1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
|
import csv
alphabet=["a","b","c","d","e","f","g","h","i","j","k","l","m","n","o","p","q","r","s","t","u","v","w","x","y","z"]
###decodage code césar###
def decodage_césar(texte,decalage:int):
nv=""
global alphabet
for lettre in texte:
if lettre in alphabet:
ind=alphabet.index(lettre)
ind=ind-decalage
if ind<0:
ind=26+ind
print(ind,len(texte))
lettre=alphabet[ind]
nv+=lettre
else:
nv+=lettre
return nv
def csv(nomFichier):
"""Fonction qui importe un fichier csv sous la forme d'une liste de
tuples en sautant la ligne d'entêtes"""
freq = {}
csvfile = open(nomFichier, 'r', newline='')
tableReader = csv.reader(csvfile, delimiter=';')
tableReader.__next__() # permet de sauter une ligne (la ligne d'entête lorsqu'elle existe)
for row in tableReader:
freq.append({row[0]:row[1]})
return freq
def test(texte):
écart=0
freq_fr={"a":7.11,"b":1.14,"c":3.18,"d":3.67,"e":12.10,"f":1.11,"g":1.23,"h":1.11,"i":6.59,"j":0.34,"k":0.29,"l":4.96,"m":2.62,"n":6.39,"o":5.02,"p":2.49,"q":0.65,"r":6.07,"s":6.51,"t":5.92,"u":4.49,"v":1.11,"w":0.17,"x":0.38,"y":0.46,"z":0.15}
#frequence d'apparition de lettre en français en pourcentage
freq_texte={"a":0,"b":0,"c":0,"d":0,"e":0,"f":0,"g":0,"h":0,"i":0,"j":0,"k":0,"l":0,"m":0,"n":0,"o":0,"p":0,"q":0,"r":0,"s":0,"t":0,"u":0,"v":0,"w":0,"x":0,"y":0,"z":0}
#frequence d'apparition de lettre dans le texte
ban=[" ","'","(",")",",","?","1","2","3","4","5","6","7","8","9",'"',"’",".","-","_","!","\n","«","»"]
#les caractère/nombre bannies pour le test
for lettre in texte:
if lettre not in ban:
freq_texte[lettre]+=1
#on ajoute +1 a chaque fois que la lettre est dans le texte
for i in alphabet:
freq_texte[i]=freq_texte[i]/len(texte)*100
#on calcule le pourcantage d'apparition
for i in alphabet:
écart=freq_texte[i]/freq_fr[i]
#on calcule la marge d'erreur
return (écart/len(freq_texte))*-1
#on le met en negatif pour un trie + efficace
def detection(texte):
compatibilité=[]
for i in range(len(alphabet)+1):
compatibilité.append((test(decodage_césar(texte,i)),i))
compatibilité.sort()
#on ajoute le resultat de toute les possibilité et on trie la liste
#ainsi la meilleur possibilité est la première
compatibilité=int(compatibilité[0][1])
#on prend le decalge pour décodé
return decodage_césar(texte,compatibilité)
texte="""papc ijgxcv thi jc bpiwtbpixrxtc, rgneidadvjt, exdccxtg st a’xcudgbpixfjt, st a’xcitaaxvtcrt pgixuxrxtaat ti st ap bdgewdvtctht tc qxdadvxt. papc bpiwxhdc ijgxcv cpxi at 23 yjxc 1912 p adcsgth. hdc etgt thi psbxcxhigpitjg rdadcxpa p bpsgph tc xcst. pj bpaqdgdjvw rdaatvt, hth sdch wdgh sj rdbbjc hdci kxit gtrdccjh. psdathrtci gtugpripxgt p ap rjaijgt raphhxfjt, hdc vdji edjg ath hrxtcrth ti hdc wdbdhtmjpaxit at bpgvxcpaxhtci p ap hwtgqdgct hrwdda. p 17 pch, ijgxcv rdbegtcs ath gtrwtgrwth s’txchitxc, bpxh rdccpxi sth trwtrh gtetith p hth tmpbtch. tc 1931, xa xcitvgt at zxcv’h rdaatvt st a’jcxktghxit st rpbqgxsvt dj xa igdjkt jc bxaxtj eajh upkdgpqat edjg tijsxtg ath bpiwtbpixfjth.sxeadbt tc 1933, papc ijgxcv p aj ath ejqaxrpixdch st zjgi vosta ti st kdc ctjbpcc hjg at udcstbtci sth bpiwtbpixfjth fjx xcuajtcrtci hth igpkpjm, vgprt pjmfjtah xa dqixtci jct qdjght s’tchtxvcpci rwtgrwtjg tc 1935. xa gthdji at egdqatbt st ap strxhxdc stuxcx epg spkxs wxaqtgi, ejxh h’xchrgxi tc sdridgpi st advxfjt bpiwtbpixfjt p a’jcxktghxit st egxcrtidc hdjh ap sxgtrixdc s’padcod rwjgrw, jc advxrxtc pbtgxrpxc fjx thi pggxkt pjm btbth rdcrajhxdch. xa stktadeet spch hp iwtht ap cdixdc s’wnetgrparja ti peejxt hp stbdchigpixdc hjg jct "bprwxct jcxktghtaat", jc dgsxcpitjg fjx thi tcrdgt jct pqhigprixdc. pavdgxiwbth, rparjapqxaxit - ath rdcrteih st ap egdvgpbbpixdc hdci edhth ti ap kdxt thi djktgit pjm dgsxcpitjgh egdvgpbbpqath. tc 1939, papc ijgxcv gtkxtci tchtxvctg p rpbqgxsvt dj xa phhxhit pj rdjgh st lxiivtchitxc fjx egtitcs sxhhdjsgt ap advxfjt bpiwtbpixfjt ! ap htrdcst vjtggt bdcsxpat trapit ti ijgxcv h’tcvpvt spch a’pgbtt qgxipccxfjt dj xa igpkpxaat p qatirwatn epgz pj strwxuugtbtci sth bthhpvth st ap bpgxct paatbpcst. hdc peedgi thi thhtcixta, rpg ijgxcv pbtaxdgt ap "qdbqt" edadcpxht, jc sxhedhxixu fjx etgbti st strwxuugtg at rdst sth bprwxcth tcxvbp jixaxhtth epg at
rdbbpcstbtci cpox. pegth ap vjtggt, papc ijgxcv igpkpxaat pj cpixdcpa ewnhxrpa apqdgpidgn ti rdcrdxi jc egdidinet st rparjapitjg tatrigdcxfjt, a’prt ( pjidbpixr rdbejixcv tcvxct), fjx egtcs sj gtipgs spch hp gtpaxhpixdc. pjhhx xa gtydxci a’jcxktghxit st bpcrwthitg fjx pkpxi rdchigjxi tc 1948 at egtbxtg dgsxcpitjg egdvgpbbpqat detgpixdccta, at bpgz1. ijgxcv epgixrxet p ap egdvgpbbpixdc ti ht ephhxdcct edjg a’xcitaaxvtcrt pgixuxrxtaat. xa tapqdgt jc ithi fjx kpaxst a’xcitaaxvtcrt s’jct bprwxct, at upbtjm "ithi st ijgxcv." epgpaatatbtci, xa h’xcitgthht pjm ewtcdbtcth st rgdxhhpcrt pcxbpat ti ktvtipat fjx at rdcsjxhtci pjm « higjrijgth st ijgxcv ». taj btbqgt st ap gdnpa hdrxtin, ijgxcv tegdjkt st vgpkth sxuuxrjaith fjpcs ap gtktapixdc st hdc wdbdhtmjpaxit egdkdfjt jc hrpcspat tc 1952. r’thi jc rgxbt edjg ap yjhixrt qgxipccxfjt. at egdrth at rdcspbct p ap egxhdc. edjg tkxitg a’tcutgbtbtci, papc ijgxcv thi rdcigpxci s’prrteitg ap rphigpixdc rwxbxfjt, bpxh hp rpggxtgt thi qgxhtt. xa ht hjxrxst p 42 pch tc rgdfjpci jct edbbt igtbett spch sj rnpcjgt at 7 yjxc 1954.
"""
#print(csv("freq_lettre_fr.csv")
print(detection(texte)) |
