mirror of
https://github.com/kuhyx/signal-bot.git
synced 2026-11-10 20:17:02 +01:00
Krzysztof kuhy Rudnicki
40538b89a1
Reported from the group: the same "Najczęściej piszesz między 12:00 a 13:00" line came back for Ala and for Jan Nowak, which is too much of a coincidence to be a statistic. It was the backfill. The 342 messages carried over from the pre-0.1.0 counter have no timestamps, so the seeded rows got a placeholder hour of 12 -- and favourite_hour was the one query that never excluded the backfilled day. For every person those synthetic noons outnumbered every real message they had sent since, so all seven got the same answer. The genuine hours are 19-21: this group talks in the evening. The comment above that placeholder said "the day is marked anyway, so nothing that cares about hours will read these", which is exactly the kind of reasoning that stops being true the moment somebody adds a query. So the fix is not another `exclude` argument to remember: the absent hour is now -1, which no real hour can be, and hour queries filter `local_hour >= 0`. Forgetting the exclusion can no longer invent an answer, and night_owl gets the same guard even though its 0..2 window happened to miss the old placeholder. Live database migrated with the service stopped and a backup taken: 342 rows moved from noon to unknown. Verified afterwards on the real data -- Ala 19:00, Jan Nowak 19:00, kuhy 20:00, and the two people whose only messages are backfilled correctly get no hour line at all. Not released. Sitting at 0.1.1 until kuhy says otherwise. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015d48t4qsQLBJnDwDeo2Nom
120 lines
4.2 KiB
Python
120 lines
4.2 KiB
Python
# Copyright (c) 2026 Krzysztof Rudnicki. MIT licence.
|
|
"""Carrying the pre-0.1.0 counter into the event log."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import TYPE_CHECKING
|
|
|
|
from signal_bot.stats.backfill import (
|
|
UNKNOWN_HOUR,
|
|
backfilled_day,
|
|
has_legacy_counter,
|
|
seed_from_counter,
|
|
)
|
|
from signal_bot.stats.queries_day import day_rows, day_totals
|
|
|
|
if TYPE_CHECKING:
|
|
from signal_bot.store import Store
|
|
|
|
GROUP = "group-a=="
|
|
OTHER = "group-b=="
|
|
DAY = "2026-08-30"
|
|
|
|
LEGACY = """
|
|
CREATE TABLE message_counts (
|
|
group_id TEXT NOT NULL,
|
|
uuid TEXT NOT NULL,
|
|
display_name TEXT NOT NULL,
|
|
count INTEGER NOT NULL DEFAULT 0,
|
|
PRIMARY KEY (group_id, uuid)
|
|
);
|
|
"""
|
|
|
|
|
|
def give_legacy_counter(store: Store, rows: list[tuple[str, str, str, int]]) -> None:
|
|
"""Recreate the pre-0.1.0 table and fill it, as a real old database has."""
|
|
store.events.connection.executescript(LEGACY)
|
|
store.events.connection.executemany(
|
|
"INSERT INTO message_counts (group_id, uuid, display_name, count) VALUES (?, ?, ?, ?)",
|
|
rows,
|
|
)
|
|
store.events.connection.commit()
|
|
|
|
|
|
def test_a_fresh_database_has_no_legacy_counter(store: Store) -> None:
|
|
"""0.1.0 stopped declaring the table, so a new file never has one."""
|
|
assert has_legacy_counter(store) is False
|
|
|
|
|
|
def test_an_old_database_is_detected(store: Store) -> None:
|
|
give_legacy_counter(store, [(GROUP, "u1", "Ala", 3)])
|
|
assert has_legacy_counter(store) is True
|
|
|
|
|
|
def test_counts_become_events_on_the_named_day(store: Store) -> None:
|
|
give_legacy_counter(
|
|
store,
|
|
[(GROUP, "u1", "Ala", 3), (GROUP, "u2", "kuhy", 2), (OTHER, "u1", "Ala", 1)],
|
|
)
|
|
seeded = seed_from_counter(store, DAY)
|
|
|
|
assert seeded == {GROUP: 5, OTHER: 1}
|
|
rows = day_rows(store.events, GROUP, DAY)
|
|
assert [(r.display_name, r.messages) for r in rows] == [("Ala", 3), ("kuhy", 2)]
|
|
assert day_totals(rows).messages == 5
|
|
|
|
|
|
def test_the_seeded_day_is_marked_per_group(store: Store) -> None:
|
|
"""Marked, so records and hour statistics can leave it out."""
|
|
give_legacy_counter(store, [(GROUP, "u1", "Ala", 1), (OTHER, "u2", "kuhy", 1)])
|
|
seed_from_counter(store, DAY)
|
|
assert backfilled_day(store, GROUP) == DAY
|
|
assert backfilled_day(store, OTHER) == DAY
|
|
|
|
|
|
def test_an_unseeded_group_is_not_marked(store: Store) -> None:
|
|
give_legacy_counter(store, [(GROUP, "u1", "Ala", 1)])
|
|
seed_from_counter(store, DAY)
|
|
assert backfilled_day(store, OTHER) is None
|
|
|
|
|
|
def test_zero_counts_are_skipped(store: Store) -> None:
|
|
"""A row at zero is somebody who was reset, not somebody who spoke."""
|
|
give_legacy_counter(store, [(GROUP, "u1", "Ala", 0)])
|
|
assert seed_from_counter(store, DAY) == {}
|
|
assert day_rows(store.events, GROUP, DAY) == []
|
|
assert backfilled_day(store, GROUP) is None
|
|
|
|
|
|
def test_seeded_people_are_known_to_the_roster(store: Store) -> None:
|
|
"""Otherwise they would show as unnamed strangers in the first report."""
|
|
give_legacy_counter(store, [(GROUP, "u1", "Ala", 2)])
|
|
seed_from_counter(store, DAY)
|
|
assert [p.display_name for p in store.events.roster(GROUP, ["u1"])] == ["Ala"]
|
|
|
|
|
|
def test_seeded_events_carry_no_invented_detail(store: Store) -> None:
|
|
"""No hours, no lengths, no media -- the counter knew none of them.
|
|
|
|
The hour is -1 rather than any real hour. It was noon once, and
|
|
favourite_hour then told all seven people they wrote most at midday: 319
|
|
synthetic noons outweighed every genuine evening.
|
|
"""
|
|
give_legacy_counter(store, [(GROUP, "u1", "Ala", 2)])
|
|
seed_from_counter(store, DAY)
|
|
rows = store.events.connection.execute(
|
|
"SELECT local_hour, char_len, media_count, is_command FROM message_events"
|
|
).fetchall()
|
|
assert len(rows) == 2
|
|
for row in rows:
|
|
assert row["local_hour"] == UNKNOWN_HOUR
|
|
assert (row["char_len"], row["media_count"], row["is_command"]) == (0, 0, 0)
|
|
|
|
|
|
def test_seeding_twice_does_not_double_the_totals(store: Store) -> None:
|
|
"""The synthetic keys are deterministic, so a rerun is absorbed."""
|
|
give_legacy_counter(store, [(GROUP, "u1", "Ala", 3)])
|
|
seed_from_counter(store, DAY)
|
|
seed_from_counter(store, DAY)
|
|
assert day_totals(day_rows(store.events, GROUP, DAY)).messages == 3
|