# Implemented a bunch of GF(2**8) stuff, so the docker isnt bloated by sage

# This defines multiplication in the Galois Field of size 2^8 with modulus x^8 + x^4 + x^3 + x + 1
MODULUS = 0x1B
def gmul(a, b):
    result = 0
    for _ in range(8):
        if b & 1:
            result ^= a
        b >>= 1

        carry = a & 0x80
        a <<= 1
        a %= 2**8

        if carry:
            a ^= MODULUS

    return result

# ginv[a] is the multiplicative inverse of a in the Galois Field
ginv = [
    0x00, 0x01, 0x8d, 0xf6, 0xcb, 0x52, 0x7b, 0xd1, 0xe8, 0x4f, 0x29, 0xc0, 0xb0, 0xe1, 0xe5, 0xc7,
    0x74, 0xb4, 0xaa, 0x4b, 0x99, 0x2b, 0x60, 0x5f, 0x58, 0x3f, 0xfd, 0xcc, 0xff, 0x40, 0xee, 0xb2,
    0x3a, 0x6e, 0x5a, 0xf1, 0x55, 0x4d, 0xa8, 0xc9, 0xc1, 0x0a, 0x98, 0x15, 0x30, 0x44, 0xa2, 0xc2,
    0x2c, 0x45, 0x92, 0x6c, 0xf3, 0x39, 0x66, 0x42, 0xf2, 0x35, 0x20, 0x6f, 0x77, 0xbb, 0x59, 0x19,
    0x1d, 0xfe, 0x37, 0x67, 0x2d, 0x31, 0xf5, 0x69, 0xa7, 0x64, 0xab, 0x13, 0x54, 0x25, 0xe9, 0x09,
    0xed, 0x5c, 0x05, 0xca, 0x4c, 0x24, 0x87, 0xbf, 0x18, 0x3e, 0x22, 0xf0, 0x51, 0xec, 0x61, 0x17,
    0x16, 0x5e, 0xaf, 0xd3, 0x49, 0xa6, 0x36, 0x43, 0xf4, 0x47, 0x91, 0xdf, 0x33, 0x93, 0x21, 0x3b,
    0x79, 0xb7, 0x97, 0x85, 0x10, 0xb5, 0xba, 0x3c, 0xb6, 0x70, 0xd0, 0x06, 0xa1, 0xfa, 0x81, 0x82,
    0x83, 0x7e, 0x7f, 0x80, 0x96, 0x73, 0xbe, 0x56, 0x9b, 0x9e, 0x95, 0xd9, 0xf7, 0x02, 0xb9, 0xa4,
    0xde, 0x6a, 0x32, 0x6d, 0xd8, 0x8a, 0x84, 0x72, 0x2a, 0x14, 0x9f, 0x88, 0xf9, 0xdc, 0x89, 0x9a,
    0xfb, 0x7c, 0x2e, 0xc3, 0x8f, 0xb8, 0x65, 0x48, 0x26, 0xc8, 0x12, 0x4a, 0xce, 0xe7, 0xd2, 0x62,
    0x0c, 0xe0, 0x1f, 0xef, 0x11, 0x75, 0x78, 0x71, 0xa5, 0x8e, 0x76, 0x3d, 0xbd, 0xbc, 0x86, 0x57,
    0x0b, 0x28, 0x2f, 0xa3, 0xda, 0xd4, 0xe4, 0x0f, 0xa9, 0x27, 0x53, 0x04, 0x1b, 0xfc, 0xac, 0xe6,
    0x7a, 0x07, 0xae, 0x63, 0xc5, 0xdb, 0xe2, 0xea, 0x94, 0x8b, 0xc4, 0xd5, 0x9d, 0xf8, 0x90, 0x6b,
    0xb1, 0x0d, 0xd6, 0xeb, 0xc6, 0x0e, 0xcf, 0xad, 0x08, 0x4e, 0xd7, 0xe3, 0x5d, 0x50, 0x1e, 0xb3,
    0x5b, 0x23, 0x38, 0x34, 0x68, 0x46, 0x03, 0x8c, 0xdd, 0x9c, 0x7d, 0xa0, 0xcd, 0x1a, 0x41, 0x1c,
]

def matrix_mul(A, B):
    result = [[0] * 4 for _ in range(4)]
    for i in range(4):
        for j in range(4):
            for k in range(4):
                result[i][j] ^= gmul(A[i][k], B[k][j])
    return result

# Calculate Inverse Matrix Using Gauss Jordan Elimination
def matrix_inv(A):
    n = 4
    augmented = [row + [1 if i == j else 0 for j in range(n)] for i, row in enumerate(A)]
    
    for col in range(n):
        pivot = -1
        for row in range(col, n):
            if augmented[row][col] != 0:
                pivot = row
                break
        if pivot == -1:
            raise ValueError("Matrix is not invertible.")
        
        augmented[col], augmented[pivot] = augmented[pivot], augmented[col]
        
        pivot_val = augmented[col][col]
        inv_pivot = ginv[pivot_val]
        for j in range(2 * n):
            augmented[col][j] = gmul(augmented[col][j], inv_pivot)
        
        for row in range(n):
            if row != col:
                factor = augmented[row][col]
                for j in range(2 * n):
                    augmented[row][j] ^= gmul(factor, augmented[col][j])
    
    inverse = [row[n:] for row in augmented]
    return inverse

# Normal AES Stuff under here

s_box = (
    0x63, 0x7C, 0x77, 0x7B, 0xF2, 0x6B, 0x6F, 0xC5, 0x30, 0x01, 0x67, 0x2B, 0xFE, 0xD7, 0xAB, 0x76,
    0xCA, 0x82, 0xC9, 0x7D, 0xFA, 0x59, 0x47, 0xF0, 0xAD, 0xD4, 0xA2, 0xAF, 0x9C, 0xA4, 0x72, 0xC0,
    0xB7, 0xFD, 0x93, 0x26, 0x36, 0x3F, 0xF7, 0xCC, 0x34, 0xA5, 0xE5, 0xF1, 0x71, 0xD8, 0x31, 0x15,
    0x04, 0xC7, 0x23, 0xC3, 0x18, 0x96, 0x05, 0x9A, 0x07, 0x12, 0x80, 0xE2, 0xEB, 0x27, 0xB2, 0x75,
    0x09, 0x83, 0x2C, 0x1A, 0x1B, 0x6E, 0x5A, 0xA0, 0x52, 0x3B, 0xD6, 0xB3, 0x29, 0xE3, 0x2F, 0x84,
    0x53, 0xD1, 0x00, 0xED, 0x20, 0xFC, 0xB1, 0x5B, 0x6A, 0xCB, 0xBE, 0x39, 0x4A, 0x4C, 0x58, 0xCF,
    0xD0, 0xEF, 0xAA, 0xFB, 0x43, 0x4D, 0x33, 0x85, 0x45, 0xF9, 0x02, 0x7F, 0x50, 0x3C, 0x9F, 0xA8,
    0x51, 0xA3, 0x40, 0x8F, 0x92, 0x9D, 0x38, 0xF5, 0xBC, 0xB6, 0xDA, 0x21, 0x10, 0xFF, 0xF3, 0xD2,
    0xCD, 0x0C, 0x13, 0xEC, 0x5F, 0x97, 0x44, 0x17, 0xC4, 0xA7, 0x7E, 0x3D, 0x64, 0x5D, 0x19, 0x73,
    0x60, 0x81, 0x4F, 0xDC, 0x22, 0x2A, 0x90, 0x88, 0x46, 0xEE, 0xB8, 0x14, 0xDE, 0x5E, 0x0B, 0xDB,
    0xE0, 0x32, 0x3A, 0x0A, 0x49, 0x06, 0x24, 0x5C, 0xC2, 0xD3, 0xAC, 0x62, 0x91, 0x95, 0xE4, 0x79,
    0xE7, 0xC8, 0x37, 0x6D, 0x8D, 0xD5, 0x4E, 0xA9, 0x6C, 0x56, 0xF4, 0xEA, 0x65, 0x7A, 0xAE, 0x08,
    0xBA, 0x78, 0x25, 0x2E, 0x1C, 0xA6, 0xB4, 0xC6, 0xE8, 0xDD, 0x74, 0x1F, 0x4B, 0xBD, 0x8B, 0x8A,
    0x70, 0x3E, 0xB5, 0x66, 0x48, 0x03, 0xF6, 0x0E, 0x61, 0x35, 0x57, 0xB9, 0x86, 0xC1, 0x1D, 0x9E,
    0xE1, 0xF8, 0x98, 0x11, 0x69, 0xD9, 0x8E, 0x94, 0x9B, 0x1E, 0x87, 0xE9, 0xCE, 0x55, 0x28, 0xDF,
    0x8C, 0xA1, 0x89, 0x0D, 0xBF, 0xE6, 0x42, 0x68, 0x41, 0x99, 0x2D, 0x0F, 0xB0, 0x54, 0xBB, 0x16,
)

inv_s_box = (
    0x52, 0x09, 0x6A, 0xD5, 0x30, 0x36, 0xA5, 0x38, 0xBF, 0x40, 0xA3, 0x9E, 0x81, 0xF3, 0xD7, 0xFB,
    0x7C, 0xE3, 0x39, 0x82, 0x9B, 0x2F, 0xFF, 0x87, 0x34, 0x8E, 0x43, 0x44, 0xC4, 0xDE, 0xE9, 0xCB,
    0x54, 0x7B, 0x94, 0x32, 0xA6, 0xC2, 0x23, 0x3D, 0xEE, 0x4C, 0x95, 0x0B, 0x42, 0xFA, 0xC3, 0x4E,
    0x08, 0x2E, 0xA1, 0x66, 0x28, 0xD9, 0x24, 0xB2, 0x76, 0x5B, 0xA2, 0x49, 0x6D, 0x8B, 0xD1, 0x25,
    0x72, 0xF8, 0xF6, 0x64, 0x86, 0x68, 0x98, 0x16, 0xD4, 0xA4, 0x5C, 0xCC, 0x5D, 0x65, 0xB6, 0x92,
    0x6C, 0x70, 0x48, 0x50, 0xFD, 0xED, 0xB9, 0xDA, 0x5E, 0x15, 0x46, 0x57, 0xA7, 0x8D, 0x9D, 0x84,
    0x90, 0xD8, 0xAB, 0x00, 0x8C, 0xBC, 0xD3, 0x0A, 0xF7, 0xE4, 0x58, 0x05, 0xB8, 0xB3, 0x45, 0x06,
    0xD0, 0x2C, 0x1E, 0x8F, 0xCA, 0x3F, 0x0F, 0x02, 0xC1, 0xAF, 0xBD, 0x03, 0x01, 0x13, 0x8A, 0x6B,
    0x3A, 0x91, 0x11, 0x41, 0x4F, 0x67, 0xDC, 0xEA, 0x97, 0xF2, 0xCF, 0xCE, 0xF0, 0xB4, 0xE6, 0x73,
    0x96, 0xAC, 0x74, 0x22, 0xE7, 0xAD, 0x35, 0x85, 0xE2, 0xF9, 0x37, 0xE8, 0x1C, 0x75, 0xDF, 0x6E,
    0x47, 0xF1, 0x1A, 0x71, 0x1D, 0x29, 0xC5, 0x89, 0x6F, 0xB7, 0x62, 0x0E, 0xAA, 0x18, 0xBE, 0x1B,
    0xFC, 0x56, 0x3E, 0x4B, 0xC6, 0xD2, 0x79, 0x20, 0x9A, 0xDB, 0xC0, 0xFE, 0x78, 0xCD, 0x5A, 0xF4,
    0x1F, 0xDD, 0xA8, 0x33, 0x88, 0x07, 0xC7, 0x31, 0xB1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xEC, 0x5F,
    0x60, 0x51, 0x7F, 0xA9, 0x19, 0xB5, 0x4A, 0x0D, 0x2D, 0xE5, 0x7A, 0x9F, 0x93, 0xC9, 0x9C, 0xEF,
    0xA0, 0xE0, 0x3B, 0x4D, 0xAE, 0x2A, 0xF5, 0xB0, 0xC8, 0xEB, 0xBB, 0x3C, 0x83, 0x53, 0x99, 0x61,
    0x17, 0x2B, 0x04, 0x7E, 0xBA, 0x77, 0xD6, 0x26, 0xE1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0C, 0x7D,
)

def bytes2matrix(text):
    return [list(text[i:i+4]) for i in range(0, len(text), 4)]

def matrix2bytes(matrix):
    result = b""
    for row in matrix :
        result += bytes(row)
    return result

def add_round_key(s, k):
    return [[s[row][col] ^ k[row][col] for col in range(4)] for row in range(4)]

def shift_rows(s):
    s[0][1], s[1][1], s[2][1], s[3][1] = s[1][1], s[2][1], s[3][1], s[0][1]
    s[0][2], s[1][2], s[2][2], s[3][2] = s[2][2], s[3][2], s[0][2], s[1][2]
    s[0][3], s[1][3], s[2][3], s[3][3] = s[3][3], s[0][3], s[1][3], s[2][3]
    return s

def inv_shift_rows(s):
    s[1][1], s[2][1], s[3][1], s[0][1] = s[0][1], s[1][1], s[2][1], s[3][1]
    s[2][2], s[3][2], s[0][2], s[1][2] = s[0][2], s[1][2], s[2][2], s[3][2]
    s[3][3], s[0][3], s[1][3], s[2][3] = s[0][3], s[1][3], s[2][3], s[3][3]
    return s

# learned from http://cs.ucsb.edu/~koc/cs178/projects/JT/aes.c
xtime = lambda a: (((a << 1) ^ 0x1B) & 0xFF) if (a & 0x80) else (a << 1)

def mix_single_column(a):
    # see Sec 4.1.2 in The Design of Rijndael
    t = a[0] ^ a[1] ^ a[2] ^ a[3]
    u = a[0]
    a[0] ^= t ^ xtime(a[0] ^ a[1])
    a[1] ^= t ^ xtime(a[1] ^ a[2])
    a[2] ^= t ^ xtime(a[2] ^ a[3])
    a[3] ^= t ^ xtime(a[3] ^ u)


def mix_columns(s):
    for i in range(4):
        mix_single_column(s[i])
    return s


def inv_mix_columns(s):
    # see Sec 4.1.3 in The Design of Rijndael
    for i in range(4):
        u = xtime(xtime(s[i][0] ^ s[i][2]))
        v = xtime(xtime(s[i][1] ^ s[i][3]))
        s[i][0] ^= u
        s[i][1] ^= v
        s[i][2] ^= u
        s[i][3] ^= v

    mix_columns(s)
    return s

def sub_bytes(s, sbox=s_box):
    return [[sbox[i] for i in row] for row in s]

def inv_sub_bytes(s) :
    return sub_bytes(s, inv_s_box)

def expand_key(master_key, N_ROUNDS):
    """
    Expands and returns a list of key matrices for the given master_key.
    """

    # Round constants https://en.wikipedia.org/wiki/AES_key_schedule#Round_constants
    r_con = (
        0x00, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40,
        0x80, 0x1B, 0x36, 0x6C, 0xD8, 0xAB, 0x4D, 0x9A,
        0x2F, 0x5E, 0xBC, 0x63, 0xC6, 0x97, 0x35, 0x6A,
        0xD4, 0xB3, 0x7D, 0xFA, 0xEF, 0xC5, 0x91, 0x39,
    )

    # Initialize round keys with raw key material.
    key_columns = bytes2matrix(master_key)
    iteration_size = len(master_key) // 4

    # Each iteration has exactly as many columns as the key material.
    i = 1
    while len(key_columns) < (N_ROUNDS + 1) * 4:
        # Copy previous word.
        word = list(key_columns[-1])

        # Perform schedule_core once every "row".
        if len(key_columns) % iteration_size == 0:
            # Circular shift.
            word.append(word.pop(0))
            # Map to S-BOX.
            word = [s_box[b] for b in word]
            # XOR with first byte of R-CON, since the others bytes of R-CON are 0.
            word[0] ^= r_con[i]
            i += 1
        elif len(master_key) == 32 and len(key_columns) % iteration_size == 4:
            # Run word through S-box in the fourth iteration when using a
            # 256-bit key.
            word = [s_box[b] for b in word]

        # XOR with equivalent word from previous iteration.
        word = [i^j for i, j in zip(word, key_columns[-iteration_size])]
        key_columns.append(word)

    # Group key words in 4x4 byte matrices.
    return [key_columns[4*i : 4*(i+1)] for i in range(len(key_columns) // 4)]