signal-bot/tests/test_poem_command.py

# Copyright (c) 2026 Krzysztof Rudnicki. MIT licence.
"""The !wiersz command: one short public-domain Polish poem, whole."""

from __future__ import annotations

import json
from typing import TYPE_CHECKING

import httpx
import pytest

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.poem_command import (
    COMMAND_NAME,
    MAX_CHARS,
    MAX_LINES,
    POEMS_FILE,
    load_slugs,
    random_slug,
    register_poem_command,
    render,
)
from signal_bot.registry import CommandRefusedError, CommandRegistry
from signal_bot.wolnelektury import PUBLIC_DOMAIN, Poem
from tests.conftest import WATCHED_GROUP, envelope

if TYPE_CHECKING:
    from pathlib import Path

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

TEXT_URL = "https://lektury.example/txt/{slug}.txt"
ALIASES = {COMMAND_NAME: ["!wiersz", "!wiersze", "!poem"]}
POOL = ("bol-tabuli", "impas", "nikt-nic")
BODY = "Pierwsza linijka wiersza,\ndruga linijka wiersza."


def _fetcher(seen: list[httpx.URL] | None = None, *, body: str = BODY) -> ImageFetcher:
    def handler(request: httpx.Request) -> httpx.Response:
        if seen is not None:
            seen.append(request.url)
        raw = f"Maria Konopnicka\n\nA co wam śpiewać\n\n\n{body}\n\n-----\n{PUBLIC_DOMAIN}\n"
        return httpx.Response(200, text=raw)

    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", ["!wiersz", "!wiersze", "!poem"])
def test_every_alias_resolves(trigger: str) -> None:
    registry = CommandRegistry()
    register_poem_command(registry, _fetcher(), TEXT_URL, aliases=ALIASES, slugs=POOL)

    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_poem_command(registry, _fetcher(), TEXT_URL, slugs=POOL)
    # The Polish spelling is the primary one !pomoc prints.
    assert registry.resolve("!wiersz") is not None
    assert registry.resolve("!poem") is not None


async def test_it_posts_the_poem_its_author_and_where_it_came_from(
    transport: FakeTransport, store: Store, config: Config
) -> None:
    registry = CommandRegistry()
    register_poem_command(registry, _fetcher(), TEXT_URL, aliases=ALIASES, slugs=("impas",))
    command = registry.resolve("!wiersz")
    assert command is not None

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

    expected = (
        f"A co wam śpiewać\n\n{BODY}\n\n— Maria Konopnicka\n"
        "https://wolnelektury.pl/katalog/lektura/impas/"
    )
    assert transport.texts == [expected]
    # Text, not an attachment: this is the one content command that posts no
    # picture, and sending an empty image would be a silent wrong turn.
    assert len(transport.sent) == 1
    assert transport.sent[0].image_base64 is None
    # ...and it still quotes the asker, like every other reply.
    assert transport.sent[0].quote is not None


async def test_the_full_author_name_is_posted_though_it_is_never_committed(
    transport: FakeTransport, store: Store, config: Config
) -> None:
    """The point of fetching rather than committing, as an assertion.

    "Maria" is a Polish given name. Posting it is fine; committing several
    hundred like it is what made check_personal_data.py refuse the first
    version of this pack. See the module docstring.
    """
    registry = CommandRegistry()
    register_poem_command(registry, _fetcher(), TEXT_URL, aliases=ALIASES, slugs=POOL)
    command = registry.resolve("!wiersz")
    assert command is not None

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

    assert "Maria Konopnicka" in transport.texts[0]


async def test_it_asks_for_the_slug_it_drew(
    transport: FakeTransport, store: Store, config: Config
) -> None:
    seen: list[httpx.URL] = []
    registry = CommandRegistry()
    register_poem_command(registry, _fetcher(seen), TEXT_URL, aliases=ALIASES, slugs=("impas",))
    command = registry.resolve("!wiersz")
    assert command is not None

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

    assert len(seen) == 1
    assert str(seen[0]) == "https://lektury.example/txt/impas.txt"


async def test_an_upstream_that_stops_serving_a_poem_is_not_posted(
    transport: FakeTransport, store: Store, config: Config
) -> None:
    """A half-parsed poem is not something to put in a group.

    The dispatcher turns this into a log line and silence, which is what
    every other command already does when its upstream misbehaves.
    """
    registry = CommandRegistry()
    fetcher = ImageFetcher(
        httpx.AsyncClient(transport=httpx.MockTransport(lambda _: httpx.Response(200, text="")))
    )
    register_poem_command(registry, fetcher, TEXT_URL, aliases=ALIASES, slugs=POOL)
    command = registry.resolve("!wiersz")
    assert command is not None

    with pytest.raises(ValueError, match="no longer serves"):
        await command.handler(_ctx(transport, store, config, "!wiersz"))

    assert transport.sent == []


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

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

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


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


def test_render_puts_the_poem_before_the_attribution() -> None:
    # The order is the point: a group reads the poem, then who wrote it.
    text = render(Poem(title="Impas", author="Bolesław Leśmian", text=BODY), "impas")
    assert text.index("Pierwsza") < text.index("— Bolesław") < text.index("wolnelektury.pl")


def test_the_shipped_pack_holds_slugs_and_no_poetry() -> None:
    """The privacy invariant this whole command is shaped around.

    Committing the poems themselves is what check_personal_data.py refused:
    three lines carried a real group member's name, and two still did after
    a filter that had already discarded 31% of the corpus. A slug cannot
    carry a name that way. This is the test that keeps the pack to slugs
    when somebody regenerates it.
    """
    raw = json.loads(POEMS_FILE.read_text(encoding="utf-8"))["poems"]
    assert raw
    assert all(isinstance(slug, str) and slug for slug in raw)
    # A slug is a lowercase hyphenated handle, never prose: no capitals, no
    # whitespace, no punctuation that a line of verse would carry.
    assert all(slug == slug.lower() for slug in raw)
    assert not any(set(slug) & set(" \n.,;:!?\"'") for slug in raw)
    assert len(set(raw)) == len(raw)
    assert raw == sorted(raw)
    # What this does NOT claim: that no slug contains a word that is also
    # somebody's name. "Zosia i jej mopsy" is a Konopnicka poem and its slug
    # is zosia-i-jej-mopsy, because a capitalised *first* word is how every
    # title starts and cannot be told from a name. That residue is acceptable
    # where a pack of poems was not, and the difference is repair: the real
    # check is scripts/check_personal_data.sh, pre-commit runs it on every
    # commit, and a colliding slug is one line to delete out of 1180. The
    # text version wedged the repository with "data nobody can edit out by
    # hand"; this is a one-line edit and a regeneration.


def test_the_shipped_pack_is_large_enough_to_be_worth_drawing_from() -> None:
    # A regeneration that silently truncated would still pass every other
    # test here, and would quietly shrink the command's whole world.
    assert len(load_slugs()) >= 300


def test_the_caps_are_the_promise_the_pack_makes() -> None:
    # Whole poems only. The caps are enforced at harvest time, so they live
    # next to the command rather than in the generator that applies them.
    assert MAX_LINES == 24
    assert MAX_CHARS == 1200


@pytest.mark.parametrize("broken", [[], ["", "impas"], [None], [3]])
def test_a_pool_that_is_not_slugs_is_refused(tmp_path: Path, broken: list[object]) -> None:
    path = tmp_path / "poems.json"
    path.write_text(json.dumps({"poems": broken}), encoding="utf-8")

    with pytest.raises(ValueError, match="slugs"):
        load_slugs(path)