Files
DocsGPT/docsgpt/parser/connectors/share_point/auth.py
T
Alex 574f96341e refactor: rename the application package to docsgpt
The backend import package is now docsgpt, the name it will carry on PyPI;
application was far too generic to install into anyone's site-packages.
git mv plus a mechanical rewrite of every import, dotted string and path
reference: 734 Python files, the compose files, Dockerfile, workflows, docs,
setup scripts, devcontainer, k8s manifests, vscode config, pytest and coverage
config, .gitignore. Behaviour is unchanged.

Kept for one release:
- A top-level application package whose meta-path finder resolves
  application.x.y to the already-imported docsgpt.x.y object, so old imports
  and entry points (celery -A application.app.celery,
  uvicorn application.asgi:asgi_app) keep working with a FutureWarning.
- Celery registers every application.* task name as an alias of its
  docsgpt.* task on start-up, so messages queued by the previous release still
  run. The redbeat key prefix moves to redbeat:docsgpt:v2: so schedule entries
  the previous release wrote are left unread instead of firing twice.

The backend image builds from the repository root (docker build -f
docsgpt/Dockerfile .) so it can ship the alias package; a root .dockerignore
allow-lists docsgpt/ and application/ and keeps caches, local data, .env
files, the sample index files and the Dockerfile out. Compose and the image
workflows point at the new context.
2026-09-07 10:20:43 +01:00

154 lines
5.8 KiB
Python

import datetime
import logging
from typing import Optional, Dict, Any
from msal import ConfidentialClientApplication
from docsgpt.core.settings import settings
from docsgpt.parser.connectors._auth_utils import session_token_fingerprint
from docsgpt.parser.connectors.base import BaseConnectorAuth
logger = logging.getLogger(__name__)
class SharePointAuth(BaseConnectorAuth):
"""
Handles Microsoft OAuth 2.0 authentication for SharePoint/OneDrive.
Note: Files.Read scope allows access to files the user has granted access to,
similar to Google Drive's drive.file scope.
"""
SCOPES = [
"Files.Read",
"Sites.Read.All",
"User.Read",
]
def __init__(self):
self.client_id = settings.MICROSOFT_CLIENT_ID
self.client_secret = settings.MICROSOFT_CLIENT_SECRET
if not self.client_id:
raise ValueError(
"Microsoft OAuth credentials not configured. Please set MICROSOFT_CLIENT_ID in settings."
)
if not self.client_secret:
raise ValueError(
"Microsoft OAuth credentials not configured. Please set MICROSOFT_CLIENT_SECRET in settings."
)
self.redirect_uri = settings.CONNECTOR_REDIRECT_BASE_URI
self.tenant_id = settings.MICROSOFT_TENANT_ID
self.authority = getattr(settings, "MICROSOFT_AUTHORITY", f"https://login.microsoftonline.com/{self.tenant_id}")
self.auth_app = ConfidentialClientApplication(
client_id=self.client_id,
client_credential=self.client_secret,
authority=self.authority
)
def get_authorization_url(self, state: Optional[str] = None) -> str:
return self.auth_app.get_authorization_request_url(
scopes=self.SCOPES, state=state, redirect_uri=self.redirect_uri
)
def exchange_code_for_tokens(self, authorization_code: str) -> Dict[str, Any]:
result = self.auth_app.acquire_token_by_authorization_code(
code=authorization_code,
scopes=self.SCOPES,
redirect_uri=self.redirect_uri
)
if "error" in result:
logger.error("Token exchange failed: %s", result.get("error_description"))
raise ValueError(f"Error acquiring token: {result.get('error_description')}")
return self.map_token_response(result)
def refresh_access_token(self, refresh_token: str) -> Dict[str, Any]:
result = self.auth_app.acquire_token_by_refresh_token(refresh_token=refresh_token, scopes=self.SCOPES)
if "error" in result:
logger.error("Token refresh failed: %s", result.get("error_description"))
raise ValueError(f"Error refreshing token: {result.get('error_description')}")
return self.map_token_response(result)
def get_token_info_from_session(self, session_token: str) -> Dict[str, Any]:
try:
from docsgpt.storage.db.repositories.connector_sessions import (
ConnectorSessionsRepository,
)
from docsgpt.storage.db.session import db_readonly
with db_readonly() as conn:
session = ConnectorSessionsRepository(conn).get_by_session_token(
session_token
)
if not session:
raise ValueError(
f"Invalid session token ({session_token_fingerprint(session_token)})"
)
token_info = session.get("token_info")
if not token_info:
raise ValueError("Session missing token information")
required_fields = ["access_token", "refresh_token"]
missing_fields = [field for field in required_fields if field not in token_info or not token_info.get(field)]
if missing_fields:
raise ValueError(f"Missing required token fields: {missing_fields}")
if 'token_uri' not in token_info:
token_info['token_uri'] = f"https://login.microsoftonline.com/{settings.MICROSOFT_TENANT_ID}/oauth2/v2.0/token"
return token_info
except Exception as e:
logger.error("Failed to retrieve token from session: %s", e)
raise ValueError(f"Failed to retrieve SharePoint token information: {str(e)}")
def is_token_expired(self, token_info: Dict[str, Any]) -> bool:
if not token_info:
return True
expiry_timestamp = token_info.get("expiry")
if expiry_timestamp is None:
return True
current_timestamp = int(datetime.datetime.now().timestamp())
return (expiry_timestamp - current_timestamp) < 60
def sanitize_token_info(self, token_info: Dict[str, Any], **extra_fields) -> Dict[str, Any]:
return super().sanitize_token_info(
token_info,
allows_shared_content=token_info.get("allows_shared_content", False),
**extra_fields,
)
PERSONAL_ACCOUNT_TENANT_ID = "9188040d-6c67-4c5b-b112-36a304b66dad"
def _allows_shared_content(self, id_token_claims: Dict[str, Any]) -> bool:
"""Return True when the account is a work/school tenant that can access SharePoint shared content."""
tid = id_token_claims.get("tid", "")
return bool(tid) and tid != self.PERSONAL_ACCOUNT_TENANT_ID
def map_token_response(self, result) -> Dict[str, Any]:
claims = result.get("id_token_claims", {})
return {
"access_token": result.get("access_token"),
"refresh_token": result.get("refresh_token"),
"token_uri": claims.get("iss"),
"scopes": result.get("scope"),
"expiry": claims.get("exp"),
"allows_shared_content": self._allows_shared_content(claims),
"user_info": {
"name": claims.get("name"),
"email": claims.get("preferred_username"),
},
}