[3.6] bpo-42967: only use '&' as a query string separator (GH-24297) (GH-24532)

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>

2 files changed, 70 insertions, 27 deletions

diff --git a/Lib/test/test_cgi.py b/Lib/test/test_cgi.py
index b3e2d4cce8..b4d5a12eef 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'],
@@ -180,6 +175,30 @@ class CgiTests(unittest.TestCase):
                     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.