 * FF, GG, HH, and II transformations for rounds 1, 2, 3, and 4.
 * Rotation is separate from addition to prevent recomputation.
 */
#define FF(a, b, c, d, x, s, ac)                        \
    {                                                   \
        (a) += F((b), (c), (d)) + (x) + (uint32_t)(ac); \
        (a) = ROTATE_LEFT((a), (s));                    \
        (a) += (b);                                     \
    }
#define GG(a, b, c, d, x, s, ac)                        \
    {                                                   \
        (a) += G((b), (c), (d)) + (x) + (uint32_t)(ac); \
        (a) = ROTATE_LEFT((a), (s));                    \
        (a) += (b);                                     \
    }
#define HH(a, b, c, d, x, s, ac)                        \
    {                                                   \
        (a) += H((b), (c), (d)) + (x) + (uint32_t)(ac); \
        (a) = ROTATE_LEFT((a), (s));                    \
        (a) += (b);                                     \
    }
#define II(a, b, c, d, x, s, ac)                        \
    {                                                   \
        (a) += I((b), (c), (d)) + (x) + (uint32_t)(ac); \
        (a) = ROTATE_LEFT((a), (s));                    \
        (a) += (b);                                     \
    }

/*
 * MD5 block update operation. Continues an MD5 message-digest
 * operation, processing another message block, and updating the
 * context.
 */

void md5_update(MD5_CTX* ctx, const uint8_t* in, const size_t len) {
    unsigned int i{0};
    const unsigned char* input = in;

    /* Compute number of bytes mod 64 */
    unsigned int index = ctx->count % 64;
    ctx->count += len;

    // ReSharper disable once CppTooWideScopeInitStatement
    const unsigned int partLen = 64 - index;

    /* Transform as many times as possible. */
    if (len >= partLen) {
        memcpy(&ctx->buffer[index], input, partLen);
        MD5Transform(ctx->state, ctx->buffer);

        for (i = partLen; i + 63 < len; i += 64) {
            MD5Transform(ctx->state, &input[i]);
        }

        index = 0;
    }

    /* Buffer remaining input */
    memcpy(&ctx->buffer[index], &input[i], len - i);
}

/*
 * MD5 padding. Adds padding followed by original length.
 */

static void MD5Pad(MD5_CTX* context) {
    unsigned char bits[8];

    /* Save number of bits */
    Encode(bits, context->count << 3);

    /* Pad out to 56 mod 64. */
    const unsigned int index = context->count % 64;
    const unsigned int padLen = index < 56 ? 56 - index : 120 - index;
    md5_update(context, PADDING, padLen);

    /* Append length (before padding) */
    md5_update(context, bits, 8);
}

/*
 * MD5 finalization. Ends an MD5 message-digest operation, writing
 * the message digest and zeroizing the context.
 */
void md5_final(MD5_CTX* ctx, uint8_t* digest) {
    /* Do padding. */
    MD5Pad(ctx);

    /* Store state in digest */
    Encode(digest, ctx->state, MD5_DIGEST_LENGTH);

    /* Zeroize sensitive information. */
    memset(ctx, 0, sizeof(*ctx));
}

/* MD5 basic transformation. Transforms state based on block. */
void MD5Transform(uint32_t state[4], const unsigned char block[64]) {
    uint32_t a = state[0], b = state[1], c = state[2], d = state[3], x[16];

    Decode(x, block, 64);

    /* Round 1 */
    constexpr int S11 = 7;
    constexpr int S12 = 12;
    constexpr int S13 = 17;
    constexpr int S14 = 22;
    FF(a, b, c, d, x[0], S11, 0xd76aa478);  /* 1 */
    FF(d, a, b, c, x[1], S12, 0xe8c7b756);  /* 2 */
    FF(c, d, a, b, x[2], S13, 0x242070db);  /* 3 */
    FF(b, c, d, a, x[3], S14, 0xc1bdceee);  /* 4 */
    FF(a, b, c, d, x[4], S11, 0xf57c0faf);  /* 5 */
    FF(d, a, b, c, x[5], S12, 0x4787c62a);  /* 6 */
    FF(c, d, a, b, x[6], S13, 0xa8304613);  /* 7 */
    FF(b, c, d, a, x[7], S14, 0xfd469501);  /* 8 */
    FF(a, b, c, d, x[8], S11, 0x698098d8);  /* 9 */
    FF(d, a, b, c, x[9], S12, 0x8b44f7af);  /* 10 */
    FF(c, d, a, b, x[10], S13, 0xffff5bb1); /* 11 */
    FF(b, c, d, a, x[11], S14, 0x895cd7be); /* 12 */
    FF(a, b, c, d, x[12], S11, 0x6b901122); /* 13 */
    FF(d, a, b, c, x[13], S12, 0xfd987193); /* 14 */
    FF(c, d, a, b, x[14], S13, 0xa679438e); /* 15 */
    FF(b, c, d, a, x[15], S14, 0x49b40821); /* 16 */

    /* Round 2 */
    constexpr int S21 = 5;
    constexpr int S22 = 9;
    constexpr int S23 = 14;
    constexpr int S24 = 20;
    GG(a, b, c, d, x[1], S21, 0xf61e2562);  /* 17 */
    GG(d, a, b, c, x[6], S22, 0xc040b340);  /* 18 */
    GG(c, d, a, b, x[11], S23, 0x265e5a51); /* 19 */
    GG(b, c, d, a, x[0], S24, 0xe9b6c7aa);  /* 20 */
    GG(a, b, c, d, x[5], S21, 0xd62f105d);  /* 21 */
    GG(d, a, b, c, x[10], S22, 0x2441453);  /* 22 */
    GG(c, d, a, b, x[15], S23, 0xd8a1e681); /* 23 */
    GG(b, c, d, a, x[4], S24, 0xe7d3fbc8);  /* 24 */
    GG(a, b, c, d, x[9], S21, 0x21e1cde6);  /* 25 */
    GG(d, a, b, c, x[14], S22, 0xc33707d6); /* 26 */
    GG(c, d, a, b, x[3], S23, 0xf4d50d87);  /* 27 */
    GG(b, c, d, a, x[8], S24, 0x455a14ed);  /* 28 */
    GG(a, b, c, d, x[13], S21, 0xa9e3e905); /* 29 */
    GG(d, a, b, c, x[2], S22, 0xfcefa3f8);  /* 30 */
    GG(c, d, a, b, x[7], S23, 0x676f02d9);  /* 31 */
    GG(b, c, d, a, x[12], S24, 0x8d2a4c8a); /* 32 */

    /* Round 3 */
    constexpr int S31 = 4;
    constexpr int S32 = 11;
    constexpr int S33 = 16;
    constexpr int S34 = 23;
    HH(a, b, c, d, x[5], S31, 0xfffa3942);  /* 33 */
    HH(d, a, b, c, x[8], S32, 0x8771f681);  /* 34 */
    HH(c, d, a, b, x[11], S33, 0x6d9d6122); /* 35 */
    HH(b, c, d, a, x[14], S34, 0xfde5380c); /* 36 */
    HH(a, b, c, d, x[1], S31, 0xa4beea44);  /* 37 */
    HH(d, a, b, c, x[4], S32, 0x4bdecfa9);  /* 38 */
    HH(c, d, a, b, x[7], S33, 0xf6bb4b60);  /* 39 */
    HH(b, c, d, a, x[10], S34, 0xbebfbc70); /* 40 */
    HH(a, b, c, d, x[13], S31, 0x289b7ec6); /* 41 */
    HH(d, a, b, c, x[0], S32, 0xeaa127fa);  /* 42 */
    HH(c, d, a, b, x[3], S33, 0xd4ef3085);  /* 43 */
    HH(b, c, d, a, x[6], S34, 0x4881d05);   /* 44 */
    HH(a, b, c, d, x[9], S31, 0xd9d4d039);  /* 45 */
    HH(d, a, b, c, x[12], S32, 0xe6db99e5); /* 46 */
    HH(c, d, a, b, x[15], S33, 0x1fa27cf8); /* 47 */
    HH(b, c, d, a, x[2], S34, 0xc4ac5665);  /* 48 */

    /* Round 4 */
    constexpr int S41 = 6;
    constexpr int S42 = 10;
    constexpr int S43 = 15;
    constexpr int S44 = 21;
    II(a, b, c, d, x[0], S41, 0xf4292244);  /* 49 */
    II(d, a, b, c, x[7], S42, 0x432aff97);  /* 50 */
    II(c, d, a, b, x[14], S43, 0xab9423a7); /* 51 */
    II(b, c, d, a, x[5], S44, 0xfc93a039);  /* 52 */
    II(a, b, c, d, x[12], S41, 0x655b59c3); /* 53 */
    II(d, a, b, c, x[3], S42, 0x8f0ccc92);  /* 54 */
    II(c, d, a, b, x[10], S43, 0xffeff47d); /* 55 */
    II(b, c, d, a, x[1], S44, 0x85845dd1);  /* 56 */
    II(a, b, c, d, x[8], S41, 0x6fa87e4f);  /* 57 */
    II(d, a, b, c, x[15], S42, 0xfe2ce6e0); /* 58 */
    II(c, d, a, b, x[6], S43, 0xa3014314);  /* 59 */
    II(b, c, d, a, x[13], S44, 0x4e0811a1); /* 60 */
    II(a, b, c, d, x[4], S41, 0xf7537e82);  /* 61 */
    II(d, a, b, c, x[11], S42, 0xbd3af235); /* 62 */
    II(c, d, a, b, x[2], S43, 0x2ad7d2bb);  /* 63 */
    II(b, c, d, a, x[9], S44, 0xeb86d391);  /* 64 */

    state[0] += a;
    state[1] += b;
    state[2] += c;
    state[3] += d;

    /* Zeroize sensitive information. */
    memset(x, 0, sizeof(x));
}