mirror of
https://github.com/kuhyx/signal-bot.git
synced 2026-11-10 20:37:03 +01:00
Krzysztof kuhy Rudnicki
63f262bddd
Two gaps kuhy pointed at, both about not losing messages the bot was not awake for. Missed *counts* already worked and now have a test saying so: an event is keyed by Signal's own send timestamp, signal-cli keeps receiving in json-rpc mode while the bot is down, and the replay on reconnect is absorbed by the primary key. Messages sent during an outage come back filed under the day they were actually sent. Missed *reports* did not. A bot that was down at 21:37 never posted that day and never went back for it. The last day reported is now written down per group, so returning from an outage posts every day it owes, oldest first, bounded at a week. A day nobody spoke on is marked settled rather than reconsidered forever; a day whose send *failed* is deliberately left unmarked so the next run retries it. The pre-0.1.0 counter is carried over rather than discarded: 342 messages across four groups, 319 of them in the real group. What the counter cannot say is when, so before assuming, four places were checked for a real inbound timestamp -- journald (commands only), signal-cli's account.db (19 tables, none inbound; message_send_log is the bot's own outgoing resend buffer), Signal Desktop (unlinked, empty, and it does not backfill on link), and signal-api/attachments (the one dated artifact). The attachment mtimes put 12 files on 29 Aug against 79 on 30 Aug inside the counter's window, which is why the whole counter is filed under 30 Aug rather than split. That day is marked in group_meta, and a marked day claims no average message length -- those messages have a count but no lengths, so "średnio 0 znaków" would be a measurement nobody took. The mark is also what will keep the day out of personal records: a merged 22-hour day would otherwise hand somebody a record they never set. render_day's options move into a DayView value object; the keyword list had reached eight and this renderer is about to be shared by several commands that each want a different subset. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015d48t4qsQLBJnDwDeo2Nom
115 lines
4.0 KiB
Python
115 lines
4.0 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 (
|
|
BACKFILL_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."""
|
|
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"] == BACKFILL_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
|