fix: resolve merge conflicts with main branch

Merge origin/main into feature branch, resolving 3 conflicts:
- app/api/__init__.py: add classification_rules_router alongside new
  routers from main (audit_logs, i18n, mobile, compliance, translation)
- app/models.py: keep ClassificationRuleModel alongside new models from
  main (MobileDevice, ComplianceTemplate, PipelineRoutingRule)
- tests/conftest.py: import both ClassificationRuleModel and new models
  from main (AuditLog, ComplianceTemplate)

Also renumber migration from 027 to 037 to chain from the latest
migration on main (036_add_document_translation_fields).

Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
This commit is contained in:
copilot-swe-agent[bot]
2026-03-16 22:33:59 +00:00
parent 23498e0a98
commit 651b48658c
318 changed files with 317516 additions and 2858 deletions
+16
View File
@@ -8,19 +8,24 @@ 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.classification_rules import router as classification_rules_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
@@ -28,7 +33,9 @@ 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
from app.api.scheduled_jobs import router as scheduled_jobs_router
from app.api.search import router as search_router
@@ -37,6 +44,7 @@ from app.api.shared_links import public_router as shared_links_public_router
from app.api.shared_links import router as shared_links_router
from app.api.similarity import router as similarity_router
from app.api.subscriptions import router as subscriptions_router
from app.api.translation import router as translation_router
from app.api.url_upload import router as url_upload_router
# Import all the individual routers
@@ -79,8 +87,16 @@ 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)
router.include_router(translation_router)
router.include_router(classification_rules_router)
+117
View File
@@ -0,0 +1,117 @@
"""
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 Annotated, 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()
DbSession = Annotated[Session, Depends(get_db)]
@router.get("/audit-logs")
@require_login
async def list_audit_logs(
request: Request,
db: DbSession,
action: Annotated[str | None, Query(description="Filter by action (exact match)")] = None,
user: Annotated[str | None, Query(description="Filter by username")] = None,
resource_type: Annotated[str | None, Query(description="Filter by resource type")] = None,
severity: Annotated[str | None, Query(description="Filter by severity level")] = None,
since: Annotated[datetime | None, Query(description="Only events at or after this ISO-8601 timestamp")] = None,
until: Annotated[datetime | None, Query(description="Only events at or before this ISO-8601 timestamp")] = None,
limit: Annotated[int, Query(ge=1, le=500, description="Max rows to return")] = 50,
offset: Annotated[int, Query(ge=0, description="Rows to skip for pagination")] = 0,
) -> 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: DbSession,
) -> 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: DbSession,
) -> 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,
}
+4 -3
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:
@@ -166,9 +168,8 @@ async def create_checkout_session(
checkout_session = client.checkout.sessions.create(params=session_params)
logger.info(
"Created Stripe checkout session %s for user %s plan %s",
"Created Stripe checkout session %s for plan %s",
checkout_session.id,
owner_id,
body.plan_id,
)
return {"checkout_url": checkout_session.url, "session_id": checkout_session.id}
@@ -211,7 +212,7 @@ async def create_portal_session(
}
)
logger.info("Created Stripe portal session for user %s", owner_id)
logger.info("Created Stripe portal session for user")
return {"portal_url": portal.url}
+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)
+49 -46
View File
@@ -6,7 +6,7 @@ import logging
import os
from typing import Annotated, Optional
import requests
import httpx
from fastapi import APIRouter, Depends, Form, HTTPException, Request, status
from sqlalchemy.orm import Session
@@ -132,57 +132,60 @@ async def test_dropbox_token(request: Request):
"message": "Dropbox credentials are not fully configured",
}
# Check token validity by getting current account info
headers = {"Authorization": f"Bearer {settings.dropbox_refresh_token}"}
response = requests.post(
"https://api.dropboxapi.com/2/users/get_current_account",
headers=headers,
timeout=settings.http_request_timeout,
)
# If token is invalid, try refreshing it
if response.status_code == 401:
logger.info("Dropbox access token invalid or expired, trying to refresh")
# Get a new access token using the refresh token
refresh_url = "https://api.dropbox.com/oauth2/token"
refresh_data = {
"grant_type": "refresh_token",
"refresh_token": settings.dropbox_refresh_token,
"client_id": settings.dropbox_app_key,
"client_secret": settings.dropbox_app_secret,
}
refresh_response = requests.post(refresh_url, data=refresh_data, timeout=settings.http_request_timeout)
if refresh_response.status_code != 200:
logger.error(f"Failed to refresh Dropbox token: {refresh_response.text}")
return {
"status": "error",
"message": "Refresh token has expired or is invalid",
"needs_reauth": True,
}
token_info = refresh_response.json()
access_token = token_info.get("access_token")
# Try again with the new access token
headers = {"Authorization": f"Bearer {access_token}"}
response = requests.post(
async with httpx.AsyncClient() as client:
# Check token validity by getting current account info
headers = {"Authorization": f"Bearer {settings.dropbox_refresh_token}"}
response = await client.post(
"https://api.dropboxapi.com/2/users/get_current_account",
headers=headers,
timeout=settings.http_request_timeout,
)
if response.status_code != 200:
logger.error(f"Dropbox token test failed: {response.status_code} {response.text}")
return {
"status": "error",
"message": f"Token validation failed with status {response.status_code}: {response.text}",
}
# If token is invalid, try refreshing it
if response.status_code == 401:
logger.info("Dropbox access token invalid or expired, trying to refresh")
# Get account info
account_info = response.json()
# Get a new access token using the refresh token
refresh_url = "https://api.dropbox.com/oauth2/token"
refresh_data = {
"grant_type": "refresh_token",
"refresh_token": settings.dropbox_refresh_token,
"client_id": settings.dropbox_app_key,
"client_secret": settings.dropbox_app_secret,
}
refresh_response = await client.post(
refresh_url, data=refresh_data, timeout=settings.http_request_timeout
)
if refresh_response.status_code != 200:
logger.error(f"Failed to refresh Dropbox token: {refresh_response.text}")
return {
"status": "error",
"message": "Refresh token has expired or is invalid",
"needs_reauth": True,
}
token_info = refresh_response.json()
access_token = token_info.get("access_token")
# Try again with the new access token
headers = {"Authorization": f"Bearer {access_token}"}
response = await client.post(
"https://api.dropboxapi.com/2/users/get_current_account",
headers=headers,
timeout=settings.http_request_timeout,
)
if response.status_code != 200:
logger.error(f"Dropbox token test failed: {response.status_code} {response.text}")
return {
"status": "error",
"message": f"Token validation failed with status {response.status_code}: {response.text}",
}
# Get account info
account_info = response.json()
account_email = account_info.get("email", "Unknown account")
account_name = account_info.get("name", {}).get("display_name", "Unknown user")
+28 -23
View File
@@ -73,33 +73,38 @@ def list_duplicate_groups(
groups = []
total_duplicate_files = 0
for filehash in dup_hashes:
# Find the original (non-duplicate) record with this hash
original = (
db.query(FileRecord)
.filter(FileRecord.filehash == filehash, FileRecord.is_duplicate.is_(False))
.order_by(FileRecord.id.asc())
.first()
if dup_hashes:
# Fetch all matching files (both original and duplicates) in a single batch query
all_records = (
db.query(FileRecord).filter(FileRecord.filehash.in_(dup_hashes)).order_by(FileRecord.id.asc()).all()
)
# Find all duplicate records for this hash
duplicates = (
db.query(FileRecord)
.filter(FileRecord.filehash == filehash, FileRecord.is_duplicate.is_(True))
.order_by(FileRecord.id.asc())
.all()
)
# Group records by hash
originals_by_hash = {}
duplicates_by_hash = {h: [] for h in dup_hashes}
total_duplicate_files += len(duplicates)
for record in all_records:
h = record.filehash
if not record.is_duplicate:
# Store only the first original record per hash, matching the old .first() behaviour
if h not in originals_by_hash:
originals_by_hash[h] = record
else:
duplicates_by_hash[h].append(record)
total_duplicate_files += 1
groups.append(
{
"filehash": filehash,
"original": _file_record_to_dict(original) if original else None,
"duplicates": [_file_record_to_dict(d) for d in duplicates],
"duplicate_count": len(duplicates),
}
)
for filehash in dup_hashes:
original = originals_by_hash.get(filehash)
duplicates = duplicates_by_hash.get(filehash, [])
groups.append(
{
"filehash": filehash,
"original": _file_record_to_dict(original) if original else None,
"duplicates": [_file_record_to_dict(d) for d in duplicates],
"duplicate_count": len(duplicates),
}
)
total_pages = (total_groups + per_page - 1) // per_page if total_groups > 0 else 1
+68 -30
View File
@@ -11,6 +11,7 @@ import zipfile
from datetime import datetime, timezone
from typing import Annotated, List, Optional
import aiofiles
from fastapi import APIRouter, Depends, File, HTTPException, Query, Request, UploadFile, status
from fastapi.responses import StreamingResponse
from sqlalchemy import asc, desc
@@ -1217,6 +1218,66 @@ def download_file(
raise HTTPException(status_code=500, detail=f"Error downloading file: {str(e)}")
async def _save_upload_file_chunks(file: UploadFile, target_path: str, max_size: int) -> int:
"""Save an uploaded file in chunks and enforce the maximum size limit."""
try:
written_size = 0
with open(target_path, "wb") as f:
chunk_size = 65536 # 64 KB chunks
while True:
chunk = await file.read(chunk_size)
if not chunk:
break
written_size += len(chunk)
if written_size > max_size:
# Exceeded limit mid-stream; clean up and reject
f.close()
os.remove(target_path)
raise HTTPException(
status_code=413,
detail=f"File too large: exceeded {max_size} bytes during upload. "
f"See SECURITY_AUDIT.md for configuration details.",
)
f.write(chunk)
return written_size
except HTTPException:
raise
except Exception as e:
if os.path.exists(target_path):
os.remove(target_path)
raise HTTPException(status_code=500, detail=f"Failed to save file: {e}")
def _check_for_exact_duplicate(db: DbSession, target_path: str, safe_filename: str) -> dict | None:
"""Check for an exact duplicate of the uploaded file and return a warning if found."""
if not settings.enable_deduplication:
return None
try:
filehash = hash_file(target_path)
existing = (
db.query(FileRecord)
.filter(FileRecord.filehash == filehash, FileRecord.is_duplicate.is_(False))
.order_by(FileRecord.id.asc())
.first()
)
if existing:
logger.info(f"Exact duplicate detected on upload: '{safe_filename}' matches file ID {existing.id}")
return {
"duplicate_type": "exact",
"original_file_id": existing.id,
"original_filename": existing.original_filename,
"message": (
"This file appears to be an exact duplicate of an already-processed document. "
"It will still be queued but will be flagged as a duplicate."
),
}
except Exception as e:
logger.warning(f"Duplicate check failed for uploaded file '{safe_filename}': {e}")
return None
@router.post("/ui-upload")
@require_login
async def ui_upload(request: Request, db: DbSession, file: UploadFile = File(...)):
@@ -1277,7 +1338,7 @@ async def ui_upload(request: Request, db: DbSession, file: UploadFile = File(...
# enforcing the size limit during the read so memory usage stays bounded.
try:
written_size = 0
with open(target_path, "wb") as f:
async with aiofiles.open(target_path, "wb") as f:
chunk_size = 65536 # 64 KB chunks
while True:
chunk = await file.read(chunk_size)
@@ -1286,14 +1347,14 @@ async def ui_upload(request: Request, db: DbSession, file: UploadFile = File(...
written_size += len(chunk)
if written_size > max_size:
# Exceeded limit mid-stream; clean up and reject
f.close()
await f.close()
os.remove(target_path)
raise HTTPException(
status_code=413,
detail=f"File too large: exceeded {max_size} bytes during upload. "
f"See SECURITY_AUDIT.md for configuration details.",
)
f.write(chunk)
await f.write(chunk)
except HTTPException:
raise
except Exception as e:
@@ -1384,29 +1445,7 @@ async def ui_upload(request: Request, db: DbSession, file: UploadFile = File(...
# Check for exact duplicates (same SHA-256 hash) before returning.
# This gives the caller an immediate warning without waiting for the pipeline.
# Only performed when deduplication is enabled in settings.
exact_duplicate_warning = None
if settings.enable_deduplication:
try:
filehash = hash_file(target_path)
existing = (
db.query(FileRecord)
.filter(FileRecord.filehash == filehash, FileRecord.is_duplicate.is_(False))
.order_by(FileRecord.id.asc())
.first()
)
if existing:
exact_duplicate_warning = {
"duplicate_type": "exact",
"original_file_id": existing.id,
"original_filename": existing.original_filename,
"message": (
"This file appears to be an exact duplicate of an already-processed document. "
"It will still be queued but will be flagged as a duplicate."
),
}
logger.info(f"Exact duplicate detected on upload: '{safe_filename}' matches file ID {existing.id}")
except Exception as e:
logger.warning(f"Duplicate check failed for uploaded file '{safe_filename}': {e}")
exact_duplicate_warning = _check_for_exact_duplicate(db, target_path, safe_filename)
response: dict = {
"task_id": task.id,
@@ -1458,7 +1497,7 @@ def claim_file(request: Request, file_id: int, db: DbSession):
logger.exception(f"Error claiming file {file_id}: {e}")
raise HTTPException(status_code=500, detail="Failed to claim document")
logger.info(f"File {file_id} claimed by user '{owner_id}'")
logger.info("File %d claimed by user", file_id)
return {"status": "success", "message": "Document claimed successfully", "file_id": file_id, "owner_id": owner_id}
@@ -1498,7 +1537,7 @@ def bulk_claim_files(request: Request, file_ids: list[int], db: DbSession):
logger.exception(f"Error during bulk claim: {e}")
raise HTTPException(status_code=500, detail="Failed to claim documents")
logger.info(f"Bulk claim by '{owner_id}': claimed={claimed}, skipped={[s['file_id'] for s in skipped]}")
logger.info("Bulk claim: claimed=%s, skipped=%s", claimed, [s["file_id"] for s in skipped])
return {
"status": "success",
"claimed_count": len(claimed),
@@ -1551,8 +1590,7 @@ def assign_owner(request: Request, db: DbSession, owner_id: str = Query(...), fi
logger.exception(f"Error assigning owner: {e}")
raise HTTPException(status_code=500, detail="Failed to assign owner")
admin_name = get_current_owner_id(request) or "admin"
logger.info(f"Admin '{admin_name}' assigned owner_id='{owner_id}' to {updated} file(s)")
logger.info("Admin assigned owner to %d file(s)", updated)
return {
"status": "success",
"message": f"Assigned owner to {updated} document(s)",
+1 -1
View File
@@ -363,7 +363,7 @@ def format_time_remaining(time_delta):
@router.post("/google-drive/save-settings")
@require_login
async def save_dropbox_settings(
async def save_google_drive_settings(
request: Request,
refresh_token: Annotated[str, Form(...)],
client_id: Annotated[Optional[str], Form()] = None,
+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)
+4 -9
View File
@@ -564,7 +564,6 @@ def _test_webdav_connection(config: dict[str, Any] | None, credentials: dict[str
return {"success": False, "message": "Missing required field: url"}
# Only allow http/https to prevent file:// or other custom scheme attacks
import ipaddress
from urllib.parse import urlparse
parsed = urlparse(url)
@@ -574,14 +573,10 @@ def _test_webdav_connection(config: dict[str, Any] | None, credentials: dict[str
# Block requests to private/internal IPs to prevent SSRF
hostname = parsed.hostname or ""
if hostname:
try:
addr = ipaddress.ip_address(hostname)
if addr.is_private or addr.is_loopback or addr.is_link_local:
return {"success": False, "message": "URLs pointing to internal or private networks are not allowed"}
except ValueError:
# Hostname is not an IP literal — allow DNS names through
if hostname in ("localhost", "localhost.localdomain"):
return {"success": False, "message": "URLs pointing to localhost are not allowed"}
from app.utils.network import is_private_ip
if is_private_ip(hostname):
return {"success": False, "message": "URLs pointing to internal or private networks are not allowed"}
try:
import base64
+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,
}
+9 -10
View File
@@ -452,17 +452,16 @@ async def update_preferences(
)
try:
# Pre-fetch existing preferences for this user to avoid N+1 queries
existing_prefs = (
db.query(UserNotificationPreference).filter(UserNotificationPreference.owner_id == owner_id).all()
)
# Build a fast lookup dictionary keyed by (event_type, channel_type, target_id)
prefs_dict = {(pref.event_type, pref.channel_type, pref.target_id): pref for pref in existing_prefs}
for item in body.preferences:
existing = (
db.query(UserNotificationPreference)
.filter(
UserNotificationPreference.owner_id == owner_id,
UserNotificationPreference.event_type == item.event_type,
UserNotificationPreference.channel_type == item.channel_type,
UserNotificationPreference.target_id == item.target_id,
)
.first()
)
existing = prefs_dict.get((item.event_type, item.channel_type, item.target_id))
if existing:
existing.is_enabled = item.is_enabled
else:
+40 -112
View File
@@ -3,17 +3,17 @@ OneDrive API endpoints
"""
import logging
import os
from datetime import datetime, timedelta
from typing import Annotated, Optional
import requests
import httpx
from fastapi import APIRouter, Depends, Form, HTTPException, Request, status
from sqlalchemy.orm import Session
from app.auth import require_login
from app.config import settings
from app.database import get_db
from app.utils.env_utils import update_env_file
from app.utils.oauth_helper import exchange_oauth_token
from app.utils.settings_service import save_setting_to_db
from app.utils.settings_sync import notify_settings_updated
@@ -92,17 +92,18 @@ async def test_onedrive_token(request: Request):
"scope": "offline_access Files.ReadWrite",
}
response = requests.post(token_url, data=refresh_data, timeout=settings.http_request_timeout)
async with httpx.AsyncClient(timeout=settings.http_request_timeout) as client:
response = await client.post(token_url, data=refresh_data)
if response.status_code != 200:
logger.error(f"Failed to refresh OneDrive token: {response.text}")
return {
"status": "error",
"message": "Refresh token has expired or is invalid",
"needs_reauth": True,
}
if response.status_code != 200:
logger.error(f"Failed to refresh OneDrive token: {response.text}")
return {
"status": "error",
"message": "Refresh token has expired or is invalid",
"needs_reauth": True,
}
token_data = response.json()
token_data = response.json()
access_token = token_data.get("access_token")
expires_in = token_data.get("expires_in", 3600) # Default to 1 hour if not specified
@@ -115,32 +116,7 @@ async def test_onedrive_token(request: Request):
settings.onedrive_refresh_token = new_refresh_token
# Also try to update .env file if it exists
try:
env_path = os.path.join(os.path.dirname(os.path.dirname(os.path.dirname(__file__))), ".env")
if os.path.exists(env_path):
with open(env_path, "r") as f:
env_lines = f.readlines()
updated_lines = []
updated = False
for line in env_lines:
if line.startswith("ONEDRIVE_REFRESH_TOKEN="):
updated_lines.append(f"ONEDRIVE_REFRESH_TOKEN={new_refresh_token}\n")
updated = True
else:
updated_lines.append(line)
if not updated:
updated_lines.append(f"ONEDRIVE_REFRESH_TOKEN={new_refresh_token}\n")
with open(env_path, "w") as f:
f.writelines(updated_lines)
logger.info("Updated refresh token in .env file")
except Exception as e:
logger.warning(f"Failed to update refresh token in .env file: {e}")
update_env_file({"ONEDRIVE_REFRESH_TOKEN": new_refresh_token})
# Persist the rotated refresh token to the database
try:
@@ -164,17 +140,18 @@ async def test_onedrive_token(request: Request):
user_info_url = "https://graph.microsoft.com/v1.0/me"
headers = {"Authorization": f"Bearer {access_token}"}
user_response = requests.get(user_info_url, headers=headers, timeout=settings.http_request_timeout)
async with httpx.AsyncClient(timeout=settings.http_request_timeout) as client:
user_response = await client.get(user_info_url, headers=headers)
if user_response.status_code != 200:
logger.error(f"OneDrive token test failed: {user_response.status_code} {user_response.text}")
return {
"status": "error",
"message": f"Token validation failed with status {user_response.status_code}: {user_response.text}",
}
if user_response.status_code != 200:
logger.error(f"OneDrive token test failed: {user_response.status_code} {user_response.text}")
return {
"status": "error",
"message": f"Token validation failed with status {user_response.status_code}: {user_response.text}",
}
# Get user info
user_info = user_response.json()
# Get user info
user_info = user_response.json()
display_name = user_info.get("displayName", "Unknown user")
email = user_info.get("userPrincipalName", "Unknown email")
@@ -246,75 +223,26 @@ async def save_onedrive_settings(
user.get("preferred_username") or user.get("username") or user.get("email") or user.get("id") or "wizard"
)
# Best-effort .env file write
try:
env_path = os.path.join(os.path.dirname(os.path.dirname(os.path.dirname(__file__))), ".env")
if not os.path.exists(env_path):
logger.warning(f".env file not found at {env_path}, skipping file write")
else:
logger.info(f"Updating OneDrive settings in {env_path}")
# Build settings dictionary mapped to database/memory keys
onedrive_settings = {
"onedrive_refresh_token": refresh_token,
"onedrive_client_id": client_id,
"onedrive_client_secret": client_secret,
"onedrive_tenant_id": tenant_id,
"onedrive_folder_path": folder_path,
}
with open(env_path, "r") as f:
env_lines = f.readlines()
# Filter out None values
onedrive_settings = {k: v for k, v in onedrive_settings.items() if v is not None}
onedrive_settings = {"ONEDRIVE_REFRESH_TOKEN": refresh_token}
if client_id:
onedrive_settings["ONEDRIVE_CLIENT_ID"] = client_id
if client_secret:
onedrive_settings["ONEDRIVE_CLIENT_SECRET"] = client_secret
if tenant_id:
onedrive_settings["ONEDRIVE_TENANT_ID"] = tenant_id
if folder_path:
onedrive_settings["ONEDRIVE_FOLDER_PATH"] = folder_path
# Best-effort .env file write using the new utility
env_settings = {k.upper(): v for k, v in onedrive_settings.items()}
update_env_file(env_settings)
updated = set()
new_env_lines = []
for line in env_lines:
stripped_line = line.rstrip()
is_updated = False
for key, value in onedrive_settings.items():
if stripped_line.startswith(f"{key}=") or stripped_line.startswith(f"# {key}="):
new_env_lines.append(f"{key}={value}")
updated.add(key)
is_updated = True
break
if not is_updated:
new_env_lines.append(stripped_line)
for key, value in onedrive_settings.items():
if key not in updated:
new_env_lines.append(f"{key}={value}")
with open(env_path, "w") as f:
f.write("\n".join(new_env_lines) + "\n")
logger.info("Successfully updated OneDrive settings in .env file")
except Exception as env_err:
logger.warning(f"Failed to write .env file (non-fatal): {env_err}")
# Update the settings in memory
if refresh_token:
settings.onedrive_refresh_token = refresh_token
if client_id:
settings.onedrive_client_id = client_id
if client_secret:
settings.onedrive_client_secret = client_secret
if tenant_id:
settings.onedrive_tenant_id = tenant_id
if folder_path:
settings.onedrive_folder_path = folder_path
# Persist to database (primary)
if refresh_token:
save_setting_to_db(db, "onedrive_refresh_token", refresh_token, changed_by=changed_by)
if client_id:
save_setting_to_db(db, "onedrive_client_id", client_id, changed_by=changed_by)
if client_secret:
save_setting_to_db(db, "onedrive_client_secret", client_secret, changed_by=changed_by)
if tenant_id:
save_setting_to_db(db, "onedrive_tenant_id", tenant_id, changed_by=changed_by)
if folder_path:
save_setting_to_db(db, "onedrive_folder_path", folder_path, changed_by=changed_by)
# Update in-memory settings and persist to database dynamically
for key, value in onedrive_settings.items():
setattr(settings, key, value)
save_setting_to_db(db, key, value, changed_by=changed_by)
notify_settings_updated()
+11 -2
View File
@@ -196,11 +196,20 @@ def seed_plans(db: DbSession, _admin: AdminUser) -> dict[str, Any]:
def reorder_plans(body: ReorderBody, db: DbSession, _admin: AdminUser) -> dict[str, Any]:
"""Update sort_order for each plan_id in *body.order* (position = index in list)."""
updated = 0
for sort_order, plan_id in enumerate(body.order):
plan = db.query(SubscriptionPlan).filter(SubscriptionPlan.plan_id == plan_id).first()
# Fetch all requested plans in a single query to avoid N+1
plan_ids = body.order
plans = db.query(SubscriptionPlan).filter(SubscriptionPlan.plan_id.in_(plan_ids)).all()
# Build a map for fast O(1) lookup
plan_map = {p.plan_id: p for p in plans}
for sort_order, plan_id in enumerate(plan_ids):
plan = plan_map.get(plan_id)
if plan:
plan.sort_order = sort_order
updated += 1
try:
db.commit()
except Exception:
+358
View File
@@ -0,0 +1,358 @@
"""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, Response, 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
default_document_language: str | None
"""ISO 639-1 code for the user's preferred document translation target language."""
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'")
default_document_language: str | None = Field(
default=None,
description="ISO 639-1 code for the default document translation target language, e.g. 'en', 'de'",
)
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]
default_document_language=profile.default_document_language, # 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, response: Response, 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]
# Keep session and cookie in sync so detect_language() picks up
# the new preference immediately (without a DB round-trip).
if hasattr(request, "session"):
if lang:
request.session["preferred_language"] = lang
else:
request.session.pop("preferred_language", None)
if lang:
response.set_cookie(
key="docuelevate_lang",
value=lang,
max_age=30 * 24 * 60 * 60,
httponly=False,
samesite="lax",
)
else:
response.delete_cookie(key="docuelevate_lang")
# 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]
# Validate default document language
if body.default_document_language is not None:
doc_lang = body.default_document_language.lower().strip()
if doc_lang and doc_lang not in SUPPORTED_LANGUAGE_CODES:
raise HTTPException(
status_code=status.HTTP_422_UNPROCESSABLE_ENTITY,
detail=f"Unsupported language code: {doc_lang}",
)
profile.default_document_language = doc_lang 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]
default_document_language=profile.default_document_language, # 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."}
+468
View File
@@ -0,0 +1,468 @@
"""Routing rules API endpoints.
Provides full CRUD for pipeline routing rules that conditionally assign
documents to pipelines based on document properties (file type, category,
metadata fields, size, etc.).
Rules are evaluated in ascending ``position`` order. The first rule whose
condition matches wins and routes the document to the specified target
pipeline. If no rule matches, the caller falls back to the owner's (or
system) default pipeline.
"""
import logging
from typing import Annotated, Any
from fastapi import APIRouter, Body, Depends, HTTPException, Request, 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 Pipeline, PipelineRoutingRule
from app.utils.routing_engine import (
BUILTIN_FIELDS,
VALID_OPERATORS,
_evaluate_condition,
_resolve_field,
)
logger = logging.getLogger(__name__)
router = APIRouter(prefix="/routing-rules", tags=["routing-rules"])
DbSession = Annotated[Session, Depends(get_db)]
MAX_RULES_PER_OWNER = 100
MAX_NAME_LENGTH = 255
# ---------------------------------------------------------------------------
# Helpers
# ---------------------------------------------------------------------------
def _get_user_id(request: Request) -> str:
"""Return the authenticated user identifier."""
user = getattr(request.state, "user", None)
if user:
if isinstance(user, dict):
return user.get("sub", user.get("email", "anonymous"))
return getattr(user, "sub", getattr(user, "email", "anonymous"))
return "anonymous"
def _is_admin(request: Request) -> bool:
"""Return ``True`` when the current user has admin privileges."""
user = getattr(request.state, "user", None)
if not user:
return False
groups = user.get("groups", []) if isinstance(user, dict) else getattr(user, "groups", [])
return "admin" in groups
def _can_access_rule(rule: PipelineRoutingRule, user_id: str, admin: bool) -> bool:
"""Check whether the user is allowed to read this rule."""
if admin:
return True
return rule.owner_id == user_id
def _can_write_rule(rule: PipelineRoutingRule, user_id: str, admin: bool) -> bool:
"""Check whether the user is allowed to modify this rule."""
if rule.owner_id is None:
return admin
return rule.owner_id == user_id
def _validate_field(field: str) -> None:
"""Raise 422 if the field name is invalid."""
if field in BUILTIN_FIELDS:
return
if field.startswith("metadata.") and len(field) > len("metadata."):
return
raise HTTPException(
status_code=status.HTTP_422_UNPROCESSABLE_ENTITY,
detail=(
f"Invalid field '{field}'. "
f"Valid built-in fields: {sorted(BUILTIN_FIELDS)}. "
"For AI metadata, use 'metadata.<key>'."
),
)
def _validate_operator(operator: str) -> None:
"""Raise 422 if the operator is not recognised."""
if operator not in VALID_OPERATORS:
raise HTTPException(
status_code=status.HTTP_422_UNPROCESSABLE_ENTITY,
detail=f"Invalid operator '{operator}'. Valid operators: {sorted(VALID_OPERATORS)}",
)
def _serialize_rule(rule: PipelineRoutingRule) -> dict[str, Any]:
"""Serialize a routing rule to a JSON-compatible dict."""
return {
"id": rule.id,
"owner_id": rule.owner_id,
"name": rule.name,
"position": rule.position,
"field": rule.field,
"operator": rule.operator,
"value": rule.value,
"target_pipeline_id": rule.target_pipeline_id,
"is_active": rule.is_active,
"created_at": rule.created_at.isoformat() if rule.created_at else None,
"updated_at": rule.updated_at.isoformat() if rule.updated_at else None,
}
# ---------------------------------------------------------------------------
# Pydantic request models
# ---------------------------------------------------------------------------
class RoutingRuleCreate(BaseModel):
"""Request body for creating a routing rule."""
name: str = Field(..., min_length=1, max_length=MAX_NAME_LENGTH)
field: str = Field(..., min_length=1, max_length=255)
operator: str = Field(..., min_length=1, max_length=50)
value: str = Field(..., max_length=1024)
target_pipeline_id: int
position: int | None = None
is_active: bool = True
class RoutingRuleUpdate(BaseModel):
"""Request body for updating a routing rule."""
name: str | None = Field(None, min_length=1, max_length=MAX_NAME_LENGTH)
field: str | None = Field(None, min_length=1, max_length=255)
operator: str | None = Field(None, min_length=1, max_length=50)
value: str | None = Field(None, max_length=1024)
target_pipeline_id: int | None = None
position: int | None = None
is_active: bool | None = None
class RoutingRuleEvaluateRequest(BaseModel):
"""Request body for dry-run rule evaluation."""
file_type: str | None = None
filename: str | None = None
size: int | None = None
document_type: str | None = None
metadata: dict[str, Any] | None = None
# ---------------------------------------------------------------------------
# Endpoints
# ---------------------------------------------------------------------------
@router.get("")
@require_login
def list_routing_rules(request: Request, db: DbSession) -> list[dict[str, Any]]:
"""List all routing rules accessible by the current user.
Returns the user's own rules plus any system-wide rules (``owner_id=NULL``).
Rules are sorted by position.
"""
user_id = _get_user_id(request)
rules = (
db.query(PipelineRoutingRule)
.filter((PipelineRoutingRule.owner_id == user_id) | (PipelineRoutingRule.owner_id.is_(None)))
.order_by(
PipelineRoutingRule.owner_id.is_(None).asc(),
PipelineRoutingRule.position.asc(),
)
.all()
)
return [_serialize_rule(r) for r in rules]
@router.post("", status_code=status.HTTP_201_CREATED)
@require_login
def create_routing_rule(request: Request, db: DbSession, body: RoutingRuleCreate) -> dict[str, Any]:
"""Create a new routing rule for the current user.
Returns:
The created routing rule.
Raises:
HTTPException 422: If the field or operator is invalid.
HTTPException 404: If the target pipeline does not exist.
HTTPException 409: If the maximum number of rules is reached.
"""
user_id = _get_user_id(request)
_validate_field(body.field)
_validate_operator(body.operator)
# Verify target pipeline exists and is accessible.
pipeline = db.query(Pipeline).filter(Pipeline.id == body.target_pipeline_id).first()
if not pipeline:
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND,
detail=f"Target pipeline {body.target_pipeline_id} not found",
)
# Enforce per-owner limit.
count = db.query(PipelineRoutingRule).filter(PipelineRoutingRule.owner_id == user_id).count()
if count >= MAX_RULES_PER_OWNER:
raise HTTPException(
status_code=status.HTTP_409_CONFLICT,
detail=f"Maximum of {MAX_RULES_PER_OWNER} routing rules per user reached",
)
# Auto-assign position if not specified.
position = body.position
if position is None:
max_pos = (
db.query(PipelineRoutingRule.position)
.filter(PipelineRoutingRule.owner_id == user_id)
.order_by(PipelineRoutingRule.position.desc())
.first()
)
position = (max_pos[0] + 1) if max_pos else 0
rule = PipelineRoutingRule(
owner_id=user_id,
name=body.name.strip(),
position=position,
field=body.field,
operator=body.operator,
value=body.value,
target_pipeline_id=body.target_pipeline_id,
is_active=body.is_active,
)
try:
db.add(rule)
db.commit()
db.refresh(rule)
except Exception:
db.rollback()
logger.exception("Failed to create routing rule for user=%s", user_id)
raise HTTPException(
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
detail="Failed to create routing rule",
)
logger.info("Routing rule created: id=%s, user=%s", rule.id, user_id)
return _serialize_rule(rule)
@router.get("/operators")
def list_operators() -> dict[str, Any]:
"""Return the list of supported operators and fields.
This is a public endpoint (no auth required) so that UIs can populate
dropdowns without hard-coding the catalogue.
"""
return {
"operators": sorted(VALID_OPERATORS),
"builtin_fields": sorted(BUILTIN_FIELDS),
"metadata_prefix": "metadata.",
}
@router.post("/evaluate")
@require_login
def evaluate_rules(request: Request, db: DbSession, body: RoutingRuleEvaluateRequest) -> dict[str, Any]:
"""Dry-run rule evaluation against the provided document properties.
Returns the first matching rule and target pipeline (if any), or
indicates that no rule matched (default pipeline will be used).
"""
user_id = _get_user_id(request)
doc_props: dict[str, Any] = {
"file_type": body.file_type,
"filename": body.filename,
"size": body.size,
"document_type": body.document_type,
"metadata": body.metadata or {},
}
rules = (
db.query(PipelineRoutingRule)
.filter(
PipelineRoutingRule.is_active.is_(True),
(PipelineRoutingRule.owner_id == user_id) | (PipelineRoutingRule.owner_id.is_(None)),
)
.order_by(
PipelineRoutingRule.owner_id.is_(None).asc(),
PipelineRoutingRule.position.asc(),
)
.all()
)
for rule in rules:
actual = _resolve_field(rule.field, doc_props)
if _evaluate_condition(actual, rule.operator, rule.value):
pipeline = db.query(Pipeline).filter(Pipeline.id == rule.target_pipeline_id).first()
return {
"matched": True,
"rule": _serialize_rule(rule),
"target_pipeline": {
"id": pipeline.id,
"name": pipeline.name,
"is_active": pipeline.is_active,
}
if pipeline
else None,
}
return {"matched": False, "rule": None, "target_pipeline": None}
@router.put("/reorder")
@require_login
def reorder_routing_rules(
request: Request,
db: DbSession,
rule_ids: list[int] = Body(..., embed=True),
) -> list[dict[str, Any]]:
"""Reorder the caller's routing rules.
Expects a JSON body ``{"rule_ids": [3, 1, 2]}`` where the list
contains the IDs of the caller's rules in the desired order.
"""
user_id = _get_user_id(request)
rules = (
db.query(PipelineRoutingRule)
.filter(PipelineRoutingRule.owner_id == user_id, PipelineRoutingRule.id.in_(rule_ids))
.all()
)
rule_map = {r.id: r for r in rules}
if len(rule_map) != len(rule_ids) or set(rule_map.keys()) != set(rule_ids):
raise HTTPException(
status_code=status.HTTP_422_UNPROCESSABLE_ENTITY,
detail="rule_ids must contain exactly the IDs of your routing rules",
)
for pos, rid in enumerate(rule_ids):
rule_map[rid].position = pos
try:
db.commit()
except Exception:
db.rollback()
logger.exception("Failed to reorder routing rules for user=%s", user_id)
raise HTTPException(
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
detail="Failed to reorder routing rules",
)
ordered = sorted(rules, key=lambda r: r.position)
return [_serialize_rule(r) for r in ordered]
@router.get("/{rule_id}")
@require_login
def get_routing_rule(rule_id: int, request: Request, db: DbSession) -> dict[str, Any]:
"""Return a single routing rule by ID."""
user_id = _get_user_id(request)
admin = _is_admin(request)
rule = db.query(PipelineRoutingRule).filter(PipelineRoutingRule.id == rule_id).first()
if not rule or not _can_access_rule(rule, user_id, admin):
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Routing rule not found")
return _serialize_rule(rule)
@router.put("/{rule_id}")
@require_login
def update_routing_rule(rule_id: int, request: Request, db: DbSession, body: RoutingRuleUpdate) -> dict[str, Any]:
"""Update a routing rule.
Only the fields present in the request body are updated.
"""
user_id = _get_user_id(request)
admin = _is_admin(request)
rule = db.query(PipelineRoutingRule).filter(PipelineRoutingRule.id == rule_id).first()
if not rule or not _can_access_rule(rule, user_id, admin):
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Routing rule not found")
if not _can_write_rule(rule, user_id, admin):
raise HTTPException(status_code=status.HTTP_403_FORBIDDEN, detail="Cannot modify this rule")
if body.field is not None:
_validate_field(body.field)
rule.field = body.field
if body.operator is not None:
_validate_operator(body.operator)
rule.operator = body.operator
if body.value is not None:
rule.value = body.value
if body.name is not None:
rule.name = body.name.strip()
if body.target_pipeline_id is not None:
pipeline = db.query(Pipeline).filter(Pipeline.id == body.target_pipeline_id).first()
if not pipeline:
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND,
detail=f"Target pipeline {body.target_pipeline_id} not found",
)
rule.target_pipeline_id = body.target_pipeline_id
if body.position is not None:
rule.position = body.position
if body.is_active is not None:
rule.is_active = body.is_active
try:
db.commit()
db.refresh(rule)
except Exception:
db.rollback()
logger.exception("Failed to update routing rule id=%s", rule_id)
raise HTTPException(
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
detail="Failed to update routing rule",
)
logger.info("Routing rule updated: id=%s, user=%s", rule_id, user_id)
return _serialize_rule(rule)
@router.delete("/{rule_id}", status_code=status.HTTP_204_NO_CONTENT)
@require_login
def delete_routing_rule(rule_id: int, request: Request, db: DbSession) -> None:
"""Delete a routing rule."""
user_id = _get_user_id(request)
admin = _is_admin(request)
rule = db.query(PipelineRoutingRule).filter(PipelineRoutingRule.id == rule_id).first()
if not rule or not _can_access_rule(rule, user_id, admin):
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Routing rule not found")
if not _can_write_rule(rule, user_id, admin):
raise HTTPException(status_code=status.HTTP_403_FORBIDDEN, detail="Cannot modify this rule")
try:
db.delete(rule)
db.commit()
except Exception:
db.rollback()
logger.exception("Failed to delete routing rule id=%s", rule_id)
raise HTTPException(
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
detail="Failed to delete routing rule",
)
logger.info("Routing rule deleted: id=%s, user=%s", rule_id, user_id)
+7 -5
View File
@@ -313,16 +313,18 @@ async def list_shared_links(
active_only: bool = Query(False, description="When true, only return active (non-revoked) links"),
) -> list[dict[str, Any]]:
"""List all shared links created by the authenticated user."""
q = db.query(SharedLink).filter(SharedLink.owner_id == owner_id)
q = (
db.query(SharedLink, FileRecord.original_filename)
.outerjoin(FileRecord, SharedLink.file_id == FileRecord.id)
.filter(SharedLink.owner_id == owner_id)
)
if active_only:
q = q.filter(SharedLink.is_active.is_(True))
links = q.order_by(SharedLink.created_at.desc()).all()
links_with_filenames = q.order_by(SharedLink.created_at.desc()).all()
base_url = str(request.base_url).rstrip("/")
result = []
for link in links:
file_record = db.query(FileRecord).filter(FileRecord.id == link.file_id).first()
filename = file_record.original_filename if file_record else None
for link, filename in links_with_filenames:
result.append(_link_to_dict(link, base_url, filename))
return result
+156
View File
@@ -0,0 +1,156 @@
"""
API endpoints for document translation.
Provides on-the-fly translation via the AI provider and access to the
persisted default-language translation.
"""
import logging
from typing import Annotated
from fastapi import APIRouter, Depends, HTTPException, Query, Request, status
from fastapi.responses import JSONResponse
from sqlalchemy.orm import Session
from app.auth import require_login
from app.config import settings
from app.database import get_db
from app.models import FileRecord
from app.utils.ai_provider import get_ai_provider
from app.utils.user_scope import apply_owner_filter
logger = logging.getLogger(__name__)
router = APIRouter()
DbSession = Annotated[Session, Depends(get_db)]
# Maximum characters sent to the AI provider for a single translation request.
_MAX_TRANSLATION_INPUT = 50_000
def _get_file_or_404(db: Session, file_id: int, request: Request) -> FileRecord:
"""Fetch a FileRecord visible to the current user or raise 404."""
query = db.query(FileRecord).filter(FileRecord.id == file_id)
query = apply_owner_filter(query, request)
record = query.first()
if not record:
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="File not found")
return record
@router.get("/files/{file_id}/translation/default")
@require_login
def get_default_translation(
request: Request,
file_id: int,
db: DbSession,
) -> JSONResponse:
"""Return the persisted default-language translation for a document.
Returns 404 if no default-language translation has been generated yet
(e.g. because the document is already in the default language).
"""
record = _get_file_or_404(db, file_id, request)
if not record.default_language_text:
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND,
detail="No default-language translation available for this file",
)
return JSONResponse(
content={
"file_id": record.id,
"detected_language": record.detected_language,
"default_language_code": record.default_language_code,
"text": record.default_language_text,
}
)
@router.get("/files/{file_id}/translate")
@require_login
def translate_on_the_fly(
request: Request,
file_id: int,
db: DbSession,
lang: str = Query(..., min_length=2, max_length=10, description="Target language ISO 639-1 code"),
) -> JSONResponse:
"""Translate a document's extracted text into an arbitrary language on the fly.
The translation is generated via the configured AI provider and is **not**
persisted. For the default-language translation, use the
``/files/{file_id}/translation/default`` endpoint instead.
"""
record = _get_file_or_404(db, file_id, request)
source_text = record.ocr_text
if not source_text:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail="No extracted text available for this file — translation requires OCR text",
)
# If the requested language matches what is already stored, return it directly.
if record.default_language_code and lang == record.default_language_code and record.default_language_text:
return JSONResponse(
content={
"file_id": record.id,
"source_language": record.detected_language,
"target_language": lang,
"text": record.default_language_text,
"cached": True,
}
)
# If the detected language already matches, return the original text.
detected = record.detected_language
if detected and detected == lang:
return JSONResponse(
content={
"file_id": record.id,
"source_language": detected,
"target_language": lang,
"text": source_text,
"cached": True,
}
)
# Truncate to keep AI costs bounded.
text_to_translate = source_text[:_MAX_TRANSLATION_INPUT]
try:
provider = get_ai_provider()
model = settings.ai_model or settings.openai_model
translated = provider.chat_completion(
messages=[
{
"role": "system",
"content": (
f"You are a professional translator. Translate the following text "
f"into {lang}. Preserve the original formatting, paragraph structure, "
f"and meaning. Do not add any commentary — output ONLY the translated text."
),
},
{"role": "user", "content": text_to_translate},
],
model=model,
temperature=0.3,
)
except Exception as exc:
logger.exception(f"On-the-fly translation failed for file {file_id}: {exc}")
raise HTTPException(
status_code=status.HTTP_502_BAD_GATEWAY,
detail="Translation failed — the AI provider returned an error",
)
return JSONResponse(
content={
"file_id": record.id,
"source_language": detected or "unknown",
"target_language": lang,
"text": translated,
"cached": False,
}
)
+64 -88
View File
@@ -2,7 +2,6 @@
API endpoint for processing files from URLs
"""
import ipaddress
import logging
import mimetypes
import os
@@ -10,7 +9,8 @@ import urllib.parse
import uuid
from typing import Optional
import requests
import aiofiles
import httpx
from fastapi import APIRouter, HTTPException, Request
from pydantic import BaseModel, HttpUrl, field_validator
@@ -19,6 +19,7 @@ from app.config import settings
from app.tasks.process_document import process_document
from app.utils.allowed_types import ALLOWED_MIME_TYPES
from app.utils.filename_utils import sanitize_filename
from app.utils.network import is_private_ip
# Set up logging
logger = logging.getLogger(__name__)
@@ -42,37 +43,6 @@ class URLUploadRequest(BaseModel):
return v
def is_private_ip(hostname: str) -> bool:
"""
Check if a hostname resolves to a private/internal IP address.
Protects against SSRF attacks by blocking access to internal networks.
"""
try:
# Try to parse as IP address directly
ip = ipaddress.ip_address(hostname)
return ip.is_private or ip.is_loopback or ip.is_link_local or ip.is_reserved
except ValueError:
# Not a direct IP, try to resolve hostname
try:
import socket
# Get all IP addresses for this hostname
addr_info = socket.getaddrinfo(hostname, None)
for info in addr_info:
ip_str = info[4][0]
ip = ipaddress.ip_address(ip_str)
# Block if ANY resolved IP is private/internal
if ip.is_private or ip.is_loopback or ip.is_link_local or ip.is_reserved:
return True
return False
except (socket.gaierror, socket.error):
# Cannot resolve - allow for testing/development
# In production, DNS should work properly
# Log this for debugging
logger.warning(f"Could not resolve hostname: {hostname}")
return False # Changed from True to False to allow external domains in tests
def validate_url_safety(url: str) -> None:
"""
Validate that URL is safe to fetch (SSRF protection).
@@ -184,67 +154,73 @@ async def process_url(request: Request, url_request: URLUploadRequest):
logger.info(f"Downloading file from URL: {url}")
# Use configured timeout to prevent hanging
response = requests.get(
url,
async with httpx.AsyncClient(
timeout=settings.http_request_timeout,
stream=True, # Stream to handle large files
allow_redirects=True, # Follow redirects
follow_redirects=True,
headers={
"User-Agent": "DocuElevate/1.0", # Identify ourselves
},
)
response.raise_for_status()
) as client:
async with client.stream("GET", url) as response:
response.raise_for_status()
# Validate content type
content_type = response.headers.get("Content-Type", "")
if not validate_file_type(content_type, safe_filename):
raise HTTPException(
status_code=400,
detail=f"Unsupported file type: {content_type}. "
"Supported types: PDF, Office documents, images, plain text",
)
# Validate content type
content_type = response.headers.get("Content-Type", "")
if not validate_file_type(content_type, safe_filename):
raise HTTPException(
status_code=400,
detail=f"Unsupported file type: {content_type}. "
"Supported types: PDF, Office documents, images, plain text",
)
# Check content length before downloading
content_length = response.headers.get("Content-Length")
if content_length:
file_size = int(content_length)
max_size = settings.max_upload_size
if file_size > max_size:
raise HTTPException(
status_code=413,
detail=f"File too large: {file_size} bytes (max {max_size} bytes)",
)
# Generate unique filename
unique_id = str(uuid.uuid4())
if "." in safe_filename:
file_extension = safe_filename.rsplit(".", 1)[1]
target_filename = f"{unique_id}.{file_extension}"
else:
target_filename = unique_id
target_path = os.path.join(settings.workdir, target_filename)
# Download file in chunks to handle large files
downloaded_size = 0
max_size = settings.max_upload_size
with open(target_path, "wb") as f:
for chunk in response.iter_content(chunk_size=8192):
if chunk:
f.write(chunk)
downloaded_size += len(chunk)
# Check size during download
if downloaded_size > max_size:
# Remove partial file
f.close()
os.remove(target_path)
# Check content length before downloading
content_length = response.headers.get("Content-Length")
if content_length:
file_size = int(content_length)
max_size = settings.max_upload_size
if file_size > max_size:
raise HTTPException(
status_code=413,
detail=f"File too large: exceeded {max_size} bytes during download",
detail=f"File too large: {file_size} bytes (max {max_size} bytes)",
)
# Generate unique filename
unique_id = str(uuid.uuid4())
# Check for extension using original_filename to avoid any CodeQL issues
# with safe_filename which is derived from the URL directly.
if "." in original_filename:
_, ext = os.path.splitext(original_filename)
# Strip out the leading dot and any non-alphanumeric chars
clean_ext = "".join(c for c in ext if c.isalnum())
if not clean_ext:
clean_ext = "bin"
target_filename = f"{unique_id}.{clean_ext}"
else:
target_filename = unique_id
target_path = os.path.join(settings.workdir, target_filename)
# Download file in chunks to handle large files
downloaded_size = 0
max_size = settings.max_upload_size
async with aiofiles.open(target_path, "wb") as f:
async for chunk in response.aiter_bytes(chunk_size=8192):
if chunk:
await f.write(chunk)
downloaded_size += len(chunk)
# Check size during download
if downloaded_size > max_size:
# Remove partial file
await f.close()
os.remove(target_path)
raise HTTPException(
status_code=413,
detail=f"File too large: exceeded {max_size} bytes during download",
)
logger.info(f"Downloaded file from URL '{url}' as '{target_filename}' ({downloaded_size} bytes)")
# Enqueue for processing
@@ -258,19 +234,19 @@ async def process_url(request: Request, url_request: URLUploadRequest):
"size": downloaded_size,
}
except requests.exceptions.Timeout:
except httpx.TimeoutException:
logger.error(f"Timeout while downloading file from URL: {url}")
raise HTTPException(status_code=408, detail="Request timeout: server took too long to respond")
except requests.exceptions.ConnectionError as e:
except httpx.ConnectError as e:
logger.error(f"Connection error while downloading file from URL: {url} - {str(e)}")
raise HTTPException(status_code=502, detail=f"Failed to connect to URL: {str(e)}")
except requests.exceptions.HTTPError as e:
except httpx.HTTPStatusError as e:
logger.error(f"HTTP error while downloading file from URL: {url} - {str(e)}")
raise HTTPException(status_code=e.response.status_code, detail=f"HTTP error: {str(e)}")
except requests.exceptions.RequestException as e:
except httpx.RequestError as e:
logger.error(f"Error downloading file from URL: {url} - {str(e)}")
raise HTTPException(status_code=500, detail=f"Failed to download file: {str(e)}")
+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")