82 lines
3.1 KiB
Python
82 lines
3.1 KiB
Python
#
|
|
# Sam Hadow - Huffman-py
|
|
# Copyright (C) 2023
|
|
#
|
|
# This program is free software: you can redistribute it and/or modify
|
|
# it under the terms of the GNU General Public License as published by
|
|
# the Free Software Foundation, either version 3 of the License, or
|
|
# (at your option) any later version.
|
|
#
|
|
# This program is distributed in the hope that it will be useful,
|
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
# GNU General Public License for more details.
|
|
#
|
|
# You should have received a copy of the GNU General Public License
|
|
# along with this program. If not, see <http://www.gnu.org/licenses/>.
|
|
#
|
|
import re
|
|
|
|
def huffman_decode(encodedData, current_node):
|
|
root = current_node
|
|
decodedOutput = []
|
|
|
|
# if single node in source tree (unique char in the text)
|
|
if (not root.left and not root.right):
|
|
string = ''.join([root.char for _ in encodedData])
|
|
return string
|
|
|
|
# else
|
|
for x in encodedData:
|
|
if x == '1':
|
|
current_node = current_node.right
|
|
elif x == '0':
|
|
current_node = current_node.left
|
|
|
|
# If internal node we keep going down, else (a leaf) we can decode a part of the binary.
|
|
try:
|
|
# internal node
|
|
if current_node.left.char == None and current_node.right.char == None:
|
|
pass
|
|
except AttributeError:
|
|
# leaf
|
|
decodedOutput.append(current_node.char)
|
|
current_node = root
|
|
|
|
if current_node != root and (current_node.right !=None or current_node.left != None):
|
|
# If we end on an internal node then source tree wasn't the correct tree.
|
|
raise ValueError ("Tree and binary don't correspond.")
|
|
|
|
string = ''.join([str(item) for item in decodedOutput])
|
|
return string
|
|
|
|
def decode_from_dict(encodedData, dict_):
|
|
# we have a Dict like this: {char:code}
|
|
# we convert it to a Dict like that: {code:char} (both codes and chars are unique)
|
|
dict_ = {value:key for key,value in dict_.items()}
|
|
text = str(encodedData)
|
|
|
|
# we check if we have a binary
|
|
invalid_char = re.compile('[^01]')
|
|
if invalid_char.search(text):
|
|
raise TypeError ('Input text must be a binary.')
|
|
|
|
decoded = ''
|
|
sorted_dict = dict(sorted(dict_.items(), key=lambda x: len(x[0]), reverse=False))
|
|
while len(text) > 0:
|
|
for i,binary in enumerate(sorted_dict.keys()):
|
|
if binary == text[0:len(binary)]:
|
|
# If we have this binary part in our Dict we can decode a char
|
|
decoded += sorted_dict[binary]
|
|
# delete decoded part
|
|
text = text[len(binary):]
|
|
# next while iteration
|
|
break
|
|
|
|
# if nothing corresponds then it's not the correct Dict
|
|
elif i == len(sorted_dict.keys())-1:
|
|
raise ValueError ("Can't convert text with current Dict.")
|
|
return decoded
|
|
|
|
|