table-extraction / utils /io_utils.py
jobian's picture
Enhance PDF table extraction for Multi-header column extraction with improved formatting and structure processing
23bc040
raw
history blame contribute delete
818 Bytes
# utils/io_utils.py
import uuid
import json
import time
from datetime import datetime, timezone
from pathlib import Path
from config import OUTPUTS_DIR
def unique_run_dir(stem: str) -> Path:
ts = datetime.now(timezone.utc).strftime("%Y%m%dT%H%M%SZ")
return OUTPUTS_DIR / f"{stem}_{ts}_{uuid.uuid4().hex[:8]}"
def save_json(path: Path, data: dict):
with open(path, "w", encoding="utf-8") as f:
json.dump(data, f, ensure_ascii=False, indent=2)
def build_metrics(file_name: str, n_pages: int, n_tables: int, per_page_counts: dict, start_time: float) -> dict:
return {
"file": file_name,
"n_pages": n_pages,
"n_tables": n_tables,
"tables_per_page": per_page_counts,
"processing_seconds": round(time.time() - start_time, 3),
"errors": []
}