Fixed #27912, CVE-2017-7233 -- Fixed is_safe_url() with numeric URLs.

This is a security fix.

1 files changed, 54 insertions, 3 deletions

diff --git a/django/utils/http.py b/django/utils/http.py
index bd2daad4b2..1433df4ff0 100644
--- a/django/utils/http.py
+++ b/django/utils/http.py
@@ -7,8 +7,9 @@ import warnings
 from binascii import Error as BinasciiError
 from email.utils import formatdate
 from urllib.parse import (
-    quote, quote_plus, unquote, unquote_plus, urlencode as original_urlencode,
-    urlparse,
+    ParseResult, SplitResult, _coerce_args, _splitnetloc, _splitparams, quote,
+    quote_plus, scheme_chars, unquote, unquote_plus,
+    urlencode as original_urlencode, uses_params,
 )
 
 from django.core.exceptions import TooManyFieldsSent
@@ -293,12 +294,62 @@ def is_safe_url(url, host=None, allowed_hosts=None, require_https=False):
             _is_safe_url(url.replace('\\', '/'), allowed_hosts, require_https=require_https))
 
 
+# Copied from urllib.parse.urlparse() but uses fixed urlsplit() function.
+def _urlparse(url, scheme='', allow_fragments=True):
+    """Parse a URL into 6 components:
+    <scheme>://<netloc>/<path>;<params>?<query>#<fragment>
+    Return a 6-tuple: (scheme, netloc, path, params, query, fragment).
+    Note that we don't break the components up in smaller bits
+    (e.g. netloc is a single string) and we don't expand % escapes."""
+    url, scheme, _coerce_result = _coerce_args(url, scheme)
+    splitresult = _urlsplit(url, scheme, allow_fragments)
+    scheme, netloc, url, query, fragment = splitresult
+    if scheme in uses_params and ';' in url:
+        url, params = _splitparams(url)
+    else:
+        params = ''
+    result = ParseResult(scheme, netloc, url, params, query, fragment)
+    return _coerce_result(result)
+
+
+# Copied from urllib.parse.urlsplit() with
+# https://github.com/python/cpython/pull/661 applied.
+def _urlsplit(url, scheme='', allow_fragments=True):
+    """Parse a URL into 5 components:
+    <scheme>://<netloc>/<path>?<query>#<fragment>
+    Return a 5-tuple: (scheme, netloc, path, query, fragment).
+    Note that we don't break the components up in smaller bits
+    (e.g. netloc is a single string) and we don't expand % escapes."""
+    url, scheme, _coerce_result = _coerce_args(url, scheme)
+    allow_fragments = bool(allow_fragments)
+    netloc = query = fragment = ''
+    i = url.find(':')
+    if i > 0:
+        for c in url[:i]:
+            if c not in scheme_chars:
+                break
+        else:
+            scheme, url = url[:i].lower(), url[i + 1:]
+
+    if url[:2] == '//':
+        netloc, url = _splitnetloc(url, 2)
+        if (('[' in netloc and ']' not in netloc) or
+                (']' in netloc and '[' not in netloc)):
+            raise ValueError("Invalid IPv6 URL")
+    if allow_fragments and '#' in url:
+        url, fragment = url.split('#', 1)
+    if '?' in url:
+        url, query = url.split('?', 1)
+    v = SplitResult(scheme, netloc, url, query, fragment)
+    return _coerce_result(v)
+
+
 def _is_safe_url(url, allowed_hosts, require_https=False):
     # Chrome considers any URL with more than two slashes to be absolute, but
     # urlparse is not so flexible. Treat any url with three slashes as unsafe.
     if url.startswith('///'):
         return False
-    url_info = urlparse(url)
+    url_info = _urlparse(url)
     # Forbid URLs like http:///example.com - with a scheme, but without a hostname.
     # In that URL, example.com is not the hostname but, a path component. However,
     # Chrome will still consider example.com to be the hostname, so we must not