66 lines
2.6 KiB
Python
66 lines
2.6 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/>.
|
||
|
|
#
|
||
|
|
from huffman_py.fonctions.occurence import *
|
||
|
|
from huffman_py.fonctions.calcul_code import *
|
||
|
|
from huffman_py.fonctions.affichage_binaire import *
|
||
|
|
from huffman_py.Sommets import Sommets
|
||
|
|
from huffman_py.Arbre import Arbre
|
||
|
|
|
||
|
|
def huffman_encode(the_data):
|
||
|
|
lettres_et_occurences = calcul_occurence(the_data)
|
||
|
|
|
||
|
|
# affichage des lettres et occurences associées (vérification bon fonctionnement)
|
||
|
|
les_lettres = lettres_et_occurences.keys()
|
||
|
|
les_occurences = lettres_et_occurences.values()
|
||
|
|
print("lettres: ", les_lettres)
|
||
|
|
print("occurences: ", les_occurences)
|
||
|
|
|
||
|
|
les_sommets = []
|
||
|
|
|
||
|
|
# conversion des lettres et occurences en sommets
|
||
|
|
for lettres in les_lettres:
|
||
|
|
les_sommets.append(Sommets(lettres_et_occurences.get(lettres), lettres))
|
||
|
|
|
||
|
|
while len(les_sommets) > 1:
|
||
|
|
# tri des sommets par ordre croissant
|
||
|
|
les_sommets = sorted(les_sommets, key = lambda x: x.occurrence)
|
||
|
|
#for node in les_sommets:
|
||
|
|
# print(node.lettres, node.occurrence)
|
||
|
|
|
||
|
|
# on récupère les 2 plus petits sommets
|
||
|
|
left = les_sommets[0]
|
||
|
|
right = les_sommets[1]
|
||
|
|
|
||
|
|
left.code = 0
|
||
|
|
right.code = 1
|
||
|
|
|
||
|
|
# on combine les 2 sommets précédents
|
||
|
|
nouveau_sommet = Sommets(left.occurrence + right.occurrence, left.lettres + right.lettres, left, right)
|
||
|
|
#nouveau_sommet = Sommets(left.occurrence + right.occurrence, 'a', left, right)
|
||
|
|
|
||
|
|
les_sommets.remove(left)
|
||
|
|
les_sommets.remove(right)
|
||
|
|
les_sommets.append(nouveau_sommet)
|
||
|
|
|
||
|
|
mon_arbre = Arbre(les_sommets[0])
|
||
|
|
|
||
|
|
huffmanEncoding = calcul_code(les_sommets[0])
|
||
|
|
print("lettres avec codes", huffmanEncoding)
|
||
|
|
encodedOutput = affichage_binaire(the_data,huffmanEncoding)
|
||
|
|
return encodedOutput, les_sommets[0], huffmanEncoding
|