Files
mule-image/backend/app/tasks/scan.py
dtoro cf7c72d437 fix: deduplicate scanner-created source_roots and folders
Two related fixes:

1. Prevention — scanner now normalizes paths before lookup/insert
   in get_or_create_source_root and get_or_create_folder. Trailing
   slashes, redundant separators, and `.` segments all collapse to
   the same row. _normalize_path uses os.path.normpath; symlinks
   are intentionally NOT resolved so mount paths stay intact for
   cross-machine portability.

2. Cleanup — new app/services/cleanup.py runs on backend startup
   (idempotent) and merges any pre-existing duplicates left over
   from older scanner versions:
   - Groups source_roots by normalized path. Picks the canonical
     row (preferring one with a non-empty name and the earliest
     added_at), re-points child Folder rows via UPDATE, and
     deletes the duplicates.
   - Same for folders, with photo_count as the tiebreaker. Photos
     get re-pointed to the canonical folder via UPDATE.
   - Recomputes folder.photo_count from the actual non-discarded
     photo membership so the sidebar count matches reality.

Wired into main.py's lifespan handler. On the dev DB this merged
the empty-name "/host/Pictures/MulitaTest/" duplicate that was
showing up alongside the canonical MulitaTest source root.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-07 23:43:53 +02:00

308 lines
12 KiB
Python

"""
Celery tasks for scanning folders and indexing photos
"""
import os
import hashlib
import asyncio
from pathlib import Path
from datetime import datetime
import logging
import json
from typing import List, Dict, Optional
from celery import shared_task
from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession
import aiofiles
from app.database import AsyncSessionLocal
from app.models import Photo, Folder, SourceRoot
from app.config import settings
from app.tasks.thumbs import generate_thumbnails
from app.services.metadata import extract_metadata
logger = logging.getLogger(__name__)
# Supported file extensions
PHOTO_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.tiff', '.tif', '.webp', '.bmp'}
RAW_EXTENSIONS = {'.cr2', '.cr3', '.nef', '.arw', '.raf', '.dng', '.orf', '.rw2', '.pef', '.srw'}
HEIC_EXTENSIONS = {'.heic', '.heif'}
VIDEO_EXTENSIONS = {'.mp4', '.mov', '.avi', '.mkv', '.mts', '.m2ts', '.3gp', '.wmv', '.flv'}
SUPPORTED_EXTENSIONS = PHOTO_EXTENSIONS | RAW_EXTENSIONS | HEIC_EXTENSIONS | VIDEO_EXTENSIONS
def get_media_type(filepath: str) -> str:
"""Determine media type from file extension"""
ext = Path(filepath).suffix.lower()
if ext in PHOTO_EXTENSIONS:
return 'photo'
elif ext in RAW_EXTENSIONS:
return 'raw'
elif ext in HEIC_EXTENSIONS:
return 'heic'
elif ext in VIDEO_EXTENSIONS:
return 'video'
return 'unknown'
async def calculate_file_hash(filepath: str) -> str:
"""Calculate SHA-256 hash of a file"""
hash_sha256 = hashlib.sha256()
try:
async with aiofiles.open(filepath, 'rb') as f:
while chunk := await f.read(8192):
hash_sha256.update(chunk)
return hash_sha256.hexdigest()
except Exception as e:
logger.error(f"Error calculating hash for {filepath}: {e}")
return ""
@shared_task(bind=True, name='scan_folder')
def scan_folder(self, folder_path: str, source_root_id: Optional[str] = None):
"""
Scan a folder and index all photos/videos
"""
# Run async function in sync context
return asyncio.run(_scan_folder_async(folder_path, source_root_id, self))
async def _scan_folder_async(folder_path: str, source_root_id: Optional[str], task):
"""Async implementation of folder scanning"""
logger.info(f"Starting scan of folder: {folder_path}")
async with AsyncSessionLocal() as session:
try:
# Get or create source root
if not source_root_id:
source_root = await get_or_create_source_root(session, folder_path)
source_root_id = source_root.id
# Walk the directory tree
total_files = 0
processed_files = 0
errors = []
for root, dirs, files in os.walk(folder_path):
# Get or create folder entry
folder = await get_or_create_folder(session, root, source_root_id)
# Filter supported files
supported_files = [f for f in files if Path(f).suffix.lower() in SUPPORTED_EXTENSIONS]
total_files += len(supported_files)
# Process files in batches
batch_size = settings.scanner.batch_size
for i in range(0, len(supported_files), batch_size):
batch = supported_files[i:i + batch_size]
for filename in batch:
filepath = os.path.join(root, filename)
try:
# Check if file already exists in database
existing = await session.execute(
select(Photo).where(Photo.filepath == filepath)
)
if existing.scalar_one_or_none():
logger.debug(f"File already indexed: {filepath}")
processed_files += 1
continue
# Get file stats
stat = os.stat(filepath)
# Calculate file hash for duplicate detection
file_hash = await calculate_file_hash(filepath)
# Check for duplicate by hash
duplicate = await session.execute(
select(Photo).where(Photo.file_hash == file_hash)
) if file_hash else None
# Create photo entry
photo = Photo(
filepath=filepath,
filename=filename,
folder_id=folder.id,
file_hash=file_hash,
media_type=get_media_type(filepath),
original_format=Path(filepath).suffix.upper()[1:],
file_size=stat.st_size,
taken_at=datetime.fromtimestamp(stat.st_mtime),
taken_at_source='filesystem',
is_duplicate=bool(duplicate.scalar_one_or_none() if duplicate else False),
processing_status='pending'
)
session.add(photo)
await session.flush() # Get the photo ID
# Queue thumbnail generation
generate_thumbnails.delay(photo.id)
# Queue metadata extraction
extract_metadata.delay(photo.id)
processed_files += 1
# Update progress
if processed_files % 10 == 0:
task.update_state(
state='PROGRESS',
meta={
'current': processed_files,
'total': total_files,
'folder': root
}
)
except Exception as e:
logger.error(f"Error processing file {filepath}: {e}")
errors.append({'file': filepath, 'error': str(e)})
continue
# Commit batch
await session.commit()
# Update folder scan timestamp
folder.last_scanned = datetime.utcnow()
folder.photo_count = processed_files
await session.commit()
logger.info(f"Scan complete. Processed {processed_files}/{total_files} files. Errors: {len(errors)}")
return {
'status': 'completed',
'processed': processed_files,
'total': total_files,
'errors': errors
}
except Exception as e:
logger.error(f"Scan failed: {e}")
await session.rollback()
raise
def _normalize_path(path: str) -> str:
"""Canonicalise a filesystem path so we don't get duplicate DB rows for
the same physical directory due to trailing slashes, redundant separators,
or `.` segments. Symlinks are NOT resolved (we want to keep mount paths
intact for cross-machine portability)."""
return os.path.normpath(path)
async def get_or_create_source_root(session: AsyncSession, path: str) -> SourceRoot:
"""Get or create a source root entry, matching by normalized path."""
from sqlalchemy import select
norm = _normalize_path(path)
result = await session.execute(
select(SourceRoot).where(SourceRoot.path == norm)
)
source_root = result.scalar_one_or_none()
if not source_root:
source_root = SourceRoot(
name=Path(norm).name,
path=norm,
)
session.add(source_root)
await session.flush()
return source_root
async def get_or_create_folder(session: AsyncSession, path: str, source_root_id: str) -> Folder:
"""Get or create a folder entry, matching by normalized path."""
from sqlalchemy import select
norm = _normalize_path(path)
result = await session.execute(
select(Folder).where(Folder.path == norm)
)
folder = result.scalar_one_or_none()
if not folder:
parent_path = _normalize_path(str(Path(norm).parent))
if parent_path != norm: # Not the filesystem root
parent_result = await session.execute(
select(Folder).where(Folder.path == parent_path)
)
parent = parent_result.scalar_one_or_none()
if parent:
parent_id = parent.id
else:
# Recursively create parent
parent = await get_or_create_folder(session, parent_path, source_root_id)
parent_id = parent.id
else:
parent_id = None
folder = Folder(
name=Path(norm).name,
path=norm,
parent_id=parent_id,
source_root_id=source_root_id,
)
session.add(folder)
await session.flush()
return folder
@shared_task(name='scan_all_source_roots')
def scan_all_source_roots():
"""Scan all configured source roots"""
for source_root in settings.source_roots:
if os.path.exists(source_root.path):
scan_folder.delay(source_root.path)
else:
logger.warning(f"Source root path does not exist: {source_root.path}")
@shared_task(name='watch_folders')
def watch_folders():
"""
Watch folders for changes using watchfiles
This is a long-running task that monitors file system events
"""
from watchfiles import watch
paths = [sr.path for sr in settings.source_roots if os.path.exists(sr.path)]
if not paths:
logger.warning("No valid source roots to watch")
return
logger.info(f"Starting folder watcher for: {paths}")
for changes in watch(*paths):
for change_type, filepath in changes:
filepath = str(filepath)
# Check if it's a supported file type
if Path(filepath).suffix.lower() not in SUPPORTED_EXTENSIONS:
continue
if change_type == 'added' or change_type == 'modified':
# Queue scan for the parent folder
parent_dir = str(Path(filepath).parent)
scan_folder.delay(parent_dir)
logger.info(f"File {change_type}: {filepath}, queued scan for {parent_dir}")
elif change_type == 'deleted':
# Handle file deletion
asyncio.run(handle_file_deletion(filepath))
async def handle_file_deletion(filepath: str):
"""Handle deletion of a file from the filesystem"""
from sqlalchemy import select
async with AsyncSessionLocal() as session:
result = await session.execute(
select(Photo).where(Photo.filepath == filepath)
)
photo = result.scalar_one_or_none()
if photo:
# Mark as missing or delete from database
photo.is_discarded = True
photo.discarded_at = datetime.utcnow()
await session.commit()
logger.info(f"Marked photo as discarded: {filepath}")