mirror of
https://github.com/kuhyx/signal-bot.git
synced 2026-11-11 14:27:50 +01:00
!pułapka (and !trap, !sidła, !wnyk, !potrzask, 26 spellings in all) posts a photograph of the literal device -- a bear trap, a mousetrap, a snare, a fish weir -- captioned with what Commons says it is. The pool is 2218 Commons page ids, harvested by tool/gen_traps.py from a curated seed list and committed. Page ids and not filenames on purpose: a filename carries photographers' and sitters' names, and one of those colliding with a label somebody mints from the chat would wedge check_personal_data.py permanently, over data nobody can edit by hand. _repo_vocabulary() subtracts aliases.json and nothing else, so it would not have caught it. An integer cannot carry a name. Nothing is cached. !papież caches because 267 portraits are a closed set a group works through; a uniform draw from 2218 warms a cache essentially never, so this fetches per call the way !kot and !pies do. What the harvest measured, and now enforces: - five plausible seed categories do not exist (Snares, Man traps, Hunting traps, Wasp traps, Animal trapping). A missing category is an empty answer, not an error, so verify_seeds() asks Commons before harvesting and fails loudly naming all of them. - depth three from Category:Fish traps reaches Alfred Sisley's net paintings. Depth one, from seeds picked by hand. - "<thing> in art" categories are paintings: Mousetraps in art put a Robert Campin altarpiece in the pool. Pruned by pattern, since Commons mints a new one whenever somebody needs it. Booby traps, the Wolfsangel, camera traps and animals dying in traps are pruned by name. - Commons rate-limits hard, so a partial harvest must not be committed silently: 429 backs off, and a short pool refuses to write at all. Descriptions are HTML and sometimes say nothing, so the tags come out, the Fisheries records' trailing catalogue list is cut, a description naming only the country falls back to the filename, and the file's own page is always linked. !łapka is not an alias: it resolves to !papa at distance two, which test_nearest.py fails on, and rightly -- the suggestion would be a coin toss. signal_bot/commons.py is the imageinfo query both Commons commands now share; portraits.py keeps its behaviour and its tests unchanged. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01416TegJ3sa8xL5qGGgrygP
117 lines
4.3 KiB
Python
117 lines
4.3 KiB
Python
# Copyright (c) 2026 Krzysztof Rudnicki. MIT licence.
|
|
"""The !pułapka command: a photograph of the device, and what it is.
|
|
|
|
The joke is literalism -- whatever the word meant to whoever typed it, what
|
|
comes back is a bear trap, a mousetrap, a snare, a cage, a fish weir. The
|
|
caption is not an apology for the joke, it is the answer to the next
|
|
question: Commons has plenty of files whose subject is genuinely unguessable
|
|
("Molchreuse", "K Pañayacu 0811"), and a newt trap nobody can identify is
|
|
just a photograph of a basket.
|
|
|
|
Nothing is cached. !papież caches because 267 portraits are a closed set a
|
|
group works through; a uniform draw from a couple of thousand traps warms a
|
|
cache essentially never, so the disk would fill with images nobody asks for
|
|
twice. This works the way !kot and !pies do instead: fetch, post, forget.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import secrets
|
|
from base64 import b64encode
|
|
from pathlib import Path
|
|
from typing import TYPE_CHECKING, Final
|
|
|
|
from signal_bot.animals import load_aliases
|
|
from signal_bot.commons import caption_for, imageinfo_params, page_of
|
|
from signal_bot.endpoints import THUMB_WIDTH
|
|
|
|
if TYPE_CHECKING:
|
|
from collections.abc import Sequence
|
|
|
|
from signal_bot.context import CommandContext
|
|
from signal_bot.decorators import Decorator
|
|
from signal_bot.http_client import ImageFetcher
|
|
from signal_bot.registry import CommandRegistry, Handler
|
|
|
|
COMMAND_NAME: Final = "trap"
|
|
DESCRIPTION: Final = "losowe zdjęcie pułapki"
|
|
TRAPS_FILE: Final = Path(__file__).with_name("traps.json")
|
|
|
|
|
|
def load_traps(path: Path = TRAPS_FILE) -> tuple[int, ...]:
|
|
"""Read the trap pool.
|
|
|
|
The file holds Commons page ids -- bare integers -- and that is checked
|
|
here rather than assumed. Filenames would be free text carrying
|
|
photographers' and sitters' names, and a name committed here collides
|
|
sooner or later with a label somebody minted from the chat, at which
|
|
point scripts/check_personal_data.py refuses every commit for good over
|
|
data nobody can edit by hand. An integer cannot do that, and this is the
|
|
guard that keeps it an integer.
|
|
|
|
Args:
|
|
path: Where to read the pool from. Defaults to the shipped file.
|
|
|
|
Returns:
|
|
Every Commons page id in the pool.
|
|
|
|
Raises:
|
|
ValueError: If the pool is empty or holds anything but integers.
|
|
"""
|
|
document = json.loads(path.read_text(encoding="utf-8"))
|
|
traps = document["traps"]
|
|
if not traps or not all(isinstance(page, int) for page in traps):
|
|
msg = f"{path} must hold a non-empty list of Commons page ids"
|
|
raise ValueError(msg)
|
|
return tuple(traps)
|
|
|
|
|
|
def random_trap(traps: Sequence[int]) -> int:
|
|
"""Return one page id, uniformly at random.
|
|
|
|
secrets rather than random for the reason animals.paged_url gives: the
|
|
choice is not security-sensitive, but ruff's ALL rule set flags `random`
|
|
and this repository forbids the noqa that would silence it.
|
|
"""
|
|
return traps[secrets.randbelow(len(traps))]
|
|
|
|
|
|
def trap_handler(
|
|
fetcher: ImageFetcher,
|
|
api_url: str,
|
|
traps: Sequence[int] | None = None,
|
|
) -> Handler:
|
|
"""Build the handler that posts one random trap."""
|
|
pool = load_traps() if traps is None else tuple(traps)
|
|
|
|
async def handler(ctx: CommandContext) -> None:
|
|
# One request, because the caption and the picture have to describe
|
|
# the same file; two would be a chance for them to disagree.
|
|
document = await fetcher.fetch_json(
|
|
api_url,
|
|
imageinfo_params(THUMB_WIDTH, page_id=random_trap(pool), describe=True),
|
|
)
|
|
page = page_of(document)
|
|
image = await fetcher.fetch_image(str(page["imageinfo"][0]["thumburl"]))
|
|
await ctx.reply_image(b64encode(image).decode("ascii"), caption_for(page))
|
|
|
|
return handler
|
|
|
|
|
|
def register_trap_command(
|
|
registry: CommandRegistry,
|
|
fetcher: ImageFetcher,
|
|
api_url: str,
|
|
*,
|
|
decorate: Decorator | None = None,
|
|
aliases: dict[str, list[str]] | None = None,
|
|
traps: Sequence[int] | None = None,
|
|
) -> None:
|
|
"""Register !pułapka under every trigger aliases.json gives it."""
|
|
table = load_aliases() if aliases is None else aliases
|
|
handler = trap_handler(fetcher, api_url, traps)
|
|
if decorate is not None:
|
|
handler = decorate(handler)
|
|
registry.register(COMMAND_NAME, table[COMMAND_NAME], handler, DESCRIPTION)
|