scripts/validate_kb.py

#!/usr/bin/env python3
from __future__ import annotations

import sys
from pathlib import Path

import pandas as pd

ROOT = Path(__file__).resolve().parents[1]
SRC = ROOT / "src"
if str(SRC) not in sys.path:
    sys.path.insert(0, str(SRC))

from dip_client import KB_COLUMNS

path = ROOT / "data" / "dip_knowledge_base.csv"
if not path.exists():
    raise SystemExit("No data/dip_knowledge_base.csv found. Build the KB first.")

df = pd.read_csv(path, dtype=str).fillna("")
missing = [c for c in KB_COLUMNS if c not in df.columns]
if missing:
    raise SystemExit(f"Missing columns: {missing}")
if df.duplicated(subset=["resource_type", "dip_id"]).any():
    raise SystemExit("Duplicate resource_type + dip_id rows found.")
print(f"OK: {len(df)} rows, {len(df.columns)} columns.")