From fbd605151fcf2899b14575f4ddb9ce3c55e684ab Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=D0=9A=D0=BE=D1=80=D0=B5=D0=BD=D0=B1=D0=B5=D1=80=D0=B3=20?=
 =?UTF-8?q?=D0=9C=D0=B0=D1=80=D0=BA?= <socketpair@gmail.com>
Date: Thu, 21 Dec 2017 17:16:17 +0500
Subject: [PATCH] bpo-32323: urllib.parse.urlsplit() must not lowercase() IPv6
 scope value (#4867)

---
 Lib/test/test_urlparse.py                              |  9 +++++++++
 Lib/urllib/parse.py                                    | 10 ++++++----
 .../Library/2017-12-14-10-10-10.bpo-32323.ideco.rst    |  2 ++
 3 files changed, 17 insertions(+), 4 deletions(-)
 create mode 100644 Misc/NEWS.d/next/Library/2017-12-14-10-10-10.bpo-32323.ideco.rst

diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index e5f6130e4a0..ddee1c38d8b 100644
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -520,6 +520,15 @@ class UrlParseTestCase(unittest.TestCase):
             self.assertEqual(result.url, defrag)
             self.assertEqual(result.fragment, frag)
 
+    def test_urlsplit_scoped_IPv6(self):
+        p = urllib.parse.urlsplit('http://[FE80::822a:a8ff:fe49:470c%tESt]:1234')
+        self.assertEqual(p.hostname, "fe80::822a:a8ff:fe49:470c%tESt")
+        self.assertEqual(p.netloc, '[FE80::822a:a8ff:fe49:470c%tESt]:1234')
+
+        p = urllib.parse.urlsplit(b'http://[FE80::822a:a8ff:fe49:470c%tESt]:1234')
+        self.assertEqual(p.hostname, b"fe80::822a:a8ff:fe49:470c%tESt")
+        self.assertEqual(p.netloc, b'[FE80::822a:a8ff:fe49:470c%tESt]:1234')
+
     def test_urlsplit_attributes(self):
         url = "HTTP://WWW.PYTHON.ORG/doc/#frag"
         p = urllib.parse.urlsplit(url)
diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py
index 76086e58bea..58460f9234f 100644
--- a/Lib/urllib/parse.py
+++ b/Lib/urllib/parse.py
@@ -155,10 +155,12 @@ class _NetlocResultMixinBase(object):
     def hostname(self):
         hostname = self._hostinfo[0]
         if not hostname:
-            hostname = None
-        elif hostname is not None:
-            hostname = hostname.lower()
-        return hostname
+            return None
+        # Scoped IPv6 address may have zone info, which must not be lowercased
+        # like http://[fe80::822a:a8ff:fe49:470c%tESt]:1234/keys
+        separator = '%' if isinstance(hostname, str) else b'%'
+        hostname, percent, zone = hostname.partition(separator)
+        return hostname.lower() + percent + zone
 
     @property
     def port(self):
diff --git a/Misc/NEWS.d/next/Library/2017-12-14-10-10-10.bpo-32323.ideco.rst b/Misc/NEWS.d/next/Library/2017-12-14-10-10-10.bpo-32323.ideco.rst
new file mode 100644
index 00000000000..3077d7cdfef
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2017-12-14-10-10-10.bpo-32323.ideco.rst
@@ -0,0 +1,2 @@
+:func:`urllib.parse.urlsplit()` does not convert zone-id (scope) to lower case
+for scoped IPv6 addresses in hostnames now.