olaf
fcc0dfbb0f
DB/model Add Conversion model + ConversionStatus enum (pending, processing, ready, failed) Alembic migrations: create conversions table, indexes, unique (source_event_media_id, target_format, file_hash), and NOT NULL on file_hash API Enqueue on upload (ppt|pptx|odp) in routes/eventmedia.py: compute sha256, upsert Conversion, enqueue job New routes: POST /api/conversions/<media_id>/pdf — ensure/enqueue conversion GET /api/conversions/<media_id>/status — latest status/details GET /api/files/converted/<path> — serve converted PDFs Register conversions blueprint in wsgi Worker server/worker.py: convert_event_media_to_pdf Calls Gotenberg /forms/libreoffice/convert, writes to server/media/converted/ Updates Conversion status, timestamps, error messages Fix media root resolution to /server/media Prefer function enqueue over string path; expose server.worker in package init for RQ string compatibility Queue/infra server/task_queue.py: RQ queue helper (REDIS_URL, default redis://redis:6379/0) docker-compose: Add redis and gotenberg services Add worker service (rq worker conversions) Pass REDIS_URL and GOTENBERG_URL to server/worker Mount shared media volume in prod for API/worker parity docker-compose.override: Add dev redis/gotenberg/worker services Ensure PYTHONPATH + working_dir allow importing server.worker Use rq CLI instead of python -m rq for worker Dashboard dev: run as appropriate user/root and pre-create/chown caches to avoid EACCES Dashboard dev UX Vite: set cacheDir .vite to avoid EACCES in node_modules Disable Node inspector by default to avoid port conflicts Docs Update copilot-instructions.md with conversion system: flow, services, env vars, endpoints, storage paths, and data model
95 lines
3.2 KiB
Python
95 lines
3.2 KiB
Python
import os
|
|
import traceback
|
|
from datetime import datetime, timezone
|
|
|
|
import requests
|
|
from sqlalchemy.orm import Session as SASession
|
|
|
|
from server.database import Session
|
|
from models.models import Conversion, ConversionStatus, EventMedia, MediaType
|
|
|
|
GOTENBERG_URL = os.getenv("GOTENBERG_URL", "http://gotenberg:3000")
|
|
|
|
|
|
def _now():
|
|
return datetime.now(timezone.utc)
|
|
|
|
|
|
def convert_event_media_to_pdf(conversion_id: int):
|
|
"""
|
|
Job entry point: convert a single EventMedia to PDF using Gotenberg.
|
|
|
|
Steps:
|
|
- Load conversion + source media
|
|
- Set status=processing, started_at
|
|
- POST to Gotenberg /forms/libreoffice/convert with the source file bytes
|
|
- Save response bytes to target_path
|
|
- Set status=ready, completed_at, target_path
|
|
- On error: set status=failed, error_message
|
|
"""
|
|
session: SASession = Session()
|
|
try:
|
|
conv: Conversion = session.query(Conversion).get(conversion_id)
|
|
if not conv:
|
|
return
|
|
|
|
media: EventMedia = session.query(
|
|
EventMedia).get(conv.source_event_media_id)
|
|
if not media or not media.file_path:
|
|
conv.status = ConversionStatus.failed
|
|
conv.error_message = "Source media or file_path missing"
|
|
conv.completed_at = _now()
|
|
session.commit()
|
|
return
|
|
|
|
conv.status = ConversionStatus.processing
|
|
conv.started_at = _now()
|
|
session.commit()
|
|
|
|
# Get the server directory (where this worker.py file is located)
|
|
server_dir = os.path.dirname(os.path.abspath(__file__))
|
|
media_root = os.path.join(server_dir, "media")
|
|
abs_source = os.path.join(media_root, media.file_path)
|
|
# Output target under media/converted
|
|
converted_dir = os.path.join(media_root, "converted")
|
|
os.makedirs(converted_dir, exist_ok=True)
|
|
filename_wo_ext = os.path.splitext(
|
|
os.path.basename(media.file_path))[0]
|
|
pdf_name = f"{filename_wo_ext}.pdf"
|
|
abs_target = os.path.join(converted_dir, pdf_name)
|
|
|
|
# Send to Gotenberg
|
|
with open(abs_source, "rb") as f:
|
|
files = {"files": (os.path.basename(abs_source), f)}
|
|
resp = requests.post(
|
|
f"{GOTENBERG_URL}/forms/libreoffice/convert",
|
|
files=files,
|
|
timeout=600,
|
|
)
|
|
resp.raise_for_status()
|
|
|
|
with open(abs_target, "wb") as out:
|
|
out.write(resp.content)
|
|
|
|
conv.status = ConversionStatus.ready
|
|
# Store relative path under media/
|
|
conv.target_path = os.path.relpath(abs_target, media_root)
|
|
conv.completed_at = _now()
|
|
session.commit()
|
|
except requests.exceptions.Timeout:
|
|
conv = session.query(Conversion).get(conversion_id)
|
|
if conv:
|
|
conv.status = ConversionStatus.failed
|
|
conv.error_message = "Conversion timeout"
|
|
conv.completed_at = _now()
|
|
session.commit()
|
|
except Exception as e:
|
|
conv = session.query(Conversion).get(conversion_id)
|
|
if conv:
|
|
conv.status = ConversionStatus.failed
|
|
conv.error_message = f"{e}\n{traceback.format_exc()}"
|
|
conv.completed_at = _now()
|
|
session.commit()
|
|
finally:
|
|
session.close()
|