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
123 lines
4.2 KiB
Python
123 lines
4.2 KiB
Python
# Copyright (c) 2026 Krzysztof Rudnicki. MIT licence.
|
|
"""Warsaw days, and the periods built out of them."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import datetime as dt
|
|
|
|
import pytest
|
|
|
|
from signal_bot.stats import periods
|
|
|
|
# 2026-09-01 21:37 Warsaw, as Signal would timestamp it.
|
|
TUESDAY_MS = int(dt.datetime(2026, 9, 1, 21, 37, tzinfo=periods.WARSAW).timestamp() * 1000)
|
|
|
|
|
|
def test_now_is_warsaw() -> None:
|
|
assert periods.now().tzinfo is periods.WARSAW
|
|
|
|
|
|
def test_day_and_hour_are_warsaw_wall_clock() -> None:
|
|
assert periods.day_of(TUESDAY_MS) == "2026-09-01"
|
|
assert periods.hour_of(TUESDAY_MS) == 21
|
|
|
|
|
|
def test_a_late_evening_message_stays_on_its_own_day() -> None:
|
|
"""23:50 Warsaw is still today, even though it is already tomorrow in UTC+3."""
|
|
late = int(dt.datetime(2026, 9, 1, 23, 50, tzinfo=periods.WARSAW).timestamp() * 1000)
|
|
assert periods.day_of(late) == "2026-09-01"
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("day", "hours"),
|
|
[("2025-10-26", 25), ("2026-03-29", 23), ("2026-10-25", 25), ("2026-09-01", 24)],
|
|
)
|
|
def test_warsaw_days_are_not_all_24_hours(day: str, hours: int) -> None:
|
|
"""The reason every period groups on the stored day string.
|
|
|
|
Computed through UTC deliberately: subtracting two aware datetimes that
|
|
share a tzinfo gives the wall-clock difference, which reports all four of
|
|
these as 24 and hides the whole problem.
|
|
"""
|
|
date = dt.date.fromisoformat(day)
|
|
start = dt.datetime.combine(date, dt.time(), periods.WARSAW).astimezone(dt.UTC)
|
|
end = dt.datetime.combine(date + dt.timedelta(days=1), dt.time(), periods.WARSAW)
|
|
assert (end.astimezone(dt.UTC) - start).total_seconds() / 3600 == hours
|
|
|
|
|
|
def test_shift_crosses_a_short_day_by_the_date() -> None:
|
|
"""Minus 86400 seconds would land at 23:00 the evening before."""
|
|
assert periods.shift("2026-03-30", -1) == "2026-03-29"
|
|
assert periods.shift("2026-03-29", -1) == "2026-03-28"
|
|
|
|
|
|
def test_today_and_previous_day_take_an_injected_clock() -> None:
|
|
at = dt.datetime(2026, 9, 2, 0, 30, tzinfo=periods.WARSAW)
|
|
assert periods.today(at) == "2026-09-02"
|
|
assert periods.previous_day(at) == "2026-09-01"
|
|
|
|
|
|
def test_a_utc_clock_is_converted_rather_than_truncated() -> None:
|
|
"""22:30 UTC is already the next day in Warsaw."""
|
|
at = dt.datetime(2026, 9, 1, 22, 30, tzinfo=dt.UTC)
|
|
assert periods.today(at) == "2026-09-02"
|
|
|
|
|
|
def test_weekday_of() -> None:
|
|
assert periods.weekday_of("2026-09-01") == 1
|
|
assert periods.WEEKDAY_NAMES[1] == "Wtorek"
|
|
assert periods.WEEKDAY_PLURAL[1] == "wtorki"
|
|
|
|
|
|
def test_pl_date_uses_the_genitive_month() -> None:
|
|
assert periods.pl_date("2026-09-01") == "Wtorek, 1 września"
|
|
assert periods.pl_date("2026-01-31") == "Sobota, 31 stycznia"
|
|
|
|
|
|
def test_week_is_monday_to_sunday() -> None:
|
|
week = periods.week_of("2026-09-01")
|
|
assert (week.start, week.end, week.days) == ("2026-08-31", "2026-09-06", 7)
|
|
assert week.label == "tydzień 36"
|
|
|
|
|
|
def test_month_bounds_and_length() -> None:
|
|
for day, end, length in [
|
|
("2026-09-15", "2026-09-30", 30),
|
|
("2026-02-03", "2026-02-28", 28),
|
|
("2028-02-03", "2028-02-29", 29),
|
|
("2026-12-31", "2026-12-31", 31),
|
|
]:
|
|
month = periods.month_of(day)
|
|
assert (month.end, month.days) == (end, length)
|
|
assert periods.month_of("2026-09-15").label == "wrzesień 2026"
|
|
|
|
|
|
def test_year_bounds() -> None:
|
|
year = periods.year_of("2026-09-01")
|
|
assert (year.start, year.end, year.label, year.days) == (
|
|
"2026-01-01",
|
|
"2026-12-31",
|
|
"2026",
|
|
365,
|
|
)
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("day", "kind", "expected_start"),
|
|
[
|
|
("2026-09-01", "week", "2026-08-24"),
|
|
("2026-09-15", "month", "2026-08-01"),
|
|
("2026-09-15", "year", "2025-01-01"),
|
|
],
|
|
)
|
|
def test_previous_period_is_exact(day: str, kind: str, expected_start: str) -> None:
|
|
"""Not "minus seven days": the month before a 31-day month is not 31 days."""
|
|
current = {"week": periods.week_of, "month": periods.month_of, "year": periods.year_of}[kind](
|
|
day
|
|
)
|
|
assert periods.previous(current).start == expected_start
|
|
|
|
|
|
def test_previous_month_of_january_is_december() -> None:
|
|
assert periods.previous(periods.month_of("2026-01-10")).label == "grudzień 2025"
|