#!/usr/bin/env python3
import argparse
import json
from pathlib import Path
import subprocess

def validate(path):
    obj = json.loads(path.read_text(encoding="utf-8"))
    if "products" in obj or "matchStrings" in obj:
        raise ValueError("Unexpected page envelope in record")
    expected = "cpe" if "/cpes/" in "/" + path.as_posix() else "matchString"
    field = "cpeNameId" if expected == "cpe" else "matchCriteriaId"
    if not isinstance(obj.get(expected), dict) or not obj[expected].get(field):
        raise ValueError(f"Invalid record {path}")

def main():
    p = argparse.ArgumentParser()
    p.add_argument("--changed", action="store_true")
    args = p.parse_args()
    if args.changed:
        result = subprocess.run(["git", "status", "--porcelain", "--untracked-files=all", "--", "data"], capture_output=True, text=True, check=True)
        files = [Path(line[3:]) for line in result.stdout.splitlines() if len(line) > 3 and line[:2] != " D" and line[:2] != "D "]
    else:
        files = list(Path("data").rglob("*.json"))
    count = 0
    for path in files:
        if not path.is_file() or path.suffix != ".json": continue
        validate(path)
        count += 1
    print(f"VALID: {count} CPE / match records", flush=True)

if __name__ == "__main__": main()