#!/usr/bin/env python3
"""Sync the canon classification allowed-values into the chart (CUST-WP-0067-T09).

The State Hub validates repository classification against
``the-custodian/canon/standards/repo-classification.allowed.yaml``. That file is
canon and must stay authoritative, but a container has no the-custodian
checkout, so a copy has to travel with the release.

A copy that nobody checks is a copy that silently drifts. This script owns the
copy: ``--check`` fails when it diverges from canon, so the release can refuse
to ship a stale vocabulary rather than validate against yesterday's rules.

Usage:
    python scripts/sync_classification_allowed.py            # write the copy
    python scripts/sync_classification_allowed.py --check    # verify, exit 1 on drift
"""
from __future__ import annotations

import argparse
import difflib
import sys
from pathlib import Path

REPO_ROOT = Path(__file__).resolve().parent.parent
CHART_COPY = (
    REPO_ROOT
    / "deploy/railiance/apps/charts/state-hub/files/repo-classification.allowed.yaml"
)
CANON_CANDIDATES = (
    Path("/home/worsch/the-custodian/canon/standards/repo-classification.allowed.yaml"),
    Path("/home/tegwick/the-custodian/canon/standards/repo-classification.allowed.yaml"),
    REPO_ROOT.parent / "the-custodian/canon/standards/repo-classification.allowed.yaml",
)

HEADER = (
    "# GENERATED — do not edit.\n"
    "# Synced from the-custodian/canon/standards/repo-classification.allowed.yaml\n"
    "# by scripts/sync_classification_allowed.py (CUST-WP-0067-T09).\n"
    "# Canon is authoritative; this copy exists only so the container has one.\n"
)


def find_canon() -> Path:
    for candidate in CANON_CANDIDATES:
        if candidate.is_file():
            return candidate
    raise SystemExit(
        "ERROR: canon allowed-values not found. Looked in:\n  "
        + "\n  ".join(str(c) for c in CANON_CANDIDATES)
    )


def main() -> int:
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument(
        "--check",
        action="store_true",
        help="Verify the chart copy matches canon; exit 1 on drift",
    )
    args = parser.parse_args()

    canon = find_canon()
    desired = HEADER + canon.read_text(encoding="utf-8")

    if args.check:
        if not CHART_COPY.is_file():
            print(f"DRIFT: {CHART_COPY} is missing; run without --check to create it")
            return 1
        current = CHART_COPY.read_text(encoding="utf-8")
        if current != desired:
            print(f"DRIFT: chart copy differs from canon ({canon})")
            sys.stdout.writelines(
                difflib.unified_diff(
                    current.splitlines(keepends=True),
                    desired.splitlines(keepends=True),
                    fromfile="chart copy",
                    tofile="canon",
                )
            )
            return 1
        print(f"OK: chart copy matches canon ({canon})")
        return 0

    CHART_COPY.parent.mkdir(parents=True, exist_ok=True)
    CHART_COPY.write_text(desired, encoding="utf-8")
    print(f"Synced {canon} -> {CHART_COPY}")
    return 0


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