45d80dfaa6
Fork of Lightning_Report adding: - n8n_report_branch.json: workflow branch for storm-triggered report delivery - report_service/: FastAPI microservice wrapping create_docx_report() so n8n can produce byte-identical reports without fighting the Python Code sandbox Made-with: Cursor
100 lines
3.4 KiB
Python
100 lines
3.4 KiB
Python
#!/usr/bin/env python3
|
|
|
|
import json
|
|
import sys
|
|
from pathlib import Path
|
|
from datetime import datetime
|
|
from typing import Dict, List, Any
|
|
import logging
|
|
from collections import defaultdict
|
|
|
|
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
|
|
logger = logging.getLogger(__name__)
|
|
|
|
def separate_json_by_month(input_file_path: str, output_dir: str = None) -> Dict[str, str]:
|
|
"""
|
|
Separate JSON file into smaller files based on months in creation_time.
|
|
|
|
Args:
|
|
input_file_path: Path to the input JSON file
|
|
output_dir: Directory to save separated files (optional)
|
|
|
|
Returns:
|
|
Dictionary mapping month to output file path
|
|
"""
|
|
try:
|
|
logger.info(f"Reading JSON file: {input_file_path}")
|
|
|
|
with open(input_file_path, 'r', encoding='utf-8') as f:
|
|
data = json.load(f)
|
|
|
|
logger.info(f"Successfully read {len(data)} records")
|
|
|
|
if output_dir is None:
|
|
input_path = Path(input_file_path)
|
|
output_dir = input_path.parent / f"{input_path.stem}_separated"
|
|
|
|
output_path = Path(output_dir)
|
|
output_path.mkdir(exist_ok=True)
|
|
|
|
month_data = defaultdict(list)
|
|
|
|
for record in data:
|
|
try:
|
|
creation_time = record['creation_time']
|
|
date_obj = datetime.strptime(creation_time[:10], '%Y-%m-%d')
|
|
month_key = date_obj.strftime('%Y-%m')
|
|
month_data[month_key].append(record)
|
|
except (KeyError, ValueError) as e:
|
|
logger.warning(f"Skipping record with invalid creation_time: {e}")
|
|
continue
|
|
|
|
output_files = {}
|
|
|
|
for month, records in month_data.items():
|
|
output_file = output_path / f"firtina_sorgulama_{month}.json"
|
|
|
|
logger.info(f"Writing {len(records)} records for {month} to {output_file}")
|
|
|
|
with open(output_file, 'w', encoding='utf-8') as f:
|
|
json.dump(records, f, indent=2, ensure_ascii=False, default=str)
|
|
|
|
file_size = output_file.stat().st_size / 1024
|
|
logger.info(f"Created {output_file} ({file_size:.2f} KB)")
|
|
output_files[month] = str(output_file)
|
|
|
|
logger.info(f"Separation completed. Created {len(output_files)} files in {output_path}")
|
|
|
|
return output_files
|
|
|
|
except FileNotFoundError:
|
|
logger.error(f"JSON file not found: {input_file_path}")
|
|
raise
|
|
except json.JSONDecodeError as e:
|
|
logger.error(f"Invalid JSON format: {e}")
|
|
raise
|
|
except Exception as e:
|
|
logger.error(f"Error separating JSON by month: {str(e)}")
|
|
raise
|
|
|
|
def main():
|
|
"""Main function to handle command line execution."""
|
|
if len(sys.argv) < 2:
|
|
print("Usage: python separate_by_month.py <json_file_path> [output_directory]")
|
|
sys.exit(1)
|
|
|
|
input_file_path = sys.argv[1]
|
|
output_dir = sys.argv[2] if len(sys.argv) > 2 else None
|
|
|
|
try:
|
|
result_files = separate_json_by_month(input_file_path, output_dir)
|
|
print(f"Separation completed successfully!")
|
|
print("Created files:")
|
|
for month, file_path in result_files.items():
|
|
print(f" {month}: {file_path}")
|
|
except Exception as e:
|
|
print(f"Error: {e}")
|
|
sys.exit(1)
|
|
|
|
if __name__ == "__main__":
|
|
main() |