from algorithms.BurrowsWheelerTransform import BurrowsWheelerTransform
from algorithms.MoveToFront import MoveToFront
from algorithms.Utils import Utils
burrowsWheelerTransform = BurrowsWheelerTransform()
moveToFront = MoveToFront()
utils = Utils()
arithmetic_encoded_file_name = "output/arithmetic_encoded.txt"
bwt_decoded_file_name = "output/bwt_decoded.txt"
mtf_decoded_file_name = "output/mtf_decoded.txt"
arithmetic_decoded_file_name = "output/arithmetic_decoded.txt"
utils.arithmetic_decode(arithmetic_encoded_file_name,
arithmetic_decoded_file_name)
utils.replace_file_endings(arithmetic_decoded_file_name)
mtf_encoded_file = open(arithmetic_decoded_file_name, "r")
code_list = [int(i) for i in mtf_encoded_file.read().split(" ")]
mtf_decoded_file = open(mtf_decoded_file_name, "w+")
decode = moveToFront.decode(code_list)
mtf_decoded_file.write(decode)
mtf_decoded_file.close()
# decode
bwt_encoded_file = open(mtf_decoded_file_name, "r")
bwt_decoded_file = open(bwt_decoded_file_name, "w+")
for byte_string in bwt_encoded_file.read().split("]"):
text = byte_string.split('[')
if len(text) > 1:
from algorithms.BurrowsWheelerTransform import BurrowsWheelerTransform
from algorithms.Utils import Utils
burrowsWheelerTransform = BurrowsWheelerTransform()
utils = Utils()
block_size = 8192
raw_file_name = "samples/dickens.txt"
bwt_encoded_file_name = "output/bwt_encoded.txt"
bwt_decoded_file_name = "output/bwt_decoded.txt"
utils.replace_file_endings(raw_file_name)
# encode
bwt_encoded_file = open(bwt_encoded_file_name, "w+")
with open(raw_file_name, mode='rb') as f:
while True:
byte = f.read(block_size)
if len(byte.decode()) > 0:
index, encoded = burrowsWheelerTransform.code(byte.decode())
bwt_encoded_file.write(str(index))
bwt_encoded_file.write('[')
bwt_encoded_file.write(encoded)
bwt_encoded_file.write("]")
if not byte:
break
bwt_encoded_file.close()
# decode
bwt_encoded_file = open(bwt_encoded_file_name, "r")
bwt_decoded_file = open(bwt_decoded_file_name, "w+")
from algorithms.BurrowsWheelerTransform import BurrowsWheelerTransform
from algorithms.MoveToFront import MoveToFront
from algorithms.Utils import Utils
import time
t1 = time.time()
burrowsWheelerTransform = BurrowsWheelerTransform()
moveToFront = MoveToFront()
utils = Utils()
block_size = 8192
raw_file_name = "samples/mobydick.txt"
bwt_encoded_file_name = "output/bwt_encoded.txt"
mtf_encoded_file_name = "output/mtf_encoded.txt"
arithmetic_encoded_file_name = "output/arithmetic_encoded.bin"
utils.replace_file_endings(raw_file_name)
# encode bwt
bwt_encoded_file = open(bwt_encoded_file_name, mode='w+')
with open(raw_file_name, "rb") as f:
while True:
byte = f.read(block_size)
if len(byte.decode()) > 0:
index, encoded = burrowsWheelerTransform.code(byte.decode())
bwt_encoded_file.write(str(index))
bwt_encoded_file.write('[')
bwt_encoded_file.write(encoded)
bwt_encoded_file.write("]")
if not byte:
break
bwt_encoded_file.close()
from algorithms.MoveToFront import MoveToFront
from algorithms.Utils import Utils
moveToFront = MoveToFront()
utils = Utils()
bwt_encoded_file_name = "output/bwt_encoded.txt"
mtf_encoded_file_name = "output/mtf_encoded.txt"
mtf_decoded_file_name = "output/mtf_decoded.txt"
utils.replace_file_endings(bwt_encoded_file_name)
# encode
bwt_encoded_file = open(bwt_encoded_file_name, "r")
encode = moveToFront.code(bwt_encoded_file.read())
mtf_encoded_file = open(mtf_encoded_file_name, "w+")
mtf_encoded_file.write(' '.join(map(str, encode)))
mtf_encoded_file.close()
# decode
mtf_encoded_file = open(mtf_encoded_file_name, "r")
code_list = [int(i) for i in mtf_encoded_file.read().split(" ")]
mtf_decoded_file = open(mtf_decoded_file_name, "w+")
decode = moveToFront.decode(code_list)
mtf_decoded_file.write(decode)
mtf_decoded_file.close()