From 2ab67552a097522a82fd250b8b36995a9bc2cd80 Mon Sep 17 00:00:00 2001
From: Mike Bayer <mike_mp@zzzcomputing.com>
Date: Mon, 24 May 2021 11:12:11 -0400
Subject: URL parsing fixes

Fixed a long-standing issue with :class:`.URL` where query parameters
following the question mark would not be parsed correctly if the URL did
not contain a database portion with a backslash.

Fixed issue where an ``@`` sign in the database portion of a URL would not
be interpreted correctly if the URL also had a username:password section.

Fixes: #6329
Fixes: #6482
Change-Id: I6cb6478affa49b618335b947a74e64090657a98c
---
 lib/sqlalchemy/engine/url.py | 39 +++++++++++++++++----------------------
 1 file changed, 17 insertions(+), 22 deletions(-)

(limited to 'lib/sqlalchemy')

diff --git a/lib/sqlalchemy/engine/url.py b/lib/sqlalchemy/engine/url.py
index 7898f9121..f60b9d56d 100644
--- a/lib/sqlalchemy/engine/url.py
+++ b/lib/sqlalchemy/engine/url.py
@@ -702,16 +702,17 @@ def _parse_rfc1738_args(name):
             (?P<name>[\w\+]+)://
             (?:
                 (?P<username>[^:/]*)
-                (?::(?P<password>.*))?
+                (?::(?P<password>[^@]*))?
             @)?
             (?:
                 (?:
-                    \[(?P<ipv6host>[^/]+)\] |
-                    (?P<ipv4host>[^/:]+)
+                    \[(?P<ipv6host>[^/\?]+)\] |
+                    (?P<ipv4host>[^/:\?]+)
                 )?
-                (?::(?P<port>[^/]*))?
+                (?::(?P<port>[^/\?]*))?
             )?
-            (?:/(?P<database>.*))?
+            (?:/(?P<database>[^\?]*))?
+            (?:\?(?P<query>.*))?
             """,
         re.X,
     )
@@ -719,23 +720,17 @@ def _parse_rfc1738_args(name):
     m = pattern.match(name)
     if m is not None:
         components = m.groupdict()
-        if components["database"] is not None:
-            tokens = components["database"].split("?", 2)
-            components["database"] = tokens[0]
-
-            if len(tokens) > 1:
-                query = {}
-
-                for key, value in util.parse_qsl(tokens[1]):
-                    if util.py2k:
-                        key = key.encode("ascii")
-                    if key in query:
-                        query[key] = util.to_list(query[key])
-                        query[key].append(value)
-                    else:
-                        query[key] = value
-            else:
-                query = None
+        if components["query"] is not None:
+            query = {}
+
+            for key, value in util.parse_qsl(components["query"]):
+                if util.py2k:
+                    key = key.encode("ascii")
+                if key in query:
+                    query[key] = util.to_list(query[key])
+                    query[key].append(value)
+                else:
+                    query[key] = value
         else:
             query = None
         components["query"] = query
-- 
cgit v1.2.1