diff options
author | 2021-02-15 10:34:14 -0800 | |
---|---|---|
committer | 2021-02-15 13:34:14 -0500 | |
commit | d0d4d30882fe3ab9b1badbecf5d15d94326fd13e (patch) | |
tree | 5f9cf7c531d89da3dab9d3315bde1142a5cde9bc | |
parent | [3.7] closes bpo-42938: Replace snprintf with Python unicode formatting in ct... (diff) | |
download | cpython-d0d4d30882fe3ab9b1badbecf5d15d94326fd13e.tar.gz cpython-d0d4d30882fe3ab9b1badbecf5d15d94326fd13e.tar.bz2 cpython-d0d4d30882fe3ab9b1badbecf5d15d94326fd13e.zip |
[3.7] bpo-42967: only use '&' as a query string separator (GH-24297) (GH-24531)
bpo-42967: [security] Address a web cache-poisoning issue reported in
urllib.parse.parse_qsl().
urllib.parse will only us "&" as query string separator by default
instead of both ";" and "&" as allowed in earlier versions. An optional
argument seperator with default value "&" is added to specify the
separator.
Co-authored-by: Éric Araujo <merwok@netwok.org>
Co-authored-by: Ken Jin <28750310+Fidget-Spinner@users.noreply.github.com>
Co-authored-by: Adam Goldschmidt <adamgold7@gmail.com>
(cherry picked from commit fcbe0cb04d35189401c0c880ebfb4311e952d776)
-rw-r--r-- | Doc/library/cgi.rst | 9 | ||||
-rw-r--r-- | Doc/library/urllib.parse.rst | 23 | ||||
-rw-r--r-- | Doc/whatsnew/3.6.rst | 13 | ||||
-rw-r--r-- | Doc/whatsnew/3.7.rst | 13 | ||||
-rwxr-xr-x | Lib/cgi.py | 23 | ||||
-rw-r--r-- | Lib/test/test_cgi.py | 29 | ||||
-rw-r--r-- | Lib/test/test_urlparse.py | 68 | ||||
-rw-r--r-- | Lib/urllib/parse.py | 19 | ||||
-rw-r--r-- | Misc/NEWS.d/next/Security/2021-02-14-15-59-16.bpo-42967.YApqDS.rst | 1 |
9 files changed, 152 insertions, 46 deletions
diff --git a/Doc/library/cgi.rst b/Doc/library/cgi.rst index 0b1aead9dd..f0ec7e8cc6 100644 --- a/Doc/library/cgi.rst +++ b/Doc/library/cgi.rst @@ -277,10 +277,10 @@ These are useful if you want more control, or if you want to employ some of the algorithms implemented in this module in other circumstances. -.. function:: parse(fp=None, environ=os.environ, keep_blank_values=False, strict_parsing=False) +.. function:: parse(fp=None, environ=os.environ, keep_blank_values=False, strict_parsing=False, separator="&") Parse a query in the environment or from a file (the file defaults to - ``sys.stdin``). The *keep_blank_values* and *strict_parsing* parameters are + ``sys.stdin``). The *keep_blank_values*, *strict_parsing* and *separator* parameters are passed to :func:`urllib.parse.parse_qs` unchanged. @@ -296,7 +296,7 @@ algorithms implemented in this module in other circumstances. instead. It is maintained here only for backward compatibility. -.. function:: parse_multipart(fp, pdict, encoding="utf-8", errors="replace") +.. function:: parse_multipart(fp, pdict, encoding="utf-8", errors="replace", separator="&") Parse input of type :mimetype:`multipart/form-data` (for file uploads). Arguments are *fp* for the input file, *pdict* for a dictionary containing @@ -315,6 +315,9 @@ algorithms implemented in this module in other circumstances. Added the *encoding* and *errors* parameters. For non-file fields, the value is now a list of strings, not bytes. + .. versionchanged:: 3.7.10 + Added the *separator* parameter. + .. function:: parse_header(string) diff --git a/Doc/library/urllib.parse.rst b/Doc/library/urllib.parse.rst index f499412144..e79faf035b 100644 --- a/Doc/library/urllib.parse.rst +++ b/Doc/library/urllib.parse.rst @@ -165,7 +165,7 @@ or on combining URL components into a URL string. now raise :exc:`ValueError`. -.. function:: parse_qs(qs, keep_blank_values=False, strict_parsing=False, encoding='utf-8', errors='replace', max_num_fields=None) +.. function:: parse_qs(qs, keep_blank_values=False, strict_parsing=False, encoding='utf-8', errors='replace', max_num_fields=None, separator='&') Parse a query string given as a string argument (data of type :mimetype:`application/x-www-form-urlencoded`). Data are returned as a @@ -190,6 +190,9 @@ or on combining URL components into a URL string. read. If set, then throws a :exc:`ValueError` if there are more than *max_num_fields* fields read. + The optional argument *separator* is the symbol to use for separating the + query arguments. It defaults to ``&``. + Use the :func:`urllib.parse.urlencode` function (with the ``doseq`` parameter set to ``True``) to convert such dictionaries into query strings. @@ -200,8 +203,14 @@ or on combining URL components into a URL string. .. versionchanged:: 3.7.2 Added *max_num_fields* parameter. + .. versionchanged:: 3.7.10 + Added *separator* parameter with the default value of ``&``. Python + versions earlier than Python 3.7.10 allowed using both ``;`` and ``&`` as + query parameter separator. This has been changed to allow only a single + separator key, with ``&`` as the default separator. + -.. function:: parse_qsl(qs, keep_blank_values=False, strict_parsing=False, encoding='utf-8', errors='replace', max_num_fields=None) +.. function:: parse_qsl(qs, keep_blank_values=False, strict_parsing=False, encoding='utf-8', errors='replace', max_num_fields=None, separator='&') Parse a query string given as a string argument (data of type :mimetype:`application/x-www-form-urlencoded`). Data are returned as a list of @@ -225,6 +234,9 @@ or on combining URL components into a URL string. read. If set, then throws a :exc:`ValueError` if there are more than *max_num_fields* fields read. + The optional argument *separator* is the symbol to use for separating the + query arguments. It defaults to ``&``. + Use the :func:`urllib.parse.urlencode` function to convert such lists of pairs into query strings. @@ -234,6 +246,13 @@ or on combining URL components into a URL string. .. versionchanged:: 3.7.2 Added *max_num_fields* parameter. + .. versionchanged:: 3.7.10 + Added *separator* parameter with the default value of ``&``. Python + versions earlier than Python 3.7.10 allowed using both ``;`` and ``&`` as + query parameter separator. This has been changed to allow only a single + separator key, with ``&`` as the default separator. + + .. function:: urlunparse(parts) Construct a URL from a tuple as returned by ``urlparse()``. The *parts* diff --git a/Doc/whatsnew/3.6.rst b/Doc/whatsnew/3.6.rst index 04c1f7e71d..4409a3a596 100644 --- a/Doc/whatsnew/3.6.rst +++ b/Doc/whatsnew/3.6.rst @@ -2443,3 +2443,16 @@ because of the behavior of the socket option ``SO_REUSEADDR`` in UDP. For more details, see the documentation for ``loop.create_datagram_endpoint()``. (Contributed by Kyle Stanley, Antoine Pitrou, and Yury Selivanov in :issue:`37228`.) + +Notable changes in Python 3.6.13 +================================ + +Earlier Python versions allowed using both ``;`` and ``&`` as +query parameter separators in :func:`urllib.parse.parse_qs` and +:func:`urllib.parse.parse_qsl`. Due to security concerns, and to conform with +newer W3C recommendations, this has been changed to allow only a single +separator key, with ``&`` as the default. This change also affects +:func:`cgi.parse` and :func:`cgi.parse_multipart` as they use the affected +functions internally. For more details, please see their respective +documentation. +(Contributed by Adam Goldschmidt, Senthil Kumaran and Ken Jin in :issue:`42967`.) diff --git a/Doc/whatsnew/3.7.rst b/Doc/whatsnew/3.7.rst index 6dcb006924..25e231dcc7 100644 --- a/Doc/whatsnew/3.7.rst +++ b/Doc/whatsnew/3.7.rst @@ -2572,3 +2572,16 @@ because of the behavior of the socket option ``SO_REUSEADDR`` in UDP. For more details, see the documentation for ``loop.create_datagram_endpoint()``. (Contributed by Kyle Stanley, Antoine Pitrou, and Yury Selivanov in :issue:`37228`.) + +Notable changes in Python 3.7.10 +================================ + +Earlier Python versions allowed using both ``;`` and ``&`` as +query parameter separators in :func:`urllib.parse.parse_qs` and +:func:`urllib.parse.parse_qsl`. Due to security concerns, and to conform with +newer W3C recommendations, this has been changed to allow only a single +separator key, with ``&`` as the default. This change also affects +:func:`cgi.parse` and :func:`cgi.parse_multipart` as they use the affected +functions internally. For more details, please see their respective +documentation. +(Contributed by Adam Goldschmidt, Senthil Kumaran and Ken Jin in :issue:`42967`.) diff --git a/Lib/cgi.py b/Lib/cgi.py index 5a001667ef..51afead1b3 100755 --- a/Lib/cgi.py +++ b/Lib/cgi.py @@ -117,7 +117,8 @@ log = initlog # The current logging function # 0 ==> unlimited input maxlen = 0 -def parse(fp=None, environ=os.environ, keep_blank_values=0, strict_parsing=0): +def parse(fp=None, environ=os.environ, keep_blank_values=0, + strict_parsing=0, separator='&'): """Parse a query in the environment or from a file (default stdin) Arguments, all optional: @@ -136,6 +137,9 @@ def parse(fp=None, environ=os.environ, keep_blank_values=0, strict_parsing=0): strict_parsing: flag indicating what to do with parsing errors. If false (the default), errors are silently ignored. If true, errors raise a ValueError exception. + + separator: str. The symbol to use for separating the query arguments. + Defaults to &. """ if fp is None: fp = sys.stdin @@ -156,7 +160,7 @@ def parse(fp=None, environ=os.environ, keep_blank_values=0, strict_parsing=0): if environ['REQUEST_METHOD'] == 'POST': ctype, pdict = parse_header(environ['CONTENT_TYPE']) if ctype == 'multipart/form-data': - return parse_multipart(fp, pdict) + return parse_multipart(fp, pdict, separator=separator) elif ctype == 'application/x-www-form-urlencoded': clength = int(environ['CONTENT_LENGTH']) if maxlen and clength > maxlen: @@ -180,7 +184,7 @@ def parse(fp=None, environ=os.environ, keep_blank_values=0, strict_parsing=0): qs = "" environ['QUERY_STRING'] = qs # XXX Shouldn't, really return urllib.parse.parse_qs(qs, keep_blank_values, strict_parsing, - encoding=encoding) + encoding=encoding, separator=separator) # parse query string function called from urlparse, @@ -198,7 +202,7 @@ def parse_qsl(qs, keep_blank_values=0, strict_parsing=0): DeprecationWarning, 2) return urllib.parse.parse_qsl(qs, keep_blank_values, strict_parsing) -def parse_multipart(fp, pdict, encoding="utf-8", errors="replace"): +def parse_multipart(fp, pdict, encoding="utf-8", errors="replace", separator='&'): """Parse multipart input. Arguments: @@ -222,7 +226,7 @@ def parse_multipart(fp, pdict, encoding="utf-8", errors="replace"): except KeyError: pass fs = FieldStorage(fp, headers=headers, encoding=encoding, errors=errors, - environ={'REQUEST_METHOD': 'POST'}) + environ={'REQUEST_METHOD': 'POST'}, separator=separator) return {k: fs.getlist(k) for k in fs} def _parseparam(s): @@ -332,7 +336,7 @@ class FieldStorage: def __init__(self, fp=None, headers=None, outerboundary=b'', environ=os.environ, keep_blank_values=0, strict_parsing=0, limit=None, encoding='utf-8', errors='replace', - max_num_fields=None): + max_num_fields=None, separator='&'): """Constructor. Read multipart/* until last part. Arguments, all optional: @@ -380,6 +384,7 @@ class FieldStorage: self.keep_blank_values = keep_blank_values self.strict_parsing = strict_parsing self.max_num_fields = max_num_fields + self.separator = separator if 'REQUEST_METHOD' in environ: method = environ['REQUEST_METHOD'].upper() self.qs_on_post = None @@ -606,7 +611,7 @@ class FieldStorage: query = urllib.parse.parse_qsl( qs, self.keep_blank_values, self.strict_parsing, encoding=self.encoding, errors=self.errors, - max_num_fields=self.max_num_fields) + max_num_fields=self.max_num_fields, separator=self.separator) self.list = [MiniFieldStorage(key, value) for key, value in query] self.skip_lines() @@ -622,7 +627,7 @@ class FieldStorage: query = urllib.parse.parse_qsl( self.qs_on_post, self.keep_blank_values, self.strict_parsing, encoding=self.encoding, errors=self.errors, - max_num_fields=self.max_num_fields) + max_num_fields=self.max_num_fields, separator=self.separator) self.list.extend(MiniFieldStorage(key, value) for key, value in query) klass = self.FieldStorageClass or self.__class__ @@ -666,7 +671,7 @@ class FieldStorage: else self.limit - self.bytes_read part = klass(self.fp, headers, ib, environ, keep_blank_values, strict_parsing, limit, - self.encoding, self.errors, max_num_fields) + self.encoding, self.errors, max_num_fields, self.separator) if max_num_fields is not None: max_num_fields -= 1 diff --git a/Lib/test/test_cgi.py b/Lib/test/test_cgi.py index 220268e14f..c2a00a2e45 100644 --- a/Lib/test/test_cgi.py +++ b/Lib/test/test_cgi.py @@ -55,12 +55,9 @@ parse_strict_test_cases = [ ("", ValueError("bad query field: ''")), ("&", ValueError("bad query field: ''")), ("&&", ValueError("bad query field: ''")), - (";", ValueError("bad query field: ''")), - (";&;", ValueError("bad query field: ''")), # Should the next few really be valid? ("=", {}), ("=&=", {}), - ("=;=", {}), # This rest seem to make sense ("=a", {'': ['a']}), ("&=a", ValueError("bad query field: ''")), @@ -75,8 +72,6 @@ parse_strict_test_cases = [ ("a=a+b&b=b+c", {'a': ['a b'], 'b': ['b c']}), ("a=a+b&a=b+a", {'a': ['a b', 'b a']}), ("x=1&y=2.0&z=2-3.%2b0", {'x': ['1'], 'y': ['2.0'], 'z': ['2-3.+0']}), - ("x=1;y=2.0&z=2-3.%2b0", {'x': ['1'], 'y': ['2.0'], 'z': ['2-3.+0']}), - ("x=1;y=2.0;z=2-3.%2b0", {'x': ['1'], 'y': ['2.0'], 'z': ['2-3.+0']}), ("Hbc5161168c542333633315dee1182227:key_store_seqid=400006&cuyer=r&view=bustomer&order_id=0bb2e248638833d48cb7fed300000f1b&expire=964546263&lobale=en-US&kid=130003.300038&ss=env", {'Hbc5161168c542333633315dee1182227:key_store_seqid': ['400006'], 'cuyer': ['r'], @@ -212,6 +207,30 @@ Content-Length: 3 else: self.assertEqual(fs.getvalue(key), expect_val[0]) + def test_separator(self): + parse_semicolon = [ + ("x=1;y=2.0", {'x': ['1'], 'y': ['2.0']}), + ("x=1;y=2.0;z=2-3.%2b0", {'x': ['1'], 'y': ['2.0'], 'z': ['2-3.+0']}), + (";", ValueError("bad query field: ''")), + (";;", ValueError("bad query field: ''")), + ("=;a", ValueError("bad query field: 'a'")), + (";b=a", ValueError("bad query field: ''")), + ("b;=a", ValueError("bad query field: 'b'")), + ("a=a+b;b=b+c", {'a': ['a b'], 'b': ['b c']}), + ("a=a+b;a=b+a", {'a': ['a b', 'b a']}), + ] + for orig, expect in parse_semicolon: + env = {'QUERY_STRING': orig} + fs = cgi.FieldStorage(separator=';', environ=env) + if isinstance(expect, dict): + for key in expect.keys(): + expect_val = expect[key] + self.assertIn(key, fs) + if len(expect_val) > 1: + self.assertEqual(fs.getvalue(key), expect_val) + else: + self.assertEqual(fs.getvalue(key), expect_val[0]) + def test_log(self): cgi.log("Testing") diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py index 68f633ca3a..e3088b2f39 100644 --- a/Lib/test/test_urlparse.py +++ b/Lib/test/test_urlparse.py @@ -32,16 +32,10 @@ parse_qsl_test_cases = [ (b"&a=b", [(b'a', b'b')]), (b"a=a+b&b=b+c", [(b'a', b'a b'), (b'b', b'b c')]), (b"a=1&a=2", [(b'a', b'1'), (b'a', b'2')]), - (";", []), - (";;", []), - (";a=b", [('a', 'b')]), - ("a=a+b;b=b+c", [('a', 'a b'), ('b', 'b c')]), - ("a=1;a=2", [('a', '1'), ('a', '2')]), - (b";", []), - (b";;", []), - (b";a=b", [(b'a', b'b')]), - (b"a=a+b;b=b+c", [(b'a', b'a b'), (b'b', b'b c')]), - (b"a=1;a=2", [(b'a', b'1'), (b'a', b'2')]), + (";a=b", [(';a', 'b')]), + ("a=a+b;b=b+c", [('a', 'a b;b=b c')]), + (b";a=b", [(b';a', b'b')]), + (b"a=a+b;b=b+c", [(b'a', b'a b;b=b c')]), ] # Each parse_qs testcase is a two-tuple that contains @@ -68,16 +62,10 @@ parse_qs_test_cases = [ (b"&a=b", {b'a': [b'b']}), (b"a=a+b&b=b+c", {b'a': [b'a b'], b'b': [b'b c']}), (b"a=1&a=2", {b'a': [b'1', b'2']}), - (";", {}), - (";;", {}), - (";a=b", {'a': ['b']}), - ("a=a+b;b=b+c", {'a': ['a b'], 'b': ['b c']}), - ("a=1;a=2", {'a': ['1', '2']}), - (b";", {}), - (b";;", {}), - (b";a=b", {b'a': [b'b']}), - (b"a=a+b;b=b+c", {b'a': [b'a b'], b'b': [b'b c']}), - (b"a=1;a=2", {b'a': [b'1', b'2']}), + (";a=b", {';a': ['b']}), + ("a=a+b;b=b+c", {'a': ['a b;b=b c']}), + (b";a=b", {b';a': [b'b']}), + (b"a=a+b;b=b+c", {b'a':[ b'a b;b=b c']}), ] class UrlParseTestCase(unittest.TestCase): @@ -884,10 +872,46 @@ class UrlParseTestCase(unittest.TestCase): def test_parse_qsl_max_num_fields(self): with self.assertRaises(ValueError): urllib.parse.parse_qs('&'.join(['a=a']*11), max_num_fields=10) - with self.assertRaises(ValueError): - urllib.parse.parse_qs(';'.join(['a=a']*11), max_num_fields=10) urllib.parse.parse_qs('&'.join(['a=a']*10), max_num_fields=10) + def test_parse_qs_separator(self): + parse_qs_semicolon_cases = [ + (";", {}), + (";;", {}), + (";a=b", {'a': ['b']}), + ("a=a+b;b=b+c", {'a': ['a b'], 'b': ['b c']}), + ("a=1;a=2", {'a': ['1', '2']}), + (b";", {}), + (b";;", {}), + (b";a=b", {b'a': [b'b']}), + (b"a=a+b;b=b+c", {b'a': [b'a b'], b'b': [b'b c']}), + (b"a=1;a=2", {b'a': [b'1', b'2']}), + ] + for orig, expect in parse_qs_semicolon_cases: + with self.subTest(f"Original: {orig!r}, Expected: {expect!r}"): + result = urllib.parse.parse_qs(orig, separator=';') + self.assertEqual(result, expect, "Error parsing %r" % orig) + + + def test_parse_qsl_separator(self): + parse_qsl_semicolon_cases = [ + (";", []), + (";;", []), + (";a=b", [('a', 'b')]), + ("a=a+b;b=b+c", [('a', 'a b'), ('b', 'b c')]), + ("a=1;a=2", [('a', '1'), ('a', '2')]), + (b";", []), + (b";;", []), + (b";a=b", [(b'a', b'b')]), + (b"a=a+b;b=b+c", [(b'a', b'a b'), (b'b', b'b c')]), + (b"a=1;a=2", [(b'a', b'1'), (b'a', b'2')]), + ] + for orig, expect in parse_qsl_semicolon_cases: + with self.subTest(f"Original: {orig!r}, Expected: {expect!r}"): + result = urllib.parse.parse_qsl(orig, separator=';') + self.assertEqual(result, expect, "Error parsing %r" % orig) + + def test_urlencode_sequences(self): # Other tests incidentally urlencode things; test non-covered cases: # Sequence and object values. diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py index 94df275c46..e67d69db36 100644 --- a/Lib/urllib/parse.py +++ b/Lib/urllib/parse.py @@ -643,7 +643,7 @@ def unquote(string, encoding='utf-8', errors='replace'): def parse_qs(qs, keep_blank_values=False, strict_parsing=False, - encoding='utf-8', errors='replace', max_num_fields=None): + encoding='utf-8', errors='replace', max_num_fields=None, separator='&'): """Parse a query given as a string argument. Arguments: @@ -667,12 +667,15 @@ def parse_qs(qs, keep_blank_values=False, strict_parsing=False, max_num_fields: int. If set, then throws a ValueError if there are more than n fields read by parse_qsl(). + separator: str. The symbol to use for separating the query arguments. + Defaults to &. + Returns a dictionary. """ parsed_result = {} pairs = parse_qsl(qs, keep_blank_values, strict_parsing, encoding=encoding, errors=errors, - max_num_fields=max_num_fields) + max_num_fields=max_num_fields, separator=separator) for name, value in pairs: if name in parsed_result: parsed_result[name].append(value) @@ -682,7 +685,7 @@ 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', max_num_fields=None): + encoding='utf-8', errors='replace', max_num_fields=None, separator='&'): """Parse a query given as a string argument. Arguments: @@ -705,19 +708,25 @@ def parse_qsl(qs, keep_blank_values=False, strict_parsing=False, max_num_fields: int. If set, then throws a ValueError if there are more than n fields read by parse_qsl(). + separator: str. The symbol to use for separating the query arguments. + Defaults to &. + Returns a list, as G-d intended. """ qs, _coerce_result = _coerce_args(qs) + if not separator or (not isinstance(separator, (str, bytes))): + raise ValueError("Separator must be of type string or bytes.") + # 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(';') + num_fields = 1 + qs.count(separator) 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(';')] + pairs = [s1 for s1 in qs.split(separator)] r = [] for name_value in pairs: if not name_value and not strict_parsing: diff --git a/Misc/NEWS.d/next/Security/2021-02-14-15-59-16.bpo-42967.YApqDS.rst b/Misc/NEWS.d/next/Security/2021-02-14-15-59-16.bpo-42967.YApqDS.rst new file mode 100644 index 0000000000..f08489b414 --- /dev/null +++ b/Misc/NEWS.d/next/Security/2021-02-14-15-59-16.bpo-42967.YApqDS.rst @@ -0,0 +1 @@ +Fix web cache poisoning vulnerability by defaulting the query args separator to ``&``, and allowing the user to choose a custom separator. |