# from sklearn.feature_extraction.text import CountVectorizer
import json
import os
questionList = os.listdir("dataset_new1")
questionList.sort()
print questionList
for i in range(len(questionList) - 2):
dirList = os.listdir("dataset_new1/" +
questionList[i]) # dir is your directory path
dirList.sort()
os.mkdir("data/" + questionList[i])
for j in range(len(dirList) - 1):
# print("**************" + dirList[j] + "*************")
try:
cfg = buildCFG("dataset_new1/" + questionList[i] + "/" +
dirList[j])
except:
cfg = buildCFG(
"dataset_new1/" + questionList[i] + "/" + dirList[j], 'main')
with open('graph.json', "r") as f1:
dta = json.load(f1)
with open(
"data/" + questionList[i] + "/" + dirList[j][:-2] +
".json", "w") as f2:
json.dump(dta, f2)
dirList = os.listdir("dataset_new1/" + questionList[i] + "/goodset")
os.mkdir("data/" + questionList[i] + "/goodset")
dirList.sort()
for j in range(len(dirList)):
# print(dirList[j])
filen = d.split(" ")[1]
if checkFuncInFile(sourcefiles+filen):
print len(dataset)
dataset.append([sourcefiles+filen,label])
print len(data)
extractFilenameLabel(database)
print "Total " + str(len(dataset))
succ = []
failed = []
for f in dataset:
try:
cfgs = buildCFG(f[0])
print f
succ.append(f)
for cfg in cfgs:
#content = "\n[+] Function: " + str(cfg[0])
content = cfg[1].printer()
dataMatrix = dictoMatrix(content)
temp = np.array(dataMatrix).flatten().tolist()
data = " ".join(str(x) for x in temp)
writetofile("CWE119/dataset", data + " " + str(f[1]) + "\n")
except:
#print f[0] + "failed"
failed.append(f)
from utils import buildCFG
cfgs = buildCFG('Using_freed_memory.c')
print cfgs
for cfg in cfgs:
print cfg
print "\n[+] Function: ", cfg[0]
print cfg[1].printer()
from utils import buildCFG
#cfgs = buildCFG('Using_freed_memory.c')
filename = 'testcode.c'
cfgs = buildCFG(filename)
print cfgs
l = []
for cfg in cfgs:
print cfg
print "\n[+] Function: ", cfg[0]
print cfg[1].printer()
with open(filename, 'r') as content_file:
content = content_file.read()
start = content.index(cfg[0])
start = content.index("{", start)
stack = []
funcContent = ""
for i in range(start,len(content)):
if content[i] == "{":
stack.append("{")
elif content[i] == "}":
stack.remove(stack[0])
if len(stack) is 0:
funcContent = content[start+len(cfg[0]):i]
break
print funcContent
from utils import buildCFG from time import sleep PATH = '/home/gbaduz/Downloads/bash-4.3/' import os from glob import glob result = [y for x in os.walk(PATH) for y in glob(os.path.join(x[0], '*.c'))] succ = [] failed = [] for f in result: try: cfgs = buildCFG(f) print f succ.append(f) for cfg in cfgs: print "\n[+] Function: ", cfg[0] print cfg[1].printer() sleep(2) except: print f + "failed" failed.append(f) print "success " + str(len(succ)) print "failed " + str(len(failed))
# for j in range(len(dirList) - 1):
# try:
# cfg = buildCFG(datasetLocation + questionList[i] + "/goodset/" + dirList[j])
# except:
# cfg = buildCFG(datasetLocation + questionList[i] + "/goodset/" + dirList[j], 'main')
# with open('graph.json', "r") as f1:
# dta = json.load(f1)
# with open(dataLocation + questionList[i] + "/goodset/" + dirList[j][:-2] + ".json", "w") as f2:
# json.dump(dta, f2)
# if (isTest < 10):
# try :
# cfg = buildCFG("test.c")
# except :
cfg = buildCFG("test.c", 'main')
# print cfg.printer()
# cfg = buildCFG('test.c', 'main')
# with open('data2/1/goodset/2.json', "r") as f1:
# dta = json.load(f1)
# with open('data2/1/1.json', "r") as f1:
# dta1 = json.load(f1)
# print dta['features'][0]['basic']
# featBasic = " ".join(dta['features'][0]['basic'])
# corpus = []
# corpus.append(featBasic)
# corpus.append(" ".join(dta1['features'][0]['basic']))
from utils import buildCFG
cfg = buildCFG('testcode/example.c', 'addNumbers')
print "[+] Size of the CFG:", str(cfg.size())
print cfg.printer()