gitea-admin/gh-christianlouis-docuelevate
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: improve join_url - use walrus op, remove posixpath.normpath

Browse Source 
Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
Agent-Logs-Url: https://github.com/christianlouis/DocuElevate/sessions/54fd29b1-b600-4e60-aa0a-a069836ad129
This commit is contained in:
copilot-swe-agent[bot]
2026-03-23 16:20:56 +00:00
parent 8984d4da70
commit 15dd1a8471
1 changed files with 10 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/utils/network.py
+10 -13
View File
@@ -1,6 +1,5 @@
import ipaddress import ipaddress
import logging import logging
import posixpath
import socket import socket
from urllib.parse import urlsplit, urlunsplit from urllib.parse import urlsplit, urlunsplit
@@ -41,23 +40,21 @@ def join_url(base: str, *parts: str) -> str:
Safely join a base URL with one or more path parts. Safely join a base URL with one or more path parts.
Uses urllib.parse to correctly handle scheme/netloc/query/fragment so that Uses urllib.parse to correctly handle scheme/netloc/query/fragment so that
only the path component is normalised (double slashes removed via only the path component is modified. Leading and trailing slashes are
posixpath.join). The scheme separator ``://`` is therefore never at risk stripped from each part before joining, preventing double-slash sequences
of being collapsed. at segment boundaries without touching the scheme separator or query string.
Examples: Examples:
join_url("https://example.com/dav/", "/remote/", "file.pdf") join_url("https://example.com/dav/", "/remote/", "file.pdf")
-> "https://example.com/dav/remote/file.pdf" -> "https://example.com/dav/remote/file.pdf"
""" """
parsed = urlsplit(base) parsed = urlsplit(base)
# Strip leading/trailing slashes from every part so posixpath.join # Strip each part once and filter out empty segments; use walrus operator
# produces a clean joined path without accidental double slashes. # to avoid calling strip twice per iteration.
stripped_parts = [p.strip("/") for p in parts if p.strip("/")] stripped_parts = [s for p in parts if (s := p.strip("/"))]
base_path = parsed.path.rstrip("/") base_path = parsed.path.rstrip("/")
if stripped_parts: new_path = base_path + "/" + "/".join(stripped_parts) if stripped_parts else base_path
new_path = base_path + "/" + "/".join(stripped_parts) # Ensure path is non-empty so the reconstructed URL is valid.
else: if not new_path:
new_path = base_path new_path = "/"
# Normalise any remaining double slashes in the path only.
new_path = posixpath.normpath(new_path) if new_path else "/"
return urlunsplit((parsed.scheme, parsed.netloc, new_path, parsed.query, parsed.fragment)) return urlunsplit((parsed.scheme, parsed.netloc, new_path, parsed.query, parsed.fragment))