[Python-checkins] cpython (3.5): Issue #26804: urllib.request will prefer lower_case proxy environment variables

senthil.kumaran python-checkins at python.org
Mon Apr 25 11:34:52 EDT 2016


https://hg.python.org/cpython/rev/49b975122022
changeset:   101140:49b975122022
branch:      3.5
parent:      101138:2c1651fbfbba
user:        Senthil Kumaran <senthil at uthcode.com>
date:        Mon Apr 25 08:16:23 2016 -0700
summary:
  Issue #26804: urllib.request will prefer lower_case proxy environment variables
over UPPER_CASE or Mixed_Case ones.

Patch contributed by Hans-Peter Jansen. Reviewed by Martin Panter and Senthil Kumaran.

files:
  Doc/library/urllib.request.rst |   2 +
  Lib/test/test_urllib.py        |  40 ++++++++++++++++++-
  Lib/urllib/request.py          |  46 ++++++++++++++++-----
  Misc/ACKS                      |   1 +
  Misc/NEWS                      |   4 +
  5 files changed, 81 insertions(+), 12 deletions(-)


diff --git a/Doc/library/urllib.request.rst b/Doc/library/urllib.request.rst
--- a/Doc/library/urllib.request.rst
+++ b/Doc/library/urllib.request.rst
@@ -166,6 +166,8 @@
    in a case insensitive approach, for all operating systems first, and when it
    cannot find it, looks for proxy information from Mac OSX System
    Configuration for Mac OS X and Windows Systems Registry for Windows.
+   If both lowercase and uppercase environment variables exist (and disagree),
+   lowercase is preferred.
 
 
 The following classes are provided:
diff --git a/Lib/test/test_urllib.py b/Lib/test/test_urllib.py
--- a/Lib/test/test_urllib.py
+++ b/Lib/test/test_urllib.py
@@ -226,8 +226,46 @@
         # getproxies_environment use lowered case truncated (no '_proxy') keys
         self.assertEqual('localhost', proxies['no'])
         # List of no_proxies with space.
-        self.env.set('NO_PROXY', 'localhost, anotherdomain.com, newdomain.com')
+        self.env.set('NO_PROXY', 'localhost, anotherdomain.com, newdomain.com:1234')
         self.assertTrue(urllib.request.proxy_bypass_environment('anotherdomain.com'))
+        self.assertTrue(urllib.request.proxy_bypass_environment('anotherdomain.com:8888'))
+        self.assertTrue(urllib.request.proxy_bypass_environment('newdomain.com:1234'))
+
+
+class ProxyTests_withOrderedEnv(unittest.TestCase):
+
+    def setUp(self):
+        # We need to test conditions, where variable order _is_ significant
+        self._saved_env = os.environ
+        # Monkey patch os.environ, start with empty fake environment
+        os.environ = collections.OrderedDict()
+
+    def tearDown(self):
+        os.environ = self._saved_env
+
+    def test_getproxies_environment_prefer_lowercase(self):
+        # Test lowercase preference with removal
+        os.environ['no_proxy'] = ''
+        os.environ['No_Proxy'] = 'localhost'
+        self.assertFalse(urllib.request.proxy_bypass_environment('localhost'))
+        self.assertFalse(urllib.request.proxy_bypass_environment('arbitrary'))
+        os.environ['http_proxy'] = ''
+        os.environ['HTTP_PROXY'] = 'http://somewhere:3128'
+        proxies = urllib.request.getproxies_environment()
+        self.assertEqual({}, proxies)
+        # Test lowercase preference of proxy bypass and correct matching including ports
+        os.environ['no_proxy'] = 'localhost, noproxy.com, my.proxy:1234'
+        os.environ['No_Proxy'] = 'xyz.com'
+        self.assertTrue(urllib.request.proxy_bypass_environment('localhost'))
+        self.assertTrue(urllib.request.proxy_bypass_environment('noproxy.com:5678'))
+        self.assertTrue(urllib.request.proxy_bypass_environment('my.proxy:1234'))
+        self.assertFalse(urllib.request.proxy_bypass_environment('my.proxy'))
+        self.assertFalse(urllib.request.proxy_bypass_environment('arbitrary'))
+        # Test lowercase preference with replacement
+        os.environ['http_proxy'] = 'http://somewhere:3128'
+        os.environ['Http_Proxy'] = 'http://somewhereelse:3128'
+        proxies = urllib.request.getproxies_environment()
+        self.assertEqual('http://somewhere:3128', proxies['http'])
 
 class urlopen_HttpTests(unittest.TestCase, FakeHTTPMixin, FakeFTPMixin):
     """Test urlopen() opening a fake http connection."""
diff --git a/Lib/urllib/request.py b/Lib/urllib/request.py
--- a/Lib/urllib/request.py
+++ b/Lib/urllib/request.py
@@ -2395,19 +2395,35 @@
 
     """
     proxies = {}
+    # in order to prefer lowercase variables, process environment in
+    # two passes: first matches any, second pass matches lowercase only
     for name, value in os.environ.items():
         name = name.lower()
         if value and name[-6:] == '_proxy':
             proxies[name[:-6]] = value
+    for name, value in os.environ.items():
+        if name[-6:] == '_proxy':
+            name = name.lower()
+            if value:
+                proxies[name[:-6]] = value
+            else:
+                proxies.pop(name[:-6], None)
     return proxies
 
-def proxy_bypass_environment(host):
+def proxy_bypass_environment(host, proxies=None):
     """Test if proxies should not be used for a particular host.
 
-    Checks the environment for a variable named no_proxy, which should
-    be a list of DNS suffixes separated by commas, or '*' for all hosts.
+    Checks the proxy dict for the value of no_proxy, which should
+    be a list of comma separated DNS suffixes, or '*' for all hosts.
+
     """
-    no_proxy = os.environ.get('no_proxy', '') or os.environ.get('NO_PROXY', '')
+    if proxies is None:
+        proxies = getproxies_environment()
+    # don't bypass, if no_proxy isn't specified
+    try:
+        no_proxy = proxies['no']
+    except KeyError:
+        return 0
     # '*' is special case for always bypass
     if no_proxy == '*':
         return 1
@@ -2502,8 +2518,15 @@
 
 
     def proxy_bypass(host):
-        if getproxies_environment():
-            return proxy_bypass_environment(host)
+        """Return True, if host should be bypassed.
+
+        Checks proxy settings gathered from the environment, if specified,
+        or from the MacOSX framework SystemConfiguration.
+
+        """
+        proxies = getproxies_environment()
+        if proxies:
+            return proxy_bypass_environment(host, proxies)
         else:
             return proxy_bypass_macosx_sysconf(host)
 
@@ -2617,14 +2640,15 @@
         return 0
 
     def proxy_bypass(host):
-        """Return a dictionary of scheme -> proxy server URL mappings.
-
-        Returns settings gathered from the environment, if specified,
+        """Return True, if host should be bypassed.
+
+        Checks proxy settings gathered from the environment, if specified,
         or the registry.
 
         """
-        if getproxies_environment():
-            return proxy_bypass_environment(host)
+        proxies = getproxies_environment()
+        if proxies:
+            return proxy_bypass_environment(host, proxies)
         else:
             return proxy_bypass_registry(host)
 
diff --git a/Misc/ACKS b/Misc/ACKS
--- a/Misc/ACKS
+++ b/Misc/ACKS
@@ -670,6 +670,7 @@
 Bertrand Janin
 Geert Jansen
 Jack Jansen
+Hans-Peter Jansen
 Bill Janssen
 Thomas Jarosch
 Juhana Jauhiainen
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -107,6 +107,10 @@
 Library
 -------
 
+- Issue #26804: urllib.request will prefer lower_case proxy environment
+  variables over UPPER_CASE or Mixed_Case ones. Patch contributed by Hans-Peter
+  Jansen.
+
 - Issue #26837: assertSequenceEqual() now correctly outputs non-stringified
   differing items (like bytes in the -b mode).  This affects assertListEqual()
   and assertTupleEqual().

-- 
Repository URL: https://hg.python.org/cpython


More information about the Python-checkins mailing list