Files
J621/backend/apps/library/views.py
T
JakeBreath d0e2901c92 Upload pipeline: staging, MD5 auto-match, IQDB, three-column board
Backend:
- TempUpload model: staged files (pending / visual_match / completed /
  error) with resolution, e621 payload, custom metadata and IQDB data
- Files land in a temp folder and only move into the watched library
  folder once resolved; duplicates resolve immediately without a copy
- Endpoints: stage (multipart), list, retrieve, temp file, IQDB save,
  resolve (link to post or custom metadata), discard/dismiss
- cleanup_temp_uploads command for old staged files
- Replaces the old direct-to-library upload endpoint

Frontend:
- Upload page is now a three-column board (Pending & Unmatched /
  Visual Similarity Detected / Auto-uploaded & Indexed)
- After upload: MD5s are batch-checked against e621 and matches
  auto-complete with full post metadata; remaining files run through
  IQDB and move to the similarity column when candidates exist
- Metadata modal with IQDB candidates, post-ID linking and custom
  tags/rating/notes; discard and dismiss actions
- e621 client gains fetchPostsByMd5 and iqdbSearch helpers

Roadmap updated with the completed upload items.
2026-09-17 11:12:03 -05:00

222 lines
8.4 KiB
Python

import re
from pathlib import Path
from urllib.parse import urlparse
from django.conf import settings
from django.db.models import Min
from django.http import Http404
from django.shortcuts import get_object_or_404
from rest_framework import mixins, status, viewsets
from rest_framework.decorators import action
from rest_framework.permissions import AllowAny, IsAuthenticatedOrReadOnly
from rest_framework.response import Response
from rest_framework.views import APIView
from . import services
from .models import MediaItem
from .permissions import CanUpload, IsUploaderOrStaffOrReadOnly
from .serializers import MediaItemSerializer
LIST_ORDERINGS = {"name", "-name", "size", "-size", "created_at", "-created_at"}
MD5_RE = re.compile(r"[0-9a-fA-F]{32}")
class MediaItemViewSet(
mixins.ListModelMixin,
mixins.RetrieveModelMixin,
mixins.UpdateModelMixin,
viewsets.GenericViewSet,
):
serializer_class = MediaItemSerializer
permission_classes = [IsAuthenticatedOrReadOnly, IsUploaderOrStaffOrReadOnly]
http_method_names = ["get", "post", "patch", "head", "options"]
def get_queryset(self):
queryset = MediaItem.objects.prefetch_related("locations").annotate(
name=Min("locations__rel_path")
)
if not self.request.user.is_authenticated:
queryset = queryset.filter(hidden_from_guests=False)
search = self.request.query_params.get("search", "").strip()
if search:
queryset = queryset.filter(locations__rel_path__icontains=search)
ratings = [
value
for value in self.request.query_params.get("rating", "").split(",")
if value in {"s", "q", "e"}
]
if ratings:
queryset = queryset.filter(rating__in=ratings)
ordering = self.request.query_params.get("ordering", "").strip()
queryset = queryset.order_by(
ordering if ordering in LIST_ORDERINGS else "-created_at"
)
return queryset.distinct()
def get_object(self):
"""Resolve J-<id>, a bare numeric id, or an MD5 fingerprint."""
value = str(self.kwargs.get("pk", "")).strip()
queryset = self.get_queryset()
if MD5_RE.fullmatch(value):
obj = get_object_or_404(queryset, md5=value.lower())
else:
numeric = value[2:] if value.upper().startswith("J-") else value
if not numeric.isdigit():
raise Http404
obj = get_object_or_404(queryset, pk=int(numeric))
self.check_object_permissions(self.request, obj)
return obj
@action(detail=True, methods=["get"])
def raw(self, request, pk=None):
item = self.get_object()
location = item.locations.first()
if location is None:
return Response(
{"detail": "No file for this item."},
status=status.HTTP_404_NOT_FOUND,
)
return services.serve_file(
request, location.path, download=request.query_params.get("download") == "1"
)
@action(detail=True, methods=["get"])
def thumbnail(self, request, pk=None):
item = self.get_object()
location = item.locations.first()
if location is None:
return Response(
{"detail": "No file for this item."},
status=status.HTTP_404_NOT_FOUND,
)
path = Path(location.path)
if path.suffix.lower() in services.VIDEO_EXTENSIONS:
thumbnail = services.generate_video_thumbnail(item.md5, path)
if thumbnail is None:
return Response(
{"detail": "Thumbnail unavailable."},
status=status.HTTP_404_NOT_FOUND,
)
return services.serve_file(request, thumbnail)
return services.serve_file(request, path)
@action(detail=False, methods=["post"], permission_classes=[AllowAny])
def lookup(self, request):
"""Report which of the given MD5s exist in the library."""
md5s = request.data.get("md5s")
if not isinstance(md5s, list):
return Response(
{"detail": "md5s must be a list."},
status=status.HTTP_400_BAD_REQUEST,
)
wanted = {str(value).strip().lower()[:32] for value in md5s if value}
queryset = MediaItem.objects.filter(md5__in=wanted)
if not request.user.is_authenticated:
queryset = queryset.filter(hidden_from_guests=False)
rows = list(queryset.values_list("md5", "id"))
return Response(
{
"found": sorted(md5 for md5, _ in rows),
"j_ids": {md5: f"J-{item_id}" for md5, item_id in rows},
}
)
@action(detail=True, methods=["get"])
def neighbors(self, request, pk=None):
"""Previous/next items in the ordered list, for keyboard navigation."""
item = self.get_object()
ordering = request.query_params.get("ordering", "-created_at").strip()
if ordering not in LIST_ORDERINGS:
ordering = "-created_at"
field = ordering.lstrip("-")
descending = ordering.startswith("-")
value = {
"size": item.size,
"created_at": item.created_at,
"name": item.name,
}[field]
queryset = self.get_queryset().exclude(pk=item.pk)
if descending:
previous_query = queryset.filter(**{f"{field}__gt": value}).order_by(field)
next_query = queryset.filter(**{f"{field}__lt": value}).order_by(f"-{field}")
else:
previous_query = queryset.filter(**{f"{field}__lt": value}).order_by(
f"-{field}"
)
next_query = queryset.filter(**{f"{field}__gt": value}).order_by(field)
def brief(obj):
location = obj.locations.first()
return {
"j_id": f"J-{obj.id}",
"md5": obj.md5,
"filename": Path(location.rel_path).name if location else obj.md5,
}
previous = previous_query.first()
next_item = next_query.first()
return Response(
{
"previous": brief(previous) if previous else None,
"next": brief(next_item) if next_item else None,
}
)
class DownloadToLibraryView(APIView):
"""Fetch an e621 file into the watched folder and index it."""
permission_classes = [CanUpload]
def post(self, request):
url = str(request.data.get("url") or "").strip()
post_id = request.data.get("post_id")
filename = str(request.data.get("filename") or "").strip()
post_payload = request.data.get("post")
if not url.startswith(("http://", "https://")):
return Response(
{"detail": "A valid file URL is required."},
status=status.HTTP_400_BAD_REQUEST,
)
folder = Path(settings.WATCHED_FOLDER)
name = (
filename
or Path(urlparse(url).path).name
or f"post-{post_id or 'download'}"
)
destination = services.unique_destination(folder, name)
try:
services.download_file(url, destination)
item, _, _ = services.index_file(destination, folder)
except Exception as exc: # noqa: BLE001 - report download failures
destination.unlink(missing_ok=True)
return Response(
{"detail": f"Download failed: {exc}"},
status=status.HTTP_400_BAD_REQUEST,
)
update_fields = []
if item.uploaded_by_id is None:
item.uploaded_by = request.user
update_fields.append("uploaded_by")
trimmed = services.trim_e621_post(post_payload)
if trimmed is not None:
if trimmed.get("id") is not None:
item.e621_post_id = int(trimmed["id"])
elif post_id and str(post_id).isdigit():
item.e621_post_id = int(post_id)
item.e621_data = trimmed
update_fields += ["e621_post_id", "e621_data"]
if not item.rating and trimmed.get("rating") in {"s", "q", "e"}:
item.rating = trimmed["rating"]
update_fields.append("rating")
if update_fields:
item.save(update_fields=update_fields + ["updated_at"])
return Response(
MediaItemSerializer(item, context={"request": request}).data,
status=status.HTTP_201_CREATED,
)