Spaces:
Runtime error
Runtime error
File size: 11,323 Bytes
b6145cd a34989b | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 | # services/data/artifacts.py
"""
Data Artifacts Service
This module provides file-based artifact generation and management for
operational data. It handles saving structured data to various formats
and managing artifact lifecycle.
Purpose:
- Save operational data to files (JSON, CSV, etc.)
- Generate standardized filenames with timestamps and metadata
- Manage artifact storage locations and cleanup
- Provide consistent artifact metadata
Design Principles:
- Configurable output directories
- Timestamped filenames for traceability
- Metadata embedding in saved files
- Error handling for storage failures
- Support for multiple output formats
Dependencies:
- json: For JSON serialization
- os: For file system operations
- datetime: For timestamp generation
Called by:
- tools/*/adapter.py: Main tool adapters for data persistence
- services/reports/*: Report generation services
- Direct usage: Emergency management data export
Security Notes:
- Validates output paths to prevent directory traversal
- Uses safe filename generation
- Handles permissions and disk space gracefully
TODO: implement permanent configurable storage with retention policies
"""
import json
import os
import csv
from typing import Dict, Any, List, Optional, Union
from datetime import datetime
from pathlib import Path
class ArtifactConfig:
"""Configuration for artifact generation"""
def __init__(
self,
base_dir: str = "/tmp/omirl_data",
include_timestamp: bool = True,
include_metadata: bool = True,
filename_format: str = "{prefix}_{timestamp}{suffix}.{extension}"
):
self.base_dir = base_dir
self.include_timestamp = include_timestamp
self.include_metadata = include_metadata
self.filename_format = filename_format
class ArtifactManager:
"""
Manages data artifact creation and storage
This class provides a standardized way to save operational data
to various file formats with consistent naming and metadata.
"""
def __init__(self, config: Optional[ArtifactConfig] = None):
self.config = config or ArtifactConfig()
self._ensure_base_directory()
def _ensure_base_directory(self):
"""Create base directory if it doesn't exist"""
try:
os.makedirs(self.config.base_dir, exist_ok=True)
except Exception as e:
print(f"⚠️ Warning: Could not create base directory {self.config.base_dir}: {e}")
async def save_station_data(
self,
stations: List[Dict[str, Any]],
filters: Dict[str, Any] = None,
source: str = "OMIRL",
format: str = "json"
) -> Optional[str]:
"""
Save weather station data to file
Args:
stations: List of station data dictionaries
filters: Applied filters for filename generation
source: Data source name
format: Output format ("json" or "csv")
Returns:
Filepath of saved file, or None if failed
"""
try:
# Generate filename
filename = self._generate_filename(
prefix="stazioni",
filters=filters,
extension=format
)
filepath = os.path.join(self.config.base_dir, filename)
# Prepare data with metadata
if format == "json":
return await self._save_as_json(stations, filepath, filters, source)
elif format == "csv":
return await self._save_as_csv(stations, filepath, filters, source)
else:
print(f"⚠️ Unsupported format: {format}")
return None
except Exception as e:
print(f"⚠️ Failed to save station data: {e}")
return None
async def save_generic_data(
self,
data: Union[List[Dict], Dict[str, Any]],
prefix: str = "data",
filters: Dict[str, Any] = None,
source: str = "Unknown",
format: str = "json"
) -> Optional[str]:
"""
Save generic operational data to file
Args:
data: Data to save (list of dicts or single dict)
prefix: Filename prefix
filters: Applied filters for filename generation
source: Data source name
format: Output format
Returns:
Filepath of saved file, or None if failed
"""
try:
filename = self._generate_filename(
prefix=prefix,
filters=filters,
extension=format
)
filepath = os.path.join(self.config.base_dir, filename)
if format == "json":
return await self._save_generic_json(data, filepath, filters, source)
else:
print(f"⚠️ Unsupported format for generic data: {format}")
return None
except Exception as e:
print(f"⚠️ Failed to save generic data: {e}")
return None
def _generate_filename(
self,
prefix: str,
filters: Dict[str, Any] = None,
extension: str = "json"
) -> str:
"""Generate standardized filename with timestamp and filters"""
# Base components
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S") if self.config.include_timestamp else ""
# Add filter-based suffix
suffix = ""
if filters:
filter_parts = []
for key, value in filters.items():
if value:
# Clean value for filename
clean_value = str(value).lower().replace(" ", "_").replace("'", "")
filter_parts.append(f"{key}_{clean_value}")
if filter_parts:
suffix = "_" + "_".join(filter_parts[:3]) # Limit to 3 filters for filename length
# Format filename
return self.config.filename_format.format(
prefix=prefix,
timestamp=timestamp,
suffix=suffix,
extension=extension
)
async def _save_as_json(
self,
stations: List[Dict[str, Any]],
filepath: str,
filters: Dict[str, Any],
source: str
) -> str:
"""Save station data as JSON with metadata"""
data_to_save = {
"metadata": {
"extraction_timestamp": datetime.now().isoformat(),
"source": source,
"filters_applied": filters or {},
"station_count": len(stations),
"format_version": "1.0"
},
"stations": stations
} if self.config.include_metadata else stations
with open(filepath, 'w', encoding='utf-8') as f:
json.dump(data_to_save, f, ensure_ascii=False, indent=2)
print(f"💾 Station data saved to: {filepath}")
return filepath
async def _save_as_csv(
self,
stations: List[Dict[str, Any]],
filepath: str,
filters: Dict[str, Any],
source: str
) -> str:
"""Save station data as CSV"""
if not stations:
# Create empty CSV with headers
with open(filepath, 'w', encoding='utf-8', newline='') as f:
writer = csv.writer(f)
writer.writerow(["Nome", "Codice", "Comune", "Provincia"])
else:
# Get headers from first station
headers = list(stations[0].keys())
with open(filepath, 'w', encoding='utf-8', newline='') as f:
writer = csv.DictWriter(f, fieldnames=headers)
writer.writeheader()
for station in stations:
writer.writerow(station)
print(f"💾 Station data saved to CSV: {filepath}")
return filepath
async def _save_generic_json(
self,
data: Union[List[Dict], Dict[str, Any]],
filepath: str,
filters: Dict[str, Any],
source: str
) -> str:
"""Save generic data as JSON with metadata"""
data_to_save = {
"metadata": {
"extraction_timestamp": datetime.now().isoformat(),
"source": source,
"filters_applied": filters or {},
"record_count": len(data) if isinstance(data, list) else 1,
"format_version": "1.0"
},
"data": data
} if self.config.include_metadata else data
with open(filepath, 'w', encoding='utf-8') as f:
json.dump(data_to_save, f, ensure_ascii=False, indent=2)
print(f"💾 Data saved to: {filepath}")
return filepath
# Factory function for common configurations
def create_artifact_manager(
base_dir: str = "/tmp/omirl_data",
include_metadata: bool = True
) -> ArtifactManager:
"""
Create an artifact manager with custom configuration
Args:
base_dir: Base directory for saving artifacts
include_metadata: Whether to include metadata in saved files
Returns:
Configured ArtifactManager instance
"""
config = ArtifactConfig(
base_dir=base_dir,
include_metadata=include_metadata
)
return ArtifactManager(config)
# Convenience functions for common use cases
async def save_omirl_stations(
stations: List[Dict[str, Any]],
filters: Dict[str, Any] = None,
format: str = "json",
base_dir: str = "/tmp/omirl_data"
) -> Optional[str]:
"""
Quick function to save OMIRL station data
This is a convenience function that creates an artifact manager
and saves station data in one call.
"""
manager = create_artifact_manager(base_dir=base_dir)
return await manager.save_station_data(
stations=stations,
filters=filters,
source="OMIRL Valori Stazioni",
format=format
)
async def save_omirl_precipitation_data(
precipitation_data: Dict[str, List[Dict[str, Any]]],
filters: Dict[str, Any] = None,
format: str = "json",
base_dir: str = "/tmp/omirl_data"
) -> Optional[str]:
"""
Quick function to save OMIRL precipitation data
This is a convenience function that creates an artifact manager
and saves precipitation data from both zona d'allerta and province tables.
"""
manager = create_artifact_manager(base_dir=base_dir)
# Flatten the precipitation data for consistent saving
# Include metadata about which table each record came from
flattened_data = []
for table_type in ["zona_allerta", "province"]:
for record in precipitation_data.get(table_type, []):
record_with_type = {**record, "table_type": table_type}
flattened_data.append(record_with_type)
return await manager.save_station_data(
stations=flattened_data,
filters=filters,
source="OMIRL Massimi Precipitazione",
format=format
)
|