summaryrefslogtreecommitdiffstats
path: root/Lib/urllib
diff options
context:
space:
mode:
authorMiss Islington (bot) <31488909+miss-islington@users.noreply.github.com>2018-10-19 11:16:57 (GMT)
committerGitHub <noreply@github.com>2018-10-19 11:16:57 (GMT)
commit322a914965368ffd7e4f97ede50b351fdf48d870 (patch)
tree6a79e88c4ef83a6df6fc5655b760db0f6a36056e /Lib/urllib
parentd85c2726b9f305ac5128764bda773a78e52101cd (diff)
downloadcpython-322a914965368ffd7e4f97ede50b351fdf48d870.zip
cpython-322a914965368ffd7e4f97ede50b351fdf48d870.tar.gz
cpython-322a914965368ffd7e4f97ede50b351fdf48d870.tar.bz2
bpo-34866: Adding max_num_fields to cgi.FieldStorage (GH-9660)
Adding `max_num_fields` to `cgi.FieldStorage` to make DOS attacks harder by limiting the number of `MiniFieldStorage` objects created by `FieldStorage`. (cherry picked from commit 209144831b0a19715bda3bd72b14a3e6192d9cc1) Co-authored-by: matthewbelisle-wf <matthew.belisle@workiva.com>
Diffstat (limited to 'Lib/urllib')
-rw-r--r--Lib/urllib/parse.py22
1 files changed, 19 insertions, 3 deletions
diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py
index f959212..85e68c8 100644
--- a/Lib/urllib/parse.py
+++ b/Lib/urllib/parse.py
@@ -624,7 +624,7 @@ def unquote(string, encoding='utf-8', errors='replace'):
def parse_qs(qs, keep_blank_values=False, strict_parsing=False,
- encoding='utf-8', errors='replace'):
+ encoding='utf-8', errors='replace', max_num_fields=None):
"""Parse a query given as a string argument.
Arguments:
@@ -645,11 +645,15 @@ def parse_qs(qs, keep_blank_values=False, strict_parsing=False,
encoding and errors: specify how to decode percent-encoded sequences
into Unicode characters, as accepted by the bytes.decode() method.
+ max_num_fields: int. If set, then throws a ValueError if there
+ are more than n fields read by parse_qsl().
+
Returns a dictionary.
"""
parsed_result = {}
pairs = parse_qsl(qs, keep_blank_values, strict_parsing,
- encoding=encoding, errors=errors)
+ encoding=encoding, errors=errors,
+ max_num_fields=max_num_fields)
for name, value in pairs:
if name in parsed_result:
parsed_result[name].append(value)
@@ -659,7 +663,7 @@ def parse_qs(qs, keep_blank_values=False, strict_parsing=False,
def parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
- encoding='utf-8', errors='replace'):
+ encoding='utf-8', errors='replace', max_num_fields=None):
"""Parse a query given as a string argument.
Arguments:
@@ -679,9 +683,21 @@ def parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
encoding and errors: specify how to decode percent-encoded sequences
into Unicode characters, as accepted by the bytes.decode() method.
+ max_num_fields: int. If set, then throws a ValueError
+ if there are more than n fields read by parse_qsl().
+
Returns a list, as G-d intended.
"""
qs, _coerce_result = _coerce_args(qs)
+
+ # If max_num_fields is defined then check that the number of fields
+ # is less than max_num_fields. This prevents a memory exhaustion DOS
+ # attack via post bodies with many fields.
+ if max_num_fields is not None:
+ num_fields = 1 + qs.count('&') + qs.count(';')
+ if max_num_fields < num_fields:
+ raise ValueError('Max number of fields exceeded')
+
pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
r = []
for name_value in pairs: