mirror of
https://github.com/kuhyx/signal-bot.git
synced 2026-11-10 20:37:03 +01:00
Krzysztof kuhy Rudnicki
08599e6056
!sztuka posts a work of art, skewed 60% Polish; !wiersz posts one short public-domain Polish poem, whole. Both follow the rule the rest of the bot already keeps: the repository commits identifiers, and the words arrive over the wire when somebody asks. !wiersz was written the other way first, and the gate caught it. A pack of short public-domain poems was harvested, name-filtered and committed, and check_personal_data.sh refused it: three lines carried a real group member's given name, and two still did after a filter that had discarded 31% of the corpus. That is structural, not a tuning problem -- Polish verse capitalises every line, so a line-initial capital carries no signal, and that is exactly where a name sits. The pack now holds Wolne Lektury slugs; the poem, its title and its author are fetched at post time and appear nowhere in git. It is also the better version: with no name filter there are no false positives, so the pool is larger and the attribution is a full name again. The gate then refused the art category list too, over a painter whose given name is somebody's. That is the popes.json case exactly, so it takes the same answer: a file-scoped allowlist entry, still refused everywhere else. The Commons harvest is now three modules by what they are, not by where the line count fell: commons_api is the conversation with Commons, commons_harvest turns categories into a pool of licensed page ids, commons_cache makes an interrupted run resumable. Along the way it gained licences in the same request that lists a category (the second pass was 1,500 requests at 2.3s each), maxlag instead of a guessed sleep, 5xx retries because one 504 used to destroy a whole run, and Wikidata for works by creators of Polish citizenship: the Polish pool grew 15,221 -> 20,092. Batching categories through CirrusSearch looked like a further 6x and was measured out again: 2,404 files where the authoritative enumeration returns 2,429, a different ~1% missing on every run. The offline run is 19s where it was four minutes, almost all of it the deafness gate waiting out three thirty-second liveness probes to prove something provable in three; the tick is configuration now, and e2e enforces a 40s budget on itself so that never silently comes back.
128 lines
4.1 KiB
Python
128 lines
4.1 KiB
Python
# Copyright (c) 2026 Krzysztof Rudnicki. MIT licence.
|
|
"""Command wiring, the daily report, and the listen loop."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import datetime as dt
|
|
from dataclasses import replace
|
|
from typing import TYPE_CHECKING
|
|
|
|
import httpx
|
|
|
|
from signal_bot.bot import Bot, build_bot, now_local
|
|
from signal_bot.liveness import Liveness
|
|
from signal_bot.stats.events import MessageEvent
|
|
from signal_bot.stats.periods import WARSAW
|
|
from tests import pack_fixture
|
|
from tests.conftest import (
|
|
WATCHED_GROUP,
|
|
envelope,
|
|
mock_client,
|
|
)
|
|
|
|
if TYPE_CHECKING:
|
|
from pathlib import Path
|
|
|
|
from signal_bot.config import Config
|
|
from signal_bot.discovery import GroupDirectory
|
|
from signal_bot.store import Store
|
|
from signal_bot.transport_fake import FakeTransport
|
|
|
|
|
|
# The report covers the day it runs on, so the tests freeze "now" and write
|
|
# their events into it.
|
|
NOW = dt.datetime(2026, 9, 2, 21, 37, tzinfo=WARSAW)
|
|
YESTERDAY = "2026-09-01"
|
|
|
|
|
|
def _bot(config: Config, store: Store, transport: FakeTransport, directory: GroupDirectory) -> Bot:
|
|
client = mock_client(lambda r: httpx.Response(200))
|
|
return build_bot(
|
|
config, client, store, transport, directory, Liveness(config, client), clock=lambda: NOW
|
|
)
|
|
|
|
|
|
def wrote(
|
|
store: Store, group_id: str, uuid: str, name: str, times: int, *, day: str = YESTERDAY
|
|
) -> None:
|
|
"""Put ``times`` messages from one person into one group on one day."""
|
|
for i in range(times):
|
|
store.events.record(
|
|
MessageEvent(
|
|
group_id=group_id,
|
|
uuid=uuid,
|
|
display_name=name,
|
|
sent_at_ms=i + 1,
|
|
day=day,
|
|
local_hour=12,
|
|
char_len=5,
|
|
)
|
|
)
|
|
store.events.note_person(group_id, uuid, name, "", day)
|
|
|
|
|
|
def test_now_local_is_timezone_aware() -> None:
|
|
assert now_local().tzinfo is not None
|
|
|
|
|
|
def test_build_bot_registers_the_animal_commands(
|
|
config: Config, store: Store, transport: FakeTransport, directory: GroupDirectory
|
|
) -> None:
|
|
bot = _bot(config, store, transport, directory)
|
|
assert bot.dispatcher.registry.resolve("!cat") is not None
|
|
assert bot.dispatcher.registry.resolve("!pies") is not None
|
|
|
|
|
|
def test_build_bot_registers_the_culture_commands(
|
|
config: Config, store: Store, transport: FakeTransport, directory: GroupDirectory
|
|
) -> None:
|
|
"""!sztuka and !wiersz reach the live registry, off the shipped packs.
|
|
|
|
Both read a committed data file at registration time rather than at the
|
|
moment somebody types the trigger, so a missing or malformed pack is a
|
|
startup failure. This is the test that would catch one.
|
|
"""
|
|
bot = _bot(config, store, transport, directory)
|
|
assert bot.dispatcher.registry.resolve("!sztuka") is not None
|
|
assert bot.dispatcher.registry.resolve("!wiersz") is not None
|
|
|
|
|
|
async def test_listen_dispatches_every_frame(
|
|
config: Config, store: Store, transport: FakeTransport, directory: GroupDirectory
|
|
) -> None:
|
|
transport.queue([envelope(text="hello", group_id=WATCHED_GROUP)])
|
|
await _bot(config, store, transport, directory).listen()
|
|
row = store.events.connection.execute(
|
|
"SELECT COUNT(*) AS n FROM message_events WHERE group_id = ?", (WATCHED_GROUP,)
|
|
).fetchone()
|
|
assert row["n"] == 1
|
|
|
|
|
|
def test_an_album_is_wired_up_only_where_there_is_one(
|
|
tmp_path: Path,
|
|
config: Config,
|
|
store: Store,
|
|
transport: FakeTransport,
|
|
directory: GroupDirectory,
|
|
) -> None:
|
|
"""Absent by default; present, and scoped, when the config names a pack."""
|
|
client = mock_client(lambda r: httpx.Response(200))
|
|
liveness = Liveness(config, client)
|
|
|
|
plain = build_bot(config, client, store, transport, directory, liveness)
|
|
assert plain.dispatcher.registry.resolve("!alfa") is None
|
|
|
|
root = pack_fixture.build(tmp_path / "pack")
|
|
with_album = build_bot(
|
|
replace(config, photo_pack_dirs=(root,)),
|
|
client,
|
|
store,
|
|
transport,
|
|
directory,
|
|
liveness,
|
|
)
|
|
command = with_album.dispatcher.registry.resolve("!alfa")
|
|
assert command is not None
|
|
assert command.name == "pack:p1"
|
|
assert command.groups == frozenset({WATCHED_GROUP})
|