def bruteForce(self, ciphertext, minReadRate=0.4): """Brute forces all the keys provided by SubClass. minReadRate enforces minimum rate of readable chars""" bestKey = None lowestChi2 = 100000 if self.onlyLowerCase(): ciphertext = ciphertext.lower() for key in self.genKeys(): # genKeys and decrypt are the subclass functions maybePlaintext = self.decrypt(ciphertext,key) if minReadRate > 0.0: readPerc = len([c for c in maybePlaintext if utils.isAlpha(c)]) / len(maybePlaintext) if readPerc < minReadRate: continue chi2 = utils.calcChiSquared(maybePlaintext) if chi2 < lowestChi2: bestKey = key lowestChi2 = chi2 #print(utils.calcTrigraphFitness(self.decrypt(ciphertext, bestKey))) return (bestKey, lowestChi2)
def rot(self, plaintext, shift):
ciphertext = ''
lowera = ord('a')
for c in plaintext:
if utils.isAlpha(c):
ciphertext += chr((
(ord(c) - lowera + shift) % utils.ALPHABET_SIZE) + lowera)
else:
ciphertext += c
return ciphertext
def encrypt(self, plaintext, key):
(a,b) = key
ciphertext = ''
lowera = ord('a')
for c in plaintext:
if utils.isAlpha(c):
x = ord(c)-lowera
y = (a*x+b) % utils.ALPHABET_SIZE
ciphertext += chr(lowera+y)
else:
ciphertext += c
return ciphertext
def decrypt(self, ciphertext, key):
(a,b) = key
plaintext = ''
lowera = ord('a')
for c in ciphertext:
if utils.isAlpha(c):
x = ord(c)-lowera
y = (utils.multInverse(a, utils.ALPHABET_SIZE)*(x-b)) % utils.ALPHABET_SIZE
plaintext += chr(lowera+y)
else:
plaintext += c
return plaintext
def encrypt(self, plaintext, key):
ciphertext = ''
lowera = ord('a')
keylen = len(key)
keyIndex = 0
for c in plaintext:
if utils.isAlpha(c):
shift = ord(key[keyIndex]) - lowera
ciphertext += chr((
(ord(c) - lowera + shift) % utils.ALPHABET_SIZE) + lowera)
keyIndex = (keyIndex + 1) % keylen # Updating the key
else:
ciphertext += c # key not updated
return ciphertext
def crack(self, ciphertext):
keyLen = self.findKeyLength(ciphertext, KEY_LENGTH_UPPER_BOUND)
key = ''
lowera = ord('a')
for i in range(
keyLen): # gets each Caesar text embedded in the ciphertext
subtext = ''
j = i
while j < len(ciphertext):
c = ciphertext[j]
if utils.isAlpha(c):
subtext += c
j += keyLen
lowestShift = 0
lowestChi2 = 100000
for j in range(min(utils.ALPHABET_SIZE, len(ciphertext))):
maybePlaintext = self.rot(subtext, j)
chi2 = utils.calcChiSquared(maybePlaintext)
if chi2 < lowestChi2:
lowestShift = j
lowestChi2 = chi2
keyShift = 0
if lowestShift != 0:
keyShift = 26 - lowestShift # We found the amount to shift for decryption, now we want the encryption key
key += chr(keyShift + lowera)
key = self.refineKey(key)
plaintext = self.decrypt(ciphertext, key)
chi2 = utils.calcChiSquared(plaintext)
return (key, chi2)
def token_recognition(token, digitDFA, charDFA, stringDFA, commentDFA, o_H_DFA,
line_number, character_table, token_l, error_l):
#关键字和标识符
if isAlpha(token[0]):
if token in keywords:
# print(token + "\t<关键字\t" + token + ">\t" + str(line_number))
# if token + "\t关键字\t" + token + "\t" + str(line_number) not in token_l:
token_l.append(token + "\t关键字\t" + token + "\t" + str(line_number))
else:
if token not in character_table:
character_table.append(token)
# print(token + "\t<标识符\t" + token + ">\t" + str(line_number))
if token + "\t标识符\t" + token + "\t" + str(
line_number) not in token_l:
token_l.append(token + "\t标识符\t" + token + "\t" +
str(line_number))
if isOp(token[0]):
# print(token + "\t<运算符\t" + token + ">\t" + str(line_number))
#if token + "\t运算符\t" + token + "\t" + str(line_number) not in token_l:
token_l.append(token + "\t运算符\t" + token + "\t" + str(line_number))
if isDigit(token[0]):
digitDFA_result, isfloat = digitDFA.in_digitDFA(token)
if digitDFA_result:
if isfloat:
# print(token + "\t<浮点型常量\t" + token + ">\t" + str(line_number))
#if token + "\t浮点型常量\t" + token + "\t" + str(line_number) not in token_l:
token_l.append(token + "\t浮点型常量\t" + token + "\t" +
str(line_number))
else:
# print(token + "\t整形常量\t" + token + "\t" + str(line_number))
#if token + "\t整形常量\t" + token + "\t" + str(line_number) not in token_l:
token_l.append(token + "\t整形常量\t" + token + "\t" +
str(line_number))
o_H_DFA_result, error_message, is_octal = o_H_DFA.in_O_H_DFA(token)
if o_H_DFA_result:
if is_octal:
# print(token + "\t<八进制常量\t" + token+ ">\t" + str(line_number))
#if token + "\t八进制常量\t" + token+ "\t" + str(line_number) not in token_l:
token_l.append(token + "\t八进制常量\t" + token + "\t" +
str(line_number))
else:
# print(token + "\t<十六进制常量\t" + token + ">\t" + str(line_number))
#if token + "\t十六进制常量\t" + token + "\t" + str(line_number) not in token_l:
token_l.append(token + "\t十六进制常量\t" + token + "\t" +
str(line_number))
if not digitDFA_result and not o_H_DFA_result:
# print("错误:在" + str(line_number) + "行, 试图将" + token + "解析为数字型常量发生错误!")
#if "错误:在" + str(line_number) + "行, 试图将" + token + "解析为数字型常量发生错误!" not in error_l:
error_l.append("错误:在" + str(line_number) + "行, 试图将" + token +
"解析为数字型常量发生错误!")
if isChar(token[0]):
charDFA_result, error_message = charDFA.in_charDFA(token)
if charDFA_result:
# print(token + "\t<字符型常量\t" + token + ">\t" + str(line_number))
#if token + "\t字符型常量\t" + token + "\t" + str(line_number) not in error_l:
token_l.append(token + "\t字符型常量\t" + token + "\t" +
str(line_number))
else:
# print("错误:在" + str(line_number) + "行, 试图将" + token + "解析为字符型常量发生错误!" )
#if "错误:在" + str(line_number) + "行, 试图将" + token + "解析为字符型常量发生错误!" not in error_l:
error_l.append("错误:在" + str(line_number) + "行, 试图将" + token +
"解析为字符型常量发生错误!")
if isString(token[0]):
stringDFA_result, error_message = stringDFA.in_stringDFA(token)
if stringDFA_result:
# print(token + "\t<字符串常量\t" + token + ">\t" + str(line_number))
#if token + "\t字符串常量\t" + token + "\t" + str(line_number) not in token_l:
token_l.append(token + "\t字符串常量\t" + token + "\t" +
str(line_number))
else:
# print("错误:在" + str(line_number) + "行, 试图将" + token + "解析为字符串常量发生错误!")
#if "错误:在" + str(line_number) + "行, 试图将" + token + "解析为字符型常量发生错误!" not in error_l:
error_l.append("错误:在" + str(line_number) + "行, 试图将" + token +
"解析为字符型常量发生错误!")
return character_table, token_l, error_l