python-botocore/Fix-rejecting-URLs-with-unsafe-characters-in.patch

48 lines
1.6 KiB
Diff

From 4f7cc3a38802c2ec54b1168815792b49656f7fa0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Micha=C5=82=20G=C3=B3rny?= <mgorny@gentoo.org>
Date: Fri, 7 May 2021 10:49:27 +0200
Subject: [PATCH] Fix rejecting URLs with unsafe characters in
---
botocore/utils.py | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/botocore/utils.py b/botocore/utils.py
index cf61e7a..57f6194 100644
--- a/botocore/utils.py
+++ b/botocore/utils.py
@@ -173,6 +173,10 @@ ZONE_ID_PAT = "(?:%25|%)(?:[" + UNRESERVED_PAT + "]|%[a-fA-F0-9]{2})+"
IPV6_ADDRZ_PAT = r"\[" + IPV6_PAT + r"(?:" + ZONE_ID_PAT + r")?\]"
IPV6_ADDRZ_RE = re.compile("^" + IPV6_ADDRZ_PAT + "$")
+# These are the characters that are stripped by post-bpo-43882 urlparse().
+UNSAFE_URL_CHARS = frozenset('\t\r\n')
+
+
def ensure_boolean(val):
"""Ensures a boolean value if a string or boolean is provided
@@ -977,6 +981,8 @@ class ArgumentGenerator(object):
def is_valid_ipv6_endpoint_url(endpoint_url):
+ if UNSAFE_URL_CHARS.intersection(endpoint_url):
+ return False
netloc = urlparse(endpoint_url).netloc
return IPV6_ADDRZ_RE.match(netloc) is not None
@@ -990,6 +996,10 @@ def is_valid_endpoint_url(endpoint_url):
:return: True if the endpoint url is valid. False otherwise.
"""
+ # post-bpo-43882 urlsplit() strips unsafe characters from URL, causing
+ # it to pass hostname validation below. Detect them early to fix that.
+ if UNSAFE_URL_CHARS.intersection(endpoint_url):
+ return False
parts = urlsplit(endpoint_url)
hostname = parts.hostname
if hostname is None:
--
2.27.0