#!/usr/bin/env python3
"""Verify the Zerebro Mind corpus against its manifest. Standard library only.

Usage: python3 verify.py corpus/manifest.json

Manifest format:
  {"generated_at": "...", "root_sha256": "<hex>",
   "items": [{"id": "...", "source": "...", "url": "...", "date": "...",
              "sha256": "<hex>", "path": "<file relative to manifest dir>"}, ...]}

root_sha256 = sha256 of the UTF-8 text made of one line per item,
"<sha256> <id>\n", sorted by id.
"""
import hashlib
import json
import sys
from pathlib import Path


def file_sha256(path):
    h = hashlib.sha256()
    with open(path, "rb") as f:
        for chunk in iter(lambda: f.read(1 << 16), b""):
            h.update(chunk)
    return h.hexdigest()


def root_hash(items):
    lines = "".join(f"{it['sha256']} {it['id']}\n" for it in sorted(items, key=lambda i: i["id"]))
    return hashlib.sha256(lines.encode("utf-8")).hexdigest()


def main():
    manifest_path = Path(sys.argv[1] if len(sys.argv) > 1 else "corpus/manifest.json")
    manifest = json.loads(manifest_path.read_text(encoding="utf-8"))
    base = manifest_path.parent
    items = manifest.get("items", [])
    bad = 0
    for it in items:
        p = base / it["path"]
        if not p.is_file():
            print(f"MISSING  {it['id']}  {p}")
            bad += 1
            continue
        got = file_sha256(p)
        if got != it["sha256"]:
            print(f"MISMATCH {it['id']}  expected {it['sha256']}  got {got}")
            bad += 1
    root = root_hash(items)
    root_ok = root == manifest.get("root_sha256")
    print(f"items checked: {len(items)}  failures: {bad}")
    print(f"root sha256:   {root}  ({'matches' if root_ok else 'DOES NOT MATCH'} manifest)")
    print(f"manifest file: {file_sha256(manifest_path)}")
    sys.exit(0 if bad == 0 and root_ok else 1)


if __name__ == "__main__":
    main()