mirror of
https://github.com/kuhyx/signal-bot.git
synced 2026-11-10 20:37:03 +01:00
Krzysztof kuhy Rudnicki
dc1995b558
The tally was one integer per person, deleted after each post. Nothing dated survived it, so weeks, months, records, streaks and weekday averages were all unanswerable. This replaces it with an append-only per-message log holding metadata only -- never a message body -- and rebuilds the nightly report on top. What changes for the group: a photo posted without a caption now counts (it was worth zero), stickers count, the bot's own messages no longer do, people who said nothing appear with a 0, and the report covers the previous full calendar day in Europe/Warsaw instead of "since the last post" -- which used to merge two days whenever a group went quiet. Notable decisions, each with the trap it avoids: - Events and people are PERMANENT_TABLES: neither forget_group nor a future SCHEMA_VERSION bump may drop them. Both paths used to cost a day's counter and would now cost the entire history, and forget_group fires on a listing that merely omits members. - is_own comes from which envelope branch carried the payload, not from comparing identities. The account is spelled as a uuid on some frames and a +E.164 number on others, so any comparison misses one of them. - The roster is stashed in refresh(), not _adopt(), which returns early once the watched set stops changing -- i.e. always, in the steady state. - The roster matches on uuid OR number because /v1/groups spells kuhy as +48123456789 while his messages carry an ACI uuid. Joining on uuid alone would have listed him twice every night, once with 0. - Members whose display name we have never seen are counted, not named: their only spellings are a uuid or a phone number. - (group, uuid, sent_at_ms) is the primary key, so a websocket redelivery after a reconnect cannot inflate the counts. - Days come from a stored Warsaw date string, never a timestamp range: 2026-03-29 is 23 hours long and 2026-10-25 is 25. - Polish number agreement is a real rule with a 12-14 exception, so "44 znaki" and "45 znaków" are both spelled correctly. config.py and startup.py were two lines under the 250-line cap and both had to grow, so config_env and startup_retry come out of them first, as pure moves. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015d48t4qsQLBJnDwDeo2Nom
102 lines
3.2 KiB
Python
102 lines
3.2 KiB
Python
# Copyright (c) 2026 Krzysztof Rudnicki. MIT licence.
|
|
"""Envelope parsing across both message shapes."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
|
|
import pytest
|
|
|
|
from signal_bot.models import parse_envelope
|
|
from tests.conftest import WATCHED_GROUP, envelope
|
|
|
|
|
|
def test_parses_group_data_message() -> None:
|
|
message = parse_envelope(envelope(text="!cat"))
|
|
assert message is not None
|
|
assert message.text == "!cat"
|
|
assert message.group_id == WATCHED_GROUP
|
|
assert message.source_uuid == "uuid-alice"
|
|
assert message.source_name == "Alice"
|
|
assert not message.is_direct_message
|
|
|
|
|
|
def test_parses_own_account_sync_message() -> None:
|
|
message = parse_envelope(envelope(text="!dog", sync=True))
|
|
assert message is not None
|
|
assert message.text == "!dog"
|
|
assert message.group_id == WATCHED_GROUP
|
|
|
|
|
|
@pytest.mark.parametrize("shape", [{"sync": False}, {"sync": True}])
|
|
def test_detects_sticker_in_both_shapes(shape: dict[str, bool]) -> None:
|
|
"""The original bot only ever looked under dataMessage, so its own
|
|
stickers were never filtered out of the tally."""
|
|
message = parse_envelope(envelope(extra="sticker", **shape))
|
|
assert message is not None
|
|
assert message.has_sticker
|
|
|
|
|
|
@pytest.mark.parametrize("shape", [{"sync": False}, {"sync": True}])
|
|
def test_detects_reaction_in_both_shapes(shape: dict[str, bool]) -> None:
|
|
message = parse_envelope(envelope(extra="reaction", **shape))
|
|
assert message is not None
|
|
assert message.is_reaction
|
|
|
|
|
|
def test_direct_message_has_no_group() -> None:
|
|
message = parse_envelope(envelope(group_id=None))
|
|
assert message is not None
|
|
assert message.group_id is None
|
|
assert message.is_direct_message
|
|
|
|
|
|
def test_missing_text_is_none() -> None:
|
|
message = parse_envelope(envelope(text=None))
|
|
assert message is not None
|
|
assert message.text is None
|
|
|
|
|
|
def test_non_string_text_is_none() -> None:
|
|
raw = json.dumps({"envelope": {"dataMessage": {"message": 42}}})
|
|
message = parse_envelope(raw)
|
|
assert message is not None
|
|
assert message.text is None
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"raw",
|
|
[
|
|
"not json at all",
|
|
json.dumps(["a", "list"]),
|
|
json.dumps({"envelope": "not a dict"}),
|
|
json.dumps({"account": "+1"}),
|
|
json.dumps({"envelope": {"receiptMessage": {"when": 1}}}),
|
|
json.dumps({"envelope": {"syncMessage": "not a dict"}}),
|
|
json.dumps({"envelope": {"syncMessage": {"readMessages": []}}}),
|
|
],
|
|
)
|
|
def test_unparseable_frames_return_none(raw: str) -> None:
|
|
assert parse_envelope(raw) is None
|
|
|
|
|
|
def test_accepts_bytes() -> None:
|
|
message = parse_envelope(envelope(text="hi").encode())
|
|
assert message is not None
|
|
assert message.text == "hi"
|
|
|
|
|
|
def test_invalid_utf8_bytes_return_none() -> None:
|
|
assert parse_envelope(b"\xff\xfe not utf8") is None
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"group_info",
|
|
["not a dict", {"type": "DELIVER"}, {"groupId": ""}, {"groupId": 12}],
|
|
)
|
|
def test_malformed_group_info_reads_as_direct_message(group_info: object) -> None:
|
|
raw = json.dumps({"envelope": {"dataMessage": {"message": "hi", "groupInfo": group_info}}})
|
|
message = parse_envelope(raw)
|
|
assert message is not None
|
|
assert message.is_direct_message
|