Merge remote-tracking branch 'origin/feat/332-image-categories-pr1' into feat/331-collections-pr1

Keep both features: a duplicate removal moves collection memberships and
copies the image category; both migrations and schema checks run; the
legacy route snapshot now records the six collection routes beside the
image category routes.
This commit is contained in:
Vito Sansevero
2026-10-28 04:34:24 -07:00
24 changed files with 1878 additions and 12 deletions
+3
View File
@@ -73,6 +73,7 @@ from .diagnostics_report import DiagnosticsReportMixin
from .autotag_routes import AutotagRoutesMixin
from .lora_integration import LoraIntegrationMixin
from .lora_import_routes import LoraImportRoutesMixin
from .image_categories import ImageCategoryRoutesMixin
try:
from ...database.operations import PromptDatabase
@@ -338,6 +339,7 @@ class PromptManagerAPI(
AutotagRoutesMixin,
LoraIntegrationMixin,
LoraImportRoutesMixin,
ImageCategoryRoutesMixin,
):
"""REST API handler for PromptManager operations and web interface.
@@ -703,6 +705,7 @@ class PromptManagerAPI(
self._register_autotag_routes(routes)
self._register_lora_routes(routes)
self._register_lora_import_routes(routes)
self._register_image_category_routes(routes)
# Register gzip compression middleware (once)
global _gzip_registered
+4
View File
@@ -591,6 +591,7 @@ class DuplicateFilesMixin:
totals = dict.fromkeys(
("moved", "merged", "favorites", "tags", "review", "collections"), 0
)
totals["categories"] = 0 # image categories kept on the kept copies (#332)
for done, target in enumerate(targets, start=1):
if failure is not None:
self._record_target(job, "kept", target, NOT_ATTEMPTED)
@@ -642,6 +643,9 @@ class DuplicateFilesMixin:
job.log_line(
f"Added {_plural(totals['tags'], 'image tag')} to the kept copies"
)
if totals.get("categories"):
kept = _plural(totals["categories"], "image category", "image categories")
job.log_line(f"Kept {kept} on the kept copies")
if totals["review"]:
job.log_line(
f"Settled {_plural(totals['review'], 'Needs review item')} "
+24 -1
View File
@@ -18,7 +18,7 @@ Blocking: each lookup stats the file's folders once (cached).
import os
from pathlib import Path
from .images import _favorite_relative_key, _favorite_root_key
from .images import _favorite_relative_key, _favorite_root_key, image_category_key
def _identity(path):
@@ -78,6 +78,15 @@ class Spellings:
)
return spelled
@property
def listed_roots(self):
"""The listed roots (the output sources), in order."""
return [root for root, _identity in self._listed]
def category_key(self, path):
"""*path*'s image category file key (#332), or None outside every source."""
return image_category_key(self.listed_roots, path)
def favorites(self, path):
"""``{listed root: path below it (POSIX)}`` for each listed root holding it."""
path = os.path.abspath(str(path))
@@ -126,9 +135,23 @@ def copy_move(target, kept_stat, spellings):
"targets": targets,
"kept_path": target["keeper_abs"],
"favorites": favorites,
"categories": _category_pairs(target, spellings),
"removed_locator": target["locator"],
"kept_locator": target["keeper_locator"],
"sha256": target["hash"],
"kept_size": kept_stat.st_size,
"kept_mtime_ns": kept_stat.st_mtime_ns,
}
def _category_pairs(target, spellings):
"""``[(removed file key, kept file key)]`` for the image category (#332).
From the two absolute paths, not the favorites tuples: those follow the
listed root, which differs from the file key when sources nest.
"""
removed = spellings.category_key(target["abs"])
kept = spellings.category_key(target["keeper_abs"])
if removed is None or kept is None:
return []
return [(removed, kept)]
+361
View File
@@ -0,0 +1,361 @@
"""Image category routes (#332): an image file's own category.
``PUT /prompt_manager/images/category`` sets the own category of up to 500
listed files; ``DELETE`` removes it (listed or not, so a missing file's
category can still be removed); ``GET /prompt_manager/images/categories``
lists the own-category values of files the sources list. Targets are the
Images listing identity (``{root_index, root_scope, path}``, checked by
``media_target``) of an output source; LoRA folders are not sources here.
Instead of ``items`` a request may name ``filter``, the Images listing's own
query ("Select all N matching", #392), resolved now up to 500 images.
Each file is stored under its file key (``images.image_category_key``).
These routes never read or write prompts, recipes or image links.
"""
import os
from pathlib import Path
from aiohttp import web
from .image_tag_jobs import MAX_JOB_TARGETS, _parse_targets
from .images import (
_favorite_relative_key,
_favorite_root_key,
_forbidden,
_json_body_or_error,
image_category_key,
)
from .prompts import bad_request
try:
from ...database.image_categories import MAX_CATEGORY_LENGTH, MAX_KEY_LENGTH
from ...utils.validators import validate_category
except ImportError:
from database.image_categories import MAX_CATEGORY_LENGTH, MAX_KEY_LENGTH
from utils.validators import validate_category
CATEGORY_MEDIA_MESSAGE = "Only media files can have a category"
_PUT_FIELDS = frozenset({"category"})
_DELETE_FIELDS = frozenset()
TOO_MANY = f"Select at most {MAX_JOB_TARGETS} images."
SOURCE_CHANGED_MESSAGE = "The sources changed. Refresh the images and try again."
WRITE_FAILED = "The category could not be changed."
READ_FAILED = "Image categories could not be read."
def _coded(status: int, code: str, message: str) -> web.Response:
return web.json_response(
{"success": False, "code": code, "error": message},
status=status,
headers={"Cache-Control": "no-store"},
)
def _category_value(raw) -> tuple[str | None, web.Response | None]:
"""The stripped category, or a 400 (an empty value is a 400: use DELETE)."""
if not isinstance(raw, str):
return None, bad_request("category must be a string")
value = raw.strip()
if not value:
return None, bad_request("category must not be empty")
if len(value) > MAX_CATEGORY_LENGTH:
return None, bad_request(
f"Category cannot exceed {MAX_CATEGORY_LENGTH} characters"
)
try:
value.encode("utf-8")
validate_category(value)
except UnicodeEncodeError:
return None, bad_request("category must be valid text")
except ValueError as exc:
return None, bad_request(str(exc))
return value, None
class _KeyRefused(Exception):
"""A target has no storable file key (outside every source, or too long)."""
def __init__(self, message: str = "Access denied"):
super().__init__(message)
self.message = message
def _file_key(roots, root, relative) -> tuple[str, str]:
"""The target's file key (blocking: resolves the sources)."""
key = image_category_key(roots, Path(root) / relative)
if key is None:
raise _KeyRefused()
if max(len(key[0]), len(key[1])) > MAX_KEY_LENGTH:
raise _KeyRefused("Path is too long")
return key
def _nested_sources(root: Path, sources) -> list[tuple[str, str]]:
"""``[(relative key prefix, source root key)]`` of sources inside *root*.
Deepest first, so the first prefix that matches is the file's source.
"""
base = os.path.join(os.path.normcase(os.path.realpath(str(root))), "")
nested = []
for source in sources:
real = os.path.realpath(str(source))
if not os.path.normcase(real).startswith(base):
continue
relative = os.path.relpath(real, os.path.realpath(str(root)))
nested.append(
(
_favorite_relative_key(relative.replace(os.sep, "/")),
_favorite_root_key(source),
)
)
nested.sort(key=lambda item: item[0].count("/"), reverse=True)
return nested
def _source_prefix(relative_key: str, nested) -> str | None:
"""The prefix of the deepest nested source holding *relative_key*."""
for prefix, _source_key in nested:
if relative_key.startswith(prefix + "/"):
return prefix
return None
class ImageCategoryRoutesMixin:
"""Routes for images' own categories (#332)."""
def _register_image_category_routes(self, routes):
# Fixed paths beside DELETE /prompt_manager/images/{image_id}, as the
# favorite routes are. Registered after it, they still win: aiohttp
# (3.10+) looks fixed paths up before dynamic resources
# (test_delete_category_never_reaches_delete_image).
@routes.put("/prompt_manager/images/category")
async def set_image_category_route(request):
return await self.set_image_category(request)
@routes.delete("/prompt_manager/images/category")
async def clear_image_category_route(request):
return await self.clear_image_category(request)
@routes.get("/prompt_manager/images/categories")
async def list_image_categories_route(request):
return await self.list_image_categories(request)
# -- reading ---------------------------------------------------------------
def _own_category_map(self, sources, listings) -> dict:
"""``{root / listed path: own category}`` for the listed files (blocking).
One primary-key range read per source; each stored row is matched to
the listing of every selected root that holds its source, so the work
follows the stored rows, not the files. A file under a nested source
is keyed by the deepest one (``image_category_key``). A row whose file
is gone matches nothing. A failed read raises.
"""
sources = list(sources)
rows = self.db.own_categories_of(_favorite_root_key(s) for s in sources)
if not rows:
return {}
by_source: dict[str, dict[str, str]] = {}
for (root_key, relative), category in rows.items():
by_source.setdefault(root_key, {})[relative] = category
found = {}
for _index, root, files in listings:
listing = self._favorite_listing(root, files)
root_key = _favorite_root_key(root)
nested = [
item for item in _nested_sources(root, sources) if item[1] != root_key
]
for relative, category in by_source.get(root_key, {}).items():
listed = listing.get(relative)
if listed is not None and _source_prefix(relative, nested) is None:
found[root / listed] = category
for prefix, source_key in nested:
for relative, category in by_source.get(source_key, {}).items():
full = f"{prefix}/{relative}"
listed = listing.get(full)
if listed is not None and _source_prefix(full, nested) == prefix:
found[root / listed] = category
return found
async def _source_listings(self, roots) -> list[tuple]:
return [
(index, root, await self._get_gallery_files(root))
for index, root in enumerate(roots)
]
async def list_image_categories(self, request):
"""GET: the own-category values of listed files, sorted."""
try:
roots = list(self._get_all_output_dirs())
listings = await self._source_listings(roots)
found = await self._run_in_executor(self._own_category_map, roots, listings)
except Exception:
self.logger.exception("Image categories read failed")
return _coded(500, "categories-failed", READ_FAILED)
return web.json_response(
{"success": True, "categories": sorted(set(found.values()))},
headers={"Cache-Control": "no-store"},
)
# -- writing ---------------------------------------------------------------
async def _filter_targets(self, raw):
"""``(targets, None)`` for an Images listing filter, else ``(None, error)``.
"Select all N matching" (#392) sends the listing's own query; it is
resolved now, up to 500 images (a 400 ``too-many-images`` above).
"""
from .images import ListingSourceChanged, parse_listing_filter
try:
selection = await self.resolve_listing_filter(
parse_listing_filter(raw), MAX_JOB_TARGETS
)
except ListingSourceChanged:
return None, _coded(409, "source-changed", SOURCE_CHANGED_MESSAGE)
except ValueError as exc:
return None, bad_request(str(exc))
if selection.truncated:
return None, _coded(400, "too-many-images", TOO_MANY)
return tuple(selection.targets), None
async def _category_request(self, request, fields: frozenset):
"""``(data, targets, roots, None)`` or ``(None, None, None, error)``.
The images are ``items`` (1 to 500 targets) or ``filter`` (all images
an Images listing filter admits), besides *fields*.
"""
data, error = await _json_body_or_error(request)
if error is not None:
return None, None, None, error
names = set(data) - fields
if set(data) & fields != fields or names not in ({"items"}, {"filter"}):
return (
None,
None,
None,
bad_request(
"Request must contain "
+ ", ".join(sorted(fields))
+ (" and " if fields else "")
+ "either items or filter"
),
)
if "filter" in data:
targets, error = await self._filter_targets(data["filter"])
if error is not None:
return None, None, None, error
return data, targets, list(self._get_all_output_dirs()), None
items = data["items"]
if not isinstance(items, list) or not 1 <= len(items) <= MAX_JOB_TARGETS:
return (
None,
None,
None,
bad_request(f"items must list 1 to {MAX_JOB_TARGETS} images"),
)
targets, error = _parse_targets(items, media_message=CATEGORY_MEDIA_MESSAGE)
if error is not None:
return None, None, None, error
try:
for _index, _scope, relative in targets:
relative.encode("utf-8")
except UnicodeEncodeError:
return None, None, None, bad_request("path must be valid text")
roots = list(self._get_all_output_dirs())
for index, scope in dict.fromkeys((t[0], t[1]) for t in targets):
if index >= len(roots):
return None, None, None, bad_request("Invalid gallery root")
error = self._gallery_scope_error(
{"root_scope": scope, "root": str(index)}, roots
)
if error is not None:
if error.status == 409:
error = _coded(409, "source-changed", SOURCE_CHANGED_MESSAGE)
return None, None, None, error
return data, targets, roots, None
def _listed_file_keys(self, roots, targets, files) -> tuple[list, list]:
"""``(listed keys, unlisted keys)`` of the targets (blocking).
A target counts as listed when its source's listing holds it; its key
then follows the listed spelling. Targets folding to one key count
once, and a key that is listed through any target is listed.
"""
listings, listed, missing = {}, {}, {}
for index, _scope, relative in targets:
root = roots[index]
if index not in listings:
listings[index] = self._favorite_listing(root, files[index])
spelled = listings[index].get(_favorite_relative_key(relative))
key = _file_key(roots, root, spelled or relative)
(missing if spelled is None else listed)[key] = True
return list(listed), [key for key in missing if key not in listed]
async def set_image_category(self, request):
"""PUT ``{items, category}``: set the own category of listed files."""
data, targets, roots, error = await self._category_request(request, _PUT_FIELDS)
if error is not None:
return error
category, error = _category_value(data["category"])
if error is not None:
return error
try:
files = {}
for index in dict.fromkeys(t[0] for t in targets):
files[index] = await self._get_gallery_files(roots[index])
listed_keys, missing_keys = await self._run_in_executor(
self._listed_file_keys, roots, targets, files
)
except _KeyRefused as refused:
return _forbidden(refused.message)
except Exception:
self.logger.exception("Image category update failed")
return _coded(500, "category-failed", WRITE_FAILED)
try:
if not listed_keys:
return _coded(
404,
"files-not-found",
"None of the selected images could be found.",
)
counts = await self._run_in_executor(
self.db.set_image_categories, listed_keys, category
)
except Exception:
self.logger.exception("Image category update failed")
return _coded(500, "category-failed", WRITE_FAILED)
return web.json_response(
{
"success": True,
"category": category,
"updated": counts["updated"],
"unchanged": counts["unchanged"],
"not_found": len(missing_keys),
},
headers={"Cache-Control": "no-store"},
)
async def clear_image_category(self, request):
"""DELETE ``{items}``: remove the own category, listed or not."""
_data, targets, roots, error = await self._category_request(
request, _DELETE_FIELDS
)
if error is not None:
return error
try:
keys = await self._run_in_executor(
lambda: list(
dict.fromkeys(_file_key(roots, roots[i], r) for i, _s, r in targets)
)
)
cleared = await self._run_in_executor(self.db.clear_image_categories, keys)
except _KeyRefused as refused:
return _forbidden(refused.message)
except Exception:
self.logger.exception("Image category removal failed")
return _coded(500, "category-failed", WRITE_FAILED)
return web.json_response(
{"success": True, "cleared": cleared},
headers={"Cache-Control": "no-store"},
)
+7 -3
View File
@@ -195,13 +195,17 @@ class _Spec:
return scope
def _parse_targets(raw):
"""Unique validated targets in request order, or ``(None, error)``."""
def _parse_targets(raw, **target_options):
"""Unique validated targets in request order, or ``(None, error)``.
``target_options`` reach the target check (the image category routes
pass their own ``media_message``, #332).
"""
if not isinstance(raw, list) or not 1 <= len(raw) <= MAX_JOB_TARGETS:
return None, bad_request(f"targets must list 1 to {MAX_JOB_TARGETS} images")
seen, targets = set(), []
for item in raw:
target, error = _target(item)
target, error = _target(item, **target_options)
if error is not None:
return None, error
if target not in seen:
+47
View File
@@ -817,6 +817,53 @@ def _favorite_root_key(root) -> str:
return _favorite_relative_key(os.path.realpath(str(root)))
def _source_depth(source: str) -> int:
return len([part for part in re.split(r"[\\/]+", source) if part])
def deepest_source(sources, absolute_path):
"""``(source, POSIX path below it)`` of the deepest source holding the path.
A source matches by its real path or by its spelling as configured (a
detected output folder can be a symlink), and the deepest real path wins.
The path is compared lexically after ``normpath`` and never resolved, so a
symlinked subfolder keeps its listed spelling. Containment folds case
where the OS does. *source* is the real path. None when no source
contains the path.
"""
path = os.path.normpath(str(absolute_path))
folded = os.path.normcase(path)
best = None
for source in sources:
real = os.path.normpath(os.path.realpath(str(source)))
for spelling in dict.fromkeys((real, os.path.normpath(str(source)))):
prefix = os.path.join(os.path.normcase(spelling), "")
if not folded.startswith(prefix):
continue
if best is None or _source_depth(real) > _source_depth(best[0]):
best = (real, spelling)
break
if best is None:
return None
relative = os.path.relpath(path, best[1])
return best[0], relative.replace(os.sep, "/")
def image_category_key(sources, absolute_path):
"""The file key of an image's own category (#332), or None.
``(root key, relative key)``: the deepest output source that contains the
file and the path below it, keyed with the favorites helpers. Without
nested sources it equals the file's favorite key. A path no source
contains has no key (and so no own category).
"""
found = deepest_source(sources, absolute_path)
if found is None:
return None
source, relative = found
return _favorite_root_key(source), _favorite_relative_key(relative)
def _name_suffix(name):
"""``Path(name).suffix`` as Python 3.10-3.13 compute it.