#!/usr/bin/env python3
"""
Resync each `_index.json` so its embedded chunks[].page reflects the corrected
markdown frontmatter (after script 43).

Idempotent.
"""
from __future__ import annotations
import json
import re
from pathlib import Path

CHUNKS_ROOT = Path("/Users/guto/ufo/raw")
PAGE_RE = re.compile(r"^page:\s*(\d+)\s*$", re.M)
CID_RE = re.compile(r"^chunk_id:\s*(\S+)\s*$", re.M)


def main() -> None:
    touched = 0
    for chunks_dir in sorted(CHUNKS_ROOT.glob("*--subagent/chunks")):
        idx_path = chunks_dir.parent / "_index.json"
        if not idx_path.is_file():
            continue
        idx = json.loads(idx_path.read_text(encoding="utf-8"))
        chunks = idx.get("chunks") or []
        if not chunks:
            continue
        # Build chunk_id -> page from disk
        truth: dict[str, int] = {}
        for f in chunks_dir.glob("*.md"):
            head = f.read_text(encoding="utf-8")[:2000]
            cm = CID_RE.search(head)
            pm = PAGE_RE.search(head)
            if cm and pm:
                truth[cm.group(1)] = int(pm.group(1))
        changed = 0
        for entry in chunks:
            cid = entry.get("chunk_id")
            real = truth.get(cid)
            if real is not None and entry.get("page") != real:
                entry["page"] = real
                changed += 1
        if changed:
            idx_path.write_text(json.dumps(idx, indent=2, ensure_ascii=False), encoding="utf-8")
            print(f"  {idx.get('doc_id')}: updated {changed} entries")
            touched += 1
    print(f"\nDocs touched: {touched}")


if __name__ == "__main__":
    main()