import PQHeap
import bitIO
'''
Authors:
Sofie Louise Madsen - [email protected]
Joachim Bülow - [email protected]
Simon Soele Madsen - [email protected]
'''
# Open the files in readbit and write binary mode
inputfile = open(sys.argv[1], "rb")
outputfile = open(sys.argv[2], "wb")
# Instantiate our bitwriter for writing to output file
bitstreamout = bitIO.BitWriter(outputfile)
# 2 arrays for keeping track of the occurrences of each character/byte
# and the Huffman codes from root to the leaf containing the byte for each byte.
occurences = 256 * [0]
codes = 256 * [0]
# reads the input file and counts the occurence of each byte
def read_file_occurences():
while True:
byte = inputfile.read(1)
if byte == b"":
break
else:
# We have a byte --> translate to integer with [0], increment occurence of that index.
occurences[byte[0]] += 1
# The file paths are declared, either from commandline arguments or simple inputs
if len(sys.argv) == 3:
inPath = sys.argv[1]
outPath = sys.argv[2]
else:
inPath = input('Write name of file to compress:')
outPath = input('Write name of compressed file:')
# The files are opened in binarymode seen by the 'rb' and 'wb'
# We stream the files
inFile = open(inPath, 'rb')
outFile = open(outPath, 'wb')
# streams for input and output file
bitstreamin = bitIO.BitReader(inFile)
bitstreamout = bitIO.BitWriter(outFile)
# The block size of the encoding is defined, in bytes
# and the required size of the table is calculated from that
blockSize = 1 #byte
tableSize = 2**(blockSize * 8)
# A table with 2^blockSize inquries, one for each of the possible bytes
table = [0] * tableSize
# Here we populate the frequency table,
# by incrementing the table in the position corresponding to the byte read
# The while loop continues as long as there are more bytes to read
byte = inFile.read(blockSize)
while byte != b'':
table[byte[0]] += 1