fix(images): background jobs skip files hidden by the removal mark; walkers skip trash folders inside output roots (#501)

- Thumbnail jobs and the legacy scan_output_dir listing leave
  library-removed files out (one mark check, mark_hides).
- Missing-file links also forgets removal marks that hide nothing any
  more (file gone from a folder that exists, or changed), only under a
  readable, non-empty source, re-checked at apply.
- The sidebar Images, Favorites and Needs review counts and the
  collection counts are read again when an image_delete job ends.
- utils/media_folders.py: one skip for thumbnails and trash folders
  (.Trash, .Trash-<uid>, .Trashes, $RECYCLE.BIN) used by every walker,
  the image monitor and the delete review.
This commit is contained in:
Vito Sansevero
2026-10-29 13:25:23 -07:00
parent 66ca988d2a
commit 245d0cdc6a
15 changed files with 635 additions and 91 deletions
+12 -6
View File
@@ -66,6 +66,7 @@ try:
from ...database.models import normalize_image_path
from ...database.run_attribution import recorded_output_lookup
from ...utils.card_seed import card_seed, header_params, parsed_positive
from ...utils.media_folders import in_skipped_folder, is_skipped_folder
from ...utils.parallel import map_parallel
from ...utils.json_strict import dumps_strict
from ...utils.inspection_response import (
@@ -91,6 +92,7 @@ except ImportError:
from database.models import normalize_image_path
from database.run_attribution import recorded_output_lookup
from utils.card_seed import card_seed, header_params, parsed_positive
from utils.media_folders import in_skipped_folder, is_skipped_folder
from utils.parallel import map_parallel
from utils.json_strict import dumps_strict
from utils.inspection_response import (
@@ -915,7 +917,8 @@ def _name_suffix(name):
def _walk_media(output_path, max_files):
"""Yield the ``os.DirEntry`` of each media file under *output_path*.
Symlinks are never followed, ``thumbnails/`` is skipped, descent stops
Symlinks are never followed, ``thumbnails/`` and trash folders are
skipped (``utils.media_folders``, #501), descent stops
at MAX_SCAN_DEPTH and at most *max_files* entries are produced. The order
is ``os.walk``'s (top-down, subfolders in ``os.scandir`` order, files by
name), which the gallery's ties in mtime keep. Each entry's type comes
@@ -927,8 +930,6 @@ def _walk_media(output_path, max_files):
produced = 0
while stack:
top, rel_parts = stack.pop()
if "thumbnails" in rel_parts:
continue
dirs, files = [], []
try:
with os.scandir(top) as entries:
@@ -952,7 +953,7 @@ def _walk_media(output_path, max_files):
if len(rel_parts) >= MAX_SCAN_DEPTH:
continue
for entry in reversed(dirs):
if not entry.is_symlink():
if not entry.is_symlink() and not is_skipped_folder(entry.name):
stack.append((entry.path, rel_parts + (entry.name,)))
@@ -976,7 +977,7 @@ def _settled_entry(root, relative):
*folders, name = relative.split(os.sep)
if _name_suffix(name).lower() not in MEDIA_EXTENSIONS:
return None
if "thumbnails" in folders or len(folders) > MAX_SCAN_DEPTH:
if in_skipped_folder(folders) or len(folders) > MAX_SCAN_DEPTH:
return None
folder = os.fspath(root)
for part in ("", *folders):
@@ -3075,7 +3076,9 @@ class ImageRoutesMixin:
no symlinks), each preview folder is listed once, and at most
MAX_THUMBNAIL_FILES targets are queued per batch (a job plans again
after each batch); ``remaining`` counts the targets beyond that cap.
Sources in *exclude* (worked on by an earlier batch) are left out.
Sources in *exclude* (worked on by an earlier batch) are left out, and
so are files removed from the library (#501: a removal mark hides
them, and their previews went with their records).
``stop()`` true ends the walk before the next file.
"""
settings = writer_settings(settings)
@@ -3084,11 +3087,14 @@ class ImageRoutesMixin:
plan = {key: 0 for key in _PLAN_COUNTS}
plan.update(targets=[], fresh_files=[])
folders = {}
removed = self._removal_check_under(output_path)
for src in _iter_media_files(output_path, MAX_GALLERY_FILES):
if stop is not None and stop():
break
if exclude and src in exclude:
continue
if removed(src):
continue
rel_no_ext = src.relative_to(output_path).with_suffix("")
stem = f"{rel_no_ext.name}{thumbnail_settings.THUMB_SUFFIX}"
dst = thumbnails_dir / rel_no_ext.parent / (stem + settings.extension)