siftlode/backend/app/downloads/service.py

"""Enqueue + cache resolution for the download center (the per-user layer over MediaAsset).

`enqueue` is the single entry point used by the API: it resolves (or creates) the shared
MediaAsset for the requested source+format, links a per-user DownloadJob to it, and — on a
cache hit (asset already ready) — marks the job done instantly with no re-download. The worker
handles everything else. State transitions used by the routes (pause/resume/cancel/delete) and
the worker live in `worker.py` / the routes; this module owns enqueue + asset bookkeeping.
"""
from datetime import datetime, timezone

from sqlalchemy import func, select
from sqlalchemy.exc import IntegrityError
from sqlalchemy.orm import Session

from app.config import settings
from app.downloads import adapters
from app.downloads import edit as editmod
from app.downloads import formats, quota, storage
from app.downloads.status import HOLDING
from app.models import Channel, DownloadJob, MediaAsset, Video


class EditError(Exception):
    """Bad edit request (empty spec / source not ready); `reason` is an i18n-mappable key."""

    def __init__(self, reason: str):
        self.reason = reason
        super().__init__(reason)


def source_url(source_kind: str, source_ref: str) -> str:
    """The URL yt-dlp should fetch. YouTube stores the 11-char id (the adapter reconstructs the watch
    URL); ad-hoc sources store the URL verbatim."""
    return adapters.resolve_adapter(source_kind, source_ref).source_url(source_ref)


def reference_url(job, asset) -> str | None:
    """The clean "downloaded from" URL for a job — shared by the private Downloads page and the public
    watch page so both surfaces always agree. None for edit derivatives (a clip's source is the user's
    own earlier download, not a web page); else the canonical page URL yt-dlp recorded; else one derived
    from source_kind+source_ref (covers queued/older rows before the worker fills it)."""
    if job is None or job.job_kind == "edit":
        return None
    if asset is not None and asset.source_webpage_url:
        return asset.source_webpage_url
    if job.source_kind in ("youtube", "url"):
        return source_url(job.source_kind, job.source_ref)
    return None


def get_or_create_asset(
    db: Session, source_kind: str, source_ref: str, format_sig: str
) -> MediaAsset:
    """Fetch the cache row for this (source, format) or create a fresh `pending` one.

    Races on the unique cache key are resolved by re-selecting after an IntegrityError, so two
    simultaneous enqueues of the same video+format converge on one shared asset."""
    stmt = select(MediaAsset).where(
        MediaAsset.source_kind == source_kind,
        MediaAsset.source_ref == source_ref,
        MediaAsset.format_sig == format_sig,
    )
    asset = db.execute(stmt).scalar_one_or_none()
    if asset is not None:
        # A previously-FAILED shared asset must be re-attempted for the new job about to hold it —
        # reset it to pending (+clear the error) so the worker actually re-downloads instead of
        # short-circuiting the new job with the asset's stale error. (Mirrors resume_download; without
        # this a fresh enqueue of a once-failed (source,format) pair is permanently poisoned, since
        # errored assets carry no expires_at and GC never clears them.)
        if asset.status == "error":
            asset.status = "pending"
            asset.error = None
        return asset
    asset = MediaAsset(
        source_kind=source_kind,
        source_ref=source_ref,
        format_sig=format_sig,
        status="pending",
        ref_count=0,
    )
    db.add(asset)
    try:
        db.flush()
    except IntegrityError:
        db.rollback()
        asset = db.execute(stmt).scalar_one()
    return asset


def populate_from_catalog(db: Session, asset: MediaAsset) -> bool:
    """Fill an asset's display metadata (title/uploader/thumbnail/date/duration) from our own
    catalog when the source is a known YouTube video — so a queued/downloading row shows the
    real title + thumbnail immediately instead of the bare id. 0 network cost. Returns True if
    it found a catalog match."""
    if asset.source_kind != "youtube" or asset.title:
        return False
    video = db.get(Video, asset.source_ref)
    if video is None:
        return False
    asset.title = video.title
    asset.thumbnail_url = video.thumbnail_url
    asset.duration_s = video.duration_seconds
    if video.published_at:
        asset.upload_date = video.published_at.date()
    channel = db.get(Channel, video.channel_id)
    if channel is not None:
        asset.uploader = channel.title
    return True


def next_queue_pos(db: Session) -> int:
    return (db.execute(select(func.coalesce(func.max(DownloadJob.queue_pos), 0))).scalar() or 0) + 1


def enqueue(
    db: Session,
    user_id: int,
    source_kind: str,
    source_ref: str,
    spec: dict,
    profile_id: int | None = None,
    display_name: str | None = None,
) -> DownloadJob:
    """Queue a download for `user_id`. Returns the DownloadJob (already `done` on a cache hit).

    Raises quota.QuotaExceeded if the user is at their job-count or footprint cap."""
    quota.check_enqueue(db, user_id)
    spec = formats.normalize(spec)
    sig = formats.format_sig(spec)
    asset = get_or_create_asset(db, source_kind, source_ref, sig)
    # Show a real title + thumbnail the moment it's queued (feed downloads are catalog videos).
    populate_from_catalog(db, asset)

    job = DownloadJob(
        user_id=user_id,
        asset_id=asset.id,
        source_kind=source_kind,
        source_ref=source_ref,
        profile_id=profile_id,
        profile_snapshot=spec,
        display_name=display_name or (asset.title[:255] if asset.status == "ready" and asset.title else None),
        status="queued",
        queue_pos=next_queue_pos(db),
    )
    db.add(job)
    asset.ref_count = (asset.ref_count or 0) + 1

    # Cache hit: the file already exists — no worker round-trip needed.
    if asset.status == "ready":
        job.status = "done"
        job.progress = 100
        asset.last_access_at = datetime.now(timezone.utc)

    db.commit()
    db.refresh(job)
    return job


def _clip_title(source_title: str | None, display_name: str | None) -> str:
    if display_name:
        return display_name[:255]
    base = source_title or "Clip"
    return f"{base} (clip)"[:255]


def enqueue_edit(
    db: Session,
    user_id: int,
    source_job: DownloadJob,
    edit_spec: dict,
    display_name: str | None = None,
) -> DownloadJob:
    """Queue a phase-2 editor derivative (trim/crop) of `source_job` for `user_id`.

    The derivative is per-user (never shared-cached): its asset uses `source_kind='edit'` with a
    cache key that embeds the user id, so an identical re-edit by the same user is a cache hit but
    it never dedups across users. Reuses the same worker/quota/GC path as a download.

    Raises quota.QuotaExceeded (holdings cap) or EditError (empty spec / source not ready)."""
    src_asset = db.get(MediaAsset, source_job.asset_id) if source_job.asset_id else None
    if src_asset is None or src_asset.status != "ready" or not src_asset.rel_path:
        raise EditError("source_not_ready")

    spec = editmod.normalize_edit_spec(edit_spec)
    if not spec:
        raise EditError("empty_edit")

    quota.check_enqueue(db, user_id)

    sig = editmod.edit_sig(spec)
    ref = f"{user_id}:{src_asset.id}"[:512]
    asset = get_or_create_asset(db, "edit", ref, sig)
    if not asset.title:
        asset.title = _clip_title(src_asset.title, display_name)
        asset.uploader = src_asset.uploader
        asset.thumbnail_url = src_asset.thumbnail_url
        asset.upload_date = src_asset.upload_date
        asset.duration_s = editmod.clip_duration(spec, src_asset.duration_s)

    job = DownloadJob(
        user_id=user_id,
        asset_id=asset.id,
        job_kind="edit",
        source_kind="edit",
        source_ref=ref,
        source_job_id=source_job.id,
        source_asset_id=src_asset.id,
        edit_spec=spec,
        profile_snapshot={},
        display_name=display_name or asset.title,
        status="queued",
        queue_pos=next_queue_pos(db),
    )
    db.add(job)
    asset.ref_count = (asset.ref_count or 0) + 1

    if asset.status == "ready":  # identical clip already produced for this user → instant
        job.status = "done"
        job.progress = 100
        asset.last_access_at = datetime.now(timezone.utc)

    db.commit()
    db.refresh(job)
    return job


def release_asset(db: Session, job: DownloadJob) -> None:
    """Drop this job's hold on its asset when it leaves a holding state. Once NO job holds the
    asset anymore, delete the file + row immediately — a deleted download should free its disk,
    and the shared cache only needs to span *overlapping* holders (a later re-add just downloads
    again). `error` counts as holding: enqueue always +1'd ref_count and the worker never
    decrements on failure (ref_count is the route's job), so an errored job releases here on
    delete — else its +1 leaks and a later resume→ready keeps the file pinned past its last holder.
    Idempotent for the cancel path: cancel already released while the job was holding, then set it
    `canceled` (∉ the set below), so delete-after-cancel is a no-op and never double-releases.

    We DON'T delete an errored asset row here even at ref==0: another request may be concurrently
    re-enqueuing the same (source,format) — get_or_create_asset would reset that row to `pending` and
    +1 it, and deleting it under that would FK-null the new job's asset (a lost update on ref_count).
    A ready asset is still freed at ref==0 (its file is the point); an orphaned errored row is cheap
    (no file) and gets reused+reset by the next enqueue, or reclaimed by a later GC pass."""
    if not job.asset_id or job.status not in HOLDING:
        return
    asset = db.get(MediaAsset, job.asset_id)
    if asset is None:
        return
    asset.ref_count = max(0, (asset.ref_count or 0) - 1)
    if asset.ref_count == 0 and asset.status == "ready":
        if asset.rel_path:
            storage.delete_asset_files(settings.download_root, asset.rel_path)
        db.delete(asset)