Files
mule-image/backend/app/tasks/scan.py
dtoro a8750afef0 feat: cleaner TopBar + live scan progress wired end-to-end
Two related polish items.

1. Drop dead TopBar buttons
   - Removed the hamburger menu (Tab already toggles the sidebar),
     the grid/list view-mode toggle (only Grid was ever
     implemented), and the FolderOpen / Upload / Settings action
     icons (no features behind them).
   - TopBar is now: logo + active heap pill | search | filter
     toggle. Removed the now-unused Grid/List/Menu/FolderOpen/
     Upload/Settings icon imports and the dead viewMode local
     state.

2. Wire live scan progress
   - The frontend ScanProgress widget was already polling
     /api/v1/library/scan/status, but the worker never wrote the
     Redis keys that endpoint reads — it only updated celery's
     internal task state. So the progress UI was permanently idle.
   - Worker now writes scan:active / scan:current_folder /
     scan:processed_files / scan:total_files / scan:errors at
     every meaningful step. _get_redis() returns None on failure
     so a Redis outage degrades gracefully (scan still runs,
     progress just doesn't show).
   - Pre-walk computes total_files upfront — without it the
     progress bar jumped every time os.walk discovered a new
     subfolder because the running total was being updated as it
     went.
   - Errors are RPUSHed to a capped list (MAX_ERROR_ENTRIES=50)
     so a noisy scan can't blow up Redis.
   - finally: clause guarantees scan:active flips to false even
     on a crash, so the UI never sticks at "scanning" forever.
   - scan_all_source_roots clears scan:errors and resets counters
     before queuing the per-root tasks, so each top-level scan
     starts with a clean slate.

   Two latent bugs caught and fixed in passing:
   - watch_folders was still reading settings.source_roots which
     no longer exists since we moved source roots to the DB. Now
     it loads them from the DB via a synchronous one-shot async
     wrapper at task startup.
   - _scan_all_source_roots_async was missing entirely after the
     last refactor — defined inline now, reads active source
     roots from the DB and dispatches scan_folder per row.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-08 00:54:11 +02:00

420 lines
16 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
import redis
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__)
# Redis keys read by GET /api/v1/library/scan/status. The frontend
# ScanProgress widget polls that endpoint, so anything we want to surface
# in the UI lives here.
REDIS_KEY_ACTIVE = 'scan:active'
REDIS_KEY_CURRENT_FOLDER = 'scan:current_folder'
REDIS_KEY_PROCESSED = 'scan:processed_files'
REDIS_KEY_TOTAL = 'scan:total_files'
REDIS_KEY_ERRORS = 'scan:errors'
MAX_ERROR_ENTRIES = 50 # cap the errors list so a noisy scan doesn't blow Redis
def _get_redis():
"""Connect to the broker for progress writes. Returns None on failure
so a Redis outage doesn't prevent the scan itself from running."""
try:
return redis.Redis.from_url(settings.celery_broker_url)
except Exception as e:
logger.warning(f"Could not reach Redis for scan progress: {e}")
return None
# 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. Writes progress to Redis so
GET /api/v1/library/scan/status can surface it to the frontend
ScanProgress widget."""
logger.info(f"Starting scan of folder: {folder_path}")
r = _get_redis()
def progress_set(key: str, value) -> None:
if r is None:
return
try:
r.set(key, str(value))
except Exception as e:
logger.debug(f"scan progress set failed: {e}")
def progress_push_error(message: str) -> None:
if r is None:
return
try:
r.lpush(REDIS_KEY_ERRORS, message)
r.ltrim(REDIS_KEY_ERRORS, 0, MAX_ERROR_ENTRIES - 1)
except Exception as e:
logger.debug(f"scan progress push_error failed: {e}")
# Mark scan active immediately so the UI starts polling fast.
progress_set(REDIS_KEY_ACTIVE, 'true')
progress_set(REDIS_KEY_CURRENT_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
# Pre-walk to compute the total file count upfront. Without this
# the progress bar would jump every time a new subfolder is
# encountered because the running total kept growing.
total_files = 0
for _root, _dirs, files in os.walk(folder_path):
total_files += sum(
1 for f in files if Path(f).suffix.lower() in SUPPORTED_EXTENSIONS
)
progress_set(REDIS_KEY_TOTAL, total_files)
progress_set(REDIS_KEY_PROCESSED, 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)
progress_set(REDIS_KEY_CURRENT_FOLDER, root)
# Filter supported files
supported_files = [f for f in files if Path(f).suffix.lower() in SUPPORTED_EXTENSIONS]
# 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]
# Defer task dispatch until AFTER commit so workers don't
# query for rows that aren't visible to other sessions yet.
pending_dispatch: list[str] = []
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
progress_set(REDIS_KEY_PROCESSED, processed_files)
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() # Assign defaults / FK ids
# Queue dispatch happens after the batch commit
# below; otherwise the worker can race the writer
# and see "Photo not found".
pending_dispatch.append(photo.id)
processed_files += 1
progress_set(REDIS_KEY_PROCESSED, processed_files)
# Celery internal progress (used by celery tooling)
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)})
progress_push_error(f"{filepath}: {e}")
continue
# Commit batch, then queue worker tasks. Dispatch order
# matters: commit first so workers can find the rows.
await session.commit()
for photo_id in pending_dispatch:
generate_thumbnails.delay(photo_id)
extract_metadata.delay(photo_id)
# 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}")
progress_push_error(f"scan failed: {e}")
await session.rollback()
raise
finally:
# Always mark inactive on the way out so a crashed scan doesn't
# leave the UI thinking we're still scanning.
progress_set(REDIS_KEY_ACTIVE, 'false')
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 every active source root currently registered in the DB."""
# Clear stale per-scan progress before queuing new work so the UI sees
# a clean slate even if a previous run crashed mid-flight.
r = _get_redis()
if r is not None:
try:
r.delete(REDIS_KEY_ERRORS)
r.set(REDIS_KEY_PROCESSED, 0)
r.set(REDIS_KEY_TOTAL, 0)
except Exception as e:
logger.debug(f"scan_all_source_roots redis reset failed: {e}")
return asyncio.run(_scan_all_source_roots_async())
async def _scan_all_source_roots_async():
"""Read every active SourceRoot from the DB and queue a scan_folder task
for each. Source roots whose path no longer exists on disk are skipped
with a warning (the cleanup service surfaces those at startup too)."""
async with AsyncSessionLocal() as session:
result = await session.execute(
select(SourceRoot).where(SourceRoot.is_active == True) # noqa: E712
)
source_roots = result.scalars().all()
for sr in source_roots:
if os.path.exists(sr.path):
scan_folder.delay(sr.path, sr.id)
else:
logger.warning(f"Source root path does not exist: {sr.path}")
@shared_task(name='watch_folders')
def watch_folders():
"""
Watch folders for changes using watchfiles. Long-running task that
monitors filesystem events under every active source root.
"""
from watchfiles import watch
# Read source roots from the DB instead of the (now-removed) YAML
# config. Synchronous lookup is fine here — this runs once at task
# start, not on every event.
paths: list[str] = []
try:
async def _load_paths():
async with AsyncSessionLocal() as session:
result = await session.execute(
select(SourceRoot).where(SourceRoot.is_active == True) # noqa: E712
)
return [
sr.path for sr in result.scalars().all()
if os.path.exists(sr.path)
]
paths = asyncio.run(_load_paths())
except Exception as e:
logger.error(f"watch_folders could not load source roots: {e}")
return
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}")