Issue #22928: Disabled HTTP header injections in http.client.

Original patch by Demian Brecht.

3 files changed, 97 insertions, 0 deletions

diff --git a/Lib/http/client.py b/Lib/http/client.py
index d3d9b30..3f9e67b 100644
--- a/Lib/http/client.py
+++ b/Lib/http/client.py
@@ -70,6 +70,7 @@ import email.parser
 import email.message
 import io
 import os
+import re
 import socket
 import collections
 from urllib.parse import urlsplit
@@ -217,6 +218,34 @@ MAXAMOUNT = 1048576
 _MAXLINE = 65536
 _MAXHEADERS = 100
 
+# Header name/value ABNF (http://tools.ietf.org/html/rfc7230#section-3.2)
+#
+# VCHAR          = %x21-7E
+# obs-text       = %x80-FF
+# header-field   = field-name ":" OWS field-value OWS
+# field-name     = token
+# field-value    = *( field-content / obs-fold )
+# field-content  = field-vchar [ 1*( SP / HTAB ) field-vchar ]
+# field-vchar    = VCHAR / obs-text
+#
+# obs-fold       = CRLF 1*( SP / HTAB )
+#                ; obsolete line folding
+#                ; see Section 3.2.4
+
+# token          = 1*tchar
+#
+# tchar          = "!" / "#" / "$" / "%" / "&" / "'" / "*"
+#                / "+" / "-" / "." / "^" / "_" / "`" / "|" / "~"
+#                / DIGIT / ALPHA
+#                ; any VCHAR, except delimiters
+#
+# VCHAR defined in http://tools.ietf.org/html/rfc5234#appendix-B.1
+
+# the patterns for both name and value are more leniant than RFC
+# definitions to allow for backwards compatibility
+_is_legal_header_name = re.compile(rb'[^:\s][^:\r\n]*').fullmatch
+_is_illegal_header_value = re.compile(rb'\n(?![ \t])|\r(?![ \t\n])').search
+
 
 class HTTPMessage(email.message.Message):
     # XXX The only usage of this method is in
@@ -1060,12 +1089,20 @@ class HTTPConnection:
 
         if hasattr(header, 'encode'):
             header = header.encode('ascii')
+
+        if not _is_legal_header_name(header):
+            raise ValueError('Invalid header name %r' % (header,))
+
         values = list(values)
         for i, one_value in enumerate(values):
             if hasattr(one_value, 'encode'):
                 values[i] = one_value.encode('latin-1')
             elif isinstance(one_value, int):
                 values[i] = str(one_value).encode('ascii')
+
+            if _is_illegal_header_value(values[i]):
+                raise ValueError('Invalid header value %r' % (values[i],))
+
         value = b'\r\n\t'.join(values)
         header = header + b': ' + value
         self._output(header)
diff --git a/Lib/test/test_httplib.py b/Lib/test/test_httplib.py
index 4c57867..e4911d9 100644
--- a/Lib/test/test_httplib.py
+++ b/Lib/test/test_httplib.py
@@ -148,6 +148,33 @@ class HeaderTests(TestCase):
         conn.putheader('Content-length', 42)
         self.assertIn(b'Content-length: 42', conn._buffer)
 
+        conn.putheader('Foo', ' bar ')
+        self.assertIn(b'Foo:  bar ', conn._buffer)
+        conn.putheader('Bar', '\tbaz\t')
+        self.assertIn(b'Bar: \tbaz\t', conn._buffer)
+        conn.putheader('Authorization', 'Bearer mytoken')
+        self.assertIn(b'Authorization: Bearer mytoken', conn._buffer)
+        conn.putheader('IterHeader', 'IterA', 'IterB')
+        self.assertIn(b'IterHeader: IterA\r\n\tIterB', conn._buffer)
+        conn.putheader('LatinHeader', b'\xFF')
+        self.assertIn(b'LatinHeader: \xFF', conn._buffer)
+        conn.putheader('Utf8Header', b'\xc3\x80')
+        self.assertIn(b'Utf8Header: \xc3\x80', conn._buffer)
+        conn.putheader('C1-Control', b'next\x85line')
+        self.assertIn(b'C1-Control: next\x85line', conn._buffer)
+        conn.putheader('Embedded-Fold-Space', 'is\r\n allowed')
+        self.assertIn(b'Embedded-Fold-Space: is\r\n allowed', conn._buffer)
+        conn.putheader('Embedded-Fold-Tab', 'is\r\n\tallowed')
+        self.assertIn(b'Embedded-Fold-Tab: is\r\n\tallowed', conn._buffer)
+        conn.putheader('Key Space', 'value')
+        self.assertIn(b'Key Space: value', conn._buffer)
+        conn.putheader('KeySpace ', 'value')
+        self.assertIn(b'KeySpace : value', conn._buffer)
+        conn.putheader(b'Nonbreak\xa0Space', 'value')
+        self.assertIn(b'Nonbreak\xa0Space: value', conn._buffer)
+        conn.putheader(b'\xa0NonbreakSpace', 'value')
+        self.assertIn(b'\xa0NonbreakSpace: value', conn._buffer)
+
     def test_ipv6host_header(self):
         # Default host header on IPv6 transaction should wrapped by [] if
         # its actual IPv6 address
@@ -177,6 +204,36 @@ class HeaderTests(TestCase):
         self.assertEqual(resp.getheader('First'), 'val')
         self.assertEqual(resp.getheader('Second'), 'val')
 
+    def test_invalid_headers(self):
+        conn = client.HTTPConnection('example.com')
+        conn.sock = FakeSocket('')
+        conn.putrequest('GET', '/')
+
+        # http://tools.ietf.org/html/rfc7230#section-3.2.4, whitespace is no
+        # longer allowed in header names
+        cases = (
+            (b'Invalid\r\nName', b'ValidValue'),
+            (b'Invalid\rName', b'ValidValue'),
+            (b'Invalid\nName', b'ValidValue'),
+            (b'\r\nInvalidName', b'ValidValue'),
+            (b'\rInvalidName', b'ValidValue'),
+            (b'\nInvalidName', b'ValidValue'),
+            (b' InvalidName', b'ValidValue'),
+            (b'\tInvalidName', b'ValidValue'),
+            (b'Invalid:Name', b'ValidValue'),
+            (b':InvalidName', b'ValidValue'),
+            (b'ValidName', b'Invalid\r\nValue'),
+            (b'ValidName', b'Invalid\rValue'),
+            (b'ValidName', b'Invalid\nValue'),
+            (b'ValidName', b'InvalidValue\r\n'),
+            (b'ValidName', b'InvalidValue\r'),
+            (b'ValidName', b'InvalidValue\n'),
+        )
+        for name, value in cases:
+            with self.subTest((name, value)):
+                with self.assertRaisesRegex(ValueError, 'Invalid header'):
+                    conn.putheader(name, value)
+
 
 class BasicTest(TestCase):
     def test_status_lines(self):
diff --git a/Misc/NEWS b/Misc/NEWS
index 2d69b76..282492c 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -18,6 +18,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #22928: Disabled HTTP header injections in http.client.
+  Original patch by Demian Brecht.
+
 - Issue #23615: Modules bz2, tarfile and tokenize now can be reloaded with
   imp.reload().  Patch by Thomas Kluyver.