Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Remove ProxyMiddleware #5607

Merged
merged 5 commits into from
May 9, 2019
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
49 changes: 47 additions & 2 deletions readthedocs/analytics/tests.py
Original file line number Diff line number Diff line change
@@ -1,7 +1,11 @@
# -*- coding: utf-8 -*-
from django.test import TestCase
from django.test import TestCase, RequestFactory

from .utils import anonymize_ip_address, anonymize_user_agent
from .utils import (
anonymize_ip_address,
anonymize_user_agent,
get_client_ip,
)


class UtilsTests(TestCase):
Expand All @@ -28,3 +32,44 @@ def test_anonymize_ua(self):
anonymize_user_agent('Some rare user agent'),
'Rare user agent',
)

def test_get_client_ip_with_x_forwarded_for(self):

# only client's ip is present
request = RequestFactory().get('/')
request.META['HTTP_X_FORWARDED_FOR'] = '203.0.113.195'
client_ip = get_client_ip(request)
self.assertEqual(client_ip, '203.0.113.195')

# proxy1 and proxy2 are present along with client's ip
request = RequestFactory().get('/')
request.META['HTTP_X_FORWARDED_FOR'] = '203.0.113.195, 70.41.3.18, 150.172.238.178'
client_ip = get_client_ip(request)
self.assertEqual(client_ip, '203.0.113.195')

# client ip with port
request = RequestFactory().get('/')
request.META['HTTP_X_FORWARDED_FOR'] = '203.0.113.195:8080, 70.41.3.18, 150.172.238.178'
client_ip = get_client_ip(request)
self.assertEqual(client_ip, '203.0.113.195')

# client ip with port but not proxy1 and proxy2
request = RequestFactory().get('/')
request.META['HTTP_X_FORWARDED_FOR'] = '203.0.113.195:8080'
client_ip = get_client_ip(request)
self.assertEqual(client_ip, '203.0.113.195')

# no header is present
request = RequestFactory().get('/')
if request.META['REMOTE_ADDR']:
del request.META['REMOTE_ADDR']
client_ip = get_client_ip(request)
self.assertEqual(client_ip, None)

def test_get_client_ip_with_remote_addr(self):

request = RequestFactory().get('/')
self.assertIsNone(request.META.get('HTTP_X_FORWARDED_FOR'))
request.META['REMOTE_ADDR'] = '203.0.113.195'
client_ip = get_client_ip(request)
self.assertEqual(client_ip, '203.0.113.195')
23 changes: 17 additions & 6 deletions readthedocs/analytics/utils.py
Original file line number Diff line number Diff line change
Expand Up @@ -17,15 +17,26 @@


def get_client_ip(request):
"""Gets the real IP based on a request object."""
ip_address = request.META.get('REMOTE_ADDR')
"""
Gets the real client's IP address.

# Get the original IP address (eg. "X-Forwarded-For: client, proxy1, proxy2")
x_forwarded_for = request.META.get('HTTP_X_FORWARDED_FOR', '').split(',')[0]
It returns the real IP address of the client based on ``HTTP_X_FORWARDED_FOR``
header. If ``HTTP_X_FORWARDED_FOR`` is not found, it returns the value of
``REMOTE_ADDR`` header and returns ``None`` if both the headers are not found.
"""
x_forwarded_for = request.META.get('HTTP_X_FORWARDED_FOR', None)
if x_forwarded_for:
ip_address = x_forwarded_for.rsplit(':')[0]
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This logic was removed and also shouldn't be. The X-Forwarded-For header is not exactly a standard but some implementations include a port number. This line strips that port number.

This function is correct and working as-is. Is there a reason to change it? I do appreciate comments which capture the reasoning though.

Copy link
Member Author

@dojutsu-user dojutsu-user Apr 20, 2019

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@davidfischer

The X-Forwarded-For header is not exactly a standard but some implementations include a port number.

Thank you for this information. I didn't found this while searching about the header and removed this line thinking that it can produce bugs.
I have updated the code.

Is there a reason to change it?

The only reason was the readability and to improve comments.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We should add tests for this also.

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@ericholscher
I have added the tests.

# HTTP_X_FORWARDED_FOR can be a comma-separated list of IPs.
# The client's IP will be the first one.
# (eg. "X-Forwarded-For: client, proxy1, proxy2")
client_ip = x_forwarded_for.split(',')[0].strip()

# Removing the port number (if present)
client_ip = client_ip.rsplit(':')[0]
else:
client_ip = request.META.get('REMOTE_ADDR', None)

return ip_address
return client_ip


def anonymize_ip_address(ip_address):
Expand Down
28 changes: 0 additions & 28 deletions readthedocs/core/middleware.py
Original file line number Diff line number Diff line change
Expand Up @@ -186,34 +186,6 @@ def process_request(self, request):
return None


# Forked from old Django
class ProxyMiddleware(MiddlewareMixin):

"""
Middleware that sets REMOTE_ADDR based on HTTP_X_FORWARDED_FOR, if the.

latter is set. This is useful if you're sitting behind a reverse proxy that
causes each request's REMOTE_ADDR to be set to 127.0.0.1. Note that this
does NOT validate HTTP_X_FORWARDED_FOR. If you're not behind a reverse proxy
that sets HTTP_X_FORWARDED_FOR automatically, do not use this middleware.
Anybody can spoof the value of HTTP_X_FORWARDED_FOR, and because this sets
REMOTE_ADDR based on HTTP_X_FORWARDED_FOR, that means anybody can "fake"
their IP address. Only use this when you can absolutely trust the value of
HTTP_X_FORWARDED_FOR.
"""

def process_request(self, request):
try:
real_ip = request.META['HTTP_X_FORWARDED_FOR']
except KeyError:
return None
else:
# HTTP_X_FORWARDED_FOR can be a comma-separated list of IPs. The
# client's IP will be the first one.
real_ip = real_ip.split(',')[0].strip()
request.META['REMOTE_ADDR'] = real_ip


class FooterNoSessionMiddleware(SessionMiddleware):

"""
Expand Down
1 change: 0 additions & 1 deletion readthedocs/settings/base.py
Original file line number Diff line number Diff line change
Expand Up @@ -126,7 +126,6 @@ def USE_PROMOS(self): # noqa
return 'readthedocsext.donate' in self.INSTALLED_APPS

MIDDLEWARE = (
'readthedocs.core.middleware.ProxyMiddleware',
'readthedocs.core.middleware.FooterNoSessionMiddleware',
'django.middleware.locale.LocaleMiddleware',
'django.middleware.common.CommonMiddleware',
Expand Down