nodes/ComfyAssets-ComfyUI_PromptManager
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

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

Browse Source 
- 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
Download Patch File Download Diff File Expand all files Collapse all files
py/api/admin.py
+12 -10
View File
@@ -36,10 +36,13 @@ except ImportError:
try:
from ...utils import exit_signal
from ...utils.media_folders import is_skipped_folder
except ImportError:
from utils import exit_signal
from utils.media_folders import is_skipped_folder
try:
from ...database.image_removal import mark_hides
from ...database.pair_ingestion import SCAN_MARKS, ingest_resolved_pair
from ...database.run_attribution import (
RecordedOutput,
@@ -60,6 +63,7 @@ try:
decide_file_prompt,
)
except ImportError:
from database.image_removal import mark_hides
from database.pair_ingestion import SCAN_MARKS, ingest_resolved_pair
from database.run_attribution import (
RecordedOutput,
@@ -118,10 +122,11 @@ DUPLICATE_FIND_LEGACY_TITLE = "Find duplicate image files (gallery page)"
def _collect_media_files(output_dirs, extensions):
"""Media files under ``output_dirs`` (blocking), bounded and symlink-free.
Walks each root without following symlinks, skips ``thumbnails``
directories and symlinked files, never descends more than MAX_SCAN_DEPTH
levels and stops after MAX_SCAN_FILES files in total. Extensions match
case-insensitively and each path is listed once.
Walks each root without following symlinks, skips ``thumbnails`` and
trash folders (``utils.media_folders``) and symlinked files, never
descends more than MAX_SCAN_DEPTH levels and stops after MAX_SCAN_FILES
files in total. Extensions match case-insensitively and each path is
listed once.
"""
wanted = {ext.lower() for ext in extensions}
found = []
@@ -136,7 +141,7 @@ def _collect_media_files(output_dirs, extensions):
dirnames[:] = sorted(
d
for d in dirnames
if d != "thumbnails"
if not is_skipped_folder(d)
and depth < MAX_SCAN_DEPTH
and not os.path.islink(os.path.join(current, d))
)
@@ -893,11 +898,8 @@ class AdminRoutesMixin:
stat = os.stat(path)
except OSError:
continue
mark = marks.get(os.path.normcase(os.path.realpath(str(path))))
if mark is not None and tuple(mark) == (
stat.st_size,
stat.st_mtime_ns,
):
locator = os.path.normcase(os.path.realpath(str(path)))
if locator in marks and mark_hides(marks, locator, path):
continue
key = _physical_file_key(path, stat)
if key not in seen:
py/api/autotag_routes.py
+13 -3
View File
@@ -23,6 +23,11 @@ from .prompts import thumbnail_url_for
from . import thumbnail_settings
from .. import model_gate
try:
from ...utils.media_folders import is_skipped_folder
except ImportError:
from utils.media_folders import is_skipped_folder
from aiohttp import web
_INTERNAL_ERROR = "An internal error occurred. Check server logs for details."
@@ -1319,8 +1324,9 @@ class AutotagRoutesMixin:
def _collect_scan_files(output_path: Path):
"""Media files under ``output_path`` from a bounded, symlink-free walk.
Descends at most ``_SCAN_MAX_DEPTH`` levels, skips ``thumbnails``
trees and symlinked files, and stops after ``_SCAN_MAX_FILES`` files.
Descends at most ``_SCAN_MAX_DEPTH`` levels, skips ``thumbnails`` and
trash folders (``utils.media_folders``) and symlinked files, and stops
after ``_SCAN_MAX_FILES`` files.
Returns ``(paths, truncated)``.
"""
found = []
@@ -1330,7 +1336,7 @@ class AutotagRoutesMixin:
dirnames[:] = sorted(
name
for name in dirnames
if name != "thumbnails" and depth + 1 <= _SCAN_MAX_DEPTH
if not is_skipped_folder(name) and depth + 1 <= _SCAN_MAX_DEPTH
)
for name in sorted(filenames):
if Path(name).suffix.lower() not in _MEDIA_EXTENSIONS:
@@ -1357,6 +1363,10 @@ class AutotagRoutesMixin:
files, truncated = await self._run_in_executor(
self._collect_scan_files, output_path
)
# #501: a file removed from the library is not offered for tagging.
files = await self._run_in_executor(
self._without_removed, output_path, files
)
has_thumbnails = (output_path / "thumbnails").is_dir()
images = []
py/api/image_delete.py
+40 -32
View File
@@ -47,12 +47,16 @@ from .maintenance import MAINTENANCE_PREVIEW_LEASE, _fail_job, _failure, backup_
try:
from ...database import image_removal_schema
from ...database.image_removal import mark_hides
from ...database.annotation_schema import MAX_LOCATOR_LENGTH
from ...utils import trash
from ...utils.media_folders import is_trash_folder
except ImportError:
from database import image_removal_schema
from database.image_removal import mark_hides
from database.annotation_schema import MAX_LOCATOR_LENGTH
from utils import trash
from utils.media_folders import is_trash_folder
IMAGE_DELETE = "delete_images"
MODES = ("library", "trash")
@@ -61,7 +65,6 @@ TITLES = {
"trash": "Delete images (move to the trash)",
}
MAX_DETAIL_ROWS = 50
TRASH_FOLDERS = frozenset({".trash", ".trashes", "$recycle.bin"})
# Reason codes (design §4.4) and the sentence each shows.
REASONS = {
@@ -93,19 +96,12 @@ SOURCES_CHANGED = "The sources changed since the review; nothing was changed."
RECORDS_FAILED = "The image records could not be removed; the job stopped."
def _is_trash_folder(name: str) -> bool:
folded = name.casefold()
return folded in TRASH_FOLDERS or (
folded.startswith(".trash-") and folded[7:].isdigit()
)
def lexical_problem(relative: str) -> str | None:
"""The refusal code a root-relative POSIX path earns before any file access."""
parts = relative.split("/")
if "thumbnails" in parts[:-1]:
return "thumbnail"
if any(_is_trash_folder(part) for part in parts[:-1]):
if any(is_trash_folder(part) for part in parts[:-1]):
return "trash-folder"
if os.path.splitext(parts[-1])[1].lower() not in DELETABLE_MEDIA_EXTENSIONS:
return "not-media"
@@ -443,37 +439,49 @@ class ImageDeleteMixin:
if not marks:
return set()
located = self._workspace_locators(listings)
hidden = set()
for locator, (size, mtime_ns) in marks.items():
entry = located.get(locator)
if entry is None:
continue
try:
info = os.lstat(entry.path)
except OSError:
continue
if (info.st_size, info.st_mtime_ns) == (size, mtime_ns):
hidden.add(entry.normalized)
return hidden
return {
entry.normalized
for locator, entry in ((locator, located.get(locator)) for locator in marks)
if entry is not None and mark_hides(marks, locator, entry.path)
}
def _removed_paths(self, paths) -> set:
"""The absolute paths among *paths* a removal mark hides (blocking)."""
marks = self._removal_marks()
if not marks:
return set()
hidden = set()
for path in paths:
mark = marks.get(os.path.normcase(os.path.realpath(str(path))))
if mark is None:
continue
try:
info = os.lstat(path)
except OSError:
continue
if (info.st_size, info.st_mtime_ns) == tuple(mark):
hidden.add(str(path))
return {
str(path)
for path in paths
if mark_hides(marks, os.path.normcase(os.path.realpath(str(path))), path)
}
def _removal_check_under(self, root):
"""``hidden(path) -> bool`` for files a walk of *root* found (blocking).
A walk never follows a link below *root*, so a file's locator is
``normcase(join(realpath(root), relative))``: no ``realpath`` per
file, and an ``lstat`` only for a marked one. Without marks it
answers False at once.
"""
marks = self._removal_marks()
if not marks:
return lambda _path: False
root = os.fspath(root)
real = os.path.realpath(root)
def hidden(path):
relative = os.path.relpath(os.fspath(path), root)
locator = os.path.normcase(os.path.join(real, relative))
return mark_hides(marks, locator, path)
return hidden
def _without_removed(self, root, paths) -> list:
"""*paths* found by a walk of *root*, less the hidden ones (blocking)."""
removed = self._removal_check_under(root)
return [path for path in paths if not removed(path)]
def parse_mode(value):
"""The apply's ``mode``, or None when it is not one of MODES."""
py/api/images.py
+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)
py/api/maintenance.py
+9 -3
View File
@@ -281,7 +281,7 @@ def short_space_message(short):
)
def _changed_line(operation, count):
def _changed_line(operation, count, marks=0):
if operation == "optimize":
return "Optimized the database"
if operation == "duplicate_prompts":
@@ -291,7 +291,11 @@ def _changed_line(operation, count):
noun = "unused prompt component" if count == 1 else "unused prompt components"
return f"Removed {count:,} {noun}"
noun = "link to a missing file" if count == 1 else "links to missing files"
return f"Removed {count:,} {noun}"
line = f"Removed {count:,} {noun}"
if marks:
gone = "removed image" if marks == 1 else "removed images"
line += f"; forgot {marks:,} {gone} whose files are gone or changed"
return line
def take_safety_backup(model, label="backup"):
@@ -419,6 +423,7 @@ class MaintenanceRoutesMixin:
draft.public(),
{
"targets": draft.targets,
"marks": draft.marks,
"roots": roots,
"protected": draft.protected["count"],
"rows": draft.scope["count"],
@@ -653,6 +658,7 @@ class MaintenanceRoutesMixin:
plan.fingerprint,
payload["targets"],
payload["roots"],
payload.get("marks", ()),
)
except PlanChanged:
return _fail_job(job, "plan-changed", PLAN_CHANGED)
@@ -664,7 +670,7 @@ class MaintenanceRoutesMixin:
)
job.record_counted("changed", result["changed"], rows)
job.record_counted("protected", payload["protected"])
line = _changed_line(plan.operation, result["changed"])
line = _changed_line(plan.operation, result["changed"], result.get("marks", 0))
job.log_line(line)
job.update(progress=100, status_line=f"{line} · {backup_note(backup)}")