Created
November 9, 2014 03:54
-
-
Save anonymous/cf096bae3df1dd9c4bd4 to your computer and use it in GitHub Desktop.
Quick and dirty fuzz tester for HTML tag strippers in Python
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# | |
# Half-assed fuzzer for HTML strip-tags functions | |
# | |
from __future__ import print_function | |
BITS = [ | |
'<', '</', '>', '<!--', '-->', 'a', 'div', 'p', 'i', | |
] | |
how_many_test_strings = 10 | |
import random | |
import re | |
import markupsafe | |
from django.utils.html import _strip_once, strip_tags | |
test_file_template = markupsafe.Markup( | |
""" | |
<html> | |
<head><title>--test--</title> | |
<body> | |
<h1>{name}</h1> | |
<big> | |
<table width="100%"> | |
<tr> | |
<td>{challenge}</td> | |
<td>{result}am i a link?</td> | |
</tr> | |
</table> | |
</big> | |
</body> | |
</html> | |
""") | |
def make_test_string(num_bits): | |
return ''.join([random.choice(BITS) for k in range(num_bits)]) | |
failure_re = re.compile(r'<a>') | |
TEST_STRINGS = [make_test_string(random.randrange(75)) for k in range(how_many_test_strings)] | |
any_fails = False | |
def gauntlet(name, fixer): | |
global any_fails | |
for num, challenge in enumerate(TEST_STRINGS): | |
result = fixer(challenge) | |
if failure_re.search(result): | |
any_fails = True | |
print("{name}-{num} FAIL: {challenge}\t\t\t\t{result}".format(**locals())) | |
with open('{name}-{num}.html'.format(**locals()), 'w') as out: | |
result = markupsafe.Markup(result) | |
out.write(test_file_template.format(**locals())) | |
else: | |
pass | |
#print("{name}-{num} SUCCESS: {challenge}\t\t\t\t({result})".format(**locals())) | |
CONTENDERS = [ | |
('markupsafe-re', r'(<!--.*?-->|<[^>]*>)'), | |
('broken-re', r'(<!--.*?-->|<[^<]*>)'), | |
] | |
def remove_html_markup(s): | |
tag = False | |
quote = False | |
out = "" | |
for c in s: | |
if c == '<' and not quote: | |
tag = True | |
elif c == '>' and not quote: | |
tag = False | |
elif (c == '"' or c == "'") and tag: | |
quote = not quote | |
elif not tag: | |
out = out + c | |
return out | |
for (name, fixer_re) in CONTENDERS: | |
print(fixer_re) | |
print() | |
fixer_re = re.compile(fixer_re) | |
fixer = lambda s: fixer_re.sub('', s) | |
gauntlet(name, fixer) | |
print("old django") | |
print() | |
gauntlet('_strip_once', _strip_once) | |
def fixed_striptags(html): | |
value = html | |
while True: | |
new_value = strip_tags(value) | |
if value == new_value: | |
return value | |
value = new_value | |
print("new django") | |
print() | |
gauntlet('strip_tags', strip_tags) | |
print("@Medeiros remove_html_markup") | |
print() | |
gauntlet('remove_html_markup', remove_html_markup) | |
exit(any_fails) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment