Files
mule-image/backend/app/tasks/thumbs.py
2026-04-06 23:30:19 +02:00

277 lines
9.8 KiB
Python

"""
Celery tasks for thumbnail generation
"""
import os
import asyncio
from pathlib import Path
import logging
from typing import Tuple, Optional
import json
from celery import shared_task
from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession
import pyvips
import rawpy
import imageio
from PIL import Image
from pillow_heif import register_heif_opener
import ffmpeg
from app.database import AsyncSessionLocal
from app.models import Photo
from app.config import settings
# Register HEIF opener with Pillow
register_heif_opener()
logger = logging.getLogger(__name__)
# Thumbnail sizes configuration
THUMB_SIZES = {
'small': settings.thumbnails.small,
'medium': settings.thumbnails.medium,
'large': settings.thumbnails.large
}
def get_thumb_path(photo_id: str, size: str) -> str:
"""Get the path for a thumbnail file"""
thumb_dir = f"/data/thumbs/{photo_id}"
os.makedirs(thumb_dir, exist_ok=True)
return f"{thumb_dir}/{size}.{settings.thumbnails.format}"
def process_standard_image(filepath: str) -> pyvips.Image:
"""Process standard image formats (JPEG, PNG, etc.)"""
return pyvips.Image.new_from_file(filepath, access='sequential')
def process_raw_image(filepath: str) -> pyvips.Image:
"""Process RAW image formats"""
try:
with rawpy.imread(filepath) as raw:
# Use half_size for faster processing
rgb = raw.postprocess(use_camera_wb=True, half_size=True)
# Convert numpy array to pyvips image
return pyvips.Image.new_from_array(rgb)
except Exception as e:
logger.error(f"Error processing RAW file {filepath}: {e}")
# Try to extract embedded JPEG preview
return extract_raw_preview(filepath)
def extract_raw_preview(filepath: str) -> Optional[pyvips.Image]:
"""Extract embedded JPEG preview from RAW file"""
try:
# Use exiftool to extract preview
import subprocess
import tempfile
with tempfile.NamedTemporaryFile(suffix='.jpg', delete=False) as tmp:
cmd = ['exiftool', '-b', '-PreviewImage', filepath]
result = subprocess.run(cmd, capture_output=True)
if result.returncode == 0 and result.stdout:
tmp.write(result.stdout)
tmp.flush()
return pyvips.Image.new_from_file(tmp.name, access='sequential')
except Exception as e:
logger.error(f"Error extracting RAW preview from {filepath}: {e}")
return None
def process_heic_image(filepath: str) -> pyvips.Image:
"""Process HEIC/HEIF image formats"""
try:
# Use pillow-heif to open the image
img = Image.open(filepath)
# Convert to RGB if needed
if img.mode != 'RGB':
img = img.convert('RGB')
# Save to temp file and load with pyvips
import tempfile
with tempfile.NamedTemporaryFile(suffix='.jpg', delete=False) as tmp:
img.save(tmp.name, 'JPEG')
return pyvips.Image.new_from_file(tmp.name, access='sequential')
except Exception as e:
logger.error(f"Error processing HEIC file {filepath}: {e}")
raise
def process_video_thumbnail(filepath: str) -> pyvips.Image:
"""Extract thumbnail from video file"""
try:
# Get video duration
probe = ffmpeg.probe(filepath)
duration = float(probe['streams'][0]['duration'])
# Extract frame at 10% of duration
timestamp = duration * 0.1
# Extract frame using ffmpeg
import tempfile
with tempfile.NamedTemporaryFile(suffix='.jpg', delete=False) as tmp:
stream = ffmpeg.input(filepath, ss=timestamp)
stream = ffmpeg.output(stream, tmp.name, vframes=1, format='image2', vcodec='mjpeg')
ffmpeg.run(stream, capture_stdout=True, capture_stderr=True)
return pyvips.Image.new_from_file(tmp.name, access='sequential')
except Exception as e:
logger.error(f"Error extracting video thumbnail from {filepath}: {e}")
# Create a placeholder thumbnail
return create_placeholder_thumbnail('video')
def create_placeholder_thumbnail(media_type: str) -> pyvips.Image:
"""Create a placeholder thumbnail for failed processing"""
# Create a simple gray placeholder
placeholder = pyvips.Image.black(640, 480)
placeholder = placeholder + [128, 128, 128] # Make it gray
return placeholder
def auto_rotate_image(image: pyvips.Image) -> pyvips.Image:
"""Auto-rotate image based on EXIF orientation"""
try:
orientation = image.get('orientation')
rotation_map = {
3: 180,
6: 90,
8: 270
}
if orientation in rotation_map:
image = image.rot(rotation_map[orientation])
except:
pass # No orientation data available
return image
def generate_thumbnail(image: pyvips.Image, size: int, output_path: str):
"""Generate a thumbnail of the specified size"""
# Calculate scale to fit within size (longest edge)
width = image.width
height = image.height
if width > height:
scale = size / width
else:
scale = size / height
# Only downscale, never upscale
if scale < 1:
image = image.resize(scale)
# Save as WebP with specified quality
image.webpsave(
output_path,
Q=settings.thumbnails.quality,
effort=4 # Balance between speed and compression
)
@shared_task(bind=True, name='generate_thumbnails')
def generate_thumbnails(self, photo_id: str):
"""Generate thumbnails for a photo"""
return asyncio.run(_generate_thumbnails_async(photo_id, self))
async def _generate_thumbnails_async(photo_id: str, task):
"""Async implementation of thumbnail generation"""
async with AsyncSessionLocal() as session:
try:
# Get photo from database
result = await session.execute(
select(Photo).where(Photo.id == photo_id)
)
photo = result.scalar_one_or_none()
if not photo:
logger.error(f"Photo not found: {photo_id}")
return {'status': 'error', 'message': 'Photo not found'}
# Check if file exists
if not os.path.exists(photo.filepath):
logger.error(f"File not found: {photo.filepath}")
photo.processing_status = 'failed'
photo.processing_error = 'File not found'
await session.commit()
return {'status': 'error', 'message': 'File not found'}
# Update processing status
photo.processing_status = 'processing'
await session.commit()
# Load and process the image based on type
image = None
if photo.media_type == 'photo':
image = process_standard_image(photo.filepath)
elif photo.media_type == 'raw':
image = process_raw_image(photo.filepath)
elif photo.media_type == 'heic':
image = process_heic_image(photo.filepath)
elif photo.media_type == 'video':
image = process_video_thumbnail(photo.filepath)
else:
logger.error(f"Unsupported media type: {photo.media_type}")
image = create_placeholder_thumbnail(photo.media_type)
if not image:
raise Exception("Failed to process image")
# Auto-rotate based on EXIF
image = auto_rotate_image(image)
# Store original dimensions
photo.width = image.width
photo.height = image.height
# Generate thumbnails for each size
for size_name, size_value in THUMB_SIZES.items():
thumb_path = get_thumb_path(photo_id, size_name)
generate_thumbnail(image, size_value, thumb_path)
# Update database with thumbnail path
setattr(photo, f'thumb_{size_name}', thumb_path)
# Update progress
task.update_state(
state='PROGRESS',
meta={'current_size': size_name, 'photo_id': photo_id}
)
# Update processing status
photo.processing_status = 'completed'
photo.processing_error = None
await session.commit()
logger.info(f"Thumbnails generated for photo {photo_id}")
return {'status': 'success', 'photo_id': photo_id}
except Exception as e:
logger.error(f"Error generating thumbnails for {photo_id}: {e}")
# Update error status
if photo:
photo.processing_status = 'failed'
photo.processing_error = str(e)
await session.commit()
return {'status': 'error', 'message': str(e)}
@shared_task(name='regenerate_all_thumbnails')
def regenerate_all_thumbnails():
"""Regenerate thumbnails for all photos"""
return asyncio.run(_regenerate_all_thumbnails_async())
async def _regenerate_all_thumbnails_async():
"""Async implementation of regenerating all thumbnails"""
async with AsyncSessionLocal() as session:
# Get all photos that need thumbnails
result = await session.execute(
select(Photo).where(
Photo.processing_status.in_(['pending', 'failed'])
)
)
photos = result.scalars().all()
logger.info(f"Regenerating thumbnails for {len(photos)} photos")
for photo in photos:
generate_thumbnails.delay(photo.id)
return {'status': 'queued', 'count': len(photos)}