feat(downloads): editor backend — trim/crop derivatives (phase 2)

Per-user trim/crop clips derived from a finished download via ffmpeg, riding the same
MediaAsset/DownloadJob/worker/quota/GC machinery (asset source_kind='edit', per-user cache key):
- migration 0041: download_jobs job_kind/source_job_id/source_asset_id/edit_spec
- app/downloads/edit.py: spec normalize+sig, ffmpeg trim/crop cmd (fast stream-copy vs frame-
  accurate re-encode, per-edit 'accurate' toggle), progress+cooperative-cancel runner, filmstrip
- service.enqueue_edit; worker _process_edit branch; storage.edit_rel_path (.edits/{user} tree)
- routes: POST /edit, GET /{id}/storyboard(.jpg)
This commit is contained in:
npeter83 2026-07-04 01:01:46 +02:00
parent c0b138cd9a
commit f0fc542260
7 changed files with 619 additions and 3 deletions

View file

@ -28,6 +28,7 @@ from sqlalchemy import text
from app.config import settings
from app.db import SessionLocal
from app.downloads import edit as editmod
from app.downloads import formats, quota, service, storage
from app.models import DownloadJob, MediaAsset
from app.titles import normalize_title
@ -141,6 +142,7 @@ def _process_job(job_id: int) -> None:
asset = db.get(MediaAsset, job.asset_id) if job.asset_id else None
spec = dict(job.profile_snapshot or {})
source_kind, source_ref = job.source_kind, job.source_ref
job_kind = job.job_kind
asset_id = asset.id if asset else None
asset_status = asset.status if asset else None
@ -160,13 +162,16 @@ def _process_job(job_id: int) -> None:
time.sleep(2)
return
# asset_status == "pending": try to win the download.
# asset_status == "pending": try to win the download / edit.
if not _claim_asset(asset_id):
_set_job(job_id, status="queued", phase="waiting")
time.sleep(2)
return
_download(job_id, asset_id, source_kind, source_ref, spec)
if job_kind == "edit":
_process_edit(job_id, asset_id)
else:
_download(job_id, asset_id, source_kind, source_ref, spec)
def _finish_from_cache(job_id: int, asset_id: int) -> None:
@ -431,6 +436,109 @@ def _reset_asset_pending(asset_id: int) -> None:
db.commit()
# --- editor derivatives (phase 2: trim/crop via ffmpeg) -------------------------------------
def _edit_staging_dir(asset_id: int) -> Path:
return Path(settings.download_root) / ".staging" / f"edit-{asset_id}"
def _fail_edit(job_id: int, asset_id: int, msg: str) -> None:
with SessionLocal() as db:
asset = db.get(MediaAsset, asset_id)
if asset:
asset.status = "error"
asset.error = msg
job = db.get(DownloadJob, job_id)
if job:
job.status = "error"
job.error = msg
job.phase = None
db.commit()
log.warning("edit job %s failed: %s", job_id, msg)
def _process_edit(job_id: int, asset_id: int) -> None:
"""Produce a per-user trim/crop clip from the source asset's downloaded file via ffmpeg."""
with SessionLocal() as db:
job = db.get(DownloadJob, job_id)
src = db.get(MediaAsset, job.source_asset_id) if job and job.source_asset_id else None
edit_spec = dict(job.edit_spec or {}) if job else {}
user_id = job.user_id if job else None
src_ready = src is not None and src.status == "ready" and bool(src.rel_path)
src_rel = src.rel_path if src else None
src_w, src_h, src_dur = (src.width, src.height, src.duration_s) if src else (None, None, None)
if not src_ready or not src_rel:
_fail_edit(job_id, asset_id, "The source download is no longer available.")
return
src_path = storage.abs_path(settings.download_root, src_rel)
if not src_path.exists():
_fail_edit(job_id, asset_id, "The source file is missing.")
return
src_ext = src_path.suffix.lstrip(".").lower() or "mp4"
crop = editmod.has_crop(edit_spec)
out_ext = "mp4" if editmod.needs_reencode(edit_spec) else src_ext
total_s = editmod.clip_duration(edit_spec, src_dur) or src_dur or 0
staging = _edit_staging_dir(asset_id)
try:
if staging.exists():
shutil.rmtree(staging, ignore_errors=True)
staging.mkdir(parents=True, exist_ok=True)
dest_staging = staging / f"out.{out_ext}"
_set_job(job_id, phase="editing", progress=0, speed_bps=None, eta_s=None)
cmd = editmod.build_edit_cmd(src_path, dest_staging, edit_spec, out_ext)
editmod.run_ffmpeg(
cmd,
total_s,
on_progress=lambda pct: _set_job(job_id, progress=int(pct), phase="editing"),
should_cancel=lambda: _job_status(job_id) not in ("running", None),
)
if not dest_staging.exists():
raise RuntimeError("ffmpeg produced no output file")
rel = storage.edit_rel_path(user_id, asset_id, out_ext)
storage.place_file(dest_staging, settings.download_root, rel)
final = storage.abs_path(settings.download_root, rel)
size = final.stat().st_size if final.exists() else None
expires = datetime.now(timezone.utc) + timedelta(days=settings.download_retention_days)
with SessionLocal() as db:
asset = db.get(MediaAsset, asset_id)
if asset:
asset.status = "ready"
asset.rel_path = rel
asset.size_bytes = size
asset.container = out_ext
asset.duration_s = total_s or asset.duration_s
if crop:
asset.width = edit_spec["crop"]["w"]
asset.height = edit_spec["crop"]["h"]
else:
asset.width, asset.height = src_w, src_h
asset.error = None
asset.last_access_at = datetime.now(timezone.utc)
asset.expires_at = expires
job = db.get(DownloadJob, job_id)
if job:
job.status = "done"
job.progress = 100
job.phase = None
db.commit()
log.info("edit job %s done: %s", job_id, rel)
except editmod.EditAborted:
# Paused/canceled mid-encode: free the asset for a later retry (ref_count is the route's job).
_reset_asset_pending(asset_id)
log.info("edit job %s aborted (pause/cancel)", job_id)
except Exception as exc: # noqa: BLE001 — surface the failure, keep the worker alive
_fail_edit(job_id, asset_id, str(exc)[:500])
finally:
shutil.rmtree(staging, ignore_errors=True)
# --- loop -----------------------------------------------------------------------------------
def _worker_loop(idx: int) -> None: