def getAmountOfData(index, amount, files):
data = []
for i in range(index * amount, (index + 1) * amount):
if i < len(files):
fileData = jsonf.getData(files[i])
data.append(fileData)
return data
def getMethodDictionary(path):
"""
Load the dictionary, which is located at 'path'
:param path: path to the location of the dictionary
:type path: string
:return: dictionary containing the method names of API traces
:rtype: list
"""
dictionary = jsonf.getData(path)
return dictionary
def createTSVForFolder(threshold, length, pathToFolder, pathToDictionary,
numberOfMalBehaviors):
data = []
# the numbering of the malicious behaviors starts at 1
for i in range(1, numberOfMalBehaviors + 1):
data.extend(
jsonf.getData(pathToFolder + 'malBehavior_' + str(i) +
'/logMaliciousWithPath_' + str(length) + '.txt'))
# insert only these files that are classified as 'malicious' regarding the threshold in the output file
files = getMaliciousFiles(threshold, data, False)
writeDataToTSVFile(files, length, threshold, pathToDictionary,
pathToFolder)
def updateNumericDictionaryOfMethods(pathToNewTraces, pathToDictionary):
"""
Update the dictionary with the method names of API calls in the given traces
:param pathToNewTraces: path to the folder containing the traces, for which the dictionary should be updated
:param pathToDictionary: path to the location of the dictionary
:type pathToNewTraces: string
:type pathToDictionary: string
:example:
dictionaryMethods.updateNumericDictionaryOfMethods('../../input_data/piggybacked_malware/', '../../input_data/dictionary.txt')
"""
old_dict = jsonf.getData(pathToDictionary)
updated_dict = update(pathToNewTraces, old_dict)
jsonf.write(pathToDictionary, updated_dict)
print('numeric dictionary of methods updated')
def getMaliciousFiles(pathToFile, threshold):
data = jsonf.getData(pathToFile)
files = hdata.getMaliciousFiles(threshold, data, True)
return files
def getFilesForTSVFile(threshold, path):
data = jsonf.getData(path)
# include only files that are classified as 'malicious' regarding the threshold
maliciousFiles = getMaliciousFiles(threshold, data, False)
return maliciousFiles
def fetchSampleFixedLength(pathToElement, pathToDictionary, length):
entries = jsonf.getData(pathToElement)
sample = createSampleFromData(entries, pathToDictionary)
# only consider the first 'x' methods of the sample in order to fix the length of the sample
sample = sample[0:length]
return sample