only use '&' as a query string separator

Origin: python/cpython#24297
Last-Update: 2021-04-03

 CVE-2021-23336

Gbp-Pq: Name CVE-2021-23336.patch

Doc/library/cgi.rst

@@ -188,6 +188,9 @@ A form submitted via POST that also has a query string will contain both
    Added support for the context management protocol to the
    :class:`FieldStorage` class.
 
+.. versionchanged:: 3.5.3-1+deb9u4
+   Added the *separator* parameter.
+
 
 Higher Level Interface
 ----------------------
@@ -277,10 +280,10 @@ 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* parameters and *separator* parameters are
    passed to :func:`urllib.parse.parse_qs` unchanged.
 
 

Doc/library/urllib.parse.rst

@@ -135,7 +135,7 @@ 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')
+.. function:: parse_qs(qs, keep_blank_values=False, strict_parsing=False, encoding='utf-8', errors='replace', separator='&')
 
    Parse a query string given as a string argument (data of type
    :mimetype:`application/x-www-form-urlencoded`).  Data are returned as a
@@ -156,6 +156,9 @@ or on combining URL components into a URL string.
    percent-encoded sequences into Unicode characters, as accepted by the
    :meth:`bytes.decode` method.
 
+   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.
@@ -164,8 +167,13 @@ or on combining URL components into a URL string.
    .. versionchanged:: 3.2
       Add *encoding* and *errors* parameters.
 
+   .. versionchanged:: 3.5.3-1+deb9u4
+      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')
+.. function:: parse_qsl(qs, keep_blank_values=False, strict_parsing=False, encoding='utf-8', errors='replace', 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
@@ -185,6 +193,9 @@ or on combining URL components into a URL string.
    percent-encoded sequences into Unicode characters, as accepted by the
    :meth:`bytes.decode` method.
 
+   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.
 

Lib/cgi.py

@@ -117,7 +117,7 @@ def closelog():
 # 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 +136,9 @@ 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 +159,7 @@ 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 +183,7 @@ 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 +201,7 @@ 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):
+def parse_multipart(fp, pdict, separator='&'):
     """Parse multipart input.
 
     Arguments:
@@ -404,7 +407,7 @@ 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'):
+                 limit=None, encoding='utf-8', errors='replace', separator='&'):
         """Constructor.  Read multipart/* until last part.
 
         Arguments, all optional:
@@ -448,6 +451,7 @@ def __init__(self, fp=None, headers=None, outerboundary=b'',
         method = 'GET'
         self.keep_blank_values = keep_blank_values
         self.strict_parsing = strict_parsing
+        self.separator = separator
         if 'REQUEST_METHOD' in environ:
             method = environ['REQUEST_METHOD'].upper()
         self.qs_on_post = None
@@ -673,7 +677,7 @@ def read_urlencoded(self):
         self.list = []
         query = urllib.parse.parse_qsl(
             qs, self.keep_blank_values, self.strict_parsing,
-            encoding=self.encoding, errors=self.errors)
+            encoding=self.encoding, errors=self.errors, separator=self.separator)
         for key, value in query:
             self.list.append(MiniFieldStorage(key, value))
         self.skip_lines()
@@ -689,7 +693,7 @@ def read_multi(self, environ, keep_blank_values, strict_parsing):
         if self.qs_on_post:
             query = urllib.parse.parse_qsl(
                 self.qs_on_post, self.keep_blank_values, self.strict_parsing,
-                encoding=self.encoding, errors=self.errors)
+                encoding=self.encoding, errors=self.errors, separator=self.separator)
             for key, value in query:
                 self.list.append(MiniFieldStorage(key, value))
 
@@ -727,7 +731,7 @@ def read_multi(self, environ, keep_blank_values, strict_parsing):
 
             part = klass(self.fp, headers, ib, environ, keep_blank_values,
                          strict_parsing,self.limit-self.bytes_read,
-                         self.encoding, self.errors)
+                         self.encoding, self.errors, self.separator)
             self.bytes_read += part.bytes_read
             self.list.append(part)
             if part.done or self.bytes_read >= self.length > 0:

Lib/test/test_cgi.py

@@ -54,12 +54,9 @@ def do_test(buf, method):
     ("", 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: ''")),
@@ -74,8 +71,6 @@ def do_test(buf, method):
     ("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'],
@@ -178,7 +173,29 @@ def test_strict(self):
                         self.assertEqual(fs.getvalue(key), expect_val)
                     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")
 

Lib/test/test_urlparse.py

@@ -32,16 +32,10 @@
     (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')]),
 ]
 
 parse_qs_test_cases = [
@@ -65,16 +59,10 @@
     (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):
@@ -867,6 +855,42 @@ def test_parse_qsl_encoding(self):
                                                           errors="ignore")
         self.assertEqual(result, [('key', '\u0141-')])
 
+    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("Original: %s, Expected: %s"%(orig, expect)):
+                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("Original: %s, Expected: %s"%(orig, expect)):
+                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.

Lib/urllib/parse.py

@@ -571,7 +571,7 @@ def unquote(string, encoding='utf-8', errors='replace'):
     return ''.join(res)
 
 def parse_qs(qs, keep_blank_values=False, strict_parsing=False,
-             encoding='utf-8', errors='replace'):
+             encoding='utf-8', errors='replace', separator='&'):
     """Parse a query given as a string argument.
 
         Arguments:
@@ -591,10 +591,13 @@ 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.
+
+        separator: str. The symbol to use for separating the query arguments.
+            Defaults to &.
     """
     parsed_result = {}
     pairs = parse_qsl(qs, keep_blank_values, strict_parsing,
-                      encoding=encoding, errors=errors)
+                      encoding=encoding, errors=errors, separator=separator)
     for name, value in pairs:
         if name in parsed_result:
             parsed_result[name].append(value)
@@ -603,7 +606,7 @@ def parse_qs(qs, keep_blank_values=False, strict_parsing=False,
     return parsed_result
 
 def parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
-              encoding='utf-8', errors='replace'):
+              encoding='utf-8', errors='replace', separator='&'):
     """Parse a query given as a string argument.
 
     Arguments:
@@ -623,10 +626,17 @@ 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.
 
+    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)
-    pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
+
+    if not separator or (not isinstance(separator, (str, bytes))):
+        raise ValueError("Separator must be of type string or bytes.")
+
+    pairs = [s1 for s1 in qs.split(separator)]
     r = []
     for name_value in pairs:
         if not name_value and not strict_parsing: