gh-91539: improve performance of get_proxies_environment (#91566)

* improve performance of get_proxies_environment when there are many environment variables

* 📜🤖 Added by blurb_it.

* fix case of short env name

* fix formatting

* fix whitespace

* whitespace

* Update Lib/urllib/request.py

Co-authored-by: Carl Meyer <carl@oddbird.net>

* Update Lib/urllib/request.py

Co-authored-by: Carl Meyer <carl@oddbird.net>

* Update Lib/urllib/request.py

Co-authored-by: Carl Meyer <carl@oddbird.net>

* Update Lib/urllib/request.py

Co-authored-by: Carl Meyer <carl@oddbird.net>

* whitespace

* Update Misc/NEWS.d/next/Library/2022-04-15-11-29-38.gh-issue-91539.7WgVuA.rst

Co-authored-by: Carl Meyer <carl@oddbird.net>

* Update Lib/urllib/request.py

Co-authored-by: Carl Meyer <carl@oddbird.net>

Co-authored-by: blurb-it[bot] <43283697+blurb-it[bot]@users.noreply.github.com>
Co-authored-by: Carl Meyer <carl@oddbird.net>

2 files changed, 17 insertions, 10 deletions

diff --git a/Lib/urllib/request.py b/Lib/urllib/request.py
index 1761e95..e2d5b8c 100644
--- a/Lib/urllib/request.py
+++ b/Lib/urllib/request.py
@@ -2508,28 +2508,34 @@ def getproxies_environment():
     this seems to be the standard convention.  If you need a
     different way, you can pass a proxies dictionary to the
     [Fancy]URLopener constructor.
-
     """
-    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
+
+    # select only environment variables which end in (after making lowercase) _proxy
+    proxies = {}
+    environment = []
+    for name in os.environ.keys():
+        # fast screen underscore position before more expensive case-folding
+        if len(name) > 5 and name[-6] == "_" and name[-5:].lower() == "proxy":
+            value = os.environ[name]
+            proxy_name = name[:-6].lower()
+            environment.append((name, value, proxy_name))
+            if value:
+                proxies[proxy_name] = value
     # CVE-2016-1000110 - If we are running as CGI script, forget HTTP_PROXY
     # (non-all-lowercase) as it may be set from the web server by a "Proxy:"
     # header from the client
     # If "proxy" is lowercase, it will still be used thanks to the next block
     if 'REQUEST_METHOD' in os.environ:
         proxies.pop('http', None)
-    for name, value in os.environ.items():
+    for name, value, proxy_name in environment:
+        # not case-folded, checking here for lower-case env vars only
         if name[-6:] == '_proxy':
-            name = name.lower()
             if value:
-                proxies[name[:-6]] = value
+                proxies[proxy_name] = value
             else:
-                proxies.pop(name[:-6], None)
+                proxies.pop(proxy_name, None)
     return proxies
 
 def proxy_bypass_environment(host, proxies=None):
diff --git a/Misc/NEWS.d/next/Library/2022-04-15-11-29-38.gh-issue-91539.7WgVuA.rst b/Misc/NEWS.d/next/Library/2022-04-15-11-29-38.gh-issue-91539.7WgVuA.rst
new file mode 100644
index 0000000..16d61f1
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2022-04-15-11-29-38.gh-issue-91539.7WgVuA.rst
@@ -0,0 +1 @@
+Improve performance of ``urllib.request.getproxies_environment`` when there are many environment variables