#!/usr/bin/env python3
"""Convert ./cvar_list (cvarlist dump) to static/data/srccfg-vocab.json.

Usage: ./l4d2web/scripts/build-vocab.py
Reads from the repo root (auto-detected via this script's path).
Writes idempotently. Run after regenerating cvar_list."""
from __future__ import annotations

import hashlib
import json
import pathlib
import re
import sys

HERE = pathlib.Path(__file__).resolve().parent
REPO_ROOT = HERE.parent.parent
SOURCE = REPO_ROOT / "cvar_list"
DEST = REPO_ROOT / "l4d2web" / "l4d2web" / "static" / "data" / "srccfg-vocab.json"


def parse(text: str) -> tuple[list[dict], list[dict]]:
    cvars: list[dict] = []
    commands: list[dict] = []
    for raw in text.splitlines()[2:]:  # skip "cvar list" + "--------…"
        if not raw.strip():
            continue
        parts = [p.strip() for p in re.split(r"\s*:\s*", raw, maxsplit=3)]
        if len(parts) < 3:
            continue
        name = parts[0]
        value = parts[1]
        desc = parts[3] if len(parts) >= 4 else ""
        target = commands if value == "cmd" else cvars
        target.append({"name": name, "desc": desc} if desc else {"name": name})
    return cvars, commands


def main() -> int:
    if not SOURCE.exists():
        print(f"ERROR: {SOURCE} not found", file=sys.stderr)
        return 1
    text = SOURCE.read_text(encoding="utf-8", errors="replace")
    cvars, commands = parse(text)
    src_sha = hashlib.sha256(text.encode("utf-8")).hexdigest()
    payload = {
        "version": 1,
        "generated_from": "cvar_list",
        "source_sha256": src_sha,
        "cvars": cvars,
        "commands": commands,
    }
    DEST.parent.mkdir(parents=True, exist_ok=True)
    DEST.write_text(json.dumps(payload, indent=2, sort_keys=False) + "\n", encoding="utf-8")
    print(f"wrote {DEST}: {len(cvars)} cvars + {len(commands)} commands")
    return 0


if __name__ == "__main__":
    raise SystemExit(main())