md5.c

/*
 * Simple MD5 implementation
 *
 * Compile with: gcc -o md5 -O3 -lm md5.c
 */
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <stdint.h>
#include <sys/mman.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <fcntl.h>
#include <unistd.h>

// leftrotate function definition
#define LEFTROTATE(x, c) (((x) << (c)) | ((x) >> (32 - (c))))

// These vars will contain the hash
uint32_t h0, h1, h2, h3;

int md5(uint8_t *initial_msg, size_t initial_len) {

    // Message block
    uint8_t msg_block[64]; // maybe 64 is enought... check it...

    // Note: All variables are unsigned 32 bit and wrap modulo 2^32 when calculating

    // r specifies the per-round shift amounts
    uint32_t r[] = {7, 12, 17, 22, 7, 12, 17, 22, 7, 12, 17, 22, 7, 12, 17, 22,
                    5,  9, 14, 20, 5,  9, 14, 20, 5,  9, 14, 20, 5,  9, 14, 20,
                    4, 11, 16, 23, 4, 11, 16, 23, 4, 11, 16, 23, 4, 11, 16, 23,
                    6, 10, 15, 21, 6, 10, 15, 21, 6, 10, 15, 21, 6, 10, 15, 21};

    // Use binary integer part of the sines of integers (Radians) as constants:
    uint32_t k[] = { 0xd76aa478, 0xe8c7b756, 0x242070db, 0xc1bdceee,
                     0xf57c0faf, 0x4787c62a, 0xa8304613, 0xfd469501,
                     0x698098d8, 0x8b44f7af, 0xffff5bb1, 0x895cd7be,
                     0x6b901122, 0xfd987193, 0xa679438e, 0x49b40821,
                     0xf61e2562, 0xc040b340, 0x265e5a51, 0xe9b6c7aa,
                     0xd62f105d, 0x02441453, 0xd8a1e681, 0xe7d3fbc8,
                     0x21e1cde6, 0xc33707d6, 0xf4d50d87, 0x455a14ed,
                     0xa9e3e905, 0xfcefa3f8, 0x676f02d9, 0x8d2a4c8a,
                     0xfffa3942, 0x8771f681, 0x6d9d6122, 0xfde5380c,
                     0xa4beea44, 0x4bdecfa9, 0xf6bb4b60, 0xbebfbc70,
                     0x289b7ec6, 0xeaa127fa, 0xd4ef3085, 0x04881d05,
                     0xd9d4d039, 0xe6db99e5, 0x1fa27cf8, 0xc4ac5665,
                     0xf4292244, 0x432aff97, 0xab9423a7, 0xfc93a039,
                     0x655b59c3, 0x8f0ccc92, 0xffeff47d, 0x85845dd1,
                     0x6fa87e4f, 0xfe2ce6e0, 0xa3014314, 0x4e0811a1,
                     0xf7537e82, 0xbd3af235, 0x2ad7d2bb, 0xeb86d391};

    // Initialize variables:
    h0 = 0x67452301;
    h1 = 0xefcdab89;
    h2 = 0x98badcfe;
    h3 = 0x10325476;

    // Pre-processing: adding a single 1 bit
    //append "1" bit to message
    /* Notice: the input bytes are considered as bits strings,
       where the first bit is the most significant bit of the byte.[37] */

    // Pre-processing: padding with zeros
    //append "0" bit until message length in bit ≡ 448 (mod 512)
    //append length mod (2 pow 64) to message

    size_t new_len;
    for(new_len = initial_len*8 + 1; new_len%512!=448; new_len++);
    new_len /= 8;

    // Process the message in successive 512-bit chunks:
    //for each 512-bit chunk of message:

    uint32_t *w; // break chunk into sixteen 32-bit words w[j], 0 ≤ j ≤ 15
    for(w = (uint32_t *) initial_msg;
        (uint32_t *) (initial_msg + initial_len - 64) > w;
        w += 16) {

#define DEBUG 1

#if DEBUG
        printf("offset: %u, initial_len %u, new_len: %u\n", ((uint8_t *) w) - initial_msg, initial_len, new_len);

        int j;
        for(j =0; j < 64; j++) printf("%x ", ((uint8_t *) w)[j]);
        puts("");
#endif

        // Initialize hash value for this chunk:
        uint32_t a = h0;
        uint32_t b = h1;
        uint32_t c = h2;
        uint32_t d = h3;

        // Main loops:

        uint32_t i=0;

        for(; i<16; i++) {

            uint32_t f = d ^ (b & (c ^ d));
            int g = i;

            uint32_t temp = d;
            d = c;
            c = b;
            b = b + LEFTROTATE((a + f + k[i] + w[g]), r[i]);
            a = temp;

        }

        for(; i<32; i++) {

            uint32_t f = c ^ (d & (b ^ c));
            int g = (5*i + 1) % 16;

            uint32_t temp = d;
            d = c;
            c = b;
            b = b + LEFTROTATE((a + f + k[i] + w[g]), r[i]);
            a = temp;

        }

        for(; i<48; i++) {

            uint32_t f = b ^ c ^ d;
            int g = (3*i + 5) % 16;

            uint32_t temp = d;
            d = c;
            c = b;
            b = b + LEFTROTATE((a + f + k[i] + w[g]), r[i]);
            a = temp;

        }

        for(; i<64; i++) {

            uint32_t f = c ^ (b | (~d));
            int g = (7*i) % 16;

            uint32_t temp = d;
            d = c;
            c = b;
            b = b + LEFTROTATE((a + f + k[i] + w[g]), r[i]);
            a = temp;

        }


        // Add this chunk's hash to result so far:

        h0 += a;
        h1 += b;
        h2 += c;
        h3 += d;

    }

    if (1) { // last chunk
        memset(msg_block, 0, 64);
        memcpy(msg_block, w, initial_len - (((uint8_t *) w) - initial_msg));
        msg_block[initial_len - (((uint8_t *) w) - initial_msg)] = 128; // write the "1" bit

#if DEBUG
        printf("offset: %u, initial_len %u, new_len: %u\n", ((uint8_t *) w) - initial_msg, initial_len, new_len);

        int j;
        for(j =0; j < 64; j++) printf("%x ", msg_block[j]);
        puts("");
#endif

        uint64_t bits_len = 8*initial_len;   // note, we append the len in bits
        memcpy(msg_block + 64 - 8, &bits_len, 8); // at the end of the buffer

#if DEBUG
        printf("offset: %u, initial_len %u, new_len: %u\n", ((uint8_t *) w) - initial_msg, initial_len, new_len);

        for(j =0; j < 64; j++) printf("%x ", msg_block[j]);
        puts("");
#endif

        w = (uint32_t *) msg_block;

        // Initialize hash value for this chunk:
        uint32_t a = h0;
        uint32_t b = h1;
        uint32_t c = h2;
        uint32_t d = h3;

        // Main loops:

        uint32_t i=0;

        for(; i<16; i++) {

            uint32_t f = d ^ (b & (c ^ d));
            int g = i;

            uint32_t temp = d;
            d = c;
            c = b;
            b = b + LEFTROTATE((a + f + k[i] + w[g]), r[i]);
            a = temp;

        }

        for(; i<32; i++) {

            uint32_t f = c ^ (d & (b ^ c));
            int g = (5*i + 1) % 16;

            uint32_t temp = d;
            d = c;
            c = b;
            b = b + LEFTROTATE((a + f + k[i] + w[g]), r[i]);
            a = temp;

        }

        for(; i<48; i++) {

            uint32_t f = b ^ c ^ d;
            int g = (3*i + 5) % 16;

            uint32_t temp = d;
            d = c;
            c = b;
            b = b + LEFTROTATE((a + f + k[i] + w[g]), r[i]);
            a = temp;

        }

        for(; i<64; i++) {

            uint32_t f = c ^ (b | (~d));
            int g = (7*i) % 16;

            uint32_t temp = d;
            d = c;
            c = b;
            b = b + LEFTROTATE((a + f + k[i] + w[g]), r[i]);
            a = temp;

        }


        // Add this chunk's hash to result so far:

        h0 += a;
        h1 += b;
        h2 += c;
        h3 += d;
    }


}

int main(int argc, char **argv) {

    if (argc < 2) {
        printf("usage: %s file_path\n", argv[0]);
        return 1;
    }

    int fd;
    struct stat sb;
    void* file_memory;

    // open the file
    fd = open (argv[1], O_RDONLY);
    if (fd == -1) {
        perror ("open");
        return 1;
    }

    // fstat to read file length
    if (fstat (fd, &sb) == -1) {
        perror ("fstat");
        return 1;
    }

    // check
    if (!S_ISREG (sb.st_mode)) {
        fprintf (stderr, "%s is not a file\n", argv[1]);
        return 1;
    }

    // create the memory mapping
    file_memory = mmap(0, sb.st_size, PROT_READ, MAP_SHARED, fd, 0);
    if (file_memory == MAP_FAILED) {
        perror ("mmap");
        return 1;
    }

    // close file descriptor
    if (close (fd) == -1) {
        perror ("close");
        return 1;
    }

    // calculate the MD5 hash
    md5(file_memory, sb.st_size);

    // release the memory
    if (munmap (file_memory, sb.st_size) == -1) {
        perror ("munmap");
        return 1;
    }

    //var char digest[16] := h0 append h1 append h2 append h3
    //(Output is in little-endian)
    uint8_t *p;

    // display result

    p=(uint8_t *)&h0;
    printf("%2.2x%2.2x%2.2x%2.2x", p[0], p[1], p[2], p[3], h0);

    p=(uint8_t *)&h1;
    printf("%2.2x%2.2x%2.2x%2.2x", p[0], p[1], p[2], p[3], h1);

    p=(uint8_t *)&h2;
    printf("%2.2x%2.2x%2.2x%2.2x", p[0], p[1], p[2], p[3], h2);

    p=(uint8_t *)&h3;
    printf("%2.2x%2.2x%2.2x%2.2x", p[0], p[1], p[2], p[3], h3);

    printf("  %s\n", argv[1]);

    return 1;
}