peter
fa35925cc6
Follow-up to user prod testing of 0.51.0: - re-download now clears job.display_name so the card title + Content-Disposition filename are re-derived from the freshly-cleaned title (previously an auto-name from an older un-cleaned title — still carrying a "… views · … reactions |" prefix — survived the rebuild). - on-disk AND served names are now a strict shell-safe slug: only [A-Za-z0-9._-] survive; every other char (the "!" the user saw, plus ( ) [ ] & $ ' " ; | ? * …) collapses to "_". The id no longer uses [brackets] (glob metacharacters). Shared _slug helper for sanitize + display_filename. - GC gains a 5th pass: sweep on-disk files/dirs no ready asset owns (old accented channel dirs, a poster from a superseded naming scheme left after a re-download), skipping the dot system trees and anything newer than an hour so an in-flight download is never touched. - Tests: slug strips !/$/()[]; rel_path is bracket-free; orphan-sweep keeps owned/system/fresh files.
71 lines
2.5 KiB
Python
71 lines
2.5 KiB
Python
"""Orphan-file sweep: remove on-disk cruft no ready asset owns (old accented dirs, stale posters),
|
|
while never touching system trees, owned files, or freshly-written downloads."""
|
|
import os
|
|
import time
|
|
from pathlib import Path
|
|
|
|
from app.downloads.gc import _sweep_orphan_files
|
|
|
|
|
|
class _Scalars:
|
|
def __init__(self, rows):
|
|
self._rows = rows
|
|
|
|
def scalars(self):
|
|
return list(self._rows)
|
|
|
|
|
|
class _StubDB:
|
|
"""Minimal stand-in: `_sweep_orphan_files` only issues one select for ready rel_paths."""
|
|
|
|
def __init__(self, rel_paths):
|
|
self._rel_paths = rel_paths
|
|
|
|
def execute(self, _stmt):
|
|
return _Scalars(self._rel_paths)
|
|
|
|
|
|
def _aged(path: Path, hours: float) -> None:
|
|
old = time.time() - hours * 3600
|
|
os.utime(path, (old, old))
|
|
|
|
|
|
def test_sweep_removes_orphans_but_keeps_owned_system_and_fresh(tmp_path: Path):
|
|
root = tmp_path
|
|
# An owned asset (in the keep set) + its sidecars.
|
|
kept_dir = root / "Chan" / "Season_2026"
|
|
kept_dir.mkdir(parents=True)
|
|
kept_media = kept_dir / "Chan_-_2026-01-01_-_Title_vid_a1.mp4"
|
|
for p in (kept_media, kept_media.with_suffix(".nfo"), kept_media.with_suffix(".jpg")):
|
|
p.write_bytes(b"x")
|
|
_aged(p, 5) # old, but owned → must survive
|
|
|
|
# An orphan poster in a stale (e.g. old accented) channel dir — old, unowned → swept.
|
|
orphan_dir = root / "OldChan" / "Season_2026"
|
|
orphan_dir.mkdir(parents=True)
|
|
orphan = orphan_dir / "OldChan_-_old_title_vid.jpg"
|
|
orphan.write_bytes(b"x")
|
|
_aged(orphan, 5)
|
|
|
|
# A system tree (storyboards) — never touched, even when old.
|
|
sysfile = root / ".storyboards" / "asset-1.jpg"
|
|
sysfile.parent.mkdir()
|
|
sysfile.write_bytes(b"x")
|
|
_aged(sysfile, 5)
|
|
|
|
# A brand-new unowned file (an in-flight download's just-placed output) — too young to sweep.
|
|
fresh_dir = root / "FreshChan" / "Season_2026"
|
|
fresh_dir.mkdir(parents=True)
|
|
fresh = fresh_dir / "FreshChan_-_now_vid_a2.mp4"
|
|
fresh.write_bytes(b"x") # mtime = now
|
|
|
|
db = _StubDB(["Chan/Season_2026/Chan_-_2026-01-01_-_Title_vid_a1.mp4"])
|
|
removed = _sweep_orphan_files(db, str(root))
|
|
|
|
assert removed == 1 # only the aged orphan
|
|
assert kept_media.exists() and kept_media.with_suffix(".jpg").exists()
|
|
assert not orphan.exists() and not orphan_dir.exists() # orphan + its emptied dirs pruned
|
|
assert not (root / "OldChan").exists()
|
|
assert sysfile.exists() # system tree untouched
|
|
assert fresh.exists() # too new to sweep
|