def find_constone(self, datas):
wordDic = Converter.convert_raw_to_count(datas)
wordDic = sorted(wordDic.items(), key=lambda x: x[1])
if (wordDic[0][1] > self.constThreshold):
return 1
else:
return 0
def inferConst(self, datas):
wordDic = Converter.convert_raw_to_count(datas)
wordDic = sorted(wordDic.items(), key=lambda x: x[1])
if (wordDic[-1][1] / len(datas) > self.constThreshold):
return 1
else:
return 0
def find_constfunc(self, datas):
"""
get the feature of the function code
:param datas: List of bytes
:return: entry and distinct num of datas
"""
t_l = Converter.convert_raw_to_count(datas)
t_en = base_analyzer.get_entry([value for value in t_l.values()])
return t_en, len(t_l)
def getFuncScore(self, Los=None, datas=None):
if Los != None:
datas = self.cverter.getDatasByLocs(self.messages, Los)
datasDic = Converter.convert_raw_to_count(datas)
sumValue = 0
for value in datasDic.values():
sumValue = sumValue + value
datas = [data / sumValue for data in datasDic.values()]
datasEntry = base_analyzer.get_entry(datas)
return datasEntry, len(datasDic)
def inferFunc(self, datas):
datasDic = Converter.convert_raw_to_count(datas)
sumValue = 0
for value in datasDic.values():
sumValue = sumValue + value
datas = [data / sumValue for data in datasDic.values()]
datasEntry = base_analyzer.get_entry(datas)
if len(datasDic) < self.FuncT:
return 1
else:
return 0
def inferConst(self, Los=None, datas=None):
#print(Los)
if Los != None:
datas = self.cverter.getDatasByLocs(self.messages, Los)
#print(datas)
wordDic = Converter.convert_raw_to_count(datas)
wordDic = sorted(wordDic.items(), key=lambda x: x[1])
#print(wordDic)
if (wordDic[-1][1] / len(datas) > self.constThreshold):
return 1
else:
return 0
def split_by_words_type(self, datas, T_max_range):
fields_set = []
w_infer = word_infer()
w_merger = base_merger()
w_convert = Converter()
b_analyzer = base_analyzer()
for i in range(T_max_range):
lo_datas = get_data_bylo(datas, i)
w_cnt = w_convert.convert_raw_to_count(lo_datas)
w_frequent = b_analyzer.convert_num_to_frequent(w_cnt)
w_type = w_infer.is_const_word(w_frequent, 0.95)
if w_type:
t_field = loc_field((i,i), 0)
else:
t_field = loc_field((i,i), 4)
fields_set.append(t_field)
words_f = w_merger.merge_words(fields_set)
candidate_borders = [w.loc[0] for w in words_f]
return words_f, candidate_borders
def inferFunc(self, datas):
datasDic = Converter.convert_raw_to_count(datas)
datasEntry = base_analyzer.get_entry(
[value for value in datasDic.values()])