fix: [Credential] add regex timeout

This commit is contained in:
Terrtia 2020-05-04 11:02:24 +02:00
parent 64fae5d7df
commit 52b7f13a6f
No known key found for this signature in database
GPG key ID: 1E1B1F50D84613D0

View file

@ -33,6 +33,17 @@ import re
import redis import redis
from pyfaup.faup import Faup from pyfaup.faup import Faup
import signal
class TimeoutException(Exception):
pass
def timeout_handler(signum, frame):
raise TimeoutException
signal.signal(signal.SIGALRM, timeout_handler)
max_execution_time = 30
#split username with spec. char or with upper case, distinguish start with upper #split username with spec. char or with upper case, distinguish start with upper
REGEX_CRED = "[a-z]+|[A-Z]{3,}|[A-Z]{1,2}[a-z]+|[0-9]+" REGEX_CRED = "[a-z]+|[A-Z]{3,}|[A-Z]{1,2}[a-z]+|[0-9]+"
REDIS_KEY_NUM_USERNAME = 'uniqNumForUsername' REDIS_KEY_NUM_USERNAME = 'uniqNumForUsername'
@ -85,13 +96,38 @@ if __name__ == "__main__":
paste = Paste.Paste(filepath) paste = Paste.Paste(filepath)
content = paste.get_p_content() content = paste.get_p_content()
item_id = filepath
# max execution time on regex
signal.alarm(max_execution_time)
try:
creds = set(re.findall(regex_cred, content)) creds = set(re.findall(regex_cred, content))
except TimeoutException:
p.incr_module_timeout_statistic() # add encoder type
err_mess = "Credential: processing timeout: {}".format(item_id)
print(err_mess)
publisher.info(err_mess)
continue
else:
signal.alarm(0)
if len(creds) == 0: if len(creds) == 0:
continue continue
sites= re.findall(regex_web, content) #Use to count occurences signal.alarm(max_execution_time)
sites_set = set(re.findall(regex_web, content)) try:
sites = re.findall(regex_web, content) #Use to count occurences
except TimeoutException:
p.incr_module_timeout_statistic()
err_mess = "Credential: site, processing timeout: {}".format(item_id)
print(err_mess)
publisher.info(err_mess)
sites = []
else:
signal.alarm(0)
sites_set = set(sites)
message = 'Checked {} credentials found.'.format(len(creds)) message = 'Checked {} credentials found.'.format(len(creds))
if sites_set: if sites_set: