signal-bot/tests/test_art_command.py

# Copyright (c) 2026 Krzysztof Rudnicki. MIT licence.
"""The !sztuka command: one work of art, skewed Polish, captioned."""

from __future__ import annotations

import base64
import json
from typing import TYPE_CHECKING

import httpx
import pytest

from signal_bot.art_command import (
    ART_FILE,
    COMMAND_NAME,
    PER_CENT,
    POLISH_SHARE,
    load_art,
    random_art,
    register_art_command,
)
from signal_bot.context import CommandContext
from signal_bot.decorators import DISPLAY_MARGIN_SECONDS, cooldown
from signal_bot.http_client import ImageFetcher
from signal_bot.models import parse_envelope
from signal_bot.registry import CommandRefusedError, CommandRegistry
from tests.conftest import WATCHED_GROUP, envelope

if TYPE_CHECKING:
    from collections.abc import Callable, Sequence
    from pathlib import Path

    from signal_bot.config import Config
    from signal_bot.store import Store
    from signal_bot.transport_fake import FakeTransport

IMAGE = b"art-bytes"
API = "https://commons.example/w/api.php"
ALIASES = {COMMAND_NAME: ["!sztuka", "!sztukę", "!art"]}
POLISH = (1001, 1002, 1003)
WORLD = (2001, 2002, 2003)
POOLS = (POLISH, WORLD)


def _fetcher(seen: list[httpx.URL] | None = None) -> ImageFetcher:
    def handler(request: httpx.Request) -> httpx.Response:
        if "commons" in str(request.url):
            if seen is not None:
                seen.append(request.url)
            page = {
                "title": "File:Bitwa pod Grunwaldem.jpg",
                "imageinfo": [
                    {
                        "thumburl": "https://cdn/art.jpg",
                        "descriptionurl": "https://commons.wikimedia.org/wiki/File:Grunwald.jpg",
                        "extmetadata": {
                            "ImageDescription": {"value": "Bitwa pod <b>Grunwaldem</b>"},
                        },
                    }
                ],
            }
            return httpx.Response(200, json={"query": {"pages": [page]}})
        return httpx.Response(200, content=IMAGE)

    return ImageFetcher(httpx.AsyncClient(transport=httpx.MockTransport(handler)))


def _ctx(transport: FakeTransport, store: Store, config: Config, text: str) -> CommandContext:
    message = parse_envelope(envelope(text=text))
    assert message is not None
    return CommandContext(
        message=message,
        group_id=WATCHED_GROUP,
        transport=transport,
        store=store,
        config=config,
        command_name=COMMAND_NAME,
        now=100.0,
        day="2026-08-31",
    )


@pytest.mark.parametrize("trigger", ["!sztuka", "!sztukę", "!art"])
def test_every_alias_resolves(trigger: str) -> None:
    registry = CommandRegistry()
    register_art_command(registry, _fetcher(), API, aliases=ALIASES, pools=POOLS)

    command = registry.resolve(trigger)
    assert command is not None
    assert command.name == COMMAND_NAME


def test_the_real_alias_file_carries_the_command() -> None:
    registry = CommandRegistry()
    register_art_command(registry, _fetcher(), API, pools=POOLS)
    # The Polish spelling is the primary one !pomoc prints.
    assert registry.resolve("!sztuka") is not None
    assert registry.resolve("!art") is not None


async def test_it_posts_an_image_captioned_with_what_the_work_is(
    transport: FakeTransport, store: Store, config: Config
) -> None:
    registry = CommandRegistry()
    register_art_command(registry, _fetcher(), API, aliases=ALIASES, pools=POOLS)
    command = registry.resolve("!sztuka")
    assert command is not None

    await command.handler(_ctx(transport, store, config, "!sztuka"))

    sent = transport.sent[0]
    assert sent.recipient == WATCHED_GROUP
    assert sent.image_base64 is not None
    assert base64.b64decode(sent.image_base64) == IMAGE
    assert len(transport.sent) == 1
    assert sent.caption == (
        "Bitwa pod Grunwaldem\nhttps://commons.wikimedia.org/wiki/File:Grunwald.jpg"
    )


async def test_it_names_the_file_by_page_id_and_never_by_title(
    transport: FakeTransport, store: Store, config: Config
) -> None:
    # A Commons painting filename is very often literally somebody's name, so
    # this is the assertion that keeps the query -- and the pool -- on ids.
    seen: list[httpx.URL] = []
    registry = CommandRegistry()
    register_art_command(registry, _fetcher(seen), API, aliases=ALIASES, pools=POOLS)
    command = registry.resolve("!sztuka")
    assert command is not None

    await command.handler(_ctx(transport, store, config, "!sztuka"))

    assert len(seen) == 1
    assert seen[0].params["pageids"] in {str(page) for page in POLISH + WORLD}
    assert "titles" not in seen[0].params


async def test_the_cooldown_decorator_applies(
    transport: FakeTransport, store: Store, config: Config
) -> None:
    registry = CommandRegistry()
    register_art_command(
        registry,
        _fetcher(),
        API,
        decorate=cooldown(10, "WAIT {seconds}"),
        aliases=ALIASES,
        pools=POOLS,
    )
    store.record_use(WATCHED_GROUP, "uuid-alice", COMMAND_NAME, 100.0, "2026-08-31")
    command = registry.resolve("!sztuka")
    assert command is not None

    with pytest.raises(CommandRefusedError):
        await command.handler(_ctx(transport, store, config, "!sztuka"))

    assert transport.texts == [f"WAIT {10 + DISPLAY_MARGIN_SECONDS}"]


def _stub(first: int, second: int = 0) -> Callable[[int], int]:
    """A randbelow whose first answer picks the pool and second picks the work."""
    answers = iter((first, second))

    def randbelow(_: int) -> int:
        return next(answers)

    return randbelow


@pytest.mark.parametrize(
    ("roll", "expected"),
    [(0, POLISH), (POLISH_SHARE - 1, POLISH), (POLISH_SHARE, WORLD), (PER_CENT - 1, WORLD)],
)
def test_the_share_decides_which_pool_is_drawn_from(roll: int, expected: Sequence[int]) -> None:
    """The 60/40 branch, named rather than sampled.

    secrets.randbelow cannot be seeded, so asserting the split by taking real
    draws would either flake or need thousands of iterations. The chooser is
    injectable precisely so this test can say which side it means.
    """
    assert random_art(POLISH, WORLD, _stub(roll)) == expected[0]


def test_the_draw_actually_varies() -> None:
    """0.0.3 posted one identical gecko forever; that is what this catches."""
    drawn = {random_art(POLISH, WORLD) for _ in range(40)}
    assert len(drawn) > 1


def test_both_shipped_pools_are_page_ids_and_nothing_else() -> None:
    """The personal-data invariant, as a unit test.

    A filename here would carry artists' and sitters' names into a public
    repository, and one of them colliding with a label somebody minted from
    the chat wedges check_personal_data.py permanently. Integers cannot.
    """
    document = json.loads(ART_FILE.read_text(encoding="utf-8"))
    for name in ("polish", "world"):
        raw = document[name]
        assert raw
        assert all(isinstance(page, int) for page in raw)
        assert len(set(raw)) == len(raw)
        assert raw == sorted(raw)


def test_the_two_shipped_pools_are_disjoint() -> None:
    # A work in both pools would be drawn at both sets of odds, which makes
    # POLISH_SHARE a number that does not mean what it says.
    polish, world = load_art()
    assert not set(polish) & set(world)


def test_the_shipped_pools_are_large_enough_to_be_worth_drawing_from() -> None:
    # A regeneration that silently truncated one pool would still pass every
    # other test here, and would quietly make the skew a draw from nothing.
    polish, world = load_art()
    assert len(polish) >= 300
    assert len(world) >= 300


@pytest.mark.parametrize("broken", [[], ["1001.jpg"], [None]])
@pytest.mark.parametrize("pool", ["polish", "world"])
def test_a_pool_that_is_not_page_ids_is_refused(
    tmp_path: Path, pool: str, broken: list[object]
) -> None:
    document: dict[str, list[object]] = {"polish": [1001], "world": [2001]}
    document[pool] = broken
    path = tmp_path / "art.json"
    path.write_text(json.dumps(document), encoding="utf-8")

    with pytest.raises(ValueError, match="page ids"):
        load_art(path)