#!/usr/bin/env python3
"""Fail when the compose stack and the Helm chart stop describing the same stack.

`infra/docker-compose.yml` is CI-canonical; `infra/helm/big-reference` is a
transcription of it (ADR-0033), and until now nothing kept the two in step — an
upstream image bump or a new service applied to only one of them landed
unnoticed. This compares what each side actually *deploys*, not the two files:
the rendered chart against `docker compose config`. Both tools are already
prerequisites of the `k8s-*` make targets.

Run it with `make k8s-drift`. No cluster needed.

ponytail: names and images only, as sets — no per-workload env/ports/volumes.
Those differ by design in four documented places (ADR-0033), so comparing them
would mean re-encoding every deviation field by field; a tag bump and a missing
service are the drift that actually bites.
"""

import json
import re
import subprocess
import sys
from pathlib import Path

ROOT = Path(__file__).resolve().parents[2]
COMPOSE = ROOT / "infra/docker-compose.yml"
CHART = ROOT / "infra/helm/big-reference"

# The busybox init container that every `waitFor` workload gets exists only in
# the chart (compose has `depends_on`). Rendering it under a sentinel makes it
# filterable without teaching the check what busybox is.
BUSYBOX = "drift-check-ignored-init-image"

# Differences that Kubernetes forces, not drift (ADR-0033). A name listed here is
# expected to be on exactly one side; anything else fails.
DEVIATIONS = {
    # The four Django services apply their own setup_configuration in the web pod
    # (`args: [sh, -c, "/setup_configuration.sh && exec /start.sh"]`) rather than in a
    # separate init Job. Both that script and /start.sh run `manage.py migrate`, and
    # Kubernetes has no `depends_on: service_completed_successfully` to serialise them,
    # so the Job and its web pod migrated the same database concurrently.
    "oz-init": "folded into the openzaak pod",
    "nrc-init": "folded into the nrc-web pod",
    "objecttypen-init": "folded into the objecttypen pod",
    "objecten-init": "folded into the objecten pod",
    # Compose seeds these from the host — the verify scripts `docker cp` the two
    # scripts into a running container, and docker-compose.local.yml carries
    # `local-seed` + `nrc-subscribe` for `make local`. A cluster has no host to seed
    # from, so both became Jobs in the chart.
    "seed-zaaktype": "compose seeds the catalogus from the host (infra/openzaak/seed_catalogus.py)",
    "nrc-subscribe": "compose registers the abonnement from the host (infra/local/register-abonnement.py)",
}

# Workloads the observability backplane adds. Off by default in both stacks'
# defaults, so they are rendered on purpose here — otherwise their images drift
# unwatched.
OBSERVABILITY = ["tempo", "prometheus", "grafana"]


def compose_services() -> dict[str, str]:
    """Service name -> image, with ${TAG:-default} interpolation already applied."""
    out = run(["docker", "compose", "-f", str(COMPOSE), "config", "--format", "json"])
    return {name: svc.get("image", "") for name, svc in json.loads(out)["services"].items()}


def chart_workloads() -> dict[str, str]:
    """Workload name -> image, read back out of the rendered manifests."""
    out = run(
        ["helm", "template", "big", str(CHART), "-n", "big", "--set", f"images.busybox={BUSYBOX}"]
        + [f"--set=workloads.{w}.enabled=true" for w in OBSERVABILITY]
    )
    workloads = {}
    for doc in out.split("\n---"):
        if not re.search(r"^kind: (Deployment|Job)$", doc, re.M):
            continue
        name = re.search(r"^  name: (\S+)$", doc, re.M)[1]
        images = [i for i in re.findall(r"^\s+image: (\S+)$", doc, re.M) if i != BUSYBOX]
        workloads[name] = images[0]
    return workloads


def run(argv: list[str]) -> str:
    proc = subprocess.run(argv, capture_output=True, text=True)
    if proc.returncode != 0:
        sys.exit(f"{argv[0]} failed:\n{proc.stderr}")
    return proc.stdout


def main() -> int:
    compose, chart = compose_services(), chart_workloads()
    problems = []

    for name in sorted(set(compose) - set(chart) - set(DEVIATIONS)):
        problems.append(f"  {name}: in docker-compose.yml, not in the chart")
    for name in sorted(set(chart) - set(compose) - set(DEVIATIONS)):
        problems.append(f"  {name}: in the chart, not in docker-compose.yml")
    for name in sorted(set(compose) & set(chart)):
        if compose[name] != chart[name]:
            problems.append(f"  {name}: compose runs {compose[name]}, the chart runs {chart[name]}")

    if problems:
        print("compose and the Helm chart describe different stacks:\n" + "\n".join(problems))
        print(
            "\nPort the change to the other stack, or — if the difference is forced by\n"
            "Kubernetes — declare it in DEVIATIONS in this file, with the reason."
        )
        return 1

    print(f"no drift: {len(chart)} workloads, images identical on both stacks")
    for name, why in sorted(DEVIATIONS.items()):
        print(f"  deviation (declared): {name} — {why}")
    return 0


if __name__ == "__main__":
    sys.exit(main())