Exemple #1
0
def feature(PATH):

	#filename = './fuzzdb/attack-payloads/sql-injection/detect/MySQL.fuzz.txt'
	filename = PATH
	test_case_list = file_operation.fileopt_line(filename)
	full_list = file_operation.fileopt_all(filename)
	full_stat_list = testcase_stat.stat_all(full_list)
	test_case_stat_list = testcase_stat.stat(test_case_list)
	tf_matrix = testcase_stat.compute_tf(test_case_stat_list)
	test_case_stat_list = testcase_stat.stat(test_case_list)
	idf_matrix = testcase_stat.compute_idf(test_case_stat_list, full_stat_list)
	tf_idf_list = testcase_stat.compute_tf_idf(tf_matrix, idf_matrix)
	test_case_feature_list = testcase_stat.feature_vector_quantify(tf_idf_list, full_stat_list)

	return test_case_feature_list
idf_matrix = testcase_stat.compute_idf(test_case_stat_list, full_stat_list)

#print idf_matrix

#combine tf_matrix and idf_matrix
#Compute tf_idf_list

tf_idf_list = testcase_stat.compute_tf_idf(tf_matrix, idf_matrix)

#print tf_idf_list

#Put them into feature vector and store in 
#test_case_feature_list
#----------------------------------------------------------------------------------------------
test_case_feature_list = testcase_stat.feature_vector_quantify(tf_idf_list, full_stat_list)
#----------------------------------------------------------------------------------------------
json.dump(test_case_feature_list, open('./statistics/test_case_feature.json', 'w'))
#demoDictList is the value we want format to output
#jsonDumpsTFIDF = json.dumps(tf_idf_list, indent=1)
#--------------------------------------------------------------------
#jsonDumpsFuature = json.dumps(test_case_feature_list, indent=1)
#json.dump(test_case_feature_list, open('./feature_list.json', 'w'))
#--------------------------------------------------------------------
#print jsonDumpsTFIDF
##print jsonDumpsFuature




#print "-------------------------------------"
idf_matrix = testcase_stat.compute_idf(test_case_stat_list, full_stat_list)

#print idf_matrix

#combine tf_matrix and idf_matrix
#Compute tf_idf_list

tf_idf_list = testcase_stat.compute_tf_idf(tf_matrix, idf_matrix)

#print tf_idf_list

#Put them into feature vector and store in
#test_case_feature_list
#----------------------------------------------------------------------------------------------
test_case_feature_list = testcase_stat.feature_vector_quantify(
    tf_idf_list, full_stat_list)
#----------------------------------------------------------------------------------------------
json.dump(test_case_feature_list,
          open('./statistics/test_case_feature.json', 'w'))
#demoDictList is the value we want format to output
#jsonDumpsTFIDF = json.dumps(tf_idf_list, indent=1)
#--------------------------------------------------------------------
#jsonDumpsFuature = json.dumps(test_case_feature_list, indent=1)
#json.dump(test_case_feature_list, open('./feature_list.json', 'w'))
#--------------------------------------------------------------------
#print jsonDumpsTFIDF
##print jsonDumpsFuature

#print "-------------------------------------"
#print test_case_list
#print full_list