inkwell/src/thoughtsync/retention.py

"""Trash retention — what "permanently deleted" means, and when it happens by itself.

Two things live here, deliberately together:

**`purge_note`** — the single definition of destroying a note. Three callers reach
permanent deletion by different routes (the user's Delete forever in the web UI,
a client's `op=delete` over sync, and the sweeper below), and if each had its own
idea of what to tear down they would drift — one would forget the files, another
the revision history, and "permanently deleted" would quietly mean three different
things depending on how you got there.

**The sweeper** — trash that nobody empties is not free: a trashed note keeps its
attachment BYTES on disk for as long as it sits there. So trash expires. The window
is the `trash_retention_days` setting (default 30, `0` = keep forever), re-read on
every pass so a change in admin Settings takes effect without a restart.

A purged note is not a deleted ROW — it's a content-less tombstone. That's what lets
an offline client that reappears next month learn the note is gone instead of
faithfully resurrecting it on the next push.
"""
from __future__ import annotations

import asyncio
import logging
from datetime import datetime, timedelta, timezone

from sqlalchemy import delete as sa_delete
from sqlalchemy import select

from .config import Config
from .db import session_scope
from .models.label import NoteLabel
from .models.note import Note
from .models.note_attachment import NoteAttachment
from .models.note_item import NoteItem
from .models.note_link import NoteLink
from .models.note_link_preview import NoteLinkPreview
from .models.note_revision import NoteRevision
from .settings import get_setting

logger = logging.getLogger(__name__)

# How often the sweeper wakes. Retention is measured in days, so anything under
# "a few times a day" buys nothing but load — a note trashed at 09:00 expiring at
# 14:00 rather than 09:00 thirty days later is not a difference anyone can feel.
SWEEP_INTERVAL_SECONDS = 6 * 60 * 60

# Let the app finish booting (migrations, first requests) before the first sweep.
SWEEP_STARTUP_DELAY_SECONDS = 60

# Rows purged per transaction. A long-neglected install could have thousands of
# expired notes on the first sweep; committing in batches keeps that from becoming
# one enormous transaction holding locks while it deletes files.
SWEEP_BATCH = 200


def expired_before(now: datetime, retention_days: int) -> datetime | None:
    """The cutoff: trash older than this has expired. `None` = retention is off.

    Kept separate from the query so the window arithmetic — including the two ways
    to say "never" (0 and negative, the latter reachable by typing a stray minus in
    Settings) — is testable without a database.
    """
    if retention_days <= 0:
        return None
    return now - timedelta(days=retention_days)


async def purge_note(db, note: Note, edited_at: datetime | None = None) -> None:
    """Turn a note into a content-less tombstone: delete its children (and the
    attachment files on disk), clear its content, stamp `purged_at`.

    The row survives on purpose — offline clients read it off the delta feed and
    learn the note is gone. Everything that carries the note's CONTENT goes, and
    that includes history: a revision row holds the full body, so leaving revisions
    behind would mean the text of a "permanently deleted" note is still on the
    server, recoverable by anyone who can read the table.
    """
    atts = (await db.scalars(select(NoteAttachment).where(NoteAttachment.note_id == note.id))).all()
    for a in atts:
        try:
            (Config.media_root() / a.path).unlink(missing_ok=True)
        except OSError:
            # A missing or unreadable file must not strand the row: the DB record is
            # what the user asked us to destroy, and a failed unlink leaving it in
            # place would make the note reappear whole on the next sweep.
            logger.warning("couldn't remove attachment file %s during purge", a.path, exc_info=True)
    await db.execute(sa_delete(NoteAttachment).where(NoteAttachment.note_id == note.id))
    await db.execute(sa_delete(NoteItem).where(NoteItem.note_id == note.id))
    await db.execute(sa_delete(NoteLabel).where(NoteLabel.note_id == note.id))
    await db.execute(sa_delete(NoteLink).where(NoteLink.source_id == note.id))
    await db.execute(sa_delete(NoteLinkPreview).where(NoteLinkPreview.note_id == note.id))
    await db.execute(sa_delete(NoteRevision).where(NoteRevision.note_id == note.id))
    note.title = None
    note.body = ""
    note.display_title = ""
    # `deleted_at` deliberately SURVIVES. It's still true — that is when the note was
    # deleted — and keeping it means every ordinary query, present and future, that
    # says "not trashed" (`deleted_at IS NULL`) excludes tombstones for free. Clearing
    # it would leave a content-less row looking like a perfectly normal active note,
    # and it would surface on the board as a blank card. Only the Trash view, which
    # asks for `deleted_at IS NOT NULL`, has to name `purged_at` explicitly.
    note.remind_at = None
    note.purged_at = datetime.now(timezone.utc)
    if edited_at is not None:
        note.updated_at = edited_at


async def sweep_expired_trash(db, retention_days: int, *, now: datetime | None = None) -> int:
    """Purge every note whose trash has expired. Returns how many were purged.

    Runs across ALL owners — it's a server-wide policy, not a per-user action, and
    the sweeper has no session to scope it by (rule 47 is about honoring the ACL on
    user-initiated reads, not about exempting rows from server maintenance).
    """
    cutoff = expired_before(now or datetime.now(timezone.utc), retention_days)
    if cutoff is None:
        return 0
    total = 0
    while True:
        expired = (
            await db.scalars(
                select(Note)
                .where(
                    Note.deleted_at.is_not(None),
                    Note.deleted_at < cutoff,
                    # Already a tombstone. Without this the purge would re-run on
                    # every sweep forever, bumping sync_revision each time and
                    # handing clients an endless stream of "news" about one note.
                    Note.purged_at.is_(None),
                )
                .order_by(Note.deleted_at)
                .limit(SWEEP_BATCH)
            )
        ).all()
        if not expired:
            return total
        for note in expired:
            await purge_note(db, note)
        await db.commit()
        total += len(expired)


async def sweep_once() -> int:
    """One sweep against the live retention setting, in its own session."""
    async with session_scope() as db:
        try:
            days = int(await get_setting(db, "trash_retention_days"))
        except (KeyError, TypeError, ValueError):
            return 0
        return await sweep_expired_trash(db, days)


async def run_sweeper() -> None:
    """The background loop. Started in `before_serving`, cancelled on shutdown.

    A sweep failure (DB blip, unreadable media directory) must never take the loop
    down with it — the next pass simply finds the same expired rows and tries again.
    """
    await asyncio.sleep(SWEEP_STARTUP_DELAY_SECONDS)
    while True:
        try:
            purged = await sweep_once()
            if purged:
                logger.info("trash retention: purged %d expired note(s)", purged)
        except asyncio.CancelledError:
            raise
        except Exception:
            logger.exception("trash retention sweep failed; will retry next pass")
        await asyncio.sleep(SWEEP_INTERVAL_SECONDS)