"""Block until Postgres and Redis accept connections. Exit 0 ready, 1 timed out.

## Why the container has to do this itself

Compose has `depends_on: {condition: service_healthy}`, and **Swarm ignores
it**. `docker stack deploy` has no ordering primitive at all: every service in
the stack starts at once, so FabledCurator races Postgres on every cold
deploy and always has.

The multi-service stack hid how sharp that is. `web` ran `alembic upgrade
head`, failed against a Postgres that was still doing `initdb`, and the task
died — but Swarm restarts a failed task forever, so the service came up a few
seconds later and nobody saw a problem worth naming.

Consolidation removes that safety net. supervisord gives each program
`startretries=3`, so a web program that fails three times in the first
seconds goes FATAL and **stays** FATAL: supervisord keeps running, the
container keeps running, and the application never starts. The healthcheck
catches it — but as a container that is permanently unhealthy for a reason
that has nothing to do with the image, on a stack whose database simply took
twenty seconds to initialise.

Operator, 2026-09-23: *"it's a single container that need to connect
successfully to redis and postgres before starting work shouldn't that simply
be a check (with retries) at the start of the container."* Yes.

## A TCP connect, not a query

The same probe `build.yml`'s integration lane and the build smoke already use.
It answers the question that is actually being asked — is something listening
— and it cannot fail for a reason that retrying will never fix.

A real query would be a stronger readiness signal and a worse gate: a wrong
password or a missing database is not a transient condition, and a loop that
waits for one to heal turns a five-second misconfiguration into a two-minute
timeout with a misleading message. Those belong to alembic, which runs
seconds later and says exactly what is wrong.

The Postgres image is well behaved here: during `initdb` it serves on a unix
socket only and opens TCP when it is ready for clients, so the connect is a
good proxy for "ready" rather than merely "process exists".
"""

from __future__ import annotations

import argparse
import os
import socket
import sys
import time
from urllib.parse import urlparse

# Long enough for a first-ever `initdb` on a slow disk, which is the worst
# case this exists for and is measured in tens of seconds, not minutes. A
# deploy that is genuinely misconfigured should fail while someone is still
# watching it rather than hold the container open for a quarter of an hour.
DEFAULT_TIMEOUT = 120.0
CONNECT_TIMEOUT = 2.0
RETRY_DELAY = 1.0
# Progress every N attempts. `docker logs` on a container that is waiting must
# say what it is waiting for — silence is indistinguishable from a hang.
REPORT_EVERY = 5


def _target(url: str | None, default_port: int) -> tuple[str, int] | None:
    """(host, port) from a connection URL, or None if there is nothing to wait for."""
    if not url:
        return None
    parsed = urlparse(url)
    if not parsed.hostname:
        return None
    return parsed.hostname, parsed.port or default_port


def targets() -> list[tuple[str, tuple[str, int]]]:
    """What this container must reach, read from the same env the app reads.

    Derived rather than passed in, so the wait cannot drift from what the
    application will actually connect to — a gate that checks a different
    host than the app uses is worse than no gate.
    """
    out: list[tuple[str, tuple[str, int]]] = []

    host = os.environ.get("DB_HOST")
    if host:
        out.append(("postgres", (host, int(os.environ.get("DB_PORT") or 5432))))

    broker = _target(os.environ.get("CELERY_BROKER_URL"), 6379)
    if broker:
        out.append(("redis", broker))

    return out


def _accepts(host: str, port: int) -> bool:
    try:
        with socket.create_connection((host, port), timeout=CONNECT_TIMEOUT):
            return True
    except OSError:
        return False


def wait(
    name: str, host: str, port: int, deadline: float, now=time.monotonic,
) -> bool:
    attempt = 0
    while True:
        if _accepts(host, port):
            print(f"[wait] {name} at {host}:{port} is accepting connections")
            return True
        attempt += 1
        if now() >= deadline:
            print(
                f"[wait] TIMEOUT: {name} at {host}:{port} never accepted a "
                f"connection ({attempt} attempts)",
                file=sys.stderr,
            )
            return False
        if attempt % REPORT_EVERY == 0:
            left = int(deadline - now())
            print(f"[wait] {name} at {host}:{port} not ready yet, {left}s left")
        time.sleep(RETRY_DELAY)


def main(argv: list[str] | None = None) -> int:
    ap = argparse.ArgumentParser(description="Wait for Postgres and Redis.")
    ap.add_argument("--timeout", type=float, default=DEFAULT_TIMEOUT)
    args = ap.parse_args(argv)

    wanted = targets()
    if not wanted:
        # Nothing configured to wait for. Not an error: `shell` and one-off
        # runs are legitimate, and refusing to start would make this gate the
        # reason a debugging container will not boot.
        print("[wait] no database or broker configured; nothing to wait for")
        return 0

    deadline = time.monotonic() + args.timeout
    for name, (host, port) in wanted:
        if not wait(name, host, port, deadline):
            return 1
    return 0


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