Files
personal-ai-assistant/backend/app/services/pdf_service.py
dolgolyov.alexei fed6a3df1b Phase 6: PDF & Polish — PDF generation, admin users/settings, AI tool
Backend:
- Setting + GeneratedPdf models, Alembic migration with default settings seed
- PDF generation service (WeasyPrint + Jinja2 with autoescape)
- Health report HTML template with memory entries + document excerpts
- Admin user management: list, create, update (role/max_chats/is_active)
- Admin settings: self_registration_enabled, default_max_chats
- Self-registration check wired into auth register endpoint
- default_max_chats applied to new user registrations
- AI tool: generate_pdf creates health compilation PDFs
- PDF compile/list/download API endpoints
- WeasyPrint system deps added to Dockerfile

Frontend:
- PDF reports page with generate + download
- Admin users page with create/edit/activate/deactivate
- Admin settings page with self-registration toggle + max chats
- Extended sidebar with PDF reports + admin users/settings links
- English + Russian translations for all new UI

Review fixes applied:
- Jinja2 autoescape enabled (XSS prevention in PDFs)
- db.refresh after flush (created_at populated correctly)
- storage_path removed from API response (no internal path leak)
- Role field uses Literal["user", "admin"] validation
- React hooks called before conditional returns (rules of hooks)
- default_max_chats setting now applied during registration

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-19 14:37:43 +03:00

108 lines
3.4 KiB
Python

import uuid
from datetime import datetime, timezone
from pathlib import Path
from jinja2 import Environment, FileSystemLoader, select_autoescape
from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession
from app.config import settings
from app.models.document import Document
from app.models.generated_pdf import GeneratedPdf
from app.models.user import User
from app.services.memory_service import get_user_memories
TEMPLATE_DIR = Path(__file__).parent.parent / "templates" / "pdf"
jinja_env = Environment(
loader=FileSystemLoader(str(TEMPLATE_DIR)),
autoescape=select_autoescape(["html"]),
)
async def generate_health_pdf(
db: AsyncSession,
user_id: uuid.UUID,
title: str,
document_ids: list[uuid.UUID] | None = None,
chat_id: uuid.UUID | None = None,
) -> GeneratedPdf:
# Load user
result = await db.execute(select(User).where(User.id == user_id))
user = result.scalar_one()
# Load memories
memories = await get_user_memories(db, user_id, is_active=True)
memory_data = [
{"category": m.category, "title": m.title, "content": m.content, "importance": m.importance}
for m in memories
]
# Load documents
doc_data = []
if document_ids:
for doc_id in document_ids:
result = await db.execute(
select(Document).where(Document.id == doc_id, Document.user_id == user_id)
)
doc = result.scalar_one_or_none()
if doc:
doc_data.append({
"original_filename": doc.original_filename,
"doc_type": doc.doc_type,
"excerpt": (doc.extracted_text or "")[:2000],
})
# Render HTML
template = jinja_env.get_template("health_report.html")
html = template.render(
title=title,
user_name=user.full_name or user.username,
generated_at=datetime.now(timezone.utc).strftime("%Y-%m-%d %H:%M UTC"),
memories=memory_data,
documents=doc_data,
ai_summary=None,
)
# Generate PDF
pdf_id = uuid.uuid4()
pdf_dir = Path(settings.UPLOAD_DIR).parent / "pdfs" / str(user_id)
pdf_dir.mkdir(parents=True, exist_ok=True)
pdf_path = pdf_dir / f"{pdf_id}.pdf"
try:
from weasyprint import HTML
HTML(string=html).write_pdf(str(pdf_path))
except ImportError:
# WeasyPrint not installed — write HTML as fallback
pdf_path = pdf_path.with_suffix(".html")
pdf_path.write_text(html, encoding="utf-8")
# Save record
generated = GeneratedPdf(
id=pdf_id,
user_id=user_id,
title=title,
storage_path=str(pdf_path),
source_document_ids=document_ids,
source_chat_id=chat_id,
)
db.add(generated)
await db.flush()
await db.refresh(generated)
return generated
async def get_user_pdfs(db: AsyncSession, user_id: uuid.UUID) -> list[GeneratedPdf]:
result = await db.execute(
select(GeneratedPdf).where(GeneratedPdf.user_id == user_id)
.order_by(GeneratedPdf.created_at.desc())
)
return list(result.scalars().all())
async def get_pdf(db: AsyncSession, pdf_id: uuid.UUID, user_id: uuid.UUID) -> GeneratedPdf | None:
result = await db.execute(
select(GeneratedPdf).where(GeneratedPdf.id == pdf_id, GeneratedPdf.user_id == user_id)
)
return result.scalar_one_or_none()