fix: merge main, resolve conflicts, address review feedback

- Resolve merge conflicts in app/api/onedrive.py and tests/test_api_google_drive_final.py
- Fix legacy Dict[str, str] type hints in update_env_file functions to use dict[str, str]
- Add admin-only access (_require_admin dependency) to save-settings endpoints
  in google_drive.py, onedrive.py, and dropbox.py
- Fix in_memory_only response field to reflect actual env_write_success status
- Update tests to override _require_admin dependency for save-settings endpoint tests
This commit is contained in:
copilot-swe-agent[bot]
2026-03-23 16:29:46 +00:00
232 changed files with 114245 additions and 911 deletions
+22
View File
@@ -296,6 +296,28 @@ def get_provider_status() -> dict[str, dict[str, object]]:
},
}
# Check SharePoint configuration
providers["SharePoint"] = {
"name": "SharePoint",
"icon": "fa-brands fa-microsoft",
"configured": bool(
getattr(settings, "sharepoint_client_id", None)
and getattr(settings, "sharepoint_client_secret", None)
and getattr(settings, "sharepoint_site_url", None)
),
"enabled": True,
"description": "Store documents in Microsoft SharePoint Online",
"details": {
"client_id": getattr(settings, "sharepoint_client_id", "Not set"),
"client_secret": mask_sensitive_value(getattr(settings, "sharepoint_client_secret", None)),
"tenant_id": getattr(settings, "sharepoint_tenant_id", "Not set"),
"refresh_token": mask_sensitive_value(getattr(settings, "sharepoint_refresh_token", None)),
"site_url": getattr(settings, "sharepoint_site_url", "Not set"),
"document_library": getattr(settings, "sharepoint_document_library", "Not set"),
"folder_path": getattr(settings, "sharepoint_folder_path", "Not set"),
},
}
# Check S3 configuration
providers["S3 Storage"] = {
"name": "S3 Storage",
+4
View File
@@ -12,6 +12,7 @@ The utility:
"""
import logging
import re
from typing import Any
from sqlalchemy import MetaData, create_engine, inspect, text
@@ -84,6 +85,9 @@ def preview_migration(source_url: str) -> dict[str, Any]:
total = 0
with src_engine.connect() as conn:
for table_name in tables:
if not re.match(r"^[a-zA-Z0-9_]+$", table_name):
logger.warning(f"Skipping table with invalid name format: {table_name}")
continue
# table_name is safe — sourced from inspect().get_table_names(), not user input
quoted_table = conn.dialect.identifier_preparer.quote(table_name)
row = conn.execute(text(f"SELECT COUNT(*) FROM {quoted_table}")).fetchone() # noqa: S608
+54
View File
@@ -0,0 +1,54 @@
import logging
import os
logger = logging.getLogger(__name__)
def update_env_file(settings_to_update: dict[str, str]) -> bool:
"""
Updates the .env file with the given settings (best-effort).
Creates or modifies existing keys.
Args:
settings_to_update: A dictionary mapping uppercase env var names to their new string values.
Returns:
True if the file was successfully updated, False otherwise.
"""
try:
env_path = os.path.join(os.path.dirname(os.path.dirname(os.path.dirname(__file__))), ".env")
if not os.path.exists(env_path):
logger.warning(f".env file not found at {env_path}, skipping file write")
return False
logger.info(f"Updating settings in {env_path}")
with open(env_path, "r") as f:
env_lines = f.readlines()
updated = set()
new_env_lines = []
for line in env_lines:
stripped_line = line.rstrip()
is_updated = False
for key, value in settings_to_update.items():
if stripped_line.startswith(f"{key}=") or stripped_line.startswith(f"# {key}="):
new_env_lines.append(f"{key}={value}")
updated.add(key)
is_updated = True
break
if not is_updated:
new_env_lines.append(stripped_line)
for key, value in settings_to_update.items():
if key not in updated:
new_env_lines.append(f"{key}={value}")
with open(env_path, "w") as f:
f.write("\n".join(new_env_lines) + "\n")
logger.info("Successfully updated settings in .env file")
return True
except Exception as env_err:
logger.warning(f"Failed to write .env file (non-fatal): {env_err}")
return False
+12 -1
View File
@@ -7,8 +7,19 @@ def hash_file(filepath: str | Path, chunk_size: int = 65536) -> str:
Returns the SHA-256 hash of the file at 'filepath'.
Reads the file in chunks to handle large files efficiently.
"""
from app.config import settings
filepath_obj = Path(filepath).resolve()
workdir_obj = Path(settings.workdir).resolve()
# Security check: Ensure the resolved path is strictly within the allowed workdir
try:
filepath_obj.relative_to(workdir_obj)
except ValueError:
raise FileNotFoundError(f"Access denied: path traversal attempt or file outside workdir '{filepath}'")
sha256 = hashlib.sha256()
with open(filepath, "rb") as f:
with open(filepath_obj, "rb") as f:
while True:
data = f.read(chunk_size)
if not data:
+79 -77
View File
@@ -34,89 +34,91 @@ logger = logging.getLogger(__name__)
SUPPORTED_LANGUAGES: list[dict[str, str]] = [
# --- Tier 1: Primary European languages ---
{"code": "en", "name": "English", "native": "English", "flag": "🇬🇧"},
{"code": "de", "name": "German", "native": "Deutsch", "flag": "🇩🇪"},
{"code": "fr", "name": "French", "native": "Français", "flag": "🇫🇷"},
{"code": "es", "name": "Spanish", "native": "Español", "flag": "🇪🇸"},
{"code": "it", "name": "Italian", "native": "Italiano", "flag": "🇮🇹"},
{"code": "pt", "name": "Portuguese", "native": "Português", "flag": "🇵🇹"},
# flag: lowercase ISO 3166-1 alpha-2 country code used with the flag-icons CSS library
# (e.g. "gb" → <span class="fi fi-gb">). Regional codes like "gb-wls" are also supported.
{"code": "en", "name": "English", "native": "English", "flag": "gb"},
{"code": "de", "name": "German", "native": "Deutsch", "flag": "de"},
{"code": "fr", "name": "French", "native": "Français", "flag": "fr"},
{"code": "es", "name": "Spanish", "native": "Español", "flag": "es"},
{"code": "it", "name": "Italian", "native": "Italiano", "flag": "it"},
{"code": "pt", "name": "Portuguese", "native": "Português", "flag": "pt"},
# --- Tier 2: Western & Northern European ---
{"code": "nl", "name": "Dutch", "native": "Nederlands", "flag": "🇳🇱"},
{"code": "nb", "name": "Norwegian Bokmål", "native": "Norsk bokmål", "flag": "🇳🇴"},
{"code": "no", "name": "Norwegian", "native": "Norsk", "flag": "🇳🇴"},
{"code": "da", "name": "Danish", "native": "Dansk", "flag": "🇩🇰"},
{"code": "sv", "name": "Swedish", "native": "Svenska", "flag": "🇸🇪"},
{"code": "fi", "name": "Finnish", "native": "Suomi", "flag": "🇫🇮"},
{"code": "is", "name": "Icelandic", "native": "Íslenska", "flag": "🇮🇸"},
{"code": "ga", "name": "Irish", "native": "Gaeilge", "flag": "🇮🇪"},
{"code": "lb", "name": "Luxembourgish", "native": "Lëtzebuergesch", "flag": "🇱🇺"},
{"code": "ca", "name": "Catalan", "native": "Català", "flag": "🏴"},
{"code": "cy", "name": "Welsh", "native": "Cymraeg", "flag": "🏴󠁧󠁢󠁷󠁬󠁳󠁿"}, # Wales subdivision flag (U+1F3F4 + tag chars)
{"code": "fy", "name": "Western Frisian", "native": "Frysk", "flag": "🇳🇱"},
{"code": "gl", "name": "Galician", "native": "Galego", "flag": "🇪🇸"},
{"code": "li", "name": "Limburgish", "native": "Limburgs", "flag": "🇳🇱"},
{"code": "vls", "name": "Flemish", "native": "West-Vlams", "flag": "🇧🇪"},
{"code": "nds", "name": "Low German", "native": "Plattdüütsch", "flag": "🇩🇪"},
{"code": "nl", "name": "Dutch", "native": "Nederlands", "flag": "nl"},
{"code": "nb", "name": "Norwegian Bokmål", "native": "Norsk bokmål", "flag": "no"},
{"code": "no", "name": "Norwegian", "native": "Norsk", "flag": "no"},
{"code": "da", "name": "Danish", "native": "Dansk", "flag": "dk"},
{"code": "sv", "name": "Swedish", "native": "Svenska", "flag": "se"},
{"code": "fi", "name": "Finnish", "native": "Suomi", "flag": "fi"},
{"code": "is", "name": "Icelandic", "native": "Íslenska", "flag": "is"},
{"code": "ga", "name": "Irish", "native": "Gaeilge", "flag": "ie"},
{"code": "lb", "name": "Luxembourgish", "native": "Lëtzebuergesch", "flag": "lu"},
{"code": "ca", "name": "Catalan", "native": "Català", "flag": "es"}, # no dedicated ISO flag; use Spain
{"code": "cy", "name": "Welsh", "native": "Cymraeg", "flag": "gb-wls"}, # flag-icons GB region code
{"code": "fy", "name": "Western Frisian", "native": "Frysk", "flag": "nl"},
{"code": "gl", "name": "Galician", "native": "Galego", "flag": "es"},
{"code": "li", "name": "Limburgish", "native": "Limburgs", "flag": "nl"},
{"code": "vls", "name": "Flemish", "native": "West-Vlams", "flag": "be"},
{"code": "nds", "name": "Low German", "native": "Plattdüütsch", "flag": "de"},
# --- Tier 3: Central & Eastern European ---
{"code": "pl", "name": "Polish", "native": "Polski", "flag": "🇵🇱"},
{"code": "cs", "name": "Czech", "native": "Čeština", "flag": "🇨🇿"},
{"code": "sk", "name": "Slovak", "native": "Slovenčina", "flag": "🇸🇰"},
{"code": "hu", "name": "Hungarian", "native": "Magyar", "flag": "🇭🇺"},
{"code": "sl", "name": "Slovenian", "native": "Slovenščina", "flag": "🇸🇮"},
{"code": "hr", "name": "Croatian", "native": "Hrvatski", "flag": "🇭🇷"},
{"code": "ro", "name": "Romanian", "native": "Română", "flag": "🇷🇴"},
{"code": "bg", "name": "Bulgarian", "native": "Български", "flag": "🇧🇬"},
{"code": "el", "name": "Greek", "native": "Ελληνικά", "flag": "🇬🇷"},
{"code": "et", "name": "Estonian", "native": "Eesti", "flag": "🇪🇪"},
{"code": "lv", "name": "Latvian", "native": "Latviešu", "flag": "🇱🇻"},
{"code": "lt", "name": "Lithuanian", "native": "Lietuvių", "flag": "🇱🇹"},
{"code": "sr", "name": "Serbian", "native": "Српски", "flag": "🇷🇸"},
{"code": "pl", "name": "Polish", "native": "Polski", "flag": "pl"},
{"code": "cs", "name": "Czech", "native": "Čeština", "flag": "cz"},
{"code": "sk", "name": "Slovak", "native": "Slovenčina", "flag": "sk"},
{"code": "hu", "name": "Hungarian", "native": "Magyar", "flag": "hu"},
{"code": "sl", "name": "Slovenian", "native": "Slovenščina", "flag": "si"},
{"code": "hr", "name": "Croatian", "native": "Hrvatski", "flag": "hr"},
{"code": "ro", "name": "Romanian", "native": "Română", "flag": "ro"},
{"code": "bg", "name": "Bulgarian", "native": "Български", "flag": "bg"},
{"code": "el", "name": "Greek", "native": "Ελληνικά", "flag": "gr"},
{"code": "et", "name": "Estonian", "native": "Eesti", "flag": "ee"},
{"code": "lv", "name": "Latvian", "native": "Latviešu", "flag": "lv"},
{"code": "lt", "name": "Lithuanian", "native": "Lietuvių", "flag": "lt"},
{"code": "sr", "name": "Serbian", "native": "Српски", "flag": "rs"},
# --- Tier 4: Non-EU European, Middle Eastern & African ---
{"code": "tr", "name": "Turkish", "native": "Türkçe", "flag": "🇹🇷"},
{"code": "uk", "name": "Ukrainian", "native": "Українська", "flag": "🇺🇦"},
{"code": "he", "name": "Hebrew", "native": "עברית", "flag": "🇮🇱"},
{"code": "ar", "name": "Arabic", "native": "العربية", "flag": "🇸🇦"},
{"code": "fa", "name": "Persian", "native": "فارسی", "flag": "🇮🇷"},
{"code": "af", "name": "Afrikaans", "native": "Afrikaans", "flag": "🇿🇦"},
{"code": "tr", "name": "Turkish", "native": "Türkçe", "flag": "tr"},
{"code": "uk", "name": "Ukrainian", "native": "Українська", "flag": "ua"},
{"code": "he", "name": "Hebrew", "native": "עברית", "flag": "il"},
{"code": "ar", "name": "Arabic", "native": "العربية", "flag": "sa"},
{"code": "fa", "name": "Persian", "native": "فارسی", "flag": "ir"},
{"code": "af", "name": "Afrikaans", "native": "Afrikaans", "flag": "za"},
# --- Tier 5: Asian languages ---
{"code": "zh", "name": "Chinese", "native": "中文", "flag": "🇨🇳"},
{"code": "zh-TW", "name": "Traditional Chinese", "native": "繁體中文", "flag": "🇹🇼"},
{"code": "ja", "name": "Japanese", "native": "日本語", "flag": "🇯🇵"},
{"code": "ko", "name": "Korean", "native": "한국어", "flag": "🇰🇷"},
{"code": "vi", "name": "Vietnamese", "native": "Tiếng Việt", "flag": "🇻🇳"},
{"code": "pa", "name": "Punjabi", "native": "ਪੰਜਾਬੀ", "flag": "🇮🇳"},
{"code": "kn", "name": "Kannada", "native": "ಕನ್ನಡ", "flag": "🇮🇳"},
{"code": "hi", "name": "Hindi", "native": "हिन्दी", "flag": "🇮🇳"},
{"code": "bn", "name": "Bengali", "native": "বাংলা", "flag": "🇧🇩"},
{"code": "gu", "name": "Gujarati", "native": "ગુજરાતી", "flag": "🇮🇳"},
{"code": "ml", "name": "Malayalam", "native": "മലയാളം", "flag": "🇮🇳"},
{"code": "mr", "name": "Marathi", "native": "मराठी", "flag": "🇮🇳"},
{"code": "ta", "name": "Tamil", "native": "தமிழ்", "flag": "🇮🇳"},
{"code": "te", "name": "Telugu", "native": "తెలుగు", "flag": "🇮🇳"},
{"code": "ur", "name": "Urdu", "native": "اردو", "flag": "🇵🇰"},
{"code": "si", "name": "Sinhala", "native": "සිංහල", "flag": "🇱🇰"},
{"code": "ne", "name": "Nepali", "native": "नेपाली", "flag": "🇳🇵"},
{"code": "th", "name": "Thai", "native": "ไทย", "flag": "🇹🇭"},
{"code": "km", "name": "Khmer", "native": "ខ្មែរ", "flag": "🇰🇭"},
{"code": "id", "name": "Indonesian", "native": "Bahasa Indonesia", "flag": "🇮🇩"},
{"code": "ms", "name": "Malay", "native": "Bahasa Melayu", "flag": "🇲🇾"},
{"code": "jv", "name": "Javanese", "native": "Basa Jawa", "flag": "🇮🇩"},
{"code": "tl", "name": "Tagalog", "native": "Filipino", "flag": "🇵🇭"},
{"code": "mn", "name": "Mongolian", "native": "Монгол", "flag": "🇲🇳"},
{"code": "kk", "name": "Kazakh", "native": "Қазақ тілі", "flag": "🇰🇿"},
{"code": "uz", "name": "Uzbek", "native": "Oʻzbekcha", "flag": "🇺🇿"},
{"code": "az", "name": "Azerbaijani", "native": "Azərbaycan dili", "flag": "🇦🇿"},
{"code": "hy", "name": "Armenian", "native": "Հայերեն", "flag": "🇦🇲"},
{"code": "ka", "name": "Georgian", "native": "ქართული", "flag": "🇬🇪"},
{"code": "zh", "name": "Chinese", "native": "中文", "flag": "cn"},
{"code": "zh-TW", "name": "Traditional Chinese", "native": "繁體中文", "flag": "tw"},
{"code": "ja", "name": "Japanese", "native": "日本語", "flag": "jp"},
{"code": "ko", "name": "Korean", "native": "한국어", "flag": "kr"},
{"code": "vi", "name": "Vietnamese", "native": "Tiếng Việt", "flag": "vn"},
{"code": "pa", "name": "Punjabi", "native": "ਪੰਜਾਬੀ", "flag": "in"},
{"code": "kn", "name": "Kannada", "native": "ಕನ್ನಡ", "flag": "in"},
{"code": "hi", "name": "Hindi", "native": "हिन्दी", "flag": "in"},
{"code": "bn", "name": "Bengali", "native": "বাংলা", "flag": "bd"},
{"code": "gu", "name": "Gujarati", "native": "ગુજરાતી", "flag": "in"},
{"code": "ml", "name": "Malayalam", "native": "മലയാളം", "flag": "in"},
{"code": "mr", "name": "Marathi", "native": "मराठी", "flag": "in"},
{"code": "ta", "name": "Tamil", "native": "தமிழ்", "flag": "in"},
{"code": "te", "name": "Telugu", "native": "తెలుగు", "flag": "in"},
{"code": "ur", "name": "Urdu", "native": "اردو", "flag": "pk"},
{"code": "si", "name": "Sinhala", "native": "සිංහල", "flag": "lk"},
{"code": "ne", "name": "Nepali", "native": "नेपाली", "flag": "np"},
{"code": "th", "name": "Thai", "native": "ไทย", "flag": "th"},
{"code": "km", "name": "Khmer", "native": "ខ្មែរ", "flag": "kh"},
{"code": "id", "name": "Indonesian", "native": "Bahasa Indonesia", "flag": "id"},
{"code": "ms", "name": "Malay", "native": "Bahasa Melayu", "flag": "my"},
{"code": "jv", "name": "Javanese", "native": "Basa Jawa", "flag": "id"},
{"code": "tl", "name": "Tagalog", "native": "Filipino", "flag": "ph"},
{"code": "mn", "name": "Mongolian", "native": "Монгол", "flag": "mn"},
{"code": "kk", "name": "Kazakh", "native": "Қазақ тілі", "flag": "kz"},
{"code": "uz", "name": "Uzbek", "native": "Oʻzbekcha", "flag": "uz"},
{"code": "az", "name": "Azerbaijani", "native": "Azərbaycan dili", "flag": "az"},
{"code": "hy", "name": "Armenian", "native": "Հայերեն", "flag": "am"},
{"code": "ka", "name": "Georgian", "native": "ქართული", "flag": "ge"},
# --- Tier 6: African languages ---
{"code": "sw", "name": "Swahili", "native": "Kiswahili", "flag": "🇰🇪"},
{"code": "am", "name": "Amharic", "native": "አማርኛ", "flag": "🇪🇹"},
{"code": "ha", "name": "Hausa", "native": "Hausa", "flag": "🇳🇬"},
{"code": "yo", "name": "Yoruba", "native": "Yorùbá", "flag": "🇳🇬"},
{"code": "ig", "name": "Igbo", "native": "Igbo", "flag": "🇳🇬"},
{"code": "zu", "name": "Zulu", "native": "isiZulu", "flag": "🇿🇦"},
{"code": "sw", "name": "Swahili", "native": "Kiswahili", "flag": "ke"},
{"code": "am", "name": "Amharic", "native": "አማርኛ", "flag": "et"},
{"code": "ha", "name": "Hausa", "native": "Hausa", "flag": "ng"},
{"code": "yo", "name": "Yoruba", "native": "Yorùbá", "flag": "ng"},
{"code": "ig", "name": "Igbo", "native": "Igbo", "flag": "ng"},
{"code": "zu", "name": "Zulu", "native": "isiZulu", "flag": "za"},
# --- Tier 7: Constructed & other languages ---
{"code": "eo", "name": "Esperanto", "native": "Esperanto", "flag": "🌍"},
{"code": "eo", "name": "Esperanto", "native": "Esperanto", "flag": "un"}, # UN flag for international language
]
SUPPORTED_LANGUAGE_CODES: set[str] = {lang["code"] for lang in SUPPORTED_LANGUAGES}
+505
View File
@@ -0,0 +1,505 @@
"""Server-side session management utilities.
Provides helpers for creating, validating, and revoking user sessions.
Sessions are tracked in the ``user_sessions`` table and referenced by a
cryptographically random token stored in the browser cookie. This enables
the "log off everywhere" feature and per-session revocation.
"""
from __future__ import annotations
import logging
import secrets
from datetime import datetime, timedelta, timezone
from sqlalchemy.orm import Session
from app.config import settings
from app.models import ApiToken, QRLoginChallenge, UserSession
logger = logging.getLogger(__name__)
def _ensure_tz_aware(dt: datetime | None) -> datetime | None:
"""Return *dt* with UTC tzinfo if it is naive, or unchanged if already aware.
SQLite does not persist timezone information, so datetimes read back from
the database are offset-naive. This helper normalises them for safe
comparison with ``datetime.now(timezone.utc)``.
"""
if dt is not None and dt.tzinfo is None:
return dt.replace(tzinfo=timezone.utc)
return dt
def get_session_lifetime_days() -> int:
"""Return the effective session lifetime in days.
If ``session_lifetime_custom_days`` is set it takes precedence over
``session_lifetime_days``.
"""
custom = getattr(settings, "session_lifetime_custom_days", None)
if custom is not None and isinstance(custom, int) and custom > 0:
return custom
return max(1, getattr(settings, "session_lifetime_days", 30))
def get_session_max_age_seconds() -> int:
"""Return the session max-age in seconds for the cookie."""
return get_session_lifetime_days() * 86400
def create_session(
db: Session,
user_id: str,
ip_address: str | None = None,
user_agent: str | None = None,
) -> UserSession:
"""Create a new server-side session record.
Args:
db: Database session.
user_id: Stable owner identifier.
ip_address: Client IP address.
user_agent: Client User-Agent header.
Returns:
The newly created ``UserSession`` instance.
"""
session_token = secrets.token_urlsafe(64)
now = datetime.now(timezone.utc)
lifetime_days = get_session_lifetime_days()
expires_at = now + timedelta(days=lifetime_days)
device_info = _parse_device_info(user_agent)
user_session = UserSession(
session_token=session_token,
user_id=user_id,
ip_address=ip_address,
user_agent=(user_agent or "")[:512],
device_info=device_info,
created_at=now,
last_active_at=now,
expires_at=expires_at,
)
try:
db.add(user_session)
db.commit()
db.refresh(user_session)
except Exception:
db.rollback()
logger.exception("Failed to create session for user_id=%s", user_id)
raise
logger.info(
"[SESSION] Created session id=%s user=%s device=%r expires=%s",
user_session.id,
user_id,
device_info,
expires_at.isoformat(),
)
return user_session
def validate_session(db: Session, session_token: str) -> UserSession | None:
"""Validate a session token and return the session if valid.
A session is valid when:
* It exists in the database.
* ``is_revoked`` is ``False``.
* ``expires_at`` is in the future.
Side-effect: updates ``last_active_at`` on valid sessions.
Returns:
The ``UserSession`` if valid, else ``None``.
"""
if not session_token:
return None
now = datetime.now(timezone.utc)
user_session = db.query(UserSession).filter(UserSession.session_token == session_token).first()
if not user_session:
logger.debug("[SESSION] Token not found in database")
return None
if user_session.is_revoked:
logger.debug("[SESSION] Session id=%s is revoked", user_session.id)
return None
if user_session.expires_at:
expires = _ensure_tz_aware(user_session.expires_at)
if expires < now:
logger.debug("[SESSION] Session id=%s has expired", user_session.id)
return None
# Update last_active_at (throttled to avoid excessive writes)
last_active = _ensure_tz_aware(user_session.last_active_at)
if not last_active or (now - last_active).total_seconds() > 60:
try:
user_session.last_active_at = now
db.commit()
except Exception:
db.rollback()
logger.debug("[SESSION] Failed to update last_active_at for session id=%s", user_session.id)
return user_session
def revoke_session(db: Session, session_id: int, user_id: str) -> bool:
"""Revoke a single session by ID.
Args:
db: Database session.
session_id: The session record ID to revoke.
user_id: The owner — ensures a user can only revoke their own sessions.
Returns:
``True`` if the session was found and revoked, ``False`` otherwise.
"""
user_session = db.get(UserSession, session_id)
if not user_session or user_session.user_id != user_id:
return False
now = datetime.now(timezone.utc)
user_session.is_revoked = True
user_session.revoked_at = now
try:
db.commit()
except Exception:
db.rollback()
raise
logger.info("[SESSION] Revoked session id=%s user=%s", session_id, user_id)
return True
def revoke_all_sessions(
db: Session,
user_id: str,
*,
except_session_id: int | None = None,
revoke_api_tokens: bool = True,
) -> int:
"""Revoke all active sessions for a user ("log off everywhere").
Args:
db: Database session.
user_id: The owner whose sessions should be revoked.
except_session_id: If provided, keep this session active (the
current browser session).
revoke_api_tokens: If ``True``, also revoke all active API tokens.
Returns:
Number of sessions revoked.
"""
now = datetime.now(timezone.utc)
query = db.query(UserSession).filter(
UserSession.user_id == user_id,
UserSession.is_revoked.is_(False),
)
if except_session_id is not None:
query = query.filter(UserSession.id != except_session_id)
sessions = query.all()
count = 0
for s in sessions:
s.is_revoked = True
s.revoked_at = now
count += 1
if revoke_api_tokens:
tokens = (
db.query(ApiToken)
.filter(
ApiToken.owner_id == user_id,
ApiToken.is_active.is_(True),
)
.all()
)
for t in tokens:
t.is_active = False
t.revoked_at = now
try:
db.commit()
except Exception:
db.rollback()
raise
logger.info(
"[SESSION] Revoked all sessions for user=%s (count=%d, except_session_id=%s, tokens_revoked=%s)",
user_id,
count,
except_session_id,
revoke_api_tokens,
)
return count
def list_user_sessions(db: Session, user_id: str) -> list[UserSession]:
"""Return all non-revoked, non-expired sessions for a user.
Results are ordered by most recently active first.
"""
now = datetime.now(timezone.utc)
sessions = (
db.query(UserSession)
.filter(
UserSession.user_id == user_id,
UserSession.is_revoked.is_(False),
)
.order_by(UserSession.last_active_at.desc())
.all()
)
# Filter expired sessions in Python to handle timezone-naive datetimes (SQLite)
result = []
for s in sessions:
expires = _ensure_tz_aware(s.expires_at)
if expires and expires > now:
result.append(s)
return result
def cleanup_expired_sessions(db: Session) -> int:
"""Delete sessions that expired more than 7 days ago.
Intended to be called periodically (e.g. via Celery beat) to keep the
table from growing unbounded.
Returns:
Number of rows deleted.
"""
cutoff = datetime.now(timezone.utc) - timedelta(days=7)
count = db.query(UserSession).filter(UserSession.expires_at < cutoff).delete(synchronize_session=False)
try:
db.commit()
except Exception:
db.rollback()
raise
if count:
logger.info("[SESSION] Cleaned up %d expired sessions", count)
return count
# ---------------------------------------------------------------------------
# QR login helpers
# ---------------------------------------------------------------------------
def create_qr_challenge(db: Session, user_id: str, ip_address: str | None = None) -> QRLoginChallenge:
"""Create a new QR login challenge.
Args:
db: Database session.
user_id: The authenticated web user creating the challenge.
ip_address: IP address of the web client.
Returns:
The newly created ``QRLoginChallenge``.
"""
token = secrets.token_urlsafe(64)
ttl = getattr(settings, "qr_login_challenge_ttl_seconds", 120)
now = datetime.now(timezone.utc)
expires_at = now + timedelta(seconds=ttl)
challenge = QRLoginChallenge(
challenge_token=token,
user_id=user_id,
created_by_ip=ip_address,
created_at=now,
expires_at=expires_at,
)
try:
db.add(challenge)
db.commit()
db.refresh(challenge)
except Exception:
db.rollback()
logger.exception("Failed to create QR login challenge for user_id=%s", user_id)
raise
logger.info("[QR_AUTH] Challenge created: id=%s user=%s expires=%s", challenge.id, user_id, expires_at.isoformat())
return challenge
def validate_qr_challenge(db: Session, challenge_token: str) -> QRLoginChallenge | None:
"""Validate a QR challenge token without claiming it.
Returns the challenge if it exists, is not expired, not claimed,
and not cancelled. Returns ``None`` otherwise.
"""
if not challenge_token:
return None
now = datetime.now(timezone.utc)
challenge = db.query(QRLoginChallenge).filter(QRLoginChallenge.challenge_token == challenge_token).first()
if not challenge:
return None
if challenge.is_claimed or challenge.is_cancelled:
return None
expires = _ensure_tz_aware(challenge.expires_at)
if expires and expires < now:
return None
return challenge
def claim_qr_challenge(
db: Session,
challenge_token: str,
device_name: str = "Mobile App",
ip_address: str | None = None,
) -> dict | None:
"""Claim a QR challenge and issue an API token.
This is the critical security path. The challenge is validated,
marked as claimed atomically, and an API token is issued for the
user who created the challenge.
Args:
db: Database session.
challenge_token: The token from the QR code.
device_name: Name provided by the mobile app.
ip_address: IP address of the claiming mobile device.
Returns:
Dict with ``token`` (plaintext), ``token_id``, ``name``, ``owner_id``
and ``created_at`` on success, or ``None`` if the challenge is invalid.
"""
from app.api.api_tokens import generate_api_token, hash_token
challenge = validate_qr_challenge(db, challenge_token)
if not challenge:
logger.warning("[QR_AUTH] Invalid or expired challenge token attempted")
return None
now = datetime.now(timezone.utc)
# Mark as claimed first to prevent race conditions
challenge.is_claimed = True
challenge.claimed_at = now
challenge.claimed_by_ip = ip_address
challenge.device_name = device_name
# Generate API token for the mobile app
token_name = f"Mobile App (QR) {device_name}"
plaintext = generate_api_token()
token_hash_value = hash_token(plaintext)
prefix = plaintext[:12]
db_token = ApiToken(
owner_id=challenge.user_id,
name=token_name,
token_hash=token_hash_value,
token_prefix=prefix,
)
try:
db.add(db_token)
db.flush()
challenge.issued_token_id = db_token.id
db.commit()
db.refresh(db_token)
except Exception:
db.rollback()
logger.exception("[QR_AUTH] Failed to issue token for challenge id=%s", challenge.id)
raise
logger.info(
"[QR_AUTH] Challenge claimed: id=%s user=%s device=%r token_id=%s",
challenge.id,
challenge.user_id,
device_name,
db_token.id,
)
return {
"token": plaintext,
"token_id": db_token.id,
"name": token_name,
"owner_id": challenge.user_id,
"created_at": db_token.created_at,
}
def get_challenge_status(db: Session, challenge_id: int, user_id: str) -> dict | None:
"""Get the current status of a QR challenge (for polling from the web UI).
Returns:
Dict with ``status`` ("pending", "claimed", "expired", "cancelled")
and metadata, or ``None`` if the challenge doesn't belong to the user.
"""
challenge = db.get(QRLoginChallenge, challenge_id)
if not challenge or challenge.user_id != user_id:
return None
now = datetime.now(timezone.utc)
expires = _ensure_tz_aware(challenge.expires_at)
if challenge.is_claimed:
status = "claimed"
elif challenge.is_cancelled:
status = "cancelled"
elif expires and expires < now:
status = "expired"
else:
status = "pending"
return {
"id": challenge.id,
"status": status,
"device_name": challenge.device_name,
"claimed_at": challenge.claimed_at,
"expires_at": challenge.expires_at,
}
def _parse_device_info(user_agent: str | None) -> str | None:
"""Extract a human-readable device description from User-Agent.
This is a lightweight parser — not a full UA library — that covers
the most common browsers and platforms.
"""
if not user_agent:
return None
ua = user_agent.lower()
# Platform detection
platform = "Unknown"
if "iphone" in ua:
platform = "iPhone"
elif "ipad" in ua:
platform = "iPad"
elif "android" in ua:
platform = "Android"
elif "macintosh" in ua or "mac os" in ua:
platform = "macOS"
elif "windows" in ua:
platform = "Windows"
elif "linux" in ua:
platform = "Linux"
elif "cros" in ua:
platform = "ChromeOS"
# Browser detection
browser = "Unknown Browser"
if "edg/" in ua or "edge/" in ua:
browser = "Edge"
elif "opr/" in ua or "opera" in ua:
browser = "Opera"
elif "chrome/" in ua and "safari/" in ua:
browser = "Chrome"
elif "safari/" in ua and "chrome/" not in ua:
browser = "Safari"
elif "firefox/" in ua:
browser = "Firefox"
elif "docuelevate" in ua:
browser = "DocuElevate App"
return f"{browser} on {platform}"
+254 -3
View File
@@ -135,6 +135,30 @@ SETTING_METADATA = {
"required": True, # Required when auth_enabled=True (validated in config.py)
"restart_required": True,
},
"session_lifetime_days": {
"category": "Authentication",
"description": "Session lifetime in days (default 30). Determines how long a user stays logged in.",
"type": "integer",
"sensitive": False,
"required": False,
"restart_required": True,
},
"session_lifetime_custom_days": {
"category": "Authentication",
"description": "Override session_lifetime_days with a custom value. Takes precedence when set.",
"type": "integer",
"sensitive": False,
"required": False,
"restart_required": True,
},
"qr_login_challenge_ttl_seconds": {
"category": "Authentication",
"description": "Time-to-live in seconds for QR login challenges (default 120).",
"type": "integer",
"sensitive": False,
"required": False,
"restart_required": False,
},
"admin_username": {
"category": "Authentication",
"description": "Admin username for local authentication",
@@ -523,6 +547,19 @@ SETTING_METADATA = {
"required": False,
"restart_required": False,
},
# Document Translation
"default_document_language": {
"category": "AI Services",
"description": (
"ISO 639-1 language code for the default document translation target "
"(e.g. 'en', 'de', 'fr'). Documents whose detected language differs "
"are automatically translated into this language after processing."
),
"type": "string",
"sensitive": False,
"required": False,
"restart_required": False,
},
# OCR Engine Configuration
"ocr_providers": {
"category": "OCR Engines",
@@ -863,6 +900,63 @@ SETTING_METADATA = {
"required": False,
"restart_required": False,
},
# Storage Providers - SharePoint
"sharepoint_client_id": {
"category": "Storage Providers",
"description": "SharePoint Azure AD application (client) ID",
"type": "string",
"sensitive": False,
"required": False,
"restart_required": False,
},
"sharepoint_client_secret": {
"category": "Storage Providers",
"description": "SharePoint Azure AD client secret",
"type": "string",
"sensitive": True,
"required": False,
"restart_required": False,
},
"sharepoint_tenant_id": {
"category": "Storage Providers",
"description": "SharePoint Azure AD tenant ID (use 'common' for multi-tenant apps)",
"type": "string",
"sensitive": False,
"required": False,
"restart_required": False,
},
"sharepoint_refresh_token": {
"category": "Storage Providers",
"description": "SharePoint OAuth refresh token",
"type": "string",
"sensitive": True,
"required": False,
"restart_required": False,
},
"sharepoint_site_url": {
"category": "Storage Providers",
"description": "SharePoint site URL (e.g. https://tenant.sharepoint.com/sites/sitename)",
"type": "string",
"sensitive": False,
"required": False,
"restart_required": False,
},
"sharepoint_document_library": {
"category": "Storage Providers",
"description": "SharePoint document library name (default: 'Documents')",
"type": "string",
"sensitive": False,
"required": False,
"restart_required": False,
},
"sharepoint_folder_path": {
"category": "Storage Providers",
"description": "Subfolder path inside the SharePoint document library",
"type": "string",
"sensitive": False,
"required": False,
"restart_required": False,
},
# Storage Providers - WebDAV
"webdav_enabled": {
"category": "Storage Providers",
@@ -1888,6 +1982,28 @@ SETTING_METADATA = {
"required": False,
"restart_required": False,
},
"factory_reset_on_startup": {
"category": "Feature Flags",
"description": (
"Wipe all user data on every startup so the instance always starts fresh. "
"Useful for demo/testing environments. Default: False."
),
"type": "boolean",
"sensitive": False,
"required": False,
"restart_required": True,
},
"enable_factory_reset": {
"category": "Feature Flags",
"description": (
"Show the System Reset page in the admin UI. Allows administrators to "
"trigger a full data wipe or a wipe-and-reimport from the web interface. Default: False."
),
"type": "boolean",
"sensitive": False,
"required": False,
"restart_required": False,
},
# Backup / Restore
"backup_enabled": {
"category": "Backup",
@@ -1911,14 +2027,26 @@ SETTING_METADATA = {
"category": "Backup",
"description": (
"Storage provider for remote backup copies. "
"Accepted values: s3, dropbox, google_drive, onedrive, nextcloud, webdav, ftp, sftp, email. "
"Accepted values: s3, dropbox, google_drive, onedrive, sharepoint, nextcloud, webdav, ftp, sftp, email. "
"Leave empty to keep backups local only."
),
"type": "string",
"sensitive": False,
"required": False,
"restart_required": False,
"options": ["", "s3", "dropbox", "google_drive", "onedrive", "nextcloud", "webdav", "ftp", "sftp", "email"],
"options": [
"",
"s3",
"dropbox",
"google_drive",
"onedrive",
"sharepoint",
"nextcloud",
"webdav",
"ftp",
"sftp",
"email",
],
},
"backup_remote_folder": {
"category": "Backup",
@@ -2430,6 +2558,72 @@ SETTING_METADATA = {
"required": False,
"restart_required": False,
},
# Database Connection Pool
"db_pool_size": {
"category": "Core",
"description": (
"Number of persistent connections kept in the SQLAlchemy QueuePool. "
"Has no effect for SQLite databases. Default: 5."
),
"type": "integer",
"sensitive": False,
"required": False,
"restart_required": True,
},
"db_max_overflow": {
"category": "Core",
"description": (
"Maximum extra connections that can be opened beyond db_pool_size. "
"Has no effect for SQLite databases. Default: 10."
),
"type": "integer",
"sensitive": False,
"required": False,
"restart_required": True,
},
"db_pool_timeout": {
"category": "Core",
"description": (
"Seconds to wait for a connection from the pool before raising an error. "
"Has no effect for SQLite databases. Default: 30."
),
"type": "integer",
"sensitive": False,
"required": False,
"restart_required": True,
},
"db_pool_recycle": {
"category": "Core",
"description": (
"Seconds after which idle connections are recycled to prevent stale connections. "
"Has no effect for SQLite databases. Default: 1800 (30 minutes)."
),
"type": "integer",
"sensitive": False,
"required": False,
"restart_required": True,
},
# Per-user upload rate limiting
"upload_rate_limit_per_user": {
"category": "Security",
"description": (
"Maximum number of uploads a single user may submit within upload_rate_limit_window seconds. "
"The health-aware limiter may reduce this dynamically under high Redis queue depth or CPU load. "
"Default: 20."
),
"type": "integer",
"sensitive": False,
"required": False,
"restart_required": False,
},
"upload_rate_limit_window": {
"category": "Security",
"description": ("Sliding window in seconds over which upload_rate_limit_per_user is enforced. Default: 60."),
"type": "integer",
"sensitive": False,
"required": False,
"restart_required": False,
},
# Rate Limiting
"rate_limiting_enabled": {
"category": "Security",
@@ -2629,6 +2823,63 @@ SETTING_METADATA = {
"required": False,
"restart_required": False,
},
# Logging
"log_level": {
"category": "Observability",
"description": (
"Python logging level for the application root logger. "
"Accepts: DEBUG, INFO, WARNING, ERROR, CRITICAL. "
"When DEBUG=True and LOG_LEVEL is not explicitly set, "
"the effective level is automatically lowered to DEBUG."
),
"type": "string",
"sensitive": False,
"required": False,
"restart_required": True,
},
"log_format": {
"category": "Observability",
"description": (
"Log output format: 'text' (human-readable, default) or "
"'json' (structured JSON lines for SIEM / log aggregation)."
),
"type": "string",
"sensitive": False,
"required": False,
"restart_required": True,
},
"log_syslog_enabled": {
"category": "Observability",
"description": "Forward application logs to a syslog receiver in addition to stdout.",
"type": "boolean",
"sensitive": False,
"required": False,
"restart_required": True,
},
"log_syslog_host": {
"category": "Observability",
"description": "Hostname or IP of the syslog receiver for application logs.",
"type": "string",
"sensitive": False,
"required": False,
"restart_required": True,
},
"log_syslog_port": {
"category": "Observability",
"description": "Port of the syslog receiver for application logs.",
"type": "integer",
"sensitive": False,
"required": False,
"restart_required": True,
},
"log_syslog_protocol": {
"category": "Observability",
"description": "Protocol for syslog transport: 'udp' or 'tcp'.",
"type": "string",
"sensitive": False,
"required": False,
"restart_required": True,
},
# Observability Sentry
"sentry_dsn": {
"category": "Observability",
@@ -3123,7 +3374,7 @@ def get_settings_for_export(db: Session, source: str = "db") -> Dict[str, str]:
return {k.upper(): v for k, v in sorted(db_settings.items()) if v is not None}
def update_env_file(env_path: str, settings_to_update: Dict[str, str]) -> bool:
def update_env_file(env_path: str, settings_to_update: dict[str, str]) -> bool:
"""
Update an .env file with new settings.
+296
View File
@@ -0,0 +1,296 @@
"""
System reset utilities for DocuElevate.
Provides functions to:
- Wipe all user data (database rows + work-files on disk) for a fresh start.
- Wipe with re-import: move original files to a dedicated folder, wipe
everything, then let the watch-folder mechanism re-ingest the files.
Security: All public functions in this module require admin-level access.
They MUST only be invoked from admin-guarded API/view endpoints.
"""
import logging
import shutil
from pathlib import Path
from sqlalchemy.orm import Session
from app.config import settings
logger = logging.getLogger(__name__)
# Subdirectories inside *workdir* that contain user-generated data.
# Everything else (app code, static assets, config) is left untouched.
_USER_DATA_SUBDIRS = ("original", "processed", "tmp", "pdfa", "backups")
# JSON cache files written by watch-folder / ingest tasks.
_CACHE_FILES = (
"watch_folder_processed.json",
"ftp_ingest_processed.json",
"sftp_ingest_processed.json",
"dropbox_ingest_processed.json",
"gdrive_ingest_processed.json",
"onedrive_ingest_processed.json",
"nextcloud_ingest_processed.json",
"s3_ingest_processed.json",
"webdav_ingest_processed.json",
"processed_mails.json",
"credential_failures.json",
)
# The folder name used for storing files prior to re-import.
REIMPORT_FOLDER_NAME = "reimport"
def _wipe_workdir_data(workdir: str) -> dict[str, int]:
"""Delete user data subdirectories and cache files inside *workdir*.
Leaves the workdir directory itself intact so the application can
continue to write into it. Also leaves any files that do not belong
to the known data subdirectories or caches.
Returns:
A dict with counts of deleted directories and files.
"""
workdir_path = Path(workdir)
deleted_dirs = 0
deleted_files = 0
# Remove data subdirectories
for subdir in _USER_DATA_SUBDIRS:
target = workdir_path / subdir
if target.is_dir():
shutil.rmtree(target)
logger.info("Deleted data directory: %s", target)
deleted_dirs += 1
# Remove cache / state JSON files
for cache_file in _CACHE_FILES:
target = workdir_path / cache_file
if target.is_file():
target.unlink()
logger.info("Deleted cache file: %s", target)
deleted_files += 1
# Also remove user_wf_*.json files (per-user watch folder caches)
for f in workdir_path.glob("user_wf_*.json"):
f.unlink()
logger.info("Deleted user watch-folder cache: %s", f)
deleted_files += 1
# Remove loose files in workdir root that are user uploads (uuid-named
# files like "a1b2c3d4-…pdf") but NOT application config files.
for entry in workdir_path.iterdir():
if entry.is_file() and entry.suffix.lower() in {
".pdf",
".png",
".jpg",
".jpeg",
".tiff",
".tif",
".docx",
".doc",
".xlsx",
".xls",
".pptx",
".heic",
".heif",
".webp",
".bmp",
".gif",
".txt",
".rtf",
".odt",
".ods",
".odp",
".csv",
".pages",
".numbers",
".keynote",
}:
entry.unlink()
logger.info("Deleted loose workdir file: %s", entry)
deleted_files += 1
return {"deleted_dirs": deleted_dirs, "deleted_files": deleted_files}
def _wipe_database(db: Session) -> dict[str, int]:
"""Delete all user-generated rows from the database.
Preserves schema (tables, migrations) and system-seeded rows that will
be re-created on the next startup (subscription plans, default pipeline,
scheduled jobs, compliance templates).
Returns:
A dict mapping table name → number of rows deleted.
"""
from app.models import (
AuditLog,
BackupRecord,
DocumentMetadata,
FileProcessingStep,
FileRecord,
InAppNotification,
ProcessingLog,
SavedSearch,
SettingsAuditLog,
SharedLink,
UserImapAccount,
UserIntegration,
UserNotificationPreference,
UserNotificationTarget,
)
# Order matters: delete children before parents to respect FK constraints.
tables_to_wipe: list[tuple[str, type]] = [
("file_processing_steps", FileProcessingStep),
("processing_logs", ProcessingLog),
("shared_links", SharedLink),
("in_app_notifications", InAppNotification),
("user_notification_preferences", UserNotificationPreference),
("user_notification_targets", UserNotificationTarget),
("user_imap_accounts", UserImapAccount),
("user_integrations", UserIntegration),
("saved_searches", SavedSearch),
("settings_audit_log", SettingsAuditLog),
("audit_logs", AuditLog),
("backup_records", BackupRecord),
("document_metadata", DocumentMetadata),
("files", FileRecord),
]
result: dict[str, int] = {}
for table_name, model in tables_to_wipe:
try:
count = db.query(model).delete()
result[table_name] = count
logger.info("Wiped %d rows from %s", count, table_name)
except Exception:
logger.exception("Failed to wipe table %s during system reset", table_name)
db.rollback()
raise
db.commit()
return result
def perform_full_reset(db: Session) -> dict:
"""Perform a complete system reset: wipe database rows + work-files.
Args:
db: An active SQLAlchemy session.
Returns:
Summary dict with ``database`` and ``filesystem`` sub-dicts.
"""
logger.warning(">>> SYSTEM RESET: wiping all user data <<<")
db_result = _wipe_database(db)
fs_result = _wipe_workdir_data(settings.workdir)
logger.warning(">>> SYSTEM RESET complete <<<")
return {"database": db_result, "filesystem": fs_result}
def perform_reset_and_reimport(db: Session) -> dict:
"""Move original files to a reimport folder, wipe everything, then
configure the reimport folder as a watch folder for re-ingestion.
The watch-folder scanner (``scan_all_watch_folders``) will pick up
the files on its next periodic run and process them exactly as if
they had been freshly uploaded — respecting the same backoff
strategy, size limits, and rate limits.
Args:
db: An active SQLAlchemy session.
Returns:
Summary dict with ``database``, ``filesystem``, and ``reimport`` sub-dicts.
"""
workdir_path = Path(settings.workdir)
reimport_dir = workdir_path / REIMPORT_FOLDER_NAME
original_dir = workdir_path / "original"
# 1. Collect original files
files_moved = 0
reimport_dir.mkdir(parents=True, exist_ok=True)
if original_dir.is_dir():
for entry in original_dir.iterdir():
if entry.is_file():
# Validate the resolved path stays within original_dir (path traversal guard)
try:
entry.resolve().relative_to(original_dir.resolve())
except ValueError:
logger.warning("Skipping file outside original dir: %s", entry)
continue
dest = reimport_dir / entry.name
# Avoid overwriting: append counter if name clash
if dest.exists():
stem = dest.stem
suffix = dest.suffix
counter = 1
while dest.exists():
dest = reimport_dir / f"{stem}_{counter}{suffix}"
counter += 1
shutil.copy2(str(entry), str(dest))
files_moved += 1
logger.info("Copied %d original files to reimport folder: %s", files_moved, reimport_dir)
# 2. Perform the full reset (wipe DB + other workdir data)
reset_result = perform_full_reset(db)
# 3. Ensure the reimport folder survived the wipe (it's not in _USER_DATA_SUBDIRS)
# and set up watch folder config to point at it.
_configure_reimport_watch_folder(str(reimport_dir))
reset_result["reimport"] = {
"files_moved": files_moved,
"reimport_folder": str(reimport_dir),
}
logger.warning(">>> SYSTEM RESET with re-import configured — %d files staged <<<", files_moved)
return reset_result
def _configure_reimport_watch_folder(reimport_path: str) -> None:
"""Append *reimport_path* to the application's watch-folder list.
The watch-folder scanner uses ``settings.watch_folders`` (a
comma-separated string). We mutate the runtime setting so the
next scan picks up the folder. We also set
``watch_folder_delete_after_process = True`` so files are cleaned
up after successful processing.
"""
current = getattr(settings, "watch_folders", None) or ""
folders = [f.strip() for f in current.split(",") if f.strip()]
if reimport_path not in folders:
folders.append(reimport_path)
# Mutate runtime settings (not persisted to .env — ephemeral)
object.__setattr__(settings, "watch_folders", ",".join(folders))
object.__setattr__(settings, "watch_folder_delete_after_process", True)
logger.info("Configured reimport watch folder: %s", reimport_path)
def perform_startup_reset() -> None:
"""Called during application startup when ``FACTORY_RESET_ON_STARTUP=True``.
Wipes database and filesystem data so the instance starts completely
fresh. Uses its own DB session so it runs before the normal lifespan
seeding logic.
"""
from app.database import SessionLocal
logger.warning("FACTORY_RESET_ON_STARTUP is enabled — wiping all data")
db = SessionLocal()
try:
perform_full_reset(db)
except Exception:
logger.exception("Factory reset on startup failed")
db.rollback()
finally:
db.close()
+56 -8
View File
@@ -20,13 +20,31 @@ from app.models import FileRecord
logger = logging.getLogger(__name__)
def _owner_id_from_user(user: dict) -> str | None:
"""Extract the owner identifier from a user dict.
Priority: ``sub`` (OAuth subject) → ``preferred_username`` → ``email`` → ``id``.
"""
return user.get("sub") or user.get("preferred_username") or user.get("email") or user.get("id")
def get_current_owner_id(request: Request) -> str | None:
"""Extract the owner identifier for the current authenticated user.
The owner ID is derived from the user's session data. It uses the
``sub`` claim (OAuth subject) when available, falling back to
``preferred_username`` or ``email``. Returns ``None`` when no user
is authenticated.
The owner ID is derived from the user's session data or, when no session
is present, from a valid Bearer API token in the ``Authorization`` header.
This ensures that both browser-based (session cookie) and mobile/API
(Bearer token) requests are correctly identified.
Priority for user resolution:
1. Session ``user`` dict (set by OAuth or local login).
2. ``request.state.api_token_user`` (set by ``require_login`` or an
earlier call to this function during the same request).
3. Direct Bearer token look-up against the database.
Within the resolved user dict the owner ID is chosen as:
``sub`` → ``preferred_username`` → ``email`` → ``id``.
Args:
request: The current FastAPI request with session data.
@@ -34,11 +52,41 @@ def get_current_owner_id(request: Request) -> str | None:
Returns:
A stable string identifier for the user, or ``None``.
"""
# 1. Session-based auth (most common for web UI)
user = request.session.get("user")
if not user or not isinstance(user, dict):
return None
# Prefer 'sub' (OAuth subject), then 'preferred_username', then 'email', then 'id'
return user.get("sub") or user.get("preferred_username") or user.get("email") or user.get("id")
if user and isinstance(user, dict):
return _owner_id_from_user(user)
# 2. Already-resolved API token user (cached by require_login or a
# prior dependency call during this request)
api_user = getattr(request.state, "api_token_user", None)
if isinstance(api_user, dict):
return _owner_id_from_user(api_user)
# 3. Direct Bearer token resolution necessary when this function is
# invoked as a FastAPI dependency (via Depends) which runs *before*
# the @require_login decorator wrapper has had a chance to resolve
# the token and populate request.state.api_token_user.
auth_header = request.headers.get("authorization", "")
if isinstance(auth_header, str) and auth_header.startswith("Bearer "):
try:
from app.auth import _resolve_bearer_user
from app.database import SessionLocal
db = SessionLocal()
try:
resolved = _resolve_bearer_user(request, db)
finally:
db.close()
if resolved:
# Cache so subsequent calls (and require_login) skip the DB
request.state.api_token_user = resolved
return _owner_id_from_user(resolved)
except Exception:
logger.debug("Bearer token resolution failed in get_current_owner_id", exc_info=True)
return None
def apply_owner_filter(query: Query, request: Request) -> Query: