mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-04 00:48:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

gh-74668: Fix support of bytes in urllib.parse.parse_qsl() (GH-115771)

Browse source 
urllib.parse functions parse_qs() and parse_qsl() now support bytes
arguments containing raw and percent-encoded non-ASCII data.
This commit is contained in:
Serhiy Storchaka 2024-03-05 17:49:50 +02:00 • committed by GitHub
parent f97f25ef5d
commit bdba8ef42b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 64 additions and 26 deletions
Download patch file Download diff file Expand all files Collapse all files

50
Lib/urllib/parse.py
View file

@ -763,42 +763,44 @@ def parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
Returns a list, as G-d intended.
"""
qs, _coerce_result = _coerce_args(qs)
separator, _ = _coerce_args(separator)
if not separator or (not isinstance(separator, (str, bytes))):
if not separator or not isinstance(separator, (str, bytes)):
raise ValueError("Separator must be of type string or bytes.")
if isinstance(qs, str):
if not isinstance(separator, str):
separator = str(separator, 'ascii')
eq = '='
def _unquote(s):
return unquote_plus(s, encoding=encoding, errors=errors)
else:
qs = bytes(qs)
if isinstance(separator, str):
separator = bytes(separator, 'ascii')
eq = b'='
def _unquote(s):
return unquote_to_bytes(s.replace(b'+', b' '))
if not qs:
return []
# 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(separator) if qs else 0
num_fields = 1 + qs.count(separator)
if max_num_fields < num_fields:
raise ValueError('Max number of fields exceeded')
r = []
query_args = qs.split(separator) if qs else []
for name_value in query_args:
if not name_value and not strict_parsing:
continue
nv = name_value.split('=', 1)
if len(nv) != 2:
if strict_parsing:
for name_value in qs.split(separator):
if name_value or strict_parsing:
name, has_eq, value = name_value.partition(eq)
if not has_eq and strict_parsing:
raise ValueError("bad query field: %r" % (name_value,))
# Handle case of a control-name with no equal sign
if keep_blank_values:
nv.append('')
else:
continue
if len(nv[1]) or keep_blank_values:
name = nv[0].replace('+', ' ')
name = unquote(name, encoding=encoding, errors=errors)
name = _coerce_result(name)
value = nv[1].replace('+', ' ')
value = unquote(value, encoding=encoding, errors=errors)
value = _coerce_result(value)
r.append((name, value))
if value or keep_blank_values:
name = _unquote(name)
value = _unquote(value)
r.append((name, value))
return r
def unquote_plus(string, encoding='utf-8', errors='replace'):