def __init__(self,
alphabet,
stat_file,
encoding,
file_input=None,
text_input=None,
top=15000,
benchmark=False):
self.alphabet = alphabet
self.file = file_input
self.bench = benchmark
self.encoding = encoding
self.stat = load_stat(stat_file, encoding)
self.word_patterns = get_wordlists_pattern(self.stat["words"].keys())
if text_input:
code_text_info = TextInfo(alphabet,
encoding,
input_text=text_input)
elif file_input:
code_text_info = TextInfo(alphabet,
encoding,
input_filename=file_input)
else:
raise Exception("Cipher's Text Input Error")
self.cipher_words_list = code_text_info.find_info(
top).make_count_dict()
self.patterns = get_wordlists_pattern(
make_words_list(self.cipher_words_list["words"], top))
self.temp_subst = create_default_substitution(alphabet)
self.key = create_default_substitution(alphabet)
self.quadgrams = self.count_quadrams()
def handle_many_files(args, files):
"""
Process a list of files
:param args:
:param files: a list of files' names
"""
handle_one_object(args, files[0])
for i in range(1, len(files)):
text_info = TextInfo(args.alph, args.encoding, input_filename=files[i])
count_info = text_info.find_info(args.top)
count_info.update_count_info(args.output, text_info.alph, args.top,
args.encoding)
updated_dict = count_info.make_count_dict()
write_json_in_file(args.output, updated_dict, args.encoding)
def learn_single_file(top, update_file = None, file_name=None):
print('Learning single file')
if file_name:
text_info = TextInfo(
'A-Za-z',
'utf-8',
input_filename=file_name)
count_info = text_info.find_info(top)
if update_file is not None:
count_info.update_count_info(
update_file,
text_info.alph,
top,
'utf-8')
updated_dict = count_info.make_count_dict()
else:
updated_dict = count_info.make_count_dict()
write_json_in_file('result.txt', updated_dict, 'utf-8')
print('Done')
def learn_multiple_files(top, files, update_file=None):
global workdone
print('Learning multiple files: {}'.format(len(files)))
for i in range(0, len(files)):
text_info = TextInfo('A-Za-z', 'utf-8', input_filename=files[i])
count_info = text_info.find_info(top)
if update_file is not None:
count_info.update_count_info(
update_file,
text_info.alph,
top,
'utf-8')
updated_dict = count_info.make_count_dict()
else:
updated_dict = count_info.make_count_dict()
write_json_in_file('result.txt', updated_dict, 'utf-8')
workdone = (i+1) / (len(files))
print("\rProgress: [{0:50s}] {1:.1f}%".format('#' * int(workdone * 50), workdone * 100), end="", flush=True)
if workdone == 1:
workdone = 0
def __count_score(self, coded_text):
score = 0
coded_quadgrams = TextInfo(
self.alphabet, self.encoding,
input_text=coded_text).find_info(15000).make_ngramms_dict()['4']
for quadgram in coded_quadgrams:
if quadgram in self.__example_quadgrams.keys():
score += self.__example_quadgrams[quadgram]
else:
score += self.__floor
return score
def count_precision_coefficient(self, coded_text):
score = 0
coded_quadgrams = TextInfo(
self.alphabet, self.encoding,
input_text=coded_text).find_info(15000).make_ngramms_dict()['4']
for quadgram in coded_quadgrams:
if quadgram in self.quadgrams.keys():
score += self.quadgrams[quadgram]
else:
score += self.floor
return score
def handle_one_object(args, file_name=None, text=None):
"""
Process one file at a time, or a given piece of text
:param args:
:param file_name:
:param text:
"""
if file_name:
text_info = TextInfo(args.alph,
args.encoding,
input_filename=file_name)
elif text:
text_info = TextInfo(args.alph, args.encoding, input_text=text)
count_info = text_info.find_info(args.top)
if args.update_fn:
count_info.update_count_info(args.update_fn, text_info.alph, args.top,
args.encoding)
updated_dict = count_info.make_count_dict()
else:
updated_dict = count_info.make_count_dict()
if args.output:
write_json_in_file(args.output, updated_dict, args.encoding)
else:
pprint(updated_dict)