Merge branch 'main' into copilot/add-conditional-routing

Resolve conflicts in app/api/__init__.py and app/models.py.
Renumber migration 027_add_routing_rules → 035_add_routing_rules.
Fix migration chain: down_revision → 034_add_user_profile_settings.
Add PipelineRoutingRule to migrations/env.py.
This commit is contained in:
copilot-swe-agent[bot]
2026-03-12 22:07:54 +00:00
163 changed files with 45250 additions and 955 deletions
+12
View File
@@ -8,18 +8,23 @@ from fastapi import APIRouter
from app.api.admin_users import router as admin_users_router
from app.api.api_tokens import router as api_tokens_router
from app.api.audit_logs import router as audit_logs_router
from app.api.azure import router as azure_router
from app.api.backup import router as backup_router
from app.api.billing import router as billing_router
from app.api.compliance import router as compliance_router
from app.api.database import router as database_router
from app.api.diagnostic import router as diagnostic_router
from app.api.dropbox import router as dropbox_router
from app.api.duplicates import router as duplicates_router
from app.api.files import router as files_router
from app.api.google_drive import router as google_drive_router
from app.api.i18n import router as i18n_router
from app.api.imap_accounts import router as imap_accounts_router
from app.api.imap_profiles import router as imap_profiles_router
from app.api.integrations import router as integrations_router
from app.api.logs import router as logs_router
from app.api.mobile import router as mobile_router
from app.api.notifications import router as notifications_router
from app.api.onboarding import router as onboarding_router
from app.api.onedrive import router as onedrive_router
@@ -27,6 +32,7 @@ from app.api.openai import router as openai_router
from app.api.pipelines import router as pipelines_router
from app.api.plans import router as plans_router
from app.api.process import router as process_router
from app.api.profile import router as profile_router
from app.api.queue import router as queue_router
from app.api.routing_rules import router as routing_rules_router
from app.api.saved_searches import router as saved_searches_router
@@ -79,8 +85,14 @@ router.include_router(plans_router)
router.include_router(onboarding_router)
router.include_router(billing_router)
router.include_router(pipelines_router)
router.include_router(profile_router)
router.include_router(routing_rules_router)
router.include_router(imap_accounts_router)
router.include_router(imap_profiles_router)
router.include_router(integrations_router)
router.include_router(notifications_router)
router.include_router(scheduled_jobs_router)
router.include_router(audit_logs_router)
router.include_router(i18n_router)
router.include_router(mobile_router)
router.include_router(compliance_router)
+115
View File
@@ -0,0 +1,115 @@
"""
Audit log REST API endpoints.
Provides read-only access to the comprehensive audit log for admin users.
Events are append-only — there are no update or delete endpoints.
"""
import logging
from datetime import datetime
from typing import Any
from fastapi import APIRouter, Depends, Query, Request
from sqlalchemy.orm import Session
from app.auth import require_login
from app.database import get_db
from app.utils.audit_service import count_events, query_events
logger = logging.getLogger(__name__)
router = APIRouter()
@router.get("/audit-logs")
@require_login
async def list_audit_logs(
request: Request,
db: Session = Depends(get_db),
action: str | None = Query(None, description="Filter by action (exact match)"),
user: str | None = Query(None, description="Filter by username"),
resource_type: str | None = Query(None, description="Filter by resource type"),
severity: str | None = Query(None, description="Filter by severity level"),
since: datetime | None = Query(None, description="Only events at or after this ISO-8601 timestamp"),
until: datetime | None = Query(None, description="Only events at or before this ISO-8601 timestamp"),
limit: int = Query(50, ge=1, le=500, description="Max rows to return"),
offset: int = Query(0, ge=0, description="Rows to skip for pagination"),
) -> dict[str, Any]:
"""Return audit log entries with optional filtering and pagination.
Requires authentication. Returns events in reverse chronological order.
"""
entries = query_events(
db,
action=action,
user=user,
resource_type=resource_type,
severity=severity,
since=since,
until=until,
limit=limit,
offset=offset,
)
total = count_events(
db,
action=action,
user=user,
resource_type=resource_type,
severity=severity,
since=since,
until=until,
)
return {
"items": [_serialize(e) for e in entries],
"total": total,
"limit": limit,
"offset": offset,
}
@router.get("/audit-logs/actions")
@require_login
async def list_distinct_actions(
request: Request,
db: Session = Depends(get_db),
) -> list[str]:
"""Return the distinct action values present in the audit log."""
from app.models import AuditLog
rows = db.query(AuditLog.action).distinct().order_by(AuditLog.action).all()
return [r[0] for r in rows]
@router.get("/audit-logs/users")
@require_login
async def list_distinct_users(
request: Request,
db: Session = Depends(get_db),
) -> list[str]:
"""Return the distinct user values present in the audit log."""
from app.models import AuditLog
rows = db.query(AuditLog.user).distinct().order_by(AuditLog.user).all()
return [r[0] for r in rows]
# ------------------------------------------------------------------
# Helpers
# ------------------------------------------------------------------
def _serialize(entry) -> dict[str, Any]:
"""Convert an AuditLog row to a JSON-safe dict."""
import json as _json
return {
"id": entry.id,
"timestamp": entry.timestamp.isoformat() if entry.timestamp else None,
"user": entry.user,
"action": entry.action,
"resource_type": entry.resource_type,
"resource_id": entry.resource_id,
"ip_address": entry.ip_address,
"details": _json.loads(entry.details) if entry.details else None,
"severity": entry.severity,
}
+2
View File
@@ -30,6 +30,7 @@ from app.auth import require_login
from app.config import settings
from app.database import get_db
from app.models import SubscriptionPlan, UserProfile
from app.utils.i18n import translate as _translate
from app.utils.user_scope import get_current_owner_id
logger = logging.getLogger(__name__)
@@ -37,6 +38,7 @@ router = APIRouter(prefix="/billing", tags=["billing"])
_templates_dir = pathlib.Path(__file__).parents[2] / "frontend" / "templates"
_templates = Jinja2Templates(directory=str(_templates_dir))
_templates.env.globals["_"] = lambda key, **kwargs: _translate(key, "en", **kwargs)
def _get_stripe() -> stripe.StripeClient | None:
+183
View File
@@ -0,0 +1,183 @@
"""API endpoints for managing compliance templates (GDPR, HIPAA, SOC2).
All endpoints require admin privileges.
Available routes:
GET /api/compliance/templates list all compliance templates
GET /api/compliance/templates/{name} get a single template with checks
POST /api/compliance/templates/{name}/apply one-click apply a template
GET /api/compliance/templates/{name}/status evaluate compliance status
GET /api/compliance/summary overall compliance dashboard data
"""
import logging
from typing import Annotated, Any
from fastapi import APIRouter, Depends, HTTPException, Request, status
from pydantic import BaseModel
from sqlalchemy.orm import Session
from app.database import get_db
from app.utils.compliance_service import (
COMPLIANCE_TEMPLATES,
apply_template,
evaluate_template_status,
get_all_templates,
get_compliance_summary,
get_template_by_name,
)
logger = logging.getLogger(__name__)
router = APIRouter(prefix="/compliance", tags=["compliance"])
DbSession = Annotated[Session, Depends(get_db)]
# ---------------------------------------------------------------------------
# Authorisation helper
# ---------------------------------------------------------------------------
def _require_admin(request: Request) -> dict:
"""Ensure the caller is an admin; raises HTTP 403 otherwise."""
user = request.session.get("user")
if not user or not user.get("is_admin"):
raise HTTPException(status_code=status.HTTP_403_FORBIDDEN, detail="Admin access required")
return user
AdminUser = Annotated[dict, Depends(_require_admin)]
# ---------------------------------------------------------------------------
# Pydantic response models
# ---------------------------------------------------------------------------
class CheckResult(BaseModel):
"""Individual compliance check result."""
key: str
label: str
description: str
expected: str
actual: str
passing: bool
class TemplateStatusResponse(BaseModel):
"""Status evaluation for a compliance template."""
status: str
total: int
passed: int
failed: int
check_results: list[CheckResult]
class TemplateResponse(BaseModel):
"""Full compliance template representation."""
id: int
name: str
display_name: str
description: str | None
enabled: bool
status: str
applied_at: str | None
applied_by: str | None
settings: dict[str, str]
checks: list[dict[str, Any]]
check_count: int
class ApplyResponse(BaseModel):
"""Result of applying a compliance template."""
success: bool
template: str | None = None
applied_settings: dict[str, str] | None = None
errors: list[str] | None = None
error: str | None = None
status: TemplateStatusResponse | None = None
class SummaryTemplateResponse(BaseModel):
"""Per-template summary for the compliance dashboard."""
name: str
display_name: str
enabled: bool
status: str
total: int
passed: int
failed: int
applied_at: str | None
applied_by: str | None
class ComplianceSummaryResponse(BaseModel):
"""Overall compliance dashboard summary."""
overall_status: str
total_checks: int
total_passed: int
total_failed: int
templates: list[SummaryTemplateResponse]
# ---------------------------------------------------------------------------
# Endpoints
# ---------------------------------------------------------------------------
@router.get("/templates", response_model=list[TemplateResponse])
async def list_templates(db: DbSession, admin: AdminUser) -> list[dict[str, Any]]:
"""List all compliance templates with their current status."""
return get_all_templates(db)
@router.get("/templates/{name}", response_model=TemplateResponse)
async def get_template(name: str, db: DbSession, admin: AdminUser) -> dict[str, Any]:
"""Get a single compliance template by name."""
templates = get_all_templates(db)
for t in templates:
if t["name"] == name:
return t
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail=f"Template '{name}' not found")
@router.post("/templates/{name}/apply", response_model=ApplyResponse)
async def apply_compliance_template(name: str, db: DbSession, admin: AdminUser) -> dict[str, Any]:
"""Apply a compliance template (one-click).
Writes all template settings to the database and evaluates the resulting
compliance status.
"""
if name not in COMPLIANCE_TEMPLATES:
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail=f"Template '{name}' not found")
template = get_template_by_name(db, name)
if template is None:
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail=f"Template '{name}' not found")
admin_email = admin.get("email", "admin")
result = apply_template(db, name, applied_by=admin_email)
if not result.get("success") and result.get("error"):
raise HTTPException(status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, detail=result["error"])
return result
@router.get("/templates/{name}/status", response_model=TemplateStatusResponse)
async def get_template_status(name: str, db: DbSession, admin: AdminUser) -> dict[str, Any]:
"""Evaluate the live compliance status of a template."""
template = get_template_by_name(db, name)
if template is None:
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail=f"Template '{name}' not found")
return evaluate_template_status(db, name)
@router.get("/summary", response_model=ComplianceSummaryResponse)
async def compliance_summary(db: DbSession, admin: AdminUser) -> dict[str, Any]:
"""Overall compliance dashboard summary across all templates."""
return get_compliance_summary(db)
+431
View File
@@ -0,0 +1,431 @@
"""
GraphQL API endpoint for DocuElevate.
Provides a flexible query interface alongside the existing REST API.
Schema covers: documents, pipelines, settings, and users.
Endpoint: /graphql
GraphiQL playground: /graphql (via browser)
"""
from __future__ import annotations
import logging
from datetime import datetime
from typing import Annotated, Any
import strawberry
from fastapi import Depends, Request
from sqlalchemy.orm import Session
from strawberry.fastapi import GraphQLRouter
from app.auth import get_current_user
from app.config import settings
from app.database import get_db
from app.models import ApplicationSettings, FileRecord, Pipeline, PipelineStep, UserProfile
logger = logging.getLogger(__name__)
# ---------------------------------------------------------------------------
# Strawberry types
# ---------------------------------------------------------------------------
@strawberry.type
class DocumentType:
"""A processed document stored in the system."""
id: int
owner_id: str | None
original_filename: str | None
local_filename: str
file_size: int
mime_type: str | None
document_title: str | None
is_duplicate: bool
ocr_quality_score: int | None
pipeline_id: int | None
created_at: datetime | None
@strawberry.type
class PipelineStepType:
"""A single step within a processing pipeline."""
id: int
pipeline_id: int
position: int
step_type: str
label: str | None
enabled: bool
created_at: datetime | None
@strawberry.type
class PipelineType:
"""A processing pipeline with its ordered steps."""
id: int
owner_id: str | None
name: str
description: str | None
is_default: bool
is_active: bool
steps: list[PipelineStepType]
created_at: datetime | None
updated_at: datetime | None
@strawberry.type
class SettingType:
"""An application configuration setting stored in the database."""
id: int
key: str
value: str | None
created_at: datetime | None
updated_at: datetime | None
@strawberry.type
class UserType:
"""A user profile in the system."""
id: int
user_id: str
display_name: str | None
is_blocked: bool
subscription_tier: str | None
onboarding_completed: bool
created_at: datetime | None
# ---------------------------------------------------------------------------
# Conversion helpers
# ---------------------------------------------------------------------------
def _document_from_record(rec: FileRecord) -> DocumentType:
return DocumentType(
id=rec.id,
owner_id=rec.owner_id,
original_filename=rec.original_filename,
local_filename=rec.local_filename,
file_size=rec.file_size,
mime_type=rec.mime_type,
document_title=rec.document_title,
is_duplicate=rec.is_duplicate,
ocr_quality_score=rec.ocr_quality_score,
pipeline_id=rec.pipeline_id,
created_at=rec.created_at,
)
def _pipeline_step_from_record(step: PipelineStep) -> PipelineStepType:
return PipelineStepType(
id=step.id,
pipeline_id=step.pipeline_id,
position=step.position,
step_type=step.step_type,
label=step.label,
enabled=step.enabled,
created_at=step.created_at,
)
def _pipeline_from_record(pipeline: Pipeline, db: Session) -> PipelineType:
steps = db.query(PipelineStep).filter(PipelineStep.pipeline_id == pipeline.id).order_by(PipelineStep.position).all()
return PipelineType(
id=pipeline.id,
owner_id=pipeline.owner_id,
name=pipeline.name,
description=pipeline.description,
is_default=pipeline.is_default,
is_active=pipeline.is_active,
steps=[_pipeline_step_from_record(s) for s in steps],
created_at=pipeline.created_at,
updated_at=pipeline.updated_at,
)
def _setting_from_record(setting: ApplicationSettings) -> SettingType:
return SettingType(
id=setting.id,
key=setting.key,
value=setting.value,
created_at=setting.created_at,
updated_at=setting.updated_at,
)
def _user_from_profile(profile: UserProfile) -> UserType:
return UserType(
id=profile.id,
user_id=profile.user_id,
display_name=profile.display_name,
is_blocked=profile.is_blocked,
subscription_tier=profile.subscription_tier,
onboarding_completed=profile.onboarding_completed,
created_at=profile.created_at,
)
# ---------------------------------------------------------------------------
# Context helpers
# ---------------------------------------------------------------------------
# Keys that contain sensitive data and must never be returned via GraphQL
_SENSITIVE_SETTING_KEYS: frozenset[str] = frozenset(
{
"openai_api_key",
"azure_ai_key",
"session_secret",
"database_url",
"redis_url",
"dropbox_app_secret",
"dropbox_refresh_token",
"google_drive_credentials_json",
"onedrive_client_secret",
"onedrive_refresh_token",
"smtp_password",
"nextcloud_password",
"s3_secret_access_key",
"ftp_password",
"sftp_password",
"webdav_password",
"stripe_secret_key",
"stripe_webhook_secret",
"sentry_dsn",
"social_auth_google_client_secret",
"social_auth_microsoft_client_secret",
"social_auth_apple_private_key",
"social_auth_dropbox_app_secret",
}
)
def _get_current_user_id(user: dict[str, Any] | None) -> str | None:
"""Extract the stable user identifier from the user dict."""
if not user:
return None
return user.get("preferred_username") or user.get("email") or user.get("id") or None
def _get_db_and_user(info: strawberry.types.Info) -> tuple[Session, dict[str, Any] | None]:
"""Extract the database session and current user from the Strawberry context."""
db: Session = info.context["db"]
user: dict[str, Any] | None = info.context.get("user")
return db, user
def _require_auth(user: dict[str, Any] | None) -> None:
"""Raise an error when authentication is enabled and no valid user is present."""
if settings.auth_enabled and not user:
raise strawberry.exceptions.StrawberryGraphQLError("Authentication required")
def _require_admin(user: dict[str, Any] | None) -> None:
"""Raise an error when the current user is not an admin.
When ``auth_enabled`` is *False* (single-user / development mode) all
callers are implicitly treated as administrators.
"""
if not settings.auth_enabled:
# Single-user mode: no auth, treat caller as admin
return
_require_auth(user)
if not (user and user.get("is_admin")):
raise strawberry.exceptions.StrawberryGraphQLError("Admin access required")
# ---------------------------------------------------------------------------
# Query resolvers
# ---------------------------------------------------------------------------
@strawberry.type
class Query:
"""Root query type for the DocuElevate GraphQL API."""
@strawberry.field(description="List documents, optionally filtered by owner.")
def documents(
self,
info: strawberry.types.Info,
owner_id: str | None = None,
limit: int = 20,
offset: int = 0,
) -> list[DocumentType]:
"""Return a paginated list of documents.
When *auth_enabled* the caller must be authenticated. Non-admin users
receive only their own documents; admins may query any *owner_id*.
"""
db, user = _get_db_and_user(info)
_require_auth(user)
limit = max(1, min(limit, 100))
offset = max(0, offset)
query = db.query(FileRecord)
if settings.auth_enabled and user:
is_admin = user.get("is_admin", False)
current_user_id = _get_current_user_id(user)
if not is_admin:
# Non-admins can only see their own documents
query = query.filter(FileRecord.owner_id == current_user_id)
elif owner_id:
query = query.filter(FileRecord.owner_id == owner_id)
elif owner_id:
query = query.filter(FileRecord.owner_id == owner_id)
records = query.order_by(FileRecord.created_at.desc()).offset(offset).limit(limit).all()
return [_document_from_record(r) for r in records]
@strawberry.field(description="Fetch a single document by ID.")
def document(self, info: strawberry.types.Info, id: int) -> DocumentType | None:
"""Return one document by its primary key, or *null* if not found."""
db, user = _get_db_and_user(info)
_require_auth(user)
rec = db.query(FileRecord).filter(FileRecord.id == id).first()
if rec is None:
return None
if settings.auth_enabled and user:
is_admin = user.get("is_admin", False)
current_user_id = _get_current_user_id(user)
if not is_admin and rec.owner_id != current_user_id:
return None
return _document_from_record(rec)
@strawberry.field(description="List processing pipelines.")
def pipelines(
self,
info: strawberry.types.Info,
owner_id: str | None = None,
limit: int = 20,
offset: int = 0,
) -> list[PipelineType]:
"""Return a paginated list of pipelines."""
db, user = _get_db_and_user(info)
_require_auth(user)
limit = max(1, min(limit, 100))
offset = max(0, offset)
query = db.query(Pipeline)
if settings.auth_enabled and user:
is_admin = user.get("is_admin", False)
current_user_id = _get_current_user_id(user)
if not is_admin:
query = query.filter((Pipeline.owner_id == current_user_id) | (Pipeline.owner_id.is_(None)))
elif owner_id:
query = query.filter(Pipeline.owner_id == owner_id)
elif owner_id:
query = query.filter(Pipeline.owner_id == owner_id)
rows = query.order_by(Pipeline.id).offset(offset).limit(limit).all()
return [_pipeline_from_record(p, db) for p in rows]
@strawberry.field(description="Fetch a single pipeline by ID.")
def pipeline(self, info: strawberry.types.Info, id: int) -> PipelineType | None:
"""Return one pipeline by its primary key, or *null* if not found."""
db, user = _get_db_and_user(info)
_require_auth(user)
row = db.query(Pipeline).filter(Pipeline.id == id).first()
if row is None:
return None
if settings.auth_enabled and user:
is_admin = user.get("is_admin", False)
current_user_id = _get_current_user_id(user)
if not is_admin and row.owner_id is not None and row.owner_id != current_user_id:
return None
return _pipeline_from_record(row, db)
@strawberry.field(description="List non-sensitive application settings (admin only).")
def settings(
self,
info: strawberry.types.Info,
limit: int = 50,
offset: int = 0,
) -> list[SettingType]:
"""Return application settings stored in the database.
Sensitive keys (API secrets, passwords, etc.) are automatically
excluded. Requires admin privileges when auth is enabled.
"""
db, user = _get_db_and_user(info)
_require_admin(user)
limit = max(1, min(limit, 200))
offset = max(0, offset)
rows = (
db.query(ApplicationSettings)
.filter(ApplicationSettings.key.notin_(_SENSITIVE_SETTING_KEYS))
.order_by(ApplicationSettings.key)
.offset(offset)
.limit(limit)
.all()
)
return [_setting_from_record(r) for r in rows]
@strawberry.field(description="List user profiles (admin only).")
def users(
self,
info: strawberry.types.Info,
limit: int = 20,
offset: int = 0,
) -> list[UserType]:
"""Return a paginated list of user profiles. Requires admin privileges."""
db, user = _get_db_and_user(info)
_require_admin(user)
limit = max(1, min(limit, 100))
offset = max(0, offset)
rows = db.query(UserProfile).order_by(UserProfile.user_id).offset(offset).limit(limit).all()
return [_user_from_profile(r) for r in rows]
@strawberry.field(description="Fetch a user profile by user_id (admin only).")
def user(self, info: strawberry.types.Info, user_id: str) -> UserType | None:
"""Return one user profile by *user_id*, or *null* if not found."""
db, user = _get_db_and_user(info)
_require_admin(user)
row = db.query(UserProfile).filter(UserProfile.user_id == user_id).first()
return _user_from_profile(row) if row else None
# ---------------------------------------------------------------------------
# Schema and router
# ---------------------------------------------------------------------------
schema = strawberry.Schema(query=Query)
async def get_graphql_context(
request: Request,
db: Annotated[Session, Depends(get_db)],
) -> dict[str, Any]:
"""Build the per-request context injected into every resolver."""
try:
user = get_current_user(request)
except Exception:
logger.debug("Could not resolve current user for GraphQL context", exc_info=True)
user = None
return {"request": request, "db": db, "user": user}
graphql_router = GraphQLRouter(
schema,
context_getter=get_graphql_context,
graphql_ide="graphiql",
)
+136
View File
@@ -0,0 +1,136 @@
"""API endpoints for internationalization (i18n).
Provides endpoints for:
* Listing available languages
* Getting/setting user language preference (persisted in session + cookie + DB)
"""
from __future__ import annotations
import logging
from fastapi import APIRouter, Depends, Request, Response
from pydantic import BaseModel
from sqlalchemy.orm import Session
from app.database import get_db
from app.models import UserProfile
from app.utils.i18n import (
DEFAULT_LANGUAGE,
SUPPORTED_LANGUAGE_CODES,
SUPPORTED_LANGUAGES,
detect_language,
)
logger = logging.getLogger(__name__)
router = APIRouter(prefix="/i18n", tags=["i18n"])
class LanguageInfo(BaseModel):
"""Schema for a supported language."""
code: str
name: str
native: str
flag: str
class LanguageListResponse(BaseModel):
"""Response for the list-languages endpoint."""
languages: list[LanguageInfo]
current: str
default: str
class SetLanguageRequest(BaseModel):
"""Request body for setting the preferred language."""
language: str
class SetLanguageResponse(BaseModel):
"""Response after changing the language."""
language: str
message: str
@router.get("/languages", response_model=LanguageListResponse)
async def list_languages(request: Request) -> LanguageListResponse:
"""Return all supported UI languages and the current active language."""
current = detect_language(request)
return LanguageListResponse(
languages=[LanguageInfo(**lang) for lang in SUPPORTED_LANGUAGES],
current=current,
default=DEFAULT_LANGUAGE,
)
@router.post("/language", response_model=SetLanguageResponse)
async def set_language(
body: SetLanguageRequest,
request: Request,
response: Response,
db: Session = Depends(get_db),
) -> SetLanguageResponse:
"""Set the preferred UI language.
Persists the choice in:
1. The server-side session
2. A ``docuelevate_lang`` cookie (30-day expiry)
3. The ``UserProfile.preferred_language`` column (if authenticated)
"""
lang = body.language.lower().strip()
if lang not in SUPPORTED_LANGUAGE_CODES:
lang = DEFAULT_LANGUAGE
# 1. Session
if hasattr(request, "session"):
request.session["preferred_language"] = lang
# 2. Cookie (30 days)
response.set_cookie(
key="docuelevate_lang",
value=lang,
max_age=30 * 24 * 60 * 60,
httponly=False,
samesite="lax",
)
# 3. Database (if user is authenticated)
_persist_language_to_profile(request, db, lang)
language_name = next(
(entry["native"] for entry in SUPPORTED_LANGUAGES if entry["code"] == lang),
lang,
)
logger.info("Language preference set to '%s'", lang)
return SetLanguageResponse(
language=lang,
message=f"Language changed to {language_name}",
)
def _persist_language_to_profile(request: Request, db: Session, lang: str) -> None:
"""Write language preference to the UserProfile row, if the user is logged in."""
user_id: str | None = None
if hasattr(request, "session"):
user = request.session.get("user")
if isinstance(user, dict):
user_id = user.get("preferred_username") or user.get("email") or user.get("id")
elif isinstance(user, str):
user_id = user
if not user_id:
return
try:
profile = db.query(UserProfile).filter(UserProfile.user_id == user_id).first()
if profile:
profile.preferred_language = lang # type: ignore[attr-defined]
db.commit()
except Exception:
db.rollback()
logger.debug("Could not persist language preference for user_id=%s", user_id)
+20
View File
@@ -110,6 +110,13 @@ class ImapAccountCreate(BaseModel):
use_ssl: bool = Field(default=True, description="Use SSL/TLS connection")
delete_after_process: bool = Field(default=False, description="Delete emails from mailbox after processing")
is_active: bool = Field(default=True, description="Whether to poll this mailbox")
profile_id: int | None = Field(
default=None,
description=(
"ID of the ImapIngestionProfile that controls which attachment types to ingest. "
"Null inherits the global imap_attachment_filter setting."
),
)
class ImapAccountUpdate(BaseModel):
@@ -123,6 +130,13 @@ class ImapAccountUpdate(BaseModel):
use_ssl: bool | None = None
delete_after_process: bool | None = None
is_active: bool | None = None
profile_id: int | None = Field(
default=None,
description=(
"ID of the ImapIngestionProfile to use. "
"Explicitly sending null clears the override (falls back to global setting)."
),
)
class ImapTestRequest(BaseModel):
@@ -155,6 +169,7 @@ def _to_response(acct: UserImapAccount) -> dict[str, Any]:
"use_ssl": acct.use_ssl,
"delete_after_process": acct.delete_after_process,
"is_active": acct.is_active,
"profile_id": acct.profile_id,
"last_checked_at": acct.last_checked_at.isoformat() if acct.last_checked_at else None,
"last_error": acct.last_error,
"created_at": acct.created_at.isoformat() if acct.created_at else None,
@@ -222,6 +237,7 @@ def create_imap_account(
use_ssl=body.use_ssl,
delete_after_process=body.delete_after_process,
is_active=body.is_active,
profile_id=body.profile_id,
)
try:
db.add(acct)
@@ -277,6 +293,10 @@ def update_imap_account(
acct.delete_after_process = body.delete_after_process
if body.is_active is not None:
acct.is_active = body.is_active
# profile_id: update whenever the field is explicitly present in the request payload
# (including sending null to clear the override).
if "profile_id" in body.model_fields_set:
acct.profile_id = body.profile_id
# Reset last_error so the next poll gives a fresh result
acct.last_error = None
+257
View File
@@ -0,0 +1,257 @@
"""API endpoints for managing IMAP ingestion profiles.
Ingestion profiles allow fine-grained control over which attachment types are
accepted when ingesting emails via IMAP. Each profile carries a list of enabled
file-type categories (e.g. ``["pdf", "office", "images"]``) drawn from the
canonical set defined in :mod:`app.utils.allowed_types`.
Built-in system profiles (``is_builtin=True``) are read-only and cannot be
deleted or modified. Users may create their own profiles which are private to
their ``owner_id``. System-level global profiles (``owner_id=None``) are visible
to all users but can only be created by administrators.
"""
import json
import logging
from datetime import datetime, timezone
from typing import Annotated, Any
from fastapi import APIRouter, Depends, HTTPException, Request, status
from pydantic import BaseModel, Field
from sqlalchemy.orm import Session
from app.database import get_db
from app.models import ImapIngestionProfile
from app.utils.allowed_types import FILE_TYPE_CATEGORIES
from app.utils.user_scope import get_current_owner_id
logger = logging.getLogger(__name__)
router = APIRouter(prefix="/imap-profiles", tags=["imap-profiles"])
DbSession = Annotated[Session, Depends(get_db)]
# ---------------------------------------------------------------------------
# Auth helpers
# ---------------------------------------------------------------------------
def _get_owner_id(request: Request) -> str:
"""Return the current user's owner ID, raising 401 if unauthenticated."""
owner_id = get_current_owner_id(request)
if owner_id is None:
raise HTTPException(status_code=status.HTTP_401_UNAUTHORIZED, detail="Not authenticated")
return owner_id
CurrentOwner = Annotated[str, Depends(_get_owner_id)]
# ---------------------------------------------------------------------------
# Pydantic schemas
# ---------------------------------------------------------------------------
_VALID_CATEGORIES = set(FILE_TYPE_CATEGORIES.keys())
class ImapProfileCreate(BaseModel):
"""Schema for creating a new ingestion profile."""
name: str = Field(..., min_length=1, max_length=255, description="Human-readable profile name")
description: str | None = Field(default=None, description="Optional description")
allowed_categories: list[str] = Field(
...,
min_length=1,
description=(f"List of enabled file-type category keys. Valid values: {sorted(_VALID_CATEGORIES)}"),
)
class ImapProfileUpdate(BaseModel):
"""Schema for updating an existing profile (all fields optional)."""
name: str | None = Field(default=None, min_length=1, max_length=255)
description: str | None = None
allowed_categories: list[str] | None = Field(default=None, min_length=1)
# ---------------------------------------------------------------------------
# Validation helpers
# ---------------------------------------------------------------------------
def _validate_categories(categories: list[str]) -> list[str]:
"""Raise 422 if any category key is unknown; return the cleaned list."""
unknown = [c for c in categories if c not in _VALID_CATEGORIES]
if unknown:
raise HTTPException(
status_code=status.HTTP_422_UNPROCESSABLE_ENTITY,
detail=f"Unknown category key(s): {unknown}. Valid keys: {sorted(_VALID_CATEGORIES)}",
)
# Deduplicate while preserving order
seen: set[str] = set()
result: list[str] = []
for cat in categories:
if cat not in seen:
seen.add(cat)
result.append(cat)
return result
# ---------------------------------------------------------------------------
# Serialisation
# ---------------------------------------------------------------------------
def _to_response(profile: ImapIngestionProfile) -> dict[str, Any]:
"""Serialize a profile row to a response dict."""
try:
categories = json.loads(profile.allowed_categories)
except (ValueError, TypeError):
categories = []
# Enrich categories with display metadata
categories_detail = [
{
"key": cat,
"label": FILE_TYPE_CATEGORIES[cat]["label"] if cat in FILE_TYPE_CATEGORIES else cat,
"description": FILE_TYPE_CATEGORIES[cat]["description"] if cat in FILE_TYPE_CATEGORIES else "",
}
for cat in categories
]
return {
"id": profile.id,
"name": profile.name,
"description": profile.description,
"owner_id": profile.owner_id,
"allowed_categories": categories,
"categories_detail": categories_detail,
"is_builtin": profile.is_builtin,
"created_at": profile.created_at.isoformat() if profile.created_at else None,
"updated_at": profile.updated_at.isoformat() if profile.updated_at else None,
}
# ---------------------------------------------------------------------------
# Endpoints
# ---------------------------------------------------------------------------
@router.get("/categories", summary="List available file-type categories")
def list_categories(request: Request, owner_id: CurrentOwner) -> list[dict[str, Any]]:
"""Return the full list of file-type categories that can be used in profiles."""
return [
{
"key": key,
"label": info["label"],
"description": info["description"],
}
for key, info in FILE_TYPE_CATEGORIES.items()
]
@router.get("/", summary="List ingestion profiles visible to the current user")
def list_profiles(request: Request, db: DbSession, owner_id: CurrentOwner) -> list[dict[str, Any]]:
"""Return all profiles: system-global (owner_id=NULL) and the user's own profiles."""
profiles = (
db.query(ImapIngestionProfile)
.filter(
# SQLAlchemy requires `== None` for IS NULL comparison in ORM filters
(ImapIngestionProfile.owner_id == None) | (ImapIngestionProfile.owner_id == owner_id) # noqa: E711
)
.order_by(ImapIngestionProfile.is_builtin.desc(), ImapIngestionProfile.id)
.all()
)
return [_to_response(p) for p in profiles]
@router.post("/", status_code=status.HTTP_201_CREATED, summary="Create a new ingestion profile")
def create_profile(request: Request, body: ImapProfileCreate, db: DbSession, owner_id: CurrentOwner) -> dict[str, Any]:
"""Create a new ingestion profile owned by the current user."""
categories = _validate_categories(body.allowed_categories)
profile = ImapIngestionProfile(
name=body.name,
description=body.description,
owner_id=owner_id,
allowed_categories=json.dumps(categories),
is_builtin=False,
)
try:
db.add(profile)
db.commit()
db.refresh(profile)
except Exception:
db.rollback()
raise
logger.info("User %s created IMAP ingestion profile %d ('%s')", owner_id, profile.id, body.name)
return _to_response(profile)
@router.get("/{profile_id}", summary="Get a single ingestion profile")
def get_profile(profile_id: int, request: Request, db: DbSession, owner_id: CurrentOwner) -> dict[str, Any]:
"""Return a single profile by ID. Only the owner or system profiles are accessible."""
profile = db.query(ImapIngestionProfile).filter(ImapIngestionProfile.id == profile_id).first()
if not profile or (profile.owner_id is not None and profile.owner_id != owner_id):
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Ingestion profile not found")
return _to_response(profile)
@router.put("/{profile_id}", summary="Update an ingestion profile")
def update_profile(
profile_id: int,
request: Request,
body: ImapProfileUpdate,
db: DbSession,
owner_id: CurrentOwner,
) -> dict[str, Any]:
"""Update an existing ingestion profile. Built-in profiles cannot be modified."""
profile = db.query(ImapIngestionProfile).filter(ImapIngestionProfile.id == profile_id).first()
if not profile or (profile.owner_id is not None and profile.owner_id != owner_id):
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Ingestion profile not found")
if profile.is_builtin:
raise HTTPException(
status_code=status.HTTP_403_FORBIDDEN,
detail="Built-in profiles cannot be modified.",
)
if body.name is not None:
profile.name = body.name
if "description" in body.model_fields_set:
profile.description = body.description
if body.allowed_categories is not None:
categories = _validate_categories(body.allowed_categories)
profile.allowed_categories = json.dumps(categories)
profile.updated_at = datetime.now(timezone.utc)
try:
db.commit()
db.refresh(profile)
except Exception:
db.rollback()
raise
logger.info("User %s updated IMAP ingestion profile %d", owner_id, profile_id)
return _to_response(profile)
@router.delete("/{profile_id}", status_code=status.HTTP_204_NO_CONTENT, summary="Delete an ingestion profile")
def delete_profile(profile_id: int, request: Request, db: DbSession, owner_id: CurrentOwner) -> None:
"""Delete an ingestion profile. Built-in profiles cannot be deleted."""
profile = db.query(ImapIngestionProfile).filter(ImapIngestionProfile.id == profile_id).first()
if not profile or (profile.owner_id is not None and profile.owner_id != owner_id):
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Ingestion profile not found")
if profile.is_builtin:
raise HTTPException(
status_code=status.HTTP_403_FORBIDDEN,
detail="Built-in profiles cannot be deleted.",
)
try:
db.delete(profile)
db.commit()
except Exception:
db.rollback()
raise
logger.info("User %s deleted IMAP ingestion profile %d", owner_id, profile_id)
+2
View File
@@ -26,6 +26,7 @@ from starlette.responses import RedirectResponse
from app.config import settings
from app.database import get_db
from app.models import LocalUser, UserProfile
from app.utils.i18n import translate as _translate
from app.utils.local_auth import (
build_session_user,
generate_token,
@@ -41,6 +42,7 @@ router = APIRouter(tags=["local-auth"])
_templates_dir = pathlib.Path(__file__).parents[2] / "frontend" / "templates"
templates = Jinja2Templates(directory=str(_templates_dir))
templates.env.globals["_"] = lambda key, **kwargs: _translate(key, "en", **kwargs)
DbSession = Annotated[Session, Depends(get_db)]
+347
View File
@@ -0,0 +1,347 @@
"""Mobile app API endpoints.
Provides endpoints specifically designed for the DocuElevate native mobile
app (iOS / Android via React Native / Expo):
* ``POST /mobile/generate-token`` exchange an active session for a
long-lived API token that the mobile app stores securely. The token is
auto-named "Mobile App <device_name>" and is identical to regular API
tokens (Bearer auth works everywhere).
* ``POST /mobile/register-device`` register a push-notification device
token (Expo push token) so the user receives push notifications when
documents finish processing.
* ``GET /mobile/devices`` list registered devices for the current user.
* ``DELETE /mobile/devices/{device_id}`` deactivate a device.
* ``GET /mobile/whoami`` lightweight profile endpoint for the mobile app
to verify authentication state.
"""
import logging
from datetime import datetime, timezone
from typing import Annotated, Any
from fastapi import APIRouter, Depends, HTTPException, Request, status
from pydantic import BaseModel, Field
from sqlalchemy.orm import Session
from app.api.api_tokens import generate_api_token, hash_token
from app.auth import require_login
from app.database import get_db
from app.models import ApiToken, MobileDevice
from app.utils.user_scope import get_current_owner_id
logger = logging.getLogger(__name__)
router = APIRouter(prefix="/mobile", tags=["mobile"])
DbSession = Annotated[Session, Depends(get_db)]
# ---------------------------------------------------------------------------
# Auth helper
# ---------------------------------------------------------------------------
def _get_owner_id(request: Request) -> str:
"""Return the current user's owner ID, raising 401 if unauthenticated."""
owner_id = get_current_owner_id(request)
if not owner_id:
raise HTTPException(status_code=status.HTTP_401_UNAUTHORIZED, detail="Not authenticated")
return owner_id
CurrentOwner = Annotated[str, Depends(_get_owner_id)]
# ---------------------------------------------------------------------------
# Request / Response schemas
# ---------------------------------------------------------------------------
class GenerateTokenRequest(BaseModel):
"""Request body for auto-generating a mobile app token."""
device_name: str = Field(
default="Mobile App",
min_length=1,
max_length=120,
description="Human-readable device name used to label the token.",
)
class GenerateTokenResponse(BaseModel):
"""Response containing the one-time-visible API token."""
token: str
token_id: int
name: str
created_at: datetime
class RegisterDeviceRequest(BaseModel):
"""Request body for registering a push-notification device token."""
push_token: str = Field(
min_length=1,
max_length=512,
description="Expo push token (ExponentPushToken[…]) obtained from the mobile app.",
)
device_name: str | None = Field(
default=None,
max_length=255,
description="Optional human-readable device name (e.g. 'John's iPhone').",
)
platform: str = Field(
default="ios",
description="Device platform: 'ios', 'android', or 'web'.",
)
class DeviceResponse(BaseModel):
"""Serialised MobileDevice record."""
id: int
device_name: str | None
platform: str
push_token_preview: str
is_active: bool
created_at: datetime
last_seen_at: datetime | None
class WhoAmIResponse(BaseModel):
"""Lightweight profile response for the mobile app."""
owner_id: str
display_name: str | None
email: str | None
avatar_url: str | None
is_admin: bool
# ---------------------------------------------------------------------------
# Helpers
# ---------------------------------------------------------------------------
def _device_to_response(device: MobileDevice) -> dict[str, Any]:
"""Convert a MobileDevice ORM object to a serialisable dict."""
# Show only first 20 chars of the push token for security.
token_preview = device.push_token[:20] + "" if len(device.push_token) > 20 else device.push_token
return {
"id": device.id,
"device_name": device.device_name,
"platform": device.platform,
"push_token_preview": token_preview,
"is_active": device.is_active,
"created_at": device.created_at,
"last_seen_at": device.last_seen_at,
}
# ---------------------------------------------------------------------------
# Endpoints
# ---------------------------------------------------------------------------
@router.post("/generate-token", status_code=status.HTTP_201_CREATED, response_model=GenerateTokenResponse)
@require_login
async def generate_mobile_token(
request: Request,
body: GenerateTokenRequest,
owner_id: CurrentOwner,
db: DbSession,
) -> dict[str, Any]:
"""Generate a long-lived API token for the mobile app.
The mobile app calls this endpoint immediately after SSO login to obtain
a Bearer token it can store in the secure keychain. The returned token
is functionally identical to manually-created API tokens and works with
every authenticated endpoint.
The token is shown **exactly once** in the response; subsequent requests
show only the prefix for identification.
"""
token_name = f"Mobile App {body.device_name}"
plaintext = generate_api_token()
token_hash_value = hash_token(plaintext)
prefix = plaintext[:12]
db_token = ApiToken(
owner_id=owner_id,
name=token_name,
token_hash=token_hash_value,
token_prefix=prefix,
)
try:
db.add(db_token)
db.commit()
db.refresh(db_token)
except Exception:
db.rollback()
logger.exception("Failed to create mobile API token for owner_id=%s", owner_id)
raise
logger.info("Mobile API token created: id=%s owner=%s device=%r", db_token.id, owner_id, body.device_name)
return {
"token": plaintext,
"token_id": db_token.id,
"name": token_name,
"created_at": db_token.created_at,
}
@router.post("/register-device", status_code=status.HTTP_201_CREATED, response_model=DeviceResponse)
@require_login
async def register_device(
request: Request,
body: RegisterDeviceRequest,
owner_id: CurrentOwner,
db: DbSession,
) -> dict[str, Any]:
"""Register or refresh a push-notification device token.
If the same ``push_token`` is already registered for this user the
record is reactivated and ``last_seen_at`` is updated rather than
creating a duplicate.
"""
platform = body.platform.lower()
if platform not in {"ios", "android", "web"}:
raise HTTPException(
status_code=status.HTTP_422_UNPROCESSABLE_ENTITY,
detail="platform must be one of: ios, android, web",
)
now = datetime.now(timezone.utc)
# Upsert: reuse existing record if the token is already known.
existing = (
db.query(MobileDevice)
.filter(MobileDevice.owner_id == owner_id, MobileDevice.push_token == body.push_token)
.first()
)
if existing:
existing.is_active = True
existing.last_seen_at = now
if body.device_name:
existing.device_name = body.device_name
try:
db.commit()
db.refresh(existing)
except Exception:
db.rollback()
raise
logger.info("Mobile device refreshed: id=%s owner=%s", existing.id, owner_id)
return _device_to_response(existing)
device = MobileDevice(
owner_id=owner_id,
device_name=body.device_name,
platform=platform,
push_token=body.push_token,
is_active=True,
last_seen_at=now,
)
try:
db.add(device)
db.commit()
db.refresh(device)
except Exception:
db.rollback()
logger.exception("Failed to register mobile device for owner_id=%s", owner_id)
raise
logger.info("Mobile device registered: id=%s owner=%s platform=%s", device.id, owner_id, platform)
return _device_to_response(device)
@router.get("/devices", response_model=list[DeviceResponse])
@require_login
async def list_devices(
request: Request,
owner_id: CurrentOwner,
db: DbSession,
) -> list[dict[str, Any]]:
"""List all registered push-notification devices for the current user."""
devices = (
db.query(MobileDevice).filter(MobileDevice.owner_id == owner_id).order_by(MobileDevice.created_at.desc()).all()
)
return [_device_to_response(d) for d in devices]
@router.delete("/devices/{device_id}", status_code=status.HTTP_204_NO_CONTENT)
@require_login
async def deactivate_device(
request: Request,
device_id: int,
owner_id: CurrentOwner,
db: DbSession,
) -> None:
"""Deactivate a push-notification device registration.
The device record is kept for audit purposes but will no longer receive
push notifications.
"""
device = db.get(MobileDevice, device_id)
if not device or device.owner_id != owner_id:
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Device not found")
device.is_active = False
try:
db.commit()
except Exception:
db.rollback()
raise
logger.info("Mobile device deactivated: id=%s owner=%s", device_id, owner_id)
@router.get("/whoami", response_model=WhoAmIResponse)
@require_login
async def whoami(
request: Request,
owner_id: CurrentOwner,
db: DbSession,
) -> dict[str, Any]:
"""Return basic profile information for the authenticated user.
The mobile app calls this after token exchange to populate the user
profile screen and verify that the stored token is still valid.
"""
from app.auth import get_gravatar_url
from app.models import LocalUser, UserProfile
profile = db.query(UserProfile).filter(UserProfile.user_id == owner_id).first()
local_user = db.query(LocalUser).filter(LocalUser.email == owner_id).first()
display_name: str | None = None
email: str | None = None
avatar_url: str | None = None
is_admin = False
if profile:
display_name = profile.display_name
if local_user:
email = local_user.email
is_admin = bool(local_user.is_admin)
if not display_name and local_user.display_name:
display_name = local_user.display_name
elif "@" in owner_id:
# SSO users commonly have their email as owner_id
email = owner_id
if email:
avatar_url = get_gravatar_url(email)
return {
"owner_id": owner_id,
"display_name": display_name,
"email": email,
"avatar_url": avatar_url,
"is_admin": is_admin,
}
+320
View File
@@ -0,0 +1,320 @@
"""User self-service profile API.
Provides endpoints for the authenticated user to view and update their own
profile settings without requiring admin access.
Routes:
GET /api/profile — read current user's profile
PATCH /api/profile — update display name, language, theme
POST /api/profile/avatar — upload a new profile picture (JPEG/PNG/GIF/WebP, max 2 MB)
DELETE /api/profile/avatar — remove custom avatar (reverts to Gravatar)
POST /api/profile/change-password — change password (local-auth users only)
"""
from __future__ import annotations
import base64
import logging
from hashlib import md5
from typing import Annotated
from fastapi import APIRouter, Depends, File, HTTPException, Request, UploadFile, status
from pydantic import BaseModel, Field
from sqlalchemy.orm import Session
from app.auth import require_login
from app.database import get_db
from app.models import LocalUser, UserProfile
from app.utils.i18n import SUPPORTED_LANGUAGE_CODES
logger = logging.getLogger(__name__)
router = APIRouter(prefix="/profile", tags=["profile"])
DbSession = Annotated[Session, Depends(get_db)]
# Maximum avatar upload size: 2 MB
_MAX_AVATAR_BYTES = 2 * 1024 * 1024
# Allowed MIME types for avatar uploads
_ALLOWED_AVATAR_TYPES = {"image/jpeg", "image/png", "image/gif", "image/webp"}
# Valid theme values
_VALID_THEMES = {"light", "dark", "system"}
# ---------------------------------------------------------------------------
# Helpers
# ---------------------------------------------------------------------------
def _get_user_id(request: Request) -> str:
"""Return the stable user identifier from the session.
Raises HTTP 401 if no user is logged in.
"""
user = request.session.get("user")
if not user or not isinstance(user, dict):
raise HTTPException(status_code=status.HTTP_401_UNAUTHORIZED, detail="Not authenticated")
uid = user.get("sub") or user.get("preferred_username") or user.get("email") or user.get("id")
if not uid:
raise HTTPException(status_code=status.HTTP_401_UNAUTHORIZED, detail="Cannot determine user identity")
return uid
def _gravatar_url(email: str | None) -> str:
"""Generate a Gravatar URL for *email*, falling back to identicon."""
if not email:
return "https://www.gravatar.com/avatar/?d=identicon"
# MD5 used for Gravatar URL generation only — not for security
h = md5(email.strip().lower().encode(), usedforsecurity=False).hexdigest()
return f"https://www.gravatar.com/avatar/{h}?d=identicon"
def _get_or_create_profile(db: Session, user_id: str) -> UserProfile:
"""Return the UserProfile for *user_id*, creating a stub if one doesn't exist."""
profile = db.query(UserProfile).filter(UserProfile.user_id == user_id).first()
if profile is None:
profile = UserProfile(user_id=user_id)
db.add(profile)
try:
db.commit()
db.refresh(profile)
except Exception:
db.rollback()
raise
return profile
# ---------------------------------------------------------------------------
# Pydantic schemas
# ---------------------------------------------------------------------------
class ProfileResponse(BaseModel):
"""Response body for GET /api/profile."""
user_id: str
display_name: str | None
contact_email: str | None
preferred_language: str | None
preferred_theme: str | None
avatar_url: str
"""Gravatar URL or ``data:`` URI for a custom uploaded avatar."""
is_local_user: bool
"""True when the account was created via local email/password sign-up."""
class ProfileUpdateRequest(BaseModel):
"""Request body for PATCH /api/profile."""
display_name: str | None = Field(default=None, max_length=255, description="Human-readable display name")
contact_email: str | None = Field(default=None, max_length=255, description="Contact / notification e-mail")
preferred_language: str | None = Field(default=None, description="ISO 639-1 language code, e.g. 'en', 'de'")
preferred_theme: str | None = Field(default=None, description="Colour scheme: 'light', 'dark', or 'system'")
class ChangePasswordRequest(BaseModel):
"""Request body for POST /api/profile/change-password."""
current_password: str = Field(..., min_length=1, max_length=128)
new_password: str = Field(..., min_length=8, max_length=128)
new_password_confirm: str = Field(..., min_length=8, max_length=128)
# ---------------------------------------------------------------------------
# Endpoints
# ---------------------------------------------------------------------------
@router.get("", response_model=ProfileResponse)
@require_login
async def get_profile(request: Request, db: DbSession) -> ProfileResponse:
"""Return the current user's profile settings."""
user_id = _get_user_id(request)
profile = _get_or_create_profile(db, user_id)
session_user = request.session.get("user", {})
email = session_user.get("email") if isinstance(session_user, dict) else None
# Determine avatar: prefer stored data, fall back to Gravatar
avatar_url = profile.avatar_data if profile.avatar_data else _gravatar_url(email) # type: ignore[attr-defined]
# Check whether this is a local (email/password) account
is_local = db.query(LocalUser).filter(LocalUser.username == user_id).first() is not None
return ProfileResponse(
user_id=user_id,
display_name=profile.display_name, # type: ignore[arg-type]
contact_email=profile.contact_email, # type: ignore[arg-type]
preferred_language=profile.preferred_language, # type: ignore[arg-type]
preferred_theme=profile.preferred_theme, # type: ignore[arg-type]
avatar_url=avatar_url,
is_local_user=is_local,
)
@router.patch("", response_model=ProfileResponse)
@require_login
async def update_profile(body: ProfileUpdateRequest, request: Request, db: DbSession) -> ProfileResponse:
"""Update the current user's editable profile settings."""
user_id = _get_user_id(request)
profile = _get_or_create_profile(db, user_id)
# Validate language code
if body.preferred_language is not None:
lang = body.preferred_language.lower().strip()
if lang and lang not in SUPPORTED_LANGUAGE_CODES:
raise HTTPException(
status_code=status.HTTP_422_UNPROCESSABLE_ENTITY,
detail=f"Unsupported language code: {lang}",
)
profile.preferred_language = lang or None # type: ignore[assignment]
# Validate theme
if body.preferred_theme is not None:
theme = body.preferred_theme.lower().strip()
if theme and theme not in _VALID_THEMES:
raise HTTPException(
status_code=status.HTTP_422_UNPROCESSABLE_ENTITY,
detail=f"Invalid theme: {theme}. Must be one of: {', '.join(sorted(_VALID_THEMES))}",
)
profile.preferred_theme = theme or None # type: ignore[assignment]
if body.display_name is not None:
profile.display_name = body.display_name.strip() or None # type: ignore[assignment]
if body.contact_email is not None:
profile.contact_email = body.contact_email.strip() or None # type: ignore[assignment]
try:
db.commit()
db.refresh(profile)
except Exception:
db.rollback()
raise
session_user = request.session.get("user", {})
email = session_user.get("email") if isinstance(session_user, dict) else None
avatar_url = profile.avatar_data if profile.avatar_data else _gravatar_url(email) # type: ignore[attr-defined]
is_local = db.query(LocalUser).filter(LocalUser.username == user_id).first() is not None
return ProfileResponse(
user_id=user_id,
display_name=profile.display_name, # type: ignore[arg-type]
contact_email=profile.contact_email, # type: ignore[arg-type]
preferred_language=profile.preferred_language, # type: ignore[arg-type]
preferred_theme=profile.preferred_theme, # type: ignore[arg-type]
avatar_url=avatar_url,
is_local_user=is_local,
)
@router.post("/avatar", status_code=status.HTTP_200_OK)
@require_login
async def upload_avatar(
request: Request,
db: DbSession,
file: UploadFile = File(..., description="Profile picture (JPEG, PNG, GIF or WebP; max 2 MB)"),
) -> dict:
"""Upload a new profile picture.
The image is stored as a base64-encoded data URL in ``UserProfile.avatar_data``.
Accepts JPEG, PNG, GIF, or WebP files up to 2 MB.
"""
user_id = _get_user_id(request)
content_type = (file.content_type or "").lower()
if content_type not in _ALLOWED_AVATAR_TYPES:
raise HTTPException(
status_code=status.HTTP_415_UNSUPPORTED_MEDIA_TYPE,
detail=f"Unsupported image type '{content_type}'. Allowed: JPEG, PNG, GIF, WebP.",
)
# Check declared size first (available when the client sends a Content-Length header)
if file.size is not None and file.size > _MAX_AVATAR_BYTES:
raise HTTPException(
status_code=status.HTTP_413_REQUEST_ENTITY_TOO_LARGE,
detail="Avatar image must be 2 MB or smaller.",
)
# Read up to one byte past the limit so we can detect oversized uploads
raw = await file.read(_MAX_AVATAR_BYTES + 1)
if len(raw) > _MAX_AVATAR_BYTES:
raise HTTPException(
status_code=status.HTTP_413_REQUEST_ENTITY_TOO_LARGE,
detail="Avatar image must be 2 MB or smaller.",
)
b64 = base64.b64encode(raw).decode("ascii")
data_url = f"data:{content_type};base64,{b64}"
profile = _get_or_create_profile(db, user_id)
profile.avatar_data = data_url # type: ignore[assignment]
try:
db.commit()
except Exception:
db.rollback()
raise
return {"avatar_url": data_url}
@router.delete("/avatar", status_code=status.HTTP_200_OK)
@require_login
async def delete_avatar(request: Request, db: DbSession) -> dict:
"""Remove the custom avatar and revert to the Gravatar fallback."""
user_id = _get_user_id(request)
profile = _get_or_create_profile(db, user_id)
profile.avatar_data = None # type: ignore[assignment]
try:
db.commit()
except Exception:
db.rollback()
raise
session_user = request.session.get("user", {})
email = session_user.get("email") if isinstance(session_user, dict) else None
return {"avatar_url": _gravatar_url(email)}
@router.post("/change-password", status_code=status.HTTP_200_OK)
@require_login
async def change_password(body: ChangePasswordRequest, request: Request, db: DbSession) -> dict:
"""Change the password for local (email/password) accounts.
Raises 403 if the account is not a local account or the current password is wrong.
Raises 422 if the new passwords do not match.
"""
from app.utils.local_auth import hash_password, verify_password
user_id = _get_user_id(request)
local_user = db.query(LocalUser).filter(LocalUser.username == user_id).first()
if local_user is None:
raise HTTPException(
status_code=status.HTTP_403_FORBIDDEN,
detail="Password change is only available for local accounts.",
)
if not verify_password(body.current_password, local_user.hashed_password):
raise HTTPException(
status_code=status.HTTP_403_FORBIDDEN,
detail="Current password is incorrect.",
)
if body.new_password != body.new_password_confirm:
raise HTTPException(
status_code=status.HTTP_422_UNPROCESSABLE_ENTITY,
detail="New passwords do not match.",
)
local_user.hashed_password = hash_password(body.new_password)
try:
db.commit()
except Exception:
db.rollback()
raise
logger.info("Password changed for local user: %s", user_id)
return {"detail": "Password changed successfully."}
+20 -7
View File
@@ -12,7 +12,7 @@ from sqlalchemy.orm import Session
from app.auth import require_login
from app.database import get_db
from app.models import FileRecord
from app.models import FileRecord, UserProfile
# Set up logging
logger = logging.getLogger(__name__)
@@ -22,7 +22,7 @@ router = APIRouter()
DbSession = Annotated[Session, Depends(get_db)]
async def whoami_handler(request: Request):
async def whoami_handler(request: Request, db: Session):
"""
Returns user info if logged in, else 401.
"""
@@ -41,20 +41,33 @@ async def whoami_handler(request: Request):
# Add the gravatar URL to the user object instead of creating a new response
user_response = user.copy() # Create a copy to avoid modifying the session
user_response["picture"] = gravatar_url
# Check if the user has a custom avatar stored in their profile
user_id = user.get("sub") or user.get("preferred_username") or user.get("email") or user.get("id")
if user_id:
try:
profile = db.query(UserProfile).filter(UserProfile.user_id == user_id).first()
if profile and profile.avatar_data:
user_response["picture"] = profile.avatar_data
else:
user_response["picture"] = gravatar_url
except Exception:
user_response["picture"] = gravatar_url
else:
user_response["picture"] = gravatar_url
return user_response
# Register the same handler under two different paths
@router.get("/whoami")
async def whoami(request: Request):
return await whoami_handler(request)
async def whoami(request: Request, db: DbSession):
return await whoami_handler(request, db)
@router.get("/auth/whoami")
async def auth_whoami(request: Request):
return await whoami_handler(request)
async def auth_whoami(request: Request, db: DbSession):
return await whoami_handler(request, db)
@router.get("/users/search")
+282 -1
View File
@@ -15,12 +15,14 @@ from starlette.responses import RedirectResponse
from app.config import settings
from app.database import get_db
from app.middleware.audit_log import get_client_ip
# Conditional imports: only used when multi_user_enabled=True. Imported here at
# module level (not inside auth()) so they don't incur repeated import overhead.
# Guards at call-sites ensure they are never *called* in single-user mode.
from app.models import LocalUser as _LocalUser
from app.models import UserProfile as _UserProfile
from app.utils.i18n import translate as _translate
from app.utils.local_auth import build_session_user as _build_session_user
from app.utils.local_auth import verify_password as _verify_password
@@ -33,11 +35,15 @@ AUTH_ENABLED = settings.auth_enabled
# Set up templates for authentication
templates_dir = pathlib.Path(__file__).parents[1] / "frontend" / "templates"
templates = Jinja2Templates(directory=str(templates_dir))
templates.env.globals["_"] = lambda key, **kwargs: _translate(key, "en", **kwargs)
# Configure OAuth provider if credentials are provided
OAUTH_CONFIGURED = False
OAUTH_PROVIDER_NAME = "Single Sign-On"
# Social login providers that are enabled and registered
SOCIAL_PROVIDERS: dict[str, dict[str, str]] = {}
if AUTH_ENABLED and settings.authentik_client_id and settings.authentik_client_secret:
oauth.register(
name="authentik",
@@ -49,6 +55,68 @@ if AUTH_ENABLED and settings.authentik_client_id and settings.authentik_client_s
OAUTH_CONFIGURED = True
OAUTH_PROVIDER_NAME = settings.oauth_provider_name or "Authentik SSO"
# --- Social Login Providers ---------------------------------------------------
if AUTH_ENABLED and settings.social_auth_google_enabled:
if settings.social_auth_google_client_id and settings.social_auth_google_client_secret:
oauth.register(
name="google",
client_id=settings.social_auth_google_client_id,
client_secret=settings.social_auth_google_client_secret,
server_metadata_url="https://accounts.google.com/.well-known/openid-configuration",
client_kwargs={"scope": "openid profile email"},
)
SOCIAL_PROVIDERS["google"] = {"name": "Google", "icon": "fab fa-google", "color": "red"}
logger.info("Social login provider registered: Google")
else:
logger.warning("SOCIAL_AUTH_GOOGLE_ENABLED=true but client ID/secret not configured")
if AUTH_ENABLED and settings.social_auth_microsoft_enabled:
if settings.social_auth_microsoft_client_id and settings.social_auth_microsoft_client_secret:
tenant = settings.social_auth_microsoft_tenant or "common"
oauth.register(
name="microsoft",
client_id=settings.social_auth_microsoft_client_id,
client_secret=settings.social_auth_microsoft_client_secret,
server_metadata_url=f"https://login.microsoftonline.com/{tenant}/v2.0/.well-known/openid-configuration",
client_kwargs={"scope": "openid profile email"},
)
SOCIAL_PROVIDERS["microsoft"] = {"name": "Microsoft", "icon": "fab fa-microsoft", "color": "blue"}
logger.info("Social login provider registered: Microsoft (tenant=%s)", tenant)
else:
logger.warning("SOCIAL_AUTH_MICROSOFT_ENABLED=true but client ID/secret not configured")
if AUTH_ENABLED and settings.social_auth_apple_enabled:
if settings.social_auth_apple_client_id and settings.social_auth_apple_team_id:
oauth.register(
name="apple",
client_id=settings.social_auth_apple_client_id,
server_metadata_url="https://appleid.apple.com/.well-known/openid-configuration",
client_kwargs={
"scope": "openid name email",
"response_mode": "form_post",
},
)
SOCIAL_PROVIDERS["apple"] = {"name": "Apple", "icon": "fab fa-apple", "color": "gray"}
logger.info("Social login provider registered: Apple")
else:
logger.warning("SOCIAL_AUTH_APPLE_ENABLED=true but client ID/team ID not configured")
if AUTH_ENABLED and settings.social_auth_dropbox_enabled:
if settings.social_auth_dropbox_client_id and settings.social_auth_dropbox_client_secret:
oauth.register(
name="dropbox",
client_id=settings.social_auth_dropbox_client_id,
client_secret=settings.social_auth_dropbox_client_secret,
authorize_url="https://www.dropbox.com/oauth2/authorize",
access_token_url="https://api.dropboxapi.com/oauth2/token",
userinfo_endpoint="https://api.dropboxapi.com/2/users/get_current_account",
client_kwargs={"token_endpoint_auth_method": "client_secret_post"},
)
SOCIAL_PROVIDERS["dropbox"] = {"name": "Dropbox", "icon": "fab fa-dropbox", "color": "blue"}
logger.info("Social login provider registered: Dropbox")
else:
logger.warning("SOCIAL_AUTH_DROPBOX_ENABLED=true but client ID/secret not configured")
router = APIRouter()
@@ -194,6 +262,7 @@ async def login(request: Request):
"message": request.query_params.get("message"),
"show_oauth": OAUTH_CONFIGURED,
"oauth_provider_name": OAUTH_PROVIDER_NAME,
"social_providers": SOCIAL_PROVIDERS,
"app_version": settings.version,
"csrf_token": getattr(request.state, "csrf_token", ""),
# "Create account" link is only shown when multi-user mode AND local signup are both enabled
@@ -211,6 +280,149 @@ async def oauth_login(request: Request):
return await oauth.authentik.authorize_redirect(request, redirect_uri)
async def social_login(request: Request, provider: str):
"""Initiate a social login flow for the given provider.
Args:
request: The current FastAPI request.
provider: One of the registered social provider keys (google, microsoft, apple, dropbox).
Returns:
A redirect to the provider's authorization page, or back to /login on error.
"""
if provider not in SOCIAL_PROVIDERS:
return RedirectResponse(url="/login?error=Unknown+social+provider", status_code=status.HTTP_302_FOUND)
redirect_uri = request.url_for("social_callback", provider=provider)
oauth_client = getattr(oauth, provider, None)
if oauth_client is None:
return RedirectResponse(url="/login?error=Provider+not+configured", status_code=status.HTTP_302_FOUND)
return await oauth_client.authorize_redirect(request, redirect_uri)
def _normalize_social_userinfo(provider: str, token: dict, raw_userinfo: dict | None) -> dict:
"""Normalize the userinfo payload from different social providers into a common format.
Returns a dict with keys: sub, email, name, preferred_username, picture.
Args:
provider: The social provider key (google, microsoft, apple, dropbox).
token: The OAuth token response from the provider. Included for future
provider-specific claim extraction (e.g. ``id_token`` claims).
raw_userinfo: The raw userinfo dict (may be None for providers without standard OIDC userinfo).
Returns:
A normalized user-data dict compatible with the session user format.
"""
userinfo: dict = raw_userinfo or {}
if provider == "dropbox":
# Dropbox returns a non-standard userinfo response
email = userinfo.get("email", "")
name_info = userinfo.get("name", {})
display_name = name_info.get("display_name", "") if isinstance(name_info, dict) else str(name_info)
return {
"sub": userinfo.get("account_id", email),
"email": email,
"name": display_name,
"preferred_username": email,
"picture": userinfo.get("profile_photo_url", ""),
}
# Standard OIDC providers (Google, Microsoft, Apple)
return {
"sub": userinfo.get("sub", ""),
"email": userinfo.get("email", ""),
"name": userinfo.get("name", ""),
"preferred_username": userinfo.get("email", ""),
"picture": userinfo.get("picture", ""),
}
async def social_callback(request: Request, provider: str, db: Session = Depends(get_db)):
"""Handle the OAuth callback from a social login provider.
After the user authorizes with the social provider, this endpoint exchanges
the authorization code for tokens, extracts user information, creates or
updates the user profile, and establishes a session.
Args:
request: The current FastAPI request.
provider: One of the registered social provider keys.
db: Database session (injected).
Returns:
A redirect to the user's original destination or the upload page.
"""
if provider not in SOCIAL_PROVIDERS:
return RedirectResponse(url="/login?error=Unknown+social+provider", status_code=status.HTTP_302_FOUND)
oauth_client = getattr(oauth, provider, None)
if oauth_client is None:
return RedirectResponse(url="/login?error=Provider+not+configured", status_code=status.HTTP_302_FOUND)
try:
token = await oauth_client.authorize_access_token(request)
# Try standard OIDC userinfo first, fall back to token-embedded userinfo
raw_userinfo = token.get("userinfo")
if not raw_userinfo:
try:
resp = await oauth_client.userinfo(token=token)
raw_userinfo = resp if isinstance(resp, dict) else resp.json() if hasattr(resp, "json") else {}
except Exception:
raw_userinfo = {}
user_data = _normalize_social_userinfo(provider, token, raw_userinfo)
if not user_data.get("email"):
return RedirectResponse(
url="/login?error=Could+not+retrieve+email+from+provider",
status_code=status.HTTP_302_FOUND,
)
# Add Gravatar if no picture provided
if not user_data.get("picture") and user_data.get("email"):
user_data["picture"] = get_gravatar_url(user_data["email"])
# Tag the login source for audit/debugging
user_data["auth_provider"] = provider
# Social login users are never admin by default (admin must be granted
# via the Authentik/OIDC admin group or manually in the admin panel)
user_data["is_admin"] = False
request.session["user"] = user_data
# Auto-create or update UserProfile
_ensure_user_profile(db, user_data, is_admin=False)
provider_name = SOCIAL_PROVIDERS[provider]["name"]
logger.info(
"[SECURITY] SOCIAL_LOGIN_SUCCESS provider=%s user=%s", provider_name, user_data.get("email", "unknown")
)
# Redirect first-time users to onboarding
user_id = (
user_data.get("sub") or user_data.get("preferred_username") or user_data.get("email") or user_data.get("id")
)
if user_id:
profile = db.query(_UserProfile).filter(_UserProfile.user_id == user_id).first()
if profile and not profile.onboarding_completed:
post_onboarding = request.session.pop("redirect_after_login", "/upload")
request.session["post_onboarding_redirect"] = post_onboarding
return RedirectResponse(url="/onboarding", status_code=status.HTTP_302_FOUND)
redirect_url = request.session.pop("redirect_after_login", "/upload")
return RedirectResponse(url=redirect_url, status_code=status.HTTP_302_FOUND)
except Exception as e:
logger.warning("[SECURITY] SOCIAL_LOGIN_FAILURE provider=%s error=%s", provider, type(e).__name__)
return RedirectResponse(
url="/login?error=Social+login+failed.+Please+try+again.", status_code=status.HTTP_302_FOUND
)
def _ensure_user_profile(db: Session, user_data: dict, is_admin: bool = False) -> None:
"""Create or update a UserProfile row for *user_data*.
@@ -344,6 +556,13 @@ async def oauth_callback(request: Request, db: Session = Depends(get_db)):
# Log the successful authentication
logger.info("[SECURITY] OAUTH_LOGIN_SUCCESS user=%s admin=%s", user_data.get("email", "unknown"), is_admin)
_record_login_event(
db,
request,
user_data.get("email") or user_data.get("preferred_username") or "unknown",
success=True,
method="oauth",
)
# Redirect first-time users to onboarding
user_id = (
@@ -364,6 +583,48 @@ async def oauth_callback(request: Request, db: Session = Depends(get_db)):
return RedirectResponse(url=f"/login?error=Authentication+failed:+{str(e)}", status_code=status.HTTP_302_FOUND)
def _record_login_event(
db: Session,
request: Request,
username: str,
*,
success: bool,
method: str = "local",
detail: str | None = None,
) -> None:
"""Write a login or login-failure audit event to the database.
Failures are silently swallowed so that an audit-service error never
prevents a legitimate login or surfaces an unrelated 500 error to the user.
Args:
db: Active database session.
request: The current HTTP request (used to extract the client IP).
username: The username that attempted authentication.
success: ``True`` for a successful login, ``False`` for a failure.
method: Authentication method, e.g. ``"local"`` or ``"oauth"``.
detail: Optional extra context for failures (e.g. ``"wrong_password"``).
"""
try:
from app.utils.audit_service import record_event
action = "login" if success else "login.failure"
details: dict = {"method": method}
if detail:
details["reason"] = detail
record_event(
db,
action=action,
user=username,
resource_type="session",
ip_address=get_client_ip(request),
details=details,
severity="info" if success else "warning",
)
except Exception:
logger.debug("Failed to write login audit event for user=%s", username, exc_info=True)
async def auth(request: Request, db: Session = Depends(get_db)):
"""Handle local username/password authentication.
@@ -413,6 +674,7 @@ async def auth(request: Request, db: Session = Depends(get_db)):
username,
local_user.is_active,
)
_record_login_event(db, request, username, success=False, detail="account_not_verified")
return RedirectResponse(
url="/login?error=Please+verify+your+email+address+before+logging+in",
status_code=302,
@@ -425,10 +687,12 @@ async def auth(request: Request, db: Session = Depends(get_db)):
)
if not pw_ok:
logger.warning("[SECURITY] LOCAL_LOGIN_FAILURE reason=wrong_password user=%s", username)
_record_login_event(db, request, username, success=False, detail="wrong_password")
return RedirectResponse(url="/login?error=Invalid+username+or+password", status_code=302)
user_data = _build_session_user(local_user)
request.session["user"] = user_data
logger.info("[SECURITY] LOCAL_LOGIN_SUCCESS user=%s", local_user.email)
_record_login_event(db, request, local_user.email, success=True)
_ensure_user_profile(db, user_data, is_admin=bool(local_user.is_admin))
profile = db.query(_UserProfile).filter(_UserProfile.user_id == local_user.email).first()
if profile and not profile.onboarding_completed:
@@ -473,6 +737,7 @@ async def auth(request: Request, db: Session = Depends(get_db)):
}
request.session["user"] = admin_user_data
logger.info("[SECURITY] LOCAL_LOGIN_SUCCESS user=%s", username)
_record_login_event(db, request, username, success=True)
_ensure_user_profile(db, admin_user_data, is_admin=True)
redirect_url = request.session.pop("redirect_after_login", "/upload")
return RedirectResponse(url=redirect_url, status_code=302)
@@ -485,16 +750,30 @@ async def auth(request: Request, db: Session = Depends(get_db)):
admin_configured,
not username and not password,
)
_record_login_event(db, request, username or "anonymous", success=False, detail="invalid_credentials")
return RedirectResponse(url="/login?error=Invalid+username+or+password", status_code=302)
async def logout(request: Request):
async def logout(request: Request, db: Session = Depends(get_db)):
"""Handle user logout"""
user = request.session.get("user")
username = "unknown"
if isinstance(user, dict):
username = user.get("preferred_username") or user.get("email") or "unknown"
logger.info(f"[SECURITY] LOGOUT user={username}")
try:
from app.utils.audit_service import record_event
record_event(
db,
action="logout",
user=username,
resource_type="session",
ip_address=get_client_ip(request),
severity="info",
)
except Exception:
logger.debug("Failed to write logout audit event for user=%s", username, exc_info=True)
request.session.pop("user", None)
return RedirectResponse(url="/login?message=You+have+been+logged+out+successfully", status_code=302)
@@ -503,6 +782,8 @@ if AUTH_ENABLED:
router.add_api_route("/login", login, methods=["GET"])
router.add_api_route("/oauth-login", oauth_login, methods=["GET"])
router.add_api_route("/oauth-callback", oauth_callback, methods=["GET"])
router.add_api_route("/social-login/{provider}", social_login, methods=["GET"])
router.add_api_route("/social-callback/{provider}", social_callback, methods=["GET"])
router.add_api_route("/auth", auth, methods=["POST"])
router.add_api_route("/logout", logout, methods=["GET"])
+1
View File
@@ -45,6 +45,7 @@ from app.tasks.upload_to_dropbox import upload_to_dropbox # noqa: F401
from app.tasks.upload_to_email import upload_to_email # noqa: F401
from app.tasks.upload_to_ftp import upload_to_ftp # noqa: F401
from app.tasks.upload_to_google_drive import upload_to_google_drive # noqa: F401
from app.tasks.upload_to_icloud import upload_to_icloud # noqa: F401
from app.tasks.upload_to_nextcloud import upload_to_nextcloud # noqa: F401
from app.tasks.upload_to_onedrive import upload_to_onedrive # noqa: F401
from app.tasks.upload_to_paperless import upload_to_paperless # noqa: F401
+145 -1
View File
@@ -49,18 +49,30 @@ class Settings(BaseSettings):
debug: bool = False # Default to False
# Making Dropbox optional
dropbox_enabled: bool = Field(
default=True,
description="Enable Dropbox as an upload destination. Set to False to disable uploads even when credentials are configured.",
)
dropbox_app_key: Optional[str] = None
dropbox_app_secret: Optional[str] = None
dropbox_folder: Optional[str] = None
dropbox_refresh_token: Optional[str] = None
# Making Nextcloud optional
nextcloud_enabled: bool = Field(
default=True,
description="Enable Nextcloud as an upload destination. Set to False to disable uploads even when credentials are configured.",
)
nextcloud_upload_url: Optional[str] = None
nextcloud_username: Optional[str] = None
nextcloud_password: Optional[str] = None
nextcloud_folder: Optional[str] = None
# Making Paperless optional
paperless_enabled: bool = Field(
default=True,
description="Enable Paperless-ngx as an upload destination. Set to False to disable uploads even when credentials are configured.",
)
paperless_ngx_api_token: Optional[str] = None
paperless_host: Optional[str] = None
paperless_custom_field_absender: Optional[str] = None # Name of the "absender" custom field in Paperless
@@ -166,12 +178,44 @@ class Settings(BaseSettings):
),
)
# Authentik
# Authentik / Generic OIDC
authentik_client_id: Optional[str] = None
authentik_client_secret: Optional[str] = None
authentik_config_url: Optional[str] = None
oauth_provider_name: Optional[str] = None # Name to display for the OAuth provider
# Social Login Providers
# Google OAuth2
social_auth_google_enabled: bool = False
social_auth_google_client_id: Optional[str] = None
social_auth_google_client_secret: Optional[str] = None
# Microsoft OAuth2 (Azure AD / Microsoft Entra ID)
social_auth_microsoft_enabled: bool = False
social_auth_microsoft_client_id: Optional[str] = None
social_auth_microsoft_client_secret: Optional[str] = None
social_auth_microsoft_tenant: str = Field(
default="common",
description=(
"Azure AD tenant ID or one of 'common', 'organizations', 'consumers'. "
"Use 'common' to allow any Microsoft account and any Azure AD org. "
"Use a specific tenant ID (GUID) to restrict to a single organization. "
"Default: common."
),
)
# Apple Sign-In
social_auth_apple_enabled: bool = False
social_auth_apple_client_id: Optional[str] = None
social_auth_apple_team_id: Optional[str] = None
social_auth_apple_key_id: Optional[str] = None
social_auth_apple_private_key: Optional[str] = None
# Dropbox OAuth2
social_auth_dropbox_enabled: bool = False
social_auth_dropbox_client_id: Optional[str] = None
social_auth_dropbox_client_secret: Optional[str] = None
# Local user signup
allow_local_signup: bool = Field(
default=False,
@@ -394,6 +438,10 @@ class Settings(BaseSettings):
imap2_delete_after_process: bool = False
# Google Drive settings
google_drive_enabled: bool = Field(
default=True,
description="Enable Google Drive as an upload destination. Set to False to disable uploads even when credentials are configured.",
)
google_drive_credentials_json: Optional[str] = ""
google_drive_folder_id: Optional[str] = ""
google_drive_delegate_to: Optional[str] = "" # Optional delegated user email
@@ -405,6 +453,10 @@ class Settings(BaseSettings):
google_drive_refresh_token: Optional[str] = ""
# WebDAV settings
webdav_enabled: bool = Field(
default=True,
description="Enable WebDAV as an upload destination. Set to False to disable uploads even when credentials are configured.",
)
webdav_url: Optional[str] = None
webdav_username: Optional[str] = None
webdav_password: Optional[str] = None
@@ -412,6 +464,10 @@ class Settings(BaseSettings):
webdav_verify_ssl: bool = True
# FTP settings
ftp_enabled: bool = Field(
default=True,
description="Enable FTP as an upload destination. Set to False to disable uploads even when credentials are configured.",
)
ftp_host: Optional[str] = None
ftp_port: Optional[int] = 21
ftp_username: Optional[str] = None
@@ -421,6 +477,10 @@ class Settings(BaseSettings):
ftp_allow_plaintext: bool = True # Default to allowing plaintext fallback
# SFTP settings
sftp_enabled: bool = Field(
default=True,
description="Enable SFTP as an upload destination. Set to False to disable uploads even when credentials are configured.",
)
sftp_host: Optional[str] = None
sftp_port: Optional[int] = 22
sftp_username: Optional[str] = None
@@ -442,6 +502,10 @@ class Settings(BaseSettings):
email_default_recipient: Optional[str] = None
# Email destination settings (dedicated SMTP for document delivery decoupled from shared email above)
dest_email_enabled: bool = Field(
default=True,
description="Enable Email as an upload destination. Set to False to disable document delivery via email even when credentials are configured.",
)
dest_email_host: Optional[str] = None
dest_email_port: Optional[int] = 587
dest_email_username: Optional[str] = None
@@ -451,6 +515,10 @@ class Settings(BaseSettings):
dest_email_default_recipient: Optional[str] = None # Fallback recipient for document delivery
# OneDrive settings
onedrive_enabled: bool = Field(
default=True,
description="Enable OneDrive as an upload destination. Set to False to disable uploads even when credentials are configured.",
)
onedrive_client_id: Optional[str] = None
onedrive_client_secret: Optional[str] = None
onedrive_tenant_id: Optional[str] = "common" # Default to "common" for personal accounts
@@ -458,6 +526,10 @@ class Settings(BaseSettings):
onedrive_folder_path: Optional[str] = None
# AWS S3 settings
s3_enabled: bool = Field(
default=True,
description="Enable Amazon S3 as an upload destination. Set to False to disable uploads even when credentials are configured.",
)
aws_access_key_id: Optional[str] = None
aws_secret_access_key: Optional[str] = None
aws_region: Optional[str] = "us-east-1" # Default region
@@ -466,6 +538,16 @@ class Settings(BaseSettings):
s3_storage_class: Optional[str] = "STANDARD" # Default storage class
s3_acl: Optional[str] = "private" # Default ACL
# iCloud Drive settings
icloud_enabled: bool = Field(
default=True,
description="Enable iCloud Drive as an upload destination. Set to False to disable uploads even when credentials are configured.",
)
icloud_username: Optional[str] = None # Apple ID email address
icloud_password: Optional[str] = None # App-specific password (required for 2FA accounts)
icloud_folder: Optional[str] = None # Target folder path in iCloud Drive (e.g. "Documents/Uploads")
icloud_cookie_directory: Optional[str] = None # Directory for session cookies (default: ~/.pyicloud)
# Uptime Kuma settings
uptime_kuma_url: Optional[str] = None
uptime_kuma_ping_interval: int = 5 # Default ping interval in minutes
@@ -484,6 +566,14 @@ class Settings(BaseSettings):
# Feature flags
allow_file_delete: bool = True # Default to allowing file deletion from database
compliance_enabled: bool = Field(
default=True,
description=(
"Enable the compliance templates dashboard (GDPR, HIPAA, SOC 2). "
"When enabled, admins can view compliance status and apply "
"pre-built regulatory configurations. Default: True."
),
)
# PDF/A archival conversion settings
enable_pdfa_conversion: bool = Field(
@@ -557,6 +647,17 @@ class Settings(BaseSettings):
),
)
imap_attachment_filter: str = Field(
default="documents_only",
description=(
"Controls which attachment types are ingested from IMAP emails. "
"Accepted values: "
"'documents_only' ingest only PDFs and office files (Word, Excel, PowerPoint, ODT, etc.); "
"'all' ingest all supported file types including images. "
"This is the global default; individual user IMAP accounts can override it."
),
)
# Batch processing settings
processall_throttle_threshold: int = Field(
default=20,
@@ -849,6 +950,49 @@ class Settings(BaseSettings):
),
)
# SIEM / External Audit Log Forwarding
# Forward audit events to external SIEM systems for centralised monitoring.
audit_siem_enabled: bool = Field(
default=False,
description="Enable forwarding of audit events to an external SIEM system.",
)
audit_siem_transport: str = Field(
default="syslog",
description=(
"Transport used to forward audit events. "
"Options: 'syslog' (RFC 5424 over UDP/TCP), 'http' (JSON POST to a webhook URL, "
"compatible with Splunk HEC, Logstash HTTP input, Grafana Loki, etc.)."
),
)
audit_siem_syslog_host: str = Field(
default="localhost",
description="Hostname or IP of the syslog receiver.",
)
audit_siem_syslog_port: int = Field(
default=514,
description="Port of the syslog receiver.",
)
audit_siem_syslog_protocol: str = Field(
default="udp",
description="Protocol for syslog transport: 'udp' or 'tcp'.",
)
audit_siem_http_url: str = Field(
default="",
description=(
"HTTP endpoint URL for SIEM webhook delivery. "
"Supports Splunk HEC (https://splunk:8088/services/collector/event), "
"Logstash HTTP input, Grafana Loki push API, or any JSON-accepting endpoint."
),
)
audit_siem_http_token: str = Field(
default="",
description="Bearer / HEC token included in the Authorization header of SIEM HTTP requests.",
)
audit_siem_http_custom_headers: str = Field(
default="",
description="Comma-separated 'Key:Value' pairs of extra headers for SIEM HTTP requests.",
)
# UI / Appearance
ui_default_color_scheme: str = Field(
default="system",
+36 -6
View File
@@ -16,6 +16,7 @@ from starlette.middleware.trustedhost import TrustedHostMiddleware
from uvicorn.middleware.proxy_headers import ProxyHeadersMiddleware
from app.api import router as api_router
from app.api.graphql_api import graphql_router
from app.api.local_auth import router as local_auth_router
from app.auth import router as auth_router
from app.config import settings
@@ -146,6 +147,20 @@ async def lifespan(app: FastAPI):
except Exception:
logging.debug("Scheduled jobs seeding skipped — DB may not be ready yet") # noqa: S110
# Seed the built-in compliance templates (GDPR, HIPAA, SOC2) so they
# are available in the admin compliance dashboard on first startup.
try:
from app.database import SessionLocal as _SessionLocal # noqa: F811
from app.utils.compliance_service import seed_compliance_templates as _seed_compliance
_db_compliance = _SessionLocal()
try:
_seed_compliance(_db_compliance)
finally:
_db_compliance.close()
except Exception:
logging.debug("Compliance template seeding skipped — DB may not be ready yet") # noqa: S110
# Application is now running
yield
@@ -239,6 +254,21 @@ else:
# Custom exception handlers that return JSON for API routes and HTML for frontend routes
# These use their own separate templates instance so that patches in tests on individual
# view modules do not affect the error handler rendering.
_error_templates_dir = pathlib.Path(__file__).parents[1] / "frontend" / "templates"
_error_templates = Jinja2Templates(directory=str(_error_templates_dir))
# Register the i18n translate helper as a global so error templates can use {{ _("key") }}.
# Error pages use the default language (English); request-specific locale is not needed here.
from app.utils.i18n import SUPPORTED_LANGUAGES as _SUPPORTED_LANGUAGES # noqa: E402
from app.utils.i18n import translate as _translate_fn # noqa: E402
_error_templates.env.globals["_"] = lambda key, **kwargs: _translate_fn(key, "en", **kwargs)
_error_templates.env.globals["min"] = min
_error_templates.env.globals["max"] = max
_error_templates.env.globals["supported_languages"] = _SUPPORTED_LANGUAGES
@app.exception_handler(HTTPException)
async def http_exception_handler(request: Request, exc: HTTPException):
"""
@@ -250,15 +280,15 @@ async def http_exception_handler(request: Request, exc: HTTPException):
return JSONResponse(status_code=exc.status_code, content={"detail": exc.detail})
# For frontend routes, return appropriate HTML templates
templates = Jinja2Templates(directory=str(static_dir.parent / "templates"))
# Handle 404 errors with a custom template
if exc.status_code == 404:
return templates.TemplateResponse("404.html", {"request": request}, status_code=status.HTTP_404_NOT_FOUND)
return _error_templates.TemplateResponse(
"404.html", {"request": request}, status_code=status.HTTP_404_NOT_FOUND
)
# For other HTTP errors, we could create specific templates or use a generic one
# For now, return a simple error page
return templates.TemplateResponse(
return _error_templates.TemplateResponse(
"404.html", # Reuse 404 template for other errors, or create a generic error template
{"request": request},
status_code=exc.status_code,
@@ -279,8 +309,7 @@ async def custom_500_handler(request: Request, exc: Exception):
)
# Serve the 500 template for non-API routes
templates = Jinja2Templates(directory=str(static_dir.parent / "templates"))
return templates.TemplateResponse(
return _error_templates.TemplateResponse(
"500.html",
{"request": request, "exc": exc},
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
@@ -298,3 +327,4 @@ app.include_router(files_router) # Explicitly include the files router
app.include_router(auth_router)
app.include_router(local_auth_router)
app.include_router(api_router, prefix="/api")
app.include_router(graphql_router, prefix="/graphql")
+137
View File
@@ -147,6 +147,27 @@ class SettingsAuditLog(Base):
action = Column(String, nullable=False) # "update" or "delete"
class AuditLog(Base):
"""Comprehensive audit log for compliance tracking.
Records all significant actions: login/logout, document CRUD, settings
changes, and administrative operations. Rows are append-only; the API
and service layer never update or delete entries.
"""
__tablename__ = "audit_logs"
id = Column(Integer, primary_key=True, index=True)
timestamp = Column(DateTime(timezone=True), server_default=func.now(), nullable=False, index=True)
user = Column(String, nullable=False, index=True) # Username or "anonymous" / "system"
action = Column(String, nullable=False, index=True) # e.g. "login", "document.create", "settings.update"
resource_type = Column(String, nullable=True, index=True) # e.g. "document", "user", "settings"
resource_id = Column(String, nullable=True) # ID of the affected resource
ip_address = Column(String, nullable=True) # Client IP address
details = Column(Text, nullable=True) # JSON-encoded extra context
severity = Column(String(16), nullable=False, server_default="info") # info / warning / error / critical
class SavedSearch(Base):
"""User-defined saved search filters for quick access to frequently used filter combinations."""
@@ -257,6 +278,17 @@ class UserProfile(Base):
preferred_destination = Column(String(50), nullable=True)
stripe_customer_id = Column(String(64), nullable=True)
# UI language preference for i18n (ISO 639-1 code, e.g. "en", "de", "fr")
# NULL means "auto-detect from browser Accept-Language header"
preferred_language = Column(String(10), nullable=True)
# UI colour scheme preference: "light" | "dark" | "system" (NULL = "system")
preferred_theme = Column(String(10), nullable=True)
# Custom profile avatar stored as a base64 data-URL (e.g. "data:image/png;base64,...")
# NULL means use the Gravatar fallback derived from the user's e-mail address.
avatar_data = Column(Text, nullable=True)
created_at = Column(DateTime(timezone=True), server_default=func.now())
updated_at = Column(DateTime(timezone=True), server_default=func.now(), onupdate=func.now())
@@ -377,6 +409,48 @@ class PipelineStep(Base):
updated_at = Column(DateTime(timezone=True), server_default=func.now(), onupdate=func.now())
class ImapIngestionProfile(Base):
"""Named ingestion profile controlling which attachment types are accepted from IMAP emails.
Profiles group file-type categories (e.g. "pdf", "office", "images") so users
can precisely control what gets ingested from each mailbox.
System-provided built-in profiles (``is_builtin=True``) are seeded by the
migration and cannot be deleted or renamed. Users may create their own profiles
(``owner_id`` set to their identifier) or rely on the global system profiles
(``owner_id=None``).
``allowed_categories`` stores a JSON list of category strings, e.g.::
'["pdf", "office", "opendocument", "text", "web"]'
Valid category names are defined in ``app.utils.allowed_types.FILE_TYPE_CATEGORIES``.
"""
__tablename__ = "imap_ingestion_profiles"
id = Column(Integer, primary_key=True, index=True)
# Human-readable profile name (e.g. "Documents Only", "Documents + Images")
name = Column(String(255), nullable=False)
# Optional description shown in the UI
description = Column(Text, nullable=True)
# Owner of this profile. NULL = global/system profile available to all users.
owner_id = Column(String, nullable=True, index=True)
# JSON-encoded list of enabled category keys. Example: '["pdf","office","text"]'
# See FILE_TYPE_CATEGORIES in app/utils/allowed_types.py for valid values.
allowed_categories = Column(Text, nullable=False, default='["pdf","office","opendocument","text","web"]')
# Built-in system profiles that cannot be deleted or modified via the API.
is_builtin = Column(Boolean, nullable=False, default=False)
created_at = Column(DateTime(timezone=True), server_default=func.now())
updated_at = Column(DateTime(timezone=True), server_default=func.now(), onupdate=func.now())
class UserImapAccount(Base):
"""Per-user IMAP ingestion account.
@@ -415,6 +489,10 @@ class UserImapAccount(Base):
# When True, emails are deleted from the mailbox after their attachments are processed
delete_after_process = Column(Boolean, nullable=False, default=False)
# Optional reference to an ImapIngestionProfile.
# NULL means "use the global imap_attachment_filter setting" (system default).
profile_id = Column(Integer, ForeignKey("imap_ingestion_profiles.id"), nullable=True)
# When False the account is not polled by the periodic task (but not deleted)
is_active = Column(Boolean, nullable=False, default=True)
@@ -506,6 +584,7 @@ class IntegrationType:
EMAIL = "EMAIL"
PAPERLESS = "PAPERLESS"
RCLONE = "RCLONE"
ICLOUD = "ICLOUD"
ALL = {
IMAP,
@@ -522,6 +601,7 @@ class IntegrationType:
EMAIL,
PAPERLESS,
RCLONE,
ICLOUD,
}
@@ -836,6 +916,63 @@ class ScheduledJob(Base):
updated_at = Column(DateTime(timezone=True), server_default=func.now(), onupdate=func.now())
class MobileDevice(Base):
"""Registered mobile device for push notifications.
Stores the push token (Expo push token, FCM token, or APNs token) for a
specific user device so that document-processing events can be forwarded
as push notifications to the native mobile app.
"""
__tablename__ = "mobile_devices"
id = Column(Integer, primary_key=True, index=True)
# User that owns this device registration.
owner_id = Column(String, nullable=False, index=True)
# Human-readable name the user gave this device (e.g. "John's iPhone").
device_name = Column(String(255), nullable=True)
# Platform: "ios", "android", or "web".
platform = Column(String(20), nullable=False, default="ios")
# Expo push token (ExponentPushToken[…]) or raw FCM/APNs token.
push_token = Column(String(512), nullable=False)
# Whether push notifications are enabled for this device.
is_active = Column(Boolean, nullable=False, default=True)
# Timestamps.
created_at = Column(DateTime(timezone=True), server_default=func.now())
last_seen_at = Column(DateTime(timezone=True), nullable=True)
__table_args__ = (UniqueConstraint("owner_id", "push_token", name="uq_mobile_device_owner_token"),)
class ComplianceTemplate(Base):
"""Pre-built compliance configuration templates (GDPR, HIPAA, SOC2).
Each row represents an applied compliance template. The ``settings_json``
column stores the concrete setting key/value pairs that were written when
the template was applied. ``status`` tracks the current compliance posture.
"""
__tablename__ = "compliance_templates"
id = Column(Integer, primary_key=True, index=True)
name = Column(String(50), unique=True, nullable=False, index=True) # GDPR, HIPAA, SOC2
display_name = Column(String(100), nullable=False)
description = Column(Text, nullable=True)
settings_json = Column(Text, nullable=False, default="{}") # JSON of applied settings
enabled = Column(Boolean, nullable=False, default=False)
status = Column(String(20), nullable=False, default="not_applied") # not_applied, compliant, partial, non_compliant
applied_at = Column(DateTime(timezone=True), nullable=True)
applied_by = Column(String(255), nullable=True)
created_at = Column(DateTime(timezone=True), server_default=func.now())
updated_at = Column(DateTime(timezone=True), server_default=func.now(), onupdate=func.now())
class PipelineRoutingRule(Base):
"""Conditional routing rule that assigns documents to pipelines.
+92 -25
View File
@@ -13,7 +13,11 @@ from celery import shared_task
from app.config import settings
from app.tasks.convert_to_pdf import convert_to_pdf # new conversion task
from app.tasks.process_document import process_document # Updated import
from app.utils.allowed_types import ALLOWED_EXTENSIONS, ALLOWED_MIME_TYPES
from app.utils.allowed_types import (
ALL_CATEGORIES,
DEFAULT_CATEGORIES,
get_allowed_types_for_categories,
)
# Database session for per-user IMAP accounts (imported lazily to avoid circular imports)
_db_session_factory = None
@@ -50,6 +54,38 @@ def _decrypt_imap_password(password: str | None) -> str | None:
return decrypt_value(password)
def _resolve_categories_for_profile(profile_id: int | None) -> list[str]:
"""Return the list of allowed categories for a profile ID.
Loads the profile from the database. If ``profile_id`` is ``None`` or the
profile is not found, falls back to the global ``settings.imap_attachment_filter``
string (``'documents_only'`` → default categories; ``'all'`` → all categories).
"""
if profile_id is not None:
try:
from app.models import ImapIngestionProfile
db = _get_db_session()
try:
profile = db.query(ImapIngestionProfile).filter(ImapIngestionProfile.id == profile_id).first()
if profile:
return json.loads(profile.allowed_categories)
finally:
db.close()
except Exception as exc: # noqa: BLE001
logger.warning(
"Could not load IMAP ingestion profile %d (%s: %s) — using global default",
profile_id,
type(exc).__name__,
exc,
)
# Fall back to global setting
if settings.imap_attachment_filter == "all":
return ALL_CATEGORIES
return DEFAULT_CATEGORIES
LOCK_KEY = "imap_lock" # Unique key for locking
LOCK_EXPIRE = 300 # Lock expires in 5 minutes
@@ -180,6 +216,7 @@ def _pull_user_imap_accounts() -> None:
use_ssl=acct.use_ssl,
delete_after_process=acct.delete_after_process,
owner_id=acct.owner_id,
allowed_categories=_resolve_categories_for_profile(acct.profile_id),
)
# Record successful poll
acct.last_checked_at = datetime.now(timezone.utc)
@@ -250,6 +287,9 @@ def _pull_user_integration_imap() -> None:
use_ssl = cfg.get("use_ssl", True)
delete_after = cfg.get("delete_after_process", False)
gmail_labels = cfg.get("gmail_apply_labels", True)
# Integrations can store a profile_id in config; fall back to global default
profile_id = cfg.get("profile_id")
allowed_categories = _resolve_categories_for_profile(profile_id)
if not (host and username and password):
logger.warning(
@@ -269,6 +309,7 @@ def _pull_user_integration_imap() -> None:
delete_after_process=delete_after,
owner_id=integ.owner_id,
gmail_apply_labels=gmail_labels,
allowed_categories=allowed_categories,
)
integ.last_used_at = datetime.now(timezone.utc)
integ.last_error = None
@@ -329,6 +370,7 @@ def pull_inbox(
delete_after_process,
owner_id=None,
gmail_apply_labels=True,
allowed_categories=None,
):
"""
Connects to the IMAP inbox, fetches new unread emails from the last 3 days,
@@ -345,8 +387,22 @@ def pull_inbox(
attributed to this user via ``process_document`` / ``convert_to_pdf``.
gmail_apply_labels: Whether to apply Gmail-specific labels and stars to
processed emails. Only relevant for Gmail hosts. Defaults to True.
allowed_categories: List of file-type category keys to ingest (e.g.
``["pdf", "office", "images"]``). ``None`` falls back to the
global ``settings.imap_attachment_filter`` mapping.
"""
logger.info("Connecting to %s at %s:%s (SSL=%s)", mailbox_key, host, port, use_ssl)
if allowed_categories is None:
allowed_categories = _resolve_categories_for_profile(None)
effective_mime_types, effective_extensions = get_allowed_types_for_categories(allowed_categories)
logger.info(
"Connecting to %s at %s:%s (SSL=%s) — categories: %s",
mailbox_key,
host,
port,
use_ssl,
allowed_categories,
)
processed_emails = load_processed_emails()
try:
@@ -405,9 +461,13 @@ def pull_inbox(
logger.info("Skipping email %s in %s, already labeled 'Ingested'.", msg_id, mailbox_key)
continue
# Process attachments (and convert non-PDF files).
# We call the function without assigning its return value since it is not used.
fetch_attachments_and_enqueue(email_message, owner_id=owner_id)
# Process attachments using the resolved mime types / extensions.
fetch_attachments_and_enqueue(
email_message,
owner_id=owner_id,
effective_mime_types=effective_mime_types,
effective_extensions=effective_extensions,
)
if settings.imap_readonly_mode:
logger.info("Readonly mode: skipping mailbox modifications for %s in %s", msg_id, mailbox_key)
@@ -436,27 +496,23 @@ def pull_inbox(
logger.exception("Error pulling mailbox %s: %s", mailbox_key, e)
def fetch_attachments_and_enqueue(email_message, owner_id: str | None = None):
def fetch_attachments_and_enqueue(
email_message,
owner_id: str | None = None,
effective_mime_types: frozenset[str] | None = None,
effective_extensions: frozenset[str] | None = None,
):
"""
Extracts attachments from the email and processes only allowed file types.
Files are accepted if either:
1. They have a MIME type from the ALLOWED_MIME_TYPES set, OR
2. They have a '.pdf' file extension (regardless of MIME type)
The caller is responsible for computing ``effective_mime_types`` and
``effective_extensions`` from the relevant :class:`ImapIngestionProfile` (or
the global default) via :func:`app.utils.allowed_types.get_allowed_types_for_categories`
before calling this function. ``pull_inbox`` does this automatically.
Allowed file types include:
- PDF: application/pdf or *.pdf extension
- Microsoft Office files:
- Word: application/msword,
application/vnd.openxmlformats-officedocument.wordprocessingml.document
- Excel: application/vnd.ms-excel,
application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
- PowerPoint: application/vnd.ms-powerpoint,
application/vnd.openxmlformats-officedocument.presentationml.presentation
- Other meaningful attachments:
- Plain text: text/plain
- CSV: text/csv
- Rich Text Format: application/rtf, text/rtf
If either set is ``None`` the function falls back to the default category list
so the function still works correctly when called directly in tests or from
other contexts.
If the attachment is a PDF (by extension or MIME type), it is enqueued for upload;
any other allowed file is enqueued for conversion to PDF.
@@ -465,9 +521,14 @@ def fetch_attachments_and_enqueue(email_message, owner_id: str | None = None):
email_message: The parsed email message to extract attachments from.
owner_id: Optional user identifier forwarded to ``process_document`` /
``convert_to_pdf`` for multi-tenant attribution.
effective_mime_types: Pre-computed frozenset of allowed MIME type strings.
effective_extensions: Pre-computed frozenset of allowed file extension strings.
Returns True if at least one allowed attachment was processed.
"""
if effective_mime_types is None or effective_extensions is None:
effective_mime_types, effective_extensions = get_allowed_types_for_categories(DEFAULT_CATEGORIES)
has_attachment = False
for part in email_message.walk():
if part.get_content_maintype() == "multipart":
@@ -482,9 +543,15 @@ def fetch_attachments_and_enqueue(email_message, owner_id: str | None = None):
mime_type = part.get_content_type()
file_ext = os.path.splitext(filename)[1].lower()
# Accept file if it has an allowed MIME type, an allowed extension, OR is a PDF by extension
if mime_type not in ALLOWED_MIME_TYPES and file_ext not in ALLOWED_EXTENSIONS and not is_pdf_by_extension:
logger.info("Skipping attachment %s with MIME type %s", filename, mime_type)
if mime_type not in effective_mime_types and file_ext not in effective_extensions and not is_pdf_by_extension:
logger.info(
"Skipping attachment %s (MIME: %s, ext: %s) — not in effective allowed set",
filename,
mime_type,
file_ext,
)
continue
file_path = os.path.join(settings.workdir, filename)
@@ -495,7 +562,7 @@ def fetch_attachments_and_enqueue(email_message, owner_id: str | None = None):
if mime_type == "application/pdf" or is_pdf_by_extension:
process_document.delay(file_path, owner_id=owner_id)
logger.info("Enqueued PDF for upload: %s (MIME: %s)", filename, mime_type)
elif mime_type in ALLOWED_MIME_TYPES:
elif mime_type in effective_mime_types:
# Other allowed files are sent for conversion
convert_to_pdf.delay(file_path, owner_id=owner_id)
logger.info("Enqueued file for conversion to PDF: %s", filename)
+61 -12
View File
@@ -12,6 +12,7 @@ from app.tasks.upload_to_dropbox import upload_to_dropbox
from app.tasks.upload_to_email import upload_to_email
from app.tasks.upload_to_ftp import upload_to_ftp
from app.tasks.upload_to_google_drive import upload_to_google_drive
from app.tasks.upload_to_icloud import upload_to_icloud
from app.tasks.upload_to_nextcloud import upload_to_nextcloud
from app.tasks.upload_to_onedrive import upload_to_onedrive
from app.tasks.upload_to_paperless import upload_to_paperless
@@ -25,18 +26,32 @@ logger = logging.getLogger(__name__)
def _should_upload_to_dropbox():
return bool(settings.dropbox_app_key and settings.dropbox_app_secret and settings.dropbox_refresh_token)
return bool(
getattr(settings, "dropbox_enabled", True)
and settings.dropbox_app_key
and settings.dropbox_app_secret
and settings.dropbox_refresh_token
)
def _should_upload_to_nextcloud():
return bool(settings.nextcloud_upload_url and settings.nextcloud_username and settings.nextcloud_password)
return bool(
getattr(settings, "nextcloud_enabled", True)
and settings.nextcloud_upload_url
and settings.nextcloud_username
and settings.nextcloud_password
)
def _should_upload_to_paperless():
return bool(settings.paperless_ngx_api_token and settings.paperless_host)
return bool(
getattr(settings, "paperless_enabled", True) and settings.paperless_ngx_api_token and settings.paperless_host
)
def _should_upload_to_google_drive():
if not getattr(settings, "google_drive_enabled", True):
return False
# Check for OAuth configuration
if getattr(settings, "google_drive_use_oauth", False):
return bool(
@@ -51,20 +66,33 @@ def _should_upload_to_google_drive():
def _should_upload_to_webdav():
return bool(settings.webdav_url and settings.webdav_username and settings.webdav_password)
return bool(
getattr(settings, "webdav_enabled", True)
and settings.webdav_url
and settings.webdav_username
and settings.webdav_password
)
def _should_upload_to_ftp():
return bool(settings.ftp_host and settings.ftp_username and settings.ftp_password)
return bool(
getattr(settings, "ftp_enabled", True) and settings.ftp_host and settings.ftp_username and settings.ftp_password
)
def _should_upload_to_sftp():
return bool(settings.sftp_host and settings.sftp_username and (settings.sftp_password or settings.sftp_private_key))
return bool(
getattr(settings, "sftp_enabled", True)
and settings.sftp_host
and settings.sftp_username
and (settings.sftp_password or settings.sftp_private_key)
)
def _should_upload_to_email():
return bool(
settings.dest_email_host
getattr(settings, "dest_email_enabled", True)
and settings.dest_email_host
and settings.dest_email_username
and settings.dest_email_password
and settings.dest_email_default_recipient
@@ -72,18 +100,32 @@ def _should_upload_to_email():
def _should_upload_to_onedrive():
return bool(settings.onedrive_client_id and settings.onedrive_client_secret and settings.onedrive_refresh_token)
return bool(
getattr(settings, "onedrive_enabled", True)
and settings.onedrive_client_id
and settings.onedrive_client_secret
and settings.onedrive_refresh_token
)
def _should_upload_to_s3():
return bool(settings.s3_bucket_name and settings.aws_access_key_id and settings.aws_secret_access_key)
return bool(
getattr(settings, "s3_enabled", True)
and settings.s3_bucket_name
and settings.aws_access_key_id
and settings.aws_secret_access_key
)
def _should_upload_to_icloud():
return bool(getattr(settings, "icloud_enabled", True) and settings.icloud_username and settings.icloud_password)
def get_configured_services_from_validator():
"""
Use the config validator to determine which services are configured properly.
Use the config validator to determine which services are configured and enabled.
Returns a dictionary with service names as keys and boolean values indicating
whether they're properly configured.
whether they're properly configured AND explicitly enabled.
"""
providers = get_provider_status()
@@ -98,12 +140,14 @@ def get_configured_services_from_validator():
"Email": "email",
"OneDrive": "onedrive",
"S3 Storage": "s3",
"iCloud Drive": "icloud",
}
result = {}
for provider_name, internal_name in service_map.items():
if provider_name in providers:
result[internal_name] = providers[provider_name].get("configured", False)
provider = providers[provider_name]
result[internal_name] = provider.get("configured", False) and provider.get("enabled", True)
return result
@@ -206,6 +250,11 @@ def send_to_all_destinations(self, file_path: str, use_validator=True, file_id:
"should_upload": _should_upload_to_s3,
"upload_func": upload_to_s3,
},
{
"name": "icloud",
"should_upload": _should_upload_to_icloud,
"upload_func": upload_to_icloud,
},
]
# Optionally get configuration status from validator
+177
View File
@@ -0,0 +1,177 @@
#!/usr/bin/env python3
"""Upload files to Apple iCloud Drive via the pyicloud library.
This module uses the ``pyicloud`` library to authenticate with Apple's iCloud
service and upload files to iCloud Drive. Because Apple does not offer a public
REST API for iCloud Drive, this integration relies on the *unofficial*
reverse-engineered protocol implemented by ``pyicloud``.
Requirements
~~~~~~~~~~~~
* An Apple ID with iCloud Drive enabled.
* An **app-specific password** generated at https://appleid.apple.com (required
when two-factor authentication is active which is the default for all modern
Apple IDs).
* The ``pyicloud`` Python package (``pip install pyicloud``).
Configuration
~~~~~~~~~~~~~
Set the following environment variables (or ``app/config.py`` fields):
* ``ICLOUD_USERNAME`` Apple ID email address.
* ``ICLOUD_PASSWORD`` App-specific password.
* ``ICLOUD_FOLDER`` Target folder path inside iCloud Drive, using ``/`` as
the separator (e.g. ``Documents/Uploads``). The folder is created
automatically if it does not exist.
* ``ICLOUD_COOKIE_DIRECTORY`` (Optional) Directory for persisting session
cookies so that re-authentication is avoided between task runs. Defaults to
``~/.pyicloud``.
"""
import logging
import os
from app.celery_app import celery
from app.config import settings
from app.tasks.retry_config import UploadTaskWithRetry
from app.utils import log_task_progress
logger = logging.getLogger(__name__)
def _get_icloud_api(
username: str,
password: str,
cookie_directory: str | None = None,
):
"""Return an authenticated ``PyiCloudService`` instance.
Args:
username: Apple ID email address.
password: App-specific password.
cookie_directory: Optional directory for session cookies.
Returns:
An authenticated ``PyiCloudService`` instance.
Raises:
ImportError: If ``pyicloud`` is not installed.
ValueError: If authentication fails or 2FA is required interactively.
"""
from pyicloud import PyiCloudService # noqa: S404 unofficial third-party iCloud client
kwargs: dict = {}
if cookie_directory:
kwargs["cookie_directory"] = cookie_directory
api = PyiCloudService(username, password, **kwargs)
# If 2SA/2FA is required the user must use an app-specific password instead.
if api.requires_2sa or api.requires_2fa:
raise ValueError(
"iCloud account requires two-factor authentication. "
"Please generate an app-specific password at https://appleid.apple.com "
"and use it as ICLOUD_PASSWORD."
)
return api
def _navigate_to_folder(drive_root, folder_path: str):
"""Navigate into (or create) the folder hierarchy described by *folder_path*.
Args:
drive_root: The iCloud Drive root node (``api.drive``).
folder_path: ``/``-separated path such as ``Documents/Uploads``.
Returns:
The drive node representing the target folder.
"""
node = drive_root
if not folder_path:
return node
parts = [p for p in folder_path.strip("/").split("/") if p]
for part in parts:
children = {child.name: child for child in node.dir()}
if part in children:
node = children[part]
else:
# Create the missing folder
node = node.mkdir(part)
return node
@celery.task(base=UploadTaskWithRetry, bind=True)
def upload_to_icloud(self, file_path: str, file_id: int = None, folder_override: str = None):
"""Upload a file to Apple iCloud Drive.
Args:
file_path: Local path to the file to upload.
file_id: Optional ``FileRecord.id`` for progress logging.
folder_override: If provided, overrides the default ``ICLOUD_FOLDER``
setting for this upload.
"""
task_id = self.request.id
logger.info(f"[{task_id}] Starting iCloud Drive upload: {file_path}")
log_task_progress(
task_id,
"upload_to_icloud",
"in_progress",
f"Uploading to iCloud Drive: {os.path.basename(file_path)}",
file_id=file_id,
)
# ------------------------------------------------------------------
# Validate inputs
# ------------------------------------------------------------------
if not os.path.exists(file_path):
error_msg = f"File not found: {file_path}"
logger.error(f"[{task_id}] {error_msg}")
log_task_progress(task_id, "upload_to_icloud", "failure", error_msg, file_id=file_id)
raise FileNotFoundError(error_msg)
if not settings.icloud_username or not settings.icloud_password:
error_msg = "iCloud credentials are not configured (ICLOUD_USERNAME / ICLOUD_PASSWORD)"
logger.error(f"[{task_id}] {error_msg}")
log_task_progress(task_id, "upload_to_icloud", "failure", error_msg, file_id=file_id)
raise ValueError(error_msg)
filename = os.path.basename(file_path)
target_folder = folder_override if folder_override is not None else (settings.icloud_folder or "")
# ------------------------------------------------------------------
# Authenticate & upload
# ------------------------------------------------------------------
try:
api = _get_icloud_api(
settings.icloud_username,
settings.icloud_password,
settings.icloud_cookie_directory,
)
folder_node = _navigate_to_folder(api.drive, target_folder)
with open(file_path, "rb") as fh:
folder_node.upload(fh)
logger.info(f"[{task_id}] Successfully uploaded {filename} to iCloud Drive folder '{target_folder}'")
log_task_progress(
task_id,
"upload_to_icloud",
"success",
f"Uploaded to iCloud Drive: {filename}",
file_id=file_id,
)
return {
"status": "Completed",
"file": file_path,
"icloud_folder": target_folder or "/",
}
except Exception as e:
error_msg = f"Error uploading {filename} to iCloud Drive: {e}"
logger.error(f"[{task_id}] {error_msg}")
log_task_progress(task_id, "upload_to_icloud", "failure", error_msg, file_id=file_id)
raise RuntimeError(error_msg) from e
+32
View File
@@ -571,6 +571,37 @@ def _upload_rclone(file_path: str, cfg: dict[str, Any], creds: dict[str, Any], t
return {"status": "Completed", "rclone_dest": dest}
def _upload_icloud(file_path: str, cfg: dict[str, Any], creds: dict[str, Any], task_id: str) -> dict[str, Any]:
"""Upload *file_path* to iCloud Drive using per-user credentials.
Expected *cfg* keys:
* ``folder`` target folder path inside iCloud Drive (e.g. ``Documents/Uploads``).
* ``cookie_directory`` (optional) path for session cookie persistence.
Expected *creds* keys:
* ``username`` Apple ID email address.
* ``password`` app-specific password.
"""
from app.tasks.upload_to_icloud import _get_icloud_api, _navigate_to_folder
username = creds.get("username") or ""
password = creds.get("password") or ""
folder = cfg.get("folder") or ""
cookie_directory = cfg.get("cookie_directory") or None
if not username or not password:
raise ValueError("iCloud integration is missing username or password in credentials")
api = _get_icloud_api(username, password, cookie_directory)
folder_node = _navigate_to_folder(api.drive, folder)
with open(file_path, "rb") as fh:
folder_node.upload(fh)
logger.info("[%s] iCloud Drive upload complete: folder=%s", task_id, folder or "/")
return {"status": "Completed", "icloud_folder": folder or "/"}
# Map IntegrationType → upload helper
_UPLOAD_HANDLERS = {
IntegrationType.DROPBOX: _upload_dropbox,
@@ -584,6 +615,7 @@ _UPLOAD_HANDLERS = {
IntegrationType.PAPERLESS: _upload_paperless,
IntegrationType.EMAIL: _upload_email,
IntegrationType.RCLONE: _upload_rclone,
IntegrationType.ICLOUD: _upload_icloud,
}
+154
View File
@@ -131,3 +131,157 @@ ALLOWED_EXTENSIONS: set[str] = {
".md",
".markdown",
}
# ---------------------------------------------------------------------------
# Fine-grained file-type categories used by IMAP ingestion profiles.
# Each category groups related MIME types and extensions so that users can
# enable/disable a logical collection of formats (e.g. "images") rather than
# having to manage individual MIME strings.
# ---------------------------------------------------------------------------
FILE_TYPE_CATEGORIES: dict[str, dict] = {
"pdf": {
"label": "PDF",
"description": "PDF documents (.pdf)",
"mime_types": frozenset({"application/pdf"}),
"extensions": frozenset({".pdf"}),
},
"office": {
"label": "Microsoft Office",
"description": "Word, Excel and PowerPoint files (.doc, .docx, .xls, .xlsx, .ppt, .pptx, …)",
"mime_types": frozenset(
{
"application/msword",
"application/vnd.openxmlformats-officedocument.wordprocessingml.document",
"application/vnd.openxmlformats-officedocument.wordprocessingml.template",
"application/vnd.ms-word.document.macroEnabled.12",
"application/vnd.ms-word.template.macroEnabled.12",
"application/vnd.ms-excel",
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
"application/vnd.openxmlformats-officedocument.spreadsheetml.template",
"application/vnd.ms-excel.sheet.macroEnabled.12",
"application/vnd.ms-excel.sheet.binary.macroEnabled.12",
"application/vnd.ms-powerpoint",
"application/vnd.openxmlformats-officedocument.presentationml.presentation",
"application/vnd.openxmlformats-officedocument.presentationml.template",
"application/vnd.openxmlformats-officedocument.presentationml.slideshow",
"application/vnd.ms-powerpoint.presentation.macroEnabled.12",
}
),
"extensions": frozenset(
{
".doc",
".docx",
".docm",
".dot",
".dotx",
".dotm",
".xls",
".xlsx",
".xlsm",
".xlsb",
".xlt",
".xltx",
".xlw",
".ppt",
".pptx",
".pptm",
".pps",
".ppsx",
".pot",
".potx",
}
),
},
"opendocument": {
"label": "OpenDocument (LibreOffice)",
"description": "LibreOffice / OpenOffice files (.odt, .ods, .odp, …)",
"mime_types": frozenset(
{
"application/vnd.oasis.opendocument.text",
"application/vnd.oasis.opendocument.spreadsheet",
"application/vnd.oasis.opendocument.presentation",
"application/vnd.oasis.opendocument.graphics",
"application/vnd.oasis.opendocument.formula",
}
),
"extensions": frozenset({".odt", ".ods", ".odp", ".odg", ".odf"}),
},
"text": {
"label": "Text & Data",
"description": "Plain text, CSV and RTF files (.txt, .csv, .rtf)",
"mime_types": frozenset(
{
"text/plain",
"text/csv",
"application/rtf",
"text/rtf",
}
),
"extensions": frozenset({".txt", ".csv", ".rtf"}),
},
"web": {
"label": "Web & Markup",
"description": "HTML and Markdown files (.html, .htm, .md, .markdown)",
"mime_types": frozenset(
{
"text/html",
"text/markdown",
"text/x-markdown",
}
),
"extensions": frozenset({".html", ".htm", ".md", ".markdown"}),
},
"images": {
"label": "Images",
"description": "Image files (.jpg, .png, .gif, .bmp, .tiff, .webp, .svg)",
"mime_types": frozenset(
{
"image/jpeg",
"image/jpg",
"image/png",
"image/gif",
"image/bmp",
"image/tiff",
"image/webp",
"image/svg+xml",
}
),
"extensions": frozenset(
{
".jpg",
".jpeg",
".png",
".gif",
".bmp",
".tiff",
".tif",
".webp",
".svg",
}
),
},
}
# Default categories for the "documents only" built-in profile (no images)
DEFAULT_CATEGORIES: list[str] = ["pdf", "office", "opendocument", "text", "web"]
# All categories including images
ALL_CATEGORIES: list[str] = ["pdf", "office", "opendocument", "text", "web", "images"]
def get_allowed_types_for_categories(
categories: list[str],
) -> tuple[frozenset[str], frozenset[str]]:
"""Return ``(mime_types, extensions)`` for the given category list.
Unknown category names are silently ignored so that future categories
don't break existing profiles.
"""
mime_types: set[str] = set()
extensions: set[str] = set()
for cat in categories:
info = FILE_TYPE_CATEGORIES.get(cat)
if info:
mime_types |= info["mime_types"]
extensions |= info["extensions"]
return frozenset(mime_types), frozenset(extensions)
+331
View File
@@ -0,0 +1,331 @@
"""
Comprehensive audit-event service for DocuElevate.
Provides helpers to **record** audit events (append-only database writes)
and to optionally **forward** them to external SIEM systems.
Supported SIEM transports:
* **Syslog** RFC 5424 structured-data messages over UDP or TCP.
* **HTTP** JSON POST payloads compatible with Splunk HEC, Logstash
HTTP input, Grafana Loki push API, and any generic webhook endpoint.
"""
import json
import logging
import re
import socket
import threading
from datetime import datetime, timezone
from typing import Any
import httpx
from fastapi import Request
from sqlalchemy.orm import Session
from app.config import settings
from app.middleware.audit_log import get_client_ip, get_username
from app.models import AuditLog
logger = logging.getLogger(__name__)
# ---------------------------------------------------------------------------
# Public helpers
# ---------------------------------------------------------------------------
def record_event(
db: Session,
*,
action: str,
user: str = "system",
resource_type: str | None = None,
resource_id: str | None = None,
ip_address: str | None = None,
details: dict[str, Any] | None = None,
severity: str = "info",
) -> AuditLog:
"""Persist an audit event and optionally forward it to SIEM.
Args:
db: Active SQLAlchemy session.
action: Short action identifier (e.g. ``"login"``, ``"document.create"``).
user: Username performing the action.
resource_type: Category of the affected resource (``"document"``, ``"user"`` …).
resource_id: Identifier of the affected resource.
ip_address: Client IP address (``None`` when not applicable).
details: Arbitrary key/value context serialised as JSON.
severity: One of ``info``, ``warning``, ``error``, ``critical``.
Returns:
The newly created :class:`AuditLog` row.
"""
details_json = json.dumps(details, default=str) if details else None
entry = AuditLog(
user=user,
action=action,
resource_type=resource_type,
resource_id=str(resource_id) if resource_id is not None else None,
ip_address=ip_address,
details=details_json,
severity=severity,
)
db.add(entry)
db.commit()
db.refresh(entry)
# Fire-and-forget SIEM forwarding in a background thread so we never
# block the request path.
if settings.audit_siem_enabled:
payload = _build_siem_payload(entry)
thread = threading.Thread(target=_forward_to_siem, args=(payload,), daemon=True)
thread.start()
return entry
def record_event_from_request(
db: Session,
request: Request,
*,
action: str,
resource_type: str | None = None,
resource_id: str | None = None,
details: dict[str, Any] | None = None,
severity: str = "info",
) -> AuditLog:
"""Convenience wrapper that extracts user and IP from a :class:`Request`.
Args:
db: Active SQLAlchemy session.
request: The current HTTP request.
action: Short action identifier.
resource_type: Category of the affected resource.
resource_id: Identifier of the affected resource.
details: Arbitrary key/value context serialised as JSON.
severity: One of ``info``, ``warning``, ``error``, ``critical``.
Returns:
The newly created :class:`AuditLog` row.
"""
return record_event(
db,
action=action,
user=get_username(request),
resource_type=resource_type,
resource_id=resource_id,
ip_address=get_client_ip(request),
details=details,
severity=severity,
)
def query_events(
db: Session,
*,
action: str | None = None,
user: str | None = None,
resource_type: str | None = None,
severity: str | None = None,
since: datetime | None = None,
until: datetime | None = None,
limit: int = 200,
offset: int = 0,
) -> list[AuditLog]:
"""Query audit log entries with optional filtering.
Args:
db: Active SQLAlchemy session.
action: Filter by action string (exact match).
user: Filter by username (exact match).
resource_type: Filter by resource type (exact match).
severity: Filter by severity level (exact match).
since: Only events at or after this timestamp.
until: Only events at or before this timestamp.
limit: Maximum number of rows to return.
offset: Number of rows to skip (for pagination).
Returns:
List of :class:`AuditLog` rows ordered by *timestamp descending*.
"""
q = db.query(AuditLog)
if action:
q = q.filter(AuditLog.action == action)
if user:
q = q.filter(AuditLog.user == user)
if resource_type:
q = q.filter(AuditLog.resource_type == resource_type)
if severity:
q = q.filter(AuditLog.severity == severity)
if since:
q = q.filter(AuditLog.timestamp >= since)
if until:
q = q.filter(AuditLog.timestamp <= until)
return q.order_by(AuditLog.timestamp.desc()).offset(offset).limit(limit).all()
def count_events(
db: Session,
*,
action: str | None = None,
user: str | None = None,
resource_type: str | None = None,
severity: str | None = None,
since: datetime | None = None,
until: datetime | None = None,
) -> int:
"""Return the total count of events matching the given filters.
Args:
db: Active SQLAlchemy session.
action: Filter by action string.
user: Filter by username.
resource_type: Filter by resource type.
severity: Filter by severity level.
since: Only events at or after this timestamp.
until: Only events at or before this timestamp.
Returns:
Integer count.
"""
q = db.query(AuditLog)
if action:
q = q.filter(AuditLog.action == action)
if user:
q = q.filter(AuditLog.user == user)
if resource_type:
q = q.filter(AuditLog.resource_type == resource_type)
if severity:
q = q.filter(AuditLog.severity == severity)
if since:
q = q.filter(AuditLog.timestamp >= since)
if until:
q = q.filter(AuditLog.timestamp <= until)
return q.count()
# ---------------------------------------------------------------------------
# SIEM forwarding internals
# ---------------------------------------------------------------------------
_SYSLOG_FACILITY_LOCAL0 = 16
_SYSLOG_SEVERITY_MAP = {
"info": 6,
"warning": 4,
"error": 3,
"critical": 2,
}
def _build_siem_payload(entry: AuditLog) -> dict[str, Any]:
"""Convert an :class:`AuditLog` row into a plain dict for SIEM delivery."""
ts = entry.timestamp if entry.timestamp else datetime.now(timezone.utc)
return {
"id": entry.id,
"timestamp": ts.isoformat(),
"user": entry.user,
"action": entry.action,
"resource_type": entry.resource_type,
"resource_id": entry.resource_id,
"ip_address": entry.ip_address,
"details": entry.details,
"severity": entry.severity,
"source": "docuelevate",
}
def _forward_to_siem(payload: dict[str, Any]) -> None:
"""Route a SIEM payload to the configured transport."""
transport = settings.audit_siem_transport.lower()
try:
if transport == "syslog":
_send_syslog(payload)
elif transport == "http":
_send_http(payload)
else:
logger.warning("Unknown SIEM transport %r; skipping forwarding", transport)
except Exception:
logger.exception("Failed to forward audit event to SIEM (%s)", transport)
def _send_syslog(payload: dict[str, Any]) -> None:
"""Send a RFC 5424 syslog message to the configured receiver."""
severity_num = _SYSLOG_SEVERITY_MAP.get(payload.get("severity", "info"), 6)
priority = _SYSLOG_FACILITY_LOCAL0 * 8 + severity_num
ts = payload.get("timestamp", datetime.now(timezone.utc).isoformat())
hostname = socket.gethostname()
app_name = "docuelevate"
msg_id = payload.get("action", "-")
# Structured data (SD) element with key event fields.
sd = (
f'[docuelevate@0 user="{payload.get("user", "-")}" '
f'action="{payload.get("action", "-")}" '
f'resource_type="{payload.get("resource_type", "-")}" '
f'resource_id="{payload.get("resource_id", "-")}" '
f'ip="{payload.get("ip_address", "-")}"]'
)
message = json.dumps(payload, default=str)
syslog_msg = f"<{priority}>1 {ts} {hostname} {app_name} - {msg_id} {sd} {message}"
proto = settings.audit_siem_syslog_protocol.lower()
host = settings.audit_siem_syslog_host
port = settings.audit_siem_syslog_port
if proto == "tcp":
with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as sock:
sock.settimeout(5)
sock.connect((host, port))
sock.sendall(syslog_msg.encode("utf-8"))
else:
with socket.socket(socket.AF_INET, socket.SOCK_DGRAM) as sock:
sock.settimeout(5)
sock.sendto(syslog_msg.encode("utf-8"), (host, port))
logger.debug("Syslog audit event sent to %s:%s (%s)", host, port, proto)
def _send_http(payload: dict[str, Any]) -> None:
"""POST a JSON audit event to the configured HTTP endpoint."""
url = settings.audit_siem_http_url
if not url:
logger.warning("SIEM HTTP URL not configured; skipping HTTP forwarding")
return
headers: dict[str, str] = {"Content-Type": "application/json"}
token = settings.audit_siem_http_token
if token:
headers["Authorization"] = f"Bearer {token}"
# Parse custom headers (comma-separated "Key:Value" pairs).
# Reject headers that could override security-critical ones already set,
# and validate that header names contain only RFC 7230 token characters.
_PROTECTED_HEADERS = {"authorization", "content-type", "host"}
_VALID_HEADER_NAME = re.compile(r"^[A-Za-z0-9!#$%&'*+\-.^_`|~]+$")
raw_custom = settings.audit_siem_http_custom_headers
if raw_custom:
for raw_pair in raw_custom.split(","):
pair = raw_pair.strip()
if ":" in pair:
k, _, v = pair.partition(":")
name = k.strip()
if not name or not _VALID_HEADER_NAME.match(name):
logger.warning("Skipping invalid SIEM custom header name: %r", name)
continue
if name.lower() in _PROTECTED_HEADERS:
logger.warning("Skipping protected SIEM custom header: %r", name)
continue
headers[name] = v.strip()
# Wrap in Splunk HEC-style envelope when URL contains ``/services/collector``.
body: dict[str, Any]
if "/services/collector" in url:
body = {"event": payload, "sourcetype": "docuelevate:audit", "source": "docuelevate"}
else:
body = payload
with httpx.Client(timeout=10) as client:
resp = client.post(url, json=body, headers=headers)
resp.raise_for_status()
logger.debug("HTTP audit event forwarded to %s (status %s)", url, resp.status_code)
+433
View File
@@ -0,0 +1,433 @@
"""Compliance service for managing GDPR, HIPAA, and SOC2 compliance templates.
Provides pre-built compliance configurations that can be applied with one click
to ensure the DocuElevate instance meets regulatory requirements.
"""
import json
import logging
from datetime import datetime, timezone
from typing import Any
from sqlalchemy.orm import Session
from app.models import ComplianceTemplate
logger = logging.getLogger(__name__)
# ---------------------------------------------------------------------------
# Pre-built compliance template definitions
# ---------------------------------------------------------------------------
COMPLIANCE_TEMPLATES: dict[str, dict[str, Any]] = {
"gdpr": {
"display_name": "GDPR (General Data Protection Regulation)",
"description": (
"European Union regulation for data protection and privacy. "
"Enforces data minimisation, encryption at rest, audit logging, "
"and limits PII exposure in telemetry."
),
"settings": {
"auth_enabled": "True",
"sentry_send_default_pii": "False",
"security_headers_enabled": "True",
"security_header_hsts_enabled": "True",
"security_header_csp_enabled": "True",
"security_header_x_frame_options_enabled": "True",
"enable_deduplication": "True",
},
"checks": [
{
"key": "auth_enabled",
"expected": "True",
"label": "Authentication enabled",
"description": "User authentication must be enabled to control access to personal data.",
},
{
"key": "sentry_send_default_pii",
"expected": "False",
"label": "PII excluded from telemetry",
"description": "Personally identifiable information must not be sent to external monitoring services.",
},
{
"key": "security_headers_enabled",
"expected": "True",
"label": "Security headers enabled",
"description": "HTTP security headers protect against common web vulnerabilities.",
},
{
"key": "security_header_hsts_enabled",
"expected": "True",
"label": "HSTS enabled",
"description": "HTTP Strict Transport Security ensures encrypted connections.",
},
{
"key": "security_header_csp_enabled",
"expected": "True",
"label": "Content Security Policy enabled",
"description": "CSP headers prevent cross-site scripting and data injection attacks.",
},
{
"key": "security_header_x_frame_options_enabled",
"expected": "True",
"label": "Clickjacking protection enabled",
"description": "X-Frame-Options header prevents clickjacking attacks.",
},
{
"key": "enable_deduplication",
"expected": "True",
"label": "Deduplication enabled",
"description": "Data minimisation: avoid storing duplicate documents.",
},
],
},
"hipaa": {
"display_name": "HIPAA (Health Insurance Portability and Accountability Act)",
"description": (
"United States regulation for protecting health information. "
"Requires strong access controls, audit trails, encryption, "
"and strict session management."
),
"settings": {
"auth_enabled": "True",
"multi_user_enabled": "True",
"sentry_send_default_pii": "False",
"security_headers_enabled": "True",
"security_header_hsts_enabled": "True",
"security_header_csp_enabled": "True",
"security_header_x_frame_options_enabled": "True",
"enable_deduplication": "True",
},
"checks": [
{
"key": "auth_enabled",
"expected": "True",
"label": "Authentication enabled",
"description": "Access controls are required to protect electronic Protected Health Information (ePHI).",
},
{
"key": "multi_user_enabled",
"expected": "True",
"label": "Multi-user mode enabled",
"description": "Individual user accounts required for access accountability.",
},
{
"key": "sentry_send_default_pii",
"expected": "False",
"label": "PII excluded from telemetry",
"description": "Protected Health Information must not be sent to external services.",
},
{
"key": "security_headers_enabled",
"expected": "True",
"label": "Security headers enabled",
"description": "Security headers protect ePHI during transmission.",
},
{
"key": "security_header_hsts_enabled",
"expected": "True",
"label": "HSTS enabled",
"description": "Encrypted transport required for all ePHI transmissions.",
},
{
"key": "security_header_csp_enabled",
"expected": "True",
"label": "Content Security Policy enabled",
"description": "CSP prevents injection attacks that could expose ePHI.",
},
{
"key": "security_header_x_frame_options_enabled",
"expected": "True",
"label": "Clickjacking protection enabled",
"description": "Prevents embedding the application in unauthorized frames.",
},
{
"key": "enable_deduplication",
"expected": "True",
"label": "Deduplication enabled",
"description": "Minimise data footprint for ePHI.",
},
],
},
"soc2": {
"display_name": "SOC 2 (Service Organization Control 2)",
"description": (
"Trust Service Criteria framework for service organisations. "
"Focuses on security, availability, processing integrity, "
"confidentiality, and privacy."
),
"settings": {
"auth_enabled": "True",
"multi_user_enabled": "True",
"sentry_send_default_pii": "False",
"security_headers_enabled": "True",
"security_header_hsts_enabled": "True",
"security_header_csp_enabled": "True",
"security_header_x_frame_options_enabled": "True",
"enable_deduplication": "True",
},
"checks": [
{
"key": "auth_enabled",
"expected": "True",
"label": "Authentication enabled",
"description": "Logical access controls required (CC6.1).",
},
{
"key": "multi_user_enabled",
"expected": "True",
"label": "Multi-user mode enabled",
"description": "Individual user accounts for access management (CC6.2).",
},
{
"key": "sentry_send_default_pii",
"expected": "False",
"label": "PII excluded from telemetry",
"description": "Confidential information must not leak to external services (CC6.7).",
},
{
"key": "security_headers_enabled",
"expected": "True",
"label": "Security headers enabled",
"description": "Protection against common web threats (CC6.6).",
},
{
"key": "security_header_hsts_enabled",
"expected": "True",
"label": "HSTS enabled",
"description": "Encrypted transport in transit (CC6.7).",
},
{
"key": "security_header_csp_enabled",
"expected": "True",
"label": "Content Security Policy enabled",
"description": "Application-level security controls (CC6.6).",
},
{
"key": "security_header_x_frame_options_enabled",
"expected": "True",
"label": "Clickjacking protection enabled",
"description": "UI redress attack prevention (CC6.6).",
},
{
"key": "enable_deduplication",
"expected": "True",
"label": "Deduplication enabled",
"description": "Data integrity through deduplication (PI1.1).",
},
],
},
}
def seed_compliance_templates(db: Session) -> None:
"""Create or update the built-in compliance template rows.
Called once at application startup to ensure the ``compliance_templates``
table always contains the latest definitions.
"""
for name, defn in COMPLIANCE_TEMPLATES.items():
existing = db.query(ComplianceTemplate).filter(ComplianceTemplate.name == name).first()
if existing is None:
template = ComplianceTemplate(
name=name,
display_name=defn["display_name"],
description=defn["description"],
settings_json=json.dumps(defn["settings"]),
enabled=False,
status="not_applied",
)
db.add(template)
logger.info(f"Seeded compliance template: {name}")
else:
# Update display_name and description if changed, but preserve user state
existing.display_name = defn["display_name"]
existing.description = defn["description"]
try:
db.commit()
except Exception:
db.rollback()
logger.exception("Failed to seed compliance templates")
def get_all_templates(db: Session) -> list[dict[str, Any]]:
"""Return all compliance templates with their current status."""
templates = db.query(ComplianceTemplate).order_by(ComplianceTemplate.name).all()
result = []
for t in templates:
defn = COMPLIANCE_TEMPLATES.get(t.name, {})
checks = defn.get("checks", [])
result.append(
{
"id": t.id,
"name": t.name,
"display_name": t.display_name,
"description": t.description,
"enabled": t.enabled,
"status": t.status,
"applied_at": t.applied_at.isoformat() if t.applied_at else None,
"applied_by": t.applied_by,
"settings": json.loads(t.settings_json) if t.settings_json else {},
"checks": checks,
"check_count": len(checks),
}
)
return result
def get_template_by_name(db: Session, name: str) -> ComplianceTemplate | None:
"""Retrieve a single compliance template by name."""
return db.query(ComplianceTemplate).filter(ComplianceTemplate.name == name).first()
def evaluate_template_status(db: Session, name: str) -> dict[str, Any]:
"""Evaluate the compliance status of a template against live settings.
Returns a dict with ``status``, ``total``, ``passed``, ``failed``, and
a list of individual ``check_results``.
"""
from app.config import settings as app_settings
from app.utils.settings_service import get_all_settings_from_db
defn = COMPLIANCE_TEMPLATES.get(name)
if defn is None:
return {"status": "unknown", "total": 0, "passed": 0, "failed": 0, "check_results": []}
db_settings = get_all_settings_from_db(db)
checks = defn.get("checks", [])
results: list[dict[str, Any]] = []
passed = 0
for check in checks:
key = check["key"]
expected = check["expected"]
# Resolve effective value: DB > config object
if key in db_settings and db_settings[key] is not None:
actual = str(db_settings[key])
else:
actual = str(getattr(app_settings, key, ""))
is_passing = actual.lower() == expected.lower()
if is_passing:
passed += 1
results.append(
{
"key": key,
"label": check["label"],
"description": check["description"],
"expected": expected,
"actual": actual,
"passing": is_passing,
}
)
total = len(checks)
if passed == total:
status = "compliant"
elif passed > 0:
status = "partial"
else:
status = "non_compliant"
return {
"status": status,
"total": total,
"passed": passed,
"failed": total - passed,
"check_results": results,
}
def apply_template(db: Session, name: str, applied_by: str = "admin") -> dict[str, Any]:
"""Apply a compliance template by writing its settings to the database.
Returns a summary of what was applied.
"""
from app.utils.settings_service import save_setting_to_db
defn = COMPLIANCE_TEMPLATES.get(name)
if defn is None:
return {"success": False, "error": f"Unknown template: {name}"}
template = get_template_by_name(db, name)
if template is None:
return {"success": False, "error": f"Template not found in database: {name}"}
applied_settings: dict[str, str] = {}
errors: list[str] = []
for key, value in defn["settings"].items():
try:
save_setting_to_db(db, key, value, changed_by=f"compliance:{name}")
applied_settings[key] = value
except Exception as e:
errors.append(f"{key}: {e}")
logger.error(f"Failed to apply compliance setting {key}={value}: {e}")
# Update the template record
now = datetime.now(timezone.utc)
template.enabled = True
template.settings_json = json.dumps(applied_settings)
template.applied_at = now
template.applied_by = applied_by
# Evaluate and store status
eval_result = evaluate_template_status(db, name)
template.status = eval_result["status"]
try:
db.commit()
except Exception:
db.rollback()
logger.exception(f"Failed to update compliance template record: {name}")
return {"success": False, "error": "Database commit failed"}
logger.info(f"Applied compliance template '{name}' by {applied_by}: {len(applied_settings)} settings written")
return {
"success": len(errors) == 0,
"template": name,
"applied_settings": applied_settings,
"errors": errors,
"status": eval_result,
}
def get_compliance_summary(db: Session) -> dict[str, Any]:
"""Return a high-level compliance dashboard summary across all templates."""
templates = db.query(ComplianceTemplate).order_by(ComplianceTemplate.name).all()
summary: list[dict[str, Any]] = []
total_checks = 0
total_passed = 0
for t in templates:
eval_result = evaluate_template_status(db, t.name)
total_checks += eval_result["total"]
total_passed += eval_result["passed"]
summary.append(
{
"name": t.name,
"display_name": t.display_name,
"enabled": t.enabled,
"status": eval_result["status"],
"total": eval_result["total"],
"passed": eval_result["passed"],
"failed": eval_result["failed"],
"applied_at": t.applied_at.isoformat() if t.applied_at else None,
"applied_by": t.applied_by,
}
)
overall = "compliant" if total_checks > 0 and total_passed == total_checks else "non_compliant"
if 0 < total_passed < total_checks:
overall = "partial"
return {
"overall_status": overall,
"total_checks": total_checks,
"total_passed": total_passed,
"total_failed": total_checks - total_passed,
"templates": summary,
}
+25 -10
View File
@@ -144,7 +144,7 @@ def get_provider_status() -> dict[str, dict[str, object]]:
and getattr(settings, "dropbox_app_secret", None)
and getattr(settings, "dropbox_refresh_token", None)
),
"enabled": True,
"enabled": getattr(settings, "dropbox_enabled", True),
"description": "Upload files to Dropbox cloud storage",
"details": {
"folder": getattr(settings, "dropbox_folder", "Not set"),
@@ -161,7 +161,7 @@ def get_provider_status() -> dict[str, dict[str, object]]:
"configured": bool(
getattr(settings, "dest_email_host", None) and getattr(settings, "dest_email_default_recipient", None)
),
"enabled": True,
"enabled": getattr(settings, "dest_email_enabled", True),
"description": "Send documents via email",
"details": {
"host": getattr(settings, "dest_email_host", "Not set"),
@@ -183,7 +183,7 @@ def get_provider_status() -> dict[str, dict[str, object]]:
and getattr(settings, "ftp_username", None)
and getattr(settings, "ftp_password", None)
),
"enabled": True,
"enabled": getattr(settings, "ftp_enabled", True),
"description": "Upload files to FTP server",
"details": {
"host": getattr(settings, "ftp_host", "Not set"),
@@ -214,7 +214,7 @@ def get_provider_status() -> dict[str, dict[str, object]]:
"name": "Google Drive",
"icon": "fa-brands fa-google-drive",
"configured": is_configured and bool(getattr(settings, "google_drive_folder_id", None)),
"enabled": True,
"enabled": getattr(settings, "google_drive_enabled", True),
"description": "Store documents in Google Drive",
"details": {
"auth_type": "OAuth" if use_oauth else "Service Account",
@@ -250,7 +250,7 @@ def get_provider_status() -> dict[str, dict[str, object]]:
and getattr(settings, "nextcloud_username", None)
and getattr(settings, "nextcloud_password", None)
),
"enabled": True,
"enabled": getattr(settings, "nextcloud_enabled", True),
"description": "Store documents in NextCloud",
"details": {
"url": getattr(settings, "nextcloud_upload_url", "Not set"),
@@ -270,7 +270,7 @@ def get_provider_status() -> dict[str, dict[str, object]]:
and getattr(settings, "onedrive_client_secret", None)
and getattr(settings, "onedrive_refresh_token", None)
),
"enabled": True,
"enabled": getattr(settings, "onedrive_enabled", True),
"description": "Store documents in Microsoft OneDrive",
"details": {
"client_id": getattr(settings, "onedrive_client_id", "Not set"),
@@ -288,7 +288,7 @@ def get_provider_status() -> dict[str, dict[str, object]]:
"configured": bool(
getattr(settings, "paperless_host", None) and getattr(settings, "paperless_ngx_api_token", None)
),
"enabled": True,
"enabled": getattr(settings, "paperless_enabled", True),
"description": "Document management system for digital archives",
"details": {
"host": getattr(settings, "paperless_host", "Not set"),
@@ -305,7 +305,7 @@ def get_provider_status() -> dict[str, dict[str, object]]:
and getattr(settings, "aws_access_key_id", None)
and getattr(settings, "aws_secret_access_key", None)
),
"enabled": True,
"enabled": getattr(settings, "s3_enabled", True),
"description": "Store documents in S3-compatible object storage",
"details": {
"bucket": getattr(settings, "s3_bucket_name", "Not set"),
@@ -327,7 +327,7 @@ def get_provider_status() -> dict[str, dict[str, object]]:
and getattr(settings, "sftp_username", None)
and (getattr(settings, "sftp_password", None) or getattr(settings, "sftp_private_key", None))
),
"enabled": True,
"enabled": getattr(settings, "sftp_enabled", True),
"description": "Upload files to SFTP server",
"details": {
"host": getattr(settings, "sftp_host", "Not set"),
@@ -362,7 +362,7 @@ def get_provider_status() -> dict[str, dict[str, object]]:
and getattr(settings, "webdav_username", None)
and getattr(settings, "webdav_password", None)
),
"enabled": True,
"enabled": getattr(settings, "webdav_enabled", True),
"description": "Store documents on WebDAV servers",
"details": {
"url": getattr(settings, "webdav_url", "Not set"),
@@ -373,4 +373,19 @@ def get_provider_status() -> dict[str, dict[str, object]]:
},
}
# Check iCloud Drive configuration
providers["iCloud Drive"] = {
"name": "iCloud Drive",
"icon": "fa-brands fa-apple",
"configured": bool(getattr(settings, "icloud_username", None) and getattr(settings, "icloud_password", None)),
"enabled": getattr(settings, "icloud_enabled", True),
"description": "Store documents in Apple iCloud Drive",
"details": {
"username": getattr(settings, "icloud_username", "Not set"),
"password": mask_sensitive_value(getattr(settings, "icloud_password", None)),
"folder": getattr(settings, "icloud_folder", "Not set"),
"cookie_directory": getattr(settings, "icloud_cookie_directory", "Not set"),
},
}
return providers
+32 -2
View File
@@ -59,13 +59,43 @@ def validate_auth_config() -> list[str]:
and getattr(settings, "authentik_config_url", None)
)
if not using_simple_auth and not using_oidc:
issues.append("Neither simple authentication nor OIDC are properly configured")
# Check if any social login provider is enabled
using_social_login = any(
getattr(settings, f"social_auth_{p}_enabled", False) for p in ("google", "microsoft", "apple", "dropbox")
)
if not using_simple_auth and not using_oidc and not using_social_login:
issues.append("Neither simple authentication, OIDC, nor social login are properly configured")
# If using OIDC, check for provider name
if using_oidc and not getattr(settings, "oauth_provider_name", None):
issues.append("OAUTH_PROVIDER_NAME is not configured but OIDC is enabled")
# Validate individual social login provider configs
if getattr(settings, "social_auth_google_enabled", False):
if not getattr(settings, "social_auth_google_client_id", None):
issues.append("SOCIAL_AUTH_GOOGLE_CLIENT_ID is required when Google login is enabled")
if not getattr(settings, "social_auth_google_client_secret", None):
issues.append("SOCIAL_AUTH_GOOGLE_CLIENT_SECRET is required when Google login is enabled")
if getattr(settings, "social_auth_microsoft_enabled", False):
if not getattr(settings, "social_auth_microsoft_client_id", None):
issues.append("SOCIAL_AUTH_MICROSOFT_CLIENT_ID is required when Microsoft login is enabled")
if not getattr(settings, "social_auth_microsoft_client_secret", None):
issues.append("SOCIAL_AUTH_MICROSOFT_CLIENT_SECRET is required when Microsoft login is enabled")
if getattr(settings, "social_auth_apple_enabled", False):
if not getattr(settings, "social_auth_apple_client_id", None):
issues.append("SOCIAL_AUTH_APPLE_CLIENT_ID is required when Apple login is enabled")
if not getattr(settings, "social_auth_apple_team_id", None):
issues.append("SOCIAL_AUTH_APPLE_TEAM_ID is required when Apple login is enabled")
if getattr(settings, "social_auth_dropbox_enabled", False):
if not getattr(settings, "social_auth_dropbox_client_id", None):
issues.append("SOCIAL_AUTH_DROPBOX_CLIENT_ID is required when Dropbox login is enabled")
if not getattr(settings, "social_auth_dropbox_client_secret", None):
issues.append("SOCIAL_AUTH_DROPBOX_CLIENT_SECRET is required when Dropbox login is enabled")
return issues
+2
View File
@@ -32,8 +32,10 @@ _TABLE_ORDER = [
"processing_logs",
"application_settings",
"settings_audit_log",
"audit_logs",
"saved_searches",
"webhook_configs",
"shared_links",
]
+542
View File
@@ -0,0 +1,542 @@
"""Internationalization (i18n) and localization (l10n) utilities.
Provides a JSON-based translation system for the DocuElevate UI with:
* **31 supported languages** covering all major European languages plus ZH
* Browser ``Accept-Language`` detection with cookie & user-profile persistence
* AI-powered fallback translation via the configured LLM provider
* Locale-aware date, number, and file-size formatting helpers
* Jinja2 integration via a ``_()`` global function
Language resolution order:
1. User profile ``preferred_language`` (persisted in DB)
2. ``docuelevate_lang`` cookie
3. ``Accept-Language`` HTTP header
4. Default (``en``)
"""
from __future__ import annotations
import json
import logging
from datetime import date, datetime
from functools import lru_cache
from pathlib import Path
from typing import Any
from starlette.requests import Request
logger = logging.getLogger(__name__)
# ---------------------------------------------------------------------------
# Supported languages (ordered by priority)
# ---------------------------------------------------------------------------
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": "🇵🇹"},
# --- Tier 2: Western & Northern European ---
{"code": "nl", "name": "Dutch", "native": "Nederlands", "flag": "🇳🇱"},
{"code": "nb", "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": "🏴"},
# --- 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": "🇱🇹"},
# --- Tier 4: Non-EU European & Other ---
{"code": "tr", "name": "Turkish", "native": "Türkçe", "flag": "🇹🇷"},
{"code": "uk", "name": "Ukrainian", "native": "Українська", "flag": "🇺🇦"},
{"code": "ru", "name": "Russian", "native": "Русский", "flag": "🇷🇺"},
{"code": "zh", "name": "Chinese", "native": "中文", "flag": "🇨🇳"},
]
SUPPORTED_LANGUAGE_CODES: set[str] = {lang["code"] for lang in SUPPORTED_LANGUAGES}
DEFAULT_LANGUAGE = "en"
# ---------------------------------------------------------------------------
# Translation file loading
# ---------------------------------------------------------------------------
_TRANSLATIONS_DIR = Path(__file__).resolve().parent.parent.parent / "frontend" / "translations"
_translation_cache: dict[str, dict[str, str]] = {}
def _load_translations(locale: str) -> dict[str, str]:
"""Load the translation JSON file for *locale*, with caching."""
if locale in _translation_cache:
return _translation_cache[locale]
filepath = _TRANSLATIONS_DIR / f"{locale}.json"
if not filepath.is_file():
logger.warning("Translation file not found for locale '%s'", locale)
_translation_cache[locale] = {}
return {}
try:
data: dict[str, str] = json.loads(filepath.read_text(encoding="utf-8"))
_translation_cache[locale] = data
return data
except (json.JSONDecodeError, OSError):
logger.exception("Failed to load translations for '%s'", locale)
_translation_cache[locale] = {}
return {}
def reload_translations() -> None:
"""Clear the translation cache so files are re-read on next access."""
_translation_cache.clear()
# ---------------------------------------------------------------------------
# Core translation function
# ---------------------------------------------------------------------------
def translate(key: str, locale: str | None = None, **kwargs: Any) -> str:
"""Return the translated string for *key* in *locale*.
Falls back through:
1. Requested *locale*
2. English (``en``)
3. The raw key itself (to keep the UI functional)
Positional placeholders ``{0}``, ``{1}`` or named placeholders
``{name}`` in the translated string are interpolated via *kwargs*.
"""
locale = locale if locale and locale in SUPPORTED_LANGUAGE_CODES else DEFAULT_LANGUAGE
translations = _load_translations(locale)
value = translations.get(key)
# Fallback to English
if value is None and locale != DEFAULT_LANGUAGE:
en_translations = _load_translations(DEFAULT_LANGUAGE)
value = en_translations.get(key)
# Fallback to key itself
if value is None:
value = key
if kwargs:
try:
value = value.format(**kwargs)
except (KeyError, IndexError):
pass # Return unformatted string rather than crash
return value
# ---------------------------------------------------------------------------
# AI fallback translation (best-effort, non-blocking)
# ---------------------------------------------------------------------------
_ai_translation_cache: dict[tuple[str, str], str] = {}
def translate_with_ai_fallback(text: str, target_locale: str) -> str:
"""Translate *text* using the configured AI provider as a fallback.
Returns the original *text* unchanged when:
* The target locale is English (source language)
* The AI provider is unavailable or returns an error
* The translation has already been cached
Results are cached in-memory for the lifetime of the process.
"""
if target_locale == DEFAULT_LANGUAGE or target_locale not in SUPPORTED_LANGUAGE_CODES:
return text
cache_key = (text, target_locale)
if cache_key in _ai_translation_cache:
return _ai_translation_cache[cache_key]
target_name = next(
(lang["name"] for lang in SUPPORTED_LANGUAGES if lang["code"] == target_locale),
target_locale,
)
try:
from litellm import completion # type: ignore[import-untyped]
from app.config import settings
model = getattr(settings, "ai_model", None) or getattr(settings, "openai_model", "gpt-4o-mini")
response = completion(
model=model,
messages=[
{
"role": "system",
"content": (
f"You are a professional translator. Translate the following UI text "
f"from English to {target_name}. Return ONLY the translated text, "
f"nothing else. Keep any HTML tags, placeholders like {{name}}, "
f"and special characters intact."
),
},
{"role": "user", "content": text},
],
max_tokens=256,
temperature=0.1,
)
translated = response.choices[0].message.content.strip()
_ai_translation_cache[cache_key] = translated
return translated
except Exception:
logger.debug("AI fallback translation failed for '%s'%s", text[:50], target_locale)
return text
# ---------------------------------------------------------------------------
# Language detection
# ---------------------------------------------------------------------------
def detect_language(request: Request) -> str:
"""Determine the preferred UI language from the request context.
Resolution order:
1. ``preferred_language`` stored in the user session
2. ``docuelevate_lang`` cookie
3. ``Accept-Language`` HTTP header (best match)
4. Default → ``en``
"""
# 1. User session preference
if hasattr(request, "session"):
session_lang = request.session.get("preferred_language")
if isinstance(session_lang, str) and session_lang in SUPPORTED_LANGUAGE_CODES:
return session_lang
# 2. Cookie
if hasattr(request, "cookies"):
cookie_lang = request.cookies.get("docuelevate_lang")
if isinstance(cookie_lang, str) and cookie_lang in SUPPORTED_LANGUAGE_CODES:
return cookie_lang
# 3. Accept-Language header
accept = ""
if hasattr(request, "headers"):
accept = request.headers.get("accept-language", "")
lang = _parse_accept_language(accept)
if lang:
return lang
return DEFAULT_LANGUAGE
def _parse_accept_language(header: str) -> str | None:
"""Extract the best matching language from an ``Accept-Language`` header.
Parses quality values and returns the highest-priority match among
:data:`SUPPORTED_LANGUAGE_CODES`, or ``None`` if nothing matches.
"""
if not header:
return None
entries: list[tuple[float, str]] = []
for raw_part in header.split(","):
part = raw_part.strip()
if not part:
continue
if ";q=" in part:
lang_tag, _, q_str = part.partition(";q=")
try:
quality = float(q_str.strip())
except ValueError:
quality = 0.0
else:
lang_tag = part
quality = 1.0
entries.append((quality, lang_tag.strip().lower()))
# Sort by quality descending
entries.sort(key=lambda e: e[0], reverse=True)
for _quality, tag in entries:
# Try exact match first (e.g., "de", "zh")
code = tag.split("-")[0]
if code in SUPPORTED_LANGUAGE_CODES:
return code
return None
# ---------------------------------------------------------------------------
# Localization helpers (l10n)
# ---------------------------------------------------------------------------
# Locale-specific formatting rules for date/number display
_LOCALE_FORMATS: dict[str, dict[str, Any]] = {
"en": {
"date": "%B %d, %Y",
"date_short": "%m/%d/%Y",
"datetime": "%B %d, %Y %I:%M %p",
"thousands_sep": ",",
"decimal_sep": ".",
},
"de": {
"date": "%d. %B %Y",
"date_short": "%d.%m.%Y",
"datetime": "%d. %B %Y %H:%M",
"thousands_sep": ".",
"decimal_sep": ",",
},
"fr": {
"date": "%d %B %Y",
"date_short": "%d/%m/%Y",
"datetime": "%d %B %Y %H:%M",
"thousands_sep": "\u202f",
"decimal_sep": ",",
},
"es": {
"date": "%d de %B de %Y",
"date_short": "%d/%m/%Y",
"datetime": "%d de %B de %Y %H:%M",
"thousands_sep": ".",
"decimal_sep": ",",
},
"it": {
"date": "%d %B %Y",
"date_short": "%d/%m/%Y",
"datetime": "%d %B %Y %H:%M",
"thousands_sep": ".",
"decimal_sep": ",",
},
"pt": {
"date": "%d de %B de %Y",
"date_short": "%d/%m/%Y",
"datetime": "%d de %B de %Y %H:%M",
"thousands_sep": ".",
"decimal_sep": ",",
},
"nl": {
"date": "%d %B %Y",
"date_short": "%d-%m-%Y",
"datetime": "%d %B %Y %H:%M",
"thousands_sep": ".",
"decimal_sep": ",",
},
"nb": {
"date": "%d. %B %Y",
"date_short": "%d.%m.%Y",
"datetime": "%d. %B %Y %H:%M",
"thousands_sep": "\u00a0",
"decimal_sep": ",",
},
"da": {
"date": "%d. %B %Y",
"date_short": "%d.%m.%Y",
"datetime": "%d. %B %Y %H:%M",
"thousands_sep": ".",
"decimal_sep": ",",
},
"sv": {
"date": "%d %B %Y",
"date_short": "%Y-%m-%d",
"datetime": "%d %B %Y %H:%M",
"thousands_sep": "\u00a0",
"decimal_sep": ",",
},
"fi": {
"date": "%d. %B %Y",
"date_short": "%d.%m.%Y",
"datetime": "%d. %B %Y %H:%M",
"thousands_sep": "\u00a0",
"decimal_sep": ",",
},
"is": {
"date": "%d. %B %Y",
"date_short": "%d.%m.%Y",
"datetime": "%d. %B %Y %H:%M",
"thousands_sep": ".",
"decimal_sep": ",",
},
"ga": {
"date": "%d %B %Y",
"date_short": "%d/%m/%Y",
"datetime": "%d %B %Y %H:%M",
"thousands_sep": ",",
"decimal_sep": ".",
},
"lb": {
"date": "%d. %B %Y",
"date_short": "%d.%m.%Y",
"datetime": "%d. %B %Y %H:%M",
"thousands_sep": ".",
"decimal_sep": ",",
},
"ca": {
"date": "%d de %B de %Y",
"date_short": "%d/%m/%Y",
"datetime": "%d de %B de %Y %H:%M",
"thousands_sep": ".",
"decimal_sep": ",",
},
"pl": {
"date": "%d %B %Y",
"date_short": "%d.%m.%Y",
"datetime": "%d %B %Y %H:%M",
"thousands_sep": "\u00a0",
"decimal_sep": ",",
},
"cs": {
"date": "%d. %B %Y",
"date_short": "%d.%m.%Y",
"datetime": "%d. %B %Y %H:%M",
"thousands_sep": "\u00a0",
"decimal_sep": ",",
},
"sk": {
"date": "%d. %B %Y",
"date_short": "%d.%m.%Y",
"datetime": "%d. %B %Y %H:%M",
"thousands_sep": "\u00a0",
"decimal_sep": ",",
},
"hu": {
"date": "%Y. %B %d.",
"date_short": "%Y.%m.%d.",
"datetime": "%Y. %B %d. %H:%M",
"thousands_sep": "\u00a0",
"decimal_sep": ",",
},
"sl": {
"date": "%d. %B %Y",
"date_short": "%d.%m.%Y",
"datetime": "%d. %B %Y %H:%M",
"thousands_sep": ".",
"decimal_sep": ",",
},
"hr": {
"date": "%d. %B %Y.",
"date_short": "%d.%m.%Y.",
"datetime": "%d. %B %Y. %H:%M",
"thousands_sep": ".",
"decimal_sep": ",",
},
"ro": {
"date": "%d %B %Y",
"date_short": "%d.%m.%Y",
"datetime": "%d %B %Y %H:%M",
"thousands_sep": ".",
"decimal_sep": ",",
},
"bg": {
"date": "%d %B %Y",
"date_short": "%d.%m.%Y",
"datetime": "%d %B %Y %H:%M",
"thousands_sep": "\u00a0",
"decimal_sep": ",",
},
"el": {
"date": "%d %B %Y",
"date_short": "%d/%m/%Y",
"datetime": "%d %B %Y %H:%M",
"thousands_sep": ".",
"decimal_sep": ",",
},
"et": {
"date": "%d. %B %Y",
"date_short": "%d.%m.%Y",
"datetime": "%d. %B %Y %H:%M",
"thousands_sep": "\u00a0",
"decimal_sep": ",",
},
"lv": {
"date": "%Y. gada %d. %B",
"date_short": "%d.%m.%Y.",
"datetime": "%Y. gada %d. %B %H:%M",
"thousands_sep": "\u00a0",
"decimal_sep": ",",
},
"lt": {
"date": "%Y m. %B %d d.",
"date_short": "%Y-%m-%d",
"datetime": "%Y m. %B %d d. %H:%M",
"thousands_sep": "\u00a0",
"decimal_sep": ",",
},
"tr": {
"date": "%d %B %Y",
"date_short": "%d.%m.%Y",
"datetime": "%d %B %Y %H:%M",
"thousands_sep": ".",
"decimal_sep": ",",
},
"uk": {
"date": "%d %B %Y",
"date_short": "%d.%m.%Y",
"datetime": "%d %B %Y %H:%M",
"thousands_sep": "\u00a0",
"decimal_sep": ",",
},
"zh": {
"date": "%Y年%m月%d",
"date_short": "%Y/%m/%d",
"datetime": "%Y年%m月%d%H:%M",
"thousands_sep": ",",
"decimal_sep": ".",
},
"ru": {
"date": "%d %B %Y",
"date_short": "%d.%m.%Y",
"datetime": "%d %B %Y %H:%M",
"thousands_sep": "\u00a0",
"decimal_sep": ",",
},
}
def format_date(value: date | datetime | None, locale: str = DEFAULT_LANGUAGE, short: bool = False) -> str:
"""Format a date/datetime value according to the locale conventions."""
if value is None:
return ""
fmt_key = "date_short" if short else "date"
fmt = _LOCALE_FORMATS.get(locale, _LOCALE_FORMATS[DEFAULT_LANGUAGE])[fmt_key]
return value.strftime(fmt)
def format_datetime(value: datetime | None, locale: str = DEFAULT_LANGUAGE) -> str:
"""Format a datetime value according to the locale conventions."""
if value is None:
return ""
fmt = _LOCALE_FORMATS.get(locale, _LOCALE_FORMATS[DEFAULT_LANGUAGE])["datetime"]
return value.strftime(fmt)
def format_number(value: int | float, locale: str = DEFAULT_LANGUAGE) -> str:
"""Format a number with locale-appropriate thousand separators."""
lf = _LOCALE_FORMATS.get(locale, _LOCALE_FORMATS[DEFAULT_LANGUAGE])
if isinstance(value, float):
int_part, _, dec_part = f"{value:,.2f}".partition(".")
formatted_int = int_part.replace(",", lf["thousands_sep"])
return f"{formatted_int}{lf['decimal_sep']}{dec_part}"
return f"{value:,}".replace(",", lf["thousands_sep"])
@lru_cache(maxsize=32)
def get_language_info(code: str) -> dict[str, str] | None:
"""Return the metadata dict for a supported language code, or ``None``."""
for lang in SUPPORTED_LANGUAGES:
if lang["code"] == code:
return lang
return None
+130
View File
@@ -0,0 +1,130 @@
"""Push notification sender for the DocuElevate mobile app.
Uses the **Expo Push Notification** service to deliver notifications to both
iOS (via APNs) and Android (via FCM) without requiring server-side APNs keys
or FCM credentials. The mobile app obtains an ``ExponentPushToken[…]`` at
startup and registers it with the backend via the mobile API.
Reference: https://docs.expo.dev/push-notifications/sending-notifications/
"""
import logging
from typing import Any
import httpx
from app.database import SessionLocal
from app.models import MobileDevice
logger = logging.getLogger(__name__)
EXPO_PUSH_URL = "https://exp.host/--/api/v2/push/send"
# Maximum tokens per batch request (Expo limit).
_EXPO_BATCH_LIMIT = 100
def send_expo_push_notification(
tokens: list[str],
title: str,
body: str,
data: dict[str, Any] | None = None,
sound: str = "default",
badge: int | None = None,
) -> list[dict[str, Any]]:
"""Send a push notification to one or more Expo push tokens.
Args:
tokens: List of Expo push tokens (``ExponentPushToken[…]``).
title: Notification title shown in the system tray.
body: Notification body text.
data: Optional JSON-serialisable dict attached to the notification
(available in the app via ``notification.request.content.data``).
sound: Notification sound. Use ``"default"`` or ``None`` for silent.
badge: iOS badge count. Pass ``0`` to clear.
Returns:
List of Expo push receipt dicts (one per token).
"""
if not tokens:
return []
results: list[dict[str, Any]] = []
# Send in batches to stay within Expo's per-request limit.
for i in range(0, len(tokens), _EXPO_BATCH_LIMIT):
batch = tokens[i : i + _EXPO_BATCH_LIMIT]
messages = []
for token in batch:
msg: dict[str, Any] = {
"to": token,
"title": title,
"body": body,
"sound": sound,
}
if data:
msg["data"] = data
if badge is not None:
msg["badge"] = badge
messages.append(msg)
try:
resp = httpx.post(
EXPO_PUSH_URL,
json=messages,
headers={
"Accept": "application/json",
"Accept-Encoding": "gzip, deflate",
"Content-Type": "application/json",
},
timeout=15,
)
resp.raise_for_status()
payload = resp.json()
batch_results = payload.get("data", [])
results.extend(batch_results)
logger.debug("Expo push batch sent: %d tokens, %d results", len(batch), len(batch_results))
except httpx.HTTPStatusError as exc:
logger.error("Expo push HTTP error: %s %s", exc.response.status_code, exc.response.text)
except Exception:
logger.exception("Expo push notification failed for batch starting at index %d", i)
return results
def send_push_to_owner(
owner_id: str,
title: str,
body: str,
data: dict[str, Any] | None = None,
) -> None:
"""Look up all active push tokens for *owner_id* and send them a notification.
This function is safe to call from Celery task workers. Database errors
and push failures are logged but never raised so that the caller task is
not retried due to a notification failure.
"""
db = SessionLocal()
try:
devices = (
db.query(MobileDevice)
.filter(
MobileDevice.owner_id == owner_id,
MobileDevice.is_active.is_(True),
MobileDevice.push_token.isnot(None),
)
.all()
)
tokens = [d.push_token for d in devices if d.push_token]
except Exception:
logger.exception("Failed to query mobile devices for owner_id=%s", owner_id)
return
finally:
db.close()
if not tokens:
logger.debug("No active push tokens for owner_id=%s", owner_id)
return
logger.info("Sending push notification to %d device(s) for owner_id=%s", len(tokens), owner_id)
send_expo_push_notification(tokens=tokens, title=title, body=body, data=data)
+364
View File
@@ -182,6 +182,153 @@ SETTING_METADATA = {
"required": False,
"restart_required": True,
},
# Social Login Providers
"social_auth_google_enabled": {
"category": "Social Login",
"description": (
"Enable Google Sign-In. Requires SOCIAL_AUTH_GOOGLE_CLIENT_ID and "
"SOCIAL_AUTH_GOOGLE_CLIENT_SECRET from the Google Cloud Console."
),
"type": "boolean",
"sensitive": False,
"required": False,
"restart_required": True,
"help_link": "https://console.cloud.google.com/apis/credentials",
"help_link_label": "Google Cloud Console",
},
"social_auth_google_client_id": {
"category": "Social Login",
"description": "Google OAuth2 client ID from the Google Cloud Console.",
"type": "string",
"sensitive": False,
"required": False,
"restart_required": True,
},
"social_auth_google_client_secret": {
"category": "Social Login",
"description": "Google OAuth2 client secret from the Google Cloud Console.",
"type": "string",
"sensitive": True,
"required": False,
"restart_required": True,
},
"social_auth_microsoft_enabled": {
"category": "Social Login",
"description": (
"Enable Microsoft Sign-In (Azure AD / Microsoft Entra ID). Requires "
"SOCIAL_AUTH_MICROSOFT_CLIENT_ID and SOCIAL_AUTH_MICROSOFT_CLIENT_SECRET "
"from Azure App Registrations."
),
"type": "boolean",
"sensitive": False,
"required": False,
"restart_required": True,
"help_link": "https://portal.azure.com/#blade/Microsoft_AAD_RegisteredApps/ApplicationsListBlade",
"help_link_label": "Azure Portal",
},
"social_auth_microsoft_client_id": {
"category": "Social Login",
"description": "Microsoft OAuth2 application (client) ID from Azure App Registrations.",
"type": "string",
"sensitive": False,
"required": False,
"restart_required": True,
},
"social_auth_microsoft_client_secret": {
"category": "Social Login",
"description": "Microsoft OAuth2 client secret from Azure App Registrations.",
"type": "string",
"sensitive": True,
"required": False,
"restart_required": True,
},
"social_auth_microsoft_tenant": {
"category": "Social Login",
"description": (
"Azure AD tenant ID or one of 'common', 'organizations', 'consumers'. "
"Use 'common' to allow any Microsoft account. Use a specific GUID to "
"restrict to a single organization."
),
"type": "string",
"sensitive": False,
"required": False,
"restart_required": True,
},
"social_auth_apple_enabled": {
"category": "Social Login",
"description": (
"Enable Sign in with Apple. Requires an Apple Developer account with "
"a Services ID configured for Sign in with Apple."
),
"type": "boolean",
"sensitive": False,
"required": False,
"restart_required": True,
"help_link": "https://developer.apple.com/account/resources/identifiers/list/serviceId",
"help_link_label": "Apple Developer Portal",
},
"social_auth_apple_client_id": {
"category": "Social Login",
"description": "Apple Services ID (e.g. com.example.docuelevate).",
"type": "string",
"sensitive": False,
"required": False,
"restart_required": True,
},
"social_auth_apple_team_id": {
"category": "Social Login",
"description": "Apple Developer Team ID (10-character alphanumeric string).",
"type": "string",
"sensitive": False,
"required": False,
"restart_required": True,
},
"social_auth_apple_key_id": {
"category": "Social Login",
"description": "Apple Sign-In private key ID from the Apple Developer Portal.",
"type": "string",
"sensitive": False,
"required": False,
"restart_required": True,
},
"social_auth_apple_private_key": {
"category": "Social Login",
"description": (
"Apple Sign-In private key (PEM format). Generate this in the Apple Developer Portal. "
"Paste the entire key content including BEGIN/END headers."
),
"type": "string",
"sensitive": True,
"required": False,
"restart_required": True,
},
"social_auth_dropbox_enabled": {
"category": "Social Login",
"description": (
"Enable Dropbox Sign-In. Uses the same Dropbox App you may already have "
"configured for storage, or a separate one."
),
"type": "boolean",
"sensitive": False,
"required": False,
"restart_required": True,
},
"social_auth_dropbox_client_id": {
"category": "Social Login",
"description": "Dropbox OAuth2 App Key from the Dropbox App Console.",
"type": "string",
"sensitive": False,
"required": False,
"restart_required": True,
},
"social_auth_dropbox_client_secret": {
"category": "Social Login",
"description": "Dropbox OAuth2 App Secret from the Dropbox App Console.",
"type": "string",
"sensitive": True,
"required": False,
"restart_required": True,
},
# AI Services
"openai_api_key": {
"category": "AI Services",
@@ -495,6 +642,14 @@ SETTING_METADATA = {
"options": ["us", "eu"],
},
# Storage Providers - Dropbox
"dropbox_enabled": {
"category": "Storage Providers",
"description": "Enable Dropbox as an upload destination. When disabled, no documents will be sent to Dropbox even if credentials are configured.",
"type": "boolean",
"sensitive": False,
"required": False,
"restart_required": False,
},
"dropbox_app_key": {
"category": "Storage Providers",
"description": "Dropbox app key for OAuth authentication",
@@ -528,6 +683,14 @@ SETTING_METADATA = {
"restart_required": False,
},
# Storage Providers - Nextcloud
"nextcloud_enabled": {
"category": "Storage Providers",
"description": "Enable Nextcloud as an upload destination. When disabled, no documents will be sent to Nextcloud even if credentials are configured.",
"type": "boolean",
"sensitive": False,
"required": False,
"restart_required": False,
},
"nextcloud_upload_url": {
"category": "Storage Providers",
"description": "Nextcloud WebDAV upload URL",
@@ -561,6 +724,14 @@ SETTING_METADATA = {
"restart_required": False,
},
# Storage Providers - Paperless-ngx
"paperless_enabled": {
"category": "Storage Providers",
"description": "Enable Paperless-ngx as an upload destination. When disabled, no documents will be sent to Paperless-ngx even if credentials are configured.",
"type": "boolean",
"sensitive": False,
"required": False,
"restart_required": False,
},
"paperless_ngx_api_token": {
"category": "Storage Providers",
"description": "Paperless-ngx API authentication token",
@@ -578,6 +749,14 @@ SETTING_METADATA = {
"restart_required": False,
},
# Storage Providers - Google Drive
"google_drive_enabled": {
"category": "Storage Providers",
"description": "Enable Google Drive as an upload destination. When disabled, no documents will be sent to Google Drive even if credentials are configured.",
"type": "boolean",
"sensitive": False,
"required": False,
"restart_required": False,
},
"google_drive_credentials_json": {
"category": "Storage Providers",
"description": "Google Drive service account credentials JSON",
@@ -635,6 +814,14 @@ SETTING_METADATA = {
"restart_required": False,
},
# Storage Providers - OneDrive
"onedrive_enabled": {
"category": "Storage Providers",
"description": "Enable OneDrive as an upload destination. When disabled, no documents will be sent to OneDrive even if credentials are configured.",
"type": "boolean",
"sensitive": False,
"required": False,
"restart_required": False,
},
"onedrive_client_id": {
"category": "Storage Providers",
"description": "OneDrive OAuth client ID",
@@ -676,6 +863,14 @@ SETTING_METADATA = {
"restart_required": False,
},
# Storage Providers - WebDAV
"webdav_enabled": {
"category": "Storage Providers",
"description": "Enable WebDAV as an upload destination. When disabled, no documents will be sent to WebDAV even if credentials are configured.",
"type": "boolean",
"sensitive": False,
"required": False,
"restart_required": False,
},
"webdav_url": {
"category": "Storage Providers",
"description": "WebDAV server URL",
@@ -717,6 +912,14 @@ SETTING_METADATA = {
"restart_required": False,
},
# Storage Providers - FTP
"ftp_enabled": {
"category": "Storage Providers",
"description": "Enable FTP as an upload destination. When disabled, no documents will be sent to FTP even if credentials are configured.",
"type": "boolean",
"sensitive": False,
"required": False,
"restart_required": False,
},
"ftp_host": {
"category": "Storage Providers",
"description": "FTP server hostname or IP address",
@@ -774,6 +977,14 @@ SETTING_METADATA = {
"restart_required": False,
},
# Storage Providers - SFTP
"sftp_enabled": {
"category": "Storage Providers",
"description": "Enable SFTP as an upload destination. When disabled, no documents will be sent to SFTP even if credentials are configured.",
"type": "boolean",
"sensitive": False,
"required": False,
"restart_required": False,
},
"sftp_host": {
"category": "Storage Providers",
"description": "SFTP server hostname or IP address",
@@ -838,7 +1049,56 @@ SETTING_METADATA = {
"required": False,
"restart_required": False,
},
# Storage Providers - iCloud Drive
"icloud_enabled": {
"category": "Storage Providers",
"description": "Enable iCloud Drive as an upload destination. When disabled, no documents will be sent to iCloud Drive even if credentials are configured.",
"type": "boolean",
"sensitive": False,
"required": False,
"restart_required": False,
},
"icloud_username": {
"category": "Storage Providers",
"description": "Apple ID email address for iCloud Drive authentication",
"type": "string",
"sensitive": False,
"required": False,
"restart_required": False,
},
"icloud_password": {
"category": "Storage Providers",
"description": "App-specific password for iCloud Drive (generate at https://appleid.apple.com)",
"type": "string",
"sensitive": True,
"required": False,
"restart_required": False,
},
"icloud_folder": {
"category": "Storage Providers",
"description": "Target folder path in iCloud Drive (e.g. Documents/Uploads)",
"type": "string",
"sensitive": False,
"required": False,
"restart_required": False,
},
"icloud_cookie_directory": {
"category": "Storage Providers",
"description": "Directory for persisting iCloud session cookies (default: ~/.pyicloud)",
"type": "string",
"sensitive": False,
"required": False,
"restart_required": False,
},
# Storage Providers - AWS S3
"s3_enabled": {
"category": "Storage Providers",
"description": "Enable Amazon S3 as an upload destination. When disabled, no documents will be sent to S3 even if credentials are configured.",
"type": "boolean",
"sensitive": False,
"required": False,
"restart_required": False,
},
"aws_access_key_id": {
"category": "Storage Providers",
"description": "AWS access key ID for S3",
@@ -972,6 +1232,14 @@ SETTING_METADATA = {
"restart_required": False,
},
# Email Destination Settings (dedicated SMTP for document delivery)
"dest_email_enabled": {
"category": "Email Destination",
"description": "Enable Email as an upload destination. When disabled, no documents will be delivered via email even if credentials are configured.",
"type": "boolean",
"sensitive": False,
"required": False,
"restart_required": False,
},
"dest_email_host": {
"category": "Email Destination",
"description": "SMTP server hostname for document delivery (separate from shared email settings)",
@@ -1392,6 +1660,18 @@ SETTING_METADATA = {
"required": False,
"restart_required": False,
},
"imap_attachment_filter": {
"category": "IMAP",
"description": (
"Controls which attachment types are ingested from IMAP emails. "
"Accepted values: 'documents_only' (PDFs and office files only, default) or 'all' (including images). "
"Per-user IMAP accounts can override this global default."
),
"type": "string",
"sensitive": False,
"required": False,
"restart_required": False,
},
# Monitoring - Uptime Kuma
"uptime_kuma_url": {
"category": "Monitoring",
@@ -1595,6 +1875,18 @@ SETTING_METADATA = {
"required": False,
"restart_required": False,
},
"compliance_enabled": {
"category": "Feature Flags",
"description": (
"Enable the compliance templates dashboard (GDPR, HIPAA, SOC 2). "
"When enabled, admins can view compliance status and apply "
"pre-built regulatory configurations. Default: True."
),
"type": "boolean",
"sensitive": False,
"required": False,
"restart_required": False,
},
# Backup / Restore
"backup_enabled": {
"category": "Backup",
@@ -2065,6 +2357,78 @@ SETTING_METADATA = {
"required": False,
"restart_required": True,
},
"audit_siem_enabled": {
"category": "Security",
"description": "Enable forwarding of audit events to an external SIEM system (Syslog, Splunk, Logstash, etc.).",
"type": "boolean",
"sensitive": False,
"required": False,
"restart_required": False,
},
"audit_siem_transport": {
"category": "Security",
"description": (
"Transport used to forward audit events. 'syslog' sends RFC 5424 messages over UDP/TCP. "
"'http' sends JSON POST payloads to a webhook URL (Splunk HEC, Logstash, Grafana Loki, etc.)."
),
"type": "string",
"sensitive": False,
"required": False,
"restart_required": False,
"options": ["syslog", "http"],
},
"audit_siem_syslog_host": {
"category": "Security",
"description": "Hostname or IP of the syslog receiver.",
"type": "string",
"sensitive": False,
"required": False,
"restart_required": False,
},
"audit_siem_syslog_port": {
"category": "Security",
"description": "Port of the syslog receiver. Default: 514.",
"type": "integer",
"sensitive": False,
"required": False,
"restart_required": False,
},
"audit_siem_syslog_protocol": {
"category": "Security",
"description": "Protocol for syslog transport: 'udp' or 'tcp'. Default: udp.",
"type": "string",
"sensitive": False,
"required": False,
"restart_required": False,
"options": ["udp", "tcp"],
},
"audit_siem_http_url": {
"category": "Security",
"description": (
"HTTP endpoint URL for SIEM webhook delivery. Supports Splunk HEC, "
"Logstash HTTP input, Grafana Loki push API, or any JSON-accepting endpoint."
),
"type": "string",
"sensitive": False,
"required": False,
"restart_required": False,
},
"audit_siem_http_token": {
"category": "Security",
"description": "Bearer / HEC token included in the Authorization header of SIEM HTTP requests.",
"type": "string",
"sensitive": True,
"required": False,
"restart_required": False,
},
"audit_siem_http_custom_headers": {
"category": "Security",
"description": "Comma-separated 'Key:Value' pairs of extra headers for SIEM HTTP requests.",
"type": "string",
"sensitive": False,
"required": False,
"restart_required": False,
},
# Rate Limiting
"rate_limiting_enabled": {
"category": "Security",
+13
View File
@@ -210,6 +210,19 @@ def dispatch_user_notification(
finally:
db.close()
# 3. Send push notifications to registered mobile devices
try:
from app.utils.push_notification import send_push_to_owner
send_push_to_owner(
owner_id=owner_id,
title=title,
body=message,
data={"event_type": event_type, "file_id": file_id},
)
except Exception:
logger.exception("Error sending push notification for owner_id=%s event=%s", owner_id, event_type)
def notify_user_document_processed(owner_id: str, filename: str, file_id: int | None = None) -> None:
"""Notify a user that their document was successfully processed."""
+6
View File
@@ -6,7 +6,9 @@ from fastapi import APIRouter
from app.views.admin_users import router as admin_users_router
from app.views.api_tokens import router as api_tokens_router
from app.views.audit_logs import router as audit_logs_router
from app.views.backup import router as backup_router
from app.views.compliance import router as compliance_router
from app.views.db_wizard import router as db_wizard_router
from app.views.dropbox import router as dropbox_router
from app.views.filemanager import router as filemanager_router
@@ -23,6 +25,7 @@ from app.views.onboarding import router as onboarding_router
from app.views.onedrive import router as onedrive_router
from app.views.pipelines import router as pipelines_router # Processing pipelines
from app.views.plans import router as plans_router # Admin Plan Designer
from app.views.profile import router as profile_router # User self-service profile
from app.views.queue import router as queue_router
from app.views.scheduled_jobs import router as scheduled_jobs_router # Scheduled batch jobs
from app.views.search import router as search_router
@@ -56,8 +59,11 @@ router.include_router(subscriptions_router) # Pricing + subscription pages
router.include_router(plans_router) # Admin Plan Designer
router.include_router(onboarding_router) # User onboarding wizard
router.include_router(pipelines_router) # Processing pipelines
router.include_router(profile_router) # User self-service profile settings
router.include_router(imap_accounts_router) # Per-user IMAP ingestion accounts
router.include_router(integrations_router) # Unified integrations dashboard
router.include_router(notifications_router) # User notification dashboard
router.include_router(scheduled_jobs_router) # Admin scheduled batch jobs
router.include_router(audit_logs_router) # Comprehensive audit log viewer
router.include_router(help_router) # Built-in help / How-To docs
router.include_router(compliance_router) # Compliance templates dashboard
+46
View File
@@ -0,0 +1,46 @@
"""
Audit log viewer UI admin-only page with filtering and SIEM status.
"""
import logging
from fastapi import Depends, HTTPException, Request, status
from sqlalchemy.orm import Session
from app.views.base import APIRouter, get_db, require_login, settings, templates
from app.views.settings import require_admin_access
logger = logging.getLogger(__name__)
router = APIRouter()
@router.get("/admin/audit-logs")
@require_login
@require_admin_access
async def audit_logs_page(request: Request, db: Session = Depends(get_db)):
"""Comprehensive audit log viewer with filtering controls.
Displays a chronological log of all significant actions: logins,
document operations, settings changes, and admin actions. The
actual data is fetched client-side via the ``/api/audit-logs`` JSON
endpoint so that filters, pagination, and live refresh work without
full-page reloads.
"""
try:
siem_enabled = settings.audit_siem_enabled
siem_transport = settings.audit_siem_transport if siem_enabled else None
return templates.TemplateResponse(
"audit_logs.html",
{
"request": request,
"app_version": settings.version,
"siem_enabled": siem_enabled,
"siem_transport": siem_transport,
},
)
except Exception as e:
logger.error("Error loading audit logs page: %s", e)
raise HTTPException(
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
detail="Failed to load audit logs page",
)
+44
View File
@@ -12,6 +12,14 @@ from sqlalchemy.orm import Session # noqa: F401
from app.auth import require_login # noqa: F401
from app.config import settings
from app.database import get_db # noqa: F401
from app.utils.i18n import (
SUPPORTED_LANGUAGES,
detect_language,
format_date,
format_datetime,
format_number,
translate,
)
# Set up Jinja2 templates
templates_dir = Path(__file__).parent.parent.parent / "frontend" / "templates"
@@ -21,6 +29,19 @@ templates = Jinja2Templates(directory=str(templates_dir))
templates.env.globals["min"] = min
templates.env.globals["max"] = max
# ---------------------------------------------------------------------------
# i18n Jinja2 integration
# ---------------------------------------------------------------------------
# The _() function is available in every template to translate UI strings.
# Usage: {{ _("nav.dashboard") }} or {{ _("upload.max_size", size="10 MB") }}
# The locale is automatically resolved from the request context.
# A default English implementation is registered as a global so error handlers
# that don't go through _inject_global_context still have the function available.
# ---------------------------------------------------------------------------
templates.env.globals["supported_languages"] = SUPPORTED_LANGUAGES
templates.env.globals["_"] = lambda key, **kwargs: translate(key, "en", **kwargs)
# Customize Jinja2Templates to include app_version in all templates
original_template_response = templates.TemplateResponse
@@ -48,8 +69,31 @@ def _inject_global_context(ctx: dict) -> None:
session_user = req.session.get("user")
# When auth is disabled every visitor is effectively "logged in"
ctx.setdefault("is_logged_in", not getattr(settings, "auth_enabled", True) or session_user is not None)
# --- i18n: detect language and register template helpers ---
current_locale = detect_language(req)
ctx.setdefault("current_locale", current_locale)
def _translate(key: str, **kwargs: object) -> str:
return translate(key, current_locale, **kwargs)
def _format_date(value: object, short: bool = False) -> str:
return format_date(value, current_locale, short=short) # type: ignore[arg-type]
def _format_datetime(value: object) -> str:
return format_datetime(value, current_locale) # type: ignore[arg-type]
def _format_number(value: object) -> str:
return format_number(value, current_locale) # type: ignore[arg-type]
ctx.setdefault("_", _translate)
ctx.setdefault("format_date_l10n", _format_date)
ctx.setdefault("format_datetime_l10n", _format_datetime)
ctx.setdefault("format_number_l10n", _format_number)
else:
ctx.setdefault("is_logged_in", not getattr(settings, "auth_enabled", True))
ctx.setdefault("current_locale", "en")
ctx.setdefault("_", lambda key, **kw: translate(key, "en", **kw))
def template_response_with_version(*args, **kwargs):
+48
View File
@@ -0,0 +1,48 @@
"""Admin view: compliance templates dashboard page."""
import logging
from fastapi import HTTPException, Request, status
from fastapi.responses import RedirectResponse
from app.views.base import APIRouter, require_login, settings, templates
logger = logging.getLogger(__name__)
router = APIRouter()
def _require_admin(request: Request):
"""Return the session user if they are an admin, else None."""
user = request.session.get("user")
if not user or not user.get("is_admin"):
logger.warning("Non-admin user attempted to access /admin/compliance")
return None
return user
@router.get("/admin/compliance")
@require_login
async def compliance_page(request: Request):
"""Admin compliance templates dashboard page.
Displays GDPR, HIPAA, and SOC2 compliance templates with their current
status and one-click apply functionality.
"""
user = _require_admin(request)
if user is None:
return RedirectResponse(url="/", status_code=status.HTTP_302_FOUND)
try:
return templates.TemplateResponse(
"compliance.html",
{
"request": request,
"app_version": settings.version,
},
)
except Exception as e:
logger.error(f"Error loading compliance page: {e}")
raise HTTPException(
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
detail="Failed to load compliance page",
)
+43 -1
View File
@@ -1,11 +1,13 @@
"""User-facing view for the per-user IMAP ingestion dashboard."""
import json
import logging
from fastapi import Request
from sqlalchemy.orm import Session
from app.models import UserImapAccount
from app.models import ImapIngestionProfile, UserImapAccount
from app.utils.allowed_types import DEFAULT_CATEGORIES, FILE_TYPE_CATEGORIES
from app.utils.subscription import get_tier, get_user_tier_id
from app.utils.user_scope import get_current_owner_id
from app.views.base import APIRouter, Depends, get_db, require_login, templates
@@ -25,6 +27,22 @@ def _get_max_mailboxes(tier: dict) -> int | None:
return max_mb
def _serialize_profile(profile: ImapIngestionProfile) -> dict:
"""Serialize a profile for JSON embedding in the template."""
try:
categories = json.loads(profile.allowed_categories)
except (ValueError, TypeError):
categories = []
return {
"id": profile.id,
"name": profile.name,
"description": profile.description,
"owner_id": profile.owner_id,
"allowed_categories": categories,
"is_builtin": profile.is_builtin,
}
@router.get("/imap-accounts")
@require_login
async def imap_accounts_page(request: Request, db: Session = Depends(get_db)):
@@ -49,11 +67,35 @@ async def imap_accounts_page(request: Request, db: Session = Depends(get_db)):
max_mailboxes = _get_max_mailboxes(tier)
can_add = max_mailboxes is None or (max_mailboxes > 0 and current_count < max_mailboxes)
# Load ingestion profiles: system-global + user's own
profiles = (
db.query(ImapIngestionProfile)
.filter(
# SQLAlchemy requires `== None` for IS NULL comparison in ORM filters
(ImapIngestionProfile.owner_id == None) | (ImapIngestionProfile.owner_id == owner_id) # noqa: E711
)
.order_by(ImapIngestionProfile.is_builtin.desc(), ImapIngestionProfile.id)
.all()
)
# Category definitions for the UI checkbox builder
categories = [
{
"key": key,
"label": info["label"],
"description": info["description"],
}
for key, info in FILE_TYPE_CATEGORIES.items()
]
return templates.TemplateResponse(
"imap_accounts.html",
{
"request": request,
"accounts": accounts,
"profiles": [_serialize_profile(p) for p in profiles],
"categories": categories,
"default_categories": DEFAULT_CATEGORIES,
"current_count": current_count,
"max_mailboxes": max_mailboxes,
"can_add": can_add,
+2
View File
@@ -27,6 +27,7 @@ _DESTINATION_META: list[dict] = [
{"id": "webdav", "name": "WebDAV", "icon": "fas fa-server"},
{"id": "sftp", "name": "SFTP", "icon": "fas fa-terminal"},
{"id": "ftp", "name": "FTP", "icon": "fas fa-server"},
{"id": "icloud", "name": "iCloud Drive", "icon": "fab fa-apple"},
]
@@ -51,6 +52,7 @@ def _get_configured_destinations(cfg: Settings) -> list[dict]:
"webdav": bool(cfg.webdav_url and cfg.webdav_username),
"sftp": bool(cfg.sftp_host and cfg.sftp_username),
"ftp": bool(cfg.ftp_host and cfg.ftp_username),
"icloud": bool(cfg.icloud_username and cfg.icloud_password),
}
return [meta for meta in _DESTINATION_META if checks.get(meta["id"], False)]
+1 -2
View File
@@ -3,12 +3,11 @@
from fastapi import Request
from fastapi.responses import HTMLResponse
from fastapi.routing import APIRouter
from fastapi.templating import Jinja2Templates
from app.auth import require_login
from app.views.base import templates
router = APIRouter()
templates = Jinja2Templates(directory="frontend/templates")
@router.get("/admin/plans", response_class=HTMLResponse)
+40
View File
@@ -0,0 +1,40 @@
"""View route for the user self-service profile settings page.
Route:
GET /profile renders the profile settings HTML page (requires login)
"""
from __future__ import annotations
import logging
from fastapi import Depends, Request
from sqlalchemy.orm import Session
from app.models import UserProfile
from app.utils.i18n import SUPPORTED_LANGUAGES
from app.views.base import APIRouter, get_db, require_login, templates
logger = logging.getLogger(__name__)
router = APIRouter()
@router.get("/profile", include_in_schema=False)
@require_login
async def profile_page(request: Request, db: Session = Depends(get_db)):
"""Serve the user profile settings page."""
user = request.session.get("user") or {}
user_id = user.get("sub") or user.get("preferred_username") or user.get("email") or user.get("id")
profile = None
if user_id:
profile = db.query(UserProfile).filter(UserProfile.user_id == user_id).first()
return templates.TemplateResponse(
"profile.html",
{
"request": request,
"profile": profile,
"supported_languages": SUPPORTED_LANGUAGES,
},
)