Last active
November 8, 2019 20:56
-
-
Save Epithumia/7374e61398a6fb0985e78949ef3a9c6b to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Prendre https://github.com/hbenbel/French-Dictionary -> le fichier avec tous les mots/verbes/etc | |
from itertools import product, groupby | |
import unicodedata | |
mots = ['', 'REPONSE', 'ETONNANTE', 'DE', 'LA', 'PART', 'DE', 'NOS', 'GRANDS', 'ASTRES', | |
'FORT', 'PEU', 'CONCLUANTE', 'BIEN', 'QUE', 'NENNI', 'LANCONS', 'NOUS', 'TOUT', 'DE', 'MEME'] | |
phrase = [[3,1,10,20,14,5], [6,4,15,17], [12,2], [19,4,18,20], [3,13], | |
[6,15,11,4,10,18], [4], [15,7,18,11,10], [5,3,12,9,4,15,13,10,4,8,14], | |
[15,19,12,11,7,17,5,13,10,20]] | |
with open('liste_francais.txt', 'r') as liste: | |
dico = liste.readlines() | |
dico_plein = [unicodedata.normalize("NFD", x.strip()).encode('ascii', 'ignore').decode('utf-8') for x in dico] | |
dico = [] | |
for i in range(12): | |
dico.append([]) | |
for mot in dico_plein: | |
if len(mot) <= 11: | |
dico[len(mot)].append(mot.upper()) | |
del dico_plein | |
i = 0 | |
for m in phrase: | |
mot = [] | |
ens = [] | |
for l in m: | |
poss = [] | |
pre = sorted(mots[l]) | |
mot_s = ''.join(ch for ch, _ in groupby(pre)) | |
for c in mot_s: | |
poss.append(c) | |
ens.append(poss) | |
p = list(product(*ens)) | |
i += 1 | |
bound = len(p) | |
st = int(bound / 100) | |
print(i, '[' + str(bound )+ ']') | |
ans = [] | |
count=0 | |
for item in p: | |
count+=1 | |
if st > 1000 and count%st == 0: | |
print(count/st, '%\r', end="") | |
w = ''.join(item) | |
if w in dico[len(w)]: | |
ans.append(w) | |
elif w[0:2] == 'RE' and w[2:] in dico[len(w[2:])]: | |
ans.append(w) | |
print(list(set(ans))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment