def analyze_file(item):
global pool_sem
os.setpgrp()
filename = item[0]
db = item[1]
use_symbol = item[2]
depth = item[3]
instruction_converter = item[4]
analyzer = RadareFunctionAnalyzer(filename, use_symbol, depth)
p = ThreadPool(1)
res = p.apply_async(analyzer.analyze)
try:
result = res.get(120)
except multiprocessing.TimeoutError:
print("Aborting due to timeout:" + str(filename))
print(
'Try to modify the timeout value in DatabaseFactory instruction result = res.get(TIMEOUT)'
)
os.killpg(0, signal.SIGKILL)
except Exception:
print("Aborting due to error:" + str(filename))
os.killpg(0, signal.SIGKILL)
for func in result:
DatabaseFactory.insert_in_db(db, pool_sem, result[func], filename,
func, instruction_converter)
analyzer.close()
return 0
def embedd_function(self, filename, address):
analyzer = RadareFunctionAnalyzer(filename, use_symbol=False, depth=0)
functions = analyzer.analyze()
instructions_list = None
for function in functions:
if functions[function]['address'] == address:
instructions_list = functions[function]['filtered_instructions']
break
if instructions_list is None:
print("Function not found")
return None
converted_instructions = self.converter.convert_to_ids(instructions_list)
instructions, length = self.normalizer.normalize_functions([converted_instructions])
embedding = self.embedder.embedd(instructions, length)
return embedding
def analyze_file(item):
global pool_sem
os.setpgrp()
filename = item[0]
db = item[1]
use_symbol = item[2]
depth = item[3]
instruction_converter = item[4]
analyzer = RadareFunctionAnalyzer(filename, use_symbol, depth)
p = ThreadPool(1)
res = p.apply_async(analyzer.analyze)
try:
result = res.get(120)
except multiprocessing.TimeoutError:
print("Aborting due to timeout:" + str(filename))
print(
'Try to modify the timeout value in DatabaseFactory instruction result = res.get(TIMEOUT)'
)
os.killpg(0, signal.SIGKILL)
except Exception:
print("Aborting due to error:" + str(filename))
os.killpg(0, signal.SIGKILL)
# use the shortest function name (ex. __glibc_malloc, __malloc, malloc)
dups = []
for f1 in result:
for f2 in result:
if f1 != f2 and result[f1]['address'] == result[f2][
'address'] and len(f1) > len(f2):
dups.append(f1)
dups = set(dups)
for func in result:
if len(result[func]['filtered_instructions']) < 16 or func in dups:
continue
DatabaseFactory.insert_in_db(db, pool_sem, result[func], filename,
func, instruction_converter)
analyzer.close()
return 0