Spaces:
Running
Running
File size: 11,123 Bytes
238c51b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 |
"""
Upload Service
Handles the core business logic for image uploads and processing
"""
import logging
import io
from typing import Optional, Dict, Any, Tuple
from fastapi import UploadFile
from sqlalchemy.orm import Session
from .. import crud, schemas, storage
from ..services.image_preprocessor import ImagePreprocessor
from ..services.thumbnail_service import ImageProcessingService
from ..services.vlm_service import vlm_manager
from ..utils.image_utils import convert_image_to_dict
logger = logging.getLogger(__name__)
class UploadService:
"""Service for handling image upload operations"""
@staticmethod
async def process_single_upload(
file: UploadFile,
source: Optional[str],
event_type: str,
countries: str,
epsg: str,
image_type: str,
title: str,
model_name: Optional[str],
# Drone-specific fields
center_lon: Optional[float] = None,
center_lat: Optional[float] = None,
amsl_m: Optional[float] = None,
agl_m: Optional[float] = None,
heading_deg: Optional[float] = None,
yaw_deg: Optional[float] = None,
pitch_deg: Optional[float] = None,
roll_deg: Optional[float] = None,
rtk_fix: Optional[bool] = None,
std_h_m: Optional[float] = None,
std_v_m: Optional[float] = None,
db: Session = None
) -> Dict[str, Any]:
"""Process a single image upload"""
logger.info(f"Processing single upload: {file.filename}")
# Parse and validate input
countries_list = [c.strip() for c in countries.split(',') if c.strip()] if countries else []
# Set defaults based on image type
if image_type == "drone_image":
if not event_type or event_type.strip() == "":
event_type = "OTHER"
if not epsg or epsg.strip() == "":
epsg = "OTHER"
else:
if not source or source.strip() == "":
source = "OTHER"
if not event_type or event_type.strip() == "":
event_type = "OTHER"
if not epsg or epsg.strip() == "":
epsg = "OTHER"
# Clear drone fields for non-drone images
center_lon = center_lat = amsl_m = agl_m = None
heading_deg = yaw_deg = pitch_deg = roll_deg = None
rtk_fix = std_h_m = std_v_m = None
if not image_type or image_type.strip() == "":
image_type = "crisis_map"
# Read file content
content = await file.read()
# Preprocess image
preprocessing_info = await UploadService._preprocess_image(content, file.filename)
# Upload to storage
key, sha = await UploadService._upload_to_storage(
preprocessing_info['processed_content'],
preprocessing_info['processed_filename'],
preprocessing_info['mime_type']
)
# Generate thumbnails and detail versions
thumbnail_result, detail_result = await UploadService._generate_image_versions(
preprocessing_info['processed_content'],
preprocessing_info['processed_filename']
)
# Create database record
img = crud.create_image(
db, source, event_type, key, sha, countries_list, epsg, image_type,
center_lon, center_lat, amsl_m, agl_m,
heading_deg, yaw_deg, pitch_deg, roll_deg,
rtk_fix, std_h_m, std_v_m,
thumbnail_key=thumbnail_result[0] if thumbnail_result else None,
detail_key=detail_result[0] if detail_result else None
)
# Generate caption if requested
if title or model_name:
await UploadService._generate_caption(
img, preprocessing_info['processed_content'], title, model_name, db
)
# Generate response
url = storage.get_object_url(key)
img_dict = convert_image_to_dict(img, url)
img_dict['preprocessing_info'] = preprocessing_info
logger.info(f"Successfully processed upload: {img.image_id}")
return {
'image': schemas.ImageOut(**img_dict),
'preprocessing_info': preprocessing_info
}
@staticmethod
async def process_multi_upload(
files: list[UploadFile],
source: Optional[str],
event_type: str,
countries: str,
epsg: str,
image_type: str,
title: str,
model_name: Optional[str],
# Drone-specific fields
center_lon: Optional[float] = None,
center_lat: Optional[float] = None,
amsl_m: Optional[float] = None,
agl_m: Optional[float] = None,
heading_deg: Optional[float] = None,
yaw_deg: Optional[float] = None,
pitch_deg: Optional[float] = None,
roll_deg: Optional[float] = None,
rtk_fix: Optional[bool] = None,
std_h_m: Optional[float] = None,
std_v_m: Optional[float] = None,
db: Session = None
) -> Dict[str, Any]:
"""Process multiple image uploads"""
logger.info(f"Processing multi upload: {len(files)} files")
results = []
for file in files:
try:
result = await UploadService.process_single_upload(
file, source, event_type, countries, epsg, image_type,
title, model_name, center_lon, center_lat, amsl_m, agl_m,
heading_deg, yaw_deg, pitch_deg, roll_deg,
rtk_fix, std_h_m, std_v_m, db
)
results.append(result)
except Exception as e:
logger.error(f"Failed to process file {file.filename}: {str(e)}")
results.append({
'error': str(e),
'filename': file.filename
})
logger.info(f"Multi upload completed: {len(results)} results")
return {
'results': results,
'total_files': len(files),
'successful': len([r for r in results if 'error' not in r])
}
@staticmethod
async def _preprocess_image(content: bytes, filename: str) -> Dict[str, Any]:
"""Preprocess an image file"""
logger.debug(f"Preprocessing image: {filename}")
try:
processed_content, processed_filename, mime_type = ImagePreprocessor.preprocess_image(
content,
filename,
target_format='PNG',
quality=95
)
preprocessing_info = {
"original_filename": filename,
"processed_filename": processed_filename,
"original_mime_type": ImagePreprocessor.detect_mime_type(content, filename),
"processed_mime_type": mime_type,
"processed_content": processed_content,
"was_preprocessed": processed_filename != filename
}
if processed_filename != filename:
logger.info(f"Image preprocessed: {filename} -> {processed_filename}")
return preprocessing_info
except Exception as e:
logger.error(f"Image preprocessing failed: {str(e)}")
# Fall back to original content
return {
"original_filename": filename,
"processed_filename": filename,
"original_mime_type": "unknown",
"processed_mime_type": "image/png",
"processed_content": content,
"was_preprocessed": False,
"error": str(e)
}
@staticmethod
async def _upload_to_storage(content: bytes, filename: str, mime_type: str) -> Tuple[str, str]:
"""Upload content to storage and return key and SHA256"""
logger.debug(f"Uploading to storage: {filename}")
key = storage.upload_fileobj(
io.BytesIO(content),
filename,
content_type=mime_type
)
sha = crud.hash_bytes(content)
logger.debug(f"Uploaded to key: {key}, SHA: {sha}")
return key, sha
@staticmethod
async def _generate_image_versions(content: bytes, filename: str) -> Tuple[Optional[Tuple], Optional[Tuple]]:
"""Generate thumbnail and detail versions of the image"""
logger.debug(f"Generating image versions: {filename}")
try:
thumbnail_result = ImageProcessingService.create_and_upload_thumbnail(
content, filename
)
detail_result = ImageProcessingService.create_and_upload_detail(
content, filename
)
if thumbnail_result:
logger.info(f"Thumbnail generated: {thumbnail_result[0]}")
if detail_result:
logger.info(f"Detail version generated: {detail_result[0]}")
return thumbnail_result, detail_result
except Exception as e:
logger.error(f"Image version generation failed: {str(e)}")
return None, None
@staticmethod
async def _generate_caption(img, image_content: bytes, title: str, model_name: Optional[str], db: Session):
"""Generate caption for the uploaded image"""
if not title and not model_name:
return
logger.debug(f"Generating caption for image {img.image_id}")
try:
# Get active prompt for image type
prompt_obj = crud.get_active_prompt_by_image_type(db, img.image_type)
if not prompt_obj:
logger.warning(f"No active prompt found for image type: {img.image_type}")
return
# Generate caption using VLM service
result = await vlm_manager.generate_caption(
image_content=image_content,
prompt=prompt_obj.label,
metadata_instructions=prompt_obj.metadata_instructions or "",
model_name=model_name,
db_session=db
)
# Create caption record
crud.create_caption(
db=db,
image_id=img.image_id,
title=title or result.get("title", ""),
prompt=prompt_obj.p_code,
model_code=result.get("model", model_name or "STUB_MODEL"),
raw_json=result.get("raw_response", {}),
text=result.get("text", ""),
metadata=result.get("metadata", {}),
image_count=1
)
logger.info(f"Caption generated for image {img.image_id}")
except Exception as e:
logger.error(f"Caption generation failed: {str(e)}")
# Continue without caption if generation fails
|