Normalize request paths in media auth (#24662)

* merge repeated slashes in the media auth path check

X-Original-URL carries only the raw request path since #24602, and extract_path parsed it with urlparse, which reads a path starting with // as a host. A restricted role could request another camera's clips or recordings with a leading // and the media check saw a non-media path and allowed it, while nginx merged the slashes and served the file. extract_path now splits the raw URI the same way the go2rtc stream check does and merges repeated slashes as nginx does before matching locations. The split helper moves from auth.py into media_auth.py so both checks share it.

* check the nginx-normalized path in the media auth dot-segment fallback

The dot-segment fallback only checked the raw first segment, so a role restricted to one camera could request `/x/../clips/back_door-1.jpg` and nginx served back_door's clip. The fallback now resolves the path the way nginx does before checking for a media root, and the URI split ends at a literal `#` since nginx ignores everything after it.

frigate/api/auth.py

@@ -11,7 +11,7 @@ import secrets
 import time
 from datetime import datetime
 from pathlib import Path
-from urllib.parse import parse_qs, unquote
+from urllib.parse import parse_qs
 
 import requests
 from fastapi import APIRouter, Depends, HTTPException, Request, Response
@@ -31,6 +31,8 @@ from frigate.api.media_auth import (
     check_camera_access,
     deny_response_for_media_uri,
     is_role_restricted,
+    normalize_request_path,
+    split_request_uri,
 )
 from frigate.config import AuthConfig, ProxyConfig
 from frigate.const import CONFIG_DIR, JWT_SECRET_ENV_VAR, PASSWORD_HASH_ALGORITHM
@@ -1185,37 +1187,6 @@ GO2RTC_STREAM_PROXY_PATHS = frozenset(
     }
 )
 
-_URI_SCHEME_AND_AUTHORITY = re.compile(r"^[A-Za-z][A-Za-z0-9+.-]*://[^/?]*")
-
-
-def _split_request_uri(request_uri: str) -> tuple[str, str]:
-    """Split a raw request URI into its path and query string.
-
-    urlparse is not used since it reads a path starting with `//` as a host.
-    """
-    uri = _URI_SCHEME_AND_AUTHORITY.sub("", request_uri, count=1)
-    path, _, query = uri.partition("?")
-    return path, query
-
-
-def _normalize_request_path(path: str) -> str:
-    """Normalize a raw request path the way nginx does before matching locations.
-
-    nginx percent-decodes the path, merges repeated slashes and resolves dot
-    segments, while `X-Original-URL` carries the raw `$request_uri`.
-    """
-    segments: list[str] = []
-    for segment in unquote(path).split("/"):
-        if segment in ("", "."):
-            continue
-        if segment == "..":
-            if segments:
-                segments.pop()
-            continue
-        segments.append(segment)
-
-    return "/" + "/".join(segments)
-
 
 def _is_go2rtc_stream_proxy_request(path: str, request: Request) -> bool:
     # nginx marks requests routed through the go2rtc stream locations, and the
@@ -1223,7 +1194,7 @@ def _is_go2rtc_stream_proxy_request(path: str, request: Request) -> bool:
     if request.headers.get("x-go2rtc-stream-proxy") == "1":
         return True
 
-    normalized = _normalize_request_path(path)
+    normalized = normalize_request_path(path)
     return any(normalized.startswith(p) for p in GO2RTC_STREAM_PROXY_PATHS)
 
 
@@ -1242,7 +1213,7 @@ def deny_response_for_go2rtc_stream(
     if not original_url:
         return None
 
-    path, query = _split_request_uri(original_url)
+    path, query = split_request_uri(original_url)
     if not _is_go2rtc_stream_proxy_request(path, request):
         return None