Restrict URL preparation to HTTP/HTTPS

Requests treats all URLs starting with the string 'http' as HTTP URLs.
Preparation with IDNA breaks non-standard URIs like http+unix. Requests
now prepares only URLs with prefix http:// and https://.

Signed-off-by: Christian Heimes <christian@python.org>

requests/models.py

@@ -347,9 +347,9 @@ class PreparedRequest(RequestEncodingMixin, RequestHooksMixin):
         url = url.lstrip()
 
         # Don't do any URL preparation for non-HTTP schemes like `mailto`,
-        # `data` etc to work around exceptions from `url_parse`, which
-        # handles RFC 3986 only.
-        if ':' in url and not url.lower().startswith('http'):
+        # `data`, `http+unix` etc to work around exceptions from `url_parse`,
+        # which handles RFC 3986 only.
+        if ':' in url and not url.lower().startswith(('http://', 'https://')):
             self.url = url
             return
 

tests/test_requests.py

@@ -2138,3 +2138,20 @@ class TestPreparingURLs(object):
         r = requests.Request('GET', url=url)
         with pytest.raises(requests.exceptions.InvalidURL):
             r.prepare()
+
+    @pytest.mark.parametrize(
+        'protocol, url',
+        (
+            ("http+unix://", b"http+unix://%2Fvar%2Frun%2Fsocket/path"),
+            ("http+unix://", u"http+unix://%2Fvar%2Frun%2Fsocket/path"),
+            ("mailto", b"mailto:user@example.org"),
+            ("mailto", u"mailto:user@example.org"),
+            ("data", b"data:SSDimaUgUHl0aG9uIQ=="),
+        )
+    )
+    def test_url_passthrough(self, protocol, url):
+        session = requests.Session()
+        session.mount(protocol, HTTPAdapter())
+        p = requests.Request('GET', url=url)
+        p.prepare()
+        assert p.url == url